$ /Users/minipro/quantdiff/work/llama-b11869/src/build/bin/llama-server -m /Users/minipro/quantdiff/models/campaign/a64fe0bbf936/Sage-A1.5-Q4_K_M.gguf --host 127.0.0.1 --port 8089 -c 4096 -np 1 -ngl 999 -fa on --jinja --seed 1234 --no-webui -a quant 0.00.044.209 I srv llama_server: initializing ... 0.00.044.216 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.046.062 I srv init_listene: The UI is disabled 0.00.046.063 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.046.366 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) 0.00.048.519 I srv load_model: loading model '/Users/minipro/quantdiff/models/campaign/a64fe0bbf936/Sage-A1.5-Q4_K_M.gguf' 0.00.330.973 W model has unused tensor blk.40.attn_norm.weight (size = 8192 bytes) -- ignoring 0.00.330.984 W model has unused tensor blk.40.post_attention_norm.weight (size = 8192 bytes) -- ignoring 0.00.330.991 W model has unused tensor blk.40.attn_q.weight (size = 9437184 bytes) -- ignoring 0.00.330.993 W model has unused tensor blk.40.attn_k.weight (size = 589824 bytes) -- ignoring 0.00.330.996 W model has unused tensor blk.40.attn_v.weight (size = 860160 bytes) -- ignoring 0.00.331.003 W model has unused tensor blk.40.attn_output.weight (size = 4718592 bytes) -- ignoring 0.00.331.006 W model has unused tensor blk.40.attn_q_norm.weight (size = 1024 bytes) -- ignoring 0.00.331.008 W model has unused tensor blk.40.attn_k_norm.weight (size = 1024 bytes) -- ignoring 0.00.331.010 W model has unused tensor blk.40.ffn_gate_inp.weight (size = 2097152 bytes) -- ignoring 0.00.331.012 W model has unused tensor blk.40.ffn_down_exps.weight (size = 220200960 bytes) -- ignoring 0.00.331.016 W model has unused tensor blk.40.ffn_gate_exps.weight (size = 150994944 bytes) -- ignoring 0.00.331.019 W model has unused tensor blk.40.ffn_up_exps.weight (size = 150994944 bytes) -- ignoring 0.00.331.021 W model has unused tensor blk.40.ffn_gate_inp_shexp.weight (size = 8192 bytes) -- ignoring 0.00.331.024 W model has unused tensor blk.40.ffn_gate_shexp.weight (size = 589824 bytes) -- ignoring 0.00.331.026 W model has unused tensor blk.40.ffn_up_shexp.weight (size = 589824 bytes) -- ignoring 0.00.331.028 W model has unused tensor blk.40.ffn_down_shexp.weight (size = 860160 bytes) -- ignoring 0.00.331.031 W model has unused tensor blk.40.nextn.eh_proj.weight (size = 4718592 bytes) -- ignoring 0.00.331.034 W model has unused tensor blk.40.nextn.enorm.weight (size = 8192 bytes) -- ignoring 0.00.331.036 W model has unused tensor blk.40.nextn.hnorm.weight (size = 8192 bytes) -- ignoring 0.00.331.043 W model has unused tensor blk.40.nextn.shared_head_norm.weight (size = 8192 bytes) -- ignoring 0.01.340.468 I cmn init: llama threadpool init, n_threads = 8 0.01.480.883 I srv load_model: initializing, n_slots = 1, n_ctx_slot = 4096, kv_unified = 'false' 0.01.486.395 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.01.486.414 I srv server_run_i: model loaded 0.01.486.416 I srv server_on_li: listening on http://127.0.0.1:8089 0.02.024.923 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.02.025.607 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.04.002.606 I slot print_timing: id 0 | task 0 | prompt eval time = 1184.93 ms / 368 tokens ( 3.22 ms per token, 310.57 tokens per second) 0.04.002.612 I slot print_timing: id 0 | task 0 | eval time = 792.03 ms / 41 tokens ( 19.80 ms per token, 50.50 tokens per second) 0.04.002.613 I slot print_timing: id 0 | task 0 | total time = 1976.96 ms / 409 tokens 0.04.002.614 I slot print_timing: id 0 | task 0 | graphs reused = 40 0.04.002.614 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.04.002.647 I slot release: id 0 | task 0 | stop processing: n_tokens = 408, truncated = 0 0.04.007.905 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 408, t_last = 385902208190 0.04.027.283 I slot launch_slot_: id 0 | task 44 | processing task, is_child = 0 0.05.631.585 I slot print_timing: id 0 | task 44 | prompt eval time = 790.04 ms / 322 tokens ( 2.45 ms per token, 407.57 tokens per second) 0.05.631.591 I slot print_timing: id 0 | task 44 | eval time = 814.25 ms / 42 tokens ( 19.86 ms per token, 50.35 tokens per second) 0.05.631.592 I slot print_timing: id 0 | task 44 | total time = 1604.29 ms / 364 tokens 0.05.631.592 I slot print_timing: id 0 | task 44 | graphs reused = 80 0.05.631.593 I slot print_timing: id 0 | task 44 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.631.627 I slot release: id 0 | task 44 | stop processing: n_tokens = 363, truncated = 0 0.05.636.127 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 363, t_last = 385903837170 0.05.655.290 I slot launch_slot_: id 0 | task 89 | processing task, is_child = 0 0.07.325.817 I slot print_timing: id 0 | task 89 | prompt eval time = 856.05 ms / 365 tokens ( 2.35 ms per token, 426.38 tokens per second) 0.07.325.824 I slot print_timing: id 0 | task 89 | eval time = 814.47 ms / 42 tokens ( 19.87 ms per token, 50.34 tokens per second) 0.07.325.825 I slot print_timing: id 0 | task 89 | total time = 1670.51 ms / 407 tokens 0.07.325.826 I slot print_timing: id 0 | task 89 | graphs reused = 120 0.07.325.826 I slot print_timing: id 0 | task 89 | graph reallocs = 0 / 0 (same size) / (changed size) 0.07.325.854 I slot release: id 0 | task 89 | stop processing: n_tokens = 406, truncated = 0 0.07.330.324 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 406, t_last = 385905531397 0.07.348.563 I slot launch_slot_: id 0 | task 134 | processing task, is_child = 0 0.09.096.642 I slot print_timing: id 0 | task 134 | prompt eval time = 912.98 ms / 397 tokens ( 2.30 ms per token, 434.84 tokens per second) 0.09.096.648 I slot print_timing: id 0 | task 134 | eval time = 835.09 ms / 43 tokens ( 19.88 ms per token, 50.29 tokens per second) 0.09.096.649 I slot print_timing: id 0 | task 134 | total time = 1748.07 ms / 440 tokens 0.09.096.650 I slot print_timing: id 0 | task 134 | graphs reused = 161 0.09.096.650 I slot print_timing: id 0 | task 134 | graph reallocs = 0 / 0 (same size) / (changed size) 0.09.096.682 I slot release: id 0 | task 134 | stop processing: n_tokens = 439, truncated = 0 0.09.101.112 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.117 (> 0.100 thold), f_keep = 0.103 0.09.126.359 I slot launch_slot_: id 0 | task 180 | processing task, is_child = 0 0.11.093.155 I slot print_timing: id 0 | task 180 | prompt eval time = 892.69 ms / 383 tokens ( 2.33 ms per token, 429.04 tokens per second) 0.11.093.164 I slot print_timing: id 0 | task 180 | eval time = 1074.10 ms / 55 tokens ( 19.89 ms per token, 50.27 tokens per second) 0.11.093.164 I slot print_timing: id 0 | task 180 | total time = 1966.78 ms / 438 tokens 0.11.093.165 I slot print_timing: id 0 | task 180 | graphs reused = 214 0.11.093.165 I slot print_timing: id 0 | task 180 | graph reallocs = 0 / 0 (same size) / (changed size) 0.11.093.197 I slot release: id 0 | task 180 | stop processing: n_tokens = 437, truncated = 0 0.11.097.577 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 385909298740 0.11.122.576 I slot launch_slot_: id 0 | task 238 | processing task, is_child = 0 0.13.025.539 I slot print_timing: id 0 | task 238 | prompt eval time = 831.09 ms / 372 tokens ( 2.23 ms per token, 447.61 tokens per second) 0.13.025.542 I slot print_timing: id 0 | task 238 | eval time = 1071.86 ms / 55 tokens ( 19.85 ms per token, 50.38 tokens per second) 0.13.025.543 I slot print_timing: id 0 | task 238 | total time = 1902.95 ms / 427 tokens 0.13.025.544 I slot print_timing: id 0 | task 238 | graphs reused = 267 0.13.025.544 I slot print_timing: id 0 | task 238 | graph reallocs = 0 / 0 (same size) / (changed size) 0.13.025.572 I slot release: id 0 | task 238 | stop processing: n_tokens = 426, truncated = 0 0.13.030.046 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 385911231115 0.13.054.648 I slot launch_slot_: id 0 | task 296 | processing task, is_child = 0 0.15.073.226 I slot print_timing: id 0 | task 296 | prompt eval time = 943.79 ms / 422 tokens ( 2.24 ms per token, 447.13 tokens per second) 0.15.073.232 I slot print_timing: id 0 | task 296 | eval time = 1074.78 ms / 55 tokens ( 19.90 ms per token, 50.24 tokens per second) 0.15.073.233 I slot print_timing: id 0 | task 296 | total time = 2018.57 ms / 477 tokens 0.15.073.234 I slot print_timing: id 0 | task 296 | graphs reused = 320 0.15.073.234 I slot print_timing: id 0 | task 296 | graph reallocs = 0 / 0 (same size) / (changed size) 0.15.073.272 I slot release: id 0 | task 296 | stop processing: n_tokens = 476, truncated = 0 0.15.077.887 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 476, t_last = 385913278815 0.15.102.520 I slot launch_slot_: id 0 | task 354 | processing task, is_child = 0 0.17.514.025 I slot print_timing: id 0 | task 354 | prompt eval time = 994.44 ms / 470 tokens ( 2.12 ms per token, 472.63 tokens per second) 0.17.514.031 I slot print_timing: id 0 | task 354 | eval time = 1417.06 ms / 72 tokens ( 19.96 ms per token, 50.10 tokens per second) 0.17.514.032 I slot print_timing: id 0 | task 354 | total time = 2411.49 ms / 542 tokens 0.17.514.033 I slot print_timing: id 0 | task 354 | graphs reused = 389 0.17.514.034 I slot print_timing: id 0 | task 354 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.514.067 I slot release: id 0 | task 354 | stop processing: n_tokens = 541, truncated = 0 0.17.518.393 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 541, t_last = 385915719610 0.17.544.672 I slot launch_slot_: id 0 | task 429 | processing task, is_child = 0 0.19.289.346 I slot print_timing: id 0 | task 429 | prompt eval time = 829.47 ms / 345 tokens ( 2.40 ms per token, 415.93 tokens per second) 0.19.289.352 I slot print_timing: id 0 | task 429 | eval time = 915.19 ms / 47 tokens ( 19.90 ms per token, 50.26 tokens per second) 0.19.289.353 I slot print_timing: id 0 | task 429 | total time = 1744.66 ms / 392 tokens 0.19.289.354 I slot print_timing: id 0 | task 429 | graphs reused = 434 0.19.289.354 I slot print_timing: id 0 | task 429 | graph reallocs = 0 / 0 (same size) / (changed size) 0.19.289.388 I slot release: id 0 | task 429 | stop processing: n_tokens = 391, truncated = 0 0.19.293.752 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 391, t_last = 385917494931 0.19.318.149 I slot launch_slot_: id 0 | task 479 | processing task, is_child = 0 0.20.966.371 I slot print_timing: id 0 | task 479 | prompt eval time = 852.56 ms / 364 tokens ( 2.34 ms per token, 426.95 tokens per second) 0.20.966.374 I slot print_timing: id 0 | task 479 | eval time = 795.65 ms / 41 tokens ( 19.89 ms per token, 50.27 tokens per second) 0.20.966.374 I slot print_timing: id 0 | task 479 | total time = 1648.21 ms / 405 tokens 0.20.966.375 I slot print_timing: id 0 | task 479 | graphs reused = 473 0.20.966.376 I slot print_timing: id 0 | task 479 | graph reallocs = 0 / 0 (same size) / (changed size) 0.20.966.404 I slot release: id 0 | task 479 | stop processing: n_tokens = 404, truncated = 0 0.20.970.770 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 404, t_last = 385919171947 0.20.992.825 I slot launch_slot_: id 0 | task 523 | processing task, is_child = 0 0.23.055.348 I slot print_timing: id 0 | task 523 | prompt eval time = 830.03 ms / 376 tokens ( 2.21 ms per token, 453.00 tokens per second) 0.23.055.354 I slot print_timing: id 0 | task 523 | eval time = 1232.48 ms / 62 tokens ( 20.20 ms per token, 49.49 tokens per second) 0.23.055.355 I slot print_timing: id 0 | task 523 | total time = 2062.51 ms / 438 tokens 0.23.055.355 I slot print_timing: id 0 | task 523 | graphs reused = 533 0.23.055.356 I slot print_timing: id 0 | task 523 | graph reallocs = 0 / 0 (same size) / (changed size) 0.23.055.385 I slot release: id 0 | task 523 | stop processing: n_tokens = 437, truncated = 0 0.23.059.869 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 385921260928 0.23.084.065 I slot launch_slot_: id 0 | task 588 | processing task, is_child = 0 0.24.915.673 I slot print_timing: id 0 | task 588 | prompt eval time = 916.21 ms / 412 tokens ( 2.22 ms per token, 449.68 tokens per second) 0.24.915.679 I slot print_timing: id 0 | task 588 | eval time = 915.39 ms / 47 tokens ( 19.90 ms per token, 50.25 tokens per second) 0.24.915.679 I slot print_timing: id 0 | task 588 | total time = 1831.60 ms / 459 tokens 0.24.915.680 I slot print_timing: id 0 | task 588 | graphs reused = 578 0.24.915.681 I slot print_timing: id 0 | task 588 | graph reallocs = 0 / 0 (same size) / (changed size) 0.24.915.713 I slot release: id 0 | task 588 | stop processing: n_tokens = 458, truncated = 0 0.24.920.199 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 385923121256 0.24.944.463 I slot launch_slot_: id 0 | task 638 | processing task, is_child = 0 0.27.024.466 I slot print_timing: id 0 | task 638 | prompt eval time = 867.81 ms / 376 tokens ( 2.31 ms per token, 433.27 tokens per second) 0.27.024.472 I slot print_timing: id 0 | task 638 | eval time = 1212.18 ms / 62 tokens ( 19.87 ms per token, 50.32 tokens per second) 0.27.024.473 I slot print_timing: id 0 | task 638 | total time = 2079.99 ms / 438 tokens 0.27.024.474 I slot print_timing: id 0 | task 638 | graphs reused = 638 0.27.024.474 I slot print_timing: id 0 | task 638 | graph reallocs = 0 / 0 (same size) / (changed size) 0.27.024.505 I slot release: id 0 | task 638 | stop processing: n_tokens = 437, truncated = 0 0.27.028.763 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 385925230048 0.27.051.898 I slot launch_slot_: id 0 | task 703 | processing task, is_child = 0 0.28.916.684 I slot print_timing: id 0 | task 703 | prompt eval time = 849.30 ms / 378 tokens ( 2.25 ms per token, 445.07 tokens per second) 0.28.916.687 I slot print_timing: id 0 | task 703 | eval time = 1015.48 ms / 52 tokens ( 19.91 ms per token, 50.22 tokens per second) 0.28.916.688 I slot print_timing: id 0 | task 703 | total time = 1864.77 ms / 430 tokens 0.28.916.688 I slot print_timing: id 0 | task 703 | graphs reused = 688 0.28.916.689 I slot print_timing: id 0 | task 703 | graph reallocs = 0 / 0 (same size) / (changed size) 0.28.916.722 I slot release: id 0 | task 703 | stop processing: n_tokens = 429, truncated = 0 0.28.921.225 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 429, t_last = 385927122265 0.28.946.719 I slot launch_slot_: id 0 | task 758 | processing task, is_child = 0 0.30.938.127 I slot print_timing: id 0 | task 758 | prompt eval time = 840.17 ms / 367 tokens ( 2.29 ms per token, 436.82 tokens per second) 0.30.938.133 I slot print_timing: id 0 | task 758 | eval time = 1151.23 ms / 58 tokens ( 20.20 ms per token, 49.51 tokens per second) 0.30.938.134 I slot print_timing: id 0 | task 758 | total time = 1991.40 ms / 425 tokens 0.30.938.135 I slot print_timing: id 0 | task 758 | graphs reused = 744 0.30.938.135 I slot print_timing: id 0 | task 758 | graph reallocs = 0 / 0 (same size) / (changed size) 0.30.938.167 I slot release: id 0 | task 758 | stop processing: n_tokens = 424, truncated = 0 0.30.942.464 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 385929143711 0.30.966.217 I slot launch_slot_: id 0 | task 819 | processing task, is_child = 0 0.32.791.025 I slot print_timing: id 0 | task 819 | prompt eval time = 832.03 ms / 347 tokens ( 2.40 ms per token, 417.05 tokens per second) 0.32.791.032 I slot print_timing: id 0 | task 819 | eval time = 992.76 ms / 51 tokens ( 19.86 ms per token, 50.36 tokens per second) 0.32.791.033 I slot print_timing: id 0 | task 819 | total time = 1824.79 ms / 398 tokens 0.32.791.034 I slot print_timing: id 0 | task 819 | graphs reused = 793 0.32.791.034 I slot print_timing: id 0 | task 819 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.791.061 I slot release: id 0 | task 819 | stop processing: n_tokens = 397, truncated = 0 0.32.795.355 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 397, t_last = 385930996604 0.32.818.536 I slot launch_slot_: id 0 | task 873 | processing task, is_child = 0 0.34.742.662 I slot print_timing: id 0 | task 873 | prompt eval time = 868.30 ms / 369 tokens ( 2.35 ms per token, 424.97 tokens per second) 0.34.742.668 I slot print_timing: id 0 | task 873 | eval time = 1055.81 ms / 54 tokens ( 19.92 ms per token, 50.20 tokens per second) 0.34.742.669 I slot print_timing: id 0 | task 873 | total time = 1924.11 ms / 423 tokens 0.34.742.670 I slot print_timing: id 0 | task 873 | graphs reused = 845 0.34.742.670 I slot print_timing: id 0 | task 873 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.742.697 I slot release: id 0 | task 873 | stop processing: n_tokens = 422, truncated = 0 0.34.746.979 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 422, t_last = 385932948240 0.34.772.355 I slot launch_slot_: id 0 | task 930 | processing task, is_child = 0 0.36.402.406 I slot print_timing: id 0 | task 930 | prompt eval time = 833.42 ms / 352 tokens ( 2.37 ms per token, 422.36 tokens per second) 0.36.402.415 I slot print_timing: id 0 | task 930 | eval time = 796.62 ms / 41 tokens ( 19.92 ms per token, 50.21 tokens per second) 0.36.402.416 I slot print_timing: id 0 | task 930 | total time = 1630.04 ms / 393 tokens 0.36.402.417 I slot print_timing: id 0 | task 930 | graphs reused = 884 0.36.402.417 I slot print_timing: id 0 | task 930 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.402.448 I slot release: id 0 | task 930 | stop processing: n_tokens = 392, truncated = 0 0.36.406.826 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 392, t_last = 385934607991 0.36.489.229 I slot launch_slot_: id 0 | task 974 | processing task, is_child = 0 0.38.103.072 I slot print_timing: id 0 | task 974 | prompt eval time = 838.44 ms / 349 tokens ( 2.40 ms per token, 416.25 tokens per second) 0.38.103.075 I slot print_timing: id 0 | task 974 | eval time = 775.39 ms / 40 tokens ( 19.88 ms per token, 50.30 tokens per second) 0.38.103.077 I slot print_timing: id 0 | task 974 | total time = 1613.83 ms / 389 tokens 0.38.103.077 I slot print_timing: id 0 | task 974 | graphs reused = 922 0.38.103.078 I slot print_timing: id 0 | task 974 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.103.114 I slot release: id 0 | task 974 | stop processing: n_tokens = 388, truncated = 0 0.38.107.655 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 388, t_last = 385936308657 0.38.193.684 I slot launch_slot_: id 0 | task 1017 | processing task, is_child = 0 0.40.343.967 I slot print_timing: id 0 | task 1017 | prompt eval time = 899.55 ms / 384 tokens ( 2.34 ms per token, 426.88 tokens per second) 0.40.343.970 I slot print_timing: id 0 | task 1017 | eval time = 1250.70 ms / 63 tokens ( 20.17 ms per token, 49.57 tokens per second) 0.40.343.971 I slot print_timing: id 0 | task 1017 | total time = 2150.26 ms / 447 tokens 0.40.343.972 I slot print_timing: id 0 | task 1017 | graphs reused = 983 0.40.343.973 I slot print_timing: id 0 | task 1017 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.344.041 I slot release: id 0 | task 1017 | stop processing: n_tokens = 446, truncated = 0 0.40.350.117 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 446, t_last = 385938549586 0.40.627.428 I slot launch_slot_: id 0 | task 1083 | processing task, is_child = 0 0.42.514.682 I slot print_timing: id 0 | task 1083 | prompt eval time = 830.67 ms / 356 tokens ( 2.33 ms per token, 428.57 tokens per second) 0.42.514.686 I slot print_timing: id 0 | task 1083 | eval time = 1056.55 ms / 54 tokens ( 19.93 ms per token, 50.16 tokens per second) 0.42.514.688 I slot print_timing: id 0 | task 1083 | total time = 1887.22 ms / 410 tokens 0.42.514.689 I slot print_timing: id 0 | task 1083 | graphs reused = 1035 0.42.514.689 I slot print_timing: id 0 | task 1083 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.515.003 I slot release: id 0 | task 1083 | stop processing: n_tokens = 409, truncated = 0 0.42.524.621 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 385940720546 0.42.556.267 I slot launch_slot_: id 0 | task 1140 | processing task, is_child = 0 0.44.842.781 I slot print_timing: id 0 | task 1140 | prompt eval time = 913.53 ms / 410 tokens ( 2.23 ms per token, 448.81 tokens per second) 0.44.842.784 I slot print_timing: id 0 | task 1140 | eval time = 1372.96 ms / 70 tokens ( 19.90 ms per token, 50.26 tokens per second) 0.44.842.785 I slot print_timing: id 0 | task 1140 | total time = 2286.49 ms / 480 tokens 0.44.842.786 I slot print_timing: id 0 | task 1140 | graphs reused = 1103 0.44.842.786 I slot print_timing: id 0 | task 1140 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.842.920 I slot release: id 0 | task 1140 | stop processing: n_tokens = 479, truncated = 0 0.44.848.848 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 479, t_last = 385943048464 0.44.879.439 I slot launch_slot_: id 0 | task 1213 | processing task, is_child = 0 0.46.900.788 I slot print_timing: id 0 | task 1213 | prompt eval time = 887.28 ms / 385 tokens ( 2.30 ms per token, 433.91 tokens per second) 0.46.900.795 I slot print_timing: id 0 | task 1213 | eval time = 1134.05 ms / 58 tokens ( 19.90 ms per token, 50.26 tokens per second) 0.46.900.795 I slot print_timing: id 0 | task 1213 | total time = 2021.34 ms / 443 tokens 0.46.900.796 I slot print_timing: id 0 | task 1213 | graphs reused = 1159 0.46.900.796 I slot print_timing: id 0 | task 1213 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.900.862 I slot release: id 0 | task 1213 | stop processing: n_tokens = 442, truncated = 0 0.46.905.953 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 442, t_last = 385945106405 0.46.931.856 I slot launch_slot_: id 0 | task 1274 | processing task, is_child = 0 0.49.217.573 I slot print_timing: id 0 | task 1274 | prompt eval time = 891.54 ms / 395 tokens ( 2.26 ms per token, 443.06 tokens per second) 0.49.217.580 I slot print_timing: id 0 | task 1274 | eval time = 1394.17 ms / 71 tokens ( 19.92 ms per token, 50.21 tokens per second) 0.49.217.581 I slot print_timing: id 0 | task 1274 | total time = 2285.71 ms / 466 tokens 0.49.217.581 I slot print_timing: id 0 | task 1274 | graphs reused = 1228 0.49.217.582 I slot print_timing: id 0 | task 1274 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.217.666 I slot release: id 0 | task 1274 | stop processing: n_tokens = 465, truncated = 0 0.49.222.784 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 465, t_last = 385947423210 0.49.246.328 I slot launch_slot_: id 0 | task 1348 | processing task, is_child = 0 0.51.396.114 I slot print_timing: id 0 | task 1348 | prompt eval time = 937.64 ms / 430 tokens ( 2.18 ms per token, 458.60 tokens per second) 0.51.396.120 I slot print_timing: id 0 | task 1348 | eval time = 1212.13 ms / 62 tokens ( 19.87 ms per token, 50.32 tokens per second) 0.51.396.120 I slot print_timing: id 0 | task 1348 | total time = 2149.77 ms / 492 tokens 0.51.396.121 I slot print_timing: id 0 | task 1348 | graphs reused = 1288 0.51.396.122 I slot print_timing: id 0 | task 1348 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.396.196 I slot release: id 0 | task 1348 | stop processing: n_tokens = 491, truncated = 0 0.51.400.812 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 491, t_last = 385949601740 0.51.427.935 I slot launch_slot_: id 0 | task 1413 | processing task, is_child = 0 0.53.528.904 I slot print_timing: id 0 | task 1413 | prompt eval time = 891.00 ms / 392 tokens ( 2.27 ms per token, 439.95 tokens per second) 0.53.528.907 I slot print_timing: id 0 | task 1413 | eval time = 1209.96 ms / 62 tokens ( 19.84 ms per token, 50.42 tokens per second) 0.53.528.908 I slot print_timing: id 0 | task 1413 | total time = 2100.96 ms / 454 tokens 0.53.528.909 I slot print_timing: id 0 | task 1413 | graphs reused = 1348 0.53.528.909 I slot print_timing: id 0 | task 1413 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.528.978 I slot release: id 0 | task 1413 | stop processing: n_tokens = 453, truncated = 0 0.53.533.659 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 453, t_last = 385951734522 0.53.564.199 I slot launch_slot_: id 0 | task 1478 | processing task, is_child = 0 0.55.355.045 I slot print_timing: id 0 | task 1478 | prompt eval time = 835.60 ms / 350 tokens ( 2.39 ms per token, 418.86 tokens per second) 0.55.355.048 I slot print_timing: id 0 | task 1478 | eval time = 955.23 ms / 49 tokens ( 19.90 ms per token, 50.25 tokens per second) 0.55.355.049 I slot print_timing: id 0 | task 1478 | total time = 1790.83 ms / 399 tokens 0.55.355.049 I slot print_timing: id 0 | task 1478 | graphs reused = 1395 0.55.355.050 I slot print_timing: id 0 | task 1478 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.355.106 I slot release: id 0 | task 1478 | stop processing: n_tokens = 398, truncated = 0 0.55.359.724 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 398, t_last = 385953560649 0.55.391.050 I slot launch_slot_: id 0 | task 1530 | processing task, is_child = 0 0.57.430.192 I slot print_timing: id 0 | task 1530 | prompt eval time = 844.61 ms / 380 tokens ( 2.22 ms per token, 449.91 tokens per second) 0.57.430.198 I slot print_timing: id 0 | task 1530 | eval time = 1194.51 ms / 61 tokens ( 19.91 ms per token, 50.23 tokens per second) 0.57.430.199 I slot print_timing: id 0 | task 1530 | total time = 2039.12 ms / 441 tokens 0.57.430.199 I slot print_timing: id 0 | task 1530 | graphs reused = 1454 0.57.430.200 I slot print_timing: id 0 | task 1530 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.430.273 I slot release: id 0 | task 1530 | stop processing: n_tokens = 440, truncated = 0 0.57.435.063 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 440, t_last = 385955635822 0.57.468.713 I slot launch_slot_: id 0 | task 1594 | processing task, is_child = 0 0.59.972.186 I slot print_timing: id 0 | task 1594 | prompt eval time = 917.31 ms / 410 tokens ( 2.24 ms per token, 446.96 tokens per second) 0.59.972.191 I slot print_timing: id 0 | task 1594 | eval time = 1586.15 ms / 80 tokens ( 20.08 ms per token, 49.81 tokens per second) 0.59.972.199 I slot print_timing: id 0 | task 1594 | total time = 2503.46 ms / 490 tokens 0.59.972.202 I slot print_timing: id 0 | task 1594 | graphs reused = 1532 0.59.972.202 I slot print_timing: id 0 | task 1594 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.972.276 I slot release: id 0 | task 1594 | stop processing: n_tokens = 489, truncated = 0 0.59.977.414 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 489, t_last = 385958177819 1.00.014.113 I slot launch_slot_: id 0 | task 1677 | processing task, is_child = 0 1.02.239.890 I slot print_timing: id 0 | task 1677 | prompt eval time = 896.23 ms / 387 tokens ( 2.32 ms per token, 431.81 tokens per second) 1.02.239.893 I slot print_timing: id 0 | task 1677 | eval time = 1329.54 ms / 68 tokens ( 19.84 ms per token, 50.39 tokens per second) 1.02.239.895 I slot print_timing: id 0 | task 1677 | total time = 2225.76 ms / 455 tokens 1.02.239.895 I slot print_timing: id 0 | task 1677 | graphs reused = 1598 1.02.239.896 I slot print_timing: id 0 | task 1677 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.239.946 I slot release: id 0 | task 1677 | stop processing: n_tokens = 454, truncated = 0 1.02.244.509 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 454, t_last = 385960445489 1.02.318.214 I slot launch_slot_: id 0 | task 1748 | processing task, is_child = 0 1.04.304.084 I slot print_timing: id 0 | task 1748 | prompt eval time = 833.91 ms / 358 tokens ( 2.33 ms per token, 429.30 tokens per second) 1.04.304.087 I slot print_timing: id 0 | task 1748 | eval time = 1151.94 ms / 59 tokens ( 19.86 ms per token, 50.35 tokens per second) 1.04.304.089 I slot print_timing: id 0 | task 1748 | total time = 1985.86 ms / 417 tokens 1.04.304.089 I slot print_timing: id 0 | task 1748 | graphs reused = 1655 1.04.304.090 I slot print_timing: id 0 | task 1748 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.304.139 I slot release: id 0 | task 1748 | stop processing: n_tokens = 416, truncated = 0 1.04.310.356 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 385962509682 1.04.407.977 I slot launch_slot_: id 0 | task 1810 | processing task, is_child = 0 1.06.356.030 I slot print_timing: id 0 | task 1810 | prompt eval time = 838.22 ms / 359 tokens ( 2.33 ms per token, 428.29 tokens per second) 1.06.356.037 I slot print_timing: id 0 | task 1810 | eval time = 1109.82 ms / 56 tokens ( 20.18 ms per token, 49.56 tokens per second) 1.06.356.038 I slot print_timing: id 0 | task 1810 | total time = 1948.04 ms / 415 tokens 1.06.356.038 I slot print_timing: id 0 | task 1810 | graphs reused = 1709 1.06.356.039 I slot print_timing: id 0 | task 1810 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.356.083 I slot release: id 0 | task 1810 | stop processing: n_tokens = 414, truncated = 0 1.06.360.926 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 385964561626 1.06.407.260 I slot launch_slot_: id 0 | task 1869 | processing task, is_child = 0 1.08.482.318 I slot print_timing: id 0 | task 1869 | prompt eval time = 883.19 ms / 387 tokens ( 2.28 ms per token, 438.19 tokens per second) 1.08.482.324 I slot print_timing: id 0 | task 1869 | eval time = 1191.86 ms / 61 tokens ( 19.86 ms per token, 50.34 tokens per second) 1.08.482.325 I slot print_timing: id 0 | task 1869 | total time = 2075.05 ms / 448 tokens 1.08.482.325 I slot print_timing: id 0 | task 1869 | graphs reused = 1768 1.08.482.326 I slot print_timing: id 0 | task 1869 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.482.387 I slot release: id 0 | task 1869 | stop processing: n_tokens = 447, truncated = 0 1.08.487.020 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 385966687930 1.08.565.152 I slot launch_slot_: id 0 | task 1933 | processing task, is_child = 0 1.10.676.451 I slot print_timing: id 0 | task 1933 | prompt eval time = 902.15 ms / 410 tokens ( 2.20 ms per token, 454.47 tokens per second) 1.10.676.457 I slot print_timing: id 0 | task 1933 | eval time = 1209.12 ms / 61 tokens ( 20.15 ms per token, 49.62 tokens per second) 1.10.676.458 I slot print_timing: id 0 | task 1933 | total time = 2111.28 ms / 471 tokens 1.10.676.458 I slot print_timing: id 0 | task 1933 | graphs reused = 1827 1.10.676.459 I slot print_timing: id 0 | task 1933 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.676.516 I slot release: id 0 | task 1933 | stop processing: n_tokens = 470, truncated = 0 1.10.681.167 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 385968882059 1.10.730.455 I slot launch_slot_: id 0 | task 1997 | processing task, is_child = 0 1.12.528.029 I slot print_timing: id 0 | task 1997 | prompt eval time = 824.80 ms / 351 tokens ( 2.35 ms per token, 425.56 tokens per second) 1.12.528.032 I slot print_timing: id 0 | task 1997 | eval time = 972.75 ms / 50 tokens ( 19.85 ms per token, 50.37 tokens per second) 1.12.528.033 I slot print_timing: id 0 | task 1997 | total time = 1797.55 ms / 401 tokens 1.12.528.034 I slot print_timing: id 0 | task 1997 | graphs reused = 1875 1.12.528.035 I slot print_timing: id 0 | task 1997 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.528.086 I slot release: id 0 | task 1997 | stop processing: n_tokens = 400, truncated = 0 1.12.533.216 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 385970733629 1.12.577.225 I slot launch_slot_: id 0 | task 2050 | processing task, is_child = 0 1.14.541.238 I slot print_timing: id 0 | task 2050 | prompt eval time = 871.72 ms / 393 tokens ( 2.22 ms per token, 450.83 tokens per second) 1.14.541.242 I slot print_timing: id 0 | task 2050 | eval time = 1092.28 ms / 56 tokens ( 19.86 ms per token, 50.35 tokens per second) 1.14.541.243 I slot print_timing: id 0 | task 2050 | total time = 1964.00 ms / 449 tokens 1.14.541.243 I slot print_timing: id 0 | task 2050 | graphs reused = 1929 1.14.541.244 I slot print_timing: id 0 | task 2050 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.541.298 I slot release: id 0 | task 2050 | stop processing: n_tokens = 448, truncated = 0 1.14.545.548 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 385972746841 1.14.619.390 I slot launch_slot_: id 0 | task 2109 | processing task, is_child = 0 1.15.972.387 I slot print_timing: id 0 | task 2109 | prompt eval time = 774.19 ms / 321 tokens ( 2.41 ms per token, 414.62 tokens per second) 1.15.972.394 I slot print_timing: id 0 | task 2109 | eval time = 578.79 ms / 30 tokens ( 19.96 ms per token, 50.10 tokens per second) 1.15.972.400 I slot print_timing: id 0 | task 2109 | total time = 1352.99 ms / 351 tokens 1.15.972.401 I slot print_timing: id 0 | task 2109 | graphs reused = 1957 1.15.972.402 I slot print_timing: id 0 | task 2109 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.972.441 I slot release: id 0 | task 2109 | stop processing: n_tokens = 350, truncated = 0 1.15.976.924 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 350, t_last = 385974177984 1.16.051.899 I slot launch_slot_: id 0 | task 2142 | processing task, is_child = 0 1.17.748.746 I slot print_timing: id 0 | task 2142 | prompt eval time = 801.56 ms / 330 tokens ( 2.43 ms per token, 411.70 tokens per second) 1.17.748.749 I slot print_timing: id 0 | task 2142 | eval time = 895.27 ms / 46 tokens ( 19.89 ms per token, 50.26 tokens per second) 1.17.748.749 I slot print_timing: id 0 | task 2142 | total time = 1696.83 ms / 376 tokens 1.17.748.750 I slot print_timing: id 0 | task 2142 | graphs reused = 2001 1.17.748.750 I slot print_timing: id 0 | task 2142 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.748.796 I slot release: id 0 | task 2142 | stop processing: n_tokens = 375, truncated = 0 1.17.753.392 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 375, t_last = 385975954339 1.17.808.367 I slot launch_slot_: id 0 | task 2191 | processing task, is_child = 0 1.19.483.226 I slot print_timing: id 0 | task 2191 | prompt eval time = 800.59 ms / 341 tokens ( 2.35 ms per token, 425.94 tokens per second) 1.19.483.229 I slot print_timing: id 0 | task 2191 | eval time = 874.25 ms / 45 tokens ( 19.87 ms per token, 50.33 tokens per second) 1.19.483.230 I slot print_timing: id 0 | task 2191 | total time = 1674.84 ms / 386 tokens 1.19.483.242 I slot print_timing: id 0 | task 2191 | graphs reused = 2044 1.19.483.244 I slot print_timing: id 0 | task 2191 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.483.281 I slot release: id 0 | task 2191 | stop processing: n_tokens = 385, truncated = 0 1.19.487.722 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 385, t_last = 385977688824 1.19.534.834 I slot launch_slot_: id 0 | task 2239 | processing task, is_child = 0 1.21.687.527 I slot print_timing: id 0 | task 2239 | prompt eval time = 1219.17 ms / 338 tokens ( 3.61 ms per token, 277.24 tokens per second) 1.21.687.530 I slot print_timing: id 0 | task 2239 | eval time = 933.50 ms / 48 tokens ( 19.86 ms per token, 50.35 tokens per second) 1.21.687.531 I slot print_timing: id 0 | task 2239 | total time = 2152.67 ms / 386 tokens 1.21.687.532 I slot print_timing: id 0 | task 2239 | graphs reused = 2090 1.21.687.532 I slot print_timing: id 0 | task 2239 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.687.573 I slot release: id 0 | task 2239 | stop processing: n_tokens = 385, truncated = 0 1.21.693.181 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 385, t_last = 385979893116 1.21.740.861 I slot launch_slot_: id 0 | task 2290 | processing task, is_child = 0 1.23.734.649 I slot print_timing: id 0 | task 2290 | prompt eval time = 898.71 ms / 395 tokens ( 2.28 ms per token, 439.52 tokens per second) 1.23.734.653 I slot print_timing: id 0 | task 2290 | eval time = 1095.07 ms / 56 tokens ( 19.91 ms per token, 50.23 tokens per second) 1.23.734.654 I slot print_timing: id 0 | task 2290 | total time = 1993.78 ms / 451 tokens 1.23.734.655 I slot print_timing: id 0 | task 2290 | graphs reused = 2144 1.23.734.655 I slot print_timing: id 0 | task 2290 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.734.697 I slot release: id 0 | task 2290 | stop processing: n_tokens = 450, truncated = 0 1.23.739.800 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 450, t_last = 385981940240 1.23.781.307 I slot launch_slot_: id 0 | task 2349 | processing task, is_child = 0 1.26.564.257 I slot print_timing: id 0 | task 2349 | prompt eval time = 1150.18 ms / 528 tokens ( 2.18 ms per token, 459.06 tokens per second) 1.26.564.263 I slot print_timing: id 0 | task 2349 | eval time = 1632.74 ms / 83 tokens ( 19.91 ms per token, 50.22 tokens per second) 1.26.564.264 I slot print_timing: id 0 | task 2349 | total time = 2782.92 ms / 611 tokens 1.26.564.265 I slot print_timing: id 0 | task 2349 | graphs reused = 2225 1.26.564.265 I slot print_timing: id 0 | task 2349 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.564.366 I slot release: id 0 | task 2349 | stop processing: n_tokens = 610, truncated = 0 1.26.570.213 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 610, t_last = 385984769910 1.26.570.272 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.418 MiB) 1.26.640.271 I slot launch_slot_: id 0 | task 2436 | processing task, is_child = 0 1.28.315.330 I slot print_timing: id 0 | task 2436 | prompt eval time = 798.38 ms / 331 tokens ( 2.41 ms per token, 414.59 tokens per second) 1.28.315.333 I slot print_timing: id 0 | task 2436 | eval time = 876.67 ms / 45 tokens ( 19.92 ms per token, 50.19 tokens per second) 1.28.315.334 I slot print_timing: id 0 | task 2436 | total time = 1675.04 ms / 376 tokens 1.28.315.334 I slot print_timing: id 0 | task 2436 | graphs reused = 2268 1.28.315.335 I slot print_timing: id 0 | task 2436 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.315.377 I slot release: id 0 | task 2436 | stop processing: n_tokens = 387, truncated = 0 1.28.320.111 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 387, t_last = 385986520920 1.28.320.147 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 195.538 MiB) 1.28.320.163 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.379 MiB) 1.28.410.049 I slot launch_slot_: id 0 | task 2484 | processing task, is_child = 0 1.30.278.892 I slot print_timing: id 0 | task 2484 | prompt eval time = 834.97 ms / 362 tokens ( 2.31 ms per token, 433.55 tokens per second) 1.30.278.898 I slot print_timing: id 0 | task 2484 | eval time = 1033.86 ms / 53 tokens ( 19.88 ms per token, 50.30 tokens per second) 1.30.278.899 I slot print_timing: id 0 | task 2484 | total time = 1868.83 ms / 415 tokens 1.30.278.900 I slot print_timing: id 0 | task 2484 | graphs reused = 2319 1.30.278.900 I slot print_timing: id 0 | task 2484 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.278.963 I slot release: id 0 | task 2484 | stop processing: n_tokens = 426, truncated = 0 1.30.283.939 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 385988484506 1.30.283.979 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 197.024 MiB) 1.30.637.905 I slot launch_slot_: id 0 | task 2540 | processing task, is_child = 0 1.32.927.371 I slot print_timing: id 0 | task 2540 | prompt eval time = 934.64 ms / 419 tokens ( 2.23 ms per token, 448.30 tokens per second) 1.32.927.376 I slot print_timing: id 0 | task 2540 | eval time = 1354.81 ms / 69 tokens ( 19.92 ms per token, 50.19 tokens per second) 1.32.927.377 I slot print_timing: id 0 | task 2540 | total time = 2289.45 ms / 488 tokens 1.32.927.377 I slot print_timing: id 0 | task 2540 | graphs reused = 2386 1.32.927.378 I slot print_timing: id 0 | task 2540 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.927.444 I slot release: id 0 | task 2540 | stop processing: n_tokens = 499, truncated = 0 1.32.932.634 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 499, t_last = 385991132987 1.32.932.670 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.985 MiB) 1.33.309.291 I slot launch_slot_: id 0 | task 2612 | processing task, is_child = 0 1.35.106.989 I slot print_timing: id 0 | task 2612 | prompt eval time = 942.75 ms / 423 tokens ( 2.23 ms per token, 448.69 tokens per second) 1.35.106.995 I slot print_timing: id 0 | task 2612 | eval time = 854.93 ms / 44 tokens ( 19.88 ms per token, 50.30 tokens per second) 1.35.106.996 I slot print_timing: id 0 | task 2612 | total time = 1797.68 ms / 467 tokens 1.35.106.997 I slot print_timing: id 0 | task 2612 | graphs reused = 2428 1.35.106.997 I slot print_timing: id 0 | task 2612 | graph reallocs = 0 / 0 (same size) / (changed size) 1.35.107.086 I slot release: id 0 | task 2612 | stop processing: n_tokens = 478, truncated = 0 1.35.111.465 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 478, t_last = 385993312630 1.35.111.499 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.770 MiB) 1.35.111.513 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 197.748 MiB) 1.35.683.449 I slot launch_slot_: id 0 | task 2659 | processing task, is_child = 0 1.37.315.481 I slot print_timing: id 0 | task 2659 | prompt eval time = 796.06 ms / 341 tokens ( 2.33 ms per token, 428.36 tokens per second) 1.37.315.487 I slot print_timing: id 0 | task 2659 | eval time = 835.95 ms / 43 tokens ( 19.90 ms per token, 50.24 tokens per second) 1.37.315.488 I slot print_timing: id 0 | task 2659 | total time = 1632.02 ms / 384 tokens 1.37.315.488 I slot print_timing: id 0 | task 2659 | graphs reused = 2469 1.37.315.489 I slot print_timing: id 0 | task 2659 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.315.524 I slot release: id 0 | task 2659 | stop processing: n_tokens = 395, truncated = 0 1.37.320.014 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 395, t_last = 385995521067 1.37.320.052 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 199.019 MiB) 1.37.811.091 I slot launch_slot_: id 0 | task 2705 | processing task, is_child = 0 1.39.575.467 I slot print_timing: id 0 | task 2705 | prompt eval time = 849.63 ms / 356 tokens ( 2.39 ms per token, 419.01 tokens per second) 1.39.575.470 I slot print_timing: id 0 | task 2705 | eval time = 914.73 ms / 47 tokens ( 19.89 ms per token, 50.29 tokens per second) 1.39.575.471 I slot print_timing: id 0 | task 2705 | total time = 1764.36 ms / 403 tokens 1.39.575.471 I slot print_timing: id 0 | task 2705 | graphs reused = 2514 1.39.575.472 I slot print_timing: id 0 | task 2705 | graph reallocs = 0 / 0 (same size) / (changed size) 1.39.575.511 I slot release: id 0 | task 2705 | stop processing: n_tokens = 414, truncated = 0 1.39.580.053 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 385997781055 1.39.580.085 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.086 MiB) 1.39.972.699 I slot launch_slot_: id 0 | task 2755 | processing task, is_child = 0 1.41.714.040 I slot print_timing: id 0 | task 2755 | prompt eval time = 842.53 ms / 362 tokens ( 2.33 ms per token, 429.66 tokens per second) 1.41.714.043 I slot print_timing: id 0 | task 2755 | eval time = 898.79 ms / 46 tokens ( 19.97 ms per token, 50.07 tokens per second) 1.41.714.044 I slot print_timing: id 0 | task 2755 | total time = 1741.32 ms / 408 tokens 1.41.714.045 I slot print_timing: id 0 | task 2755 | graphs reused = 2558 1.41.714.046 I slot print_timing: id 0 | task 2755 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.714.093 I slot release: id 0 | task 2755 | stop processing: n_tokens = 419, truncated = 0 1.41.718.938 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 385999919636 1.41.718.969 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.340 MiB) 1.42.106.265 I slot launch_slot_: id 0 | task 2804 | processing task, is_child = 0 1.44.363.054 I slot print_timing: id 0 | task 2804 | prompt eval time = 920.44 ms / 391 tokens ( 2.35 ms per token, 424.80 tokens per second) 1.44.363.058 I slot print_timing: id 0 | task 2804 | eval time = 1336.34 ms / 68 tokens ( 19.95 ms per token, 50.14 tokens per second) 1.44.363.059 I slot print_timing: id 0 | task 2804 | total time = 2256.77 ms / 459 tokens 1.44.363.059 I slot print_timing: id 0 | task 2804 | graphs reused = 2624 1.44.363.060 I slot print_timing: id 0 | task 2804 | graph reallocs = 0 / 0 (same size) / (changed size) 1.44.363.127 I slot release: id 0 | task 2804 | stop processing: n_tokens = 470, truncated = 0 1.44.367.671 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 386002568671 1.44.367.712 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.985 MiB) 1.44.367.729 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 197.396 MiB) 1.44.983.976 I slot launch_slot_: id 0 | task 2875 | processing task, is_child = 0 1.46.920.201 I slot print_timing: id 0 | task 2875 | prompt eval time = 834.50 ms / 343 tokens ( 2.43 ms per token, 411.02 tokens per second) 1.46.920.207 I slot print_timing: id 0 | task 2875 | eval time = 1101.71 ms / 55 tokens ( 20.40 ms per token, 49.01 tokens per second) 1.46.920.208 I slot print_timing: id 0 | task 2875 | total time = 1936.21 ms / 398 tokens 1.46.920.208 I slot print_timing: id 0 | task 2875 | graphs reused = 2677 1.46.920.209 I slot print_timing: id 0 | task 2875 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.920.238 I slot release: id 0 | task 2875 | stop processing: n_tokens = 409, truncated = 0 1.46.930.630 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 386005125781 1.46.930.660 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.985 MiB) 1.47.583.565 I slot launch_slot_: id 0 | task 2933 | processing task, is_child = 0 1.49.393.608 I slot print_timing: id 0 | task 2933 | prompt eval time = 912.99 ms / 401 tokens ( 2.28 ms per token, 439.22 tokens per second) 1.49.393.612 I slot print_timing: id 0 | task 2933 | eval time = 897.04 ms / 46 tokens ( 19.93 ms per token, 50.17 tokens per second) 1.49.393.612 I slot print_timing: id 0 | task 2933 | total time = 1810.02 ms / 447 tokens 1.49.393.613 I slot print_timing: id 0 | task 2933 | graphs reused = 2721 1.49.393.614 I slot print_timing: id 0 | task 2933 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.394.899 I slot release: id 0 | task 2933 | stop processing: n_tokens = 458, truncated = 0 1.49.401.139 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 386007600443 1.49.401.173 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.829 MiB) 1.49.814.372 I slot launch_slot_: id 0 | task 2982 | processing task, is_child = 0 1.51.977.979 I slot print_timing: id 0 | task 2982 | prompt eval time = 829.94 ms / 355 tokens ( 2.34 ms per token, 427.74 tokens per second) 1.51.977.982 I slot print_timing: id 0 | task 2982 | eval time = 1333.65 ms / 68 tokens ( 19.91 ms per token, 50.24 tokens per second) 1.51.977.982 I slot print_timing: id 0 | task 2982 | total time = 2163.59 ms / 423 tokens 1.51.977.983 I slot print_timing: id 0 | task 2982 | graphs reused = 2787 1.51.977.984 I slot print_timing: id 0 | task 2982 | graph reallocs = 0 / 0 (same size) / (changed size) 1.51.978.030 I slot release: id 0 | task 2982 | stop processing: n_tokens = 434, truncated = 0 1.51.984.027 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 434, t_last = 386010183573 1.51.984.073 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.731 MiB) 1.51.984.090 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.203 MiB) 1.52.545.247 I slot launch_slot_: id 0 | task 3053 | processing task, is_child = 0 1.54.528.221 I slot print_timing: id 0 | task 3053 | prompt eval time = 847.23 ms / 351 tokens ( 2.41 ms per token, 414.29 tokens per second) 1.54.528.226 I slot print_timing: id 0 | task 3053 | eval time = 1135.72 ms / 57 tokens ( 20.28 ms per token, 49.31 tokens per second) 1.54.528.227 I slot print_timing: id 0 | task 3053 | total time = 1982.96 ms / 408 tokens 1.54.528.227 I slot print_timing: id 0 | task 3053 | graphs reused = 2842 1.54.528.228 I slot print_timing: id 0 | task 3053 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.529.564 I slot release: id 0 | task 3053 | stop processing: n_tokens = 419, truncated = 0 1.54.537.283 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 386012735108 1.54.537.313 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.692 MiB) 1.55.117.761 I slot launch_slot_: id 0 | task 3113 | processing task, is_child = 0 1.57.961.924 I slot print_timing: id 0 | task 3113 | prompt eval time = 1004.70 ms / 475 tokens ( 2.12 ms per token, 472.78 tokens per second) 1.57.961.930 I slot print_timing: id 0 | task 3113 | eval time = 1839.45 ms / 93 tokens ( 19.99 ms per token, 50.01 tokens per second) 1.57.961.931 I slot print_timing: id 0 | task 3113 | total time = 2844.15 ms / 568 tokens 1.57.961.932 I slot print_timing: id 0 | task 3113 | graphs reused = 2932 1.57.961.932 I slot print_timing: id 0 | task 3113 | graph reallocs = 0 / 0 (same size) / (changed size) 1.57.961.997 I slot release: id 0 | task 3113 | stop processing: n_tokens = 579, truncated = 0 1.57.974.200 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 579, t_last = 386016167541 1.57.974.238 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.105 MiB) 1.58.402.942 I slot launch_slot_: id 0 | task 3209 | processing task, is_child = 0 2.01.185.180 I slot print_timing: id 0 | task 3209 | prompt eval time = 965.72 ms / 440 tokens ( 2.19 ms per token, 455.62 tokens per second) 2.01.185.187 I slot print_timing: id 0 | task 3209 | eval time = 1816.50 ms / 92 tokens ( 19.96 ms per token, 50.10 tokens per second) 2.01.185.188 I slot print_timing: id 0 | task 3209 | total time = 2782.22 ms / 532 tokens 2.01.185.188 I slot print_timing: id 0 | task 3209 | graphs reused = 3021 2.01.185.191 I slot print_timing: id 0 | task 3209 | graph reallocs = 0 / 0 (same size) / (changed size) 2.01.186.516 I slot release: id 0 | task 3209 | stop processing: n_tokens = 543, truncated = 0 2.01.191.973 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 543, t_last = 386019392060 2.01.192.009 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.027 MiB) 2.01.192.342 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 197.161 MiB) 2.01.860.562 I slot launch_slot_: id 0 | task 3304 | processing task, is_child = 0 2.03.750.064 I slot print_timing: id 0 | task 3304 | prompt eval time = 814.25 ms / 345 tokens ( 2.36 ms per token, 423.70 tokens per second) 2.03.750.068 I slot print_timing: id 0 | task 3304 | eval time = 1075.23 ms / 55 tokens ( 19.91 ms per token, 50.22 tokens per second) 2.03.750.068 I slot print_timing: id 0 | task 3304 | total time = 1889.48 ms / 400 tokens 2.03.750.069 I slot print_timing: id 0 | task 3304 | graphs reused = 3074 2.03.750.070 I slot print_timing: id 0 | task 3304 | graph reallocs = 0 / 0 (same size) / (changed size) 2.03.750.110 I slot release: id 0 | task 3304 | stop processing: n_tokens = 411, truncated = 0 2.03.759.366 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 386021955653 2.03.759.397 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.438 MiB) 2.04.360.742 I slot launch_slot_: id 0 | task 3362 | processing task, is_child = 0 2.06.339.734 I slot print_timing: id 0 | task 3362 | prompt eval time = 904.49 ms / 382 tokens ( 2.37 ms per token, 422.34 tokens per second) 2.06.339.746 I slot print_timing: id 0 | task 3362 | eval time = 1074.49 ms / 55 tokens ( 19.90 ms per token, 50.26 tokens per second) 2.06.339.749 I slot print_timing: id 0 | task 3362 | total time = 1978.98 ms / 437 tokens 2.06.339.749 I slot print_timing: id 0 | task 3362 | graphs reused = 3127 2.06.339.752 I slot print_timing: id 0 | task 3362 | graph reallocs = 0 / 0 (same size) / (changed size) 2.06.340.822 I slot release: id 0 | task 3362 | stop processing: n_tokens = 448, truncated = 0 2.06.346.623 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 386024546367 2.06.346.661 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 197.806 MiB) 2.06.902.487 I slot launch_slot_: id 0 | task 3420 | processing task, is_child = 0 2.08.586.254 I slot print_timing: id 0 | task 3420 | prompt eval time = 809.19 ms / 337 tokens ( 2.40 ms per token, 416.47 tokens per second) 2.08.586.260 I slot print_timing: id 0 | task 3420 | eval time = 874.56 ms / 45 tokens ( 19.88 ms per token, 50.31 tokens per second) 2.08.586.261 I slot print_timing: id 0 | task 3420 | total time = 1683.75 ms / 382 tokens 2.08.586.262 I slot print_timing: id 0 | task 3420 | graphs reused = 3170 2.08.586.262 I slot print_timing: id 0 | task 3420 | graph reallocs = 0 / 0 (same size) / (changed size) 2.08.587.584 I slot release: id 0 | task 3420 | stop processing: n_tokens = 393, truncated = 0 2.08.594.153 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 386026793128 2.08.594.185 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 197.083 MiB) 2.08.594.201 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 197.533 MiB) 2.09.127.637 I slot launch_slot_: id 0 | task 3468 | processing task, is_child = 0 2.11.413.034 I slot print_timing: id 0 | task 3468 | prompt eval time = 892.45 ms / 402 tokens ( 2.22 ms per token, 450.45 tokens per second) 2.11.413.040 I slot print_timing: id 0 | task 3468 | eval time = 1392.94 ms / 70 tokens ( 20.19 ms per token, 49.54 tokens per second) 2.11.413.041 I slot print_timing: id 0 | task 3468 | total time = 2285.38 ms / 472 tokens 2.11.413.042 I slot print_timing: id 0 | task 3468 | graphs reused = 3238 2.11.413.042 I slot print_timing: id 0 | task 3468 | graph reallocs = 0 / 0 (same size) / (changed size) 2.11.413.097 I slot release: id 0 | task 3468 | stop processing: n_tokens = 483, truncated = 0 2.11.422.692 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 483, t_last = 386029618640 2.11.422.733 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 198.041 MiB) 2.11.957.187 I slot launch_slot_: id 0 | task 3541 | processing task, is_child = 0 2.14.330.137 I slot print_timing: id 0 | task 3541 | prompt eval time = 1254.08 ms / 549 tokens ( 2.28 ms per token, 437.77 tokens per second) 2.14.330.144 I slot print_timing: id 0 | task 3541 | eval time = 1118.85 ms / 57 tokens ( 19.98 ms per token, 50.05 tokens per second) 2.14.330.145 I slot print_timing: id 0 | task 3541 | total time = 2372.93 ms / 606 tokens 2.14.330.146 I slot print_timing: id 0 | task 3541 | graphs reused = 3293 2.14.330.146 I slot print_timing: id 0 | task 3541 | graph reallocs = 0 / 0 (same size) / (changed size) 2.14.330.361 I slot release: id 0 | task 3541 | stop processing: n_tokens = 617, truncated = 0 2.14.340.790 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 617, t_last = 386032535905 2.14.340.839 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 197.298 MiB) 2.14.340.857 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.222 MiB) 2.15.101.903 I slot launch_slot_: id 0 | task 3602 | processing task, is_child = 0 2.17.655.587 I slot print_timing: id 0 | task 3602 | prompt eval time = 1414.95 ms / 616 tokens ( 2.30 ms per token, 435.35 tokens per second) 2.17.655.589 I slot print_timing: id 0 | task 3602 | eval time = 1138.71 ms / 58 tokens ( 19.98 ms per token, 50.06 tokens per second) 2.17.655.590 I slot print_timing: id 0 | task 3602 | total time = 2553.66 ms / 674 tokens 2.17.655.590 I slot print_timing: id 0 | task 3602 | graphs reused = 3349 2.17.655.591 I slot print_timing: id 0 | task 3602 | graph reallocs = 0 / 0 (same size) / (changed size) 2.17.656.634 I slot release: id 0 | task 3602 | stop processing: n_tokens = 685, truncated = 0 2.17.669.539 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 685, t_last = 386035862178 2.17.669.583 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 197.044 MiB) 2.18.094.946 I slot launch_slot_: id 0 | task 3664 | processing task, is_child = 0 2.20.750.197 I slot print_timing: id 0 | task 3664 | prompt eval time = 1456.19 ms / 665 tokens ( 2.19 ms per token, 456.67 tokens per second) 2.20.750.203 I slot print_timing: id 0 | task 3664 | eval time = 1199.05 ms / 61 tokens ( 19.98 ms per token, 50.04 tokens per second) 2.20.750.204 I slot print_timing: id 0 | task 3664 | total time = 2655.24 ms / 726 tokens 2.20.750.204 I slot print_timing: id 0 | task 3664 | graphs reused = 3408 2.20.750.205 I slot print_timing: id 0 | task 3664 | graph reallocs = 0 / 0 (same size) / (changed size) 2.20.751.822 I slot release: id 0 | task 3664 | stop processing: n_tokens = 737, truncated = 0 2.20.759.655 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 737, t_last = 386038957366 2.20.759.702 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 198.002 MiB) 2.20.759.714 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 197.317 MiB) 2.21.616.790 I slot launch_slot_: id 0 | task 3729 | processing task, is_child = 0 2.24.140.799 I slot print_timing: id 0 | task 3729 | prompt eval time = 1442.03 ms / 645 tokens ( 2.24 ms per token, 447.29 tokens per second) 2.24.140.802 I slot print_timing: id 0 | task 3729 | eval time = 1081.96 ms / 55 tokens ( 20.04 ms per token, 49.91 tokens per second) 2.24.140.804 I slot print_timing: id 0 | task 3729 | total time = 2523.99 ms / 700 tokens 2.24.140.804 I slot print_timing: id 0 | task 3729 | graphs reused = 3461 2.24.140.805 I slot print_timing: id 0 | task 3729 | graph reallocs = 0 / 0 (same size) / (changed size) 2.24.141.270 I slot release: id 0 | task 3729 | stop processing: n_tokens = 711, truncated = 0 2.24.147.955 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 711, t_last = 386042346814 2.24.147.999 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.574 MiB) 2.24.148.013 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.535 MiB) 2.24.971.465 I slot launch_slot_: id 0 | task 3788 | processing task, is_child = 0 2.27.007.098 I slot print_timing: id 0 | task 3788 | prompt eval time = 1012.36 ms / 474 tokens ( 2.14 ms per token, 468.21 tokens per second) 2.27.007.104 I slot print_timing: id 0 | task 3788 | eval time = 1023.26 ms / 52 tokens ( 20.06 ms per token, 49.84 tokens per second) 2.27.008.381 I slot print_timing: id 0 | task 3788 | total time = 2035.62 ms / 526 tokens 2.27.008.385 I slot print_timing: id 0 | task 3788 | graphs reused = 3510 2.27.008.386 I slot print_timing: id 0 | task 3788 | graph reallocs = 0 / 0 (same size) / (changed size) 2.27.008.832 I slot release: id 0 | task 3788 | stop processing: n_tokens = 537, truncated = 0 2.27.016.464 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 537, t_last = 386045214376 2.27.016.500 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 197.181 MiB) 2.27.617.406 I slot launch_slot_: id 0 | task 3843 | processing task, is_child = 0 2.29.820.567 I slot print_timing: id 0 | task 3843 | prompt eval time = 1383.05 ms / 617 tokens ( 2.24 ms per token, 446.12 tokens per second) 2.29.820.573 I slot print_timing: id 0 | task 3843 | eval time = 820.10 ms / 42 tokens ( 20.00 ms per token, 49.99 tokens per second) 2.29.820.573 I slot print_timing: id 0 | task 3843 | total time = 2203.15 ms / 659 tokens 2.29.820.574 I slot print_timing: id 0 | task 3843 | graphs reused = 3550 2.29.820.575 I slot print_timing: id 0 | task 3843 | graph reallocs = 0 / 0 (same size) / (changed size) 2.29.820.678 I slot release: id 0 | task 3843 | stop processing: n_tokens = 670, truncated = 0 2.29.832.251 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 670, t_last = 386048026222 2.29.832.292 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 197.630 MiB) 2.29.832.304 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.262 MiB) 2.30.705.463 I slot launch_slot_: id 0 | task 3889 | processing task, is_child = 0 2.33.044.540 I slot print_timing: id 0 | task 3889 | prompt eval time = 1398.74 ms / 601 tokens ( 2.33 ms per token, 429.67 tokens per second) 2.33.044.547 I slot print_timing: id 0 | task 3889 | eval time = 940.32 ms / 48 tokens ( 20.01 ms per token, 49.98 tokens per second) 2.33.044.548 I slot print_timing: id 0 | task 3889 | total time = 2339.06 ms / 649 tokens 2.33.044.549 I slot print_timing: id 0 | task 3889 | graphs reused = 3596 2.33.044.549 I slot print_timing: id 0 | task 3889 | graph reallocs = 0 / 0 (same size) / (changed size) 2.33.044.620 I slot release: id 0 | task 3889 | stop processing: n_tokens = 660, truncated = 0 2.33.051.436 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 660, t_last = 386051250165 2.33.051.480 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 197.200 MiB) 2.33.573.590 I slot launch_slot_: id 0 | task 3941 | processing task, is_child = 0 2.35.680.639 I slot print_timing: id 0 | task 3941 | prompt eval time = 1186.44 ms / 533 tokens ( 2.23 ms per token, 449.24 tokens per second) 2.35.680.645 I slot print_timing: id 0 | task 3941 | eval time = 920.60 ms / 47 tokens ( 20.01 ms per token, 49.97 tokens per second) 2.35.680.646 I slot print_timing: id 0 | task 3941 | total time = 2107.03 ms / 580 tokens 2.35.680.646 I slot print_timing: id 0 | task 3941 | graphs reused = 3641 2.35.680.647 I slot print_timing: id 0 | task 3941 | graph reallocs = 0 / 0 (same size) / (changed size) 2.35.680.702 I slot release: id 0 | task 3941 | stop processing: n_tokens = 591, truncated = 0 2.35.687.461 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 591, t_last = 386053886245 2.35.687.498 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 195.284 MiB) 2.35.687.510 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 195.773 MiB) 2.36.454.972 I slot launch_slot_: id 0 | task 3992 | processing task, is_child = 0 2.38.498.564 I slot print_timing: id 0 | task 3992 | prompt eval time = 1019.93 ms / 480 tokens ( 2.12 ms per token, 470.62 tokens per second) 2.38.498.567 I slot print_timing: id 0 | task 3992 | eval time = 1023.64 ms / 52 tokens ( 20.07 ms per token, 49.82 tokens per second) 2.38.498.567 I slot print_timing: id 0 | task 3992 | total time = 2043.57 ms / 532 tokens 2.38.498.568 I slot print_timing: id 0 | task 3992 | graphs reused = 3690 2.38.498.569 I slot print_timing: id 0 | task 3992 | graph reallocs = 0 / 0 (same size) / (changed size) 2.38.498.621 I slot release: id 0 | task 3992 | stop processing: n_tokens = 560, truncated = 0 2.38.506.435 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 386056704164 2.38.506.475 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 195.968 MiB) 2.38.506.494 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 195.968 MiB) 2.39.359.851 I slot launch_slot_: id 0 | task 4047 | processing task, is_child = 0 2.41.433.905 I slot print_timing: id 0 | task 4047 | prompt eval time = 1255.23 ms / 567 tokens ( 2.21 ms per token, 451.71 tokens per second) 2.41.433.910 I slot print_timing: id 0 | task 4047 | eval time = 818.81 ms / 42 tokens ( 19.97 ms per token, 50.07 tokens per second) 2.41.433.911 I slot print_timing: id 0 | task 4047 | total time = 2074.04 ms / 609 tokens 2.41.433.911 I slot print_timing: id 0 | task 4047 | graphs reused = 3730 2.41.433.912 I slot print_timing: id 0 | task 4047 | graph reallocs = 0 / 0 (same size) / (changed size) 2.41.435.267 I slot release: id 0 | task 4047 | stop processing: n_tokens = 637, truncated = 0 2.41.442.088 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 386059640811 2.41.442.127 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 197.239 MiB) 2.41.442.148 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 263.181 MiB) 2.42.247.896 I slot launch_slot_: id 0 | task 4093 | processing task, is_child = 0 2.44.523.925 I slot print_timing: id 0 | task 4093 | prompt eval time = 1033.25 ms / 506 tokens ( 2.04 ms per token, 489.72 tokens per second) 2.44.523.928 I slot print_timing: id 0 | task 4093 | eval time = 1242.76 ms / 63 tokens ( 20.04 ms per token, 49.89 tokens per second) 2.44.523.929 I slot print_timing: id 0 | task 4093 | total time = 2276.00 ms / 569 tokens 2.44.523.930 I slot print_timing: id 0 | task 4093 | graphs reused = 3791 2.44.523.930 I slot print_timing: id 0 | task 4093 | graph reallocs = 0 / 0 (same size) / (changed size) 2.44.524.006 I slot release: id 0 | task 4093 | stop processing: n_tokens = 597, truncated = 0 2.44.530.588 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 597, t_last = 386062729550 2.44.530.641 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 258.821 MiB) 2.45.169.263 I slot launch_slot_: id 0 | task 4159 | processing task, is_child = 0 2.46.884.935 I slot print_timing: id 0 | task 4159 | prompt eval time = 932.45 ms / 436 tokens ( 2.14 ms per token, 467.59 tokens per second) 2.46.884.938 I slot print_timing: id 0 | task 4159 | eval time = 783.21 ms / 40 tokens ( 20.08 ms per token, 49.80 tokens per second) 2.46.884.940 I slot print_timing: id 0 | task 4159 | total time = 1715.65 ms / 476 tokens 2.46.884.940 I slot print_timing: id 0 | task 4159 | graphs reused = 3829 2.46.884.941 I slot print_timing: id 0 | task 4159 | graph reallocs = 0 / 0 (same size) / (changed size) 2.46.884.999 I slot release: id 0 | task 4159 | stop processing: n_tokens = 504, truncated = 0 2.46.894.843 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 386065090543 2.46.894.881 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 259.583 MiB) 2.47.707.756 I slot launch_slot_: id 0 | task 4202 | processing task, is_child = 0 2.50.046.764 I slot print_timing: id 0 | task 4202 | prompt eval time = 1118.40 ms / 519 tokens ( 2.15 ms per token, 464.06 tokens per second) 2.50.046.767 I slot print_timing: id 0 | task 4202 | eval time = 1220.59 ms / 62 tokens ( 20.01 ms per token, 49.98 tokens per second) 2.50.046.768 I slot print_timing: id 0 | task 4202 | total time = 2338.99 ms / 581 tokens 2.50.046.769 I slot print_timing: id 0 | task 4202 | graphs reused = 3889 2.50.046.769 I slot print_timing: id 0 | task 4202 | graph reallocs = 0 / 0 (same size) / (changed size) 2.50.047.891 I slot release: id 0 | task 4202 | stop processing: n_tokens = 609, truncated = 0 2.50.055.346 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 609, t_last = 386068253435 2.50.055.383 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 261.011 MiB) 2.50.055.407 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 260.600 MiB) 2.51.139.677 I slot launch_slot_: id 0 | task 4268 | processing task, is_child = 0 2.53.010.267 I slot print_timing: id 0 | task 4268 | prompt eval time = 967.72 ms / 465 tokens ( 2.08 ms per token, 480.51 tokens per second) 2.53.010.273 I slot print_timing: id 0 | task 4268 | eval time = 902.85 ms / 46 tokens ( 20.06 ms per token, 49.84 tokens per second) 2.53.010.274 I slot print_timing: id 0 | task 4268 | total time = 1870.57 ms / 511 tokens 2.53.010.274 I slot print_timing: id 0 | task 4268 | graphs reused = 3932 2.53.010.275 I slot print_timing: id 0 | task 4268 | graph reallocs = 0 / 0 (same size) / (changed size) 2.53.010.395 I slot release: id 0 | task 4268 | stop processing: n_tokens = 542, truncated = 0 2.53.017.668 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 542, t_last = 386071215939 2.53.017.705 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 258.977 MiB) 2.53.617.375 I slot launch_slot_: id 0 | task 4317 | processing task, is_child = 0 2.55.362.796 I slot print_timing: id 0 | task 4317 | prompt eval time = 944.59 ms / 431 tokens ( 2.19 ms per token, 456.28 tokens per second) 2.55.362.799 I slot print_timing: id 0 | task 4317 | eval time = 800.81 ms / 41 tokens ( 20.02 ms per token, 49.95 tokens per second) 2.55.362.800 I slot print_timing: id 0 | task 4317 | total time = 1745.40 ms / 472 tokens 2.55.362.800 I slot print_timing: id 0 | task 4317 | graphs reused = 3971 2.55.362.801 I slot print_timing: id 0 | task 4317 | graph reallocs = 0 / 0 (same size) / (changed size) 2.55.362.896 I slot release: id 0 | task 4317 | stop processing: n_tokens = 503, truncated = 0 2.55.370.553 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 503, t_last = 386073568440 2.55.370.594 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 259.349 MiB) 2.55.370.620 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 259.446 MiB) 2.56.387.821 I slot launch_slot_: id 0 | task 4361 | processing task, is_child = 0 2.58.352.795 I slot print_timing: id 0 | task 4361 | prompt eval time = 1105.79 ms / 457 tokens ( 2.42 ms per token, 413.28 tokens per second) 2.58.352.799 I slot print_timing: id 0 | task 4361 | eval time = 859.16 ms / 44 tokens ( 19.98 ms per token, 50.05 tokens per second) 2.58.352.800 I slot print_timing: id 0 | task 4361 | total time = 1964.96 ms / 501 tokens 2.58.352.800 I slot print_timing: id 0 | task 4361 | graphs reused = 4012 2.58.352.801 I slot print_timing: id 0 | task 4361 | graph reallocs = 0 / 0 (same size) / (changed size) 2.58.352.867 I slot release: id 0 | task 4361 | stop processing: n_tokens = 532, truncated = 0 2.58.359.790 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 532, t_last = 386076558410 2.58.359.827 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 260.444 MiB) 2.59.044.908 I slot launch_slot_: id 0 | task 4408 | processing task, is_child = 0 3.00.821.021 I slot print_timing: id 0 | task 4408 | prompt eval time = 958.33 ms / 439 tokens ( 2.18 ms per token, 458.09 tokens per second) 3.00.821.027 I slot print_timing: id 0 | task 4408 | eval time = 817.76 ms / 42 tokens ( 19.95 ms per token, 50.14 tokens per second) 3.00.821.027 I slot print_timing: id 0 | task 4408 | total time = 1776.09 ms / 481 tokens 3.00.821.028 I slot print_timing: id 0 | task 4408 | graphs reused = 4052 3.00.821.028 I slot print_timing: id 0 | task 4408 | graph reallocs = 0 / 0 (same size) / (changed size) 3.00.822.199 I slot release: id 0 | task 4408 | stop processing: n_tokens = 512, truncated = 0 3.00.829.601 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 512, t_last = 386079027743 3.00.829.636 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 259.251 MiB) 3.00.829.977 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 260.209 MiB) 3.02.164.519 I slot launch_slot_: id 0 | task 4453 | processing task, is_child = 0 3.04.601.893 I slot print_timing: id 0 | task 4453 | prompt eval time = 1344.68 ms / 606 tokens ( 2.22 ms per token, 450.67 tokens per second) 3.04.601.896 I slot print_timing: id 0 | task 4453 | eval time = 1092.68 ms / 56 tokens ( 19.87 ms per token, 50.33 tokens per second) 3.04.601.896 I slot print_timing: id 0 | task 4453 | total time = 2437.36 ms / 662 tokens 3.04.601.897 I slot print_timing: id 0 | task 4453 | graphs reused = 4106 3.04.601.898 I slot print_timing: id 0 | task 4453 | graph reallocs = 0 / 0 (same size) / (changed size) 3.04.603.434 I slot release: id 0 | task 4453 | stop processing: n_tokens = 693, truncated = 0 3.04.612.490 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 386082808980 3.04.612.533 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 259.740 MiB) 3.05.368.335 I slot launch_slot_: id 0 | task 4513 | processing task, is_child = 0 3.07.181.030 I slot print_timing: id 0 | task 4513 | prompt eval time = 1006.49 ms / 477 tokens ( 2.11 ms per token, 473.92 tokens per second) 3.07.181.033 I slot print_timing: id 0 | task 4513 | eval time = 806.19 ms / 41 tokens ( 20.15 ms per token, 49.62 tokens per second) 3.07.181.034 I slot print_timing: id 0 | task 4513 | total time = 1812.68 ms / 518 tokens 3.07.181.034 I slot print_timing: id 0 | task 4513 | graphs reused = 4144 3.07.181.035 I slot print_timing: id 0 | task 4513 | graph reallocs = 0 / 0 (same size) / (changed size) 3.07.181.588 I slot release: id 0 | task 4513 | stop processing: n_tokens = 549, truncated = 0 3.07.193.899 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 386085387133 3.07.193.938 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 259.446 MiB) 3.07.193.958 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 262.575 MiB) 3.08.438.114 I slot launch_slot_: id 0 | task 4557 | processing task, is_child = 0 3.11.372.958 I slot print_timing: id 0 | task 4557 | prompt eval time = 1753.41 ms / 845 tokens ( 2.08 ms per token, 481.92 tokens per second) 3.11.372.962 I slot print_timing: id 0 | task 4557 | eval time = 1181.41 ms / 60 tokens ( 20.02 ms per token, 49.94 tokens per second) 3.11.372.963 I slot print_timing: id 0 | task 4557 | total time = 2934.83 ms / 905 tokens 3.11.372.963 I slot print_timing: id 0 | task 4557 | graphs reused = 4202 3.11.372.964 I slot print_timing: id 0 | task 4557 | graph reallocs = 0 / 0 (same size) / (changed size) 3.11.374.885 I slot release: id 0 | task 4557 | stop processing: n_tokens = 936, truncated = 0 3.11.382.885 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 936, t_last = 386089580429 3.11.382.935 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 261.871 MiB) 3.12.135.729 I slot launch_slot_: id 0 | task 4621 | processing task, is_child = 0 3.13.978.291 I slot print_timing: id 0 | task 4621 | prompt eval time = 1000.26 ms / 459 tokens ( 2.18 ms per token, 458.88 tokens per second) 3.13.978.294 I slot print_timing: id 0 | task 4621 | eval time = 842.29 ms / 43 tokens ( 20.05 ms per token, 49.86 tokens per second) 3.13.978.294 I slot print_timing: id 0 | task 4621 | total time = 1842.55 ms / 502 tokens 3.13.978.295 I slot print_timing: id 0 | task 4621 | graphs reused = 4242 3.13.978.298 I slot print_timing: id 0 | task 4621 | graph reallocs = 0 / 0 (same size) / (changed size) 3.13.978.608 I slot release: id 0 | task 4621 | stop processing: n_tokens = 533, truncated = 0 3.13.997.586 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 533, t_last = 386092184152 3.13.997.622 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 259.290 MiB) 3.13.997.642 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 260.013 MiB) 3.15.028.612 I slot launch_slot_: id 0 | task 4667 | processing task, is_child = 0 3.17.411.456 I slot print_timing: id 0 | task 4667 | prompt eval time = 1464.54 ms / 670 tokens ( 2.19 ms per token, 457.48 tokens per second) 3.17.411.462 I slot print_timing: id 0 | task 4667 | eval time = 918.28 ms / 47 tokens ( 19.96 ms per token, 50.09 tokens per second) 3.17.411.462 I slot print_timing: id 0 | task 4667 | total time = 2382.83 ms / 717 tokens 3.17.411.463 I slot print_timing: id 0 | task 4667 | graphs reused = 4287 3.17.411.464 I slot print_timing: id 0 | task 4667 | graph reallocs = 0 / 0 (same size) / (changed size) 3.17.411.600 I slot release: id 0 | task 4667 | stop processing: n_tokens = 748, truncated = 0 3.17.423.428 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 748, t_last = 386095617144 3.17.423.470 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 258.938 MiB) 3.17.423.486 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 260.698 MiB) 3.18.881.505 I slot launch_slot_: id 0 | task 4718 | processing task, is_child = 0 3.21.810.141 I slot print_timing: id 0 | task 4718 | prompt eval time = 1649.37 ms / 775 tokens ( 2.13 ms per token, 469.88 tokens per second) 3.21.810.145 I slot print_timing: id 0 | task 4718 | eval time = 1279.25 ms / 63 tokens ( 20.63 ms per token, 48.47 tokens per second) 3.21.810.146 I slot print_timing: id 0 | task 4718 | total time = 2928.62 ms / 838 tokens 3.21.810.147 I slot print_timing: id 0 | task 4718 | graphs reused = 4348 3.21.810.147 I slot print_timing: id 0 | task 4718 | graph reallocs = 0 / 0 (same size) / (changed size) 3.21.812.296 I slot release: id 0 | task 4718 | stop processing: n_tokens = 869, truncated = 0 3.21.823.260 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 869, t_last = 386100017840 3.21.823.307 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 326.131 MiB) 3.22.631.131 I slot launch_slot_: id 0 | task 4785 | processing task, is_child = 0 3.25.314.141 I slot print_timing: id 0 | task 4785 | prompt eval time = 1285.26 ms / 573 tokens ( 2.24 ms per token, 445.82 tokens per second) 3.25.314.147 I slot print_timing: id 0 | task 4785 | eval time = 1397.74 ms / 71 tokens ( 19.97 ms per token, 50.08 tokens per second) 3.25.314.148 I slot print_timing: id 0 | task 4785 | total time = 2683.00 ms / 644 tokens 3.25.314.149 I slot print_timing: id 0 | task 4785 | graphs reused = 4417 3.25.314.149 I slot print_timing: id 0 | task 4785 | graph reallocs = 0 / 0 (same size) / (changed size) 3.25.316.218 I slot release: id 0 | task 4785 | stop processing: n_tokens = 675, truncated = 0 3.25.322.890 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 675, t_last = 386103521762 3.25.322.929 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 327.461 MiB) 3.25.322.962 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.478 MiB) 3.26.607.627 I slot launch_slot_: id 0 | task 4860 | processing task, is_child = 0 3.28.881.423 I slot print_timing: id 0 | task 4860 | prompt eval time = 1013.05 ms / 461 tokens ( 2.20 ms per token, 455.06 tokens per second) 3.28.881.426 I slot print_timing: id 0 | task 4860 | eval time = 1260.72 ms / 64 tokens ( 20.01 ms per token, 49.97 tokens per second) 3.28.881.426 I slot print_timing: id 0 | task 4860 | total time = 2273.77 ms / 525 tokens 3.28.881.856 I slot print_timing: id 0 | task 4860 | graphs reused = 4478 3.28.881.859 I slot print_timing: id 0 | task 4860 | graph reallocs = 0 / 0 (same size) / (changed size) 3.28.881.904 I slot release: id 0 | task 4860 | stop processing: n_tokens = 556, truncated = 0 3.28.912.969 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 556, t_last = 386107087447 3.28.913.004 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 327.969 MiB) 3.29.689.472 I slot launch_slot_: id 0 | task 4927 | processing task, is_child = 0 3.31.885.966 I slot print_timing: id 0 | task 4927 | prompt eval time = 1336.08 ms / 609 tokens ( 2.19 ms per token, 455.81 tokens per second) 3.31.885.973 I slot print_timing: id 0 | task 4927 | eval time = 860.39 ms / 43 tokens ( 20.49 ms per token, 48.81 tokens per second) 3.31.885.974 I slot print_timing: id 0 | task 4927 | total time = 2196.48 ms / 652 tokens 3.31.885.975 I slot print_timing: id 0 | task 4927 | graphs reused = 4519 3.31.885.975 I slot print_timing: id 0 | task 4927 | graph reallocs = 0 / 0 (same size) / (changed size) 3.31.886.044 I slot release: id 0 | task 4927 | stop processing: n_tokens = 683, truncated = 0 3.31.894.743 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 683, t_last = 386110091587 3.31.894.785 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 261.754 MiB) 3.32.246.284 I slot launch_slot_: id 0 | task 4974 | processing task, is_child = 0 3.35.088.422 I slot print_timing: id 0 | task 4974 | prompt eval time = 1641.57 ms / 791 tokens ( 2.08 ms per token, 481.86 tokens per second) 3.35.088.425 I slot print_timing: id 0 | task 4974 | eval time = 1200.55 ms / 61 tokens ( 20.01 ms per token, 49.98 tokens per second) 3.35.088.426 I slot print_timing: id 0 | task 4974 | total time = 2842.12 ms / 852 tokens 3.35.088.427 I slot print_timing: id 0 | task 4974 | graphs reused = 4578 3.35.088.427 I slot print_timing: id 0 | task 4974 | graph reallocs = 0 / 0 (same size) / (changed size) 3.35.089.716 I slot release: id 0 | task 4974 | stop processing: n_tokens = 883, truncated = 0 3.35.098.121 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 883, t_last = 386113295260 3.35.098.173 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 327.168 MiB) 3.35.098.189 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 326.972 MiB) 3.36.488.884 I slot launch_slot_: id 0 | task 5039 | processing task, is_child = 0 3.38.806.495 I slot print_timing: id 0 | task 5039 | prompt eval time = 1220.17 ms / 533 tokens ( 2.29 ms per token, 436.82 tokens per second) 3.38.806.504 I slot print_timing: id 0 | task 5039 | eval time = 1097.43 ms / 56 tokens ( 19.95 ms per token, 50.12 tokens per second) 3.38.806.505 I slot print_timing: id 0 | task 5039 | total time = 2317.60 ms / 589 tokens 3.38.806.505 I slot print_timing: id 0 | task 5039 | graphs reused = 4632 3.38.806.506 I slot print_timing: id 0 | task 5039 | graph reallocs = 0 / 0 (same size) / (changed size) 3.38.806.589 I slot release: id 0 | task 5039 | stop processing: n_tokens = 677, truncated = 0 3.38.814.039 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 677, t_last = 386117012133 3.39.467.773 I slot launch_slot_: id 0 | task 5099 | processing task, is_child = 0 3.41.680.078 I slot print_timing: id 0 | task 5099 | prompt eval time = 1288.38 ms / 566 tokens ( 2.28 ms per token, 439.31 tokens per second) 3.41.680.081 I slot print_timing: id 0 | task 5099 | eval time = 923.90 ms / 46 tokens ( 20.53 ms per token, 48.71 tokens per second) 3.41.680.082 I slot print_timing: id 0 | task 5099 | total time = 2212.28 ms / 612 tokens 3.41.680.083 I slot print_timing: id 0 | task 5099 | graphs reused = 4676 3.41.680.083 I slot print_timing: id 0 | task 5099 | graph reallocs = 0 / 0 (same size) / (changed size) 3.41.681.642 I slot release: id 0 | task 5099 | stop processing: n_tokens = 643, truncated = 0 3.41.690.579 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 643, t_last = 386119887186 3.41.690.619 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.623 MiB) 3.42.719.845 I slot launch_slot_: id 0 | task 5149 | processing task, is_child = 0 3.44.543.511 I slot print_timing: id 0 | task 5149 | prompt eval time = 974.85 ms / 443 tokens ( 2.20 ms per token, 454.43 tokens per second) 3.44.543.516 I slot print_timing: id 0 | task 5149 | eval time = 848.80 ms / 43 tokens ( 20.21 ms per token, 49.48 tokens per second) 3.44.543.517 I slot print_timing: id 0 | task 5149 | total time = 1823.65 ms / 486 tokens 3.44.543.518 I slot print_timing: id 0 | task 5149 | graphs reused = 4716 3.44.543.518 I slot print_timing: id 0 | task 5149 | graph reallocs = 0 / 0 (same size) / (changed size) 3.44.544.031 I slot release: id 0 | task 5149 | stop processing: n_tokens = 517, truncated = 0 3.44.552.324 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 517, t_last = 386122749575 3.44.552.359 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.017 MiB) 3.44.552.384 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 389.336 MiB) 3.45.697.948 I slot launch_slot_: id 0 | task 5195 | processing task, is_child = 0 3.47.989.790 I slot print_timing: id 0 | task 5195 | prompt eval time = 1015.21 ms / 487 tokens ( 2.08 ms per token, 479.71 tokens per second) 3.47.989.797 I slot print_timing: id 0 | task 5195 | eval time = 1276.62 ms / 65 tokens ( 19.95 ms per token, 50.13 tokens per second) 3.47.989.798 I slot print_timing: id 0 | task 5195 | total time = 2291.83 ms / 552 tokens 3.47.989.798 I slot print_timing: id 0 | task 5195 | graphs reused = 4779 3.47.989.799 I slot print_timing: id 0 | task 5195 | graph reallocs = 0 / 0 (same size) / (changed size) 3.47.991.037 I slot release: id 0 | task 5195 | stop processing: n_tokens = 583, truncated = 0 3.48.004.878 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 583, t_last = 386126196583 3.48.004.912 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.740 MiB) 3.49.106.377 I slot launch_slot_: id 0 | task 5263 | processing task, is_child = 0 3.51.092.060 I slot print_timing: id 0 | task 5263 | prompt eval time = 1064.44 ms / 507 tokens ( 2.10 ms per token, 476.31 tokens per second) 3.51.092.066 I slot print_timing: id 0 | task 5263 | eval time = 921.23 ms / 47 tokens ( 20.03 ms per token, 49.93 tokens per second) 3.51.092.067 I slot print_timing: id 0 | task 5263 | total time = 1985.67 ms / 554 tokens 3.51.093.015 I slot print_timing: id 0 | task 5263 | graphs reused = 4824 3.51.093.019 I slot print_timing: id 0 | task 5263 | graph reallocs = 0 / 0 (same size) / (changed size) 3.51.093.627 I slot release: id 0 | task 5263 | stop processing: n_tokens = 585, truncated = 0 3.51.103.352 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 585, t_last = 386129299171 3.51.103.389 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.922 MiB) 3.52.022.343 I slot launch_slot_: id 0 | task 5313 | processing task, is_child = 0 3.54.711.192 I slot print_timing: id 0 | task 5313 | prompt eval time = 1389.16 ms / 633 tokens ( 2.19 ms per token, 455.67 tokens per second) 3.54.711.196 I slot print_timing: id 0 | task 5313 | eval time = 1299.67 ms / 66 tokens ( 19.99 ms per token, 50.01 tokens per second) 3.54.711.196 I slot print_timing: id 0 | task 5313 | total time = 2688.84 ms / 699 tokens 3.54.711.197 I slot print_timing: id 0 | task 5313 | graphs reused = 4888 3.54.711.198 I slot print_timing: id 0 | task 5313 | graph reallocs = 0 / 0 (same size) / (changed size) 3.54.711.283 I slot release: id 0 | task 5313 | stop processing: n_tokens = 730, truncated = 0 3.54.719.070 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 730, t_last = 386132916826 3.54.719.115 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.788 MiB) 3.56.065.415 I slot launch_slot_: id 0 | task 5383 | processing task, is_child = 0 3.58.290.904 I slot print_timing: id 0 | task 5383 | prompt eval time = 1304.42 ms / 571 tokens ( 2.28 ms per token, 437.74 tokens per second) 3.58.290.910 I slot print_timing: id 0 | task 5383 | eval time = 921.06 ms / 47 tokens ( 20.02 ms per token, 49.94 tokens per second) 3.58.290.925 I slot print_timing: id 0 | task 5383 | total time = 2225.47 ms / 618 tokens 3.58.290.928 I slot print_timing: id 0 | task 5383 | graphs reused = 4933 3.58.290.932 I slot print_timing: id 0 | task 5383 | graph reallocs = 0 / 0 (same size) / (changed size) 3.58.291.017 I slot release: id 0 | task 5383 | stop processing: n_tokens = 649, truncated = 0 3.58.301.584 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 649, t_last = 386136496561 3.58.301.624 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.478 MiB) 3.59.499.013 I slot launch_slot_: id 0 | task 5434 | processing task, is_child = 0 4.02.014.151 I slot print_timing: id 0 | task 5434 | prompt eval time = 1651.28 ms / 798 tokens ( 2.07 ms per token, 483.26 tokens per second) 4.02.014.154 I slot print_timing: id 0 | task 5434 | eval time = 863.84 ms / 44 tokens ( 20.09 ms per token, 49.78 tokens per second) 4.02.014.155 I slot print_timing: id 0 | task 5434 | total time = 2515.12 ms / 842 tokens 4.02.014.156 I slot print_timing: id 0 | task 5434 | graphs reused = 4975 4.02.014.156 I slot print_timing: id 0 | task 5434 | graph reallocs = 0 / 0 (same size) / (changed size) 4.02.015.188 I slot release: id 0 | task 5434 | stop processing: n_tokens = 873, truncated = 0 4.02.022.904 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 873, t_last = 386140220732 4.02.022.954 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.715 MiB) 4.03.182.132 I slot launch_slot_: id 0 | task 5482 | processing task, is_child = 0 4.05.347.003 I slot print_timing: id 0 | task 5482 | prompt eval time = 1323.33 ms / 572 tokens ( 2.31 ms per token, 432.24 tokens per second) 4.05.347.010 I slot print_timing: id 0 | task 5482 | eval time = 841.53 ms / 43 tokens ( 20.04 ms per token, 49.91 tokens per second) 4.05.347.010 I slot print_timing: id 0 | task 5482 | total time = 2164.86 ms / 615 tokens 4.05.347.011 I slot print_timing: id 0 | task 5482 | graphs reused = 5016 4.05.347.012 I slot print_timing: id 0 | task 5482 | graph reallocs = 0 / 0 (same size) / (changed size) 4.05.348.046 I slot release: id 0 | task 5482 | stop processing: n_tokens = 646, truncated = 0 4.05.355.786 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 646, t_last = 386143553590 4.05.355.825 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.282 MiB) 4.05.355.851 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.891 MiB) 4.06.714.572 I slot launch_slot_: id 0 | task 5529 | processing task, is_child = 0 4.09.366.017 I slot print_timing: id 0 | task 5529 | prompt eval time = 1391.85 ms / 613 tokens ( 2.27 ms per token, 440.42 tokens per second) 4.09.366.021 I slot print_timing: id 0 | task 5529 | eval time = 1259.57 ms / 64 tokens ( 19.99 ms per token, 50.02 tokens per second) 4.09.366.021 I slot print_timing: id 0 | task 5529 | total time = 2651.42 ms / 677 tokens 4.09.366.022 I slot print_timing: id 0 | task 5529 | graphs reused = 5078 4.09.366.023 I slot print_timing: id 0 | task 5529 | graph reallocs = 0 / 0 (same size) / (changed size) 4.09.367.164 I slot release: id 0 | task 5529 | stop processing: n_tokens = 708, truncated = 0 4.09.377.117 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 708, t_last = 386147572708 4.09.377.158 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 453.244 MiB) 4.10.289.968 I slot launch_slot_: id 0 | task 5597 | processing task, is_child = 0 4.12.839.717 I slot print_timing: id 0 | task 5597 | prompt eval time = 1289.02 ms / 580 tokens ( 2.22 ms per token, 449.95 tokens per second) 4.12.839.723 I slot print_timing: id 0 | task 5597 | eval time = 1260.71 ms / 64 tokens ( 20.01 ms per token, 49.97 tokens per second) 4.12.839.724 I slot print_timing: id 0 | task 5597 | total time = 2549.73 ms / 644 tokens 4.12.839.725 I slot print_timing: id 0 | task 5597 | graphs reused = 5140 4.12.839.725 I slot print_timing: id 0 | task 5597 | graph reallocs = 0 / 0 (same size) / (changed size) 4.12.841.423 I slot release: id 0 | task 5597 | stop processing: n_tokens = 675, truncated = 0 4.12.850.233 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 675, t_last = 386151046967 4.12.850.273 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.615 MiB) 4.14.182.180 I slot launch_slot_: id 0 | task 5665 | processing task, is_child = 0 4.16.722.309 I slot print_timing: id 0 | task 5665 | prompt eval time = 1552.89 ms / 716 tokens ( 2.17 ms per token, 461.08 tokens per second) 4.16.722.315 I slot print_timing: id 0 | task 5665 | eval time = 987.22 ms / 50 tokens ( 20.15 ms per token, 49.63 tokens per second) 4.16.722.316 I slot print_timing: id 0 | task 5665 | total time = 2540.11 ms / 766 tokens 4.16.722.784 I slot print_timing: id 0 | task 5665 | graphs reused = 5187 4.16.722.787 I slot print_timing: id 0 | task 5665 | graph reallocs = 0 / 0 (same size) / (changed size) 4.16.723.225 I slot release: id 0 | task 5665 | stop processing: n_tokens = 797, truncated = 0 4.16.733.140 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 797, t_last = 386154928769 4.16.733.191 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 457.995 MiB) 4.17.635.967 I slot launch_slot_: id 0 | task 5719 | processing task, is_child = 0 4.21.308.499 I slot print_timing: id 0 | task 5719 | prompt eval time = 1632.05 ms / 799 tokens ( 2.04 ms per token, 489.57 tokens per second) 4.21.308.505 I slot print_timing: id 0 | task 5719 | eval time = 2040.47 ms / 103 tokens ( 20.00 ms per token, 49.99 tokens per second) 4.21.308.506 I slot print_timing: id 0 | task 5719 | total time = 3672.52 ms / 902 tokens 4.21.308.507 I slot print_timing: id 0 | task 5719 | graphs reused = 5288 4.21.308.507 I slot print_timing: id 0 | task 5719 | graph reallocs = 0 / 0 (same size) / (changed size) 4.21.308.617 I slot release: id 0 | task 5719 | stop processing: n_tokens = 933, truncated = 0 4.21.316.271 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 933, t_last = 386159514160 4.21.316.324 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.302 MiB) 4.22.472.299 I slot launch_slot_: id 0 | task 5826 | processing task, is_child = 0 4.25.548.464 I slot print_timing: id 0 | task 5826 | prompt eval time = 871.76 ms / 361 tokens ( 2.41 ms per token, 414.11 tokens per second) 4.25.548.467 I slot print_timing: id 0 | task 5826 | eval time = 2204.39 ms / 112 tokens ( 19.86 ms per token, 50.35 tokens per second) 4.25.548.467 I slot print_timing: id 0 | task 5826 | total time = 3076.15 ms / 473 tokens 4.25.548.468 I slot print_timing: id 0 | task 5826 | graphs reused = 5398 4.25.548.468 I slot print_timing: id 0 | task 5826 | graph reallocs = 0 / 0 (same size) / (changed size) 4.25.548.825 I slot release: id 0 | task 5826 | stop processing: n_tokens = 504, truncated = 0 4.25.555.511 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 386163754369 4.25.555.545 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 454.319 MiB) 4.26.993.955 I slot launch_slot_: id 0 | task 5941 | processing task, is_child = 0 4.30.033.122 I slot print_timing: id 0 | task 5941 | prompt eval time = 906.36 ms / 381 tokens ( 2.38 ms per token, 420.36 tokens per second) 4.30.033.128 I slot print_timing: id 0 | task 5941 | eval time = 2132.79 ms / 108 tokens ( 19.93 ms per token, 50.17 tokens per second) 4.30.033.129 I slot print_timing: id 0 | task 5941 | total time = 3039.15 ms / 489 tokens 4.30.033.129 I slot print_timing: id 0 | task 5941 | graphs reused = 5503 4.30.033.130 I slot print_timing: id 0 | task 5941 | graph reallocs = 0 / 0 (same size) / (changed size) 4.30.034.237 I slot release: id 0 | task 5941 | stop processing: n_tokens = 520, truncated = 0 4.30.042.550 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 386168239781 4.30.042.584 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 456.685 MiB) 4.31.044.859 I slot launch_slot_: id 0 | task 6052 | processing task, is_child = 0 4.34.356.124 I slot print_timing: id 0 | task 6052 | prompt eval time = 863.11 ms / 365 tokens ( 2.36 ms per token, 422.89 tokens per second) 4.34.356.130 I slot print_timing: id 0 | task 6052 | eval time = 2448.14 ms / 124 tokens ( 19.90 ms per token, 50.24 tokens per second) 4.34.356.131 I slot print_timing: id 0 | task 6052 | total time = 3311.25 ms / 489 tokens 4.34.356.132 I slot print_timing: id 0 | task 6052 | graphs reused = 5624 4.34.356.132 I slot print_timing: id 0 | task 6052 | graph reallocs = 0 / 0 (same size) / (changed size) 4.34.356.194 I slot release: id 0 | task 6052 | stop processing: n_tokens = 520, truncated = 0 4.34.363.475 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 386172561737 4.34.363.510 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.752 MiB) 4.35.291.311 I slot launch_slot_: id 0 | task 6179 | processing task, is_child = 0 4.38.228.334 I slot print_timing: id 0 | task 6179 | prompt eval time = 828.69 ms / 333 tokens ( 2.49 ms per token, 401.84 tokens per second) 4.38.228.337 I slot print_timing: id 0 | task 6179 | eval time = 2108.32 ms / 107 tokens ( 19.89 ms per token, 50.28 tokens per second) 4.38.228.338 I slot print_timing: id 0 | task 6179 | total time = 2937.01 ms / 440 tokens 4.38.228.338 I slot print_timing: id 0 | task 6179 | graphs reused = 5729 4.38.228.339 I slot print_timing: id 0 | task 6179 | graph reallocs = 0 / 0 (same size) / (changed size) 4.38.228.388 I slot release: id 0 | task 6179 | stop processing: n_tokens = 471, truncated = 0 4.38.234.943 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 471, t_last = 386176433931 4.38.234.979 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 453.048 MiB) 4.39.314.100 I slot launch_slot_: id 0 | task 6289 | processing task, is_child = 0 4.42.966.928 I slot print_timing: id 0 | task 6289 | prompt eval time = 923.78 ms / 403 tokens ( 2.29 ms per token, 436.25 tokens per second) 4.42.966.932 I slot print_timing: id 0 | task 6289 | eval time = 2729.02 ms / 138 tokens ( 19.92 ms per token, 50.20 tokens per second) 4.42.966.932 I slot print_timing: id 0 | task 6289 | total time = 3652.80 ms / 541 tokens 4.42.966.933 I slot print_timing: id 0 | task 6289 | graphs reused = 5864 4.42.966.934 I slot print_timing: id 0 | task 6289 | graph reallocs = 0 / 0 (same size) / (changed size) 4.42.966.987 I slot release: id 0 | task 6289 | stop processing: n_tokens = 572, truncated = 0 4.42.974.235 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 572, t_last = 386181172530 4.43.795.011 I slot launch_slot_: id 0 | task 6430 | processing task, is_child = 0 4.47.742.047 I slot print_timing: id 0 | task 6430 | n_gen = 152, tg = 50.24 t/s, tg_3s = 50.58 t/s 4.48.398.359 I slot print_timing: id 0 | task 6430 | prompt eval time = 941.64 ms / 411 tokens ( 2.29 ms per token, 436.47 tokens per second) 4.48.398.362 I slot print_timing: id 0 | task 6430 | eval time = 3661.69 ms / 185 tokens ( 19.90 ms per token, 50.25 tokens per second) 4.48.398.363 I slot print_timing: id 0 | task 6430 | total time = 4603.33 ms / 596 tokens 4.48.398.363 I slot print_timing: id 0 | task 6430 | graphs reused = 6046 4.48.398.364 I slot print_timing: id 0 | task 6430 | graph reallocs = 0 / 0 (same size) / (changed size) 4.48.398.413 I slot release: id 0 | task 6430 | stop processing: n_tokens = 627, truncated = 0 4.48.406.065 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 627, t_last = 386186603956 4.48.406.107 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 456.959 MiB) 4.49.765.766 I slot launch_slot_: id 0 | task 6618 | processing task, is_child = 0 4.53.847.540 I slot print_timing: id 0 | task 6618 | n_gen = 152, tg = 50.18 t/s, tg_3s = 50.51 t/s 4.55.298.666 I slot print_timing: id 0 | task 6618 | prompt eval time = 1072.64 ms / 490 tokens ( 2.19 ms per token, 456.82 tokens per second) 4.55.298.672 I slot print_timing: id 0 | task 6618 | eval time = 4460.24 ms / 225 tokens ( 19.91 ms per token, 50.22 tokens per second) 4.55.298.673 I slot print_timing: id 0 | task 6618 | total time = 5532.89 ms / 715 tokens 4.55.298.674 I slot print_timing: id 0 | task 6618 | graphs reused = 6269 4.55.298.674 I slot print_timing: id 0 | task 6618 | graph reallocs = 0 / 0 (same size) / (changed size) 4.55.298.748 I slot release: id 0 | task 6618 | stop processing: n_tokens = 746, truncated = 0 4.55.303.357 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 746, t_last = 386193504294 4.55.303.404 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 515.744 MiB) 4.55.816.519 I slot launch_slot_: id 0 | task 6846 | processing task, is_child = 0 4.59.686.468 I slot print_timing: id 0 | task 6846 | n_gen = 152, tg = 50.18 t/s, tg_3s = 50.51 t/s 5.02.626.889 I slot print_timing: id 0 | task 6846 | prompt eval time = 860.47 ms / 344 tokens ( 2.50 ms per token, 399.78 tokens per second) 5.02.626.894 I slot print_timing: id 0 | task 6846 | eval time = 5949.88 ms / 300 tokens ( 19.90 ms per token, 50.25 tokens per second) 5.02.626.895 I slot print_timing: id 0 | task 6846 | total time = 6810.35 ms / 644 tokens 5.02.626.896 I slot print_timing: id 0 | task 6846 | graphs reused = 6566 5.02.626.896 I slot print_timing: id 0 | task 6846 | graph reallocs = 0 / 0 (same size) / (changed size) 5.02.626.932 I slot release: id 0 | task 6846 | stop processing: n_tokens = 675, truncated = 0 5.02.635.038 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 675, t_last = 386200832475 5.02.635.081 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 452.266 MiB) 5.03.590.077 I slot launch_slot_: id 0 | task 7149 | processing task, is_child = 0 5.07.473.381 I slot print_timing: id 0 | task 7149 | n_gen = 153, tg = 50.39 t/s, tg_3s = 50.72 t/s 5.07.831.623 I slot print_timing: id 0 | task 7149 | prompt eval time = 866.94 ms / 347 tokens ( 2.50 ms per token, 400.26 tokens per second) 5.07.831.632 I slot print_timing: id 0 | task 7149 | eval time = 3374.59 ms / 171 tokens ( 19.85 ms per token, 50.38 tokens per second) 5.07.831.632 I slot print_timing: id 0 | task 7149 | total time = 4241.53 ms / 518 tokens 5.07.831.633 I slot print_timing: id 0 | task 7149 | graphs reused = 6734 5.07.831.634 I slot print_timing: id 0 | task 7149 | graph reallocs = 0 / 0 (same size) / (changed size) 5.07.831.718 I slot release: id 0 | task 7149 | stop processing: n_tokens = 549, truncated = 0 5.07.840.193 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 386206037262 5.07.840.230 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.989 MiB) 5.08.920.122 I slot launch_slot_: id 0 | task 7323 | processing task, is_child = 0 5.12.324.341 I slot print_timing: id 0 | task 7323 | prompt eval time = 916.25 ms / 401 tokens ( 2.28 ms per token, 437.65 tokens per second) 5.12.324.345 I slot print_timing: id 0 | task 7323 | eval time = 2487.96 ms / 126 tokens ( 19.90 ms per token, 50.24 tokens per second) 5.12.324.346 I slot print_timing: id 0 | task 7323 | total time = 3404.21 ms / 527 tokens 5.12.324.346 I slot print_timing: id 0 | task 7323 | graphs reused = 6857 5.12.324.347 I slot print_timing: id 0 | task 7323 | graph reallocs = 0 / 0 (same size) / (changed size) 5.12.324.396 I slot release: id 0 | task 7323 | stop processing: n_tokens = 558, truncated = 0 5.12.332.355 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 386210529939 5.12.332.393 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.280 MiB) 5.13.740.425 I slot launch_slot_: id 0 | task 7452 | processing task, is_child = 0 5.17.069.934 I slot print_timing: id 0 | task 7452 | prompt eval time = 1032.17 ms / 456 tokens ( 2.26 ms per token, 441.79 tokens per second) 5.17.069.940 I slot print_timing: id 0 | task 7452 | eval time = 2297.32 ms / 115 tokens ( 20.15 ms per token, 49.62 tokens per second) 5.17.069.942 I slot print_timing: id 0 | task 7452 | total time = 3329.49 ms / 571 tokens 5.17.069.943 I slot print_timing: id 0 | task 7452 | graphs reused = 6969 5.17.069.943 I slot print_timing: id 0 | task 7452 | graph reallocs = 0 / 0 (same size) / (changed size) 5.17.070.000 I slot release: id 0 | task 7452 | stop processing: n_tokens = 602, truncated = 0 5.17.077.044 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 5.17.077.082 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.319 MiB) 5.17.964.732 I slot launch_slot_: id 0 | task 7570 | processing task, is_child = 0 5.21.929.025 I slot print_timing: id 0 | task 7570 | n_gen = 152, tg = 50.22 t/s, tg_3s = 50.55 t/s 5.23.700.061 I slot print_timing: id 0 | task 7570 | prompt eval time = 957.31 ms / 406 tokens ( 2.36 ms per token, 424.10 tokens per second) 5.23.700.065 I slot print_timing: id 0 | task 7570 | eval time = 4778.00 ms / 241 tokens ( 19.91 ms per token, 50.23 tokens per second) 5.23.700.066 I slot print_timing: id 0 | task 7570 | total time = 5735.31 ms / 647 tokens 5.23.700.066 I slot print_timing: id 0 | task 7570 | graphs reused = 7207 5.23.700.067 I slot print_timing: id 0 | task 7570 | graph reallocs = 0 / 0 (same size) / (changed size) 5.23.703.536 I slot release: id 0 | task 7570 | stop processing: n_tokens = 678, truncated = 0 5.23.715.260 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 678, t_last = 386221909080 5.23.715.304 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 453.967 MiB) 5.24.811.095 I slot launch_slot_: id 0 | task 7814 | processing task, is_child = 0 5.28.749.010 I slot print_timing: id 0 | task 7814 | n_gen = 152, tg = 50.06 t/s, tg_3s = 50.39 t/s 5.29.285.849 I slot print_timing: id 0 | task 7814 | prompt eval time = 921.31 ms / 406 tokens ( 2.27 ms per token, 440.68 tokens per second) 5.29.285.852 I slot print_timing: id 0 | task 7814 | eval time = 3553.42 ms / 179 tokens ( 19.96 ms per token, 50.09 tokens per second) 5.29.285.852 I slot print_timing: id 0 | task 7814 | total time = 4474.73 ms / 585 tokens 5.29.285.853 I slot print_timing: id 0 | task 7814 | graphs reused = 7383 5.29.285.853 I slot print_timing: id 0 | task 7814 | graph reallocs = 0 / 0 (same size) / (changed size) 5.29.285.917 I slot release: id 0 | task 7814 | stop processing: n_tokens = 616, truncated = 0 5.29.294.999 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 616, t_last = 386227491460 5.29.295.036 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 452.383 MiB) 5.30.436.730 I slot launch_slot_: id 0 | task 7996 | processing task, is_child = 0 5.34.457.921 I slot print_timing: id 0 | task 7996 | n_gen = 152, tg = 50.16 t/s, tg_3s = 50.49 t/s 5.37.227.692 I slot print_timing: id 0 | task 7996 | prompt eval time = 1010.95 ms / 444 tokens ( 2.28 ms per token, 439.19 tokens per second) 5.37.227.696 I slot print_timing: id 0 | task 7996 | eval time = 5779.99 ms / 290 tokens ( 20.00 ms per token, 50.00 tokens per second) 5.37.227.697 I slot print_timing: id 0 | task 7996 | total time = 6790.95 ms / 734 tokens 5.37.227.698 I slot print_timing: id 0 | task 7996 | graphs reused = 7670 5.37.227.698 I slot print_timing: id 0 | task 7996 | graph reallocs = 0 / 0 (same size) / (changed size) 5.37.229.211 I slot release: id 0 | task 7996 | stop processing: n_tokens = 765, truncated = 0 5.37.237.291 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 765, t_last = 386235434755 5.37.564.379 I slot launch_slot_: id 0 | task 8289 | processing task, is_child = 0 5.40.506.832 I slot print_timing: id 0 | task 8289 | prompt eval time = 917.62 ms / 372 tokens ( 2.47 ms per token, 405.40 tokens per second) 5.40.506.838 I slot print_timing: id 0 | task 8289 | eval time = 2024.82 ms / 103 tokens ( 19.85 ms per token, 50.37 tokens per second) 5.40.506.839 I slot print_timing: id 0 | task 8289 | total time = 2942.43 ms / 475 tokens 5.40.506.840 I slot print_timing: id 0 | task 8289 | graphs reused = 7771 5.40.506.840 I slot print_timing: id 0 | task 8289 | graph reallocs = 0 / 0 (same size) / (changed size) 5.40.506.910 I slot release: id 0 | task 8289 | stop processing: n_tokens = 506, truncated = 0 5.40.516.658 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 506, t_last = 386238712453 5.40.516.700 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 456.764 MiB) 5.41.496.039 I slot launch_slot_: id 0 | task 8395 | processing task, is_child = 0 5.45.523.350 I slot print_timing: id 0 | task 8395 | n_gen = 152, tg = 50.12 t/s, tg_3s = 50.46 t/s 5.47.073.834 I slot print_timing: id 0 | task 8395 | prompt eval time = 1014.73 ms / 454 tokens ( 2.24 ms per token, 447.41 tokens per second) 5.47.073.840 I slot print_timing: id 0 | task 8395 | eval time = 4563.05 ms / 230 tokens ( 19.93 ms per token, 50.19 tokens per second) 5.47.073.841 I slot print_timing: id 0 | task 8395 | total time = 5577.78 ms / 684 tokens 5.47.073.841 I slot print_timing: id 0 | task 8395 | graphs reused = 7998 5.47.073.842 I slot print_timing: id 0 | task 8395 | graph reallocs = 0 / 0 (same size) / (changed size) 5.47.074.924 I slot release: id 0 | task 8395 | stop processing: n_tokens = 715, truncated = 0 5.47.081.617 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 715, t_last = 386245280468 5.47.081.660 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 452.325 MiB) 5.48.129.736 I slot launch_slot_: id 0 | task 8628 | processing task, is_child = 0 5.52.002.551 I slot print_timing: id 0 | task 8628 | n_gen = 152, tg = 50.18 t/s, tg_3s = 50.51 t/s 5.53.473.769 I slot print_timing: id 0 | task 8628 | prompt eval time = 863.36 ms / 354 tokens ( 2.44 ms per token, 410.03 tokens per second) 5.53.473.772 I slot print_timing: id 0 | task 8628 | eval time = 4480.66 ms / 226 tokens ( 19.91 ms per token, 50.22 tokens per second) 5.53.473.772 I slot print_timing: id 0 | task 8628 | total time = 5344.02 ms / 580 tokens 5.53.473.773 I slot print_timing: id 0 | task 8628 | graphs reused = 8221 5.53.473.774 I slot print_timing: id 0 | task 8628 | graph reallocs = 0 / 0 (same size) / (changed size) 5.53.474.941 I slot release: id 0 | task 8628 | stop processing: n_tokens = 611, truncated = 0 5.53.482.781 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 611, t_last = 386251680485 5.53.482.822 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 453.537 MiB) 5.54.933.349 I slot launch_slot_: id 0 | task 8857 | processing task, is_child = 0 5.58.537.695 I slot print_timing: id 0 | task 8857 | prompt eval time = 844.63 ms / 334 tokens ( 2.53 ms per token, 395.44 tokens per second) 5.58.537.701 I slot print_timing: id 0 | task 8857 | eval time = 2759.70 ms / 140 tokens ( 19.85 ms per token, 50.37 tokens per second) 5.58.537.702 I slot print_timing: id 0 | task 8857 | total time = 3604.33 ms / 474 tokens 5.58.537.703 I slot print_timing: id 0 | task 8857 | graphs reused = 8359 5.58.537.703 I slot print_timing: id 0 | task 8857 | graph reallocs = 0 / 0 (same size) / (changed size) 5.58.537.746 I slot release: id 0 | task 8857 | stop processing: n_tokens = 505, truncated = 0 5.58.547.829 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 505, t_last = 386256743289 5.58.547.866 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 452.892 MiB) 5.59.841.994 I slot launch_slot_: id 0 | task 9000 | processing task, is_child = 0 6.03.824.743 I slot print_timing: id 0 | task 9000 | n_gen = 152, tg = 50.17 t/s, tg_3s = 50.50 t/s 6.04.282.620 I slot print_timing: id 0 | task 9000 | prompt eval time = 973.03 ms / 426 tokens ( 2.28 ms per token, 437.81 tokens per second) 6.04.282.623 I slot print_timing: id 0 | task 9000 | eval time = 3467.58 ms / 175 tokens ( 19.93 ms per token, 50.18 tokens per second) 6.04.282.624 I slot print_timing: id 0 | task 9000 | total time = 4440.61 ms / 601 tokens 6.04.282.625 I slot print_timing: id 0 | task 9000 | graphs reused = 8531 6.04.282.626 I slot print_timing: id 0 | task 9000 | graph reallocs = 0 / 0 (same size) / (changed size) 6.04.283.371 I slot release: id 0 | task 9000 | stop processing: n_tokens = 632, truncated = 0 6.04.291.024 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 632, t_last = 386262488915 6.04.291.490 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 455.277 MiB) 6.04.970.734 I slot launch_slot_: id 0 | task 9178 | processing task, is_child = 0 6.08.162.826 I slot print_timing: id 0 | task 9178 | prompt eval time = 882.89 ms / 366 tokens ( 2.41 ms per token, 414.55 tokens per second) 6.08.162.829 I slot print_timing: id 0 | task 9178 | eval time = 2309.18 ms / 117 tokens ( 19.91 ms per token, 50.23 tokens per second) 6.08.162.829 I slot print_timing: id 0 | task 9178 | total time = 3192.07 ms / 483 tokens 6.08.162.830 I slot print_timing: id 0 | task 9178 | graphs reused = 8645 6.08.162.831 I slot print_timing: id 0 | task 9178 | graph reallocs = 0 / 0 (same size) / (changed size) 6.08.164.304 I slot release: id 0 | task 9178 | stop processing: n_tokens = 514, truncated = 0 6.08.172.174 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 514, t_last = 386266369848 6.08.172.207 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 457.937 MiB) 6.09.147.784 I slot launch_slot_: id 0 | task 9298 | processing task, is_child = 0 6.13.161.095 I slot print_timing: id 0 | task 9298 | n_gen = 151, tg = 49.98 t/s, tg_3s = 50.31 t/s 6.16.171.179 I slot print_timing: id 0 | task 9298 | n_gen = 302, tg = 50.07 t/s, tg_3s = 50.16 t/s 6.17.510.884 I slot print_timing: id 0 | task 9298 | prompt eval time = 1011.85 ms / 462 tokens ( 2.19 ms per token, 456.59 tokens per second) 6.17.510.887 I slot print_timing: id 0 | task 9298 | eval time = 7351.23 ms / 369 tokens ( 19.98 ms per token, 50.06 tokens per second) 6.17.510.888 I slot print_timing: id 0 | task 9298 | total time = 8363.08 ms / 831 tokens 6.17.510.889 I slot print_timing: id 0 | task 9298 | graphs reused = 9010 6.17.510.890 I slot print_timing: id 0 | task 9298 | graph reallocs = 0 / 0 (same size) / (changed size) 6.17.510.947 I slot release: id 0 | task 9298 | stop processing: n_tokens = 862, truncated = 0 6.17.519.691 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 862, t_last = 386275716490 6.18.819.435 I slot launch_slot_: id 0 | task 9670 | processing task, is_child = 0 6.22.483.883 I slot print_timing: id 0 | task 9670 | prompt eval time = 913.46 ms / 396 tokens ( 2.31 ms per token, 433.52 tokens per second) 6.22.483.886 I slot print_timing: id 0 | task 9670 | eval time = 2750.98 ms / 139 tokens ( 19.93 ms per token, 50.16 tokens per second) 6.22.483.887 I slot print_timing: id 0 | task 9670 | total time = 3664.43 ms / 535 tokens 6.22.483.887 I slot print_timing: id 0 | task 9670 | graphs reused = 9146 6.22.483.888 I slot print_timing: id 0 | task 9670 | graph reallocs = 0 / 0 (same size) / (changed size) 6.22.483.949 I slot release: id 0 | task 9670 | stop processing: n_tokens = 566, truncated = 0 6.22.494.811 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 566, t_last = 386280689492 6.22.494.852 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.735 MiB) 6.23.651.856 I slot launch_slot_: id 0 | task 9812 | processing task, is_child = 0 6.27.712.400 I slot print_timing: id 0 | task 9812 | n_gen = 152, tg = 50.11 t/s, tg_3s = 50.44 t/s 6.27.891.502 I slot print_timing: id 0 | task 9812 | prompt eval time = 1047.12 ms / 458 tokens ( 2.29 ms per token, 437.39 tokens per second) 6.27.891.505 I slot print_timing: id 0 | task 9812 | eval time = 3192.51 ms / 161 tokens ( 19.95 ms per token, 50.12 tokens per second) 6.27.891.506 I slot print_timing: id 0 | task 9812 | total time = 4239.63 ms / 619 tokens 6.27.891.507 I slot print_timing: id 0 | task 9812 | graphs reused = 9304 6.27.891.507 I slot print_timing: id 0 | task 9812 | graph reallocs = 0 / 0 (same size) / (changed size) 6.27.892.670 I slot release: id 0 | task 9812 | stop processing: n_tokens = 650, truncated = 0 6.27.900.407 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 650, t_last = 386286098214 6.27.900.447 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.048 MiB) 6.28.816.302 I slot launch_slot_: id 0 | task 9976 | processing task, is_child = 0 6.32.847.837 I slot print_timing: id 0 | task 9976 | n_gen = 152, tg = 50.08 t/s, tg_3s = 50.41 t/s 6.35.858.388 I slot print_timing: id 0 | task 9976 | n_gen = 303, tg = 50.12 t/s, tg_3s = 50.16 t/s 6.38.066.460 I slot print_timing: id 0 | task 9976 | prompt eval time = 1016.45 ms / 458 tokens ( 2.22 ms per token, 450.59 tokens per second) 6.38.066.465 I slot print_timing: id 0 | task 9976 | eval time = 8233.70 ms / 414 tokens ( 19.94 ms per token, 50.16 tokens per second) 6.38.066.466 I slot print_timing: id 0 | task 9976 | total time = 9250.14 ms / 872 tokens 6.38.066.467 I slot print_timing: id 0 | task 9976 | graphs reused = 9714 6.38.066.467 I slot print_timing: id 0 | task 9976 | graph reallocs = 0 / 0 (same size) / (changed size) 6.38.066.520 I slot release: id 0 | task 9976 | stop processing: n_tokens = 903, truncated = 0 6.38.076.257 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 903, t_last = 386296272063 6.38.076.313 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.048 MiB) 6.39.073.903 I slot launch_slot_: id 0 | task 10393 | processing task, is_child = 0 6.43.088.825 I slot print_timing: id 0 | task 10393 | n_gen = 152, tg = 50.12 t/s, tg_3s = 50.45 t/s 6.46.100.753 I slot print_timing: id 0 | task 10393 | n_gen = 303, tg = 50.13 t/s, tg_3s = 50.13 t/s 6.49.103.782 I slot print_timing: id 0 | task 10393 | n_gen = 454, tg = 50.18 t/s, tg_3s = 50.28 t/s 6.49.442.605 I slot print_timing: id 0 | task 10393 | prompt eval time = 1002.28 ms / 452 tokens ( 2.22 ms per token, 450.97 tokens per second) 6.49.442.610 I slot print_timing: id 0 | task 10393 | eval time = 9366.41 ms / 471 tokens ( 19.93 ms per token, 50.18 tokens per second) 6.49.442.611 I slot print_timing: id 0 | task 10393 | total time = 10368.69 ms / 923 tokens 6.49.442.612 I slot print_timing: id 0 | task 10393 | graphs reused = 10181 6.49.442.612 I slot print_timing: id 0 | task 10393 | graph reallocs = 0 / 0 (same size) / (changed size) 6.49.442.647 I slot release: id 0 | task 10393 | stop processing: n_tokens = 954, truncated = 0 6.49.450.939 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 954, t_last = 386307648190 6.49.450.991 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.090 MiB) 6.50.551.777 I slot launch_slot_: id 0 | task 10867 | processing task, is_child = 0 6.54.493.093 I slot print_timing: id 0 | task 10867 | n_gen = 152, tg = 50.17 t/s, tg_3s = 50.50 t/s 6.56.303.893 I slot print_timing: id 0 | task 10867 | prompt eval time = 931.40 ms / 404 tokens ( 2.31 ms per token, 433.75 tokens per second) 6.56.303.896 I slot print_timing: id 0 | task 10867 | eval time = 4820.17 ms / 243 tokens ( 19.92 ms per token, 50.21 tokens per second) 6.56.303.897 I slot print_timing: id 0 | task 10867 | total time = 5751.57 ms / 647 tokens 6.56.303.898 I slot print_timing: id 0 | task 10867 | graphs reused = 10421 6.56.303.898 I slot print_timing: id 0 | task 10867 | graph reallocs = 0 / 0 (same size) / (changed size) 6.56.303.945 I slot release: id 0 | task 10867 | stop processing: n_tokens = 678, truncated = 0 6.56.310.666 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 678, t_last = 386314509488 6.56.310.710 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.064 MiB) 6.57.168.316 I slot launch_slot_: id 0 | task 11113 | processing task, is_child = 0 7.00.104.755 I slot print_timing: id 0 | task 11113 | prompt eval time = 847.83 ms / 345 tokens ( 2.46 ms per token, 406.92 tokens per second) 7.00.104.760 I slot print_timing: id 0 | task 11113 | eval time = 2088.59 ms / 106 tokens ( 19.89 ms per token, 50.27 tokens per second) 7.00.104.761 I slot print_timing: id 0 | task 11113 | total time = 2936.42 ms / 451 tokens 7.00.104.762 I slot print_timing: id 0 | task 11113 | graphs reused = 10525 7.00.104.762 I slot print_timing: id 0 | task 11113 | graph reallocs = 0 / 0 (same size) / (changed size) 7.00.106.061 I slot release: id 0 | task 11113 | stop processing: n_tokens = 482, truncated = 0 7.00.112.935 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 482, t_last = 386318311605 7.00.112.976 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 389.140 MiB) 7.01.295.751 I slot launch_slot_: id 0 | task 11222 | processing task, is_child = 0 7.05.327.691 I slot print_timing: id 0 | task 11222 | n_gen = 152, tg = 50.15 t/s, tg_3s = 50.48 t/s 7.06.619.134 I slot print_timing: id 0 | task 11222 | prompt eval time = 1021.01 ms / 430 tokens ( 2.37 ms per token, 421.15 tokens per second) 7.06.619.139 I slot print_timing: id 0 | task 11222 | eval time = 4302.35 ms / 217 tokens ( 19.92 ms per token, 50.21 tokens per second) 7.06.619.141 I slot print_timing: id 0 | task 11222 | total time = 5323.36 ms / 647 tokens 7.06.619.142 I slot print_timing: id 0 | task 11222 | graphs reused = 10739 7.06.619.142 I slot print_timing: id 0 | task 11222 | graph reallocs = 0 / 0 (same size) / (changed size) 7.06.619.261 I slot release: id 0 | task 11222 | stop processing: n_tokens = 678, truncated = 0 7.06.627.687 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 678, t_last = 386324824805 7.06.627.727 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 391.467 MiB) 7.07.535.502 I slot launch_slot_: id 0 | task 11442 | processing task, is_child = 0 7.10.025.733 I slot print_timing: id 0 | task 11442 | prompt eval time = 801.18 ms / 316 tokens ( 2.54 ms per token, 394.42 tokens per second) 7.10.025.739 I slot print_timing: id 0 | task 11442 | eval time = 1689.04 ms / 85 tokens ( 20.11 ms per token, 49.73 tokens per second) 7.10.025.739 I slot print_timing: id 0 | task 11442 | total time = 2490.22 ms / 401 tokens 7.10.025.740 I slot print_timing: id 0 | task 11442 | graphs reused = 10822 7.10.025.741 I slot print_timing: id 0 | task 11442 | graph reallocs = 0 / 0 (same size) / (changed size) 7.10.025.798 I slot release: id 0 | task 11442 | stop processing: n_tokens = 432, truncated = 0 7.10.032.948 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 432, t_last = 386328231342 7.10.032.982 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 390.079 MiB) 7.11.287.708 I slot launch_slot_: id 0 | task 11530 | processing task, is_child = 0 7.14.265.033 I slot print_timing: id 0 | task 11530 | prompt eval time = 872.42 ms / 354 tokens ( 2.46 ms per token, 405.77 tokens per second) 7.14.265.040 I slot print_timing: id 0 | task 11530 | eval time = 2104.89 ms / 107 tokens ( 19.86 ms per token, 50.36 tokens per second) 7.14.265.040 I slot print_timing: id 0 | task 11530 | total time = 2977.31 ms / 461 tokens 7.14.265.041 I slot print_timing: id 0 | task 11530 | graphs reused = 10927 7.14.265.042 I slot print_timing: id 0 | task 11530 | graph reallocs = 0 / 0 (same size) / (changed size) 7.14.265.091 I slot release: id 0 | task 11530 | stop processing: n_tokens = 492, truncated = 0 7.14.272.562 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 492, t_last = 386332470634 7.14.272.595 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.615 MiB) 7.15.608.687 I slot launch_slot_: id 0 | task 11640 | processing task, is_child = 0 7.18.556.408 I slot print_timing: id 0 | task 11640 | prompt eval time = 989.28 ms / 438 tokens ( 2.26 ms per token, 442.75 tokens per second) 7.18.556.411 I slot print_timing: id 0 | task 11640 | eval time = 1958.42 ms / 98 tokens ( 20.19 ms per token, 49.53 tokens per second) 7.18.556.412 I slot print_timing: id 0 | task 11640 | total time = 2947.70 ms / 536 tokens 7.18.556.413 I slot print_timing: id 0 | task 11640 | graphs reused = 11022 7.18.556.414 I slot print_timing: id 0 | task 11640 | graph reallocs = 0 / 0 (same size) / (changed size) 7.18.556.483 I slot release: id 0 | task 11640 | stop processing: n_tokens = 567, truncated = 0 7.18.563.772 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 567, t_last = 386336762027 7.18.563.814 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.791 MiB) 7.19.434.187 I slot launch_slot_: id 0 | task 11741 | processing task, is_child = 0 7.21.810.833 I slot print_timing: id 0 | task 11741 | prompt eval time = 994.43 ms / 457 tokens ( 2.18 ms per token, 459.56 tokens per second) 7.21.810.839 I slot print_timing: id 0 | task 11741 | eval time = 1382.20 ms / 70 tokens ( 20.03 ms per token, 49.92 tokens per second) 7.21.810.840 I slot print_timing: id 0 | task 11741 | total time = 2376.63 ms / 527 tokens 7.21.810.841 I slot print_timing: id 0 | task 11741 | graphs reused = 11089 7.21.810.841 I slot print_timing: id 0 | task 11741 | graph reallocs = 0 / 0 (same size) / (changed size) 7.21.812.451 I slot release: id 0 | task 11741 | stop processing: n_tokens = 558, truncated = 0 7.21.820.974 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 386340017995 7.21.821.011 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.651 MiB) 7.22.853.413 I slot launch_slot_: id 0 | task 11814 | processing task, is_child = 0 7.25.813.038 I slot print_timing: id 0 | task 11814 | prompt eval time = 1021.40 ms / 473 tokens ( 2.16 ms per token, 463.09 tokens per second) 7.25.813.041 I slot print_timing: id 0 | task 11814 | eval time = 1938.19 ms / 98 tokens ( 19.98 ms per token, 50.05 tokens per second) 7.25.813.042 I slot print_timing: id 0 | task 11814 | total time = 2959.60 ms / 571 tokens 7.25.813.043 I slot print_timing: id 0 | task 11814 | graphs reused = 11184 7.25.813.043 I slot print_timing: id 0 | task 11814 | graph reallocs = 0 / 0 (same size) / (changed size) 7.25.814.088 I slot release: id 0 | task 11814 | stop processing: n_tokens = 602, truncated = 0 7.25.823.162 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 602, t_last = 386344019632 7.25.823.198 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 390.137 MiB) 7.26.771.925 I slot launch_slot_: id 0 | task 11915 | processing task, is_child = 0 7.28.315.993 I slot print_timing: id 0 | task 11915 | prompt eval time = 1016.93 ms / 476 tokens ( 2.14 ms per token, 468.08 tokens per second) 7.28.315.999 I slot print_timing: id 0 | task 11915 | eval time = 527.12 ms / 27 tokens ( 20.27 ms per token, 49.32 tokens per second) 7.28.315.999 I slot print_timing: id 0 | task 11915 | total time = 1544.05 ms / 503 tokens 7.28.316.000 I slot print_timing: id 0 | task 11915 | graphs reused = 11208 7.28.316.001 I slot print_timing: id 0 | task 11915 | graph reallocs = 0 / 0 (same size) / (changed size) 7.28.317.877 I slot release: id 0 | task 11915 | stop processing: n_tokens = 534, truncated = 0 7.28.326.168 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 534, t_last = 386346523421 7.28.326.203 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.925 MiB) 7.29.543.184 I slot launch_slot_: id 0 | task 11945 | processing task, is_child = 0 7.32.695.568 I slot print_timing: id 0 | task 11945 | prompt eval time = 1035.54 ms / 466 tokens ( 2.22 ms per token, 450.01 tokens per second) 7.32.695.571 I slot print_timing: id 0 | task 11945 | eval time = 2116.83 ms / 107 tokens ( 19.97 ms per token, 50.07 tokens per second) 7.32.695.572 I slot print_timing: id 0 | task 11945 | total time = 3152.37 ms / 573 tokens 7.32.695.572 I slot print_timing: id 0 | task 11945 | graphs reused = 11312 7.32.695.573 I slot print_timing: id 0 | task 11945 | graph reallocs = 0 / 0 (same size) / (changed size) 7.32.697.096 I slot release: id 0 | task 11945 | stop processing: n_tokens = 604, truncated = 0 7.32.704.706 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 604, t_last = 386350902640 7.32.704.745 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 391.838 MiB) 7.33.526.215 I slot launch_slot_: id 0 | task 12055 | processing task, is_child = 0 7.36.261.371 I slot print_timing: id 0 | task 12055 | prompt eval time = 921.28 ms / 415 tokens ( 2.22 ms per token, 450.46 tokens per second) 7.36.261.377 I slot print_timing: id 0 | task 12055 | eval time = 1813.86 ms / 91 tokens ( 20.15 ms per token, 49.62 tokens per second) 7.36.261.378 I slot print_timing: id 0 | task 12055 | total time = 2735.14 ms / 506 tokens 7.36.261.379 I slot print_timing: id 0 | task 12055 | graphs reused = 11400 7.36.261.379 I slot print_timing: id 0 | task 12055 | graph reallocs = 0 / 0 (same size) / (changed size) 7.36.261.426 I slot release: id 0 | task 12055 | stop processing: n_tokens = 537, truncated = 0 7.36.271.249 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 537, t_last = 386354466969 7.36.271.284 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.774 MiB) 7.37.765.734 I slot launch_slot_: id 0 | task 12149 | processing task, is_child = 0 7.39.850.292 I slot print_timing: id 0 | task 12149 | prompt eval time = 826.02 ms / 352 tokens ( 2.35 ms per token, 426.14 tokens per second) 7.39.850.298 I slot print_timing: id 0 | task 12149 | eval time = 1258.51 ms / 64 tokens ( 19.98 ms per token, 50.06 tokens per second) 7.39.850.300 I slot print_timing: id 0 | task 12149 | total time = 2084.53 ms / 416 tokens 7.39.850.300 I slot print_timing: id 0 | task 12149 | graphs reused = 11462 7.39.850.301 I slot print_timing: id 0 | task 12149 | graph reallocs = 0 / 0 (same size) / (changed size) 7.39.851.848 I slot release: id 0 | task 12149 | stop processing: n_tokens = 447, truncated = 0 7.39.861.833 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 386358057392 7.39.861.864 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 390.861 MiB) 7.40.732.880 I slot launch_slot_: id 0 | task 12216 | processing task, is_child = 0 7.44.711.272 I slot print_timing: id 0 | task 12216 | prompt eval time = 1348.38 ms / 550 tokens ( 2.45 ms per token, 407.90 tokens per second) 7.44.711.275 I slot print_timing: id 0 | task 12216 | eval time = 2630.00 ms / 133 tokens ( 19.92 ms per token, 50.19 tokens per second) 7.44.711.275 I slot print_timing: id 0 | task 12216 | total time = 3978.38 ms / 683 tokens 7.44.711.276 I slot print_timing: id 0 | task 12216 | graphs reused = 11593 7.44.711.277 I slot print_timing: id 0 | task 12216 | graph reallocs = 0 / 0 (same size) / (changed size) 7.44.711.359 I slot release: id 0 | task 12216 | stop processing: n_tokens = 714, truncated = 0 7.44.724.854 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 714, t_last = 386362916902 7.44.724.895 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.827 MiB) 7.44.724.919 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.754 MiB) 7.45.951.172 I slot launch_slot_: id 0 | task 12353 | processing task, is_child = 0 7.50.597.591 I slot print_timing: id 0 | task 12353 | n_gen = 152, tg = 50.00 t/s, tg_3s = 50.33 t/s 7.53.602.481 I slot print_timing: id 0 | task 12353 | n_gen = 302, tg = 49.96 t/s, tg_3s = 49.92 t/s 7.56.605.506 I slot print_timing: id 0 | task 12353 | n_gen = 452, tg = 49.96 t/s, tg_3s = 49.95 t/s 7.59.614.464 I slot print_timing: id 0 | task 12353 | n_gen = 602, tg = 49.93 t/s, tg_3s = 49.85 t/s 8.01.165.134 I slot print_timing: id 0 | task 12353 | prompt eval time = 1626.63 ms / 772 tokens ( 2.11 ms per token, 474.60 tokens per second) 8.01.165.140 I slot print_timing: id 0 | task 12353 | eval time = 13587.32 ms / 679 tokens ( 20.04 ms per token, 49.90 tokens per second) 8.01.165.141 I slot print_timing: id 0 | task 12353 | total time = 15213.95 ms / 1451 tokens 8.01.165.141 I slot print_timing: id 0 | task 12353 | graphs reused = 12268 8.01.165.142 I slot print_timing: id 0 | task 12353 | graph reallocs = 0 / 0 (same size) / (changed size) 8.01.166.144 I slot release: id 0 | task 12353 | stop processing: n_tokens = 1482, truncated = 0 8.01.178.178 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1482, t_last = 386379371689 8.01.178.254 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 389.238 MiB) 8.02.259.097 I slot launch_slot_: id 0 | task 13036 | processing task, is_child = 0 8.06.778.906 I slot print_timing: id 0 | task 13036 | n_gen = 152, tg = 50.11 t/s, tg_3s = 50.44 t/s 8.07.356.372 I slot print_timing: id 0 | task 13036 | prompt eval time = 1506.32 ms / 683 tokens ( 2.21 ms per token, 453.42 tokens per second) 8.07.356.378 I slot print_timing: id 0 | task 13036 | eval time = 3590.94 ms / 181 tokens ( 19.95 ms per token, 50.13 tokens per second) 8.07.356.379 I slot print_timing: id 0 | task 13036 | total time = 5097.26 ms / 864 tokens 8.07.356.379 I slot print_timing: id 0 | task 13036 | graphs reused = 12446 8.07.356.380 I slot print_timing: id 0 | task 13036 | graph reallocs = 0 / 0 (same size) / (changed size) 8.07.357.468 I slot release: id 0 | task 13036 | stop processing: n_tokens = 895, truncated = 0 8.07.368.113 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 895, t_last = 386385563012 8.07.368.162 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.930 MiB) 8.08.588.757 I slot launch_slot_: id 0 | task 13221 | processing task, is_child = 0 8.12.944.056 I slot print_timing: id 0 | task 13221 | n_gen = 152, tg = 50.13 t/s, tg_3s = 50.46 t/s 8.15.953.435 I slot print_timing: id 0 | task 13221 | n_gen = 303, tg = 50.15 t/s, tg_3s = 50.18 t/s 8.16.929.203 I slot print_timing: id 0 | task 13221 | prompt eval time = 1343.18 ms / 579 tokens ( 2.32 ms per token, 431.07 tokens per second) 8.16.929.207 I slot print_timing: id 0 | task 13221 | eval time = 6997.26 ms / 352 tokens ( 19.94 ms per token, 50.16 tokens per second) 8.16.929.208 I slot print_timing: id 0 | task 13221 | total time = 8340.43 ms / 931 tokens 8.16.929.209 I slot print_timing: id 0 | task 13221 | graphs reused = 12795 8.16.929.209 I slot print_timing: id 0 | task 13221 | graph reallocs = 0 / 0 (same size) / (changed size) 8.16.930.985 I slot release: id 0 | task 13221 | stop processing: n_tokens = 962, truncated = 0 8.16.938.637 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 962, t_last = 386395136529 8.16.938.689 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 393.735 MiB) 8.18.326.544 I slot launch_slot_: id 0 | task 13577 | processing task, is_child = 0 8.21.502.399 I slot print_timing: id 0 | task 13577 | prompt eval time = 1082.91 ms / 500 tokens ( 2.17 ms per token, 461.72 tokens per second) 8.21.502.405 I slot print_timing: id 0 | task 13577 | eval time = 2092.92 ms / 106 tokens ( 19.93 ms per token, 50.17 tokens per second) 8.21.502.406 I slot print_timing: id 0 | task 13577 | total time = 3175.84 ms / 606 tokens 8.21.502.406 I slot print_timing: id 0 | task 13577 | graphs reused = 12899 8.21.502.407 I slot print_timing: id 0 | task 13577 | graph reallocs = 0 / 0 (same size) / (changed size) 8.21.503.458 I slot release: id 0 | task 13577 | stop processing: n_tokens = 637, truncated = 0 8.21.515.823 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 386399709002 8.21.515.863 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.947 MiB) 8.22.480.141 I slot launch_slot_: id 0 | task 13686 | processing task, is_child = 0 8.27.131.907 I slot print_timing: id 0 | task 13686 | n_gen = 152, tg = 50.13 t/s, tg_3s = 50.46 t/s 8.30.149.034 I slot print_timing: id 0 | task 13686 | n_gen = 303, tg = 50.09 t/s, tg_3s = 50.05 t/s 8.33.090.927 I slot print_timing: id 0 | task 13686 | prompt eval time = 1639.68 ms / 776 tokens ( 2.11 ms per token, 473.26 tokens per second) 8.33.090.933 I slot print_timing: id 0 | task 13686 | eval time = 8971.09 ms / 450 tokens ( 19.98 ms per token, 50.05 tokens per second) 8.33.090.934 I slot print_timing: id 0 | task 13686 | total time = 10610.77 ms / 1226 tokens 8.33.090.934 I slot print_timing: id 0 | task 13686 | graphs reused = 13346 8.33.090.935 I slot print_timing: id 0 | task 13686 | graph reallocs = 0 / 0 (same size) / (changed size) 8.33.091.002 I slot release: id 0 | task 13686 | stop processing: n_tokens = 1257, truncated = 0 8.33.100.359 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1257, t_last = 386411296545 8.33.100.424 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 389.590 MiB) 8.34.341.162 I slot launch_slot_: id 0 | task 14140 | processing task, is_child = 0 8.38.423.523 I slot print_timing: id 0 | task 14140 | n_gen = 152, tg = 50.16 t/s, tg_3s = 50.49 t/s 8.39.318.176 I slot print_timing: id 0 | task 14140 | prompt eval time = 1071.81 ms / 504 tokens ( 2.13 ms per token, 470.23 tokens per second) 8.39.318.183 I slot print_timing: id 0 | task 14140 | eval time = 3905.19 ms / 197 tokens ( 19.92 ms per token, 50.19 tokens per second) 8.39.318.184 I slot print_timing: id 0 | task 14140 | total time = 4977.00 ms / 701 tokens 8.39.318.185 I slot print_timing: id 0 | task 14140 | graphs reused = 13541 8.39.318.189 I slot print_timing: id 0 | task 14140 | graph reallocs = 0 / 0 (same size) / (changed size) 8.39.318.255 I slot release: id 0 | task 14140 | stop processing: n_tokens = 732, truncated = 0 8.39.326.719 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 732, t_last = 386417523798 8.39.326.763 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 394.537 MiB) 8.40.237.581 I slot launch_slot_: id 0 | task 14340 | processing task, is_child = 0 8.44.683.429 I slot print_timing: id 0 | task 14340 | n_gen = 152, tg = 50.14 t/s, tg_3s = 50.47 t/s 8.47.691.986 I slot print_timing: id 0 | task 14340 | n_gen = 303, tg = 50.16 t/s, tg_3s = 50.19 t/s 8.50.511.389 I slot print_timing: id 0 | task 14340 | prompt eval time = 1434.11 ms / 633 tokens ( 2.27 ms per token, 441.39 tokens per second) 8.50.511.395 I slot print_timing: id 0 | task 14340 | eval time = 8839.68 ms / 444 tokens ( 19.95 ms per token, 50.11 tokens per second) 8.50.511.396 I slot print_timing: id 0 | task 14340 | total time = 10273.79 ms / 1077 tokens 8.50.511.396 I slot print_timing: id 0 | task 14340 | graphs reused = 13981 8.50.511.397 I slot print_timing: id 0 | task 14340 | graph reallocs = 0 / 0 (same size) / (changed size) 8.50.511.468 I slot release: id 0 | task 14340 | stop processing: n_tokens = 1108, truncated = 0 8.50.519.395 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1108, t_last = 386428717011 8.50.519.804 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 395.534 MiB) 8.50.519.826 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 390.137 MiB) 8.51.961.561 I slot launch_slot_: id 0 | task 14788 | processing task, is_child = 0 8.54.179.955 I slot print_timing: id 0 | task 14788 | prompt eval time = 939.65 ms / 395 tokens ( 2.38 ms per token, 420.37 tokens per second) 8.54.179.962 I slot print_timing: id 0 | task 14788 | eval time = 1278.70 ms / 65 tokens ( 19.98 ms per token, 50.05 tokens per second) 8.54.179.963 I slot print_timing: id 0 | task 14788 | total time = 2218.36 ms / 460 tokens 8.54.179.963 I slot print_timing: id 0 | task 14788 | graphs reused = 14044 8.54.179.964 I slot print_timing: id 0 | task 14788 | graph reallocs = 0 / 0 (same size) / (changed size) 8.54.181.454 I slot release: id 0 | task 14788 | stop processing: n_tokens = 491, truncated = 0 8.54.193.607 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 491, t_last = 386432386998 8.54.193.640 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.305 MiB) 8.55.509.741 I slot launch_slot_: id 0 | task 14856 | processing task, is_child = 0 8.59.896.205 I slot print_timing: id 0 | task 14856 | n_gen = 152, tg = 50.05 t/s, tg_3s = 50.38 t/s 9.01.033.293 I slot print_timing: id 0 | task 14856 | prompt eval time = 1369.32 ms / 584 tokens ( 2.34 ms per token, 426.49 tokens per second) 9.01.033.299 I slot print_timing: id 0 | task 14856 | eval time = 4154.21 ms / 209 tokens ( 19.97 ms per token, 50.07 tokens per second) 9.01.033.300 I slot print_timing: id 0 | task 14856 | total time = 5523.53 ms / 793 tokens 9.01.033.301 I slot print_timing: id 0 | task 14856 | graphs reused = 14250 9.01.033.310 I slot print_timing: id 0 | task 14856 | graph reallocs = 0 / 0 (same size) / (changed size) 9.01.034.768 I slot release: id 0 | task 14856 | stop processing: n_tokens = 824, truncated = 0 9.01.045.694 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 824, t_last = 386439240312 9.01.045.740 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 390.137 MiB) 9.02.144.876 I slot launch_slot_: id 0 | task 15069 | processing task, is_child = 0 9.06.699.261 I slot print_timing: id 0 | task 15069 | n_gen = 151, tg = 49.73 t/s, tg_3s = 50.06 t/s 9.08.312.076 I slot print_timing: id 0 | task 15069 | prompt eval time = 1537.97 ms / 695 tokens ( 2.21 ms per token, 451.90 tokens per second) 9.08.312.082 I slot print_timing: id 0 | task 15069 | eval time = 4629.22 ms / 232 tokens ( 20.04 ms per token, 49.90 tokens per second) 9.08.312.083 I slot print_timing: id 0 | task 15069 | total time = 6167.18 ms / 927 tokens 9.08.312.084 I slot print_timing: id 0 | task 15069 | graphs reused = 14479 9.08.312.085 I slot print_timing: id 0 | task 15069 | graph reallocs = 0 / 0 (same size) / (changed size) 9.08.312.139 I slot release: id 0 | task 15069 | stop processing: n_tokens = 958, truncated = 0 9.08.324.991 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 958, t_last = 386446517682 9.08.325.040 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 385.327 MiB) 9.09.563.489 I slot launch_slot_: id 0 | task 15305 | processing task, is_child = 0 9.14.207.377 I slot print_timing: id 0 | task 15305 | n_gen = 152, tg = 50.01 t/s, tg_3s = 50.34 t/s 9.14.985.497 I slot print_timing: id 0 | task 15305 | prompt eval time = 1624.66 ms / 769 tokens ( 2.11 ms per token, 473.33 tokens per second) 9.14.985.503 I slot print_timing: id 0 | task 15305 | eval time = 3797.33 ms / 191 tokens ( 19.99 ms per token, 50.04 tokens per second) 9.14.985.504 I slot print_timing: id 0 | task 15305 | total time = 5421.99 ms / 960 tokens 9.14.985.504 I slot print_timing: id 0 | task 15305 | graphs reused = 14668 9.14.985.505 I slot print_timing: id 0 | task 15305 | graph reallocs = 0 / 0 (same size) / (changed size) 9.14.986.550 I slot release: id 0 | task 15305 | stop processing: n_tokens = 991, truncated = 0 9.14.996.425 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 991, t_last = 386453192094 9.14.996.478 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.500 MiB) 9.16.120.484 I slot launch_slot_: id 0 | task 15500 | processing task, is_child = 0 9.19.894.760 I slot print_timing: id 0 | task 15500 | prompt eval time = 1298.15 ms / 576 tokens ( 2.25 ms per token, 443.71 tokens per second) 9.19.894.766 I slot print_timing: id 0 | task 15500 | eval time = 2476.11 ms / 124 tokens ( 20.13 ms per token, 49.67 tokens per second) 9.19.894.766 I slot print_timing: id 0 | task 15500 | total time = 3774.26 ms / 700 tokens 9.19.894.767 I slot print_timing: id 0 | task 15500 | graphs reused = 14790 9.19.894.768 I slot print_timing: id 0 | task 15500 | graph reallocs = 0 / 0 (same size) / (changed size) 9.19.895.883 I slot release: id 0 | task 15500 | stop processing: n_tokens = 731, truncated = 0 9.19.906.007 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 731, t_last = 386458101427 9.19.906.050 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.967 MiB) 9.21.148.030 I slot launch_slot_: id 0 | task 15628 | processing task, is_child = 0 9.25.628.238 I slot print_timing: id 0 | task 15628 | n_gen = 152, tg = 50.01 t/s, tg_3s = 50.34 t/s 9.28.081.349 I slot print_timing: id 0 | task 15628 | prompt eval time = 1460.79 ms / 655 tokens ( 2.23 ms per token, 448.39 tokens per second) 9.28.081.352 I slot print_timing: id 0 | task 15628 | eval time = 5472.51 ms / 275 tokens ( 19.97 ms per token, 50.07 tokens per second) 9.28.081.353 I slot print_timing: id 0 | task 15628 | total time = 6933.30 ms / 930 tokens 9.28.081.354 I slot print_timing: id 0 | task 15628 | graphs reused = 15062 9.28.081.354 I slot print_timing: id 0 | task 15628 | graph reallocs = 0 / 0 (same size) / (changed size) 9.28.081.424 I slot release: id 0 | task 15628 | stop processing: n_tokens = 961, truncated = 0 9.28.093.140 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 961, t_last = 386466286967 9.28.093.192 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.791 MiB) 9.29.161.959 I slot launch_slot_: id 0 | task 15907 | processing task, is_child = 0 9.32.982.572 I slot print_timing: id 0 | task 15907 | prompt eval time = 1429.61 ms / 621 tokens ( 2.30 ms per token, 434.39 tokens per second) 9.32.982.575 I slot print_timing: id 0 | task 15907 | eval time = 2390.99 ms / 121 tokens ( 19.92 ms per token, 50.19 tokens per second) 9.32.982.576 I slot print_timing: id 0 | task 15907 | total time = 3820.59 ms / 742 tokens 9.32.983.593 I slot print_timing: id 0 | task 15907 | graphs reused = 15180 9.32.983.596 I slot print_timing: id 0 | task 15907 | graph reallocs = 0 / 0 (same size) / (changed size) 9.32.984.543 I slot release: id 0 | task 15907 | stop processing: n_tokens = 773, truncated = 0 9.32.993.491 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 773, t_last = 386471190087 9.32.993.539 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.651 MiB) 9.32.993.556 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.321 MiB) 9.34.391.243 I slot launch_slot_: id 0 | task 16032 | processing task, is_child = 0 9.39.043.990 I slot print_timing: id 0 | task 16032 | n_gen = 152, tg = 50.00 t/s, tg_3s = 50.33 t/s 9.42.049.193 I slot print_timing: id 0 | task 16032 | n_gen = 302, tg = 49.96 t/s, tg_3s = 49.91 t/s 9.45.052.626 I slot print_timing: id 0 | task 16032 | n_gen = 458, tg = 50.62 t/s, tg_3s = 51.94 t/s 9.48.064.540 I slot print_timing: id 0 | task 16032 | n_gen = 614, tg = 50.91 t/s, tg_3s = 51.79 t/s 9.49.834.221 I slot print_timing: id 0 | task 16032 | prompt eval time = 1632.82 ms / 767 tokens ( 2.13 ms per token, 469.74 tokens per second) 9.49.834.226 I slot print_timing: id 0 | task 16032 | eval time = 13810.14 ms / 706 tokens ( 19.59 ms per token, 51.05 tokens per second) 9.49.834.226 I slot print_timing: id 0 | task 16032 | total time = 15442.96 ms / 1473 tokens 9.49.834.227 I slot print_timing: id 0 | task 16032 | graphs reused = 15882 9.49.834.227 I slot print_timing: id 0 | task 16032 | graph reallocs = 0 / 0 (same size) / (changed size) 9.49.834.793 I slot release: id 0 | task 16032 | stop processing: n_tokens = 1504, truncated = 0 9.49.853.816 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1504, t_last = 386488040337 9.49.853.889 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.690 MiB) 9.51.206.723 I slot launch_slot_: id 0 | task 16742 | processing task, is_child = 0 9.55.962.945 I slot print_timing: id 0 | task 16742 | n_gen = 158, tg = 52.13 t/s, tg_3s = 52.46 t/s 9.56.822.729 I slot print_timing: id 0 | task 16742 | prompt eval time = 1744.47 ms / 864 tokens ( 2.02 ms per token, 495.28 tokens per second) 9.56.822.731 I slot print_timing: id 0 | task 16742 | eval time = 3871.52 ms / 203 tokens ( 19.17 ms per token, 52.18 tokens per second) 9.56.822.732 I slot print_timing: id 0 | task 16742 | total time = 5615.99 ms / 1067 tokens 9.56.822.732 I slot print_timing: id 0 | task 16742 | graphs reused = 16082 9.56.822.733 I slot print_timing: id 0 | task 16742 | graph reallocs = 0 / 0 (same size) / (changed size) 9.56.823.115 I slot release: id 0 | task 16742 | stop processing: n_tokens = 1098, truncated = 0 9.56.833.749 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1098, t_last = 386495028658 9.56.833.802 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.380 MiB) 9.57.990.031 I slot launch_slot_: id 0 | task 16949 | processing task, is_child = 0 10.01.858.019 I slot print_timing: id 0 | task 16949 | prompt eval time = 1427.65 ms / 646 tokens ( 2.21 ms per token, 452.49 tokens per second) 10.01.858.024 I slot print_timing: id 0 | task 16949 | eval time = 2440.32 ms / 129 tokens ( 19.07 ms per token, 52.45 tokens per second) 10.01.858.025 I slot print_timing: id 0 | task 16949 | total time = 3867.97 ms / 775 tokens 10.01.858.025 I slot print_timing: id 0 | task 16949 | graphs reused = 16208 10.01.858.026 I slot print_timing: id 0 | task 16949 | graph reallocs = 0 / 0 (same size) / (changed size) 10.01.858.461 I slot release: id 0 | task 16949 | stop processing: n_tokens = 806, truncated = 0 10.01.870.372 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 806, t_last = 386500064005 10.01.870.409 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 385.620 MiB) 10.02.877.312 I slot launch_slot_: id 0 | task 17082 | processing task, is_child = 0 10.07.436.165 I slot print_timing: id 0 | task 17082 | n_gen = 158, tg = 52.07 t/s, tg_3s = 52.40 t/s 10.08.669.046 I slot print_timing: id 0 | task 17082 | prompt eval time = 1543.57 ms / 720 tokens ( 2.14 ms per token, 466.45 tokens per second) 10.08.669.051 I slot print_timing: id 0 | task 17082 | eval time = 4248.15 ms / 222 tokens ( 19.22 ms per token, 52.02 tokens per second) 10.08.669.052 I slot print_timing: id 0 | task 17082 | total time = 5791.72 ms / 942 tokens 10.08.669.052 I slot print_timing: id 0 | task 17082 | graphs reused = 16427 10.08.669.053 I slot print_timing: id 0 | task 17082 | graph reallocs = 0 / 0 (same size) / (changed size) 10.08.669.121 I slot release: id 0 | task 17082 | stop processing: n_tokens = 973, truncated = 0 10.08.676.082 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 973, t_last = 386506874664 10.08.676.129 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 453.654 MiB) 10.09.869.779 I slot launch_slot_: id 0 | task 17308 | processing task, is_child = 0 10.13.944.918 I slot print_timing: id 0 | task 17308 | n_gen = 159, tg = 52.60 t/s, tg_3s = 52.93 t/s 10.14.991.648 I slot print_timing: id 0 | task 17308 | prompt eval time = 1071.42 ms / 509 tokens ( 2.10 ms per token, 475.07 tokens per second) 10.14.991.651 I slot print_timing: id 0 | task 17308 | eval time = 4050.43 ms / 214 tokens ( 19.02 ms per token, 52.59 tokens per second) 10.14.991.651 I slot print_timing: id 0 | task 17308 | total time = 5121.85 ms / 723 tokens 10.14.991.652 I slot print_timing: id 0 | task 17308 | graphs reused = 16639 10.14.991.652 I slot print_timing: id 0 | task 17308 | graph reallocs = 0 / 0 (same size) / (changed size) 10.14.991.707 I slot release: id 0 | task 17308 | stop processing: n_tokens = 754, truncated = 0 10.14.999.545 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 754, t_last = 386513197250 10.14.999.584 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 468.672 MiB) 10.15.941.050 I slot launch_slot_: id 0 | task 17525 | processing task, is_child = 0 10.20.288.860 I slot print_timing: id 0 | task 17525 | n_gen = 159, tg = 52.46 t/s, tg_3s = 52.79 t/s 10.21.868.381 I slot print_timing: id 0 | task 17525 | prompt eval time = 1336.13 ms / 581 tokens ( 2.30 ms per token, 434.84 tokens per second) 10.21.868.386 I slot print_timing: id 0 | task 17525 | eval time = 4591.19 ms / 242 tokens ( 19.05 ms per token, 52.49 tokens per second) 10.21.868.386 I slot print_timing: id 0 | task 17525 | total time = 5927.32 ms / 823 tokens 10.21.868.387 I slot print_timing: id 0 | task 17525 | graphs reused = 16878 10.21.868.387 I slot print_timing: id 0 | task 17525 | graph reallocs = 0 / 0 (same size) / (changed size) 10.21.868.480 I slot release: id 0 | task 17525 | stop processing: n_tokens = 854, truncated = 0 10.21.881.975 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 854, t_last = 386520074023 10.21.882.016 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 457.194 MiB) 10.23.048.197 I slot launch_slot_: id 0 | task 17771 | processing task, is_child = 0 10.27.886.529 I slot print_timing: id 0 | task 17771 | n_gen = 151, tg = 49.76 t/s, tg_3s = 50.09 t/s 10.30.894.262 I slot print_timing: id 0 | task 17771 | n_gen = 301, tg = 49.82 t/s, tg_3s = 49.87 t/s 10.33.903.998 I slot print_timing: id 0 | task 17771 | n_gen = 451, tg = 49.82 t/s, tg_3s = 49.84 t/s 10.34.325.756 I slot print_timing: id 0 | task 17771 | prompt eval time = 1823.85 ms / 925 tokens ( 1.97 ms per token, 507.17 tokens per second) 10.34.325.763 I slot print_timing: id 0 | task 17771 | eval time = 9453.69 ms / 472 tokens ( 20.07 ms per token, 49.82 tokens per second) 10.34.325.764 I slot print_timing: id 0 | task 17771 | total time = 11277.54 ms / 1397 tokens 10.34.325.765 I slot print_timing: id 0 | task 17771 | graphs reused = 17346 10.34.325.765 I slot print_timing: id 0 | task 17771 | graph reallocs = 0 / 0 (same size) / (changed size) 10.34.325.919 I slot release: id 0 | task 17771 | stop processing: n_tokens = 1428, truncated = 0 10.34.336.624 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1428, t_last = 386532531463 10.34.336.701 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 458.504 MiB) 10.35.141.828 I slot launch_slot_: id 0 | task 18247 | processing task, is_child = 0 10.39.945.422 I slot print_timing: id 0 | task 18247 | n_gen = 150, tg = 49.47 t/s, tg_3s = 49.81 t/s 10.41.852.411 I slot print_timing: id 0 | task 18247 | prompt eval time = 1791.93 ms / 885 tokens ( 2.02 ms per token, 493.88 tokens per second) 10.41.852.414 I slot print_timing: id 0 | task 18247 | eval time = 4918.64 ms / 245 tokens ( 20.16 ms per token, 49.61 tokens per second) 10.41.852.415 I slot print_timing: id 0 | task 18247 | total time = 6710.57 ms / 1130 tokens 10.41.852.415 I slot print_timing: id 0 | task 18247 | graphs reused = 17588 10.41.852.416 I slot print_timing: id 0 | task 18247 | graph reallocs = 0 / 0 (same size) / (changed size) 10.41.852.495 I slot release: id 0 | task 18247 | stop processing: n_tokens = 1161, truncated = 0 10.41.858.695 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1161, t_last = 386540058038 10.41.858.761 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 389.336 MiB) 10.42.894.827 I slot launch_slot_: id 0 | task 18496 | processing task, is_child = 0 10.46.774.034 I slot print_timing: id 0 | task 18496 | n_gen = 152, tg = 50.14 t/s, tg_3s = 50.47 t/s 10.47.332.292 I slot print_timing: id 0 | task 18496 | prompt eval time = 867.36 ms / 392 tokens ( 2.21 ms per token, 451.95 tokens per second) 10.47.332.299 I slot print_timing: id 0 | task 18496 | eval time = 3570.09 ms / 180 tokens ( 19.94 ms per token, 50.14 tokens per second) 10.47.332.300 I slot print_timing: id 0 | task 18496 | total time = 4437.45 ms / 572 tokens 10.47.332.301 I slot print_timing: id 0 | task 18496 | graphs reused = 17765 10.47.332.301 I slot print_timing: id 0 | task 18496 | graph reallocs = 0 / 0 (same size) / (changed size) 10.47.332.363 I slot release: id 0 | task 18496 | stop processing: n_tokens = 603, truncated = 0 10.47.338.781 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 603, t_last = 386545537907 10.47.338.820 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 464.272 MiB) 10.48.276.151 I slot launch_slot_: id 0 | task 18679 | processing task, is_child = 0 10.49.836.420 I slot print_timing: id 0 | task 18679 | prompt eval time = 757.54 ms / 331 tokens ( 2.29 ms per token, 436.94 tokens per second) 10.49.836.426 I slot print_timing: id 0 | task 18679 | eval time = 802.71 ms / 41 tokens ( 20.07 ms per token, 49.83 tokens per second) 10.49.836.427 I slot print_timing: id 0 | task 18679 | total time = 1560.25 ms / 372 tokens 10.49.836.427 I slot print_timing: id 0 | task 18679 | graphs reused = 17804 10.49.836.428 I slot print_timing: id 0 | task 18679 | graph reallocs = 0 / 0 (same size) / (changed size) 10.49.836.465 I slot release: id 0 | task 18679 | stop processing: n_tokens = 403, truncated = 0 10.49.842.214 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 403, t_last = 386548042009 10.49.842.244 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 391.193 MiB) 10.50.989.167 I slot launch_slot_: id 0 | task 18723 | processing task, is_child = 0 10.54.873.638 I slot print_timing: id 0 | task 18723 | n_gen = 152, tg = 50.08 t/s, tg_3s = 50.42 t/s 10.57.882.817 I slot print_timing: id 0 | task 18723 | n_gen = 303, tg = 50.13 t/s, tg_3s = 50.18 t/s 11.00.899.579 I slot print_timing: id 0 | task 18723 | n_gen = 454, tg = 50.11 t/s, tg_3s = 50.05 t/s 11.03.912.725 I slot print_timing: id 0 | task 18723 | n_gen = 605, tg = 50.11 t/s, tg_3s = 50.11 t/s 11.06.925.973 I slot print_timing: id 0 | task 18723 | n_gen = 755, tg = 50.04 t/s, tg_3s = 49.78 t/s 11.09.942.802 I slot print_timing: id 0 | task 18723 | n_gen = 905, tg = 49.99 t/s, tg_3s = 49.72 t/s 11.12.331.704 I slot print_timing: id 0 | task 18723 | prompt eval time = 869.53 ms / 357 tokens ( 2.44 ms per token, 410.57 tokens per second) 11.12.331.711 I slot print_timing: id 0 | task 18723 | eval time = 20472.98 ms / 1024 tokens ( 20.01 ms per token, 49.97 tokens per second) 11.12.331.711 I slot print_timing: id 0 | task 18723 | total time = 21342.51 ms / 1381 tokens 11.12.331.712 I slot print_timing: id 0 | task 18723 | graphs reused = 18822 11.12.331.713 I slot print_timing: id 0 | task 18723 | graph reallocs = 0 / 0 (same size) / (changed size) 11.12.331.767 I slot release: id 0 | task 18723 | stop processing: n_tokens = 1412, truncated = 0 11.12.342.230 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1412, t_last = 386570537310 11.12.342.299 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 461.359 MiB) 11.13.598.897 I slot launch_slot_: id 0 | task 19750 | processing task, is_child = 0 11.17.368.095 I slot print_timing: id 0 | task 19750 | n_gen = 152, tg = 50.25 t/s, tg_3s = 50.58 t/s 11.17.669.875 I slot print_timing: id 0 | task 19750 | prompt eval time = 764.11 ms / 315 tokens ( 2.43 ms per token, 412.25 tokens per second) 11.17.669.881 I slot print_timing: id 0 | task 19750 | eval time = 3306.86 ms / 167 tokens ( 19.92 ms per token, 50.20 tokens per second) 11.17.669.887 I slot print_timing: id 0 | task 19750 | total time = 4070.96 ms / 482 tokens 11.17.669.891 I slot print_timing: id 0 | task 19750 | graphs reused = 18986 11.17.669.892 I slot print_timing: id 0 | task 19750 | graph reallocs = 0 / 0 (same size) / (changed size) 11.17.669.932 I slot release: id 0 | task 19750 | stop processing: n_tokens = 513, truncated = 0 11.17.677.428 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 513, t_last = 386575875475 11.17.677.467 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.481 MiB) 11.19.037.272 I slot launch_slot_: id 0 | task 19920 | processing task, is_child = 0 11.22.951.733 I slot print_timing: id 0 | task 19920 | n_gen = 152, tg = 50.14 t/s, tg_3s = 50.48 t/s 11.25.962.262 I slot print_timing: id 0 | task 19920 | n_gen = 303, tg = 50.15 t/s, tg_3s = 50.16 t/s 11.28.979.782 I slot print_timing: id 0 | task 19920 | n_gen = 454, tg = 50.11 t/s, tg_3s = 50.04 t/s 11.31.993.777 I slot print_timing: id 0 | task 19920 | n_gen = 605, tg = 50.11 t/s, tg_3s = 50.10 t/s 11.35.005.592 I slot print_timing: id 0 | task 19920 | n_gen = 755, tg = 50.05 t/s, tg_3s = 49.80 t/s 11.38.014.221 I slot print_timing: id 0 | task 19920 | n_gen = 905, tg = 50.02 t/s, tg_3s = 49.86 t/s 11.40.399.323 I slot print_timing: id 0 | task 19920 | prompt eval time = 903.05 ms / 378 tokens ( 2.39 ms per token, 418.58 tokens per second) 11.40.399.330 I slot print_timing: id 0 | task 19920 | eval time = 20458.98 ms / 1024 tokens ( 20.00 ms per token, 50.00 tokens per second) 11.40.399.330 I slot print_timing: id 0 | task 19920 | total time = 21362.04 ms / 1402 tokens 11.40.399.331 I slot print_timing: id 0 | task 19920 | graphs reused = 20004 11.40.399.332 I slot print_timing: id 0 | task 19920 | graph reallocs = 0 / 0 (same size) / (changed size) 11.40.399.392 I slot release: id 0 | task 19920 | stop processing: n_tokens = 1433, truncated = 0 11.40.406.541 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1433, t_last = 386598604935 11.40.406.620 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 455.805 MiB) 11.41.388.439 I slot launch_slot_: id 0 | task 20947 | processing task, is_child = 0 11.42.676.759 I slot print_timing: id 0 | task 20947 | prompt eval time = 747.70 ms / 295 tokens ( 2.53 ms per token, 394.54 tokens per second) 11.42.676.766 I slot print_timing: id 0 | task 20947 | eval time = 540.60 ms / 28 tokens ( 20.02 ms per token, 49.94 tokens per second) 11.42.676.767 I slot print_timing: id 0 | task 20947 | total time = 1288.30 ms / 323 tokens 11.42.676.767 I slot print_timing: id 0 | task 20947 | graphs reused = 20030 11.42.676.768 I slot print_timing: id 0 | task 20947 | graph reallocs = 0 / 0 (same size) / (changed size) 11.42.676.806 I slot release: id 0 | task 20947 | stop processing: n_tokens = 354, truncated = 0 11.42.683.778 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 354, t_last = 386600882349 11.42.683.807 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 458.426 MiB) 11.43.834.289 I slot launch_slot_: id 0 | task 20978 | processing task, is_child = 0 11.45.505.369 I slot print_timing: id 0 | task 20978 | prompt eval time = 772.91 ms / 337 tokens ( 2.29 ms per token, 436.01 tokens per second) 11.45.505.373 I slot print_timing: id 0 | task 20978 | eval time = 898.15 ms / 46 tokens ( 19.96 ms per token, 50.10 tokens per second) 11.45.505.374 I slot print_timing: id 0 | task 20978 | total time = 1671.06 ms / 383 tokens 11.45.505.374 I slot print_timing: id 0 | task 20978 | graphs reused = 20074 11.45.505.375 I slot print_timing: id 0 | task 20978 | graph reallocs = 0 / 0 (same size) / (changed size) 11.45.505.489 I slot release: id 0 | task 20978 | stop processing: n_tokens = 414, truncated = 0 11.45.512.324 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 386603711033 11.46.185.850 I slot launch_slot_: id 0 | task 21027 | processing task, is_child = 0 11.50.000.221 I slot print_timing: id 0 | task 21027 | n_gen = 152, tg = 50.24 t/s, tg_3s = 50.58 t/s 11.51.445.248 I slot print_timing: id 0 | task 21027 | prompt eval time = 808.98 ms / 325 tokens ( 2.49 ms per token, 401.74 tokens per second) 11.51.445.254 I slot print_timing: id 0 | task 21027 | eval time = 4450.40 ms / 224 tokens ( 19.96 ms per token, 50.11 tokens per second) 11.51.445.254 I slot print_timing: id 0 | task 21027 | total time = 5259.38 ms / 549 tokens 11.51.445.255 I slot print_timing: id 0 | task 21027 | graphs reused = 20295 11.51.445.256 I slot print_timing: id 0 | task 21027 | graph reallocs = 0 / 0 (same size) / (changed size) 11.51.445.775 I slot release: id 0 | task 21027 | stop processing: n_tokens = 580, truncated = 0 11.51.452.184 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.108 (> 0.100 thold), f_keep = 0.055 11.51.452.223 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 459.071 MiB) 11.52.772.595 I slot launch_slot_: id 0 | task 21254 | processing task, is_child = 0 11.54.044.642 I slot print_timing: id 0 | task 21254 | prompt eval time = 713.29 ms / 264 tokens ( 2.70 ms per token, 370.11 tokens per second) 11.54.044.648 I slot print_timing: id 0 | task 21254 | eval time = 558.74 ms / 29 tokens ( 19.95 ms per token, 50.11 tokens per second) 11.54.044.649 I slot print_timing: id 0 | task 21254 | total time = 1272.03 ms / 293 tokens 11.54.044.650 I slot print_timing: id 0 | task 21254 | graphs reused = 20322 11.54.044.650 I slot print_timing: id 0 | task 21254 | graph reallocs = 0 / 0 (same size) / (changed size) 11.54.044.694 I slot release: id 0 | task 21254 | stop processing: n_tokens = 324, truncated = 0 11.54.051.112 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 324, t_last = 386612250237 11.54.051.142 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 453.987 MiB) 11.54.994.937 I slot launch_slot_: id 0 | task 21286 | processing task, is_child = 0 11.56.679.206 I slot print_timing: id 0 | task 21286 | prompt eval time = 819.79 ms / 331 tokens ( 2.48 ms per token, 403.76 tokens per second) 11.56.679.212 I slot print_timing: id 0 | task 21286 | eval time = 864.47 ms / 44 tokens ( 20.10 ms per token, 49.74 tokens per second) 11.56.679.214 I slot print_timing: id 0 | task 21286 | total time = 1684.26 ms / 375 tokens 11.56.679.214 I slot print_timing: id 0 | task 21286 | graphs reused = 20364 11.56.679.215 I slot print_timing: id 0 | task 21286 | graph reallocs = 0 / 0 (same size) / (changed size) 11.56.679.270 I slot release: id 0 | task 21286 | stop processing: n_tokens = 406, truncated = 0 11.56.686.214 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 406, t_last = 386614884813 11.56.686.247 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 458.484 MiB) 11.58.086.016 I slot launch_slot_: id 0 | task 21333 | processing task, is_child = 0 11.59.749.899 I slot print_timing: id 0 | task 21333 | prompt eval time = 815.85 ms / 333 tokens ( 2.45 ms per token, 408.17 tokens per second) 11.59.749.902 I slot print_timing: id 0 | task 21333 | eval time = 848.02 ms / 42 tokens ( 20.68 ms per token, 48.35 tokens per second) 11.59.749.903 I slot print_timing: id 0 | task 21333 | total time = 1663.87 ms / 375 tokens 11.59.749.904 I slot print_timing: id 0 | task 21333 | graphs reused = 20404 11.59.749.904 I slot print_timing: id 0 | task 21333 | graph reallocs = 0 / 0 (same size) / (changed size) 11.59.749.973 I slot release: id 0 | task 21333 | stop processing: n_tokens = 406, truncated = 0 11.59.756.106 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 406, t_last = 386617955516 11.59.756.142 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 454.808 MiB) 12.00.855.482 I slot launch_slot_: id 0 | task 21378 | processing task, is_child = 0 12.04.709.323 I slot print_timing: id 0 | task 21378 | n_gen = 152, tg = 50.21 t/s, tg_3s = 50.54 t/s 12.07.720.669 I slot print_timing: id 0 | task 21378 | n_gen = 303, tg = 50.18 t/s, tg_3s = 50.14 t/s 12.10.738.674 I slot print_timing: id 0 | task 21378 | n_gen = 454, tg = 50.13 t/s, tg_3s = 50.03 t/s 12.13.751.917 I slot print_timing: id 0 | task 21378 | n_gen = 605, tg = 50.13 t/s, tg_3s = 50.11 t/s 12.16.759.341 I slot print_timing: id 0 | task 21378 | n_gen = 755, tg = 50.08 t/s, tg_3s = 49.88 t/s 12.19.765.751 I slot print_timing: id 0 | task 21378 | n_gen = 905, tg = 50.05 t/s, tg_3s = 49.89 t/s 12.21.029.564 I slot print_timing: id 0 | task 21378 | prompt eval time = 846.57 ms / 346 tokens ( 2.45 ms per token, 408.71 tokens per second) 12.21.029.567 I slot print_timing: id 0 | task 21378 | eval time = 19327.50 ms / 968 tokens ( 19.99 ms per token, 50.03 tokens per second) 12.21.029.568 I slot print_timing: id 0 | task 21378 | total time = 20174.07 ms / 1314 tokens 12.21.029.569 I slot print_timing: id 0 | task 21378 | graphs reused = 21366 12.21.029.569 I slot print_timing: id 0 | task 21378 | graph reallocs = 0 / 0 (same size) / (changed size) 12.21.029.613 I slot release: id 0 | task 21378 | stop processing: n_tokens = 1345, truncated = 0 12.21.036.229 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1345, t_last = 386639235156 12.21.036.298 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 469.102 MiB) 12.22.303.461 I slot launch_slot_: id 0 | task 22349 | processing task, is_child = 0 12.24.587.958 I slot print_timing: id 0 | task 22349 | prompt eval time = 787.97 ms / 325 tokens ( 2.42 ms per token, 412.45 tokens per second) 12.24.587.964 I slot print_timing: id 0 | task 22349 | eval time = 1496.51 ms / 76 tokens ( 19.95 ms per token, 50.12 tokens per second) 12.24.587.965 I slot print_timing: id 0 | task 22349 | total time = 2284.48 ms / 401 tokens 12.24.587.966 I slot print_timing: id 0 | task 22349 | graphs reused = 21440 12.24.587.966 I slot print_timing: id 0 | task 22349 | graph reallocs = 0 / 0 (same size) / (changed size) 12.24.589.068 I slot release: id 0 | task 22349 | stop processing: n_tokens = 432, truncated = 0 12.24.596.939 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 432, t_last = 386642794612 12.24.596.974 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 461.163 MiB) 12.25.696.560 I slot launch_slot_: id 0 | task 22428 | processing task, is_child = 0 12.29.499.049 I slot print_timing: id 0 | task 22428 | n_gen = 152, tg = 50.06 t/s, tg_3s = 50.39 t/s 12.30.482.026 I slot print_timing: id 0 | task 22428 | prompt eval time = 786.08 ms / 322 tokens ( 2.44 ms per token, 409.63 tokens per second) 12.30.482.033 I slot print_timing: id 0 | task 22428 | eval time = 3999.37 ms / 201 tokens ( 20.00 ms per token, 50.01 tokens per second) 12.30.482.033 I slot print_timing: id 0 | task 22428 | total time = 4785.45 ms / 523 tokens 12.30.482.034 I slot print_timing: id 0 | task 22428 | graphs reused = 21638 12.30.482.034 I slot print_timing: id 0 | task 22428 | graph reallocs = 0 / 0 (same size) / (changed size) 12.30.482.089 I slot release: id 0 | task 22428 | stop processing: n_tokens = 554, truncated = 0 12.30.489.093 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 554, t_last = 386648687632 12.31.101.672 I slot launch_slot_: id 0 | task 22632 | processing task, is_child = 0 12.34.918.693 I slot print_timing: id 0 | task 22632 | n_gen = 152, tg = 50.08 t/s, tg_3s = 50.41 t/s 12.37.927.967 I slot print_timing: id 0 | task 22632 | n_gen = 302, tg = 49.96 t/s, tg_3s = 49.85 t/s 12.40.941.727 I slot print_timing: id 0 | task 22632 | n_gen = 452, tg = 49.90 t/s, tg_3s = 49.77 t/s 12.42.480.736 I slot print_timing: id 0 | task 22632 | prompt eval time = 801.67 ms / 338 tokens ( 2.37 ms per token, 421.62 tokens per second) 12.42.480.742 I slot print_timing: id 0 | task 22632 | eval time = 10577.38 ms / 529 tokens ( 20.03 ms per token, 49.92 tokens per second) 12.42.480.743 I slot print_timing: id 0 | task 22632 | total time = 11379.05 ms / 867 tokens 12.42.480.743 I slot print_timing: id 0 | task 22632 | graphs reused = 22163 12.42.480.744 I slot print_timing: id 0 | task 22632 | graph reallocs = 0 / 0 (same size) / (changed size) 12.42.480.794 I slot release: id 0 | task 22632 | stop processing: n_tokens = 898, truncated = 0 12.42.490.118 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 898, t_last = 386660686337 12.42.490.170 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 455.453 MiB) 12.43.573.048 I slot launch_slot_: id 0 | task 23164 | processing task, is_child = 0 12.47.403.635 I slot print_timing: id 0 | task 23164 | n_gen = 151, tg = 49.91 t/s, tg_3s = 50.25 t/s 12.50.191.858 I slot print_timing: id 0 | task 23164 | prompt eval time = 825.34 ms / 347 tokens ( 2.38 ms per token, 420.43 tokens per second) 12.50.191.864 I slot print_timing: id 0 | task 23164 | eval time = 5793.46 ms / 290 tokens ( 20.05 ms per token, 49.88 tokens per second) 12.50.191.865 I slot print_timing: id 0 | task 23164 | total time = 6618.80 ms / 637 tokens 12.50.191.866 I slot print_timing: id 0 | task 23164 | graphs reused = 22450 12.50.191.867 I slot print_timing: id 0 | task 23164 | graph reallocs = 0 / 0 (same size) / (changed size) 12.50.193.480 I slot release: id 0 | task 23164 | stop processing: n_tokens = 668, truncated = 0 12.50.203.237 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 668, t_last = 386668399023 12.50.203.280 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 458.719 MiB) 12.51.426.815 I slot launch_slot_: id 0 | task 23457 | processing task, is_child = 0 12.53.332.290 I slot print_timing: id 0 | task 23457 | prompt eval time = 827.56 ms / 331 tokens ( 2.50 ms per token, 399.97 tokens per second) 12.53.332.293 I slot print_timing: id 0 | task 23457 | eval time = 1077.90 ms / 55 tokens ( 19.96 ms per token, 50.10 tokens per second) 12.53.332.293 I slot print_timing: id 0 | task 23457 | total time = 1905.46 ms / 386 tokens 12.53.332.294 I slot print_timing: id 0 | task 23457 | graphs reused = 22503 12.53.332.295 I slot print_timing: id 0 | task 23457 | graph reallocs = 0 / 0 (same size) / (changed size) 12.53.332.326 I slot release: id 0 | task 23457 | stop processing: n_tokens = 417, truncated = 0 12.53.343.687 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 417, t_last = 386671537869 12.53.343.721 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 391.623 MiB) 12.54.287.381 I slot launch_slot_: id 0 | task 23515 | processing task, is_child = 0 12.55.990.765 I slot print_timing: id 0 | task 23515 | prompt eval time = 800.78 ms / 345 tokens ( 2.32 ms per token, 430.83 tokens per second) 12.55.990.768 I slot print_timing: id 0 | task 23515 | eval time = 902.58 ms / 45 tokens ( 20.51 ms per token, 48.75 tokens per second) 12.55.990.769 I slot print_timing: id 0 | task 23515 | total time = 1703.36 ms / 390 tokens 12.55.990.770 I slot print_timing: id 0 | task 23515 | graphs reused = 22546 12.55.990.770 I slot print_timing: id 0 | task 23515 | graph reallocs = 0 / 0 (same size) / (changed size) 12.55.990.841 I slot release: id 0 | task 23515 | stop processing: n_tokens = 421, truncated = 0 12.55.998.591 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 421, t_last = 386674196384 12.55.998.628 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 456.392 MiB) 12.57.232.324 I slot launch_slot_: id 0 | task 23563 | processing task, is_child = 0 13.01.026.210 I slot print_timing: id 0 | task 23563 | n_gen = 152, tg = 50.33 t/s, tg_3s = 50.67 t/s 13.04.038.600 I slot print_timing: id 0 | task 23563 | n_gen = 303, tg = 50.23 t/s, tg_3s = 50.13 t/s 13.04.278.683 I slot print_timing: id 0 | task 23563 | prompt eval time = 793.79 ms / 320 tokens ( 2.48 ms per token, 403.13 tokens per second) 13.04.278.689 I slot print_timing: id 0 | task 23563 | eval time = 6252.55 ms / 315 tokens ( 19.91 ms per token, 50.22 tokens per second) 13.04.278.690 I slot print_timing: id 0 | task 23563 | total time = 7046.34 ms / 635 tokens 13.04.278.690 I slot print_timing: id 0 | task 23563 | graphs reused = 22858 13.04.278.691 I slot print_timing: id 0 | task 23563 | graph reallocs = 0 / 0 (same size) / (changed size) 13.04.278.736 I slot release: id 0 | task 23563 | stop processing: n_tokens = 666, truncated = 0 13.04.286.818 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 666, t_last = 386682484279 13.04.286.857 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 467.616 MiB) 13.05.705.924 I slot launch_slot_: id 0 | task 23881 | processing task, is_child = 0 13.07.376.588 I slot print_timing: id 0 | task 23881 | prompt eval time = 733.00 ms / 297 tokens ( 2.47 ms per token, 405.18 tokens per second) 13.07.376.596 I slot print_timing: id 0 | task 23881 | eval time = 937.64 ms / 47 tokens ( 20.38 ms per token, 49.06 tokens per second) 13.07.376.597 I slot print_timing: id 0 | task 23881 | total time = 1670.65 ms / 344 tokens 13.07.376.597 I slot print_timing: id 0 | task 23881 | graphs reused = 22903 13.07.376.598 I slot print_timing: id 0 | task 23881 | graph reallocs = 0 / 0 (same size) / (changed size) 13.07.376.632 I slot release: id 0 | task 23881 | stop processing: n_tokens = 375, truncated = 0 13.07.387.729 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 375, t_last = 386685582175 13.07.387.758 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 462.395 MiB) 13.08.965.018 I slot launch_slot_: id 0 | task 23931 | processing task, is_child = 0 13.12.803.234 I slot print_timing: id 0 | task 23931 | n_gen = 152, tg = 50.09 t/s, tg_3s = 50.42 t/s 13.15.820.189 I slot print_timing: id 0 | task 23931 | n_gen = 303, tg = 50.07 t/s, tg_3s = 50.05 t/s 13.17.675.984 I slot print_timing: id 0 | task 23931 | prompt eval time = 823.42 ms / 343 tokens ( 2.40 ms per token, 416.55 tokens per second) 13.17.675.990 I slot print_timing: id 0 | task 23931 | eval time = 7887.52 ms / 395 tokens ( 20.02 ms per token, 49.95 tokens per second) 13.17.675.991 I slot print_timing: id 0 | task 23931 | total time = 8710.95 ms / 738 tokens 13.17.675.991 I slot print_timing: id 0 | task 23931 | graphs reused = 23294 13.17.675.992 I slot print_timing: id 0 | task 23931 | graph reallocs = 0 / 0 (same size) / (changed size) 13.17.677.032 I slot release: id 0 | task 23931 | stop processing: n_tokens = 769, truncated = 0 13.17.686.802 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 769, t_last = 386695882577 13.18.526.640 I slot launch_slot_: id 0 | task 24329 | processing task, is_child = 0 13.21.791.398 I slot print_timing: id 0 | task 24329 | prompt eval time = 831.33 ms / 371 tokens ( 2.24 ms per token, 446.27 tokens per second) 13.21.791.401 I slot print_timing: id 0 | task 24329 | eval time = 2433.41 ms / 122 tokens ( 20.11 ms per token, 49.72 tokens per second) 13.21.791.402 I slot print_timing: id 0 | task 24329 | total time = 3264.74 ms / 493 tokens 13.21.791.403 I slot print_timing: id 0 | task 24329 | graphs reused = 23413 13.21.791.403 I slot print_timing: id 0 | task 24329 | graph reallocs = 0 / 0 (same size) / (changed size) 13.21.791.894 I slot release: id 0 | task 24329 | stop processing: n_tokens = 524, truncated = 0 13.21.797.827 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 524, t_last = 386699997438 13.21.797.863 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.671 MiB) 13.23.151.047 I slot launch_slot_: id 0 | task 24454 | processing task, is_child = 0 13.24.541.745 I slot print_timing: id 0 | task 24454 | prompt eval time = 771.48 ms / 292 tokens ( 2.64 ms per token, 378.49 tokens per second) 13.24.541.751 I slot print_timing: id 0 | task 24454 | eval time = 619.21 ms / 32 tokens ( 19.97 ms per token, 50.06 tokens per second) 13.24.541.753 I slot print_timing: id 0 | task 24454 | total time = 1390.68 ms / 324 tokens 13.24.541.753 I slot print_timing: id 0 | task 24454 | graphs reused = 23443 13.24.542.814 I slot print_timing: id 0 | task 24454 | graph reallocs = 0 / 0 (same size) / (changed size) 13.24.543.377 I slot release: id 0 | task 24454 | stop processing: n_tokens = 355, truncated = 0 13.24.549.040 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 355, t_last = 386702748921 13.24.549.070 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 384.760 MiB) 13.25.503.234 I slot launch_slot_: id 0 | task 24489 | processing task, is_child = 0 13.27.573.776 I slot print_timing: id 0 | task 24489 | prompt eval time = 735.50 ms / 301 tokens ( 2.44 ms per token, 409.25 tokens per second) 13.27.573.782 I slot print_timing: id 0 | task 24489 | eval time = 1335.03 ms / 68 tokens ( 19.93 ms per token, 50.19 tokens per second) 13.27.573.783 I slot print_timing: id 0 | task 24489 | total time = 2070.53 ms / 369 tokens 13.27.573.783 I slot print_timing: id 0 | task 24489 | graphs reused = 23509 13.27.573.784 I slot print_timing: id 0 | task 24489 | graph reallocs = 0 / 0 (same size) / (changed size) 13.27.574.814 I slot release: id 0 | task 24489 | stop processing: n_tokens = 400, truncated = 0 13.27.581.712 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 386705780358 13.27.581.743 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 404.490 MiB) 13.28.775.086 I slot launch_slot_: id 0 | task 24560 | processing task, is_child = 0 13.32.552.525 I slot print_timing: id 0 | task 24560 | n_gen = 152, tg = 50.16 t/s, tg_3s = 50.49 t/s 13.35.565.356 I slot print_timing: id 0 | task 24560 | n_gen = 303, tg = 50.14 t/s, tg_3s = 50.12 t/s 13.37.066.836 I slot print_timing: id 0 | task 24560 | prompt eval time = 767.00 ms / 303 tokens ( 2.53 ms per token, 395.05 tokens per second) 13.37.066.839 I slot print_timing: id 0 | task 24560 | eval time = 7524.74 ms / 378 tokens ( 19.96 ms per token, 50.10 tokens per second) 13.37.066.840 I slot print_timing: id 0 | task 24560 | total time = 8291.74 ms / 681 tokens 13.37.066.841 I slot print_timing: id 0 | task 24560 | graphs reused = 23884 13.37.066.842 I slot print_timing: id 0 | task 24560 | graph reallocs = 0 / 0 (same size) / (changed size) 13.37.066.880 I slot release: id 0 | task 24560 | stop processing: n_tokens = 712, truncated = 0 13.37.072.527 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 712, t_last = 386715272423 13.37.072.579 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.911 MiB) 13.38.104.105 I slot launch_slot_: id 0 | task 24941 | processing task, is_child = 0 13.39.825.817 I slot print_timing: id 0 | task 24941 | prompt eval time = 782.98 ms / 321 tokens ( 2.44 ms per token, 409.97 tokens per second) 13.39.825.823 I slot print_timing: id 0 | task 24941 | eval time = 938.71 ms / 48 tokens ( 19.97 ms per token, 50.07 tokens per second) 13.39.825.824 I slot print_timing: id 0 | task 24941 | total time = 1721.70 ms / 369 tokens 13.39.825.824 I slot print_timing: id 0 | task 24941 | graphs reused = 23930 13.39.825.825 I slot print_timing: id 0 | task 24941 | graph reallocs = 0 / 0 (same size) / (changed size) 13.39.825.857 I slot release: id 0 | task 24941 | stop processing: n_tokens = 400, truncated = 0 13.39.833.718 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 386718031400 13.39.833.750 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 404.901 MiB) 13.41.227.560 I slot launch_slot_: id 0 | task 24992 | processing task, is_child = 0 13.43.042.842 I slot print_timing: id 0 | task 24992 | prompt eval time = 794.72 ms / 322 tokens ( 2.47 ms per token, 405.18 tokens per second) 13.43.042.846 I slot print_timing: id 0 | task 24992 | eval time = 1020.53 ms / 52 tokens ( 20.01 ms per token, 49.97 tokens per second) 13.43.042.847 I slot print_timing: id 0 | task 24992 | total time = 1815.25 ms / 374 tokens 13.43.042.848 I slot print_timing: id 0 | task 24992 | graphs reused = 23980 13.43.042.848 I slot print_timing: id 0 | task 24992 | graph reallocs = 0 / 0 (same size) / (changed size) 13.43.042.979 I slot release: id 0 | task 24992 | stop processing: n_tokens = 405, truncated = 0 13.43.051.428 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 405, t_last = 386721248523 13.43.051.460 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 383.802 MiB) 13.44.208.923 I slot launch_slot_: id 0 | task 25047 | processing task, is_child = 0 13.45.901.575 I slot print_timing: id 0 | task 25047 | prompt eval time = 797.50 ms / 323 tokens ( 2.47 ms per token, 405.02 tokens per second) 13.45.901.581 I slot print_timing: id 0 | task 25047 | eval time = 895.13 ms / 46 tokens ( 19.89 ms per token, 50.27 tokens per second) 13.45.901.582 I slot print_timing: id 0 | task 25047 | total time = 1692.63 ms / 369 tokens 13.45.901.583 I slot print_timing: id 0 | task 25047 | graphs reused = 24024 13.45.901.583 I slot print_timing: id 0 | task 25047 | graph reallocs = 0 / 0 (same size) / (changed size) 13.45.902.615 I slot release: id 0 | task 25047 | stop processing: n_tokens = 400, truncated = 0 13.45.914.191 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 386724108159 13.45.914.220 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 384.975 MiB) 13.47.032.303 I slot launch_slot_: id 0 | task 25096 | processing task, is_child = 0 13.50.802.277 I slot print_timing: id 0 | task 25096 | n_gen = 150, tg = 49.62 t/s, tg_3s = 49.95 t/s 13.53.819.952 I slot print_timing: id 0 | task 25096 | n_gen = 294, tg = 48.67 t/s, tg_3s = 47.72 t/s 13.56.820.909 I slot print_timing: id 0 | task 25096 | n_gen = 437, tg = 48.33 t/s, tg_3s = 47.65 t/s 13.59.833.784 I slot print_timing: id 0 | task 25096 | n_gen = 582, tg = 48.28 t/s, tg_3s = 48.13 t/s 14.02.852.387 I slot print_timing: id 0 | task 25096 | n_gen = 727, tg = 48.23 t/s, tg_3s = 48.04 t/s 14.04.323.168 I slot print_timing: id 0 | task 25096 | prompt eval time = 766.90 ms / 321 tokens ( 2.39 ms per token, 418.57 tokens per second) 14.04.323.172 I slot print_timing: id 0 | task 25096 | eval time = 16523.96 ms / 798 tokens ( 20.73 ms per token, 48.23 tokens per second) 14.04.323.173 I slot print_timing: id 0 | task 25096 | total time = 17290.85 ms / 1119 tokens 14.04.323.174 I slot print_timing: id 0 | task 25096 | graphs reused = 24817 14.04.323.174 I slot print_timing: id 0 | task 25096 | graph reallocs = 0 / 0 (same size) / (changed size) 14.04.323.213 I slot release: id 0 | task 25096 | stop processing: n_tokens = 1150, truncated = 0 14.04.333.093 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1150, t_last = 386742528756 14.04.333.157 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.221 MiB) 14.05.338.795 I slot launch_slot_: id 0 | task 25897 | processing task, is_child = 0 14.09.110.989 I slot print_timing: id 0 | task 25897 | n_gen = 153, tg = 50.38 t/s, tg_3s = 50.71 t/s 14.12.122.901 I slot print_timing: id 0 | task 25897 | n_gen = 304, tg = 50.26 t/s, tg_3s = 50.13 t/s 14.13.800.532 I slot print_timing: id 0 | task 25897 | prompt eval time = 754.93 ms / 322 tokens ( 2.34 ms per token, 426.53 tokens per second) 14.13.800.538 I slot print_timing: id 0 | task 25897 | eval time = 7706.79 ms / 388 tokens ( 19.91 ms per token, 50.22 tokens per second) 14.13.800.538 I slot print_timing: id 0 | task 25897 | total time = 8461.72 ms / 710 tokens 14.13.800.539 I slot print_timing: id 0 | task 25897 | graphs reused = 25202 14.13.800.540 I slot print_timing: id 0 | task 25897 | graph reallocs = 0 / 0 (same size) / (changed size) 14.13.800.582 I slot release: id 0 | task 25897 | stop processing: n_tokens = 741, truncated = 0 14.13.809.111 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 741, t_last = 386752006125 14.13.809.162 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 383.215 MiB) 14.15.373.287 I slot launch_slot_: id 0 | task 26288 | processing task, is_child = 0 14.17.089.623 I slot print_timing: id 0 | task 26288 | prompt eval time = 821.26 ms / 337 tokens ( 2.44 ms per token, 410.34 tokens per second) 14.17.089.627 I slot print_timing: id 0 | task 26288 | eval time = 895.06 ms / 46 tokens ( 19.89 ms per token, 50.28 tokens per second) 14.17.089.627 I slot print_timing: id 0 | task 26288 | total time = 1716.32 ms / 383 tokens 14.17.089.628 I slot print_timing: id 0 | task 26288 | graphs reused = 25246 14.17.089.629 I slot print_timing: id 0 | task 26288 | graph reallocs = 0 / 0 (same size) / (changed size) 14.17.090.139 I slot release: id 0 | task 26288 | stop processing: n_tokens = 414, truncated = 0 14.17.097.737 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 386755295683 14.17.097.768 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 384.819 MiB) 14.18.153.482 I slot launch_slot_: id 0 | task 26337 | processing task, is_child = 0 14.19.858.607 I slot print_timing: id 0 | task 26337 | prompt eval time = 789.13 ms / 325 tokens ( 2.43 ms per token, 411.85 tokens per second) 14.19.858.613 I slot print_timing: id 0 | task 26337 | eval time = 915.98 ms / 47 tokens ( 19.91 ms per token, 50.22 tokens per second) 14.19.858.614 I slot print_timing: id 0 | task 26337 | total time = 1705.11 ms / 372 tokens 14.19.858.615 I slot print_timing: id 0 | task 26337 | graphs reused = 25291 14.19.858.615 I slot print_timing: id 0 | task 26337 | graph reallocs = 0 / 0 (same size) / (changed size) 14.19.858.653 I slot release: id 0 | task 26337 | stop processing: n_tokens = 403, truncated = 0 14.19.864.917 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 403, t_last = 386758064197 14.19.864.954 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 384.819 MiB) 14.21.119.877 I slot launch_slot_: id 0 | task 26387 | processing task, is_child = 0 14.24.949.067 I slot print_timing: id 0 | task 26387 | n_gen = 152, tg = 50.19 t/s, tg_3s = 50.53 t/s 14.27.583.495 I slot print_timing: id 0 | task 26387 | prompt eval time = 820.88 ms / 331 tokens ( 2.48 ms per token, 403.23 tokens per second) 14.27.583.500 I slot print_timing: id 0 | task 26387 | eval time = 5642.73 ms / 284 tokens ( 19.94 ms per token, 50.15 tokens per second) 14.27.583.501 I slot print_timing: id 0 | task 26387 | total time = 6463.60 ms / 615 tokens 14.27.583.502 I slot print_timing: id 0 | task 26387 | graphs reused = 25572 14.27.583.502 I slot print_timing: id 0 | task 26387 | graph reallocs = 0 / 0 (same size) / (changed size) 14.27.583.547 I slot release: id 0 | task 26387 | stop processing: n_tokens = 646, truncated = 0 14.27.591.799 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 646, t_last = 386765789090 14.27.591.838 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 403.180 MiB) 14.28.773.416 I slot launch_slot_: id 0 | task 26674 | processing task, is_child = 0 14.30.618.107 I slot print_timing: id 0 | task 26674 | prompt eval time = 771.50 ms / 336 tokens ( 2.30 ms per token, 435.52 tokens per second) 14.30.618.110 I slot print_timing: id 0 | task 26674 | eval time = 1073.18 ms / 55 tokens ( 19.87 ms per token, 50.32 tokens per second) 14.30.618.111 I slot print_timing: id 0 | task 26674 | total time = 1844.67 ms / 391 tokens 14.30.618.112 I slot print_timing: id 0 | task 26674 | graphs reused = 25625 14.30.618.112 I slot print_timing: id 0 | task 26674 | graph reallocs = 0 / 0 (same size) / (changed size) 14.30.618.180 I slot release: id 0 | task 26674 | stop processing: n_tokens = 422, truncated = 0 14.30.626.445 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 422, t_last = 386768823723 14.30.626.475 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 385.327 MiB) 14.32.047.054 I slot launch_slot_: id 0 | task 26732 | processing task, is_child = 0 14.33.491.318 I slot print_timing: id 0 | task 26732 | prompt eval time = 847.12 ms / 349 tokens ( 2.43 ms per token, 411.98 tokens per second) 14.33.491.323 I slot print_timing: id 0 | task 26732 | eval time = 597.13 ms / 31 tokens ( 19.90 ms per token, 50.24 tokens per second) 14.33.491.324 I slot print_timing: id 0 | task 26732 | total time = 1444.25 ms / 380 tokens 14.33.491.325 I slot print_timing: id 0 | task 26732 | graphs reused = 25654 14.33.491.325 I slot print_timing: id 0 | task 26732 | graph reallocs = 0 / 0 (same size) / (changed size) 14.33.491.375 I slot release: id 0 | task 26732 | stop processing: n_tokens = 411, truncated = 0 14.33.501.639 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 386771696918 14.33.501.669 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.713 MiB) 14.34.230.175 I slot launch_slot_: id 0 | task 26766 | processing task, is_child = 0 14.36.558.474 I slot print_timing: id 0 | task 26766 | prompt eval time = 771.00 ms / 336 tokens ( 2.29 ms per token, 435.80 tokens per second) 14.36.558.479 I slot print_timing: id 0 | task 26766 | eval time = 1557.29 ms / 79 tokens ( 19.97 ms per token, 50.09 tokens per second) 14.36.558.480 I slot print_timing: id 0 | task 26766 | total time = 2328.28 ms / 415 tokens 14.36.558.480 I slot print_timing: id 0 | task 26766 | graphs reused = 25731 14.36.558.481 I slot print_timing: id 0 | task 26766 | graph reallocs = 0 / 0 (same size) / (changed size) 14.36.558.993 I slot release: id 0 | task 26766 | stop processing: n_tokens = 446, truncated = 0 14.36.570.659 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 446, t_last = 386774764540 14.36.570.690 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 394.439 MiB) 14.37.574.134 I slot launch_slot_: id 0 | task 26848 | processing task, is_child = 0 14.41.378.213 I slot print_timing: id 0 | task 26848 | n_gen = 152, tg = 50.09 t/s, tg_3s = 50.42 t/s 14.42.837.909 I slot print_timing: id 0 | task 26848 | prompt eval time = 789.39 ms / 349 tokens ( 2.26 ms per token, 442.11 tokens per second) 14.42.837.912 I slot print_timing: id 0 | task 26848 | eval time = 4474.36 ms / 225 tokens ( 19.97 ms per token, 50.06 tokens per second) 14.42.837.912 I slot print_timing: id 0 | task 26848 | total time = 5263.76 ms / 574 tokens 14.42.837.913 I slot print_timing: id 0 | task 26848 | graphs reused = 25953 14.42.837.914 I slot print_timing: id 0 | task 26848 | graph reallocs = 0 / 0 (same size) / (changed size) 14.42.837.989 I slot release: id 0 | task 26848 | stop processing: n_tokens = 605, truncated = 0 14.42.844.453 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 605, t_last = 386781043533 14.42.844.494 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 389.942 MiB) 14.44.424.149 I slot launch_slot_: id 0 | task 27076 | processing task, is_child = 0 14.46.400.704 I slot print_timing: id 0 | task 27076 | prompt eval time = 821.92 ms / 349 tokens ( 2.36 ms per token, 424.62 tokens per second) 14.46.400.708 I slot print_timing: id 0 | task 27076 | eval time = 1154.63 ms / 59 tokens ( 19.91 ms per token, 50.23 tokens per second) 14.46.400.708 I slot print_timing: id 0 | task 27076 | total time = 1976.54 ms / 408 tokens 14.46.401.198 I slot print_timing: id 0 | task 27076 | graphs reused = 26010 14.46.401.201 I slot print_timing: id 0 | task 27076 | graph reallocs = 0 / 0 (same size) / (changed size) 14.46.401.247 I slot release: id 0 | task 27076 | stop processing: n_tokens = 439, truncated = 0 14.46.411.687 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 439, t_last = 386784606790 14.46.411.731 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 385.034 MiB) 14.47.457.413 I slot launch_slot_: id 0 | task 27138 | processing task, is_child = 0 14.49.679.841 I slot print_timing: id 0 | task 27138 | prompt eval time = 879.02 ms / 385 tokens ( 2.28 ms per token, 437.99 tokens per second) 14.49.679.848 I slot print_timing: id 0 | task 27138 | eval time = 1343.39 ms / 68 tokens ( 20.05 ms per token, 49.87 tokens per second) 14.49.679.849 I slot print_timing: id 0 | task 27138 | total time = 2222.41 ms / 453 tokens 14.49.679.849 I slot print_timing: id 0 | task 27138 | graphs reused = 26076 14.49.679.850 I slot print_timing: id 0 | task 27138 | graph reallocs = 0 / 0 (same size) / (changed size) 14.49.679.880 I slot release: id 0 | task 27138 | stop processing: n_tokens = 484, truncated = 0 14.49.687.718 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 484, t_last = 386787885423 14.49.687.753 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 385.112 MiB) 14.51.026.352 I slot launch_slot_: id 0 | task 27209 | processing task, is_child = 0 14.52.960.151 I slot print_timing: id 0 | task 27209 | prompt eval time = 817.69 ms / 328 tokens ( 2.49 ms per token, 401.13 tokens per second) 14.52.960.155 I slot print_timing: id 0 | task 27209 | eval time = 1116.09 ms / 57 tokens ( 19.93 ms per token, 50.18 tokens per second) 14.52.960.155 I slot print_timing: id 0 | task 27209 | total time = 1933.78 ms / 385 tokens 14.52.960.156 I slot print_timing: id 0 | task 27209 | graphs reused = 26131 14.52.960.157 I slot print_timing: id 0 | task 27209 | graph reallocs = 0 / 0 (same size) / (changed size) 14.52.960.210 I slot release: id 0 | task 27209 | stop processing: n_tokens = 416, truncated = 0 14.53.218.789 I srv operator(): operator(): cleaning up before exit...