$ C:\quantdiff\llama.cpp\bin\llama-server.exe -m C:\quantdiff\dl\campaign\e4d9634a3b65\Ornith-1.5-9B-Q5_K_M.gguf --host 127.0.0.1 --port 8089 -c 4096 -np 1 -ngl 999 -fa on --jinja --seed 1234 --no-webui -a quant 0.00.100.818 I srv llama_server: initializing ... 0.00.100.825 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.100.948 I srv init_listene: The UI is disabled 0.00.100.950 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.101.029 W srv llama_server: security: no API key is set and CORS allows all origins (see https://github.com/ggml-org/llama.cpp/pull/25655) 0.00.107.990 I srv load_model: loading model 'C:\quantdiff\dl\campaign\e4d9634a3b65\Ornith-1.5-9B-Q5_K_M.gguf' 0.01.028.314 W model has unused tensor blk.32.attn_norm.weight (size = 16384 bytes) -- ignoring 0.01.028.329 W model has unused tensor blk.32.post_attention_norm.weight (size = 16384 bytes) -- ignoring 0.01.028.354 W model has unused tensor blk.32.attn_q.weight (size = 23068672 bytes) -- ignoring 0.01.028.365 W model has unused tensor blk.32.attn_k.weight (size = 2883584 bytes) -- ignoring 0.01.028.374 W model has unused tensor blk.32.attn_v.weight (size = 3440640 bytes) -- ignoring 0.01.028.407 W model has unused tensor blk.32.attn_output.weight (size = 11534336 bytes) -- ignoring 0.01.028.417 W model has unused tensor blk.32.attn_q_norm.weight (size = 1024 bytes) -- ignoring 0.01.028.426 W model has unused tensor blk.32.attn_k_norm.weight (size = 1024 bytes) -- ignoring 0.01.028.435 W model has unused tensor blk.32.ffn_gate.weight (size = 34603008 bytes) -- ignoring 0.01.028.444 W model has unused tensor blk.32.ffn_down.weight (size = 41287680 bytes) -- ignoring 0.01.028.453 W model has unused tensor blk.32.ffn_up.weight (size = 34603008 bytes) -- ignoring 0.01.028.464 W model has unused tensor blk.32.nextn.eh_proj.weight (size = 23068672 bytes) -- ignoring 0.01.028.475 W model has unused tensor blk.32.nextn.enorm.weight (size = 16384 bytes) -- ignoring 0.01.028.485 W model has unused tensor blk.32.nextn.hnorm.weight (size = 16384 bytes) -- ignoring 0.01.028.515 W model has unused tensor blk.32.nextn.shared_head_norm.weight (size = 16384 bytes) -- ignoring 0.03.047.244 I cmn init: llama threadpool init, n_threads = 8 0.03.128.363 I srv load_model: initializing, n_slots = 1, n_ctx_slot = 4096, kv_unified = 'false' 0.03.133.371 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.03.133.391 I srv llama_server: model loaded 0.03.133.394 I srv llama_server: listening on http://127.0.0.1:8089 0.04.565.355 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.04.565.537 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.05.488.767 I slot print_timing: id 0 | task 0 | prompt eval time = 149.37 ms / 368 tokens ( 0.41 ms per token, 2463.76 tokens per second) 0.05.488.773 I slot print_timing: id 0 | task 0 | eval time = 773.85 ms / 70 tokens ( 11.22 ms per token, 89.16 tokens per second) 0.05.488.774 I slot print_timing: id 0 | task 0 | total time = 923.21 ms / 438 tokens 0.05.488.780 I slot print_timing: id 0 | task 0 | graphs reused = 69 0.05.488.781 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.488.821 I slot release: id 0 | task 0 | stop processing: n_tokens = 437, truncated = 0 0.05.517.666 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 5390270 0.05.542.506 I slot launch_slot_: id 0 | task 73 | processing task, is_child = 0 0.06.312.515 I slot print_timing: id 0 | task 73 | prompt eval time = 123.98 ms / 322 tokens ( 0.39 ms per token, 2597.15 tokens per second) 0.06.312.520 I slot print_timing: id 0 | task 73 | eval time = 646.01 ms / 59 tokens ( 11.14 ms per token, 89.78 tokens per second) 0.06.312.521 I slot print_timing: id 0 | task 73 | total time = 769.99 ms / 381 tokens 0.06.312.522 I slot print_timing: id 0 | task 73 | graphs reused = 126 0.06.312.523 I slot print_timing: id 0 | task 73 | graph reallocs = 0 / 0 (same size) / (changed size) 0.06.312.548 I slot release: id 0 | task 73 | stop processing: n_tokens = 380, truncated = 0 0.06.344.726 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 380, t_last = 6213998 0.06.368.496 I slot launch_slot_: id 0 | task 135 | processing task, is_child = 0 0.07.157.387 I slot print_timing: id 0 | task 135 | prompt eval time = 128.71 ms / 365 tokens ( 0.35 ms per token, 2835.85 tokens per second) 0.07.157.393 I slot print_timing: id 0 | task 135 | eval time = 660.16 ms / 58 tokens ( 11.58 ms per token, 86.34 tokens per second) 0.07.157.395 I slot print_timing: id 0 | task 135 | total time = 788.87 ms / 423 tokens 0.07.157.396 I slot print_timing: id 0 | task 135 | graphs reused = 182 0.07.157.397 I slot print_timing: id 0 | task 135 | graph reallocs = 0 / 0 (same size) / (changed size) 0.07.157.428 I slot release: id 0 | task 135 | stop processing: n_tokens = 422, truncated = 0 0.07.172.607 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 422, t_last = 7058878 0.07.197.324 I slot launch_slot_: id 0 | task 196 | processing task, is_child = 0 0.08.219.658 I slot print_timing: id 0 | task 196 | prompt eval time = 134.41 ms / 397 tokens ( 0.34 ms per token, 2953.74 tokens per second) 0.08.219.664 I slot print_timing: id 0 | task 196 | eval time = 887.91 ms / 78 tokens ( 11.53 ms per token, 86.72 tokens per second) 0.08.219.665 I slot print_timing: id 0 | task 196 | total time = 1022.31 ms / 475 tokens 0.08.219.665 I slot print_timing: id 0 | task 196 | graphs reused = 258 0.08.219.666 I slot print_timing: id 0 | task 196 | graph reallocs = 0 / 0 (same size) / (changed size) 0.08.219.697 I slot release: id 0 | task 196 | stop processing: n_tokens = 474, truncated = 0 0.08.248.456 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.117 (> 0.100 thold), f_keep = 0.095 0.08.272.958 I slot launch_slot_: id 0 | task 277 | processing task, is_child = 0 0.09.189.275 I slot print_timing: id 0 | task 277 | prompt eval time = 131.24 ms / 383 tokens ( 0.34 ms per token, 2918.27 tokens per second) 0.09.189.281 I slot print_timing: id 0 | task 277 | eval time = 785.05 ms / 70 tokens ( 11.38 ms per token, 87.89 tokens per second) 0.09.189.282 I slot print_timing: id 0 | task 277 | total time = 916.29 ms / 453 tokens 0.09.189.283 I slot print_timing: id 0 | task 277 | graphs reused = 326 0.09.189.284 I slot print_timing: id 0 | task 277 | graph reallocs = 0 / 0 (same size) / (changed size) 0.09.189.311 I slot release: id 0 | task 277 | stop processing: n_tokens = 452, truncated = 0 0.09.226.645 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 452, t_last = 9090761 0.09.251.175 I slot launch_slot_: id 0 | task 350 | processing task, is_child = 0 0.10.146.473 I slot print_timing: id 0 | task 350 | prompt eval time = 127.70 ms / 372 tokens ( 0.34 ms per token, 2913.12 tokens per second) 0.10.146.479 I slot print_timing: id 0 | task 350 | eval time = 767.58 ms / 70 tokens ( 11.12 ms per token, 89.89 tokens per second) 0.10.146.480 I slot print_timing: id 0 | task 350 | total time = 895.28 ms / 442 tokens 0.10.146.481 I slot print_timing: id 0 | task 350 | graphs reused = 394 0.10.146.481 I slot print_timing: id 0 | task 350 | graph reallocs = 0 / 0 (same size) / (changed size) 0.10.146.508 I slot release: id 0 | task 350 | stop processing: n_tokens = 441, truncated = 0 0.10.174.987 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 441, t_last = 10047958 0.10.199.258 I slot launch_slot_: id 0 | task 423 | processing task, is_child = 0 0.11.105.664 I slot print_timing: id 0 | task 423 | prompt eval time = 147.14 ms / 422 tokens ( 0.35 ms per token, 2868.08 tokens per second) 0.11.105.670 I slot print_timing: id 0 | task 423 | eval time = 759.25 ms / 67 tokens ( 11.50 ms per token, 86.93 tokens per second) 0.11.105.671 I slot print_timing: id 0 | task 423 | total time = 906.39 ms / 489 tokens 0.11.105.672 I slot print_timing: id 0 | task 423 | graphs reused = 459 0.11.105.673 I slot print_timing: id 0 | task 423 | graph reallocs = 0 / 0 (same size) / (changed size) 0.11.105.704 I slot release: id 0 | task 423 | stop processing: n_tokens = 488, truncated = 0 0.11.110.852 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 488, t_last = 11007153 0.11.136.171 I slot launch_slot_: id 0 | task 493 | processing task, is_child = 0 0.12.313.304 I slot print_timing: id 0 | task 493 | prompt eval time = 156.16 ms / 470 tokens ( 0.33 ms per token, 3009.79 tokens per second) 0.12.313.310 I slot print_timing: id 0 | task 493 | eval time = 1020.96 ms / 89 tokens ( 11.60 ms per token, 86.19 tokens per second) 0.12.313.311 I slot print_timing: id 0 | task 493 | total time = 1177.12 ms / 559 tokens 0.12.313.312 I slot print_timing: id 0 | task 493 | graphs reused = 545 0.12.313.313 I slot print_timing: id 0 | task 493 | graph reallocs = 0 / 0 (same size) / (changed size) 0.12.313.348 I slot release: id 0 | task 493 | stop processing: n_tokens = 558, truncated = 0 0.12.331.318 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 12214798 0.12.357.698 I slot launch_slot_: id 0 | task 585 | processing task, is_child = 0 0.13.299.667 I slot print_timing: id 0 | task 585 | prompt eval time = 127.96 ms / 345 tokens ( 0.37 ms per token, 2696.22 tokens per second) 0.13.299.673 I slot print_timing: id 0 | task 585 | eval time = 813.99 ms / 72 tokens ( 11.46 ms per token, 87.22 tokens per second) 0.13.299.674 I slot print_timing: id 0 | task 585 | total time = 941.95 ms / 417 tokens 0.13.299.675 I slot print_timing: id 0 | task 585 | graphs reused = 615 0.13.299.675 I slot print_timing: id 0 | task 585 | graph reallocs = 0 / 0 (same size) / (changed size) 0.13.299.703 I slot release: id 0 | task 585 | stop processing: n_tokens = 416, truncated = 0 0.13.329.031 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 13201153 0.13.353.399 I slot launch_slot_: id 0 | task 660 | processing task, is_child = 0 0.13.926.848 I slot print_timing: id 0 | task 660 | prompt eval time = 125.55 ms / 364 tokens ( 0.34 ms per token, 2899.24 tokens per second) 0.13.926.854 I slot print_timing: id 0 | task 660 | eval time = 447.88 ms / 41 tokens ( 11.20 ms per token, 89.31 tokens per second) 0.13.926.855 I slot print_timing: id 0 | task 660 | total time = 573.43 ms / 405 tokens 0.13.926.856 I slot print_timing: id 0 | task 660 | graphs reused = 654 0.13.926.857 I slot print_timing: id 0 | task 660 | graph reallocs = 0 / 0 (same size) / (changed size) 0.13.926.887 I slot release: id 0 | task 660 | stop processing: n_tokens = 404, truncated = 0 0.13.968.513 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 404, t_last = 13828337 0.13.992.550 I slot launch_slot_: id 0 | task 704 | processing task, is_child = 0 0.15.022.799 I slot print_timing: id 0 | task 704 | prompt eval time = 128.79 ms / 376 tokens ( 0.34 ms per token, 2919.44 tokens per second) 0.15.022.804 I slot print_timing: id 0 | task 704 | eval time = 901.44 ms / 80 tokens ( 11.41 ms per token, 87.64 tokens per second) 0.15.022.805 I slot print_timing: id 0 | task 704 | total time = 1030.23 ms / 456 tokens 0.15.022.806 I slot print_timing: id 0 | task 704 | graphs reused = 732 0.15.022.807 I slot print_timing: id 0 | task 704 | graph reallocs = 0 / 0 (same size) / (changed size) 0.15.022.835 I slot release: id 0 | task 704 | stop processing: n_tokens = 455, truncated = 0 0.15.042.590 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 455, t_last = 14924285 0.15.070.296 I slot launch_slot_: id 0 | task 787 | processing task, is_child = 0 0.16.015.617 I slot print_timing: id 0 | task 787 | prompt eval time = 137.75 ms / 412 tokens ( 0.33 ms per token, 2990.97 tokens per second) 0.16.015.622 I slot print_timing: id 0 | task 787 | eval time = 807.55 ms / 71 tokens ( 11.54 ms per token, 86.68 tokens per second) 0.16.015.623 I slot print_timing: id 0 | task 787 | total time = 945.30 ms / 483 tokens 0.16.015.624 I slot print_timing: id 0 | task 787 | graphs reused = 801 0.16.015.625 I slot print_timing: id 0 | task 787 | graph reallocs = 0 / 0 (same size) / (changed size) 0.16.015.656 I slot release: id 0 | task 787 | stop processing: n_tokens = 482, truncated = 0 0.16.041.338 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 482, t_last = 15917106 0.16.065.919 I slot launch_slot_: id 0 | task 861 | processing task, is_child = 0 0.16.906.884 I slot print_timing: id 0 | task 861 | prompt eval time = 130.70 ms / 376 tokens ( 0.35 ms per token, 2876.86 tokens per second) 0.16.906.890 I slot print_timing: id 0 | task 861 | eval time = 710.25 ms / 62 tokens ( 11.64 ms per token, 85.89 tokens per second) 0.16.906.891 I slot print_timing: id 0 | task 861 | total time = 840.95 ms / 438 tokens 0.16.906.892 I slot print_timing: id 0 | task 861 | graphs reused = 861 0.16.906.893 I slot print_timing: id 0 | task 861 | graph reallocs = 0 / 0 (same size) / (changed size) 0.16.906.921 I slot release: id 0 | task 861 | stop processing: n_tokens = 437, truncated = 0 0.16.911.615 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 16808370 0.16.935.516 I slot launch_slot_: id 0 | task 926 | processing task, is_child = 0 0.17.833.107 I slot print_timing: id 0 | task 926 | prompt eval time = 131.33 ms / 378 tokens ( 0.35 ms per token, 2878.20 tokens per second) 0.17.833.113 I slot print_timing: id 0 | task 926 | eval time = 766.24 ms / 70 tokens ( 11.10 ms per token, 90.05 tokens per second) 0.17.833.114 I slot print_timing: id 0 | task 926 | total time = 897.57 ms / 448 tokens 0.17.833.115 I slot print_timing: id 0 | task 926 | graphs reused = 929 0.17.833.116 I slot print_timing: id 0 | task 926 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.833.156 I slot release: id 0 | task 926 | stop processing: n_tokens = 447, truncated = 0 0.17.838.133 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 17734605 0.17.862.585 I slot launch_slot_: id 0 | task 999 | processing task, is_child = 0 0.18.890.721 I slot print_timing: id 0 | task 999 | prompt eval time = 128.74 ms / 367 tokens ( 0.35 ms per token, 2850.71 tokens per second) 0.18.890.727 I slot print_timing: id 0 | task 999 | eval time = 899.38 ms / 80 tokens ( 11.38 ms per token, 87.84 tokens per second) 0.18.890.728 I slot print_timing: id 0 | task 999 | total time = 1028.12 ms / 447 tokens 0.18.890.729 I slot print_timing: id 0 | task 999 | graphs reused = 1007 0.18.890.730 I slot print_timing: id 0 | task 999 | graph reallocs = 0 / 0 (same size) / (changed size) 0.18.890.759 I slot release: id 0 | task 999 | stop processing: n_tokens = 446, truncated = 0 0.18.923.677 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 446, t_last = 18792208 0.18.948.977 I slot launch_slot_: id 0 | task 1082 | processing task, is_child = 0 0.19.964.447 I slot print_timing: id 0 | task 1082 | prompt eval time = 127.27 ms / 347 tokens ( 0.37 ms per token, 2726.40 tokens per second) 0.19.964.453 I slot print_timing: id 0 | task 1082 | eval time = 888.18 ms / 78 tokens ( 11.53 ms per token, 86.69 tokens per second) 0.19.964.454 I slot print_timing: id 0 | task 1082 | total time = 1015.45 ms / 425 tokens 0.19.964.455 I slot print_timing: id 0 | task 1082 | graphs reused = 1083 0.19.964.455 I slot print_timing: id 0 | task 1082 | graph reallocs = 0 / 0 (same size) / (changed size) 0.19.964.484 I slot release: id 0 | task 1082 | stop processing: n_tokens = 424, truncated = 0 0.19.985.484 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 19865933 0.20.009.553 I slot launch_slot_: id 0 | task 1163 | processing task, is_child = 0 0.20.602.574 I slot print_timing: id 0 | task 1163 | prompt eval time = 127.94 ms / 369 tokens ( 0.35 ms per token, 2884.23 tokens per second) 0.20.602.579 I slot print_timing: id 0 | task 1163 | eval time = 465.06 ms / 41 tokens ( 11.63 ms per token, 86.01 tokens per second) 0.20.602.580 I slot print_timing: id 0 | task 1163 | total time = 593.00 ms / 410 tokens 0.20.602.582 I slot print_timing: id 0 | task 1163 | graphs reused = 1122 0.20.602.583 I slot print_timing: id 0 | task 1163 | graph reallocs = 0 / 0 (same size) / (changed size) 0.20.602.612 I slot release: id 0 | task 1163 | stop processing: n_tokens = 409, truncated = 0 0.20.607.306 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 20504061 0.20.633.633 I slot launch_slot_: id 0 | task 1207 | processing task, is_child = 0 0.21.219.435 I slot print_timing: id 0 | task 1207 | prompt eval time = 127.95 ms / 352 tokens ( 0.36 ms per token, 2751.05 tokens per second) 0.21.219.441 I slot print_timing: id 0 | task 1207 | eval time = 457.83 ms / 41 tokens ( 11.45 ms per token, 87.37 tokens per second) 0.21.219.442 I slot print_timing: id 0 | task 1207 | total time = 585.78 ms / 393 tokens 0.21.219.443 I slot print_timing: id 0 | task 1207 | graphs reused = 1161 0.21.219.443 I slot print_timing: id 0 | task 1207 | graph reallocs = 0 / 0 (same size) / (changed size) 0.21.219.471 I slot release: id 0 | task 1207 | stop processing: n_tokens = 392, truncated = 0 0.21.240.841 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 392, t_last = 21120921 0.21.265.065 I slot launch_slot_: id 0 | task 1251 | processing task, is_child = 0 0.21.978.642 I slot print_timing: id 0 | task 1251 | prompt eval time = 123.15 ms / 349 tokens ( 0.35 ms per token, 2833.87 tokens per second) 0.21.978.648 I slot print_timing: id 0 | task 1251 | eval time = 590.40 ms / 54 tokens ( 11.14 ms per token, 89.77 tokens per second) 0.21.978.649 I slot print_timing: id 0 | task 1251 | total time = 713.56 ms / 403 tokens 0.21.978.650 I slot print_timing: id 0 | task 1251 | graphs reused = 1213 0.21.978.651 I slot print_timing: id 0 | task 1251 | graph reallocs = 0 / 0 (same size) / (changed size) 0.21.978.678 I slot release: id 0 | task 1251 | stop processing: n_tokens = 402, truncated = 0 0.21.994.274 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 402, t_last = 21880127 0.22.018.102 I slot launch_slot_: id 0 | task 1308 | processing task, is_child = 0 0.23.098.471 I slot print_timing: id 0 | task 1308 | prompt eval time = 131.06 ms / 384 tokens ( 0.34 ms per token, 2929.98 tokens per second) 0.23.098.477 I slot print_timing: id 0 | task 1308 | eval time = 949.29 ms / 84 tokens ( 11.44 ms per token, 87.43 tokens per second) 0.23.098.479 I slot print_timing: id 0 | task 1308 | total time = 1080.35 ms / 468 tokens 0.23.098.480 I slot print_timing: id 0 | task 1308 | graphs reused = 1295 0.23.098.481 I slot print_timing: id 0 | task 1308 | graph reallocs = 0 / 0 (same size) / (changed size) 0.23.098.512 I slot release: id 0 | task 1308 | stop processing: n_tokens = 467, truncated = 0 0.23.103.453 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 467, t_last = 22999962 0.23.131.053 I slot launch_slot_: id 0 | task 1395 | processing task, is_child = 0 0.24.072.143 I slot print_timing: id 0 | task 1395 | prompt eval time = 129.55 ms / 356 tokens ( 0.36 ms per token, 2747.95 tokens per second) 0.24.072.148 I slot print_timing: id 0 | task 1395 | eval time = 811.52 ms / 71 tokens ( 11.59 ms per token, 86.26 tokens per second) 0.24.072.149 I slot print_timing: id 0 | task 1395 | total time = 941.07 ms / 427 tokens 0.24.072.150 I slot print_timing: id 0 | task 1395 | graphs reused = 1364 0.24.072.151 I slot print_timing: id 0 | task 1395 | graph reallocs = 0 / 0 (same size) / (changed size) 0.24.072.180 I slot release: id 0 | task 1395 | stop processing: n_tokens = 426, truncated = 0 0.24.092.302 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 23973629 0.24.116.349 I slot launch_slot_: id 0 | task 1469 | processing task, is_child = 0 0.25.227.729 I slot print_timing: id 0 | task 1469 | prompt eval time = 136.26 ms / 410 tokens ( 0.33 ms per token, 3008.93 tokens per second) 0.25.227.735 I slot print_timing: id 0 | task 1469 | eval time = 975.10 ms / 85 tokens ( 11.61 ms per token, 86.15 tokens per second) 0.25.227.736 I slot print_timing: id 0 | task 1469 | total time = 1111.36 ms / 495 tokens 0.25.227.737 I slot print_timing: id 0 | task 1469 | graphs reused = 1447 0.25.227.738 I slot print_timing: id 0 | task 1469 | graph reallocs = 0 / 0 (same size) / (changed size) 0.25.227.767 I slot release: id 0 | task 1469 | stop processing: n_tokens = 494, truncated = 0 0.25.244.236 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 494, t_last = 25129216 0.25.269.739 I slot launch_slot_: id 0 | task 1557 | processing task, is_child = 0 0.26.253.197 I slot print_timing: id 0 | task 1557 | prompt eval time = 129.92 ms / 385 tokens ( 0.34 ms per token, 2963.41 tokens per second) 0.26.253.203 I slot print_timing: id 0 | task 1557 | eval time = 853.52 ms / 78 tokens ( 11.08 ms per token, 90.21 tokens per second) 0.26.253.204 I slot print_timing: id 0 | task 1557 | total time = 983.44 ms / 463 tokens 0.26.253.206 I slot print_timing: id 0 | task 1557 | graphs reused = 1523 0.26.253.207 I slot print_timing: id 0 | task 1557 | graph reallocs = 0 / 0 (same size) / (changed size) 0.26.253.236 I slot release: id 0 | task 1557 | stop processing: n_tokens = 462, truncated = 0 0.26.273.321 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 462, t_last = 26154685 0.26.297.648 I slot launch_slot_: id 0 | task 1638 | processing task, is_child = 0 0.27.495.360 I slot print_timing: id 0 | task 1638 | prompt eval time = 131.69 ms / 395 tokens ( 0.33 ms per token, 2999.54 tokens per second) 0.27.495.366 I slot print_timing: id 0 | task 1638 | eval time = 1066.01 ms / 94 tokens ( 11.46 ms per token, 87.24 tokens per second) 0.27.495.367 I slot print_timing: id 0 | task 1638 | total time = 1197.69 ms / 489 tokens 0.27.495.368 I slot print_timing: id 0 | task 1638 | graphs reused = 1615 0.27.495.369 I slot print_timing: id 0 | task 1638 | graph reallocs = 0 / 0 (same size) / (changed size) 0.27.495.398 I slot release: id 0 | task 1638 | stop processing: n_tokens = 488, truncated = 0 0.27.519.484 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 488, t_last = 27396848 0.27.544.301 I slot launch_slot_: id 0 | task 1735 | processing task, is_child = 0 0.29.038.278 I slot print_timing: id 0 | task 1735 | prompt eval time = 138.22 ms / 430 tokens ( 0.32 ms per token, 3110.98 tokens per second) 0.29.038.284 I slot print_timing: id 0 | task 1735 | eval time = 1355.74 ms / 118 tokens ( 11.59 ms per token, 86.30 tokens per second) 0.29.038.285 I slot print_timing: id 0 | task 1735 | total time = 1493.96 ms / 548 tokens 0.29.038.287 I slot print_timing: id 0 | task 1735 | graphs reused = 1730 0.29.038.289 I slot print_timing: id 0 | task 1735 | graph reallocs = 0 / 0 (same size) / (changed size) 0.29.038.320 I slot release: id 0 | task 1735 | stop processing: n_tokens = 547, truncated = 0 0.29.062.801 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 547, t_last = 28939769 0.29.088.121 I slot launch_slot_: id 0 | task 1856 | processing task, is_child = 0 0.29.902.609 I slot print_timing: id 0 | task 1856 | prompt eval time = 135.10 ms / 392 tokens ( 0.34 ms per token, 2901.62 tokens per second) 0.29.902.614 I slot print_timing: id 0 | task 1856 | eval time = 679.37 ms / 62 tokens ( 11.14 ms per token, 89.79 tokens per second) 0.29.902.615 I slot print_timing: id 0 | task 1856 | total time = 814.47 ms / 454 tokens 0.29.902.616 I slot print_timing: id 0 | task 1856 | graphs reused = 1790 0.29.902.617 I slot print_timing: id 0 | task 1856 | graph reallocs = 0 / 0 (same size) / (changed size) 0.29.902.645 I slot release: id 0 | task 1856 | stop processing: n_tokens = 453, truncated = 0 0.29.920.422 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 453, t_last = 29804095 0.29.944.895 I slot launch_slot_: id 0 | task 1921 | processing task, is_child = 0 0.30.842.085 I slot print_timing: id 0 | task 1921 | prompt eval time = 123.62 ms / 350 tokens ( 0.35 ms per token, 2831.28 tokens per second) 0.30.842.090 I slot print_timing: id 0 | task 1921 | eval time = 773.55 ms / 70 tokens ( 11.21 ms per token, 89.20 tokens per second) 0.30.842.091 I slot print_timing: id 0 | task 1921 | total time = 897.17 ms / 420 tokens 0.30.842.092 I slot print_timing: id 0 | task 1921 | graphs reused = 1858 0.30.842.093 I slot print_timing: id 0 | task 1921 | graph reallocs = 0 / 0 (same size) / (changed size) 0.30.842.121 I slot release: id 0 | task 1921 | stop processing: n_tokens = 419, truncated = 0 0.30.866.760 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 30743571 0.30.890.692 I slot launch_slot_: id 0 | task 1994 | processing task, is_child = 0 0.31.968.066 I slot print_timing: id 0 | task 1994 | prompt eval time = 133.68 ms / 380 tokens ( 0.35 ms per token, 2842.59 tokens per second) 0.31.968.072 I slot print_timing: id 0 | task 1994 | eval time = 943.67 ms / 83 tokens ( 11.51 ms per token, 86.89 tokens per second) 0.31.968.073 I slot print_timing: id 0 | task 1994 | total time = 1077.35 ms / 463 tokens 0.31.968.074 I slot print_timing: id 0 | task 1994 | graphs reused = 1939 0.31.968.074 I slot print_timing: id 0 | task 1994 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.968.104 I slot release: id 0 | task 1994 | stop processing: n_tokens = 462, truncated = 0 0.31.987.789 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 462, t_last = 31869553 0.32.012.164 I slot launch_slot_: id 0 | task 2080 | processing task, is_child = 0 0.33.247.198 I slot print_timing: id 0 | task 2080 | prompt eval time = 140.55 ms / 410 tokens ( 0.34 ms per token, 2917.09 tokens per second) 0.33.247.203 I slot print_timing: id 0 | task 2080 | eval time = 1094.46 ms / 96 tokens ( 11.52 ms per token, 86.80 tokens per second) 0.33.247.204 I slot print_timing: id 0 | task 2080 | total time = 1235.01 ms / 506 tokens 0.33.247.206 I slot print_timing: id 0 | task 2080 | graphs reused = 2033 0.33.247.207 I slot print_timing: id 0 | task 2080 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.247.238 I slot release: id 0 | task 2080 | stop processing: n_tokens = 505, truncated = 0 0.33.263.891 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 505, t_last = 33148688 0.33.288.777 I slot launch_slot_: id 0 | task 2179 | processing task, is_child = 0 0.34.163.766 I slot print_timing: id 0 | task 2179 | prompt eval time = 131.51 ms / 387 tokens ( 0.34 ms per token, 2942.81 tokens per second) 0.34.163.772 I slot print_timing: id 0 | task 2179 | eval time = 743.46 ms / 68 tokens ( 11.10 ms per token, 90.12 tokens per second) 0.34.163.773 I slot print_timing: id 0 | task 2179 | total time = 874.97 ms / 455 tokens 0.34.163.774 I slot print_timing: id 0 | task 2179 | graphs reused = 2099 0.34.163.775 I slot print_timing: id 0 | task 2179 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.163.803 I slot release: id 0 | task 2179 | stop processing: n_tokens = 454, truncated = 0 0.34.202.805 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 454, t_last = 34065252 0.34.227.136 I slot launch_slot_: id 0 | task 2250 | processing task, is_child = 0 0.35.213.894 I slot print_timing: id 0 | task 2250 | prompt eval time = 123.33 ms / 358 tokens ( 0.34 ms per token, 2902.71 tokens per second) 0.35.213.900 I slot print_timing: id 0 | task 2250 | eval time = 863.40 ms / 77 tokens ( 11.36 ms per token, 88.02 tokens per second) 0.35.213.901 I slot print_timing: id 0 | task 2250 | total time = 986.74 ms / 435 tokens 0.35.213.902 I slot print_timing: id 0 | task 2250 | graphs reused = 2174 0.35.213.903 I slot print_timing: id 0 | task 2250 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.213.932 I slot release: id 0 | task 2250 | stop processing: n_tokens = 434, truncated = 0 0.35.243.585 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 434, t_last = 35115382 0.35.267.752 I slot launch_slot_: id 0 | task 2330 | processing task, is_child = 0 0.36.182.648 I slot print_timing: id 0 | task 2330 | prompt eval time = 129.81 ms / 359 tokens ( 0.36 ms per token, 2765.47 tokens per second) 0.36.182.654 I slot print_timing: id 0 | task 2330 | eval time = 785.06 ms / 69 tokens ( 11.55 ms per token, 86.62 tokens per second) 0.36.182.655 I slot print_timing: id 0 | task 2330 | total time = 914.88 ms / 428 tokens 0.36.182.656 I slot print_timing: id 0 | task 2330 | graphs reused = 2241 0.36.182.657 I slot print_timing: id 0 | task 2330 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.182.684 I slot release: id 0 | task 2330 | stop processing: n_tokens = 427, truncated = 0 0.36.202.155 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 427, t_last = 36084134 0.36.226.779 I slot launch_slot_: id 0 | task 2402 | processing task, is_child = 0 0.37.274.453 I slot print_timing: id 0 | task 2402 | prompt eval time = 133.38 ms / 387 tokens ( 0.34 ms per token, 2901.57 tokens per second) 0.37.274.459 I slot print_timing: id 0 | task 2402 | eval time = 914.28 ms / 82 tokens ( 11.29 ms per token, 88.59 tokens per second) 0.37.274.460 I slot print_timing: id 0 | task 2402 | total time = 1047.65 ms / 469 tokens 0.37.274.461 I slot print_timing: id 0 | task 2402 | graphs reused = 2321 0.37.274.462 I slot print_timing: id 0 | task 2402 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.274.491 I slot release: id 0 | task 2402 | stop processing: n_tokens = 468, truncated = 0 0.37.288.753 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 468, t_last = 37175941 0.37.313.331 I slot launch_slot_: id 0 | task 2487 | processing task, is_child = 0 0.38.379.975 I slot print_timing: id 0 | task 2487 | prompt eval time = 131.94 ms / 410 tokens ( 0.32 ms per token, 3107.50 tokens per second) 0.38.379.980 I slot print_timing: id 0 | task 2487 | eval time = 934.69 ms / 85 tokens ( 11.13 ms per token, 89.87 tokens per second) 0.38.379.981 I slot print_timing: id 0 | task 2487 | total time = 1066.63 ms / 495 tokens 0.38.379.982 I slot print_timing: id 0 | task 2487 | graphs reused = 2404 0.38.379.983 I slot print_timing: id 0 | task 2487 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.380.011 I slot release: id 0 | task 2487 | stop processing: n_tokens = 494, truncated = 0 0.38.384.634 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 494, t_last = 38281461 0.38.409.474 I slot launch_slot_: id 0 | task 2575 | processing task, is_child = 0 0.39.265.624 I slot print_timing: id 0 | task 2575 | prompt eval time = 123.21 ms / 351 tokens ( 0.35 ms per token, 2848.75 tokens per second) 0.39.265.629 I slot print_timing: id 0 | task 2575 | eval time = 732.92 ms / 67 tokens ( 11.10 ms per token, 90.05 tokens per second) 0.39.265.631 I slot print_timing: id 0 | task 2575 | total time = 856.13 ms / 418 tokens 0.39.265.632 I slot print_timing: id 0 | task 2575 | graphs reused = 2469 0.39.265.632 I slot print_timing: id 0 | task 2575 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.265.659 I slot release: id 0 | task 2575 | stop processing: n_tokens = 417, truncated = 0 0.39.295.445 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 417, t_last = 39167109 0.39.319.968 I slot launch_slot_: id 0 | task 2645 | processing task, is_child = 0 0.42.128.243 I slot print_timing: id 0 | task 2645 | prompt eval time = 129.66 ms / 393 tokens ( 0.33 ms per token, 3031.10 tokens per second) 0.42.128.248 I slot print_timing: id 0 | task 2645 | eval time = 2678.60 ms / 243 tokens ( 11.07 ms per token, 90.35 tokens per second) 0.42.128.249 I slot print_timing: id 0 | task 2645 | total time = 2808.25 ms / 636 tokens 0.42.128.250 I slot print_timing: id 0 | task 2645 | graphs reused = 2709 0.42.128.251 I slot print_timing: id 0 | task 2645 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.128.282 I slot release: id 0 | task 2645 | stop processing: n_tokens = 635, truncated = 0 0.42.132.994 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 635, t_last = 42029731 0.42.158.513 I slot launch_slot_: id 0 | task 2891 | processing task, is_child = 0 0.42.605.326 I slot print_timing: id 0 | task 2891 | prompt eval time = 121.91 ms / 321 tokens ( 0.38 ms per token, 2633.11 tokens per second) 0.42.605.331 I slot print_timing: id 0 | task 2891 | eval time = 324.88 ms / 30 tokens ( 11.20 ms per token, 89.26 tokens per second) 0.42.605.332 I slot print_timing: id 0 | task 2891 | total time = 446.79 ms / 351 tokens 0.42.605.333 I slot print_timing: id 0 | task 2891 | graphs reused = 2737 0.42.605.333 I slot print_timing: id 0 | task 2891 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.605.360 I slot release: id 0 | task 2891 | stop processing: n_tokens = 350, truncated = 0 0.42.641.338 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 350, t_last = 42506810 0.42.665.092 I slot launch_slot_: id 0 | task 2924 | processing task, is_child = 0 0.44.283.791 I slot print_timing: id 0 | task 2924 | prompt eval time = 122.28 ms / 330 tokens ( 0.37 ms per token, 2698.68 tokens per second) 0.44.283.796 I slot print_timing: id 0 | task 2924 | eval time = 1496.40 ms / 136 tokens ( 11.08 ms per token, 90.22 tokens per second) 0.44.283.798 I slot print_timing: id 0 | task 2924 | total time = 1618.68 ms / 466 tokens 0.44.283.799 I slot print_timing: id 0 | task 2924 | graphs reused = 2871 0.44.283.799 I slot print_timing: id 0 | task 2924 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.283.827 I slot release: id 0 | task 2924 | stop processing: n_tokens = 465, truncated = 0 0.44.312.906 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 465, t_last = 44185276 0.44.337.504 I slot launch_slot_: id 0 | task 3063 | processing task, is_child = 0 0.45.116.607 I slot print_timing: id 0 | task 3063 | prompt eval time = 123.21 ms / 341 tokens ( 0.36 ms per token, 2767.61 tokens per second) 0.45.116.613 I slot print_timing: id 0 | task 3063 | eval time = 655.88 ms / 60 tokens ( 11.12 ms per token, 89.96 tokens per second) 0.45.116.614 I slot print_timing: id 0 | task 3063 | total time = 779.09 ms / 401 tokens 0.45.116.615 I slot print_timing: id 0 | task 3063 | graphs reused = 2929 0.45.116.616 I slot print_timing: id 0 | task 3063 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.116.643 I slot release: id 0 | task 3063 | stop processing: n_tokens = 400, truncated = 0 0.45.121.636 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 45018093 0.45.145.861 I slot launch_slot_: id 0 | task 3126 | processing task, is_child = 0 0.45.925.334 I slot print_timing: id 0 | task 3126 | prompt eval time = 123.32 ms / 338 tokens ( 0.36 ms per token, 2740.75 tokens per second) 0.45.925.340 I slot print_timing: id 0 | task 3126 | eval time = 656.13 ms / 60 tokens ( 11.12 ms per token, 89.92 tokens per second) 0.45.925.341 I slot print_timing: id 0 | task 3126 | total time = 779.45 ms / 398 tokens 0.45.925.342 I slot print_timing: id 0 | task 3126 | graphs reused = 2987 0.45.925.343 I slot print_timing: id 0 | task 3126 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.925.370 I slot release: id 0 | task 3126 | stop processing: n_tokens = 397, truncated = 0 0.45.942.372 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 397, t_last = 45826820 0.45.966.127 I slot launch_slot_: id 0 | task 3189 | processing task, is_child = 0 0.46.711.004 I slot print_timing: id 0 | task 3189 | prompt eval time = 132.56 ms / 395 tokens ( 0.34 ms per token, 2979.74 tokens per second) 0.46.711.010 I slot print_timing: id 0 | task 3189 | eval time = 612.29 ms / 56 tokens ( 11.13 ms per token, 89.83 tokens per second) 0.46.711.011 I slot print_timing: id 0 | task 3189 | total time = 744.86 ms / 451 tokens 0.46.711.011 I slot print_timing: id 0 | task 3189 | graphs reused = 3041 0.46.711.012 I slot print_timing: id 0 | task 3189 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.711.042 I slot release: id 0 | task 3189 | stop processing: n_tokens = 450, truncated = 0 0.46.738.371 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 450, t_last = 46612492 0.46.763.005 I slot launch_slot_: id 0 | task 3248 | processing task, is_child = 0 0.47.858.997 I slot print_timing: id 0 | task 3248 | prompt eval time = 183.01 ms / 528 tokens ( 0.35 ms per token, 2885.07 tokens per second) 0.47.859.002 I slot print_timing: id 0 | task 3248 | eval time = 912.96 ms / 83 tokens ( 11.13 ms per token, 89.82 tokens per second) 0.47.859.004 I slot print_timing: id 0 | task 3248 | total time = 1095.97 ms / 611 tokens 0.47.859.004 I slot print_timing: id 0 | task 3248 | graphs reused = 3122 0.47.859.005 I slot print_timing: id 0 | task 3248 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.859.039 I slot release: id 0 | task 3248 | stop processing: n_tokens = 610, truncated = 0 0.47.878.666 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 610, t_last = 47760488 0.47.908.658 I slot launch_slot_: id 0 | task 3335 | processing task, is_child = 0 0.48.705.678 I slot print_timing: id 0 | task 3335 | prompt eval time = 140.60 ms / 331 tokens ( 0.42 ms per token, 2354.23 tokens per second) 0.48.705.683 I slot print_timing: id 0 | task 3335 | eval time = 656.40 ms / 60 tokens ( 11.13 ms per token, 89.88 tokens per second) 0.48.705.684 I slot print_timing: id 0 | task 3335 | total time = 797.00 ms / 391 tokens 0.48.705.685 I slot print_timing: id 0 | task 3335 | graphs reused = 3180 0.48.705.686 I slot print_timing: id 0 | task 3335 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.705.715 I slot release: id 0 | task 3335 | stop processing: n_tokens = 402, truncated = 0 0.48.748.947 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 402, t_last = 48607164 0.48.778.008 I slot launch_slot_: id 0 | task 3398 | processing task, is_child = 0 0.49.692.039 I slot print_timing: id 0 | task 3398 | prompt eval time = 147.08 ms / 362 tokens ( 0.41 ms per token, 2461.25 tokens per second) 0.49.692.045 I slot print_timing: id 0 | task 3398 | eval time = 766.93 ms / 70 tokens ( 11.11 ms per token, 89.97 tokens per second) 0.49.692.046 I slot print_timing: id 0 | task 3398 | total time = 914.01 ms / 432 tokens 0.49.692.047 I slot print_timing: id 0 | task 3398 | graphs reused = 3248 0.49.692.048 I slot print_timing: id 0 | task 3398 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.692.076 I slot release: id 0 | task 3398 | stop processing: n_tokens = 443, truncated = 0 0.49.720.078 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 443, t_last = 49593525 0.49.749.275 I slot launch_slot_: id 0 | task 3471 | processing task, is_child = 0 0.50.960.836 I slot print_timing: id 0 | task 3471 | prompt eval time = 150.92 ms / 419 tokens ( 0.36 ms per token, 2776.23 tokens per second) 0.50.960.842 I slot print_timing: id 0 | task 3471 | eval time = 1060.61 ms / 96 tokens ( 11.16 ms per token, 89.57 tokens per second) 0.50.960.843 I slot print_timing: id 0 | task 3471 | total time = 1211.54 ms / 515 tokens 0.50.960.844 I slot print_timing: id 0 | task 3471 | graphs reused = 3341 0.50.960.845 I slot print_timing: id 0 | task 3471 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.960.880 I slot release: id 0 | task 3471 | stop processing: n_tokens = 526, truncated = 0 0.51.003.141 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 526, t_last = 50862330 0.51.033.221 I slot launch_slot_: id 0 | task 3570 | processing task, is_child = 0 0.52.158.257 I slot print_timing: id 0 | task 3570 | prompt eval time = 165.75 ms / 423 tokens ( 0.39 ms per token, 2552.11 tokens per second) 0.52.158.263 I slot print_timing: id 0 | task 3570 | eval time = 959.27 ms / 87 tokens ( 11.15 ms per token, 89.65 tokens per second) 0.52.158.264 I slot print_timing: id 0 | task 3570 | total time = 1125.02 ms / 510 tokens 0.52.158.264 I slot print_timing: id 0 | task 3570 | graphs reused = 3425 0.52.158.265 I slot print_timing: id 0 | task 3570 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.158.296 I slot release: id 0 | task 3570 | stop processing: n_tokens = 521, truncated = 0 0.52.172.462 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 521, t_last = 52059746 0.52.202.565 I slot launch_slot_: id 0 | task 3660 | processing task, is_child = 0 0.52.812.460 I slot print_timing: id 0 | task 3660 | prompt eval time = 141.42 ms / 341 tokens ( 0.41 ms per token, 2411.21 tokens per second) 0.52.812.466 I slot print_timing: id 0 | task 3660 | eval time = 468.45 ms / 43 tokens ( 11.15 ms per token, 89.66 tokens per second) 0.52.812.467 I slot print_timing: id 0 | task 3660 | total time = 609.88 ms / 384 tokens 0.52.812.468 I slot print_timing: id 0 | task 3660 | graphs reused = 3466 0.52.812.469 I slot print_timing: id 0 | task 3660 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.812.496 I slot release: id 0 | task 3660 | stop processing: n_tokens = 395, truncated = 0 0.52.846.494 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 395, t_last = 52713946 0.52.875.719 I slot launch_slot_: id 0 | task 3706 | processing task, is_child = 0 0.53.753.759 I slot print_timing: id 0 | task 3706 | prompt eval time = 142.78 ms / 356 tokens ( 0.40 ms per token, 2493.42 tokens per second) 0.53.753.765 I slot print_timing: id 0 | task 3706 | eval time = 735.25 ms / 67 tokens ( 11.14 ms per token, 89.77 tokens per second) 0.53.753.766 I slot print_timing: id 0 | task 3706 | total time = 878.02 ms / 423 tokens 0.53.753.767 I slot print_timing: id 0 | task 3706 | graphs reused = 3531 0.53.753.768 I slot print_timing: id 0 | task 3706 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.753.795 I slot release: id 0 | task 3706 | stop processing: n_tokens = 434, truncated = 0 0.53.771.553 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 434, t_last = 53655244 0.53.771.600 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 0.53.811.800 I slot launch_slot_: id 0 | task 3776 | processing task, is_child = 0 0.54.628.552 I slot print_timing: id 0 | task 3776 | prompt eval time = 148.39 ms / 362 tokens ( 0.41 ms per token, 2439.52 tokens per second) 0.54.628.558 I slot print_timing: id 0 | task 3776 | eval time = 668.35 ms / 61 tokens ( 11.14 ms per token, 89.77 tokens per second) 0.54.628.559 I slot print_timing: id 0 | task 3776 | total time = 816.74 ms / 423 tokens 0.54.628.560 I slot print_timing: id 0 | task 3776 | graphs reused = 3590 0.54.628.561 I slot print_timing: id 0 | task 3776 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.628.590 I slot release: id 0 | task 3776 | stop processing: n_tokens = 434, truncated = 0 0.54.633.382 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 434, t_last = 54530040 0.54.633.428 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.636 MiB) 0.54.672.517 I slot launch_slot_: id 0 | task 3840 | processing task, is_child = 0 0.55.817.394 I slot print_timing: id 0 | task 3840 | prompt eval time = 150.55 ms / 391 tokens ( 0.39 ms per token, 2597.20 tokens per second) 0.55.817.400 I slot print_timing: id 0 | task 3840 | eval time = 994.31 ms / 90 tokens ( 11.17 ms per token, 89.51 tokens per second) 0.55.817.401 I slot print_timing: id 0 | task 3840 | total time = 1144.86 ms / 481 tokens 0.55.817.402 I slot print_timing: id 0 | task 3840 | graphs reused = 3678 0.55.817.402 I slot print_timing: id 0 | task 3840 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.817.432 I slot release: id 0 | task 3840 | stop processing: n_tokens = 492, truncated = 0 0.55.843.729 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 492, t_last = 55718882 0.55.843.773 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.949 MiB) 0.55.846.614 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.575 MiB) 0.55.889.098 I slot launch_slot_: id 0 | task 3933 | processing task, is_child = 0 0.56.789.034 I slot print_timing: id 0 | task 3933 | prompt eval time = 143.31 ms / 343 tokens ( 0.42 ms per token, 2393.50 tokens per second) 0.56.789.040 I slot print_timing: id 0 | task 3933 | eval time = 756.61 ms / 69 tokens ( 11.13 ms per token, 89.87 tokens per second) 0.56.789.041 I slot print_timing: id 0 | task 3933 | total time = 899.92 ms / 412 tokens 0.56.789.041 I slot print_timing: id 0 | task 3933 | graphs reused = 3745 0.56.789.042 I slot print_timing: id 0 | task 3933 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.789.069 I slot release: id 0 | task 3933 | stop processing: n_tokens = 423, truncated = 0 0.56.793.876 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 423, t_last = 56690519 0.56.793.924 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.887 MiB) 0.56.832.357 I slot launch_slot_: id 0 | task 4005 | processing task, is_child = 0 0.57.681.984 I slot print_timing: id 0 | task 4005 | prompt eval time = 148.95 ms / 401 tokens ( 0.37 ms per token, 2692.20 tokens per second) 0.57.681.989 I slot print_timing: id 0 | task 4005 | eval time = 700.66 ms / 64 tokens ( 11.12 ms per token, 89.92 tokens per second) 0.57.681.990 I slot print_timing: id 0 | task 4005 | total time = 849.61 ms / 465 tokens 0.57.681.992 I slot print_timing: id 0 | task 4005 | graphs reused = 3807 0.57.681.992 I slot print_timing: id 0 | task 4005 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.682.022 I slot release: id 0 | task 4005 | stop processing: n_tokens = 476, truncated = 0 0.57.702.041 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 476, t_last = 57583472 0.57.702.091 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.543 MiB) 0.57.741.648 I slot launch_slot_: id 0 | task 4072 | processing task, is_child = 0 0.58.627.985 I slot print_timing: id 0 | task 4072 | prompt eval time = 142.64 ms / 355 tokens ( 0.40 ms per token, 2488.84 tokens per second) 0.58.627.990 I slot print_timing: id 0 | task 4072 | eval time = 743.68 ms / 68 tokens ( 11.10 ms per token, 90.09 tokens per second) 0.58.627.991 I slot print_timing: id 0 | task 4072 | total time = 886.32 ms / 423 tokens 0.58.627.992 I slot print_timing: id 0 | task 4072 | graphs reused = 3873 0.58.627.993 I slot print_timing: id 0 | task 4072 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.628.020 I slot release: id 0 | task 4072 | stop processing: n_tokens = 434, truncated = 0 0.58.646.549 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 434, t_last = 58529470 0.58.646.602 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.013 MiB) 0.58.649.550 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 168.202 MiB) 0.58.691.449 I slot launch_slot_: id 0 | task 4143 | processing task, is_child = 0 0.59.697.994 I slot print_timing: id 0 | task 4143 | prompt eval time = 143.74 ms / 351 tokens ( 0.41 ms per token, 2441.86 tokens per second) 0.59.697.999 I slot print_timing: id 0 | task 4143 | eval time = 862.78 ms / 76 tokens ( 11.50 ms per token, 86.93 tokens per second) 0.59.698.001 I slot print_timing: id 0 | task 4143 | total time = 1006.53 ms / 427 tokens 0.59.698.001 I slot print_timing: id 0 | task 4143 | graphs reused = 3947 0.59.698.002 I slot print_timing: id 0 | task 4143 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.698.031 I slot release: id 0 | task 4143 | stop processing: n_tokens = 438, truncated = 0 0.59.702.950 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 438, t_last = 59599480 0.59.702.998 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.761 MiB) 0.59.735.940 I slot launch_slot_: id 0 | task 4222 | processing task, is_child = 0 1.01.047.679 I slot print_timing: id 0 | task 4222 | prompt eval time = 168.94 ms / 475 tokens ( 0.36 ms per token, 2811.70 tokens per second) 1.01.047.685 I slot print_timing: id 0 | task 4222 | eval time = 1142.78 ms / 103 tokens ( 11.20 ms per token, 89.26 tokens per second) 1.01.047.686 I slot print_timing: id 0 | task 4222 | total time = 1311.72 ms / 578 tokens 1.01.047.687 I slot print_timing: id 0 | task 4222 | graphs reused = 4047 1.01.047.688 I slot print_timing: id 0 | task 4222 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.047.722 I slot release: id 0 | task 4222 | stop processing: n_tokens = 589, truncated = 0 1.01.067.887 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 589, t_last = 60949172 1.01.067.937 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.386 MiB) 1.01.107.653 I slot launch_slot_: id 0 | task 4328 | processing task, is_child = 0 1.02.767.392 I slot print_timing: id 0 | task 4328 | prompt eval time = 168.32 ms / 440 tokens ( 0.38 ms per token, 2614.01 tokens per second) 1.02.767.398 I slot print_timing: id 0 | task 4328 | eval time = 1491.40 ms / 135 tokens ( 11.13 ms per token, 89.85 tokens per second) 1.02.767.399 I slot print_timing: id 0 | task 4328 | total time = 1659.72 ms / 575 tokens 1.02.767.400 I slot print_timing: id 0 | task 4328 | graphs reused = 4179 1.02.767.401 I slot print_timing: id 0 | task 4328 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.767.430 I slot release: id 0 | task 4328 | stop processing: n_tokens = 586, truncated = 0 1.02.811.024 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 586, t_last = 62668879 1.02.811.078 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.981 MiB) 1.02.844.829 I slot launch_slot_: id 0 | task 4466 | processing task, is_child = 0 1.03.773.115 I slot print_timing: id 0 | task 4466 | prompt eval time = 141.06 ms / 345 tokens ( 0.41 ms per token, 2445.80 tokens per second) 1.03.773.121 I slot print_timing: id 0 | task 4466 | eval time = 787.21 ms / 72 tokens ( 11.09 ms per token, 90.19 tokens per second) 1.03.773.122 I slot print_timing: id 0 | task 4466 | total time = 928.26 ms / 417 tokens 1.03.773.123 I slot print_timing: id 0 | task 4466 | graphs reused = 4249 1.03.773.124 I slot print_timing: id 0 | task 4466 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.773.150 I slot release: id 0 | task 4466 | stop processing: n_tokens = 428, truncated = 0 1.03.807.907 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 428, t_last = 63674600 1.03.807.957 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.825 MiB) 1.03.810.555 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 1.03.848.822 I slot launch_slot_: id 0 | task 4541 | processing task, is_child = 0 1.04.840.213 I slot print_timing: id 0 | task 4541 | prompt eval time = 148.16 ms / 382 tokens ( 0.39 ms per token, 2578.38 tokens per second) 1.04.840.220 I slot print_timing: id 0 | task 4541 | eval time = 843.22 ms / 77 tokens ( 11.09 ms per token, 90.13 tokens per second) 1.04.840.221 I slot print_timing: id 0 | task 4541 | total time = 991.37 ms / 459 tokens 1.04.840.221 I slot print_timing: id 0 | task 4541 | graphs reused = 4324 1.04.840.222 I slot print_timing: id 0 | task 4541 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.840.252 I slot release: id 0 | task 4541 | stop processing: n_tokens = 470, truncated = 0 1.04.863.847 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 64741701 1.04.863.891 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.731 MiB) 1.04.897.163 I slot launch_slot_: id 0 | task 4621 | processing task, is_child = 0 1.05.529.413 I slot print_timing: id 0 | task 4621 | prompt eval time = 141.73 ms / 337 tokens ( 0.42 ms per token, 2377.69 tokens per second) 1.05.529.418 I slot print_timing: id 0 | task 4621 | eval time = 490.50 ms / 45 tokens ( 11.15 ms per token, 89.71 tokens per second) 1.05.529.419 I slot print_timing: id 0 | task 4621 | total time = 632.23 ms / 382 tokens 1.05.529.420 I slot print_timing: id 0 | task 4621 | graphs reused = 4367 1.05.529.421 I slot print_timing: id 0 | task 4621 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.529.448 I slot release: id 0 | task 4621 | stop processing: n_tokens = 393, truncated = 0 1.05.549.156 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 65430898 1.05.549.204 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.700 MiB) 1.05.581.760 I slot launch_slot_: id 0 | task 4669 | processing task, is_child = 0 1.06.738.162 I slot print_timing: id 0 | task 4669 | prompt eval time = 149.53 ms / 402 tokens ( 0.37 ms per token, 2688.35 tokens per second) 1.06.738.168 I slot print_timing: id 0 | task 4669 | eval time = 1006.85 ms / 89 tokens ( 11.44 ms per token, 87.40 tokens per second) 1.06.738.169 I slot print_timing: id 0 | task 4669 | total time = 1156.38 ms / 491 tokens 1.06.738.170 I slot print_timing: id 0 | task 4669 | graphs reused = 4454 1.06.738.171 I slot print_timing: id 0 | task 4669 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.738.200 I slot release: id 0 | task 4669 | stop processing: n_tokens = 502, truncated = 0 1.06.743.470 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 502, t_last = 66639649 1.06.743.519 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.012 MiB) 1.06.746.227 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.543 MiB) 1.06.786.323 I slot launch_slot_: id 0 | task 4761 | processing task, is_child = 0 1.07.891.106 I slot print_timing: id 0 | task 4761 | prompt eval time = 190.47 ms / 549 tokens ( 0.35 ms per token, 2882.31 tokens per second) 1.07.891.112 I slot print_timing: id 0 | task 4761 | eval time = 914.29 ms / 83 tokens ( 11.15 ms per token, 89.69 tokens per second) 1.07.891.113 I slot print_timing: id 0 | task 4761 | total time = 1104.76 ms / 632 tokens 1.07.891.114 I slot print_timing: id 0 | task 4761 | graphs reused = 4535 1.07.891.115 I slot print_timing: id 0 | task 4761 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.891.148 I slot release: id 0 | task 4761 | stop processing: n_tokens = 643, truncated = 0 1.07.907.794 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 643, t_last = 67792598 1.07.907.854 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.011 MiB) 1.07.952.484 I slot launch_slot_: id 0 | task 4848 | processing task, is_child = 0 1.08.949.797 I slot print_timing: id 0 | task 4848 | prompt eval time = 204.75 ms / 616 tokens ( 0.33 ms per token, 3008.49 tokens per second) 1.08.949.803 I slot print_timing: id 0 | task 4848 | eval time = 792.54 ms / 72 tokens ( 11.16 ms per token, 89.59 tokens per second) 1.08.949.804 I slot print_timing: id 0 | task 4848 | total time = 997.30 ms / 688 tokens 1.08.949.805 I slot print_timing: id 0 | task 4848 | graphs reused = 4605 1.08.949.806 I slot print_timing: id 0 | task 4848 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.949.840 I slot release: id 0 | task 4848 | stop processing: n_tokens = 699, truncated = 0 1.08.973.968 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 699, t_last = 68851290 1.08.974.030 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.324 MiB) 1.08.976.593 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.356 MiB) 1.09.021.505 I slot launch_slot_: id 0 | task 4924 | processing task, is_child = 0 1.10.161.061 I slot print_timing: id 0 | task 4924 | prompt eval time = 215.21 ms / 665 tokens ( 0.32 ms per token, 3090.08 tokens per second) 1.10.161.067 I slot print_timing: id 0 | task 4924 | eval time = 924.33 ms / 84 tokens ( 11.14 ms per token, 89.79 tokens per second) 1.10.161.068 I slot print_timing: id 0 | task 4924 | total time = 1139.54 ms / 749 tokens 1.10.161.068 I slot print_timing: id 0 | task 4924 | graphs reused = 4687 1.10.161.069 I slot print_timing: id 0 | task 4924 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.161.106 I slot release: id 0 | task 4924 | stop processing: n_tokens = 760, truncated = 0 1.10.191.098 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 760, t_last = 70062556 1.10.191.163 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.074 MiB) 1.10.193.820 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.201 MiB) 1.10.237.045 I slot launch_slot_: id 0 | task 5012 | processing task, is_child = 0 1.11.197.578 I slot print_timing: id 0 | task 5012 | prompt eval time = 212.28 ms / 645 tokens ( 0.33 ms per token, 3038.41 tokens per second) 1.11.197.584 I slot print_timing: id 0 | task 5012 | eval time = 748.23 ms / 68 tokens ( 11.17 ms per token, 89.54 tokens per second) 1.11.197.585 I slot print_timing: id 0 | task 5012 | total time = 960.51 ms / 713 tokens 1.11.197.586 I slot print_timing: id 0 | task 5012 | graphs reused = 4753 1.11.197.587 I slot print_timing: id 0 | task 5012 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.197.622 I slot release: id 0 | task 5012 | stop processing: n_tokens = 724, truncated = 0 1.11.202.602 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 724, t_last = 71099072 1.11.202.665 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.200 MiB) 1.11.243.564 I slot launch_slot_: id 0 | task 5084 | processing task, is_child = 0 1.12.243.371 I slot print_timing: id 0 | task 5084 | prompt eval time = 169.90 ms / 474 tokens ( 0.36 ms per token, 2789.96 tokens per second) 1.12.243.376 I slot print_timing: id 0 | task 5084 | eval time = 829.90 ms / 75 tokens ( 11.21 ms per token, 89.17 tokens per second) 1.12.243.378 I slot print_timing: id 0 | task 5084 | total time = 999.79 ms / 549 tokens 1.12.243.379 I slot print_timing: id 0 | task 5084 | graphs reused = 4825 1.12.243.379 I slot print_timing: id 0 | task 5084 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.243.413 I slot release: id 0 | task 5084 | stop processing: n_tokens = 560, truncated = 0 1.12.248.741 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 72144862 1.12.248.794 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.013 MiB) 1.12.251.587 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 167.858 MiB) 1.12.286.046 I slot launch_slot_: id 0 | task 5162 | processing task, is_child = 0 1.13.199.526 I slot print_timing: id 0 | task 5162 | prompt eval time = 201.25 ms / 617 tokens ( 0.33 ms per token, 3065.85 tokens per second) 1.13.199.531 I slot print_timing: id 0 | task 5162 | eval time = 712.21 ms / 65 tokens ( 11.13 ms per token, 89.86 tokens per second) 1.13.199.532 I slot print_timing: id 0 | task 5162 | total time = 913.46 ms / 682 tokens 1.13.199.533 I slot print_timing: id 0 | task 5162 | graphs reused = 4888 1.13.199.534 I slot print_timing: id 0 | task 5162 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.199.568 I slot release: id 0 | task 5162 | stop processing: n_tokens = 693, truncated = 0 1.13.204.696 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 73101017 1.13.204.756 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.919 MiB) 1.13.244.816 I slot launch_slot_: id 0 | task 5231 | processing task, is_child = 0 1.14.264.300 I slot print_timing: id 0 | task 5231 | prompt eval time = 199.34 ms / 601 tokens ( 0.33 ms per token, 3014.95 tokens per second) 1.14.264.306 I slot print_timing: id 0 | task 5231 | eval time = 820.12 ms / 72 tokens ( 11.55 ms per token, 86.57 tokens per second) 1.14.264.307 I slot print_timing: id 0 | task 5231 | total time = 1019.47 ms / 673 tokens 1.14.264.308 I slot print_timing: id 0 | task 5231 | graphs reused = 4958 1.14.264.308 I slot print_timing: id 0 | task 5231 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.264.345 I slot release: id 0 | task 5231 | stop processing: n_tokens = 684, truncated = 0 1.14.282.363 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 684, t_last = 74165795 1.14.282.427 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.855 MiB) 1.14.285.217 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.200 MiB) 1.14.326.759 I slot launch_slot_: id 0 | task 5307 | processing task, is_child = 0 1.15.186.693 I slot print_timing: id 0 | task 5307 | prompt eval time = 190.60 ms / 533 tokens ( 0.36 ms per token, 2796.48 tokens per second) 1.15.186.700 I slot print_timing: id 0 | task 5307 | eval time = 669.32 ms / 61 tokens ( 11.16 ms per token, 89.64 tokens per second) 1.15.186.701 I slot print_timing: id 0 | task 5307 | total time = 859.91 ms / 594 tokens 1.15.186.701 I slot print_timing: id 0 | task 5307 | graphs reused = 5017 1.15.186.702 I slot print_timing: id 0 | task 5307 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.186.734 I slot release: id 0 | task 5307 | stop processing: n_tokens = 605, truncated = 0 1.15.191.790 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 605, t_last = 75088183 1.15.191.846 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.545 MiB) 1.15.194.613 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.950 MiB) 1.15.235.704 I slot launch_slot_: id 0 | task 5372 | processing task, is_child = 0 1.16.211.831 I slot print_timing: id 0 | task 5372 | prompt eval time = 174.29 ms / 480 tokens ( 0.36 ms per token, 2753.95 tokens per second) 1.16.211.837 I slot print_timing: id 0 | task 5372 | eval time = 801.81 ms / 71 tokens ( 11.45 ms per token, 87.30 tokens per second) 1.16.211.838 I slot print_timing: id 0 | task 5372 | total time = 976.11 ms / 551 tokens 1.16.211.839 I slot print_timing: id 0 | task 5372 | graphs reused = 5085 1.16.211.840 I slot print_timing: id 0 | task 5372 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.211.871 I slot release: id 0 | task 5372 | stop processing: n_tokens = 579, truncated = 0 1.16.250.759 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 579, t_last = 76113320 1.16.250.817 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.324 MiB) 1.16.291.085 I slot launch_slot_: id 0 | task 5446 | processing task, is_child = 0 1.17.138.373 I slot print_timing: id 0 | task 5446 | prompt eval time = 197.53 ms / 567 tokens ( 0.35 ms per token, 2870.45 tokens per second) 1.17.138.379 I slot print_timing: id 0 | task 5446 | eval time = 649.74 ms / 57 tokens ( 11.60 ms per token, 86.19 tokens per second) 1.17.138.380 I slot print_timing: id 0 | task 5446 | total time = 847.27 ms / 624 tokens 1.17.138.381 I slot print_timing: id 0 | task 5446 | graphs reused = 5140 1.17.138.382 I slot print_timing: id 0 | task 5446 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.138.415 I slot release: id 0 | task 5446 | stop processing: n_tokens = 652, truncated = 0 1.17.143.745 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 652, t_last = 77039865 1.17.143.806 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.105 MiB) 1.17.146.508 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.388 MiB) 1.17.194.385 I slot launch_slot_: id 0 | task 5507 | processing task, is_child = 0 1.18.540.682 I slot print_timing: id 0 | task 5507 | prompt eval time = 181.50 ms / 506 tokens ( 0.36 ms per token, 2787.83 tokens per second) 1.18.540.688 I slot print_timing: id 0 | task 5507 | eval time = 1164.78 ms / 102 tokens ( 11.53 ms per token, 86.71 tokens per second) 1.18.540.689 I slot print_timing: id 0 | task 5507 | total time = 1346.28 ms / 608 tokens 1.18.540.690 I slot print_timing: id 0 | task 5507 | graphs reused = 5240 1.18.540.691 I slot print_timing: id 0 | task 5507 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.540.723 I slot release: id 0 | task 5507 | stop processing: n_tokens = 636, truncated = 0 1.18.557.954 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 636, t_last = 78442172 1.18.558.012 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.201 MiB) 1.18.560.645 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.793 MiB) 1.18.606.277 I slot launch_slot_: id 0 | task 5612 | processing task, is_child = 0 1.19.207.059 I slot print_timing: id 0 | task 5612 | prompt eval time = 165.19 ms / 436 tokens ( 0.38 ms per token, 2639.43 tokens per second) 1.19.207.064 I slot print_timing: id 0 | task 5612 | eval time = 435.57 ms / 40 tokens ( 11.17 ms per token, 89.54 tokens per second) 1.19.207.065 I slot print_timing: id 0 | task 5612 | total time = 600.76 ms / 476 tokens 1.19.207.066 I slot print_timing: id 0 | task 5612 | graphs reused = 5278 1.19.207.067 I slot print_timing: id 0 | task 5612 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.207.096 I slot release: id 0 | task 5612 | stop processing: n_tokens = 504, truncated = 0 1.19.230.483 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 79108545 1.19.230.536 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 170.610 MiB) 1.19.270.662 I slot launch_slot_: id 0 | task 5655 | processing task, is_child = 0 1.20.358.173 I slot print_timing: id 0 | task 5655 | prompt eval time = 182.06 ms / 519 tokens ( 0.35 ms per token, 2850.69 tokens per second) 1.20.358.178 I slot print_timing: id 0 | task 5655 | eval time = 905.43 ms / 81 tokens ( 11.32 ms per token, 88.36 tokens per second) 1.20.358.179 I slot print_timing: id 0 | task 5655 | total time = 1087.49 ms / 600 tokens 1.20.358.181 I slot print_timing: id 0 | task 5655 | graphs reused = 5357 1.20.358.182 I slot print_timing: id 0 | task 5655 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.358.217 I slot release: id 0 | task 5655 | stop processing: n_tokens = 628, truncated = 0 1.20.385.172 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 628, t_last = 80259666 1.20.385.234 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 161.697 MiB) 1.20.387.869 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.294 MiB) 1.20.437.747 I slot launch_slot_: id 0 | task 5740 | processing task, is_child = 0 1.21.139.565 I slot print_timing: id 0 | task 5740 | prompt eval time = 171.78 ms / 465 tokens ( 0.37 ms per token, 2706.90 tokens per second) 1.21.139.571 I slot print_timing: id 0 | task 5740 | eval time = 530.01 ms / 46 tokens ( 11.78 ms per token, 84.90 tokens per second) 1.21.139.572 I slot print_timing: id 0 | task 5740 | total time = 701.80 ms / 511 tokens 1.21.139.572 I slot print_timing: id 0 | task 5740 | graphs reused = 5400 1.21.139.573 I slot print_timing: id 0 | task 5740 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.139.606 I slot release: id 0 | task 5740 | stop processing: n_tokens = 542, truncated = 0 1.21.159.798 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 542, t_last = 81041056 1.21.159.852 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.261 MiB) 1.21.162.540 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.167 MiB) 1.21.208.949 I slot launch_slot_: id 0 | task 5789 | processing task, is_child = 0 1.22.060.521 I slot print_timing: id 0 | task 5789 | prompt eval time = 171.43 ms / 431 tokens ( 0.40 ms per token, 2514.16 tokens per second) 1.22.060.525 I slot print_timing: id 0 | task 5789 | eval time = 680.12 ms / 59 tokens ( 11.73 ms per token, 85.28 tokens per second) 1.22.060.526 I slot print_timing: id 0 | task 5789 | total time = 851.55 ms / 490 tokens 1.22.060.527 I slot print_timing: id 0 | task 5789 | graphs reused = 5456 1.22.060.528 I slot print_timing: id 0 | task 5789 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.060.559 I slot release: id 0 | task 5789 | stop processing: n_tokens = 521, truncated = 0 1.22.078.634 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 521, t_last = 81962009 1.22.078.684 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.825 MiB) 1.22.081.464 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 220.079 MiB) 1.22.127.490 I slot launch_slot_: id 0 | task 5851 | processing task, is_child = 0 1.22.981.945 I slot print_timing: id 0 | task 5851 | prompt eval time = 171.64 ms / 457 tokens ( 0.38 ms per token, 2662.60 tokens per second) 1.22.981.950 I slot print_timing: id 0 | task 5851 | eval time = 682.79 ms / 61 tokens ( 11.38 ms per token, 87.87 tokens per second) 1.22.981.951 I slot print_timing: id 0 | task 5851 | total time = 854.43 ms / 518 tokens 1.22.981.952 I slot print_timing: id 0 | task 5851 | graphs reused = 5514 1.22.981.953 I slot print_timing: id 0 | task 5851 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.981.983 I slot release: id 0 | task 5851 | stop processing: n_tokens = 549, truncated = 0 1.23.009.717 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 82883432 1.23.009.771 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.574 MiB) 1.23.013.220 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.856 MiB) 1.23.061.404 I slot launch_slot_: id 0 | task 5915 | processing task, is_child = 0 1.23.946.807 I slot print_timing: id 0 | task 5915 | prompt eval time = 167.56 ms / 439 tokens ( 0.38 ms per token, 2619.88 tokens per second) 1.23.946.812 I slot print_timing: id 0 | task 5915 | eval time = 717.82 ms / 65 tokens ( 11.22 ms per token, 89.16 tokens per second) 1.23.946.813 I slot print_timing: id 0 | task 5915 | total time = 885.38 ms / 504 tokens 1.23.946.814 I slot print_timing: id 0 | task 5915 | graphs reused = 5576 1.23.946.815 I slot print_timing: id 0 | task 5915 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.946.848 I slot release: id 0 | task 5915 | stop processing: n_tokens = 535, truncated = 0 1.23.970.822 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 535, t_last = 83848297 1.23.970.875 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 217.452 MiB) 1.24.019.481 I slot launch_slot_: id 0 | task 5983 | processing task, is_child = 0 1.25.021.399 I slot print_timing: id 0 | task 5983 | prompt eval time = 205.18 ms / 606 tokens ( 0.34 ms per token, 2953.49 tokens per second) 1.25.021.405 I slot print_timing: id 0 | task 5983 | eval time = 796.72 ms / 70 tokens ( 11.55 ms per token, 86.61 tokens per second) 1.25.021.406 I slot print_timing: id 0 | task 5983 | total time = 1001.90 ms / 676 tokens 1.25.021.407 I slot print_timing: id 0 | task 5983 | graphs reused = 5644 1.25.021.408 I slot print_timing: id 0 | task 5983 | graph reallocs = 0 / 0 (same size) / (changed size) 1.25.021.446 I slot release: id 0 | task 5983 | stop processing: n_tokens = 707, truncated = 0 1.25.045.053 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 707, t_last = 84922895 1.25.045.116 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 217.296 MiB) 1.25.048.524 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.355 MiB) 1.25.106.849 I slot launch_slot_: id 0 | task 6057 | processing task, is_child = 0 1.26.054.568 I slot print_timing: id 0 | task 6057 | prompt eval time = 174.70 ms / 477 tokens ( 0.37 ms per token, 2730.44 tokens per second) 1.26.054.574 I slot print_timing: id 0 | task 6057 | eval time = 773.00 ms / 67 tokens ( 11.71 ms per token, 85.38 tokens per second) 1.26.054.575 I slot print_timing: id 0 | task 6057 | total time = 947.70 ms / 544 tokens 1.26.054.576 I slot print_timing: id 0 | task 6057 | graphs reused = 5708 1.26.054.577 I slot print_timing: id 0 | task 6057 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.054.609 I slot release: id 0 | task 6057 | stop processing: n_tokens = 575, truncated = 0 1.26.061.072 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 575, t_last = 85956058 1.26.061.119 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.575 MiB) 1.26.114.485 I slot launch_slot_: id 0 | task 6127 | processing task, is_child = 0 1.27.171.146 I slot print_timing: id 0 | task 6127 | prompt eval time = 257.31 ms / 845 tokens ( 0.30 ms per token, 3284.04 tokens per second) 1.27.171.152 I slot print_timing: id 0 | task 6127 | eval time = 799.34 ms / 72 tokens ( 11.26 ms per token, 88.82 tokens per second) 1.27.171.153 I slot print_timing: id 0 | task 6127 | total time = 1056.64 ms / 917 tokens 1.27.171.154 I slot print_timing: id 0 | task 6127 | graphs reused = 5778 1.27.171.155 I slot print_timing: id 0 | task 6127 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.171.201 I slot release: id 0 | task 6127 | stop processing: n_tokens = 948, truncated = 0 1.27.193.508 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 948, t_last = 87072650 1.27.193.582 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.575 MiB) 1.27.197.364 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.389 MiB) 1.27.268.345 I slot launch_slot_: id 0 | task 6203 | processing task, is_child = 0 1.28.186.923 I slot print_timing: id 0 | task 6203 | prompt eval time = 170.14 ms / 459 tokens ( 0.37 ms per token, 2697.79 tokens per second) 1.28.186.929 I slot print_timing: id 0 | task 6203 | eval time = 748.42 ms / 67 tokens ( 11.34 ms per token, 88.19 tokens per second) 1.28.186.930 I slot print_timing: id 0 | task 6203 | total time = 918.56 ms / 526 tokens 1.28.186.932 I slot print_timing: id 0 | task 6203 | graphs reused = 5842 1.28.186.933 I slot print_timing: id 0 | task 6203 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.186.965 I slot release: id 0 | task 6203 | stop processing: n_tokens = 557, truncated = 0 1.28.219.839 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 557, t_last = 88088414 1.28.219.892 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.231 MiB) 1.28.275.215 I slot launch_slot_: id 0 | task 6273 | processing task, is_child = 0 1.29.297.456 I slot print_timing: id 0 | task 6273 | prompt eval time = 219.12 ms / 670 tokens ( 0.33 ms per token, 3057.74 tokens per second) 1.29.297.461 I slot print_timing: id 0 | task 6273 | eval time = 803.10 ms / 70 tokens ( 11.64 ms per token, 85.92 tokens per second) 1.29.297.462 I slot print_timing: id 0 | task 6273 | total time = 1022.22 ms / 740 tokens 1.29.297.463 I slot print_timing: id 0 | task 6273 | graphs reused = 5909 1.29.297.464 I slot print_timing: id 0 | task 6273 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.297.502 I slot release: id 0 | task 6273 | stop processing: n_tokens = 771, truncated = 0 1.29.317.246 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 771, t_last = 89198952 1.29.317.310 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.888 MiB) 1.29.321.087 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.575 MiB) 1.29.389.005 I slot launch_slot_: id 0 | task 6347 | processing task, is_child = 0 1.30.584.683 I slot print_timing: id 0 | task 6347 | prompt eval time = 246.80 ms / 775 tokens ( 0.32 ms per token, 3140.16 tokens per second) 1.30.584.690 I slot print_timing: id 0 | task 6347 | eval time = 948.86 ms / 83 tokens ( 11.57 ms per token, 86.42 tokens per second) 1.30.584.691 I slot print_timing: id 0 | task 6347 | total time = 1195.66 ms / 858 tokens 1.30.584.691 I slot print_timing: id 0 | task 6347 | graphs reused = 5990 1.30.584.692 I slot print_timing: id 0 | task 6347 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.584.745 I slot release: id 0 | task 6347 | stop processing: n_tokens = 889, truncated = 0 1.30.610.930 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 889, t_last = 90486195 1.30.610.999 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.700 MiB) 1.30.614.648 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 219.422 MiB) 1.30.682.251 I slot launch_slot_: id 0 | task 6434 | processing task, is_child = 0 1.31.778.161 I slot print_timing: id 0 | task 6434 | prompt eval time = 194.19 ms / 573 tokens ( 0.34 ms per token, 2950.73 tokens per second) 1.31.778.167 I slot print_timing: id 0 | task 6434 | eval time = 901.70 ms / 82 tokens ( 11.13 ms per token, 89.83 tokens per second) 1.31.778.168 I slot print_timing: id 0 | task 6434 | total time = 1095.89 ms / 655 tokens 1.31.778.168 I slot print_timing: id 0 | task 6434 | graphs reused = 6070 1.31.778.169 I slot print_timing: id 0 | task 6434 | graph reallocs = 0 / 0 (same size) / (changed size) 1.31.778.204 I slot release: id 0 | task 6434 | stop processing: n_tokens = 686, truncated = 0 1.31.793.812 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 686, t_last = 91679653 1.31.793.872 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 219.328 MiB) 1.31.797.562 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.387 MiB) 1.31.855.588 I slot launch_slot_: id 0 | task 6520 | processing task, is_child = 0 1.32.901.898 I slot print_timing: id 0 | task 6520 | prompt eval time = 168.98 ms / 461 tokens ( 0.37 ms per token, 2728.07 tokens per second) 1.32.901.904 I slot print_timing: id 0 | task 6520 | eval time = 877.31 ms / 77 tokens ( 11.54 ms per token, 86.63 tokens per second) 1.32.901.905 I slot print_timing: id 0 | task 6520 | total time = 1046.29 ms / 538 tokens 1.32.901.905 I slot print_timing: id 0 | task 6520 | graphs reused = 6144 1.32.901.906 I slot print_timing: id 0 | task 6520 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.901.938 I slot release: id 0 | task 6520 | stop processing: n_tokens = 569, truncated = 0 1.32.947.635 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 569, t_last = 92803388 1.32.947.685 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.701 MiB) 1.32.993.387 I slot launch_slot_: id 0 | task 6600 | processing task, is_child = 0 1.34.688.180 I slot print_timing: id 0 | task 6600 | prompt eval time = 202.37 ms / 609 tokens ( 0.33 ms per token, 3009.34 tokens per second) 1.34.688.186 I slot print_timing: id 0 | task 6600 | eval time = 1492.40 ms / 130 tokens ( 11.57 ms per token, 86.44 tokens per second) 1.34.688.187 I slot print_timing: id 0 | task 6600 | total time = 1694.77 ms / 739 tokens 1.34.688.188 I slot print_timing: id 0 | task 6600 | graphs reused = 6271 1.34.688.189 I slot print_timing: id 0 | task 6600 | graph reallocs = 0 / 0 (same size) / (changed size) 1.34.688.227 I slot release: id 0 | task 6600 | stop processing: n_tokens = 770, truncated = 0 1.34.694.078 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 770, t_last = 94589677 1.34.694.141 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.293 MiB) 1.34.697.765 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.701 MiB) 1.34.756.454 I slot launch_slot_: id 0 | task 6734 | processing task, is_child = 0 1.35.877.835 I slot print_timing: id 0 | task 6734 | prompt eval time = 239.30 ms / 791 tokens ( 0.30 ms per token, 3305.46 tokens per second) 1.35.877.840 I slot print_timing: id 0 | task 6734 | eval time = 882.06 ms / 80 tokens ( 11.17 ms per token, 89.56 tokens per second) 1.35.877.841 I slot print_timing: id 0 | task 6734 | total time = 1121.36 ms / 871 tokens 1.35.877.842 I slot print_timing: id 0 | task 6734 | graphs reused = 6349 1.35.877.843 I slot print_timing: id 0 | task 6734 | graph reallocs = 0 / 0 (same size) / (changed size) 1.35.877.885 I slot release: id 0 | task 6734 | stop processing: n_tokens = 902, truncated = 0 1.35.893.854 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 902, t_last = 95779334 1.35.893.924 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 271.362 MiB) 1.35.965.163 I slot launch_slot_: id 0 | task 6818 | processing task, is_child = 0 1.36.991.146 I slot print_timing: id 0 | task 6818 | prompt eval time = 185.47 ms / 533 tokens ( 0.35 ms per token, 2873.80 tokens per second) 1.36.991.151 I slot print_timing: id 0 | task 6818 | eval time = 840.49 ms / 74 tokens ( 11.51 ms per token, 86.85 tokens per second) 1.36.991.152 I slot print_timing: id 0 | task 6818 | total time = 1025.96 ms / 607 tokens 1.36.991.153 I slot print_timing: id 0 | task 6818 | graphs reused = 6421 1.36.991.154 I slot print_timing: id 0 | task 6818 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.991.189 I slot release: id 0 | task 6818 | stop processing: n_tokens = 695, truncated = 0 1.37.031.885 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 695, t_last = 96892639 1.37.031.947 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.113 MiB) 1.37.096.621 I slot launch_slot_: id 0 | task 6896 | processing task, is_child = 0 1.37.850.543 I slot print_timing: id 0 | task 6896 | prompt eval time = 200.51 ms / 566 tokens ( 0.35 ms per token, 2822.79 tokens per second) 1.37.850.549 I slot print_timing: id 0 | task 6896 | eval time = 553.39 ms / 46 tokens ( 12.30 ms per token, 81.32 tokens per second) 1.37.850.550 I slot print_timing: id 0 | task 6896 | total time = 753.90 ms / 612 tokens 1.37.850.551 I slot print_timing: id 0 | task 6896 | graphs reused = 6465 1.37.850.552 I slot print_timing: id 0 | task 6896 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.850.588 I slot release: id 0 | task 6896 | stop processing: n_tokens = 643, truncated = 0 1.37.876.358 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 643, t_last = 97752038 1.37.876.417 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 275.020 MiB) 1.37.933.065 I slot launch_slot_: id 0 | task 6946 | processing task, is_child = 0 1.38.772.221 I slot print_timing: id 0 | task 6946 | prompt eval time = 172.95 ms / 443 tokens ( 0.39 ms per token, 2561.46 tokens per second) 1.38.772.227 I slot print_timing: id 0 | task 6946 | eval time = 666.19 ms / 58 tokens ( 11.69 ms per token, 85.56 tokens per second) 1.38.772.228 I slot print_timing: id 0 | task 6946 | total time = 839.13 ms / 501 tokens 1.38.772.229 I slot print_timing: id 0 | task 6946 | graphs reused = 6520 1.38.772.230 I slot print_timing: id 0 | task 6946 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.772.261 I slot release: id 0 | task 6946 | stop processing: n_tokens = 532, truncated = 0 1.38.777.801 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 532, t_last = 98673711 1.38.777.847 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.895 MiB) 1.38.826.616 I slot launch_slot_: id 0 | task 7007 | processing task, is_child = 0 1.40.063.557 I slot print_timing: id 0 | task 7007 | prompt eval time = 172.16 ms / 487 tokens ( 0.35 ms per token, 2828.83 tokens per second) 1.40.063.563 I slot print_timing: id 0 | task 7007 | eval time = 1064.77 ms / 96 tokens ( 11.21 ms per token, 89.22 tokens per second) 1.40.063.564 I slot print_timing: id 0 | task 7007 | total time = 1236.92 ms / 583 tokens 1.40.063.565 I slot print_timing: id 0 | task 7007 | graphs reused = 6614 1.40.063.565 I slot print_timing: id 0 | task 7007 | graph reallocs = 0 / 0 (same size) / (changed size) 1.40.063.599 I slot release: id 0 | task 7007 | stop processing: n_tokens = 614, truncated = 0 1.40.104.876 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 614, t_last = 99965049 1.40.104.932 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 218.515 MiB) 1.40.108.599 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 272.925 MiB) 1.40.158.407 I slot launch_slot_: id 0 | task 7106 | processing task, is_child = 0 1.41.107.008 I slot print_timing: id 0 | task 7106 | prompt eval time = 175.72 ms / 507 tokens ( 0.35 ms per token, 2885.32 tokens per second) 1.41.107.013 I slot print_timing: id 0 | task 7106 | eval time = 772.86 ms / 68 tokens ( 11.54 ms per token, 86.69 tokens per second) 1.41.107.014 I slot print_timing: id 0 | task 7106 | total time = 948.58 ms / 575 tokens 1.41.107.015 I slot print_timing: id 0 | task 7106 | graphs reused = 6680 1.41.107.016 I slot print_timing: id 0 | task 7106 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.107.050 I slot release: id 0 | task 7106 | stop processing: n_tokens = 606, truncated = 0 1.41.112.555 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 606, t_last = 101008499 1.41.112.603 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 272.644 MiB) 1.41.160.826 I slot launch_slot_: id 0 | task 7177 | processing task, is_child = 0 1.42.117.770 I slot print_timing: id 0 | task 7177 | prompt eval time = 206.89 ms / 633 tokens ( 0.33 ms per token, 3059.66 tokens per second) 1.42.117.776 I slot print_timing: id 0 | task 7177 | eval time = 750.04 ms / 66 tokens ( 11.54 ms per token, 86.66 tokens per second) 1.42.117.777 I slot print_timing: id 0 | task 7177 | total time = 956.93 ms / 699 tokens 1.42.117.778 I slot print_timing: id 0 | task 7177 | graphs reused = 6744 1.42.117.778 I slot print_timing: id 0 | task 7177 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.117.815 I slot release: id 0 | task 7177 | stop processing: n_tokens = 730, truncated = 0 1.42.139.757 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 730, t_last = 102019265 1.42.139.822 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 270.173 MiB) 1.42.198.531 I slot launch_slot_: id 0 | task 7247 | processing task, is_child = 0 1.43.089.184 I slot print_timing: id 0 | task 7247 | prompt eval time = 203.27 ms / 571 tokens ( 0.36 ms per token, 2809.10 tokens per second) 1.43.089.191 I slot print_timing: id 0 | task 7247 | eval time = 687.36 ms / 59 tokens ( 11.85 ms per token, 84.38 tokens per second) 1.43.089.192 I slot print_timing: id 0 | task 7247 | total time = 890.63 ms / 630 tokens 1.43.089.193 I slot print_timing: id 0 | task 7247 | graphs reused = 6801 1.43.089.194 I slot print_timing: id 0 | task 7247 | graph reallocs = 0 / 0 (same size) / (changed size) 1.43.089.239 I slot release: id 0 | task 7247 | stop processing: n_tokens = 661, truncated = 0 1.43.120.912 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 661, t_last = 102990689 1.43.120.981 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 269.360 MiB) 1.43.182.124 I slot launch_slot_: id 0 | task 7310 | processing task, is_child = 0 1.43.921.476 I slot print_timing: id 0 | task 7310 | prompt eval time = 243.14 ms / 798 tokens ( 0.30 ms per token, 3282.11 tokens per second) 1.43.921.482 I slot print_timing: id 0 | task 7310 | eval time = 496.19 ms / 44 tokens ( 11.54 ms per token, 86.66 tokens per second) 1.43.921.483 I slot print_timing: id 0 | task 7310 | total time = 739.32 ms / 842 tokens 1.43.921.484 I slot print_timing: id 0 | task 7310 | graphs reused = 6843 1.43.921.485 I slot print_timing: id 0 | task 7310 | graph reallocs = 0 / 0 (same size) / (changed size) 1.43.921.535 I slot release: id 0 | task 7310 | stop processing: n_tokens = 873, truncated = 0 1.43.953.037 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 873, t_last = 103822985 1.43.953.111 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.894 MiB) 1.43.958.495 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 271.143 MiB) 1.44.030.540 I slot launch_slot_: id 0 | task 7358 | processing task, is_child = 0 1.44.959.400 I slot print_timing: id 0 | task 7358 | prompt eval time = 197.32 ms / 572 tokens ( 0.34 ms per token, 2898.84 tokens per second) 1.44.959.406 I slot print_timing: id 0 | task 7358 | eval time = 731.52 ms / 63 tokens ( 11.80 ms per token, 84.76 tokens per second) 1.44.959.407 I slot print_timing: id 0 | task 7358 | total time = 928.84 ms / 635 tokens 1.44.959.408 I slot print_timing: id 0 | task 7358 | graphs reused = 6904 1.44.959.409 I slot print_timing: id 0 | task 7358 | graph reallocs = 0 / 0 (same size) / (changed size) 1.44.959.451 I slot release: id 0 | task 7358 | stop processing: n_tokens = 666, truncated = 0 1.44.965.705 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 666, t_last = 104860901 1.44.965.774 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 267.015 MiB) 1.45.027.827 I slot launch_slot_: id 0 | task 7425 | processing task, is_child = 0 1.46.248.261 I slot print_timing: id 0 | task 7425 | prompt eval time = 210.96 ms / 613 tokens ( 0.34 ms per token, 2905.74 tokens per second) 1.46.248.267 I slot print_timing: id 0 | task 7425 | eval time = 1009.45 ms / 86 tokens ( 11.88 ms per token, 84.20 tokens per second) 1.46.248.269 I slot print_timing: id 0 | task 7425 | total time = 1220.41 ms / 699 tokens 1.46.248.269 I slot print_timing: id 0 | task 7425 | graphs reused = 6988 1.46.248.270 I slot print_timing: id 0 | task 7425 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.248.307 I slot release: id 0 | task 7425 | stop processing: n_tokens = 730, truncated = 0 1.46.277.819 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 730, t_last = 106149757 1.46.277.874 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.143 MiB) 1.46.342.368 I slot launch_slot_: id 0 | task 7515 | processing task, is_child = 0 1.47.604.876 I slot print_timing: id 0 | task 7515 | prompt eval time = 202.90 ms / 580 tokens ( 0.35 ms per token, 2858.57 tokens per second) 1.47.604.881 I slot print_timing: id 0 | task 7515 | eval time = 1059.59 ms / 93 tokens ( 11.52 ms per token, 86.83 tokens per second) 1.47.604.883 I slot print_timing: id 0 | task 7515 | total time = 1262.49 ms / 673 tokens 1.47.604.883 I slot print_timing: id 0 | task 7515 | graphs reused = 7079 1.47.604.884 I slot print_timing: id 0 | task 7515 | graph reallocs = 0 / 0 (same size) / (changed size) 1.47.604.920 I slot release: id 0 | task 7515 | stop processing: n_tokens = 704, truncated = 0 1.47.650.102 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 704, t_last = 107506370 1.47.650.164 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.454 MiB) 1.47.705.241 I slot launch_slot_: id 0 | task 7612 | processing task, is_child = 0 1.48.706.297 I slot print_timing: id 0 | task 7612 | prompt eval time = 221.66 ms / 716 tokens ( 0.31 ms per token, 3230.23 tokens per second) 1.48.706.302 I slot print_timing: id 0 | task 7612 | eval time = 779.38 ms / 70 tokens ( 11.30 ms per token, 88.53 tokens per second) 1.48.706.303 I slot print_timing: id 0 | task 7612 | total time = 1001.04 ms / 786 tokens 1.48.706.304 I slot print_timing: id 0 | task 7612 | graphs reused = 7146 1.48.706.305 I slot print_timing: id 0 | task 7612 | graph reallocs = 0 / 0 (same size) / (changed size) 1.48.706.344 I slot release: id 0 | task 7612 | stop processing: n_tokens = 817, truncated = 0 1.48.736.719 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 817, t_last = 108607793 1.48.736.787 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.797 MiB) 1.48.741.868 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 1.48.802.380 I slot launch_slot_: id 0 | task 7686 | processing task, is_child = 0 1.50.447.852 I slot print_timing: id 0 | task 7686 | prompt eval time = 246.39 ms / 799 tokens ( 0.31 ms per token, 3242.81 tokens per second) 1.50.447.858 I slot print_timing: id 0 | task 7686 | eval time = 1399.06 ms / 122 tokens ( 11.56 ms per token, 86.49 tokens per second) 1.50.447.859 I slot print_timing: id 0 | task 7686 | total time = 1645.45 ms / 921 tokens 1.50.447.860 I slot print_timing: id 0 | task 7686 | graphs reused = 7266 1.50.447.860 I slot print_timing: id 0 | task 7686 | graph reallocs = 0 / 0 (same size) / (changed size) 1.50.447.903 I slot release: id 0 | task 7686 | stop processing: n_tokens = 952, truncated = 0 1.50.453.102 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 952, t_last = 110349352 1.50.453.172 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.235 MiB) 1.50.511.713 I slot launch_slot_: id 0 | task 7812 | processing task, is_child = 0 1.52.100.056 I slot print_timing: id 0 | task 7812 | prompt eval time = 154.74 ms / 361 tokens ( 0.43 ms per token, 2332.93 tokens per second) 1.52.100.061 I slot print_timing: id 0 | task 7812 | eval time = 1433.58 ms / 129 tokens ( 11.20 ms per token, 89.29 tokens per second) 1.52.100.062 I slot print_timing: id 0 | task 7812 | total time = 1588.32 ms / 490 tokens 1.52.100.063 I slot print_timing: id 0 | task 7812 | graphs reused = 7392 1.52.100.064 I slot print_timing: id 0 | task 7812 | graph reallocs = 0 / 0 (same size) / (changed size) 1.52.100.094 I slot release: id 0 | task 7812 | stop processing: n_tokens = 521, truncated = 0 1.52.124.317 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 521, t_last = 112001544 1.52.124.367 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.864 MiB) 1.52.179.124 I slot launch_slot_: id 0 | task 7944 | processing task, is_child = 0 1.53.703.079 I slot print_timing: id 0 | task 7944 | prompt eval time = 147.12 ms / 381 tokens ( 0.39 ms per token, 2589.74 tokens per second) 1.53.703.084 I slot print_timing: id 0 | task 7944 | eval time = 1376.82 ms / 121 tokens ( 11.47 ms per token, 87.16 tokens per second) 1.53.703.085 I slot print_timing: id 0 | task 7944 | total time = 1523.94 ms / 502 tokens 1.53.703.086 I slot print_timing: id 0 | task 7944 | graphs reused = 7510 1.53.703.086 I slot print_timing: id 0 | task 7944 | graph reallocs = 0 / 0 (same size) / (changed size) 1.53.703.117 I slot release: id 0 | task 7944 | stop processing: n_tokens = 533, truncated = 0 1.53.727.794 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 533, t_last = 113604566 1.53.727.845 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.486 MiB) 1.53.782.499 I slot launch_slot_: id 0 | task 8068 | processing task, is_child = 0 1.55.466.152 I slot print_timing: id 0 | task 8068 | prompt eval time = 147.78 ms / 365 tokens ( 0.40 ms per token, 2469.94 tokens per second) 1.55.466.157 I slot print_timing: id 0 | task 8068 | eval time = 1535.86 ms / 135 tokens ( 11.46 ms per token, 87.25 tokens per second) 1.55.466.158 I slot print_timing: id 0 | task 8068 | total time = 1683.63 ms / 500 tokens 1.55.466.159 I slot print_timing: id 0 | task 8068 | graphs reused = 7642 1.55.466.159 I slot print_timing: id 0 | task 8068 | graph reallocs = 0 / 0 (same size) / (changed size) 1.55.466.188 I slot release: id 0 | task 8068 | stop processing: n_tokens = 531, truncated = 0 1.55.499.574 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 531, t_last = 115367638 1.55.499.623 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.401 MiB) 1.55.560.932 I slot launch_slot_: id 0 | task 8206 | processing task, is_child = 0 1.57.214.523 I slot print_timing: id 0 | task 8206 | prompt eval time = 143.20 ms / 333 tokens ( 0.43 ms per token, 2325.44 tokens per second) 1.57.214.530 I slot print_timing: id 0 | task 8206 | eval time = 1510.37 ms / 136 tokens ( 11.19 ms per token, 89.38 tokens per second) 1.57.214.531 I slot print_timing: id 0 | task 8206 | total time = 1653.57 ms / 469 tokens 1.57.214.532 I slot print_timing: id 0 | task 8206 | graphs reused = 7776 1.57.214.532 I slot print_timing: id 0 | task 8206 | graph reallocs = 0 / 0 (same size) / (changed size) 1.57.214.566 I slot release: id 0 | task 8206 | stop processing: n_tokens = 500, truncated = 0 1.57.240.603 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 500, t_last = 117116016 1.57.281.071 I slot launch_slot_: id 0 | task 8345 | processing task, is_child = 0 1.58.655.309 I slot print_timing: id 0 | task 8345 | prompt eval time = 153.26 ms / 403 tokens ( 0.38 ms per token, 2629.50 tokens per second) 1.58.655.314 I slot print_timing: id 0 | task 8345 | eval time = 1220.96 ms / 107 tokens ( 11.52 ms per token, 86.82 tokens per second) 1.58.655.315 I slot print_timing: id 0 | task 8345 | total time = 1374.22 ms / 510 tokens 1.58.655.316 I slot print_timing: id 0 | task 8345 | graphs reused = 7880 1.58.655.317 I slot print_timing: id 0 | task 8345 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.655.348 I slot release: id 0 | task 8345 | stop processing: n_tokens = 541, truncated = 0 1.58.669.529 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 541, t_last = 118556797 1.58.669.580 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.923 MiB) 1.58.725.848 I slot launch_slot_: id 0 | task 8455 | processing task, is_child = 0 2.01.111.127 I slot print_timing: id 0 | task 8455 | prompt eval time = 155.29 ms / 411 tokens ( 0.38 ms per token, 2646.68 tokens per second) 2.01.111.132 I slot print_timing: id 0 | task 8455 | eval time = 2229.97 ms / 200 tokens ( 11.21 ms per token, 89.24 tokens per second) 2.01.111.133 I slot print_timing: id 0 | task 8455 | total time = 2385.26 ms / 611 tokens 2.01.111.134 I slot print_timing: id 0 | task 8455 | graphs reused = 8077 2.01.111.135 I slot print_timing: id 0 | task 8455 | graph reallocs = 0 / 0 (same size) / (changed size) 2.01.111.165 I slot release: id 0 | task 8455 | stop processing: n_tokens = 642, truncated = 0 2.01.146.828 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 642, t_last = 121012614 2.01.146.879 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 375.866 MiB) 2.01.208.966 I slot launch_slot_: id 0 | task 8658 | processing task, is_child = 0 2.04.046.352 I slot print_timing: id 0 | task 8658 | prompt eval time = 182.59 ms / 490 tokens ( 0.37 ms per token, 2683.59 tokens per second) 2.04.046.357 I slot print_timing: id 0 | task 8658 | eval time = 2654.78 ms / 235 tokens ( 11.35 ms per token, 88.14 tokens per second) 2.04.046.358 I slot print_timing: id 0 | task 8658 | total time = 2837.37 ms / 725 tokens 2.04.046.359 I slot print_timing: id 0 | task 8658 | graphs reused = 8310 2.04.046.360 I slot print_timing: id 0 | task 8658 | graph reallocs = 0 / 0 (same size) / (changed size) 2.04.046.391 I slot release: id 0 | task 8658 | stop processing: n_tokens = 756, truncated = 0 2.04.065.751 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 756, t_last = 123947841 2.04.065.813 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.556 MiB) 2.04.124.163 I slot launch_slot_: id 0 | task 8896 | processing task, is_child = 0 2.06.373.917 I slot print_timing: id 0 | task 8896 | prompt eval time = 142.70 ms / 344 tokens ( 0.41 ms per token, 2410.67 tokens per second) 2.06.373.923 I slot print_timing: id 0 | task 8896 | eval time = 2107.03 ms / 186 tokens ( 11.39 ms per token, 87.80 tokens per second) 2.06.373.924 I slot print_timing: id 0 | task 8896 | total time = 2249.73 ms / 530 tokens 2.06.373.925 I slot print_timing: id 0 | task 8896 | graphs reused = 8493 2.06.373.926 I slot print_timing: id 0 | task 8896 | graph reallocs = 0 / 0 (same size) / (changed size) 2.06.373.955 I slot release: id 0 | task 8896 | stop processing: n_tokens = 561, truncated = 0 2.06.378.757 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 561, t_last = 126275405 2.06.378.811 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.298 MiB) 2.06.428.116 I slot launch_slot_: id 0 | task 9085 | processing task, is_child = 0 2.08.639.336 I slot print_timing: id 0 | task 9085 | prompt eval time = 148.07 ms / 347 tokens ( 0.43 ms per token, 2343.50 tokens per second) 2.08.639.341 I slot print_timing: id 0 | task 9085 | eval time = 2063.13 ms / 187 tokens ( 11.09 ms per token, 90.15 tokens per second) 2.08.639.342 I slot print_timing: id 0 | task 9085 | total time = 2211.20 ms / 534 tokens 2.08.639.343 I slot print_timing: id 0 | task 9085 | graphs reused = 8677 2.08.639.344 I slot print_timing: id 0 | task 9085 | graph reallocs = 0 / 0 (same size) / (changed size) 2.08.639.371 I slot release: id 0 | task 9085 | stop processing: n_tokens = 565, truncated = 0 2.08.666.292 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 565, t_last = 128540821 2.08.666.343 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 375.834 MiB) 2.08.721.543 I slot launch_slot_: id 0 | task 9275 | processing task, is_child = 0 2.10.368.322 I slot print_timing: id 0 | task 9275 | prompt eval time = 156.02 ms / 401 tokens ( 0.39 ms per token, 2570.17 tokens per second) 2.10.368.327 I slot print_timing: id 0 | task 9275 | eval time = 1490.74 ms / 135 tokens ( 11.12 ms per token, 89.89 tokens per second) 2.10.368.328 I slot print_timing: id 0 | task 9275 | total time = 1646.76 ms / 536 tokens 2.10.368.329 I slot print_timing: id 0 | task 9275 | graphs reused = 8809 2.10.368.330 I slot print_timing: id 0 | task 9275 | graph reallocs = 0 / 0 (same size) / (changed size) 2.10.368.359 I slot release: id 0 | task 9275 | stop processing: n_tokens = 567, truncated = 0 2.10.389.737 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 567, t_last = 130269809 2.10.389.792 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.962 MiB) 2.10.441.074 I slot launch_slot_: id 0 | task 9413 | processing task, is_child = 0 2.12.071.351 I slot print_timing: id 0 | task 9413 | prompt eval time = 161.16 ms / 456 tokens ( 0.35 ms per token, 2829.52 tokens per second) 2.12.071.357 I slot print_timing: id 0 | task 9413 | eval time = 1469.10 ms / 131 tokens ( 11.30 ms per token, 88.49 tokens per second) 2.12.071.358 I slot print_timing: id 0 | task 9413 | total time = 1630.26 ms / 587 tokens 2.12.071.359 I slot print_timing: id 0 | task 9413 | graphs reused = 8937 2.12.071.360 I slot print_timing: id 0 | task 9413 | graph reallocs = 0 / 0 (same size) / (changed size) 2.12.071.391 I slot release: id 0 | task 9413 | stop processing: n_tokens = 618, truncated = 0 2.12.103.773 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.107 (> 0.100 thold), f_keep = 0.076 2.12.103.828 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 423.739 MiB) 2.12.166.457 I slot launch_slot_: id 0 | task 9547 | processing task, is_child = 0 2.13.718.335 I slot print_timing: id 0 | task 9547 | prompt eval time = 155.23 ms / 406 tokens ( 0.38 ms per token, 2615.49 tokens per second) 2.13.718.341 I slot print_timing: id 0 | task 9547 | eval time = 1396.63 ms / 127 tokens ( 11.08 ms per token, 90.22 tokens per second) 2.13.718.342 I slot print_timing: id 0 | task 9547 | total time = 1551.86 ms / 533 tokens 2.13.718.343 I slot print_timing: id 0 | task 9547 | graphs reused = 9061 2.13.718.344 I slot print_timing: id 0 | task 9547 | graph reallocs = 0 / 0 (same size) / (changed size) 2.13.718.375 I slot release: id 0 | task 9547 | stop processing: n_tokens = 564, truncated = 0 2.13.723.302 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 564, t_last = 133619825 2.13.762.998 I slot launch_slot_: id 0 | task 9677 | processing task, is_child = 0 2.16.068.308 I slot print_timing: id 0 | task 9677 | prompt eval time = 156.91 ms / 406 tokens ( 0.39 ms per token, 2587.54 tokens per second) 2.16.068.313 I slot print_timing: id 0 | task 9677 | eval time = 2148.39 ms / 195 tokens ( 11.07 ms per token, 90.30 tokens per second) 2.16.068.314 I slot print_timing: id 0 | task 9677 | total time = 2305.29 ms / 601 tokens 2.16.068.315 I slot print_timing: id 0 | task 9677 | graphs reused = 9253 2.16.068.316 I slot print_timing: id 0 | task 9677 | graph reallocs = 0 / 0 (same size) / (changed size) 2.16.068.348 I slot release: id 0 | task 9677 | stop processing: n_tokens = 632, truncated = 0 2.16.083.576 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 632, t_last = 135969797 2.16.083.631 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 371.863 MiB) 2.16.137.011 I slot launch_slot_: id 0 | task 9875 | processing task, is_child = 0 2.17.881.172 I slot print_timing: id 0 | task 9875 | prompt eval time = 159.05 ms / 444 tokens ( 0.36 ms per token, 2791.50 tokens per second) 2.17.881.178 I slot print_timing: id 0 | task 9875 | eval time = 1585.09 ms / 144 tokens ( 11.08 ms per token, 90.22 tokens per second) 2.17.881.179 I slot print_timing: id 0 | task 9875 | total time = 1744.14 ms / 588 tokens 2.17.881.180 I slot print_timing: id 0 | task 9875 | graphs reused = 9394 2.17.881.181 I slot print_timing: id 0 | task 9875 | graph reallocs = 0 / 0 (same size) / (changed size) 2.17.881.210 I slot release: id 0 | task 9875 | stop processing: n_tokens = 619, truncated = 0 2.17.912.713 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 619, t_last = 137782660 2.17.912.767 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.141 MiB) 2.17.961.311 I slot launch_slot_: id 0 | task 10022 | processing task, is_child = 0 2.19.442.497 I slot print_timing: id 0 | task 10022 | prompt eval time = 148.90 ms / 372 tokens ( 0.40 ms per token, 2498.34 tokens per second) 2.19.442.503 I slot print_timing: id 0 | task 10022 | eval time = 1332.27 ms / 121 tokens ( 11.10 ms per token, 90.07 tokens per second) 2.19.442.504 I slot print_timing: id 0 | task 10022 | total time = 1481.17 ms / 493 tokens 2.19.442.505 I slot print_timing: id 0 | task 10022 | graphs reused = 9512 2.19.442.506 I slot print_timing: id 0 | task 10022 | graph reallocs = 0 / 0 (same size) / (changed size) 2.19.442.536 I slot release: id 0 | task 10022 | stop processing: n_tokens = 524, truncated = 0 2.19.471.018 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 524, t_last = 139343986 2.19.471.068 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.705 MiB) 2.19.521.572 I slot launch_slot_: id 0 | task 10146 | processing task, is_child = 0 2.22.447.081 I slot print_timing: id 0 | task 10146 | prompt eval time = 158.16 ms / 454 tokens ( 0.35 ms per token, 2870.53 tokens per second) 2.22.447.086 I slot print_timing: id 0 | task 10146 | eval time = 2767.33 ms / 248 tokens ( 11.20 ms per token, 89.26 tokens per second) 2.22.447.087 I slot print_timing: id 0 | task 10146 | total time = 2925.49 ms / 702 tokens 2.22.447.088 I slot print_timing: id 0 | task 10146 | graphs reused = 9757 2.22.447.089 I slot print_timing: id 0 | task 10146 | graph reallocs = 0 / 0 (same size) / (changed size) 2.22.447.120 I slot release: id 0 | task 10146 | stop processing: n_tokens = 733, truncated = 0 2.22.467.936 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 733, t_last = 142348570 2.22.467.997 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.455 MiB) 2.22.519.530 I slot launch_slot_: id 0 | task 10397 | processing task, is_child = 0 2.25.399.544 I slot print_timing: id 0 | task 10397 | prompt eval time = 149.58 ms / 354 tokens ( 0.42 ms per token, 2366.61 tokens per second) 2.25.399.550 I slot print_timing: id 0 | task 10397 | eval time = 2730.41 ms / 243 tokens ( 11.28 ms per token, 88.63 tokens per second) 2.25.399.551 I slot print_timing: id 0 | task 10397 | total time = 2879.99 ms / 597 tokens 2.25.399.551 I slot print_timing: id 0 | task 10397 | graphs reused = 9997 2.25.399.553 I slot print_timing: id 0 | task 10397 | graph reallocs = 0 / 0 (same size) / (changed size) 2.25.399.583 I slot release: id 0 | task 10397 | stop processing: n_tokens = 628, truncated = 0 2.25.426.572 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 628, t_last = 145301032 2.25.426.633 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.583 MiB) 2.25.478.662 I slot launch_slot_: id 0 | task 10643 | processing task, is_child = 0 2.27.431.063 I slot print_timing: id 0 | task 10643 | prompt eval time = 146.43 ms / 334 tokens ( 0.44 ms per token, 2280.91 tokens per second) 2.27.431.069 I slot print_timing: id 0 | task 10643 | eval time = 1805.95 ms / 160 tokens ( 11.36 ms per token, 88.04 tokens per second) 2.27.431.070 I slot print_timing: id 0 | task 10643 | total time = 1952.38 ms / 494 tokens 2.27.431.071 I slot print_timing: id 0 | task 10643 | graphs reused = 10154 2.27.431.072 I slot print_timing: id 0 | task 10643 | graph reallocs = 0 / 0 (same size) / (changed size) 2.27.431.100 I slot release: id 0 | task 10643 | stop processing: n_tokens = 525, truncated = 0 2.27.456.284 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 525, t_last = 147332550 2.27.456.338 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 372.426 MiB) 2.27.508.352 I slot launch_slot_: id 0 | task 10806 | processing task, is_child = 0 2.29.847.224 I slot print_timing: id 0 | task 10806 | prompt eval time = 161.39 ms / 426 tokens ( 0.38 ms per token, 2639.52 tokens per second) 2.29.847.229 I slot print_timing: id 0 | task 10806 | eval time = 2177.46 ms / 192 tokens ( 11.40 ms per token, 87.72 tokens per second) 2.29.847.230 I slot print_timing: id 0 | task 10806 | total time = 2338.85 ms / 618 tokens 2.29.847.231 I slot print_timing: id 0 | task 10806 | graphs reused = 10343 2.29.847.232 I slot print_timing: id 0 | task 10806 | graph reallocs = 0 / 0 (same size) / (changed size) 2.29.847.264 I slot release: id 0 | task 10806 | stop processing: n_tokens = 649, truncated = 0 2.29.879.834 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 649, t_last = 149748713 2.29.879.893 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.055 MiB) 2.29.955.304 I slot launch_slot_: id 0 | task 11001 | processing task, is_child = 0 2.31.712.599 I slot print_timing: id 0 | task 11001 | prompt eval time = 150.64 ms / 366 tokens ( 0.41 ms per token, 2429.65 tokens per second) 2.31.712.604 I slot print_timing: id 0 | task 11001 | eval time = 1606.64 ms / 144 tokens ( 11.24 ms per token, 89.01 tokens per second) 2.31.712.606 I slot print_timing: id 0 | task 11001 | total time = 1757.28 ms / 510 tokens 2.31.712.607 I slot print_timing: id 0 | task 11001 | graphs reused = 10484 2.31.712.608 I slot print_timing: id 0 | task 11001 | graph reallocs = 0 / 0 (same size) / (changed size) 2.31.712.636 I slot release: id 0 | task 11001 | stop processing: n_tokens = 541, truncated = 0 2.31.757.986 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 541, t_last = 151614086 2.31.758.036 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 372.582 MiB) 2.31.808.699 I slot launch_slot_: id 0 | task 11148 | processing task, is_child = 0 2.34.979.181 I slot print_timing: id 0 | task 11148 | n_gen = 264, tg = 87.56 t/s, tg_3s = 87.89 t/s 2.35.248.249 I slot print_timing: id 0 | task 11148 | prompt eval time = 166.84 ms / 462 tokens ( 0.36 ms per token, 2769.09 tokens per second) 2.35.248.254 I slot print_timing: id 0 | task 11148 | eval time = 3272.69 ms / 288 tokens ( 11.40 ms per token, 87.70 tokens per second) 2.35.248.256 I slot print_timing: id 0 | task 11148 | total time = 3439.53 ms / 750 tokens 2.35.248.257 I slot print_timing: id 0 | task 11148 | graphs reused = 10768 2.35.248.257 I slot print_timing: id 0 | task 11148 | graph reallocs = 0 / 0 (same size) / (changed size) 2.35.248.287 I slot release: id 0 | task 11148 | stop processing: n_tokens = 781, truncated = 0 2.35.266.356 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 781, t_last = 155149737 2.35.266.417 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.583 MiB) 2.35.321.110 I slot launch_slot_: id 0 | task 11439 | processing task, is_child = 0 2.37.261.696 I slot print_timing: id 0 | task 11439 | prompt eval time = 150.59 ms / 396 tokens ( 0.38 ms per token, 2629.69 tokens per second) 2.37.261.702 I slot print_timing: id 0 | task 11439 | eval time = 1789.97 ms / 160 tokens ( 11.26 ms per token, 88.83 tokens per second) 2.37.261.703 I slot print_timing: id 0 | task 11439 | total time = 1940.56 ms / 556 tokens 2.37.261.704 I slot print_timing: id 0 | task 11439 | graphs reused = 10925 2.37.261.705 I slot print_timing: id 0 | task 11439 | graph reallocs = 0 / 0 (same size) / (changed size) 2.37.261.740 I slot release: id 0 | task 11439 | stop processing: n_tokens = 587, truncated = 0 2.37.296.918 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 587, t_last = 157163189 2.37.337.609 I slot launch_slot_: id 0 | task 11602 | processing task, is_child = 0 2.39.503.182 I slot print_timing: id 0 | task 11602 | prompt eval time = 166.26 ms / 458 tokens ( 0.36 ms per token, 2754.77 tokens per second) 2.39.503.188 I slot print_timing: id 0 | task 11602 | eval time = 1999.30 ms / 175 tokens ( 11.49 ms per token, 87.03 tokens per second) 2.39.503.189 I slot print_timing: id 0 | task 11602 | total time = 2165.55 ms / 633 tokens 2.39.503.190 I slot print_timing: id 0 | task 11602 | graphs reused = 11097 2.39.503.190 I slot print_timing: id 0 | task 11602 | graph reallocs = 0 / 0 (same size) / (changed size) 2.39.503.221 I slot release: id 0 | task 11602 | stop processing: n_tokens = 664, truncated = 0 2.39.540.670 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 664, t_last = 159404670 2.39.540.718 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.770 MiB) 2.39.592.597 I slot launch_slot_: id 0 | task 11780 | processing task, is_child = 0 2.41.959.753 I slot print_timing: id 0 | task 11780 | prompt eval time = 167.15 ms / 458 tokens ( 0.36 ms per token, 2740.14 tokens per second) 2.41.959.759 I slot print_timing: id 0 | task 11780 | eval time = 2199.99 ms / 195 tokens ( 11.34 ms per token, 88.18 tokens per second) 2.41.959.760 I slot print_timing: id 0 | task 11780 | total time = 2367.13 ms / 653 tokens 2.41.959.761 I slot print_timing: id 0 | task 11780 | graphs reused = 11289 2.41.959.762 I slot print_timing: id 0 | task 11780 | graph reallocs = 0 / 0 (same size) / (changed size) 2.41.959.792 I slot release: id 0 | task 11780 | stop processing: n_tokens = 684, truncated = 0 2.41.977.434 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 684, t_last = 161861242 2.41.977.495 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 377.304 MiB) 2.42.032.888 I slot launch_slot_: id 0 | task 11978 | processing task, is_child = 0 2.44.838.852 I slot print_timing: id 0 | task 11978 | prompt eval time = 167.60 ms / 452 tokens ( 0.37 ms per token, 2696.90 tokens per second) 2.44.838.857 I slot print_timing: id 0 | task 11978 | eval time = 2638.34 ms / 234 tokens ( 11.32 ms per token, 88.31 tokens per second) 2.44.838.858 I slot print_timing: id 0 | task 11978 | total time = 2805.94 ms / 686 tokens 2.44.838.860 I slot print_timing: id 0 | task 11978 | graphs reused = 11520 2.44.838.861 I slot print_timing: id 0 | task 11978 | graph reallocs = 0 / 0 (same size) / (changed size) 2.44.838.893 I slot release: id 0 | task 11978 | stop processing: n_tokens = 717, truncated = 0 2.44.864.211 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 717, t_last = 164740343 2.44.864.270 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.526 MiB) 2.44.917.384 I slot launch_slot_: id 0 | task 12215 | processing task, is_child = 0 2.46.672.104 I slot print_timing: id 0 | task 12215 | prompt eval time = 158.92 ms / 404 tokens ( 0.39 ms per token, 2542.14 tokens per second) 2.46.672.110 I slot print_timing: id 0 | task 12215 | eval time = 1595.78 ms / 139 tokens ( 11.56 ms per token, 86.48 tokens per second) 2.46.672.111 I slot print_timing: id 0 | task 12215 | total time = 1754.70 ms / 543 tokens 2.46.672.112 I slot print_timing: id 0 | task 12215 | graphs reused = 11656 2.46.672.113 I slot print_timing: id 0 | task 12215 | graph reallocs = 0 / 0 (same size) / (changed size) 2.46.672.142 I slot release: id 0 | task 12215 | stop processing: n_tokens = 574, truncated = 0 2.46.705.104 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 574, t_last = 166573592 2.46.705.157 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.797 MiB) 2.46.761.389 I slot launch_slot_: id 0 | task 12357 | processing task, is_child = 0 2.48.294.160 I slot print_timing: id 0 | task 12357 | prompt eval time = 148.98 ms / 345 tokens ( 0.43 ms per token, 2315.81 tokens per second) 2.48.294.165 I slot print_timing: id 0 | task 12357 | eval time = 1383.77 ms / 124 tokens ( 11.25 ms per token, 88.89 tokens per second) 2.48.294.166 I slot print_timing: id 0 | task 12357 | total time = 1532.75 ms / 469 tokens 2.48.294.166 I slot print_timing: id 0 | task 12357 | graphs reused = 11778 2.48.294.167 I slot print_timing: id 0 | task 12357 | graph reallocs = 0 / 0 (same size) / (changed size) 2.48.294.195 I slot release: id 0 | task 12357 | stop processing: n_tokens = 500, truncated = 0 2.48.311.786 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 500, t_last = 168195645 2.48.311.836 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.172 MiB) 2.48.365.553 I slot launch_slot_: id 0 | task 12484 | processing task, is_child = 0 2.49.866.361 I slot print_timing: id 0 | task 12484 | prompt eval time = 169.27 ms / 430 tokens ( 0.39 ms per token, 2540.38 tokens per second) 2.49.866.367 I slot print_timing: id 0 | task 12484 | eval time = 1331.52 ms / 118 tokens ( 11.38 ms per token, 87.87 tokens per second) 2.49.866.368 I slot print_timing: id 0 | task 12484 | total time = 1500.79 ms / 548 tokens 2.49.866.369 I slot print_timing: id 0 | task 12484 | graphs reused = 11893 2.49.866.370 I slot print_timing: id 0 | task 12484 | graph reallocs = 0 / 0 (same size) / (changed size) 2.49.866.401 I slot release: id 0 | task 12484 | stop processing: n_tokens = 579, truncated = 0 2.49.871.043 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 579, t_last = 169767850 2.49.871.095 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.110 MiB) 2.49.932.159 I slot launch_slot_: id 0 | task 12605 | processing task, is_child = 0 2.51.177.708 I slot print_timing: id 0 | task 12605 | prompt eval time = 139.98 ms / 316 tokens ( 0.44 ms per token, 2257.53 tokens per second) 2.51.177.714 I slot print_timing: id 0 | task 12605 | eval time = 1105.55 ms / 97 tokens ( 11.52 ms per token, 86.83 tokens per second) 2.51.177.715 I slot print_timing: id 0 | task 12605 | total time = 1245.53 ms / 413 tokens 2.51.177.716 I slot print_timing: id 0 | task 12605 | graphs reused = 11988 2.51.177.717 I slot print_timing: id 0 | task 12605 | graph reallocs = 0 / 0 (same size) / (changed size) 2.51.177.746 I slot release: id 0 | task 12605 | stop processing: n_tokens = 444, truncated = 0 2.51.205.745 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 444, t_last = 171079196 2.51.205.793 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.140 MiB) 2.51.252.997 I slot launch_slot_: id 0 | task 12705 | processing task, is_child = 0 2.52.791.617 I slot print_timing: id 0 | task 12705 | prompt eval time = 149.85 ms / 354 tokens ( 0.42 ms per token, 2362.38 tokens per second) 2.52.791.623 I slot print_timing: id 0 | task 12705 | eval time = 1388.75 ms / 126 tokens ( 11.11 ms per token, 90.01 tokens per second) 2.52.791.624 I slot print_timing: id 0 | task 12705 | total time = 1538.60 ms / 480 tokens 2.52.791.625 I slot print_timing: id 0 | task 12705 | graphs reused = 12112 2.52.791.626 I slot print_timing: id 0 | task 12705 | graph reallocs = 0 / 0 (same size) / (changed size) 2.52.791.654 I slot release: id 0 | task 12705 | stop processing: n_tokens = 511, truncated = 0 2.52.827.139 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 511, t_last = 172693104 2.52.827.181 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.422 MiB) 2.52.882.996 I slot launch_slot_: id 0 | task 12834 | processing task, is_child = 0 2.54.316.617 I slot print_timing: id 0 | task 12834 | prompt eval time = 167.98 ms / 438 tokens ( 0.38 ms per token, 2607.42 tokens per second) 2.54.316.623 I slot print_timing: id 0 | task 12834 | eval time = 1265.62 ms / 111 tokens ( 11.51 ms per token, 86.91 tokens per second) 2.54.316.624 I slot print_timing: id 0 | task 12834 | total time = 1433.60 ms / 549 tokens 2.54.316.625 I slot print_timing: id 0 | task 12834 | graphs reused = 12220 2.54.316.625 I slot print_timing: id 0 | task 12834 | graph reallocs = 0 / 0 (same size) / (changed size) 2.54.316.656 I slot release: id 0 | task 12834 | stop processing: n_tokens = 580, truncated = 0 2.54.321.633 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 580, t_last = 174218105 2.54.321.686 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.581 MiB) 2.54.382.437 I slot launch_slot_: id 0 | task 12948 | processing task, is_child = 0 2.55.697.808 I slot print_timing: id 0 | task 12948 | prompt eval time = 172.44 ms / 457 tokens ( 0.38 ms per token, 2650.21 tokens per second) 2.55.697.813 I slot print_timing: id 0 | task 12948 | eval time = 1142.91 ms / 100 tokens ( 11.54 ms per token, 86.62 tokens per second) 2.55.697.814 I slot print_timing: id 0 | task 12948 | total time = 1315.35 ms / 557 tokens 2.55.697.815 I slot print_timing: id 0 | task 12948 | graphs reused = 12317 2.55.697.816 I slot print_timing: id 0 | task 12948 | graph reallocs = 0 / 0 (same size) / (changed size) 2.55.697.847 I slot release: id 0 | task 12948 | stop processing: n_tokens = 588, truncated = 0 2.55.735.550 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 588, t_last = 175599296 2.55.735.604 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.146 MiB) 2.55.794.079 I slot launch_slot_: id 0 | task 13051 | processing task, is_child = 0 2.57.219.877 I slot print_timing: id 0 | task 13051 | prompt eval time = 172.50 ms / 473 tokens ( 0.36 ms per token, 2742.11 tokens per second) 2.57.219.883 I slot print_timing: id 0 | task 13051 | eval time = 1253.28 ms / 113 tokens ( 11.19 ms per token, 89.37 tokens per second) 2.57.219.884 I slot print_timing: id 0 | task 13051 | total time = 1425.78 ms / 586 tokens 2.57.219.884 I slot print_timing: id 0 | task 13051 | graphs reused = 12427 2.57.219.885 I slot print_timing: id 0 | task 13051 | graph reallocs = 0 / 0 (same size) / (changed size) 2.57.219.917 I slot release: id 0 | task 13051 | stop processing: n_tokens = 617, truncated = 0 2.57.252.843 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 617, t_last = 177121367 2.57.252.902 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.048 MiB) 2.57.302.839 I slot launch_slot_: id 0 | task 13167 | processing task, is_child = 0 2.58.068.852 I slot print_timing: id 0 | task 13167 | prompt eval time = 172.27 ms / 476 tokens ( 0.36 ms per token, 2763.04 tokens per second) 2.58.068.858 I slot print_timing: id 0 | task 13167 | eval time = 593.72 ms / 52 tokens ( 11.64 ms per token, 85.90 tokens per second) 2.58.068.859 I slot print_timing: id 0 | task 13167 | total time = 765.99 ms / 528 tokens 2.58.068.859 I slot print_timing: id 0 | task 13167 | graphs reused = 12476 2.58.068.860 I slot print_timing: id 0 | task 13167 | graph reallocs = 0 / 0 (same size) / (changed size) 2.58.068.894 I slot release: id 0 | task 13167 | stop processing: n_tokens = 559, truncated = 0 2.58.105.700 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 559, t_last = 177970343 2.58.105.756 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.173 MiB) 2.58.160.458 I slot launch_slot_: id 0 | task 13222 | processing task, is_child = 0 2.59.685.447 I slot print_timing: id 0 | task 13222 | prompt eval time = 178.92 ms / 466 tokens ( 0.38 ms per token, 2604.50 tokens per second) 2.59.685.453 I slot print_timing: id 0 | task 13222 | eval time = 1346.05 ms / 118 tokens ( 11.50 ms per token, 86.92 tokens per second) 2.59.685.454 I slot print_timing: id 0 | task 13222 | total time = 1524.97 ms / 584 tokens 2.59.685.455 I slot print_timing: id 0 | task 13222 | graphs reused = 12591 2.59.685.455 I slot print_timing: id 0 | task 13222 | graph reallocs = 0 / 0 (same size) / (changed size) 2.59.685.488 I slot release: id 0 | task 13222 | stop processing: n_tokens = 615, truncated = 0 2.59.704.459 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 615, t_last = 179586938 2.59.704.513 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.235 MiB) 2.59.754.954 I slot launch_slot_: id 0 | task 13343 | processing task, is_child = 0 3.01.109.913 I slot print_timing: id 0 | task 13343 | prompt eval time = 150.10 ms / 415 tokens ( 0.36 ms per token, 2764.77 tokens per second) 3.01.109.918 I slot print_timing: id 0 | task 13343 | eval time = 1204.84 ms / 109 tokens ( 11.16 ms per token, 89.64 tokens per second) 3.01.109.919 I slot print_timing: id 0 | task 13343 | total time = 1354.94 ms / 524 tokens 3.01.109.920 I slot print_timing: id 0 | task 13343 | graphs reused = 12697 3.01.109.921 I slot print_timing: id 0 | task 13343 | graph reallocs = 0 / 0 (same size) / (changed size) 3.01.109.952 I slot release: id 0 | task 13343 | stop processing: n_tokens = 555, truncated = 0 3.01.114.671 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 555, t_last = 181011402 3.01.114.724 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.830 MiB) 3.01.175.547 I slot launch_slot_: id 0 | task 13455 | processing task, is_child = 0 3.02.368.251 I slot print_timing: id 0 | task 13455 | prompt eval time = 147.21 ms / 352 tokens ( 0.42 ms per token, 2391.11 tokens per second) 3.02.368.257 I slot print_timing: id 0 | task 13455 | eval time = 1045.47 ms / 92 tokens ( 11.49 ms per token, 87.04 tokens per second) 3.02.368.258 I slot print_timing: id 0 | task 13455 | total time = 1192.68 ms / 444 tokens 3.02.368.259 I slot print_timing: id 0 | task 13455 | graphs reused = 12787 3.02.368.259 I slot print_timing: id 0 | task 13455 | graph reallocs = 0 / 0 (same size) / (changed size) 3.02.368.288 I slot release: id 0 | task 13455 | stop processing: n_tokens = 475, truncated = 0 3.02.409.708 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 475, t_last = 182269737 3.02.409.759 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.142 MiB) 3.02.455.530 I slot launch_slot_: id 0 | task 13550 | processing task, is_child = 0 3.04.561.266 I slot print_timing: id 0 | task 13550 | prompt eval time = 196.02 ms / 550 tokens ( 0.36 ms per token, 2805.84 tokens per second) 3.04.561.272 I slot print_timing: id 0 | task 13550 | eval time = 1909.69 ms / 170 tokens ( 11.30 ms per token, 88.50 tokens per second) 3.04.561.273 I slot print_timing: id 0 | task 13550 | total time = 2105.71 ms / 720 tokens 3.04.561.274 I slot print_timing: id 0 | task 13550 | graphs reused = 12955 3.04.561.275 I slot print_timing: id 0 | task 13550 | graph reallocs = 0 / 0 (same size) / (changed size) 3.04.561.313 I slot release: id 0 | task 13550 | stop processing: n_tokens = 751, truncated = 0 3.04.566.961 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 751, t_last = 184462763 3.04.567.021 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.268 MiB) 3.04.627.923 I slot launch_slot_: id 0 | task 13724 | processing task, is_child = 0 3.07.701.048 I slot print_timing: id 0 | task 13724 | prompt eval time = 229.56 ms / 772 tokens ( 0.30 ms per token, 3363.00 tokens per second) 3.07.701.054 I slot print_timing: id 0 | task 13724 | eval time = 2843.55 ms / 250 tokens ( 11.42 ms per token, 87.57 tokens per second) 3.07.701.055 I slot print_timing: id 0 | task 13724 | total time = 3073.10 ms / 1022 tokens 3.07.701.056 I slot print_timing: id 0 | task 13724 | graphs reused = 13202 3.07.701.057 I slot print_timing: id 0 | task 13724 | graph reallocs = 0 / 0 (same size) / (changed size) 3.07.701.097 I slot release: id 0 | task 13724 | stop processing: n_tokens = 1053, truncated = 0 3.07.736.905 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1053, t_last = 187602547 3.07.736.981 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.862 MiB) 3.07.793.998 I slot launch_slot_: id 0 | task 13978 | processing task, is_child = 0 3.10.035.637 I slot print_timing: id 0 | task 13978 | prompt eval time = 222.96 ms / 683 tokens ( 0.33 ms per token, 3063.33 tokens per second) 3.10.035.642 I slot print_timing: id 0 | task 13978 | eval time = 2018.66 ms / 181 tokens ( 11.21 ms per token, 89.17 tokens per second) 3.10.035.643 I slot print_timing: id 0 | task 13978 | total time = 2241.62 ms / 864 tokens 3.10.035.644 I slot print_timing: id 0 | task 13978 | graphs reused = 13380 3.10.035.644 I slot print_timing: id 0 | task 13978 | graph reallocs = 0 / 0 (same size) / (changed size) 3.10.035.683 I slot release: id 0 | task 13978 | stop processing: n_tokens = 895, truncated = 0 3.10.064.582 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 895, t_last = 189937133 3.10.064.652 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.891 MiB) 3.10.122.865 I slot launch_slot_: id 0 | task 14163 | processing task, is_child = 0 3.13.051.285 I slot print_timing: id 0 | task 14163 | prompt eval time = 203.87 ms / 579 tokens ( 0.35 ms per token, 2840.09 tokens per second) 3.13.051.291 I slot print_timing: id 0 | task 14163 | eval time = 2724.53 ms / 242 tokens ( 11.31 ms per token, 88.46 tokens per second) 3.13.051.292 I slot print_timing: id 0 | task 14163 | total time = 2928.40 ms / 821 tokens 3.13.051.293 I slot print_timing: id 0 | task 14163 | graphs reused = 13619 3.13.051.294 I slot print_timing: id 0 | task 14163 | graph reallocs = 0 / 0 (same size) / (changed size) 3.13.051.328 I slot release: id 0 | task 14163 | stop processing: n_tokens = 852, truncated = 0 3.13.086.601 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 852, t_last = 192952777 3.13.086.666 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 324.427 MiB) 3.13.092.046 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.143 MiB) 3.13.153.926 I slot launch_slot_: id 0 | task 14409 | processing task, is_child = 0 3.14.925.356 I slot print_timing: id 0 | task 14409 | prompt eval time = 177.84 ms / 500 tokens ( 0.36 ms per token, 2811.56 tokens per second) 3.14.925.361 I slot print_timing: id 0 | task 14409 | eval time = 1593.57 ms / 140 tokens ( 11.46 ms per token, 87.23 tokens per second) 3.14.925.362 I slot print_timing: id 0 | task 14409 | total time = 1771.41 ms / 640 tokens 3.14.925.363 I slot print_timing: id 0 | task 14409 | graphs reused = 13757 3.14.925.363 I slot print_timing: id 0 | task 14409 | graph reallocs = 0 / 0 (same size) / (changed size) 3.14.925.395 I slot release: id 0 | task 14409 | stop processing: n_tokens = 671, truncated = 0 3.14.947.278 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 671, t_last = 194826845 3.14.947.337 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.922 MiB) 3.14.998.758 I slot launch_slot_: id 0 | task 14552 | processing task, is_child = 0 3.17.791.171 I slot print_timing: id 0 | task 14552 | prompt eval time = 242.17 ms / 776 tokens ( 0.31 ms per token, 3204.33 tokens per second) 3.17.791.176 I slot print_timing: id 0 | task 14552 | eval time = 2550.22 ms / 228 tokens ( 11.23 ms per token, 89.01 tokens per second) 3.17.791.177 I slot print_timing: id 0 | task 14552 | total time = 2792.39 ms / 1004 tokens 3.17.791.178 I slot print_timing: id 0 | task 14552 | graphs reused = 13982 3.17.791.179 I slot print_timing: id 0 | task 14552 | graph reallocs = 0 / 0 (same size) / (changed size) 3.17.791.218 I slot release: id 0 | task 14552 | stop processing: n_tokens = 1035, truncated = 0 3.17.818.655 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1035, t_last = 197692667 3.17.818.731 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.800 MiB) 3.17.886.194 I slot launch_slot_: id 0 | task 14784 | processing task, is_child = 0 3.20.667.176 I slot print_timing: id 0 | task 14784 | prompt eval time = 178.97 ms / 504 tokens ( 0.36 ms per token, 2816.10 tokens per second) 3.20.667.181 I slot print_timing: id 0 | task 14784 | eval time = 2601.99 ms / 230 tokens ( 11.36 ms per token, 88.01 tokens per second) 3.20.667.183 I slot print_timing: id 0 | task 14784 | total time = 2780.96 ms / 734 tokens 3.20.667.183 I slot print_timing: id 0 | task 14784 | graphs reused = 14210 3.20.667.184 I slot print_timing: id 0 | task 14784 | graph reallocs = 0 / 0 (same size) / (changed size) 3.20.667.217 I slot release: id 0 | task 14784 | stop processing: n_tokens = 765, truncated = 0 3.20.707.003 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 765, t_last = 200568666 3.20.707.073 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.422 MiB) 3.20.758.570 I slot launch_slot_: id 0 | task 15017 | processing task, is_child = 0 3.23.646.382 I slot print_timing: id 0 | task 15017 | prompt eval time = 207.96 ms / 633 tokens ( 0.33 ms per token, 3043.81 tokens per second) 3.23.646.389 I slot print_timing: id 0 | task 15017 | eval time = 2679.83 ms / 235 tokens ( 11.45 ms per token, 87.32 tokens per second) 3.23.646.390 I slot print_timing: id 0 | task 15017 | total time = 2887.79 ms / 868 tokens 3.23.646.391 I slot print_timing: id 0 | task 15017 | graphs reused = 14442 3.23.646.392 I slot print_timing: id 0 | task 15017 | graph reallocs = 0 / 0 (same size) / (changed size) 3.23.646.432 I slot release: id 0 | task 15017 | stop processing: n_tokens = 899, truncated = 0 3.23.651.308 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 899, t_last = 203547882 3.23.651.375 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.928 MiB) 3.23.711.704 I slot launch_slot_: id 0 | task 15256 | processing task, is_child = 0 3.25.689.186 I slot print_timing: id 0 | task 15256 | prompt eval time = 156.83 ms / 395 tokens ( 0.40 ms per token, 2518.72 tokens per second) 3.25.689.191 I slot print_timing: id 0 | task 15256 | eval time = 1820.64 ms / 164 tokens ( 11.17 ms per token, 89.53 tokens per second) 3.25.689.193 I slot print_timing: id 0 | task 15256 | total time = 1977.46 ms / 559 tokens 3.25.689.194 I slot print_timing: id 0 | task 15256 | graphs reused = 14603 3.25.689.194 I slot print_timing: id 0 | task 15256 | graph reallocs = 0 / 0 (same size) / (changed size) 3.25.689.224 I slot release: id 0 | task 15256 | stop processing: n_tokens = 590, truncated = 0 3.25.705.559 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 590, t_last = 205590673 3.25.705.614 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.861 MiB) 3.25.751.487 I slot launch_slot_: id 0 | task 15423 | processing task, is_child = 0 3.28.562.138 I slot print_timing: id 0 | task 15423 | prompt eval time = 202.53 ms / 584 tokens ( 0.35 ms per token, 2883.48 tokens per second) 3.28.562.144 I slot print_timing: id 0 | task 15423 | eval time = 2608.10 ms / 229 tokens ( 11.44 ms per token, 87.42 tokens per second) 3.28.562.145 I slot print_timing: id 0 | task 15423 | total time = 2810.63 ms / 813 tokens 3.28.562.145 I slot print_timing: id 0 | task 15423 | graphs reused = 14829 3.28.562.147 I slot print_timing: id 0 | task 15423 | graph reallocs = 0 / 0 (same size) / (changed size) 3.28.562.182 I slot release: id 0 | task 15423 | stop processing: n_tokens = 844, truncated = 0 3.28.578.152 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 844, t_last = 208463632 3.28.578.215 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 322.269 MiB) 3.28.635.791 I slot launch_slot_: id 0 | task 15656 | processing task, is_child = 0 3.31.806.580 I slot print_timing: id 0 | task 15656 | prompt eval time = 227.38 ms / 695 tokens ( 0.33 ms per token, 3056.60 tokens per second) 3.31.806.585 I slot print_timing: id 0 | task 15656 | eval time = 2943.39 ms / 260 tokens ( 11.36 ms per token, 87.99 tokens per second) 3.31.806.586 I slot print_timing: id 0 | task 15656 | total time = 3170.77 ms / 955 tokens 3.31.806.587 I slot print_timing: id 0 | task 15656 | graphs reused = 15086 3.31.806.588 I slot print_timing: id 0 | task 15656 | graph reallocs = 0 / 0 (same size) / (changed size) 3.31.806.627 I slot release: id 0 | task 15656 | stop processing: n_tokens = 986, truncated = 0 3.31.812.476 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 986, t_last = 211708076 3.31.812.536 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 322.894 MiB) 3.31.874.415 I slot launch_slot_: id 0 | task 15920 | processing task, is_child = 0 3.34.476.943 I slot print_timing: id 0 | task 15920 | prompt eval time = 240.26 ms / 769 tokens ( 0.31 ms per token, 3200.75 tokens per second) 3.34.476.949 I slot print_timing: id 0 | task 15920 | eval time = 2362.25 ms / 212 tokens ( 11.20 ms per token, 89.32 tokens per second) 3.34.476.950 I slot print_timing: id 0 | task 15920 | total time = 2602.51 ms / 981 tokens 3.34.476.952 I slot print_timing: id 0 | task 15920 | graphs reused = 15296 3.34.476.953 I slot print_timing: id 0 | task 15920 | graph reallocs = 0 / 0 (same size) / (changed size) 3.34.476.996 I slot release: id 0 | task 15920 | stop processing: n_tokens = 1012, truncated = 0 3.34.500.826 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1012, t_last = 214378445 3.34.500.900 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.926 MiB) 3.34.506.307 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.454 MiB) 3.34.576.791 I slot launch_slot_: id 0 | task 16136 | processing task, is_child = 0 3.36.702.116 I slot print_timing: id 0 | task 16136 | prompt eval time = 196.55 ms / 576 tokens ( 0.34 ms per token, 2930.58 tokens per second) 3.36.702.122 I slot print_timing: id 0 | task 16136 | eval time = 1928.76 ms / 169 tokens ( 11.48 ms per token, 87.10 tokens per second) 3.36.702.123 I slot print_timing: id 0 | task 16136 | total time = 2125.31 ms / 745 tokens 3.36.702.124 I slot print_timing: id 0 | task 16136 | graphs reused = 15462 3.36.702.125 I slot print_timing: id 0 | task 16136 | graph reallocs = 0 / 0 (same size) / (changed size) 3.36.702.160 I slot release: id 0 | task 16136 | stop processing: n_tokens = 776, truncated = 0 3.36.716.900 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 776, t_last = 216603610 3.36.716.951 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.140 MiB) 3.36.778.143 I slot launch_slot_: id 0 | task 16309 | processing task, is_child = 0 3.40.000.047 I slot print_timing: id 0 | task 16309 | n_gen = 266, tg = 88.01 t/s, tg_3s = 88.34 t/s 3.40.458.609 I slot print_timing: id 0 | task 16309 | prompt eval time = 210.90 ms / 655 tokens ( 0.32 ms per token, 3105.71 tokens per second) 3.40.458.615 I slot print_timing: id 0 | task 16309 | eval time = 3469.54 ms / 306 tokens ( 11.38 ms per token, 87.91 tokens per second) 3.40.458.616 I slot print_timing: id 0 | task 16309 | total time = 3680.45 ms / 961 tokens 3.40.458.617 I slot print_timing: id 0 | task 16309 | graphs reused = 15765 3.40.458.617 I slot print_timing: id 0 | task 16309 | graph reallocs = 0 / 0 (same size) / (changed size) 3.40.458.655 I slot release: id 0 | task 16309 | stop processing: n_tokens = 992, truncated = 0 3.40.481.124 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 992, t_last = 220360104 3.40.481.198 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.611 MiB) 3.40.549.511 I slot launch_slot_: id 0 | task 16619 | processing task, is_child = 0 3.42.352.880 I slot print_timing: id 0 | task 16619 | prompt eval time = 204.32 ms / 621 tokens ( 0.33 ms per token, 3039.35 tokens per second) 3.42.352.886 I slot print_timing: id 0 | task 16619 | eval time = 1599.03 ms / 144 tokens ( 11.18 ms per token, 89.43 tokens per second) 3.42.352.887 I slot print_timing: id 0 | task 16619 | total time = 1803.35 ms / 765 tokens 3.42.352.888 I slot print_timing: id 0 | task 16619 | graphs reused = 15906 3.42.352.889 I slot print_timing: id 0 | task 16619 | graph reallocs = 0 / 0 (same size) / (changed size) 3.42.352.926 I slot release: id 0 | task 16619 | stop processing: n_tokens = 796, truncated = 0 3.42.369.170 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 796, t_last = 222254376 3.42.369.232 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.389 MiB) 3.42.424.549 I slot launch_slot_: id 0 | task 16767 | processing task, is_child = 0 3.44.698.694 I slot print_timing: id 0 | task 16767 | prompt eval time = 238.88 ms / 767 tokens ( 0.31 ms per token, 3210.78 tokens per second) 3.44.698.699 I slot print_timing: id 0 | task 16767 | eval time = 2035.24 ms / 179 tokens ( 11.43 ms per token, 87.46 tokens per second) 3.44.698.700 I slot print_timing: id 0 | task 16767 | total time = 2274.12 ms / 946 tokens 3.44.698.701 I slot print_timing: id 0 | task 16767 | graphs reused = 16083 3.44.698.701 I slot print_timing: id 0 | task 16767 | graph reallocs = 0 / 0 (same size) / (changed size) 3.44.698.744 I slot release: id 0 | task 16767 | stop processing: n_tokens = 977, truncated = 0 3.44.722.310 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 977, t_last = 224600194 3.44.722.371 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.484 MiB) 3.44.786.087 I slot launch_slot_: id 0 | task 16950 | processing task, is_child = 0 3.47.522.425 I slot print_timing: id 0 | task 16950 | prompt eval time = 254.70 ms / 864 tokens ( 0.29 ms per token, 3392.27 tokens per second) 3.47.522.431 I slot print_timing: id 0 | task 16950 | eval time = 2481.62 ms / 220 tokens ( 11.33 ms per token, 88.25 tokens per second) 3.47.522.432 I slot print_timing: id 0 | task 16950 | total time = 2736.32 ms / 1084 tokens 3.47.522.432 I slot print_timing: id 0 | task 16950 | graphs reused = 16300 3.47.522.433 I slot print_timing: id 0 | task 16950 | graph reallocs = 0 / 0 (same size) / (changed size) 3.47.522.478 I slot release: id 0 | task 16950 | stop processing: n_tokens = 1115, truncated = 0 3.47.543.953 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1115, t_last = 227423927 3.47.544.034 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.642 MiB) 3.47.549.671 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.892 MiB) 3.47.625.457 I slot launch_slot_: id 0 | task 17174 | processing task, is_child = 0 3.49.619.705 I slot print_timing: id 0 | task 17174 | prompt eval time = 223.57 ms / 646 tokens ( 0.35 ms per token, 2889.42 tokens per second) 3.49.619.710 I slot print_timing: id 0 | task 17174 | eval time = 1770.65 ms / 158 tokens ( 11.28 ms per token, 88.67 tokens per second) 3.49.619.711 I slot print_timing: id 0 | task 17174 | total time = 1994.23 ms / 804 tokens 3.49.619.712 I slot print_timing: id 0 | task 17174 | graphs reused = 16455 3.49.619.713 I slot print_timing: id 0 | task 17174 | graph reallocs = 0 / 0 (same size) / (changed size) 3.49.619.749 I slot release: id 0 | task 17174 | stop processing: n_tokens = 835, truncated = 0 3.49.645.203 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 835, t_last = 229521199 3.49.645.265 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.799 MiB) 3.49.702.108 I slot launch_slot_: id 0 | task 17336 | processing task, is_child = 0 3.52.692.892 I slot print_timing: id 0 | task 17336 | prompt eval time = 221.07 ms / 720 tokens ( 0.31 ms per token, 3256.95 tokens per second) 3.52.692.897 I slot print_timing: id 0 | task 17336 | eval time = 2769.70 ms / 240 tokens ( 11.59 ms per token, 86.29 tokens per second) 3.52.692.898 I slot print_timing: id 0 | task 17336 | total time = 2990.76 ms / 960 tokens 3.52.692.899 I slot print_timing: id 0 | task 17336 | graphs reused = 16692 3.52.692.900 I slot print_timing: id 0 | task 17336 | graph reallocs = 0 / 0 (same size) / (changed size) 3.52.692.940 I slot release: id 0 | task 17336 | stop processing: n_tokens = 991, truncated = 0 3.52.734.666 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 991, t_last = 232594390 3.52.734.738 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.985 MiB) 3.52.797.113 I slot launch_slot_: id 0 | task 17580 | processing task, is_child = 0 3.55.574.796 I slot print_timing: id 0 | task 17580 | prompt eval time = 179.28 ms / 509 tokens ( 0.35 ms per token, 2839.18 tokens per second) 3.55.574.801 I slot print_timing: id 0 | task 17580 | eval time = 2598.39 ms / 231 tokens ( 11.30 ms per token, 88.52 tokens per second) 3.55.574.802 I slot print_timing: id 0 | task 17580 | total time = 2777.66 ms / 740 tokens 3.55.574.803 I slot print_timing: id 0 | task 17580 | graphs reused = 16920 3.55.574.804 I slot print_timing: id 0 | task 17580 | graph reallocs = 0 / 0 (same size) / (changed size) 3.55.574.838 I slot release: id 0 | task 17580 | stop processing: n_tokens = 771, truncated = 0 3.55.580.185 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 771, t_last = 235476288 3.55.580.238 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.736 MiB) 3.55.632.950 I slot launch_slot_: id 0 | task 17814 | processing task, is_child = 0 3.58.814.631 I slot print_timing: id 0 | task 17814 | prompt eval time = 208.13 ms / 581 tokens ( 0.36 ms per token, 2791.54 tokens per second) 3.58.814.637 I slot print_timing: id 0 | task 17814 | eval time = 2973.53 ms / 265 tokens ( 11.26 ms per token, 88.78 tokens per second) 3.58.814.638 I slot print_timing: id 0 | task 17814 | total time = 3181.66 ms / 846 tokens 3.58.814.639 I slot print_timing: id 0 | task 17814 | graphs reused = 17182 3.58.814.640 I slot print_timing: id 0 | task 17814 | graph reallocs = 0 / 0 (same size) / (changed size) 3.58.814.679 I slot release: id 0 | task 17814 | stop processing: n_tokens = 877, truncated = 0 3.58.832.138 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 877, t_last = 238716128 3.58.832.207 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.860 MiB) 3.58.899.275 I slot launch_slot_: id 0 | task 18083 | processing task, is_child = 0 4.01.873.564 I slot print_timing: id 0 | task 18083 | prompt eval time = 276.16 ms / 925 tokens ( 0.30 ms per token, 3349.51 tokens per second) 4.01.873.570 I slot print_timing: id 0 | task 18083 | eval time = 2698.11 ms / 239 tokens ( 11.34 ms per token, 88.21 tokens per second) 4.01.873.571 I slot print_timing: id 0 | task 18083 | total time = 2974.27 ms / 1164 tokens 4.01.873.571 I slot print_timing: id 0 | task 18083 | graphs reused = 17418 4.01.873.572 I slot print_timing: id 0 | task 18083 | graph reallocs = 0 / 0 (same size) / (changed size) 4.01.873.617 I slot release: id 0 | task 18083 | stop processing: n_tokens = 1195, truncated = 0 4.01.908.305 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1195, t_last = 241775067 4.01.908.385 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.358 MiB) 4.01.963.831 I slot launch_slot_: id 0 | task 18326 | processing task, is_child = 0 4.05.224.049 I slot print_timing: id 0 | task 18326 | prompt eval time = 253.12 ms / 885 tokens ( 0.29 ms per token, 3496.39 tokens per second) 4.05.224.054 I slot print_timing: id 0 | task 18326 | eval time = 3007.08 ms / 264 tokens ( 11.43 ms per token, 87.46 tokens per second) 4.05.224.055 I slot print_timing: id 0 | task 18326 | total time = 3260.20 ms / 1149 tokens 4.05.224.056 I slot print_timing: id 0 | task 18326 | graphs reused = 17679 4.05.224.057 I slot print_timing: id 0 | task 18326 | graph reallocs = 0 / 0 (same size) / (changed size) 4.05.224.101 I slot release: id 0 | task 18326 | stop processing: n_tokens = 1180, truncated = 0 4.05.268.889 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1180, t_last = 245125551 4.05.268.972 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 375.240 MiB) 4.05.330.809 I slot launch_slot_: id 0 | task 18594 | processing task, is_child = 0 4.07.653.292 I slot print_timing: id 0 | task 18594 | prompt eval time = 148.92 ms / 392 tokens ( 0.38 ms per token, 2632.27 tokens per second) 4.07.653.297 I slot print_timing: id 0 | task 18594 | eval time = 2173.54 ms / 193 tokens ( 11.32 ms per token, 88.33 tokens per second) 4.07.653.298 I slot print_timing: id 0 | task 18594 | total time = 2322.46 ms / 585 tokens 4.07.653.299 I slot print_timing: id 0 | task 18594 | graphs reused = 17869 4.07.653.300 I slot print_timing: id 0 | task 18594 | graph reallocs = 0 / 0 (same size) / (changed size) 4.07.653.329 I slot release: id 0 | task 18594 | stop processing: n_tokens = 616, truncated = 0 4.07.657.850 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 616, t_last = 247554779 4.07.657.901 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 384.685 MiB) 4.07.710.570 I slot launch_slot_: id 0 | task 18790 | processing task, is_child = 0 4.10.111.884 I slot print_timing: id 0 | task 18790 | prompt eval time = 144.83 ms / 331 tokens ( 0.44 ms per token, 2285.37 tokens per second) 4.10.111.889 I slot print_timing: id 0 | task 18790 | eval time = 2256.46 ms / 201 tokens ( 11.28 ms per token, 88.63 tokens per second) 4.10.111.890 I slot print_timing: id 0 | task 18790 | total time = 2401.29 ms / 532 tokens 4.10.111.891 I slot print_timing: id 0 | task 18790 | graphs reused = 18067 4.10.111.891 I slot print_timing: id 0 | task 18790 | graph reallocs = 0 / 0 (same size) / (changed size) 4.10.111.919 I slot release: id 0 | task 18790 | stop processing: n_tokens = 563, truncated = 0 4.10.155.562 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 563, t_last = 250013369 4.10.155.613 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.743 MiB) 4.10.207.420 I slot launch_slot_: id 0 | task 18994 | processing task, is_child = 0 4.11.163.233 I slot print_timing: id 0 | task 18994 | prompt eval time = 142.29 ms / 357 tokens ( 0.40 ms per token, 2508.98 tokens per second) 4.11.163.239 I slot print_timing: id 0 | task 18994 | eval time = 813.51 ms / 72 tokens ( 11.46 ms per token, 87.28 tokens per second) 4.11.163.240 I slot print_timing: id 0 | task 18994 | total time = 955.80 ms / 429 tokens 4.11.163.241 I slot print_timing: id 0 | task 18994 | graphs reused = 18137 4.11.163.242 I slot print_timing: id 0 | task 18994 | graph reallocs = 0 / 0 (same size) / (changed size) 4.11.163.271 I slot release: id 0 | task 18994 | stop processing: n_tokens = 460, truncated = 0 4.11.188.360 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 460, t_last = 251064720 4.11.188.408 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.399 MiB) 4.11.244.636 I slot launch_slot_: id 0 | task 19069 | processing task, is_child = 0 4.12.986.656 I slot print_timing: id 0 | task 19069 | prompt eval time = 144.16 ms / 315 tokens ( 0.46 ms per token, 2185.03 tokens per second) 4.12.986.662 I slot print_timing: id 0 | task 19069 | eval time = 1597.84 ms / 140 tokens ( 11.50 ms per token, 86.99 tokens per second) 4.12.986.663 I slot print_timing: id 0 | task 19069 | total time = 1742.00 ms / 455 tokens 4.12.986.663 I slot print_timing: id 0 | task 19069 | graphs reused = 18275 4.12.986.664 I slot print_timing: id 0 | task 19069 | graph reallocs = 0 / 0 (same size) / (changed size) 4.12.986.689 I slot release: id 0 | task 19069 | stop processing: n_tokens = 486, truncated = 0 4.12.991.438 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 486, t_last = 252888139 4.12.991.486 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 322.488 MiB) 4.13.042.224 I slot launch_slot_: id 0 | task 19212 | processing task, is_child = 0 4.14.194.165 I slot print_timing: id 0 | task 19212 | prompt eval time = 145.14 ms / 378 tokens ( 0.38 ms per token, 2604.36 tokens per second) 4.14.194.171 I slot print_timing: id 0 | task 19212 | eval time = 1006.78 ms / 92 tokens ( 11.06 ms per token, 90.39 tokens per second) 4.14.194.172 I slot print_timing: id 0 | task 19212 | total time = 1151.92 ms / 470 tokens 4.14.194.173 I slot print_timing: id 0 | task 19212 | graphs reused = 18365 4.14.194.174 I slot print_timing: id 0 | task 19212 | graph reallocs = 0 / 0 (same size) / (changed size) 4.14.194.202 I slot release: id 0 | task 19212 | stop processing: n_tokens = 501, truncated = 0 4.14.227.716 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 501, t_last = 254095652 4.14.227.765 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 384.122 MiB) 4.14.287.813 I slot launch_slot_: id 0 | task 19307 | processing task, is_child = 0 4.15.131.209 I slot print_timing: id 0 | task 19307 | prompt eval time = 133.69 ms / 295 tokens ( 0.45 ms per token, 2206.63 tokens per second) 4.15.131.215 I slot print_timing: id 0 | task 19307 | eval time = 709.69 ms / 63 tokens ( 11.45 ms per token, 87.36 tokens per second) 4.15.131.216 I slot print_timing: id 0 | task 19307 | total time = 843.38 ms / 358 tokens 4.15.131.217 I slot print_timing: id 0 | task 19307 | graphs reused = 18426 4.15.131.218 I slot print_timing: id 0 | task 19307 | graph reallocs = 0 / 0 (same size) / (changed size) 4.15.131.246 I slot release: id 0 | task 19307 | stop processing: n_tokens = 389, truncated = 0 4.15.164.584 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 389, t_last = 255032695 4.15.164.629 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.427 MiB) 4.15.213.838 I slot launch_slot_: id 0 | task 19373 | processing task, is_child = 0 4.18.363.341 I slot print_timing: id 0 | task 19373 | n_gen = 267, tg = 88.48 t/s, tg_3s = 88.82 t/s 4.19.246.849 I slot print_timing: id 0 | task 19373 | prompt eval time = 143.25 ms / 337 tokens ( 0.43 ms per token, 2352.46 tokens per second) 4.19.246.855 I slot print_timing: id 0 | task 19373 | eval time = 3889.74 ms / 345 tokens ( 11.31 ms per token, 88.44 tokens per second) 4.19.246.856 I slot print_timing: id 0 | task 19373 | total time = 4032.99 ms / 682 tokens 4.19.246.856 I slot print_timing: id 0 | task 19373 | graphs reused = 18768 4.19.246.857 I slot print_timing: id 0 | task 19373 | graph reallocs = 0 / 0 (same size) / (changed size) 4.19.246.884 I slot release: id 0 | task 19373 | stop processing: n_tokens = 713, truncated = 0 4.19.251.556 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 713, t_last = 259148334 4.19.251.604 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.869 MiB) 4.19.306.878 I slot launch_slot_: id 0 | task 19721 | processing task, is_child = 0 4.21.556.630 I slot print_timing: id 0 | task 19721 | prompt eval time = 144.25 ms / 325 tokens ( 0.44 ms per token, 2253.11 tokens per second) 4.21.556.635 I slot print_timing: id 0 | task 19721 | eval time = 2105.49 ms / 185 tokens ( 11.44 ms per token, 87.39 tokens per second) 4.21.556.636 I slot print_timing: id 0 | task 19721 | total time = 2249.73 ms / 510 tokens 4.21.556.637 I slot print_timing: id 0 | task 19721 | graphs reused = 18950 4.21.556.638 I slot print_timing: id 0 | task 19721 | graph reallocs = 0 / 0 (same size) / (changed size) 4.21.556.666 I slot release: id 0 | task 19721 | stop processing: n_tokens = 541, truncated = 0 4.21.597.371 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.108 (> 0.100 thold), f_keep = 0.059 4.21.637.337 I slot launch_slot_: id 0 | task 19909 | processing task, is_child = 0 4.22.662.074 I slot print_timing: id 0 | task 19909 | prompt eval time = 123.35 ms / 264 tokens ( 0.47 ms per token, 2140.20 tokens per second) 4.22.662.080 I slot print_timing: id 0 | task 19909 | eval time = 901.36 ms / 82 tokens ( 11.13 ms per token, 89.86 tokens per second) 4.22.662.081 I slot print_timing: id 0 | task 19909 | total time = 1024.71 ms / 346 tokens 4.22.662.082 I slot print_timing: id 0 | task 19909 | graphs reused = 19030 4.22.662.082 I slot print_timing: id 0 | task 19909 | graph reallocs = 0 / 0 (same size) / (changed size) 4.22.662.107 I slot release: id 0 | task 19909 | stop processing: n_tokens = 377, truncated = 0 4.22.679.826 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 377, t_last = 262563557 4.22.679.871 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.955 MiB) 4.22.724.153 I slot launch_slot_: id 0 | task 19994 | processing task, is_child = 0 4.24.520.034 I slot print_timing: id 0 | task 19994 | prompt eval time = 144.34 ms / 331 tokens ( 0.44 ms per token, 2293.28 tokens per second) 4.24.520.040 I slot print_timing: id 0 | task 19994 | eval time = 1651.53 ms / 145 tokens ( 11.47 ms per token, 87.19 tokens per second) 4.24.520.041 I slot print_timing: id 0 | task 19994 | total time = 1795.86 ms / 476 tokens 4.24.520.042 I slot print_timing: id 0 | task 19994 | graphs reused = 19173 4.24.520.043 I slot print_timing: id 0 | task 19994 | graph reallocs = 0 / 0 (same size) / (changed size) 4.24.520.070 I slot release: id 0 | task 19994 | stop processing: n_tokens = 507, truncated = 0 4.24.546.055 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 507, t_last = 264421520 4.24.546.105 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.149 MiB) 4.24.597.523 I slot launch_slot_: id 0 | task 20142 | processing task, is_child = 0 4.26.831.396 I slot print_timing: id 0 | task 20142 | prompt eval time = 144.15 ms / 333 tokens ( 0.43 ms per token, 2310.16 tokens per second) 4.26.831.401 I slot print_timing: id 0 | task 20142 | eval time = 2089.71 ms / 187 tokens ( 11.23 ms per token, 89.01 tokens per second) 4.26.831.402 I slot print_timing: id 0 | task 20142 | total time = 2233.85 ms / 520 tokens 4.26.831.403 I slot print_timing: id 0 | task 20142 | graphs reused = 19357 4.26.831.404 I slot print_timing: id 0 | task 20142 | graph reallocs = 0 / 0 (same size) / (changed size) 4.26.831.430 I slot release: id 0 | task 20142 | stop processing: n_tokens = 551, truncated = 0 4.26.856.248 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 551, t_last = 266732879 4.26.856.298 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.589 MiB) 4.26.911.309 I slot launch_slot_: id 0 | task 20332 | processing task, is_child = 0 4.28.391.296 I slot print_timing: id 0 | task 20332 | prompt eval time = 147.85 ms / 346 tokens ( 0.43 ms per token, 2340.19 tokens per second) 4.28.391.302 I slot print_timing: id 0 | task 20332 | eval time = 1332.12 ms / 117 tokens ( 11.48 ms per token, 87.08 tokens per second) 4.28.391.303 I slot print_timing: id 0 | task 20332 | total time = 1479.97 ms / 463 tokens 4.28.391.304 I slot print_timing: id 0 | task 20332 | graphs reused = 19472 4.28.391.304 I slot print_timing: id 0 | task 20332 | graph reallocs = 0 / 0 (same size) / (changed size) 4.28.391.332 I slot release: id 0 | task 20332 | stop processing: n_tokens = 494, truncated = 0 4.28.424.804 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 494, t_last = 268292782 4.28.424.852 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 383.402 MiB) 4.28.485.618 I slot launch_slot_: id 0 | task 20452 | processing task, is_child = 0 4.29.375.944 I slot print_timing: id 0 | task 20452 | prompt eval time = 143.52 ms / 325 tokens ( 0.44 ms per token, 2264.54 tokens per second) 4.29.375.949 I slot print_timing: id 0 | task 20452 | eval time = 746.79 ms / 66 tokens ( 11.49 ms per token, 87.04 tokens per second) 4.29.375.950 I slot print_timing: id 0 | task 20452 | total time = 890.31 ms / 391 tokens 4.29.375.951 I slot print_timing: id 0 | task 20452 | graphs reused = 19536 4.29.375.952 I slot print_timing: id 0 | task 20452 | graph reallocs = 0 / 0 (same size) / (changed size) 4.29.375.981 I slot release: id 0 | task 20452 | stop processing: n_tokens = 422, truncated = 0 4.29.391.022 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 422, t_last = 269277430 4.29.391.067 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 376.022 MiB) 4.29.446.430 I slot launch_slot_: id 0 | task 20521 | processing task, is_child = 0 4.31.880.496 I slot print_timing: id 0 | task 20521 | prompt eval time = 139.93 ms / 322 tokens ( 0.43 ms per token, 2301.12 tokens per second) 4.31.880.502 I slot print_timing: id 0 | task 20521 | eval time = 2294.11 ms / 205 tokens ( 11.25 ms per token, 88.92 tokens per second) 4.31.880.503 I slot print_timing: id 0 | task 20521 | total time = 2434.05 ms / 527 tokens 4.31.880.504 I slot print_timing: id 0 | task 20521 | graphs reused = 19738 4.31.880.505 I slot print_timing: id 0 | task 20521 | graph reallocs = 0 / 0 (same size) / (changed size) 4.31.880.534 I slot release: id 0 | task 20521 | stop processing: n_tokens = 558, truncated = 0 4.31.919.817 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 271781983 4.31.919.871 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.777 MiB) 4.31.981.030 I slot launch_slot_: id 0 | task 20729 | processing task, is_child = 0 4.35.132.055 I slot print_timing: id 0 | task 20729 | n_gen = 268, tg = 88.80 t/s, tg_3s = 89.13 t/s 4.36.747.431 I slot print_timing: id 0 | task 20729 | prompt eval time = 144.28 ms / 338 tokens ( 0.43 ms per token, 2342.73 tokens per second) 4.36.747.436 I slot print_timing: id 0 | task 20729 | eval time = 4622.10 ms / 409 tokens ( 11.33 ms per token, 88.27 tokens per second) 4.36.747.438 I slot print_timing: id 0 | task 20729 | total time = 4766.38 ms / 747 tokens 4.36.747.439 I slot print_timing: id 0 | task 20729 | graphs reused = 20143 4.36.747.439 I slot print_timing: id 0 | task 20729 | graph reallocs = 0 / 0 (same size) / (changed size) 4.36.747.468 I slot release: id 0 | task 20729 | stop processing: n_tokens = 778, truncated = 0 4.36.777.307 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 778, t_last = 276648918 4.36.818.127 I slot launch_slot_: id 0 | task 21141 | processing task, is_child = 0 4.38.847.201 I slot print_timing: id 0 | task 21141 | prompt eval time = 149.63 ms / 347 tokens ( 0.43 ms per token, 2319.12 tokens per second) 4.38.847.206 I slot print_timing: id 0 | task 21141 | eval time = 1879.43 ms / 169 tokens ( 11.19 ms per token, 89.39 tokens per second) 4.38.847.207 I slot print_timing: id 0 | task 21141 | total time = 2029.06 ms / 516 tokens 4.38.847.208 I slot print_timing: id 0 | task 21141 | graphs reused = 20309 4.38.847.209 I slot print_timing: id 0 | task 21141 | graph reallocs = 0 / 0 (same size) / (changed size) 4.38.847.236 I slot release: id 0 | task 21141 | stop processing: n_tokens = 547, truncated = 0 4.38.869.281 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 547, t_last = 278748686 4.38.869.332 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 376.647 MiB) 4.38.919.064 I slot launch_slot_: id 0 | task 21313 | processing task, is_child = 0 4.42.065.259 I slot print_timing: id 0 | task 21313 | n_gen = 264, tg = 87.62 t/s, tg_3s = 87.95 t/s 4.42.924.872 I slot print_timing: id 0 | task 21313 | prompt eval time = 144.46 ms / 331 tokens ( 0.44 ms per token, 2291.29 tokens per second) 4.42.924.877 I slot print_timing: id 0 | task 21313 | eval time = 3861.33 ms / 342 tokens ( 11.32 ms per token, 88.31 tokens per second) 4.42.924.879 I slot print_timing: id 0 | task 21313 | total time = 4005.79 ms / 673 tokens 4.42.924.879 I slot print_timing: id 0 | task 21313 | graphs reused = 20648 4.42.924.880 I slot print_timing: id 0 | task 21313 | graph reallocs = 0 / 0 (same size) / (changed size) 4.42.924.906 I slot release: id 0 | task 21313 | stop processing: n_tokens = 704, truncated = 0 4.42.958.235 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 704, t_last = 282826356 4.42.958.294 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.308 MiB) 4.43.016.240 I slot launch_slot_: id 0 | task 21658 | processing task, is_child = 0 4.46.170.012 I slot print_timing: id 0 | task 21658 | n_gen = 265, tg = 87.72 t/s, tg_3s = 88.05 t/s 4.46.809.564 I slot print_timing: id 0 | task 21658 | prompt eval time = 144.19 ms / 345 tokens ( 0.42 ms per token, 2392.63 tokens per second) 4.46.809.570 I slot print_timing: id 0 | task 21658 | eval time = 3649.11 ms / 323 tokens ( 11.33 ms per token, 88.24 tokens per second) 4.46.809.572 I slot print_timing: id 0 | task 21658 | total time = 3793.31 ms / 668 tokens 4.46.809.573 I slot print_timing: id 0 | task 21658 | graphs reused = 20968 4.46.809.573 I slot print_timing: id 0 | task 21658 | graph reallocs = 0 / 0 (same size) / (changed size) 4.46.809.601 I slot release: id 0 | task 21658 | stop processing: n_tokens = 699, truncated = 0 4.46.838.957 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 699, t_last = 286711051 4.46.839.014 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.624 MiB) 4.46.901.377 I slot launch_slot_: id 0 | task 21984 | processing task, is_child = 0 4.48.825.966 I slot print_timing: id 0 | task 21984 | prompt eval time = 140.19 ms / 320 tokens ( 0.44 ms per token, 2282.63 tokens per second) 4.48.825.971 I slot print_timing: id 0 | task 21984 | eval time = 1784.38 ms / 157 tokens ( 11.44 ms per token, 87.43 tokens per second) 4.48.825.972 I slot print_timing: id 0 | task 21984 | total time = 1924.57 ms / 477 tokens 4.48.825.973 I slot print_timing: id 0 | task 21984 | graphs reused = 21123 4.48.825.974 I slot print_timing: id 0 | task 21984 | graph reallocs = 0 / 0 (same size) / (changed size) 4.48.826.002 I slot release: id 0 | task 21984 | stop processing: n_tokens = 508, truncated = 0 4.48.862.161 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 508, t_last = 288727452 4.48.862.213 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 377.867 MiB) 4.48.920.198 I slot launch_slot_: id 0 | task 22144 | processing task, is_child = 0 4.49.750.141 I slot print_timing: id 0 | task 22144 | prompt eval time = 135.85 ms / 297 tokens ( 0.46 ms per token, 2186.25 tokens per second) 4.49.750.147 I slot print_timing: id 0 | task 22144 | eval time = 694.07 ms / 59 tokens ( 11.97 ms per token, 83.56 tokens per second) 4.49.750.148 I slot print_timing: id 0 | task 22144 | total time = 829.92 ms / 356 tokens 4.49.750.149 I slot print_timing: id 0 | task 22144 | graphs reused = 21180 4.49.750.150 I slot print_timing: id 0 | task 22144 | graph reallocs = 0 / 0 (same size) / (changed size) 4.49.750.174 I slot release: id 0 | task 22144 | stop processing: n_tokens = 387, truncated = 0 4.49.754.870 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 387, t_last = 289651624 4.49.754.913 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.746 MiB) 4.49.809.957 I slot launch_slot_: id 0 | task 22206 | processing task, is_child = 0 4.52.308.239 I slot print_timing: id 0 | task 22206 | prompt eval time = 140.49 ms / 343 tokens ( 0.41 ms per token, 2441.54 tokens per second) 4.52.308.244 I slot print_timing: id 0 | task 22206 | eval time = 2357.78 ms / 210 tokens ( 11.28 ms per token, 88.64 tokens per second) 4.52.308.245 I slot print_timing: id 0 | task 22206 | total time = 2498.26 ms / 553 tokens 4.52.308.247 I slot print_timing: id 0 | task 22206 | graphs reused = 21387 4.52.308.247 I slot print_timing: id 0 | task 22206 | graph reallocs = 0 / 0 (same size) / (changed size) 4.52.308.275 I slot release: id 0 | task 22206 | stop processing: n_tokens = 584, truncated = 0 4.52.337.412 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 584, t_last = 292209724 4.52.377.719 I slot launch_slot_: id 0 | task 22419 | processing task, is_child = 0 4.54.740.414 I slot print_timing: id 0 | task 22419 | prompt eval time = 151.52 ms / 371 tokens ( 0.41 ms per token, 2448.49 tokens per second) 4.54.740.420 I slot print_timing: id 0 | task 22419 | eval time = 2211.15 ms / 196 tokens ( 11.34 ms per token, 88.19 tokens per second) 4.54.740.421 I slot print_timing: id 0 | task 22419 | total time = 2362.68 ms / 567 tokens 4.54.740.422 I slot print_timing: id 0 | task 22419 | graphs reused = 21580 4.54.740.423 I slot print_timing: id 0 | task 22419 | graph reallocs = 0 / 0 (same size) / (changed size) 4.54.740.454 I slot release: id 0 | task 22419 | stop processing: n_tokens = 598, truncated = 0 4.54.770.310 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 598, t_last = 294641904 4.54.770.364 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.615 MiB) 4.54.823.538 I slot launch_slot_: id 0 | task 22618 | processing task, is_child = 0 4.57.300.996 I slot print_timing: id 0 | task 22618 | prompt eval time = 133.56 ms / 292 tokens ( 0.46 ms per token, 2186.37 tokens per second) 4.57.301.001 I slot print_timing: id 0 | task 22618 | eval time = 2343.89 ms / 206 tokens ( 11.43 ms per token, 87.46 tokens per second) 4.57.301.003 I slot print_timing: id 0 | task 22618 | total time = 2477.44 ms / 498 tokens 4.57.301.003 I slot print_timing: id 0 | task 22618 | graphs reused = 21783 4.57.301.004 I slot print_timing: id 0 | task 22618 | graph reallocs = 0 / 0 (same size) / (changed size) 4.57.301.029 I slot release: id 0 | task 22618 | stop processing: n_tokens = 529, truncated = 0 4.57.329.190 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 529, t_last = 297202478 4.57.329.243 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.181 MiB) 4.57.390.289 I slot launch_slot_: id 0 | task 22827 | processing task, is_child = 0 4.58.696.416 I slot print_timing: id 0 | task 22827 | prompt eval time = 136.24 ms / 301 tokens ( 0.45 ms per token, 2209.30 tokens per second) 4.58.696.422 I slot print_timing: id 0 | task 22827 | eval time = 1169.87 ms / 106 tokens ( 11.14 ms per token, 89.75 tokens per second) 4.58.696.423 I slot print_timing: id 0 | task 22827 | total time = 1306.11 ms / 407 tokens 4.58.696.424 I slot print_timing: id 0 | task 22827 | graphs reused = 21887 4.58.696.425 I slot print_timing: id 0 | task 22827 | graph reallocs = 0 / 0 (same size) / (changed size) 4.58.696.449 I slot release: id 0 | task 22827 | stop processing: n_tokens = 438, truncated = 0 4.58.701.023 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 438, t_last = 298597899 4.58.701.067 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 389.125 MiB) 4.58.748.055 I slot launch_slot_: id 0 | task 22936 | processing task, is_child = 0 5.01.186.218 I slot print_timing: id 0 | task 22936 | prompt eval time = 134.09 ms / 303 tokens ( 0.44 ms per token, 2259.76 tokens per second) 5.01.186.224 I slot print_timing: id 0 | task 22936 | eval time = 2304.06 ms / 203 tokens ( 11.41 ms per token, 87.67 tokens per second) 5.01.186.225 I slot print_timing: id 0 | task 22936 | total time = 2438.14 ms / 506 tokens 5.01.186.226 I slot print_timing: id 0 | task 22936 | graphs reused = 22087 5.01.186.226 I slot print_timing: id 0 | task 22936 | graph reallocs = 0 / 0 (same size) / (changed size) 5.01.186.252 I slot release: id 0 | task 22936 | stop processing: n_tokens = 537, truncated = 0 5.01.190.773 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 537, t_last = 301087701 5.01.190.823 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.656 MiB) 5.01.244.031 I slot launch_slot_: id 0 | task 23142 | processing task, is_child = 0 5.03.020.468 I slot print_timing: id 0 | task 23142 | prompt eval time = 143.85 ms / 321 tokens ( 0.45 ms per token, 2231.51 tokens per second) 5.03.020.473 I slot print_timing: id 0 | task 23142 | eval time = 1632.57 ms / 147 tokens ( 11.18 ms per token, 89.43 tokens per second) 5.03.020.474 I slot print_timing: id 0 | task 23142 | total time = 1776.42 ms / 468 tokens 5.03.020.475 I slot print_timing: id 0 | task 23142 | graphs reused = 22232 5.03.020.477 I slot print_timing: id 0 | task 23142 | graph reallocs = 0 / 0 (same size) / (changed size) 5.03.020.504 I slot release: id 0 | task 23142 | stop processing: n_tokens = 499, truncated = 0 5.03.056.394 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 499, t_last = 302921953 5.03.056.443 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.768 MiB) 5.03.105.376 I slot launch_slot_: id 0 | task 23292 | processing task, is_child = 0 5.04.102.941 I slot print_timing: id 0 | task 23292 | prompt eval time = 139.79 ms / 322 tokens ( 0.43 ms per token, 2303.42 tokens per second) 5.04.102.947 I slot print_timing: id 0 | task 23292 | eval time = 857.75 ms / 76 tokens ( 11.44 ms per token, 87.44 tokens per second) 5.04.102.948 I slot print_timing: id 0 | task 23292 | total time = 997.55 ms / 398 tokens 5.04.102.949 I slot print_timing: id 0 | task 23292 | graphs reused = 22306 5.04.102.949 I slot print_timing: id 0 | task 23292 | graph reallocs = 0 / 0 (same size) / (changed size) 5.04.102.978 I slot release: id 0 | task 23292 | stop processing: n_tokens = 429, truncated = 0 5.04.107.844 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 429, t_last = 304004427 5.04.107.892 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.110 MiB) 5.04.158.594 I slot launch_slot_: id 0 | task 23371 | processing task, is_child = 0 5.05.931.258 I slot print_timing: id 0 | task 23371 | prompt eval time = 143.85 ms / 323 tokens ( 0.45 ms per token, 2245.32 tokens per second) 5.05.931.263 I slot print_timing: id 0 | task 23371 | eval time = 1628.79 ms / 143 tokens ( 11.47 ms per token, 87.18 tokens per second) 5.05.931.264 I slot print_timing: id 0 | task 23371 | total time = 1772.64 ms / 466 tokens 5.05.931.266 I slot print_timing: id 0 | task 23371 | graphs reused = 22447 5.05.931.267 I slot print_timing: id 0 | task 23371 | graph reallocs = 0 / 0 (same size) / (changed size) 5.05.931.295 I slot release: id 0 | task 23371 | stop processing: n_tokens = 497, truncated = 0 5.05.959.118 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 497, t_last = 305832745 5.05.959.169 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.889 MiB) 5.06.014.116 I slot launch_slot_: id 0 | task 23517 | processing task, is_child = 0 5.07.096.022 I slot print_timing: id 0 | task 23517 | prompt eval time = 140.89 ms / 321 tokens ( 0.44 ms per token, 2278.32 tokens per second) 5.07.096.028 I slot print_timing: id 0 | task 23517 | eval time = 940.99 ms / 85 tokens ( 11.20 ms per token, 89.27 tokens per second) 5.07.096.029 I slot print_timing: id 0 | task 23517 | total time = 1081.89 ms / 406 tokens 5.07.096.030 I slot print_timing: id 0 | task 23517 | graphs reused = 22530 5.07.096.031 I slot print_timing: id 0 | task 23517 | graph reallocs = 0 / 0 (same size) / (changed size) 5.07.096.059 I slot release: id 0 | task 23517 | stop processing: n_tokens = 437, truncated = 0 5.07.124.499 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 306997509 5.07.124.549 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.702 MiB) 5.07.175.183 I slot launch_slot_: id 0 | task 23605 | processing task, is_child = 0 5.08.138.292 I slot print_timing: id 0 | task 23605 | prompt eval time = 139.54 ms / 322 tokens ( 0.43 ms per token, 2307.65 tokens per second) 5.08.138.298 I slot print_timing: id 0 | task 23605 | eval time = 823.55 ms / 73 tokens ( 11.44 ms per token, 87.43 tokens per second) 5.08.138.299 I slot print_timing: id 0 | task 23605 | total time = 963.09 ms / 395 tokens 5.08.138.301 I slot print_timing: id 0 | task 23605 | graphs reused = 22601 5.08.138.302 I slot print_timing: id 0 | task 23605 | graph reallocs = 0 / 0 (same size) / (changed size) 5.08.138.331 I slot release: id 0 | task 23605 | stop processing: n_tokens = 426, truncated = 0 5.08.142.995 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 308039780 5.08.143.042 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.171 MiB) 5.08.202.579 I slot launch_slot_: id 0 | task 23681 | processing task, is_child = 0 5.09.017.277 I slot print_timing: id 0 | task 23681 | prompt eval time = 146.09 ms / 337 tokens ( 0.43 ms per token, 2306.88 tokens per second) 5.09.017.282 I slot print_timing: id 0 | task 23681 | eval time = 668.59 ms / 59 tokens ( 11.53 ms per token, 86.75 tokens per second) 5.09.017.283 I slot print_timing: id 0 | task 23681 | total time = 814.68 ms / 396 tokens 5.09.017.284 I slot print_timing: id 0 | task 23681 | graphs reused = 22658 5.09.017.285 I slot print_timing: id 0 | task 23681 | graph reallocs = 0 / 0 (same size) / (changed size) 5.09.017.313 I slot release: id 0 | task 23681 | stop processing: n_tokens = 427, truncated = 0 5.09.038.940 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 427, t_last = 308918762 5.09.038.984 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 313.669 MiB) 5.09.088.135 I slot launch_slot_: id 0 | task 23743 | processing task, is_child = 0 5.10.026.080 I slot print_timing: id 0 | task 23743 | prompt eval time = 144.01 ms / 325 tokens ( 0.44 ms per token, 2256.73 tokens per second) 5.10.026.086 I slot print_timing: id 0 | task 23743 | eval time = 793.91 ms / 70 tokens ( 11.51 ms per token, 86.91 tokens per second) 5.10.026.087 I slot print_timing: id 0 | task 23743 | total time = 937.93 ms / 395 tokens 5.10.026.088 I slot print_timing: id 0 | task 23743 | graphs reused = 22726 5.10.026.089 I slot print_timing: id 0 | task 23743 | graph reallocs = 0 / 0 (same size) / (changed size) 5.10.026.118 I slot release: id 0 | task 23743 | stop processing: n_tokens = 426, truncated = 0 5.10.069.809 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 309927568 5.10.069.856 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.801 MiB) 5.10.122.248 I slot launch_slot_: id 0 | task 23816 | processing task, is_child = 0 5.12.468.569 I slot print_timing: id 0 | task 23816 | prompt eval time = 140.25 ms / 331 tokens ( 0.42 ms per token, 2359.99 tokens per second) 5.12.468.574 I slot print_timing: id 0 | task 23816 | eval time = 2206.05 ms / 197 tokens ( 11.26 ms per token, 88.85 tokens per second) 5.12.468.575 I slot print_timing: id 0 | task 23816 | total time = 2346.30 ms / 528 tokens 5.12.468.577 I slot print_timing: id 0 | task 23816 | graphs reused = 22920 5.12.468.577 I slot print_timing: id 0 | task 23816 | graph reallocs = 0 / 0 (same size) / (changed size) 5.12.468.606 I slot release: id 0 | task 23816 | stop processing: n_tokens = 559, truncated = 0 5.12.488.817 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 559, t_last = 312370056 5.12.488.869 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.422 MiB) 5.12.534.216 I slot launch_slot_: id 0 | task 24016 | processing task, is_child = 0 5.14.521.045 I slot print_timing: id 0 | task 24016 | prompt eval time = 150.48 ms / 336 tokens ( 0.45 ms per token, 2232.91 tokens per second) 5.14.521.051 I slot print_timing: id 0 | task 24016 | eval time = 1836.33 ms / 162 tokens ( 11.41 ms per token, 87.67 tokens per second) 5.14.521.052 I slot print_timing: id 0 | task 24016 | total time = 1986.81 ms / 498 tokens 5.14.521.053 I slot print_timing: id 0 | task 24016 | graphs reused = 23079 5.14.521.054 I slot print_timing: id 0 | task 24016 | graph reallocs = 0 / 0 (same size) / (changed size) 5.14.521.080 I slot release: id 0 | task 24016 | stop processing: n_tokens = 529, truncated = 0 5.14.525.542 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 529, t_last = 314422529 5.14.525.592 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 313.294 MiB) 5.14.571.403 I slot launch_slot_: id 0 | task 24181 | processing task, is_child = 0 5.15.212.661 I slot print_timing: id 0 | task 24181 | prompt eval time = 140.82 ms / 349 tokens ( 0.40 ms per token, 2478.29 tokens per second) 5.15.212.666 I slot print_timing: id 0 | task 24181 | eval time = 500.42 ms / 46 tokens ( 11.12 ms per token, 89.93 tokens per second) 5.15.212.667 I slot print_timing: id 0 | task 24181 | total time = 641.24 ms / 395 tokens 5.15.212.669 I slot print_timing: id 0 | task 24181 | graphs reused = 23123 5.15.212.670 I slot print_timing: id 0 | task 24181 | graph reallocs = 0 / 0 (same size) / (changed size) 5.15.212.699 I slot release: id 0 | task 24181 | stop processing: n_tokens = 426, truncated = 0 5.15.217.351 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 315114149 5.15.217.388 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.359 MiB) 5.15.267.573 I slot launch_slot_: id 0 | task 24230 | processing task, is_child = 0 5.18.414.645 I slot print_timing: id 0 | task 24230 | n_gen = 263, tg = 87.16 t/s, tg_3s = 87.49 t/s 5.21.414.829 I slot print_timing: id 0 | task 24230 | n_gen = 527, tg = 87.57 t/s, tg_3s = 87.99 t/s 5.21.601.596 I slot print_timing: id 0 | task 24230 | prompt eval time = 140.93 ms / 336 tokens ( 0.42 ms per token, 2384.11 tokens per second) 5.21.601.602 I slot print_timing: id 0 | task 24230 | eval time = 6193.07 ms / 543 tokens ( 11.43 ms per token, 87.52 tokens per second) 5.21.601.603 I slot print_timing: id 0 | task 24230 | total time = 6334.00 ms / 879 tokens 5.21.601.604 I slot print_timing: id 0 | task 24230 | graphs reused = 23662 5.21.601.604 I slot print_timing: id 0 | task 24230 | graph reallocs = 0 / 0 (same size) / (changed size) 5.21.601.632 I slot release: id 0 | task 24230 | stop processing: n_tokens = 910, truncated = 0 5.21.623.769 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 910, t_last = 321503082 5.21.623.830 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.735 MiB) 5.21.684.035 I slot launch_slot_: id 0 | task 24776 | processing task, is_child = 0 5.24.835.461 I slot print_timing: id 0 | task 24776 | n_gen = 268, tg = 88.79 t/s, tg_3s = 89.12 t/s 5.25.534.608 I slot print_timing: id 0 | task 24776 | prompt eval time = 144.34 ms / 349 tokens ( 0.41 ms per token, 2417.97 tokens per second) 5.25.534.613 I slot print_timing: id 0 | task 24776 | eval time = 3706.22 ms / 329 tokens ( 11.30 ms per token, 88.50 tokens per second) 5.25.534.614 I slot print_timing: id 0 | task 24776 | total time = 3850.56 ms / 678 tokens 5.25.534.615 I slot print_timing: id 0 | task 24776 | graphs reused = 23988 5.25.534.616 I slot print_timing: id 0 | task 24776 | graph reallocs = 0 / 0 (same size) / (changed size) 5.25.534.645 I slot release: id 0 | task 24776 | stop processing: n_tokens = 709, truncated = 0 5.25.555.275 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 709, t_last = 325436095 5.25.555.325 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.952 MiB) 5.25.615.898 I slot launch_slot_: id 0 | task 25108 | processing task, is_child = 0 5.26.667.035 I slot print_timing: id 0 | task 25108 | prompt eval time = 145.90 ms / 349 tokens ( 0.42 ms per token, 2392.02 tokens per second) 5.26.667.041 I slot print_timing: id 0 | task 25108 | eval time = 905.22 ms / 81 tokens ( 11.32 ms per token, 88.38 tokens per second) 5.26.667.042 I slot print_timing: id 0 | task 25108 | total time = 1051.12 ms / 430 tokens 5.26.667.043 I slot print_timing: id 0 | task 25108 | graphs reused = 24067 5.26.667.044 I slot print_timing: id 0 | task 25108 | graph reallocs = 0 / 0 (same size) / (changed size) 5.26.667.075 I slot release: id 0 | task 25108 | stop processing: n_tokens = 461, truncated = 0 5.26.708.288 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 461, t_last = 326568525 5.26.708.333 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.701 MiB) 5.26.765.144 I slot launch_slot_: id 0 | task 25192 | processing task, is_child = 0 5.28.671.251 I slot print_timing: id 0 | task 25192 | prompt eval time = 146.69 ms / 385 tokens ( 0.38 ms per token, 2624.56 tokens per second) 5.28.671.256 I slot print_timing: id 0 | task 25192 | eval time = 1759.40 ms / 157 tokens ( 11.28 ms per token, 88.67 tokens per second) 5.28.671.257 I slot print_timing: id 0 | task 25192 | total time = 1906.09 ms / 542 tokens 5.28.671.258 I slot print_timing: id 0 | task 25192 | graphs reused = 24221 5.28.671.259 I slot print_timing: id 0 | task 25192 | graph reallocs = 0 / 0 (same size) / (changed size) 5.28.671.286 I slot release: id 0 | task 25192 | stop processing: n_tokens = 573, truncated = 0 5.28.690.489 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 573, t_last = 328572736 5.28.690.540 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.954 MiB) 5.28.751.078 I slot launch_slot_: id 0 | task 25352 | processing task, is_child = 0 5.29.735.442 I slot print_timing: id 0 | task 25352 | prompt eval time = 143.52 ms / 328 tokens ( 0.44 ms per token, 2285.36 tokens per second) 5.29.735.448 I slot print_timing: id 0 | task 25352 | eval time = 840.82 ms / 74 tokens ( 11.52 ms per token, 86.82 tokens per second) 5.29.735.449 I slot print_timing: id 0 | task 25352 | total time = 984.35 ms / 402 tokens 5.29.735.450 I slot print_timing: id 0 | task 25352 | graphs reused = 24293 5.29.735.450 I slot print_timing: id 0 | task 25352 | graph reallocs = 0 / 0 (same size) / (changed size) 5.29.735.476 I slot release: id 0 | task 25352 | stop processing: n_tokens = 433, truncated = 0