$ /Users/minipro/quantdiff/work/llama-b11869/src/build/bin/llama-server -m /Users/minipro/quantdiff/models/campaign/be92beb4e0fd/Sage-A1.5-IQ4_XS-exps.gguf --host 127.0.0.1 --port 8089 -c 4096 -np 1 -ngl 999 -fa on --jinja --seed 1234 --no-webui -a quant 0.00.042.787 I srv llama_server: initializing ... 0.00.042.798 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.042.889 I srv init_listene: The UI is disabled 0.00.042.890 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.042.936 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) 0.00.044.584 I srv load_model: loading model '/Users/minipro/quantdiff/models/campaign/be92beb4e0fd/Sage-A1.5-IQ4_XS-exps.gguf' 0.00.333.771 W model has unused tensor blk.40.attn_norm.weight (size = 8192 bytes) -- ignoring 0.00.333.779 W model has unused tensor blk.40.post_attention_norm.weight (size = 8192 bytes) -- ignoring 0.00.333.786 W model has unused tensor blk.40.attn_q.weight (size = 9437184 bytes) -- ignoring 0.00.333.788 W model has unused tensor blk.40.attn_k.weight (size = 589824 bytes) -- ignoring 0.00.333.791 W model has unused tensor blk.40.attn_v.weight (size = 860160 bytes) -- ignoring 0.00.333.798 W model has unused tensor blk.40.attn_output.weight (size = 4718592 bytes) -- ignoring 0.00.333.800 W model has unused tensor blk.40.attn_q_norm.weight (size = 1024 bytes) -- ignoring 0.00.333.802 W model has unused tensor blk.40.attn_k_norm.weight (size = 1024 bytes) -- ignoring 0.00.333.804 W model has unused tensor blk.40.ffn_gate_inp.weight (size = 2097152 bytes) -- ignoring 0.00.333.807 W model has unused tensor blk.40.ffn_down_exps.weight (size = 220200960 bytes) -- ignoring 0.00.333.811 W model has unused tensor blk.40.ffn_gate_exps.weight (size = 150994944 bytes) -- ignoring 0.00.333.813 W model has unused tensor blk.40.ffn_up_exps.weight (size = 150994944 bytes) -- ignoring 0.00.333.816 W model has unused tensor blk.40.ffn_gate_inp_shexp.weight (size = 8192 bytes) -- ignoring 0.00.333.818 W model has unused tensor blk.40.ffn_gate_shexp.weight (size = 589824 bytes) -- ignoring 0.00.333.820 W model has unused tensor blk.40.ffn_up_shexp.weight (size = 589824 bytes) -- ignoring 0.00.333.823 W model has unused tensor blk.40.ffn_down_shexp.weight (size = 860160 bytes) -- ignoring 0.00.333.825 W model has unused tensor blk.40.nextn.eh_proj.weight (size = 4718592 bytes) -- ignoring 0.00.333.828 W model has unused tensor blk.40.nextn.enorm.weight (size = 8192 bytes) -- ignoring 0.00.333.830 W model has unused tensor blk.40.nextn.hnorm.weight (size = 8192 bytes) -- ignoring 0.00.333.837 W model has unused tensor blk.40.nextn.shared_head_norm.weight (size = 8192 bytes) -- ignoring 0.01.167.862 I cmn init: llama threadpool init, n_threads = 8 0.01.241.239 I srv load_model: initializing, n_slots = 1, n_ctx_slot = 4096, kv_unified = 'false' 0.01.245.504 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.01.245.516 I srv server_run_i: model loaded 0.01.245.519 I srv server_on_li: listening on http://127.0.0.1:8089 0.02.025.595 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.02.025.827 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.03.731.760 I slot print_timing: id 0 | task 0 | prompt eval time = 896.46 ms / 368 tokens ( 2.44 ms per token, 410.50 tokens per second) 0.03.731.767 I slot print_timing: id 0 | task 0 | eval time = 809.45 ms / 41 tokens ( 20.24 ms per token, 49.42 tokens per second) 0.03.731.767 I slot print_timing: id 0 | task 0 | total time = 1705.92 ms / 409 tokens 0.03.731.768 I slot print_timing: id 0 | task 0 | graphs reused = 40 0.03.731.768 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.03.731.875 I slot release: id 0 | task 0 | stop processing: n_tokens = 408, truncated = 0 0.03.736.316 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 408, t_last = 390584183335 0.03.755.154 I slot launch_slot_: id 0 | task 44 | processing task, is_child = 0 0.05.362.638 I slot print_timing: id 0 | task 44 | prompt eval time = 779.24 ms / 322 tokens ( 2.42 ms per token, 413.22 tokens per second) 0.05.362.642 I slot print_timing: id 0 | task 44 | eval time = 828.23 ms / 42 tokens ( 20.20 ms per token, 49.50 tokens per second) 0.05.362.643 I slot print_timing: id 0 | task 44 | total time = 1607.47 ms / 364 tokens 0.05.362.643 I slot print_timing: id 0 | task 44 | graphs reused = 80 0.05.362.644 I slot print_timing: id 0 | task 44 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.362.683 I slot release: id 0 | task 44 | stop processing: n_tokens = 363, truncated = 0 0.05.367.150 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 363, t_last = 390585814142 0.05.384.923 I slot launch_slot_: id 0 | task 89 | processing task, is_child = 0 0.07.057.371 I slot print_timing: id 0 | task 89 | prompt eval time = 845.44 ms / 365 tokens ( 2.32 ms per token, 431.73 tokens per second) 0.07.057.376 I slot print_timing: id 0 | task 89 | eval time = 827.00 ms / 42 tokens ( 20.17 ms per token, 49.58 tokens per second) 0.07.057.377 I slot print_timing: id 0 | task 89 | total time = 1672.44 ms / 407 tokens 0.07.057.377 I slot print_timing: id 0 | task 89 | graphs reused = 120 0.07.057.378 I slot print_timing: id 0 | task 89 | graph reallocs = 0 / 0 (same size) / (changed size) 0.07.057.418 I slot release: id 0 | task 89 | stop processing: n_tokens = 406, truncated = 0 0.07.062.279 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 406, t_last = 390587508877 0.07.080.340 I slot launch_slot_: id 0 | task 134 | processing task, is_child = 0 0.08.833.003 I slot print_timing: id 0 | task 134 | prompt eval time = 903.85 ms / 397 tokens ( 2.28 ms per token, 439.23 tokens per second) 0.08.833.009 I slot print_timing: id 0 | task 134 | eval time = 848.80 ms / 43 tokens ( 20.21 ms per token, 49.48 tokens per second) 0.08.833.011 I slot print_timing: id 0 | task 134 | total time = 1752.65 ms / 440 tokens 0.08.833.011 I slot print_timing: id 0 | task 134 | graphs reused = 161 0.08.833.012 I slot print_timing: id 0 | task 134 | graph reallocs = 0 / 0 (same size) / (changed size) 0.08.833.067 I slot release: id 0 | task 134 | stop processing: n_tokens = 439, truncated = 0 0.08.837.723 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 0.08.855.424 I slot launch_slot_: id 0 | task 180 | processing task, is_child = 0 0.10.814.677 I slot print_timing: id 0 | task 180 | prompt eval time = 869.26 ms / 383 tokens ( 2.27 ms per token, 440.61 tokens per second) 0.10.814.682 I slot print_timing: id 0 | task 180 | eval time = 1089.98 ms / 55 tokens ( 20.18 ms per token, 49.54 tokens per second) 0.10.814.683 I slot print_timing: id 0 | task 180 | total time = 1959.24 ms / 438 tokens 0.10.814.683 I slot print_timing: id 0 | task 180 | graphs reused = 214 0.10.814.686 I slot print_timing: id 0 | task 180 | graph reallocs = 0 / 0 (same size) / (changed size) 0.10.814.718 I slot release: id 0 | task 180 | stop processing: n_tokens = 437, truncated = 0 0.10.819.308 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 390591266177 0.10.837.589 I slot launch_slot_: id 0 | task 238 | processing task, is_child = 0 0.12.745.197 I slot print_timing: id 0 | task 238 | prompt eval time = 818.36 ms / 372 tokens ( 2.20 ms per token, 454.57 tokens per second) 0.12.745.203 I slot print_timing: id 0 | task 238 | eval time = 1089.23 ms / 55 tokens ( 20.17 ms per token, 49.58 tokens per second) 0.12.745.203 I slot print_timing: id 0 | task 238 | total time = 1907.60 ms / 427 tokens 0.12.745.204 I slot print_timing: id 0 | task 238 | graphs reused = 267 0.12.745.204 I slot print_timing: id 0 | task 238 | graph reallocs = 0 / 0 (same size) / (changed size) 0.12.745.246 I slot release: id 0 | task 238 | stop processing: n_tokens = 426, truncated = 0 0.12.749.783 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 390593196705 0.12.767.846 I slot launch_slot_: id 0 | task 296 | processing task, is_child = 0 0.14.795.482 I slot print_timing: id 0 | task 296 | prompt eval time = 934.80 ms / 422 tokens ( 2.22 ms per token, 451.43 tokens per second) 0.14.795.489 I slot print_timing: id 0 | task 296 | eval time = 1092.82 ms / 55 tokens ( 20.24 ms per token, 49.41 tokens per second) 0.14.795.490 I slot print_timing: id 0 | task 296 | total time = 2027.63 ms / 477 tokens 0.14.795.490 I slot print_timing: id 0 | task 296 | graphs reused = 320 0.14.795.491 I slot print_timing: id 0 | task 296 | graph reallocs = 0 / 0 (same size) / (changed size) 0.14.795.537 I slot release: id 0 | task 296 | stop processing: n_tokens = 476, truncated = 0 0.14.800.521 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 476, t_last = 390595246996 0.14.818.756 I slot launch_slot_: id 0 | task 354 | processing task, is_child = 0 0.17.236.185 I slot print_timing: id 0 | task 354 | prompt eval time = 976.79 ms / 470 tokens ( 2.08 ms per token, 481.17 tokens per second) 0.17.236.192 I slot print_timing: id 0 | task 354 | eval time = 1440.62 ms / 72 tokens ( 20.29 ms per token, 49.28 tokens per second) 0.17.236.192 I slot print_timing: id 0 | task 354 | total time = 2417.42 ms / 542 tokens 0.17.236.193 I slot print_timing: id 0 | task 354 | graphs reused = 389 0.17.236.193 I slot print_timing: id 0 | task 354 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.236.253 I slot release: id 0 | task 354 | stop processing: n_tokens = 541, truncated = 0 0.17.240.543 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 541, t_last = 390597687712 0.17.259.339 I slot launch_slot_: id 0 | task 429 | processing task, is_child = 0 0.19.008.532 I slot print_timing: id 0 | task 429 | prompt eval time = 819.89 ms / 345 tokens ( 2.38 ms per token, 420.79 tokens per second) 0.19.008.539 I slot print_timing: id 0 | task 429 | eval time = 929.29 ms / 47 tokens ( 20.20 ms per token, 49.50 tokens per second) 0.19.008.539 I slot print_timing: id 0 | task 429 | total time = 1749.18 ms / 392 tokens 0.19.008.540 I slot print_timing: id 0 | task 429 | graphs reused = 434 0.19.008.540 I slot print_timing: id 0 | task 429 | graph reallocs = 0 / 0 (same size) / (changed size) 0.19.008.576 I slot release: id 0 | task 429 | stop processing: n_tokens = 391, truncated = 0 0.19.013.123 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 391, t_last = 390599460035 0.19.031.047 I slot launch_slot_: id 0 | task 479 | processing task, is_child = 0 0.20.678.249 I slot print_timing: id 0 | task 479 | prompt eval time = 837.70 ms / 364 tokens ( 2.30 ms per token, 434.52 tokens per second) 0.20.678.256 I slot print_timing: id 0 | task 479 | eval time = 809.49 ms / 41 tokens ( 20.24 ms per token, 49.41 tokens per second) 0.20.678.257 I slot print_timing: id 0 | task 479 | total time = 1647.19 ms / 405 tokens 0.20.678.258 I slot print_timing: id 0 | task 479 | graphs reused = 473 0.20.678.258 I slot print_timing: id 0 | task 479 | graph reallocs = 0 / 0 (same size) / (changed size) 0.20.678.304 I slot release: id 0 | task 479 | stop processing: n_tokens = 404, truncated = 0 0.20.682.908 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 404, t_last = 390601129763 0.20.700.992 I slot launch_slot_: id 0 | task 523 | processing task, is_child = 0 0.22.776.086 I slot print_timing: id 0 | task 523 | prompt eval time = 820.64 ms / 376 tokens ( 2.18 ms per token, 458.18 tokens per second) 0.22.776.092 I slot print_timing: id 0 | task 523 | eval time = 1254.45 ms / 62 tokens ( 20.56 ms per token, 48.63 tokens per second) 0.22.776.092 I slot print_timing: id 0 | task 523 | total time = 2075.09 ms / 438 tokens 0.22.776.093 I slot print_timing: id 0 | task 523 | graphs reused = 533 0.22.776.093 I slot print_timing: id 0 | task 523 | graph reallocs = 0 / 0 (same size) / (changed size) 0.22.776.124 I slot release: id 0 | task 523 | stop processing: n_tokens = 437, truncated = 0 0.22.780.807 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 390603227583 0.22.798.797 I slot launch_slot_: id 0 | task 588 | processing task, is_child = 0 0.24.635.489 I slot print_timing: id 0 | task 588 | prompt eval time = 906.24 ms / 412 tokens ( 2.20 ms per token, 454.63 tokens per second) 0.24.635.495 I slot print_timing: id 0 | task 588 | eval time = 930.44 ms / 47 tokens ( 20.23 ms per token, 49.44 tokens per second) 0.24.635.496 I slot print_timing: id 0 | task 588 | total time = 1836.68 ms / 459 tokens 0.24.635.496 I slot print_timing: id 0 | task 588 | graphs reused = 578 0.24.635.497 I slot print_timing: id 0 | task 588 | graph reallocs = 0 / 0 (same size) / (changed size) 0.24.635.530 I slot release: id 0 | task 588 | stop processing: n_tokens = 458, truncated = 0 0.24.640.126 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 390605086989 0.24.659.122 I slot launch_slot_: id 0 | task 638 | processing task, is_child = 0 0.26.741.582 I slot print_timing: id 0 | task 638 | prompt eval time = 851.23 ms / 376 tokens ( 2.26 ms per token, 441.71 tokens per second) 0.26.741.587 I slot print_timing: id 0 | task 638 | eval time = 1231.22 ms / 62 tokens ( 20.18 ms per token, 49.54 tokens per second) 0.26.741.588 I slot print_timing: id 0 | task 638 | total time = 2082.45 ms / 438 tokens 0.26.741.589 I slot print_timing: id 0 | task 638 | graphs reused = 638 0.26.741.591 I slot print_timing: id 0 | task 638 | graph reallocs = 0 / 0 (same size) / (changed size) 0.26.741.624 I slot release: id 0 | task 638 | stop processing: n_tokens = 437, truncated = 0 0.26.746.304 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 390607193083 0.26.764.496 I slot launch_slot_: id 0 | task 703 | processing task, is_child = 0 0.28.632.854 I slot print_timing: id 0 | task 703 | prompt eval time = 837.26 ms / 378 tokens ( 2.21 ms per token, 451.47 tokens per second) 0.28.632.857 I slot print_timing: id 0 | task 703 | eval time = 1031.09 ms / 52 tokens ( 20.22 ms per token, 49.46 tokens per second) 0.28.632.858 I slot print_timing: id 0 | task 703 | total time = 1868.35 ms / 430 tokens 0.28.632.858 I slot print_timing: id 0 | task 703 | graphs reused = 688 0.28.632.859 I slot print_timing: id 0 | task 703 | graph reallocs = 0 / 0 (same size) / (changed size) 0.28.632.893 I slot release: id 0 | task 703 | stop processing: n_tokens = 429, truncated = 0 0.28.637.338 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 429, t_last = 390609084353 0.28.655.521 I slot launch_slot_: id 0 | task 758 | processing task, is_child = 0 0.30.653.031 I slot print_timing: id 0 | task 758 | prompt eval time = 829.44 ms / 367 tokens ( 2.26 ms per token, 442.47 tokens per second) 0.30.653.038 I slot print_timing: id 0 | task 758 | eval time = 1168.06 ms / 58 tokens ( 20.49 ms per token, 48.80 tokens per second) 0.30.653.038 I slot print_timing: id 0 | task 758 | total time = 1997.50 ms / 425 tokens 0.30.653.039 I slot print_timing: id 0 | task 758 | graphs reused = 744 0.30.653.040 I slot print_timing: id 0 | task 758 | graph reallocs = 0 / 0 (same size) / (changed size) 0.30.653.067 I slot release: id 0 | task 758 | stop processing: n_tokens = 424, truncated = 0 0.30.657.550 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 390611104526 0.30.676.002 I slot launch_slot_: id 0 | task 819 | processing task, is_child = 0 0.32.511.282 I slot print_timing: id 0 | task 819 | prompt eval time = 822.21 ms / 347 tokens ( 2.37 ms per token, 422.03 tokens per second) 0.32.511.285 I slot print_timing: id 0 | task 819 | eval time = 1013.06 ms / 51 tokens ( 20.26 ms per token, 49.36 tokens per second) 0.32.511.287 I slot print_timing: id 0 | task 819 | total time = 1835.26 ms / 398 tokens 0.32.511.287 I slot print_timing: id 0 | task 819 | graphs reused = 793 0.32.511.288 I slot print_timing: id 0 | task 819 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.511.325 I slot release: id 0 | task 819 | stop processing: n_tokens = 397, truncated = 0 0.32.516.013 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 397, t_last = 390612962784 0.32.534.282 I slot launch_slot_: id 0 | task 873 | processing task, is_child = 0 0.34.464.975 I slot print_timing: id 0 | task 873 | prompt eval time = 859.90 ms / 369 tokens ( 2.33 ms per token, 429.12 tokens per second) 0.34.464.981 I slot print_timing: id 0 | task 873 | eval time = 1070.78 ms / 54 tokens ( 20.20 ms per token, 49.50 tokens per second) 0.34.464.982 I slot print_timing: id 0 | task 873 | total time = 1930.68 ms / 423 tokens 0.34.464.982 I slot print_timing: id 0 | task 873 | graphs reused = 845 0.34.464.983 I slot print_timing: id 0 | task 873 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.465.013 I slot release: id 0 | task 873 | stop processing: n_tokens = 422, truncated = 0 0.34.469.653 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 422, t_last = 390614916472 0.34.487.901 I slot launch_slot_: id 0 | task 930 | processing task, is_child = 0 0.36.121.149 I slot print_timing: id 0 | task 930 | prompt eval time = 825.06 ms / 352 tokens ( 2.34 ms per token, 426.64 tokens per second) 0.36.121.151 I slot print_timing: id 0 | task 930 | eval time = 808.18 ms / 41 tokens ( 20.20 ms per token, 49.49 tokens per second) 0.36.121.152 I slot print_timing: id 0 | task 930 | total time = 1633.24 ms / 393 tokens 0.36.121.153 I slot print_timing: id 0 | task 930 | graphs reused = 884 0.36.121.153 I slot print_timing: id 0 | task 930 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.121.184 I slot release: id 0 | task 930 | stop processing: n_tokens = 392, truncated = 0 0.36.125.691 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 392, t_last = 390616572644 0.36.144.189 I slot launch_slot_: id 0 | task 974 | processing task, is_child = 0 0.37.750.331 I slot print_timing: id 0 | task 974 | prompt eval time = 815.90 ms / 349 tokens ( 2.34 ms per token, 427.75 tokens per second) 0.37.750.337 I slot print_timing: id 0 | task 974 | eval time = 790.23 ms / 40 tokens ( 20.26 ms per token, 49.35 tokens per second) 0.37.750.338 I slot print_timing: id 0 | task 974 | total time = 1606.13 ms / 389 tokens 0.37.750.338 I slot print_timing: id 0 | task 974 | graphs reused = 922 0.37.750.339 I slot print_timing: id 0 | task 974 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.750.374 I slot release: id 0 | task 974 | stop processing: n_tokens = 388, truncated = 0 0.37.755.054 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 388, t_last = 390618201833 0.37.772.923 I slot launch_slot_: id 0 | task 1017 | processing task, is_child = 0 0.39.902.408 I slot print_timing: id 0 | task 1017 | prompt eval time = 859.15 ms / 384 tokens ( 2.24 ms per token, 446.95 tokens per second) 0.39.902.414 I slot print_timing: id 0 | task 1017 | eval time = 1270.33 ms / 63 tokens ( 20.49 ms per token, 48.81 tokens per second) 0.39.902.414 I slot print_timing: id 0 | task 1017 | total time = 2129.48 ms / 447 tokens 0.39.902.415 I slot print_timing: id 0 | task 1017 | graphs reused = 983 0.39.902.415 I slot print_timing: id 0 | task 1017 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.902.448 I slot release: id 0 | task 1017 | stop processing: n_tokens = 446, truncated = 0 0.39.907.001 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 446, t_last = 390620353908 0.39.925.208 I slot launch_slot_: id 0 | task 1083 | processing task, is_child = 0 0.41.784.645 I slot print_timing: id 0 | task 1083 | prompt eval time = 789.63 ms / 356 tokens ( 2.22 ms per token, 450.84 tokens per second) 0.41.784.651 I slot print_timing: id 0 | task 1083 | eval time = 1069.80 ms / 54 tokens ( 20.18 ms per token, 49.54 tokens per second) 0.41.784.652 I slot print_timing: id 0 | task 1083 | total time = 1859.43 ms / 410 tokens 0.41.784.652 I slot print_timing: id 0 | task 1083 | graphs reused = 1035 0.41.784.655 I slot print_timing: id 0 | task 1083 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.784.688 I slot release: id 0 | task 1083 | stop processing: n_tokens = 409, truncated = 0 0.41.790.086 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 390622236147 0.41.808.048 I slot launch_slot_: id 0 | task 1140 | processing task, is_child = 0 0.44.095.256 I slot print_timing: id 0 | task 1140 | prompt eval time = 895.33 ms / 410 tokens ( 2.18 ms per token, 457.93 tokens per second) 0.44.095.262 I slot print_timing: id 0 | task 1140 | eval time = 1391.86 ms / 70 tokens ( 20.17 ms per token, 49.57 tokens per second) 0.44.095.262 I slot print_timing: id 0 | task 1140 | total time = 2287.19 ms / 480 tokens 0.44.095.263 I slot print_timing: id 0 | task 1140 | graphs reused = 1103 0.44.095.263 I slot print_timing: id 0 | task 1140 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.095.298 I slot release: id 0 | task 1140 | stop processing: n_tokens = 479, truncated = 0 0.44.099.888 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 479, t_last = 390624546757 0.44.117.700 I slot launch_slot_: id 0 | task 1213 | processing task, is_child = 0 0.46.147.231 I slot print_timing: id 0 | task 1213 | prompt eval time = 877.14 ms / 385 tokens ( 2.28 ms per token, 438.93 tokens per second) 0.46.147.238 I slot print_timing: id 0 | task 1213 | eval time = 1152.38 ms / 58 tokens ( 20.22 ms per token, 49.46 tokens per second) 0.46.147.238 I slot print_timing: id 0 | task 1213 | total time = 2029.52 ms / 443 tokens 0.46.147.239 I slot print_timing: id 0 | task 1213 | graphs reused = 1159 0.46.147.240 I slot print_timing: id 0 | task 1213 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.147.267 I slot release: id 0 | task 1213 | stop processing: n_tokens = 442, truncated = 0 0.46.151.959 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 442, t_last = 390626598726 0.46.169.842 I slot launch_slot_: id 0 | task 1274 | processing task, is_child = 0 0.48.457.112 I slot print_timing: id 0 | task 1274 | prompt eval time = 874.91 ms / 395 tokens ( 2.21 ms per token, 451.48 tokens per second) 0.48.457.117 I slot print_timing: id 0 | task 1274 | eval time = 1412.35 ms / 71 tokens ( 20.18 ms per token, 49.56 tokens per second) 0.48.457.118 I slot print_timing: id 0 | task 1274 | total time = 2287.26 ms / 466 tokens 0.48.457.119 I slot print_timing: id 0 | task 1274 | graphs reused = 1228 0.48.457.119 I slot print_timing: id 0 | task 1274 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.457.150 I slot release: id 0 | task 1274 | stop processing: n_tokens = 465, truncated = 0 0.48.461.782 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 465, t_last = 390628908609 0.48.480.194 I slot launch_slot_: id 0 | task 1348 | processing task, is_child = 0 0.50.633.685 I slot print_timing: id 0 | task 1348 | prompt eval time = 918.75 ms / 430 tokens ( 2.14 ms per token, 468.03 tokens per second) 0.50.633.691 I slot print_timing: id 0 | task 1348 | eval time = 1234.73 ms / 62 tokens ( 20.24 ms per token, 49.40 tokens per second) 0.50.633.692 I slot print_timing: id 0 | task 1348 | total time = 2153.48 ms / 492 tokens 0.50.633.692 I slot print_timing: id 0 | task 1348 | graphs reused = 1288 0.50.633.693 I slot print_timing: id 0 | task 1348 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.633.723 I slot release: id 0 | task 1348 | stop processing: n_tokens = 491, truncated = 0 0.50.638.256 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 491, t_last = 390631085182 0.50.656.589 I slot launch_slot_: id 0 | task 1413 | processing task, is_child = 0 0.52.758.762 I slot print_timing: id 0 | task 1413 | prompt eval time = 869.92 ms / 392 tokens ( 2.22 ms per token, 450.62 tokens per second) 0.52.758.769 I slot print_timing: id 0 | task 1413 | eval time = 1232.24 ms / 62 tokens ( 20.20 ms per token, 49.50 tokens per second) 0.52.758.769 I slot print_timing: id 0 | task 1413 | total time = 2102.16 ms / 454 tokens 0.52.758.770 I slot print_timing: id 0 | task 1413 | graphs reused = 1348 0.52.758.770 I slot print_timing: id 0 | task 1413 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.758.805 I slot release: id 0 | task 1413 | stop processing: n_tokens = 453, truncated = 0 0.52.763.330 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 453, t_last = 390633210264 0.52.781.181 I slot launch_slot_: id 0 | task 1478 | processing task, is_child = 0 0.54.573.884 I slot print_timing: id 0 | task 1478 | prompt eval time = 823.37 ms / 350 tokens ( 2.35 ms per token, 425.08 tokens per second) 0.54.573.886 I slot print_timing: id 0 | task 1478 | eval time = 969.32 ms / 49 tokens ( 20.19 ms per token, 49.52 tokens per second) 0.54.573.887 I slot print_timing: id 0 | task 1478 | total time = 1792.69 ms / 399 tokens 0.54.573.887 I slot print_timing: id 0 | task 1478 | graphs reused = 1395 0.54.573.888 I slot print_timing: id 0 | task 1478 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.573.916 I slot release: id 0 | task 1478 | stop processing: n_tokens = 398, truncated = 0 0.54.578.514 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 398, t_last = 390635025375 0.54.596.500 I slot launch_slot_: id 0 | task 1530 | processing task, is_child = 0 0.56.630.852 I slot print_timing: id 0 | task 1530 | prompt eval time = 821.89 ms / 380 tokens ( 2.16 ms per token, 462.35 tokens per second) 0.56.630.859 I slot print_timing: id 0 | task 1530 | eval time = 1212.45 ms / 61 tokens ( 20.21 ms per token, 49.49 tokens per second) 0.56.630.859 I slot print_timing: id 0 | task 1530 | total time = 2034.34 ms / 441 tokens 0.56.630.860 I slot print_timing: id 0 | task 1530 | graphs reused = 1454 0.56.630.860 I slot print_timing: id 0 | task 1530 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.630.894 I slot release: id 0 | task 1530 | stop processing: n_tokens = 440, truncated = 0 0.56.635.489 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 440, t_last = 390637082353 0.56.653.453 I slot launch_slot_: id 0 | task 1594 | processing task, is_child = 0 0.59.166.024 I slot print_timing: id 0 | task 1594 | prompt eval time = 898.18 ms / 410 tokens ( 2.19 ms per token, 456.48 tokens per second) 0.59.166.030 I slot print_timing: id 0 | task 1594 | eval time = 1614.38 ms / 80 tokens ( 20.44 ms per token, 48.94 tokens per second) 0.59.166.031 I slot print_timing: id 0 | task 1594 | total time = 2512.56 ms / 490 tokens 0.59.166.031 I slot print_timing: id 0 | task 1594 | graphs reused = 1532 0.59.166.035 I slot print_timing: id 0 | task 1594 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.166.068 I slot release: id 0 | task 1594 | stop processing: n_tokens = 489, truncated = 0 0.59.170.627 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 489, t_last = 390639617527 0.59.188.637 I slot launch_slot_: id 0 | task 1677 | processing task, is_child = 0 1.01.425.734 I slot print_timing: id 0 | task 1677 | prompt eval time = 883.15 ms / 387 tokens ( 2.28 ms per token, 438.20 tokens per second) 1.01.425.740 I slot print_timing: id 0 | task 1677 | eval time = 1353.94 ms / 68 tokens ( 20.21 ms per token, 49.49 tokens per second) 1.01.425.741 I slot print_timing: id 0 | task 1677 | total time = 2237.09 ms / 455 tokens 1.01.425.741 I slot print_timing: id 0 | task 1677 | graphs reused = 1598 1.01.425.742 I slot print_timing: id 0 | task 1677 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.425.770 I slot release: id 0 | task 1677 | stop processing: n_tokens = 454, truncated = 0 1.01.430.442 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 454, t_last = 390641877229 1.01.449.092 I slot launch_slot_: id 0 | task 1748 | processing task, is_child = 0 1.03.447.737 I slot print_timing: id 0 | task 1748 | prompt eval time = 827.24 ms / 358 tokens ( 2.31 ms per token, 432.76 tokens per second) 1.03.447.740 I slot print_timing: id 0 | task 1748 | eval time = 1171.39 ms / 59 tokens ( 20.20 ms per token, 49.51 tokens per second) 1.03.447.741 I slot print_timing: id 0 | task 1748 | total time = 1998.63 ms / 417 tokens 1.03.447.742 I slot print_timing: id 0 | task 1748 | graphs reused = 1655 1.03.447.742 I slot print_timing: id 0 | task 1748 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.447.772 I slot release: id 0 | task 1748 | stop processing: n_tokens = 416, truncated = 0 1.03.452.234 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 390643899231 1.03.470.293 I slot launch_slot_: id 0 | task 1810 | processing task, is_child = 0 1.05.416.251 I slot print_timing: id 0 | task 1810 | prompt eval time = 817.36 ms / 359 tokens ( 2.28 ms per token, 439.22 tokens per second) 1.05.416.257 I slot print_timing: id 0 | task 1810 | eval time = 1128.59 ms / 56 tokens ( 20.52 ms per token, 48.73 tokens per second) 1.05.416.258 I slot print_timing: id 0 | task 1810 | total time = 1945.95 ms / 415 tokens 1.05.416.259 I slot print_timing: id 0 | task 1810 | graphs reused = 1709 1.05.416.259 I slot print_timing: id 0 | task 1810 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.416.286 I slot release: id 0 | task 1810 | stop processing: n_tokens = 414, truncated = 0 1.05.421.026 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 390645867745 1.05.439.520 I slot launch_slot_: id 0 | task 1869 | processing task, is_child = 0 1.07.519.442 I slot print_timing: id 0 | task 1869 | prompt eval time = 867.01 ms / 387 tokens ( 2.24 ms per token, 446.36 tokens per second) 1.07.519.448 I slot print_timing: id 0 | task 1869 | eval time = 1212.90 ms / 61 tokens ( 20.21 ms per token, 49.47 tokens per second) 1.07.519.449 I slot print_timing: id 0 | task 1869 | total time = 2079.91 ms / 448 tokens 1.07.519.450 I slot print_timing: id 0 | task 1869 | graphs reused = 1768 1.07.519.450 I slot print_timing: id 0 | task 1869 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.519.479 I slot release: id 0 | task 1869 | stop processing: n_tokens = 447, truncated = 0 1.07.524.069 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 390647970938 1.07.542.461 I slot launch_slot_: id 0 | task 1933 | processing task, is_child = 0 1.09.641.831 I slot print_timing: id 0 | task 1933 | prompt eval time = 867.99 ms / 410 tokens ( 2.12 ms per token, 472.36 tokens per second) 1.09.641.837 I slot print_timing: id 0 | task 1933 | eval time = 1231.37 ms / 61 tokens ( 20.52 ms per token, 48.73 tokens per second) 1.09.641.837 I slot print_timing: id 0 | task 1933 | total time = 2099.36 ms / 471 tokens 1.09.641.838 I slot print_timing: id 0 | task 1933 | graphs reused = 1827 1.09.641.838 I slot print_timing: id 0 | task 1933 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.641.870 I slot release: id 0 | task 1933 | stop processing: n_tokens = 470, truncated = 0 1.09.646.439 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 390650093329 1.09.664.996 I slot launch_slot_: id 0 | task 1997 | processing task, is_child = 0 1.11.465.720 I slot print_timing: id 0 | task 1997 | prompt eval time = 811.18 ms / 351 tokens ( 2.31 ms per token, 432.70 tokens per second) 1.11.465.727 I slot print_timing: id 0 | task 1997 | eval time = 989.53 ms / 50 tokens ( 20.19 ms per token, 49.52 tokens per second) 1.11.465.727 I slot print_timing: id 0 | task 1997 | total time = 1800.71 ms / 401 tokens 1.11.465.728 I slot print_timing: id 0 | task 1997 | graphs reused = 1875 1.11.465.728 I slot print_timing: id 0 | task 1997 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.465.759 I slot release: id 0 | task 1997 | stop processing: n_tokens = 400, truncated = 0 1.11.470.305 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 390651917218 1.11.488.348 I slot launch_slot_: id 0 | task 2050 | processing task, is_child = 0 1.13.461.729 I slot print_timing: id 0 | task 2050 | prompt eval time = 861.05 ms / 393 tokens ( 2.19 ms per token, 456.42 tokens per second) 1.13.461.736 I slot print_timing: id 0 | task 2050 | eval time = 1112.33 ms / 56 tokens ( 20.22 ms per token, 49.45 tokens per second) 1.13.461.737 I slot print_timing: id 0 | task 2050 | total time = 1973.37 ms / 449 tokens 1.13.461.737 I slot print_timing: id 0 | task 2050 | graphs reused = 1929 1.13.461.738 I slot print_timing: id 0 | task 2050 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.461.773 I slot release: id 0 | task 2050 | stop processing: n_tokens = 448, truncated = 0 1.13.466.088 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 390653913232 1.13.484.660 I slot launch_slot_: id 0 | task 2109 | processing task, is_child = 0 1.14.832.234 I slot print_timing: id 0 | task 2109 | prompt eval time = 757.67 ms / 321 tokens ( 2.36 ms per token, 423.67 tokens per second) 1.14.832.237 I slot print_timing: id 0 | task 2109 | eval time = 589.90 ms / 30 tokens ( 20.34 ms per token, 49.16 tokens per second) 1.14.832.238 I slot print_timing: id 0 | task 2109 | total time = 1347.56 ms / 351 tokens 1.14.832.238 I slot print_timing: id 0 | task 2109 | graphs reused = 1957 1.14.832.241 I slot print_timing: id 0 | task 2109 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.832.268 I slot release: id 0 | task 2109 | stop processing: n_tokens = 350, truncated = 0 1.14.836.526 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 350, t_last = 390655283727 1.14.854.785 I slot launch_slot_: id 0 | task 2142 | processing task, is_child = 0 1.16.545.076 I slot print_timing: id 0 | task 2142 | prompt eval time = 780.25 ms / 330 tokens ( 2.36 ms per token, 422.94 tokens per second) 1.16.545.082 I slot print_timing: id 0 | task 2142 | eval time = 910.03 ms / 46 tokens ( 20.22 ms per token, 49.45 tokens per second) 1.16.545.084 I slot print_timing: id 0 | task 2142 | total time = 1690.28 ms / 376 tokens 1.16.545.084 I slot print_timing: id 0 | task 2142 | graphs reused = 2001 1.16.545.085 I slot print_timing: id 0 | task 2142 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.545.119 I slot release: id 0 | task 2142 | stop processing: n_tokens = 375, truncated = 0 1.16.549.478 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 375, t_last = 390656996578 1.16.567.376 I slot launch_slot_: id 0 | task 2191 | processing task, is_child = 0 1.17.970.038 I slot print_timing: id 0 | task 2191 | prompt eval time = 773.80 ms / 341 tokens ( 2.27 ms per token, 440.68 tokens per second) 1.17.970.044 I slot print_timing: id 0 | task 2191 | eval time = 628.85 ms / 32 tokens ( 20.29 ms per token, 49.30 tokens per second) 1.17.970.045 I slot print_timing: id 0 | task 2191 | total time = 1402.65 ms / 373 tokens 1.17.970.048 I slot print_timing: id 0 | task 2191 | graphs reused = 2031 1.17.970.049 I slot print_timing: id 0 | task 2191 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.970.082 I slot release: id 0 | task 2191 | stop processing: n_tokens = 372, truncated = 0 1.17.974.438 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 372, t_last = 390658421541 1.17.992.478 I slot launch_slot_: id 0 | task 2226 | processing task, is_child = 0 1.19.685.180 I slot print_timing: id 0 | task 2226 | prompt eval time = 742.67 ms / 338 tokens ( 2.20 ms per token, 455.12 tokens per second) 1.19.685.186 I slot print_timing: id 0 | task 2226 | eval time = 950.02 ms / 48 tokens ( 20.21 ms per token, 49.47 tokens per second) 1.19.685.187 I slot print_timing: id 0 | task 2226 | total time = 1692.69 ms / 386 tokens 1.19.685.188 I slot print_timing: id 0 | task 2226 | graphs reused = 2077 1.19.685.188 I slot print_timing: id 0 | task 2226 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.685.215 I slot release: id 0 | task 2226 | stop processing: n_tokens = 385, truncated = 0 1.19.689.555 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 385, t_last = 390660136674 1.19.713.067 I slot launch_slot_: id 0 | task 2277 | processing task, is_child = 0 1.21.691.885 I slot print_timing: id 0 | task 2277 | prompt eval time = 867.06 ms / 395 tokens ( 2.20 ms per token, 455.56 tokens per second) 1.21.691.890 I slot print_timing: id 0 | task 2277 | eval time = 1111.75 ms / 56 tokens ( 20.21 ms per token, 49.47 tokens per second) 1.21.691.892 I slot print_timing: id 0 | task 2277 | total time = 1978.81 ms / 451 tokens 1.21.691.892 I slot print_timing: id 0 | task 2277 | graphs reused = 2131 1.21.691.893 I slot print_timing: id 0 | task 2277 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.691.923 I slot release: id 0 | task 2277 | stop processing: n_tokens = 450, truncated = 0 1.21.696.647 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 450, t_last = 390662143382 1.21.721.270 I slot launch_slot_: id 0 | task 2336 | processing task, is_child = 0 1.24.521.370 I slot print_timing: id 0 | task 2336 | prompt eval time = 1135.57 ms / 528 tokens ( 2.15 ms per token, 464.96 tokens per second) 1.24.521.377 I slot print_timing: id 0 | task 2336 | eval time = 1664.51 ms / 83 tokens ( 20.30 ms per token, 49.26 tokens per second) 1.24.521.377 I slot print_timing: id 0 | task 2336 | total time = 2800.09 ms / 611 tokens 1.24.521.378 I slot print_timing: id 0 | task 2336 | graphs reused = 2212 1.24.521.379 I slot print_timing: id 0 | task 2336 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.521.418 I slot release: id 0 | task 2336 | stop processing: n_tokens = 610, truncated = 0 1.24.525.915 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 610, t_last = 390664972877 1.24.525.961 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.418 MiB) 1.24.546.374 I slot launch_slot_: id 0 | task 2423 | processing task, is_child = 0 1.26.226.549 I slot print_timing: id 0 | task 2423 | prompt eval time = 788.62 ms / 331 tokens ( 2.38 ms per token, 419.72 tokens per second) 1.26.226.555 I slot print_timing: id 0 | task 2423 | eval time = 891.55 ms / 45 tokens ( 20.26 ms per token, 49.35 tokens per second) 1.26.226.557 I slot print_timing: id 0 | task 2423 | total time = 1680.16 ms / 376 tokens 1.26.226.557 I slot print_timing: id 0 | task 2423 | graphs reused = 2255 1.26.226.558 I slot print_timing: id 0 | task 2423 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.226.586 I slot release: id 0 | task 2423 | stop processing: n_tokens = 387, truncated = 0 1.26.231.210 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 387, t_last = 390666678045 1.26.231.244 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 195.538 MiB) 1.26.231.256 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.379 MiB) 1.26.242.498 I slot launch_slot_: id 0 | task 2471 | processing task, is_child = 0 1.28.113.541 I slot print_timing: id 0 | task 2471 | prompt eval time = 819.17 ms / 362 tokens ( 2.26 ms per token, 441.91 tokens per second) 1.28.113.547 I slot print_timing: id 0 | task 2471 | eval time = 1051.86 ms / 53 tokens ( 20.23 ms per token, 49.44 tokens per second) 1.28.113.548 I slot print_timing: id 0 | task 2471 | total time = 1871.03 ms / 415 tokens 1.28.113.549 I slot print_timing: id 0 | task 2471 | graphs reused = 2306 1.28.113.549 I slot print_timing: id 0 | task 2471 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.113.581 I slot release: id 0 | task 2471 | stop processing: n_tokens = 426, truncated = 0 1.28.118.153 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 390668565040 1.28.118.188 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 197.024 MiB) 1.28.127.407 I slot launch_slot_: id 0 | task 2527 | processing task, is_child = 0 1.30.414.681 I slot print_timing: id 0 | task 2527 | prompt eval time = 911.35 ms / 419 tokens ( 2.18 ms per token, 459.76 tokens per second) 1.30.414.688 I slot print_timing: id 0 | task 2527 | eval time = 1375.91 ms / 69 tokens ( 20.23 ms per token, 49.42 tokens per second) 1.30.414.688 I slot print_timing: id 0 | task 2527 | total time = 2287.26 ms / 488 tokens 1.30.414.689 I slot print_timing: id 0 | task 2527 | graphs reused = 2373 1.30.414.690 I slot print_timing: id 0 | task 2527 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.414.722 I slot release: id 0 | task 2527 | stop processing: n_tokens = 499, truncated = 0 1.30.419.423 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 499, t_last = 390670866181 1.30.419.462 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.985 MiB) 1.30.441.773 I slot launch_slot_: id 0 | task 2599 | processing task, is_child = 0 1.32.248.197 I slot print_timing: id 0 | task 2599 | prompt eval time = 935.90 ms / 423 tokens ( 2.21 ms per token, 451.97 tokens per second) 1.32.248.200 I slot print_timing: id 0 | task 2599 | eval time = 870.51 ms / 44 tokens ( 20.24 ms per token, 49.40 tokens per second) 1.32.248.201 I slot print_timing: id 0 | task 2599 | total time = 1806.41 ms / 467 tokens 1.32.248.202 I slot print_timing: id 0 | task 2599 | graphs reused = 2415 1.32.248.202 I slot print_timing: id 0 | task 2599 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.248.239 I slot release: id 0 | task 2599 | stop processing: n_tokens = 478, truncated = 0 1.32.252.589 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 478, t_last = 390672699698 1.32.252.627 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.770 MiB) 1.32.252.631 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 197.748 MiB) 1.32.278.406 I slot launch_slot_: id 0 | task 2646 | processing task, is_child = 0 1.33.899.338 I slot print_timing: id 0 | task 2646 | prompt eval time = 772.06 ms / 341 tokens ( 2.26 ms per token, 441.68 tokens per second) 1.33.899.343 I slot print_timing: id 0 | task 2646 | eval time = 848.86 ms / 43 tokens ( 20.21 ms per token, 49.48 tokens per second) 1.33.899.344 I slot print_timing: id 0 | task 2646 | total time = 1620.92 ms / 384 tokens 1.33.899.345 I slot print_timing: id 0 | task 2646 | graphs reused = 2456 1.33.899.345 I slot print_timing: id 0 | task 2646 | graph reallocs = 0 / 0 (same size) / (changed size) 1.33.899.372 I slot release: id 0 | task 2646 | stop processing: n_tokens = 395, truncated = 0 1.33.903.969 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 395, t_last = 390674350831 1.33.904.003 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 199.019 MiB) 1.33.913.657 I slot launch_slot_: id 0 | task 2692 | processing task, is_child = 0 1.35.676.375 I slot print_timing: id 0 | task 2692 | prompt eval time = 832.48 ms / 356 tokens ( 2.34 ms per token, 427.64 tokens per second) 1.35.676.381 I slot print_timing: id 0 | task 2692 | eval time = 930.23 ms / 47 tokens ( 20.22 ms per token, 49.45 tokens per second) 1.35.676.382 I slot print_timing: id 0 | task 2692 | total time = 1762.71 ms / 403 tokens 1.35.676.382 I slot print_timing: id 0 | task 2692 | graphs reused = 2501 1.35.676.383 I slot print_timing: id 0 | task 2692 | graph reallocs = 0 / 0 (same size) / (changed size) 1.35.676.410 I slot release: id 0 | task 2692 | stop processing: n_tokens = 414, truncated = 0 1.35.680.736 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 390676127869 1.35.680.769 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.086 MiB) 1.35.688.905 I slot launch_slot_: id 0 | task 2742 | processing task, is_child = 0 1.37.420.199 I slot print_timing: id 0 | task 2742 | prompt eval time = 820.89 ms / 362 tokens ( 2.27 ms per token, 440.99 tokens per second) 1.37.420.206 I slot print_timing: id 0 | task 2742 | eval time = 910.40 ms / 46 tokens ( 20.23 ms per token, 49.43 tokens per second) 1.37.420.207 I slot print_timing: id 0 | task 2742 | total time = 1731.28 ms / 408 tokens 1.37.420.207 I slot print_timing: id 0 | task 2742 | graphs reused = 2545 1.37.420.208 I slot print_timing: id 0 | task 2742 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.420.240 I slot release: id 0 | task 2742 | stop processing: n_tokens = 419, truncated = 0 1.37.424.859 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 390677871699 1.37.424.893 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.340 MiB) 1.37.433.438 I slot launch_slot_: id 0 | task 2791 | processing task, is_child = 0 1.39.688.286 I slot print_timing: id 0 | task 2791 | prompt eval time = 901.70 ms / 391 tokens ( 2.31 ms per token, 433.63 tokens per second) 1.39.688.292 I slot print_timing: id 0 | task 2791 | eval time = 1353.14 ms / 68 tokens ( 20.20 ms per token, 49.51 tokens per second) 1.39.688.293 I slot print_timing: id 0 | task 2791 | total time = 2254.84 ms / 459 tokens 1.39.688.293 I slot print_timing: id 0 | task 2791 | graphs reused = 2611 1.39.688.294 I slot print_timing: id 0 | task 2791 | graph reallocs = 0 / 0 (same size) / (changed size) 1.39.688.323 I slot release: id 0 | task 2791 | stop processing: n_tokens = 470, truncated = 0 1.39.692.695 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 390680139782 1.39.692.730 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.985 MiB) 1.39.692.734 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 197.396 MiB) 1.39.703.081 I slot launch_slot_: id 0 | task 2862 | processing task, is_child = 0 1.41.607.195 I slot print_timing: id 0 | task 2862 | prompt eval time = 794.50 ms / 343 tokens ( 2.32 ms per token, 431.72 tokens per second) 1.41.607.198 I slot print_timing: id 0 | task 2862 | eval time = 1109.60 ms / 55 tokens ( 20.55 ms per token, 48.67 tokens per second) 1.41.607.199 I slot print_timing: id 0 | task 2862 | total time = 1904.10 ms / 398 tokens 1.41.607.200 I slot print_timing: id 0 | task 2862 | graphs reused = 2664 1.41.607.200 I slot print_timing: id 0 | task 2862 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.607.227 I slot release: id 0 | task 2862 | stop processing: n_tokens = 409, truncated = 0 1.41.611.863 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 390682058686 1.41.611.897 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.985 MiB) 1.41.621.309 I slot launch_slot_: id 0 | task 2920 | processing task, is_child = 0 1.43.429.249 I slot print_timing: id 0 | task 2920 | prompt eval time = 897.23 ms / 401 tokens ( 2.24 ms per token, 446.93 tokens per second) 1.43.429.255 I slot print_timing: id 0 | task 2920 | eval time = 910.70 ms / 46 tokens ( 20.24 ms per token, 49.41 tokens per second) 1.43.429.256 I slot print_timing: id 0 | task 2920 | total time = 1807.93 ms / 447 tokens 1.43.429.256 I slot print_timing: id 0 | task 2920 | graphs reused = 2708 1.43.429.257 I slot print_timing: id 0 | task 2920 | graph reallocs = 0 / 0 (same size) / (changed size) 1.43.429.289 I slot release: id 0 | task 2920 | stop processing: n_tokens = 458, truncated = 0 1.43.433.662 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 390683880748 1.43.433.696 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.829 MiB) 1.43.442.213 I slot launch_slot_: id 0 | task 2969 | processing task, is_child = 0 1.45.599.703 I slot print_timing: id 0 | task 2969 | prompt eval time = 802.56 ms / 355 tokens ( 2.26 ms per token, 442.34 tokens per second) 1.45.599.706 I slot print_timing: id 0 | task 2969 | eval time = 1354.92 ms / 68 tokens ( 20.22 ms per token, 49.45 tokens per second) 1.45.599.707 I slot print_timing: id 0 | task 2969 | total time = 2157.48 ms / 423 tokens 1.45.599.707 I slot print_timing: id 0 | task 2969 | graphs reused = 2774 1.45.599.708 I slot print_timing: id 0 | task 2969 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.599.735 I slot release: id 0 | task 2969 | stop processing: n_tokens = 434, truncated = 0 1.45.604.521 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 434, t_last = 390686051194 1.45.604.562 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.731 MiB) 1.45.604.566 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.203 MiB) 1.45.616.550 I slot launch_slot_: id 0 | task 3040 | processing task, is_child = 0 1.47.594.087 I slot print_timing: id 0 | task 3040 | prompt eval time = 827.93 ms / 351 tokens ( 2.36 ms per token, 423.95 tokens per second) 1.47.594.093 I slot print_timing: id 0 | task 3040 | eval time = 1149.59 ms / 57 tokens ( 20.53 ms per token, 48.71 tokens per second) 1.47.594.094 I slot print_timing: id 0 | task 3040 | total time = 1977.53 ms / 408 tokens 1.47.594.094 I slot print_timing: id 0 | task 3040 | graphs reused = 2829 1.47.594.095 I slot print_timing: id 0 | task 3040 | graph reallocs = 0 / 0 (same size) / (changed size) 1.47.594.123 I slot release: id 0 | task 3040 | stop processing: n_tokens = 419, truncated = 0 1.47.599.033 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 390688045582 1.47.599.066 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.692 MiB) 1.47.608.847 I slot launch_slot_: id 0 | task 3100 | processing task, is_child = 0 1.50.457.070 I slot print_timing: id 0 | task 3100 | prompt eval time = 978.90 ms / 475 tokens ( 2.06 ms per token, 485.24 tokens per second) 1.50.457.074 I slot print_timing: id 0 | task 3100 | eval time = 1869.31 ms / 93 tokens ( 20.32 ms per token, 49.22 tokens per second) 1.50.457.075 I slot print_timing: id 0 | task 3100 | total time = 2848.21 ms / 568 tokens 1.50.457.076 I slot print_timing: id 0 | task 3100 | graphs reused = 2919 1.50.457.076 I slot print_timing: id 0 | task 3100 | graph reallocs = 0 / 0 (same size) / (changed size) 1.50.457.114 I slot release: id 0 | task 3100 | stop processing: n_tokens = 579, truncated = 0 1.50.461.815 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 579, t_last = 390690908573 1.50.461.857 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.105 MiB) 1.50.517.122 I slot launch_slot_: id 0 | task 3196 | processing task, is_child = 0 1.53.302.123 I slot print_timing: id 0 | task 3196 | prompt eval time = 940.51 ms / 440 tokens ( 2.14 ms per token, 467.83 tokens per second) 1.53.302.127 I slot print_timing: id 0 | task 3196 | eval time = 1844.47 ms / 92 tokens ( 20.27 ms per token, 49.34 tokens per second) 1.53.302.134 I slot print_timing: id 0 | task 3196 | total time = 2784.98 ms / 532 tokens 1.53.302.135 I slot print_timing: id 0 | task 3196 | graphs reused = 3008 1.53.302.135 I slot print_timing: id 0 | task 3196 | graph reallocs = 0 / 0 (same size) / (changed size) 1.53.302.182 I slot release: id 0 | task 3196 | stop processing: n_tokens = 543, truncated = 0 1.53.306.867 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 543, t_last = 390693753641 1.53.306.920 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.027 MiB) 1.53.306.932 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 197.161 MiB) 1.53.578.227 I slot launch_slot_: id 0 | task 3291 | processing task, is_child = 0 1.55.477.299 I slot print_timing: id 0 | task 3291 | prompt eval time = 809.54 ms / 345 tokens ( 2.35 ms per token, 426.17 tokens per second) 1.55.477.304 I slot print_timing: id 0 | task 3291 | eval time = 1089.51 ms / 55 tokens ( 20.18 ms per token, 49.56 tokens per second) 1.55.477.304 I slot print_timing: id 0 | task 3291 | total time = 1899.04 ms / 400 tokens 1.55.477.305 I slot print_timing: id 0 | task 3291 | graphs reused = 3061 1.55.477.305 I slot print_timing: id 0 | task 3291 | graph reallocs = 0 / 0 (same size) / (changed size) 1.55.477.344 I slot release: id 0 | task 3291 | stop processing: n_tokens = 411, truncated = 0 1.55.482.896 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 390695928803 1.55.482.940 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.438 MiB) 1.55.546.931 I slot launch_slot_: id 0 | task 3349 | processing task, is_child = 0 1.57.506.004 I slot print_timing: id 0 | task 3349 | prompt eval time = 868.50 ms / 382 tokens ( 2.27 ms per token, 439.84 tokens per second) 1.57.506.010 I slot print_timing: id 0 | task 3349 | eval time = 1090.56 ms / 55 tokens ( 20.20 ms per token, 49.52 tokens per second) 1.57.506.011 I slot print_timing: id 0 | task 3349 | total time = 1959.06 ms / 437 tokens 1.57.506.011 I slot print_timing: id 0 | task 3349 | graphs reused = 3114 1.57.506.012 I slot print_timing: id 0 | task 3349 | graph reallocs = 0 / 0 (same size) / (changed size) 1.57.506.049 I slot release: id 0 | task 3349 | stop processing: n_tokens = 448, truncated = 0 1.57.510.552 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 390697957508 1.57.510.585 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 197.806 MiB) 1.57.563.087 I slot launch_slot_: id 0 | task 3407 | processing task, is_child = 0 1.59.241.215 I slot print_timing: id 0 | task 3407 | prompt eval time = 788.77 ms / 337 tokens ( 2.34 ms per token, 427.25 tokens per second) 1.59.241.223 I slot print_timing: id 0 | task 3407 | eval time = 889.35 ms / 45 tokens ( 20.21 ms per token, 49.47 tokens per second) 1.59.241.223 I slot print_timing: id 0 | task 3407 | total time = 1678.11 ms / 382 tokens 1.59.241.224 I slot print_timing: id 0 | task 3407 | graphs reused = 3157 1.59.241.224 I slot print_timing: id 0 | task 3407 | graph reallocs = 0 / 0 (same size) / (changed size) 1.59.241.264 I slot release: id 0 | task 3407 | stop processing: n_tokens = 393, truncated = 0 1.59.246.156 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 390699692723 1.59.246.188 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 197.083 MiB) 1.59.246.201 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 197.533 MiB) 1.59.300.067 I slot launch_slot_: id 0 | task 3455 | processing task, is_child = 0 2.01.586.695 I slot print_timing: id 0 | task 3455 | prompt eval time = 867.77 ms / 402 tokens ( 2.16 ms per token, 463.26 tokens per second) 2.01.586.701 I slot print_timing: id 0 | task 3455 | eval time = 1418.85 ms / 70 tokens ( 20.56 ms per token, 48.63 tokens per second) 2.01.586.702 I slot print_timing: id 0 | task 3455 | total time = 2286.61 ms / 472 tokens 2.01.586.703 I slot print_timing: id 0 | task 3455 | graphs reused = 3225 2.01.586.703 I slot print_timing: id 0 | task 3455 | graph reallocs = 0 / 0 (same size) / (changed size) 2.01.586.738 I slot release: id 0 | task 3455 | stop processing: n_tokens = 483, truncated = 0 2.01.591.832 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 483, t_last = 390702038197 2.01.591.871 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 198.041 MiB) 2.01.643.577 I slot launch_slot_: id 0 | task 3528 | processing task, is_child = 0 2.03.996.762 I slot print_timing: id 0 | task 3528 | prompt eval time = 1217.55 ms / 549 tokens ( 2.22 ms per token, 450.90 tokens per second) 2.03.996.768 I slot print_timing: id 0 | task 3528 | eval time = 1135.62 ms / 57 tokens ( 20.28 ms per token, 49.31 tokens per second) 2.03.996.769 I slot print_timing: id 0 | task 3528 | total time = 2353.17 ms / 606 tokens 2.03.996.769 I slot print_timing: id 0 | task 3528 | graphs reused = 3280 2.03.996.770 I slot print_timing: id 0 | task 3528 | graph reallocs = 0 / 0 (same size) / (changed size) 2.03.996.804 I slot release: id 0 | task 3528 | stop processing: n_tokens = 617, truncated = 0 2.04.002.105 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 617, t_last = 390704448263 2.04.002.144 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 197.298 MiB) 2.04.002.157 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.222 MiB) 2.04.070.113 I slot launch_slot_: id 0 | task 3589 | processing task, is_child = 0 2.06.581.509 I slot print_timing: id 0 | task 3589 | prompt eval time = 1356.90 ms / 616 tokens ( 2.20 ms per token, 453.98 tokens per second) 2.06.581.515 I slot print_timing: id 0 | task 3589 | eval time = 1154.49 ms / 58 tokens ( 20.25 ms per token, 49.37 tokens per second) 2.06.581.515 I slot print_timing: id 0 | task 3589 | total time = 2511.38 ms / 674 tokens 2.06.581.516 I slot print_timing: id 0 | task 3589 | graphs reused = 3336 2.06.581.516 I slot print_timing: id 0 | task 3589 | graph reallocs = 0 / 0 (same size) / (changed size) 2.06.581.558 I slot release: id 0 | task 3589 | stop processing: n_tokens = 685, truncated = 0 2.06.587.080 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 685, t_last = 390707033017 2.06.587.126 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 197.044 MiB) 2.06.645.583 I slot launch_slot_: id 0 | task 3651 | processing task, is_child = 0 2.09.272.713 I slot print_timing: id 0 | task 3651 | prompt eval time = 1409.79 ms / 665 tokens ( 2.12 ms per token, 471.70 tokens per second) 2.09.272.717 I slot print_timing: id 0 | task 3651 | eval time = 1217.33 ms / 61 tokens ( 20.29 ms per token, 49.29 tokens per second) 2.09.272.719 I slot print_timing: id 0 | task 3651 | total time = 2627.11 ms / 726 tokens 2.09.272.719 I slot print_timing: id 0 | task 3651 | graphs reused = 3395 2.09.272.720 I slot print_timing: id 0 | task 3651 | graph reallocs = 0 / 0 (same size) / (changed size) 2.09.272.779 I slot release: id 0 | task 3651 | stop processing: n_tokens = 737, truncated = 0 2.09.278.413 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 737, t_last = 390709724238 2.09.278.461 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 198.002 MiB) 2.09.278.474 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 197.317 MiB) 2.09.343.817 I slot launch_slot_: id 0 | task 3716 | processing task, is_child = 0 2.11.855.469 I slot print_timing: id 0 | task 3716 | prompt eval time = 1414.82 ms / 645 tokens ( 2.19 ms per token, 455.89 tokens per second) 2.11.855.474 I slot print_timing: id 0 | task 3716 | eval time = 1096.81 ms / 55 tokens ( 20.31 ms per token, 49.23 tokens per second) 2.11.855.476 I slot print_timing: id 0 | task 3716 | total time = 2511.64 ms / 700 tokens 2.11.855.476 I slot print_timing: id 0 | task 3716 | graphs reused = 3448 2.11.855.477 I slot print_timing: id 0 | task 3716 | graph reallocs = 0 / 0 (same size) / (changed size) 2.11.855.514 I slot release: id 0 | task 3716 | stop processing: n_tokens = 711, truncated = 0 2.11.860.478 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 711, t_last = 390712306973 2.11.860.525 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.574 MiB) 2.11.860.541 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.535 MiB) 2.11.932.250 I slot launch_slot_: id 0 | task 3775 | processing task, is_child = 0 2.13.962.558 I slot print_timing: id 0 | task 3775 | prompt eval time = 992.82 ms / 474 tokens ( 2.09 ms per token, 477.43 tokens per second) 2.13.962.565 I slot print_timing: id 0 | task 3775 | eval time = 1037.47 ms / 52 tokens ( 20.34 ms per token, 49.16 tokens per second) 2.13.962.565 I slot print_timing: id 0 | task 3775 | total time = 2030.29 ms / 526 tokens 2.13.962.566 I slot print_timing: id 0 | task 3775 | graphs reused = 3497 2.13.962.567 I slot print_timing: id 0 | task 3775 | graph reallocs = 0 / 0 (same size) / (changed size) 2.13.962.601 I slot release: id 0 | task 3775 | stop processing: n_tokens = 537, truncated = 0 2.13.967.980 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 537, t_last = 390714414060 2.13.968.019 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 197.181 MiB) 2.14.009.493 I slot launch_slot_: id 0 | task 3830 | processing task, is_child = 0 2.16.204.995 I slot print_timing: id 0 | task 3830 | prompt eval time = 1362.08 ms / 617 tokens ( 2.21 ms per token, 452.98 tokens per second) 2.16.205.001 I slot print_timing: id 0 | task 3830 | eval time = 833.40 ms / 42 tokens ( 20.33 ms per token, 49.20 tokens per second) 2.16.205.002 I slot print_timing: id 0 | task 3830 | total time = 2195.49 ms / 659 tokens 2.16.205.002 I slot print_timing: id 0 | task 3830 | graphs reused = 3537 2.16.205.003 I slot print_timing: id 0 | task 3830 | graph reallocs = 0 / 0 (same size) / (changed size) 2.16.205.042 I slot release: id 0 | task 3830 | stop processing: n_tokens = 670, truncated = 0 2.16.210.247 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 670, t_last = 390716656501 2.16.210.291 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 197.630 MiB) 2.16.210.305 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.262 MiB) 2.16.316.110 I slot launch_slot_: id 0 | task 3876 | processing task, is_child = 0 2.18.614.462 I slot print_timing: id 0 | task 3876 | prompt eval time = 1343.36 ms / 601 tokens ( 2.24 ms per token, 447.39 tokens per second) 2.18.614.465 I slot print_timing: id 0 | task 3876 | eval time = 954.98 ms / 48 tokens ( 20.32 ms per token, 49.22 tokens per second) 2.18.614.466 I slot print_timing: id 0 | task 3876 | total time = 2298.33 ms / 649 tokens 2.18.614.467 I slot print_timing: id 0 | task 3876 | graphs reused = 3583 2.18.614.467 I slot print_timing: id 0 | task 3876 | graph reallocs = 0 / 0 (same size) / (changed size) 2.18.614.506 I slot release: id 0 | task 3876 | stop processing: n_tokens = 660, truncated = 0 2.18.619.634 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 660, t_last = 390719065965 2.18.619.684 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 197.200 MiB) 2.18.788.253 I slot launch_slot_: id 0 | task 3928 | processing task, is_child = 0 2.20.915.067 I slot print_timing: id 0 | task 3928 | prompt eval time = 1186.49 ms / 533 tokens ( 2.23 ms per token, 449.22 tokens per second) 2.20.915.070 I slot print_timing: id 0 | task 3928 | eval time = 940.30 ms / 47 tokens ( 20.44 ms per token, 48.92 tokens per second) 2.20.915.071 I slot print_timing: id 0 | task 3928 | total time = 2126.79 ms / 580 tokens 2.20.915.071 I slot print_timing: id 0 | task 3928 | graphs reused = 3628 2.20.915.072 I slot print_timing: id 0 | task 3928 | graph reallocs = 0 / 0 (same size) / (changed size) 2.20.915.115 I slot release: id 0 | task 3928 | stop processing: n_tokens = 591, truncated = 0 2.20.920.508 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 591, t_last = 390721366574 2.20.920.552 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 195.284 MiB) 2.20.920.570 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 195.773 MiB) 2.20.981.189 I slot launch_slot_: id 0 | task 3979 | processing task, is_child = 0 2.23.014.279 I slot print_timing: id 0 | task 3979 | prompt eval time = 994.50 ms / 480 tokens ( 2.07 ms per token, 482.65 tokens per second) 2.23.014.285 I slot print_timing: id 0 | task 3979 | eval time = 1038.57 ms / 52 tokens ( 20.36 ms per token, 49.11 tokens per second) 2.23.014.286 I slot print_timing: id 0 | task 3979 | total time = 2033.07 ms / 532 tokens 2.23.014.286 I slot print_timing: id 0 | task 3979 | graphs reused = 3677 2.23.014.287 I slot print_timing: id 0 | task 3979 | graph reallocs = 0 / 0 (same size) / (changed size) 2.23.014.321 I slot release: id 0 | task 3979 | stop processing: n_tokens = 560, truncated = 0 2.23.019.479 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 390723465780 2.23.019.520 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 195.714 MiB) 2.23.019.537 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 195.968 MiB) 2.23.081.242 I slot launch_slot_: id 0 | task 4034 | processing task, is_child = 0 2.25.153.515 I slot print_timing: id 0 | task 4034 | prompt eval time = 1239.94 ms / 567 tokens ( 2.19 ms per token, 457.28 tokens per second) 2.25.153.518 I slot print_timing: id 0 | task 4034 | eval time = 832.31 ms / 42 tokens ( 20.30 ms per token, 49.26 tokens per second) 2.25.153.518 I slot print_timing: id 0 | task 4034 | total time = 2072.25 ms / 609 tokens 2.25.153.519 I slot print_timing: id 0 | task 4034 | graphs reused = 3717 2.25.153.519 I slot print_timing: id 0 | task 4034 | graph reallocs = 0 / 0 (same size) / (changed size) 2.25.153.562 I slot release: id 0 | task 4034 | stop processing: n_tokens = 637, truncated = 0 2.25.158.813 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 390725605021 2.25.158.853 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 197.239 MiB) 2.25.158.866 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 263.181 MiB) 2.25.227.256 I slot launch_slot_: id 0 | task 4080 | processing task, is_child = 0 2.27.505.505 I slot print_timing: id 0 | task 4080 | prompt eval time = 1018.97 ms / 506 tokens ( 2.01 ms per token, 496.58 tokens per second) 2.27.505.512 I slot print_timing: id 0 | task 4080 | eval time = 1259.26 ms / 63 tokens ( 20.31 ms per token, 49.24 tokens per second) 2.27.505.513 I slot print_timing: id 0 | task 4080 | total time = 2278.23 ms / 569 tokens 2.27.505.513 I slot print_timing: id 0 | task 4080 | graphs reused = 3778 2.27.505.514 I slot print_timing: id 0 | task 4080 | graph reallocs = 0 / 0 (same size) / (changed size) 2.27.505.551 I slot release: id 0 | task 4080 | stop processing: n_tokens = 597, truncated = 0 2.27.510.202 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 597, t_last = 390727957010 2.27.510.244 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 258.821 MiB) 2.27.536.559 I slot launch_slot_: id 0 | task 4146 | processing task, is_child = 0 2.29.238.329 I slot print_timing: id 0 | task 4146 | prompt eval time = 911.52 ms / 436 tokens ( 2.09 ms per token, 478.32 tokens per second) 2.29.238.335 I slot print_timing: id 0 | task 4146 | eval time = 790.24 ms / 40 tokens ( 20.26 ms per token, 49.35 tokens per second) 2.29.238.336 I slot print_timing: id 0 | task 4146 | total time = 1701.76 ms / 476 tokens 2.29.238.337 I slot print_timing: id 0 | task 4146 | graphs reused = 3816 2.29.238.337 I slot print_timing: id 0 | task 4146 | graph reallocs = 0 / 0 (same size) / (changed size) 2.29.238.373 I slot release: id 0 | task 4146 | stop processing: n_tokens = 504, truncated = 0 2.29.243.541 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 390729689832 2.29.243.580 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 259.583 MiB) 2.29.293.484 I slot launch_slot_: id 0 | task 4189 | processing task, is_child = 0 2.31.614.498 I slot print_timing: id 0 | task 4189 | prompt eval time = 1084.11 ms / 519 tokens ( 2.09 ms per token, 478.73 tokens per second) 2.31.614.505 I slot print_timing: id 0 | task 4189 | eval time = 1236.88 ms / 62 tokens ( 20.28 ms per token, 49.32 tokens per second) 2.31.614.506 I slot print_timing: id 0 | task 4189 | total time = 2321.00 ms / 581 tokens 2.31.614.507 I slot print_timing: id 0 | task 4189 | graphs reused = 3876 2.31.614.508 I slot print_timing: id 0 | task 4189 | graph reallocs = 0 / 0 (same size) / (changed size) 2.31.614.558 I slot release: id 0 | task 4189 | stop processing: n_tokens = 609, truncated = 0 2.31.619.618 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 609, t_last = 390732066017 2.31.619.666 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 261.011 MiB) 2.31.619.671 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 260.600 MiB) 2.31.688.700 I slot launch_slot_: id 0 | task 4255 | processing task, is_child = 0 2.33.558.313 I slot print_timing: id 0 | task 4255 | prompt eval time = 951.09 ms / 465 tokens ( 2.05 ms per token, 488.91 tokens per second) 2.33.558.317 I slot print_timing: id 0 | task 4255 | eval time = 918.50 ms / 46 tokens ( 20.41 ms per token, 48.99 tokens per second) 2.33.558.317 I slot print_timing: id 0 | task 4255 | total time = 1869.59 ms / 511 tokens 2.33.558.318 I slot print_timing: id 0 | task 4255 | graphs reused = 3919 2.33.558.318 I slot print_timing: id 0 | task 4255 | graph reallocs = 0 / 0 (same size) / (changed size) 2.33.558.353 I slot release: id 0 | task 4255 | stop processing: n_tokens = 542, truncated = 0 2.33.563.346 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 542, t_last = 390734009812 2.33.563.385 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 258.977 MiB) 2.33.635.260 I slot launch_slot_: id 0 | task 4304 | processing task, is_child = 0 2.35.371.542 I slot print_timing: id 0 | task 4304 | prompt eval time = 923.85 ms / 431 tokens ( 2.14 ms per token, 466.53 tokens per second) 2.35.371.548 I slot print_timing: id 0 | task 4304 | eval time = 812.42 ms / 41 tokens ( 20.31 ms per token, 49.24 tokens per second) 2.35.371.548 I slot print_timing: id 0 | task 4304 | total time = 1736.27 ms / 472 tokens 2.35.371.549 I slot print_timing: id 0 | task 4304 | graphs reused = 3958 2.35.371.549 I slot print_timing: id 0 | task 4304 | graph reallocs = 0 / 0 (same size) / (changed size) 2.35.371.580 I slot release: id 0 | task 4304 | stop processing: n_tokens = 503, truncated = 0 2.35.376.714 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 503, t_last = 390735823039 2.35.376.751 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 259.349 MiB) 2.35.376.771 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 259.446 MiB) 2.35.449.349 I slot launch_slot_: id 0 | task 4348 | processing task, is_child = 0 2.37.291.089 I slot print_timing: id 0 | task 4348 | prompt eval time = 966.16 ms / 457 tokens ( 2.11 ms per token, 473.01 tokens per second) 2.37.291.095 I slot print_timing: id 0 | task 4348 | eval time = 875.55 ms / 44 tokens ( 20.36 ms per token, 49.11 tokens per second) 2.37.291.096 I slot print_timing: id 0 | task 4348 | total time = 1841.71 ms / 501 tokens 2.37.291.096 I slot print_timing: id 0 | task 4348 | graphs reused = 3999 2.37.291.097 I slot print_timing: id 0 | task 4348 | graph reallocs = 0 / 0 (same size) / (changed size) 2.37.291.132 I slot release: id 0 | task 4348 | stop processing: n_tokens = 532, truncated = 0 2.37.296.058 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 532, t_last = 390737742591 2.37.296.097 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 260.444 MiB) 2.37.374.591 I slot launch_slot_: id 0 | task 4395 | processing task, is_child = 0 2.39.142.456 I slot print_timing: id 0 | task 4395 | prompt eval time = 936.95 ms / 439 tokens ( 2.13 ms per token, 468.54 tokens per second) 2.39.142.462 I slot print_timing: id 0 | task 4395 | eval time = 830.90 ms / 42 tokens ( 20.27 ms per token, 49.34 tokens per second) 2.39.142.463 I slot print_timing: id 0 | task 4395 | total time = 1767.85 ms / 481 tokens 2.39.142.463 I slot print_timing: id 0 | task 4395 | graphs reused = 4039 2.39.142.464 I slot print_timing: id 0 | task 4395 | graph reallocs = 0 / 0 (same size) / (changed size) 2.39.142.498 I slot release: id 0 | task 4395 | stop processing: n_tokens = 512, truncated = 0 2.39.147.902 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 512, t_last = 390739593957 2.39.147.940 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 259.251 MiB) 2.39.147.956 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 260.209 MiB) 2.39.219.859 I slot launch_slot_: id 0 | task 4440 | processing task, is_child = 0 2.41.651.007 I slot print_timing: id 0 | task 4440 | prompt eval time = 1316.31 ms / 606 tokens ( 2.17 ms per token, 460.38 tokens per second) 2.41.651.010 I slot print_timing: id 0 | task 4440 | eval time = 1114.82 ms / 56 tokens ( 20.27 ms per token, 49.34 tokens per second) 2.41.651.010 I slot print_timing: id 0 | task 4440 | total time = 2431.13 ms / 662 tokens 2.41.651.011 I slot print_timing: id 0 | task 4440 | graphs reused = 4093 2.41.651.011 I slot print_timing: id 0 | task 4440 | graph reallocs = 0 / 0 (same size) / (changed size) 2.41.651.051 I slot release: id 0 | task 4440 | stop processing: n_tokens = 693, truncated = 0 2.41.655.945 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 390742102511 2.41.655.990 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 259.740 MiB) 2.41.741.263 I slot launch_slot_: id 0 | task 4500 | processing task, is_child = 0 2.43.561.580 I slot print_timing: id 0 | task 4500 | prompt eval time = 1002.58 ms / 477 tokens ( 2.10 ms per token, 475.77 tokens per second) 2.43.561.583 I slot print_timing: id 0 | task 4500 | eval time = 817.73 ms / 41 tokens ( 20.44 ms per token, 48.92 tokens per second) 2.43.561.584 I slot print_timing: id 0 | task 4500 | total time = 1820.30 ms / 518 tokens 2.43.561.584 I slot print_timing: id 0 | task 4500 | graphs reused = 4131 2.43.561.585 I slot print_timing: id 0 | task 4500 | graph reallocs = 0 / 0 (same size) / (changed size) 2.43.561.620 I slot release: id 0 | task 4500 | stop processing: n_tokens = 549, truncated = 0 2.43.568.289 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 390744013079 2.43.568.332 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 259.446 MiB) 2.43.568.354 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 262.575 MiB) 2.43.640.563 I slot launch_slot_: id 0 | task 4544 | processing task, is_child = 0 2.46.537.655 I slot print_timing: id 0 | task 4544 | prompt eval time = 1698.89 ms / 845 tokens ( 2.01 ms per token, 497.38 tokens per second) 2.46.537.661 I slot print_timing: id 0 | task 4544 | eval time = 1198.19 ms / 60 tokens ( 20.31 ms per token, 49.24 tokens per second) 2.46.537.662 I slot print_timing: id 0 | task 4544 | total time = 2897.07 ms / 905 tokens 2.46.537.663 I slot print_timing: id 0 | task 4544 | graphs reused = 4189 2.46.537.663 I slot print_timing: id 0 | task 4544 | graph reallocs = 0 / 0 (same size) / (changed size) 2.46.537.733 I slot release: id 0 | task 4544 | stop processing: n_tokens = 936, truncated = 0 2.46.542.596 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 936, t_last = 390746989192 2.46.542.651 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 261.871 MiB) 2.46.601.573 I slot launch_slot_: id 0 | task 4608 | processing task, is_child = 0 2.48.432.981 I slot print_timing: id 0 | task 4608 | prompt eval time = 976.02 ms / 459 tokens ( 2.13 ms per token, 470.28 tokens per second) 2.48.432.984 I slot print_timing: id 0 | task 4608 | eval time = 855.37 ms / 43 tokens ( 20.37 ms per token, 49.10 tokens per second) 2.48.432.985 I slot print_timing: id 0 | task 4608 | total time = 1831.39 ms / 502 tokens 2.48.432.985 I slot print_timing: id 0 | task 4608 | graphs reused = 4229 2.48.432.986 I slot print_timing: id 0 | task 4608 | graph reallocs = 0 / 0 (same size) / (changed size) 2.48.433.033 I slot release: id 0 | task 4608 | stop processing: n_tokens = 533, truncated = 0 2.48.438.556 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 533, t_last = 390748884492 2.48.438.594 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 259.290 MiB) 2.48.438.613 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 260.013 MiB) 2.48.514.160 I slot launch_slot_: id 0 | task 4654 | processing task, is_child = 0 2.50.869.034 I slot print_timing: id 0 | task 4654 | prompt eval time = 1421.70 ms / 670 tokens ( 2.12 ms per token, 471.27 tokens per second) 2.50.869.039 I slot print_timing: id 0 | task 4654 | eval time = 933.16 ms / 47 tokens ( 20.29 ms per token, 49.30 tokens per second) 2.50.869.040 I slot print_timing: id 0 | task 4654 | total time = 2354.86 ms / 717 tokens 2.50.869.040 I slot print_timing: id 0 | task 4654 | graphs reused = 4274 2.50.869.041 I slot print_timing: id 0 | task 4654 | graph reallocs = 0 / 0 (same size) / (changed size) 2.50.869.086 I slot release: id 0 | task 4654 | stop processing: n_tokens = 748, truncated = 0 2.50.875.271 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 748, t_last = 390751320545 2.50.875.315 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 258.938 MiB) 2.50.875.330 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 260.698 MiB) 2.50.949.660 I slot launch_slot_: id 0 | task 4705 | processing task, is_child = 0 2.53.820.442 I slot print_timing: id 0 | task 4705 | prompt eval time = 1590.21 ms / 775 tokens ( 2.05 ms per token, 487.36 tokens per second) 2.53.820.448 I slot print_timing: id 0 | task 4705 | eval time = 1280.56 ms / 63 tokens ( 20.65 ms per token, 48.42 tokens per second) 2.53.820.449 I slot print_timing: id 0 | task 4705 | total time = 2870.77 ms / 838 tokens 2.53.820.449 I slot print_timing: id 0 | task 4705 | graphs reused = 4335 2.53.820.450 I slot print_timing: id 0 | task 4705 | graph reallocs = 0 / 0 (same size) / (changed size) 2.53.820.514 I slot release: id 0 | task 4705 | stop processing: n_tokens = 869, truncated = 0 2.53.825.950 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 869, t_last = 390754271973 2.53.825.999 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 326.131 MiB) 2.53.908.078 I slot launch_slot_: id 0 | task 4772 | processing task, is_child = 0 2.56.591.208 I slot print_timing: id 0 | task 4772 | prompt eval time = 1263.83 ms / 573 tokens ( 2.21 ms per token, 453.38 tokens per second) 2.56.591.214 I slot print_timing: id 0 | task 4772 | eval time = 1419.29 ms / 71 tokens ( 20.28 ms per token, 49.32 tokens per second) 2.56.591.214 I slot print_timing: id 0 | task 4772 | total time = 2683.12 ms / 644 tokens 2.56.591.215 I slot print_timing: id 0 | task 4772 | graphs reused = 4404 2.56.591.215 I slot print_timing: id 0 | task 4772 | graph reallocs = 0 / 0 (same size) / (changed size) 2.56.591.263 I slot release: id 0 | task 4772 | stop processing: n_tokens = 675, truncated = 0 2.56.596.311 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 675, t_last = 390757042722 2.56.596.356 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 327.461 MiB) 2.56.596.370 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.478 MiB) 2.56.694.851 I slot launch_slot_: id 0 | task 4847 | processing task, is_child = 0 2.58.952.513 I slot print_timing: id 0 | task 4847 | prompt eval time = 976.72 ms / 461 tokens ( 2.12 ms per token, 471.99 tokens per second) 2.58.952.519 I slot print_timing: id 0 | task 4847 | eval time = 1280.93 ms / 64 tokens ( 20.33 ms per token, 49.18 tokens per second) 2.58.952.519 I slot print_timing: id 0 | task 4847 | total time = 2257.65 ms / 525 tokens 2.58.952.520 I slot print_timing: id 0 | task 4847 | graphs reused = 4465 2.58.952.520 I slot print_timing: id 0 | task 4847 | graph reallocs = 0 / 0 (same size) / (changed size) 2.58.952.554 I slot release: id 0 | task 4847 | stop processing: n_tokens = 556, truncated = 0 2.58.958.095 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 556, t_last = 390759404013 2.58.958.134 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 327.969 MiB) 2.59.016.011 I slot launch_slot_: id 0 | task 4914 | processing task, is_child = 0 3.01.206.578 I slot print_timing: id 0 | task 4914 | prompt eval time = 1319.32 ms / 609 tokens ( 2.17 ms per token, 461.60 tokens per second) 3.01.206.582 I slot print_timing: id 0 | task 4914 | eval time = 871.23 ms / 43 tokens ( 20.74 ms per token, 48.21 tokens per second) 3.01.206.583 I slot print_timing: id 0 | task 4914 | total time = 2190.55 ms / 652 tokens 3.01.206.583 I slot print_timing: id 0 | task 4914 | graphs reused = 4506 3.01.206.584 I slot print_timing: id 0 | task 4914 | graph reallocs = 0 / 0 (same size) / (changed size) 3.01.206.627 I slot release: id 0 | task 4914 | stop processing: n_tokens = 683, truncated = 0 3.01.212.552 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 683, t_last = 390761658086 3.01.212.596 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 261.754 MiB) 3.01.278.052 I slot launch_slot_: id 0 | task 4961 | processing task, is_child = 0 3.04.115.673 I slot print_timing: id 0 | task 4961 | prompt eval time = 1615.98 ms / 791 tokens ( 2.04 ms per token, 489.49 tokens per second) 3.04.115.679 I slot print_timing: id 0 | task 4961 | eval time = 1221.63 ms / 61 tokens ( 20.36 ms per token, 49.11 tokens per second) 3.04.115.680 I slot print_timing: id 0 | task 4961 | total time = 2837.61 ms / 852 tokens 3.04.115.680 I slot print_timing: id 0 | task 4961 | graphs reused = 4565 3.04.115.681 I slot print_timing: id 0 | task 4961 | graph reallocs = 0 / 0 (same size) / (changed size) 3.04.115.736 I slot release: id 0 | task 4961 | stop processing: n_tokens = 883, truncated = 0 3.04.121.127 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 883, t_last = 390764567195 3.04.121.180 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 327.168 MiB) 3.04.121.185 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 326.972 MiB) 3.04.327.219 I slot launch_slot_: id 0 | task 5026 | processing task, is_child = 0 3.06.648.664 I slot print_timing: id 0 | task 5026 | prompt eval time = 1203.48 ms / 533 tokens ( 2.26 ms per token, 442.88 tokens per second) 3.06.648.668 I slot print_timing: id 0 | task 5026 | eval time = 1117.95 ms / 56 tokens ( 20.33 ms per token, 49.20 tokens per second) 3.06.648.669 I slot print_timing: id 0 | task 5026 | total time = 2321.43 ms / 589 tokens 3.06.648.669 I slot print_timing: id 0 | task 5026 | graphs reused = 4619 3.06.648.670 I slot print_timing: id 0 | task 5026 | graph reallocs = 0 / 0 (same size) / (changed size) 3.06.648.748 I slot release: id 0 | task 5026 | stop processing: n_tokens = 677, truncated = 0 3.06.654.872 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 677, t_last = 390767100207 3.06.724.778 I slot launch_slot_: id 0 | task 5086 | processing task, is_child = 0 3.08.913.340 I slot print_timing: id 0 | task 5086 | prompt eval time = 1254.78 ms / 566 tokens ( 2.22 ms per token, 451.08 tokens per second) 3.08.913.344 I slot print_timing: id 0 | task 5086 | eval time = 933.76 ms / 46 tokens ( 20.75 ms per token, 48.19 tokens per second) 3.08.913.344 I slot print_timing: id 0 | task 5086 | total time = 2188.54 ms / 612 tokens 3.08.913.345 I slot print_timing: id 0 | task 5086 | graphs reused = 4663 3.08.913.345 I slot print_timing: id 0 | task 5086 | graph reallocs = 0 / 0 (same size) / (changed size) 3.08.913.440 I slot release: id 0 | task 5086 | stop processing: n_tokens = 643, truncated = 0 3.08.920.033 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 643, t_last = 390769364899 3.08.920.078 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.623 MiB) 3.09.003.880 I slot launch_slot_: id 0 | task 5136 | processing task, is_child = 0 3.10.810.530 I slot print_timing: id 0 | task 5136 | prompt eval time = 951.38 ms / 443 tokens ( 2.15 ms per token, 465.64 tokens per second) 3.10.810.535 I slot print_timing: id 0 | task 5136 | eval time = 855.25 ms / 43 tokens ( 20.36 ms per token, 49.11 tokens per second) 3.10.810.536 I slot print_timing: id 0 | task 5136 | total time = 1806.63 ms / 486 tokens 3.10.810.537 I slot print_timing: id 0 | task 5136 | graphs reused = 4703 3.10.810.537 I slot print_timing: id 0 | task 5136 | graph reallocs = 0 / 0 (same size) / (changed size) 3.10.810.584 I slot release: id 0 | task 5136 | stop processing: n_tokens = 517, truncated = 0 3.10.815.996 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 517, t_last = 390771262043 3.10.816.030 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.017 MiB) 3.10.816.038 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 389.336 MiB) 3.10.877.390 I slot launch_slot_: id 0 | task 5182 | processing task, is_child = 0 3.13.178.814 I slot print_timing: id 0 | task 5182 | prompt eval time = 1002.47 ms / 487 tokens ( 2.06 ms per token, 485.80 tokens per second) 3.13.178.818 I slot print_timing: id 0 | task 5182 | eval time = 1298.94 ms / 65 tokens ( 20.30 ms per token, 49.27 tokens per second) 3.13.178.819 I slot print_timing: id 0 | task 5182 | total time = 2301.41 ms / 552 tokens 3.13.178.819 I slot print_timing: id 0 | task 5182 | graphs reused = 4766 3.13.178.820 I slot print_timing: id 0 | task 5182 | graph reallocs = 0 / 0 (same size) / (changed size) 3.13.178.905 I slot release: id 0 | task 5182 | stop processing: n_tokens = 583, truncated = 0 3.13.184.401 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 583, t_last = 390773630365 3.13.184.442 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.740 MiB) 3.13.251.429 I slot launch_slot_: id 0 | task 5250 | processing task, is_child = 0 3.15.219.607 I slot print_timing: id 0 | task 5250 | prompt eval time = 1034.28 ms / 507 tokens ( 2.04 ms per token, 490.19 tokens per second) 3.15.219.610 I slot print_timing: id 0 | task 5250 | eval time = 933.88 ms / 47 tokens ( 20.30 ms per token, 49.26 tokens per second) 3.15.219.611 I slot print_timing: id 0 | task 5250 | total time = 1968.16 ms / 554 tokens 3.15.219.611 I slot print_timing: id 0 | task 5250 | graphs reused = 4811 3.15.219.612 I slot print_timing: id 0 | task 5250 | graph reallocs = 0 / 0 (same size) / (changed size) 3.15.219.661 I slot release: id 0 | task 5250 | stop processing: n_tokens = 585, truncated = 0 3.15.225.332 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 585, t_last = 390775671120 3.15.225.376 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.922 MiB) 3.15.273.122 I slot launch_slot_: id 0 | task 5300 | processing task, is_child = 0 3.17.949.039 I slot print_timing: id 0 | task 5300 | prompt eval time = 1357.64 ms / 633 tokens ( 2.14 ms per token, 466.25 tokens per second) 3.17.949.045 I slot print_timing: id 0 | task 5300 | eval time = 1318.26 ms / 66 tokens ( 20.28 ms per token, 49.31 tokens per second) 3.17.949.046 I slot print_timing: id 0 | task 5300 | total time = 2675.90 ms / 699 tokens 3.17.949.046 I slot print_timing: id 0 | task 5300 | graphs reused = 4875 3.17.949.047 I slot print_timing: id 0 | task 5300 | graph reallocs = 0 / 0 (same size) / (changed size) 3.17.949.112 I slot release: id 0 | task 5300 | stop processing: n_tokens = 730, truncated = 0 3.17.955.030 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 730, t_last = 390778400571 3.17.955.077 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.788 MiB) 3.18.030.082 I slot launch_slot_: id 0 | task 5370 | processing task, is_child = 0 3.20.228.646 I slot print_timing: id 0 | task 5370 | prompt eval time = 1263.68 ms / 571 tokens ( 2.21 ms per token, 451.86 tokens per second) 3.20.228.651 I slot print_timing: id 0 | task 5370 | eval time = 934.87 ms / 47 tokens ( 20.32 ms per token, 49.20 tokens per second) 3.20.228.655 I slot print_timing: id 0 | task 5370 | total time = 2198.55 ms / 618 tokens 3.20.228.655 I slot print_timing: id 0 | task 5370 | graphs reused = 4920 3.20.228.656 I slot print_timing: id 0 | task 5370 | graph reallocs = 0 / 0 (same size) / (changed size) 3.20.228.700 I slot release: id 0 | task 5370 | stop processing: n_tokens = 649, truncated = 0 3.20.234.979 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 649, t_last = 390780680159 3.20.235.020 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.478 MiB) 3.20.314.854 I slot launch_slot_: id 0 | task 5421 | processing task, is_child = 0 3.22.774.243 I slot print_timing: id 0 | task 5421 | prompt eval time = 1583.58 ms / 798 tokens ( 1.98 ms per token, 503.92 tokens per second) 3.22.774.247 I slot print_timing: id 0 | task 5421 | eval time = 875.79 ms / 44 tokens ( 20.37 ms per token, 49.10 tokens per second) 3.22.774.247 I slot print_timing: id 0 | task 5421 | total time = 2459.37 ms / 842 tokens 3.22.774.248 I slot print_timing: id 0 | task 5421 | graphs reused = 4962 3.22.774.249 I slot print_timing: id 0 | task 5421 | graph reallocs = 0 / 0 (same size) / (changed size) 3.22.774.324 I slot release: id 0 | task 5421 | stop processing: n_tokens = 873, truncated = 0 3.22.779.575 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 873, t_last = 390783225783 3.22.779.628 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.715 MiB) 3.22.862.034 I slot launch_slot_: id 0 | task 5469 | processing task, is_child = 0 3.24.991.667 I slot print_timing: id 0 | task 5469 | prompt eval time = 1276.48 ms / 572 tokens ( 2.23 ms per token, 448.11 tokens per second) 3.24.991.674 I slot print_timing: id 0 | task 5469 | eval time = 853.13 ms / 43 tokens ( 20.31 ms per token, 49.23 tokens per second) 3.24.991.675 I slot print_timing: id 0 | task 5469 | total time = 2129.62 ms / 615 tokens 3.24.991.675 I slot print_timing: id 0 | task 5469 | graphs reused = 5003 3.24.991.676 I slot print_timing: id 0 | task 5469 | graph reallocs = 0 / 0 (same size) / (changed size) 3.24.991.718 I slot release: id 0 | task 5469 | stop processing: n_tokens = 646, truncated = 0 3.24.997.213 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 646, t_last = 390785443177 3.24.997.257 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.282 MiB) 3.24.997.281 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.891 MiB) 3.25.140.499 I slot launch_slot_: id 0 | task 5516 | processing task, is_child = 0 3.27.486.502 I slot print_timing: id 0 | task 5516 | prompt eval time = 1371.36 ms / 613 tokens ( 2.24 ms per token, 447.00 tokens per second) 3.27.486.505 I slot print_timing: id 0 | task 5516 | eval time = 974.63 ms / 49 tokens ( 20.30 ms per token, 49.25 tokens per second) 3.27.486.506 I slot print_timing: id 0 | task 5516 | total time = 2345.99 ms / 662 tokens 3.27.486.506 I slot print_timing: id 0 | task 5516 | graphs reused = 5050 3.27.486.507 I slot print_timing: id 0 | task 5516 | graph reallocs = 0 / 0 (same size) / (changed size) 3.27.486.571 I slot release: id 0 | task 5516 | stop processing: n_tokens = 693, truncated = 0 3.27.492.254 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 390787938030 3.27.492.312 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 453.244 MiB) 3.27.568.016 I slot launch_slot_: id 0 | task 5569 | processing task, is_child = 0 3.30.114.995 I slot print_timing: id 0 | task 5569 | prompt eval time = 1267.16 ms / 580 tokens ( 2.18 ms per token, 457.71 tokens per second) 3.30.115.002 I slot print_timing: id 0 | task 5569 | eval time = 1279.80 ms / 64 tokens ( 20.31 ms per token, 49.23 tokens per second) 3.30.115.002 I slot print_timing: id 0 | task 5569 | total time = 2546.96 ms / 644 tokens 3.30.115.003 I slot print_timing: id 0 | task 5569 | graphs reused = 5112 3.30.115.003 I slot print_timing: id 0 | task 5569 | graph reallocs = 0 / 0 (same size) / (changed size) 3.30.115.078 I slot release: id 0 | task 5569 | stop processing: n_tokens = 675, truncated = 0 3.30.121.120 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 675, t_last = 390790566538 3.30.121.164 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.615 MiB) 3.30.425.986 I slot launch_slot_: id 0 | task 5637 | processing task, is_child = 0 3.32.933.828 I slot print_timing: id 0 | task 5637 | prompt eval time = 1505.87 ms / 716 tokens ( 2.10 ms per token, 475.47 tokens per second) 3.32.933.831 I slot print_timing: id 0 | task 5637 | eval time = 1001.96 ms / 50 tokens ( 20.45 ms per token, 48.90 tokens per second) 3.32.933.833 I slot print_timing: id 0 | task 5637 | total time = 2507.82 ms / 766 tokens 3.32.933.833 I slot print_timing: id 0 | task 5637 | graphs reused = 5159 3.32.933.834 I slot print_timing: id 0 | task 5637 | graph reallocs = 0 / 0 (same size) / (changed size) 3.32.933.918 I slot release: id 0 | task 5637 | stop processing: n_tokens = 797, truncated = 0 3.32.941.562 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 797, t_last = 390793385377 3.32.941.627 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 457.995 MiB) 3.33.041.629 I slot launch_slot_: id 0 | task 5691 | processing task, is_child = 0 3.36.724.003 I slot print_timing: id 0 | task 5691 | prompt eval time = 1612.03 ms / 799 tokens ( 2.02 ms per token, 495.65 tokens per second) 3.36.724.007 I slot print_timing: id 0 | task 5691 | eval time = 2070.32 ms / 103 tokens ( 20.30 ms per token, 49.27 tokens per second) 3.36.724.007 I slot print_timing: id 0 | task 5691 | total time = 3682.35 ms / 902 tokens 3.36.724.008 I slot print_timing: id 0 | task 5691 | graphs reused = 5260 3.36.724.008 I slot print_timing: id 0 | task 5691 | graph reallocs = 0 / 0 (same size) / (changed size) 3.36.724.075 I slot release: id 0 | task 5691 | stop processing: n_tokens = 933, truncated = 0 3.36.728.810 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 933, t_last = 390797175534 3.36.728.911 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.302 MiB) 3.36.809.991 I slot launch_slot_: id 0 | task 5798 | processing task, is_child = 0 3.39.879.977 I slot print_timing: id 0 | task 5798 | prompt eval time = 830.31 ms / 361 tokens ( 2.30 ms per token, 434.78 tokens per second) 3.39.879.980 I slot print_timing: id 0 | task 5798 | eval time = 2239.66 ms / 112 tokens ( 20.18 ms per token, 49.56 tokens per second) 3.39.879.981 I slot print_timing: id 0 | task 5798 | total time = 3069.97 ms / 473 tokens 3.39.879.982 I slot print_timing: id 0 | task 5798 | graphs reused = 5370 3.39.879.982 I slot print_timing: id 0 | task 5798 | graph reallocs = 0 / 0 (same size) / (changed size) 3.39.880.026 I slot release: id 0 | task 5798 | stop processing: n_tokens = 504, truncated = 0 3.39.884.978 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 390800331485 3.39.885.015 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 454.319 MiB) 3.39.951.045 I slot launch_slot_: id 0 | task 5913 | processing task, is_child = 0 3.42.984.773 I slot print_timing: id 0 | task 5913 | prompt eval time = 871.92 ms / 381 tokens ( 2.29 ms per token, 436.97 tokens per second) 3.42.984.776 I slot print_timing: id 0 | task 5913 | eval time = 2161.78 ms / 108 tokens ( 20.20 ms per token, 49.50 tokens per second) 3.42.984.777 I slot print_timing: id 0 | task 5913 | total time = 3033.70 ms / 489 tokens 3.42.984.778 I slot print_timing: id 0 | task 5913 | graphs reused = 5475 3.42.984.779 I slot print_timing: id 0 | task 5913 | graph reallocs = 0 / 0 (same size) / (changed size) 3.42.984.827 I slot release: id 0 | task 5913 | stop processing: n_tokens = 520, truncated = 0 3.42.989.568 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 390803436287 3.42.989.607 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 456.685 MiB) 3.43.038.264 I slot launch_slot_: id 0 | task 6024 | processing task, is_child = 0 3.46.361.728 I slot print_timing: id 0 | task 6024 | prompt eval time = 835.16 ms / 365 tokens ( 2.29 ms per token, 437.04 tokens per second) 3.46.361.731 I slot print_timing: id 0 | task 6024 | eval time = 2488.28 ms / 124 tokens ( 20.23 ms per token, 49.43 tokens per second) 3.46.361.732 I slot print_timing: id 0 | task 6024 | total time = 3323.45 ms / 489 tokens 3.46.361.733 I slot print_timing: id 0 | task 6024 | graphs reused = 5596 3.46.361.733 I slot print_timing: id 0 | task 6024 | graph reallocs = 0 / 0 (same size) / (changed size) 3.46.361.781 I slot release: id 0 | task 6024 | stop processing: n_tokens = 520, truncated = 0 3.46.366.533 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 390806813241 3.46.366.571 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.752 MiB) 3.46.433.317 I slot launch_slot_: id 0 | task 6151 | processing task, is_child = 0 3.49.382.956 I slot print_timing: id 0 | task 6151 | prompt eval time = 806.29 ms / 333 tokens ( 2.42 ms per token, 413.00 tokens per second) 3.49.382.962 I slot print_timing: id 0 | task 6151 | eval time = 2143.33 ms / 107 tokens ( 20.22 ms per token, 49.46 tokens per second) 3.49.382.963 I slot print_timing: id 0 | task 6151 | total time = 2949.62 ms / 440 tokens 3.49.382.963 I slot print_timing: id 0 | task 6151 | graphs reused = 5701 3.49.382.964 I slot print_timing: id 0 | task 6151 | graph reallocs = 0 / 0 (same size) / (changed size) 3.49.383.004 I slot release: id 0 | task 6151 | stop processing: n_tokens = 471, truncated = 0 3.49.388.026 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 471, t_last = 390809834463 3.49.388.059 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 453.048 MiB) 3.49.453.254 I slot launch_slot_: id 0 | task 6261 | processing task, is_child = 0 3.53.113.081 I slot print_timing: id 0 | task 6261 | prompt eval time = 889.69 ms / 403 tokens ( 2.21 ms per token, 452.97 tokens per second) 3.53.113.086 I slot print_timing: id 0 | task 6261 | eval time = 2770.12 ms / 138 tokens ( 20.22 ms per token, 49.46 tokens per second) 3.53.113.087 I slot print_timing: id 0 | task 6261 | total time = 3659.81 ms / 541 tokens 3.53.113.087 I slot print_timing: id 0 | task 6261 | graphs reused = 5836 3.53.113.088 I slot print_timing: id 0 | task 6261 | graph reallocs = 0 / 0 (same size) / (changed size) 3.53.113.122 I slot release: id 0 | task 6261 | stop processing: n_tokens = 572, truncated = 0 3.53.117.885 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 572, t_last = 390813564581 3.53.155.352 I slot launch_slot_: id 0 | task 6402 | processing task, is_child = 0 3.57.086.110 I slot print_timing: id 0 | task 6402 | n_gen = 150, tg = 49.46 t/s, tg_3s = 49.79 t/s 3.57.793.410 I slot print_timing: id 0 | task 6402 | prompt eval time = 918.30 ms / 411 tokens ( 2.23 ms per token, 447.57 tokens per second) 3.57.793.413 I slot print_timing: id 0 | task 6402 | eval time = 3719.75 ms / 185 tokens ( 20.22 ms per token, 49.47 tokens per second) 3.57.793.413 I slot print_timing: id 0 | task 6402 | total time = 4638.04 ms / 596 tokens 3.57.793.414 I slot print_timing: id 0 | task 6402 | graphs reused = 6018 3.57.793.414 I slot print_timing: id 0 | task 6402 | graph reallocs = 0 / 0 (same size) / (changed size) 3.57.793.457 I slot release: id 0 | task 6402 | stop processing: n_tokens = 627, truncated = 0 3.57.798.827 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 627, t_last = 390818244916 3.57.798.871 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 456.959 MiB) 3.57.867.035 I slot launch_slot_: id 0 | task 6590 | processing task, is_child = 0 4.01.921.963 I slot print_timing: id 0 | task 6590 | n_gen = 150, tg = 49.36 t/s, tg_3s = 49.69 t/s 4.03.437.649 I slot print_timing: id 0 | task 6590 | prompt eval time = 1036.04 ms / 490 tokens ( 2.11 ms per token, 472.95 tokens per second) 4.03.437.656 I slot print_timing: id 0 | task 6590 | eval time = 4534.56 ms / 225 tokens ( 20.24 ms per token, 49.40 tokens per second) 4.03.437.656 I slot print_timing: id 0 | task 6590 | total time = 5570.60 ms / 715 tokens 4.03.437.657 I slot print_timing: id 0 | task 6590 | graphs reused = 6241 4.03.437.657 I slot print_timing: id 0 | task 6590 | graph reallocs = 0 / 0 (same size) / (changed size) 4.03.437.705 I slot release: id 0 | task 6590 | stop processing: n_tokens = 746, truncated = 0 4.03.442.406 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 746, t_last = 390823889164 4.03.442.454 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 515.744 MiB) 4.03.498.257 I slot launch_slot_: id 0 | task 6818 | processing task, is_child = 0 4.07.337.244 I slot print_timing: id 0 | task 6818 | n_gen = 150, tg = 49.56 t/s, tg_3s = 49.89 t/s 4.07.760.698 I slot print_timing: id 0 | task 6818 | prompt eval time = 832.39 ms / 344 tokens ( 2.42 ms per token, 413.27 tokens per second) 4.07.760.702 I slot print_timing: id 0 | task 6818 | eval time = 3430.03 ms / 171 tokens ( 20.18 ms per token, 49.56 tokens per second) 4.07.760.702 I slot print_timing: id 0 | task 6818 | total time = 4262.42 ms / 515 tokens 4.07.760.703 I slot print_timing: id 0 | task 6818 | graphs reused = 6409 4.07.760.704 I slot print_timing: id 0 | task 6818 | graph reallocs = 0 / 0 (same size) / (changed size) 4.07.760.752 I slot release: id 0 | task 6818 | stop processing: n_tokens = 546, truncated = 0 4.07.765.607 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 546, t_last = 390828212211 4.07.765.648 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 452.266 MiB) 4.07.823.423 I slot launch_slot_: id 0 | task 6992 | processing task, is_child = 0 4.11.676.253 I slot print_timing: id 0 | task 6992 | n_gen = 150, tg = 49.52 t/s, tg_3s = 49.86 t/s 4.12.100.399 I slot print_timing: id 0 | task 6992 | prompt eval time = 844.18 ms / 347 tokens ( 2.43 ms per token, 411.05 tokens per second) 4.12.100.401 I slot print_timing: id 0 | task 6992 | eval time = 3432.77 ms / 171 tokens ( 20.19 ms per token, 49.52 tokens per second) 4.12.100.402 I slot print_timing: id 0 | task 6992 | total time = 4276.96 ms / 518 tokens 4.12.100.402 I slot print_timing: id 0 | task 6992 | graphs reused = 6577 4.12.100.403 I slot print_timing: id 0 | task 6992 | graph reallocs = 0 / 0 (same size) / (changed size) 4.12.100.434 I slot release: id 0 | task 6992 | stop processing: n_tokens = 549, truncated = 0 4.12.105.277 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 390832551893 4.12.105.316 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.989 MiB) 4.12.168.246 I slot launch_slot_: id 0 | task 7166 | processing task, is_child = 0 4.15.597.145 I slot print_timing: id 0 | task 7166 | prompt eval time = 902.02 ms / 401 tokens ( 2.25 ms per token, 444.56 tokens per second) 4.15.597.150 I slot print_timing: id 0 | task 7166 | eval time = 2526.86 ms / 126 tokens ( 20.21 ms per token, 49.47 tokens per second) 4.15.597.151 I slot print_timing: id 0 | task 7166 | total time = 3428.88 ms / 527 tokens 4.15.597.151 I slot print_timing: id 0 | task 7166 | graphs reused = 6700 4.15.597.152 I slot print_timing: id 0 | task 7166 | graph reallocs = 0 / 0 (same size) / (changed size) 4.15.597.186 I slot release: id 0 | task 7166 | stop processing: n_tokens = 558, truncated = 0 4.15.602.051 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 390836048645 4.15.602.091 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.280 MiB) 4.15.668.167 I slot launch_slot_: id 0 | task 7295 | processing task, is_child = 0 4.19.009.333 I slot print_timing: id 0 | task 7295 | prompt eval time = 993.62 ms / 456 tokens ( 2.18 ms per token, 458.93 tokens per second) 4.19.009.336 I slot print_timing: id 0 | task 7295 | eval time = 2347.54 ms / 115 tokens ( 20.59 ms per token, 48.56 tokens per second) 4.19.009.337 I slot print_timing: id 0 | task 7295 | total time = 3341.15 ms / 571 tokens 4.19.009.338 I slot print_timing: id 0 | task 7295 | graphs reused = 6812 4.19.009.338 I slot print_timing: id 0 | task 7295 | graph reallocs = 0 / 0 (same size) / (changed size) 4.19.009.387 I slot release: id 0 | task 7295 | stop processing: n_tokens = 602, truncated = 0 4.19.014.350 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 4.19.014.392 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.319 MiB) 4.19.091.286 I slot launch_slot_: id 0 | task 7413 | processing task, is_child = 0 4.22.272.921 I slot print_timing: id 0 | task 7413 | prompt eval time = 936.54 ms / 406 tokens ( 2.31 ms per token, 433.51 tokens per second) 4.22.272.931 I slot print_timing: id 0 | task 7413 | eval time = 2245.07 ms / 112 tokens ( 20.23 ms per token, 49.44 tokens per second) 4.22.272.931 I slot print_timing: id 0 | task 7413 | total time = 3181.61 ms / 518 tokens 4.22.272.937 I slot print_timing: id 0 | task 7413 | graphs reused = 6921 4.22.272.937 I slot print_timing: id 0 | task 7413 | graph reallocs = 0 / 0 (same size) / (changed size) 4.22.272.981 I slot release: id 0 | task 7413 | stop processing: n_tokens = 549, truncated = 0 4.22.277.948 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 390842724440 4.22.277.993 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 453.967 MiB) 4.22.347.420 I slot launch_slot_: id 0 | task 7528 | processing task, is_child = 0 4.26.253.849 I slot print_timing: id 0 | task 7528 | n_gen = 150, tg = 49.39 t/s, tg_3s = 49.72 t/s 4.26.838.865 I slot print_timing: id 0 | task 7528 | prompt eval time = 889.73 ms / 406 tokens ( 2.19 ms per token, 456.32 tokens per second) 4.26.838.871 I slot print_timing: id 0 | task 7528 | eval time = 3601.70 ms / 179 tokens ( 20.23 ms per token, 49.42 tokens per second) 4.26.838.872 I slot print_timing: id 0 | task 7528 | total time = 4491.43 ms / 585 tokens 4.26.838.879 I slot print_timing: id 0 | task 7528 | graphs reused = 7097 4.26.838.882 I slot print_timing: id 0 | task 7528 | graph reallocs = 0 / 0 (same size) / (changed size) 4.26.838.916 I slot release: id 0 | task 7528 | stop processing: n_tokens = 616, truncated = 0 4.26.843.619 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 616, t_last = 390847290375 4.26.843.659 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 452.383 MiB) 4.26.913.510 I slot launch_slot_: id 0 | task 7710 | processing task, is_child = 0 4.29.257.519 I slot print_timing: id 0 | task 7710 | prompt eval time = 987.70 ms / 444 tokens ( 2.22 ms per token, 449.53 tokens per second) 4.29.257.525 I slot print_timing: id 0 | task 7710 | eval time = 1356.29 ms / 67 tokens ( 20.55 ms per token, 48.66 tokens per second) 4.29.257.526 I slot print_timing: id 0 | task 7710 | total time = 2343.99 ms / 511 tokens 4.29.257.526 I slot print_timing: id 0 | task 7710 | graphs reused = 7161 4.29.257.527 I slot print_timing: id 0 | task 7710 | graph reallocs = 0 / 0 (same size) / (changed size) 4.29.257.568 I slot release: id 0 | task 7710 | stop processing: n_tokens = 542, truncated = 0 4.29.262.073 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 542, t_last = 390849709027 4.29.315.282 I slot launch_slot_: id 0 | task 7780 | processing task, is_child = 0 4.32.244.512 I slot print_timing: id 0 | task 7780 | prompt eval time = 873.06 ms / 372 tokens ( 2.35 ms per token, 426.09 tokens per second) 4.32.244.519 I slot print_timing: id 0 | task 7780 | eval time = 2056.15 ms / 103 tokens ( 20.16 ms per token, 49.61 tokens per second) 4.32.244.519 I slot print_timing: id 0 | task 7780 | total time = 2929.21 ms / 475 tokens 4.32.244.520 I slot print_timing: id 0 | task 7780 | graphs reused = 7262 4.32.244.520 I slot print_timing: id 0 | task 7780 | graph reallocs = 0 / 0 (same size) / (changed size) 4.32.244.553 I slot release: id 0 | task 7780 | stop processing: n_tokens = 506, truncated = 0 4.32.249.569 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 506, t_last = 390852696012 4.32.249.606 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 456.764 MiB) 4.32.315.916 I slot launch_slot_: id 0 | task 7886 | processing task, is_child = 0 4.36.327.825 I slot print_timing: id 0 | task 7886 | n_gen = 150, tg = 49.39 t/s, tg_3s = 49.72 t/s 4.37.943.433 I slot print_timing: id 0 | task 7886 | prompt eval time = 994.83 ms / 454 tokens ( 2.19 ms per token, 456.36 tokens per second) 4.37.943.439 I slot print_timing: id 0 | task 7886 | eval time = 4632.67 ms / 230 tokens ( 20.23 ms per token, 49.43 tokens per second) 4.37.943.439 I slot print_timing: id 0 | task 7886 | total time = 5627.50 ms / 684 tokens 4.37.943.440 I slot print_timing: id 0 | task 7886 | graphs reused = 7489 4.37.943.441 I slot print_timing: id 0 | task 7886 | graph reallocs = 0 / 0 (same size) / (changed size) 4.37.943.482 I slot release: id 0 | task 7886 | stop processing: n_tokens = 715, truncated = 0 4.37.948.116 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 715, t_last = 390858394941 4.37.948.159 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 452.325 MiB) 4.38.019.267 I slot launch_slot_: id 0 | task 8119 | processing task, is_child = 0 4.41.860.919 I slot print_timing: id 0 | task 8119 | n_gen = 150, tg = 49.54 t/s, tg_3s = 49.87 t/s 4.43.397.397 I slot print_timing: id 0 | task 8119 | prompt eval time = 833.83 ms / 354 tokens ( 2.36 ms per token, 424.55 tokens per second) 4.43.397.403 I slot print_timing: id 0 | task 8119 | eval time = 4544.28 ms / 226 tokens ( 20.20 ms per token, 49.51 tokens per second) 4.43.397.404 I slot print_timing: id 0 | task 8119 | total time = 5378.11 ms / 580 tokens 4.43.397.404 I slot print_timing: id 0 | task 8119 | graphs reused = 7712 4.43.397.405 I slot print_timing: id 0 | task 8119 | graph reallocs = 0 / 0 (same size) / (changed size) 4.43.397.448 I slot release: id 0 | task 8119 | stop processing: n_tokens = 611, truncated = 0 4.43.402.181 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 611, t_last = 390863848907 4.43.402.223 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 453.244 MiB) 4.43.472.247 I slot launch_slot_: id 0 | task 8348 | processing task, is_child = 0 4.47.078.011 I slot print_timing: id 0 | task 8348 | prompt eval time = 804.65 ms / 334 tokens ( 2.41 ms per token, 415.09 tokens per second) 4.47.078.015 I slot print_timing: id 0 | task 8348 | eval time = 2801.09 ms / 140 tokens ( 20.15 ms per token, 49.62 tokens per second) 4.47.078.015 I slot print_timing: id 0 | task 8348 | total time = 3605.74 ms / 474 tokens 4.47.078.016 I slot print_timing: id 0 | task 8348 | graphs reused = 7850 4.47.078.016 I slot print_timing: id 0 | task 8348 | graph reallocs = 0 / 0 (same size) / (changed size) 4.47.078.050 I slot release: id 0 | task 8348 | stop processing: n_tokens = 505, truncated = 0 4.47.083.057 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 505, t_last = 390867529509 4.47.083.097 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 452.892 MiB) 4.47.159.290 I slot launch_slot_: id 0 | task 8491 | processing task, is_child = 0 4.51.112.870 I slot print_timing: id 0 | task 8491 | n_gen = 150, tg = 49.39 t/s, tg_3s = 49.73 t/s 4.51.618.871 I slot print_timing: id 0 | task 8491 | prompt eval time = 937.06 ms / 426 tokens ( 2.20 ms per token, 454.61 tokens per second) 4.51.618.877 I slot print_timing: id 0 | task 8491 | eval time = 3522.50 ms / 175 tokens ( 20.24 ms per token, 49.40 tokens per second) 4.51.618.878 I slot print_timing: id 0 | task 8491 | total time = 4459.56 ms / 601 tokens 4.51.618.878 I slot print_timing: id 0 | task 8491 | graphs reused = 8022 4.51.618.879 I slot print_timing: id 0 | task 8491 | graph reallocs = 0 / 0 (same size) / (changed size) 4.51.618.923 I slot release: id 0 | task 8491 | stop processing: n_tokens = 632, truncated = 0 4.51.623.713 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 632, t_last = 390872070382 4.51.623.756 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 455.277 MiB) 4.51.657.918 I slot launch_slot_: id 0 | task 8669 | processing task, is_child = 0 4.54.846.324 I slot print_timing: id 0 | task 8669 | prompt eval time = 846.12 ms / 366 tokens ( 2.31 ms per token, 432.56 tokens per second) 4.54.846.329 I slot print_timing: id 0 | task 8669 | eval time = 2342.26 ms / 117 tokens ( 20.19 ms per token, 49.52 tokens per second) 4.54.846.346 I slot print_timing: id 0 | task 8669 | total time = 3188.39 ms / 483 tokens 4.54.846.349 I slot print_timing: id 0 | task 8669 | graphs reused = 8136 4.54.846.349 I slot print_timing: id 0 | task 8669 | graph reallocs = 0 / 0 (same size) / (changed size) 4.54.846.398 I slot release: id 0 | task 8669 | stop processing: n_tokens = 514, truncated = 0 4.54.851.038 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 514, t_last = 390875297857 4.54.851.076 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 457.937 MiB) 4.54.864.820 I slot launch_slot_: id 0 | task 8789 | processing task, is_child = 0 4.58.875.017 I slot print_timing: id 0 | task 8789 | n_gen = 150, tg = 49.34 t/s, tg_3s = 49.67 t/s 5.01.100.012 I slot print_timing: id 0 | task 8789 | prompt eval time = 990.45 ms / 462 tokens ( 2.14 ms per token, 466.46 tokens per second) 5.01.100.018 I slot print_timing: id 0 | task 8789 | eval time = 5244.73 ms / 260 tokens ( 20.25 ms per token, 49.38 tokens per second) 5.01.100.019 I slot print_timing: id 0 | task 8789 | total time = 6235.18 ms / 722 tokens 5.01.100.019 I slot print_timing: id 0 | task 8789 | graphs reused = 8393 5.01.100.020 I slot print_timing: id 0 | task 8789 | graph reallocs = 0 / 0 (same size) / (changed size) 5.01.100.071 I slot release: id 0 | task 8789 | stop processing: n_tokens = 753, truncated = 0 5.01.104.850 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 753, t_last = 390881551530 5.01.131.668 I slot launch_slot_: id 0 | task 9052 | processing task, is_child = 0 5.04.830.716 I slot print_timing: id 0 | task 9052 | prompt eval time = 906.96 ms / 396 tokens ( 2.29 ms per token, 436.62 tokens per second) 5.04.830.723 I slot print_timing: id 0 | task 9052 | eval time = 2792.07 ms / 139 tokens ( 20.23 ms per token, 49.43 tokens per second) 5.04.830.723 I slot print_timing: id 0 | task 9052 | total time = 3699.03 ms / 535 tokens 5.04.830.724 I slot print_timing: id 0 | task 9052 | graphs reused = 8529 5.04.830.724 I slot print_timing: id 0 | task 9052 | graph reallocs = 0 / 0 (same size) / (changed size) 5.04.830.767 I slot release: id 0 | task 9052 | stop processing: n_tokens = 566, truncated = 0 5.04.835.785 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 566, t_last = 390885282226 5.04.835.823 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.735 MiB) 5.04.855.757 I slot launch_slot_: id 0 | task 9194 | processing task, is_child = 0 5.08.878.943 I slot print_timing: id 0 | task 9194 | n_gen = 150, tg = 49.34 t/s, tg_3s = 49.67 t/s 5.09.101.548 I slot print_timing: id 0 | task 9194 | prompt eval time = 1003.31 ms / 458 tokens ( 2.19 ms per token, 456.49 tokens per second) 5.09.101.554 I slot print_timing: id 0 | task 9194 | eval time = 3242.47 ms / 161 tokens ( 20.27 ms per token, 49.35 tokens per second) 5.09.101.555 I slot print_timing: id 0 | task 9194 | total time = 4245.78 ms / 619 tokens 5.09.101.556 I slot print_timing: id 0 | task 9194 | graphs reused = 8687 5.09.101.556 I slot print_timing: id 0 | task 9194 | graph reallocs = 0 / 0 (same size) / (changed size) 5.09.101.606 I slot release: id 0 | task 9194 | stop processing: n_tokens = 650, truncated = 0 5.09.106.493 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 650, t_last = 390889553065 5.09.106.536 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.048 MiB) 5.09.119.425 I slot launch_slot_: id 0 | task 9358 | processing task, is_child = 0 5.13.119.996 I slot print_timing: id 0 | task 9358 | n_gen = 149, tg = 49.30 t/s, tg_3s = 49.64 t/s 5.16.136.124 I slot print_timing: id 0 | task 9358 | n_gen = 297, tg = 49.19 t/s, tg_3s = 49.07 t/s 5.18.220.410 I slot print_timing: id 0 | task 9358 | prompt eval time = 998.67 ms / 458 tokens ( 2.18 ms per token, 458.61 tokens per second) 5.18.220.414 I slot print_timing: id 0 | task 9358 | eval time = 8102.30 ms / 400 tokens ( 20.31 ms per token, 49.25 tokens per second) 5.18.220.415 I slot print_timing: id 0 | task 9358 | total time = 9100.98 ms / 858 tokens 5.18.220.416 I slot print_timing: id 0 | task 9358 | graphs reused = 9083 5.18.220.416 I slot print_timing: id 0 | task 9358 | graph reallocs = 0 / 0 (same size) / (changed size) 5.18.220.455 I slot release: id 0 | task 9358 | stop processing: n_tokens = 889, truncated = 0 5.18.225.490 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 889, t_last = 390898671914 5.18.225.541 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.048 MiB) 5.18.249.409 I slot launch_slot_: id 0 | task 9761 | processing task, is_child = 0 5.22.231.944 I slot print_timing: id 0 | task 9761 | n_gen = 149, tg = 49.30 t/s, tg_3s = 49.63 t/s 5.23.466.598 I slot print_timing: id 0 | task 9761 | prompt eval time = 980.31 ms / 452 tokens ( 2.17 ms per token, 461.08 tokens per second) 5.23.466.605 I slot print_timing: id 0 | task 9761 | eval time = 4236.86 ms / 210 tokens ( 20.27 ms per token, 49.33 tokens per second) 5.23.466.606 I slot print_timing: id 0 | task 9761 | total time = 5217.18 ms / 662 tokens 5.23.466.606 I slot print_timing: id 0 | task 9761 | graphs reused = 9290 5.23.466.606 I slot print_timing: id 0 | task 9761 | graph reallocs = 0 / 0 (same size) / (changed size) 5.23.466.639 I slot release: id 0 | task 9761 | stop processing: n_tokens = 693, truncated = 0 5.23.471.520 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 390903918098 5.23.471.567 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.090 MiB) 5.23.491.820 I slot launch_slot_: id 0 | task 9974 | processing task, is_child = 0 5.26.823.439 I slot print_timing: id 0 | task 9974 | prompt eval time = 920.22 ms / 404 tokens ( 2.28 ms per token, 439.03 tokens per second) 5.26.823.442 I slot print_timing: id 0 | task 9974 | eval time = 2411.39 ms / 120 tokens ( 20.26 ms per token, 49.35 tokens per second) 5.26.823.442 I slot print_timing: id 0 | task 9974 | total time = 3331.61 ms / 524 tokens 5.26.823.443 I slot print_timing: id 0 | task 9974 | graphs reused = 9407 5.26.823.444 I slot print_timing: id 0 | task 9974 | graph reallocs = 0 / 0 (same size) / (changed size) 5.26.823.488 I slot release: id 0 | task 9974 | stop processing: n_tokens = 555, truncated = 0 5.26.828.116 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 555, t_last = 390907274947 5.26.828.157 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.064 MiB) 5.26.845.171 I slot launch_slot_: id 0 | task 10097 | processing task, is_child = 0 5.29.785.666 I slot print_timing: id 0 | task 10097 | prompt eval time = 818.98 ms / 345 tokens ( 2.37 ms per token, 421.26 tokens per second) 5.29.785.673 I slot print_timing: id 0 | task 10097 | eval time = 2121.51 ms / 106 tokens ( 20.20 ms per token, 49.49 tokens per second) 5.29.785.673 I slot print_timing: id 0 | task 10097 | total time = 2940.48 ms / 451 tokens 5.29.785.674 I slot print_timing: id 0 | task 10097 | graphs reused = 9511 5.29.785.674 I slot print_timing: id 0 | task 10097 | graph reallocs = 0 / 0 (same size) / (changed size) 5.29.785.704 I slot release: id 0 | task 10097 | stop processing: n_tokens = 482, truncated = 0 5.29.790.220 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 482, t_last = 390910237163 5.29.790.256 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 389.140 MiB) 5.29.816.842 I slot launch_slot_: id 0 | task 10206 | processing task, is_child = 0 5.32.914.235 I slot print_timing: id 0 | task 10206 | prompt eval time = 988.35 ms / 430 tokens ( 2.30 ms per token, 435.07 tokens per second) 5.32.914.241 I slot print_timing: id 0 | task 10206 | eval time = 2109.03 ms / 105 tokens ( 20.28 ms per token, 49.31 tokens per second) 5.32.914.242 I slot print_timing: id 0 | task 10206 | total time = 3097.38 ms / 535 tokens 5.32.914.242 I slot print_timing: id 0 | task 10206 | graphs reused = 9613 5.32.914.243 I slot print_timing: id 0 | task 10206 | graph reallocs = 0 / 0 (same size) / (changed size) 5.32.914.274 I slot release: id 0 | task 10206 | stop processing: n_tokens = 566, truncated = 0 5.32.918.767 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 566, t_last = 390913365733 5.32.918.807 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 391.467 MiB) 5.32.932.901 I slot launch_slot_: id 0 | task 10314 | processing task, is_child = 0 5.35.427.131 I slot print_timing: id 0 | task 10314 | prompt eval time = 780.65 ms / 316 tokens ( 2.47 ms per token, 404.79 tokens per second) 5.35.427.138 I slot print_timing: id 0 | task 10314 | eval time = 1713.57 ms / 85 tokens ( 20.40 ms per token, 49.02 tokens per second) 5.35.427.138 I slot print_timing: id 0 | task 10314 | total time = 2494.22 ms / 401 tokens 5.35.427.139 I slot print_timing: id 0 | task 10314 | graphs reused = 9696 5.35.427.140 I slot print_timing: id 0 | task 10314 | graph reallocs = 0 / 0 (same size) / (changed size) 5.35.427.167 I slot release: id 0 | task 10314 | stop processing: n_tokens = 432, truncated = 0 5.35.431.884 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 432, t_last = 390915878626 5.35.431.919 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.556 MiB) 5.35.446.023 I slot launch_slot_: id 0 | task 10402 | processing task, is_child = 0 5.38.421.372 I slot print_timing: id 0 | task 10402 | prompt eval time = 834.22 ms / 354 tokens ( 2.36 ms per token, 424.35 tokens per second) 5.38.421.378 I slot print_timing: id 0 | task 10402 | eval time = 2141.12 ms / 107 tokens ( 20.20 ms per token, 49.51 tokens per second) 5.38.421.379 I slot print_timing: id 0 | task 10402 | total time = 2975.34 ms / 461 tokens 5.38.421.379 I slot print_timing: id 0 | task 10402 | graphs reused = 9801 5.38.421.380 I slot print_timing: id 0 | task 10402 | graph reallocs = 0 / 0 (same size) / (changed size) 5.38.421.409 I slot release: id 0 | task 10402 | stop processing: n_tokens = 492, truncated = 0 5.38.426.382 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 492, t_last = 390918872868 5.38.426.418 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.615 MiB) 5.38.454.872 I slot launch_slot_: id 0 | task 10512 | processing task, is_child = 0 5.41.361.031 I slot print_timing: id 0 | task 10512 | prompt eval time = 939.88 ms / 438 tokens ( 2.15 ms per token, 466.02 tokens per second) 5.41.361.038 I slot print_timing: id 0 | task 10512 | eval time = 1966.27 ms / 98 tokens ( 20.27 ms per token, 49.33 tokens per second) 5.41.361.039 I slot print_timing: id 0 | task 10512 | total time = 2906.14 ms / 536 tokens 5.41.361.040 I slot print_timing: id 0 | task 10512 | graphs reused = 9896 5.41.361.040 I slot print_timing: id 0 | task 10512 | graph reallocs = 0 / 0 (same size) / (changed size) 5.41.361.072 I slot release: id 0 | task 10512 | stop processing: n_tokens = 567, truncated = 0 5.41.366.176 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 567, t_last = 390921812531 5.41.366.215 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.791 MiB) 5.41.379.857 I slot launch_slot_: id 0 | task 10613 | processing task, is_child = 0 5.43.751.287 I slot print_timing: id 0 | task 10613 | prompt eval time = 969.10 ms / 457 tokens ( 2.12 ms per token, 471.57 tokens per second) 5.43.751.293 I slot print_timing: id 0 | task 10613 | eval time = 1402.32 ms / 70 tokens ( 20.32 ms per token, 49.20 tokens per second) 5.43.751.293 I slot print_timing: id 0 | task 10613 | total time = 2371.42 ms / 527 tokens 5.43.751.294 I slot print_timing: id 0 | task 10613 | graphs reused = 9963 5.43.751.294 I slot print_timing: id 0 | task 10613 | graph reallocs = 0 / 0 (same size) / (changed size) 5.43.751.337 I slot release: id 0 | task 10613 | stop processing: n_tokens = 558, truncated = 0 5.43.756.384 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 390924202796 5.43.756.423 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.651 MiB) 5.43.770.511 I slot launch_slot_: id 0 | task 10686 | processing task, is_child = 0 5.46.736.255 I slot print_timing: id 0 | task 10686 | prompt eval time = 995.77 ms / 473 tokens ( 2.11 ms per token, 475.01 tokens per second) 5.46.736.261 I slot print_timing: id 0 | task 10686 | eval time = 1969.96 ms / 98 tokens ( 20.31 ms per token, 49.24 tokens per second) 5.46.736.262 I slot print_timing: id 0 | task 10686 | total time = 2965.74 ms / 571 tokens 5.46.736.263 I slot print_timing: id 0 | task 10686 | graphs reused = 10058 5.46.736.264 I slot print_timing: id 0 | task 10686 | graph reallocs = 0 / 0 (same size) / (changed size) 5.46.736.311 I slot release: id 0 | task 10686 | stop processing: n_tokens = 602, truncated = 0 5.46.741.188 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 602, t_last = 390927187770 5.46.741.227 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.615 MiB) 5.46.758.431 I slot launch_slot_: id 0 | task 10787 | processing task, is_child = 0 5.48.286.281 I slot print_timing: id 0 | task 10787 | prompt eval time = 992.63 ms / 476 tokens ( 2.09 ms per token, 479.54 tokens per second) 5.48.286.284 I slot print_timing: id 0 | task 10787 | eval time = 535.20 ms / 27 tokens ( 20.58 ms per token, 48.58 tokens per second) 5.48.286.284 I slot print_timing: id 0 | task 10787 | total time = 1527.83 ms / 503 tokens 5.48.286.285 I slot print_timing: id 0 | task 10787 | graphs reused = 10082 5.48.286.286 I slot print_timing: id 0 | task 10787 | graph reallocs = 0 / 0 (same size) / (changed size) 5.48.286.326 I slot release: id 0 | task 10787 | stop processing: n_tokens = 534, truncated = 0 5.48.291.164 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 534, t_last = 390928737785 5.48.291.203 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.925 MiB) 5.48.305.853 I slot launch_slot_: id 0 | task 10817 | processing task, is_child = 0 5.51.458.466 I slot print_timing: id 0 | task 10817 | prompt eval time = 1000.88 ms / 466 tokens ( 2.15 ms per token, 465.59 tokens per second) 5.51.458.473 I slot print_timing: id 0 | task 10817 | eval time = 2151.72 ms / 107 tokens ( 20.30 ms per token, 49.26 tokens per second) 5.51.458.473 I slot print_timing: id 0 | task 10817 | total time = 3152.60 ms / 573 tokens 5.51.458.474 I slot print_timing: id 0 | task 10817 | graphs reused = 10186 5.51.458.475 I slot print_timing: id 0 | task 10817 | graph reallocs = 0 / 0 (same size) / (changed size) 5.51.458.523 I slot release: id 0 | task 10817 | stop processing: n_tokens = 604, truncated = 0 5.51.463.349 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 604, t_last = 390931909982 5.51.463.390 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.478 MiB) 5.51.476.593 I slot launch_slot_: id 0 | task 10927 | processing task, is_child = 0 5.53.937.287 I slot print_timing: id 0 | task 10927 | prompt eval time = 899.79 ms / 415 tokens ( 2.17 ms per token, 461.22 tokens per second) 5.53.937.290 I slot print_timing: id 0 | task 10927 | eval time = 1560.89 ms / 78 tokens ( 20.27 ms per token, 49.33 tokens per second) 5.53.937.291 I slot print_timing: id 0 | task 10927 | total time = 2460.68 ms / 493 tokens 5.53.937.291 I slot print_timing: id 0 | task 10927 | graphs reused = 10261 5.53.937.292 I slot print_timing: id 0 | task 10927 | graph reallocs = 0 / 0 (same size) / (changed size) 5.53.937.328 I slot release: id 0 | task 10927 | stop processing: n_tokens = 524, truncated = 0 5.53.942.424 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 524, t_last = 390934388787 5.53.942.466 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.774 MiB) 5.53.959.196 I slot launch_slot_: id 0 | task 11008 | processing task, is_child = 0 5.56.047.877 I slot print_timing: id 0 | task 11008 | prompt eval time = 813.42 ms / 352 tokens ( 2.31 ms per token, 432.74 tokens per second) 5.56.047.883 I slot print_timing: id 0 | task 11008 | eval time = 1275.25 ms / 64 tokens ( 20.24 ms per token, 49.40 tokens per second) 5.56.047.884 I slot print_timing: id 0 | task 11008 | total time = 2088.67 ms / 416 tokens 5.56.047.884 I slot print_timing: id 0 | task 11008 | graphs reused = 10323 5.56.047.885 I slot print_timing: id 0 | task 11008 | graph reallocs = 0 / 0 (same size) / (changed size) 5.56.047.915 I slot release: id 0 | task 11008 | stop processing: n_tokens = 447, truncated = 0 5.56.053.222 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 390936499374 5.56.053.258 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 390.861 MiB) 5.56.067.681 I slot launch_slot_: id 0 | task 11075 | processing task, is_child = 0 5.59.967.643 I slot print_timing: id 0 | task 11075 | prompt eval time = 1226.93 ms / 550 tokens ( 2.23 ms per token, 448.27 tokens per second) 5.59.967.650 I slot print_timing: id 0 | task 11075 | eval time = 2673.03 ms / 133 tokens ( 20.25 ms per token, 49.38 tokens per second) 5.59.967.650 I slot print_timing: id 0 | task 11075 | total time = 3899.95 ms / 683 tokens 5.59.967.651 I slot print_timing: id 0 | task 11075 | graphs reused = 10454 5.59.967.652 I slot print_timing: id 0 | task 11075 | graph reallocs = 0 / 0 (same size) / (changed size) 5.59.967.692 I slot release: id 0 | task 11075 | stop processing: n_tokens = 714, truncated = 0 5.59.973.385 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 714, t_last = 390940419151 5.59.973.434 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.827 MiB) 5.59.973.438 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.754 MiB) 6.00.002.833 I slot launch_slot_: id 0 | task 11212 | processing task, is_child = 0 6.04.605.632 I slot print_timing: id 0 | task 11212 | n_gen = 149, tg = 49.28 t/s, tg_3s = 49.61 t/s 6.07.611.111 I slot print_timing: id 0 | task 11212 | n_gen = 297, tg = 49.26 t/s, tg_3s = 49.24 t/s 6.10.618.948 I slot print_timing: id 0 | task 11212 | n_gen = 445, tg = 49.24 t/s, tg_3s = 49.20 t/s 6.11.374.211 I slot print_timing: id 0 | task 11212 | prompt eval time = 1599.33 ms / 772 tokens ( 2.07 ms per token, 482.70 tokens per second) 6.11.374.214 I slot print_timing: id 0 | task 11212 | eval time = 9772.04 ms / 482 tokens ( 20.32 ms per token, 49.22 tokens per second) 6.11.374.215 I slot print_timing: id 0 | task 11212 | total time = 11371.37 ms / 1254 tokens 6.11.374.216 I slot print_timing: id 0 | task 11212 | graphs reused = 10932 6.11.374.216 I slot print_timing: id 0 | task 11212 | graph reallocs = 0 / 0 (same size) / (changed size) 6.11.374.261 I slot release: id 0 | task 11212 | stop processing: n_tokens = 1285, truncated = 0 6.11.379.665 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1285, t_last = 390951825720 6.11.379.740 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 389.238 MiB) 6.11.419.772 I slot launch_slot_: id 0 | task 11698 | processing task, is_child = 0 6.15.909.249 I slot print_timing: id 0 | task 11698 | n_gen = 150, tg = 49.36 t/s, tg_3s = 49.69 t/s 6.16.537.713 I slot print_timing: id 0 | task 11698 | prompt eval time = 1470.61 ms / 683 tokens ( 2.15 ms per token, 464.43 tokens per second) 6.16.537.719 I slot print_timing: id 0 | task 11698 | eval time = 3647.31 ms / 181 tokens ( 20.26 ms per token, 49.35 tokens per second) 6.16.537.720 I slot print_timing: id 0 | task 11698 | total time = 5117.92 ms / 864 tokens 6.16.537.720 I slot print_timing: id 0 | task 11698 | graphs reused = 11110 6.16.537.721 I slot print_timing: id 0 | task 11698 | graph reallocs = 0 / 0 (same size) / (changed size) 6.16.537.785 I slot release: id 0 | task 11698 | stop processing: n_tokens = 895, truncated = 0 6.16.543.277 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 895, t_last = 390956989245 6.16.543.330 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.930 MiB) 6.16.569.358 I slot launch_slot_: id 0 | task 11883 | processing task, is_child = 0 6.20.893.841 I slot print_timing: id 0 | task 11883 | n_gen = 149, tg = 49.10 t/s, tg_3s = 49.43 t/s 6.22.414.335 I slot print_timing: id 0 | task 11883 | prompt eval time = 1310.00 ms / 579 tokens ( 2.26 ms per token, 441.99 tokens per second) 6.22.414.341 I slot print_timing: id 0 | task 11883 | eval time = 4534.97 ms / 224 tokens ( 20.34 ms per token, 49.17 tokens per second) 6.22.414.342 I slot print_timing: id 0 | task 11883 | total time = 5844.96 ms / 803 tokens 6.22.414.342 I slot print_timing: id 0 | task 11883 | graphs reused = 11331 6.22.414.343 I slot print_timing: id 0 | task 11883 | graph reallocs = 0 / 0 (same size) / (changed size) 6.22.414.382 I slot release: id 0 | task 11883 | stop processing: n_tokens = 834, truncated = 0 6.22.419.679 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 834, t_last = 390962865842 6.22.419.730 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 391.604 MiB) 6.22.458.327 I slot launch_slot_: id 0 | task 12111 | processing task, is_child = 0 6.25.617.054 I slot print_timing: id 0 | task 12111 | prompt eval time = 1030.91 ms / 500 tokens ( 2.06 ms per token, 485.01 tokens per second) 6.25.617.060 I slot print_timing: id 0 | task 12111 | eval time = 2127.80 ms / 106 tokens ( 20.26 ms per token, 49.35 tokens per second) 6.25.617.061 I slot print_timing: id 0 | task 12111 | total time = 3158.71 ms / 606 tokens 6.25.617.061 I slot print_timing: id 0 | task 12111 | graphs reused = 11435 6.25.617.062 I slot print_timing: id 0 | task 12111 | graph reallocs = 0 / 0 (same size) / (changed size) 6.25.617.100 I slot release: id 0 | task 12111 | stop processing: n_tokens = 637, truncated = 0 6.25.623.127 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 390966068559 6.25.623.170 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.947 MiB) 6.25.633.223 I slot launch_slot_: id 0 | task 12220 | processing task, is_child = 0 6.30.267.696 I slot print_timing: id 0 | task 12220 | n_gen = 150, tg = 49.33 t/s, tg_3s = 49.67 t/s 6.33.273.780 I slot print_timing: id 0 | task 12220 | n_gen = 298, tg = 49.28 t/s, tg_3s = 49.23 t/s 6.34.677.427 I slot print_timing: id 0 | task 12220 | prompt eval time = 1614.25 ms / 776 tokens ( 2.08 ms per token, 480.72 tokens per second) 6.34.677.431 I slot print_timing: id 0 | task 12220 | eval time = 7429.94 ms / 367 tokens ( 20.30 ms per token, 49.26 tokens per second) 6.34.677.431 I slot print_timing: id 0 | task 12220 | total time = 9044.19 ms / 1143 tokens 6.34.677.432 I slot print_timing: id 0 | task 12220 | graphs reused = 11799 6.34.677.432 I slot print_timing: id 0 | task 12220 | graph reallocs = 0 / 0 (same size) / (changed size) 6.34.677.474 I slot release: id 0 | task 12220 | stop processing: n_tokens = 1174, truncated = 0 6.34.683.110 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1174, t_last = 390975128933 6.34.683.182 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 389.590 MiB) 6.34.859.853 I slot launch_slot_: id 0 | task 12591 | processing task, is_child = 0 6.37.032.383 I slot print_timing: id 0 | task 12591 | prompt eval time = 1036.97 ms / 504 tokens ( 2.06 ms per token, 486.03 tokens per second) 6.37.032.387 I slot print_timing: id 0 | task 12591 | eval time = 1135.54 ms / 57 tokens ( 20.28 ms per token, 49.32 tokens per second) 6.37.032.388 I slot print_timing: id 0 | task 12591 | total time = 2172.51 ms / 561 tokens 6.37.032.388 I slot print_timing: id 0 | task 12591 | graphs reused = 11854 6.37.032.389 I slot print_timing: id 0 | task 12591 | graph reallocs = 0 / 0 (same size) / (changed size) 6.37.032.436 I slot release: id 0 | task 12591 | stop processing: n_tokens = 592, truncated = 0 6.37.037.841 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 592, t_last = 390977483895 6.37.037.889 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 394.263 MiB) 6.37.062.712 I slot launch_slot_: id 0 | task 12651 | processing task, is_child = 0 6.41.460.263 I slot print_timing: id 0 | task 12651 | n_gen = 149, tg = 49.30 t/s, tg_3s = 49.63 t/s 6.44.479.480 I slot print_timing: id 0 | task 12651 | n_gen = 298, tg = 49.32 t/s, tg_3s = 49.35 t/s 6.47.490.426 I slot print_timing: id 0 | task 12651 | n_gen = 446, tg = 49.27 t/s, tg_3s = 49.15 t/s 6.50.256.564 I slot print_timing: id 0 | task 12651 | prompt eval time = 1395.41 ms / 633 tokens ( 2.20 ms per token, 453.63 tokens per second) 6.50.256.567 I slot print_timing: id 0 | task 12651 | eval time = 11798.42 ms / 582 tokens ( 20.31 ms per token, 49.24 tokens per second) 6.50.256.568 I slot print_timing: id 0 | task 12651 | total time = 13193.84 ms / 1215 tokens 6.50.256.568 I slot print_timing: id 0 | task 12651 | graphs reused = 12432 6.50.256.569 I slot print_timing: id 0 | task 12651 | graph reallocs = 0 / 0 (same size) / (changed size) 6.50.256.625 I slot release: id 0 | task 12651 | stop processing: n_tokens = 1246, truncated = 0 6.50.261.852 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1246, t_last = 390990708084 6.50.261.921 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 390.431 MiB) 6.50.507.588 I slot launch_slot_: id 0 | task 13237 | processing task, is_child = 0 6.52.679.020 I slot print_timing: id 0 | task 13237 | prompt eval time = 883.26 ms / 395 tokens ( 2.24 ms per token, 447.21 tokens per second) 6.52.679.022 I slot print_timing: id 0 | task 13237 | eval time = 1288.16 ms / 65 tokens ( 20.13 ms per token, 49.68 tokens per second) 6.52.679.023 I slot print_timing: id 0 | task 13237 | total time = 2171.41 ms / 460 tokens 6.52.679.025 I slot print_timing: id 0 | task 13237 | graphs reused = 12495 6.52.679.026 I slot print_timing: id 0 | task 13237 | graph reallocs = 0 / 0 (same size) / (changed size) 6.52.679.068 I slot release: id 0 | task 13237 | stop processing: n_tokens = 491, truncated = 0 6.52.684.163 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 491, t_last = 390993130527 6.52.684.197 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.732 MiB) 6.52.723.960 I slot launch_slot_: id 0 | task 13305 | processing task, is_child = 0 6.57.046.948 I slot print_timing: id 0 | task 13305 | n_gen = 149, tg = 49.23 t/s, tg_3s = 49.57 t/s 6.58.264.398 I slot print_timing: id 0 | task 13305 | prompt eval time = 1316.82 ms / 584 tokens ( 2.25 ms per token, 443.49 tokens per second) 6.58.264.402 I slot print_timing: id 0 | task 13305 | eval time = 4223.60 ms / 209 tokens ( 20.31 ms per token, 49.25 tokens per second) 6.58.264.402 I slot print_timing: id 0 | task 13305 | total time = 5540.42 ms / 793 tokens 6.58.264.403 I slot print_timing: id 0 | task 13305 | graphs reused = 12701 6.58.264.404 I slot print_timing: id 0 | task 13305 | graph reallocs = 0 / 0 (same size) / (changed size) 6.58.264.464 I slot release: id 0 | task 13305 | stop processing: n_tokens = 824, truncated = 0 6.58.270.480 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 824, t_last = 390998715923 6.58.270.534 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.305 MiB) 6.58.270.557 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.947 MiB) 6.58.336.462 I slot launch_slot_: id 0 | task 13518 | processing task, is_child = 0 7.02.829.737 I slot print_timing: id 0 | task 13518 | n_gen = 149, tg = 49.30 t/s, tg_3s = 49.63 t/s 7.04.469.324 I slot print_timing: id 0 | task 13518 | prompt eval time = 1491.19 ms / 695 tokens ( 2.15 ms per token, 466.07 tokens per second) 7.04.469.333 I slot print_timing: id 0 | task 13518 | eval time = 4641.66 ms / 230 tokens ( 20.27 ms per token, 49.34 tokens per second) 7.04.469.334 I slot print_timing: id 0 | task 13518 | total time = 6132.84 ms / 925 tokens 7.04.469.335 I slot print_timing: id 0 | task 13518 | graphs reused = 12928 7.04.469.335 I slot print_timing: id 0 | task 13518 | graph reallocs = 0 / 0 (same size) / (changed size) 7.04.469.388 I slot release: id 0 | task 13518 | stop processing: n_tokens = 956, truncated = 0 7.04.475.406 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 956, t_last = 391004920847 7.04.475.461 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 385.327 MiB) 7.04.528.549 I slot launch_slot_: id 0 | task 13752 | processing task, is_child = 0 7.09.102.101 I slot print_timing: id 0 | task 13752 | n_gen = 149, tg = 49.33 t/s, tg_3s = 49.67 t/s 7.09.954.104 I slot print_timing: id 0 | task 13752 | prompt eval time = 1573.51 ms / 769 tokens ( 2.05 ms per token, 488.72 tokens per second) 7.09.954.110 I slot print_timing: id 0 | task 13752 | eval time = 3852.03 ms / 191 tokens ( 20.27 ms per token, 49.32 tokens per second) 7.09.954.110 I slot print_timing: id 0 | task 13752 | total time = 5425.54 ms / 960 tokens 7.09.954.111 I slot print_timing: id 0 | task 13752 | graphs reused = 13117 7.09.954.112 I slot print_timing: id 0 | task 13752 | graph reallocs = 0 / 0 (same size) / (changed size) 7.09.954.166 I slot release: id 0 | task 13752 | stop processing: n_tokens = 991, truncated = 0 7.09.959.739 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 991, t_last = 391010405625 7.09.959.797 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.500 MiB) 7.10.032.057 I slot launch_slot_: id 0 | task 13947 | processing task, is_child = 0 7.13.811.968 I slot print_timing: id 0 | task 13947 | prompt eval time = 1269.48 ms / 576 tokens ( 2.20 ms per token, 453.73 tokens per second) 7.13.811.975 I slot print_timing: id 0 | task 13947 | eval time = 2510.41 ms / 124 tokens ( 20.41 ms per token, 49.00 tokens per second) 7.13.811.976 I slot print_timing: id 0 | task 13947 | total time = 3779.90 ms / 700 tokens 7.13.811.976 I slot print_timing: id 0 | task 13947 | graphs reused = 13239 7.13.811.977 I slot print_timing: id 0 | task 13947 | graph reallocs = 0 / 0 (same size) / (changed size) 7.13.812.023 I slot release: id 0 | task 13947 | stop processing: n_tokens = 731, truncated = 0 7.13.817.524 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 731, t_last = 391014263482 7.13.817.568 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.967 MiB) 7.13.883.653 I slot launch_slot_: id 0 | task 14075 | processing task, is_child = 0 7.18.315.039 I slot print_timing: id 0 | task 14075 | n_gen = 150, tg = 49.39 t/s, tg_3s = 49.73 t/s 7.20.887.265 I slot print_timing: id 0 | task 14075 | prompt eval time = 1414.80 ms / 655 tokens ( 2.16 ms per token, 462.96 tokens per second) 7.20.887.269 I slot print_timing: id 0 | task 14075 | eval time = 5588.79 ms / 275 tokens ( 20.40 ms per token, 49.03 tokens per second) 7.20.887.270 I slot print_timing: id 0 | task 14075 | total time = 7003.59 ms / 930 tokens 7.20.887.270 I slot print_timing: id 0 | task 14075 | graphs reused = 13511 7.20.887.271 I slot print_timing: id 0 | task 14075 | graph reallocs = 0 / 0 (same size) / (changed size) 7.20.887.429 I slot release: id 0 | task 14075 | stop processing: n_tokens = 961, truncated = 0 7.20.895.442 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 961, t_last = 391021338889 7.20.895.505 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.791 MiB) 7.20.990.482 I slot launch_slot_: id 0 | task 14354 | processing task, is_child = 0 7.24.829.535 I slot print_timing: id 0 | task 14354 | prompt eval time = 1414.12 ms / 621 tokens ( 2.28 ms per token, 439.14 tokens per second) 7.24.829.542 I slot print_timing: id 0 | task 14354 | eval time = 2424.91 ms / 121 tokens ( 20.21 ms per token, 49.49 tokens per second) 7.24.829.543 I slot print_timing: id 0 | task 14354 | total time = 3839.04 ms / 742 tokens 7.24.829.543 I slot print_timing: id 0 | task 14354 | graphs reused = 13629 7.24.829.544 I slot print_timing: id 0 | task 14354 | graph reallocs = 0 / 0 (same size) / (changed size) 7.24.829.691 I slot release: id 0 | task 14354 | stop processing: n_tokens = 773, truncated = 0 7.24.836.490 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 773, t_last = 391025281150 7.24.836.536 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.651 MiB) 7.24.836.559 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.321 MiB) 7.24.936.302 I slot launch_slot_: id 0 | task 14479 | processing task, is_child = 0 7.29.557.508 I slot print_timing: id 0 | task 14479 | n_gen = 149, tg = 49.19 t/s, tg_3s = 49.52 t/s 7.30.263.524 I slot print_timing: id 0 | task 14479 | prompt eval time = 1612.16 ms / 767 tokens ( 2.10 ms per token, 475.76 tokens per second) 7.30.263.530 I slot print_timing: id 0 | task 14479 | eval time = 3715.04 ms / 184 tokens ( 20.30 ms per token, 49.26 tokens per second) 7.30.263.531 I slot print_timing: id 0 | task 14479 | total time = 5327.20 ms / 951 tokens 7.30.263.539 I slot print_timing: id 0 | task 14479 | graphs reused = 13811 7.30.263.541 I slot print_timing: id 0 | task 14479 | graph reallocs = 0 / 0 (same size) / (changed size) 7.30.263.693 I slot release: id 0 | task 14479 | stop processing: n_tokens = 982, truncated = 0 7.30.270.530 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 982, t_last = 391030715152 7.30.270.587 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.690 MiB) 7.30.351.626 I slot launch_slot_: id 0 | task 14667 | processing task, is_child = 0 7.35.093.014 I slot print_timing: id 0 | task 14667 | n_gen = 149, tg = 49.18 t/s, tg_3s = 49.51 t/s 7.38.100.136 I slot print_timing: id 0 | task 14667 | n_gen = 297, tg = 49.20 t/s, tg_3s = 49.22 t/s 7.41.117.075 I slot print_timing: id 0 | task 14667 | n_gen = 445, tg = 49.15 t/s, tg_3s = 49.06 t/s 7.43.376.701 I slot print_timing: id 0 | task 14667 | prompt eval time = 1731.81 ms / 864 tokens ( 2.00 ms per token, 498.90 tokens per second) 7.43.376.707 I slot print_timing: id 0 | task 14667 | eval time = 11293.24 ms / 555 tokens ( 20.38 ms per token, 49.06 tokens per second) 7.43.376.709 I slot print_timing: id 0 | task 14667 | total time = 13025.06 ms / 1419 tokens 7.43.376.710 I slot print_timing: id 0 | task 14667 | graphs reused = 14362 7.43.376.711 I slot print_timing: id 0 | task 14667 | graph reallocs = 0 / 0 (same size) / (changed size) 7.43.376.788 I slot release: id 0 | task 14667 | stop processing: n_tokens = 1450, truncated = 0 7.43.383.666 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1450, t_last = 391043828247 7.43.383.739 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.126 MiB) 7.43.474.613 I slot launch_slot_: id 0 | task 15226 | processing task, is_child = 0 7.47.500.330 I slot print_timing: id 0 | task 15226 | prompt eval time = 1429.70 ms / 646 tokens ( 2.21 ms per token, 451.84 tokens per second) 7.47.500.337 I slot print_timing: id 0 | task 15226 | eval time = 2595.99 ms / 129 tokens ( 20.28 ms per token, 49.31 tokens per second) 7.47.500.337 I slot print_timing: id 0 | task 15226 | total time = 4025.70 ms / 775 tokens 7.47.500.338 I slot print_timing: id 0 | task 15226 | graphs reused = 14488 7.47.500.338 I slot print_timing: id 0 | task 15226 | graph reallocs = 0 / 0 (same size) / (changed size) 7.47.500.411 I slot release: id 0 | task 15226 | stop processing: n_tokens = 806, truncated = 0 7.47.506.537 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 806, t_last = 391047951870 7.47.506.587 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 385.620 MiB) 7.47.593.294 I slot launch_slot_: id 0 | task 15359 | processing task, is_child = 0 7.52.159.049 I slot print_timing: id 0 | task 15359 | n_gen = 149, tg = 49.01 t/s, tg_3s = 49.34 t/s 7.53.656.933 I slot print_timing: id 0 | task 15359 | prompt eval time = 1545.82 ms / 720 tokens ( 2.15 ms per token, 465.77 tokens per second) 7.53.656.936 I slot print_timing: id 0 | task 15359 | eval time = 4517.80 ms / 222 tokens ( 20.44 ms per token, 48.92 tokens per second) 7.53.656.936 I slot print_timing: id 0 | task 15359 | total time = 6063.62 ms / 942 tokens 7.53.656.937 I slot print_timing: id 0 | task 15359 | graphs reused = 14707 7.53.656.938 I slot print_timing: id 0 | task 15359 | graph reallocs = 0 / 0 (same size) / (changed size) 7.53.656.978 I slot release: id 0 | task 15359 | stop processing: n_tokens = 973, truncated = 0 7.53.662.362 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 973, t_last = 391054108437 7.53.662.422 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 453.654 MiB) 7.53.747.503 I slot launch_slot_: id 0 | task 15585 | processing task, is_child = 0 7.57.836.475 I slot print_timing: id 0 | task 15585 | n_gen = 150, tg = 49.40 t/s, tg_3s = 49.73 t/s 7.59.131.731 I slot print_timing: id 0 | task 15585 | prompt eval time = 1072.80 ms / 509 tokens ( 2.11 ms per token, 474.46 tokens per second) 7.59.131.737 I slot print_timing: id 0 | task 15585 | eval time = 4311.41 ms / 214 tokens ( 20.24 ms per token, 49.40 tokens per second) 7.59.131.737 I slot print_timing: id 0 | task 15585 | total time = 5384.21 ms / 723 tokens 7.59.131.738 I slot print_timing: id 0 | task 15585 | graphs reused = 14919 7.59.131.738 I slot print_timing: id 0 | task 15585 | graph reallocs = 0 / 0 (same size) / (changed size) 7.59.131.790 I slot release: id 0 | task 15585 | stop processing: n_tokens = 754, truncated = 0 7.59.137.516 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 754, t_last = 391059583250 7.59.137.563 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 464.820 MiB) 7.59.213.378 I slot launch_slot_: id 0 | task 15802 | processing task, is_child = 0 8.03.549.236 I slot print_timing: id 0 | task 15802 | n_gen = 150, tg = 49.42 t/s, tg_3s = 49.75 t/s 8.05.415.155 I slot print_timing: id 0 | task 15802 | prompt eval time = 1320.64 ms / 581 tokens ( 2.27 ms per token, 439.94 tokens per second) 8.05.415.160 I slot print_timing: id 0 | task 15802 | eval time = 4881.12 ms / 242 tokens ( 20.25 ms per token, 49.37 tokens per second) 8.05.415.161 I slot print_timing: id 0 | task 15802 | total time = 6201.76 ms / 823 tokens 8.05.415.161 I slot print_timing: id 0 | task 15802 | graphs reused = 15158 8.05.415.162 I slot print_timing: id 0 | task 15802 | graph reallocs = 0 / 0 (same size) / (changed size) 8.05.415.221 I slot release: id 0 | task 15802 | stop processing: n_tokens = 854, truncated = 0 8.05.422.063 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 854, t_last = 391065866680 8.05.422.115 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 457.194 MiB) 8.05.507.900 I slot launch_slot_: id 0 | task 16048 | processing task, is_child = 0 8.10.345.409 I slot print_timing: id 0 | task 16048 | n_gen = 149, tg = 49.21 t/s, tg_3s = 49.54 t/s 8.13.357.904 I slot print_timing: id 0 | task 16048 | n_gen = 297, tg = 49.17 t/s, tg_3s = 49.13 t/s 8.14.094.046 I slot print_timing: id 0 | task 16048 | prompt eval time = 1829.83 ms / 925 tokens ( 1.98 ms per token, 505.51 tokens per second) 8.14.094.051 I slot print_timing: id 0 | task 16048 | eval time = 6756.30 ms / 333 tokens ( 20.35 ms per token, 49.14 tokens per second) 8.14.094.052 I slot print_timing: id 0 | task 16048 | total time = 8586.13 ms / 1258 tokens 8.14.094.052 I slot print_timing: id 0 | task 16048 | graphs reused = 15487 8.14.094.053 I slot print_timing: id 0 | task 16048 | graph reallocs = 0 / 0 (same size) / (changed size) 8.14.094.135 I slot release: id 0 | task 16048 | stop processing: n_tokens = 1289, truncated = 0 8.14.100.640 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1289, t_last = 391074545594 8.14.100.710 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 456.001 MiB) 8.14.194.895 I slot launch_slot_: id 0 | task 16385 | processing task, is_child = 0 8.18.967.692 I slot print_timing: id 0 | task 16385 | n_gen = 148, tg = 48.94 t/s, tg_3s = 49.28 t/s 8.20.941.603 I slot print_timing: id 0 | task 16385 | prompt eval time = 1769.32 ms / 885 tokens ( 2.00 ms per token, 500.19 tokens per second) 8.20.941.609 I slot print_timing: id 0 | task 16385 | eval time = 4977.38 ms / 245 tokens ( 20.40 ms per token, 49.02 tokens per second) 8.20.941.610 I slot print_timing: id 0 | task 16385 | total time = 6746.70 ms / 1130 tokens 8.20.941.611 I slot print_timing: id 0 | task 16385 | graphs reused = 15729 8.20.941.611 I slot print_timing: id 0 | task 16385 | graph reallocs = 0 / 0 (same size) / (changed size) 8.20.941.673 I slot release: id 0 | task 16385 | stop processing: n_tokens = 1161, truncated = 0 8.20.946.894 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1161, t_last = 391081393132 8.20.946.963 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 389.336 MiB) 8.21.092.166 I slot launch_slot_: id 0 | task 16634 | processing task, is_child = 0 8.24.968.843 I slot print_timing: id 0 | task 16634 | n_gen = 150, tg = 49.45 t/s, tg_3s = 49.78 t/s 8.25.636.619 I slot print_timing: id 0 | task 16634 | prompt eval time = 863.25 ms / 392 tokens ( 2.20 ms per token, 454.10 tokens per second) 8.25.636.625 I slot print_timing: id 0 | task 16634 | eval time = 3681.18 ms / 183 tokens ( 20.23 ms per token, 49.44 tokens per second) 8.25.636.626 I slot print_timing: id 0 | task 16634 | total time = 4544.44 ms / 575 tokens 8.25.636.626 I slot print_timing: id 0 | task 16634 | graphs reused = 15909 8.25.636.627 I slot print_timing: id 0 | task 16634 | graph reallocs = 0 / 0 (same size) / (changed size) 8.25.636.669 I slot release: id 0 | task 16634 | stop processing: n_tokens = 606, truncated = 0 8.25.641.328 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 606, t_last = 391086088128 8.25.641.370 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 462.649 MiB) 8.25.706.625 I slot launch_slot_: id 0 | task 16820 | processing task, is_child = 0 8.29.462.434 I slot print_timing: id 0 | task 16820 | n_gen = 150, tg = 49.45 t/s, tg_3s = 49.78 t/s 8.31.393.231 I slot print_timing: id 0 | task 16820 | prompt eval time = 742.76 ms / 331 tokens ( 2.24 ms per token, 445.64 tokens per second) 8.31.393.235 I slot print_timing: id 0 | task 16820 | eval time = 4943.83 ms / 245 tokens ( 20.26 ms per token, 49.35 tokens per second) 8.31.393.235 I slot print_timing: id 0 | task 16820 | total time = 5686.59 ms / 576 tokens 8.31.393.236 I slot print_timing: id 0 | task 16820 | graphs reused = 16151 8.31.393.237 I slot print_timing: id 0 | task 16820 | graph reallocs = 0 / 0 (same size) / (changed size) 8.31.393.273 I slot release: id 0 | task 16820 | stop processing: n_tokens = 607, truncated = 0 8.31.398.032 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 607, t_last = 391091844733 8.31.398.070 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.456 MiB) 8.31.433.861 I slot launch_slot_: id 0 | task 17068 | processing task, is_child = 0 8.35.267.810 I slot print_timing: id 0 | task 17068 | n_gen = 150, tg = 49.41 t/s, tg_3s = 49.74 t/s 8.38.285.926 I slot print_timing: id 0 | task 17068 | n_gen = 299, tg = 49.39 t/s, tg_3s = 49.37 t/s 8.41.304.909 I slot print_timing: id 0 | task 17068 | n_gen = 448, tg = 49.38 t/s, tg_3s = 49.35 t/s 8.44.306.840 I slot print_timing: id 0 | task 17068 | n_gen = 596, tg = 49.36 t/s, tg_3s = 49.30 t/s 8.47.315.903 I slot print_timing: id 0 | task 17068 | n_gen = 744, tg = 49.32 t/s, tg_3s = 49.18 t/s 8.50.326.980 I slot print_timing: id 0 | task 17068 | n_gen = 892, tg = 49.29 t/s, tg_3s = 49.15 t/s 8.53.027.502 I slot print_timing: id 0 | task 17068 | prompt eval time = 818.16 ms / 357 tokens ( 2.29 ms per token, 436.35 tokens per second) 8.53.027.505 I slot print_timing: id 0 | task 17068 | eval time = 20775.46 ms / 1024 tokens ( 20.31 ms per token, 49.24 tokens per second) 8.53.027.506 I slot print_timing: id 0 | task 17068 | total time = 21593.62 ms / 1381 tokens 8.53.027.506 I slot print_timing: id 0 | task 17068 | graphs reused = 17169 8.53.027.507 I slot print_timing: id 0 | task 17068 | graph reallocs = 0 / 0 (same size) / (changed size) 8.53.027.541 I slot release: id 0 | task 17068 | stop processing: n_tokens = 1412, truncated = 0 8.53.032.320 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1412, t_last = 391113479000 8.53.032.398 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 464.057 MiB) 8.53.130.169 I slot launch_slot_: id 0 | task 18095 | processing task, is_child = 0 8.56.889.576 I slot print_timing: id 0 | task 18095 | n_gen = 150, tg = 49.53 t/s, tg_3s = 49.86 t/s 8.58.835.890 I slot print_timing: id 0 | task 18095 | prompt eval time = 751.24 ms / 315 tokens ( 2.38 ms per token, 419.31 tokens per second) 8.58.835.897 I slot print_timing: id 0 | task 18095 | eval time = 4954.47 ms / 246 tokens ( 20.22 ms per token, 49.45 tokens per second) 8.58.835.898 I slot print_timing: id 0 | task 18095 | total time = 5705.71 ms / 561 tokens 8.58.835.898 I slot print_timing: id 0 | task 18095 | graphs reused = 17412 8.58.835.899 I slot print_timing: id 0 | task 18095 | graph reallocs = 0 / 0 (same size) / (changed size) 8.58.835.941 I slot release: id 0 | task 18095 | stop processing: n_tokens = 592, truncated = 0 8.58.840.743 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 592, t_last = 391119287401 8.58.840.785 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.481 MiB) 8.58.885.647 I slot launch_slot_: id 0 | task 18344 | processing task, is_child = 0 9.02.758.409 I slot print_timing: id 0 | task 18344 | n_gen = 150, tg = 49.40 t/s, tg_3s = 49.73 t/s 9.05.769.425 I slot print_timing: id 0 | task 18344 | n_gen = 297, tg = 49.11 t/s, tg_3s = 48.82 t/s 9.08.772.561 I slot print_timing: id 0 | task 18344 | n_gen = 445, tg = 49.17 t/s, tg_3s = 49.28 t/s 9.11.789.941 I slot print_timing: id 0 | task 18344 | n_gen = 594, tg = 49.22 t/s, tg_3s = 49.38 t/s 9.14.657.357 I slot print_timing: id 0 | task 18344 | prompt eval time = 856.27 ms / 378 tokens ( 2.27 ms per token, 441.45 tokens per second) 9.14.657.369 I slot print_timing: id 0 | task 18344 | eval time = 14915.42 ms / 735 tokens ( 20.32 ms per token, 49.21 tokens per second) 9.14.657.373 I slot print_timing: id 0 | task 18344 | total time = 15771.70 ms / 1113 tokens 9.14.657.373 I slot print_timing: id 0 | task 18344 | graphs reused = 18142 9.14.657.374 I slot print_timing: id 0 | task 18344 | graph reallocs = 0 / 0 (same size) / (changed size) 9.14.657.442 I slot release: id 0 | task 18344 | stop processing: n_tokens = 1144, truncated = 0 9.14.661.935 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1144, t_last = 391135108902 9.14.661.999 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 455.805 MiB) 9.14.717.469 I slot launch_slot_: id 0 | task 19082 | processing task, is_child = 0 9.15.988.213 I slot print_timing: id 0 | task 19082 | prompt eval time = 725.45 ms / 295 tokens ( 2.46 ms per token, 406.65 tokens per second) 9.15.988.219 I slot print_timing: id 0 | task 19082 | eval time = 545.28 ms / 28 tokens ( 20.20 ms per token, 49.52 tokens per second) 9.15.988.220 I slot print_timing: id 0 | task 19082 | total time = 1270.72 ms / 323 tokens 9.15.988.220 I slot print_timing: id 0 | task 19082 | graphs reused = 18168 9.15.988.221 I slot print_timing: id 0 | task 19082 | graph reallocs = 0 / 0 (same size) / (changed size) 9.15.988.264 I slot release: id 0 | task 19082 | stop processing: n_tokens = 354, truncated = 0 9.15.992.778 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 354, t_last = 391136439723 9.15.992.809 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 458.387 MiB) 9.16.076.415 I slot launch_slot_: id 0 | task 19113 | processing task, is_child = 0 9.17.746.797 I slot print_timing: id 0 | task 19113 | prompt eval time = 762.44 ms / 337 tokens ( 2.26 ms per token, 442.00 tokens per second) 9.17.746.803 I slot print_timing: id 0 | task 19113 | eval time = 907.92 ms / 46 tokens ( 20.18 ms per token, 49.56 tokens per second) 9.17.746.804 I slot print_timing: id 0 | task 19113 | total time = 1670.36 ms / 383 tokens 9.17.746.804 I slot print_timing: id 0 | task 19113 | graphs reused = 18212 9.17.746.805 I slot print_timing: id 0 | task 19113 | graph reallocs = 0 / 0 (same size) / (changed size) 9.17.746.849 I slot release: id 0 | task 19113 | stop processing: n_tokens = 414, truncated = 0 9.17.751.355 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 391138198308 9.17.823.407 I slot launch_slot_: id 0 | task 19162 | processing task, is_child = 0 9.20.594.113 I slot print_timing: id 0 | task 19162 | prompt eval time = 768.52 ms / 325 tokens ( 2.36 ms per token, 422.89 tokens per second) 9.20.594.119 I slot print_timing: id 0 | task 19162 | eval time = 2002.17 ms / 100 tokens ( 20.22 ms per token, 49.45 tokens per second) 9.20.594.120 I slot print_timing: id 0 | task 19162 | total time = 2770.69 ms / 425 tokens 9.20.594.121 I slot print_timing: id 0 | task 19162 | graphs reused = 18310 9.20.594.121 I slot print_timing: id 0 | task 19162 | graph reallocs = 0 / 0 (same size) / (changed size) 9.20.594.170 I slot release: id 0 | task 19162 | stop processing: n_tokens = 456, truncated = 0 9.20.598.601 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.108 (> 0.100 thold), f_keep = 0.070 9.20.598.636 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 459.071 MiB) 9.20.677.365 I slot launch_slot_: id 0 | task 19265 | processing task, is_child = 0 9.21.933.893 I slot print_timing: id 0 | task 19265 | prompt eval time = 689.17 ms / 264 tokens ( 2.61 ms per token, 383.07 tokens per second) 9.21.933.899 I slot print_timing: id 0 | task 19265 | eval time = 567.34 ms / 29 tokens ( 20.26 ms per token, 49.35 tokens per second) 9.21.933.900 I slot print_timing: id 0 | task 19265 | total time = 1256.51 ms / 293 tokens 9.21.933.901 I slot print_timing: id 0 | task 19265 | graphs reused = 18337 9.21.933.901 I slot print_timing: id 0 | task 19265 | graph reallocs = 0 / 0 (same size) / (changed size) 9.21.933.927 I slot release: id 0 | task 19265 | stop processing: n_tokens = 324, truncated = 0 9.21.938.431 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 324, t_last = 391142385387 9.21.938.459 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 453.987 MiB) 9.22.037.656 I slot launch_slot_: id 0 | task 19297 | processing task, is_child = 0 9.23.713.794 I slot print_timing: id 0 | task 19297 | prompt eval time = 805.92 ms / 331 tokens ( 2.43 ms per token, 410.71 tokens per second) 9.23.713.801 I slot print_timing: id 0 | task 19297 | eval time = 870.21 ms / 44 tokens ( 20.24 ms per token, 49.41 tokens per second) 9.23.713.802 I slot print_timing: id 0 | task 19297 | total time = 1676.12 ms / 375 tokens 9.23.713.802 I slot print_timing: id 0 | task 19297 | graphs reused = 18379 9.23.713.803 I slot print_timing: id 0 | task 19297 | graph reallocs = 0 / 0 (same size) / (changed size) 9.23.713.840 I slot release: id 0 | task 19297 | stop processing: n_tokens = 406, truncated = 0 9.23.718.305 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 406, t_last = 391144165299 9.23.718.339 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 458.484 MiB) 9.23.802.644 I slot launch_slot_: id 0 | task 19344 | processing task, is_child = 0 9.27.283.418 I slot print_timing: id 0 | task 19344 | prompt eval time = 776.47 ms / 333 tokens ( 2.33 ms per token, 428.86 tokens per second) 9.27.283.424 I slot print_timing: id 0 | task 19344 | eval time = 2704.29 ms / 135 tokens ( 20.18 ms per token, 49.55 tokens per second) 9.27.283.425 I slot print_timing: id 0 | task 19344 | total time = 3480.76 ms / 468 tokens 9.27.283.425 I slot print_timing: id 0 | task 19344 | graphs reused = 18512 9.27.283.426 I slot print_timing: id 0 | task 19344 | graph reallocs = 0 / 0 (same size) / (changed size) 9.27.283.458 I slot release: id 0 | task 19344 | stop processing: n_tokens = 499, truncated = 0 9.27.288.241 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 499, t_last = 391147734917 9.27.288.275 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 454.808 MiB) 9.27.371.311 I slot launch_slot_: id 0 | task 19482 | processing task, is_child = 0 9.31.219.689 I slot print_timing: id 0 | task 19482 | n_gen = 150, tg = 49.48 t/s, tg_3s = 49.81 t/s 9.34.237.280 I slot print_timing: id 0 | task 19482 | n_gen = 299, tg = 49.43 t/s, tg_3s = 49.38 t/s 9.37.238.982 I slot print_timing: id 0 | task 19482 | n_gen = 447, tg = 49.39 t/s, tg_3s = 49.31 t/s 9.40.239.664 I slot print_timing: id 0 | task 19482 | n_gen = 595, tg = 49.37 t/s, tg_3s = 49.32 t/s 9.43.249.622 I slot print_timing: id 0 | task 19482 | n_gen = 743, tg = 49.33 t/s, tg_3s = 49.17 t/s 9.46.264.577 I slot print_timing: id 0 | task 19482 | n_gen = 891, tg = 49.29 t/s, tg_3s = 49.09 t/s 9.48.977.703 I slot print_timing: id 0 | task 19482 | prompt eval time = 837.16 ms / 346 tokens ( 2.42 ms per token, 413.30 tokens per second) 9.48.977.710 I slot print_timing: id 0 | task 19482 | eval time = 20769.22 ms / 1024 tokens ( 20.30 ms per token, 49.26 tokens per second) 9.48.977.710 I slot print_timing: id 0 | task 19482 | total time = 21606.38 ms / 1370 tokens 9.48.977.711 I slot print_timing: id 0 | task 19482 | graphs reused = 19530 9.48.977.711 I slot print_timing: id 0 | task 19482 | graph reallocs = 0 / 0 (same size) / (changed size) 9.48.977.751 I slot release: id 0 | task 19482 | stop processing: n_tokens = 1401, truncated = 0 9.48.982.780 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1401, t_last = 391169429210 9.48.982.863 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 458.895 MiB) 9.49.048.875 I slot launch_slot_: id 0 | task 20509 | processing task, is_child = 0 9.51.912.763 I slot print_timing: id 0 | task 20509 | prompt eval time = 745.91 ms / 325 tokens ( 2.30 ms per token, 435.71 tokens per second) 9.51.912.768 I slot print_timing: id 0 | task 20509 | eval time = 2117.96 ms / 106 tokens ( 20.17 ms per token, 49.58 tokens per second) 9.51.912.769 I slot print_timing: id 0 | task 20509 | total time = 2863.87 ms / 431 tokens 9.51.912.769 I slot print_timing: id 0 | task 20509 | graphs reused = 19634 9.51.912.770 I slot print_timing: id 0 | task 20509 | graph reallocs = 0 / 0 (same size) / (changed size) 9.51.912.814 I slot release: id 0 | task 20509 | stop processing: n_tokens = 462, truncated = 0 9.51.918.569 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 462, t_last = 391172364273 9.51.918.602 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 468.046 MiB) 9.51.987.663 I slot launch_slot_: id 0 | task 20618 | processing task, is_child = 0 9.55.766.514 I slot print_timing: id 0 | task 20618 | n_gen = 150, tg = 49.36 t/s, tg_3s = 49.69 t/s 9.57.860.226 I slot print_timing: id 0 | task 20618 | prompt eval time = 760.01 ms / 322 tokens ( 2.36 ms per token, 423.68 tokens per second) 9.57.860.233 I slot print_timing: id 0 | task 20618 | eval time = 5112.53 ms / 253 tokens ( 20.29 ms per token, 49.29 tokens per second) 9.57.860.233 I slot print_timing: id 0 | task 20618 | total time = 5872.55 ms / 575 tokens 9.57.860.234 I slot print_timing: id 0 | task 20618 | graphs reused = 19884 9.57.860.235 I slot print_timing: id 0 | task 20618 | graph reallocs = 0 / 0 (same size) / (changed size) 9.57.860.279 I slot release: id 0 | task 20618 | stop processing: n_tokens = 606, truncated = 0 9.57.865.061 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 606, t_last = 391178311738 9.57.932.361 I slot launch_slot_: id 0 | task 20874 | processing task, is_child = 0 10.01.726.493 I slot print_timing: id 0 | task 20874 | n_gen = 150, tg = 49.40 t/s, tg_3s = 49.73 t/s 10.04.726.922 I slot print_timing: id 0 | task 20874 | n_gen = 298, tg = 49.36 t/s, tg_3s = 49.33 t/s 10.06.432.649 I slot print_timing: id 0 | task 20874 | prompt eval time = 777.70 ms / 338 tokens ( 2.30 ms per token, 434.61 tokens per second) 10.06.432.654 I slot print_timing: id 0 | task 20874 | eval time = 7722.57 ms / 382 tokens ( 20.27 ms per token, 49.34 tokens per second) 10.06.432.655 I slot print_timing: id 0 | task 20874 | total time = 8500.27 ms / 720 tokens 10.06.432.655 I slot print_timing: id 0 | task 20874 | graphs reused = 20263 10.06.432.656 I slot print_timing: id 0 | task 20874 | graph reallocs = 0 / 0 (same size) / (changed size) 10.06.432.694 I slot release: id 0 | task 20874 | stop processing: n_tokens = 751, truncated = 0 10.06.437.507 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 751, t_last = 391186884154 10.06.437.561 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 455.453 MiB) 10.06.517.516 I slot launch_slot_: id 0 | task 21259 | processing task, is_child = 0 10.10.356.036 I slot print_timing: id 0 | task 21259 | n_gen = 150, tg = 49.36 t/s, tg_3s = 49.69 t/s 10.13.362.696 I slot print_timing: id 0 | task 21259 | n_gen = 298, tg = 49.29 t/s, tg_3s = 49.22 t/s 10.14.418.643 I slot print_timing: id 0 | task 21259 | prompt eval time = 819.84 ms / 347 tokens ( 2.36 ms per token, 423.25 tokens per second) 10.14.418.649 I slot print_timing: id 0 | task 21259 | eval time = 7081.27 ms / 350 tokens ( 20.29 ms per token, 49.28 tokens per second) 10.14.418.650 I slot print_timing: id 0 | task 21259 | total time = 7901.11 ms / 697 tokens 10.14.418.650 I slot print_timing: id 0 | task 21259 | graphs reused = 20610 10.14.418.651 I slot print_timing: id 0 | task 21259 | graph reallocs = 0 / 0 (same size) / (changed size) 10.14.418.705 I slot release: id 0 | task 21259 | stop processing: n_tokens = 728, truncated = 0 10.14.423.248 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 728, t_last = 391194870164 10.14.423.292 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 458.719 MiB) 10.14.503.008 I slot launch_slot_: id 0 | task 21612 | processing task, is_child = 0 10.16.389.373 I slot print_timing: id 0 | task 21612 | prompt eval time = 796.47 ms / 331 tokens ( 2.41 ms per token, 415.58 tokens per second) 10.16.389.377 I slot print_timing: id 0 | task 21612 | eval time = 1089.88 ms / 55 tokens ( 20.18 ms per token, 49.55 tokens per second) 10.16.389.377 I slot print_timing: id 0 | task 21612 | total time = 1886.35 ms / 386 tokens 10.16.389.378 I slot print_timing: id 0 | task 21612 | graphs reused = 20663 10.16.389.379 I slot print_timing: id 0 | task 21612 | graph reallocs = 0 / 0 (same size) / (changed size) 10.16.389.405 I slot release: id 0 | task 21612 | stop processing: n_tokens = 417, truncated = 0 10.16.394.418 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 417, t_last = 391196840864 10.16.394.452 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 391.623 MiB) 10.16.483.342 I slot launch_slot_: id 0 | task 21670 | processing task, is_child = 0 10.18.192.607 I slot print_timing: id 0 | task 21670 | prompt eval time = 796.63 ms / 345 tokens ( 2.31 ms per token, 433.07 tokens per second) 10.18.192.611 I slot print_timing: id 0 | task 21670 | eval time = 912.62 ms / 45 tokens ( 20.74 ms per token, 48.21 tokens per second) 10.18.192.611 I slot print_timing: id 0 | task 21670 | total time = 1709.25 ms / 390 tokens 10.18.192.625 I slot print_timing: id 0 | task 21670 | graphs reused = 20706 10.18.192.627 I slot print_timing: id 0 | task 21670 | graph reallocs = 0 / 0 (same size) / (changed size) 10.18.192.667 I slot release: id 0 | task 21670 | stop processing: n_tokens = 421, truncated = 0 10.18.197.200 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 421, t_last = 391198644126 10.18.197.235 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 456.392 MiB) 10.18.265.737 I slot launch_slot_: id 0 | task 21718 | processing task, is_child = 0 10.22.045.549 I slot print_timing: id 0 | task 21718 | n_gen = 150, tg = 49.53 t/s, tg_3s = 49.87 t/s 10.23.968.044 I slot print_timing: id 0 | task 21718 | prompt eval time = 771.74 ms / 320 tokens ( 2.41 ms per token, 414.65 tokens per second) 10.23.968.051 I slot print_timing: id 0 | task 21718 | eval time = 4930.55 ms / 245 tokens ( 20.21 ms per token, 49.49 tokens per second) 10.23.968.051 I slot print_timing: id 0 | task 21718 | total time = 5702.29 ms / 565 tokens 10.23.968.052 I slot print_timing: id 0 | task 21718 | graphs reused = 20948 10.23.968.052 I slot print_timing: id 0 | task 21718 | graph reallocs = 0 / 0 (same size) / (changed size) 10.23.968.080 I slot release: id 0 | task 21718 | stop processing: n_tokens = 596, truncated = 0 10.23.972.768 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 596, t_last = 391204419539 10.23.972.810 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 464.898 MiB) 10.24.047.968 I slot launch_slot_: id 0 | task 21966 | processing task, is_child = 0 10.25.692.966 I slot print_timing: id 0 | task 21966 | prompt eval time = 698.51 ms / 297 tokens ( 2.35 ms per token, 425.19 tokens per second) 10.25.692.971 I slot print_timing: id 0 | task 21966 | eval time = 946.48 ms / 47 tokens ( 20.58 ms per token, 48.60 tokens per second) 10.25.692.972 I slot print_timing: id 0 | task 21966 | total time = 1644.98 ms / 344 tokens 10.25.692.973 I slot print_timing: id 0 | task 21966 | graphs reused = 20993 10.25.692.973 I slot print_timing: id 0 | task 21966 | graph reallocs = 0 / 0 (same size) / (changed size) 10.25.693.003 I slot release: id 0 | task 21966 | stop processing: n_tokens = 375, truncated = 0 10.25.697.383 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 375, t_last = 391206144462 10.25.697.435 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 462.395 MiB) 10.25.801.070 I slot launch_slot_: id 0 | task 22016 | processing task, is_child = 0 10.29.596.477 I slot print_timing: id 0 | task 22016 | n_gen = 150, tg = 49.49 t/s, tg_3s = 49.83 t/s 10.32.599.141 I slot print_timing: id 0 | task 22016 | n_gen = 298, tg = 49.39 t/s, tg_3s = 49.29 t/s 10.34.101.928 I slot print_timing: id 0 | task 22016 | prompt eval time = 784.93 ms / 343 tokens ( 2.29 ms per token, 436.98 tokens per second) 10.34.101.931 I slot print_timing: id 0 | task 22016 | eval time = 7515.91 ms / 372 tokens ( 20.26 ms per token, 49.36 tokens per second) 10.34.101.932 I slot print_timing: id 0 | task 22016 | total time = 8300.84 ms / 715 tokens 10.34.101.933 I slot print_timing: id 0 | task 22016 | graphs reused = 21362 10.34.101.934 I slot print_timing: id 0 | task 22016 | graph reallocs = 0 / 0 (same size) / (changed size) 10.34.101.978 I slot release: id 0 | task 22016 | stop processing: n_tokens = 746, truncated = 0 10.34.106.980 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 746, t_last = 391214553437 10.34.162.329 I slot launch_slot_: id 0 | task 22391 | processing task, is_child = 0 10.37.986.262 I slot print_timing: id 0 | task 22391 | n_gen = 150, tg = 49.50 t/s, tg_3s = 49.83 t/s 10.40.988.097 I slot print_timing: id 0 | task 22391 | n_gen = 298, tg = 49.40 t/s, tg_3s = 49.30 t/s 10.42.595.659 I slot print_timing: id 0 | task 22391 | prompt eval time = 813.80 ms / 371 tokens ( 2.19 ms per token, 455.89 tokens per second) 10.42.595.665 I slot print_timing: id 0 | task 22391 | eval time = 7619.52 ms / 377 tokens ( 20.26 ms per token, 49.35 tokens per second) 10.42.595.666 I slot print_timing: id 0 | task 22391 | total time = 8433.32 ms / 748 tokens 10.42.595.667 I slot print_timing: id 0 | task 22391 | graphs reused = 21735 10.42.595.667 I slot print_timing: id 0 | task 22391 | graph reallocs = 0 / 0 (same size) / (changed size) 10.42.595.712 I slot release: id 0 | task 22391 | stop processing: n_tokens = 779, truncated = 0 10.42.600.187 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 779, t_last = 391223047171 10.42.600.236 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.729 MiB) 10.42.670.048 I slot launch_slot_: id 0 | task 22771 | processing task, is_child = 0 10.44.024.885 I slot print_timing: id 0 | task 22771 | prompt eval time = 727.76 ms / 292 tokens ( 2.49 ms per token, 401.23 tokens per second) 10.44.024.891 I slot print_timing: id 0 | task 22771 | eval time = 627.06 ms / 32 tokens ( 20.23 ms per token, 49.44 tokens per second) 10.44.024.891 I slot print_timing: id 0 | task 22771 | total time = 1354.82 ms / 324 tokens 10.44.024.892 I slot print_timing: id 0 | task 22771 | graphs reused = 21765 10.44.024.892 I slot print_timing: id 0 | task 22771 | graph reallocs = 0 / 0 (same size) / (changed size) 10.44.024.932 I slot release: id 0 | task 22771 | stop processing: n_tokens = 355, truncated = 0 10.44.030.285 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 355, t_last = 391224476391 10.44.030.315 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.749 MiB) 10.44.087.473 I slot launch_slot_: id 0 | task 22806 | processing task, is_child = 0 10.46.539.795 I slot print_timing: id 0 | task 22806 | prompt eval time = 712.43 ms / 301 tokens ( 2.37 ms per token, 422.50 tokens per second) 10.46.539.798 I slot print_timing: id 0 | task 22806 | eval time = 1739.87 ms / 87 tokens ( 20.23 ms per token, 49.43 tokens per second) 10.46.539.799 I slot print_timing: id 0 | task 22806 | total time = 2452.31 ms / 388 tokens 10.46.539.799 I slot print_timing: id 0 | task 22806 | graphs reused = 21850 10.46.539.800 I slot print_timing: id 0 | task 22806 | graph reallocs = 0 / 0 (same size) / (changed size) 10.46.539.837 I slot release: id 0 | task 22806 | stop processing: n_tokens = 419, truncated = 0 10.46.544.244 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 391226991296 10.46.544.279 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 404.490 MiB) 10.46.622.133 I slot launch_slot_: id 0 | task 22896 | processing task, is_child = 0 10.50.372.667 I slot print_timing: id 0 | task 22896 | n_gen = 150, tg = 49.53 t/s, tg_3s = 49.86 t/s 10.51.892.331 I slot print_timing: id 0 | task 22896 | prompt eval time = 742.06 ms / 303 tokens ( 2.45 ms per token, 408.32 tokens per second) 10.51.892.337 I slot print_timing: id 0 | task 22896 | eval time = 4528.12 ms / 225 tokens ( 20.21 ms per token, 49.47 tokens per second) 10.51.892.338 I slot print_timing: id 0 | task 22896 | total time = 5270.18 ms / 528 tokens 10.51.892.339 I slot print_timing: id 0 | task 22896 | graphs reused = 22072 10.51.892.339 I slot print_timing: id 0 | task 22896 | graph reallocs = 0 / 0 (same size) / (changed size) 10.51.892.366 I slot release: id 0 | task 22896 | stop processing: n_tokens = 559, truncated = 0 10.51.896.875 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 559, t_last = 391232343825 10.51.896.912 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.456 MiB) 10.51.941.608 I slot launch_slot_: id 0 | task 23124 | processing task, is_child = 0 10.53.650.883 I slot print_timing: id 0 | task 23124 | prompt eval time = 759.78 ms / 321 tokens ( 2.37 ms per token, 422.49 tokens per second) 10.53.650.889 I slot print_timing: id 0 | task 23124 | eval time = 949.48 ms / 48 tokens ( 20.20 ms per token, 49.50 tokens per second) 10.53.650.890 I slot print_timing: id 0 | task 23124 | total time = 1709.26 ms / 369 tokens 10.53.650.890 I slot print_timing: id 0 | task 23124 | graphs reused = 22118 10.53.650.891 I slot print_timing: id 0 | task 23124 | graph reallocs = 0 / 0 (same size) / (changed size) 10.53.650.918 I slot release: id 0 | task 23124 | stop processing: n_tokens = 400, truncated = 0 10.53.655.535 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 391234102377 10.53.655.569 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 399.249 MiB) 10.53.670.744 I slot launch_slot_: id 0 | task 23175 | processing task, is_child = 0 10.56.158.922 I slot print_timing: id 0 | task 23175 | prompt eval time = 768.09 ms / 322 tokens ( 2.39 ms per token, 419.22 tokens per second) 10.56.158.928 I slot print_timing: id 0 | task 23175 | eval time = 1720.07 ms / 86 tokens ( 20.24 ms per token, 49.42 tokens per second) 10.56.158.929 I slot print_timing: id 0 | task 23175 | total time = 2488.16 ms / 408 tokens 10.56.158.930 I slot print_timing: id 0 | task 23175 | graphs reused = 22202 10.56.158.930 I slot print_timing: id 0 | task 23175 | graph reallocs = 0 / 0 (same size) / (changed size) 10.56.158.962 I slot release: id 0 | task 23175 | stop processing: n_tokens = 439, truncated = 0 10.56.163.399 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 439, t_last = 391236610421 10.56.163.431 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 383.802 MiB) 10.56.181.928 I slot launch_slot_: id 0 | task 23264 | processing task, is_child = 0 10.57.855.438 I slot print_timing: id 0 | task 23264 | prompt eval time = 765.22 ms / 323 tokens ( 2.37 ms per token, 422.10 tokens per second) 10.57.855.444 I slot print_timing: id 0 | task 23264 | eval time = 908.28 ms / 46 tokens ( 20.18 ms per token, 49.54 tokens per second) 10.57.855.445 I slot print_timing: id 0 | task 23264 | total time = 1673.50 ms / 369 tokens 10.57.855.445 I slot print_timing: id 0 | task 23264 | graphs reused = 22246 10.57.855.446 I slot print_timing: id 0 | task 23264 | graph reallocs = 0 / 0 (same size) / (changed size) 10.57.855.485 I slot release: id 0 | task 23264 | stop processing: n_tokens = 400, truncated = 0 10.57.859.908 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 391238306945 10.57.859.938 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 384.975 MiB) 10.57.873.943 I slot launch_slot_: id 0 | task 23313 | processing task, is_child = 0 11.01.638.610 I slot print_timing: id 0 | task 23313 | n_gen = 150, tg = 49.37 t/s, tg_3s = 49.71 t/s 11.04.645.116 I slot print_timing: id 0 | task 23313 | n_gen = 298, tg = 49.30 t/s, tg_3s = 49.23 t/s 11.07.653.157 I slot print_timing: id 0 | task 23313 | n_gen = 446, tg = 49.27 t/s, tg_3s = 49.20 t/s 11.10.661.473 I slot print_timing: id 0 | task 23313 | n_gen = 594, tg = 49.25 t/s, tg_3s = 49.20 t/s 11.13.677.682 I slot print_timing: id 0 | task 23313 | n_gen = 742, tg = 49.21 t/s, tg_3s = 49.07 t/s 11.13.738.429 I slot print_timing: id 0 | task 23313 | prompt eval time = 746.90 ms / 321 tokens ( 2.33 ms per token, 429.77 tokens per second) 11.13.738.431 I slot print_timing: id 0 | task 23313 | eval time = 15117.57 ms / 745 tokens ( 20.32 ms per token, 49.21 tokens per second) 11.13.738.432 I slot print_timing: id 0 | task 23313 | total time = 15864.47 ms / 1066 tokens 11.13.738.433 I slot print_timing: id 0 | task 23313 | graphs reused = 22986 11.13.738.433 I slot print_timing: id 0 | task 23313 | graph reallocs = 0 / 0 (same size) / (changed size) 11.13.738.463 I slot release: id 0 | task 23313 | stop processing: n_tokens = 1097, truncated = 0 11.13.742.833 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1097, t_last = 391254189922 11.13.742.898 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 385.796 MiB) 11.13.757.900 I slot launch_slot_: id 0 | task 24061 | processing task, is_child = 0 11.17.502.383 I slot print_timing: id 0 | task 24061 | n_gen = 150, tg = 49.56 t/s, tg_3s = 49.89 t/s 11.20.522.281 I slot print_timing: id 0 | task 24061 | n_gen = 299, tg = 49.45 t/s, tg_3s = 49.34 t/s 11.23.526.518 I slot print_timing: id 0 | task 24061 | n_gen = 447, tg = 49.39 t/s, tg_3s = 49.26 t/s 11.24.559.473 I slot print_timing: id 0 | task 24061 | prompt eval time = 737.82 ms / 322 tokens ( 2.29 ms per token, 436.42 tokens per second) 11.24.559.480 I slot print_timing: id 0 | task 24061 | eval time = 10063.75 ms / 498 tokens ( 20.25 ms per token, 49.39 tokens per second) 11.24.559.480 I slot print_timing: id 0 | task 24061 | total time = 10801.56 ms / 820 tokens 11.24.559.481 I slot print_timing: id 0 | task 24061 | graphs reused = 23480 11.24.559.481 I slot print_timing: id 0 | task 24061 | graph reallocs = 0 / 0 (same size) / (changed size) 11.24.559.510 I slot release: id 0 | task 24061 | stop processing: n_tokens = 851, truncated = 0 11.24.564.181 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 851, t_last = 391265010969 11.24.564.235 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 383.215 MiB) 11.24.579.261 I slot launch_slot_: id 0 | task 24562 | processing task, is_child = 0 11.26.275.869 I slot print_timing: id 0 | task 24562 | prompt eval time = 783.48 ms / 337 tokens ( 2.32 ms per token, 430.13 tokens per second) 11.26.275.886 I slot print_timing: id 0 | task 24562 | eval time = 913.11 ms / 46 tokens ( 20.29 ms per token, 49.28 tokens per second) 11.26.275.889 I slot print_timing: id 0 | task 24562 | total time = 1696.60 ms / 383 tokens 11.26.275.890 I slot print_timing: id 0 | task 24562 | graphs reused = 23524 11.26.275.891 I slot print_timing: id 0 | task 24562 | graph reallocs = 0 / 0 (same size) / (changed size) 11.26.275.928 I slot release: id 0 | task 24562 | stop processing: n_tokens = 414, truncated = 0 11.26.280.438 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 391266727387 11.26.280.469 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 384.819 MiB) 11.26.298.671 I slot launch_slot_: id 0 | task 24611 | processing task, is_child = 0 11.27.993.163 I slot print_timing: id 0 | task 24611 | prompt eval time = 764.82 ms / 325 tokens ( 2.35 ms per token, 424.93 tokens per second) 11.27.993.172 I slot print_timing: id 0 | task 24611 | eval time = 929.66 ms / 47 tokens ( 20.21 ms per token, 49.48 tokens per second) 11.27.993.173 I slot print_timing: id 0 | task 24611 | total time = 1694.48 ms / 372 tokens 11.27.993.174 I slot print_timing: id 0 | task 24611 | graphs reused = 23569 11.27.993.174 I slot print_timing: id 0 | task 24611 | graph reallocs = 0 / 0 (same size) / (changed size) 11.27.993.204 I slot release: id 0 | task 24611 | stop processing: n_tokens = 403, truncated = 0 11.27.997.834 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 403, t_last = 391268444663 11.27.997.870 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.637 MiB) 11.28.019.106 I slot launch_slot_: id 0 | task 24661 | processing task, is_child = 0 11.30.803.493 I slot print_timing: id 0 | task 24661 | prompt eval time = 784.94 ms / 331 tokens ( 2.37 ms per token, 421.69 tokens per second) 11.30.803.496 I slot print_timing: id 0 | task 24661 | eval time = 1999.43 ms / 100 tokens ( 20.20 ms per token, 49.51 tokens per second) 11.30.803.496 I slot print_timing: id 0 | task 24661 | total time = 2784.38 ms / 431 tokens 11.30.803.497 I slot print_timing: id 0 | task 24661 | graphs reused = 23667 11.30.803.497 I slot print_timing: id 0 | task 24661 | graph reallocs = 0 / 0 (same size) / (changed size) 11.30.803.529 I slot release: id 0 | task 24661 | stop processing: n_tokens = 462, truncated = 0 11.30.808.156 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 462, t_last = 391271254988 11.30.808.195 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 404.275 MiB) 11.30.820.173 I slot launch_slot_: id 0 | task 24764 | processing task, is_child = 0 11.32.637.347 I slot print_timing: id 0 | task 24764 | prompt eval time = 745.61 ms / 336 tokens ( 2.22 ms per token, 450.64 tokens per second) 11.32.637.354 I slot print_timing: id 0 | task 24764 | eval time = 1071.56 ms / 54 tokens ( 20.22 ms per token, 49.46 tokens per second) 11.32.637.355 I slot print_timing: id 0 | task 24764 | total time = 1817.16 ms / 390 tokens 11.32.637.355 I slot print_timing: id 0 | task 24764 | graphs reused = 23719 11.32.637.356 I slot print_timing: id 0 | task 24764 | graph reallocs = 0 / 0 (same size) / (changed size) 11.32.637.384 I slot release: id 0 | task 24764 | stop processing: n_tokens = 421, truncated = 0 11.32.641.966 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 421, t_last = 391273088843 11.32.642.003 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 385.914 MiB) 11.32.657.221 I slot launch_slot_: id 0 | task 24821 | processing task, is_child = 0 11.33.865.884 I slot print_timing: id 0 | task 24821 | prompt eval time = 822.43 ms / 349 tokens ( 2.36 ms per token, 424.35 tokens per second) 11.33.865.891 I slot print_timing: id 0 | task 24821 | eval time = 386.22 ms / 20 tokens ( 20.33 ms per token, 49.19 tokens per second) 11.33.865.891 I slot print_timing: id 0 | task 24821 | total time = 1208.65 ms / 369 tokens 11.33.865.892 I slot print_timing: id 0 | task 24821 | graphs reused = 23737 11.33.865.892 I slot print_timing: id 0 | task 24821 | graph reallocs = 0 / 0 (same size) / (changed size) 11.33.865.929 I slot release: id 0 | task 24821 | stop processing: n_tokens = 400, truncated = 0 11.33.870.616 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 391274317388 11.33.870.653 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.729 MiB) 11.33.921.222 I slot launch_slot_: id 0 | task 24844 | processing task, is_child = 0 11.37.689.446 I slot print_timing: id 0 | task 24844 | n_gen = 150, tg = 49.37 t/s, tg_3s = 49.70 t/s 11.40.694.839 I slot print_timing: id 0 | task 24844 | n_gen = 298, tg = 49.31 t/s, tg_3s = 49.24 t/s 11.43.706.403 I slot print_timing: id 0 | task 24844 | n_gen = 446, tg = 49.25 t/s, tg_3s = 49.14 t/s 11.46.711.423 I slot print_timing: id 0 | task 24844 | n_gen = 594, tg = 49.25 t/s, tg_3s = 49.25 t/s 11.49.728.524 I slot print_timing: id 0 | task 24844 | n_gen = 742, tg = 49.21 t/s, tg_3s = 49.05 t/s 11.52.745.445 I slot print_timing: id 0 | task 24844 | n_gen = 890, tg = 49.19 t/s, tg_3s = 49.06 t/s 11.55.114.884 I slot print_timing: id 0 | task 24844 | prompt eval time = 750.20 ms / 336 tokens ( 2.23 ms per token, 447.88 tokens per second) 11.55.114.890 I slot print_timing: id 0 | task 24844 | eval time = 20443.45 ms / 1006 tokens ( 20.34 ms per token, 49.16 tokens per second) 11.55.114.891 I slot print_timing: id 0 | task 24844 | total time = 21193.65 ms / 1342 tokens 11.55.114.892 I slot print_timing: id 0 | task 24844 | graphs reused = 24737 11.55.114.892 I slot print_timing: id 0 | task 24844 | graph reallocs = 0 / 0 (same size) / (changed size) 11.55.114.925 I slot release: id 0 | task 24844 | stop processing: n_tokens = 1373, truncated = 0 11.55.119.901 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1373, t_last = 391295566384 11.55.119.978 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 391.565 MiB) 11.55.152.491 I slot launch_slot_: id 0 | task 25853 | processing task, is_child = 0 11.58.953.713 I slot print_timing: id 0 | task 25853 | n_gen = 150, tg = 49.34 t/s, tg_3s = 49.67 t/s 12.01.011.170 I slot print_timing: id 0 | task 25853 | prompt eval time = 781.35 ms / 349 tokens ( 2.24 ms per token, 446.66 tokens per second) 12.01.011.173 I slot print_timing: id 0 | task 25853 | eval time = 5077.31 ms / 251 tokens ( 20.31 ms per token, 49.24 tokens per second) 12.01.011.174 I slot print_timing: id 0 | task 25853 | total time = 5858.67 ms / 600 tokens 12.01.011.174 I slot print_timing: id 0 | task 25853 | graphs reused = 24985 12.01.011.175 I slot print_timing: id 0 | task 25853 | graph reallocs = 0 / 0 (same size) / (changed size) 12.01.011.211 I slot release: id 0 | task 25853 | stop processing: n_tokens = 631, truncated = 0 12.01.016.235 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 631, t_last = 391301462670 12.01.016.278 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 391.115 MiB) 12.01.032.427 I slot launch_slot_: id 0 | task 26107 | processing task, is_child = 0 12.02.984.452 I slot print_timing: id 0 | task 26107 | prompt eval time = 780.45 ms / 349 tokens ( 2.24 ms per token, 447.18 tokens per second) 12.02.984.455 I slot print_timing: id 0 | task 26107 | eval time = 1171.56 ms / 59 tokens ( 20.20 ms per token, 49.51 tokens per second) 12.02.984.456 I slot print_timing: id 0 | task 26107 | total time = 1952.01 ms / 408 tokens 12.02.984.456 I slot print_timing: id 0 | task 26107 | graphs reused = 25042 12.02.984.457 I slot print_timing: id 0 | task 26107 | graph reallocs = 0 / 0 (same size) / (changed size) 12.02.984.488 I slot release: id 0 | task 26107 | stop processing: n_tokens = 439, truncated = 0 12.02.989.154 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 439, t_last = 391303435948 12.02.989.192 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 385.034 MiB) 12.03.003.709 I slot launch_slot_: id 0 | task 26169 | processing task, is_child = 0 12.05.209.550 I slot print_timing: id 0 | task 26169 | prompt eval time = 850.88 ms / 385 tokens ( 2.21 ms per token, 452.47 tokens per second) 12.05.209.554 I slot print_timing: id 0 | task 26169 | eval time = 1354.95 ms / 68 tokens ( 20.22 ms per token, 49.45 tokens per second) 12.05.209.554 I slot print_timing: id 0 | task 26169 | total time = 2205.83 ms / 453 tokens 12.05.209.555 I slot print_timing: id 0 | task 26169 | graphs reused = 25108 12.05.209.556 I slot print_timing: id 0 | task 26169 | graph reallocs = 0 / 0 (same size) / (changed size) 12.05.209.586 I slot release: id 0 | task 26169 | stop processing: n_tokens = 484, truncated = 0 12.05.214.109 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 484, t_last = 391305661045 12.05.214.144 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 385.112 MiB) 12.05.232.851 I slot launch_slot_: id 0 | task 26240 | processing task, is_child = 0 12.07.140.310 I slot print_timing: id 0 | task 26240 | prompt eval time = 776.75 ms / 328 tokens ( 2.37 ms per token, 422.27 tokens per second) 12.07.140.316 I slot print_timing: id 0 | task 26240 | eval time = 1130.70 ms / 57 tokens ( 20.19 ms per token, 49.53 tokens per second) 12.07.140.317 I slot print_timing: id 0 | task 26240 | total time = 1907.45 ms / 385 tokens 12.07.140.317 I slot print_timing: id 0 | task 26240 | graphs reused = 25163 12.07.140.318 I slot print_timing: id 0 | task 26240 | graph reallocs = 0 / 0 (same size) / (changed size) 12.07.140.346 I slot release: id 0 | task 26240 | stop processing: n_tokens = 416, truncated = 0 12.07.222.683 I srv operator(): operator(): cleaning up before exit...