$ C:\quantdiff\llama.cpp\bin\llama-server.exe -m C:\quantdiff\hf-cache\models--bartowski--Qwen_Qwen3.5-4B-GGUF\snapshots\4168f45a16a1290d65a4ec0fa312ae917a4c15d6\Qwen_Qwen3.5-4B-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 0.00.094.916 I srv llama_server: initializing ... 0.00.094.923 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.095.040 I srv init_listene: The UI is disabled 0.00.095.042 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.095.122 W srv llama_server: security: no API key is set and CORS allows all origins (see https://github.com/ggml-org/llama.cpp/pull/25655) 0.00.104.548 I srv load_model: loading model 'C:\quantdiff\hf-cache\models--bartowski--Qwen_Qwen3.5-4B-GGUF\snapshots\4168f45a16a1290d65a4ec0fa312ae917a4c15d6\Qwen_Qwen3.5-4B-Q4_K_M.gguf' 0.00.956.510 W model has unused tensor blk.32.attn_norm.weight (size = 10240 bytes) -- ignoring 0.00.956.524 W model has unused tensor blk.32.post_attention_norm.weight (size = 10240 bytes) -- ignoring 0.00.956.550 W model has unused tensor blk.32.attn_q.weight (size = 22282240 bytes) -- ignoring 0.00.956.559 W model has unused tensor blk.32.attn_k.weight (size = 2785280 bytes) -- ignoring 0.00.956.568 W model has unused tensor blk.32.attn_v.weight (size = 2785280 bytes) -- ignoring 0.00.956.601 W model has unused tensor blk.32.attn_output.weight (size = 11141120 bytes) -- ignoring 0.00.956.611 W model has unused tensor blk.32.attn_q_norm.weight (size = 1024 bytes) -- ignoring 0.00.956.619 W model has unused tensor blk.32.attn_k_norm.weight (size = 1024 bytes) -- ignoring 0.00.956.629 W model has unused tensor blk.32.ffn_gate.weight (size = 25067520 bytes) -- ignoring 0.00.956.638 W model has unused tensor blk.32.ffn_down.weight (size = 25067520 bytes) -- ignoring 0.00.956.647 W model has unused tensor blk.32.ffn_up.weight (size = 25067520 bytes) -- ignoring 0.00.956.658 W model has unused tensor blk.32.nextn.eh_proj.weight (size = 13926400 bytes) -- ignoring 0.00.956.670 W model has unused tensor blk.32.nextn.enorm.weight (size = 10240 bytes) -- ignoring 0.00.956.679 W model has unused tensor blk.32.nextn.hnorm.weight (size = 10240 bytes) -- ignoring 0.00.956.708 W model has unused tensor blk.32.nextn.shared_head_norm.weight (size = 10240 bytes) -- ignoring 0.01.992.614 I cmn init: llama threadpool init, n_threads = 8 0.02.070.662 I srv load_model: initializing, n_slots = 1, n_ctx_slot = 4096, kv_unified = 'false' 0.02.075.370 I srv llama_server: model loaded 0.02.075.377 I srv llama_server: listening on http://127.0.0.1:8089 0.02.519.686 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.02.519.868 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.03.065.930 I slot print_timing: id 0 | task 0 | prompt eval time = 185.54 ms / 368 tokens ( 0.50 ms per token, 1983.38 tokens per second) 0.03.065.935 I slot print_timing: id 0 | task 0 | eval time = 360.50 ms / 53 tokens ( 6.93 ms per token, 144.24 tokens per second) 0.03.065.936 I slot print_timing: id 0 | task 0 | total time = 546.04 ms / 421 tokens 0.03.065.943 I slot print_timing: id 0 | task 0 | graphs reused = 52 0.03.065.944 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.03.065.973 I slot release: id 0 | task 0 | stop processing: n_tokens = 420, truncated = 0 0.03.088.646 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 420, t_last = 2973009 0.03.114.324 I slot launch_slot_: id 0 | task 56 | processing task, is_child = 0 0.03.486.937 I slot print_timing: id 0 | task 56 | prompt eval time = 90.01 ms / 322 tokens ( 0.28 ms per token, 3577.54 tokens per second) 0.03.486.942 I slot print_timing: id 0 | task 56 | eval time = 282.59 ms / 42 tokens ( 6.89 ms per token, 145.09 tokens per second) 0.03.486.943 I slot print_timing: id 0 | task 56 | total time = 372.59 ms / 364 tokens 0.03.486.944 I slot print_timing: id 0 | task 56 | graphs reused = 92 0.03.486.945 I slot print_timing: id 0 | task 56 | graph reallocs = 0 / 0 (same size) / (changed size) 0.03.486.971 I slot release: id 0 | task 56 | stop processing: n_tokens = 363, truncated = 0 0.03.512.887 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 363, t_last = 3394006 0.03.538.548 I slot launch_slot_: id 0 | task 101 | processing task, is_child = 0 0.03.913.817 I slot print_timing: id 0 | task 101 | prompt eval time = 91.80 ms / 365 tokens ( 0.25 ms per token, 3976.03 tokens per second) 0.03.913.823 I slot print_timing: id 0 | task 101 | eval time = 283.45 ms / 42 tokens ( 6.91 ms per token, 144.65 tokens per second) 0.03.913.825 I slot print_timing: id 0 | task 101 | total time = 375.25 ms / 407 tokens 0.03.913.825 I slot print_timing: id 0 | task 101 | graphs reused = 132 0.03.913.826 I slot print_timing: id 0 | task 101 | graph reallocs = 0 / 0 (same size) / (changed size) 0.03.913.855 I slot release: id 0 | task 101 | stop processing: n_tokens = 406, truncated = 0 0.03.932.609 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 406, t_last = 3820890 0.03.957.999 I slot launch_slot_: id 0 | task 146 | processing task, is_child = 0 0.04.341.233 I slot print_timing: id 0 | task 146 | prompt eval time = 94.50 ms / 397 tokens ( 0.24 ms per token, 4200.84 tokens per second) 0.04.341.239 I slot print_timing: id 0 | task 146 | eval time = 288.71 ms / 43 tokens ( 6.87 ms per token, 145.47 tokens per second) 0.04.341.240 I slot print_timing: id 0 | task 146 | total time = 383.22 ms / 440 tokens 0.04.341.240 I slot print_timing: id 0 | task 146 | graphs reused = 173 0.04.341.241 I slot print_timing: id 0 | task 146 | graph reallocs = 0 / 0 (same size) / (changed size) 0.04.341.268 I slot release: id 0 | task 146 | stop processing: n_tokens = 439, truncated = 0 0.04.369.485 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 0.04.396.046 I slot launch_slot_: id 0 | task 192 | processing task, is_child = 0 0.04.858.670 I slot print_timing: id 0 | task 192 | prompt eval time = 91.83 ms / 383 tokens ( 0.24 ms per token, 4170.84 tokens per second) 0.04.858.675 I slot print_timing: id 0 | task 192 | eval time = 370.78 ms / 55 tokens ( 6.87 ms per token, 145.64 tokens per second) 0.04.858.676 I slot print_timing: id 0 | task 192 | total time = 462.61 ms / 438 tokens 0.04.858.677 I slot print_timing: id 0 | task 192 | graphs reused = 226 0.04.858.678 I slot print_timing: id 0 | task 192 | graph reallocs = 0 / 0 (same size) / (changed size) 0.04.858.704 I slot release: id 0 | task 192 | stop processing: n_tokens = 437, truncated = 0 0.04.885.887 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 4765740 0.04.912.589 I slot launch_slot_: id 0 | task 250 | processing task, is_child = 0 0.05.376.909 I slot print_timing: id 0 | task 250 | prompt eval time = 93.72 ms / 372 tokens ( 0.25 ms per token, 3969.10 tokens per second) 0.05.376.917 I slot print_timing: id 0 | task 250 | eval time = 370.58 ms / 55 tokens ( 6.86 ms per token, 145.72 tokens per second) 0.05.376.918 I slot print_timing: id 0 | task 250 | total time = 464.31 ms / 427 tokens 0.05.376.919 I slot print_timing: id 0 | task 250 | graphs reused = 279 0.05.376.919 I slot print_timing: id 0 | task 250 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.376.945 I slot release: id 0 | task 250 | stop processing: n_tokens = 426, truncated = 0 0.05.397.182 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 5283981 0.05.426.844 I slot launch_slot_: id 0 | task 308 | processing task, is_child = 0 0.05.898.744 I slot print_timing: id 0 | task 308 | prompt eval time = 101.98 ms / 422 tokens ( 0.24 ms per token, 4138.11 tokens per second) 0.05.898.749 I slot print_timing: id 0 | task 308 | eval time = 369.90 ms / 55 tokens ( 6.85 ms per token, 145.99 tokens per second) 0.05.898.750 I slot print_timing: id 0 | task 308 | total time = 471.88 ms / 477 tokens 0.05.898.751 I slot print_timing: id 0 | task 308 | graphs reused = 332 0.05.898.752 I slot print_timing: id 0 | task 308 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.898.780 I slot release: id 0 | task 308 | stop processing: n_tokens = 476, truncated = 0 0.05.912.805 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 476, t_last = 5805816 0.05.939.560 I slot launch_slot_: id 0 | task 366 | processing task, is_child = 0 0.06.532.528 I slot print_timing: id 0 | task 366 | prompt eval time = 102.96 ms / 470 tokens ( 0.22 ms per token, 4564.75 tokens per second) 0.06.532.534 I slot print_timing: id 0 | task 366 | eval time = 489.98 ms / 72 tokens ( 6.90 ms per token, 144.90 tokens per second) 0.06.532.535 I slot print_timing: id 0 | task 366 | total time = 592.95 ms / 542 tokens 0.06.532.536 I slot print_timing: id 0 | task 366 | graphs reused = 401 0.06.532.537 I slot print_timing: id 0 | task 366 | graph reallocs = 0 / 0 (same size) / (changed size) 0.06.532.566 I slot release: id 0 | task 366 | stop processing: n_tokens = 541, truncated = 0 0.06.554.741 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 541, t_last = 6439601 0.06.582.195 I slot launch_slot_: id 0 | task 441 | processing task, is_child = 0 0.06.989.993 I slot print_timing: id 0 | task 441 | prompt eval time = 91.17 ms / 345 tokens ( 0.26 ms per token, 3784.22 tokens per second) 0.06.989.999 I slot print_timing: id 0 | task 441 | eval time = 316.61 ms / 47 tokens ( 6.88 ms per token, 145.29 tokens per second) 0.06.990.000 I slot print_timing: id 0 | task 441 | total time = 407.78 ms / 392 tokens 0.06.990.001 I slot print_timing: id 0 | task 441 | graphs reused = 446 0.06.990.002 I slot print_timing: id 0 | task 441 | graph reallocs = 0 / 0 (same size) / (changed size) 0.06.990.028 I slot release: id 0 | task 441 | stop processing: n_tokens = 391, truncated = 0 0.07.006.682 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 391, t_last = 6897063 0.07.031.838 I slot launch_slot_: id 0 | task 491 | processing task, is_child = 0 0.07.494.005 I slot print_timing: id 0 | task 491 | prompt eval time = 91.75 ms / 364 tokens ( 0.25 ms per token, 3967.48 tokens per second) 0.07.494.010 I slot print_timing: id 0 | task 491 | eval time = 370.40 ms / 55 tokens ( 6.86 ms per token, 145.79 tokens per second) 0.07.494.011 I slot print_timing: id 0 | task 491 | total time = 462.15 ms / 419 tokens 0.07.494.012 I slot print_timing: id 0 | task 491 | graphs reused = 499 0.07.494.013 I slot print_timing: id 0 | task 491 | graph reallocs = 0 / 0 (same size) / (changed size) 0.07.494.038 I slot release: id 0 | task 491 | stop processing: n_tokens = 418, truncated = 0 0.07.509.623 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 418, t_last = 7401074 0.07.535.875 I slot launch_slot_: id 0 | task 549 | processing task, is_child = 0 0.08.080.787 I slot print_timing: id 0 | task 549 | prompt eval time = 94.45 ms / 376 tokens ( 0.25 ms per token, 3980.82 tokens per second) 0.08.080.793 I slot print_timing: id 0 | task 549 | eval time = 450.44 ms / 62 tokens ( 7.38 ms per token, 135.42 tokens per second) 0.08.080.794 I slot print_timing: id 0 | task 549 | total time = 544.89 ms / 438 tokens 0.08.080.794 I slot print_timing: id 0 | task 549 | graphs reused = 559 0.08.080.795 I slot print_timing: id 0 | task 549 | graph reallocs = 0 / 0 (same size) / (changed size) 0.08.080.822 I slot release: id 0 | task 549 | stop processing: n_tokens = 437, truncated = 0 0.08.104.185 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 7987857 0.08.130.266 I slot launch_slot_: id 0 | task 614 | processing task, is_child = 0 0.08.541.074 I slot print_timing: id 0 | task 614 | prompt eval time = 94.78 ms / 412 tokens ( 0.23 ms per token, 4346.82 tokens per second) 0.08.541.080 I slot print_timing: id 0 | task 614 | eval time = 316.01 ms / 47 tokens ( 6.87 ms per token, 145.57 tokens per second) 0.08.541.081 I slot print_timing: id 0 | task 614 | total time = 410.79 ms / 459 tokens 0.08.541.082 I slot print_timing: id 0 | task 614 | graphs reused = 604 0.08.541.083 I slot print_timing: id 0 | task 614 | graph reallocs = 0 / 0 (same size) / (changed size) 0.08.541.112 I slot release: id 0 | task 614 | stop processing: n_tokens = 458, truncated = 0 0.08.555.117 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 8448148 0.08.586.181 I slot launch_slot_: id 0 | task 664 | processing task, is_child = 0 0.09.096.260 I slot print_timing: id 0 | task 664 | prompt eval time = 92.94 ms / 376 tokens ( 0.25 ms per token, 4045.71 tokens per second) 0.09.096.266 I slot print_timing: id 0 | task 664 | eval time = 417.12 ms / 62 tokens ( 6.84 ms per token, 146.24 tokens per second) 0.09.096.267 I slot print_timing: id 0 | task 664 | total time = 510.06 ms / 438 tokens 0.09.096.268 I slot print_timing: id 0 | task 664 | graphs reused = 664 0.09.096.269 I slot print_timing: id 0 | task 664 | graph reallocs = 0 / 0 (same size) / (changed size) 0.09.096.293 I slot release: id 0 | task 664 | stop processing: n_tokens = 437, truncated = 0 0.09.117.734 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 9003329 0.09.143.239 I slot launch_slot_: id 0 | task 729 | processing task, is_child = 0 0.09.587.481 I slot print_timing: id 0 | task 729 | prompt eval time = 93.71 ms / 378 tokens ( 0.25 ms per token, 4033.76 tokens per second) 0.09.587.487 I slot print_timing: id 0 | task 729 | eval time = 350.51 ms / 52 tokens ( 6.87 ms per token, 145.50 tokens per second) 0.09.587.488 I slot print_timing: id 0 | task 729 | total time = 444.22 ms / 430 tokens 0.09.587.489 I slot print_timing: id 0 | task 729 | graphs reused = 714 0.09.587.490 I slot print_timing: id 0 | task 729 | graph reallocs = 0 / 0 (same size) / (changed size) 0.09.587.518 I slot release: id 0 | task 729 | stop processing: n_tokens = 429, truncated = 0 0.09.616.770 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 429, t_last = 9494553 0.09.641.900 I slot launch_slot_: id 0 | task 784 | processing task, is_child = 0 0.10.153.959 I slot print_timing: id 0 | task 784 | prompt eval time = 93.78 ms / 367 tokens ( 0.26 ms per token, 3913.46 tokens per second) 0.10.153.964 I slot print_timing: id 0 | task 784 | eval time = 418.26 ms / 58 tokens ( 7.34 ms per token, 136.28 tokens per second) 0.10.153.965 I slot print_timing: id 0 | task 784 | total time = 512.04 ms / 425 tokens 0.10.153.966 I slot print_timing: id 0 | task 784 | graphs reused = 770 0.10.153.967 I slot print_timing: id 0 | task 784 | graph reallocs = 0 / 0 (same size) / (changed size) 0.10.153.994 I slot release: id 0 | task 784 | stop processing: n_tokens = 424, truncated = 0 0.10.179.641 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 10061029 0.10.205.366 I slot launch_slot_: id 0 | task 845 | processing task, is_child = 0 0.10.638.187 I slot print_timing: id 0 | task 845 | prompt eval time = 89.68 ms / 347 tokens ( 0.26 ms per token, 3869.44 tokens per second) 0.10.638.193 I slot print_timing: id 0 | task 845 | eval time = 343.12 ms / 51 tokens ( 6.86 ms per token, 145.72 tokens per second) 0.10.638.194 I slot print_timing: id 0 | task 845 | total time = 432.80 ms / 398 tokens 0.10.638.194 I slot print_timing: id 0 | task 845 | graphs reused = 819 0.10.638.195 I slot print_timing: id 0 | task 845 | graph reallocs = 0 / 0 (same size) / (changed size) 0.10.638.225 I slot release: id 0 | task 845 | stop processing: n_tokens = 397, truncated = 0 0.10.656.035 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 397, t_last = 10545261 0.10.681.044 I slot launch_slot_: id 0 | task 899 | processing task, is_child = 0 0.12.911.115 I slot print_timing: id 0 | task 899 | prompt eval time = 90.92 ms / 369 tokens ( 0.25 ms per token, 4058.38 tokens per second) 0.12.911.120 I slot print_timing: id 0 | task 899 | eval time = 2139.13 ms / 315 tokens ( 6.81 ms per token, 146.79 tokens per second) 0.12.911.121 I slot print_timing: id 0 | task 899 | total time = 2230.05 ms / 684 tokens 0.12.911.122 I slot print_timing: id 0 | task 899 | graphs reused = 1131 0.12.911.123 I slot print_timing: id 0 | task 899 | graph reallocs = 0 / 0 (same size) / (changed size) 0.12.911.150 I slot release: id 0 | task 899 | stop processing: n_tokens = 683, truncated = 0 0.12.936.380 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 683, t_last = 12818186 0.12.963.336 I slot launch_slot_: id 0 | task 1217 | processing task, is_child = 0 0.13.328.241 I slot print_timing: id 0 | task 1217 | prompt eval time = 89.46 ms / 352 tokens ( 0.25 ms per token, 3934.59 tokens per second) 0.13.328.247 I slot print_timing: id 0 | task 1217 | eval time = 275.42 ms / 41 tokens ( 6.89 ms per token, 145.23 tokens per second) 0.13.328.248 I slot print_timing: id 0 | task 1217 | total time = 364.88 ms / 393 tokens 0.13.328.249 I slot print_timing: id 0 | task 1217 | graphs reused = 1170 0.13.328.249 I slot print_timing: id 0 | task 1217 | graph reallocs = 0 / 0 (same size) / (changed size) 0.13.328.275 I slot release: id 0 | task 1217 | stop processing: n_tokens = 392, truncated = 0 0.13.354.996 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 392, t_last = 13235311 0.13.380.119 I slot launch_slot_: id 0 | task 1261 | processing task, is_child = 0 0.13.737.653 I slot print_timing: id 0 | task 1261 | prompt eval time = 89.01 ms / 349 tokens ( 0.26 ms per token, 3921.04 tokens per second) 0.13.737.659 I slot print_timing: id 0 | task 1261 | eval time = 268.50 ms / 40 tokens ( 6.88 ms per token, 145.25 tokens per second) 0.13.737.660 I slot print_timing: id 0 | task 1261 | total time = 357.51 ms / 389 tokens 0.13.737.660 I slot print_timing: id 0 | task 1261 | graphs reused = 1208 0.13.737.661 I slot print_timing: id 0 | task 1261 | graph reallocs = 0 / 0 (same size) / (changed size) 0.13.737.687 I slot release: id 0 | task 1261 | stop processing: n_tokens = 388, truncated = 0 0.13.760.211 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 388, t_last = 13644723 0.13.785.404 I slot launch_slot_: id 0 | task 1304 | processing task, is_child = 0 0.14.332.211 I slot print_timing: id 0 | task 1304 | prompt eval time = 94.23 ms / 384 tokens ( 0.25 ms per token, 4075.14 tokens per second) 0.14.332.217 I slot print_timing: id 0 | task 1304 | eval time = 452.56 ms / 63 tokens ( 7.30 ms per token, 137.00 tokens per second) 0.14.332.219 I slot print_timing: id 0 | task 1304 | total time = 546.79 ms / 447 tokens 0.14.332.219 I slot print_timing: id 0 | task 1304 | graphs reused = 1269 0.14.332.220 I slot print_timing: id 0 | task 1304 | graph reallocs = 0 / 0 (same size) / (changed size) 0.14.332.250 I slot release: id 0 | task 1304 | stop processing: n_tokens = 446, truncated = 0 0.14.356.772 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 446, t_last = 14239286 0.14.382.437 I slot launch_slot_: id 0 | task 1370 | processing task, is_child = 0 0.14.836.238 I slot print_timing: id 0 | task 1370 | prompt eval time = 89.38 ms / 356 tokens ( 0.25 ms per token, 3983.08 tokens per second) 0.14.836.243 I slot print_timing: id 0 | task 1370 | eval time = 364.40 ms / 54 tokens ( 6.88 ms per token, 145.44 tokens per second) 0.14.836.245 I slot print_timing: id 0 | task 1370 | total time = 453.78 ms / 410 tokens 0.14.836.245 I slot print_timing: id 0 | task 1370 | graphs reused = 1321 0.14.836.246 I slot print_timing: id 0 | task 1370 | graph reallocs = 0 / 0 (same size) / (changed size) 0.14.836.273 I slot release: id 0 | task 1370 | stop processing: n_tokens = 409, truncated = 0 0.14.854.076 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 14743309 0.14.879.536 I slot launch_slot_: id 0 | task 1427 | processing task, is_child = 0 0.15.447.199 I slot print_timing: id 0 | task 1427 | prompt eval time = 95.12 ms / 410 tokens ( 0.23 ms per token, 4310.25 tokens per second) 0.15.447.205 I slot print_timing: id 0 | task 1427 | eval time = 472.52 ms / 70 tokens ( 6.85 ms per token, 146.03 tokens per second) 0.15.447.206 I slot print_timing: id 0 | task 1427 | total time = 567.64 ms / 480 tokens 0.15.447.207 I slot print_timing: id 0 | task 1427 | graphs reused = 1389 0.15.447.207 I slot print_timing: id 0 | task 1427 | graph reallocs = 0 / 0 (same size) / (changed size) 0.15.447.235 I slot release: id 0 | task 1427 | stop processing: n_tokens = 479, truncated = 0 0.15.461.683 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 479, t_last = 15354271 0.15.488.065 I slot launch_slot_: id 0 | task 1500 | processing task, is_child = 0 0.15.973.954 I slot print_timing: id 0 | task 1500 | prompt eval time = 94.39 ms / 385 tokens ( 0.25 ms per token, 4078.82 tokens per second) 0.15.973.960 I slot print_timing: id 0 | task 1500 | eval time = 391.48 ms / 58 tokens ( 6.87 ms per token, 145.60 tokens per second) 0.15.973.961 I slot print_timing: id 0 | task 1500 | total time = 485.87 ms / 443 tokens 0.15.973.962 I slot print_timing: id 0 | task 1500 | graphs reused = 1445 0.15.973.963 I slot print_timing: id 0 | task 1500 | graph reallocs = 0 / 0 (same size) / (changed size) 0.15.973.990 I slot release: id 0 | task 1500 | stop processing: n_tokens = 442, truncated = 0 0.15.988.721 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 442, t_last = 15881026 0.16.014.546 I slot launch_slot_: id 0 | task 1561 | processing task, is_child = 0 0.16.589.149 I slot print_timing: id 0 | task 1561 | prompt eval time = 96.18 ms / 395 tokens ( 0.24 ms per token, 4106.93 tokens per second) 0.16.589.154 I slot print_timing: id 0 | task 1561 | eval time = 478.40 ms / 71 tokens ( 6.83 ms per token, 146.32 tokens per second) 0.16.589.155 I slot print_timing: id 0 | task 1561 | total time = 574.58 ms / 466 tokens 0.16.589.156 I slot print_timing: id 0 | task 1561 | graphs reused = 1514 0.16.589.157 I slot print_timing: id 0 | task 1561 | graph reallocs = 0 / 0 (same size) / (changed size) 0.16.589.184 I slot release: id 0 | task 1561 | stop processing: n_tokens = 465, truncated = 0 0.16.614.996 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 465, t_last = 16496220 0.16.640.412 I slot launch_slot_: id 0 | task 1635 | processing task, is_child = 0 0.17.135.442 I slot print_timing: id 0 | task 1635 | prompt eval time = 96.61 ms / 430 tokens ( 0.22 ms per token, 4451.12 tokens per second) 0.17.135.447 I slot print_timing: id 0 | task 1635 | eval time = 398.40 ms / 59 tokens ( 6.87 ms per token, 145.58 tokens per second) 0.17.135.449 I slot print_timing: id 0 | task 1635 | total time = 495.01 ms / 489 tokens 0.17.135.449 I slot print_timing: id 0 | task 1635 | graphs reused = 1571 0.17.135.450 I slot print_timing: id 0 | task 1635 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.135.479 I slot release: id 0 | task 1635 | stop processing: n_tokens = 488, truncated = 0 0.17.164.469 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 488, t_last = 17042515 0.17.190.694 I slot launch_slot_: id 0 | task 1697 | processing task, is_child = 0 0.17.703.111 I slot print_timing: id 0 | task 1697 | prompt eval time = 94.62 ms / 392 tokens ( 0.24 ms per token, 4143.06 tokens per second) 0.17.703.116 I slot print_timing: id 0 | task 1697 | eval time = 417.78 ms / 62 tokens ( 6.85 ms per token, 146.01 tokens per second) 0.17.703.117 I slot print_timing: id 0 | task 1697 | total time = 512.40 ms / 454 tokens 0.17.703.118 I slot print_timing: id 0 | task 1697 | graphs reused = 1631 0.17.703.118 I slot print_timing: id 0 | task 1697 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.703.147 I slot release: id 0 | task 1697 | stop processing: n_tokens = 453, truncated = 0 0.17.728.694 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 453, t_last = 17610183 0.17.754.023 I slot launch_slot_: id 0 | task 1762 | processing task, is_child = 0 0.18.172.562 I slot print_timing: id 0 | task 1762 | prompt eval time = 88.48 ms / 350 tokens ( 0.25 ms per token, 3955.70 tokens per second) 0.18.172.568 I slot print_timing: id 0 | task 1762 | eval time = 330.04 ms / 49 tokens ( 6.88 ms per token, 145.44 tokens per second) 0.18.172.569 I slot print_timing: id 0 | task 1762 | total time = 418.52 ms / 399 tokens 0.18.172.569 I slot print_timing: id 0 | task 1762 | graphs reused = 1678 0.18.172.570 I slot print_timing: id 0 | task 1762 | graph reallocs = 0 / 0 (same size) / (changed size) 0.18.172.598 I slot release: id 0 | task 1762 | stop processing: n_tokens = 398, truncated = 0 0.18.197.084 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 398, t_last = 18079633 0.18.222.710 I slot launch_slot_: id 0 | task 1814 | processing task, is_child = 0 0.18.728.129 I slot print_timing: id 0 | task 1814 | prompt eval time = 94.11 ms / 380 tokens ( 0.25 ms per token, 4037.87 tokens per second) 0.18.728.134 I slot print_timing: id 0 | task 1814 | eval time = 411.29 ms / 61 tokens ( 6.85 ms per token, 145.88 tokens per second) 0.18.728.135 I slot print_timing: id 0 | task 1814 | total time = 505.40 ms / 441 tokens 0.18.728.137 I slot print_timing: id 0 | task 1814 | graphs reused = 1737 0.18.728.138 I slot print_timing: id 0 | task 1814 | graph reallocs = 0 / 0 (same size) / (changed size) 0.18.728.168 I slot release: id 0 | task 1814 | stop processing: n_tokens = 440, truncated = 0 0.18.743.215 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 440, t_last = 18635204 0.18.768.785 I slot launch_slot_: id 0 | task 1878 | processing task, is_child = 0 0.19.433.680 I slot print_timing: id 0 | task 1878 | prompt eval time = 96.93 ms / 410 tokens ( 0.24 ms per token, 4229.73 tokens per second) 0.19.433.686 I slot print_timing: id 0 | task 1878 | eval time = 567.94 ms / 80 tokens ( 7.19 ms per token, 139.10 tokens per second) 0.19.433.687 I slot print_timing: id 0 | task 1878 | total time = 664.88 ms / 490 tokens 0.19.433.688 I slot print_timing: id 0 | task 1878 | graphs reused = 1815 0.19.433.689 I slot print_timing: id 0 | task 1878 | graph reallocs = 0 / 0 (same size) / (changed size) 0.19.433.718 I slot release: id 0 | task 1878 | stop processing: n_tokens = 489, truncated = 0 0.19.453.083 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 489, t_last = 19340754 0.19.478.850 I slot launch_slot_: id 0 | task 1961 | processing task, is_child = 0 0.20.031.645 I slot print_timing: id 0 | task 1961 | prompt eval time = 94.40 ms / 387 tokens ( 0.24 ms per token, 4099.49 tokens per second) 0.20.031.650 I slot print_timing: id 0 | task 1961 | eval time = 458.37 ms / 68 tokens ( 6.84 ms per token, 146.17 tokens per second) 0.20.031.651 I slot print_timing: id 0 | task 1961 | total time = 552.78 ms / 455 tokens 0.20.031.652 I slot print_timing: id 0 | task 1961 | graphs reused = 1881 0.20.031.653 I slot print_timing: id 0 | task 1961 | graph reallocs = 0 / 0 (same size) / (changed size) 0.20.031.682 I slot release: id 0 | task 1961 | stop processing: n_tokens = 454, truncated = 0 0.20.048.339 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 454, t_last = 19938717 0.20.074.080 I slot launch_slot_: id 0 | task 2032 | processing task, is_child = 0 0.20.560.731 I slot print_timing: id 0 | task 2032 | prompt eval time = 89.28 ms / 358 tokens ( 0.25 ms per token, 4009.77 tokens per second) 0.20.560.736 I slot print_timing: id 0 | task 2032 | eval time = 397.35 ms / 59 tokens ( 6.85 ms per token, 145.97 tokens per second) 0.20.560.737 I slot print_timing: id 0 | task 2032 | total time = 486.63 ms / 417 tokens 0.20.560.738 I slot print_timing: id 0 | task 2032 | graphs reused = 1938 0.20.560.739 I slot print_timing: id 0 | task 2032 | graph reallocs = 0 / 0 (same size) / (changed size) 0.20.560.768 I slot release: id 0 | task 2032 | stop processing: n_tokens = 416, truncated = 0 0.20.581.230 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 20467803 0.20.607.393 I slot launch_slot_: id 0 | task 2094 | processing task, is_child = 0 0.21.103.646 I slot print_timing: id 0 | task 2094 | prompt eval time = 90.03 ms / 359 tokens ( 0.25 ms per token, 3987.47 tokens per second) 0.21.103.652 I slot print_timing: id 0 | task 2094 | eval time = 406.20 ms / 56 tokens ( 7.39 ms per token, 135.40 tokens per second) 0.21.103.653 I slot print_timing: id 0 | task 2094 | total time = 496.23 ms / 415 tokens 0.21.103.654 I slot print_timing: id 0 | task 2094 | graphs reused = 1992 0.21.103.654 I slot print_timing: id 0 | task 2094 | graph reallocs = 0 / 0 (same size) / (changed size) 0.21.103.680 I slot release: id 0 | task 2094 | stop processing: n_tokens = 414, truncated = 0 0.21.125.176 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 21010715 0.21.150.600 I slot launch_slot_: id 0 | task 2153 | processing task, is_child = 0 0.21.655.019 I slot print_timing: id 0 | task 2153 | prompt eval time = 93.06 ms / 387 tokens ( 0.24 ms per token, 4158.65 tokens per second) 0.21.655.024 I slot print_timing: id 0 | task 2153 | eval time = 411.34 ms / 61 tokens ( 6.86 ms per token, 145.86 tokens per second) 0.21.655.025 I slot print_timing: id 0 | task 2153 | total time = 504.40 ms / 448 tokens 0.21.655.026 I slot print_timing: id 0 | task 2153 | graphs reused = 2051 0.21.655.027 I slot print_timing: id 0 | task 2153 | graph reallocs = 0 / 0 (same size) / (changed size) 0.21.655.055 I slot release: id 0 | task 2153 | stop processing: n_tokens = 447, truncated = 0 0.21.676.722 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 21562091 0.21.703.442 I slot launch_slot_: id 0 | task 2217 | processing task, is_child = 0 0.22.210.543 I slot print_timing: id 0 | task 2217 | prompt eval time = 94.94 ms / 410 tokens ( 0.23 ms per token, 4318.65 tokens per second) 0.22.210.548 I slot print_timing: id 0 | task 2217 | eval time = 412.14 ms / 61 tokens ( 6.87 ms per token, 145.58 tokens per second) 0.22.210.549 I slot print_timing: id 0 | task 2217 | total time = 507.08 ms / 471 tokens 0.22.210.550 I slot print_timing: id 0 | task 2217 | graphs reused = 2110 0.22.210.551 I slot print_timing: id 0 | task 2217 | graph reallocs = 0 / 0 (same size) / (changed size) 0.22.210.580 I slot release: id 0 | task 2217 | stop processing: n_tokens = 470, truncated = 0 0.22.226.720 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 22117616 0.22.252.494 I slot launch_slot_: id 0 | task 2281 | processing task, is_child = 0 0.22.678.701 I slot print_timing: id 0 | task 2281 | prompt eval time = 88.29 ms / 351 tokens ( 0.25 ms per token, 3975.58 tokens per second) 0.22.678.708 I slot print_timing: id 0 | task 2281 | eval time = 337.89 ms / 50 tokens ( 6.90 ms per token, 145.02 tokens per second) 0.22.678.709 I slot print_timing: id 0 | task 2281 | total time = 426.18 ms / 401 tokens 0.22.678.710 I slot print_timing: id 0 | task 2281 | graphs reused = 2158 0.22.678.712 I slot print_timing: id 0 | task 2281 | graph reallocs = 0 / 0 (same size) / (changed size) 0.22.678.742 I slot release: id 0 | task 2281 | stop processing: n_tokens = 400, truncated = 0 0.22.682.502 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 22585778 0.22.709.942 I slot launch_slot_: id 0 | task 2334 | processing task, is_child = 0 0.24.330.149 I slot print_timing: id 0 | task 2334 | prompt eval time = 97.85 ms / 393 tokens ( 0.25 ms per token, 4016.27 tokens per second) 0.24.330.154 I slot print_timing: id 0 | task 2334 | eval time = 1522.33 ms / 224 tokens ( 6.83 ms per token, 146.49 tokens per second) 0.24.330.155 I slot print_timing: id 0 | task 2334 | total time = 1620.19 ms / 617 tokens 0.24.330.156 I slot print_timing: id 0 | task 2334 | graphs reused = 2379 0.24.330.157 I slot print_timing: id 0 | task 2334 | graph reallocs = 0 / 0 (same size) / (changed size) 0.24.330.186 I slot release: id 0 | task 2334 | stop processing: n_tokens = 616, truncated = 0 0.24.356.781 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 616, t_last = 24237222 0.24.383.091 I slot launch_slot_: id 0 | task 2561 | processing task, is_child = 0 0.24.672.288 I slot print_timing: id 0 | task 2561 | prompt eval time = 87.76 ms / 321 tokens ( 0.27 ms per token, 3657.87 tokens per second) 0.24.672.293 I slot print_timing: id 0 | task 2561 | eval time = 201.42 ms / 30 tokens ( 6.95 ms per token, 143.98 tokens per second) 0.24.672.294 I slot print_timing: id 0 | task 2561 | total time = 289.18 ms / 351 tokens 0.24.672.295 I slot print_timing: id 0 | task 2561 | graphs reused = 2407 0.24.672.296 I slot print_timing: id 0 | task 2561 | graph reallocs = 0 / 0 (same size) / (changed size) 0.24.672.321 I slot release: id 0 | task 2561 | stop processing: n_tokens = 350, truncated = 0 0.24.686.732 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 350, t_last = 24579357 0.24.711.708 I slot launch_slot_: id 0 | task 2594 | processing task, is_child = 0 0.25.381.147 I slot print_timing: id 0 | task 2594 | prompt eval time = 89.20 ms / 330 tokens ( 0.27 ms per token, 3699.68 tokens per second) 0.25.381.153 I slot print_timing: id 0 | task 2594 | eval time = 580.22 ms / 86 tokens ( 6.83 ms per token, 146.50 tokens per second) 0.25.381.154 I slot print_timing: id 0 | task 2594 | total time = 669.42 ms / 416 tokens 0.25.381.155 I slot print_timing: id 0 | task 2594 | graphs reused = 2491 0.25.381.156 I slot print_timing: id 0 | task 2594 | graph reallocs = 0 / 0 (same size) / (changed size) 0.25.381.183 I slot release: id 0 | task 2594 | stop processing: n_tokens = 415, truncated = 0 0.25.404.982 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 415, t_last = 25288219 0.25.430.268 I slot launch_slot_: id 0 | task 2683 | processing task, is_child = 0 0.25.732.662 I slot print_timing: id 0 | task 2683 | prompt eval time = 87.95 ms / 341 tokens ( 0.26 ms per token, 3877.11 tokens per second) 0.25.732.669 I slot print_timing: id 0 | task 2683 | eval time = 214.42 ms / 32 tokens ( 6.92 ms per token, 144.58 tokens per second) 0.25.732.670 I slot print_timing: id 0 | task 2683 | total time = 302.37 ms / 373 tokens 0.25.732.671 I slot print_timing: id 0 | task 2683 | graphs reused = 2521 0.25.732.672 I slot print_timing: id 0 | task 2683 | graph reallocs = 0 / 0 (same size) / (changed size) 0.25.732.703 I slot release: id 0 | task 2683 | stop processing: n_tokens = 372, truncated = 0 0.25.759.692 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 372, t_last = 25639739 0.25.784.696 I slot launch_slot_: id 0 | task 2718 | processing task, is_child = 0 0.26.200.365 I slot print_timing: id 0 | task 2718 | prompt eval time = 91.92 ms / 338 tokens ( 0.27 ms per token, 3677.23 tokens per second) 0.26.200.371 I slot print_timing: id 0 | task 2718 | eval time = 323.73 ms / 48 tokens ( 6.89 ms per token, 145.18 tokens per second) 0.26.200.372 I slot print_timing: id 0 | task 2718 | total time = 415.65 ms / 386 tokens 0.26.200.373 I slot print_timing: id 0 | task 2718 | graphs reused = 2567 0.26.200.374 I slot print_timing: id 0 | task 2718 | graph reallocs = 0 / 0 (same size) / (changed size) 0.26.200.400 I slot release: id 0 | task 2718 | stop processing: n_tokens = 385, truncated = 0 0.26.229.151 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 385, t_last = 26107436 0.26.255.642 I slot launch_slot_: id 0 | task 2769 | processing task, is_child = 0 0.26.727.967 I slot print_timing: id 0 | task 2769 | prompt eval time = 94.85 ms / 395 tokens ( 0.24 ms per token, 4164.56 tokens per second) 0.26.727.973 I slot print_timing: id 0 | task 2769 | eval time = 377.46 ms / 56 tokens ( 6.86 ms per token, 145.71 tokens per second) 0.26.727.974 I slot print_timing: id 0 | task 2769 | total time = 472.30 ms / 451 tokens 0.26.727.975 I slot print_timing: id 0 | task 2769 | graphs reused = 2621 0.26.727.976 I slot print_timing: id 0 | task 2769 | graph reallocs = 0 / 0 (same size) / (changed size) 0.26.728.005 I slot release: id 0 | task 2769 | stop processing: n_tokens = 450, truncated = 0 0.26.745.761 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 450, t_last = 26635041 0.26.772.217 I slot launch_slot_: id 0 | task 2828 | processing task, is_child = 0 0.27.465.768 I slot print_timing: id 0 | task 2828 | prompt eval time = 131.33 ms / 528 tokens ( 0.25 ms per token, 4020.31 tokens per second) 0.27.465.774 I slot print_timing: id 0 | task 2828 | eval time = 562.20 ms / 83 tokens ( 6.86 ms per token, 145.86 tokens per second) 0.27.465.775 I slot print_timing: id 0 | task 2828 | total time = 693.53 ms / 611 tokens 0.27.465.775 I slot print_timing: id 0 | task 2828 | graphs reused = 2702 0.27.465.776 I slot print_timing: id 0 | task 2828 | graph reallocs = 0 / 0 (same size) / (changed size) 0.27.465.811 I slot release: id 0 | task 2828 | stop processing: n_tokens = 610, truncated = 0 0.27.493.938 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 610, t_last = 27372846 0.27.525.983 I slot launch_slot_: id 0 | task 2915 | processing task, is_child = 0 0.27.937.218 I slot print_timing: id 0 | task 2915 | prompt eval time = 107.76 ms / 331 tokens ( 0.33 ms per token, 3071.53 tokens per second) 0.27.937.224 I slot print_timing: id 0 | task 2915 | eval time = 303.45 ms / 45 tokens ( 6.90 ms per token, 145.00 tokens per second) 0.27.937.225 I slot print_timing: id 0 | task 2915 | total time = 411.22 ms / 376 tokens 0.27.937.226 I slot print_timing: id 0 | task 2915 | graphs reused = 2745 0.27.937.227 I slot print_timing: id 0 | task 2915 | graph reallocs = 0 / 0 (same size) / (changed size) 0.27.937.254 I slot release: id 0 | task 2915 | stop processing: n_tokens = 387, truncated = 0 0.27.959.304 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 387, t_last = 27844290 0.27.990.416 I slot launch_slot_: id 0 | task 2963 | processing task, is_child = 0 0.28.460.127 I slot print_timing: id 0 | task 2963 | prompt eval time = 111.90 ms / 362 tokens ( 0.31 ms per token, 3235.06 tokens per second) 0.28.460.133 I slot print_timing: id 0 | task 2963 | eval time = 357.79 ms / 53 tokens ( 6.88 ms per token, 145.34 tokens per second) 0.28.460.134 I slot print_timing: id 0 | task 2963 | total time = 469.69 ms / 415 tokens 0.28.460.134 I slot print_timing: id 0 | task 2963 | graphs reused = 2796 0.28.460.135 I slot print_timing: id 0 | task 2963 | graph reallocs = 0 / 0 (same size) / (changed size) 0.28.460.164 I slot release: id 0 | task 2963 | stop processing: n_tokens = 426, truncated = 0 0.28.475.152 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 28367199 0.28.506.079 I slot launch_slot_: id 0 | task 3019 | processing task, is_child = 0 0.29.086.251 I slot print_timing: id 0 | task 3019 | prompt eval time = 114.86 ms / 419 tokens ( 0.27 ms per token, 3648.08 tokens per second) 0.29.086.257 I slot print_timing: id 0 | task 3019 | eval time = 465.30 ms / 69 tokens ( 6.84 ms per token, 146.14 tokens per second) 0.29.086.258 I slot print_timing: id 0 | task 3019 | total time = 580.15 ms / 488 tokens 0.29.086.260 I slot print_timing: id 0 | task 3019 | graphs reused = 2863 0.29.086.260 I slot print_timing: id 0 | task 3019 | graph reallocs = 0 / 0 (same size) / (changed size) 0.29.086.288 I slot release: id 0 | task 3019 | stop processing: n_tokens = 499, truncated = 0 0.29.099.526 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 499, t_last = 28993324 0.29.131.563 I slot launch_slot_: id 0 | task 3091 | processing task, is_child = 0 0.29.805.632 I slot print_timing: id 0 | task 3091 | prompt eval time = 127.49 ms / 423 tokens ( 0.30 ms per token, 3317.86 tokens per second) 0.29.805.638 I slot print_timing: id 0 | task 3091 | eval time = 546.56 ms / 72 tokens ( 7.70 ms per token, 129.90 tokens per second) 0.29.805.639 I slot print_timing: id 0 | task 3091 | total time = 674.05 ms / 495 tokens 0.29.805.639 I slot print_timing: id 0 | task 3091 | graphs reused = 2933 0.29.805.640 I slot print_timing: id 0 | task 3091 | graph reallocs = 0 / 0 (same size) / (changed size) 0.29.805.670 I slot release: id 0 | task 3091 | stop processing: n_tokens = 506, truncated = 0 0.29.834.321 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 506, t_last = 29712706 0.29.866.917 I slot launch_slot_: id 0 | task 3166 | processing task, is_child = 0 0.30.266.070 I slot print_timing: id 0 | task 3166 | prompt eval time = 110.15 ms / 341 tokens ( 0.32 ms per token, 3095.72 tokens per second) 0.30.266.076 I slot print_timing: id 0 | task 3166 | eval time = 288.98 ms / 43 tokens ( 6.88 ms per token, 145.34 tokens per second) 0.30.266.077 I slot print_timing: id 0 | task 3166 | total time = 399.13 ms / 384 tokens 0.30.266.078 I slot print_timing: id 0 | task 3166 | graphs reused = 2974 0.30.266.079 I slot print_timing: id 0 | task 3166 | graph reallocs = 0 / 0 (same size) / (changed size) 0.30.266.106 I slot release: id 0 | task 3166 | stop processing: n_tokens = 395, truncated = 0 0.30.280.811 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 395, t_last = 30173142 0.30.331.644 I slot launch_slot_: id 0 | task 3212 | processing task, is_child = 0 0.30.758.991 I slot print_timing: id 0 | task 3212 | prompt eval time = 111.66 ms / 356 tokens ( 0.31 ms per token, 3188.39 tokens per second) 0.30.758.996 I slot print_timing: id 0 | task 3212 | eval time = 315.67 ms / 47 tokens ( 6.86 ms per token, 145.72 tokens per second) 0.30.758.997 I slot print_timing: id 0 | task 3212 | total time = 427.33 ms / 403 tokens 0.30.758.999 I slot print_timing: id 0 | task 3212 | graphs reused = 3019 0.30.759.000 I slot print_timing: id 0 | task 3212 | graph reallocs = 0 / 0 (same size) / (changed size) 0.30.759.028 I slot release: id 0 | task 3212 | stop processing: n_tokens = 414, truncated = 0 0.30.782.956 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 30666064 0.30.783.000 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.887 MiB) 0.30.841.983 I slot launch_slot_: id 0 | task 3262 | processing task, is_child = 0 0.31.267.852 I slot print_timing: id 0 | task 3262 | prompt eval time = 116.45 ms / 362 tokens ( 0.32 ms per token, 3108.55 tokens per second) 0.31.267.857 I slot print_timing: id 0 | task 3262 | eval time = 309.40 ms / 46 tokens ( 6.88 ms per token, 145.44 tokens per second) 0.31.267.858 I slot print_timing: id 0 | task 3262 | total time = 425.85 ms / 408 tokens 0.31.267.859 I slot print_timing: id 0 | task 3262 | graphs reused = 3063 0.31.267.860 I slot print_timing: id 0 | task 3262 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.267.889 I slot release: id 0 | task 3262 | stop processing: n_tokens = 419, truncated = 0 0.31.281.564 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 31174924 0.31.281.611 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.104 MiB) 0.31.338.400 I slot launch_slot_: id 0 | task 3311 | processing task, is_child = 0 0.31.915.084 I slot print_timing: id 0 | task 3311 | prompt eval time = 117.72 ms / 391 tokens ( 0.30 ms per token, 3321.44 tokens per second) 0.31.915.090 I slot print_timing: id 0 | task 3311 | eval time = 458.94 ms / 68 tokens ( 6.85 ms per token, 145.99 tokens per second) 0.31.915.091 I slot print_timing: id 0 | task 3311 | total time = 576.66 ms / 459 tokens 0.31.915.092 I slot print_timing: id 0 | task 3311 | graphs reused = 3129 0.31.915.093 I slot print_timing: id 0 | task 3311 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.915.121 I slot release: id 0 | task 3311 | stop processing: n_tokens = 470, truncated = 0 0.31.934.921 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 31822157 0.31.934.969 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.449 MiB) 0.31.945.038 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.481 MiB) 0.32.005.566 I slot launch_slot_: id 0 | task 3382 | processing task, is_child = 0 0.32.483.461 I slot print_timing: id 0 | task 3382 | prompt eval time = 114.07 ms / 343 tokens ( 0.33 ms per token, 3007.00 tokens per second) 0.32.483.467 I slot print_timing: id 0 | task 3382 | eval time = 363.81 ms / 54 tokens ( 6.86 ms per token, 145.68 tokens per second) 0.32.483.468 I slot print_timing: id 0 | task 3382 | total time = 477.88 ms / 397 tokens 0.32.483.469 I slot print_timing: id 0 | task 3382 | graphs reused = 3181 0.32.483.470 I slot print_timing: id 0 | task 3382 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.483.499 I slot release: id 0 | task 3382 | stop processing: n_tokens = 408, truncated = 0 0.32.498.509 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 408, t_last = 32390535 0.32.498.549 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 0.32.556.469 I slot launch_slot_: id 0 | task 3439 | processing task, is_child = 0 0.32.983.542 I slot print_timing: id 0 | task 3439 | prompt eval time = 117.56 ms / 401 tokens ( 0.29 ms per token, 3411.17 tokens per second) 0.32.983.548 I slot print_timing: id 0 | task 3439 | eval time = 309.50 ms / 46 tokens ( 6.88 ms per token, 145.40 tokens per second) 0.32.983.549 I slot print_timing: id 0 | task 3439 | total time = 427.05 ms / 447 tokens 0.32.983.550 I slot print_timing: id 0 | task 3439 | graphs reused = 3225 0.32.983.550 I slot print_timing: id 0 | task 3439 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.983.580 I slot release: id 0 | task 3439 | stop processing: n_tokens = 458, truncated = 0 0.33.012.028 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 32890616 0.33.012.069 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.074 MiB) 0.33.065.061 I slot launch_slot_: id 0 | task 3488 | processing task, is_child = 0 0.33.637.064 I slot print_timing: id 0 | task 3488 | prompt eval time = 113.87 ms / 355 tokens ( 0.32 ms per token, 3117.51 tokens per second) 0.33.637.069 I slot print_timing: id 0 | task 3488 | eval time = 458.11 ms / 68 tokens ( 6.84 ms per token, 146.25 tokens per second) 0.33.637.070 I slot print_timing: id 0 | task 3488 | total time = 571.98 ms / 423 tokens 0.33.637.071 I slot print_timing: id 0 | task 3488 | graphs reused = 3291 0.33.637.072 I slot print_timing: id 0 | task 3488 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.637.100 I slot release: id 0 | task 3488 | stop processing: n_tokens = 434, truncated = 0 0.33.660.450 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 434, t_last = 33544136 0.33.660.491 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.638 MiB) 0.33.715.896 I slot launch_slot_: id 0 | task 3559 | processing task, is_child = 0 0.34.242.912 I slot print_timing: id 0 | task 3559 | prompt eval time = 112.73 ms / 351 tokens ( 0.32 ms per token, 3113.69 tokens per second) 0.34.242.918 I slot print_timing: id 0 | task 3559 | eval time = 414.27 ms / 57 tokens ( 7.40 ms per token, 135.18 tokens per second) 0.34.242.919 I slot print_timing: id 0 | task 3559 | total time = 527.00 ms / 408 tokens 0.34.242.920 I slot print_timing: id 0 | task 3559 | graphs reused = 3346 0.34.242.920 I slot print_timing: id 0 | task 3559 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.242.948 I slot release: id 0 | task 3559 | stop processing: n_tokens = 419, truncated = 0 0.34.266.741 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 34149984 0.34.266.790 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 167.671 MiB) 0.34.277.351 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.980 MiB) 0.34.338.428 I slot launch_slot_: id 0 | task 3619 | processing task, is_child = 0 0.35.099.359 I slot print_timing: id 0 | task 3619 | prompt eval time = 127.00 ms / 475 tokens ( 0.27 ms per token, 3740.01 tokens per second) 0.35.099.365 I slot print_timing: id 0 | task 3619 | eval time = 633.90 ms / 93 tokens ( 6.89 ms per token, 145.13 tokens per second) 0.35.099.366 I slot print_timing: id 0 | task 3619 | total time = 760.91 ms / 568 tokens 0.35.099.367 I slot print_timing: id 0 | task 3619 | graphs reused = 3436 0.35.099.368 I slot print_timing: id 0 | task 3619 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.099.401 I slot release: id 0 | task 3619 | stop processing: n_tokens = 579, truncated = 0 0.35.124.839 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 579, t_last = 35006437 0.35.124.895 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.824 MiB) 0.35.174.315 I slot launch_slot_: id 0 | task 3715 | processing task, is_child = 0 0.35.929.919 I slot print_timing: id 0 | task 3715 | prompt eval time = 128.13 ms / 440 tokens ( 0.29 ms per token, 3434.12 tokens per second) 0.35.929.926 I slot print_timing: id 0 | task 3715 | eval time = 627.46 ms / 92 tokens ( 6.90 ms per token, 145.03 tokens per second) 0.35.929.927 I slot print_timing: id 0 | task 3715 | total time = 755.59 ms / 532 tokens 0.35.929.928 I slot print_timing: id 0 | task 3715 | graphs reused = 3525 0.35.929.929 I slot print_timing: id 0 | task 3715 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.929.959 I slot release: id 0 | task 3715 | stop processing: n_tokens = 543, truncated = 0 0.35.948.932 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 543, t_last = 35836994 0.35.948.986 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 0.36.004.015 I slot launch_slot_: id 0 | task 3810 | processing task, is_child = 0 0.36.501.049 I slot print_timing: id 0 | task 3810 | prompt eval time = 113.44 ms / 345 tokens ( 0.33 ms per token, 3041.26 tokens per second) 0.36.501.055 I slot print_timing: id 0 | task 3810 | eval time = 383.58 ms / 57 tokens ( 6.85 ms per token, 145.99 tokens per second) 0.36.501.056 I slot print_timing: id 0 | task 3810 | total time = 497.02 ms / 402 tokens 0.36.501.057 I slot print_timing: id 0 | task 3810 | graphs reused = 3580 0.36.501.058 I slot print_timing: id 0 | task 3810 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.501.087 I slot release: id 0 | task 3810 | stop processing: n_tokens = 413, truncated = 0 0.36.528.040 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 413, t_last = 36408123 0.36.528.087 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.075 MiB) 0.36.538.170 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 0.36.596.919 I slot launch_slot_: id 0 | task 3870 | processing task, is_child = 0 0.37.083.900 I slot print_timing: id 0 | task 3870 | prompt eval time = 116.89 ms / 382 tokens ( 0.31 ms per token, 3267.97 tokens per second) 0.37.083.906 I slot print_timing: id 0 | task 3870 | eval time = 370.07 ms / 55 tokens ( 6.85 ms per token, 145.92 tokens per second) 0.37.083.907 I slot print_timing: id 0 | task 3870 | total time = 486.96 ms / 437 tokens 0.37.083.908 I slot print_timing: id 0 | task 3870 | graphs reused = 3633 0.37.083.908 I slot print_timing: id 0 | task 3870 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.083.937 I slot release: id 0 | task 3870 | stop processing: n_tokens = 448, truncated = 0 0.37.107.250 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 36990973 0.37.107.297 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.168 MiB) 0.37.156.238 I slot launch_slot_: id 0 | task 3928 | processing task, is_child = 0 0.37.570.919 I slot print_timing: id 0 | task 3928 | prompt eval time = 111.80 ms / 337 tokens ( 0.33 ms per token, 3014.23 tokens per second) 0.37.570.924 I slot print_timing: id 0 | task 3928 | eval time = 302.86 ms / 45 tokens ( 6.88 ms per token, 145.28 tokens per second) 0.37.570.925 I slot print_timing: id 0 | task 3928 | total time = 414.66 ms / 382 tokens 0.37.570.926 I slot print_timing: id 0 | task 3928 | graphs reused = 3676 0.37.570.927 I slot print_timing: id 0 | task 3928 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.570.954 I slot release: id 0 | task 3928 | stop processing: n_tokens = 393, truncated = 0 0.37.588.690 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 37477990 0.37.588.736 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.012 MiB) 0.37.639.964 I slot launch_slot_: id 0 | task 3976 | processing task, is_child = 0 0.38.258.290 I slot print_timing: id 0 | task 3976 | prompt eval time = 115.26 ms / 402 tokens ( 0.29 ms per token, 3487.65 tokens per second) 0.38.258.296 I slot print_timing: id 0 | task 3976 | eval time = 503.04 ms / 70 tokens ( 7.29 ms per token, 137.17 tokens per second) 0.38.258.297 I slot print_timing: id 0 | task 3976 | total time = 618.31 ms / 472 tokens 0.38.258.298 I slot print_timing: id 0 | task 3976 | graphs reused = 3744 0.38.258.298 I slot print_timing: id 0 | task 3976 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.258.327 I slot release: id 0 | task 3976 | stop processing: n_tokens = 483, truncated = 0 0.38.273.512 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 483, t_last = 38165363 0.38.273.559 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.167 MiB) 0.38.283.604 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 172.111 MiB) 0.38.342.945 I slot launch_slot_: id 0 | task 4049 | processing task, is_child = 0 0.38.861.314 I slot print_timing: id 0 | task 4049 | prompt eval time = 133.59 ms / 549 tokens ( 0.24 ms per token, 4109.68 tokens per second) 0.38.861.320 I slot print_timing: id 0 | task 4049 | eval time = 384.76 ms / 57 tokens ( 6.87 ms per token, 145.54 tokens per second) 0.38.861.321 I slot print_timing: id 0 | task 4049 | total time = 518.35 ms / 606 tokens 0.38.861.323 I slot print_timing: id 0 | task 4049 | graphs reused = 3799 0.38.861.323 I slot print_timing: id 0 | task 4049 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.861.361 I slot release: id 0 | task 4049 | stop processing: n_tokens = 617, truncated = 0 0.38.877.635 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 617, t_last = 38768396 0.38.877.686 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.011 MiB) 0.38.946.440 I slot launch_slot_: id 0 | task 4110 | processing task, is_child = 0 0.39.483.663 I slot print_timing: id 0 | task 4110 | prompt eval time = 146.12 ms / 616 tokens ( 0.24 ms per token, 4215.57 tokens per second) 0.39.483.669 I slot print_timing: id 0 | task 4110 | eval time = 391.07 ms / 58 tokens ( 6.86 ms per token, 145.75 tokens per second) 0.39.483.670 I slot print_timing: id 0 | task 4110 | total time = 537.20 ms / 674 tokens 0.39.483.671 I slot print_timing: id 0 | task 4110 | graphs reused = 3855 0.39.483.671 I slot print_timing: id 0 | task 4110 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.483.707 I slot release: id 0 | task 4110 | stop processing: n_tokens = 685, truncated = 0 0.39.502.346 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 685, t_last = 39390743 0.39.502.406 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.886 MiB) 0.39.512.330 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.700 MiB) 0.39.582.762 I slot launch_slot_: id 0 | task 4172 | processing task, is_child = 0 0.40.146.477 I slot print_timing: id 0 | task 4172 | prompt eval time = 151.90 ms / 665 tokens ( 0.23 ms per token, 4377.94 tokens per second) 0.40.146.482 I slot print_timing: id 0 | task 4172 | eval time = 411.80 ms / 61 tokens ( 6.86 ms per token, 145.70 tokens per second) 0.40.146.483 I slot print_timing: id 0 | task 4172 | total time = 563.69 ms / 726 tokens 0.40.146.484 I slot print_timing: id 0 | task 4172 | graphs reused = 3914 0.40.146.485 I slot print_timing: id 0 | task 4172 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.146.521 I slot release: id 0 | task 4172 | stop processing: n_tokens = 737, truncated = 0 0.40.170.887 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 737, t_last = 40053557 0.40.170.950 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.543 MiB) 0.40.180.966 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.732 MiB) 0.40.248.697 I slot launch_slot_: id 0 | task 4237 | processing task, is_child = 0 0.40.769.952 I slot print_timing: id 0 | task 4237 | prompt eval time = 150.19 ms / 645 tokens ( 0.23 ms per token, 4294.62 tokens per second) 0.40.769.958 I slot print_timing: id 0 | task 4237 | eval time = 371.05 ms / 55 tokens ( 6.87 ms per token, 145.53 tokens per second) 0.40.769.959 I slot print_timing: id 0 | task 4237 | total time = 521.24 ms / 700 tokens 0.40.769.959 I slot print_timing: id 0 | task 4237 | graphs reused = 3967 0.40.769.960 I slot print_timing: id 0 | task 4237 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.769.995 I slot release: id 0 | task 4237 | stop processing: n_tokens = 711, truncated = 0 0.40.791.455 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 711, t_last = 40677031 0.40.791.518 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.575 MiB) 0.40.855.549 I slot launch_slot_: id 0 | task 4296 | processing task, is_child = 0 0.41.339.770 I slot print_timing: id 0 | task 4296 | prompt eval time = 129.61 ms / 474 tokens ( 0.27 ms per token, 3657.01 tokens per second) 0.41.339.776 I slot print_timing: id 0 | task 4296 | eval time = 354.59 ms / 52 tokens ( 6.95 ms per token, 143.83 tokens per second) 0.41.339.777 I slot print_timing: id 0 | task 4296 | total time = 484.20 ms / 526 tokens 0.41.339.778 I slot print_timing: id 0 | task 4296 | graphs reused = 4016 0.41.339.779 I slot print_timing: id 0 | task 4296 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.339.810 I slot release: id 0 | task 4296 | stop processing: n_tokens = 537, truncated = 0 0.41.353.947 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 537, t_last = 41246846 0.41.353.999 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.294 MiB) 0.41.364.142 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.013 MiB) 0.41.424.864 I slot launch_slot_: id 0 | task 4351 | processing task, is_child = 0 0.41.850.756 I slot print_timing: id 0 | task 4351 | prompt eval time = 142.27 ms / 617 tokens ( 0.23 ms per token, 4336.70 tokens per second) 0.41.850.762 I slot print_timing: id 0 | task 4351 | eval time = 283.60 ms / 42 tokens ( 6.92 ms per token, 144.57 tokens per second) 0.41.850.764 I slot print_timing: id 0 | task 4351 | total time = 425.87 ms / 659 tokens 0.41.850.764 I slot print_timing: id 0 | task 4351 | graphs reused = 4056 0.41.850.765 I slot print_timing: id 0 | task 4351 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.850.805 I slot release: id 0 | task 4351 | stop processing: n_tokens = 670, truncated = 0 0.41.872.332 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 670, t_last = 41757841 0.41.872.399 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.919 MiB) 0.41.945.469 I slot launch_slot_: id 0 | task 4397 | processing task, is_child = 0 0.42.414.117 I slot print_timing: id 0 | task 4397 | prompt eval time = 143.82 ms / 601 tokens ( 0.24 ms per token, 4178.89 tokens per second) 0.42.414.130 I slot print_timing: id 0 | task 4397 | eval time = 324.81 ms / 48 tokens ( 6.91 ms per token, 144.70 tokens per second) 0.42.414.132 I slot print_timing: id 0 | task 4397 | total time = 468.63 ms / 649 tokens 0.42.414.133 I slot print_timing: id 0 | task 4397 | graphs reused = 4102 0.42.414.134 I slot print_timing: id 0 | task 4397 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.414.174 I slot release: id 0 | task 4397 | stop processing: n_tokens = 660, truncated = 0 0.42.434.884 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 660, t_last = 42321209 0.42.434.945 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.199 MiB) 0.42.444.972 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.512 MiB) 0.42.519.591 I slot launch_slot_: id 0 | task 4449 | processing task, is_child = 0 0.42.976.664 I slot print_timing: id 0 | task 4449 | prompt eval time = 137.29 ms / 533 tokens ( 0.26 ms per token, 3882.41 tokens per second) 0.42.976.670 I slot print_timing: id 0 | task 4449 | eval time = 319.77 ms / 47 tokens ( 6.95 ms per token, 143.86 tokens per second) 0.42.976.671 I slot print_timing: id 0 | task 4449 | total time = 457.05 ms / 580 tokens 0.42.976.673 I slot print_timing: id 0 | task 4449 | graphs reused = 4147 0.42.976.674 I slot print_timing: id 0 | task 4449 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.976.706 I slot release: id 0 | task 4449 | stop processing: n_tokens = 591, truncated = 0 0.42.997.100 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 591, t_last = 42883742 0.42.997.155 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.044 MiB) 0.43.063.873 I slot launch_slot_: id 0 | task 4500 | processing task, is_child = 0 0.43.550.113 I slot print_timing: id 0 | task 4500 | prompt eval time = 131.21 ms / 480 tokens ( 0.27 ms per token, 3658.15 tokens per second) 0.43.550.119 I slot print_timing: id 0 | task 4500 | eval time = 355.01 ms / 52 tokens ( 6.96 ms per token, 143.66 tokens per second) 0.43.550.120 I slot print_timing: id 0 | task 4500 | total time = 486.22 ms / 532 tokens 0.43.550.121 I slot print_timing: id 0 | task 4500 | graphs reused = 4196 0.43.550.121 I slot print_timing: id 0 | task 4500 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.550.152 I slot release: id 0 | task 4500 | stop processing: n_tokens = 560, truncated = 0 0.43.576.273 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 43457188 0.43.576.326 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.950 MiB) 0.43.586.399 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.761 MiB) 0.43.648.461 I slot launch_slot_: id 0 | task 4555 | processing task, is_child = 0 0.44.067.243 I slot print_timing: id 0 | task 4555 | prompt eval time = 136.36 ms / 567 tokens ( 0.24 ms per token, 4158.11 tokens per second) 0.44.067.249 I slot print_timing: id 0 | task 4555 | eval time = 282.40 ms / 42 tokens ( 6.89 ms per token, 145.18 tokens per second) 0.44.067.250 I slot print_timing: id 0 | task 4555 | total time = 418.76 ms / 609 tokens 0.44.067.251 I slot print_timing: id 0 | task 4555 | graphs reused = 4236 0.44.067.251 I slot print_timing: id 0 | task 4555 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.067.286 I slot release: id 0 | task 4555 | stop processing: n_tokens = 637, truncated = 0 0.44.094.816 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 43974321 0.44.094.875 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.699 MiB) 0.44.104.829 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.731 MiB) 0.44.186.596 I slot launch_slot_: id 0 | task 4601 | processing task, is_child = 0 0.44.747.132 I slot print_timing: id 0 | task 4601 | prompt eval time = 134.23 ms / 506 tokens ( 0.27 ms per token, 3769.76 tokens per second) 0.44.747.138 I slot print_timing: id 0 | task 4601 | eval time = 426.29 ms / 63 tokens ( 6.88 ms per token, 145.44 tokens per second) 0.44.747.139 I slot print_timing: id 0 | task 4601 | total time = 560.52 ms / 569 tokens 0.44.747.139 I slot print_timing: id 0 | task 4601 | graphs reused = 4297 0.44.747.140 I slot print_timing: id 0 | task 4601 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.747.179 I slot release: id 0 | task 4601 | stop processing: n_tokens = 597, truncated = 0 0.44.768.131 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 597, t_last = 44654214 0.44.768.188 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.450 MiB) 0.44.778.305 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.261 MiB) 0.44.843.984 I slot launch_slot_: id 0 | task 4667 | processing task, is_child = 0 0.45.244.357 I slot print_timing: id 0 | task 4667 | prompt eval time = 125.75 ms / 436 tokens ( 0.29 ms per token, 3467.31 tokens per second) 0.45.244.362 I slot print_timing: id 0 | task 4667 | eval time = 274.60 ms / 40 tokens ( 7.04 ms per token, 142.02 tokens per second) 0.45.244.363 I slot print_timing: id 0 | task 4667 | total time = 400.35 ms / 476 tokens 0.45.244.364 I slot print_timing: id 0 | task 4667 | graphs reused = 4335 0.45.244.365 I slot print_timing: id 0 | task 4667 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.244.399 I slot release: id 0 | task 4667 | stop processing: n_tokens = 504, truncated = 0 0.45.271.972 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 45151435 0.45.272.022 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 170.016 MiB) 0.45.346.719 I slot launch_slot_: id 0 | task 4710 | processing task, is_child = 0 0.45.916.276 I slot print_timing: id 0 | task 4710 | prompt eval time = 143.06 ms / 519 tokens ( 0.28 ms per token, 3627.80 tokens per second) 0.45.916.282 I slot print_timing: id 0 | task 4710 | eval time = 426.48 ms / 62 tokens ( 6.99 ms per token, 143.03 tokens per second) 0.45.916.283 I slot print_timing: id 0 | task 4710 | total time = 569.54 ms / 581 tokens 0.45.916.283 I slot print_timing: id 0 | task 4710 | graphs reused = 4395 0.45.916.284 I slot print_timing: id 0 | task 4710 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.916.318 I slot release: id 0 | task 4710 | stop processing: n_tokens = 609, truncated = 0 0.45.943.458 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 609, t_last = 45823353 0.45.943.519 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 161.697 MiB) 0.45.953.400 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.730 MiB) 0.46.039.879 I slot launch_slot_: id 0 | task 4776 | processing task, is_child = 0 0.46.486.294 I slot print_timing: id 0 | task 4776 | prompt eval time = 128.05 ms / 465 tokens ( 0.28 ms per token, 3631.39 tokens per second) 0.46.486.301 I slot print_timing: id 0 | task 4776 | eval time = 318.35 ms / 46 tokens ( 7.07 ms per token, 141.36 tokens per second) 0.46.486.302 I slot print_timing: id 0 | task 4776 | total time = 446.40 ms / 511 tokens 0.46.486.302 I slot print_timing: id 0 | task 4776 | graphs reused = 4438 0.46.486.304 I slot print_timing: id 0 | task 4776 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.486.336 I slot release: id 0 | task 4776 | stop processing: n_tokens = 542, truncated = 0 0.46.503.128 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 542, t_last = 46393372 0.46.503.183 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.385 MiB) 0.46.513.247 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.792 MiB) 0.46.595.717 I slot launch_slot_: id 0 | task 4825 | processing task, is_child = 0 0.46.997.514 I slot print_timing: id 0 | task 4825 | prompt eval time = 122.07 ms / 431 tokens ( 0.28 ms per token, 3530.73 tokens per second) 0.46.997.520 I slot print_timing: id 0 | task 4825 | eval time = 279.71 ms / 41 tokens ( 6.99 ms per token, 143.01 tokens per second) 0.46.997.521 I slot print_timing: id 0 | task 4825 | total time = 401.78 ms / 472 tokens 0.46.997.522 I slot print_timing: id 0 | task 4825 | graphs reused = 4477 0.46.997.523 I slot print_timing: id 0 | task 4825 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.997.556 I slot release: id 0 | task 4825 | stop processing: n_tokens = 503, truncated = 0 0.47.001.569 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 503, t_last = 46904592 0.47.001.625 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.825 MiB) 0.47.013.020 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 220.079 MiB) 0.47.104.105 I slot launch_slot_: id 0 | task 4869 | processing task, is_child = 0 0.47.539.974 I slot print_timing: id 0 | task 4869 | prompt eval time = 128.36 ms / 457 tokens ( 0.28 ms per token, 3560.27 tokens per second) 0.47.539.981 I slot print_timing: id 0 | task 4869 | eval time = 307.49 ms / 44 tokens ( 7.15 ms per token, 139.84 tokens per second) 0.47.539.982 I slot print_timing: id 0 | task 4869 | total time = 435.85 ms / 501 tokens 0.47.539.983 I slot print_timing: id 0 | task 4869 | graphs reused = 4518 0.47.539.984 I slot print_timing: id 0 | task 4869 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.540.019 I slot release: id 0 | task 4869 | stop processing: n_tokens = 532, truncated = 0 0.47.561.475 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 532, t_last = 47447055 0.47.561.532 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.105 MiB) 0.47.638.389 I slot launch_slot_: id 0 | task 4916 | processing task, is_child = 0 0.48.046.960 I slot print_timing: id 0 | task 4916 | prompt eval time = 124.92 ms / 439 tokens ( 0.28 ms per token, 3514.39 tokens per second) 0.48.046.966 I slot print_timing: id 0 | task 4916 | eval time = 283.63 ms / 42 tokens ( 6.92 ms per token, 144.55 tokens per second) 0.48.046.968 I slot print_timing: id 0 | task 4916 | total time = 408.55 ms / 481 tokens 0.48.046.968 I slot print_timing: id 0 | task 4916 | graphs reused = 4558 0.48.046.969 I slot print_timing: id 0 | task 4916 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.047.004 I slot release: id 0 | task 4916 | stop processing: n_tokens = 512, truncated = 0 0.48.072.837 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 512, t_last = 47954040 0.48.072.888 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.325 MiB) 0.48.086.115 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.608 MiB) 0.48.169.716 I slot launch_slot_: id 0 | task 4961 | processing task, is_child = 0 0.48.689.916 I slot print_timing: id 0 | task 4961 | prompt eval time = 140.52 ms / 606 tokens ( 0.23 ms per token, 4312.58 tokens per second) 0.48.689.922 I slot print_timing: id 0 | task 4961 | eval time = 379.66 ms / 56 tokens ( 6.90 ms per token, 144.87 tokens per second) 0.48.689.923 I slot print_timing: id 0 | task 4961 | total time = 520.18 ms / 662 tokens 0.48.689.924 I slot print_timing: id 0 | task 4961 | graphs reused = 4612 0.48.689.925 I slot print_timing: id 0 | task 4961 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.689.960 I slot release: id 0 | task 4961 | stop processing: n_tokens = 693, truncated = 0 0.48.713.896 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 48596996 0.48.713.946 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.827 MiB) 0.48.727.102 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.355 MiB) 0.48.817.431 I slot launch_slot_: id 0 | task 5021 | processing task, is_child = 0 0.49.230.413 I slot print_timing: id 0 | task 5021 | prompt eval time = 130.17 ms / 477 tokens ( 0.27 ms per token, 3664.44 tokens per second) 0.49.230.419 I slot print_timing: id 0 | task 5021 | eval time = 282.79 ms / 41 tokens ( 7.07 ms per token, 141.45 tokens per second) 0.49.230.420 I slot print_timing: id 0 | task 5021 | total time = 412.96 ms / 518 tokens 0.49.230.421 I slot print_timing: id 0 | task 5021 | graphs reused = 4650 0.49.230.422 I slot print_timing: id 0 | task 5021 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.230.453 I slot release: id 0 | task 5021 | stop processing: n_tokens = 549, truncated = 0 0.49.246.964 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 49137489 0.49.247.015 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.949 MiB) 0.49.320.521 I slot launch_slot_: id 0 | task 5065 | processing task, is_child = 0 0.49.899.977 I slot print_timing: id 0 | task 5065 | prompt eval time = 169.19 ms / 845 tokens ( 0.20 ms per token, 4994.24 tokens per second) 0.49.899.984 I slot print_timing: id 0 | task 5065 | eval time = 410.24 ms / 60 tokens ( 6.95 ms per token, 143.82 tokens per second) 0.49.899.985 I slot print_timing: id 0 | task 5065 | total time = 579.44 ms / 905 tokens 0.49.899.986 I slot print_timing: id 0 | task 5065 | graphs reused = 4708 0.49.899.987 I slot print_timing: id 0 | task 5065 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.900.037 I slot release: id 0 | task 5065 | stop processing: n_tokens = 936, truncated = 0 0.49.918.943 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 936, t_last = 49807073 0.49.919.002 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.106 MiB) 0.49.930.830 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.701 MiB) 0.50.007.708 I slot launch_slot_: id 0 | task 5129 | processing task, is_child = 0 0.50.426.760 I slot print_timing: id 0 | task 5129 | prompt eval time = 124.51 ms / 459 tokens ( 0.27 ms per token, 3686.42 tokens per second) 0.50.426.766 I slot print_timing: id 0 | task 5129 | eval time = 294.52 ms / 43 tokens ( 7.01 ms per token, 142.60 tokens per second) 0.50.426.767 I slot print_timing: id 0 | task 5129 | total time = 419.03 ms / 502 tokens 0.50.426.768 I slot print_timing: id 0 | task 5129 | graphs reused = 4748 0.50.426.769 I slot print_timing: id 0 | task 5129 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.426.803 I slot release: id 0 | task 5129 | stop processing: n_tokens = 533, truncated = 0 0.50.447.964 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 533, t_last = 50333838 0.50.448.018 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.762 MiB) 0.50.532.648 I slot launch_slot_: id 0 | task 5175 | processing task, is_child = 0 0.50.997.081 I slot print_timing: id 0 | task 5175 | prompt eval time = 147.85 ms / 670 tokens ( 0.22 ms per token, 4531.50 tokens per second) 0.50.997.087 I slot print_timing: id 0 | task 5175 | eval time = 316.56 ms / 47 tokens ( 6.88 ms per token, 145.31 tokens per second) 0.50.997.088 I slot print_timing: id 0 | task 5175 | total time = 464.41 ms / 717 tokens 0.50.997.089 I slot print_timing: id 0 | task 5175 | graphs reused = 4793 0.50.997.089 I slot print_timing: id 0 | task 5175 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.997.129 I slot release: id 0 | task 5175 | stop processing: n_tokens = 748, truncated = 0 0.51.002.432 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 748, t_last = 50904165 0.51.002.492 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.325 MiB) 0.51.015.614 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.575 MiB) 0.51.095.633 I slot launch_slot_: id 0 | task 5226 | processing task, is_child = 0 0.51.716.272 I slot print_timing: id 0 | task 5226 | prompt eval time = 164.06 ms / 775 tokens ( 0.21 ms per token, 4723.74 tokens per second) 0.51.716.278 I slot print_timing: id 0 | task 5226 | eval time = 456.55 ms / 63 tokens ( 7.36 ms per token, 135.80 tokens per second) 0.51.716.279 I slot print_timing: id 0 | task 5226 | total time = 620.62 ms / 838 tokens 0.51.716.280 I slot print_timing: id 0 | task 5226 | graphs reused = 4854 0.51.716.282 I slot print_timing: id 0 | task 5226 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.716.325 I slot release: id 0 | task 5226 | stop processing: n_tokens = 869, truncated = 0 0.51.731.953 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 869, t_last = 51623361 0.51.732.019 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.106 MiB) 0.51.746.564 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 219.110 MiB) 0.51.821.677 I slot launch_slot_: id 0 | task 5293 | processing task, is_child = 0 0.52.441.808 I slot print_timing: id 0 | task 5293 | prompt eval time = 139.56 ms / 573 tokens ( 0.24 ms per token, 4105.85 tokens per second) 0.52.441.814 I slot print_timing: id 0 | task 5293 | eval time = 480.55 ms / 71 tokens ( 6.87 ms per token, 145.67 tokens per second) 0.52.441.815 I slot print_timing: id 0 | task 5293 | total time = 620.11 ms / 644 tokens 0.52.441.816 I slot print_timing: id 0 | task 5293 | graphs reused = 4923 0.52.441.817 I slot print_timing: id 0 | task 5293 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.441.852 I slot release: id 0 | task 5293 | stop processing: n_tokens = 675, truncated = 0 0.52.465.214 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 675, t_last = 52348888 0.52.465.272 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 217.984 MiB) 0.52.478.459 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.918 MiB) 0.52.572.752 I slot launch_slot_: id 0 | task 5368 | processing task, is_child = 0 0.53.138.701 I slot print_timing: id 0 | task 5368 | prompt eval time = 129.14 ms / 461 tokens ( 0.28 ms per token, 3569.88 tokens per second) 0.53.138.706 I slot print_timing: id 0 | task 5368 | eval time = 436.79 ms / 64 tokens ( 6.93 ms per token, 144.23 tokens per second) 0.53.138.708 I slot print_timing: id 0 | task 5368 | total time = 565.93 ms / 525 tokens 0.53.138.708 I slot print_timing: id 0 | task 5368 | graphs reused = 4984 0.53.138.709 I slot print_timing: id 0 | task 5368 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.138.741 I slot release: id 0 | task 5368 | stop processing: n_tokens = 556, truncated = 0 0.53.168.270 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 556, t_last = 53045776 0.53.168.320 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.013 MiB) 0.53.238.151 I slot launch_slot_: id 0 | task 5435 | processing task, is_child = 0 0.54.068.687 I slot print_timing: id 0 | task 5435 | prompt eval time = 139.44 ms / 609 tokens ( 0.23 ms per token, 4367.31 tokens per second) 0.54.068.693 I slot print_timing: id 0 | task 5435 | eval time = 691.07 ms / 98 tokens ( 7.12 ms per token, 140.36 tokens per second) 0.54.068.694 I slot print_timing: id 0 | task 5435 | total time = 830.52 ms / 707 tokens 0.54.068.694 I slot print_timing: id 0 | task 5435 | graphs reused = 5080 0.54.068.695 I slot print_timing: id 0 | task 5435 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.068.735 I slot release: id 0 | task 5435 | stop processing: n_tokens = 738, truncated = 0 0.54.087.850 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 738, t_last = 53975771 0.54.087.907 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.293 MiB) 0.54.100.908 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.107 MiB) 0.54.193.531 I slot launch_slot_: id 0 | task 5537 | processing task, is_child = 0 0.54.772.696 I slot print_timing: id 0 | task 5537 | prompt eval time = 166.19 ms / 791 tokens ( 0.21 ms per token, 4759.47 tokens per second) 0.54.772.702 I slot print_timing: id 0 | task 5537 | eval time = 412.95 ms / 61 tokens ( 6.88 ms per token, 145.30 tokens per second) 0.54.772.703 I slot print_timing: id 0 | task 5537 | total time = 579.14 ms / 852 tokens 0.54.772.704 I slot print_timing: id 0 | task 5537 | graphs reused = 5139 0.54.772.704 I slot print_timing: id 0 | task 5537 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.772.746 I slot release: id 0 | task 5537 | stop processing: n_tokens = 883, truncated = 0 0.54.789.973 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 883, t_last = 54679782 0.54.790.028 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 270.548 MiB) 0.54.910.509 I slot launch_slot_: id 0 | task 5602 | processing task, is_child = 0 0.55.423.783 I slot print_timing: id 0 | task 5602 | prompt eval time = 133.88 ms / 533 tokens ( 0.25 ms per token, 3981.15 tokens per second) 0.55.423.789 I slot print_timing: id 0 | task 5602 | eval time = 379.37 ms / 56 tokens ( 6.90 ms per token, 144.98 tokens per second) 0.55.423.790 I slot print_timing: id 0 | task 5602 | total time = 513.25 ms / 589 tokens 0.55.423.792 I slot print_timing: id 0 | task 5602 | graphs reused = 5193 0.55.423.793 I slot print_timing: id 0 | task 5602 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.423.827 I slot release: id 0 | task 5602 | stop processing: n_tokens = 677, truncated = 0 0.55.443.615 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 677, t_last = 55330863 0.55.443.673 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 272.675 MiB) 0.55.553.174 I slot launch_slot_: id 0 | task 5662 | processing task, is_child = 0 0.56.034.986 I slot print_timing: id 0 | task 5662 | prompt eval time = 141.26 ms / 566 tokens ( 0.25 ms per token, 4006.82 tokens per second) 0.56.034.991 I slot print_timing: id 0 | task 5662 | eval time = 340.54 ms / 46 tokens ( 7.57 ms per token, 132.15 tokens per second) 0.56.034.992 I slot print_timing: id 0 | task 5662 | total time = 481.79 ms / 612 tokens 0.56.034.993 I slot print_timing: id 0 | task 5662 | graphs reused = 5237 0.56.034.994 I slot print_timing: id 0 | task 5662 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.035.028 I slot release: id 0 | task 5662 | stop processing: n_tokens = 643, truncated = 0 0.56.050.025 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 643, t_last = 55942064 0.56.050.080 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.301 MiB) 0.56.130.965 I slot launch_slot_: id 0 | task 5712 | processing task, is_child = 0 0.56.553.992 I slot print_timing: id 0 | task 5712 | prompt eval time = 128.99 ms / 443 tokens ( 0.29 ms per token, 3434.48 tokens per second) 0.56.553.998 I slot print_timing: id 0 | task 5712 | eval time = 294.02 ms / 43 tokens ( 7.00 ms per token, 142.85 tokens per second) 0.56.553.999 I slot print_timing: id 0 | task 5712 | total time = 423.01 ms / 486 tokens 0.56.554.000 I slot print_timing: id 0 | task 5712 | graphs reused = 5277 0.56.554.001 I slot print_timing: id 0 | task 5712 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.554.032 I slot release: id 0 | task 5712 | stop processing: n_tokens = 517, truncated = 0 0.56.581.893 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 517, t_last = 56461068 0.56.581.959 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.488 MiB) 0.56.663.286 I slot launch_slot_: id 0 | task 5758 | processing task, is_child = 0 0.57.226.141 I slot print_timing: id 0 | task 5758 | prompt eval time = 122.74 ms / 487 tokens ( 0.25 ms per token, 3967.74 tokens per second) 0.57.226.146 I slot print_timing: id 0 | task 5758 | eval time = 440.09 ms / 65 tokens ( 6.88 ms per token, 145.42 tokens per second) 0.57.226.147 I slot print_timing: id 0 | task 5758 | total time = 562.83 ms / 552 tokens 0.57.226.148 I slot print_timing: id 0 | task 5758 | graphs reused = 5340 0.57.226.149 I slot print_timing: id 0 | task 5758 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.226.182 I slot release: id 0 | task 5758 | stop processing: n_tokens = 583, truncated = 0 0.57.240.014 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 583, t_last = 57133218 0.57.240.065 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 217.796 MiB) 0.57.323.443 I slot launch_slot_: id 0 | task 5826 | processing task, is_child = 0 0.57.771.395 I slot print_timing: id 0 | task 5826 | prompt eval time = 131.26 ms / 507 tokens ( 0.26 ms per token, 3862.53 tokens per second) 0.57.771.401 I slot print_timing: id 0 | task 5826 | eval time = 316.68 ms / 47 tokens ( 6.88 ms per token, 145.26 tokens per second) 0.57.771.402 I slot print_timing: id 0 | task 5826 | total time = 447.94 ms / 554 tokens 0.57.771.403 I slot print_timing: id 0 | task 5826 | graphs reused = 5385 0.57.771.404 I slot print_timing: id 0 | task 5826 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.771.438 I slot release: id 0 | task 5826 | stop processing: n_tokens = 585, truncated = 0 0.57.792.083 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 585, t_last = 57678474 0.57.792.127 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 272.206 MiB) 0.57.808.515 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 271.893 MiB) 0.57.891.526 I slot launch_slot_: id 0 | task 5876 | processing task, is_child = 0 0.58.482.355 I slot print_timing: id 0 | task 5876 | prompt eval time = 144.80 ms / 633 tokens ( 0.23 ms per token, 4371.55 tokens per second) 0.58.482.361 I slot print_timing: id 0 | task 5876 | eval time = 446.01 ms / 66 tokens ( 6.86 ms per token, 145.74 tokens per second) 0.58.482.362 I slot print_timing: id 0 | task 5876 | total time = 590.81 ms / 699 tokens 0.58.482.363 I slot print_timing: id 0 | task 5876 | graphs reused = 5449 0.58.482.364 I slot print_timing: id 0 | task 5876 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.482.401 I slot release: id 0 | task 5876 | stop processing: n_tokens = 730, truncated = 0 0.58.510.178 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 730, t_last = 58389437 0.58.510.236 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 269.735 MiB) 0.58.609.846 I slot launch_slot_: id 0 | task 5946 | processing task, is_child = 0 0.59.150.096 I slot print_timing: id 0 | task 5946 | prompt eval time = 140.85 ms / 571 tokens ( 0.25 ms per token, 4054.04 tokens per second) 0.59.150.102 I slot print_timing: id 0 | task 5946 | eval time = 399.38 ms / 59 tokens ( 6.89 ms per token, 145.22 tokens per second) 0.59.150.103 I slot print_timing: id 0 | task 5946 | total time = 540.23 ms / 630 tokens 0.59.150.104 I slot print_timing: id 0 | task 5946 | graphs reused = 5506 0.59.150.105 I slot print_timing: id 0 | task 5946 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.150.142 I slot release: id 0 | task 5946 | stop processing: n_tokens = 661, truncated = 0 0.59.164.707 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 661, t_last = 59057177 0.59.164.760 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 268.766 MiB) 0.59.251.869 I slot launch_slot_: id 0 | task 6009 | processing task, is_child = 0 0.59.715.093 I slot print_timing: id 0 | task 6009 | prompt eval time = 165.92 ms / 798 tokens ( 0.21 ms per token, 4809.60 tokens per second) 0.59.715.099 I slot print_timing: id 0 | task 6009 | eval time = 297.29 ms / 44 tokens ( 6.91 ms per token, 144.64 tokens per second) 0.59.715.100 I slot print_timing: id 0 | task 6009 | total time = 463.20 ms / 842 tokens 0.59.715.101 I slot print_timing: id 0 | task 6009 | graphs reused = 5548 0.59.715.101 I slot print_timing: id 0 | task 6009 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.715.144 I slot release: id 0 | task 6009 | stop processing: n_tokens = 873, truncated = 0 0.59.737.389 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 873, t_last = 59622180 0.59.737.456 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.424 MiB) 0.59.756.842 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 269.923 MiB) 0.59.862.723 I slot launch_slot_: id 0 | task 6057 | processing task, is_child = 0 1.00.293.927 I slot print_timing: id 0 | task 6057 | prompt eval time = 140.74 ms / 572 tokens ( 0.25 ms per token, 4064.32 tokens per second) 1.00.293.932 I slot print_timing: id 0 | task 6057 | eval time = 290.45 ms / 43 tokens ( 6.92 ms per token, 144.60 tokens per second) 1.00.293.934 I slot print_timing: id 0 | task 6057 | total time = 431.18 ms / 615 tokens 1.00.293.935 I slot print_timing: id 0 | task 6057 | graphs reused = 5589 1.00.293.935 I slot print_timing: id 0 | task 6057 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.293.971 I slot release: id 0 | task 6057 | stop processing: n_tokens = 646, truncated = 0 1.00.318.400 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 646, t_last = 60201007 1.00.318.455 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 267.015 MiB) 1.00.418.731 I slot launch_slot_: id 0 | task 6104 | processing task, is_child = 0 1.00.995.181 I slot print_timing: id 0 | task 6104 | prompt eval time = 144.60 ms / 613 tokens ( 0.24 ms per token, 4239.34 tokens per second) 1.00.995.187 I slot print_timing: id 0 | task 6104 | eval time = 431.83 ms / 64 tokens ( 6.85 ms per token, 145.89 tokens per second) 1.00.995.188 I slot print_timing: id 0 | task 6104 | total time = 576.43 ms / 677 tokens 1.00.995.189 I slot print_timing: id 0 | task 6104 | graphs reused = 5651 1.00.995.189 I slot print_timing: id 0 | task 6104 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.995.226 I slot release: id 0 | task 6104 | stop processing: n_tokens = 708, truncated = 0 1.01.020.581 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 708, t_last = 60902262 1.01.020.637 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.549 MiB) 1.01.114.544 I slot launch_slot_: id 0 | task 6172 | processing task, is_child = 0 1.01.686.379 I slot print_timing: id 0 | task 6172 | prompt eval time = 140.20 ms / 580 tokens ( 0.24 ms per token, 4136.98 tokens per second) 1.01.686.385 I slot print_timing: id 0 | task 6172 | eval time = 431.62 ms / 64 tokens ( 6.85 ms per token, 145.96 tokens per second) 1.01.686.386 I slot print_timing: id 0 | task 6172 | total time = 571.82 ms / 644 tokens 1.01.686.386 I slot print_timing: id 0 | task 6172 | graphs reused = 5713 1.01.686.387 I slot print_timing: id 0 | task 6172 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.686.423 I slot release: id 0 | task 6172 | stop processing: n_tokens = 675, truncated = 0 1.01.710.290 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 675, t_last = 61593459 1.01.710.346 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.454 MiB) 1.01.802.839 I slot launch_slot_: id 0 | task 6240 | processing task, is_child = 0 1.02.303.853 I slot print_timing: id 0 | task 6240 | prompt eval time = 158.26 ms / 716 tokens ( 0.22 ms per token, 4524.09 tokens per second) 1.02.303.859 I slot print_timing: id 0 | task 6240 | eval time = 342.73 ms / 50 tokens ( 6.99 ms per token, 142.97 tokens per second) 1.02.303.860 I slot print_timing: id 0 | task 6240 | total time = 501.00 ms / 766 tokens 1.02.303.861 I slot print_timing: id 0 | task 6240 | graphs reused = 5760 1.02.303.862 I slot print_timing: id 0 | task 6240 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.303.901 I slot release: id 0 | task 6240 | stop processing: n_tokens = 797, truncated = 0 1.02.323.012 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 797, t_last = 62210937 1.02.323.075 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.234 MiB) 1.02.342.194 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.141 MiB) 1.02.445.766 I slot launch_slot_: id 0 | task 6294 | processing task, is_child = 0 1.03.303.047 I slot print_timing: id 0 | task 6294 | prompt eval time = 165.27 ms / 799 tokens ( 0.21 ms per token, 4834.54 tokens per second) 1.03.303.053 I slot print_timing: id 0 | task 6294 | eval time = 691.99 ms / 102 tokens ( 6.85 ms per token, 145.96 tokens per second) 1.03.303.054 I slot print_timing: id 0 | task 6294 | total time = 857.26 ms / 901 tokens 1.03.303.055 I slot print_timing: id 0 | task 6294 | graphs reused = 5860 1.03.303.056 I slot print_timing: id 0 | task 6294 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.303.098 I slot release: id 0 | task 6294 | stop processing: n_tokens = 932, truncated = 0 1.03.321.259 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 932, t_last = 63210134 1.03.321.328 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.515 MiB) 1.03.402.605 I slot launch_slot_: id 0 | task 6400 | processing task, is_child = 0 1.04.274.695 I slot print_timing: id 0 | task 6400 | prompt eval time = 115.67 ms / 361 tokens ( 0.32 ms per token, 3120.81 tokens per second) 1.04.274.701 I slot print_timing: id 0 | task 6400 | eval time = 756.39 ms / 112 tokens ( 6.81 ms per token, 146.75 tokens per second) 1.04.274.702 I slot print_timing: id 0 | task 6400 | total time = 872.07 ms / 473 tokens 1.04.274.702 I slot print_timing: id 0 | task 6400 | graphs reused = 5970 1.04.274.703 I slot print_timing: id 0 | task 6400 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.274.734 I slot release: id 0 | task 6400 | stop processing: n_tokens = 504, truncated = 0 1.04.299.165 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 64181769 1.04.299.242 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.426 MiB) 1.04.372.337 I slot launch_slot_: id 0 | task 6515 | processing task, is_child = 0 1.05.224.186 I slot print_timing: id 0 | task 6515 | prompt eval time = 117.11 ms / 381 tokens ( 0.31 ms per token, 3253.32 tokens per second) 1.05.224.192 I slot print_timing: id 0 | task 6515 | eval time = 734.72 ms / 108 tokens ( 6.87 ms per token, 145.63 tokens per second) 1.05.224.193 I slot print_timing: id 0 | task 6515 | total time = 851.83 ms / 489 tokens 1.05.224.193 I slot print_timing: id 0 | task 6515 | graphs reused = 6075 1.05.224.194 I slot print_timing: id 0 | task 6515 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.224.223 I slot release: id 0 | task 6515 | stop processing: n_tokens = 520, truncated = 0 1.05.240.635 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 65131259 1.05.240.681 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 1.05.305.966 I slot launch_slot_: id 0 | task 6626 | processing task, is_child = 0 1.06.258.360 I slot print_timing: id 0 | task 6626 | prompt eval time = 109.02 ms / 365 tokens ( 0.30 ms per token, 3348.04 tokens per second) 1.06.258.365 I slot print_timing: id 0 | task 6626 | eval time = 843.36 ms / 124 tokens ( 6.86 ms per token, 145.85 tokens per second) 1.06.258.366 I slot print_timing: id 0 | task 6626 | total time = 952.38 ms / 489 tokens 1.06.258.367 I slot print_timing: id 0 | task 6626 | graphs reused = 6196 1.06.258.368 I slot print_timing: id 0 | task 6626 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.258.397 I slot release: id 0 | task 6626 | stop processing: n_tokens = 520, truncated = 0 1.06.274.710 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 66165432 1.06.274.759 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.026 MiB) 1.06.347.990 I slot launch_slot_: id 0 | task 6753 | processing task, is_child = 0 1.07.180.584 I slot print_timing: id 0 | task 6753 | prompt eval time = 108.11 ms / 333 tokens ( 0.32 ms per token, 3080.20 tokens per second) 1.07.180.590 I slot print_timing: id 0 | task 6753 | eval time = 724.47 ms / 107 tokens ( 6.83 ms per token, 146.31 tokens per second) 1.07.180.591 I slot print_timing: id 0 | task 6753 | total time = 832.58 ms / 440 tokens 1.07.180.591 I slot print_timing: id 0 | task 6753 | graphs reused = 6301 1.07.180.592 I slot print_timing: id 0 | task 6753 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.180.620 I slot release: id 0 | task 6753 | stop processing: n_tokens = 471, truncated = 0 1.07.197.077 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 471, t_last = 67087655 1.07.239.862 I slot launch_slot_: id 0 | task 6863 | processing task, is_child = 0 1.08.293.937 I slot print_timing: id 0 | task 6863 | prompt eval time = 113.78 ms / 403 tokens ( 0.28 ms per token, 3542.02 tokens per second) 1.08.293.942 I slot print_timing: id 0 | task 6863 | eval time = 940.28 ms / 138 tokens ( 6.86 ms per token, 145.70 tokens per second) 1.08.293.944 I slot print_timing: id 0 | task 6863 | total time = 1054.05 ms / 541 tokens 1.08.293.945 I slot print_timing: id 0 | task 6863 | graphs reused = 6436 1.08.293.946 I slot print_timing: id 0 | task 6863 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.293.979 I slot release: id 0 | task 6863 | stop processing: n_tokens = 572, truncated = 0 1.08.317.166 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 572, t_last = 68201014 1.08.317.219 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.172 MiB) 1.08.400.687 I slot launch_slot_: id 0 | task 7004 | processing task, is_child = 0 1.09.777.663 I slot print_timing: id 0 | task 7004 | prompt eval time = 117.60 ms / 411 tokens ( 0.29 ms per token, 3494.87 tokens per second) 1.09.777.669 I slot print_timing: id 0 | task 7004 | eval time = 1259.36 ms / 185 tokens ( 6.84 ms per token, 146.11 tokens per second) 1.09.777.670 I slot print_timing: id 0 | task 7004 | total time = 1376.96 ms / 596 tokens 1.09.777.671 I slot print_timing: id 0 | task 7004 | graphs reused = 6618 1.09.777.671 I slot print_timing: id 0 | task 7004 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.777.701 I slot release: id 0 | task 7004 | stop processing: n_tokens = 627, truncated = 0 1.09.803.844 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 627, t_last = 69684737 1.09.803.895 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 375.146 MiB) 1.09.873.316 I slot launch_slot_: id 0 | task 7192 | processing task, is_child = 0 1.11.526.666 I slot print_timing: id 0 | task 7192 | prompt eval time = 127.26 ms / 490 tokens ( 0.26 ms per token, 3850.42 tokens per second) 1.11.526.672 I slot print_timing: id 0 | task 7192 | eval time = 1526.07 ms / 225 tokens ( 6.81 ms per token, 146.78 tokens per second) 1.11.526.673 I slot print_timing: id 0 | task 7192 | total time = 1653.33 ms / 715 tokens 1.11.526.674 I slot print_timing: id 0 | task 7192 | graphs reused = 6841 1.11.526.674 I slot print_timing: id 0 | task 7192 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.526.706 I slot release: id 0 | task 7192 | stop processing: n_tokens = 746, truncated = 0 1.11.549.319 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 746, t_last = 71433741 1.11.549.376 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.930 MiB) 1.11.623.421 I slot launch_slot_: id 0 | task 7420 | processing task, is_child = 0 1.14.006.347 I slot print_timing: id 0 | task 7420 | prompt eval time = 108.43 ms / 344 tokens ( 0.32 ms per token, 3172.67 tokens per second) 1.14.006.352 I slot print_timing: id 0 | task 7420 | eval time = 2274.48 ms / 335 tokens ( 6.81 ms per token, 146.85 tokens per second) 1.14.006.353 I slot print_timing: id 0 | task 7420 | total time = 2382.91 ms / 679 tokens 1.14.006.354 I slot print_timing: id 0 | task 7420 | graphs reused = 7173 1.14.006.355 I slot print_timing: id 0 | task 7420 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.006.384 I slot release: id 0 | task 7420 | stop processing: n_tokens = 710, truncated = 0 1.14.021.452 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 710, t_last = 73913420 1.14.021.509 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.891 MiB) 1.14.096.315 I slot launch_slot_: id 0 | task 7758 | processing task, is_child = 0 1.16.422.715 I slot print_timing: id 0 | task 7758 | prompt eval time = 111.74 ms / 347 tokens ( 0.32 ms per token, 3105.42 tokens per second) 1.16.422.721 I slot print_timing: id 0 | task 7758 | eval time = 2214.64 ms / 325 tokens ( 6.84 ms per token, 146.30 tokens per second) 1.16.422.722 I slot print_timing: id 0 | task 7758 | total time = 2326.38 ms / 672 tokens 1.16.422.722 I slot print_timing: id 0 | task 7758 | graphs reused = 7495 1.16.422.723 I slot print_timing: id 0 | task 7758 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.422.752 I slot release: id 0 | task 7758 | stop processing: n_tokens = 703, truncated = 0 1.16.447.252 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 703, t_last = 76329787 1.16.447.308 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.834 MiB) 1.16.529.253 I slot launch_slot_: id 0 | task 8086 | processing task, is_child = 0 1.17.505.664 I slot print_timing: id 0 | task 8086 | prompt eval time = 119.07 ms / 401 tokens ( 0.30 ms per token, 3367.85 tokens per second) 1.17.505.670 I slot print_timing: id 0 | task 8086 | eval time = 857.33 ms / 126 tokens ( 6.86 ms per token, 145.80 tokens per second) 1.17.505.671 I slot print_timing: id 0 | task 8086 | total time = 976.39 ms / 527 tokens 1.17.505.672 I slot print_timing: id 0 | task 8086 | graphs reused = 7618 1.17.505.673 I slot print_timing: id 0 | task 8086 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.505.701 I slot release: id 0 | task 8086 | stop processing: n_tokens = 558, truncated = 0 1.17.532.837 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 77412737 1.17.532.885 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.368 MiB) 1.17.610.852 I slot launch_slot_: id 0 | task 8215 | processing task, is_child = 0 1.18.544.021 I slot print_timing: id 0 | task 8215 | prompt eval time = 125.98 ms / 456 tokens ( 0.28 ms per token, 3619.74 tokens per second) 1.18.544.026 I slot print_timing: id 0 | task 8215 | eval time = 807.17 ms / 115 tokens ( 7.08 ms per token, 141.23 tokens per second) 1.18.544.027 I slot print_timing: id 0 | task 8215 | total time = 933.15 ms / 571 tokens 1.18.544.028 I slot print_timing: id 0 | task 8215 | graphs reused = 7730 1.18.544.028 I slot print_timing: id 0 | task 8215 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.544.060 I slot release: id 0 | task 8215 | stop processing: n_tokens = 602, truncated = 0 1.18.561.552 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 1.18.561.601 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 423.177 MiB) 1.18.641.227 I slot launch_slot_: id 0 | task 8333 | processing task, is_child = 0 1.19.522.218 I slot print_timing: id 0 | task 8333 | prompt eval time = 119.47 ms / 406 tokens ( 0.29 ms per token, 3398.46 tokens per second) 1.19.522.223 I slot print_timing: id 0 | task 8333 | eval time = 761.51 ms / 112 tokens ( 6.86 ms per token, 145.76 tokens per second) 1.19.522.224 I slot print_timing: id 0 | task 8333 | total time = 880.97 ms / 518 tokens 1.19.522.225 I slot print_timing: id 0 | task 8333 | graphs reused = 7839 1.19.522.226 I slot print_timing: id 0 | task 8333 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.522.259 I slot release: id 0 | task 8333 | stop processing: n_tokens = 549, truncated = 0 1.19.550.822 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 79429295 1.19.594.994 I slot launch_slot_: id 0 | task 8448 | processing task, is_child = 0 1.21.988.695 I slot print_timing: id 0 | task 8448 | prompt eval time = 115.41 ms / 406 tokens ( 0.28 ms per token, 3517.95 tokens per second) 1.21.988.701 I slot print_timing: id 0 | task 8448 | eval time = 2278.28 ms / 335 tokens ( 6.82 ms per token, 146.60 tokens per second) 1.21.988.702 I slot print_timing: id 0 | task 8448 | total time = 2393.68 ms / 741 tokens 1.21.988.702 I slot print_timing: id 0 | task 8448 | graphs reused = 8170 1.21.988.703 I slot print_timing: id 0 | task 8448 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.988.732 I slot release: id 0 | task 8448 | stop processing: n_tokens = 772, truncated = 0 1.22.008.357 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 772, t_last = 81895768 1.22.008.415 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 371.863 MiB) 1.22.097.944 I slot launch_slot_: id 0 | task 8786 | processing task, is_child = 0 1.23.158.102 I slot print_timing: id 0 | task 8786 | prompt eval time = 122.72 ms / 444 tokens ( 0.28 ms per token, 3617.99 tokens per second) 1.23.158.108 I slot print_timing: id 0 | task 8786 | eval time = 937.42 ms / 134 tokens ( 7.05 ms per token, 141.88 tokens per second) 1.23.158.109 I slot print_timing: id 0 | task 8786 | total time = 1060.14 ms / 578 tokens 1.23.158.110 I slot print_timing: id 0 | task 8786 | graphs reused = 8301 1.23.158.111 I slot print_timing: id 0 | task 8786 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.158.141 I slot release: id 0 | task 8786 | stop processing: n_tokens = 609, truncated = 0 1.23.172.573 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 609, t_last = 83065177 1.23.172.625 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.672 MiB) 1.23.260.093 I slot launch_slot_: id 0 | task 8923 | processing task, is_child = 0 1.24.070.454 I slot print_timing: id 0 | task 8923 | prompt eval time = 115.44 ms / 372 tokens ( 0.31 ms per token, 3222.37 tokens per second) 1.24.070.459 I slot print_timing: id 0 | task 8923 | eval time = 694.90 ms / 103 tokens ( 6.81 ms per token, 146.78 tokens per second) 1.24.070.460 I slot print_timing: id 0 | task 8923 | total time = 810.34 ms / 475 tokens 1.24.070.461 I slot print_timing: id 0 | task 8923 | graphs reused = 8402 1.24.070.462 I slot print_timing: id 0 | task 8923 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.070.491 I slot release: id 0 | task 8923 | stop processing: n_tokens = 506, truncated = 0 1.24.091.666 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 506, t_last = 83977527 1.24.091.707 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.736 MiB) 1.24.171.643 I slot launch_slot_: id 0 | task 9029 | processing task, is_child = 0 1.25.856.101 I slot print_timing: id 0 | task 9029 | prompt eval time = 122.21 ms / 454 tokens ( 0.27 ms per token, 3715.01 tokens per second) 1.25.856.108 I slot print_timing: id 0 | task 9029 | eval time = 1562.23 ms / 230 tokens ( 6.82 ms per token, 146.58 tokens per second) 1.25.856.109 I slot print_timing: id 0 | task 9029 | total time = 1684.44 ms / 684 tokens 1.25.856.110 I slot print_timing: id 0 | task 9029 | graphs reused = 8629 1.25.856.110 I slot print_timing: id 0 | task 9029 | graph reallocs = 0 / 0 (same size) / (changed size) 1.25.856.142 I slot release: id 0 | task 9029 | stop processing: n_tokens = 715, truncated = 0 1.25.859.948 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 715, t_last = 85763178 1.25.860.003 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.798 MiB) 1.25.942.631 I slot launch_slot_: id 0 | task 9262 | processing task, is_child = 0 1.27.591.683 I slot print_timing: id 0 | task 9262 | prompt eval time = 114.09 ms / 354 tokens ( 0.32 ms per token, 3102.81 tokens per second) 1.27.591.688 I slot print_timing: id 0 | task 9262 | eval time = 1534.94 ms / 226 tokens ( 6.82 ms per token, 146.59 tokens per second) 1.27.591.689 I slot print_timing: id 0 | task 9262 | total time = 1649.03 ms / 580 tokens 1.27.591.692 I slot print_timing: id 0 | task 9262 | graphs reused = 8852 1.27.591.693 I slot print_timing: id 0 | task 9262 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.591.722 I slot release: id 0 | task 9262 | stop processing: n_tokens = 611, truncated = 0 1.27.595.441 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 611, t_last = 87498758 1.27.595.495 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.583 MiB) 1.27.677.143 I slot launch_slot_: id 0 | task 9491 | processing task, is_child = 0 1.28.733.516 I slot print_timing: id 0 | task 9491 | prompt eval time = 110.78 ms / 334 tokens ( 0.33 ms per token, 3015.07 tokens per second) 1.28.733.522 I slot print_timing: id 0 | task 9491 | eval time = 945.58 ms / 140 tokens ( 6.80 ms per token, 147.00 tokens per second) 1.28.733.523 I slot print_timing: id 0 | task 9491 | total time = 1056.36 ms / 474 tokens 1.28.733.524 I slot print_timing: id 0 | task 9491 | graphs reused = 8990 1.28.733.525 I slot print_timing: id 0 | task 9491 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.733.552 I slot release: id 0 | task 9491 | stop processing: n_tokens = 505, truncated = 0 1.28.753.856 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 505, t_last = 88640588 1.28.753.902 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 372.426 MiB) 1.28.833.621 I slot launch_slot_: id 0 | task 9634 | processing task, is_child = 0 1.30.144.442 I slot print_timing: id 0 | task 9634 | prompt eval time = 121.08 ms / 426 tokens ( 0.28 ms per token, 3518.33 tokens per second) 1.30.144.448 I slot print_timing: id 0 | task 9634 | eval time = 1189.72 ms / 175 tokens ( 6.84 ms per token, 146.25 tokens per second) 1.30.144.448 I slot print_timing: id 0 | task 9634 | total time = 1310.80 ms / 601 tokens 1.30.144.449 I slot print_timing: id 0 | task 9634 | graphs reused = 9162 1.30.144.450 I slot print_timing: id 0 | task 9634 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.144.482 I slot release: id 0 | task 9634 | stop processing: n_tokens = 632, truncated = 0 1.30.160.753 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 632, t_last = 90051517 1.30.160.806 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.055 MiB) 1.30.239.848 I slot launch_slot_: id 0 | task 9812 | processing task, is_child = 0 1.31.148.689 I slot print_timing: id 0 | task 9812 | prompt eval time = 114.00 ms / 366 tokens ( 0.31 ms per token, 3210.50 tokens per second) 1.31.148.694 I slot print_timing: id 0 | task 9812 | eval time = 794.82 ms / 117 tokens ( 6.85 ms per token, 145.94 tokens per second) 1.31.148.695 I slot print_timing: id 0 | task 9812 | total time = 908.82 ms / 483 tokens 1.31.148.696 I slot print_timing: id 0 | task 9812 | graphs reused = 9276 1.31.148.697 I slot print_timing: id 0 | task 9812 | graph reallocs = 0 / 0 (same size) / (changed size) 1.31.148.726 I slot release: id 0 | task 9812 | stop processing: n_tokens = 514, truncated = 0 1.31.176.690 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 514, t_last = 91055762 1.31.176.736 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 371.957 MiB) 1.31.248.927 I slot launch_slot_: id 0 | task 9932 | processing task, is_child = 0 1.33.620.855 I slot print_timing: id 0 | task 9932 | prompt eval time = 124.90 ms / 462 tokens ( 0.27 ms per token, 3698.84 tokens per second) 1.33.620.860 I slot print_timing: id 0 | task 9932 | eval time = 2247.01 ms / 330 tokens ( 6.83 ms per token, 146.42 tokens per second) 1.33.620.861 I slot print_timing: id 0 | task 9932 | total time = 2371.91 ms / 792 tokens 1.33.620.862 I slot print_timing: id 0 | task 9932 | graphs reused = 9602 1.33.620.863 I slot print_timing: id 0 | task 9932 | graph reallocs = 0 / 0 (same size) / (changed size) 1.33.620.894 I slot release: id 0 | task 9932 | stop processing: n_tokens = 823, truncated = 0 1.33.644.540 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 823, t_last = 93527929 1.33.644.601 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.895 MiB) 1.33.719.481 I slot launch_slot_: id 0 | task 10265 | processing task, is_child = 0 1.34.783.951 I slot print_timing: id 0 | task 10265 | prompt eval time = 117.25 ms / 396 tokens ( 0.30 ms per token, 3377.34 tokens per second) 1.34.783.957 I slot print_timing: id 0 | task 10265 | eval time = 947.20 ms / 139 tokens ( 6.86 ms per token, 145.69 tokens per second) 1.34.783.958 I slot print_timing: id 0 | task 10265 | total time = 1064.45 ms / 535 tokens 1.34.783.959 I slot print_timing: id 0 | task 10265 | graphs reused = 9738 1.34.783.960 I slot print_timing: id 0 | task 10265 | graph reallocs = 0 / 0 (same size) / (changed size) 1.34.783.991 I slot release: id 0 | task 10265 | stop processing: n_tokens = 566, truncated = 0 1.34.787.825 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 566, t_last = 94691027 1.34.836.779 I slot launch_slot_: id 0 | task 10407 | processing task, is_child = 0 1.36.055.014 I slot print_timing: id 0 | task 10407 | prompt eval time = 122.89 ms / 458 tokens ( 0.27 ms per token, 3726.88 tokens per second) 1.36.055.019 I slot print_timing: id 0 | task 10407 | eval time = 1095.33 ms / 161 tokens ( 6.85 ms per token, 146.08 tokens per second) 1.36.055.020 I slot print_timing: id 0 | task 10407 | total time = 1218.22 ms / 619 tokens 1.36.055.021 I slot print_timing: id 0 | task 10407 | graphs reused = 9896 1.36.055.022 I slot print_timing: id 0 | task 10407 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.055.052 I slot release: id 0 | task 10407 | stop processing: n_tokens = 650, truncated = 0 1.36.076.594 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 650, t_last = 95962088 1.36.076.648 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 372.863 MiB) 1.36.164.838 I slot launch_slot_: id 0 | task 10571 | processing task, is_child = 0 1.37.518.642 I slot print_timing: id 0 | task 10571 | prompt eval time = 125.98 ms / 458 tokens ( 0.28 ms per token, 3635.53 tokens per second) 1.37.518.648 I slot print_timing: id 0 | task 10571 | eval time = 1227.81 ms / 176 tokens ( 7.02 ms per token, 142.53 tokens per second) 1.37.518.649 I slot print_timing: id 0 | task 10571 | total time = 1353.79 ms / 634 tokens 1.37.518.650 I slot print_timing: id 0 | task 10571 | graphs reused = 10069 1.37.518.651 I slot print_timing: id 0 | task 10571 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.518.683 I slot release: id 0 | task 10571 | stop processing: n_tokens = 665, truncated = 0 1.37.539.221 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 665, t_last = 97425718 1.37.539.273 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 376.679 MiB) 1.37.627.327 I slot launch_slot_: id 0 | task 10750 | processing task, is_child = 0 1.39.178.765 I slot print_timing: id 0 | task 10750 | prompt eval time = 123.69 ms / 452 tokens ( 0.27 ms per token, 3654.42 tokens per second) 1.39.178.770 I slot print_timing: id 0 | task 10750 | eval time = 1427.73 ms / 210 tokens ( 6.83 ms per token, 146.39 tokens per second) 1.39.178.771 I slot print_timing: id 0 | task 10750 | total time = 1551.42 ms / 662 tokens 1.39.178.772 I slot print_timing: id 0 | task 10750 | graphs reused = 10276 1.39.178.773 I slot print_timing: id 0 | task 10750 | graph reallocs = 0 / 0 (same size) / (changed size) 1.39.178.803 I slot release: id 0 | task 10750 | stop processing: n_tokens = 693, truncated = 0 1.39.200.438 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 99085839 1.39.200.493 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 380.901 MiB) 1.39.281.517 I slot launch_slot_: id 0 | task 10963 | processing task, is_child = 0 1.40.182.870 I slot print_timing: id 0 | task 10963 | prompt eval time = 125.81 ms / 404 tokens ( 0.31 ms per token, 3211.24 tokens per second) 1.40.182.876 I slot print_timing: id 0 | task 10963 | eval time = 775.52 ms / 114 tokens ( 6.86 ms per token, 145.71 tokens per second) 1.40.182.877 I slot print_timing: id 0 | task 10963 | total time = 901.33 ms / 518 tokens 1.40.182.878 I slot print_timing: id 0 | task 10963 | graphs reused = 10387 1.40.182.878 I slot print_timing: id 0 | task 10963 | graph reallocs = 0 / 0 (same size) / (changed size) 1.40.182.908 I slot release: id 0 | task 10963 | stop processing: n_tokens = 549, truncated = 0 1.40.200.885 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 100089944 1.40.200.934 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.265 MiB) 1.40.273.195 I slot launch_slot_: id 0 | task 11080 | processing task, is_child = 0 1.41.111.971 I slot print_timing: id 0 | task 11080 | prompt eval time = 123.42 ms / 345 tokens ( 0.36 ms per token, 2795.45 tokens per second) 1.41.111.977 I slot print_timing: id 0 | task 11080 | eval time = 715.34 ms / 106 tokens ( 6.81 ms per token, 146.78 tokens per second) 1.41.111.978 I slot print_timing: id 0 | task 11080 | total time = 838.76 ms / 451 tokens 1.41.111.979 I slot print_timing: id 0 | task 11080 | graphs reused = 10491 1.41.111.979 I slot print_timing: id 0 | task 11080 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.112.007 I slot release: id 0 | task 11080 | stop processing: n_tokens = 482, truncated = 0 1.41.132.006 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 482, t_last = 101019043 1.41.132.052 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.766 MiB) 1.41.197.509 I slot launch_slot_: id 0 | task 11189 | processing task, is_child = 0 1.42.033.006 I slot print_timing: id 0 | task 11189 | prompt eval time = 121.03 ms / 430 tokens ( 0.28 ms per token, 3552.69 tokens per second) 1.42.033.012 I slot print_timing: id 0 | task 11189 | eval time = 714.44 ms / 105 tokens ( 6.87 ms per token, 145.57 tokens per second) 1.42.033.013 I slot print_timing: id 0 | task 11189 | total time = 835.48 ms / 535 tokens 1.42.033.014 I slot print_timing: id 0 | task 11189 | graphs reused = 10593 1.42.033.015 I slot print_timing: id 0 | task 11189 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.033.045 I slot release: id 0 | task 11189 | stop processing: n_tokens = 566, truncated = 0 1.42.053.806 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 566, t_last = 101940081 1.42.053.855 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.766 MiB) 1.42.119.583 I slot launch_slot_: id 0 | task 11297 | processing task, is_child = 0 1.42.826.154 I slot print_timing: id 0 | task 11297 | prompt eval time = 104.82 ms / 316 tokens ( 0.33 ms per token, 3014.78 tokens per second) 1.42.826.160 I slot print_timing: id 0 | task 11297 | eval time = 601.74 ms / 85 tokens ( 7.16 ms per token, 139.60 tokens per second) 1.42.826.161 I slot print_timing: id 0 | task 11297 | total time = 706.55 ms / 401 tokens 1.42.826.162 I slot print_timing: id 0 | task 11297 | graphs reused = 10676 1.42.826.163 I slot print_timing: id 0 | task 11297 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.826.189 I slot release: id 0 | task 11297 | stop processing: n_tokens = 432, truncated = 0 1.42.849.849 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 432, t_last = 102733224 1.42.849.894 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.233 MiB) 1.42.928.601 I slot launch_slot_: id 0 | task 11385 | processing task, is_child = 0 1.43.766.678 I slot print_timing: id 0 | task 11385 | prompt eval time = 115.66 ms / 354 tokens ( 0.33 ms per token, 3060.83 tokens per second) 1.43.766.684 I slot print_timing: id 0 | task 11385 | eval time = 722.40 ms / 107 tokens ( 6.82 ms per token, 146.73 tokens per second) 1.43.766.685 I slot print_timing: id 0 | task 11385 | total time = 838.06 ms / 461 tokens 1.43.766.685 I slot print_timing: id 0 | task 11385 | graphs reused = 10781 1.43.766.686 I slot print_timing: id 0 | task 11385 | graph reallocs = 0 / 0 (same size) / (changed size) 1.43.766.716 I slot release: id 0 | task 11385 | stop processing: n_tokens = 492, truncated = 0 1.43.792.975 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 492, t_last = 103673752 1.43.793.022 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.392 MiB) 1.43.865.617 I slot launch_slot_: id 0 | task 11495 | processing task, is_child = 0 1.44.657.227 I slot print_timing: id 0 | task 11495 | prompt eval time = 125.01 ms / 438 tokens ( 0.29 ms per token, 3503.72 tokens per second) 1.44.657.233 I slot print_timing: id 0 | task 11495 | eval time = 666.58 ms / 98 tokens ( 6.87 ms per token, 145.52 tokens per second) 1.44.657.234 I slot print_timing: id 0 | task 11495 | total time = 791.59 ms / 536 tokens 1.44.657.235 I slot print_timing: id 0 | task 11495 | graphs reused = 10876 1.44.657.236 I slot print_timing: id 0 | task 11495 | graph reallocs = 0 / 0 (same size) / (changed size) 1.44.657.266 I slot release: id 0 | task 11495 | stop processing: n_tokens = 567, truncated = 0 1.44.683.318 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 567, t_last = 104564302 1.44.683.370 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.112 MiB) 1.44.749.576 I slot launch_slot_: id 0 | task 11596 | processing task, is_child = 0 1.45.347.204 I slot print_timing: id 0 | task 11596 | prompt eval time = 120.41 ms / 457 tokens ( 0.26 ms per token, 3795.49 tokens per second) 1.45.347.210 I slot print_timing: id 0 | task 11596 | eval time = 477.20 ms / 70 tokens ( 6.92 ms per token, 144.59 tokens per second) 1.45.347.211 I slot print_timing: id 0 | task 11596 | total time = 597.61 ms / 527 tokens 1.45.347.212 I slot print_timing: id 0 | task 11596 | graphs reused = 10943 1.45.347.212 I slot print_timing: id 0 | task 11596 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.347.243 I slot release: id 0 | task 11596 | stop processing: n_tokens = 558, truncated = 0 1.45.367.832 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 105254279 1.45.367.883 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 324.833 MiB) 1.45.443.413 I slot launch_slot_: id 0 | task 11669 | processing task, is_child = 0 1.46.234.771 I slot print_timing: id 0 | task 11669 | prompt eval time = 124.45 ms / 473 tokens ( 0.26 ms per token, 3800.63 tokens per second) 1.46.234.777 I slot print_timing: id 0 | task 11669 | eval time = 666.88 ms / 98 tokens ( 6.88 ms per token, 145.45 tokens per second) 1.46.234.778 I slot print_timing: id 0 | task 11669 | total time = 791.34 ms / 571 tokens 1.46.234.779 I slot print_timing: id 0 | task 11669 | graphs reused = 11038 1.46.234.780 I slot print_timing: id 0 | task 11669 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.234.810 I slot release: id 0 | task 11669 | stop processing: n_tokens = 602, truncated = 0 1.46.256.010 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 602, t_last = 106141846 1.46.256.065 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.707 MiB) 1.46.336.024 I slot launch_slot_: id 0 | task 11770 | processing task, is_child = 0 1.46.648.217 I slot print_timing: id 0 | task 11770 | prompt eval time = 126.51 ms / 476 tokens ( 0.27 ms per token, 3762.58 tokens per second) 1.46.648.222 I slot print_timing: id 0 | task 11770 | eval time = 185.66 ms / 27 tokens ( 7.14 ms per token, 140.04 tokens per second) 1.46.648.223 I slot print_timing: id 0 | task 11770 | total time = 312.17 ms / 503 tokens 1.46.648.224 I slot print_timing: id 0 | task 11770 | graphs reused = 11062 1.46.648.225 I slot print_timing: id 0 | task 11770 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.648.258 I slot release: id 0 | task 11770 | stop processing: n_tokens = 534, truncated = 0 1.46.662.631 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 534, t_last = 106555293 1.46.662.679 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.489 MiB) 1.46.739.772 I slot launch_slot_: id 0 | task 11800 | processing task, is_child = 0 1.47.594.869 I slot print_timing: id 0 | task 11800 | prompt eval time = 127.47 ms / 466 tokens ( 0.27 ms per token, 3655.85 tokens per second) 1.47.594.875 I slot print_timing: id 0 | task 11800 | eval time = 727.61 ms / 107 tokens ( 6.86 ms per token, 145.68 tokens per second) 1.47.594.876 I slot print_timing: id 0 | task 11800 | total time = 855.08 ms / 573 tokens 1.47.594.877 I slot print_timing: id 0 | task 11800 | graphs reused = 11166 1.47.594.878 I slot print_timing: id 0 | task 11800 | graph reallocs = 0 / 0 (same size) / (changed size) 1.47.594.908 I slot release: id 0 | task 11800 | stop processing: n_tokens = 604, truncated = 0 1.47.613.356 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 604, t_last = 107501944 1.47.613.410 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.954 MiB) 1.47.690.707 I slot launch_slot_: id 0 | task 11910 | processing task, is_child = 0 1.48.338.100 I slot print_timing: id 0 | task 11910 | prompt eval time = 115.72 ms / 415 tokens ( 0.28 ms per token, 3586.24 tokens per second) 1.48.338.106 I slot print_timing: id 0 | task 11910 | eval time = 531.65 ms / 78 tokens ( 6.90 ms per token, 144.83 tokens per second) 1.48.338.107 I slot print_timing: id 0 | task 11910 | total time = 647.37 ms / 493 tokens 1.48.338.108 I slot print_timing: id 0 | task 11910 | graphs reused = 11241 1.48.338.109 I slot print_timing: id 0 | task 11910 | graph reallocs = 0 / 0 (same size) / (changed size) 1.48.338.140 I slot release: id 0 | task 11910 | stop processing: n_tokens = 524, truncated = 0 1.48.363.185 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 524, t_last = 108245176 1.48.363.233 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.330 MiB) 1.48.450.413 I slot launch_slot_: id 0 | task 11991 | processing task, is_child = 0 1.48.994.427 I slot print_timing: id 0 | task 11991 | prompt eval time = 113.29 ms / 352 tokens ( 0.32 ms per token, 3107.07 tokens per second) 1.48.994.433 I slot print_timing: id 0 | task 11991 | eval time = 430.71 ms / 64 tokens ( 6.84 ms per token, 146.27 tokens per second) 1.48.994.434 I slot print_timing: id 0 | task 11991 | total time = 544.00 ms / 416 tokens 1.48.994.435 I slot print_timing: id 0 | task 11991 | graphs reused = 11303 1.48.994.436 I slot print_timing: id 0 | task 11991 | graph reallocs = 0 / 0 (same size) / (changed size) 1.48.994.463 I slot release: id 0 | task 11991 | stop processing: n_tokens = 447, truncated = 0 1.49.017.426 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 108901498 1.49.017.468 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 1.49.086.894 I slot launch_slot_: id 0 | task 12058 | processing task, is_child = 0 1.50.122.738 I slot print_timing: id 0 | task 12058 | prompt eval time = 136.16 ms / 550 tokens ( 0.25 ms per token, 4039.51 tokens per second) 1.50.122.744 I slot print_timing: id 0 | task 12058 | eval time = 899.67 ms / 133 tokens ( 6.82 ms per token, 146.72 tokens per second) 1.50.122.745 I slot print_timing: id 0 | task 12058 | total time = 1035.83 ms / 683 tokens 1.50.122.746 I slot print_timing: id 0 | task 12058 | graphs reused = 11434 1.50.122.747 I slot print_timing: id 0 | task 12058 | graph reallocs = 0 / 0 (same size) / (changed size) 1.50.122.782 I slot release: id 0 | task 12058 | stop processing: n_tokens = 714, truncated = 0 1.50.140.676 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 714, t_last = 110029818 1.50.140.731 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.646 MiB) 1.50.236.458 I slot launch_slot_: id 0 | task 12195 | processing task, is_child = 0 1.52.204.750 I slot print_timing: id 0 | task 12195 | prompt eval time = 157.72 ms / 772 tokens ( 0.20 ms per token, 4894.75 tokens per second) 1.52.204.755 I slot print_timing: id 0 | task 12195 | eval time = 1810.55 ms / 263 tokens ( 6.91 ms per token, 144.71 tokens per second) 1.52.204.756 I slot print_timing: id 0 | task 12195 | total time = 1968.27 ms / 1035 tokens 1.52.204.757 I slot print_timing: id 0 | task 12195 | graphs reused = 11694 1.52.204.758 I slot print_timing: id 0 | task 12195 | graph reallocs = 0 / 0 (same size) / (changed size) 1.52.204.796 I slot release: id 0 | task 12195 | stop processing: n_tokens = 1066, truncated = 0 1.52.219.679 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1066, t_last = 112111832 1.52.219.765 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.549 MiB) 1.52.325.175 I slot launch_slot_: id 0 | task 12462 | processing task, is_child = 0 1.53.716.250 I slot print_timing: id 0 | task 12462 | prompt eval time = 155.05 ms / 683 tokens ( 0.23 ms per token, 4404.97 tokens per second) 1.53.716.255 I slot print_timing: id 0 | task 12462 | eval time = 1236.01 ms / 181 tokens ( 6.87 ms per token, 145.63 tokens per second) 1.53.716.257 I slot print_timing: id 0 | task 12462 | total time = 1391.06 ms / 864 tokens 1.53.716.257 I slot print_timing: id 0 | task 12462 | graphs reused = 11872 1.53.716.258 I slot print_timing: id 0 | task 12462 | graph reallocs = 0 / 0 (same size) / (changed size) 1.53.716.295 I slot release: id 0 | task 12462 | stop processing: n_tokens = 895, truncated = 0 1.53.731.353 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 895, t_last = 113623331 1.53.731.421 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.328 MiB) 1.53.831.218 I slot launch_slot_: id 0 | task 12647 | processing task, is_child = 0 1.55.458.440 I slot print_timing: id 0 | task 12647 | prompt eval time = 141.89 ms / 579 tokens ( 0.25 ms per token, 4080.71 tokens per second) 1.55.458.445 I slot print_timing: id 0 | task 12647 | eval time = 1485.32 ms / 218 tokens ( 6.84 ms per token, 146.10 tokens per second) 1.55.458.446 I slot print_timing: id 0 | task 12647 | total time = 1627.20 ms / 797 tokens 1.55.458.448 I slot print_timing: id 0 | task 12647 | graphs reused = 12087 1.55.458.448 I slot print_timing: id 0 | task 12647 | graph reallocs = 0 / 0 (same size) / (changed size) 1.55.458.484 I slot release: id 0 | task 12647 | stop processing: n_tokens = 828, truncated = 0 1.55.478.103 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 828, t_last = 115365520 1.55.478.167 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.864 MiB) 1.55.498.324 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.611 MiB) 1.55.602.032 I slot launch_slot_: id 0 | task 12869 | processing task, is_child = 0 1.56.456.875 I slot print_timing: id 0 | task 12869 | prompt eval time = 136.24 ms / 500 tokens ( 0.27 ms per token, 3669.91 tokens per second) 1.56.456.881 I slot print_timing: id 0 | task 12869 | eval time = 718.58 ms / 106 tokens ( 6.84 ms per token, 146.12 tokens per second) 1.56.456.882 I slot print_timing: id 0 | task 12869 | total time = 854.82 ms / 606 tokens 1.56.456.883 I slot print_timing: id 0 | task 12869 | graphs reused = 12191 1.56.456.884 I slot print_timing: id 0 | task 12869 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.456.917 I slot release: id 0 | task 12869 | stop processing: n_tokens = 637, truncated = 0 1.56.486.290 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 116363953 1.56.486.346 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.296 MiB) 1.56.554.958 I slot launch_slot_: id 0 | task 12978 | processing task, is_child = 0 1.57.505.004 I slot print_timing: id 0 | task 12978 | prompt eval time = 162.76 ms / 776 tokens ( 0.21 ms per token, 4767.70 tokens per second) 1.57.505.009 I slot print_timing: id 0 | task 12978 | eval time = 787.26 ms / 116 tokens ( 6.85 ms per token, 146.08 tokens per second) 1.57.505.010 I slot print_timing: id 0 | task 12978 | total time = 950.03 ms / 892 tokens 1.57.505.011 I slot print_timing: id 0 | task 12978 | graphs reused = 12305 1.57.505.012 I slot print_timing: id 0 | task 12978 | graph reallocs = 0 / 0 (same size) / (changed size) 1.57.505.052 I slot release: id 0 | task 12978 | stop processing: n_tokens = 923, truncated = 0 1.57.529.881 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 923, t_last = 117412088 1.57.529.948 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.268 MiB) 1.57.617.803 I slot launch_slot_: id 0 | task 13098 | processing task, is_child = 0 1.59.087.189 I slot print_timing: id 0 | task 13098 | prompt eval time = 132.53 ms / 504 tokens ( 0.26 ms per token, 3802.80 tokens per second) 1.59.087.195 I slot print_timing: id 0 | task 13098 | eval time = 1336.83 ms / 197 tokens ( 6.82 ms per token, 146.62 tokens per second) 1.59.087.197 I slot print_timing: id 0 | task 13098 | total time = 1469.37 ms / 701 tokens 1.59.087.197 I slot print_timing: id 0 | task 13098 | graphs reused = 12500 1.59.087.198 I slot print_timing: id 0 | task 13098 | graph reallocs = 0 / 0 (same size) / (changed size) 1.59.087.231 I slot release: id 0 | task 13098 | stop processing: n_tokens = 732, truncated = 0 1.59.101.365 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 732, t_last = 118994267 1.59.101.422 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.578 MiB) 1.59.179.282 I slot launch_slot_: id 0 | task 13298 | processing task, is_child = 0 2.00.741.072 I slot print_timing: id 0 | task 13298 | prompt eval time = 149.48 ms / 633 tokens ( 0.24 ms per token, 4234.60 tokens per second) 2.00.741.077 I slot print_timing: id 0 | task 13298 | eval time = 1412.28 ms / 207 tokens ( 6.86 ms per token, 145.86 tokens per second) 2.00.741.078 I slot print_timing: id 0 | task 13298 | total time = 1561.77 ms / 840 tokens 2.00.741.079 I slot print_timing: id 0 | task 13298 | graphs reused = 12704 2.00.741.079 I slot print_timing: id 0 | task 13298 | graph reallocs = 0 / 0 (same size) / (changed size) 2.00.741.117 I slot release: id 0 | task 13298 | stop processing: n_tokens = 871, truncated = 0 2.00.767.066 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 871, t_last = 120648152 2.00.767.129 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 327.241 MiB) 2.00.857.356 I slot launch_slot_: id 0 | task 13509 | processing task, is_child = 0 2.01.890.998 I slot print_timing: id 0 | task 13509 | prompt eval time = 122.37 ms / 395 tokens ( 0.31 ms per token, 3227.81 tokens per second) 2.01.891.005 I slot print_timing: id 0 | task 13509 | eval time = 911.25 ms / 134 tokens ( 6.85 ms per token, 145.95 tokens per second) 2.01.891.006 I slot print_timing: id 0 | task 13509 | total time = 1033.62 ms / 529 tokens 2.01.891.007 I slot print_timing: id 0 | task 13509 | graphs reused = 12835 2.01.891.008 I slot print_timing: id 0 | task 13509 | graph reallocs = 0 / 0 (same size) / (changed size) 2.01.891.036 I slot release: id 0 | task 13509 | stop processing: n_tokens = 560, truncated = 0 2.01.920.676 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 121798072 2.01.920.725 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.204 MiB) 2.01.996.792 I slot launch_slot_: id 0 | task 13646 | processing task, is_child = 0 2.03.558.762 I slot print_timing: id 0 | task 13646 | prompt eval time = 138.21 ms / 584 tokens ( 0.24 ms per token, 4225.52 tokens per second) 2.03.558.769 I slot print_timing: id 0 | task 13646 | eval time = 1423.74 ms / 209 tokens ( 6.84 ms per token, 146.09 tokens per second) 2.03.558.770 I slot print_timing: id 0 | task 13646 | total time = 1561.95 ms / 793 tokens 2.03.558.771 I slot print_timing: id 0 | task 13646 | graphs reused = 13041 2.03.558.772 I slot print_timing: id 0 | task 13646 | graph reallocs = 0 / 0 (same size) / (changed size) 2.03.558.812 I slot release: id 0 | task 13646 | stop processing: n_tokens = 824, truncated = 0 2.03.577.337 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 824, t_last = 123465848 2.03.577.391 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.831 MiB) 2.03.663.417 I slot launch_slot_: id 0 | task 13859 | processing task, is_child = 0 2.05.384.703 I slot print_timing: id 0 | task 13859 | prompt eval time = 154.41 ms / 695 tokens ( 0.22 ms per token, 4501.09 tokens per second) 2.05.384.708 I slot print_timing: id 0 | task 13859 | eval time = 1566.86 ms / 230 tokens ( 6.84 ms per token, 146.15 tokens per second) 2.05.384.709 I slot print_timing: id 0 | task 13859 | total time = 1721.27 ms / 925 tokens 2.05.384.710 I slot print_timing: id 0 | task 13859 | graphs reused = 13268 2.05.384.711 I slot print_timing: id 0 | task 13859 | graph reallocs = 0 / 0 (same size) / (changed size) 2.05.384.749 I slot release: id 0 | task 13859 | stop processing: n_tokens = 956, truncated = 0 2.05.406.885 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 956, t_last = 125291785 2.05.406.952 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 322.300 MiB) 2.05.505.626 I slot launch_slot_: id 0 | task 14093 | processing task, is_child = 0 2.06.966.510 I slot print_timing: id 0 | task 14093 | prompt eval time = 163.03 ms / 769 tokens ( 0.21 ms per token, 4716.92 tokens per second) 2.06.966.515 I slot print_timing: id 0 | task 14093 | eval time = 1297.83 ms / 191 tokens ( 6.83 ms per token, 146.40 tokens per second) 2.06.966.516 I slot print_timing: id 0 | task 14093 | total time = 1460.86 ms / 960 tokens 2.06.966.517 I slot print_timing: id 0 | task 14093 | graphs reused = 13457 2.06.966.518 I slot print_timing: id 0 | task 14093 | graph reallocs = 0 / 0 (same size) / (changed size) 2.06.966.557 I slot release: id 0 | task 14093 | stop processing: n_tokens = 991, truncated = 0 2.06.983.778 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 991, t_last = 126873593 2.06.983.847 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.176 MiB) 2.07.004.044 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 2.07.112.819 I slot launch_slot_: id 0 | task 14288 | processing task, is_child = 0 2.08.146.119 I slot print_timing: id 0 | task 14288 | prompt eval time = 137.44 ms / 576 tokens ( 0.24 ms per token, 4190.89 tokens per second) 2.08.146.124 I slot print_timing: id 0 | task 14288 | eval time = 895.84 ms / 124 tokens ( 7.28 ms per token, 137.30 tokens per second) 2.08.146.125 I slot print_timing: id 0 | task 14288 | total time = 1033.28 ms / 700 tokens 2.08.146.126 I slot print_timing: id 0 | task 14288 | graphs reused = 13579 2.08.146.127 I slot print_timing: id 0 | task 14288 | graph reallocs = 0 / 0 (same size) / (changed size) 2.08.146.161 I slot release: id 0 | task 14288 | stop processing: n_tokens = 731, truncated = 0 2.08.168.192 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 731, t_last = 128053197 2.08.168.253 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.577 MiB) 2.08.245.094 I slot launch_slot_: id 0 | task 14416 | processing task, is_child = 0 2.10.267.175 I slot print_timing: id 0 | task 14416 | prompt eval time = 149.57 ms / 655 tokens ( 0.23 ms per token, 4379.34 tokens per second) 2.10.267.181 I slot print_timing: id 0 | task 14416 | eval time = 1872.50 ms / 275 tokens ( 6.83 ms per token, 146.33 tokens per second) 2.10.267.182 I slot print_timing: id 0 | task 14416 | total time = 2022.06 ms / 930 tokens 2.10.267.183 I slot print_timing: id 0 | task 14416 | graphs reused = 13851 2.10.267.184 I slot print_timing: id 0 | task 14416 | graph reallocs = 0 / 0 (same size) / (changed size) 2.10.267.220 I slot release: id 0 | task 14416 | stop processing: n_tokens = 961, truncated = 0 2.10.287.548 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 961, t_last = 130174256 2.10.287.617 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.204 MiB) 2.10.363.017 I slot launch_slot_: id 0 | task 14695 | processing task, is_child = 0 2.11.333.899 I slot print_timing: id 0 | task 14695 | prompt eval time = 145.35 ms / 621 tokens ( 0.23 ms per token, 4272.39 tokens per second) 2.11.333.905 I slot print_timing: id 0 | task 14695 | eval time = 825.51 ms / 121 tokens ( 6.88 ms per token, 145.36 tokens per second) 2.11.333.906 I slot print_timing: id 0 | task 14695 | total time = 970.86 ms / 742 tokens 2.11.333.907 I slot print_timing: id 0 | task 14695 | graphs reused = 13969 2.11.333.908 I slot print_timing: id 0 | task 14695 | graph reallocs = 0 / 0 (same size) / (changed size) 2.11.333.945 I slot release: id 0 | task 14695 | stop processing: n_tokens = 773, truncated = 0 2.11.362.035 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 773, t_last = 131240980 2.11.362.086 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.014 MiB) 2.11.462.994 I slot launch_slot_: id 0 | task 14820 | processing task, is_child = 0 2.12.859.503 I slot print_timing: id 0 | task 14820 | prompt eval time = 159.97 ms / 767 tokens ( 0.21 ms per token, 4794.50 tokens per second) 2.12.859.509 I slot print_timing: id 0 | task 14820 | eval time = 1236.52 ms / 178 tokens ( 6.99 ms per token, 143.14 tokens per second) 2.12.859.510 I slot print_timing: id 0 | task 14820 | total time = 1396.49 ms / 945 tokens 2.12.859.510 I slot print_timing: id 0 | task 14820 | graphs reused = 14145 2.12.859.511 I slot print_timing: id 0 | task 14820 | graph reallocs = 0 / 0 (same size) / (changed size) 2.12.859.557 I slot release: id 0 | task 14820 | stop processing: n_tokens = 976, truncated = 0 2.12.884.319 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 976, t_last = 132766593 2.12.884.388 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.890 MiB) 2.12.979.765 I slot launch_slot_: id 0 | task 15002 | processing task, is_child = 0 2.14.571.819 I slot print_timing: id 0 | task 15002 | prompt eval time = 176.27 ms / 864 tokens ( 0.20 ms per token, 4901.52 tokens per second) 2.14.571.824 I slot print_timing: id 0 | task 15002 | eval time = 1415.76 ms / 203 tokens ( 7.01 ms per token, 142.68 tokens per second) 2.14.571.825 I slot print_timing: id 0 | task 15002 | total time = 1592.03 ms / 1067 tokens 2.14.571.826 I slot print_timing: id 0 | task 15002 | graphs reused = 14345 2.14.571.827 I slot print_timing: id 0 | task 15002 | graph reallocs = 0 / 0 (same size) / (changed size) 2.14.571.871 I slot release: id 0 | task 15002 | stop processing: n_tokens = 1098, truncated = 0 2.14.595.875 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1098, t_last = 134478907 2.14.595.948 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.235 MiB) 2.14.617.879 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.954 MiB) 2.14.700.596 I slot launch_slot_: id 0 | task 15209 | processing task, is_child = 0 2.15.732.719 I slot print_timing: id 0 | task 15209 | prompt eval time = 152.76 ms / 646 tokens ( 0.24 ms per token, 4228.94 tokens per second) 2.15.732.725 I slot print_timing: id 0 | task 15209 | eval time = 879.35 ms / 129 tokens ( 6.87 ms per token, 145.56 tokens per second) 2.15.732.726 I slot print_timing: id 0 | task 15209 | total time = 1032.10 ms / 775 tokens 2.15.732.727 I slot print_timing: id 0 | task 15209 | graphs reused = 14471 2.15.732.728 I slot print_timing: id 0 | task 15209 | graph reallocs = 0 / 0 (same size) / (changed size) 2.15.732.767 I slot release: id 0 | task 15209 | stop processing: n_tokens = 806, truncated = 0 2.15.748.276 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 806, t_last = 135639802 2.15.748.342 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.330 MiB) 2.15.839.434 I slot launch_slot_: id 0 | task 15342 | processing task, is_child = 0 2.17.561.126 I slot print_timing: id 0 | task 15342 | prompt eval time = 168.67 ms / 720 tokens ( 0.23 ms per token, 4268.77 tokens per second) 2.17.561.132 I slot print_timing: id 0 | task 15342 | eval time = 1553.01 ms / 219 tokens ( 7.12 ms per token, 140.37 tokens per second) 2.17.561.133 I slot print_timing: id 0 | task 15342 | total time = 1721.67 ms / 939 tokens 2.17.561.134 I slot print_timing: id 0 | task 15342 | graphs reused = 14687 2.17.561.135 I slot print_timing: id 0 | task 15342 | graph reallocs = 0 / 0 (same size) / (changed size) 2.17.561.177 I slot release: id 0 | task 15342 | stop processing: n_tokens = 970, truncated = 0 2.17.586.622 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 970, t_last = 137468213 2.17.586.690 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.203 MiB) 2.17.672.665 I slot launch_slot_: id 0 | task 15565 | processing task, is_child = 0 2.19.259.870 I slot print_timing: id 0 | task 15565 | prompt eval time = 135.71 ms / 509 tokens ( 0.27 ms per token, 3750.56 tokens per second) 2.19.259.875 I slot print_timing: id 0 | task 15565 | eval time = 1451.47 ms / 214 tokens ( 6.81 ms per token, 146.75 tokens per second) 2.19.259.876 I slot print_timing: id 0 | task 15565 | total time = 1587.19 ms / 723 tokens 2.19.259.877 I slot print_timing: id 0 | task 15565 | graphs reused = 14899 2.19.259.878 I slot print_timing: id 0 | task 15565 | graph reallocs = 0 / 0 (same size) / (changed size) 2.19.259.910 I slot release: id 0 | task 15565 | stop processing: n_tokens = 754, truncated = 0 2.19.280.008 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 754, t_last = 139166946 2.19.280.074 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.392 MiB) 2.19.356.185 I slot launch_slot_: id 0 | task 15782 | processing task, is_child = 0 2.21.142.215 I slot print_timing: id 0 | task 15782 | prompt eval time = 138.35 ms / 581 tokens ( 0.24 ms per token, 4199.43 tokens per second) 2.21.142.221 I slot print_timing: id 0 | task 15782 | eval time = 1647.66 ms / 242 tokens ( 6.84 ms per token, 146.27 tokens per second) 2.21.142.222 I slot print_timing: id 0 | task 15782 | total time = 1786.01 ms / 823 tokens 2.21.142.223 I slot print_timing: id 0 | task 15782 | graphs reused = 15138 2.21.142.223 I slot print_timing: id 0 | task 15782 | graph reallocs = 0 / 0 (same size) / (changed size) 2.21.142.259 I slot release: id 0 | task 15782 | stop processing: n_tokens = 854, truncated = 0 2.21.158.656 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 854, t_last = 141049295 2.21.158.720 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.891 MiB) 2.21.258.257 I slot launch_slot_: id 0 | task 16028 | processing task, is_child = 0 2.22.939.997 I slot print_timing: id 0 | task 16028 | prompt eval time = 179.74 ms / 925 tokens ( 0.19 ms per token, 5146.32 tokens per second) 2.22.940.002 I slot print_timing: id 0 | task 16028 | eval time = 1501.98 ms / 220 tokens ( 6.86 ms per token, 145.81 tokens per second) 2.22.940.003 I slot print_timing: id 0 | task 16028 | total time = 1681.72 ms / 1145 tokens 2.22.940.004 I slot print_timing: id 0 | task 16028 | graphs reused = 15355 2.22.940.005 I slot print_timing: id 0 | task 16028 | graph reallocs = 0 / 0 (same size) / (changed size) 2.22.940.050 I slot release: id 0 | task 16028 | stop processing: n_tokens = 1176, truncated = 0 2.22.959.944 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1176, t_last = 142847086 2.22.960.026 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.483 MiB) 2.23.057.268 I slot launch_slot_: id 0 | task 16252 | processing task, is_child = 0 2.24.934.291 I slot print_timing: id 0 | task 16252 | prompt eval time = 175.37 ms / 885 tokens ( 0.20 ms per token, 5046.39 tokens per second) 2.24.934.297 I slot print_timing: id 0 | task 16252 | eval time = 1701.63 ms / 245 tokens ( 6.97 ms per token, 143.39 tokens per second) 2.24.934.298 I slot print_timing: id 0 | task 16252 | total time = 1877.00 ms / 1130 tokens 2.24.934.298 I slot print_timing: id 0 | task 16252 | graphs reused = 15597 2.24.934.299 I slot print_timing: id 0 | task 16252 | graph reallocs = 0 / 0 (same size) / (changed size) 2.24.934.345 I slot release: id 0 | task 16252 | stop processing: n_tokens = 1161, truncated = 0 2.24.953.418 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1161, t_last = 144841381 2.24.953.496 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.083 MiB) 2.25.068.930 I slot launch_slot_: id 0 | task 16501 | processing task, is_child = 0 2.26.554.390 I slot print_timing: id 0 | task 16501 | prompt eval time = 120.21 ms / 392 tokens ( 0.31 ms per token, 3260.93 tokens per second) 2.26.554.396 I slot print_timing: id 0 | task 16501 | eval time = 1365.23 ms / 201 tokens ( 6.83 ms per token, 146.50 tokens per second) 2.26.554.397 I slot print_timing: id 0 | task 16501 | total time = 1485.44 ms / 593 tokens 2.26.554.398 I slot print_timing: id 0 | task 16501 | graphs reused = 15795 2.26.554.399 I slot print_timing: id 0 | task 16501 | graph reallocs = 0 / 0 (same size) / (changed size) 2.26.554.429 I slot release: id 0 | task 16501 | stop processing: n_tokens = 624, truncated = 0 2.26.574.038 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 624, t_last = 146461464 2.26.574.095 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 385.091 MiB) 2.26.660.661 I slot launch_slot_: id 0 | task 16705 | processing task, is_child = 0 2.27.169.330 I slot print_timing: id 0 | task 16705 | prompt eval time = 110.97 ms / 331 tokens ( 0.34 ms per token, 2982.65 tokens per second) 2.27.169.336 I slot print_timing: id 0 | task 16705 | eval time = 397.67 ms / 59 tokens ( 6.86 ms per token, 145.85 tokens per second) 2.27.169.337 I slot print_timing: id 0 | task 16705 | total time = 508.65 ms / 390 tokens 2.27.169.337 I slot print_timing: id 0 | task 16705 | graphs reused = 15852 2.27.169.338 I slot print_timing: id 0 | task 16705 | graph reallocs = 0 / 0 (same size) / (changed size) 2.27.169.366 I slot release: id 0 | task 16705 | stop processing: n_tokens = 421, truncated = 0 2.27.196.915 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 421, t_last = 147076402 2.27.196.953 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.743 MiB) 2.27.289.633 I slot launch_slot_: id 0 | task 16767 | processing task, is_child = 0 2.28.766.873 I slot print_timing: id 0 | task 16767 | prompt eval time = 113.15 ms / 357 tokens ( 0.32 ms per token, 3155.16 tokens per second) 2.28.766.879 I slot print_timing: id 0 | task 16767 | eval time = 1364.07 ms / 201 tokens ( 6.82 ms per token, 146.62 tokens per second) 2.28.766.880 I slot print_timing: id 0 | task 16767 | total time = 1477.22 ms / 558 tokens 2.28.766.881 I slot print_timing: id 0 | task 16767 | graphs reused = 16050 2.28.766.881 I slot print_timing: id 0 | task 16767 | graph reallocs = 0 / 0 (same size) / (changed size) 2.28.766.909 I slot release: id 0 | task 16767 | stop processing: n_tokens = 589, truncated = 0 2.28.786.133 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 589, t_last = 148673945 2.28.786.186 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 377.648 MiB) 2.28.866.864 I slot launch_slot_: id 0 | task 16971 | processing task, is_child = 0 2.29.450.878 I slot print_timing: id 0 | task 16971 | prompt eval time = 116.35 ms / 315 tokens ( 0.37 ms per token, 2707.44 tokens per second) 2.29.450.884 I slot print_timing: id 0 | task 16971 | eval time = 467.65 ms / 69 tokens ( 6.88 ms per token, 145.41 tokens per second) 2.29.450.885 I slot print_timing: id 0 | task 16971 | total time = 584.00 ms / 384 tokens 2.29.450.886 I slot print_timing: id 0 | task 16971 | graphs reused = 16117 2.29.450.886 I slot print_timing: id 0 | task 16971 | graph reallocs = 0 / 0 (same size) / (changed size) 2.29.450.914 I slot release: id 0 | task 16971 | stop processing: n_tokens = 415, truncated = 0 2.29.473.120 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 415, t_last = 149357950 2.29.473.169 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.424 MiB) 2.29.569.375 I slot launch_slot_: id 0 | task 17043 | processing task, is_child = 0 2.30.100.658 I slot print_timing: id 0 | task 17043 | prompt eval time = 115.75 ms / 378 tokens ( 0.31 ms per token, 3265.66 tokens per second) 2.30.100.664 I slot print_timing: id 0 | task 17043 | eval time = 415.51 ms / 60 tokens ( 7.04 ms per token, 141.99 tokens per second) 2.30.100.665 I slot print_timing: id 0 | task 17043 | total time = 531.26 ms / 438 tokens 2.30.100.666 I slot print_timing: id 0 | task 17043 | graphs reused = 16175 2.30.100.667 I slot print_timing: id 0 | task 17043 | graph reallocs = 0 / 0 (same size) / (changed size) 2.30.100.698 I slot release: id 0 | task 17043 | stop processing: n_tokens = 469, truncated = 0 2.30.126.803 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 469, t_last = 150007733 2.30.126.848 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 380.619 MiB) 2.30.207.465 I slot launch_slot_: id 0 | task 17106 | processing task, is_child = 0 2.30.512.692 I slot print_timing: id 0 | task 17106 | prompt eval time = 116.23 ms / 295 tokens ( 0.39 ms per token, 2538.11 tokens per second) 2.30.512.698 I slot print_timing: id 0 | task 17106 | eval time = 188.98 ms / 28 tokens ( 7.00 ms per token, 142.87 tokens per second) 2.30.512.699 I slot print_timing: id 0 | task 17106 | total time = 305.21 ms / 323 tokens 2.30.512.699 I slot print_timing: id 0 | task 17106 | graphs reused = 16201 2.30.512.700 I slot print_timing: id 0 | task 17106 | graph reallocs = 0 / 0 (same size) / (changed size) 2.30.512.727 I slot release: id 0 | task 17106 | stop processing: n_tokens = 354, truncated = 0 2.30.533.440 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 354, t_last = 150419763 2.30.533.481 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 324.395 MiB) 2.30.625.555 I slot launch_slot_: id 0 | task 17137 | processing task, is_child = 0 2.31.229.269 I slot print_timing: id 0 | task 17137 | prompt eval time = 116.33 ms / 337 tokens ( 0.35 ms per token, 2896.83 tokens per second) 2.31.229.275 I slot print_timing: id 0 | task 17137 | eval time = 487.36 ms / 72 tokens ( 6.86 ms per token, 145.68 tokens per second) 2.31.229.276 I slot print_timing: id 0 | task 17137 | total time = 603.69 ms / 409 tokens 2.31.229.277 I slot print_timing: id 0 | task 17137 | graphs reused = 16271 2.31.229.278 I slot print_timing: id 0 | task 17137 | graph reallocs = 0 / 0 (same size) / (changed size) 2.31.229.306 I slot release: id 0 | task 17137 | stop processing: n_tokens = 440, truncated = 0 2.31.249.803 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 440, t_last = 151136341 2.31.249.849 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.993 MiB) 2.31.355.082 I slot launch_slot_: id 0 | task 17212 | processing task, is_child = 0 2.32.164.339 I slot print_timing: id 0 | task 17212 | prompt eval time = 113.84 ms / 325 tokens ( 0.35 ms per token, 2854.91 tokens per second) 2.32.164.345 I slot print_timing: id 0 | task 17212 | eval time = 695.40 ms / 103 tokens ( 6.82 ms per token, 146.68 tokens per second) 2.32.164.346 I slot print_timing: id 0 | task 17212 | total time = 809.24 ms / 428 tokens 2.32.164.347 I slot print_timing: id 0 | task 17212 | graphs reused = 16372 2.32.164.348 I slot print_timing: id 0 | task 17212 | graph reallocs = 0 / 0 (same size) / (changed size) 2.32.164.376 I slot release: id 0 | task 17212 | stop processing: n_tokens = 459, truncated = 0 2.32.188.159 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.108 (> 0.100 thold), f_keep = 0.070 2.32.235.696 I slot launch_slot_: id 0 | task 17318 | processing task, is_child = 0 2.33.797.981 I slot print_timing: id 0 | task 17318 | prompt eval time = 100.42 ms / 264 tokens ( 0.38 ms per token, 2628.85 tokens per second) 2.33.797.987 I slot print_timing: id 0 | task 17318 | eval time = 1461.84 ms / 216 tokens ( 6.80 ms per token, 147.07 tokens per second) 2.33.797.987 I slot print_timing: id 0 | task 17318 | total time = 1562.26 ms / 480 tokens 2.33.797.988 I slot print_timing: id 0 | task 17318 | graphs reused = 16586 2.33.797.989 I slot print_timing: id 0 | task 17318 | graph reallocs = 0 / 0 (same size) / (changed size) 2.33.798.013 I slot release: id 0 | task 17318 | stop processing: n_tokens = 511, truncated = 0 2.33.818.925 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 511, t_last = 153705048 2.33.818.972 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.016 MiB) 2.33.907.909 I slot launch_slot_: id 0 | task 17537 | processing task, is_child = 0 2.34.078.823 I slot print_timing: id 0 | task 17537 | prompt eval time = 112.39 ms / 331 tokens ( 0.34 ms per token, 2945.18 tokens per second) 2.34.078.828 I slot print_timing: id 0 | task 17537 | eval time = 58.51 ms / 9 tokens ( 7.31 ms per token, 136.73 tokens per second) 2.34.078.829 I slot print_timing: id 0 | task 17537 | total time = 170.90 ms / 340 tokens 2.34.078.830 I slot print_timing: id 0 | task 17537 | graphs reused = 16593 2.34.078.831 I slot print_timing: id 0 | task 17537 | graph reallocs = 0 / 0 (same size) / (changed size) 2.34.078.858 I slot release: id 0 | task 17537 | stop processing: n_tokens = 371, truncated = 0 2.34.101.342 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 371, t_last = 153985894 2.34.101.386 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 377.523 MiB) 2.34.197.849 I slot launch_slot_: id 0 | task 17549 | processing task, is_child = 0 2.35.123.302 I slot print_timing: id 0 | task 17549 | prompt eval time = 114.17 ms / 333 tokens ( 0.34 ms per token, 2916.83 tokens per second) 2.35.123.308 I slot print_timing: id 0 | task 17549 | eval time = 811.27 ms / 120 tokens ( 6.82 ms per token, 146.68 tokens per second) 2.35.123.309 I slot print_timing: id 0 | task 17549 | total time = 925.43 ms / 453 tokens 2.35.123.310 I slot print_timing: id 0 | task 17549 | graphs reused = 16711 2.35.123.311 I slot print_timing: id 0 | task 17549 | graph reallocs = 0 / 0 (same size) / (changed size) 2.35.123.340 I slot release: id 0 | task 17549 | stop processing: n_tokens = 484, truncated = 0 2.35.141.182 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 484, t_last = 155030376 2.35.141.232 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.651 MiB) 2.35.224.162 I slot launch_slot_: id 0 | task 17672 | processing task, is_child = 0 2.38.337.554 I slot print_timing: id 0 | task 17672 | n_gen = 441, tg = 146.66 t/s, tg_3s = 147.00 t/s 2.40.090.822 I slot print_timing: id 0 | task 17672 | prompt eval time = 113.33 ms / 346 tokens ( 0.33 ms per token, 3052.90 tokens per second) 2.40.090.827 I slot print_timing: id 0 | task 17672 | eval time = 4753.31 ms / 698 tokens ( 6.82 ms per token, 146.63 tokens per second) 2.40.090.828 I slot print_timing: id 0 | task 17672 | total time = 4866.64 ms / 1044 tokens 2.40.090.829 I slot print_timing: id 0 | task 17672 | graphs reused = 17404 2.40.090.830 I slot print_timing: id 0 | task 17672 | graph reallocs = 0 / 0 (same size) / (changed size) 2.40.090.858 I slot release: id 0 | task 17672 | stop processing: n_tokens = 1075, truncated = 0 2.40.117.314 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1075, t_last = 159997894 2.40.117.388 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.746 MiB) 2.40.197.144 I slot launch_slot_: id 0 | task 18373 | processing task, is_child = 0 2.40.578.358 I slot print_timing: id 0 | task 18373 | prompt eval time = 111.88 ms / 325 tokens ( 0.34 ms per token, 2904.87 tokens per second) 2.40.578.364 I slot print_timing: id 0 | task 18373 | eval time = 269.31 ms / 40 tokens ( 6.91 ms per token, 144.81 tokens per second) 2.40.578.365 I slot print_timing: id 0 | task 18373 | total time = 381.20 ms / 365 tokens 2.40.578.366 I slot print_timing: id 0 | task 18373 | graphs reused = 17442 2.40.578.367 I slot print_timing: id 0 | task 18373 | graph reallocs = 0 / 0 (same size) / (changed size) 2.40.578.395 I slot release: id 0 | task 18373 | stop processing: n_tokens = 396, truncated = 0 2.40.597.366 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 396, t_last = 160485431 2.40.597.411 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.615 MiB) 2.40.681.585 I slot launch_slot_: id 0 | task 18416 | processing task, is_child = 0 2.42.225.483 I slot print_timing: id 0 | task 18416 | prompt eval time = 110.32 ms / 322 tokens ( 0.34 ms per token, 2918.68 tokens per second) 2.42.225.489 I slot print_timing: id 0 | task 18416 | eval time = 1433.55 ms / 211 tokens ( 6.83 ms per token, 146.49 tokens per second) 2.42.225.490 I slot print_timing: id 0 | task 18416 | total time = 1543.88 ms / 533 tokens 2.42.225.490 I slot print_timing: id 0 | task 18416 | graphs reused = 17650 2.42.225.491 I slot print_timing: id 0 | task 18416 | graph reallocs = 0 / 0 (same size) / (changed size) 2.42.225.521 I slot release: id 0 | task 18416 | stop processing: n_tokens = 564, truncated = 0 2.42.249.384 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 564, t_last = 162132557 2.42.249.435 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.807 MiB) 2.42.321.368 I slot launch_slot_: id 0 | task 18630 | processing task, is_child = 0 2.44.134.726 I slot print_timing: id 0 | task 18630 | prompt eval time = 108.18 ms / 338 tokens ( 0.32 ms per token, 3124.39 tokens per second) 2.44.134.731 I slot print_timing: id 0 | task 18630 | eval time = 1705.16 ms / 251 tokens ( 6.82 ms per token, 146.61 tokens per second) 2.44.134.733 I slot print_timing: id 0 | task 18630 | total time = 1813.34 ms / 589 tokens 2.44.134.734 I slot print_timing: id 0 | task 18630 | graphs reused = 17898 2.44.134.734 I slot print_timing: id 0 | task 18630 | graph reallocs = 0 / 0 (same size) / (changed size) 2.44.134.763 I slot release: id 0 | task 18630 | stop processing: n_tokens = 620, truncated = 0 2.44.152.450 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 620, t_last = 164041799 2.44.196.734 I slot launch_slot_: id 0 | task 18884 | processing task, is_child = 0 2.46.878.303 I slot print_timing: id 0 | task 18884 | prompt eval time = 108.52 ms / 347 tokens ( 0.31 ms per token, 3197.45 tokens per second) 2.46.878.309 I slot print_timing: id 0 | task 18884 | eval time = 2573.03 ms / 375 tokens ( 6.88 ms per token, 145.35 tokens per second) 2.46.878.310 I slot print_timing: id 0 | task 18884 | total time = 2681.55 ms / 722 tokens 2.46.878.311 I slot print_timing: id 0 | task 18884 | graphs reused = 18270 2.46.878.312 I slot print_timing: id 0 | task 18884 | graph reallocs = 0 / 0 (same size) / (changed size) 2.46.878.341 I slot release: id 0 | task 18884 | stop processing: n_tokens = 753, truncated = 0 2.46.903.072 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 753, t_last = 166785377 2.46.903.135 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 375.928 MiB) 2.46.996.315 I slot launch_slot_: id 0 | task 19262 | processing task, is_child = 0 2.48.789.200 I slot print_timing: id 0 | task 19262 | prompt eval time = 117.11 ms / 331 tokens ( 0.35 ms per token, 2826.45 tokens per second) 2.48.789.206 I slot print_timing: id 0 | task 19262 | eval time = 1675.76 ms / 246 tokens ( 6.84 ms per token, 146.20 tokens per second) 2.48.789.207 I slot print_timing: id 0 | task 19262 | total time = 1792.87 ms / 577 tokens 2.48.789.208 I slot print_timing: id 0 | task 19262 | graphs reused = 18513 2.48.789.209 I slot print_timing: id 0 | task 19262 | graph reallocs = 0 / 0 (same size) / (changed size) 2.48.789.237 I slot release: id 0 | task 19262 | stop processing: n_tokens = 608, truncated = 0 2.48.813.350 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 608, t_last = 168696273 2.48.813.401 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.277 MiB) 2.48.912.097 I slot launch_slot_: id 0 | task 19511 | processing task, is_child = 0 2.49.441.314 I slot print_timing: id 0 | task 19511 | prompt eval time = 117.95 ms / 345 tokens ( 0.34 ms per token, 2925.04 tokens per second) 2.49.441.320 I slot print_timing: id 0 | task 19511 | eval time = 411.25 ms / 61 tokens ( 6.85 ms per token, 145.90 tokens per second) 2.49.441.321 I slot print_timing: id 0 | task 19511 | total time = 529.20 ms / 406 tokens 2.49.441.322 I slot print_timing: id 0 | task 19511 | graphs reused = 18572 2.49.441.323 I slot print_timing: id 0 | task 19511 | graph reallocs = 0 / 0 (same size) / (changed size) 2.49.441.350 I slot release: id 0 | task 19511 | stop processing: n_tokens = 437, truncated = 0 2.49.466.114 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 169348386 2.49.466.158 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.092 MiB) 2.49.548.862 I slot launch_slot_: id 0 | task 19575 | processing task, is_child = 0 2.50.135.269 I slot print_timing: id 0 | task 19575 | prompt eval time = 107.58 ms / 320 tokens ( 0.34 ms per token, 2974.39 tokens per second) 2.50.135.275 I slot print_timing: id 0 | task 19575 | eval time = 478.80 ms / 71 tokens ( 6.84 ms per token, 146.20 tokens per second) 2.50.135.276 I slot print_timing: id 0 | task 19575 | total time = 586.39 ms / 391 tokens 2.50.135.277 I slot print_timing: id 0 | task 19575 | graphs reused = 18641 2.50.135.277 I slot print_timing: id 0 | task 19575 | graph reallocs = 0 / 0 (same size) / (changed size) 2.50.135.305 I slot release: id 0 | task 19575 | stop processing: n_tokens = 422, truncated = 0 2.50.154.445 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 422, t_last = 170042341 2.50.154.487 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 376.960 MiB) 2.50.237.486 I slot launch_slot_: id 0 | task 19649 | processing task, is_child = 0 2.50.701.869 I slot print_timing: id 0 | task 19649 | prompt eval time = 108.00 ms / 297 tokens ( 0.36 ms per token, 2750.05 tokens per second) 2.50.701.875 I slot print_timing: id 0 | task 19649 | eval time = 356.36 ms / 47 tokens ( 7.75 ms per token, 129.08 tokens per second) 2.50.701.876 I slot print_timing: id 0 | task 19649 | total time = 464.36 ms / 344 tokens 2.50.701.876 I slot print_timing: id 0 | task 19649 | graphs reused = 18686 2.50.701.877 I slot print_timing: id 0 | task 19649 | graph reallocs = 0 / 0 (same size) / (changed size) 2.50.701.904 I slot release: id 0 | task 19649 | stop processing: n_tokens = 375, truncated = 0 2.50.716.457 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 375, t_last = 170608940 2.50.716.498 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.089 MiB) 2.50.790.121 I slot launch_slot_: id 0 | task 19699 | processing task, is_child = 0 2.52.576.956 I slot print_timing: id 0 | task 19699 | prompt eval time = 113.80 ms / 343 tokens ( 0.33 ms per token, 3013.95 tokens per second) 2.52.576.962 I slot print_timing: id 0 | task 19699 | eval time = 1673.01 ms / 246 tokens ( 6.83 ms per token, 146.44 tokens per second) 2.52.576.963 I slot print_timing: id 0 | task 19699 | total time = 1786.82 ms / 589 tokens 2.52.576.963 I slot print_timing: id 0 | task 19699 | graphs reused = 18929 2.52.576.964 I slot print_timing: id 0 | task 19699 | graph reallocs = 0 / 0 (same size) / (changed size) 2.52.576.992 I slot release: id 0 | task 19699 | stop processing: n_tokens = 620, truncated = 0 2.52.603.144 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 620, t_last = 172484028 2.52.647.307 I slot launch_slot_: id 0 | task 19948 | processing task, is_child = 0 2.53.390.393 I slot print_timing: id 0 | task 19948 | prompt eval time = 115.33 ms / 371 tokens ( 0.31 ms per token, 3217.00 tokens per second) 2.53.390.399 I slot print_timing: id 0 | task 19948 | eval time = 627.74 ms / 93 tokens ( 6.82 ms per token, 146.56 tokens per second) 2.53.390.400 I slot print_timing: id 0 | task 19948 | total time = 743.07 ms / 464 tokens 2.53.390.401 I slot print_timing: id 0 | task 19948 | graphs reused = 19020 2.53.390.402 I slot print_timing: id 0 | task 19948 | graph reallocs = 0 / 0 (same size) / (changed size) 2.53.390.431 I slot release: id 0 | task 19948 | stop processing: n_tokens = 495, truncated = 0 2.53.412.412 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 495, t_last = 173297467 2.53.412.453 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.083 MiB) 2.53.501.812 I slot launch_slot_: id 0 | task 20044 | processing task, is_child = 0 2.54.609.731 I slot print_timing: id 0 | task 20044 | prompt eval time = 108.02 ms / 292 tokens ( 0.37 ms per token, 2703.28 tokens per second) 2.54.609.736 I slot print_timing: id 0 | task 20044 | eval time = 999.88 ms / 148 tokens ( 6.80 ms per token, 147.02 tokens per second) 2.54.609.737 I slot print_timing: id 0 | task 20044 | total time = 1107.90 ms / 440 tokens 2.54.609.738 I slot print_timing: id 0 | task 20044 | graphs reused = 19166 2.54.609.739 I slot print_timing: id 0 | task 20044 | graph reallocs = 0 / 0 (same size) / (changed size) 2.54.609.764 I slot release: id 0 | task 20044 | stop processing: n_tokens = 471, truncated = 0 2.54.625.024 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 471, t_last = 174516799 2.54.625.073 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.461 MiB) 2.54.723.241 I slot launch_slot_: id 0 | task 20195 | processing task, is_child = 0 2.55.289.201 I slot print_timing: id 0 | task 20195 | prompt eval time = 107.34 ms / 301 tokens ( 0.36 ms per token, 2804.17 tokens per second) 2.55.289.207 I slot print_timing: id 0 | task 20195 | eval time = 458.60 ms / 68 tokens ( 6.84 ms per token, 146.10 tokens per second) 2.55.289.208 I slot print_timing: id 0 | task 20195 | total time = 565.94 ms / 369 tokens 2.55.289.209 I slot print_timing: id 0 | task 20195 | graphs reused = 19232 2.55.289.210 I slot print_timing: id 0 | task 20195 | graph reallocs = 0 / 0 (same size) / (changed size) 2.55.289.236 I slot release: id 0 | task 20195 | stop processing: n_tokens = 400, truncated = 0 2.55.313.080 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 175196271 2.55.313.122 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.531 MiB) 2.55.405.938 I slot launch_slot_: id 0 | task 20266 | processing task, is_child = 0 2.55.924.561 I slot print_timing: id 0 | task 20266 | prompt eval time = 107.92 ms / 303 tokens ( 0.36 ms per token, 2807.64 tokens per second) 2.55.924.567 I slot print_timing: id 0 | task 20266 | eval time = 410.69 ms / 61 tokens ( 6.84 ms per token, 146.10 tokens per second) 2.55.924.568 I slot print_timing: id 0 | task 20266 | total time = 518.61 ms / 364 tokens 2.55.924.568 I slot print_timing: id 0 | task 20266 | graphs reused = 19291 2.55.924.569 I slot print_timing: id 0 | task 20266 | graph reallocs = 0 / 0 (same size) / (changed size) 2.55.924.596 I slot release: id 0 | task 20266 | stop processing: n_tokens = 395, truncated = 0 2.55.947.475 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 395, t_last = 175831631 2.55.947.516 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.062 MiB) 2.56.028.907 I slot launch_slot_: id 0 | task 20330 | processing task, is_child = 0 2.56.336.233 I slot print_timing: id 0 | task 20330 | prompt eval time = 113.56 ms / 321 tokens ( 0.35 ms per token, 2826.77 tokens per second) 2.56.336.238 I slot print_timing: id 0 | task 20330 | eval time = 193.75 ms / 29 tokens ( 6.92 ms per token, 144.52 tokens per second) 2.56.336.239 I slot print_timing: id 0 | task 20330 | total time = 307.31 ms / 350 tokens 2.56.336.240 I slot print_timing: id 0 | task 20330 | graphs reused = 19318 2.56.336.241 I slot print_timing: id 0 | task 20330 | graph reallocs = 0 / 0 (same size) / (changed size) 2.56.336.268 I slot release: id 0 | task 20330 | stop processing: n_tokens = 381, truncated = 0 2.56.354.792 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 381, t_last = 176243303 2.56.354.835 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.018 MiB) 2.56.447.042 I slot launch_slot_: id 0 | task 20362 | processing task, is_child = 0 2.56.776.682 I slot print_timing: id 0 | task 20362 | prompt eval time = 112.28 ms / 322 tokens ( 0.35 ms per token, 2867.93 tokens per second) 2.56.776.687 I slot print_timing: id 0 | task 20362 | eval time = 217.34 ms / 32 tokens ( 7.01 ms per token, 142.63 tokens per second) 2.56.776.688 I slot print_timing: id 0 | task 20362 | total time = 329.62 ms / 354 tokens 2.56.776.689 I slot print_timing: id 0 | task 20362 | graphs reused = 19348 2.56.776.690 I slot print_timing: id 0 | task 20362 | graph reallocs = 0 / 0 (same size) / (changed size) 2.56.776.719 I slot release: id 0 | task 20362 | stop processing: n_tokens = 385, truncated = 0 2.56.790.677 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 385, t_last = 176683755 2.56.790.719 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.670 MiB) 2.56.858.937 I slot launch_slot_: id 0 | task 20397 | processing task, is_child = 0 2.57.999.264 I slot print_timing: id 0 | task 20397 | prompt eval time = 112.43 ms / 323 tokens ( 0.35 ms per token, 2872.92 tokens per second) 2.57.999.269 I slot print_timing: id 0 | task 20397 | eval time = 1027.88 ms / 152 tokens ( 6.81 ms per token, 146.90 tokens per second) 2.57.999.270 I slot print_timing: id 0 | task 20397 | total time = 1140.31 ms / 475 tokens 2.57.999.271 I slot print_timing: id 0 | task 20397 | graphs reused = 19498 2.57.999.272 I slot print_timing: id 0 | task 20397 | graph reallocs = 0 / 0 (same size) / (changed size) 2.57.999.299 I slot release: id 0 | task 20397 | stop processing: n_tokens = 506, truncated = 0 2.58.025.816 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 506, t_last = 177906334 2.58.025.857 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.923 MiB) 2.58.095.521 I slot launch_slot_: id 0 | task 20552 | processing task, is_child = 0 3.01.209.754 I slot print_timing: id 0 | task 20552 | n_gen = 441, tg = 146.57 t/s, tg_3s = 146.91 t/s 3.02.374.596 I slot print_timing: id 0 | task 20552 | prompt eval time = 112.30 ms / 321 tokens ( 0.35 ms per token, 2858.39 tokens per second) 3.02.374.601 I slot print_timing: id 0 | task 20552 | eval time = 4166.76 ms / 612 tokens ( 6.82 ms per token, 146.64 tokens per second) 3.02.374.603 I slot print_timing: id 0 | task 20552 | total time = 4279.06 ms / 933 tokens 3.02.374.603 I slot print_timing: id 0 | task 20552 | graphs reused = 20106 3.02.374.604 I slot print_timing: id 0 | task 20552 | graph reallocs = 0 / 0 (same size) / (changed size) 3.02.374.632 I slot release: id 0 | task 20552 | stop processing: n_tokens = 964, truncated = 0 3.02.395.871 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 964, t_last = 182281668 3.02.395.934 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.482 MiB) 3.02.471.025 I slot launch_slot_: id 0 | task 21167 | processing task, is_child = 0 3.04.376.880 I slot print_timing: id 0 | task 21167 | prompt eval time = 117.36 ms / 322 tokens ( 0.36 ms per token, 2743.60 tokens per second) 3.04.376.886 I slot print_timing: id 0 | task 21167 | eval time = 1788.47 ms / 263 tokens ( 6.83 ms per token, 146.49 tokens per second) 3.04.376.887 I slot print_timing: id 0 | task 21167 | total time = 1905.84 ms / 585 tokens 3.04.376.887 I slot print_timing: id 0 | task 21167 | graphs reused = 20366 3.04.376.888 I slot print_timing: id 0 | task 21167 | graph reallocs = 0 / 0 (same size) / (changed size) 3.04.376.917 I slot release: id 0 | task 21167 | stop processing: n_tokens = 616, truncated = 0 3.04.399.887 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 616, t_last = 184283953 3.04.399.940 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.171 MiB) 3.04.471.221 I slot launch_slot_: id 0 | task 21433 | processing task, is_child = 0 3.04.898.124 I slot print_timing: id 0 | task 21433 | prompt eval time = 115.79 ms / 337 tokens ( 0.34 ms per token, 2910.52 tokens per second) 3.04.898.129 I slot print_timing: id 0 | task 21433 | eval time = 311.10 ms / 46 tokens ( 6.91 ms per token, 144.65 tokens per second) 3.04.898.130 I slot print_timing: id 0 | task 21433 | total time = 426.88 ms / 383 tokens 3.04.898.131 I slot print_timing: id 0 | task 21433 | graphs reused = 20410 3.04.898.132 I slot print_timing: id 0 | task 21433 | graph reallocs = 0 / 0 (same size) / (changed size) 3.04.898.164 I slot release: id 0 | task 21433 | stop processing: n_tokens = 414, truncated = 0 3.04.916.655 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 184805200 3.04.916.699 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 312.574 MiB) 3.04.987.547 I slot launch_slot_: id 0 | task 21482 | processing task, is_child = 0 3.05.416.780 I slot print_timing: id 0 | task 21482 | prompt eval time = 112.49 ms / 325 tokens ( 0.35 ms per token, 2889.07 tokens per second) 3.05.416.787 I slot print_timing: id 0 | task 21482 | eval time = 316.71 ms / 47 tokens ( 6.89 ms per token, 145.24 tokens per second) 3.05.416.788 I slot print_timing: id 0 | task 21482 | total time = 429.21 ms / 372 tokens 3.05.416.790 I slot print_timing: id 0 | task 21482 | graphs reused = 20455 3.05.416.791 I slot print_timing: id 0 | task 21482 | graph reallocs = 0 / 0 (same size) / (changed size) 3.05.416.831 I slot release: id 0 | task 21482 | stop processing: n_tokens = 403, truncated = 0 3.05.420.654 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 403, t_last = 185323867 3.05.420.697 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.264 MiB) 3.05.510.682 I slot launch_slot_: id 0 | task 21532 | processing task, is_child = 0 3.06.050.155 I slot print_timing: id 0 | task 21532 | prompt eval time = 121.27 ms / 331 tokens ( 0.37 ms per token, 2729.49 tokens per second) 3.06.050.161 I slot print_timing: id 0 | task 21532 | eval time = 418.19 ms / 62 tokens ( 6.86 ms per token, 145.87 tokens per second) 3.06.050.162 I slot print_timing: id 0 | task 21532 | total time = 539.45 ms / 393 tokens 3.06.050.163 I slot print_timing: id 0 | task 21532 | graphs reused = 20515 3.06.050.164 I slot print_timing: id 0 | task 21532 | graph reallocs = 0 / 0 (same size) / (changed size) 3.06.050.192 I slot release: id 0 | task 21532 | stop processing: n_tokens = 424, truncated = 0 3.06.078.595 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 185957227 3.06.078.632 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.858 MiB) 3.06.147.462 I slot launch_slot_: id 0 | task 21597 | processing task, is_child = 0 3.07.111.394 I slot print_timing: id 0 | task 21597 | prompt eval time = 112.25 ms / 336 tokens ( 0.33 ms per token, 2993.19 tokens per second) 3.07.111.400 I slot print_timing: id 0 | task 21597 | eval time = 851.66 ms / 126 tokens ( 6.81 ms per token, 146.77 tokens per second) 3.07.111.401 I slot print_timing: id 0 | task 21597 | total time = 963.91 ms / 462 tokens 3.07.111.402 I slot print_timing: id 0 | task 21597 | graphs reused = 20639 3.07.111.403 I slot print_timing: id 0 | task 21597 | graph reallocs = 0 / 0 (same size) / (changed size) 3.07.111.431 I slot release: id 0 | task 21597 | stop processing: n_tokens = 493, truncated = 0 3.07.136.254 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 493, t_last = 187018467 3.07.136.301 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.484 MiB) 3.07.206.308 I slot launch_slot_: id 0 | task 21726 | processing task, is_child = 0 3.07.446.177 I slot print_timing: id 0 | task 21726 | prompt eval time = 113.54 ms / 349 tokens ( 0.33 ms per token, 3073.89 tokens per second) 3.07.446.183 I slot print_timing: id 0 | task 21726 | eval time = 126.31 ms / 19 tokens ( 7.02 ms per token, 142.50 tokens per second) 3.07.446.184 I slot print_timing: id 0 | task 21726 | total time = 239.85 ms / 368 tokens 3.07.446.185 I slot print_timing: id 0 | task 21726 | graphs reused = 20656 3.07.446.186 I slot print_timing: id 0 | task 21726 | graph reallocs = 0 / 0 (same size) / (changed size) 3.07.446.214 I slot release: id 0 | task 21726 | stop processing: n_tokens = 399, truncated = 0 3.07.474.667 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 399, t_last = 187353249 3.07.474.714 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 313.106 MiB) 3.07.561.283 I slot launch_slot_: id 0 | task 21748 | processing task, is_child = 0 3.10.678.521 I slot print_timing: id 0 | task 21748 | n_gen = 441, tg = 146.39 t/s, tg_3s = 146.72 t/s 3.13.684.275 I slot print_timing: id 0 | task 21748 | n_gen = 881, tg = 146.39 t/s, tg_3s = 146.39 t/s 3.14.289.615 I slot print_timing: id 0 | task 21748 | prompt eval time = 111.56 ms / 336 tokens ( 0.33 ms per token, 3011.94 tokens per second) 3.14.289.621 I slot print_timing: id 0 | task 21748 | eval time = 6616.76 ms / 969 tokens ( 6.84 ms per token, 146.30 tokens per second) 3.14.289.622 I slot print_timing: id 0 | task 21748 | total time = 6728.31 ms / 1305 tokens 3.14.289.622 I slot print_timing: id 0 | task 21748 | graphs reused = 21619 3.14.289.623 I slot print_timing: id 0 | task 21748 | graph reallocs = 0 / 0 (same size) / (changed size) 3.14.289.653 I slot release: id 0 | task 21748 | stop processing: n_tokens = 1336, truncated = 0 3.14.313.666 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1336, t_last = 194196689 3.14.313.756 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.640 MiB) 3.14.389.202 I slot launch_slot_: id 0 | task 22720 | processing task, is_child = 0 3.17.504.458 I slot print_timing: id 0 | task 22720 | n_gen = 441, tg = 146.60 t/s, tg_3s = 146.93 t/s 3.17.681.086 I slot print_timing: id 0 | task 22720 | prompt eval time = 113.87 ms / 349 tokens ( 0.33 ms per token, 3064.87 tokens per second) 3.17.681.092 I slot print_timing: id 0 | task 22720 | eval time = 3178.00 ms / 467 tokens ( 6.82 ms per token, 146.63 tokens per second) 3.17.681.093 I slot print_timing: id 0 | task 22720 | total time = 3291.87 ms / 816 tokens 3.17.681.093 I slot print_timing: id 0 | task 22720 | graphs reused = 22082 3.17.681.094 I slot print_timing: id 0 | task 22720 | graph reallocs = 0 / 0 (same size) / (changed size) 3.17.681.123 I slot release: id 0 | task 22720 | stop processing: n_tokens = 847, truncated = 0 3.17.708.937 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 847, t_last = 197588158 3.17.708.998 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.122 MiB) 3.17.782.291 I slot launch_slot_: id 0 | task 23190 | processing task, is_child = 0 3.18.298.650 I slot print_timing: id 0 | task 23190 | prompt eval time = 118.78 ms / 349 tokens ( 0.34 ms per token, 2938.33 tokens per second) 3.18.298.656 I slot print_timing: id 0 | task 23190 | eval time = 397.57 ms / 59 tokens ( 6.85 ms per token, 145.89 tokens per second) 3.18.298.657 I slot print_timing: id 0 | task 23190 | total time = 516.34 ms / 408 tokens 3.18.298.658 I slot print_timing: id 0 | task 23190 | graphs reused = 22139 3.18.298.659 I slot print_timing: id 0 | task 23190 | graph reallocs = 0 / 0 (same size) / (changed size) 3.18.298.688 I slot release: id 0 | task 23190 | stop processing: n_tokens = 439, truncated = 0 3.18.312.358 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 439, t_last = 198205724 3.18.312.402 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 313.888 MiB) 3.18.394.275 I slot launch_slot_: id 0 | task 23252 | processing task, is_child = 0 3.18.790.019 I slot print_timing: id 0 | task 23252 | prompt eval time = 113.94 ms / 385 tokens ( 0.30 ms per token, 3379.03 tokens per second) 3.18.790.024 I slot print_timing: id 0 | task 23252 | eval time = 281.79 ms / 42 tokens ( 6.87 ms per token, 145.50 tokens per second) 3.18.790.026 I slot print_timing: id 0 | task 23252 | total time = 395.72 ms / 427 tokens 3.18.790.026 I slot print_timing: id 0 | task 23252 | graphs reused = 22179 3.18.790.027 I slot print_timing: id 0 | task 23252 | graph reallocs = 0 / 0 (same size) / (changed size) 3.18.790.055 I slot release: id 0 | task 23252 | stop processing: n_tokens = 458, truncated = 0 3.18.814.339 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 198697091 3.18.814.377 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.142 MiB) 3.18.879.843 I slot launch_slot_: id 0 | task 23297 | processing task, is_child = 0 3.19.371.408 I slot print_timing: id 0 | task 23297 | prompt eval time = 106.76 ms / 328 tokens ( 0.33 ms per token, 3072.20 tokens per second) 3.19.371.414 I slot print_timing: id 0 | task 23297 | eval time = 384.78 ms / 57 tokens ( 6.87 ms per token, 145.54 tokens per second) 3.19.371.415 I slot print_timing: id 0 | task 23297 | total time = 491.55 ms / 385 tokens 3.19.371.416 I slot print_timing: id 0 | task 23297 | graphs reused = 22234 3.19.371.417 I slot print_timing: id 0 | task 23297 | graph reallocs = 0 / 0 (same size) / (changed size) 3.19.371.443 I slot release: id 0 | task 23297 | stop processing: n_tokens = 416, truncated = 0