$ /Users/minipro/quantdiff/work/llama-b11869/src/build/bin/llama-server -m /Users/minipro/quantdiff/models/campaign/3376b755f9ab/Sage-A1.5.i1-IQ3_M.gguf --host 127.0.0.1 --port 8089 -c 4096 -np 1 -ngl 999 -fa on --jinja --seed 1234 --no-webui -a quant 0.00.045.725 I srv llama_server: initializing ... 0.00.045.735 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.047.566 I srv init_listene: The UI is disabled 0.00.047.568 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.047.865 W srv server_setup: security: no API key is set and CORS allows all origins (see https://github.com/ggml-org/llama.cpp/pull/25655) 0.00.050.145 I srv load_model: loading model '/Users/minipro/quantdiff/models/campaign/3376b755f9ab/Sage-A1.5.i1-IQ3_M.gguf' 0.00.338.783 W model has unused tensor blk.40.attn_norm.weight (size = 8192 bytes) -- ignoring 0.00.338.792 W model has unused tensor blk.40.post_attention_norm.weight (size = 8192 bytes) -- ignoring 0.00.338.799 W model has unused tensor blk.40.attn_q.weight (size = 7208960 bytes) -- ignoring 0.00.338.801 W model has unused tensor blk.40.attn_k.weight (size = 450560 bytes) -- ignoring 0.00.338.804 W model has unused tensor blk.40.attn_v.weight (size = 589824 bytes) -- ignoring 0.00.338.812 W model has unused tensor blk.40.attn_output.weight (size = 4718592 bytes) -- ignoring 0.00.338.815 W model has unused tensor blk.40.attn_q_norm.weight (size = 1024 bytes) -- ignoring 0.00.338.817 W model has unused tensor blk.40.attn_k_norm.weight (size = 1024 bytes) -- ignoring 0.00.338.819 W model has unused tensor blk.40.ffn_gate_inp.weight (size = 2097152 bytes) -- ignoring 0.00.338.821 W model has unused tensor blk.40.ffn_down_exps.weight (size = 115343360 bytes) -- ignoring 0.00.338.825 W model has unused tensor blk.40.ffn_gate_exps.weight (size = 115343360 bytes) -- ignoring 0.00.338.828 W model has unused tensor blk.40.ffn_up_exps.weight (size = 115343360 bytes) -- ignoring 0.00.338.830 W model has unused tensor blk.40.ffn_gate_inp_shexp.weight (size = 8192 bytes) -- ignoring 0.00.338.832 W model has unused tensor blk.40.ffn_gate_shexp.weight (size = 450560 bytes) -- ignoring 0.00.338.835 W model has unused tensor blk.40.ffn_up_shexp.weight (size = 450560 bytes) -- ignoring 0.00.338.837 W model has unused tensor blk.40.ffn_down_shexp.weight (size = 450560 bytes) -- ignoring 0.00.338.840 W model has unused tensor blk.40.nextn.eh_proj.weight (size = 3604480 bytes) -- ignoring 0.00.338.842 W model has unused tensor blk.40.nextn.enorm.weight (size = 8192 bytes) -- ignoring 0.00.338.844 W model has unused tensor blk.40.nextn.hnorm.weight (size = 8192 bytes) -- ignoring 0.00.338.851 W model has unused tensor blk.40.nextn.shared_head_norm.weight (size = 8192 bytes) -- ignoring 0.01.032.996 I cmn init: llama threadpool init, n_threads = 8 0.01.199.031 I srv load_model: initializing, n_slots = 1, n_ctx_slot = 4096, kv_unified = 'false' 0.01.205.681 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.01.205.894 I srv server_run_i: model loaded 0.01.205.897 I srv server_on_li: listening on http://127.0.0.1:8089 0.02.023.596 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.02.024.477 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.03.959.507 I slot print_timing: id 0 | task 0 | prompt eval time = 888.37 ms / 368 tokens ( 2.41 ms per token, 414.24 tokens per second) 0.03.959.511 I slot print_timing: id 0 | task 0 | eval time = 1046.48 ms / 53 tokens ( 20.12 ms per token, 49.69 tokens per second) 0.03.959.511 I slot print_timing: id 0 | task 0 | total time = 1934.85 ms / 421 tokens 0.03.959.512 I slot print_timing: id 0 | task 0 | graphs reused = 52 0.03.959.513 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.03.959.543 I slot release: id 0 | task 0 | stop processing: n_tokens = 420, truncated = 0 0.03.964.933 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 420, t_last = 387735002928 0.03.983.117 I slot launch_slot_: id 0 | task 56 | processing task, is_child = 0 0.05.621.554 I slot print_timing: id 0 | task 56 | prompt eval time = 813.42 ms / 322 tokens ( 2.53 ms per token, 395.86 tokens per second) 0.05.621.557 I slot print_timing: id 0 | task 56 | eval time = 825.01 ms / 42 tokens ( 20.12 ms per token, 49.70 tokens per second) 0.05.621.558 I slot print_timing: id 0 | task 56 | total time = 1638.42 ms / 364 tokens 0.05.621.559 I slot print_timing: id 0 | task 56 | graphs reused = 92 0.05.621.560 I slot print_timing: id 0 | task 56 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.621.590 I slot release: id 0 | task 56 | stop processing: n_tokens = 363, truncated = 0 0.05.625.813 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 363, t_last = 387736664975 0.05.642.990 I slot launch_slot_: id 0 | task 101 | processing task, is_child = 0 0.07.345.347 I slot print_timing: id 0 | task 101 | prompt eval time = 880.87 ms / 365 tokens ( 2.41 ms per token, 414.36 tokens per second) 0.07.345.357 I slot print_timing: id 0 | task 101 | eval time = 821.48 ms / 42 tokens ( 20.04 ms per token, 49.91 tokens per second) 0.07.345.358 I slot print_timing: id 0 | task 101 | total time = 1702.35 ms / 407 tokens 0.07.345.358 I slot print_timing: id 0 | task 101 | graphs reused = 132 0.07.345.359 I slot print_timing: id 0 | task 101 | graph reallocs = 0 / 0 (same size) / (changed size) 0.07.345.387 I slot release: id 0 | task 101 | stop processing: n_tokens = 406, truncated = 0 0.07.349.919 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 406, t_last = 387738388772 0.07.366.738 I slot launch_slot_: id 0 | task 146 | processing task, is_child = 0 0.09.148.711 I slot print_timing: id 0 | task 146 | prompt eval time = 936.14 ms / 397 tokens ( 2.36 ms per token, 424.08 tokens per second) 0.09.148.718 I slot print_timing: id 0 | task 146 | eval time = 845.83 ms / 43 tokens ( 20.14 ms per token, 49.66 tokens per second) 0.09.148.718 I slot print_timing: id 0 | task 146 | total time = 1781.96 ms / 440 tokens 0.09.148.719 I slot print_timing: id 0 | task 146 | graphs reused = 173 0.09.148.720 I slot print_timing: id 0 | task 146 | graph reallocs = 0 / 0 (same size) / (changed size) 0.09.148.753 I slot release: id 0 | task 146 | stop processing: n_tokens = 439, truncated = 0 0.09.153.113 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.117 (> 0.100 thold), f_keep = 0.103 0.09.170.939 I slot launch_slot_: id 0 | task 192 | processing task, is_child = 0 0.11.182.864 I slot print_timing: id 0 | task 192 | prompt eval time = 925.76 ms / 383 tokens ( 2.42 ms per token, 413.72 tokens per second) 0.11.182.870 I slot print_timing: id 0 | task 192 | eval time = 1086.16 ms / 55 tokens ( 20.11 ms per token, 49.72 tokens per second) 0.11.182.871 I slot print_timing: id 0 | task 192 | total time = 2011.91 ms / 438 tokens 0.11.182.871 I slot print_timing: id 0 | task 192 | graphs reused = 226 0.11.182.872 I slot print_timing: id 0 | task 192 | graph reallocs = 0 / 0 (same size) / (changed size) 0.11.182.899 I slot release: id 0 | task 192 | stop processing: n_tokens = 437, truncated = 0 0.11.187.186 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 387742226284 0.11.205.386 I slot launch_slot_: id 0 | task 250 | processing task, is_child = 0 0.13.144.915 I slot print_timing: id 0 | task 250 | prompt eval time = 856.09 ms / 372 tokens ( 2.30 ms per token, 434.54 tokens per second) 0.13.144.923 I slot print_timing: id 0 | task 250 | eval time = 1083.43 ms / 55 tokens ( 20.06 ms per token, 49.84 tokens per second) 0.13.144.924 I slot print_timing: id 0 | task 250 | total time = 1939.52 ms / 427 tokens 0.13.144.925 I slot print_timing: id 0 | task 250 | graphs reused = 279 0.13.144.925 I slot print_timing: id 0 | task 250 | graph reallocs = 0 / 0 (same size) / (changed size) 0.13.144.955 I slot release: id 0 | task 250 | stop processing: n_tokens = 426, truncated = 0 0.13.149.561 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 387744188340 0.13.167.330 I slot launch_slot_: id 0 | task 308 | processing task, is_child = 0 0.15.226.829 I slot print_timing: id 0 | task 308 | prompt eval time = 970.94 ms / 422 tokens ( 2.30 ms per token, 434.63 tokens per second) 0.15.226.832 I slot print_timing: id 0 | task 308 | eval time = 1088.54 ms / 55 tokens ( 20.16 ms per token, 49.61 tokens per second) 0.15.226.834 I slot print_timing: id 0 | task 308 | total time = 2059.49 ms / 477 tokens 0.15.226.834 I slot print_timing: id 0 | task 308 | graphs reused = 332 0.15.226.835 I slot print_timing: id 0 | task 308 | graph reallocs = 0 / 0 (same size) / (changed size) 0.15.226.873 I slot release: id 0 | task 308 | stop processing: n_tokens = 476, truncated = 0 0.15.231.568 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 476, t_last = 387746270258 0.15.249.284 I slot launch_slot_: id 0 | task 366 | processing task, is_child = 0 0.17.723.125 I slot print_timing: id 0 | task 366 | prompt eval time = 1038.67 ms / 470 tokens ( 2.21 ms per token, 452.50 tokens per second) 0.17.723.147 I slot print_timing: id 0 | task 366 | eval time = 1435.16 ms / 72 tokens ( 20.21 ms per token, 49.47 tokens per second) 0.17.723.148 I slot print_timing: id 0 | task 366 | total time = 2473.83 ms / 542 tokens 0.17.723.148 I slot print_timing: id 0 | task 366 | graphs reused = 401 0.17.723.149 I slot print_timing: id 0 | task 366 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.723.182 I slot release: id 0 | task 366 | stop processing: n_tokens = 541, truncated = 0 0.17.727.543 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 541, t_last = 387748766567 0.17.745.571 I slot launch_slot_: id 0 | task 441 | processing task, is_child = 0 0.19.520.571 I slot print_timing: id 0 | task 441 | prompt eval time = 848.65 ms / 345 tokens ( 2.46 ms per token, 406.53 tokens per second) 0.19.520.577 I slot print_timing: id 0 | task 441 | eval time = 926.34 ms / 47 tokens ( 20.14 ms per token, 49.66 tokens per second) 0.19.520.578 I slot print_timing: id 0 | task 441 | total time = 1774.99 ms / 392 tokens 0.19.520.578 I slot print_timing: id 0 | task 441 | graphs reused = 446 0.19.520.579 I slot print_timing: id 0 | task 441 | graph reallocs = 0 / 0 (same size) / (changed size) 0.19.520.605 I slot release: id 0 | task 441 | stop processing: n_tokens = 391, truncated = 0 0.19.525.011 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 391, t_last = 387750563991 0.19.542.790 I slot launch_slot_: id 0 | task 491 | processing task, is_child = 0 0.21.241.721 I slot print_timing: id 0 | task 491 | prompt eval time = 893.06 ms / 364 tokens ( 2.45 ms per token, 407.59 tokens per second) 0.21.241.727 I slot print_timing: id 0 | task 491 | eval time = 805.86 ms / 41 tokens ( 20.15 ms per token, 49.64 tokens per second) 0.21.241.728 I slot print_timing: id 0 | task 491 | total time = 1698.92 ms / 405 tokens 0.21.241.728 I slot print_timing: id 0 | task 491 | graphs reused = 485 0.21.241.729 I slot print_timing: id 0 | task 491 | graph reallocs = 0 / 0 (same size) / (changed size) 0.21.241.758 I slot release: id 0 | task 491 | stop processing: n_tokens = 404, truncated = 0 0.21.246.153 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 404, t_last = 387752285143 0.21.263.249 I slot launch_slot_: id 0 | task 535 | processing task, is_child = 0 0.23.368.811 I slot print_timing: id 0 | task 535 | prompt eval time = 857.44 ms / 376 tokens ( 2.28 ms per token, 438.52 tokens per second) 0.23.368.817 I slot print_timing: id 0 | task 535 | eval time = 1248.11 ms / 62 tokens ( 20.46 ms per token, 48.87 tokens per second) 0.23.368.817 I slot print_timing: id 0 | task 535 | total time = 2105.55 ms / 438 tokens 0.23.368.818 I slot print_timing: id 0 | task 535 | graphs reused = 545 0.23.368.819 I slot print_timing: id 0 | task 535 | graph reallocs = 0 / 0 (same size) / (changed size) 0.23.368.851 I slot release: id 0 | task 535 | stop processing: n_tokens = 437, truncated = 0 0.23.373.316 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 387754412236 0.23.390.485 I slot launch_slot_: id 0 | task 600 | processing task, is_child = 0 0.25.259.800 I slot print_timing: id 0 | task 600 | prompt eval time = 940.52 ms / 412 tokens ( 2.28 ms per token, 438.06 tokens per second) 0.25.259.806 I slot print_timing: id 0 | task 600 | eval time = 928.78 ms / 47 tokens ( 20.19 ms per token, 49.53 tokens per second) 0.25.259.807 I slot print_timing: id 0 | task 600 | total time = 1869.30 ms / 459 tokens 0.25.259.808 I slot print_timing: id 0 | task 600 | graphs reused = 590 0.25.259.809 I slot print_timing: id 0 | task 600 | graph reallocs = 0 / 0 (same size) / (changed size) 0.25.259.843 I slot release: id 0 | task 600 | stop processing: n_tokens = 458, truncated = 0 0.25.264.149 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 387756303228 0.25.281.295 I slot launch_slot_: id 0 | task 650 | processing task, is_child = 0 0.27.414.496 I slot print_timing: id 0 | task 650 | prompt eval time = 904.42 ms / 376 tokens ( 2.41 ms per token, 415.73 tokens per second) 0.27.414.499 I slot print_timing: id 0 | task 650 | eval time = 1228.76 ms / 62 tokens ( 20.14 ms per token, 49.64 tokens per second) 0.27.414.500 I slot print_timing: id 0 | task 650 | total time = 2133.19 ms / 438 tokens 0.27.414.501 I slot print_timing: id 0 | task 650 | graphs reused = 650 0.27.414.501 I slot print_timing: id 0 | task 650 | graph reallocs = 0 / 0 (same size) / (changed size) 0.27.414.533 I slot release: id 0 | task 650 | stop processing: n_tokens = 437, truncated = 0 0.27.418.984 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 387758457918 0.27.436.040 I slot launch_slot_: id 0 | task 715 | processing task, is_child = 0 0.29.336.538 I slot print_timing: id 0 | task 715 | prompt eval time = 872.91 ms / 378 tokens ( 2.31 ms per token, 433.04 tokens per second) 0.29.336.544 I slot print_timing: id 0 | task 715 | eval time = 1027.58 ms / 52 tokens ( 20.15 ms per token, 49.63 tokens per second) 0.29.336.546 I slot print_timing: id 0 | task 715 | total time = 1900.49 ms / 430 tokens 0.29.336.546 I slot print_timing: id 0 | task 715 | graphs reused = 700 0.29.336.547 I slot print_timing: id 0 | task 715 | graph reallocs = 0 / 0 (same size) / (changed size) 0.29.336.574 I slot release: id 0 | task 715 | stop processing: n_tokens = 429, truncated = 0 0.29.340.941 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 429, t_last = 387760379959 0.29.358.403 I slot launch_slot_: id 0 | task 770 | processing task, is_child = 0 0.31.388.560 I slot print_timing: id 0 | task 770 | prompt eval time = 865.68 ms / 367 tokens ( 2.36 ms per token, 423.94 tokens per second) 0.31.388.566 I slot print_timing: id 0 | task 770 | eval time = 1164.46 ms / 58 tokens ( 20.43 ms per token, 48.95 tokens per second) 0.31.388.567 I slot print_timing: id 0 | task 770 | total time = 2030.15 ms / 425 tokens 0.31.388.567 I slot print_timing: id 0 | task 770 | graphs reused = 756 0.31.388.568 I slot print_timing: id 0 | task 770 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.388.595 I slot release: id 0 | task 770 | stop processing: n_tokens = 424, truncated = 0 0.31.392.957 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 387762431980 0.31.410.295 I slot launch_slot_: id 0 | task 831 | processing task, is_child = 0 0.33.270.869 I slot print_timing: id 0 | task 831 | prompt eval time = 852.99 ms / 347 tokens ( 2.46 ms per token, 406.81 tokens per second) 0.33.270.875 I slot print_timing: id 0 | task 831 | eval time = 1007.58 ms / 51 tokens ( 20.15 ms per token, 49.62 tokens per second) 0.33.270.876 I slot print_timing: id 0 | task 831 | total time = 1860.56 ms / 398 tokens 0.33.270.877 I slot print_timing: id 0 | task 831 | graphs reused = 805 0.33.270.877 I slot print_timing: id 0 | task 831 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.270.904 I slot release: id 0 | task 831 | stop processing: n_tokens = 397, truncated = 0 0.33.275.208 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 397, t_last = 387764314289 0.33.292.513 I slot launch_slot_: id 0 | task 885 | processing task, is_child = 0 0.35.250.603 I slot print_timing: id 0 | task 885 | prompt eval time = 891.02 ms / 369 tokens ( 2.41 ms per token, 414.13 tokens per second) 0.35.250.609 I slot print_timing: id 0 | task 885 | eval time = 1067.06 ms / 54 tokens ( 20.13 ms per token, 49.67 tokens per second) 0.35.250.610 I slot print_timing: id 0 | task 885 | total time = 1958.08 ms / 423 tokens 0.35.250.610 I slot print_timing: id 0 | task 885 | graphs reused = 857 0.35.250.611 I slot print_timing: id 0 | task 885 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.250.640 I slot release: id 0 | task 885 | stop processing: n_tokens = 422, truncated = 0 0.35.254.908 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 422, t_last = 387766294025 0.35.272.409 I slot launch_slot_: id 0 | task 942 | processing task, is_child = 0 0.36.939.652 I slot print_timing: id 0 | task 942 | prompt eval time = 859.65 ms / 352 tokens ( 2.44 ms per token, 409.47 tokens per second) 0.36.939.658 I slot print_timing: id 0 | task 942 | eval time = 807.58 ms / 41 tokens ( 20.19 ms per token, 49.53 tokens per second) 0.36.939.659 I slot print_timing: id 0 | task 942 | total time = 1667.23 ms / 393 tokens 0.36.939.660 I slot print_timing: id 0 | task 942 | graphs reused = 896 0.36.939.660 I slot print_timing: id 0 | task 942 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.939.690 I slot release: id 0 | task 942 | stop processing: n_tokens = 392, truncated = 0 0.36.943.970 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 392, t_last = 387767983075 0.36.960.574 I slot launch_slot_: id 0 | task 986 | processing task, is_child = 0 0.38.588.143 I slot print_timing: id 0 | task 986 | prompt eval time = 840.30 ms / 349 tokens ( 2.41 ms per token, 415.33 tokens per second) 0.38.588.149 I slot print_timing: id 0 | task 986 | eval time = 787.26 ms / 40 tokens ( 20.19 ms per token, 49.54 tokens per second) 0.38.588.150 I slot print_timing: id 0 | task 986 | total time = 1627.56 ms / 389 tokens 0.38.588.151 I slot print_timing: id 0 | task 986 | graphs reused = 934 0.38.588.152 I slot print_timing: id 0 | task 986 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.588.180 I slot release: id 0 | task 986 | stop processing: n_tokens = 388, truncated = 0 0.38.592.661 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 388, t_last = 387769631565 0.38.610.372 I slot launch_slot_: id 0 | task 1029 | processing task, is_child = 0 0.40.790.721 I slot print_timing: id 0 | task 1029 | prompt eval time = 916.41 ms / 384 tokens ( 2.39 ms per token, 419.03 tokens per second) 0.40.790.727 I slot print_timing: id 0 | task 1029 | eval time = 1263.93 ms / 63 tokens ( 20.39 ms per token, 49.05 tokens per second) 0.40.790.728 I slot print_timing: id 0 | task 1029 | total time = 2180.34 ms / 447 tokens 0.40.790.729 I slot print_timing: id 0 | task 1029 | graphs reused = 995 0.40.790.729 I slot print_timing: id 0 | task 1029 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.790.761 I slot release: id 0 | task 1029 | stop processing: n_tokens = 446, truncated = 0 0.40.795.077 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 446, t_last = 387771834146 0.40.811.896 I slot launch_slot_: id 0 | task 1095 | processing task, is_child = 0 0.42.724.336 I slot print_timing: id 0 | task 1095 | prompt eval time = 845.17 ms / 356 tokens ( 2.37 ms per token, 421.22 tokens per second) 0.42.724.341 I slot print_timing: id 0 | task 1095 | eval time = 1067.26 ms / 54 tokens ( 20.14 ms per token, 49.66 tokens per second) 0.42.724.342 I slot print_timing: id 0 | task 1095 | total time = 1912.43 ms / 410 tokens 0.42.724.343 I slot print_timing: id 0 | task 1095 | graphs reused = 1047 0.42.724.343 I slot print_timing: id 0 | task 1095 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.724.373 I slot release: id 0 | task 1095 | stop processing: n_tokens = 409, truncated = 0 0.42.728.870 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 387773767758 0.42.746.145 I slot launch_slot_: id 0 | task 1152 | processing task, is_child = 0 0.45.082.532 I slot print_timing: id 0 | task 1152 | prompt eval time = 948.40 ms / 410 tokens ( 2.31 ms per token, 432.30 tokens per second) 0.45.082.539 I slot print_timing: id 0 | task 1152 | eval time = 1387.97 ms / 70 tokens ( 20.12 ms per token, 49.71 tokens per second) 0.45.082.539 I slot print_timing: id 0 | task 1152 | total time = 2336.38 ms / 480 tokens 0.45.082.540 I slot print_timing: id 0 | task 1152 | graphs reused = 1115 0.45.082.541 I slot print_timing: id 0 | task 1152 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.082.578 I slot release: id 0 | task 1152 | stop processing: n_tokens = 479, truncated = 0 0.45.086.848 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 479, t_last = 387776125963 0.45.103.375 I slot launch_slot_: id 0 | task 1225 | processing task, is_child = 0 0.47.162.458 I slot print_timing: id 0 | task 1225 | prompt eval time = 910.02 ms / 385 tokens ( 2.36 ms per token, 423.07 tokens per second) 0.47.162.464 I slot print_timing: id 0 | task 1225 | eval time = 1149.05 ms / 58 tokens ( 20.16 ms per token, 49.61 tokens per second) 0.47.162.465 I slot print_timing: id 0 | task 1225 | total time = 2059.07 ms / 443 tokens 0.47.162.465 I slot print_timing: id 0 | task 1225 | graphs reused = 1171 0.47.162.466 I slot print_timing: id 0 | task 1225 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.162.497 I slot release: id 0 | task 1225 | stop processing: n_tokens = 442, truncated = 0 0.47.166.973 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 442, t_last = 387778205882 0.47.184.852 I slot launch_slot_: id 0 | task 1286 | processing task, is_child = 0 0.49.516.928 I slot print_timing: id 0 | task 1286 | prompt eval time = 918.28 ms / 395 tokens ( 2.32 ms per token, 430.15 tokens per second) 0.49.516.935 I slot print_timing: id 0 | task 1286 | eval time = 1413.79 ms / 71 tokens ( 20.20 ms per token, 49.51 tokens per second) 0.49.516.936 I slot print_timing: id 0 | task 1286 | total time = 2332.07 ms / 466 tokens 0.49.516.937 I slot print_timing: id 0 | task 1286 | graphs reused = 1240 0.49.516.938 I slot print_timing: id 0 | task 1286 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.516.969 I slot release: id 0 | task 1286 | stop processing: n_tokens = 465, truncated = 0 0.49.521.624 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 465, t_last = 387780560354 0.49.539.301 I slot launch_slot_: id 0 | task 1360 | processing task, is_child = 0 0.51.747.146 I slot print_timing: id 0 | task 1360 | prompt eval time = 976.72 ms / 430 tokens ( 2.27 ms per token, 440.25 tokens per second) 0.51.747.149 I slot print_timing: id 0 | task 1360 | eval time = 1231.11 ms / 62 tokens ( 20.18 ms per token, 49.55 tokens per second) 0.51.747.150 I slot print_timing: id 0 | task 1360 | total time = 2207.83 ms / 492 tokens 0.51.747.151 I slot print_timing: id 0 | task 1360 | graphs reused = 1300 0.51.747.151 I slot print_timing: id 0 | task 1360 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.747.187 I slot release: id 0 | task 1360 | stop processing: n_tokens = 491, truncated = 0 0.51.751.612 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 491, t_last = 387782790572 0.51.769.617 I slot launch_slot_: id 0 | task 1425 | processing task, is_child = 0 0.53.926.681 I slot print_timing: id 0 | task 1425 | prompt eval time = 927.40 ms / 392 tokens ( 2.37 ms per token, 422.69 tokens per second) 0.53.926.686 I slot print_timing: id 0 | task 1425 | eval time = 1229.65 ms / 62 tokens ( 20.16 ms per token, 49.61 tokens per second) 0.53.926.686 I slot print_timing: id 0 | task 1425 | total time = 2157.05 ms / 454 tokens 0.53.926.687 I slot print_timing: id 0 | task 1425 | graphs reused = 1360 0.53.926.688 I slot print_timing: id 0 | task 1425 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.926.721 I slot release: id 0 | task 1425 | stop processing: n_tokens = 453, truncated = 0 0.53.931.056 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 453, t_last = 387784970106 0.53.948.736 I slot launch_slot_: id 0 | task 1490 | processing task, is_child = 0 0.55.773.220 I slot print_timing: id 0 | task 1490 | prompt eval time = 856.06 ms / 350 tokens ( 2.45 ms per token, 408.85 tokens per second) 0.55.773.223 I slot print_timing: id 0 | task 1490 | eval time = 968.42 ms / 49 tokens ( 20.18 ms per token, 49.57 tokens per second) 0.55.773.224 I slot print_timing: id 0 | task 1490 | total time = 1824.47 ms / 399 tokens 0.55.773.225 I slot print_timing: id 0 | task 1490 | graphs reused = 1407 0.55.773.226 I slot print_timing: id 0 | task 1490 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.773.257 I slot release: id 0 | task 1490 | stop processing: n_tokens = 398, truncated = 0 0.55.777.797 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 398, t_last = 387786816642 0.55.795.450 I slot launch_slot_: id 0 | task 1542 | processing task, is_child = 0 0.57.883.571 I slot print_timing: id 0 | task 1542 | prompt eval time = 876.18 ms / 380 tokens ( 2.31 ms per token, 433.70 tokens per second) 0.57.883.574 I slot print_timing: id 0 | task 1542 | eval time = 1211.93 ms / 61 tokens ( 20.20 ms per token, 49.51 tokens per second) 0.57.883.575 I slot print_timing: id 0 | task 1542 | total time = 2088.11 ms / 441 tokens 0.57.883.576 I slot print_timing: id 0 | task 1542 | graphs reused = 1466 0.57.883.576 I slot print_timing: id 0 | task 1542 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.883.608 I slot release: id 0 | task 1542 | stop processing: n_tokens = 440, truncated = 0 0.57.888.211 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 440, t_last = 387788926993 0.57.906.642 I slot launch_slot_: id 0 | task 1606 | processing task, is_child = 0 1.00.472.387 I slot print_timing: id 0 | task 1606 | prompt eval time = 957.14 ms / 410 tokens ( 2.33 ms per token, 428.36 tokens per second) 1.00.472.392 I slot print_timing: id 0 | task 1606 | eval time = 1608.59 ms / 80 tokens ( 20.36 ms per token, 49.11 tokens per second) 1.00.472.392 I slot print_timing: id 0 | task 1606 | total time = 2565.73 ms / 490 tokens 1.00.472.393 I slot print_timing: id 0 | task 1606 | graphs reused = 1544 1.00.472.394 I slot print_timing: id 0 | task 1606 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.472.432 I slot release: id 0 | task 1606 | stop processing: n_tokens = 489, truncated = 0 1.00.476.856 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 489, t_last = 387791515817 1.00.494.921 I slot launch_slot_: id 0 | task 1689 | processing task, is_child = 0 1.02.763.063 I slot print_timing: id 0 | task 1689 | prompt eval time = 918.63 ms / 387 tokens ( 2.37 ms per token, 421.28 tokens per second) 1.02.763.067 I slot print_timing: id 0 | task 1689 | eval time = 1349.50 ms / 68 tokens ( 20.14 ms per token, 49.65 tokens per second) 1.02.763.068 I slot print_timing: id 0 | task 1689 | total time = 2268.13 ms / 455 tokens 1.02.763.068 I slot print_timing: id 0 | task 1689 | graphs reused = 1610 1.02.763.069 I slot print_timing: id 0 | task 1689 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.763.098 I slot release: id 0 | task 1689 | stop processing: n_tokens = 454, truncated = 0 1.02.767.585 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 454, t_last = 387793806483 1.02.792.440 I slot launch_slot_: id 0 | task 1760 | processing task, is_child = 0 1.04.823.126 I slot print_timing: id 0 | task 1760 | prompt eval time = 862.46 ms / 358 tokens ( 2.41 ms per token, 415.09 tokens per second) 1.04.823.130 I slot print_timing: id 0 | task 1760 | eval time = 1168.21 ms / 59 tokens ( 20.14 ms per token, 49.65 tokens per second) 1.04.823.131 I slot print_timing: id 0 | task 1760 | total time = 2030.68 ms / 417 tokens 1.04.823.132 I slot print_timing: id 0 | task 1760 | graphs reused = 1667 1.04.823.132 I slot print_timing: id 0 | task 1760 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.823.160 I slot release: id 0 | task 1760 | stop processing: n_tokens = 416, truncated = 0 1.04.827.476 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 387795866545 1.04.849.305 I slot launch_slot_: id 0 | task 1822 | processing task, is_child = 0 1.06.826.755 I slot print_timing: id 0 | task 1822 | prompt eval time = 851.82 ms / 359 tokens ( 2.37 ms per token, 421.45 tokens per second) 1.06.826.759 I slot print_timing: id 0 | task 1822 | eval time = 1125.61 ms / 56 tokens ( 20.47 ms per token, 48.86 tokens per second) 1.06.826.760 I slot print_timing: id 0 | task 1822 | total time = 1977.43 ms / 415 tokens 1.06.826.760 I slot print_timing: id 0 | task 1822 | graphs reused = 1721 1.06.826.761 I slot print_timing: id 0 | task 1822 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.826.788 I slot release: id 0 | task 1822 | stop processing: n_tokens = 414, truncated = 0 1.06.831.324 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 387797870173 1.06.854.529 I slot launch_slot_: id 0 | task 1881 | processing task, is_child = 0 1.08.967.238 I slot print_timing: id 0 | task 1881 | prompt eval time = 904.11 ms / 387 tokens ( 2.34 ms per token, 428.04 tokens per second) 1.08.967.242 I slot print_timing: id 0 | task 1881 | eval time = 1208.58 ms / 61 tokens ( 20.14 ms per token, 49.64 tokens per second) 1.08.967.242 I slot print_timing: id 0 | task 1881 | total time = 2112.70 ms / 448 tokens 1.08.967.243 I slot print_timing: id 0 | task 1881 | graphs reused = 1780 1.08.967.243 I slot print_timing: id 0 | task 1881 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.967.272 I slot release: id 0 | task 1881 | stop processing: n_tokens = 447, truncated = 0 1.08.971.712 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 387800010657 1.08.996.050 I slot launch_slot_: id 0 | task 1945 | processing task, is_child = 0 1.11.148.768 I slot print_timing: id 0 | task 1945 | prompt eval time = 926.02 ms / 410 tokens ( 2.26 ms per token, 442.76 tokens per second) 1.11.148.775 I slot print_timing: id 0 | task 1945 | eval time = 1226.69 ms / 61 tokens ( 20.44 ms per token, 48.91 tokens per second) 1.11.148.775 I slot print_timing: id 0 | task 1945 | total time = 2152.71 ms / 471 tokens 1.11.148.776 I slot print_timing: id 0 | task 1945 | graphs reused = 1839 1.11.148.777 I slot print_timing: id 0 | task 1945 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.148.810 I slot release: id 0 | task 1945 | stop processing: n_tokens = 470, truncated = 0 1.11.153.134 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 387802192195 1.11.175.581 I slot launch_slot_: id 0 | task 2009 | processing task, is_child = 0 1.13.010.213 I slot print_timing: id 0 | task 2009 | prompt eval time = 846.44 ms / 351 tokens ( 2.41 ms per token, 414.68 tokens per second) 1.13.010.219 I slot print_timing: id 0 | task 2009 | eval time = 988.18 ms / 50 tokens ( 20.17 ms per token, 49.59 tokens per second) 1.13.010.220 I slot print_timing: id 0 | task 2009 | total time = 1834.62 ms / 401 tokens 1.13.010.220 I slot print_timing: id 0 | task 2009 | graphs reused = 1887 1.13.010.221 I slot print_timing: id 0 | task 2009 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.010.253 I slot release: id 0 | task 2009 | stop processing: n_tokens = 400, truncated = 0 1.13.014.769 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 387804053638 1.13.036.872 I slot launch_slot_: id 0 | task 2062 | processing task, is_child = 0 1.15.048.234 I slot print_timing: id 0 | task 2062 | prompt eval time = 900.32 ms / 393 tokens ( 2.29 ms per token, 436.51 tokens per second) 1.15.048.237 I slot print_timing: id 0 | task 2062 | eval time = 1111.03 ms / 56 tokens ( 20.20 ms per token, 49.50 tokens per second) 1.15.048.237 I slot print_timing: id 0 | task 2062 | total time = 2011.35 ms / 449 tokens 1.15.048.238 I slot print_timing: id 0 | task 2062 | graphs reused = 1941 1.15.048.239 I slot print_timing: id 0 | task 2062 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.048.270 I slot release: id 0 | task 2062 | stop processing: n_tokens = 448, truncated = 0 1.15.052.498 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 387806091655 1.15.077.860 I slot launch_slot_: id 0 | task 2121 | processing task, is_child = 0 1.16.458.864 I slot print_timing: id 0 | task 2121 | prompt eval time = 793.58 ms / 321 tokens ( 2.47 ms per token, 404.49 tokens per second) 1.16.458.867 I slot print_timing: id 0 | task 2121 | eval time = 587.41 ms / 30 tokens ( 20.26 ms per token, 49.37 tokens per second) 1.16.458.868 I slot print_timing: id 0 | task 2121 | total time = 1380.99 ms / 351 tokens 1.16.458.869 I slot print_timing: id 0 | task 2121 | graphs reused = 1969 1.16.458.870 I slot print_timing: id 0 | task 2121 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.458.902 I slot release: id 0 | task 2121 | stop processing: n_tokens = 350, truncated = 0 1.16.463.161 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 350, t_last = 387807502287 1.16.486.415 I slot launch_slot_: id 0 | task 2154 | processing task, is_child = 0 1.18.207.079 I slot print_timing: id 0 | task 2154 | prompt eval time = 815.21 ms / 330 tokens ( 2.47 ms per token, 404.80 tokens per second) 1.18.207.083 I slot print_timing: id 0 | task 2154 | eval time = 905.44 ms / 46 tokens ( 20.12 ms per token, 49.70 tokens per second) 1.18.207.083 I slot print_timing: id 0 | task 2154 | total time = 1720.65 ms / 376 tokens 1.18.207.084 I slot print_timing: id 0 | task 2154 | graphs reused = 2013 1.18.207.085 I slot print_timing: id 0 | task 2154 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.207.114 I slot release: id 0 | task 2154 | stop processing: n_tokens = 375, truncated = 0 1.18.211.319 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 375, t_last = 387809250499 1.18.232.824 I slot launch_slot_: id 0 | task 2203 | processing task, is_child = 0 1.19.929.413 I slot print_timing: id 0 | task 2203 | prompt eval time = 810.91 ms / 341 tokens ( 2.38 ms per token, 420.52 tokens per second) 1.19.929.419 I slot print_timing: id 0 | task 2203 | eval time = 885.67 ms / 45 tokens ( 20.13 ms per token, 49.68 tokens per second) 1.19.929.420 I slot print_timing: id 0 | task 2203 | total time = 1696.58 ms / 386 tokens 1.19.929.421 I slot print_timing: id 0 | task 2203 | graphs reused = 2056 1.19.929.421 I slot print_timing: id 0 | task 2203 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.929.448 I slot release: id 0 | task 2203 | stop processing: n_tokens = 385, truncated = 0 1.19.933.686 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 385, t_last = 387810972833 1.19.956.920 I slot launch_slot_: id 0 | task 2251 | processing task, is_child = 0 1.21.824.142 I slot print_timing: id 0 | task 2251 | prompt eval time = 922.88 ms / 338 tokens ( 2.73 ms per token, 366.24 tokens per second) 1.21.824.145 I slot print_timing: id 0 | task 2251 | eval time = 944.33 ms / 48 tokens ( 20.09 ms per token, 49.77 tokens per second) 1.21.824.146 I slot print_timing: id 0 | task 2251 | total time = 1867.21 ms / 386 tokens 1.21.824.147 I slot print_timing: id 0 | task 2251 | graphs reused = 2102 1.21.824.147 I slot print_timing: id 0 | task 2251 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.824.177 I slot release: id 0 | task 2251 | stop processing: n_tokens = 385, truncated = 0 1.21.828.764 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 385, t_last = 387812867562 1.21.852.518 I slot launch_slot_: id 0 | task 2302 | processing task, is_child = 0 1.23.880.619 I slot print_timing: id 0 | task 2302 | prompt eval time = 921.26 ms / 395 tokens ( 2.33 ms per token, 428.76 tokens per second) 1.23.880.625 I slot print_timing: id 0 | task 2302 | eval time = 1106.83 ms / 56 tokens ( 20.12 ms per token, 49.69 tokens per second) 1.23.880.626 I slot print_timing: id 0 | task 2302 | total time = 2028.09 ms / 451 tokens 1.23.880.626 I slot print_timing: id 0 | task 2302 | graphs reused = 2156 1.23.880.627 I slot print_timing: id 0 | task 2302 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.880.668 I slot release: id 0 | task 2302 | stop processing: n_tokens = 450, truncated = 0 1.23.885.500 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 450, t_last = 387814924053 1.23.909.433 I slot launch_slot_: id 0 | task 2361 | processing task, is_child = 0 1.26.755.418 I slot print_timing: id 0 | task 2361 | prompt eval time = 1188.91 ms / 528 tokens ( 2.25 ms per token, 444.10 tokens per second) 1.26.755.422 I slot print_timing: id 0 | task 2361 | eval time = 1657.06 ms / 83 tokens ( 20.21 ms per token, 49.49 tokens per second) 1.26.755.422 I slot print_timing: id 0 | task 2361 | total time = 2845.97 ms / 611 tokens 1.26.755.423 I slot print_timing: id 0 | task 2361 | graphs reused = 2237 1.26.755.424 I slot print_timing: id 0 | task 2361 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.755.459 I slot release: id 0 | task 2361 | stop processing: n_tokens = 610, truncated = 0 1.26.759.668 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 610, t_last = 387817798844 1.26.759.715 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.653 MiB) 1.26.777.073 I slot launch_slot_: id 0 | task 2448 | processing task, is_child = 0 1.28.470.012 I slot print_timing: id 0 | task 2448 | prompt eval time = 807.16 ms / 331 tokens ( 2.44 ms per token, 410.08 tokens per second) 1.28.470.016 I slot print_timing: id 0 | task 2448 | eval time = 885.77 ms / 45 tokens ( 20.13 ms per token, 49.67 tokens per second) 1.28.470.016 I slot print_timing: id 0 | task 2448 | total time = 1692.93 ms / 376 tokens 1.28.470.017 I slot print_timing: id 0 | task 2448 | graphs reused = 2280 1.28.470.018 I slot print_timing: id 0 | task 2448 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.470.047 I slot release: id 0 | task 2448 | stop processing: n_tokens = 387, truncated = 0 1.28.474.580 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 387, t_last = 387819513432 1.28.474.621 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 195.538 MiB) 1.28.474.625 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.379 MiB) 1.28.481.476 I slot launch_slot_: id 0 | task 2496 | processing task, is_child = 0 1.30.383.446 I slot print_timing: id 0 | task 2496 | prompt eval time = 853.53 ms / 362 tokens ( 2.36 ms per token, 424.12 tokens per second) 1.30.383.448 I slot print_timing: id 0 | task 2496 | eval time = 1048.43 ms / 53 tokens ( 20.16 ms per token, 49.60 tokens per second) 1.30.383.449 I slot print_timing: id 0 | task 2496 | total time = 1901.96 ms / 415 tokens 1.30.383.450 I slot print_timing: id 0 | task 2496 | graphs reused = 2331 1.30.383.450 I slot print_timing: id 0 | task 2496 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.383.492 I slot release: id 0 | task 2496 | stop processing: n_tokens = 426, truncated = 0 1.30.388.091 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 387821426877 1.30.388.150 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 197.024 MiB) 1.30.394.587 I slot launch_slot_: id 0 | task 2552 | processing task, is_child = 0 1.32.732.523 I slot print_timing: id 0 | task 2552 | prompt eval time = 968.42 ms / 419 tokens ( 2.31 ms per token, 432.66 tokens per second) 1.32.732.526 I slot print_timing: id 0 | task 2552 | eval time = 1369.51 ms / 69 tokens ( 20.14 ms per token, 49.65 tokens per second) 1.32.732.526 I slot print_timing: id 0 | task 2552 | total time = 2337.93 ms / 488 tokens 1.32.732.527 I slot print_timing: id 0 | task 2552 | graphs reused = 2398 1.32.732.528 I slot print_timing: id 0 | task 2552 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.732.560 I slot release: id 0 | task 2552 | stop processing: n_tokens = 499, truncated = 0 1.32.737.028 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 499, t_last = 387823775945 1.32.737.070 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.985 MiB) 1.32.753.805 I slot launch_slot_: id 0 | task 2624 | processing task, is_child = 0 1.36.732.475 I slot print_timing: id 0 | task 2624 | n_gen = 150, tg = 49.55 t/s, tg_3s = 49.88 t/s 1.37.236.212 I slot print_timing: id 0 | task 2624 | prompt eval time = 971.56 ms / 423 tokens ( 2.30 ms per token, 435.38 tokens per second) 1.37.236.215 I slot print_timing: id 0 | task 2624 | eval time = 3510.83 ms / 175 tokens ( 20.18 ms per token, 49.56 tokens per second) 1.37.236.216 I slot print_timing: id 0 | task 2624 | total time = 4482.39 ms / 598 tokens 1.37.236.217 I slot print_timing: id 0 | task 2624 | graphs reused = 2570 1.37.236.217 I slot print_timing: id 0 | task 2624 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.236.252 I slot release: id 0 | task 2624 | stop processing: n_tokens = 609, truncated = 0 1.37.240.454 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 609, t_last = 387828279637 1.37.240.495 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.770 MiB) 1.37.240.500 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 197.748 MiB) 1.37.257.100 I slot launch_slot_: id 0 | task 2802 | processing task, is_child = 0 1.38.913.774 I slot print_timing: id 0 | task 2802 | prompt eval time = 809.72 ms / 341 tokens ( 2.37 ms per token, 421.13 tokens per second) 1.38.913.778 I slot print_timing: id 0 | task 2802 | eval time = 846.94 ms / 43 tokens ( 20.17 ms per token, 49.59 tokens per second) 1.38.913.778 I slot print_timing: id 0 | task 2802 | total time = 1656.66 ms / 384 tokens 1.38.913.779 I slot print_timing: id 0 | task 2802 | graphs reused = 2611 1.38.913.779 I slot print_timing: id 0 | task 2802 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.913.809 I slot release: id 0 | task 2802 | stop processing: n_tokens = 395, truncated = 0 1.38.918.145 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 395, t_last = 387829957194 1.38.918.215 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 199.019 MiB) 1.38.924.716 I slot launch_slot_: id 0 | task 2848 | processing task, is_child = 0 1.40.720.629 I slot print_timing: id 0 | task 2848 | prompt eval time = 868.50 ms / 356 tokens ( 2.44 ms per token, 409.90 tokens per second) 1.40.720.633 I slot print_timing: id 0 | task 2848 | eval time = 927.40 ms / 47 tokens ( 20.16 ms per token, 49.60 tokens per second) 1.40.720.634 I slot print_timing: id 0 | task 2848 | total time = 1795.90 ms / 403 tokens 1.40.720.634 I slot print_timing: id 0 | task 2848 | graphs reused = 2656 1.40.720.635 I slot print_timing: id 0 | task 2848 | graph reallocs = 0 / 0 (same size) / (changed size) 1.40.720.662 I slot release: id 0 | task 2848 | stop processing: n_tokens = 414, truncated = 0 1.40.725.028 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 387831764047 1.40.725.066 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.086 MiB) 1.40.731.537 I slot launch_slot_: id 0 | task 2898 | processing task, is_child = 0 1.42.498.571 I slot print_timing: id 0 | task 2898 | prompt eval time = 859.90 ms / 362 tokens ( 2.38 ms per token, 420.98 tokens per second) 1.42.498.575 I slot print_timing: id 0 | task 2898 | eval time = 907.11 ms / 46 tokens ( 20.16 ms per token, 49.61 tokens per second) 1.42.498.576 I slot print_timing: id 0 | task 2898 | total time = 1767.02 ms / 408 tokens 1.42.498.576 I slot print_timing: id 0 | task 2898 | graphs reused = 2700 1.42.498.577 I slot print_timing: id 0 | task 2898 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.498.605 I slot release: id 0 | task 2898 | stop processing: n_tokens = 419, truncated = 0 1.42.503.218 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 387833541990 1.42.503.256 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.340 MiB) 1.42.509.692 I slot launch_slot_: id 0 | task 2947 | processing task, is_child = 0 1.44.793.503 I slot print_timing: id 0 | task 2947 | prompt eval time = 933.91 ms / 391 tokens ( 2.39 ms per token, 418.67 tokens per second) 1.44.793.507 I slot print_timing: id 0 | task 2947 | eval time = 1349.89 ms / 68 tokens ( 20.15 ms per token, 49.63 tokens per second) 1.44.793.508 I slot print_timing: id 0 | task 2947 | total time = 2283.80 ms / 459 tokens 1.44.793.509 I slot print_timing: id 0 | task 2947 | graphs reused = 2766 1.44.793.509 I slot print_timing: id 0 | task 2947 | graph reallocs = 0 / 0 (same size) / (changed size) 1.44.793.538 I slot release: id 0 | task 2947 | stop processing: n_tokens = 470, truncated = 0 1.44.797.900 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 387835836923 1.44.797.941 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.985 MiB) 1.44.797.945 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 197.396 MiB) 1.44.804.487 I slot launch_slot_: id 0 | task 3018 | processing task, is_child = 0 1.46.729.165 I slot print_timing: id 0 | task 3018 | prompt eval time = 820.78 ms / 343 tokens ( 2.39 ms per token, 417.90 tokens per second) 1.46.729.169 I slot print_timing: id 0 | task 3018 | eval time = 1103.88 ms / 55 tokens ( 20.44 ms per token, 48.92 tokens per second) 1.46.729.169 I slot print_timing: id 0 | task 3018 | total time = 1924.66 ms / 398 tokens 1.46.729.170 I slot print_timing: id 0 | task 3018 | graphs reused = 2819 1.46.729.170 I slot print_timing: id 0 | task 3018 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.729.198 I slot release: id 0 | task 3018 | stop processing: n_tokens = 409, truncated = 0 1.46.733.763 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 387837772583 1.46.733.801 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.985 MiB) 1.46.740.264 I slot launch_slot_: id 0 | task 3076 | processing task, is_child = 0 1.48.580.337 I slot print_timing: id 0 | task 3076 | prompt eval time = 930.84 ms / 401 tokens ( 2.32 ms per token, 430.79 tokens per second) 1.48.580.341 I slot print_timing: id 0 | task 3076 | eval time = 909.22 ms / 46 tokens ( 20.20 ms per token, 49.49 tokens per second) 1.48.580.342 I slot print_timing: id 0 | task 3076 | total time = 1840.06 ms / 447 tokens 1.48.580.342 I slot print_timing: id 0 | task 3076 | graphs reused = 2863 1.48.580.343 I slot print_timing: id 0 | task 3076 | graph reallocs = 0 / 0 (same size) / (changed size) 1.48.580.380 I slot release: id 0 | task 3076 | stop processing: n_tokens = 458, truncated = 0 1.48.585.063 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 387839623765 1.48.585.100 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.829 MiB) 1.48.591.594 I slot launch_slot_: id 0 | task 3125 | processing task, is_child = 0 1.50.783.161 I slot print_timing: id 0 | task 3125 | prompt eval time = 841.27 ms / 355 tokens ( 2.37 ms per token, 421.98 tokens per second) 1.50.783.165 I slot print_timing: id 0 | task 3125 | eval time = 1350.28 ms / 68 tokens ( 20.15 ms per token, 49.62 tokens per second) 1.50.783.167 I slot print_timing: id 0 | task 3125 | total time = 2191.56 ms / 423 tokens 1.50.783.167 I slot print_timing: id 0 | task 3125 | graphs reused = 2929 1.50.783.168 I slot print_timing: id 0 | task 3125 | graph reallocs = 0 / 0 (same size) / (changed size) 1.50.783.195 I slot release: id 0 | task 3125 | stop processing: n_tokens = 434, truncated = 0 1.50.787.634 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 434, t_last = 387841826580 1.50.787.673 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.731 MiB) 1.50.787.683 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.203 MiB) 1.50.794.175 I slot launch_slot_: id 0 | task 3196 | processing task, is_child = 0 1.52.802.407 I slot print_timing: id 0 | task 3196 | prompt eval time = 863.73 ms / 351 tokens ( 2.46 ms per token, 406.38 tokens per second) 1.52.802.414 I slot print_timing: id 0 | task 3196 | eval time = 1144.49 ms / 57 tokens ( 20.44 ms per token, 48.93 tokens per second) 1.52.802.415 I slot print_timing: id 0 | task 3196 | total time = 2008.22 ms / 408 tokens 1.52.802.415 I slot print_timing: id 0 | task 3196 | graphs reused = 2984 1.52.802.416 I slot print_timing: id 0 | task 3196 | graph reallocs = 0 / 0 (same size) / (changed size) 1.52.802.442 I slot release: id 0 | task 3196 | stop processing: n_tokens = 419, truncated = 0 1.52.807.259 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 387843845827 1.52.807.295 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.692 MiB) 1.52.813.734 I slot launch_slot_: id 0 | task 3256 | processing task, is_child = 0 1.55.721.683 I slot print_timing: id 0 | task 3256 | prompt eval time = 1041.70 ms / 475 tokens ( 2.19 ms per token, 455.99 tokens per second) 1.55.721.686 I slot print_timing: id 0 | task 3256 | eval time = 1866.24 ms / 93 tokens ( 20.29 ms per token, 49.30 tokens per second) 1.55.721.687 I slot print_timing: id 0 | task 3256 | total time = 2907.94 ms / 568 tokens 1.55.721.688 I slot print_timing: id 0 | task 3256 | graphs reused = 3074 1.55.721.688 I slot print_timing: id 0 | task 3256 | graph reallocs = 0 / 0 (same size) / (changed size) 1.55.721.725 I slot release: id 0 | task 3256 | stop processing: n_tokens = 579, truncated = 0 1.55.726.402 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 579, t_last = 387846765110 1.55.726.445 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.105 MiB) 1.55.743.096 I slot launch_slot_: id 0 | task 3352 | processing task, is_child = 0 1.58.576.361 I slot print_timing: id 0 | task 3352 | prompt eval time = 994.64 ms / 440 tokens ( 2.26 ms per token, 442.37 tokens per second) 1.58.576.367 I slot print_timing: id 0 | task 3352 | eval time = 1838.61 ms / 92 tokens ( 20.20 ms per token, 49.49 tokens per second) 1.58.576.368 I slot print_timing: id 0 | task 3352 | total time = 2833.25 ms / 532 tokens 1.58.576.369 I slot print_timing: id 0 | task 3352 | graphs reused = 3163 1.58.576.369 I slot print_timing: id 0 | task 3352 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.576.401 I slot release: id 0 | task 3352 | stop processing: n_tokens = 543, truncated = 0 1.58.580.801 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 543, t_last = 387849619786 1.58.580.846 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.027 MiB) 1.58.580.853 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 197.161 MiB) 1.58.596.575 I slot launch_slot_: id 0 | task 3447 | processing task, is_child = 0 2.00.517.716 I slot print_timing: id 0 | task 3447 | prompt eval time = 832.65 ms / 345 tokens ( 2.41 ms per token, 414.34 tokens per second) 2.00.517.719 I slot print_timing: id 0 | task 3447 | eval time = 1088.48 ms / 55 tokens ( 20.16 ms per token, 49.61 tokens per second) 2.00.517.720 I slot print_timing: id 0 | task 3447 | total time = 1921.13 ms / 400 tokens 2.00.517.721 I slot print_timing: id 0 | task 3447 | graphs reused = 3216 2.00.517.721 I slot print_timing: id 0 | task 3447 | graph reallocs = 0 / 0 (same size) / (changed size) 2.00.517.748 I slot release: id 0 | task 3447 | stop processing: n_tokens = 411, truncated = 0 2.00.522.288 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 387851561133 2.00.522.357 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.438 MiB) 2.00.528.850 I slot launch_slot_: id 0 | task 3505 | processing task, is_child = 0 2.02.526.050 I slot print_timing: id 0 | task 3505 | prompt eval time = 908.12 ms / 382 tokens ( 2.38 ms per token, 420.65 tokens per second) 2.02.526.054 I slot print_timing: id 0 | task 3505 | eval time = 1089.07 ms / 55 tokens ( 20.17 ms per token, 49.58 tokens per second) 2.02.526.055 I slot print_timing: id 0 | task 3505 | total time = 1997.19 ms / 437 tokens 2.02.526.055 I slot print_timing: id 0 | task 3505 | graphs reused = 3269 2.02.526.056 I slot print_timing: id 0 | task 3505 | graph reallocs = 0 / 0 (same size) / (changed size) 2.02.526.095 I slot release: id 0 | task 3505 | stop processing: n_tokens = 448, truncated = 0 2.02.530.465 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 387853569480 2.02.530.499 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 197.806 MiB) 2.02.537.207 I slot launch_slot_: id 0 | task 3563 | processing task, is_child = 0 2.04.248.066 I slot print_timing: id 0 | task 3563 | prompt eval time = 822.70 ms / 337 tokens ( 2.44 ms per token, 409.63 tokens per second) 2.04.248.069 I slot print_timing: id 0 | task 3563 | eval time = 888.15 ms / 45 tokens ( 20.19 ms per token, 49.54 tokens per second) 2.04.248.071 I slot print_timing: id 0 | task 3563 | total time = 1710.85 ms / 382 tokens 2.04.248.071 I slot print_timing: id 0 | task 3563 | graphs reused = 3312 2.04.248.072 I slot print_timing: id 0 | task 3563 | graph reallocs = 0 / 0 (same size) / (changed size) 2.04.248.098 I slot release: id 0 | task 3563 | stop processing: n_tokens = 393, truncated = 0 2.04.252.763 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 387855291483 2.04.252.801 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 197.083 MiB) 2.04.252.808 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 197.533 MiB) 2.04.259.209 I slot launch_slot_: id 0 | task 3611 | processing task, is_child = 0 2.06.594.477 I slot print_timing: id 0 | task 3611 | prompt eval time = 925.08 ms / 402 tokens ( 2.30 ms per token, 434.56 tokens per second) 2.06.594.481 I slot print_timing: id 0 | task 3611 | eval time = 1410.17 ms / 70 tokens ( 20.44 ms per token, 48.93 tokens per second) 2.06.594.482 I slot print_timing: id 0 | task 3611 | total time = 2335.25 ms / 472 tokens 2.06.594.483 I slot print_timing: id 0 | task 3611 | graphs reused = 3380 2.06.594.483 I slot print_timing: id 0 | task 3611 | graph reallocs = 0 / 0 (same size) / (changed size) 2.06.594.519 I slot release: id 0 | task 3611 | stop processing: n_tokens = 483, truncated = 0 2.06.599.475 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 483, t_last = 387857637904 2.06.599.509 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 198.041 MiB) 2.06.605.905 I slot launch_slot_: id 0 | task 3684 | processing task, is_child = 0 2.09.037.308 I slot print_timing: id 0 | task 3684 | prompt eval time = 1297.47 ms / 549 tokens ( 2.36 ms per token, 423.13 tokens per second) 2.09.037.312 I slot print_timing: id 0 | task 3684 | eval time = 1133.92 ms / 57 tokens ( 20.25 ms per token, 49.39 tokens per second) 2.09.037.312 I slot print_timing: id 0 | task 3684 | total time = 2431.39 ms / 606 tokens 2.09.037.313 I slot print_timing: id 0 | task 3684 | graphs reused = 3435 2.09.037.314 I slot print_timing: id 0 | task 3684 | graph reallocs = 0 / 0 (same size) / (changed size) 2.09.037.353 I slot release: id 0 | task 3684 | stop processing: n_tokens = 617, truncated = 0 2.09.042.483 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 617, t_last = 387860080738 2.09.042.530 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 197.298 MiB) 2.09.042.533 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.222 MiB) 2.09.060.714 I slot launch_slot_: id 0 | task 3745 | processing task, is_child = 0 2.11.668.506 I slot print_timing: id 0 | task 3745 | prompt eval time = 1451.46 ms / 616 tokens ( 2.36 ms per token, 424.40 tokens per second) 2.11.668.510 I slot print_timing: id 0 | task 3745 | eval time = 1156.31 ms / 58 tokens ( 20.29 ms per token, 49.29 tokens per second) 2.11.668.510 I slot print_timing: id 0 | task 3745 | total time = 2607.78 ms / 674 tokens 2.11.668.511 I slot print_timing: id 0 | task 3745 | graphs reused = 3491 2.11.668.511 I slot print_timing: id 0 | task 3745 | graph reallocs = 0 / 0 (same size) / (changed size) 2.11.668.556 I slot release: id 0 | task 3745 | stop processing: n_tokens = 685, truncated = 0 2.11.674.118 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 685, t_last = 387862711941 2.11.674.203 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 197.044 MiB) 2.11.692.350 I slot launch_slot_: id 0 | task 3807 | processing task, is_child = 0 2.14.412.171 I slot print_timing: id 0 | task 3807 | prompt eval time = 1504.49 ms / 665 tokens ( 2.26 ms per token, 442.01 tokens per second) 2.14.412.174 I slot print_timing: id 0 | task 3807 | eval time = 1215.32 ms / 61 tokens ( 20.26 ms per token, 49.37 tokens per second) 2.14.412.175 I slot print_timing: id 0 | task 3807 | total time = 2719.81 ms / 726 tokens 2.14.412.176 I slot print_timing: id 0 | task 3807 | graphs reused = 3550 2.14.412.176 I slot print_timing: id 0 | task 3807 | graph reallocs = 0 / 0 (same size) / (changed size) 2.14.412.215 I slot release: id 0 | task 3807 | stop processing: n_tokens = 737, truncated = 0 2.14.417.531 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 737, t_last = 387865455600 2.14.417.579 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 198.002 MiB) 2.14.417.586 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 197.317 MiB) 2.14.447.550 I slot launch_slot_: id 0 | task 3872 | processing task, is_child = 0 2.17.033.523 I slot print_timing: id 0 | task 3872 | prompt eval time = 1489.81 ms / 645 tokens ( 2.31 ms per token, 432.94 tokens per second) 2.17.033.527 I slot print_timing: id 0 | task 3872 | eval time = 1096.15 ms / 55 tokens ( 20.30 ms per token, 49.26 tokens per second) 2.17.033.527 I slot print_timing: id 0 | task 3872 | total time = 2585.96 ms / 700 tokens 2.17.033.528 I slot print_timing: id 0 | task 3872 | graphs reused = 3603 2.17.033.528 I slot print_timing: id 0 | task 3872 | graph reallocs = 0 / 0 (same size) / (changed size) 2.17.033.578 I slot release: id 0 | task 3872 | stop processing: n_tokens = 711, truncated = 0 2.17.038.559 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 711, t_last = 387868076963 2.17.038.622 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.574 MiB) 2.17.038.626 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.535 MiB) 2.17.123.057 I slot launch_slot_: id 0 | task 3931 | processing task, is_child = 0 2.19.193.995 I slot print_timing: id 0 | task 3931 | prompt eval time = 1037.23 ms / 474 tokens ( 2.19 ms per token, 456.99 tokens per second) 2.19.194.000 I slot print_timing: id 0 | task 3931 | eval time = 1033.69 ms / 52 tokens ( 20.27 ms per token, 49.34 tokens per second) 2.19.194.001 I slot print_timing: id 0 | task 3931 | total time = 2070.92 ms / 526 tokens 2.19.194.001 I slot print_timing: id 0 | task 3931 | graphs reused = 3652 2.19.194.002 I slot print_timing: id 0 | task 3931 | graph reallocs = 0 / 0 (same size) / (changed size) 2.19.194.035 I slot release: id 0 | task 3931 | stop processing: n_tokens = 537, truncated = 0 2.19.199.280 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 537, t_last = 387870237420 2.19.199.324 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 197.181 MiB) 2.19.252.622 I slot launch_slot_: id 0 | task 3986 | processing task, is_child = 0 2.21.517.354 I slot print_timing: id 0 | task 3986 | prompt eval time = 1433.90 ms / 617 tokens ( 2.32 ms per token, 430.29 tokens per second) 2.21.517.360 I slot print_timing: id 0 | task 3986 | eval time = 830.82 ms / 42 tokens ( 20.26 ms per token, 49.35 tokens per second) 2.21.517.360 I slot print_timing: id 0 | task 3986 | total time = 2264.72 ms / 659 tokens 2.21.517.361 I slot print_timing: id 0 | task 3986 | graphs reused = 3692 2.21.517.362 I slot print_timing: id 0 | task 3986 | graph reallocs = 0 / 0 (same size) / (changed size) 2.21.517.398 I slot release: id 0 | task 3986 | stop processing: n_tokens = 670, truncated = 0 2.21.522.417 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 670, t_last = 387872560783 2.21.522.467 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 197.630 MiB) 2.21.522.471 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.262 MiB) 2.21.609.272 I slot launch_slot_: id 0 | task 4032 | processing task, is_child = 0 2.23.899.262 I slot print_timing: id 0 | task 4032 | prompt eval time = 1380.62 ms / 601 tokens ( 2.30 ms per token, 435.31 tokens per second) 2.23.899.268 I slot print_timing: id 0 | task 4032 | eval time = 909.35 ms / 48 tokens ( 19.35 ms per token, 51.69 tokens per second) 2.23.899.268 I slot print_timing: id 0 | task 4032 | total time = 2289.97 ms / 649 tokens 2.23.899.269 I slot print_timing: id 0 | task 4032 | graphs reused = 3738 2.23.899.269 I slot print_timing: id 0 | task 4032 | graph reallocs = 0 / 0 (same size) / (changed size) 2.23.899.306 I slot release: id 0 | task 4032 | stop processing: n_tokens = 660, truncated = 0 2.23.903.483 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 660, t_last = 387874942691 2.23.903.523 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 197.200 MiB) 2.23.942.850 I slot launch_slot_: id 0 | task 4084 | processing task, is_child = 0 2.26.008.543 I slot print_timing: id 0 | task 4084 | prompt eval time = 1173.29 ms / 533 tokens ( 2.20 ms per token, 454.28 tokens per second) 2.26.008.545 I slot print_timing: id 0 | task 4084 | eval time = 892.38 ms / 47 tokens ( 19.40 ms per token, 51.55 tokens per second) 2.26.008.547 I slot print_timing: id 0 | task 4084 | total time = 2065.68 ms / 580 tokens 2.26.008.547 I slot print_timing: id 0 | task 4084 | graphs reused = 3783 2.26.008.548 I slot print_timing: id 0 | task 4084 | graph reallocs = 0 / 0 (same size) / (changed size) 2.26.008.583 I slot release: id 0 | task 4084 | stop processing: n_tokens = 591, truncated = 0 2.26.012.683 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 591, t_last = 387877051968 2.26.012.716 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 195.284 MiB) 2.26.012.719 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 195.773 MiB) 2.26.075.138 I slot launch_slot_: id 0 | task 4135 | processing task, is_child = 0 2.28.073.849 I slot print_timing: id 0 | task 4135 | prompt eval time = 1007.82 ms / 480 tokens ( 2.10 ms per token, 476.28 tokens per second) 2.28.073.851 I slot print_timing: id 0 | task 4135 | eval time = 990.88 ms / 52 tokens ( 19.43 ms per token, 51.47 tokens per second) 2.28.073.851 I slot print_timing: id 0 | task 4135 | total time = 1998.70 ms / 532 tokens 2.28.073.852 I slot print_timing: id 0 | task 4135 | graphs reused = 3832 2.28.073.852 I slot print_timing: id 0 | task 4135 | graph reallocs = 0 / 0 (same size) / (changed size) 2.28.073.884 I slot release: id 0 | task 4135 | stop processing: n_tokens = 560, truncated = 0 2.28.078.281 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 387879117269 2.28.078.315 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 195.968 MiB) 2.28.078.336 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 195.968 MiB) 2.28.137.043 I slot launch_slot_: id 0 | task 4190 | processing task, is_child = 0 2.30.198.839 I slot print_timing: id 0 | task 4190 | prompt eval time = 1268.88 ms / 567 tokens ( 2.24 ms per token, 446.85 tokens per second) 2.30.198.844 I slot print_timing: id 0 | task 4190 | eval time = 792.91 ms / 42 tokens ( 19.34 ms per token, 51.71 tokens per second) 2.30.198.845 I slot print_timing: id 0 | task 4190 | total time = 2061.78 ms / 609 tokens 2.30.198.845 I slot print_timing: id 0 | task 4190 | graphs reused = 3872 2.30.198.846 I slot print_timing: id 0 | task 4190 | graph reallocs = 0 / 0 (same size) / (changed size) 2.30.198.884 I slot release: id 0 | task 4190 | stop processing: n_tokens = 637, truncated = 0 2.30.203.076 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 387881242269 2.30.203.114 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 197.239 MiB) 2.30.203.128 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 263.181 MiB) 2.30.255.342 I slot launch_slot_: id 0 | task 4236 | processing task, is_child = 0 2.32.488.453 I slot print_timing: id 0 | task 4236 | prompt eval time = 1031.66 ms / 506 tokens ( 2.04 ms per token, 490.47 tokens per second) 2.32.488.455 I slot print_timing: id 0 | task 4236 | eval time = 1201.43 ms / 63 tokens ( 19.38 ms per token, 51.61 tokens per second) 2.32.488.456 I slot print_timing: id 0 | task 4236 | total time = 2233.09 ms / 569 tokens 2.32.488.456 I slot print_timing: id 0 | task 4236 | graphs reused = 3933 2.32.488.457 I slot print_timing: id 0 | task 4236 | graph reallocs = 0 / 0 (same size) / (changed size) 2.32.488.491 I slot release: id 0 | task 4236 | stop processing: n_tokens = 597, truncated = 0 2.32.492.582 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 597, t_last = 387883531876 2.32.492.617 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 258.821 MiB) 2.32.501.687 I slot launch_slot_: id 0 | task 4302 | processing task, is_child = 0 2.34.181.772 I slot print_timing: id 0 | task 4302 | prompt eval time = 925.92 ms / 436 tokens ( 2.12 ms per token, 470.88 tokens per second) 2.34.181.777 I slot print_timing: id 0 | task 4302 | eval time = 754.15 ms / 40 tokens ( 19.34 ms per token, 51.71 tokens per second) 2.34.181.777 I slot print_timing: id 0 | task 4302 | total time = 1680.08 ms / 476 tokens 2.34.181.778 I slot print_timing: id 0 | task 4302 | graphs reused = 3971 2.34.181.778 I slot print_timing: id 0 | task 4302 | graph reallocs = 0 / 0 (same size) / (changed size) 2.34.181.809 I slot release: id 0 | task 4302 | stop processing: n_tokens = 504, truncated = 0 2.34.186.014 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 387885225194 2.34.186.046 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 259.583 MiB) 2.34.214.649 I slot launch_slot_: id 0 | task 4345 | processing task, is_child = 0 2.36.487.573 I slot print_timing: id 0 | task 4345 | prompt eval time = 1093.88 ms / 519 tokens ( 2.11 ms per token, 474.46 tokens per second) 2.36.487.576 I slot print_timing: id 0 | task 4345 | eval time = 1179.04 ms / 62 tokens ( 19.33 ms per token, 51.74 tokens per second) 2.36.487.576 I slot print_timing: id 0 | task 4345 | total time = 2272.91 ms / 581 tokens 2.36.487.577 I slot print_timing: id 0 | task 4345 | graphs reused = 4031 2.36.487.577 I slot print_timing: id 0 | task 4345 | graph reallocs = 0 / 0 (same size) / (changed size) 2.36.487.615 I slot release: id 0 | task 4345 | stop processing: n_tokens = 609, truncated = 0 2.36.491.570 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 609, t_last = 387887531000 2.36.491.608 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 261.011 MiB) 2.36.491.616 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 263.162 MiB) 2.36.529.477 I slot launch_slot_: id 0 | task 4411 | processing task, is_child = 0 2.38.365.518 I slot print_timing: id 0 | task 4411 | prompt eval time = 963.88 ms / 465 tokens ( 2.07 ms per token, 482.43 tokens per second) 2.38.365.523 I slot print_timing: id 0 | task 4411 | eval time = 872.15 ms / 46 tokens ( 19.38 ms per token, 51.60 tokens per second) 2.38.365.524 I slot print_timing: id 0 | task 4411 | total time = 1836.03 ms / 511 tokens 2.38.365.524 I slot print_timing: id 0 | task 4411 | graphs reused = 4074 2.38.365.525 I slot print_timing: id 0 | task 4411 | graph reallocs = 0 / 0 (same size) / (changed size) 2.38.365.552 I slot release: id 0 | task 4411 | stop processing: n_tokens = 542, truncated = 0 2.38.369.479 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 542, t_last = 387889408937 2.38.369.513 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 258.977 MiB) 2.38.413.455 I slot launch_slot_: id 0 | task 4460 | processing task, is_child = 0 2.40.118.058 I slot print_timing: id 0 | task 4460 | prompt eval time = 933.80 ms / 431 tokens ( 2.17 ms per token, 461.55 tokens per second) 2.40.118.060 I slot print_timing: id 0 | task 4460 | eval time = 770.79 ms / 41 tokens ( 19.27 ms per token, 51.89 tokens per second) 2.40.118.061 I slot print_timing: id 0 | task 4460 | total time = 1704.59 ms / 472 tokens 2.40.118.061 I slot print_timing: id 0 | task 4460 | graphs reused = 4113 2.40.118.062 I slot print_timing: id 0 | task 4460 | graph reallocs = 0 / 0 (same size) / (changed size) 2.40.118.096 I slot release: id 0 | task 4460 | stop processing: n_tokens = 503, truncated = 0 2.40.122.192 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 503, t_last = 387891161481 2.40.122.228 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 259.349 MiB) 2.40.122.248 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 259.446 MiB) 2.40.193.317 I slot launch_slot_: id 0 | task 4504 | processing task, is_child = 0 2.41.991.272 I slot print_timing: id 0 | task 4504 | prompt eval time = 964.15 ms / 457 tokens ( 2.11 ms per token, 473.99 tokens per second) 2.41.991.274 I slot print_timing: id 0 | task 4504 | eval time = 833.79 ms / 44 tokens ( 19.39 ms per token, 51.57 tokens per second) 2.41.991.274 I slot print_timing: id 0 | task 4504 | total time = 1797.94 ms / 501 tokens 2.41.991.275 I slot print_timing: id 0 | task 4504 | graphs reused = 4154 2.41.991.275 I slot print_timing: id 0 | task 4504 | graph reallocs = 0 / 0 (same size) / (changed size) 2.41.991.306 I slot release: id 0 | task 4504 | stop processing: n_tokens = 532, truncated = 0 2.41.995.170 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 532, t_last = 387893034691 2.41.995.204 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 260.444 MiB) 2.42.059.296 I slot launch_slot_: id 0 | task 4551 | processing task, is_child = 0 2.43.795.799 I slot print_timing: id 0 | task 4551 | prompt eval time = 945.65 ms / 439 tokens ( 2.15 ms per token, 464.23 tokens per second) 2.43.795.804 I slot print_timing: id 0 | task 4551 | eval time = 790.84 ms / 42 tokens ( 19.29 ms per token, 51.84 tokens per second) 2.43.795.804 I slot print_timing: id 0 | task 4551 | total time = 1736.49 ms / 481 tokens 2.43.795.805 I slot print_timing: id 0 | task 4551 | graphs reused = 4194 2.43.795.805 I slot print_timing: id 0 | task 4551 | graph reallocs = 0 / 0 (same size) / (changed size) 2.43.795.840 I slot release: id 0 | task 4551 | stop processing: n_tokens = 512, truncated = 0 2.43.800.085 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 512, t_last = 387894839225 2.43.800.114 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 259.251 MiB) 2.43.800.136 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 260.209 MiB) 2.43.873.560 I slot launch_slot_: id 0 | task 4596 | processing task, is_child = 0 2.46.305.249 I slot print_timing: id 0 | task 4596 | prompt eval time = 1368.73 ms / 606 tokens ( 2.26 ms per token, 442.75 tokens per second) 2.46.305.254 I slot print_timing: id 0 | task 4596 | eval time = 1062.95 ms / 56 tokens ( 19.33 ms per token, 51.74 tokens per second) 2.46.305.255 I slot print_timing: id 0 | task 4596 | total time = 2431.68 ms / 662 tokens 2.46.305.255 I slot print_timing: id 0 | task 4596 | graphs reused = 4248 2.46.305.256 I slot print_timing: id 0 | task 4596 | graph reallocs = 0 / 0 (same size) / (changed size) 2.46.305.344 I slot release: id 0 | task 4596 | stop processing: n_tokens = 693, truncated = 0 2.46.309.898 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 387897348729 2.46.309.934 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 259.740 MiB) 2.46.392.320 I slot launch_slot_: id 0 | task 4656 | processing task, is_child = 0 2.48.190.774 I slot print_timing: id 0 | task 4656 | prompt eval time = 1022.47 ms / 477 tokens ( 2.14 ms per token, 466.52 tokens per second) 2.48.190.781 I slot print_timing: id 0 | task 4656 | eval time = 775.97 ms / 41 tokens ( 19.40 ms per token, 51.55 tokens per second) 2.48.190.782 I slot print_timing: id 0 | task 4656 | total time = 1798.43 ms / 518 tokens 2.48.190.782 I slot print_timing: id 0 | task 4656 | graphs reused = 4286 2.48.190.783 I slot print_timing: id 0 | task 4656 | graph reallocs = 0 / 0 (same size) / (changed size) 2.48.190.862 I slot release: id 0 | task 4656 | stop processing: n_tokens = 549, truncated = 0 2.48.196.747 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 387899234247 2.48.196.783 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 259.446 MiB) 2.48.196.803 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 262.575 MiB) 2.48.259.418 I slot launch_slot_: id 0 | task 4700 | processing task, is_child = 0 2.51.178.903 I slot print_timing: id 0 | task 4700 | prompt eval time = 1757.84 ms / 845 tokens ( 2.08 ms per token, 480.70 tokens per second) 2.51.178.906 I slot print_timing: id 0 | task 4700 | eval time = 1161.62 ms / 61 tokens ( 19.36 ms per token, 51.65 tokens per second) 2.51.178.907 I slot print_timing: id 0 | task 4700 | total time = 2919.47 ms / 906 tokens 2.51.178.907 I slot print_timing: id 0 | task 4700 | graphs reused = 4345 2.51.178.908 I slot print_timing: id 0 | task 4700 | graph reallocs = 0 / 0 (same size) / (changed size) 2.51.178.990 I slot release: id 0 | task 4700 | stop processing: n_tokens = 937, truncated = 0 2.51.183.315 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 937, t_last = 387902222375 2.51.183.358 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 261.871 MiB) 2.51.256.517 I slot launch_slot_: id 0 | task 4765 | processing task, is_child = 0 2.53.079.481 I slot print_timing: id 0 | task 4765 | prompt eval time = 1010.01 ms / 459 tokens ( 2.20 ms per token, 454.45 tokens per second) 2.53.079.484 I slot print_timing: id 0 | task 4765 | eval time = 812.94 ms / 43 tokens ( 19.36 ms per token, 51.66 tokens per second) 2.53.079.485 I slot print_timing: id 0 | task 4765 | total time = 1822.95 ms / 502 tokens 2.53.079.486 I slot print_timing: id 0 | task 4765 | graphs reused = 4385 2.53.079.486 I slot print_timing: id 0 | task 4765 | graph reallocs = 0 / 0 (same size) / (changed size) 2.53.079.530 I slot release: id 0 | task 4765 | stop processing: n_tokens = 533, truncated = 0 2.53.084.106 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 533, t_last = 387904122915 2.53.084.136 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 259.290 MiB) 2.53.084.152 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 260.013 MiB) 2.53.143.270 I slot launch_slot_: id 0 | task 4811 | processing task, is_child = 0 2.55.507.207 I slot print_timing: id 0 | task 4811 | prompt eval time = 1473.17 ms / 670 tokens ( 2.20 ms per token, 454.80 tokens per second) 2.55.507.210 I slot print_timing: id 0 | task 4811 | eval time = 890.75 ms / 47 tokens ( 19.36 ms per token, 51.64 tokens per second) 2.55.507.211 I slot print_timing: id 0 | task 4811 | total time = 2363.92 ms / 717 tokens 2.55.507.211 I slot print_timing: id 0 | task 4811 | graphs reused = 4430 2.55.507.211 I slot print_timing: id 0 | task 4811 | graph reallocs = 0 / 0 (same size) / (changed size) 2.55.507.302 I slot release: id 0 | task 4811 | stop processing: n_tokens = 748, truncated = 0 2.55.512.462 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 748, t_last = 387906550687 2.55.512.498 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 258.938 MiB) 2.55.512.514 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 260.698 MiB) 2.55.589.909 I slot launch_slot_: id 0 | task 4862 | processing task, is_child = 0 2.58.446.010 I slot print_timing: id 0 | task 4862 | prompt eval time = 1630.74 ms / 775 tokens ( 2.10 ms per token, 475.24 tokens per second) 2.58.446.016 I slot print_timing: id 0 | task 4862 | eval time = 1225.34 ms / 63 tokens ( 19.76 ms per token, 50.60 tokens per second) 2.58.446.016 I slot print_timing: id 0 | task 4862 | total time = 2856.09 ms / 838 tokens 2.58.446.017 I slot print_timing: id 0 | task 4862 | graphs reused = 4491 2.58.446.017 I slot print_timing: id 0 | task 4862 | graph reallocs = 0 / 0 (same size) / (changed size) 2.58.446.129 I slot release: id 0 | task 4862 | stop processing: n_tokens = 869, truncated = 0 2.58.450.665 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 869, t_last = 387909489514 2.58.450.705 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 326.131 MiB) 2.58.523.818 I slot launch_slot_: id 0 | task 4929 | processing task, is_child = 0 3.01.174.046 I slot print_timing: id 0 | task 4929 | prompt eval time = 1296.47 ms / 573 tokens ( 2.26 ms per token, 441.97 tokens per second) 3.01.174.050 I slot print_timing: id 0 | task 4929 | eval time = 1353.74 ms / 71 tokens ( 19.34 ms per token, 51.71 tokens per second) 3.01.174.050 I slot print_timing: id 0 | task 4929 | total time = 2650.21 ms / 644 tokens 3.01.174.051 I slot print_timing: id 0 | task 4929 | graphs reused = 4560 3.01.174.051 I slot print_timing: id 0 | task 4929 | graph reallocs = 0 / 0 (same size) / (changed size) 3.01.174.133 I slot release: id 0 | task 4929 | stop processing: n_tokens = 675, truncated = 0 3.01.178.438 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 675, t_last = 387912217518 3.01.178.472 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 327.461 MiB) 3.01.178.486 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.478 MiB) 3.01.216.816 I slot launch_slot_: id 0 | task 5004 | processing task, is_child = 0 3.03.437.521 I slot print_timing: id 0 | task 5004 | prompt eval time = 1001.88 ms / 461 tokens ( 2.17 ms per token, 460.13 tokens per second) 3.03.437.535 I slot print_timing: id 0 | task 5004 | eval time = 1218.81 ms / 64 tokens ( 19.35 ms per token, 51.69 tokens per second) 3.03.437.542 I slot print_timing: id 0 | task 5004 | total time = 2220.69 ms / 525 tokens 3.03.437.543 I slot print_timing: id 0 | task 5004 | graphs reused = 4621 3.03.437.543 I slot print_timing: id 0 | task 5004 | graph reallocs = 0 / 0 (same size) / (changed size) 3.03.437.583 I slot release: id 0 | task 5004 | stop processing: n_tokens = 556, truncated = 0 3.03.442.255 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 556, t_last = 387914480968 3.03.442.286 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 327.969 MiB) 3.03.492.337 I slot launch_slot_: id 0 | task 5071 | processing task, is_child = 0 3.05.664.033 I slot print_timing: id 0 | task 5071 | prompt eval time = 1345.48 ms / 609 tokens ( 2.21 ms per token, 452.63 tokens per second) 3.05.664.038 I slot print_timing: id 0 | task 5071 | eval time = 826.19 ms / 43 tokens ( 19.67 ms per token, 50.84 tokens per second) 3.05.664.038 I slot print_timing: id 0 | task 5071 | total time = 2171.68 ms / 652 tokens 3.05.664.039 I slot print_timing: id 0 | task 5071 | graphs reused = 4662 3.05.664.039 I slot print_timing: id 0 | task 5071 | graph reallocs = 0 / 0 (same size) / (changed size) 3.05.664.097 I slot release: id 0 | task 5071 | stop processing: n_tokens = 683, truncated = 0 3.05.668.966 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 683, t_last = 387916707482 3.05.669.000 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 261.754 MiB) 3.05.730.909 I slot launch_slot_: id 0 | task 5118 | processing task, is_child = 0 3.08.540.537 I slot print_timing: id 0 | task 5118 | prompt eval time = 1648.72 ms / 791 tokens ( 2.08 ms per token, 479.76 tokens per second) 3.08.540.539 I slot print_timing: id 0 | task 5118 | eval time = 1160.89 ms / 61 tokens ( 19.35 ms per token, 51.68 tokens per second) 3.08.540.540 I slot print_timing: id 0 | task 5118 | total time = 2809.61 ms / 852 tokens 3.08.540.541 I slot print_timing: id 0 | task 5118 | graphs reused = 4721 3.08.540.541 I slot print_timing: id 0 | task 5118 | graph reallocs = 0 / 0 (same size) / (changed size) 3.08.540.625 I slot release: id 0 | task 5118 | stop processing: n_tokens = 883, truncated = 0 3.08.545.138 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 883, t_last = 387919584010 3.08.545.178 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 327.168 MiB) 3.08.545.182 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 326.972 MiB) 3.08.627.832 I slot launch_slot_: id 0 | task 5183 | processing task, is_child = 0 3.10.870.191 I slot print_timing: id 0 | task 5183 | prompt eval time = 1177.85 ms / 533 tokens ( 2.21 ms per token, 452.52 tokens per second) 3.10.870.193 I slot print_timing: id 0 | task 5183 | eval time = 1064.49 ms / 56 tokens ( 19.35 ms per token, 51.67 tokens per second) 3.10.870.194 I slot print_timing: id 0 | task 5183 | total time = 2242.35 ms / 589 tokens 3.10.870.194 I slot print_timing: id 0 | task 5183 | graphs reused = 4775 3.10.870.194 I slot print_timing: id 0 | task 5183 | graph reallocs = 0 / 0 (same size) / (changed size) 3.10.870.262 I slot release: id 0 | task 5183 | stop processing: n_tokens = 677, truncated = 0 3.10.874.809 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 677, t_last = 387921913647 3.10.891.732 I slot launch_slot_: id 0 | task 5243 | processing task, is_child = 0 3.13.073.573 I slot print_timing: id 0 | task 5243 | prompt eval time = 1295.80 ms / 566 tokens ( 2.29 ms per token, 436.80 tokens per second) 3.13.073.578 I slot print_timing: id 0 | task 5243 | eval time = 886.03 ms / 46 tokens ( 19.69 ms per token, 50.79 tokens per second) 3.13.073.579 I slot print_timing: id 0 | task 5243 | total time = 2181.83 ms / 612 tokens 3.13.073.579 I slot print_timing: id 0 | task 5243 | graphs reused = 4819 3.13.073.580 I slot print_timing: id 0 | task 5243 | graph reallocs = 0 / 0 (same size) / (changed size) 3.13.073.631 I slot release: id 0 | task 5243 | stop processing: n_tokens = 643, truncated = 0 3.13.078.053 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 643, t_last = 387924117016 3.13.078.088 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.623 MiB) 3.13.140.390 I slot launch_slot_: id 0 | task 5293 | processing task, is_child = 0 3.14.902.853 I slot print_timing: id 0 | task 5293 | prompt eval time = 949.72 ms / 443 tokens ( 2.14 ms per token, 466.46 tokens per second) 3.14.902.855 I slot print_timing: id 0 | task 5293 | eval time = 812.74 ms / 43 tokens ( 19.35 ms per token, 51.68 tokens per second) 3.14.902.856 I slot print_timing: id 0 | task 5293 | total time = 1762.45 ms / 486 tokens 3.14.902.856 I slot print_timing: id 0 | task 5293 | graphs reused = 4859 3.14.902.857 I slot print_timing: id 0 | task 5293 | graph reallocs = 0 / 0 (same size) / (changed size) 3.14.902.898 I slot release: id 0 | task 5293 | stop processing: n_tokens = 517, truncated = 0 3.14.906.917 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 517, t_last = 387925946284 3.14.906.947 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.017 MiB) 3.14.906.951 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 389.336 MiB) 3.14.969.993 I slot launch_slot_: id 0 | task 5339 | processing task, is_child = 0 3.17.238.925 I slot print_timing: id 0 | task 5339 | prompt eval time = 1033.58 ms / 487 tokens ( 2.12 ms per token, 471.18 tokens per second) 3.17.238.929 I slot print_timing: id 0 | task 5339 | eval time = 1235.34 ms / 65 tokens ( 19.30 ms per token, 51.81 tokens per second) 3.17.238.929 I slot print_timing: id 0 | task 5339 | total time = 2268.92 ms / 552 tokens 3.17.238.930 I slot print_timing: id 0 | task 5339 | graphs reused = 4922 3.17.238.930 I slot print_timing: id 0 | task 5339 | graph reallocs = 0 / 0 (same size) / (changed size) 3.17.238.976 I slot release: id 0 | task 5339 | stop processing: n_tokens = 583, truncated = 0 3.17.243.651 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 583, t_last = 387928282361 3.17.243.688 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.740 MiB) 3.17.303.833 I slot launch_slot_: id 0 | task 5407 | processing task, is_child = 0 3.19.238.606 I slot print_timing: id 0 | task 5407 | prompt eval time = 1044.77 ms / 507 tokens ( 2.06 ms per token, 485.28 tokens per second) 3.19.238.619 I slot print_timing: id 0 | task 5407 | eval time = 889.99 ms / 47 tokens ( 19.35 ms per token, 51.69 tokens per second) 3.19.238.621 I slot print_timing: id 0 | task 5407 | total time = 1934.76 ms / 554 tokens 3.19.238.622 I slot print_timing: id 0 | task 5407 | graphs reused = 4967 3.19.238.622 I slot print_timing: id 0 | task 5407 | graph reallocs = 0 / 0 (same size) / (changed size) 3.19.238.671 I slot release: id 0 | task 5407 | stop processing: n_tokens = 585, truncated = 0 3.19.243.330 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 585, t_last = 387930282056 3.19.243.362 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.922 MiB) 3.19.290.766 I slot launch_slot_: id 0 | task 5457 | processing task, is_child = 0 3.21.995.060 I slot print_timing: id 0 | task 5457 | prompt eval time = 1385.55 ms / 633 tokens ( 2.19 ms per token, 456.86 tokens per second) 3.21.995.066 I slot print_timing: id 0 | task 5457 | eval time = 1318.73 ms / 66 tokens ( 20.29 ms per token, 49.29 tokens per second) 3.21.995.067 I slot print_timing: id 0 | task 5457 | total time = 2704.28 ms / 699 tokens 3.21.995.067 I slot print_timing: id 0 | task 5457 | graphs reused = 5031 3.21.995.068 I slot print_timing: id 0 | task 5457 | graph reallocs = 0 / 0 (same size) / (changed size) 3.21.995.137 I slot release: id 0 | task 5457 | stop processing: n_tokens = 730, truncated = 0 3.22.000.821 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 730, t_last = 387933038522 3.22.000.867 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.788 MiB) 3.22.046.742 I slot launch_slot_: id 0 | task 5527 | processing task, is_child = 0 3.24.283.976 I slot print_timing: id 0 | task 5527 | prompt eval time = 1298.27 ms / 571 tokens ( 2.27 ms per token, 439.82 tokens per second) 3.24.283.982 I slot print_timing: id 0 | task 5527 | eval time = 938.94 ms / 47 tokens ( 20.41 ms per token, 48.99 tokens per second) 3.24.283.984 I slot print_timing: id 0 | task 5527 | total time = 2237.22 ms / 618 tokens 3.24.283.984 I slot print_timing: id 0 | task 5527 | graphs reused = 5076 3.24.283.985 I slot print_timing: id 0 | task 5527 | graph reallocs = 0 / 0 (same size) / (changed size) 3.24.284.028 I slot release: id 0 | task 5527 | stop processing: n_tokens = 649, truncated = 0 3.24.290.386 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 649, t_last = 387935327413 3.24.290.426 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.478 MiB) 3.24.338.323 I slot launch_slot_: id 0 | task 5578 | processing task, is_child = 0 3.26.848.130 I slot print_timing: id 0 | task 5578 | prompt eval time = 1633.29 ms / 798 tokens ( 2.05 ms per token, 488.58 tokens per second) 3.26.848.136 I slot print_timing: id 0 | task 5578 | eval time = 876.50 ms / 44 tokens ( 20.38 ms per token, 49.06 tokens per second) 3.26.848.137 I slot print_timing: id 0 | task 5578 | total time = 2509.79 ms / 842 tokens 3.26.848.138 I slot print_timing: id 0 | task 5578 | graphs reused = 5118 3.26.848.138 I slot print_timing: id 0 | task 5578 | graph reallocs = 0 / 0 (same size) / (changed size) 3.26.848.226 I slot release: id 0 | task 5578 | stop processing: n_tokens = 873, truncated = 0 3.26.853.803 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 873, t_last = 387937891611 3.26.853.860 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.715 MiB) 3.26.944.075 I slot launch_slot_: id 0 | task 5626 | processing task, is_child = 0 3.29.119.390 I slot print_timing: id 0 | task 5626 | prompt eval time = 1318.49 ms / 572 tokens ( 2.31 ms per token, 433.83 tokens per second) 3.29.119.395 I slot print_timing: id 0 | task 5626 | eval time = 856.81 ms / 43 tokens ( 20.40 ms per token, 49.02 tokens per second) 3.29.119.396 I slot print_timing: id 0 | task 5626 | total time = 2175.30 ms / 615 tokens 3.29.119.397 I slot print_timing: id 0 | task 5626 | graphs reused = 5159 3.29.119.397 I slot print_timing: id 0 | task 5626 | graph reallocs = 0 / 0 (same size) / (changed size) 3.29.119.448 I slot release: id 0 | task 5626 | stop processing: n_tokens = 646, truncated = 0 3.29.124.817 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 646, t_last = 387940162833 3.29.124.861 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.282 MiB) 3.29.124.875 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.891 MiB) 3.29.216.917 I slot launch_slot_: id 0 | task 5673 | processing task, is_child = 0 3.31.589.972 I slot print_timing: id 0 | task 5673 | prompt eval time = 1394.72 ms / 613 tokens ( 2.28 ms per token, 439.51 tokens per second) 3.31.589.975 I slot print_timing: id 0 | task 5673 | eval time = 978.31 ms / 49 tokens ( 20.38 ms per token, 49.06 tokens per second) 3.31.589.975 I slot print_timing: id 0 | task 5673 | total time = 2373.04 ms / 662 tokens 3.31.589.976 I slot print_timing: id 0 | task 5673 | graphs reused = 5206 3.31.589.977 I slot print_timing: id 0 | task 5673 | graph reallocs = 0 / 0 (same size) / (changed size) 3.31.590.041 I slot release: id 0 | task 5673 | stop processing: n_tokens = 693, truncated = 0 3.31.595.547 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 387942633426 3.31.595.589 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 453.244 MiB) 3.31.671.480 I slot launch_slot_: id 0 | task 5726 | processing task, is_child = 0 3.34.259.415 I slot print_timing: id 0 | task 5726 | prompt eval time = 1304.91 ms / 580 tokens ( 2.25 ms per token, 444.47 tokens per second) 3.34.259.422 I slot print_timing: id 0 | task 5726 | eval time = 1283.01 ms / 64 tokens ( 20.37 ms per token, 49.10 tokens per second) 3.34.259.423 I slot print_timing: id 0 | task 5726 | total time = 2587.92 ms / 644 tokens 3.34.259.423 I slot print_timing: id 0 | task 5726 | graphs reused = 5268 3.34.259.424 I slot print_timing: id 0 | task 5726 | graph reallocs = 0 / 0 (same size) / (changed size) 3.34.259.506 I slot release: id 0 | task 5726 | stop processing: n_tokens = 675, truncated = 0 3.34.265.453 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 675, t_last = 387945302891 3.34.265.497 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.615 MiB) 3.34.355.479 I slot launch_slot_: id 0 | task 5794 | processing task, is_child = 0 3.36.916.330 I slot print_timing: id 0 | task 5794 | prompt eval time = 1557.52 ms / 716 tokens ( 2.18 ms per token, 459.70 tokens per second) 3.36.916.342 I slot print_timing: id 0 | task 5794 | eval time = 1003.31 ms / 50 tokens ( 20.48 ms per token, 48.84 tokens per second) 3.36.916.344 I slot print_timing: id 0 | task 5794 | total time = 2560.83 ms / 766 tokens 3.36.916.345 I slot print_timing: id 0 | task 5794 | graphs reused = 5315 3.36.916.354 I slot print_timing: id 0 | task 5794 | graph reallocs = 0 / 0 (same size) / (changed size) 3.36.916.419 I slot release: id 0 | task 5794 | stop processing: n_tokens = 797, truncated = 0 3.36.922.727 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 797, t_last = 387947959805 3.36.922.776 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 458.015 MiB) 3.36.999.162 I slot launch_slot_: id 0 | task 5848 | processing task, is_child = 0 3.40.747.069 I slot print_timing: id 0 | task 5848 | prompt eval time = 1667.95 ms / 799 tokens ( 2.09 ms per token, 479.03 tokens per second) 3.40.747.072 I slot print_timing: id 0 | task 5848 | eval time = 2079.94 ms / 103 tokens ( 20.39 ms per token, 49.04 tokens per second) 3.40.747.073 I slot print_timing: id 0 | task 5848 | total time = 3747.89 ms / 902 tokens 3.40.747.074 I slot print_timing: id 0 | task 5848 | graphs reused = 5416 3.40.747.074 I slot print_timing: id 0 | task 5848 | graph reallocs = 0 / 0 (same size) / (changed size) 3.40.747.134 I slot release: id 0 | task 5848 | stop processing: n_tokens = 933, truncated = 0 3.40.751.970 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 933, t_last = 387951790519 3.40.752.036 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.302 MiB) 3.40.851.508 I slot launch_slot_: id 0 | task 5955 | processing task, is_child = 0 3.42.842.078 I slot print_timing: id 0 | task 5955 | prompt eval time = 873.96 ms / 361 tokens ( 2.42 ms per token, 413.06 tokens per second) 3.42.842.085 I slot print_timing: id 0 | task 5955 | eval time = 1116.60 ms / 56 tokens ( 20.30 ms per token, 49.26 tokens per second) 3.42.842.085 I slot print_timing: id 0 | task 5955 | total time = 1990.56 ms / 417 tokens 3.42.842.086 I slot print_timing: id 0 | task 5955 | graphs reused = 5470 3.42.842.086 I slot print_timing: id 0 | task 5955 | graph reallocs = 0 / 0 (same size) / (changed size) 3.42.842.134 I slot release: id 0 | task 5955 | stop processing: n_tokens = 448, truncated = 0 3.42.846.966 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 387953885519 3.42.846.999 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 454.319 MiB) 3.42.913.816 I slot launch_slot_: id 0 | task 6014 | processing task, is_child = 0 3.45.992.352 I slot print_timing: id 0 | task 6014 | prompt eval time = 906.08 ms / 381 tokens ( 2.38 ms per token, 420.49 tokens per second) 3.45.992.357 I slot print_timing: id 0 | task 6014 | eval time = 2172.44 ms / 108 tokens ( 20.30 ms per token, 49.25 tokens per second) 3.45.992.358 I slot print_timing: id 0 | task 6014 | total time = 3078.52 ms / 489 tokens 3.45.992.359 I slot print_timing: id 0 | task 6014 | graphs reused = 5575 3.45.992.359 I slot print_timing: id 0 | task 6014 | graph reallocs = 0 / 0 (same size) / (changed size) 3.45.992.404 I slot release: id 0 | task 6014 | stop processing: n_tokens = 520, truncated = 0 3.45.997.337 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 387957035789 3.45.997.383 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 456.685 MiB) 3.46.076.911 I slot launch_slot_: id 0 | task 6125 | processing task, is_child = 0 3.49.451.724 I slot print_timing: id 0 | task 6125 | prompt eval time = 880.25 ms / 365 tokens ( 2.41 ms per token, 414.66 tokens per second) 3.49.451.727 I slot print_timing: id 0 | task 6125 | eval time = 2494.55 ms / 124 tokens ( 20.28 ms per token, 49.31 tokens per second) 3.49.451.728 I slot print_timing: id 0 | task 6125 | total time = 3374.80 ms / 489 tokens 3.49.451.729 I slot print_timing: id 0 | task 6125 | graphs reused = 5696 3.49.451.729 I slot print_timing: id 0 | task 6125 | graph reallocs = 0 / 0 (same size) / (changed size) 3.49.451.780 I slot release: id 0 | task 6125 | stop processing: n_tokens = 520, truncated = 0 3.49.456.540 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 387960495165 3.49.456.582 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.752 MiB) 3.49.516.374 I slot launch_slot_: id 0 | task 6252 | processing task, is_child = 0 3.52.510.646 I slot print_timing: id 0 | task 6252 | prompt eval time = 842.02 ms / 333 tokens ( 2.53 ms per token, 395.48 tokens per second) 3.52.510.650 I slot print_timing: id 0 | task 6252 | eval time = 2152.23 ms / 107 tokens ( 20.30 ms per token, 49.25 tokens per second) 3.52.510.650 I slot print_timing: id 0 | task 6252 | total time = 2994.25 ms / 440 tokens 3.52.510.651 I slot print_timing: id 0 | task 6252 | graphs reused = 5801 3.52.510.651 I slot print_timing: id 0 | task 6252 | graph reallocs = 0 / 0 (same size) / (changed size) 3.52.510.681 I slot release: id 0 | task 6252 | stop processing: n_tokens = 471, truncated = 0 3.52.515.622 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 471, t_last = 387963554066 3.52.515.655 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 453.048 MiB) 3.52.578.469 I slot launch_slot_: id 0 | task 6362 | processing task, is_child = 0 3.56.288.020 I slot print_timing: id 0 | task 6362 | prompt eval time = 927.72 ms / 403 tokens ( 2.30 ms per token, 434.40 tokens per second) 3.56.288.023 I slot print_timing: id 0 | task 6362 | eval time = 2781.81 ms / 138 tokens ( 20.31 ms per token, 49.25 tokens per second) 3.56.288.024 I slot print_timing: id 0 | task 6362 | total time = 3709.53 ms / 541 tokens 3.56.288.024 I slot print_timing: id 0 | task 6362 | graphs reused = 5936 3.56.288.025 I slot print_timing: id 0 | task 6362 | graph reallocs = 0 / 0 (same size) / (changed size) 3.56.288.066 I slot release: id 0 | task 6362 | stop processing: n_tokens = 572, truncated = 0 3.56.293.051 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 572, t_last = 387967331451 3.56.353.614 I slot launch_slot_: id 0 | task 6503 | processing task, is_child = 0 4.00.310.982 I slot print_timing: id 0 | task 6503 | n_gen = 149, tg = 49.28 t/s, tg_3s = 49.61 t/s 4.01.041.102 I slot print_timing: id 0 | task 6503 | prompt eval time = 954.08 ms / 411 tokens ( 2.32 ms per token, 430.78 tokens per second) 4.01.041.108 I slot print_timing: id 0 | task 6503 | eval time = 3733.39 ms / 185 tokens ( 20.29 ms per token, 49.29 tokens per second) 4.01.041.116 I slot print_timing: id 0 | task 6503 | total time = 4687.47 ms / 596 tokens 4.01.041.119 I slot print_timing: id 0 | task 6503 | graphs reused = 6118 4.01.041.119 I slot print_timing: id 0 | task 6503 | graph reallocs = 0 / 0 (same size) / (changed size) 4.01.041.153 I slot release: id 0 | task 6503 | stop processing: n_tokens = 627, truncated = 0 4.01.046.668 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 627, t_last = 387972084538 4.01.046.710 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 456.959 MiB) 4.01.119.575 I slot launch_slot_: id 0 | task 6691 | processing task, is_child = 0 4.05.202.760 I slot print_timing: id 0 | task 6691 | n_gen = 149, tg = 49.22 t/s, tg_3s = 49.55 t/s 4.06.745.521 I slot print_timing: id 0 | task 6691 | prompt eval time = 1076.23 ms / 490 tokens ( 2.20 ms per token, 455.29 tokens per second) 4.06.745.524 I slot print_timing: id 0 | task 6691 | eval time = 4549.70 ms / 225 tokens ( 20.31 ms per token, 49.23 tokens per second) 4.06.745.524 I slot print_timing: id 0 | task 6691 | total time = 5625.93 ms / 715 tokens 4.06.745.525 I slot print_timing: id 0 | task 6691 | graphs reused = 6341 4.06.745.525 I slot print_timing: id 0 | task 6691 | graph reallocs = 0 / 0 (same size) / (changed size) 4.06.745.571 I slot release: id 0 | task 6691 | stop processing: n_tokens = 746, truncated = 0 4.06.750.356 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 746, t_last = 387977788956 4.06.750.406 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 515.744 MiB) 4.06.772.230 I slot launch_slot_: id 0 | task 6919 | processing task, is_child = 0 4.10.661.491 I slot print_timing: id 0 | task 6919 | n_gen = 150, tg = 49.35 t/s, tg_3s = 49.68 t/s 4.11.087.436 I slot print_timing: id 0 | task 6919 | prompt eval time = 869.83 ms / 344 tokens ( 2.53 ms per token, 395.48 tokens per second) 4.11.087.441 I slot print_timing: id 0 | task 6919 | eval time = 3445.37 ms / 171 tokens ( 20.27 ms per token, 49.34 tokens per second) 4.11.087.442 I slot print_timing: id 0 | task 6919 | total time = 4315.19 ms / 515 tokens 4.11.087.443 I slot print_timing: id 0 | task 6919 | graphs reused = 6509 4.11.087.443 I slot print_timing: id 0 | task 6919 | graph reallocs = 0 / 0 (same size) / (changed size) 4.11.087.475 I slot release: id 0 | task 6919 | stop processing: n_tokens = 546, truncated = 0 4.11.092.448 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 546, t_last = 387982130860 4.11.092.489 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 452.266 MiB) 4.11.132.515 I slot launch_slot_: id 0 | task 7093 | processing task, is_child = 0 4.15.029.800 I slot print_timing: id 0 | task 7093 | n_gen = 150, tg = 49.39 t/s, tg_3s = 49.72 t/s 4.15.455.010 I slot print_timing: id 0 | task 7093 | prompt eval time = 880.35 ms / 347 tokens ( 2.54 ms per token, 394.16 tokens per second) 4.15.455.015 I slot print_timing: id 0 | task 7093 | eval time = 3442.13 ms / 171 tokens ( 20.25 ms per token, 49.39 tokens per second) 4.15.455.016 I slot print_timing: id 0 | task 7093 | total time = 4322.48 ms / 518 tokens 4.15.455.017 I slot print_timing: id 0 | task 7093 | graphs reused = 6677 4.15.455.017 I slot print_timing: id 0 | task 7093 | graph reallocs = 0 / 0 (same size) / (changed size) 4.15.455.046 I slot release: id 0 | task 7093 | stop processing: n_tokens = 549, truncated = 0 4.15.459.883 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 387986498431 4.15.459.923 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.989 MiB) 4.15.486.000 I slot launch_slot_: id 0 | task 7267 | processing task, is_child = 0 4.18.968.202 I slot print_timing: id 0 | task 7267 | prompt eval time = 944.26 ms / 401 tokens ( 2.35 ms per token, 424.67 tokens per second) 4.18.968.205 I slot print_timing: id 0 | task 7267 | eval time = 2537.93 ms / 126 tokens ( 20.30 ms per token, 49.25 tokens per second) 4.18.968.206 I slot print_timing: id 0 | task 7267 | total time = 3482.19 ms / 527 tokens 4.18.968.206 I slot print_timing: id 0 | task 7267 | graphs reused = 6800 4.18.968.207 I slot print_timing: id 0 | task 7267 | graph reallocs = 0 / 0 (same size) / (changed size) 4.18.968.236 I slot release: id 0 | task 7267 | stop processing: n_tokens = 558, truncated = 0 4.18.973.264 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 387990011621 4.18.973.306 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.280 MiB) 4.18.998.489 I slot launch_slot_: id 0 | task 7396 | processing task, is_child = 0 4.22.370.831 I slot print_timing: id 0 | task 7396 | prompt eval time = 1035.85 ms / 456 tokens ( 2.27 ms per token, 440.22 tokens per second) 4.22.370.835 I slot print_timing: id 0 | task 7396 | eval time = 2336.48 ms / 115 tokens ( 20.50 ms per token, 48.79 tokens per second) 4.22.370.836 I slot print_timing: id 0 | task 7396 | total time = 3372.33 ms / 571 tokens 4.22.370.836 I slot print_timing: id 0 | task 7396 | graphs reused = 6912 4.22.370.837 I slot print_timing: id 0 | task 7396 | graph reallocs = 0 / 0 (same size) / (changed size) 4.22.370.874 I slot release: id 0 | task 7396 | stop processing: n_tokens = 602, truncated = 0 4.22.375.851 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.107 (> 0.100 thold), f_keep = 0.078 4.22.375.891 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.319 MiB) 4.22.397.016 I slot launch_slot_: id 0 | task 7514 | processing task, is_child = 0 4.25.627.393 I slot print_timing: id 0 | task 7514 | prompt eval time = 975.89 ms / 406 tokens ( 2.40 ms per token, 416.03 tokens per second) 4.25.627.396 I slot print_timing: id 0 | task 7514 | eval time = 2254.48 ms / 112 tokens ( 20.31 ms per token, 49.24 tokens per second) 4.25.627.398 I slot print_timing: id 0 | task 7514 | total time = 3230.37 ms / 518 tokens 4.25.627.399 I slot print_timing: id 0 | task 7514 | graphs reused = 7021 4.25.627.399 I slot print_timing: id 0 | task 7514 | graph reallocs = 0 / 0 (same size) / (changed size) 4.25.627.433 I slot release: id 0 | task 7514 | stop processing: n_tokens = 549, truncated = 0 4.25.632.390 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 387996670818 4.25.632.433 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 453.967 MiB) 4.25.644.380 I slot launch_slot_: id 0 | task 7629 | processing task, is_child = 0 4.27.839.243 I slot print_timing: id 0 | task 7629 | prompt eval time = 930.22 ms / 406 tokens ( 2.29 ms per token, 436.45 tokens per second) 4.27.839.247 I slot print_timing: id 0 | task 7629 | eval time = 1264.62 ms / 63 tokens ( 20.40 ms per token, 49.03 tokens per second) 4.27.839.248 I slot print_timing: id 0 | task 7629 | total time = 2194.84 ms / 469 tokens 4.27.839.248 I slot print_timing: id 0 | task 7629 | graphs reused = 7082 4.27.839.249 I slot print_timing: id 0 | task 7629 | graph reallocs = 0 / 0 (same size) / (changed size) 4.27.839.283 I slot release: id 0 | task 7629 | stop processing: n_tokens = 500, truncated = 0 4.27.844.048 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 500, t_last = 387998882668 4.27.844.085 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 452.383 MiB) 4.27.865.161 I slot launch_slot_: id 0 | task 7695 | processing task, is_child = 0 4.31.904.275 I slot print_timing: id 0 | task 7695 | n_gen = 149, tg = 49.16 t/s, tg_3s = 49.49 t/s 4.34.913.519 I slot print_timing: id 0 | task 7695 | n_gen = 296, tg = 49.01 t/s, tg_3s = 48.85 t/s 4.35.461.919 I slot print_timing: id 0 | task 7695 | prompt eval time = 1028.60 ms / 444 tokens ( 2.32 ms per token, 431.66 tokens per second) 4.35.461.923 I slot print_timing: id 0 | task 7695 | eval time = 6568.15 ms / 323 tokens ( 20.40 ms per token, 49.02 tokens per second) 4.35.461.925 I slot print_timing: id 0 | task 7695 | total time = 7596.75 ms / 767 tokens 4.35.461.926 I slot print_timing: id 0 | task 7695 | graphs reused = 7401 4.35.461.926 I slot print_timing: id 0 | task 7695 | graph reallocs = 0 / 0 (same size) / (changed size) 4.35.461.980 I slot release: id 0 | task 7695 | stop processing: n_tokens = 798, truncated = 0 4.35.466.554 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 798, t_last = 388006505365 4.35.477.362 I slot launch_slot_: id 0 | task 8021 | processing task, is_child = 0 4.38.454.961 I slot print_timing: id 0 | task 8021 | prompt eval time = 909.71 ms / 372 tokens ( 2.45 ms per token, 408.92 tokens per second) 4.38.454.965 I slot print_timing: id 0 | task 8021 | eval time = 2067.88 ms / 103 tokens ( 20.27 ms per token, 49.33 tokens per second) 4.38.454.966 I slot print_timing: id 0 | task 8021 | total time = 2977.59 ms / 475 tokens 4.38.454.966 I slot print_timing: id 0 | task 8021 | graphs reused = 7502 4.38.454.967 I slot print_timing: id 0 | task 8021 | graph reallocs = 0 / 0 (same size) / (changed size) 4.38.455.003 I slot release: id 0 | task 8021 | stop processing: n_tokens = 506, truncated = 0 4.38.460.001 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 506, t_last = 388009498388 4.38.460.037 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 456.764 MiB) 4.38.479.622 I slot launch_slot_: id 0 | task 8127 | processing task, is_child = 0 4.42.526.831 I slot print_timing: id 0 | task 8127 | n_gen = 149, tg = 49.17 t/s, tg_3s = 49.51 t/s 4.44.171.682 I slot print_timing: id 0 | task 8127 | prompt eval time = 1037.44 ms / 454 tokens ( 2.29 ms per token, 437.62 tokens per second) 4.44.171.686 I slot print_timing: id 0 | task 8127 | eval time = 4654.61 ms / 230 tokens ( 20.33 ms per token, 49.20 tokens per second) 4.44.171.687 I slot print_timing: id 0 | task 8127 | total time = 5692.05 ms / 684 tokens 4.44.171.687 I slot print_timing: id 0 | task 8127 | graphs reused = 7729 4.44.171.688 I slot print_timing: id 0 | task 8127 | graph reallocs = 0 / 0 (same size) / (changed size) 4.44.171.723 I slot release: id 0 | task 8127 | stop processing: n_tokens = 715, truncated = 0 4.44.176.424 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 715, t_last = 388015215108 4.44.176.474 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 452.325 MiB) 4.44.190.752 I slot launch_slot_: id 0 | task 8360 | processing task, is_child = 0 4.48.067.003 I slot print_timing: id 0 | task 8360 | n_gen = 149, tg = 49.21 t/s, tg_3s = 49.54 t/s 4.49.630.843 I slot print_timing: id 0 | task 8360 | prompt eval time = 868.83 ms / 354 tokens ( 2.45 ms per token, 407.44 tokens per second) 4.49.630.848 I slot print_timing: id 0 | task 8360 | eval time = 4571.25 ms / 226 tokens ( 20.32 ms per token, 49.22 tokens per second) 4.49.630.849 I slot print_timing: id 0 | task 8360 | total time = 5440.08 ms / 580 tokens 4.49.630.849 I slot print_timing: id 0 | task 8360 | graphs reused = 7952 4.49.630.850 I slot print_timing: id 0 | task 8360 | graph reallocs = 0 / 0 (same size) / (changed size) 4.49.630.881 I slot release: id 0 | task 8360 | stop processing: n_tokens = 611, truncated = 0 4.49.635.688 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 611, t_last = 388020674266 4.49.635.731 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 453.244 MiB) 4.49.657.592 I slot launch_slot_: id 0 | task 8589 | processing task, is_child = 0 4.53.313.309 I slot print_timing: id 0 | task 8589 | prompt eval time = 840.62 ms / 334 tokens ( 2.52 ms per token, 397.32 tokens per second) 4.53.313.315 I slot print_timing: id 0 | task 8589 | eval time = 2815.08 ms / 140 tokens ( 20.25 ms per token, 49.38 tokens per second) 4.53.313.315 I slot print_timing: id 0 | task 8589 | total time = 3655.71 ms / 474 tokens 4.53.313.316 I slot print_timing: id 0 | task 8589 | graphs reused = 8090 4.53.313.317 I slot print_timing: id 0 | task 8589 | graph reallocs = 0 / 0 (same size) / (changed size) 4.53.313.345 I slot release: id 0 | task 8589 | stop processing: n_tokens = 505, truncated = 0 4.53.318.175 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 505, t_last = 388024356730 4.53.318.212 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 452.892 MiB) 4.53.334.404 I slot launch_slot_: id 0 | task 8732 | processing task, is_child = 0 4.57.320.061 I slot print_timing: id 0 | task 8732 | n_gen = 149, tg = 49.17 t/s, tg_3s = 49.50 t/s 4.57.848.236 I slot print_timing: id 0 | task 8732 | prompt eval time = 975.43 ms / 426 tokens ( 2.29 ms per token, 436.73 tokens per second) 4.57.848.243 I slot print_timing: id 0 | task 8732 | eval time = 3538.39 ms / 175 tokens ( 20.34 ms per token, 49.17 tokens per second) 4.57.848.244 I slot print_timing: id 0 | task 8732 | total time = 4513.82 ms / 601 tokens 4.57.848.244 I slot print_timing: id 0 | task 8732 | graphs reused = 8262 4.57.848.245 I slot print_timing: id 0 | task 8732 | graph reallocs = 0 / 0 (same size) / (changed size) 4.57.848.280 I slot release: id 0 | task 8732 | stop processing: n_tokens = 632, truncated = 0 4.57.852.886 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 632, t_last = 388028891665 4.57.852.928 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 455.277 MiB) 4.57.869.901 I slot launch_slot_: id 0 | task 8910 | processing task, is_child = 0 4.59.906.799 I slot print_timing: id 0 | task 8910 | prompt eval time = 880.84 ms / 366 tokens ( 2.41 ms per token, 415.51 tokens per second) 4.59.906.804 I slot print_timing: id 0 | task 8910 | eval time = 1156.05 ms / 58 tokens ( 20.28 ms per token, 49.31 tokens per second) 4.59.906.805 I slot print_timing: id 0 | task 8910 | total time = 2036.89 ms / 424 tokens 4.59.906.805 I slot print_timing: id 0 | task 8910 | graphs reused = 8318 4.59.906.806 I slot print_timing: id 0 | task 8910 | graph reallocs = 0 / 0 (same size) / (changed size) 4.59.906.835 I slot release: id 0 | task 8910 | stop processing: n_tokens = 455, truncated = 0 4.59.911.520 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 455, t_last = 388030950220 4.59.911.555 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 457.937 MiB) 4.59.937.968 I slot launch_slot_: id 0 | task 8971 | processing task, is_child = 0 5.03.985.353 I slot print_timing: id 0 | task 8971 | n_gen = 149, tg = 49.12 t/s, tg_3s = 49.45 t/s 5.06.238.333 I slot print_timing: id 0 | task 8971 | prompt eval time = 1034.40 ms / 462 tokens ( 2.24 ms per token, 446.63 tokens per second) 5.06.238.339 I slot print_timing: id 0 | task 8971 | eval time = 5265.95 ms / 260 tokens ( 20.33 ms per token, 49.18 tokens per second) 5.06.238.339 I slot print_timing: id 0 | task 8971 | total time = 6300.35 ms / 722 tokens 5.06.238.340 I slot print_timing: id 0 | task 8971 | graphs reused = 8575 5.06.238.340 I slot print_timing: id 0 | task 8971 | graph reallocs = 0 / 0 (same size) / (changed size) 5.06.238.386 I slot release: id 0 | task 8971 | stop processing: n_tokens = 753, truncated = 0 5.06.243.124 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 753, t_last = 388037281771 5.06.260.555 I slot launch_slot_: id 0 | task 9234 | processing task, is_child = 0 5.10.010.144 I slot print_timing: id 0 | task 9234 | prompt eval time = 944.84 ms / 396 tokens ( 2.39 ms per token, 419.12 tokens per second) 5.10.010.150 I slot print_timing: id 0 | task 9234 | eval time = 2804.74 ms / 139 tokens ( 20.32 ms per token, 49.20 tokens per second) 5.10.010.150 I slot print_timing: id 0 | task 9234 | total time = 3749.58 ms / 535 tokens 5.10.010.151 I slot print_timing: id 0 | task 9234 | graphs reused = 8711 5.10.010.152 I slot print_timing: id 0 | task 9234 | graph reallocs = 0 / 0 (same size) / (changed size) 5.10.010.181 I slot release: id 0 | task 9234 | stop processing: n_tokens = 566, truncated = 0 5.10.015.105 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 566, t_last = 388041053566 5.10.015.145 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 385.640 MiB) 5.10.030.201 I slot launch_slot_: id 0 | task 9376 | processing task, is_child = 0 5.14.084.555 I slot print_timing: id 0 | task 9376 | n_gen = 149, tg = 49.17 t/s, tg_3s = 49.51 t/s 5.14.327.545 I slot print_timing: id 0 | task 9376 | prompt eval time = 1044.61 ms / 458 tokens ( 2.28 ms per token, 438.44 tokens per second) 5.14.327.551 I slot print_timing: id 0 | task 9376 | eval time = 3252.73 ms / 161 tokens ( 20.33 ms per token, 49.19 tokens per second) 5.14.327.551 I slot print_timing: id 0 | task 9376 | total time = 4297.34 ms / 619 tokens 5.14.327.552 I slot print_timing: id 0 | task 9376 | graphs reused = 8869 5.14.327.553 I slot print_timing: id 0 | task 9376 | graph reallocs = 0 / 0 (same size) / (changed size) 5.14.327.587 I slot release: id 0 | task 9376 | stop processing: n_tokens = 650, truncated = 0 5.14.332.503 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 650, t_last = 388045370972 5.14.332.547 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.048 MiB) 5.14.353.446 I slot launch_slot_: id 0 | task 9540 | processing task, is_child = 0 5.18.401.499 I slot print_timing: id 0 | task 9540 | n_gen = 148, tg = 48.84 t/s, tg_3s = 49.17 t/s 5.18.970.603 I slot print_timing: id 0 | task 9540 | prompt eval time = 1038.08 ms / 458 tokens ( 2.27 ms per token, 441.20 tokens per second) 5.18.970.609 I slot print_timing: id 0 | task 9540 | eval time = 3579.07 ms / 176 tokens ( 20.45 ms per token, 48.90 tokens per second) 5.18.970.610 I slot print_timing: id 0 | task 9540 | total time = 4617.15 ms / 634 tokens 5.18.970.610 I slot print_timing: id 0 | task 9540 | graphs reused = 9042 5.18.970.611 I slot print_timing: id 0 | task 9540 | graph reallocs = 0 / 0 (same size) / (changed size) 5.18.970.642 I slot release: id 0 | task 9540 | stop processing: n_tokens = 665, truncated = 0 5.18.975.727 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 665, t_last = 388050014027 5.18.975.772 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.048 MiB) 5.18.999.495 I slot launch_slot_: id 0 | task 9719 | processing task, is_child = 0 5.23.030.214 I slot print_timing: id 0 | task 9719 | n_gen = 149, tg = 49.15 t/s, tg_3s = 49.49 t/s 5.24.267.904 I slot print_timing: id 0 | task 9719 | prompt eval time = 1019.70 ms / 452 tokens ( 2.26 ms per token, 443.27 tokens per second) 5.24.267.908 I slot print_timing: id 0 | task 9719 | eval time = 4248.69 ms / 210 tokens ( 20.33 ms per token, 49.19 tokens per second) 5.24.267.909 I slot print_timing: id 0 | task 9719 | total time = 5268.39 ms / 662 tokens 5.24.267.909 I slot print_timing: id 0 | task 9719 | graphs reused = 9249 5.24.267.910 I slot print_timing: id 0 | task 9719 | graph reallocs = 0 / 0 (same size) / (changed size) 5.24.267.946 I slot release: id 0 | task 9719 | stop processing: n_tokens = 693, truncated = 0 5.24.272.733 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 388055311331 5.24.272.778 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.090 MiB) 5.24.288.487 I slot launch_slot_: id 0 | task 9932 | processing task, is_child = 0 5.27.665.112 I slot print_timing: id 0 | task 9932 | prompt eval time = 957.77 ms / 404 tokens ( 2.37 ms per token, 421.81 tokens per second) 5.27.665.118 I slot print_timing: id 0 | task 9932 | eval time = 2418.85 ms / 120 tokens ( 20.33 ms per token, 49.20 tokens per second) 5.27.665.119 I slot print_timing: id 0 | task 9932 | total time = 3376.61 ms / 524 tokens 5.27.665.120 I slot print_timing: id 0 | task 9932 | graphs reused = 9366 5.27.665.142 I slot print_timing: id 0 | task 9932 | graph reallocs = 0 / 0 (same size) / (changed size) 5.27.665.174 I slot release: id 0 | task 9932 | stop processing: n_tokens = 555, truncated = 0 5.27.669.898 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 555, t_last = 388058708559 5.27.669.937 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.064 MiB) 5.27.686.359 I slot launch_slot_: id 0 | task 10055 | processing task, is_child = 0 5.30.672.684 I slot print_timing: id 0 | task 10055 | prompt eval time = 854.33 ms / 345 tokens ( 2.48 ms per token, 403.82 tokens per second) 5.30.672.690 I slot print_timing: id 0 | task 10055 | eval time = 2131.98 ms / 106 tokens ( 20.30 ms per token, 49.25 tokens per second) 5.30.672.692 I slot print_timing: id 0 | task 10055 | total time = 2986.32 ms / 451 tokens 5.30.672.692 I slot print_timing: id 0 | task 10055 | graphs reused = 9470 5.30.672.693 I slot print_timing: id 0 | task 10055 | graph reallocs = 0 / 0 (same size) / (changed size) 5.30.672.722 I slot release: id 0 | task 10055 | stop processing: n_tokens = 482, truncated = 0 5.30.677.451 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 482, t_last = 388061716107 5.30.677.487 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 389.140 MiB) 5.30.708.750 I slot launch_slot_: id 0 | task 10164 | processing task, is_child = 0 5.33.850.652 I slot print_timing: id 0 | task 10164 | prompt eval time = 1027.61 ms / 430 tokens ( 2.39 ms per token, 418.45 tokens per second) 5.33.850.658 I slot print_timing: id 0 | task 10164 | eval time = 2114.28 ms / 105 tokens ( 20.33 ms per token, 49.19 tokens per second) 5.33.850.659 I slot print_timing: id 0 | task 10164 | total time = 3141.89 ms / 535 tokens 5.33.850.660 I slot print_timing: id 0 | task 10164 | graphs reused = 9572 5.33.850.660 I slot print_timing: id 0 | task 10164 | graph reallocs = 0 / 0 (same size) / (changed size) 5.33.850.697 I slot release: id 0 | task 10164 | stop processing: n_tokens = 566, truncated = 0 5.33.855.278 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 566, t_last = 388064894082 5.33.855.317 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 391.467 MiB) 5.33.866.740 I slot launch_slot_: id 0 | task 10272 | processing task, is_child = 0 5.36.400.605 I slot print_timing: id 0 | task 10272 | prompt eval time = 814.68 ms / 316 tokens ( 2.58 ms per token, 387.88 tokens per second) 5.36.400.612 I slot print_timing: id 0 | task 10272 | eval time = 1719.17 ms / 85 tokens ( 20.47 ms per token, 48.86 tokens per second) 5.36.400.613 I slot print_timing: id 0 | task 10272 | total time = 2533.86 ms / 401 tokens 5.36.400.614 I slot print_timing: id 0 | task 10272 | graphs reused = 9655 5.36.400.614 I slot print_timing: id 0 | task 10272 | graph reallocs = 0 / 0 (same size) / (changed size) 5.36.400.644 I slot release: id 0 | task 10272 | stop processing: n_tokens = 432, truncated = 0 5.36.405.265 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 432, t_last = 388067444029 5.36.405.300 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.556 MiB) 5.36.430.788 I slot launch_slot_: id 0 | task 10360 | processing task, is_child = 0 5.39.447.105 I slot print_timing: id 0 | task 10360 | prompt eval time = 869.67 ms / 354 tokens ( 2.46 ms per token, 407.05 tokens per second) 5.39.447.110 I slot print_timing: id 0 | task 10360 | eval time = 2146.63 ms / 107 tokens ( 20.25 ms per token, 49.38 tokens per second) 5.39.447.111 I slot print_timing: id 0 | task 10360 | total time = 3016.31 ms / 461 tokens 5.39.447.112 I slot print_timing: id 0 | task 10360 | graphs reused = 9760 5.39.447.113 I slot print_timing: id 0 | task 10360 | graph reallocs = 0 / 0 (same size) / (changed size) 5.39.447.143 I slot release: id 0 | task 10360 | stop processing: n_tokens = 492, truncated = 0 5.39.452.018 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 492, t_last = 388070490529 5.39.452.054 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.615 MiB) 5.39.461.460 I slot launch_slot_: id 0 | task 10470 | processing task, is_child = 0 5.42.411.973 I slot print_timing: id 0 | task 10470 | prompt eval time = 977.80 ms / 438 tokens ( 2.23 ms per token, 447.95 tokens per second) 5.42.411.979 I slot print_timing: id 0 | task 10470 | eval time = 1972.70 ms / 98 tokens ( 20.34 ms per token, 49.17 tokens per second) 5.42.411.980 I slot print_timing: id 0 | task 10470 | total time = 2950.50 ms / 536 tokens 5.42.411.981 I slot print_timing: id 0 | task 10470 | graphs reused = 9855 5.42.411.981 I slot print_timing: id 0 | task 10470 | graph reallocs = 0 / 0 (same size) / (changed size) 5.42.412.014 I slot release: id 0 | task 10470 | stop processing: n_tokens = 567, truncated = 0 5.42.417.174 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 567, t_last = 388073455399 5.42.417.214 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.791 MiB) 5.42.426.855 I slot launch_slot_: id 0 | task 10571 | processing task, is_child = 0 5.44.841.142 I slot print_timing: id 0 | task 10571 | prompt eval time = 1007.67 ms / 457 tokens ( 2.20 ms per token, 453.52 tokens per second) 5.44.841.148 I slot print_timing: id 0 | task 10571 | eval time = 1406.61 ms / 70 tokens ( 20.39 ms per token, 49.05 tokens per second) 5.44.841.149 I slot print_timing: id 0 | task 10571 | total time = 2414.28 ms / 527 tokens 5.44.841.150 I slot print_timing: id 0 | task 10571 | graphs reused = 9922 5.44.841.150 I slot print_timing: id 0 | task 10571 | graph reallocs = 0 / 0 (same size) / (changed size) 5.44.841.196 I slot release: id 0 | task 10571 | stop processing: n_tokens = 558, truncated = 0 5.44.846.063 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 388075884581 5.44.846.102 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.651 MiB) 5.44.855.331 I slot launch_slot_: id 0 | task 10644 | processing task, is_child = 0 5.47.868.259 I slot print_timing: id 0 | task 10644 | prompt eval time = 1035.54 ms / 473 tokens ( 2.19 ms per token, 456.77 tokens per second) 5.47.868.262 I slot print_timing: id 0 | task 10644 | eval time = 1977.38 ms / 98 tokens ( 20.39 ms per token, 49.05 tokens per second) 5.47.868.264 I slot print_timing: id 0 | task 10644 | total time = 3012.91 ms / 571 tokens 5.47.868.264 I slot print_timing: id 0 | task 10644 | graphs reused = 10017 5.47.868.265 I slot print_timing: id 0 | task 10644 | graph reallocs = 0 / 0 (same size) / (changed size) 5.47.868.311 I slot release: id 0 | task 10644 | stop processing: n_tokens = 602, truncated = 0 5.47.873.587 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 602, t_last = 388078911696 5.47.873.632 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.615 MiB) 5.47.883.199 I slot launch_slot_: id 0 | task 10745 | processing task, is_child = 0 5.49.693.514 I slot print_timing: id 0 | task 10745 | prompt eval time = 1031.42 ms / 476 tokens ( 2.17 ms per token, 461.50 tokens per second) 5.49.693.520 I slot print_timing: id 0 | task 10745 | eval time = 778.89 ms / 39 tokens ( 20.50 ms per token, 48.79 tokens per second) 5.49.693.522 I slot print_timing: id 0 | task 10745 | total time = 1810.31 ms / 515 tokens 5.49.693.522 I slot print_timing: id 0 | task 10745 | graphs reused = 10053 5.49.693.523 I slot print_timing: id 0 | task 10745 | graph reallocs = 0 / 0 (same size) / (changed size) 5.49.693.558 I slot release: id 0 | task 10745 | stop processing: n_tokens = 546, truncated = 0 5.49.698.578 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 546, t_last = 388080736943 5.49.698.617 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.657 MiB) 5.49.708.653 I slot launch_slot_: id 0 | task 10787 | processing task, is_child = 0 5.52.910.527 I slot print_timing: id 0 | task 10787 | prompt eval time = 1042.22 ms / 466 tokens ( 2.24 ms per token, 447.12 tokens per second) 5.52.910.534 I slot print_timing: id 0 | task 10787 | eval time = 2159.64 ms / 107 tokens ( 20.37 ms per token, 49.08 tokens per second) 5.52.910.535 I slot print_timing: id 0 | task 10787 | total time = 3201.86 ms / 573 tokens 5.52.910.536 I slot print_timing: id 0 | task 10787 | graphs reused = 10157 5.52.910.536 I slot print_timing: id 0 | task 10787 | graph reallocs = 0 / 0 (same size) / (changed size) 5.52.910.587 I slot release: id 0 | task 10787 | stop processing: n_tokens = 604, truncated = 0 5.52.915.511 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 604, t_last = 388083953972 5.52.915.551 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 392.484 MiB) 5.52.925.176 I slot launch_slot_: id 0 | task 10897 | processing task, is_child = 0 5.55.714.013 I slot print_timing: id 0 | task 10897 | prompt eval time = 937.30 ms / 415 tokens ( 2.26 ms per token, 442.76 tokens per second) 5.55.714.020 I slot print_timing: id 0 | task 10897 | eval time = 1851.52 ms / 91 tokens ( 20.57 ms per token, 48.61 tokens per second) 5.55.714.020 I slot print_timing: id 0 | task 10897 | total time = 2788.83 ms / 506 tokens 5.55.714.021 I slot print_timing: id 0 | task 10897 | graphs reused = 10245 5.55.714.021 I slot print_timing: id 0 | task 10897 | graph reallocs = 0 / 0 (same size) / (changed size) 5.55.714.053 I slot release: id 0 | task 10897 | stop processing: n_tokens = 537, truncated = 0 5.55.718.734 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 537, t_last = 388086757438 5.55.718.772 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.774 MiB) 5.55.728.213 I slot launch_slot_: id 0 | task 10991 | processing task, is_child = 0 5.57.855.313 I slot print_timing: id 0 | task 10991 | prompt eval time = 846.11 ms / 352 tokens ( 2.40 ms per token, 416.02 tokens per second) 5.57.855.320 I slot print_timing: id 0 | task 10991 | eval time = 1280.98 ms / 64 tokens ( 20.33 ms per token, 49.18 tokens per second) 5.57.855.320 I slot print_timing: id 0 | task 10991 | total time = 2127.09 ms / 416 tokens 5.57.855.321 I slot print_timing: id 0 | task 10991 | graphs reused = 10307 5.57.855.321 I slot print_timing: id 0 | task 10991 | graph reallocs = 0 / 0 (same size) / (changed size) 5.57.855.349 I slot release: id 0 | task 10991 | stop processing: n_tokens = 447, truncated = 0 5.57.860.403 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 388088898734 5.57.860.441 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 390.861 MiB) 5.57.870.077 I slot launch_slot_: id 0 | task 11058 | processing task, is_child = 0 6.01.834.997 I slot print_timing: id 0 | task 11058 | prompt eval time = 1279.81 ms / 550 tokens ( 2.33 ms per token, 429.75 tokens per second) 6.01.835.000 I slot print_timing: id 0 | task 11058 | eval time = 2685.10 ms / 133 tokens ( 20.34 ms per token, 49.16 tokens per second) 6.01.835.001 I slot print_timing: id 0 | task 11058 | total time = 3964.91 ms / 683 tokens 6.01.835.002 I slot print_timing: id 0 | task 11058 | graphs reused = 10438 6.01.835.002 I slot print_timing: id 0 | task 11058 | graph reallocs = 0 / 0 (same size) / (changed size) 6.01.835.040 I slot release: id 0 | task 11058 | stop processing: n_tokens = 714, truncated = 0 6.01.840.916 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 714, t_last = 388092878425 6.01.840.959 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.827 MiB) 6.01.840.964 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.754 MiB) 6.01.851.739 I slot launch_slot_: id 0 | task 11195 | processing task, is_child = 0 6.06.529.749 I slot print_timing: id 0 | task 11195 | n_gen = 149, tg = 49.11 t/s, tg_3s = 49.44 t/s 6.09.545.288 I slot print_timing: id 0 | task 11195 | n_gen = 297, tg = 49.09 t/s, tg_3s = 49.08 t/s 6.12.545.686 I slot print_timing: id 0 | task 11195 | n_gen = 444, tg = 49.06 t/s, tg_3s = 48.99 t/s 6.13.158.339 I slot print_timing: id 0 | task 11195 | prompt eval time = 1664.13 ms / 772 tokens ( 2.16 ms per token, 463.91 tokens per second) 6.13.158.342 I slot print_timing: id 0 | task 11195 | eval time = 9642.46 ms / 474 tokens ( 20.39 ms per token, 49.05 tokens per second) 6.13.158.343 I slot print_timing: id 0 | task 11195 | total time = 11306.59 ms / 1246 tokens 6.13.158.344 I slot print_timing: id 0 | task 11195 | graphs reused = 10909 6.13.158.344 I slot print_timing: id 0 | task 11195 | graph reallocs = 0 / 0 (same size) / (changed size) 6.13.158.389 I slot release: id 0 | task 11195 | stop processing: n_tokens = 1277, truncated = 0 6.13.164.544 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1277, t_last = 388104201774 6.13.164.622 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 389.238 MiB) 6.13.182.384 I slot launch_slot_: id 0 | task 11673 | processing task, is_child = 0 6.17.725.965 I slot print_timing: id 0 | task 11673 | n_gen = 149, tg = 49.10 t/s, tg_3s = 49.44 t/s 6.18.376.676 I slot print_timing: id 0 | task 11673 | prompt eval time = 1529.59 ms / 683 tokens ( 2.24 ms per token, 446.53 tokens per second) 6.18.376.682 I slot print_timing: id 0 | task 11673 | eval time = 3664.69 ms / 181 tokens ( 20.36 ms per token, 49.12 tokens per second) 6.18.376.683 I slot print_timing: id 0 | task 11673 | total time = 5194.28 ms / 864 tokens 6.18.376.684 I slot print_timing: id 0 | task 11673 | graphs reused = 11087 6.18.376.684 I slot print_timing: id 0 | task 11673 | graph reallocs = 0 / 0 (same size) / (changed size) 6.18.376.726 I slot release: id 0 | task 11673 | stop processing: n_tokens = 895, truncated = 0 6.18.382.129 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 895, t_last = 388109420111 6.18.382.186 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 385.777 MiB) 6.18.393.124 I slot launch_slot_: id 0 | task 11858 | processing task, is_child = 0 6.22.771.757 I slot print_timing: id 0 | task 11858 | n_gen = 149, tg = 49.19 t/s, tg_3s = 49.52 t/s 6.25.783.613 I slot print_timing: id 0 | task 11858 | n_gen = 297, tg = 49.16 t/s, tg_3s = 49.14 t/s 6.26.779.200 I slot print_timing: id 0 | task 11858 | prompt eval time = 1369.68 ms / 579 tokens ( 2.37 ms per token, 422.73 tokens per second) 6.26.779.206 I slot print_timing: id 0 | task 11858 | eval time = 7016.39 ms / 346 tokens ( 20.34 ms per token, 49.17 tokens per second) 6.26.779.206 I slot print_timing: id 0 | task 11858 | total time = 8386.07 ms / 925 tokens 6.26.779.207 I slot print_timing: id 0 | task 11858 | graphs reused = 11430 6.26.779.208 I slot print_timing: id 0 | task 11858 | graph reallocs = 0 / 0 (same size) / (changed size) 6.26.779.247 I slot release: id 0 | task 11858 | stop processing: n_tokens = 956, truncated = 0 6.26.784.650 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 956, t_last = 388117822632 6.26.784.709 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 391.604 MiB) 6.26.800.582 I slot launch_slot_: id 0 | task 12208 | processing task, is_child = 0 6.30.010.430 I slot print_timing: id 0 | task 12208 | prompt eval time = 1072.21 ms / 500 tokens ( 2.14 ms per token, 466.33 tokens per second) 6.30.010.436 I slot print_timing: id 0 | task 12208 | eval time = 2137.63 ms / 106 tokens ( 20.36 ms per token, 49.12 tokens per second) 6.30.010.437 I slot print_timing: id 0 | task 12208 | total time = 3209.83 ms / 606 tokens 6.30.010.438 I slot print_timing: id 0 | task 12208 | graphs reused = 11534 6.30.010.438 I slot print_timing: id 0 | task 12208 | graph reallocs = 0 / 0 (same size) / (changed size) 6.30.010.474 I slot release: id 0 | task 12208 | stop processing: n_tokens = 637, truncated = 0 6.30.016.494 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 388121053859 6.30.016.537 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.947 MiB) 6.30.025.870 I slot launch_slot_: id 0 | task 12317 | processing task, is_child = 0 6.34.716.601 I slot print_timing: id 0 | task 12317 | n_gen = 149, tg = 49.12 t/s, tg_3s = 49.45 t/s 6.35.936.517 I slot print_timing: id 0 | task 12317 | prompt eval time = 1677.79 ms / 776 tokens ( 2.16 ms per token, 462.51 tokens per second) 6.35.936.522 I slot print_timing: id 0 | task 12317 | eval time = 4232.85 ms / 209 tokens ( 20.35 ms per token, 49.14 tokens per second) 6.35.936.522 I slot print_timing: id 0 | task 12317 | total time = 5910.64 ms / 985 tokens 6.35.936.523 I slot print_timing: id 0 | task 12317 | graphs reused = 11741 6.35.936.523 I slot print_timing: id 0 | task 12317 | graph reallocs = 0 / 0 (same size) / (changed size) 6.35.936.566 I slot release: id 0 | task 12317 | stop processing: n_tokens = 1016, truncated = 0 6.35.941.963 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1016, t_last = 388126979951 6.35.942.024 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 389.590 MiB) 6.35.960.241 I slot launch_slot_: id 0 | task 12530 | processing task, is_child = 0 6.38.182.466 I slot print_timing: id 0 | task 12530 | prompt eval time = 1078.76 ms / 504 tokens ( 2.14 ms per token, 467.21 tokens per second) 6.38.182.475 I slot print_timing: id 0 | task 12530 | eval time = 1143.46 ms / 57 tokens ( 20.42 ms per token, 48.97 tokens per second) 6.38.182.476 I slot print_timing: id 0 | task 12530 | total time = 2222.21 ms / 561 tokens 6.38.182.477 I slot print_timing: id 0 | task 12530 | graphs reused = 11796 6.38.182.477 I slot print_timing: id 0 | task 12530 | graph reallocs = 0 / 0 (same size) / (changed size) 6.38.182.512 I slot release: id 0 | task 12530 | stop processing: n_tokens = 592, truncated = 0 6.38.187.917 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 592, t_last = 388129225897 6.38.187.958 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 389.883 MiB) 6.38.197.284 I slot launch_slot_: id 0 | task 12590 | processing task, is_child = 0 6.42.671.855 I slot print_timing: id 0 | task 12590 | n_gen = 149, tg = 49.10 t/s, tg_3s = 49.43 t/s 6.43.850.232 I slot print_timing: id 0 | task 12590 | prompt eval time = 1460.04 ms / 633 tokens ( 2.31 ms per token, 433.55 tokens per second) 6.43.850.237 I slot print_timing: id 0 | task 12590 | eval time = 4192.90 ms / 207 tokens ( 20.35 ms per token, 49.13 tokens per second) 6.43.850.238 I slot print_timing: id 0 | task 12590 | total time = 5652.94 ms / 840 tokens 6.43.850.239 I slot print_timing: id 0 | task 12590 | graphs reused = 12000 6.43.850.239 I slot print_timing: id 0 | task 12590 | graph reallocs = 0 / 0 (same size) / (changed size) 6.43.850.276 I slot release: id 0 | task 12590 | stop processing: n_tokens = 871, truncated = 0 6.43.855.173 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 871, t_last = 388134893661 6.43.855.227 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 390.431 MiB) 6.43.866.060 I slot launch_slot_: id 0 | task 12801 | processing task, is_child = 0 6.46.078.862 I slot print_timing: id 0 | task 12801 | prompt eval time = 911.31 ms / 395 tokens ( 2.31 ms per token, 433.44 tokens per second) 6.46.078.868 I slot print_timing: id 0 | task 12801 | eval time = 1301.48 ms / 65 tokens ( 20.34 ms per token, 49.17 tokens per second) 6.46.078.868 I slot print_timing: id 0 | task 12801 | total time = 2212.79 ms / 460 tokens 6.46.078.869 I slot print_timing: id 0 | task 12801 | graphs reused = 12063 6.46.078.869 I slot print_timing: id 0 | task 12801 | graph reallocs = 0 / 0 (same size) / (changed size) 6.46.078.904 I slot release: id 0 | task 12801 | stop processing: n_tokens = 491, truncated = 0 6.46.084.066 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 491, t_last = 388137122289 6.46.084.100 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.732 MiB) 6.46.093.460 I slot launch_slot_: id 0 | task 12869 | processing task, is_child = 0 6.50.487.530 I slot print_timing: id 0 | task 12869 | n_gen = 149, tg = 49.03 t/s, tg_3s = 49.36 t/s 6.51.710.068 I slot print_timing: id 0 | task 12869 | prompt eval time = 1375.66 ms / 584 tokens ( 2.36 ms per token, 424.52 tokens per second) 6.51.710.074 I slot print_timing: id 0 | task 12869 | eval time = 4240.94 ms / 209 tokens ( 20.39 ms per token, 49.05 tokens per second) 6.51.710.074 I slot print_timing: id 0 | task 12869 | total time = 5616.60 ms / 793 tokens 6.51.710.075 I slot print_timing: id 0 | task 12869 | graphs reused = 12269 6.51.710.075 I slot print_timing: id 0 | task 12869 | graph reallocs = 0 / 0 (same size) / (changed size) 6.51.710.132 I slot release: id 0 | task 12869 | stop processing: n_tokens = 824, truncated = 0 6.51.715.955 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 824, t_last = 388142753517 6.51.716.006 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.305 MiB) 6.51.716.011 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.947 MiB) 6.51.734.405 I slot launch_slot_: id 0 | task 13082 | processing task, is_child = 0 6.56.308.900 I slot print_timing: id 0 | task 13082 | n_gen = 149, tg = 49.07 t/s, tg_3s = 49.40 t/s 6.57.956.110 I slot print_timing: id 0 | task 13082 | prompt eval time = 1558.14 ms / 695 tokens ( 2.24 ms per token, 446.04 tokens per second) 6.57.956.116 I slot print_timing: id 0 | task 13082 | eval time = 4663.55 ms / 230 tokens ( 20.36 ms per token, 49.10 tokens per second) 6.57.956.117 I slot print_timing: id 0 | task 13082 | total time = 6221.69 ms / 925 tokens 6.57.956.117 I slot print_timing: id 0 | task 13082 | graphs reused = 12496 6.57.956.118 I slot print_timing: id 0 | task 13082 | graph reallocs = 0 / 0 (same size) / (changed size) 6.57.956.161 I slot release: id 0 | task 13082 | stop processing: n_tokens = 956, truncated = 0 6.57.961.980 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 956, t_last = 388148999546 6.57.962.032 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 385.327 MiB) 6.57.979.648 I slot launch_slot_: id 0 | task 13316 | processing task, is_child = 0 7.02.635.942 I slot print_timing: id 0 | task 13316 | n_gen = 149, tg = 49.11 t/s, tg_3s = 49.44 t/s 7.03.449.081 I slot print_timing: id 0 | task 13316 | prompt eval time = 1642.53 ms / 769 tokens ( 2.14 ms per token, 468.18 tokens per second) 7.03.449.084 I slot print_timing: id 0 | task 13316 | eval time = 3826.89 ms / 189 tokens ( 20.36 ms per token, 49.13 tokens per second) 7.03.449.085 I slot print_timing: id 0 | task 13316 | total time = 5469.42 ms / 958 tokens 7.03.449.086 I slot print_timing: id 0 | task 13316 | graphs reused = 12683 7.03.449.086 I slot print_timing: id 0 | task 13316 | graph reallocs = 0 / 0 (same size) / (changed size) 7.03.449.130 I slot release: id 0 | task 13316 | stop processing: n_tokens = 989, truncated = 0 7.03.454.657 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 989, t_last = 388154492515 7.03.454.717 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.500 MiB) 7.03.471.603 I slot launch_slot_: id 0 | task 13509 | processing task, is_child = 0 7.07.317.686 I slot print_timing: id 0 | task 13509 | prompt eval time = 1325.45 ms / 576 tokens ( 2.30 ms per token, 434.57 tokens per second) 7.07.317.692 I slot print_timing: id 0 | task 13509 | eval time = 2520.62 ms / 124 tokens ( 20.49 ms per token, 48.80 tokens per second) 7.07.317.692 I slot print_timing: id 0 | task 13509 | total time = 3846.07 ms / 700 tokens 7.07.317.693 I slot print_timing: id 0 | task 13509 | graphs reused = 12805 7.07.317.693 I slot print_timing: id 0 | task 13509 | graph reallocs = 0 / 0 (same size) / (changed size) 7.07.317.747 I slot release: id 0 | task 13509 | stop processing: n_tokens = 731, truncated = 0 7.07.322.966 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 731, t_last = 388158361132 7.07.323.009 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.967 MiB) 7.07.340.036 I slot launch_slot_: id 0 | task 13637 | processing task, is_child = 0 7.11.838.833 I slot print_timing: id 0 | task 13637 | n_gen = 149, tg = 49.07 t/s, tg_3s = 49.40 t/s 7.14.402.525 I slot print_timing: id 0 | task 13637 | prompt eval time = 1482.51 ms / 655 tokens ( 2.26 ms per token, 441.82 tokens per second) 7.14.402.531 I slot print_timing: id 0 | task 13637 | eval time = 5579.97 ms / 275 tokens ( 20.36 ms per token, 49.10 tokens per second) 7.14.402.532 I slot print_timing: id 0 | task 13637 | total time = 7062.47 ms / 930 tokens 7.14.402.533 I slot print_timing: id 0 | task 13637 | graphs reused = 13077 7.14.402.533 I slot print_timing: id 0 | task 13637 | graph reallocs = 0 / 0 (same size) / (changed size) 7.14.402.571 I slot release: id 0 | task 13637 | stop processing: n_tokens = 961, truncated = 0 7.14.408.223 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 961, t_last = 388165445957 7.14.408.282 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.791 MiB) 7.14.427.585 I slot launch_slot_: id 0 | task 13916 | processing task, is_child = 0 7.18.338.624 I slot print_timing: id 0 | task 13916 | prompt eval time = 1464.65 ms / 621 tokens ( 2.36 ms per token, 423.99 tokens per second) 7.18.338.629 I slot print_timing: id 0 | task 13916 | eval time = 2446.37 ms / 121 tokens ( 20.39 ms per token, 49.05 tokens per second) 7.18.338.630 I slot print_timing: id 0 | task 13916 | total time = 3911.02 ms / 742 tokens 7.18.338.630 I slot print_timing: id 0 | task 13916 | graphs reused = 13195 7.18.338.631 I slot print_timing: id 0 | task 13916 | graph reallocs = 0 / 0 (same size) / (changed size) 7.18.338.672 I slot release: id 0 | task 13916 | stop processing: n_tokens = 773, truncated = 0 7.18.344.496 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 773, t_last = 388169382057 7.18.344.544 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.651 MiB) 7.18.344.549 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.556 MiB) 7.18.363.207 I slot launch_slot_: id 0 | task 14041 | processing task, is_child = 0 7.23.031.707 I slot print_timing: id 0 | task 14041 | n_gen = 148, tg = 48.82 t/s, tg_3s = 49.15 t/s 7.23.762.858 I slot print_timing: id 0 | task 14041 | prompt eval time = 1657.14 ms / 767 tokens ( 2.16 ms per token, 462.85 tokens per second) 7.23.762.864 I slot print_timing: id 0 | task 14041 | eval time = 3742.50 ms / 184 tokens ( 20.45 ms per token, 48.90 tokens per second) 7.23.762.865 I slot print_timing: id 0 | task 14041 | total time = 5399.64 ms / 951 tokens 7.23.762.865 I slot print_timing: id 0 | task 14041 | graphs reused = 13377 7.23.762.866 I slot print_timing: id 0 | task 14041 | graph reallocs = 0 / 0 (same size) / (changed size) 7.23.762.915 I slot release: id 0 | task 14041 | stop processing: n_tokens = 982, truncated = 0 7.23.769.547 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 982, t_last = 388174806300 7.23.769.609 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.690 MiB) 7.23.787.922 I slot launch_slot_: id 0 | task 14229 | processing task, is_child = 0 7.28.612.776 I slot print_timing: id 0 | task 14229 | n_gen = 148, tg = 48.70 t/s, tg_3s = 49.03 t/s 7.29.733.653 I slot print_timing: id 0 | task 14229 | prompt eval time = 1806.19 ms / 864 tokens ( 2.09 ms per token, 478.36 tokens per second) 7.29.733.659 I slot print_timing: id 0 | task 14229 | eval time = 4139.53 ms / 203 tokens ( 20.49 ms per token, 48.80 tokens per second) 7.29.733.660 I slot print_timing: id 0 | task 14229 | total time = 5945.72 ms / 1067 tokens 7.29.733.660 I slot print_timing: id 0 | task 14229 | graphs reused = 13577 7.29.733.661 I slot print_timing: id 0 | task 14229 | graph reallocs = 0 / 0 (same size) / (changed size) 7.29.733.723 I slot release: id 0 | task 14229 | stop processing: n_tokens = 1098, truncated = 0 7.29.739.389 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1098, t_last = 388180777108 7.29.739.450 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.380 MiB) 7.29.757.074 I slot launch_slot_: id 0 | task 14436 | processing task, is_child = 0 7.33.847.501 I slot print_timing: id 0 | task 14436 | prompt eval time = 1480.96 ms / 646 tokens ( 2.29 ms per token, 436.20 tokens per second) 7.33.847.508 I slot print_timing: id 0 | task 14436 | eval time = 2609.45 ms / 129 tokens ( 20.39 ms per token, 49.05 tokens per second) 7.33.847.509 I slot print_timing: id 0 | task 14436 | total time = 4090.42 ms / 775 tokens 7.33.847.509 I slot print_timing: id 0 | task 14436 | graphs reused = 13703 7.33.847.510 I slot print_timing: id 0 | task 14436 | graph reallocs = 0 / 0 (same size) / (changed size) 7.33.847.552 I slot release: id 0 | task 14436 | stop processing: n_tokens = 806, truncated = 0 7.33.853.482 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 806, t_last = 388184890937 7.33.853.531 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 385.620 MiB) 7.33.864.367 I slot launch_slot_: id 0 | task 14569 | processing task, is_child = 0 7.38.484.148 I slot print_timing: id 0 | task 14569 | n_gen = 148, tg = 48.76 t/s, tg_3s = 49.09 t/s 7.40.008.209 I slot print_timing: id 0 | task 14569 | prompt eval time = 1605.13 ms / 720 tokens ( 2.23 ms per token, 448.56 tokens per second) 7.40.008.216 I slot print_timing: id 0 | task 14569 | eval time = 4538.69 ms / 222 tokens ( 20.54 ms per token, 48.69 tokens per second) 7.40.008.216 I slot print_timing: id 0 | task 14569 | total time = 6143.82 ms / 942 tokens 7.40.008.217 I slot print_timing: id 0 | task 14569 | graphs reused = 13922 7.40.008.218 I slot print_timing: id 0 | task 14569 | graph reallocs = 0 / 0 (same size) / (changed size) 7.40.008.261 I slot release: id 0 | task 14569 | stop processing: n_tokens = 973, truncated = 0 7.40.013.436 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 973, t_last = 388191051646 7.40.013.495 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 453.654 MiB) 7.40.031.210 I slot launch_slot_: id 0 | task 14795 | processing task, is_child = 0 7.44.142.063 I slot print_timing: id 0 | task 14795 | n_gen = 149, tg = 49.15 t/s, tg_3s = 49.48 t/s 7.45.462.434 I slot print_timing: id 0 | task 14795 | prompt eval time = 1099.70 ms / 509 tokens ( 2.16 ms per token, 462.86 tokens per second) 7.45.462.441 I slot print_timing: id 0 | task 14795 | eval time = 4331.52 ms / 214 tokens ( 20.34 ms per token, 49.17 tokens per second) 7.45.462.442 I slot print_timing: id 0 | task 14795 | total time = 5431.21 ms / 723 tokens 7.45.462.442 I slot print_timing: id 0 | task 14795 | graphs reused = 14134 7.45.462.443 I slot print_timing: id 0 | task 14795 | graph reallocs = 0 / 0 (same size) / (changed size) 7.45.462.481 I slot release: id 0 | task 14795 | stop processing: n_tokens = 754, truncated = 0 7.45.468.053 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 754, t_last = 388196505866 7.45.468.100 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 464.663 MiB) 7.45.477.737 I slot launch_slot_: id 0 | task 15012 | processing task, is_child = 0 7.49.871.648 I slot print_timing: id 0 | task 15012 | n_gen = 149, tg = 49.16 t/s, tg_3s = 49.49 t/s 7.51.765.274 I slot print_timing: id 0 | task 15012 | prompt eval time = 1383.25 ms / 581 tokens ( 2.38 ms per token, 420.03 tokens per second) 7.51.765.280 I slot print_timing: id 0 | task 15012 | eval time = 4904.28 ms / 242 tokens ( 20.35 ms per token, 49.14 tokens per second) 7.51.765.281 I slot print_timing: id 0 | task 15012 | total time = 6287.53 ms / 823 tokens 7.51.765.281 I slot print_timing: id 0 | task 15012 | graphs reused = 14373 7.51.765.282 I slot print_timing: id 0 | task 15012 | graph reallocs = 0 / 0 (same size) / (changed size) 7.51.765.320 I slot release: id 0 | task 15012 | stop processing: n_tokens = 854, truncated = 0 7.51.771.831 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 854, t_last = 388202808705 7.51.771.885 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 457.194 MiB) 7.51.782.715 I slot launch_slot_: id 0 | task 15258 | processing task, is_child = 0 7.56.680.596 I slot print_timing: id 0 | task 15258 | n_gen = 148, tg = 49.00 t/s, tg_3s = 49.33 t/s 7.59.681.278 I slot print_timing: id 0 | task 15258 | n_gen = 295, tg = 48.99 t/s, tg_3s = 48.99 t/s 8.01.953.611 I slot print_timing: id 0 | task 15258 | prompt eval time = 1897.61 ms / 925 tokens ( 2.05 ms per token, 487.46 tokens per second) 8.01.953.615 I slot print_timing: id 0 | task 15258 | eval time = 8273.28 ms / 406 tokens ( 20.43 ms per token, 48.95 tokens per second) 8.01.953.616 I slot print_timing: id 0 | task 15258 | total time = 10170.89 ms / 1331 tokens 8.01.953.616 I slot print_timing: id 0 | task 15258 | graphs reused = 14775 8.01.953.617 I slot print_timing: id 0 | task 15258 | graph reallocs = 0 / 0 (same size) / (changed size) 8.01.953.674 I slot release: id 0 | task 15258 | stop processing: n_tokens = 1362, truncated = 0 8.01.959.935 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1362, t_last = 388212997059 8.01.960.012 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 458.387 MiB) 8.01.977.069 I slot launch_slot_: id 0 | task 15668 | processing task, is_child = 0 8.06.830.495 I slot print_timing: id 0 | task 15668 | n_gen = 148, tg = 48.70 t/s, tg_3s = 49.04 t/s 8.08.810.584 I slot print_timing: id 0 | task 15668 | prompt eval time = 1835.24 ms / 885 tokens ( 2.07 ms per token, 482.23 tokens per second) 8.08.810.589 I slot print_timing: id 0 | task 15668 | eval time = 4998.27 ms / 245 tokens ( 20.48 ms per token, 48.82 tokens per second) 8.08.810.591 I slot print_timing: id 0 | task 15668 | total time = 6833.51 ms / 1130 tokens 8.08.810.591 I slot print_timing: id 0 | task 15668 | graphs reused = 15017 8.08.810.592 I slot print_timing: id 0 | task 15668 | graph reallocs = 0 / 0 (same size) / (changed size) 8.08.810.639 I slot release: id 0 | task 15668 | stop processing: n_tokens = 1161, truncated = 0 8.08.815.723 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1161, t_last = 388219854024 8.08.815.788 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 389.336 MiB) 8.08.826.879 I slot launch_slot_: id 0 | task 15917 | processing task, is_child = 0 8.10.813.379 I slot print_timing: id 0 | task 15917 | prompt eval time = 870.04 ms / 392 tokens ( 2.22 ms per token, 450.56 tokens per second) 8.10.813.385 I slot print_timing: id 0 | task 15917 | eval time = 1116.45 ms / 56 tokens ( 20.30 ms per token, 49.26 tokens per second) 8.10.813.385 I slot print_timing: id 0 | task 15917 | total time = 1986.49 ms / 448 tokens 8.10.813.386 I slot print_timing: id 0 | task 15917 | graphs reused = 15071 8.10.813.386 I slot print_timing: id 0 | task 15917 | graph reallocs = 0 / 0 (same size) / (changed size) 8.10.813.424 I slot release: id 0 | task 15917 | stop processing: n_tokens = 479, truncated = 0 8.10.817.988 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 479, t_last = 388221856809 8.10.818.024 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 459.560 MiB) 8.10.827.515 I slot launch_slot_: id 0 | task 15976 | processing task, is_child = 0 8.14.605.076 I slot print_timing: id 0 | task 15976 | n_gen = 150, tg = 49.37 t/s, tg_3s = 49.70 t/s 8.15.747.527 I slot print_timing: id 0 | task 15976 | prompt eval time = 759.24 ms / 331 tokens ( 2.29 ms per token, 435.96 tokens per second) 8.15.747.534 I slot print_timing: id 0 | task 15976 | eval time = 4160.77 ms / 206 tokens ( 20.30 ms per token, 49.27 tokens per second) 8.15.747.535 I slot print_timing: id 0 | task 15976 | total time = 4920.00 ms / 537 tokens 8.15.747.536 I slot print_timing: id 0 | task 15976 | graphs reused = 15274 8.15.747.536 I slot print_timing: id 0 | task 15976 | graph reallocs = 0 / 0 (same size) / (changed size) 8.15.747.567 I slot release: id 0 | task 15976 | stop processing: n_tokens = 568, truncated = 0 8.15.752.242 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 568, t_last = 388226790952 8.15.752.281 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.456 MiB) 8.15.761.577 I slot launch_slot_: id 0 | task 16185 | processing task, is_child = 0 8.17.726.706 I slot print_timing: id 0 | task 16185 | prompt eval time = 849.92 ms / 357 tokens ( 2.38 ms per token, 420.04 tokens per second) 8.17.726.711 I slot print_timing: id 0 | task 16185 | eval time = 1115.20 ms / 55 tokens ( 20.65 ms per token, 48.42 tokens per second) 8.17.726.712 I slot print_timing: id 0 | task 16185 | total time = 1965.12 ms / 412 tokens 8.17.726.712 I slot print_timing: id 0 | task 16185 | graphs reused = 15327 8.17.726.713 I slot print_timing: id 0 | task 16185 | graph reallocs = 0 / 0 (same size) / (changed size) 8.17.726.741 I slot release: id 0 | task 16185 | stop processing: n_tokens = 443, truncated = 0 8.17.731.678 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 443, t_last = 388228770126 8.17.731.713 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 456.724 MiB) 8.17.742.615 I slot launch_slot_: id 0 | task 16243 | processing task, is_child = 0 8.21.170.313 I slot print_timing: id 0 | task 16243 | prompt eval time = 753.37 ms / 315 tokens ( 2.39 ms per token, 418.12 tokens per second) 8.21.170.316 I slot print_timing: id 0 | task 16243 | eval time = 2674.32 ms / 133 tokens ( 20.26 ms per token, 49.36 tokens per second) 8.21.170.317 I slot print_timing: id 0 | task 16243 | total time = 3427.69 ms / 448 tokens 8.21.170.317 I slot print_timing: id 0 | task 16243 | graphs reused = 15458 8.21.170.318 I slot print_timing: id 0 | task 16243 | graph reallocs = 0 / 0 (same size) / (changed size) 8.21.170.347 I slot release: id 0 | task 16243 | stop processing: n_tokens = 479, truncated = 0 8.21.175.145 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 479, t_last = 388232213732 8.21.175.181 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.481 MiB) 8.21.184.446 I slot launch_slot_: id 0 | task 16379 | processing task, is_child = 0 8.25.087.325 I slot print_timing: id 0 | task 16379 | n_gen = 149, tg = 49.17 t/s, tg_3s = 49.51 t/s 8.28.095.620 I slot print_timing: id 0 | task 16379 | n_gen = 297, tg = 49.19 t/s, tg_3s = 49.20 t/s 8.31.110.153 I slot print_timing: id 0 | task 16379 | n_gen = 445, tg = 49.16 t/s, tg_3s = 49.10 t/s 8.34.118.331 I slot print_timing: id 0 | task 16379 | n_gen = 593, tg = 49.17 t/s, tg_3s = 49.20 t/s 8.37.137.772 I slot print_timing: id 0 | task 16379 | n_gen = 741, tg = 49.14 t/s, tg_3s = 49.02 t/s 8.40.142.320 I slot print_timing: id 0 | task 16379 | n_gen = 888, tg = 49.10 t/s, tg_3s = 48.93 t/s 8.42.920.302 I slot print_timing: id 0 | task 16379 | prompt eval time = 893.16 ms / 378 tokens ( 2.36 ms per token, 423.22 tokens per second) 8.42.920.305 I slot print_timing: id 0 | task 16379 | eval time = 20842.69 ms / 1024 tokens ( 20.37 ms per token, 49.08 tokens per second) 8.42.920.305 I slot print_timing: id 0 | task 16379 | total time = 21735.85 ms / 1402 tokens 8.42.920.306 I slot print_timing: id 0 | task 16379 | graphs reused = 16476 8.42.920.307 I slot print_timing: id 0 | task 16379 | graph reallocs = 0 / 0 (same size) / (changed size) 8.42.920.341 I slot release: id 0 | task 16379 | stop processing: n_tokens = 1433, truncated = 0 8.42.925.107 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1433, t_last = 388253963726 8.42.925.189 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 455.805 MiB) 8.42.942.135 I slot launch_slot_: id 0 | task 17406 | processing task, is_child = 0 8.44.495.858 I slot print_timing: id 0 | task 17406 | prompt eval time = 740.63 ms / 295 tokens ( 2.51 ms per token, 398.31 tokens per second) 8.44.495.864 I slot print_timing: id 0 | task 17406 | eval time = 813.08 ms / 41 tokens ( 20.33 ms per token, 49.20 tokens per second) 8.44.495.864 I slot print_timing: id 0 | task 17406 | total time = 1553.71 ms / 336 tokens 8.44.495.865 I slot print_timing: id 0 | task 17406 | graphs reused = 16515 8.44.495.865 I slot print_timing: id 0 | task 17406 | graph reallocs = 0 / 0 (same size) / (changed size) 8.44.495.894 I slot release: id 0 | task 17406 | stop processing: n_tokens = 367, truncated = 0 8.44.500.190 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 367, t_last = 388255539279 8.44.500.221 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 458.387 MiB) 8.44.510.626 I slot launch_slot_: id 0 | task 17450 | processing task, is_child = 0 8.46.193.750 I slot print_timing: id 0 | task 17450 | prompt eval time = 769.34 ms / 337 tokens ( 2.28 ms per token, 438.04 tokens per second) 8.46.193.757 I slot print_timing: id 0 | task 17450 | eval time = 913.78 ms / 46 tokens ( 20.31 ms per token, 49.25 tokens per second) 8.46.193.757 I slot print_timing: id 0 | task 17450 | total time = 1683.12 ms / 383 tokens 8.46.193.758 I slot print_timing: id 0 | task 17450 | graphs reused = 16559 8.46.193.758 I slot print_timing: id 0 | task 17450 | graph reallocs = 0 / 0 (same size) / (changed size) 8.46.193.790 I slot release: id 0 | task 17450 | stop processing: n_tokens = 414, truncated = 0 8.46.198.398 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 388257237175 8.46.209.066 I slot launch_slot_: id 0 | task 17499 | processing task, is_child = 0 8.50.013.817 I slot print_timing: id 0 | task 17499 | n_gen = 150, tg = 49.34 t/s, tg_3s = 49.67 t/s 8.51.849.990 I slot print_timing: id 0 | task 17499 | prompt eval time = 784.66 ms / 325 tokens ( 2.41 ms per token, 414.19 tokens per second) 8.51.849.995 I slot print_timing: id 0 | task 17499 | eval time = 4856.25 ms / 240 tokens ( 20.32 ms per token, 49.21 tokens per second) 8.51.849.996 I slot print_timing: id 0 | task 17499 | total time = 5640.91 ms / 565 tokens 8.51.849.996 I slot print_timing: id 0 | task 17499 | graphs reused = 16796 8.51.849.997 I slot print_timing: id 0 | task 17499 | graph reallocs = 0 / 0 (same size) / (changed size) 8.51.850.030 I slot release: id 0 | task 17499 | stop processing: n_tokens = 596, truncated = 0 8.51.854.317 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.108 (> 0.100 thold), f_keep = 0.054 8.51.854.363 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 459.032 MiB) 8.51.863.635 I slot launch_slot_: id 0 | task 17742 | processing task, is_child = 0 8.53.697.884 I slot print_timing: id 0 | task 17742 | prompt eval time = 700.80 ms / 264 tokens ( 2.65 ms per token, 376.71 tokens per second) 8.53.697.890 I slot print_timing: id 0 | task 17742 | eval time = 1133.44 ms / 57 tokens ( 20.24 ms per token, 49.41 tokens per second) 8.53.697.891 I slot print_timing: id 0 | task 17742 | total time = 1834.24 ms / 321 tokens 8.53.697.891 I slot print_timing: id 0 | task 17742 | graphs reused = 16851 8.53.697.892 I slot print_timing: id 0 | task 17742 | graph reallocs = 0 / 0 (same size) / (changed size) 8.53.697.916 I slot release: id 0 | task 17742 | stop processing: n_tokens = 352, truncated = 0 8.53.702.398 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 352, t_last = 388264741301 8.53.702.429 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 453.987 MiB) 8.53.712.775 I slot launch_slot_: id 0 | task 17802 | processing task, is_child = 0 8.55.315.975 I slot print_timing: id 0 | task 17802 | prompt eval time = 806.76 ms / 331 tokens ( 2.44 ms per token, 410.28 tokens per second) 8.55.315.981 I slot print_timing: id 0 | task 17802 | eval time = 796.43 ms / 40 tokens ( 20.42 ms per token, 48.97 tokens per second) 8.55.315.982 I slot print_timing: id 0 | task 17802 | total time = 1603.19 ms / 371 tokens 8.55.315.982 I slot print_timing: id 0 | task 17802 | graphs reused = 16889 8.55.315.983 I slot print_timing: id 0 | task 17802 | graph reallocs = 0 / 0 (same size) / (changed size) 8.55.316.017 I slot release: id 0 | task 17802 | stop processing: n_tokens = 402, truncated = 0 8.55.320.589 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 402, t_last = 388266359402 8.55.320.620 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 458.484 MiB) 8.55.331.552 I slot launch_slot_: id 0 | task 17845 | processing task, is_child = 0 8.57.036.256 I slot print_timing: id 0 | task 17845 | prompt eval time = 790.20 ms / 333 tokens ( 2.37 ms per token, 421.41 tokens per second) 8.57.036.259 I slot print_timing: id 0 | task 17845 | eval time = 914.49 ms / 45 tokens ( 20.78 ms per token, 48.11 tokens per second) 8.57.036.259 I slot print_timing: id 0 | task 17845 | total time = 1704.69 ms / 378 tokens 8.57.036.260 I slot print_timing: id 0 | task 17845 | graphs reused = 16932 8.57.036.260 I slot print_timing: id 0 | task 17845 | graph reallocs = 0 / 0 (same size) / (changed size) 8.57.036.289 I slot release: id 0 | task 17845 | stop processing: n_tokens = 409, truncated = 0 8.57.041.033 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 388268079674 8.57.041.066 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 454.808 MiB) 8.57.050.716 I slot launch_slot_: id 0 | task 17893 | processing task, is_child = 0 9.00.911.807 I slot print_timing: id 0 | task 17893 | n_gen = 149, tg = 49.23 t/s, tg_3s = 49.56 t/s 9.03.917.305 I slot print_timing: id 0 | task 17893 | n_gen = 297, tg = 49.24 t/s, tg_3s = 49.24 t/s 9.06.934.325 I slot print_timing: id 0 | task 17893 | n_gen = 445, tg = 49.18 t/s, tg_3s = 49.06 t/s 9.09.944.826 I slot print_timing: id 0 | task 17893 | n_gen = 593, tg = 49.17 t/s, tg_3s = 49.16 t/s 9.12.964.896 I slot print_timing: id 0 | task 17893 | n_gen = 741, tg = 49.14 t/s, tg_3s = 49.01 t/s 9.15.965.403 I slot print_timing: id 0 | task 17893 | n_gen = 888, tg = 49.11 t/s, tg_3s = 48.99 t/s 9.18.749.461 I slot print_timing: id 0 | task 17893 | prompt eval time = 854.82 ms / 346 tokens ( 2.47 ms per token, 404.76 tokens per second) 9.18.749.467 I slot print_timing: id 0 | task 17893 | eval time = 20843.91 ms / 1024 tokens ( 20.38 ms per token, 49.08 tokens per second) 9.18.749.468 I slot print_timing: id 0 | task 17893 | total time = 21698.73 ms / 1370 tokens 9.18.749.469 I slot print_timing: id 0 | task 17893 | graphs reused = 17950 9.18.749.469 I slot print_timing: id 0 | task 17893 | graph reallocs = 0 / 0 (same size) / (changed size) 9.18.749.501 I slot release: id 0 | task 17893 | stop processing: n_tokens = 1401, truncated = 0 9.18.754.317 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1401, t_last = 388289792886 9.18.754.394 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 458.895 MiB) 9.18.769.941 I slot launch_slot_: id 0 | task 18920 | processing task, is_child = 0 9.20.848.450 I slot print_timing: id 0 | task 18920 | prompt eval time = 761.58 ms / 325 tokens ( 2.34 ms per token, 426.75 tokens per second) 9.20.848.456 I slot print_timing: id 0 | task 18920 | eval time = 1316.92 ms / 66 tokens ( 20.26 ms per token, 49.36 tokens per second) 9.20.848.457 I slot print_timing: id 0 | task 18920 | total time = 2078.50 ms / 391 tokens 9.20.848.457 I slot print_timing: id 0 | task 18920 | graphs reused = 18014 9.20.848.458 I slot print_timing: id 0 | task 18920 | graph reallocs = 0 / 0 (same size) / (changed size) 9.20.848.494 I slot release: id 0 | task 18920 | stop processing: n_tokens = 422, truncated = 0 9.20.853.106 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 422, t_last = 388291891879 9.20.853.140 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 461.163 MiB) 9.20.862.298 I slot launch_slot_: id 0 | task 18989 | processing task, is_child = 0 9.24.658.122 I slot print_timing: id 0 | task 18989 | n_gen = 150, tg = 49.35 t/s, tg_3s = 49.69 t/s 9.27.673.140 I slot print_timing: id 0 | task 18989 | n_gen = 298, tg = 49.22 t/s, tg_3s = 49.09 t/s 9.30.675.198 I slot print_timing: id 0 | task 18989 | n_gen = 445, tg = 49.14 t/s, tg_3s = 48.97 t/s 9.31.101.942 I slot print_timing: id 0 | task 18989 | prompt eval time = 776.86 ms / 322 tokens ( 2.41 ms per token, 414.49 tokens per second) 9.31.101.946 I slot print_timing: id 0 | task 18989 | eval time = 9462.77 ms / 466 tokens ( 20.35 ms per token, 49.14 tokens per second) 9.31.101.946 I slot print_timing: id 0 | task 18989 | total time = 10239.64 ms / 788 tokens 9.31.101.947 I slot print_timing: id 0 | task 18989 | graphs reused = 18476 9.31.101.948 I slot print_timing: id 0 | task 18989 | graph reallocs = 0 / 0 (same size) / (changed size) 9.31.101.975 I slot release: id 0 | task 18989 | stop processing: n_tokens = 819, truncated = 0 9.31.106.431 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 819, t_last = 388302145360 9.31.116.298 I slot launch_slot_: id 0 | task 19458 | processing task, is_child = 0 9.34.912.643 I slot print_timing: id 0 | task 19458 | n_gen = 150, tg = 49.61 t/s, tg_3s = 49.94 t/s 9.37.931.161 I slot print_timing: id 0 | task 19458 | n_gen = 298, tg = 49.32 t/s, tg_3s = 49.03 t/s 9.40.238.927 I slot print_timing: id 0 | task 19458 | prompt eval time = 792.64 ms / 338 tokens ( 2.35 ms per token, 426.42 tokens per second) 9.40.238.932 I slot print_timing: id 0 | task 19458 | eval time = 8329.98 ms / 411 tokens ( 20.32 ms per token, 49.22 tokens per second) 9.40.238.933 I slot print_timing: id 0 | task 19458 | total time = 9122.62 ms / 749 tokens 9.40.238.933 I slot print_timing: id 0 | task 19458 | graphs reused = 18883 9.40.238.934 I slot print_timing: id 0 | task 19458 | graph reallocs = 0 / 0 (same size) / (changed size) 9.40.238.967 I slot release: id 0 | task 19458 | stop processing: n_tokens = 780, truncated = 0 9.40.243.836 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 780, t_last = 388311282352 9.40.243.904 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 455.453 MiB) 9.40.253.446 I slot launch_slot_: id 0 | task 19872 | processing task, is_child = 0 9.44.078.578 I slot print_timing: id 0 | task 19872 | n_gen = 149, tg = 49.22 t/s, tg_3s = 49.55 t/s 9.47.092.164 I slot print_timing: id 0 | task 19872 | n_gen = 297, tg = 49.16 t/s, tg_3s = 49.11 t/s 9.50.104.359 I slot print_timing: id 0 | task 19872 | n_gen = 445, tg = 49.15 t/s, tg_3s = 49.13 t/s 9.53.115.365 I slot print_timing: id 0 | task 19872 | n_gen = 593, tg = 49.15 t/s, tg_3s = 49.15 t/s 9.56.116.724 I slot print_timing: id 0 | task 19872 | n_gen = 740, tg = 49.12 t/s, tg_3s = 48.98 t/s 9.59.134.704 I slot print_timing: id 0 | task 19872 | n_gen = 886, tg = 48.99 t/s, tg_3s = 48.38 t/s 10.01.963.770 I slot print_timing: id 0 | task 19872 | prompt eval time = 817.95 ms / 347 tokens ( 2.36 ms per token, 424.23 tokens per second) 10.01.963.775 I slot print_timing: id 0 | task 19872 | eval time = 20892.37 ms / 1024 tokens ( 20.42 ms per token, 48.97 tokens per second) 10.01.963.775 I slot print_timing: id 0 | task 19872 | total time = 21710.31 ms / 1371 tokens 10.01.963.776 I slot print_timing: id 0 | task 19872 | graphs reused = 19901 10.01.963.776 I slot print_timing: id 0 | task 19872 | graph reallocs = 0 / 0 (same size) / (changed size) 10.01.963.809 I slot release: id 0 | task 19872 | stop processing: n_tokens = 1402, truncated = 0 10.01.968.405 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1402, t_last = 388333007195 10.01.968.485 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 458.719 MiB) 10.01.991.098 I slot launch_slot_: id 0 | task 20899 | processing task, is_child = 0 10.03.898.329 I slot print_timing: id 0 | task 20899 | prompt eval time = 795.53 ms / 331 tokens ( 2.40 ms per token, 416.07 tokens per second) 10.03.898.334 I slot print_timing: id 0 | task 20899 | eval time = 1111.69 ms / 56 tokens ( 20.21 ms per token, 49.47 tokens per second) 10.03.898.335 I slot print_timing: id 0 | task 20899 | total time = 1907.22 ms / 387 tokens 10.03.898.336 I slot print_timing: id 0 | task 20899 | graphs reused = 19955 10.03.898.336 I slot print_timing: id 0 | task 20899 | graph reallocs = 0 / 0 (same size) / (changed size) 10.03.898.369 I slot release: id 0 | task 20899 | stop processing: n_tokens = 418, truncated = 0 10.03.902.657 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 418, t_last = 388334941754 10.03.902.687 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 391.623 MiB) 10.03.911.681 I slot launch_slot_: id 0 | task 20958 | processing task, is_child = 0 10.05.626.396 I slot print_timing: id 0 | task 20958 | prompt eval time = 804.09 ms / 345 tokens ( 2.33 ms per token, 429.05 tokens per second) 10.05.626.402 I slot print_timing: id 0 | task 20958 | eval time = 910.61 ms / 45 tokens ( 20.70 ms per token, 48.32 tokens per second) 10.05.626.403 I slot print_timing: id 0 | task 20958 | total time = 1714.70 ms / 390 tokens 10.05.626.403 I slot print_timing: id 0 | task 20958 | graphs reused = 19998 10.05.626.404 I slot print_timing: id 0 | task 20958 | graph reallocs = 0 / 0 (same size) / (changed size) 10.05.626.436 I slot release: id 0 | task 20958 | stop processing: n_tokens = 421, truncated = 0 10.05.630.739 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 421, t_last = 388336669821 10.05.630.771 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 456.392 MiB) 10.05.640.123 I slot launch_slot_: id 0 | task 21006 | processing task, is_child = 0 10.09.430.692 I slot print_timing: id 0 | task 21006 | n_gen = 149, tg = 49.25 t/s, tg_3s = 49.58 t/s 10.11.184.349 I slot print_timing: id 0 | task 21006 | prompt eval time = 785.54 ms / 320 tokens ( 2.45 ms per token, 407.36 tokens per second) 10.11.184.356 I slot print_timing: id 0 | task 21006 | eval time = 4758.68 ms / 235 tokens ( 20.34 ms per token, 49.17 tokens per second) 10.11.184.356 I slot print_timing: id 0 | task 21006 | total time = 5544.22 ms / 555 tokens 10.11.184.357 I slot print_timing: id 0 | task 21006 | graphs reused = 20230 10.11.184.357 I slot print_timing: id 0 | task 21006 | graph reallocs = 0 / 0 (same size) / (changed size) 10.11.184.385 I slot release: id 0 | task 21006 | stop processing: n_tokens = 586, truncated = 0 10.11.189.048 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 586, t_last = 388342227770 10.11.189.090 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 466.325 MiB) 10.11.199.259 I slot launch_slot_: id 0 | task 21244 | processing task, is_child = 0 10.12.866.098 I slot print_timing: id 0 | task 21244 | prompt eval time = 715.33 ms / 297 tokens ( 2.41 ms per token, 415.19 tokens per second) 10.12.866.104 I slot print_timing: id 0 | task 21244 | eval time = 951.50 ms / 47 tokens ( 20.68 ms per token, 48.34 tokens per second) 10.12.866.105 I slot print_timing: id 0 | task 21244 | total time = 1666.83 ms / 344 tokens 10.12.866.106 I slot print_timing: id 0 | task 21244 | graphs reused = 20275 10.12.866.106 I slot print_timing: id 0 | task 21244 | graph reallocs = 0 / 0 (same size) / (changed size) 10.12.866.137 I slot release: id 0 | task 21244 | stop processing: n_tokens = 375, truncated = 0 10.12.870.682 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 375, t_last = 388343909522 10.12.870.714 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 462.395 MiB) 10.12.879.902 I slot launch_slot_: id 0 | task 21294 | processing task, is_child = 0 10.16.691.267 I slot print_timing: id 0 | task 21294 | n_gen = 149, tg = 49.20 t/s, tg_3s = 49.53 t/s 10.19.103.142 I slot print_timing: id 0 | task 21294 | prompt eval time = 803.22 ms / 343 tokens ( 2.34 ms per token, 427.03 tokens per second) 10.19.103.148 I slot print_timing: id 0 | task 21294 | eval time = 5420.01 ms / 267 tokens ( 20.38 ms per token, 49.08 tokens per second) 10.19.103.149 I slot print_timing: id 0 | task 21294 | total time = 6223.23 ms / 610 tokens 10.19.103.149 I slot print_timing: id 0 | task 21294 | graphs reused = 20539 10.19.103.150 I slot print_timing: id 0 | task 21294 | graph reallocs = 0 / 0 (same size) / (changed size) 10.19.103.182 I slot release: id 0 | task 21294 | stop processing: n_tokens = 641, truncated = 0 10.19.107.828 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 641, t_last = 388350146567 10.19.117.234 I slot launch_slot_: id 0 | task 21564 | processing task, is_child = 0 10.21.943.605 I slot print_timing: id 0 | task 21564 | prompt eval time = 831.95 ms / 371 tokens ( 2.24 ms per token, 445.94 tokens per second) 10.21.943.611 I slot print_timing: id 0 | task 21564 | eval time = 1994.41 ms / 99 tokens ( 20.35 ms per token, 49.14 tokens per second) 10.21.943.612 I slot print_timing: id 0 | task 21564 | total time = 2826.36 ms / 470 tokens 10.21.943.612 I slot print_timing: id 0 | task 21564 | graphs reused = 20636 10.21.943.613 I slot print_timing: id 0 | task 21564 | graph reallocs = 0 / 0 (same size) / (changed size) 10.21.943.645 I slot release: id 0 | task 21564 | stop processing: n_tokens = 501, truncated = 0 10.21.947.687 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 501, t_last = 388352987030 10.21.947.722 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.246 MiB) 10.21.956.986 I slot launch_slot_: id 0 | task 21666 | processing task, is_child = 0 10.23.594.100 I slot print_timing: id 0 | task 21666 | prompt eval time = 744.33 ms / 292 tokens ( 2.55 ms per token, 392.30 tokens per second) 10.23.594.105 I slot print_timing: id 0 | task 21666 | eval time = 892.77 ms / 45 tokens ( 20.29 ms per token, 49.28 tokens per second) 10.23.594.106 I slot print_timing: id 0 | task 21666 | total time = 1637.10 ms / 337 tokens 10.23.594.107 I slot print_timing: id 0 | task 21666 | graphs reused = 20679 10.23.594.107 I slot print_timing: id 0 | task 21666 | graph reallocs = 0 / 0 (same size) / (changed size) 10.23.594.132 I slot release: id 0 | task 21666 | stop processing: n_tokens = 368, truncated = 0 10.23.598.571 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 368, t_last = 388354637517 10.23.598.600 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.986 MiB) 10.23.607.736 I slot launch_slot_: id 0 | task 21714 | processing task, is_child = 0 10.25.247.963 I slot print_timing: id 0 | task 21714 | prompt eval time = 726.14 ms / 301 tokens ( 2.41 ms per token, 414.52 tokens per second) 10.25.247.966 I slot print_timing: id 0 | task 21714 | eval time = 914.08 ms / 46 tokens ( 20.31 ms per token, 49.23 tokens per second) 10.25.247.967 I slot print_timing: id 0 | task 21714 | total time = 1640.22 ms / 347 tokens 10.25.247.967 I slot print_timing: id 0 | task 21714 | graphs reused = 20723 10.25.247.968 I slot print_timing: id 0 | task 21714 | graph reallocs = 0 / 0 (same size) / (changed size) 10.25.247.994 I slot release: id 0 | task 21714 | stop processing: n_tokens = 378, truncated = 0 10.25.252.405 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 378, t_last = 388356291380 10.25.252.437 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 385.542 MiB) 10.25.263.110 I slot launch_slot_: id 0 | task 21763 | processing task, is_child = 0 10.29.012.790 I slot print_timing: id 0 | task 21763 | n_gen = 149, tg = 49.27 t/s, tg_3s = 49.60 t/s 10.29.421.385 I slot print_timing: id 0 | task 21763 | prompt eval time = 745.76 ms / 303 tokens ( 2.46 ms per token, 406.30 tokens per second) 10.29.421.391 I slot print_timing: id 0 | task 21763 | eval time = 3412.50 ms / 169 tokens ( 20.31 ms per token, 49.23 tokens per second) 10.29.421.391 I slot print_timing: id 0 | task 21763 | total time = 4158.26 ms / 472 tokens 10.29.421.392 I slot print_timing: id 0 | task 21763 | graphs reused = 20890 10.29.421.392 I slot print_timing: id 0 | task 21763 | graph reallocs = 0 / 0 (same size) / (changed size) 10.29.421.422 I slot release: id 0 | task 21763 | stop processing: n_tokens = 503, truncated = 0 10.29.425.892 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 503, t_last = 388360464807 10.29.425.929 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.246 MiB) 10.29.435.160 I slot launch_slot_: id 0 | task 21935 | processing task, is_child = 0 10.31.166.336 I slot print_timing: id 0 | task 21935 | prompt eval time = 776.28 ms / 321 tokens ( 2.42 ms per token, 413.51 tokens per second) 10.31.166.342 I slot print_timing: id 0 | task 21935 | eval time = 954.88 ms / 48 tokens ( 20.32 ms per token, 49.22 tokens per second) 10.31.166.342 I slot print_timing: id 0 | task 21935 | total time = 1731.16 ms / 369 tokens 10.31.166.343 I slot print_timing: id 0 | task 21935 | graphs reused = 20936 10.31.166.344 I slot print_timing: id 0 | task 21935 | graph reallocs = 0 / 0 (same size) / (changed size) 10.31.166.371 I slot release: id 0 | task 21935 | stop processing: n_tokens = 400, truncated = 0 10.31.170.878 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 388362209757 10.31.170.911 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 404.901 MiB) 10.31.180.785 I slot launch_slot_: id 0 | task 21986 | processing task, is_child = 0 10.33.043.215 I slot print_timing: id 0 | task 21986 | prompt eval time = 783.65 ms / 322 tokens ( 2.43 ms per token, 410.90 tokens per second) 10.33.043.221 I slot print_timing: id 0 | task 21986 | eval time = 1078.77 ms / 54 tokens ( 20.35 ms per token, 49.13 tokens per second) 10.33.043.222 I slot print_timing: id 0 | task 21986 | total time = 1862.42 ms / 376 tokens 10.33.043.222 I slot print_timing: id 0 | task 21986 | graphs reused = 20988 10.33.043.223 I slot print_timing: id 0 | task 21986 | graph reallocs = 0 / 0 (same size) / (changed size) 10.33.043.250 I slot release: id 0 | task 21986 | stop processing: n_tokens = 407, truncated = 0 10.33.047.838 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 407, t_last = 388364086635 10.33.047.870 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 384.056 MiB) 10.33.057.271 I slot launch_slot_: id 0 | task 22043 | processing task, is_child = 0 10.34.751.328 I slot print_timing: id 0 | task 22043 | prompt eval time = 781.21 ms / 323 tokens ( 2.42 ms per token, 413.46 tokens per second) 10.34.751.335 I slot print_timing: id 0 | task 22043 | eval time = 912.84 ms / 46 tokens ( 20.29 ms per token, 49.30 tokens per second) 10.34.751.335 I slot print_timing: id 0 | task 22043 | total time = 1694.05 ms / 369 tokens 10.34.751.336 I slot print_timing: id 0 | task 22043 | graphs reused = 21032 10.34.751.337 I slot print_timing: id 0 | task 22043 | graph reallocs = 0 / 0 (same size) / (changed size) 10.34.751.374 I slot release: id 0 | task 22043 | stop processing: n_tokens = 400, truncated = 0 10.34.755.862 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 388365794759 10.34.755.892 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 384.975 MiB) 10.34.765.320 I slot launch_slot_: id 0 | task 22092 | processing task, is_child = 0 10.38.528.123 I slot print_timing: id 0 | task 22092 | n_gen = 149, tg = 49.28 t/s, tg_3s = 49.61 t/s 10.40.016.201 I slot print_timing: id 0 | task 22092 | prompt eval time = 759.52 ms / 321 tokens ( 2.37 ms per token, 422.64 tokens per second) 10.40.016.207 I slot print_timing: id 0 | task 22092 | eval time = 4491.35 ms / 222 tokens ( 20.32 ms per token, 49.21 tokens per second) 10.40.016.208 I slot print_timing: id 0 | task 22092 | total time = 5250.87 ms / 543 tokens 10.40.016.208 I slot print_timing: id 0 | task 22092 | graphs reused = 21251 10.40.016.209 I slot print_timing: id 0 | task 22092 | graph reallocs = 0 / 0 (same size) / (changed size) 10.40.016.236 I slot release: id 0 | task 22092 | stop processing: n_tokens = 574, truncated = 0 10.40.020.841 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 574, t_last = 388371059621 10.40.020.885 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.534 MiB) 10.40.030.150 I slot launch_slot_: id 0 | task 22317 | processing task, is_child = 0 10.43.801.691 I slot print_timing: id 0 | task 22317 | n_gen = 150, tg = 49.38 t/s, tg_3s = 49.71 t/s 10.46.814.601 I slot print_timing: id 0 | task 22317 | n_gen = 298, tg = 49.25 t/s, tg_3s = 49.12 t/s 10.47.302.154 I slot print_timing: id 0 | task 22317 | prompt eval time = 753.97 ms / 322 tokens ( 2.34 ms per token, 427.07 tokens per second) 10.47.302.160 I slot print_timing: id 0 | task 22317 | eval time = 6518.03 ms / 322 tokens ( 20.31 ms per token, 49.25 tokens per second) 10.47.302.160 I slot print_timing: id 0 | task 22317 | total time = 7271.99 ms / 644 tokens 10.47.302.161 I slot print_timing: id 0 | task 22317 | graphs reused = 21570 10.47.302.162 I slot print_timing: id 0 | task 22317 | graph reallocs = 0 / 0 (same size) / (changed size) 10.47.302.188 I slot release: id 0 | task 22317 | stop processing: n_tokens = 675, truncated = 0 10.47.306.748 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 675, t_last = 388378345574 10.47.306.793 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 383.763 MiB) 10.47.316.136 I slot launch_slot_: id 0 | task 22642 | processing task, is_child = 0 10.49.028.319 I slot print_timing: id 0 | task 22642 | prompt eval time = 797.11 ms / 337 tokens ( 2.37 ms per token, 422.78 tokens per second) 10.49.028.326 I slot print_timing: id 0 | task 22642 | eval time = 915.07 ms / 46 tokens ( 20.33 ms per token, 49.18 tokens per second) 10.49.028.326 I slot print_timing: id 0 | task 22642 | total time = 1712.18 ms / 383 tokens 10.49.028.327 I slot print_timing: id 0 | task 22642 | graphs reused = 21614 10.49.028.327 I slot print_timing: id 0 | task 22642 | graph reallocs = 0 / 0 (same size) / (changed size) 10.49.028.355 I slot release: id 0 | task 22642 | stop processing: n_tokens = 414, truncated = 0 10.49.032.845 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 388380071740 10.49.032.881 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 384.740 MiB) 10.49.042.383 I slot launch_slot_: id 0 | task 22691 | processing task, is_child = 0 10.50.757.026 I slot print_timing: id 0 | task 22691 | prompt eval time = 780.50 ms / 325 tokens ( 2.40 ms per token, 416.40 tokens per second) 10.50.757.032 I slot print_timing: id 0 | task 22691 | eval time = 934.13 ms / 47 tokens ( 20.31 ms per token, 49.24 tokens per second) 10.50.757.034 I slot print_timing: id 0 | task 22691 | total time = 1714.63 ms / 372 tokens 10.50.757.035 I slot print_timing: id 0 | task 22691 | graphs reused = 21659 10.50.757.035 I slot print_timing: id 0 | task 22691 | graph reallocs = 0 / 0 (same size) / (changed size) 10.50.757.063 I slot release: id 0 | task 22691 | stop processing: n_tokens = 403, truncated = 0 10.50.761.655 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 403, t_last = 388381800448 10.50.761.687 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 384.877 MiB) 10.50.771.311 I slot launch_slot_: id 0 | task 22741 | processing task, is_child = 0 10.53.455.910 I slot print_timing: id 0 | task 22741 | prompt eval time = 799.32 ms / 331 tokens ( 2.41 ms per token, 414.10 tokens per second) 10.53.455.916 I slot print_timing: id 0 | task 22741 | eval time = 1885.27 ms / 94 tokens ( 20.27 ms per token, 49.33 tokens per second) 10.53.455.917 I slot print_timing: id 0 | task 22741 | total time = 2684.59 ms / 425 tokens 10.53.455.918 I slot print_timing: id 0 | task 22741 | graphs reused = 21751 10.53.455.918 I slot print_timing: id 0 | task 22741 | graph reallocs = 0 / 0 (same size) / (changed size) 10.53.455.949 I slot release: id 0 | task 22741 | stop processing: n_tokens = 456, truncated = 0 10.53.460.428 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 456, t_last = 388384499334 10.53.460.460 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 404.275 MiB) 10.53.470.378 I slot launch_slot_: id 0 | task 22838 | processing task, is_child = 0 10.57.237.966 I slot print_timing: id 0 | task 22838 | n_gen = 149, tg = 49.27 t/s, tg_3s = 49.60 t/s 10.58.398.513 I slot print_timing: id 0 | task 22838 | prompt eval time = 763.83 ms / 336 tokens ( 2.27 ms per token, 439.89 tokens per second) 10.58.398.519 I slot print_timing: id 0 | task 22838 | eval time = 4164.29 ms / 206 tokens ( 20.31 ms per token, 49.23 tokens per second) 10.58.398.520 I slot print_timing: id 0 | task 22838 | total time = 4928.13 ms / 542 tokens 10.58.398.520 I slot print_timing: id 0 | task 22838 | graphs reused = 21954 10.58.398.521 I slot print_timing: id 0 | task 22838 | graph reallocs = 0 / 0 (same size) / (changed size) 10.58.398.563 I slot release: id 0 | task 22838 | stop processing: n_tokens = 573, truncated = 0 10.58.403.233 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 573, t_last = 388389441948 10.58.403.274 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 385.131 MiB) 10.58.412.668 I slot launch_slot_: id 0 | task 23047 | processing task, is_child = 0 10.59.639.032 I slot print_timing: id 0 | task 23047 | prompt eval time = 837.88 ms / 349 tokens ( 2.40 ms per token, 416.53 tokens per second) 10.59.639.038 I slot print_timing: id 0 | task 23047 | eval time = 388.48 ms / 20 tokens ( 20.45 ms per token, 48.91 tokens per second) 10.59.639.039 I slot print_timing: id 0 | task 23047 | total time = 1226.36 ms / 369 tokens 10.59.639.040 I slot print_timing: id 0 | task 23047 | graphs reused = 21972 10.59.639.040 I slot print_timing: id 0 | task 23047 | graph reallocs = 0 / 0 (same size) / (changed size) 10.59.639.070 I slot release: id 0 | task 23047 | stop processing: n_tokens = 400, truncated = 0 10.59.643.651 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 388390682456 10.59.643.680 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 392.894 MiB) 10.59.652.991 I slot launch_slot_: id 0 | task 23070 | processing task, is_child = 0 11.03.427.849 I slot print_timing: id 0 | task 23070 | n_gen = 149, tg = 49.18 t/s, tg_3s = 49.51 t/s 11.06.428.559 I slot print_timing: id 0 | task 23070 | n_gen = 296, tg = 49.08 t/s, tg_3s = 48.99 t/s 11.09.432.106 I slot print_timing: id 0 | task 23070 | n_gen = 443, tg = 49.04 t/s, tg_3s = 48.94 t/s 11.12.432.488 I slot print_timing: id 0 | task 23070 | n_gen = 590, tg = 49.03 t/s, tg_3s = 48.99 t/s 11.14.742.730 I slot print_timing: id 0 | task 23070 | prompt eval time = 765.36 ms / 336 tokens ( 2.28 ms per token, 439.01 tokens per second) 11.14.742.732 I slot print_timing: id 0 | task 23070 | eval time = 14324.37 ms / 703 tokens ( 20.41 ms per token, 49.01 tokens per second) 11.14.742.733 I slot print_timing: id 0 | task 23070 | total time = 15089.73 ms / 1039 tokens 11.14.742.734 I slot print_timing: id 0 | task 23070 | graphs reused = 22670 11.14.742.735 I slot print_timing: id 0 | task 23070 | graph reallocs = 0 / 0 (same size) / (changed size) 11.14.742.763 I slot release: id 0 | task 23070 | stop processing: n_tokens = 1070, truncated = 0 11.14.747.398 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1070, t_last = 388405786148 11.14.747.458 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 392.132 MiB) 11.14.758.422 I slot launch_slot_: id 0 | task 23776 | processing task, is_child = 0 11.18.561.646 I slot print_timing: id 0 | task 23776 | n_gen = 149, tg = 49.22 t/s, tg_3s = 49.55 t/s 11.21.562.370 I slot print_timing: id 0 | task 23776 | n_gen = 296, tg = 49.10 t/s, tg_3s = 48.99 t/s 11.24.483.923 I slot print_timing: id 0 | task 23776 | prompt eval time = 796.05 ms / 349 tokens ( 2.28 ms per token, 438.41 tokens per second) 11.24.483.929 I slot print_timing: id 0 | task 23776 | eval time = 8929.44 ms / 439 tokens ( 20.39 ms per token, 49.05 tokens per second) 11.24.483.929 I slot print_timing: id 0 | task 23776 | total time = 9725.49 ms / 788 tokens 11.24.483.930 I slot print_timing: id 0 | task 23776 | graphs reused = 23105 11.24.483.930 I slot print_timing: id 0 | task 23776 | graph reallocs = 0 / 0 (same size) / (changed size) 11.24.483.962 I slot release: id 0 | task 23776 | stop processing: n_tokens = 819, truncated = 0 11.24.488.751 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 819, t_last = 388415527347 11.24.488.801 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 404.294 MiB) 11.24.498.262 I slot launch_slot_: id 0 | task 24218 | processing task, is_child = 0 11.26.473.230 I slot print_timing: id 0 | task 24218 | prompt eval time = 796.89 ms / 349 tokens ( 2.28 ms per token, 437.95 tokens per second) 11.26.473.237 I slot print_timing: id 0 | task 24218 | eval time = 1178.07 ms / 59 tokens ( 20.31 ms per token, 49.23 tokens per second) 11.26.473.238 I slot print_timing: id 0 | task 24218 | total time = 1974.96 ms / 408 tokens 11.26.473.238 I slot print_timing: id 0 | task 24218 | graphs reused = 23162 11.26.473.239 I slot print_timing: id 0 | task 24218 | graph reallocs = 0 / 0 (same size) / (changed size) 11.26.473.271 I slot release: id 0 | task 24218 | stop processing: n_tokens = 439, truncated = 0 11.26.477.868 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 439, t_last = 388417516656 11.26.477.903 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 385.053 MiB) 11.26.487.245 I slot launch_slot_: id 0 | task 24280 | processing task, is_child = 0 11.30.366.421 I slot print_timing: id 0 | task 24280 | n_gen = 149, tg = 49.18 t/s, tg_3s = 49.51 t/s 11.33.377.651 I slot print_timing: id 0 | task 24280 | n_gen = 297, tg = 49.17 t/s, tg_3s = 49.15 t/s 11.33.886.737 I slot print_timing: id 0 | task 24280 | prompt eval time = 869.94 ms / 385 tokens ( 2.26 ms per token, 442.56 tokens per second) 11.33.886.742 I slot print_timing: id 0 | task 24280 | eval time = 6529.54 ms / 322 tokens ( 20.34 ms per token, 49.16 tokens per second) 11.33.886.742 I slot print_timing: id 0 | task 24280 | total time = 7399.48 ms / 707 tokens 11.33.886.743 I slot print_timing: id 0 | task 24280 | graphs reused = 23481 11.33.886.744 I slot print_timing: id 0 | task 24280 | graph reallocs = 0 / 0 (same size) / (changed size) 11.33.886.778 I slot release: id 0 | task 24280 | stop processing: n_tokens = 738, truncated = 0 11.33.891.399 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 738, t_last = 388424930163 11.33.891.448 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 385.112 MiB) 11.33.901.104 I slot launch_slot_: id 0 | task 24605 | processing task, is_child = 0 11.35.828.343 I slot print_timing: id 0 | task 24605 | prompt eval time = 792.34 ms / 328 tokens ( 2.42 ms per token, 413.96 tokens per second) 11.35.828.349 I slot print_timing: id 0 | task 24605 | eval time = 1134.88 ms / 57 tokens ( 20.27 ms per token, 49.34 tokens per second) 11.35.828.349 I slot print_timing: id 0 | task 24605 | total time = 1927.23 ms / 385 tokens 11.35.828.350 I slot print_timing: id 0 | task 24605 | graphs reused = 23536 11.35.828.350 I slot print_timing: id 0 | task 24605 | graph reallocs = 0 / 0 (same size) / (changed size) 11.35.828.379 I slot release: id 0 | task 24605 | stop processing: n_tokens = 416, truncated = 0 11.35.897.765 I srv operator(): operator(): cleaning up before exit...