$ C:\quantdiff\llama.cpp\bin\llama-server.exe -m C:\quantdiff\hf-cache\models--bartowski--Qwen_Qwen3.5-9B-GGUF\snapshots\182be2fd6c7bc44887d88a91cb03ff009cc9f549\Qwen_Qwen3.5-9B-IQ3_M.gguf --host 127.0.0.1 --port 8089 -c 4096 -np 1 -ngl 999 -fa on --jinja --seed 1234 --no-webui -a quant 0.00.094.611 I srv llama_server: initializing ... 0.00.094.617 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.094.725 I srv init_listene: The UI is disabled 0.00.094.727 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.094.806 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) 0.00.109.123 I srv load_model: loading model 'C:\quantdiff\hf-cache\models--bartowski--Qwen_Qwen3.5-9B-GGUF\snapshots\182be2fd6c7bc44887d88a91cb03ff009cc9f549\Qwen_Qwen3.5-9B-IQ3_M.gguf' 0.00.948.645 W model has unused tensor blk.32.attn_norm.weight (size = 16384 bytes) -- ignoring 0.00.948.660 W model has unused tensor blk.32.post_attention_norm.weight (size = 16384 bytes) -- ignoring 0.00.948.686 W model has unused tensor blk.32.attn_q.weight (size = 35651584 bytes) -- ignoring 0.00.948.695 W model has unused tensor blk.32.attn_k.weight (size = 4456448 bytes) -- ignoring 0.00.948.704 W model has unused tensor blk.32.attn_v.weight (size = 4456448 bytes) -- ignoring 0.00.948.738 W model has unused tensor blk.32.attn_output.weight (size = 17825792 bytes) -- ignoring 0.00.948.748 W model has unused tensor blk.32.attn_q_norm.weight (size = 1024 bytes) -- ignoring 0.00.948.757 W model has unused tensor blk.32.attn_k_norm.weight (size = 1024 bytes) -- ignoring 0.00.948.768 W model has unused tensor blk.32.ffn_gate.weight (size = 53477376 bytes) -- ignoring 0.00.948.777 W model has unused tensor blk.32.ffn_down.weight (size = 53477376 bytes) -- ignoring 0.00.948.786 W model has unused tensor blk.32.ffn_up.weight (size = 53477376 bytes) -- ignoring 0.00.948.797 W model has unused tensor blk.32.nextn.eh_proj.weight (size = 35651584 bytes) -- ignoring 0.00.948.807 W model has unused tensor blk.32.nextn.enorm.weight (size = 16384 bytes) -- ignoring 0.00.948.817 W model has unused tensor blk.32.nextn.hnorm.weight (size = 16384 bytes) -- ignoring 0.00.948.845 W model has unused tensor blk.32.nextn.shared_head_norm.weight (size = 16384 bytes) -- ignoring 0.02.406.535 I cmn init: llama threadpool init, n_threads = 8 0.02.493.856 I srv load_model: initializing, n_slots = 1, n_ctx_slot = 4096, kv_unified = 'false' 0.02.498.442 I srv llama_server: model loaded 0.02.498.448 I srv llama_server: listening on http://127.0.0.1:8089 0.02.532.796 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.02.532.968 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.04.294.425 I slot print_timing: id 0 | task 0 | prompt eval time = 222.18 ms / 368 tokens ( 0.60 ms per token, 1656.33 tokens per second) 0.04.294.431 I slot print_timing: id 0 | task 0 | eval time = 1539.26 ms / 168 tokens ( 9.22 ms per token, 108.49 tokens per second) 0.04.294.431 I slot print_timing: id 0 | task 0 | total time = 1761.44 ms / 536 tokens 0.04.294.437 I slot print_timing: id 0 | task 0 | graphs reused = 166 0.04.294.437 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.04.294.468 I slot release: id 0 | task 0 | stop processing: n_tokens = 535, truncated = 0 0.04.308.369 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 535, t_last = 4201821 0.04.334.284 I slot launch_slot_: id 0 | task 171 | processing task, is_child = 0 0.05.639.980 I slot print_timing: id 0 | task 171 | prompt eval time = 122.00 ms / 322 tokens ( 0.38 ms per token, 2639.32 tokens per second) 0.05.639.986 I slot print_timing: id 0 | task 171 | eval time = 1183.68 ms / 130 tokens ( 9.18 ms per token, 108.98 tokens per second) 0.05.639.987 I slot print_timing: id 0 | task 171 | total time = 1305.68 ms / 452 tokens 0.05.639.988 I slot print_timing: id 0 | task 171 | graphs reused = 294 0.05.639.988 I slot print_timing: id 0 | task 171 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.640.015 I slot release: id 0 | task 171 | stop processing: n_tokens = 451, truncated = 0 0.05.662.499 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 451, t_last = 5547367 0.05.689.858 I slot launch_slot_: id 0 | task 304 | processing task, is_child = 0 0.06.192.235 I slot print_timing: id 0 | task 304 | prompt eval time = 122.82 ms / 365 tokens ( 0.34 ms per token, 2971.93 tokens per second) 0.06.192.240 I slot print_timing: id 0 | task 304 | eval time = 379.54 ms / 42 tokens ( 9.26 ms per token, 108.03 tokens per second) 0.06.192.242 I slot print_timing: id 0 | task 304 | total time = 502.36 ms / 407 tokens 0.06.192.243 I slot print_timing: id 0 | task 304 | graphs reused = 334 0.06.192.244 I slot print_timing: id 0 | task 304 | graph reallocs = 0 / 0 (same size) / (changed size) 0.06.192.272 I slot release: id 0 | task 304 | stop processing: n_tokens = 406, truncated = 0 0.06.206.787 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 406, t_last = 6099624 0.06.233.337 I slot launch_slot_: id 0 | task 349 | processing task, is_child = 0 0.06.753.008 I slot print_timing: id 0 | task 349 | prompt eval time = 128.88 ms / 397 tokens ( 0.32 ms per token, 3080.38 tokens per second) 0.06.753.014 I slot print_timing: id 0 | task 349 | eval time = 390.77 ms / 43 tokens ( 9.30 ms per token, 107.48 tokens per second) 0.06.753.015 I slot print_timing: id 0 | task 349 | total time = 519.65 ms / 440 tokens 0.06.753.016 I slot print_timing: id 0 | task 349 | graphs reused = 375 0.06.753.017 I slot print_timing: id 0 | task 349 | graph reallocs = 0 / 0 (same size) / (changed size) 0.06.753.045 I slot release: id 0 | task 349 | stop processing: n_tokens = 439, truncated = 0 0.06.768.244 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 0.06.814.187 I slot launch_slot_: id 0 | task 395 | processing task, is_child = 0 0.08.034.394 I slot print_timing: id 0 | task 395 | prompt eval time = 128.29 ms / 383 tokens ( 0.33 ms per token, 2985.38 tokens per second) 0.08.034.399 I slot print_timing: id 0 | task 395 | eval time = 1091.90 ms / 120 tokens ( 9.18 ms per token, 108.98 tokens per second) 0.08.034.400 I slot print_timing: id 0 | task 395 | total time = 1220.19 ms / 503 tokens 0.08.034.402 I slot print_timing: id 0 | task 395 | graphs reused = 493 0.08.034.403 I slot print_timing: id 0 | task 395 | graph reallocs = 0 / 0 (same size) / (changed size) 0.08.034.431 I slot release: id 0 | task 395 | stop processing: n_tokens = 502, truncated = 0 0.08.059.142 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 502, t_last = 7941783 0.08.086.733 I slot launch_slot_: id 0 | task 518 | processing task, is_child = 0 0.08.713.673 I slot print_timing: id 0 | task 518 | prompt eval time = 125.83 ms / 372 tokens ( 0.34 ms per token, 2956.44 tokens per second) 0.08.713.679 I slot print_timing: id 0 | task 518 | eval time = 501.10 ms / 55 tokens ( 9.28 ms per token, 107.76 tokens per second) 0.08.713.680 I slot print_timing: id 0 | task 518 | total time = 626.92 ms / 427 tokens 0.08.713.681 I slot print_timing: id 0 | task 518 | graphs reused = 546 0.08.713.682 I slot print_timing: id 0 | task 518 | graph reallocs = 0 / 0 (same size) / (changed size) 0.08.713.709 I slot release: id 0 | task 518 | stop processing: n_tokens = 426, truncated = 0 0.08.742.594 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 8621061 0.08.768.446 I slot launch_slot_: id 0 | task 576 | processing task, is_child = 0 0.09.410.734 I slot print_timing: id 0 | task 576 | prompt eval time = 143.21 ms / 422 tokens ( 0.34 ms per token, 2946.82 tokens per second) 0.09.410.739 I slot print_timing: id 0 | task 576 | eval time = 499.06 ms / 55 tokens ( 9.24 ms per token, 108.20 tokens per second) 0.09.410.741 I slot print_timing: id 0 | task 576 | total time = 642.27 ms / 477 tokens 0.09.410.742 I slot print_timing: id 0 | task 576 | graphs reused = 599 0.09.410.742 I slot print_timing: id 0 | task 576 | graph reallocs = 0 / 0 (same size) / (changed size) 0.09.410.770 I slot release: id 0 | task 576 | stop processing: n_tokens = 476, truncated = 0 0.09.425.696 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 476, t_last = 9318123 0.09.457.404 I slot launch_slot_: id 0 | task 634 | processing task, is_child = 0 0.10.262.835 I slot print_timing: id 0 | task 634 | prompt eval time = 149.05 ms / 470 tokens ( 0.32 ms per token, 3153.28 tokens per second) 0.10.262.841 I slot print_timing: id 0 | task 634 | eval time = 656.36 ms / 72 tokens ( 9.24 ms per token, 108.17 tokens per second) 0.10.262.842 I slot print_timing: id 0 | task 634 | total time = 805.41 ms / 542 tokens 0.10.262.843 I slot print_timing: id 0 | task 634 | graphs reused = 668 0.10.262.843 I slot print_timing: id 0 | task 634 | graph reallocs = 0 / 0 (same size) / (changed size) 0.10.262.875 I slot release: id 0 | task 634 | stop processing: n_tokens = 541, truncated = 0 0.10.283.721 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 541, t_last = 10170227 0.10.311.098 I slot launch_slot_: id 0 | task 709 | processing task, is_child = 0 0.10.857.288 I slot print_timing: id 0 | task 709 | prompt eval time = 122.60 ms / 345 tokens ( 0.36 ms per token, 2813.98 tokens per second) 0.10.857.294 I slot print_timing: id 0 | task 709 | eval time = 423.57 ms / 47 tokens ( 9.21 ms per token, 108.60 tokens per second) 0.10.857.295 I slot print_timing: id 0 | task 709 | total time = 546.17 ms / 392 tokens 0.10.857.296 I slot print_timing: id 0 | task 709 | graphs reused = 713 0.10.857.297 I slot print_timing: id 0 | task 709 | graph reallocs = 0 / 0 (same size) / (changed size) 0.10.857.325 I slot release: id 0 | task 709 | stop processing: n_tokens = 391, truncated = 0 0.10.878.471 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 391, t_last = 10764678 0.10.904.866 I slot launch_slot_: id 0 | task 759 | processing task, is_child = 0 0.12.039.572 I slot print_timing: id 0 | task 759 | prompt eval time = 126.03 ms / 364 tokens ( 0.35 ms per token, 2888.20 tokens per second) 0.12.039.578 I slot print_timing: id 0 | task 759 | eval time = 1008.65 ms / 110 tokens ( 9.25 ms per token, 108.06 tokens per second) 0.12.039.580 I slot print_timing: id 0 | task 759 | total time = 1134.68 ms / 474 tokens 0.12.039.581 I slot print_timing: id 0 | task 759 | graphs reused = 821 0.12.039.581 I slot print_timing: id 0 | task 759 | graph reallocs = 0 / 0 (same size) / (changed size) 0.12.039.614 I slot release: id 0 | task 759 | stop processing: n_tokens = 473, truncated = 0 0.12.058.109 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 473, t_last = 11946966 0.12.084.826 I slot launch_slot_: id 0 | task 872 | processing task, is_child = 0 0.12.805.343 I slot print_timing: id 0 | task 872 | prompt eval time = 127.43 ms / 376 tokens ( 0.34 ms per token, 2950.57 tokens per second) 0.12.805.348 I slot print_timing: id 0 | task 872 | eval time = 593.06 ms / 62 tokens ( 9.72 ms per token, 102.86 tokens per second) 0.12.805.349 I slot print_timing: id 0 | task 872 | total time = 720.50 ms / 438 tokens 0.12.805.350 I slot print_timing: id 0 | task 872 | graphs reused = 881 0.12.805.351 I slot print_timing: id 0 | task 872 | graph reallocs = 0 / 0 (same size) / (changed size) 0.12.805.378 I slot release: id 0 | task 872 | stop processing: n_tokens = 437, truncated = 0 0.12.820.354 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 12712731 0.12.845.944 I slot launch_slot_: id 0 | task 937 | processing task, is_child = 0 0.13.400.066 I slot print_timing: id 0 | task 937 | prompt eval time = 129.63 ms / 412 tokens ( 0.31 ms per token, 3178.18 tokens per second) 0.13.400.071 I slot print_timing: id 0 | task 937 | eval time = 424.47 ms / 47 tokens ( 9.23 ms per token, 108.37 tokens per second) 0.13.400.072 I slot print_timing: id 0 | task 937 | total time = 554.10 ms / 459 tokens 0.13.400.073 I slot print_timing: id 0 | task 937 | graphs reused = 926 0.13.400.074 I slot print_timing: id 0 | task 937 | graph reallocs = 0 / 0 (same size) / (changed size) 0.13.400.105 I slot release: id 0 | task 937 | stop processing: n_tokens = 458, truncated = 0 0.13.426.427 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 13307458 0.13.461.344 I slot launch_slot_: id 0 | task 987 | processing task, is_child = 0 0.14.145.278 I slot print_timing: id 0 | task 987 | prompt eval time = 123.17 ms / 376 tokens ( 0.33 ms per token, 3052.62 tokens per second) 0.14.145.284 I slot print_timing: id 0 | task 987 | eval time = 560.74 ms / 62 tokens ( 9.19 ms per token, 108.78 tokens per second) 0.14.145.285 I slot print_timing: id 0 | task 987 | total time = 683.91 ms / 438 tokens 0.14.145.286 I slot print_timing: id 0 | task 987 | graphs reused = 986 0.14.145.287 I slot print_timing: id 0 | task 987 | graph reallocs = 0 / 0 (same size) / (changed size) 0.14.145.314 I slot release: id 0 | task 987 | stop processing: n_tokens = 437, truncated = 0 0.14.172.290 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 14052667 0.14.198.207 I slot launch_slot_: id 0 | task 1052 | processing task, is_child = 0 0.14.794.657 I slot print_timing: id 0 | task 1052 | prompt eval time = 127.41 ms / 378 tokens ( 0.34 ms per token, 2966.75 tokens per second) 0.14.794.663 I slot print_timing: id 0 | task 1052 | eval time = 469.02 ms / 52 tokens ( 9.20 ms per token, 108.74 tokens per second) 0.14.794.665 I slot print_timing: id 0 | task 1052 | total time = 596.43 ms / 430 tokens 0.14.794.666 I slot print_timing: id 0 | task 1052 | graphs reused = 1036 0.14.794.667 I slot print_timing: id 0 | task 1052 | graph reallocs = 0 / 0 (same size) / (changed size) 0.14.794.695 I slot release: id 0 | task 1052 | stop processing: n_tokens = 429, truncated = 0 0.14.812.943 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 429, t_last = 14702048 0.14.838.929 I slot launch_slot_: id 0 | task 1107 | processing task, is_child = 0 0.15.522.015 I slot print_timing: id 0 | task 1107 | prompt eval time = 128.59 ms / 367 tokens ( 0.35 ms per token, 2854.08 tokens per second) 0.15.522.021 I slot print_timing: id 0 | task 1107 | eval time = 554.48 ms / 58 tokens ( 9.73 ms per token, 102.80 tokens per second) 0.15.522.022 I slot print_timing: id 0 | task 1107 | total time = 683.07 ms / 425 tokens 0.15.522.023 I slot print_timing: id 0 | task 1107 | graphs reused = 1092 0.15.522.024 I slot print_timing: id 0 | task 1107 | graph reallocs = 0 / 0 (same size) / (changed size) 0.15.522.052 I slot release: id 0 | task 1107 | stop processing: n_tokens = 424, truncated = 0 0.15.548.918 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 15429404 0.15.575.031 I slot launch_slot_: id 0 | task 1168 | processing task, is_child = 0 0.16.159.243 I slot print_timing: id 0 | task 1168 | prompt eval time = 123.38 ms / 347 tokens ( 0.36 ms per token, 2812.54 tokens per second) 0.16.159.249 I slot print_timing: id 0 | task 1168 | eval time = 460.81 ms / 51 tokens ( 9.22 ms per token, 108.50 tokens per second) 0.16.159.250 I slot print_timing: id 0 | task 1168 | total time = 584.19 ms / 398 tokens 0.16.159.250 I slot print_timing: id 0 | task 1168 | graphs reused = 1141 0.16.159.251 I slot print_timing: id 0 | task 1168 | graph reallocs = 0 / 0 (same size) / (changed size) 0.16.159.278 I slot release: id 0 | task 1168 | stop processing: n_tokens = 397, truncated = 0 0.16.181.712 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 397, t_last = 16066630 0.16.207.186 I slot launch_slot_: id 0 | task 1222 | processing task, is_child = 0 0.16.976.002 I slot print_timing: id 0 | task 1222 | prompt eval time = 123.65 ms / 369 tokens ( 0.34 ms per token, 2984.28 tokens per second) 0.16.976.010 I slot print_timing: id 0 | task 1222 | eval time = 645.15 ms / 71 tokens ( 9.22 ms per token, 108.50 tokens per second) 0.16.976.011 I slot print_timing: id 0 | task 1222 | total time = 768.80 ms / 440 tokens 0.16.976.012 I slot print_timing: id 0 | task 1222 | graphs reused = 1210 0.16.976.013 I slot print_timing: id 0 | task 1222 | graph reallocs = 0 / 0 (same size) / (changed size) 0.16.976.045 I slot release: id 0 | task 1222 | stop processing: n_tokens = 439, truncated = 0 0.16.992.957 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 439, t_last = 16883398 0.17.018.325 I slot launch_slot_: id 0 | task 1296 | processing task, is_child = 0 0.17.514.175 I slot print_timing: id 0 | task 1296 | prompt eval time = 125.59 ms / 352 tokens ( 0.36 ms per token, 2802.68 tokens per second) 0.17.514.180 I slot print_timing: id 0 | task 1296 | eval time = 370.23 ms / 41 tokens ( 9.26 ms per token, 108.04 tokens per second) 0.17.514.181 I slot print_timing: id 0 | task 1296 | total time = 495.83 ms / 393 tokens 0.17.514.182 I slot print_timing: id 0 | task 1296 | graphs reused = 1249 0.17.514.183 I slot print_timing: id 0 | task 1296 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.514.210 I slot release: id 0 | task 1296 | stop processing: n_tokens = 392, truncated = 0 0.17.539.449 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 392, t_last = 17421563 0.17.564.838 I slot launch_slot_: id 0 | task 1340 | processing task, is_child = 0 0.18.549.918 I slot print_timing: id 0 | task 1340 | prompt eval time = 123.79 ms / 349 tokens ( 0.35 ms per token, 2819.38 tokens per second) 0.18.549.924 I slot print_timing: id 0 | task 1340 | eval time = 861.27 ms / 95 tokens ( 9.16 ms per token, 109.14 tokens per second) 0.18.549.925 I slot print_timing: id 0 | task 1340 | total time = 985.06 ms / 444 tokens 0.18.549.926 I slot print_timing: id 0 | task 1340 | graphs reused = 1342 0.18.549.927 I slot print_timing: id 0 | task 1340 | graph reallocs = 0 / 0 (same size) / (changed size) 0.18.549.953 I slot release: id 0 | task 1340 | stop processing: n_tokens = 443, truncated = 0 0.18.567.758 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 443, t_last = 18457305 0.18.594.192 I slot launch_slot_: id 0 | task 1438 | processing task, is_child = 0 0.19.324.575 I slot print_timing: id 0 | task 1438 | prompt eval time = 129.58 ms / 384 tokens ( 0.34 ms per token, 2963.47 tokens per second) 0.19.324.581 I slot print_timing: id 0 | task 1438 | eval time = 600.78 ms / 63 tokens ( 9.69 ms per token, 103.20 tokens per second) 0.19.324.582 I slot print_timing: id 0 | task 1438 | total time = 730.36 ms / 447 tokens 0.19.324.583 I slot print_timing: id 0 | task 1438 | graphs reused = 1403 0.19.324.583 I slot print_timing: id 0 | task 1438 | graph reallocs = 0 / 0 (same size) / (changed size) 0.19.324.614 I slot release: id 0 | task 1438 | stop processing: n_tokens = 446, truncated = 0 0.19.328.484 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 446, t_last = 19231967 0.19.358.912 I slot launch_slot_: id 0 | task 1504 | processing task, is_child = 0 0.19.971.127 I slot print_timing: id 0 | task 1504 | prompt eval time = 124.70 ms / 356 tokens ( 0.35 ms per token, 2854.94 tokens per second) 0.19.971.133 I slot print_timing: id 0 | task 1504 | eval time = 487.50 ms / 54 tokens ( 9.20 ms per token, 108.72 tokens per second) 0.19.971.134 I slot print_timing: id 0 | task 1504 | total time = 612.20 ms / 410 tokens 0.19.971.135 I slot print_timing: id 0 | task 1504 | graphs reused = 1455 0.19.971.136 I slot print_timing: id 0 | task 1504 | graph reallocs = 0 / 0 (same size) / (changed size) 0.19.971.164 I slot release: id 0 | task 1504 | stop processing: n_tokens = 409, truncated = 0 0.19.975.052 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 19878517 0.20.001.043 I slot launch_slot_: id 0 | task 1561 | processing task, is_child = 0 0.20.764.300 I slot print_timing: id 0 | task 1561 | prompt eval time = 130.26 ms / 410 tokens ( 0.32 ms per token, 3147.43 tokens per second) 0.20.764.306 I slot print_timing: id 0 | task 1561 | eval time = 632.97 ms / 70 tokens ( 9.17 ms per token, 109.01 tokens per second) 0.20.764.308 I slot print_timing: id 0 | task 1561 | total time = 763.24 ms / 480 tokens 0.20.764.310 I slot print_timing: id 0 | task 1561 | graphs reused = 1523 0.20.764.311 I slot print_timing: id 0 | task 1561 | graph reallocs = 0 / 0 (same size) / (changed size) 0.20.764.339 I slot release: id 0 | task 1561 | stop processing: n_tokens = 479, truncated = 0 0.20.781.712 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 479, t_last = 20671692 0.20.808.259 I slot launch_slot_: id 0 | task 1634 | processing task, is_child = 0 0.21.464.909 I slot print_timing: id 0 | task 1634 | prompt eval time = 128.83 ms / 385 tokens ( 0.33 ms per token, 2988.46 tokens per second) 0.21.464.915 I slot print_timing: id 0 | task 1634 | eval time = 527.80 ms / 58 tokens ( 9.26 ms per token, 108.00 tokens per second) 0.21.464.917 I slot print_timing: id 0 | task 1634 | total time = 656.63 ms / 443 tokens 0.21.464.918 I slot print_timing: id 0 | task 1634 | graphs reused = 1579 0.21.464.918 I slot print_timing: id 0 | task 1634 | graph reallocs = 0 / 0 (same size) / (changed size) 0.21.464.949 I slot release: id 0 | task 1634 | stop processing: n_tokens = 442, truncated = 0 0.21.468.757 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 442, t_last = 21372301 0.21.494.651 I slot launch_slot_: id 0 | task 1695 | processing task, is_child = 0 0.22.267.892 I slot print_timing: id 0 | task 1695 | prompt eval time = 130.28 ms / 395 tokens ( 0.33 ms per token, 3031.88 tokens per second) 0.22.267.898 I slot print_timing: id 0 | task 1695 | eval time = 642.94 ms / 71 tokens ( 9.18 ms per token, 108.88 tokens per second) 0.22.267.899 I slot print_timing: id 0 | task 1695 | total time = 773.22 ms / 466 tokens 0.22.267.899 I slot print_timing: id 0 | task 1695 | graphs reused = 1648 0.22.267.900 I slot print_timing: id 0 | task 1695 | graph reallocs = 0 / 0 (same size) / (changed size) 0.22.267.927 I slot release: id 0 | task 1695 | stop processing: n_tokens = 465, truncated = 0 0.22.293.344 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 465, t_last = 22175280 0.22.319.535 I slot launch_slot_: id 0 | task 1769 | processing task, is_child = 0 0.23.013.363 I slot print_timing: id 0 | task 1769 | prompt eval time = 132.89 ms / 430 tokens ( 0.31 ms per token, 3235.76 tokens per second) 0.23.013.369 I slot print_timing: id 0 | task 1769 | eval time = 560.92 ms / 62 tokens ( 9.20 ms per token, 108.75 tokens per second) 0.23.013.370 I slot print_timing: id 0 | task 1769 | total time = 693.81 ms / 492 tokens 0.23.013.371 I slot print_timing: id 0 | task 1769 | graphs reused = 1708 0.23.013.372 I slot print_timing: id 0 | task 1769 | graph reallocs = 0 / 0 (same size) / (changed size) 0.23.013.402 I slot release: id 0 | task 1769 | stop processing: n_tokens = 491, truncated = 0 0.23.041.797 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 491, t_last = 22920755 0.23.069.582 I slot launch_slot_: id 0 | task 1834 | processing task, is_child = 0 0.23.759.590 I slot print_timing: id 0 | task 1834 | prompt eval time = 130.22 ms / 392 tokens ( 0.33 ms per token, 3010.34 tokens per second) 0.23.759.596 I slot print_timing: id 0 | task 1834 | eval time = 559.77 ms / 62 tokens ( 9.18 ms per token, 108.97 tokens per second) 0.23.759.597 I slot print_timing: id 0 | task 1834 | total time = 689.99 ms / 454 tokens 0.23.759.598 I slot print_timing: id 0 | task 1834 | graphs reused = 1768 0.23.759.598 I slot print_timing: id 0 | task 1834 | graph reallocs = 0 / 0 (same size) / (changed size) 0.23.759.626 I slot release: id 0 | task 1834 | stop processing: n_tokens = 453, truncated = 0 0.23.783.802 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 453, t_last = 23666979 0.23.809.683 I slot launch_slot_: id 0 | task 1899 | processing task, is_child = 0 0.24.374.251 I slot print_timing: id 0 | task 1899 | prompt eval time = 122.56 ms / 350 tokens ( 0.35 ms per token, 2855.77 tokens per second) 0.24.374.257 I slot print_timing: id 0 | task 1899 | eval time = 441.99 ms / 49 tokens ( 9.21 ms per token, 108.60 tokens per second) 0.24.374.258 I slot print_timing: id 0 | task 1899 | total time = 564.55 ms / 399 tokens 0.24.374.259 I slot print_timing: id 0 | task 1899 | graphs reused = 1815 0.24.374.259 I slot print_timing: id 0 | task 1899 | graph reallocs = 0 / 0 (same size) / (changed size) 0.24.374.288 I slot release: id 0 | task 1899 | stop processing: n_tokens = 398, truncated = 0 0.24.392.635 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 398, t_last = 24281640 0.24.418.977 I slot launch_slot_: id 0 | task 1951 | processing task, is_child = 0 0.25.102.770 I slot print_timing: id 0 | task 1951 | prompt eval time = 130.77 ms / 380 tokens ( 0.34 ms per token, 2905.89 tokens per second) 0.25.102.776 I slot print_timing: id 0 | task 1951 | eval time = 553.00 ms / 61 tokens ( 9.22 ms per token, 108.50 tokens per second) 0.25.102.777 I slot print_timing: id 0 | task 1951 | total time = 683.77 ms / 441 tokens 0.25.102.778 I slot print_timing: id 0 | task 1951 | graphs reused = 1874 0.25.102.779 I slot print_timing: id 0 | task 1951 | graph reallocs = 0 / 0 (same size) / (changed size) 0.25.102.807 I slot release: id 0 | task 1951 | stop processing: n_tokens = 440, truncated = 0 0.25.125.310 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 440, t_last = 25010159 0.25.162.441 I slot launch_slot_: id 0 | task 2015 | processing task, is_child = 0 0.26.059.897 I slot print_timing: id 0 | task 2015 | prompt eval time = 134.69 ms / 410 tokens ( 0.33 ms per token, 3043.94 tokens per second) 0.26.059.902 I slot print_timing: id 0 | task 2015 | eval time = 762.74 ms / 80 tokens ( 9.65 ms per token, 103.57 tokens per second) 0.26.059.903 I slot print_timing: id 0 | task 2015 | total time = 897.44 ms / 490 tokens 0.26.059.904 I slot print_timing: id 0 | task 2015 | graphs reused = 1952 0.26.059.905 I slot print_timing: id 0 | task 2015 | graph reallocs = 0 / 0 (same size) / (changed size) 0.26.059.935 I slot release: id 0 | task 2015 | stop processing: n_tokens = 489, truncated = 0 0.26.078.763 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 489, t_last = 25967287 0.26.104.922 I slot launch_slot_: id 0 | task 2098 | processing task, is_child = 0 0.26.848.454 I slot print_timing: id 0 | task 2098 | prompt eval time = 128.36 ms / 387 tokens ( 0.33 ms per token, 3014.86 tokens per second) 0.26.848.460 I slot print_timing: id 0 | task 2098 | eval time = 615.15 ms / 68 tokens ( 9.18 ms per token, 108.92 tokens per second) 0.26.848.461 I slot print_timing: id 0 | task 2098 | total time = 743.51 ms / 455 tokens 0.26.848.462 I slot print_timing: id 0 | task 2098 | graphs reused = 2018 0.26.848.463 I slot print_timing: id 0 | task 2098 | graph reallocs = 0 / 0 (same size) / (changed size) 0.26.848.493 I slot release: id 0 | task 2098 | stop processing: n_tokens = 454, truncated = 0 0.26.874.068 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 454, t_last = 26755846 0.26.900.188 I slot launch_slot_: id 0 | task 2169 | processing task, is_child = 0 0.27.556.475 I slot print_timing: id 0 | task 2169 | prompt eval time = 122.79 ms / 358 tokens ( 0.34 ms per token, 2915.57 tokens per second) 0.27.556.481 I slot print_timing: id 0 | task 2169 | eval time = 533.48 ms / 59 tokens ( 9.20 ms per token, 108.72 tokens per second) 0.27.556.483 I slot print_timing: id 0 | task 2169 | total time = 656.27 ms / 417 tokens 0.27.556.483 I slot print_timing: id 0 | task 2169 | graphs reused = 2075 0.27.556.484 I slot print_timing: id 0 | task 2169 | graph reallocs = 0 / 0 (same size) / (changed size) 0.27.556.511 I slot release: id 0 | task 2169 | stop processing: n_tokens = 416, truncated = 0 0.27.574.822 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 27463864 0.27.600.329 I slot launch_slot_: id 0 | task 2231 | processing task, is_child = 0 0.28.260.960 I slot print_timing: id 0 | task 2231 | prompt eval time = 122.29 ms / 359 tokens ( 0.34 ms per token, 2935.67 tokens per second) 0.28.260.966 I slot print_timing: id 0 | task 2231 | eval time = 538.32 ms / 56 tokens ( 9.79 ms per token, 102.17 tokens per second) 0.28.260.967 I slot print_timing: id 0 | task 2231 | total time = 660.61 ms / 415 tokens 0.28.260.968 I slot print_timing: id 0 | task 2231 | graphs reused = 2129 0.28.260.969 I slot print_timing: id 0 | task 2231 | graph reallocs = 0 / 0 (same size) / (changed size) 0.28.260.997 I slot release: id 0 | task 2231 | stop processing: n_tokens = 414, truncated = 0 0.28.277.245 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 28168349 0.28.303.129 I slot launch_slot_: id 0 | task 2290 | processing task, is_child = 0 0.28.984.637 I slot print_timing: id 0 | task 2290 | prompt eval time = 128.72 ms / 387 tokens ( 0.33 ms per token, 3006.64 tokens per second) 0.28.984.643 I slot print_timing: id 0 | task 2290 | eval time = 552.77 ms / 61 tokens ( 9.21 ms per token, 108.54 tokens per second) 0.28.984.644 I slot print_timing: id 0 | task 2290 | total time = 681.48 ms / 448 tokens 0.28.984.645 I slot print_timing: id 0 | task 2290 | graphs reused = 2188 0.28.984.646 I slot print_timing: id 0 | task 2290 | graph reallocs = 0 / 0 (same size) / (changed size) 0.28.984.681 I slot release: id 0 | task 2290 | stop processing: n_tokens = 447, truncated = 0 0.28.988.561 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 28892034 0.29.015.728 I slot launch_slot_: id 0 | task 2354 | processing task, is_child = 0 0.29.729.169 I slot print_timing: id 0 | task 2354 | prompt eval time = 132.43 ms / 410 tokens ( 0.32 ms per token, 3096.07 tokens per second) 0.29.729.175 I slot print_timing: id 0 | task 2354 | eval time = 581.00 ms / 61 tokens ( 9.68 ms per token, 103.27 tokens per second) 0.29.729.176 I slot print_timing: id 0 | task 2354 | total time = 713.42 ms / 471 tokens 0.29.729.176 I slot print_timing: id 0 | task 2354 | graphs reused = 2247 0.29.729.177 I slot print_timing: id 0 | task 2354 | graph reallocs = 0 / 0 (same size) / (changed size) 0.29.729.209 I slot release: id 0 | task 2354 | stop processing: n_tokens = 470, truncated = 0 0.29.753.393 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 29636562 0.29.779.785 I slot launch_slot_: id 0 | task 2418 | processing task, is_child = 0 0.30.354.045 I slot print_timing: id 0 | task 2418 | prompt eval time = 122.09 ms / 351 tokens ( 0.35 ms per token, 2875.02 tokens per second) 0.30.354.051 I slot print_timing: id 0 | task 2418 | eval time = 452.15 ms / 50 tokens ( 9.23 ms per token, 108.37 tokens per second) 0.30.354.052 I slot print_timing: id 0 | task 2418 | total time = 574.24 ms / 401 tokens 0.30.354.053 I slot print_timing: id 0 | task 2418 | graphs reused = 2295 0.30.354.054 I slot print_timing: id 0 | task 2418 | graph reallocs = 0 / 0 (same size) / (changed size) 0.30.354.082 I slot release: id 0 | task 2418 | stop processing: n_tokens = 400, truncated = 0 0.30.371.974 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 30261434 0.30.397.691 I slot launch_slot_: id 0 | task 2471 | processing task, is_child = 0 0.31.034.615 I slot print_timing: id 0 | task 2471 | prompt eval time = 129.69 ms / 393 tokens ( 0.33 ms per token, 3030.19 tokens per second) 0.31.034.621 I slot print_timing: id 0 | task 2471 | eval time = 507.21 ms / 56 tokens ( 9.22 ms per token, 108.44 tokens per second) 0.31.034.622 I slot print_timing: id 0 | task 2471 | total time = 636.90 ms / 449 tokens 0.31.034.623 I slot print_timing: id 0 | task 2471 | graphs reused = 2349 0.31.034.623 I slot print_timing: id 0 | task 2471 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.034.652 I slot release: id 0 | task 2471 | stop processing: n_tokens = 448, truncated = 0 0.31.059.291 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 30942005 0.31.085.615 I slot launch_slot_: id 0 | task 2530 | processing task, is_child = 0 0.31.477.864 I slot print_timing: id 0 | task 2530 | prompt eval time = 123.40 ms / 321 tokens ( 0.38 ms per token, 2601.21 tokens per second) 0.31.477.870 I slot print_timing: id 0 | task 2530 | eval time = 268.82 ms / 30 tokens ( 9.27 ms per token, 107.88 tokens per second) 0.31.477.871 I slot print_timing: id 0 | task 2530 | total time = 392.23 ms / 351 tokens 0.31.477.872 I slot print_timing: id 0 | task 2530 | graphs reused = 2377 0.31.477.873 I slot print_timing: id 0 | task 2530 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.477.899 I slot release: id 0 | task 2530 | stop processing: n_tokens = 350, truncated = 0 0.31.493.755 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 350, t_last = 31385251 0.31.519.632 I slot launch_slot_: id 0 | task 2563 | processing task, is_child = 0 0.32.803.385 I slot print_timing: id 0 | task 2563 | prompt eval time = 121.76 ms / 330 tokens ( 0.37 ms per token, 2710.32 tokens per second) 0.32.803.390 I slot print_timing: id 0 | task 2563 | eval time = 1161.98 ms / 128 tokens ( 9.15 ms per token, 109.30 tokens per second) 0.32.803.391 I slot print_timing: id 0 | task 2563 | total time = 1283.73 ms / 458 tokens 0.32.803.392 I slot print_timing: id 0 | task 2563 | graphs reused = 2503 0.32.803.393 I slot print_timing: id 0 | task 2563 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.803.419 I slot release: id 0 | task 2563 | stop processing: n_tokens = 457, truncated = 0 0.32.807.040 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 457, t_last = 32710772 0.32.833.769 I slot launch_slot_: id 0 | task 2694 | processing task, is_child = 0 0.33.926.650 I slot print_timing: id 0 | task 2694 | prompt eval time = 122.15 ms / 341 tokens ( 0.36 ms per token, 2791.58 tokens per second) 0.33.926.656 I slot print_timing: id 0 | task 2694 | eval time = 970.71 ms / 107 tokens ( 9.16 ms per token, 109.20 tokens per second) 0.33.926.657 I slot print_timing: id 0 | task 2694 | total time = 1092.86 ms / 448 tokens 0.33.926.657 I slot print_timing: id 0 | task 2694 | graphs reused = 2608 0.33.926.658 I slot print_timing: id 0 | task 2694 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.926.687 I slot release: id 0 | task 2694 | stop processing: n_tokens = 447, truncated = 0 0.33.941.723 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 33834040 0.33.967.465 I slot launch_slot_: id 0 | task 2804 | processing task, is_child = 0 0.34.526.735 I slot print_timing: id 0 | task 2804 | prompt eval time = 125.42 ms / 338 tokens ( 0.37 ms per token, 2694.99 tokens per second) 0.34.526.741 I slot print_timing: id 0 | task 2804 | eval time = 433.83 ms / 48 tokens ( 9.23 ms per token, 108.34 tokens per second) 0.34.526.742 I slot print_timing: id 0 | task 2804 | total time = 559.25 ms / 386 tokens 0.34.526.743 I slot print_timing: id 0 | task 2804 | graphs reused = 2654 0.34.526.744 I slot print_timing: id 0 | task 2804 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.526.773 I slot release: id 0 | task 2804 | stop processing: n_tokens = 385, truncated = 0 0.34.549.238 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 385, t_last = 34434126 0.34.574.789 I slot launch_slot_: id 0 | task 2855 | processing task, is_child = 0 0.35.210.551 I slot print_timing: id 0 | task 2855 | prompt eval time = 130.64 ms / 395 tokens ( 0.33 ms per token, 3023.62 tokens per second) 0.35.210.557 I slot print_timing: id 0 | task 2855 | eval time = 505.10 ms / 56 tokens ( 9.18 ms per token, 108.89 tokens per second) 0.35.210.558 I slot print_timing: id 0 | task 2855 | total time = 635.74 ms / 451 tokens 0.35.210.559 I slot print_timing: id 0 | task 2855 | graphs reused = 2708 0.35.210.560 I slot print_timing: id 0 | task 2855 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.210.588 I slot release: id 0 | task 2855 | stop processing: n_tokens = 450, truncated = 0 0.35.234.726 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 450, t_last = 35117941 0.35.273.949 I slot launch_slot_: id 0 | task 2914 | processing task, is_child = 0 0.36.211.151 I slot print_timing: id 0 | task 2914 | prompt eval time = 183.73 ms / 528 tokens ( 0.35 ms per token, 2873.84 tokens per second) 0.36.211.157 I slot print_timing: id 0 | task 2914 | eval time = 753.46 ms / 83 tokens ( 9.19 ms per token, 108.83 tokens per second) 0.36.211.158 I slot print_timing: id 0 | task 2914 | total time = 937.18 ms / 611 tokens 0.36.211.159 I slot print_timing: id 0 | task 2914 | graphs reused = 2789 0.36.211.160 I slot print_timing: id 0 | task 2914 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.211.194 I slot release: id 0 | task 2914 | stop processing: n_tokens = 610, truncated = 0 0.36.232.895 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 610, t_last = 36118547 0.36.270.594 I slot launch_slot_: id 0 | task 3001 | processing task, is_child = 0 0.36.817.318 I slot print_timing: id 0 | task 3001 | prompt eval time = 141.52 ms / 331 tokens ( 0.43 ms per token, 2338.93 tokens per second) 0.36.817.325 I slot print_timing: id 0 | task 3001 | eval time = 405.18 ms / 45 tokens ( 9.21 ms per token, 108.59 tokens per second) 0.36.817.326 I slot print_timing: id 0 | task 3001 | total time = 546.70 ms / 376 tokens 0.36.817.327 I slot print_timing: id 0 | task 3001 | graphs reused = 2832 0.36.817.328 I slot print_timing: id 0 | task 3001 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.817.358 I slot release: id 0 | task 3001 | stop processing: n_tokens = 387, truncated = 0 0.36.840.967 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 387, t_last = 36724710 0.36.872.422 I slot launch_slot_: id 0 | task 3049 | processing task, is_child = 0 0.37.500.910 I slot print_timing: id 0 | task 3049 | prompt eval time = 149.34 ms / 362 tokens ( 0.41 ms per token, 2424.00 tokens per second) 0.37.500.916 I slot print_timing: id 0 | task 3049 | eval time = 479.13 ms / 53 tokens ( 9.21 ms per token, 108.53 tokens per second) 0.37.500.917 I slot print_timing: id 0 | task 3049 | total time = 628.47 ms / 415 tokens 0.37.500.917 I slot print_timing: id 0 | task 3049 | graphs reused = 2883 0.37.500.918 I slot print_timing: id 0 | task 3049 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.500.946 I slot release: id 0 | task 3049 | stop processing: n_tokens = 426, truncated = 0 0.37.526.155 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 37408298 0.37.557.820 I slot launch_slot_: id 0 | task 3105 | processing task, is_child = 0 0.38.333.244 I slot print_timing: id 0 | task 3105 | prompt eval time = 151.53 ms / 419 tokens ( 0.36 ms per token, 2765.15 tokens per second) 0.38.333.251 I slot print_timing: id 0 | task 3105 | eval time = 623.87 ms / 69 tokens ( 9.17 ms per token, 109.00 tokens per second) 0.38.333.252 I slot print_timing: id 0 | task 3105 | total time = 775.40 ms / 488 tokens 0.38.333.253 I slot print_timing: id 0 | task 3105 | graphs reused = 2950 0.38.333.254 I slot print_timing: id 0 | task 3105 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.333.289 I slot release: id 0 | task 3105 | stop processing: n_tokens = 499, truncated = 0 0.38.351.106 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 499, t_last = 38240641 0.38.385.505 I slot launch_slot_: id 0 | task 3177 | processing task, is_child = 0 0.39.644.723 I slot print_timing: id 0 | task 3177 | prompt eval time = 172.87 ms / 423 tokens ( 0.41 ms per token, 2446.88 tokens per second) 0.39.644.729 I slot print_timing: id 0 | task 3177 | eval time = 1086.33 ms / 119 tokens ( 9.21 ms per token, 108.62 tokens per second) 0.39.644.730 I slot print_timing: id 0 | task 3177 | total time = 1259.20 ms / 542 tokens 0.39.644.731 I slot print_timing: id 0 | task 3177 | graphs reused = 3066 0.39.644.732 I slot print_timing: id 0 | task 3177 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.644.763 I slot release: id 0 | task 3177 | stop processing: n_tokens = 553, truncated = 0 0.39.658.024 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 553, t_last = 39552115 0.39.719.472 I slot launch_slot_: id 0 | task 3299 | processing task, is_child = 0 0.40.378.595 I slot print_timing: id 0 | task 3299 | prompt eval time = 145.21 ms / 341 tokens ( 0.43 ms per token, 2348.39 tokens per second) 0.40.378.600 I slot print_timing: id 0 | task 3299 | eval time = 513.90 ms / 57 tokens ( 9.18 ms per token, 108.97 tokens per second) 0.40.378.602 I slot print_timing: id 0 | task 3299 | total time = 659.10 ms / 398 tokens 0.40.378.602 I slot print_timing: id 0 | task 3299 | graphs reused = 3121 0.40.378.604 I slot print_timing: id 0 | task 3299 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.378.632 I slot release: id 0 | task 3299 | stop processing: n_tokens = 409, truncated = 0 0.40.406.115 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 40285985 0.40.452.543 I slot launch_slot_: id 0 | task 3359 | processing task, is_child = 0 0.41.020.743 I slot print_timing: id 0 | task 3359 | prompt eval time = 144.98 ms / 356 tokens ( 0.41 ms per token, 2455.56 tokens per second) 0.41.020.749 I slot print_timing: id 0 | task 3359 | eval time = 423.20 ms / 47 tokens ( 9.20 ms per token, 108.70 tokens per second) 0.41.020.750 I slot print_timing: id 0 | task 3359 | total time = 568.18 ms / 403 tokens 0.41.020.751 I slot print_timing: id 0 | task 3359 | graphs reused = 3166 0.41.020.752 I slot print_timing: id 0 | task 3359 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.020.780 I slot release: id 0 | task 3359 | stop processing: n_tokens = 414, truncated = 0 0.41.046.522 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 40928133 0.41.046.576 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 167.483 MiB) 0.41.086.945 I slot launch_slot_: id 0 | task 3409 | processing task, is_child = 0 0.41.654.110 I slot print_timing: id 0 | task 3409 | prompt eval time = 152.46 ms / 362 tokens ( 0.42 ms per token, 2374.42 tokens per second) 0.41.654.116 I slot print_timing: id 0 | task 3409 | eval time = 414.69 ms / 46 tokens ( 9.22 ms per token, 108.52 tokens per second) 0.41.654.117 I slot print_timing: id 0 | task 3409 | total time = 567.15 ms / 408 tokens 0.41.654.118 I slot print_timing: id 0 | task 3409 | graphs reused = 3210 0.41.654.119 I slot print_timing: id 0 | task 3409 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.654.150 I slot release: id 0 | task 3409 | stop processing: n_tokens = 419, truncated = 0 0.41.680.865 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 41561503 0.41.680.915 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.856 MiB) 0.41.723.522 I slot launch_slot_: id 0 | task 3458 | processing task, is_child = 0 0.42.491.644 I slot print_timing: id 0 | task 3458 | prompt eval time = 152.06 ms / 391 tokens ( 0.39 ms per token, 2571.27 tokens per second) 0.42.491.650 I slot print_timing: id 0 | task 3458 | eval time = 616.04 ms / 68 tokens ( 9.19 ms per token, 108.76 tokens per second) 0.42.491.651 I slot print_timing: id 0 | task 3458 | total time = 768.10 ms / 459 tokens 0.42.491.652 I slot print_timing: id 0 | task 3458 | graphs reused = 3276 0.42.491.653 I slot print_timing: id 0 | task 3458 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.491.683 I slot release: id 0 | task 3458 | stop processing: n_tokens = 470, truncated = 0 0.42.511.537 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 42399036 0.42.511.592 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.449 MiB) 0.42.521.650 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.481 MiB) 0.42.587.581 I slot launch_slot_: id 0 | task 3529 | processing task, is_child = 0 0.43.217.235 I slot print_timing: id 0 | task 3529 | prompt eval time = 143.27 ms / 343 tokens ( 0.42 ms per token, 2394.11 tokens per second) 0.43.217.240 I slot print_timing: id 0 | task 3529 | eval time = 486.36 ms / 54 tokens ( 9.18 ms per token, 108.97 tokens per second) 0.43.217.241 I slot print_timing: id 0 | task 3529 | total time = 629.63 ms / 397 tokens 0.43.217.243 I slot print_timing: id 0 | task 3529 | graphs reused = 3328 0.43.217.244 I slot print_timing: id 0 | task 3529 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.217.271 I slot release: id 0 | task 3529 | stop processing: n_tokens = 408, truncated = 0 0.43.244.307 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 408, t_last = 43124624 0.43.244.355 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.451 MiB) 0.43.298.174 I slot launch_slot_: id 0 | task 3586 | processing task, is_child = 0 0.43.865.147 I slot print_timing: id 0 | task 3586 | prompt eval time = 152.89 ms / 401 tokens ( 0.38 ms per token, 2622.78 tokens per second) 0.43.865.154 I slot print_timing: id 0 | task 3586 | eval time = 414.06 ms / 46 tokens ( 9.20 ms per token, 108.68 tokens per second) 0.43.865.155 I slot print_timing: id 0 | task 3586 | total time = 566.95 ms / 447 tokens 0.43.865.156 I slot print_timing: id 0 | task 3586 | graphs reused = 3372 0.43.865.157 I slot print_timing: id 0 | task 3586 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.865.191 I slot release: id 0 | task 3586 | stop processing: n_tokens = 458, truncated = 0 0.43.882.852 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 43772543 0.43.882.904 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.074 MiB) 0.43.940.878 I slot launch_slot_: id 0 | task 3635 | processing task, is_child = 0 0.44.929.553 I slot print_timing: id 0 | task 3635 | prompt eval time = 144.75 ms / 355 tokens ( 0.41 ms per token, 2452.57 tokens per second) 0.44.929.559 I slot print_timing: id 0 | task 3635 | eval time = 843.91 ms / 93 tokens ( 9.17 ms per token, 109.02 tokens per second) 0.44.929.560 I slot print_timing: id 0 | task 3635 | total time = 988.66 ms / 448 tokens 0.44.929.561 I slot print_timing: id 0 | task 3635 | graphs reused = 3463 0.44.929.562 I slot print_timing: id 0 | task 3635 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.929.591 I slot release: id 0 | task 3635 | stop processing: n_tokens = 459, truncated = 0 0.44.943.529 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 459, t_last = 44836943 0.44.943.572 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.638 MiB) 0.45.006.519 I slot launch_slot_: id 0 | task 3731 | processing task, is_child = 0 0.45.700.424 I slot print_timing: id 0 | task 3731 | prompt eval time = 144.77 ms / 351 tokens ( 0.41 ms per token, 2424.49 tokens per second) 0.45.700.429 I slot print_timing: id 0 | task 3731 | eval time = 549.11 ms / 57 tokens ( 9.81 ms per token, 101.98 tokens per second) 0.45.700.430 I slot print_timing: id 0 | task 3731 | total time = 693.89 ms / 408 tokens 0.45.700.431 I slot print_timing: id 0 | task 3731 | graphs reused = 3518 0.45.700.432 I slot print_timing: id 0 | task 3731 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.700.460 I slot release: id 0 | task 3731 | stop processing: n_tokens = 419, truncated = 0 0.45.725.039 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 45607813 0.45.725.091 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 167.671 MiB) 0.45.735.450 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.980 MiB) 0.45.796.021 I slot launch_slot_: id 0 | task 3791 | processing task, is_child = 0 0.46.820.816 I slot print_timing: id 0 | task 3791 | prompt eval time = 167.35 ms / 475 tokens ( 0.35 ms per token, 2838.29 tokens per second) 0.46.820.821 I slot print_timing: id 0 | task 3791 | eval time = 857.42 ms / 94 tokens ( 9.22 ms per token, 108.46 tokens per second) 0.46.820.822 I slot print_timing: id 0 | task 3791 | total time = 1024.78 ms / 569 tokens 0.46.820.823 I slot print_timing: id 0 | task 3791 | graphs reused = 3609 0.46.820.824 I slot print_timing: id 0 | task 3791 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.820.857 I slot release: id 0 | task 3791 | stop processing: n_tokens = 580, truncated = 0 0.46.848.532 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 580, t_last = 46728210 0.46.848.603 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.544 MiB) 0.46.903.144 I slot launch_slot_: id 0 | task 3888 | processing task, is_child = 0 0.48.034.988 I slot print_timing: id 0 | task 3888 | prompt eval time = 166.19 ms / 440 tokens ( 0.38 ms per token, 2647.64 tokens per second) 0.48.034.994 I slot print_timing: id 0 | task 3888 | eval time = 965.64 ms / 106 tokens ( 9.20 ms per token, 108.74 tokens per second) 0.48.034.995 I slot print_timing: id 0 | task 3888 | total time = 1131.82 ms / 546 tokens 0.48.034.996 I slot print_timing: id 0 | task 3888 | graphs reused = 3712 0.48.034.997 I slot print_timing: id 0 | task 3888 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.035.028 I slot release: id 0 | task 3888 | stop processing: n_tokens = 557, truncated = 0 0.48.061.962 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 557, t_last = 47942381 0.48.062.018 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 0.48.119.407 I slot launch_slot_: id 0 | task 3997 | processing task, is_child = 0 0.48.781.216 I slot print_timing: id 0 | task 3997 | prompt eval time = 152.01 ms / 345 tokens ( 0.44 ms per token, 2269.63 tokens per second) 0.48.781.222 I slot print_timing: id 0 | task 3997 | eval time = 509.78 ms / 55 tokens ( 9.44 ms per token, 105.93 tokens per second) 0.48.781.223 I slot print_timing: id 0 | task 3997 | total time = 661.79 ms / 400 tokens 0.48.781.224 I slot print_timing: id 0 | task 3997 | graphs reused = 3765 0.48.781.225 I slot print_timing: id 0 | task 3997 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.781.252 I slot release: id 0 | task 3997 | stop processing: n_tokens = 411, truncated = 0 0.48.808.017 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 48688605 0.48.808.066 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.075 MiB) 0.48.818.669 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 0.48.888.178 I slot launch_slot_: id 0 | task 4055 | processing task, is_child = 0 0.49.541.438 I slot print_timing: id 0 | task 4055 | prompt eval time = 152.47 ms / 382 tokens ( 0.40 ms per token, 2505.38 tokens per second) 0.49.541.444 I slot print_timing: id 0 | task 4055 | eval time = 500.77 ms / 55 tokens ( 9.27 ms per token, 107.83 tokens per second) 0.49.541.445 I slot print_timing: id 0 | task 4055 | total time = 653.24 ms / 437 tokens 0.49.541.446 I slot print_timing: id 0 | task 4055 | graphs reused = 3818 0.49.541.447 I slot print_timing: id 0 | task 4055 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.541.478 I slot release: id 0 | task 4055 | stop processing: n_tokens = 448, truncated = 0 0.49.557.354 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 49448830 0.49.557.400 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.168 MiB) 0.49.611.209 I slot launch_slot_: id 0 | task 4113 | processing task, is_child = 0 0.50.161.977 I slot print_timing: id 0 | task 4113 | prompt eval time = 144.29 ms / 337 tokens ( 0.43 ms per token, 2335.57 tokens per second) 0.50.161.983 I slot print_timing: id 0 | task 4113 | eval time = 406.46 ms / 45 tokens ( 9.24 ms per token, 108.25 tokens per second) 0.50.161.984 I slot print_timing: id 0 | task 4113 | total time = 550.75 ms / 382 tokens 0.50.161.985 I slot print_timing: id 0 | task 4113 | graphs reused = 3861 0.50.161.986 I slot print_timing: id 0 | task 4113 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.162.014 I slot release: id 0 | task 4113 | stop processing: n_tokens = 393, truncated = 0 0.50.179.990 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 50069366 0.50.180.032 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.012 MiB) 0.50.246.017 I slot launch_slot_: id 0 | task 4161 | processing task, is_child = 0 0.51.062.678 I slot print_timing: id 0 | task 4161 | prompt eval time = 150.57 ms / 402 tokens ( 0.37 ms per token, 2669.77 tokens per second) 0.51.062.684 I slot print_timing: id 0 | task 4161 | eval time = 666.07 ms / 70 tokens ( 9.65 ms per token, 103.59 tokens per second) 0.51.062.685 I slot print_timing: id 0 | task 4161 | total time = 816.64 ms / 472 tokens 0.51.062.686 I slot print_timing: id 0 | task 4161 | graphs reused = 3929 0.51.062.687 I slot print_timing: id 0 | task 4161 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.062.716 I slot release: id 0 | task 4161 | stop processing: n_tokens = 483, truncated = 0 0.51.066.917 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 483, t_last = 50970069 0.51.066.966 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.167 MiB) 0.51.077.396 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.481 MiB) 0.51.136.202 I slot launch_slot_: id 0 | task 4234 | processing task, is_child = 0 0.51.842.353 I slot print_timing: id 0 | task 4234 | prompt eval time = 189.12 ms / 549 tokens ( 0.34 ms per token, 2902.92 tokens per second) 0.51.842.360 I slot print_timing: id 0 | task 4234 | eval time = 517.01 ms / 57 tokens ( 9.23 ms per token, 108.32 tokens per second) 0.51.842.361 I slot print_timing: id 0 | task 4234 | total time = 706.13 ms / 606 tokens 0.51.842.362 I slot print_timing: id 0 | task 4234 | graphs reused = 3984 0.51.842.363 I slot print_timing: id 0 | task 4234 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.842.404 I slot release: id 0 | task 4234 | stop processing: n_tokens = 617, truncated = 0 0.51.864.036 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 617, t_last = 51749757 0.51.864.101 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.011 MiB) 0.51.939.540 I slot launch_slot_: id 0 | task 4295 | processing task, is_child = 0 0.52.668.939 I slot print_timing: id 0 | task 4295 | prompt eval time = 203.31 ms / 616 tokens ( 0.33 ms per token, 3029.93 tokens per second) 0.52.668.945 I slot print_timing: id 0 | task 4295 | eval time = 526.07 ms / 58 tokens ( 9.23 ms per token, 108.35 tokens per second) 0.52.668.946 I slot print_timing: id 0 | task 4295 | total time = 729.38 ms / 674 tokens 0.52.668.947 I slot print_timing: id 0 | task 4295 | graphs reused = 4040 0.52.668.948 I slot print_timing: id 0 | task 4295 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.668.984 I slot release: id 0 | task 4295 | stop processing: n_tokens = 685, truncated = 0 0.52.693.802 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 685, t_last = 52576336 0.52.693.865 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.606 MiB) 0.52.703.962 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.700 MiB) 0.52.776.155 I slot launch_slot_: id 0 | task 4357 | processing task, is_child = 0 0.53.557.121 I slot print_timing: id 0 | task 4357 | prompt eval time = 217.90 ms / 665 tokens ( 0.33 ms per token, 3051.82 tokens per second) 0.53.557.128 I slot print_timing: id 0 | task 4357 | eval time = 563.04 ms / 62 tokens ( 9.23 ms per token, 108.34 tokens per second) 0.53.557.129 I slot print_timing: id 0 | task 4357 | total time = 780.95 ms / 727 tokens 0.53.557.130 I slot print_timing: id 0 | task 4357 | graphs reused = 4100 0.53.557.130 I slot print_timing: id 0 | task 4357 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.557.169 I slot release: id 0 | task 4357 | stop processing: n_tokens = 738, truncated = 0 0.53.585.068 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 738, t_last = 53464521 0.53.585.132 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.543 MiB) 0.53.595.316 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.732 MiB) 0.53.669.441 I slot launch_slot_: id 0 | task 4423 | processing task, is_child = 0 0.54.379.274 I slot print_timing: id 0 | task 4423 | prompt eval time = 212.12 ms / 645 tokens ( 0.33 ms per token, 3040.73 tokens per second) 0.54.379.280 I slot print_timing: id 0 | task 4423 | eval time = 497.69 ms / 55 tokens ( 9.22 ms per token, 108.50 tokens per second) 0.54.379.281 I slot print_timing: id 0 | task 4423 | total time = 709.81 ms / 700 tokens 0.54.379.282 I slot print_timing: id 0 | task 4423 | graphs reused = 4153 0.54.379.283 I slot print_timing: id 0 | task 4423 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.379.318 I slot release: id 0 | task 4423 | stop processing: n_tokens = 711, truncated = 0 0.54.395.701 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 711, t_last = 54286671 0.54.395.756 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.575 MiB) 0.54.472.725 I slot launch_slot_: id 0 | task 4482 | processing task, is_child = 0 0.55.457.281 I slot print_timing: id 0 | task 4482 | prompt eval time = 170.31 ms / 474 tokens ( 0.36 ms per token, 2783.23 tokens per second) 0.55.457.286 I slot print_timing: id 0 | task 4482 | eval time = 814.23 ms / 88 tokens ( 9.36 ms per token, 106.85 tokens per second) 0.55.457.287 I slot print_timing: id 0 | task 4482 | total time = 984.54 ms / 562 tokens 0.55.457.288 I slot print_timing: id 0 | task 4482 | graphs reused = 4238 0.55.457.289 I slot print_timing: id 0 | task 4482 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.457.322 I slot release: id 0 | task 4482 | stop processing: n_tokens = 573, truncated = 0 0.55.481.332 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 573, t_last = 55364675 0.55.481.382 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.294 MiB) 0.55.491.803 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.107 MiB) 0.55.553.064 I slot launch_slot_: id 0 | task 4573 | processing task, is_child = 0 0.56.130.804 I slot print_timing: id 0 | task 4573 | prompt eval time = 198.97 ms / 617 tokens ( 0.32 ms per token, 3100.92 tokens per second) 0.56.130.810 I slot print_timing: id 0 | task 4573 | eval time = 378.75 ms / 42 tokens ( 9.24 ms per token, 108.25 tokens per second) 0.56.130.811 I slot print_timing: id 0 | task 4573 | total time = 577.72 ms / 659 tokens 0.56.130.811 I slot print_timing: id 0 | task 4573 | graphs reused = 4278 0.56.130.812 I slot print_timing: id 0 | task 4573 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.130.846 I slot release: id 0 | task 4573 | stop processing: n_tokens = 670, truncated = 0 0.56.147.450 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 670, t_last = 56038198 0.56.147.511 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.919 MiB) 0.56.214.977 I slot launch_slot_: id 0 | task 4619 | processing task, is_child = 0 0.56.848.276 I slot print_timing: id 0 | task 4619 | prompt eval time = 200.06 ms / 601 tokens ( 0.33 ms per token, 3004.11 tokens per second) 0.56.848.282 I slot print_timing: id 0 | task 4619 | eval time = 433.22 ms / 48 tokens ( 9.22 ms per token, 108.49 tokens per second) 0.56.848.283 I slot print_timing: id 0 | task 4619 | total time = 633.28 ms / 649 tokens 0.56.848.284 I slot print_timing: id 0 | task 4619 | graphs reused = 4324 0.56.848.285 I slot print_timing: id 0 | task 4619 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.848.320 I slot release: id 0 | task 4619 | stop processing: n_tokens = 660, truncated = 0 0.56.866.049 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 660, t_last = 56755672 0.56.866.109 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.199 MiB) 0.56.876.231 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.512 MiB) 0.56.949.112 I slot launch_slot_: id 0 | task 4671 | processing task, is_child = 0 0.57.567.305 I slot print_timing: id 0 | task 4671 | prompt eval time = 191.27 ms / 533 tokens ( 0.36 ms per token, 2786.68 tokens per second) 0.57.567.311 I slot print_timing: id 0 | task 4671 | eval time = 426.91 ms / 47 tokens ( 9.28 ms per token, 107.75 tokens per second) 0.57.567.312 I slot print_timing: id 0 | task 4671 | total time = 618.17 ms / 580 tokens 0.57.567.314 I slot print_timing: id 0 | task 4671 | graphs reused = 4369 0.57.567.315 I slot print_timing: id 0 | task 4671 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.567.347 I slot release: id 0 | task 4671 | stop processing: n_tokens = 591, truncated = 0 0.57.585.071 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 591, t_last = 57474700 0.57.585.127 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.044 MiB) 0.57.664.664 I slot launch_slot_: id 0 | task 4722 | processing task, is_child = 0 0.58.317.122 I slot print_timing: id 0 | task 4722 | prompt eval time = 174.77 ms / 480 tokens ( 0.36 ms per token, 2746.53 tokens per second) 0.58.317.129 I slot print_timing: id 0 | task 4722 | eval time = 477.67 ms / 52 tokens ( 9.37 ms per token, 106.77 tokens per second) 0.58.317.130 I slot print_timing: id 0 | task 4722 | total time = 652.44 ms / 532 tokens 0.58.317.131 I slot print_timing: id 0 | task 4722 | graphs reused = 4418 0.58.317.132 I slot print_timing: id 0 | task 4722 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.317.164 I slot release: id 0 | task 4722 | stop processing: n_tokens = 560, truncated = 0 0.58.337.117 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 58224517 0.58.337.168 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.950 MiB) 0.58.347.318 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.761 MiB) 0.58.419.051 I slot launch_slot_: id 0 | task 4777 | processing task, is_child = 0 0.58.987.242 I slot print_timing: id 0 | task 4777 | prompt eval time = 188.63 ms / 567 tokens ( 0.33 ms per token, 3005.82 tokens per second) 0.58.987.248 I slot print_timing: id 0 | task 4777 | eval time = 379.54 ms / 42 tokens ( 9.26 ms per token, 108.03 tokens per second) 0.58.987.249 I slot print_timing: id 0 | task 4777 | total time = 568.17 ms / 609 tokens 0.58.987.250 I slot print_timing: id 0 | task 4777 | graphs reused = 4458 0.58.987.251 I slot print_timing: id 0 | task 4777 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.987.286 I slot release: id 0 | task 4777 | stop processing: n_tokens = 637, truncated = 0 0.59.005.573 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 58894638 0.59.005.636 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.699 MiB) 0.59.015.691 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.731 MiB) 0.59.097.976 I slot launch_slot_: id 0 | task 4823 | processing task, is_child = 0 0.59.856.692 I slot print_timing: id 0 | task 4823 | prompt eval time = 185.78 ms / 506 tokens ( 0.37 ms per token, 2723.65 tokens per second) 0.59.856.698 I slot print_timing: id 0 | task 4823 | eval time = 572.92 ms / 63 tokens ( 9.24 ms per token, 108.22 tokens per second) 0.59.856.699 I slot print_timing: id 0 | task 4823 | total time = 758.70 ms / 569 tokens 0.59.856.700 I slot print_timing: id 0 | task 4823 | graphs reused = 4519 0.59.856.701 I slot print_timing: id 0 | task 4823 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.856.733 I slot release: id 0 | task 4823 | stop processing: n_tokens = 597, truncated = 0 0.59.872.463 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 597, t_last = 59764086 0.59.872.520 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.450 MiB) 0.59.882.734 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.261 MiB) 0.59.955.065 I slot launch_slot_: id 0 | task 4889 | processing task, is_child = 0 1.00.484.092 I slot print_timing: id 0 | task 4889 | prompt eval time = 168.76 ms / 436 tokens ( 0.39 ms per token, 2583.61 tokens per second) 1.00.484.098 I slot print_timing: id 0 | task 4889 | eval time = 360.25 ms / 40 tokens ( 9.24 ms per token, 108.26 tokens per second) 1.00.484.099 I slot print_timing: id 0 | task 4889 | total time = 529.00 ms / 476 tokens 1.00.484.100 I slot print_timing: id 0 | task 4889 | graphs reused = 4557 1.00.484.101 I slot print_timing: id 0 | task 4889 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.484.131 I slot release: id 0 | task 4889 | stop processing: n_tokens = 504, truncated = 0 1.00.512.828 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 60391484 1.00.512.882 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.762 MiB) 1.00.579.160 I slot launch_slot_: id 0 | task 4932 | processing task, is_child = 0 1.01.301.926 I slot print_timing: id 0 | task 4932 | prompt eval time = 178.95 ms / 519 tokens ( 0.34 ms per token, 2900.30 tokens per second) 1.01.301.932 I slot print_timing: id 0 | task 4932 | eval time = 543.80 ms / 60 tokens ( 9.22 ms per token, 108.50 tokens per second) 1.01.301.933 I slot print_timing: id 0 | task 4932 | total time = 722.75 ms / 579 tokens 1.01.301.934 I slot print_timing: id 0 | task 4932 | graphs reused = 4615 1.01.301.935 I slot print_timing: id 0 | task 4932 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.301.968 I slot release: id 0 | task 4932 | stop processing: n_tokens = 607, truncated = 0 1.01.320.175 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 607, t_last = 61209321 1.01.320.232 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 161.697 MiB) 1.01.330.287 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.044 MiB) 1.01.426.996 I slot launch_slot_: id 0 | task 4996 | processing task, is_child = 0 1.02.022.292 I slot print_timing: id 0 | task 4996 | prompt eval time = 170.09 ms / 465 tokens ( 0.37 ms per token, 2733.85 tokens per second) 1.02.022.298 I slot print_timing: id 0 | task 4996 | eval time = 425.19 ms / 46 tokens ( 9.45 ms per token, 105.84 tokens per second) 1.02.022.300 I slot print_timing: id 0 | task 4996 | total time = 595.28 ms / 511 tokens 1.02.022.300 I slot print_timing: id 0 | task 4996 | graphs reused = 4658 1.02.022.301 I slot print_timing: id 0 | task 4996 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.022.333 I slot release: id 0 | task 4996 | stop processing: n_tokens = 542, truncated = 0 1.02.050.302 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 542, t_last = 61929686 1.02.050.353 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.731 MiB) 1.02.060.977 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.792 MiB) 1.02.143.259 I slot launch_slot_: id 0 | task 5045 | processing task, is_child = 0 1.02.681.263 I slot print_timing: id 0 | task 5045 | prompt eval time = 168.29 ms / 431 tokens ( 0.39 ms per token, 2561.06 tokens per second) 1.02.681.269 I slot print_timing: id 0 | task 5045 | eval time = 369.69 ms / 41 tokens ( 9.24 ms per token, 108.20 tokens per second) 1.02.681.270 I slot print_timing: id 0 | task 5045 | total time = 537.98 ms / 472 tokens 1.02.681.271 I slot print_timing: id 0 | task 5045 | graphs reused = 4697 1.02.681.272 I slot print_timing: id 0 | task 5045 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.681.303 I slot release: id 0 | task 5045 | stop processing: n_tokens = 503, truncated = 0 1.02.707.733 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 503, t_last = 62588656 1.02.707.786 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.825 MiB) 1.02.717.931 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 220.079 MiB) 1.02.807.605 I slot launch_slot_: id 0 | task 5089 | processing task, is_child = 0 1.03.379.810 I slot print_timing: id 0 | task 5089 | prompt eval time = 168.75 ms / 457 tokens ( 0.37 ms per token, 2708.08 tokens per second) 1.03.379.816 I slot print_timing: id 0 | task 5089 | eval time = 403.43 ms / 44 tokens ( 9.38 ms per token, 106.59 tokens per second) 1.03.379.817 I slot print_timing: id 0 | task 5089 | total time = 572.19 ms / 501 tokens 1.03.379.818 I slot print_timing: id 0 | task 5089 | graphs reused = 4738 1.03.379.818 I slot print_timing: id 0 | task 5089 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.379.852 I slot release: id 0 | task 5089 | stop processing: n_tokens = 532, truncated = 0 1.03.394.083 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 532, t_last = 63287205 1.03.394.126 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.105 MiB) 1.03.483.847 I slot launch_slot_: id 0 | task 5136 | processing task, is_child = 0 1.04.548.197 I slot print_timing: id 0 | task 5136 | prompt eval time = 168.71 ms / 439 tokens ( 0.38 ms per token, 2602.07 tokens per second) 1.04.548.203 I slot print_timing: id 0 | task 5136 | eval time = 895.62 ms / 98 tokens ( 9.23 ms per token, 108.31 tokens per second) 1.04.548.204 I slot print_timing: id 0 | task 5136 | total time = 1064.33 ms / 537 tokens 1.04.548.205 I slot print_timing: id 0 | task 5136 | graphs reused = 4833 1.04.548.205 I slot print_timing: id 0 | task 5136 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.548.238 I slot release: id 0 | task 5136 | stop processing: n_tokens = 568, truncated = 0 1.04.576.971 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 568, t_last = 64455590 1.04.577.027 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.325 MiB) 1.04.590.292 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.608 MiB) 1.04.676.394 I slot launch_slot_: id 0 | task 5237 | processing task, is_child = 0 1.05.379.255 I slot print_timing: id 0 | task 5237 | prompt eval time = 196.01 ms / 606 tokens ( 0.32 ms per token, 3091.62 tokens per second) 1.05.379.261 I slot print_timing: id 0 | task 5237 | eval time = 506.83 ms / 56 tokens ( 9.22 ms per token, 108.52 tokens per second) 1.05.379.262 I slot print_timing: id 0 | task 5237 | total time = 702.84 ms / 662 tokens 1.05.379.263 I slot print_timing: id 0 | task 5237 | graphs reused = 4887 1.05.379.264 I slot print_timing: id 0 | task 5237 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.379.301 I slot release: id 0 | task 5237 | stop processing: n_tokens = 693, truncated = 0 1.05.401.637 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 65286654 1.05.401.688 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 218.296 MiB) 1.05.415.001 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.793 MiB) 1.05.507.179 I slot launch_slot_: id 0 | task 5297 | processing task, is_child = 0 1.06.055.655 I slot print_timing: id 0 | task 5297 | prompt eval time = 174.72 ms / 477 tokens ( 0.37 ms per token, 2730.07 tokens per second) 1.06.055.661 I slot print_timing: id 0 | task 5297 | eval time = 373.73 ms / 41 tokens ( 9.34 ms per token, 107.03 tokens per second) 1.06.055.662 I slot print_timing: id 0 | task 5297 | total time = 548.45 ms / 518 tokens 1.06.055.663 I slot print_timing: id 0 | task 5297 | graphs reused = 4925 1.06.055.664 I slot print_timing: id 0 | task 5297 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.055.696 I slot release: id 0 | task 5297 | stop processing: n_tokens = 549, truncated = 0 1.06.075.670 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 65963049 1.06.075.725 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.949 MiB) 1.06.130.397 I slot launch_slot_: id 0 | task 5341 | processing task, is_child = 0 1.06.915.573 I slot print_timing: id 0 | task 5341 | prompt eval time = 241.13 ms / 845 tokens ( 0.29 ms per token, 3504.32 tokens per second) 1.06.915.578 I slot print_timing: id 0 | task 5341 | eval time = 544.03 ms / 60 tokens ( 9.22 ms per token, 108.45 tokens per second) 1.06.915.580 I slot print_timing: id 0 | task 5341 | total time = 785.16 ms / 905 tokens 1.06.915.580 I slot print_timing: id 0 | task 5341 | graphs reused = 4983 1.06.915.581 I slot print_timing: id 0 | task 5341 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.915.626 I slot release: id 0 | task 5341 | stop processing: n_tokens = 936, truncated = 0 1.06.938.132 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 936, t_last = 66822978 1.06.938.202 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.106 MiB) 1.06.949.546 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.701 MiB) 1.07.025.808 I slot launch_slot_: id 0 | task 5405 | processing task, is_child = 0 1.07.590.454 I slot print_timing: id 0 | task 5405 | prompt eval time = 172.03 ms / 459 tokens ( 0.37 ms per token, 2668.17 tokens per second) 1.07.590.460 I slot print_timing: id 0 | task 5405 | eval time = 392.60 ms / 43 tokens ( 9.35 ms per token, 106.98 tokens per second) 1.07.590.461 I slot print_timing: id 0 | task 5405 | total time = 564.63 ms / 502 tokens 1.07.590.462 I slot print_timing: id 0 | task 5405 | graphs reused = 5023 1.07.590.463 I slot print_timing: id 0 | task 5405 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.590.495 I slot release: id 0 | task 5405 | stop processing: n_tokens = 533, truncated = 0 1.07.605.502 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 533, t_last = 67497848 1.07.605.552 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.762 MiB) 1.07.697.521 I slot launch_slot_: id 0 | task 5451 | processing task, is_child = 0 1.08.331.107 I slot print_timing: id 0 | task 5451 | prompt eval time = 209.22 ms / 670 tokens ( 0.31 ms per token, 3202.37 tokens per second) 1.08.331.114 I slot print_timing: id 0 | task 5451 | eval time = 424.35 ms / 47 tokens ( 9.22 ms per token, 108.40 tokens per second) 1.08.331.115 I slot print_timing: id 0 | task 5451 | total time = 633.57 ms / 717 tokens 1.08.331.115 I slot print_timing: id 0 | task 5451 | graphs reused = 5068 1.08.331.116 I slot print_timing: id 0 | task 5451 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.331.156 I slot release: id 0 | task 5451 | stop processing: n_tokens = 748, truncated = 0 1.08.356.861 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 748, t_last = 68238509 1.08.356.925 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.325 MiB) 1.08.370.152 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.357 MiB) 1.08.468.471 I slot launch_slot_: id 0 | task 5502 | processing task, is_child = 0 1.09.308.063 I slot print_timing: id 0 | task 5502 | prompt eval time = 236.69 ms / 775 tokens ( 0.31 ms per token, 3274.27 tokens per second) 1.09.308.068 I slot print_timing: id 0 | task 5502 | eval time = 602.88 ms / 63 tokens ( 9.72 ms per token, 102.84 tokens per second) 1.09.308.070 I slot print_timing: id 0 | task 5502 | total time = 839.57 ms / 838 tokens 1.09.308.070 I slot print_timing: id 0 | task 5502 | graphs reused = 5129 1.09.308.071 I slot print_timing: id 0 | task 5502 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.308.113 I slot release: id 0 | task 5502 | stop processing: n_tokens = 869, truncated = 0 1.09.337.453 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 869, t_last = 69215466 1.09.337.523 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.106 MiB) 1.09.350.966 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 219.141 MiB) 1.09.450.302 I slot launch_slot_: id 0 | task 5569 | processing task, is_child = 0 1.10.287.274 I slot print_timing: id 0 | task 5569 | prompt eval time = 192.89 ms / 573 tokens ( 0.34 ms per token, 2970.65 tokens per second) 1.10.287.280 I slot print_timing: id 0 | task 5569 | eval time = 644.07 ms / 71 tokens ( 9.20 ms per token, 108.68 tokens per second) 1.10.287.281 I slot print_timing: id 0 | task 5569 | total time = 836.95 ms / 644 tokens 1.10.287.282 I slot print_timing: id 0 | task 5569 | graphs reused = 5198 1.10.287.282 I slot print_timing: id 0 | task 5569 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.287.318 I slot release: id 0 | task 5569 | stop processing: n_tokens = 675, truncated = 0 1.10.301.690 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 675, t_last = 70194671 1.10.301.746 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 218.422 MiB) 1.10.315.137 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.856 MiB) 1.10.413.614 I slot launch_slot_: id 0 | task 5644 | processing task, is_child = 0 1.11.170.648 I slot print_timing: id 0 | task 5644 | prompt eval time = 173.23 ms / 461 tokens ( 0.38 ms per token, 2661.19 tokens per second) 1.11.170.654 I slot print_timing: id 0 | task 5644 | eval time = 583.78 ms / 64 tokens ( 9.27 ms per token, 107.92 tokens per second) 1.11.170.655 I slot print_timing: id 0 | task 5644 | total time = 757.01 ms / 525 tokens 1.11.170.656 I slot print_timing: id 0 | task 5644 | graphs reused = 5259 1.11.170.657 I slot print_timing: id 0 | task 5644 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.170.688 I slot release: id 0 | task 5644 | stop processing: n_tokens = 556, truncated = 0 1.11.198.159 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 556, t_last = 71078041 1.11.198.202 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.013 MiB) 1.11.274.082 I slot launch_slot_: id 0 | task 5711 | processing task, is_child = 0 1.12.590.269 I slot print_timing: id 0 | task 5711 | prompt eval time = 197.12 ms / 609 tokens ( 0.32 ms per token, 3089.50 tokens per second) 1.12.590.275 I slot print_timing: id 0 | task 5711 | eval time = 1119.05 ms / 123 tokens ( 9.17 ms per token, 109.02 tokens per second) 1.12.590.276 I slot print_timing: id 0 | task 5711 | total time = 1316.16 ms / 732 tokens 1.12.590.277 I slot print_timing: id 0 | task 5711 | graphs reused = 5380 1.12.590.278 I slot print_timing: id 0 | task 5711 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.590.317 I slot release: id 0 | task 5711 | stop processing: n_tokens = 763, truncated = 0 1.12.615.518 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 763, t_last = 72497670 1.12.615.582 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.293 MiB) 1.12.628.620 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.107 MiB) 1.12.711.978 I slot launch_slot_: id 0 | task 5838 | processing task, is_child = 0 1.13.508.391 I slot print_timing: id 0 | task 5838 | prompt eval time = 238.57 ms / 791 tokens ( 0.30 ms per token, 3315.62 tokens per second) 1.13.508.397 I slot print_timing: id 0 | task 5838 | eval time = 557.82 ms / 61 tokens ( 9.30 ms per token, 107.56 tokens per second) 1.13.508.399 I slot print_timing: id 0 | task 5838 | total time = 796.39 ms / 852 tokens 1.13.508.399 I slot print_timing: id 0 | task 5838 | graphs reused = 5439 1.13.508.400 I slot print_timing: id 0 | task 5838 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.508.446 I slot release: id 0 | task 5838 | stop processing: n_tokens = 883, truncated = 0 1.13.529.544 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 883, t_last = 73415799 1.13.529.611 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 270.548 MiB) 1.13.673.926 I slot launch_slot_: id 0 | task 5903 | processing task, is_child = 0 1.14.370.921 I slot print_timing: id 0 | task 5903 | prompt eval time = 188.27 ms / 533 tokens ( 0.35 ms per token, 2831.03 tokens per second) 1.14.370.927 I slot print_timing: id 0 | task 5903 | eval time = 508.70 ms / 56 tokens ( 9.25 ms per token, 108.12 tokens per second) 1.14.370.928 I slot print_timing: id 0 | task 5903 | total time = 696.97 ms / 589 tokens 1.14.370.928 I slot print_timing: id 0 | task 5903 | graphs reused = 5493 1.14.370.929 I slot print_timing: id 0 | task 5903 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.370.965 I slot release: id 0 | task 5903 | stop processing: n_tokens = 677, truncated = 0 1.14.398.602 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 677, t_last = 74278318 1.14.398.662 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 272.675 MiB) 1.14.492.753 I slot launch_slot_: id 0 | task 5963 | processing task, is_child = 0 1.15.137.279 I slot print_timing: id 0 | task 5963 | prompt eval time = 198.09 ms / 566 tokens ( 0.35 ms per token, 2857.24 tokens per second) 1.15.137.284 I slot print_timing: id 0 | task 5963 | eval time = 446.41 ms / 46 tokens ( 9.92 ms per token, 100.80 tokens per second) 1.15.137.286 I slot print_timing: id 0 | task 5963 | total time = 644.51 ms / 612 tokens 1.15.137.287 I slot print_timing: id 0 | task 5963 | graphs reused = 5537 1.15.137.288 I slot print_timing: id 0 | task 5963 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.137.326 I slot release: id 0 | task 5963 | stop processing: n_tokens = 643, truncated = 0 1.15.163.774 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 643, t_last = 75044678 1.15.163.821 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.332 MiB) 1.15.251.634 I slot launch_slot_: id 0 | task 6013 | processing task, is_child = 0 1.15.817.578 I slot print_timing: id 0 | task 6013 | prompt eval time = 171.20 ms / 443 tokens ( 0.39 ms per token, 2587.62 tokens per second) 1.15.817.584 I slot print_timing: id 0 | task 6013 | eval time = 394.72 ms / 43 tokens ( 9.40 ms per token, 106.40 tokens per second) 1.15.817.585 I slot print_timing: id 0 | task 6013 | total time = 565.92 ms / 486 tokens 1.15.817.586 I slot print_timing: id 0 | task 6013 | graphs reused = 5577 1.15.817.587 I slot print_timing: id 0 | task 6013 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.817.618 I slot release: id 0 | task 6013 | stop processing: n_tokens = 517, truncated = 0 1.15.832.913 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 517, t_last = 75724971 1.15.832.962 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.488 MiB) 1.15.912.194 I slot launch_slot_: id 0 | task 6059 | processing task, is_child = 0 1.16.676.587 I slot print_timing: id 0 | task 6059 | prompt eval time = 173.11 ms / 487 tokens ( 0.36 ms per token, 2813.22 tokens per second) 1.16.676.593 I slot print_timing: id 0 | task 6059 | eval time = 591.26 ms / 65 tokens ( 9.24 ms per token, 108.24 tokens per second) 1.16.676.594 I slot print_timing: id 0 | task 6059 | total time = 764.37 ms / 552 tokens 1.16.676.595 I slot print_timing: id 0 | task 6059 | graphs reused = 5640 1.16.676.596 I slot print_timing: id 0 | task 6059 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.676.631 I slot release: id 0 | task 6059 | stop processing: n_tokens = 583, truncated = 0 1.16.704.992 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 583, t_last = 76583983 1.16.705.036 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 218.922 MiB) 1.16.795.867 I slot launch_slot_: id 0 | task 6127 | processing task, is_child = 0 1.17.396.197 I slot print_timing: id 0 | task 6127 | prompt eval time = 173.16 ms / 507 tokens ( 0.34 ms per token, 2927.89 tokens per second) 1.17.396.203 I slot print_timing: id 0 | task 6127 | eval time = 427.14 ms / 47 tokens ( 9.29 ms per token, 107.69 tokens per second) 1.17.396.204 I slot print_timing: id 0 | task 6127 | total time = 600.31 ms / 554 tokens 1.17.396.205 I slot print_timing: id 0 | task 6127 | graphs reused = 5685 1.17.396.207 I slot print_timing: id 0 | task 6127 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.396.245 I slot release: id 0 | task 6127 | stop processing: n_tokens = 585, truncated = 0 1.17.425.961 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 585, t_last = 77303598 1.17.426.009 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 272.206 MiB) 1.17.442.888 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 271.893 MiB) 1.17.534.935 I slot launch_slot_: id 0 | task 6177 | processing task, is_child = 0 1.18.334.944 I slot print_timing: id 0 | task 6177 | prompt eval time = 201.76 ms / 633 tokens ( 0.32 ms per token, 3137.42 tokens per second) 1.18.334.950 I slot print_timing: id 0 | task 6177 | eval time = 598.23 ms / 66 tokens ( 9.20 ms per token, 108.65 tokens per second) 1.18.334.951 I slot print_timing: id 0 | task 6177 | total time = 799.99 ms / 699 tokens 1.18.334.952 I slot print_timing: id 0 | task 6177 | graphs reused = 5749 1.18.334.953 I slot print_timing: id 0 | task 6177 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.334.992 I slot release: id 0 | task 6177 | stop processing: n_tokens = 730, truncated = 0 1.18.358.219 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 730, t_last = 78242344 1.18.358.278 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 269.735 MiB) 1.18.447.493 I slot launch_slot_: id 0 | task 6247 | processing task, is_child = 0 1.19.065.688 I slot print_timing: id 0 | task 6247 | prompt eval time = 193.58 ms / 571 tokens ( 0.34 ms per token, 2949.62 tokens per second) 1.19.065.693 I slot print_timing: id 0 | task 6247 | eval time = 424.59 ms / 47 tokens ( 9.23 ms per token, 108.34 tokens per second) 1.19.065.694 I slot print_timing: id 0 | task 6247 | total time = 618.17 ms / 618 tokens 1.19.065.695 I slot print_timing: id 0 | task 6247 | graphs reused = 5794 1.19.065.696 I slot print_timing: id 0 | task 6247 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.065.731 I slot release: id 0 | task 6247 | stop processing: n_tokens = 649, truncated = 0 1.19.091.749 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 649, t_last = 78973084 1.19.091.806 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 268.766 MiB) 1.19.188.450 I slot launch_slot_: id 0 | task 6298 | processing task, is_child = 0 1.19.826.616 I slot print_timing: id 0 | task 6298 | prompt eval time = 239.28 ms / 798 tokens ( 0.30 ms per token, 3334.98 tokens per second) 1.19.826.622 I slot print_timing: id 0 | task 6298 | eval time = 398.86 ms / 44 tokens ( 9.28 ms per token, 107.81 tokens per second) 1.19.826.623 I slot print_timing: id 0 | task 6298 | total time = 638.14 ms / 842 tokens 1.19.826.623 I slot print_timing: id 0 | task 6298 | graphs reused = 5836 1.19.826.624 I slot print_timing: id 0 | task 6298 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.826.668 I slot release: id 0 | task 6298 | stop processing: n_tokens = 873, truncated = 0 1.19.852.589 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 873, t_last = 79734020 1.19.852.658 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.424 MiB) 1.19.872.418 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 269.923 MiB) 1.19.975.729 I slot launch_slot_: id 0 | task 6346 | processing task, is_child = 0 1.20.562.261 I slot print_timing: id 0 | task 6346 | prompt eval time = 198.03 ms / 572 tokens ( 0.35 ms per token, 2888.41 tokens per second) 1.20.562.268 I slot print_timing: id 0 | task 6346 | eval time = 388.48 ms / 43 tokens ( 9.25 ms per token, 108.11 tokens per second) 1.20.562.269 I slot print_timing: id 0 | task 6346 | total time = 586.51 ms / 615 tokens 1.20.562.269 I slot print_timing: id 0 | task 6346 | graphs reused = 5877 1.20.562.270 I slot print_timing: id 0 | task 6346 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.562.307 I slot release: id 0 | task 6346 | stop processing: n_tokens = 646, truncated = 0 1.20.582.955 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 646, t_last = 80469659 1.20.583.000 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 267.015 MiB) 1.20.665.435 I slot launch_slot_: id 0 | task 6393 | processing task, is_child = 0 1.21.310.283 I slot print_timing: id 0 | task 6393 | prompt eval time = 200.90 ms / 613 tokens ( 0.33 ms per token, 3051.27 tokens per second) 1.21.310.289 I slot print_timing: id 0 | task 6393 | eval time = 443.93 ms / 49 tokens ( 9.25 ms per token, 108.13 tokens per second) 1.21.310.290 I slot print_timing: id 0 | task 6393 | total time = 644.83 ms / 662 tokens 1.21.310.290 I slot print_timing: id 0 | task 6393 | graphs reused = 5924 1.21.310.291 I slot print_timing: id 0 | task 6393 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.310.328 I slot release: id 0 | task 6393 | stop processing: n_tokens = 693, truncated = 0 1.21.314.878 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 81217680 1.21.314.926 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.486 MiB) 1.21.422.596 I slot launch_slot_: id 0 | task 6446 | processing task, is_child = 0 1.22.195.844 I slot print_timing: id 0 | task 6446 | prompt eval time = 194.26 ms / 580 tokens ( 0.33 ms per token, 2985.67 tokens per second) 1.22.195.850 I slot print_timing: id 0 | task 6446 | eval time = 578.97 ms / 64 tokens ( 9.19 ms per token, 108.81 tokens per second) 1.22.195.851 I slot print_timing: id 0 | task 6446 | total time = 773.23 ms / 644 tokens 1.22.195.852 I slot print_timing: id 0 | task 6446 | graphs reused = 5986 1.22.195.852 I slot print_timing: id 0 | task 6446 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.195.888 I slot release: id 0 | task 6446 | stop processing: n_tokens = 675, truncated = 0 1.22.220.378 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 675, t_last = 82103240 1.22.220.427 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.454 MiB) 1.22.324.295 I slot launch_slot_: id 0 | task 6514 | processing task, is_child = 0 1.23.002.639 I slot print_timing: id 0 | task 6514 | prompt eval time = 220.09 ms / 716 tokens ( 0.31 ms per token, 3253.24 tokens per second) 1.23.002.645 I slot print_timing: id 0 | task 6514 | eval time = 458.24 ms / 50 tokens ( 9.35 ms per token, 106.93 tokens per second) 1.23.002.646 I slot print_timing: id 0 | task 6514 | total time = 678.33 ms / 766 tokens 1.23.002.647 I slot print_timing: id 0 | task 6514 | graphs reused = 6033 1.23.002.647 I slot print_timing: id 0 | task 6514 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.002.690 I slot release: id 0 | task 6514 | stop processing: n_tokens = 797, truncated = 0 1.23.032.219 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 797, t_last = 82910043 1.23.032.274 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.234 MiB) 1.23.052.434 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.141 MiB) 1.23.154.599 I slot launch_slot_: id 0 | task 6568 | processing task, is_child = 0 1.24.324.213 I slot print_timing: id 0 | task 6568 | prompt eval time = 238.00 ms / 799 tokens ( 0.30 ms per token, 3357.20 tokens per second) 1.24.324.219 I slot print_timing: id 0 | task 6568 | eval time = 931.60 ms / 102 tokens ( 9.22 ms per token, 108.42 tokens per second) 1.24.324.220 I slot print_timing: id 0 | task 6568 | total time = 1169.60 ms / 901 tokens 1.24.324.221 I slot print_timing: id 0 | task 6568 | graphs reused = 6133 1.24.324.221 I slot print_timing: id 0 | task 6568 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.324.264 I slot release: id 0 | task 6568 | stop processing: n_tokens = 932, truncated = 0 1.24.338.481 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 932, t_last = 84231616 1.24.338.549 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.267 MiB) 1.24.426.666 I slot launch_slot_: id 0 | task 6674 | processing task, is_child = 0 1.25.594.635 I slot print_timing: id 0 | task 6674 | prompt eval time = 147.83 ms / 361 tokens ( 0.41 ms per token, 2441.99 tokens per second) 1.25.594.640 I slot print_timing: id 0 | task 6674 | eval time = 1020.12 ms / 112 tokens ( 9.19 ms per token, 108.81 tokens per second) 1.25.594.641 I slot print_timing: id 0 | task 6674 | total time = 1167.95 ms / 473 tokens 1.25.594.642 I slot print_timing: id 0 | task 6674 | graphs reused = 6243 1.25.594.643 I slot print_timing: id 0 | task 6674 | graph reallocs = 0 / 0 (same size) / (changed size) 1.25.594.675 I slot release: id 0 | task 6674 | stop processing: n_tokens = 504, truncated = 0 1.25.598.776 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 85502027 1.25.598.824 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.426 MiB) 1.25.689.155 I slot launch_slot_: id 0 | task 6789 | processing task, is_child = 0 1.26.840.133 I slot print_timing: id 0 | task 6789 | prompt eval time = 150.82 ms / 381 tokens ( 0.40 ms per token, 2526.16 tokens per second) 1.26.840.139 I slot print_timing: id 0 | task 6789 | eval time = 1000.13 ms / 108 tokens ( 9.35 ms per token, 106.99 tokens per second) 1.26.840.140 I slot print_timing: id 0 | task 6789 | total time = 1150.96 ms / 489 tokens 1.26.840.141 I slot print_timing: id 0 | task 6789 | graphs reused = 6348 1.26.840.142 I slot print_timing: id 0 | task 6789 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.840.176 I slot release: id 0 | task 6789 | stop processing: n_tokens = 520, truncated = 0 1.26.844.152 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 86747529 1.26.844.213 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 1.26.913.879 I slot launch_slot_: id 0 | task 6900 | processing task, is_child = 0 1.28.205.496 I slot print_timing: id 0 | task 6900 | prompt eval time = 148.35 ms / 365 tokens ( 0.41 ms per token, 2460.31 tokens per second) 1.28.205.502 I slot print_timing: id 0 | task 6900 | eval time = 1143.24 ms / 124 tokens ( 9.29 ms per token, 107.59 tokens per second) 1.28.205.504 I slot print_timing: id 0 | task 6900 | total time = 1291.59 ms / 489 tokens 1.28.205.504 I slot print_timing: id 0 | task 6900 | graphs reused = 6469 1.28.205.505 I slot print_timing: id 0 | task 6900 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.205.539 I slot release: id 0 | task 6900 | stop processing: n_tokens = 520, truncated = 0 1.28.223.604 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 88112892 1.28.223.653 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.026 MiB) 1.28.296.657 I slot launch_slot_: id 0 | task 7027 | processing task, is_child = 0 1.29.416.052 I slot print_timing: id 0 | task 7027 | prompt eval time = 144.57 ms / 333 tokens ( 0.43 ms per token, 2303.41 tokens per second) 1.29.416.058 I slot print_timing: id 0 | task 7027 | eval time = 974.81 ms / 107 tokens ( 9.20 ms per token, 108.74 tokens per second) 1.29.416.060 I slot print_timing: id 0 | task 7027 | total time = 1119.38 ms / 440 tokens 1.29.416.061 I slot print_timing: id 0 | task 7027 | graphs reused = 6574 1.29.416.061 I slot print_timing: id 0 | task 7027 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.416.090 I slot release: id 0 | task 7027 | stop processing: n_tokens = 471, truncated = 0 1.29.441.923 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 471, t_last = 89323442 1.29.496.903 I slot launch_slot_: id 0 | task 7137 | processing task, is_child = 0 1.31.073.461 I slot print_timing: id 0 | task 7137 | prompt eval time = 150.70 ms / 403 tokens ( 0.37 ms per token, 2674.22 tokens per second) 1.31.073.467 I slot print_timing: id 0 | task 7137 | eval time = 1425.84 ms / 156 tokens ( 9.20 ms per token, 108.71 tokens per second) 1.31.073.468 I slot print_timing: id 0 | task 7137 | total time = 1576.54 ms / 559 tokens 1.31.073.469 I slot print_timing: id 0 | task 7137 | graphs reused = 6727 1.31.073.469 I slot print_timing: id 0 | task 7137 | graph reallocs = 0 / 0 (same size) / (changed size) 1.31.073.500 I slot release: id 0 | task 7137 | stop processing: n_tokens = 590, truncated = 0 1.31.098.608 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 590, t_last = 90980853 1.31.098.653 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.172 MiB) 1.31.190.372 I slot launch_slot_: id 0 | task 7296 | processing task, is_child = 0 1.33.141.138 I slot print_timing: id 0 | task 7296 | prompt eval time = 151.42 ms / 411 tokens ( 0.37 ms per token, 2714.23 tokens per second) 1.33.141.143 I slot print_timing: id 0 | task 7296 | eval time = 1799.32 ms / 195 tokens ( 9.27 ms per token, 107.82 tokens per second) 1.33.141.144 I slot print_timing: id 0 | task 7296 | total time = 1950.75 ms / 606 tokens 1.33.141.145 I slot print_timing: id 0 | task 7296 | graphs reused = 6919 1.33.141.146 I slot print_timing: id 0 | task 7296 | graph reallocs = 0 / 0 (same size) / (changed size) 1.33.141.177 I slot release: id 0 | task 7296 | stop processing: n_tokens = 637, truncated = 0 1.33.160.067 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 93048529 1.33.160.122 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 375.146 MiB) 1.33.255.128 I slot launch_slot_: id 0 | task 7494 | processing task, is_child = 0 1.35.483.101 I slot print_timing: id 0 | task 7494 | prompt eval time = 175.56 ms / 490 tokens ( 0.36 ms per token, 2791.05 tokens per second) 1.35.483.107 I slot print_timing: id 0 | task 7494 | eval time = 2052.39 ms / 225 tokens ( 9.16 ms per token, 109.14 tokens per second) 1.35.483.108 I slot print_timing: id 0 | task 7494 | total time = 2227.95 ms / 715 tokens 1.35.483.109 I slot print_timing: id 0 | task 7494 | graphs reused = 7142 1.35.483.110 I slot print_timing: id 0 | task 7494 | graph reallocs = 0 / 0 (same size) / (changed size) 1.35.483.143 I slot release: id 0 | task 7494 | stop processing: n_tokens = 746, truncated = 0 1.35.508.292 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 746, t_last = 95390496 1.35.508.355 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.930 MiB) 1.35.609.022 I slot launch_slot_: id 0 | task 7722 | processing task, is_child = 0 1.38.754.938 I slot print_timing: id 0 | task 7722 | n_gen = 329, tg = 109.25 t/s, tg_3s = 109.59 t/s 1.39.427.164 I slot print_timing: id 0 | task 7722 | prompt eval time = 143.69 ms / 344 tokens ( 0.42 ms per token, 2394.09 tokens per second) 1.39.427.169 I slot print_timing: id 0 | task 7722 | eval time = 3674.43 ms / 402 tokens ( 9.16 ms per token, 109.13 tokens per second) 1.39.427.171 I slot print_timing: id 0 | task 7722 | total time = 3818.12 ms / 746 tokens 1.39.427.171 I slot print_timing: id 0 | task 7722 | graphs reused = 7540 1.39.427.172 I slot print_timing: id 0 | task 7722 | graph reallocs = 0 / 0 (same size) / (changed size) 1.39.427.201 I slot release: id 0 | task 7722 | stop processing: n_tokens = 777, truncated = 0 1.39.451.256 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 777, t_last = 99334554 1.39.451.312 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.891 MiB) 1.39.544.058 I slot launch_slot_: id 0 | task 8127 | processing task, is_child = 0 1.42.690.842 I slot print_timing: id 0 | task 8127 | prompt eval time = 144.67 ms / 347 tokens ( 0.42 ms per token, 2398.53 tokens per second) 1.42.690.847 I slot print_timing: id 0 | task 8127 | eval time = 3002.09 ms / 327 tokens ( 9.21 ms per token, 108.59 tokens per second) 1.42.690.849 I slot print_timing: id 0 | task 8127 | total time = 3146.76 ms / 674 tokens 1.42.690.850 I slot print_timing: id 0 | task 8127 | graphs reused = 7864 1.42.690.850 I slot print_timing: id 0 | task 8127 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.690.882 I slot release: id 0 | task 8127 | stop processing: n_tokens = 705, truncated = 0 1.42.715.701 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 705, t_last = 102598235 1.42.715.759 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 375.615 MiB) 1.42.791.668 I slot launch_slot_: id 0 | task 8457 | processing task, is_child = 0 1.44.092.271 I slot print_timing: id 0 | task 8457 | prompt eval time = 151.28 ms / 401 tokens ( 0.38 ms per token, 2650.63 tokens per second) 1.44.092.277 I slot print_timing: id 0 | task 8457 | eval time = 1149.30 ms / 126 tokens ( 9.19 ms per token, 108.76 tokens per second) 1.44.092.278 I slot print_timing: id 0 | task 8457 | total time = 1300.58 ms / 527 tokens 1.44.092.279 I slot print_timing: id 0 | task 8457 | graphs reused = 7987 1.44.092.280 I slot print_timing: id 0 | task 8457 | graph reallocs = 0 / 0 (same size) / (changed size) 1.44.092.309 I slot release: id 0 | task 8457 | stop processing: n_tokens = 558, truncated = 0 1.44.118.017 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 103999662 1.44.118.068 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.368 MiB) 1.44.211.880 I slot launch_slot_: id 0 | task 8586 | processing task, is_child = 0 1.46.288.030 I slot print_timing: id 0 | task 8586 | prompt eval time = 162.07 ms / 456 tokens ( 0.36 ms per token, 2813.55 tokens per second) 1.46.288.036 I slot print_timing: id 0 | task 8586 | eval time = 1914.06 ms / 205 tokens ( 9.38 ms per token, 106.58 tokens per second) 1.46.288.037 I slot print_timing: id 0 | task 8586 | total time = 2076.13 ms / 661 tokens 1.46.288.037 I slot print_timing: id 0 | task 8586 | graphs reused = 8189 1.46.288.038 I slot print_timing: id 0 | task 8586 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.288.072 I slot release: id 0 | task 8586 | stop processing: n_tokens = 692, truncated = 0 1.46.310.020 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.107 (> 0.100 thold), f_keep = 0.068 1.46.310.067 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 423.177 MiB) 1.46.405.077 I slot launch_slot_: id 0 | task 8794 | processing task, is_child = 0 1.47.586.577 I slot print_timing: id 0 | task 8794 | prompt eval time = 156.13 ms / 406 tokens ( 0.38 ms per token, 2600.41 tokens per second) 1.47.586.583 I slot print_timing: id 0 | task 8794 | eval time = 1025.35 ms / 112 tokens ( 9.24 ms per token, 108.26 tokens per second) 1.47.586.584 I slot print_timing: id 0 | task 8794 | total time = 1181.48 ms / 518 tokens 1.47.586.585 I slot print_timing: id 0 | task 8794 | graphs reused = 8298 1.47.586.586 I slot print_timing: id 0 | task 8794 | graph reallocs = 0 / 0 (same size) / (changed size) 1.47.586.618 I slot release: id 0 | task 8794 | stop processing: n_tokens = 549, truncated = 0 1.47.606.476 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 107493970 1.47.668.441 I slot launch_slot_: id 0 | task 8909 | processing task, is_child = 0 1.49.452.727 I slot print_timing: id 0 | task 8909 | prompt eval time = 151.52 ms / 406 tokens ( 0.37 ms per token, 2679.46 tokens per second) 1.49.452.732 I slot print_timing: id 0 | task 8909 | eval time = 1632.74 ms / 179 tokens ( 9.17 ms per token, 109.02 tokens per second) 1.49.452.733 I slot print_timing: id 0 | task 8909 | total time = 1784.27 ms / 585 tokens 1.49.452.734 I slot print_timing: id 0 | task 8909 | graphs reused = 8474 1.49.452.735 I slot print_timing: id 0 | task 8909 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.452.766 I slot release: id 0 | task 8909 | stop processing: n_tokens = 616, truncated = 0 1.49.473.653 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 616, t_last = 109360119 1.49.473.707 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 371.863 MiB) 1.49.571.729 I slot launch_slot_: id 0 | task 9091 | processing task, is_child = 0 1.51.041.307 I slot print_timing: id 0 | task 9091 | prompt eval time = 158.19 ms / 444 tokens ( 0.36 ms per token, 2806.80 tokens per second) 1.51.041.313 I slot print_timing: id 0 | task 9091 | eval time = 1311.37 ms / 144 tokens ( 9.17 ms per token, 109.05 tokens per second) 1.51.041.314 I slot print_timing: id 0 | task 9091 | total time = 1469.56 ms / 588 tokens 1.51.041.314 I slot print_timing: id 0 | task 9091 | graphs reused = 8615 1.51.041.315 I slot print_timing: id 0 | task 9091 | graph reallocs = 0 / 0 (same size) / (changed size) 1.51.041.348 I slot release: id 0 | task 9091 | stop processing: n_tokens = 619, truncated = 0 1.51.059.703 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 619, t_last = 110948701 1.51.059.766 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.672 MiB) 1.51.150.288 I slot launch_slot_: id 0 | task 9238 | processing task, is_child = 0 1.52.239.889 I slot print_timing: id 0 | task 9238 | prompt eval time = 147.96 ms / 372 tokens ( 0.40 ms per token, 2514.28 tokens per second) 1.52.239.895 I slot print_timing: id 0 | task 9238 | eval time = 941.63 ms / 103 tokens ( 9.23 ms per token, 108.32 tokens per second) 1.52.239.896 I slot print_timing: id 0 | task 9238 | total time = 1089.58 ms / 475 tokens 1.52.239.897 I slot print_timing: id 0 | task 9238 | graphs reused = 8716 1.52.239.897 I slot print_timing: id 0 | task 9238 | graph reallocs = 0 / 0 (same size) / (changed size) 1.52.239.930 I slot release: id 0 | task 9238 | stop processing: n_tokens = 506, truncated = 0 1.52.261.834 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 506, t_last = 112147283 1.52.261.889 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.736 MiB) 1.52.351.795 I slot launch_slot_: id 0 | task 9344 | processing task, is_child = 0 1.54.609.704 I slot print_timing: id 0 | task 9344 | prompt eval time = 156.35 ms / 454 tokens ( 0.34 ms per token, 2903.74 tokens per second) 1.54.609.711 I slot print_timing: id 0 | task 9344 | eval time = 2101.54 ms / 230 tokens ( 9.18 ms per token, 108.97 tokens per second) 1.54.609.712 I slot print_timing: id 0 | task 9344 | total time = 2257.89 ms / 684 tokens 1.54.609.713 I slot print_timing: id 0 | task 9344 | graphs reused = 8943 1.54.609.714 I slot print_timing: id 0 | task 9344 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.609.754 I slot release: id 0 | task 9344 | stop processing: n_tokens = 715, truncated = 0 1.54.635.749 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 715, t_last = 114517107 1.54.635.815 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.798 MiB) 1.54.722.903 I slot launch_slot_: id 0 | task 9577 | processing task, is_child = 0 1.56.931.945 I slot print_timing: id 0 | task 9577 | prompt eval time = 146.65 ms / 354 tokens ( 0.41 ms per token, 2413.91 tokens per second) 1.56.931.950 I slot print_timing: id 0 | task 9577 | eval time = 2062.37 ms / 226 tokens ( 9.17 ms per token, 109.10 tokens per second) 1.56.931.951 I slot print_timing: id 0 | task 9577 | total time = 2209.02 ms / 580 tokens 1.56.931.953 I slot print_timing: id 0 | task 9577 | graphs reused = 9166 1.56.931.954 I slot print_timing: id 0 | task 9577 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.931.982 I slot release: id 0 | task 9577 | stop processing: n_tokens = 611, truncated = 0 1.56.935.854 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 611, t_last = 116839335 1.56.935.906 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.583 MiB) 1.57.016.896 I slot launch_slot_: id 0 | task 9806 | processing task, is_child = 0 1.58.596.537 I slot print_timing: id 0 | task 9806 | prompt eval time = 141.30 ms / 334 tokens ( 0.42 ms per token, 2363.78 tokens per second) 1.58.596.542 I slot print_timing: id 0 | task 9806 | eval time = 1438.32 ms / 158 tokens ( 9.16 ms per token, 109.15 tokens per second) 1.58.596.543 I slot print_timing: id 0 | task 9806 | total time = 1579.62 ms / 492 tokens 1.58.596.544 I slot print_timing: id 0 | task 9806 | graphs reused = 9321 1.58.596.545 I slot print_timing: id 0 | task 9806 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.596.572 I slot release: id 0 | task 9806 | stop processing: n_tokens = 523, truncated = 0 1.58.610.823 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 523, t_last = 118503924 1.58.610.865 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 372.050 MiB) 1.58.704.988 I slot launch_slot_: id 0 | task 9967 | processing task, is_child = 0 2.00.605.340 I slot print_timing: id 0 | task 9967 | prompt eval time = 155.42 ms / 426 tokens ( 0.36 ms per token, 2740.94 tokens per second) 2.00.605.346 I slot print_timing: id 0 | task 9967 | eval time = 1744.91 ms / 191 tokens ( 9.18 ms per token, 108.89 tokens per second) 2.00.605.347 I slot print_timing: id 0 | task 9967 | total time = 1900.33 ms / 617 tokens 2.00.605.348 I slot print_timing: id 0 | task 9967 | graphs reused = 9509 2.00.605.349 I slot print_timing: id 0 | task 9967 | graph reallocs = 0 / 0 (same size) / (changed size) 2.00.605.378 I slot release: id 0 | task 9967 | stop processing: n_tokens = 648, truncated = 0 2.00.625.911 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 648, t_last = 120512731 2.00.625.967 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.055 MiB) 2.00.720.292 I slot launch_slot_: id 0 | task 10161 | processing task, is_child = 0 2.02.179.937 I slot print_timing: id 0 | task 10161 | prompt eval time = 147.64 ms / 366 tokens ( 0.40 ms per token, 2479.00 tokens per second) 2.02.179.943 I slot print_timing: id 0 | task 10161 | eval time = 1311.98 ms / 144 tokens ( 9.17 ms per token, 109.00 tokens per second) 2.02.179.944 I slot print_timing: id 0 | task 10161 | total time = 1459.62 ms / 510 tokens 2.02.179.944 I slot print_timing: id 0 | task 10161 | graphs reused = 9650 2.02.179.945 I slot print_timing: id 0 | task 10161 | graph reallocs = 0 / 0 (same size) / (changed size) 2.02.179.974 I slot release: id 0 | task 10161 | stop processing: n_tokens = 541, truncated = 0 2.02.204.040 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 541, t_last = 122087327 2.02.204.091 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 371.957 MiB) 2.02.302.334 I slot launch_slot_: id 0 | task 10308 | processing task, is_child = 0 2.05.471.670 I slot print_timing: id 0 | task 10308 | n_gen = 329, tg = 109.20 t/s, tg_3s = 109.53 t/s 2.06.613.873 I slot print_timing: id 0 | task 10308 | prompt eval time = 165.53 ms / 462 tokens ( 0.36 ms per token, 2791.03 tokens per second) 2.06.613.879 I slot print_timing: id 0 | task 10308 | eval time = 4145.99 ms / 454 tokens ( 9.15 ms per token, 109.26 tokens per second) 2.06.613.880 I slot print_timing: id 0 | task 10308 | total time = 4311.52 ms / 916 tokens 2.06.613.881 I slot print_timing: id 0 | task 10308 | graphs reused = 10100 2.06.613.882 I slot print_timing: id 0 | task 10308 | graph reallocs = 0 / 0 (same size) / (changed size) 2.06.613.914 I slot release: id 0 | task 10308 | stop processing: n_tokens = 947, truncated = 0 2.06.641.329 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 947, t_last = 126521267 2.06.641.397 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.426 MiB) 2.06.737.198 I slot launch_slot_: id 0 | task 10765 | processing task, is_child = 0 2.08.996.263 I slot print_timing: id 0 | task 10765 | prompt eval time = 152.53 ms / 396 tokens ( 0.39 ms per token, 2596.28 tokens per second) 2.08.996.269 I slot print_timing: id 0 | task 10765 | eval time = 2106.52 ms / 231 tokens ( 9.16 ms per token, 109.18 tokens per second) 2.08.996.271 I slot print_timing: id 0 | task 10765 | total time = 2259.04 ms / 627 tokens 2.08.996.272 I slot print_timing: id 0 | task 10765 | graphs reused = 10328 2.08.996.273 I slot print_timing: id 0 | task 10765 | graph reallocs = 0 / 0 (same size) / (changed size) 2.08.996.304 I slot release: id 0 | task 10765 | stop processing: n_tokens = 658, truncated = 0 2.09.021.959 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 658, t_last = 128903657 2.09.094.173 I slot launch_slot_: id 0 | task 10999 | processing task, is_child = 0 2.10.725.828 I slot print_timing: id 0 | task 10999 | prompt eval time = 159.71 ms / 458 tokens ( 0.35 ms per token, 2867.63 tokens per second) 2.10.725.834 I slot print_timing: id 0 | task 10999 | eval time = 1471.92 ms / 161 tokens ( 9.20 ms per token, 108.70 tokens per second) 2.10.725.835 I slot print_timing: id 0 | task 10999 | total time = 1631.64 ms / 619 tokens 2.10.725.836 I slot print_timing: id 0 | task 10999 | graphs reused = 10486 2.10.725.837 I slot print_timing: id 0 | task 10999 | graph reallocs = 0 / 0 (same size) / (changed size) 2.10.725.868 I slot release: id 0 | task 10999 | stop processing: n_tokens = 650, truncated = 0 2.10.729.761 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 650, t_last = 130633220 2.10.729.808 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 372.863 MiB) 2.10.824.141 I slot launch_slot_: id 0 | task 11163 | processing task, is_child = 0 2.12.131.151 I slot print_timing: id 0 | task 11163 | prompt eval time = 165.15 ms / 458 tokens ( 0.36 ms per token, 2773.19 tokens per second) 2.12.131.156 I slot print_timing: id 0 | task 11163 | eval time = 1141.84 ms / 125 tokens ( 9.21 ms per token, 108.60 tokens per second) 2.12.131.157 I slot print_timing: id 0 | task 11163 | total time = 1306.99 ms / 583 tokens 2.12.131.158 I slot print_timing: id 0 | task 11163 | graphs reused = 10608 2.12.131.159 I slot print_timing: id 0 | task 11163 | graph reallocs = 0 / 0 (same size) / (changed size) 2.12.131.191 I slot release: id 0 | task 11163 | stop processing: n_tokens = 614, truncated = 0 2.12.152.530 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 614, t_last = 132038544 2.12.152.583 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 376.679 MiB) 2.12.245.665 I slot launch_slot_: id 0 | task 11291 | processing task, is_child = 0 2.14.327.210 I slot print_timing: id 0 | task 11291 | prompt eval time = 161.59 ms / 452 tokens ( 0.36 ms per token, 2797.12 tokens per second) 2.14.327.216 I slot print_timing: id 0 | task 11291 | eval time = 1919.93 ms / 210 tokens ( 9.19 ms per token, 108.86 tokens per second) 2.14.327.217 I slot print_timing: id 0 | task 11291 | total time = 2081.53 ms / 662 tokens 2.14.327.218 I slot print_timing: id 0 | task 11291 | graphs reused = 10815 2.14.327.219 I slot print_timing: id 0 | task 11291 | graph reallocs = 0 / 0 (same size) / (changed size) 2.14.327.251 I slot release: id 0 | task 11291 | stop processing: n_tokens = 693, truncated = 0 2.14.346.665 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 134234604 2.14.346.723 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 380.901 MiB) 2.14.443.529 I slot launch_slot_: id 0 | task 11504 | processing task, is_child = 0 2.15.897.294 I slot print_timing: id 0 | task 11504 | prompt eval time = 155.05 ms / 404 tokens ( 0.38 ms per token, 2605.59 tokens per second) 2.15.897.299 I slot print_timing: id 0 | task 11504 | eval time = 1298.69 ms / 142 tokens ( 9.21 ms per token, 108.57 tokens per second) 2.15.897.301 I slot print_timing: id 0 | task 11504 | total time = 1453.74 ms / 546 tokens 2.15.897.302 I slot print_timing: id 0 | task 11504 | graphs reused = 10954 2.15.897.303 I slot print_timing: id 0 | task 11504 | graph reallocs = 0 / 0 (same size) / (changed size) 2.15.897.332 I slot release: id 0 | task 11504 | stop processing: n_tokens = 577, truncated = 0 2.15.920.152 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 577, t_last = 135804685 2.15.920.202 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.265 MiB) 2.16.001.709 I slot launch_slot_: id 0 | task 11649 | processing task, is_child = 0 2.17.107.138 I slot print_timing: id 0 | task 11649 | prompt eval time = 144.70 ms / 345 tokens ( 0.42 ms per token, 2384.19 tokens per second) 2.17.107.144 I slot print_timing: id 0 | task 11649 | eval time = 960.71 ms / 106 tokens ( 9.15 ms per token, 109.29 tokens per second) 2.17.107.145 I slot print_timing: id 0 | task 11649 | total time = 1105.41 ms / 451 tokens 2.17.107.146 I slot print_timing: id 0 | task 11649 | graphs reused = 11058 2.17.107.147 I slot print_timing: id 0 | task 11649 | graph reallocs = 0 / 0 (same size) / (changed size) 2.17.107.177 I slot release: id 0 | task 11649 | stop processing: n_tokens = 482, truncated = 0 2.17.134.767 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 482, t_last = 137014529 2.17.134.809 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.766 MiB) 2.17.196.472 I slot launch_slot_: id 0 | task 11758 | processing task, is_child = 0 2.18.459.261 I slot print_timing: id 0 | task 11758 | prompt eval time = 164.80 ms / 430 tokens ( 0.38 ms per token, 2609.21 tokens per second) 2.18.459.267 I slot print_timing: id 0 | task 11758 | eval time = 1097.97 ms / 120 tokens ( 9.23 ms per token, 108.38 tokens per second) 2.18.459.268 I slot print_timing: id 0 | task 11758 | total time = 1262.77 ms / 550 tokens 2.18.459.270 I slot print_timing: id 0 | task 11758 | graphs reused = 11175 2.18.459.271 I slot print_timing: id 0 | task 11758 | graph reallocs = 0 / 0 (same size) / (changed size) 2.18.459.300 I slot release: id 0 | task 11758 | stop processing: n_tokens = 581, truncated = 0 2.18.487.580 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 581, t_last = 138366653 2.18.487.634 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.766 MiB) 2.18.554.180 I slot launch_slot_: id 0 | task 11881 | processing task, is_child = 0 2.19.506.700 I slot print_timing: id 0 | task 11881 | prompt eval time = 139.21 ms / 316 tokens ( 0.44 ms per token, 2269.92 tokens per second) 2.19.506.706 I slot print_timing: id 0 | task 11881 | eval time = 813.29 ms / 85 tokens ( 9.68 ms per token, 103.28 tokens per second) 2.19.506.707 I slot print_timing: id 0 | task 11881 | total time = 952.50 ms / 401 tokens 2.19.506.708 I slot print_timing: id 0 | task 11881 | graphs reused = 11258 2.19.506.709 I slot print_timing: id 0 | task 11881 | graph reallocs = 0 / 0 (same size) / (changed size) 2.19.506.736 I slot release: id 0 | task 11881 | stop processing: n_tokens = 432, truncated = 0 2.19.526.364 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 432, t_last = 139414088 2.19.526.410 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.233 MiB) 2.19.616.891 I slot launch_slot_: id 0 | task 11969 | processing task, is_child = 0 2.20.738.553 I slot print_timing: id 0 | task 11969 | prompt eval time = 148.31 ms / 354 tokens ( 0.42 ms per token, 2386.86 tokens per second) 2.20.738.559 I slot print_timing: id 0 | task 11969 | eval time = 973.33 ms / 107 tokens ( 9.18 ms per token, 108.90 tokens per second) 2.20.738.560 I slot print_timing: id 0 | task 11969 | total time = 1121.64 ms / 461 tokens 2.20.738.561 I slot print_timing: id 0 | task 11969 | graphs reused = 11363 2.20.738.561 I slot print_timing: id 0 | task 11969 | graph reallocs = 0 / 0 (same size) / (changed size) 2.20.738.592 I slot release: id 0 | task 11969 | stop processing: n_tokens = 492, truncated = 0 2.20.765.112 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 492, t_last = 140645944 2.20.765.158 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.955 MiB) 2.20.858.466 I slot launch_slot_: id 0 | task 12079 | processing task, is_child = 0 2.21.924.683 I slot print_timing: id 0 | task 12079 | prompt eval time = 166.86 ms / 438 tokens ( 0.38 ms per token, 2624.91 tokens per second) 2.21.924.689 I slot print_timing: id 0 | task 12079 | eval time = 899.33 ms / 98 tokens ( 9.27 ms per token, 107.86 tokens per second) 2.21.924.690 I slot print_timing: id 0 | task 12079 | total time = 1066.20 ms / 536 tokens 2.21.924.691 I slot print_timing: id 0 | task 12079 | graphs reused = 11458 2.21.924.692 I slot print_timing: id 0 | task 12079 | graph reallocs = 0 / 0 (same size) / (changed size) 2.21.924.724 I slot release: id 0 | task 12079 | stop processing: n_tokens = 567, truncated = 0 2.21.953.243 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 567, t_last = 141832076 2.21.953.296 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.424 MiB) 2.22.046.453 I slot launch_slot_: id 0 | task 12180 | processing task, is_child = 0 2.22.854.865 I slot print_timing: id 0 | task 12180 | prompt eval time = 167.90 ms / 457 tokens ( 0.37 ms per token, 2721.79 tokens per second) 2.22.854.871 I slot print_timing: id 0 | task 12180 | eval time = 640.49 ms / 70 tokens ( 9.28 ms per token, 107.73 tokens per second) 2.22.854.872 I slot print_timing: id 0 | task 12180 | total time = 808.39 ms / 527 tokens 2.22.854.873 I slot print_timing: id 0 | task 12180 | graphs reused = 11525 2.22.854.873 I slot print_timing: id 0 | task 12180 | graph reallocs = 0 / 0 (same size) / (changed size) 2.22.854.904 I slot release: id 0 | task 12180 | stop processing: n_tokens = 558, truncated = 0 2.22.876.797 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 142762257 2.22.876.842 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 324.833 MiB) 2.22.972.229 I slot launch_slot_: id 0 | task 12253 | processing task, is_child = 0 2.24.042.258 I slot print_timing: id 0 | task 12253 | prompt eval time = 172.60 ms / 473 tokens ( 0.36 ms per token, 2740.44 tokens per second) 2.24.042.264 I slot print_timing: id 0 | task 12253 | eval time = 897.41 ms / 98 tokens ( 9.25 ms per token, 108.09 tokens per second) 2.24.042.265 I slot print_timing: id 0 | task 12253 | total time = 1070.01 ms / 571 tokens 2.24.042.266 I slot print_timing: id 0 | task 12253 | graphs reused = 11620 2.24.042.267 I slot print_timing: id 0 | task 12253 | graph reallocs = 0 / 0 (same size) / (changed size) 2.24.042.301 I slot release: id 0 | task 12253 | stop processing: n_tokens = 602, truncated = 0 2.24.062.409 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 602, t_last = 143949653 2.24.062.460 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.803 MiB) 2.24.160.692 I slot launch_slot_: id 0 | task 12354 | processing task, is_child = 0 2.24.961.548 I slot print_timing: id 0 | task 12354 | prompt eval time = 170.92 ms / 476 tokens ( 0.36 ms per token, 2784.88 tokens per second) 2.24.961.554 I slot print_timing: id 0 | task 12354 | eval time = 629.91 ms / 69 tokens ( 9.26 ms per token, 107.95 tokens per second) 2.24.961.555 I slot print_timing: id 0 | task 12354 | total time = 800.83 ms / 545 tokens 2.24.961.556 I slot print_timing: id 0 | task 12354 | graphs reused = 11686 2.24.961.557 I slot print_timing: id 0 | task 12354 | graph reallocs = 0 / 0 (same size) / (changed size) 2.24.961.591 I slot release: id 0 | task 12354 | stop processing: n_tokens = 576, truncated = 0 2.24.988.935 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 576, t_last = 144868944 2.24.988.989 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.551 MiB) 2.25.064.277 I slot launch_slot_: id 0 | task 12426 | processing task, is_child = 0 2.26.414.633 I slot print_timing: id 0 | task 12426 | prompt eval time = 179.43 ms / 466 tokens ( 0.39 ms per token, 2597.08 tokens per second) 2.26.414.639 I slot print_timing: id 0 | task 12426 | eval time = 1170.90 ms / 128 tokens ( 9.22 ms per token, 108.46 tokens per second) 2.26.414.640 I slot print_timing: id 0 | task 12426 | total time = 1350.34 ms / 594 tokens 2.26.414.641 I slot print_timing: id 0 | task 12426 | graphs reused = 11811 2.26.414.643 I slot print_timing: id 0 | task 12426 | graph reallocs = 0 / 0 (same size) / (changed size) 2.26.414.675 I slot release: id 0 | task 12426 | stop processing: n_tokens = 625, truncated = 0 2.26.441.724 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 625, t_last = 146322028 2.26.441.780 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.954 MiB) 2.26.534.129 I slot launch_slot_: id 0 | task 12557 | processing task, is_child = 0 2.27.400.261 I slot print_timing: id 0 | task 12557 | prompt eval time = 151.44 ms / 415 tokens ( 0.36 ms per token, 2740.40 tokens per second) 2.27.400.266 I slot print_timing: id 0 | task 12557 | eval time = 714.67 ms / 78 tokens ( 9.28 ms per token, 107.74 tokens per second) 2.27.400.267 I slot print_timing: id 0 | task 12557 | total time = 866.11 ms / 493 tokens 2.27.400.268 I slot print_timing: id 0 | task 12557 | graphs reused = 11886 2.27.400.269 I slot print_timing: id 0 | task 12557 | graph reallocs = 0 / 0 (same size) / (changed size) 2.27.400.300 I slot release: id 0 | task 12557 | stop processing: n_tokens = 524, truncated = 0 2.27.415.039 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 524, t_last = 147307652 2.27.415.089 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.145 MiB) 2.27.506.835 I slot launch_slot_: id 0 | task 12638 | processing task, is_child = 0 2.28.660.835 I slot print_timing: id 0 | task 12638 | prompt eval time = 146.46 ms / 352 tokens ( 0.42 ms per token, 2403.45 tokens per second) 2.28.660.841 I slot print_timing: id 0 | task 12638 | eval time = 1007.52 ms / 111 tokens ( 9.16 ms per token, 109.18 tokens per second) 2.28.660.842 I slot print_timing: id 0 | task 12638 | total time = 1153.98 ms / 463 tokens 2.28.660.843 I slot print_timing: id 0 | task 12638 | graphs reused = 11995 2.28.660.844 I slot print_timing: id 0 | task 12638 | graph reallocs = 0 / 0 (same size) / (changed size) 2.28.660.873 I slot release: id 0 | task 12638 | stop processing: n_tokens = 494, truncated = 0 2.28.676.614 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 494, t_last = 148568225 2.28.676.659 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 2.28.739.900 I slot launch_slot_: id 0 | task 12752 | processing task, is_child = 0 2.30.140.308 I slot print_timing: id 0 | task 12752 | prompt eval time = 188.03 ms / 550 tokens ( 0.34 ms per token, 2925.05 tokens per second) 2.30.140.315 I slot print_timing: id 0 | task 12752 | eval time = 1212.36 ms / 133 tokens ( 9.18 ms per token, 108.88 tokens per second) 2.30.140.316 I slot print_timing: id 0 | task 12752 | total time = 1400.39 ms / 683 tokens 2.30.140.318 I slot print_timing: id 0 | task 12752 | graphs reused = 12126 2.30.140.318 I slot print_timing: id 0 | task 12752 | graph reallocs = 0 / 0 (same size) / (changed size) 2.30.140.353 I slot release: id 0 | task 12752 | stop processing: n_tokens = 714, truncated = 0 2.30.157.294 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 714, t_last = 150047706 2.30.157.354 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.768 MiB) 2.30.270.773 I slot launch_slot_: id 0 | task 12889 | processing task, is_child = 0 2.32.965.880 I slot print_timing: id 0 | task 12889 | prompt eval time = 223.24 ms / 772 tokens ( 0.29 ms per token, 3458.18 tokens per second) 2.32.965.885 I slot print_timing: id 0 | task 12889 | eval time = 2471.85 ms / 269 tokens ( 9.22 ms per token, 108.42 tokens per second) 2.32.965.886 I slot print_timing: id 0 | task 12889 | total time = 2695.09 ms / 1041 tokens 2.32.965.888 I slot print_timing: id 0 | task 12889 | graphs reused = 12392 2.32.965.889 I slot print_timing: id 0 | task 12889 | graph reallocs = 0 / 0 (same size) / (changed size) 2.32.965.929 I slot release: id 0 | task 12889 | stop processing: n_tokens = 1072, truncated = 0 2.32.992.749 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1072, t_last = 152873281 2.32.992.824 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.862 MiB) 2.33.097.351 I slot launch_slot_: id 0 | task 13162 | processing task, is_child = 0 2.34.971.599 I slot print_timing: id 0 | task 13162 | prompt eval time = 217.67 ms / 683 tokens ( 0.32 ms per token, 3137.75 tokens per second) 2.34.971.605 I slot print_timing: id 0 | task 13162 | eval time = 1656.56 ms / 181 tokens ( 9.20 ms per token, 108.66 tokens per second) 2.34.971.606 I slot print_timing: id 0 | task 13162 | total time = 1874.23 ms / 864 tokens 2.34.971.607 I slot print_timing: id 0 | task 13162 | graphs reused = 12570 2.34.971.608 I slot print_timing: id 0 | task 13162 | graph reallocs = 0 / 0 (same size) / (changed size) 2.34.971.646 I slot release: id 0 | task 13162 | stop processing: n_tokens = 895, truncated = 0 2.34.992.094 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 895, t_last = 154878998 2.34.992.165 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.328 MiB) 2.35.093.115 I slot launch_slot_: id 0 | task 13347 | processing task, is_child = 0 2.37.283.497 I slot print_timing: id 0 | task 13347 | prompt eval time = 196.08 ms / 579 tokens ( 0.34 ms per token, 2952.92 tokens per second) 2.37.283.504 I slot print_timing: id 0 | task 13347 | eval time = 1994.29 ms / 218 tokens ( 9.19 ms per token, 108.81 tokens per second) 2.37.283.505 I slot print_timing: id 0 | task 13347 | total time = 2190.36 ms / 797 tokens 2.37.283.506 I slot print_timing: id 0 | task 13347 | graphs reused = 12785 2.37.283.507 I slot print_timing: id 0 | task 13347 | graph reallocs = 0 / 0 (same size) / (changed size) 2.37.283.544 I slot release: id 0 | task 13347 | stop processing: n_tokens = 828, truncated = 0 2.37.303.610 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 828, t_last = 157190896 2.37.303.675 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.864 MiB) 2.37.325.393 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.611 MiB) 2.37.411.867 I slot launch_slot_: id 0 | task 13569 | processing task, is_child = 0 2.38.562.643 I slot print_timing: id 0 | task 13569 | prompt eval time = 179.97 ms / 500 tokens ( 0.36 ms per token, 2778.19 tokens per second) 2.38.562.650 I slot print_timing: id 0 | task 13569 | eval time = 970.78 ms / 106 tokens ( 9.25 ms per token, 108.16 tokens per second) 2.38.562.651 I slot print_timing: id 0 | task 13569 | total time = 1150.75 ms / 606 tokens 2.38.562.652 I slot print_timing: id 0 | task 13569 | graphs reused = 12889 2.38.562.653 I slot print_timing: id 0 | task 13569 | graph reallocs = 0 / 0 (same size) / (changed size) 2.38.562.688 I slot release: id 0 | task 13569 | stop processing: n_tokens = 637, truncated = 0 2.38.585.152 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 158470040 2.38.585.209 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.859 MiB) 2.38.663.139 I slot launch_slot_: id 0 | task 13678 | processing task, is_child = 0 2.41.897.332 I slot print_timing: id 0 | task 13678 | n_gen = 328, tg = 108.93 t/s, tg_3s = 109.26 t/s 2.42.400.612 I slot print_timing: id 0 | task 13678 | prompt eval time = 232.15 ms / 776 tokens ( 0.30 ms per token, 3342.65 tokens per second) 2.42.400.618 I slot print_timing: id 0 | task 13678 | eval time = 3505.30 ms / 383 tokens ( 9.18 ms per token, 108.98 tokens per second) 2.42.400.619 I slot print_timing: id 0 | task 13678 | total time = 3737.45 ms / 1159 tokens 2.42.400.620 I slot print_timing: id 0 | task 13678 | graphs reused = 13269 2.42.400.621 I slot print_timing: id 0 | task 13678 | graph reallocs = 0 / 0 (same size) / (changed size) 2.42.400.661 I slot release: id 0 | task 13678 | stop processing: n_tokens = 1190, truncated = 0 2.42.419.587 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1190, t_last = 162308014 2.42.419.656 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.768 MiB) 2.42.521.718 I slot launch_slot_: id 0 | task 14065 | processing task, is_child = 0 2.44.496.641 I slot print_timing: id 0 | task 14065 | prompt eval time = 176.88 ms / 504 tokens ( 0.35 ms per token, 2849.32 tokens per second) 2.44.496.647 I slot print_timing: id 0 | task 14065 | eval time = 1798.02 ms / 197 tokens ( 9.17 ms per token, 109.01 tokens per second) 2.44.496.648 I slot print_timing: id 0 | task 14065 | total time = 1974.90 ms / 701 tokens 2.44.496.649 I slot print_timing: id 0 | task 14065 | graphs reused = 13464 2.44.496.651 I slot print_timing: id 0 | task 14065 | graph reallocs = 0 / 0 (same size) / (changed size) 2.44.496.685 I slot release: id 0 | task 14065 | stop processing: n_tokens = 732, truncated = 0 2.44.521.932 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 732, t_last = 164404038 2.44.521.987 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.422 MiB) 2.44.632.778 I slot launch_slot_: id 0 | task 14265 | processing task, is_child = 0 2.46.732.015 I slot print_timing: id 0 | task 14265 | prompt eval time = 204.31 ms / 633 tokens ( 0.32 ms per token, 3098.31 tokens per second) 2.46.732.021 I slot print_timing: id 0 | task 14265 | eval time = 1894.91 ms / 207 tokens ( 9.20 ms per token, 108.71 tokens per second) 2.46.732.022 I slot print_timing: id 0 | task 14265 | total time = 2099.22 ms / 840 tokens 2.46.732.022 I slot print_timing: id 0 | task 14265 | graphs reused = 13668 2.46.732.023 I slot print_timing: id 0 | task 14265 | graph reallocs = 0 / 0 (same size) / (changed size) 2.46.732.060 I slot release: id 0 | task 14265 | stop processing: n_tokens = 871, truncated = 0 2.46.748.995 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 871, t_last = 166639413 2.46.749.061 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.119 MiB) 2.46.853.954 I slot launch_slot_: id 0 | task 14476 | processing task, is_child = 0 2.48.233.755 I slot print_timing: id 0 | task 14476 | prompt eval time = 157.92 ms / 395 tokens ( 0.40 ms per token, 2501.27 tokens per second) 2.48.233.761 I slot print_timing: id 0 | task 14476 | eval time = 1221.86 ms / 134 tokens ( 9.19 ms per token, 108.85 tokens per second) 2.48.233.762 I slot print_timing: id 0 | task 14476 | total time = 1379.78 ms / 529 tokens 2.48.233.762 I slot print_timing: id 0 | task 14476 | graphs reused = 13799 2.48.233.763 I slot print_timing: id 0 | task 14476 | graph reallocs = 0 / 0 (same size) / (changed size) 2.48.233.793 I slot release: id 0 | task 14476 | stop processing: n_tokens = 560, truncated = 0 2.48.261.584 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 168141145 2.48.261.637 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 322.081 MiB) 2.48.354.764 I slot launch_slot_: id 0 | task 14613 | processing task, is_child = 0 2.50.460.527 I slot print_timing: id 0 | task 14613 | prompt eval time = 196.22 ms / 584 tokens ( 0.34 ms per token, 2976.18 tokens per second) 2.50.460.532 I slot print_timing: id 0 | task 14613 | eval time = 1909.52 ms / 209 tokens ( 9.18 ms per token, 108.93 tokens per second) 2.50.460.534 I slot print_timing: id 0 | task 14613 | total time = 2105.74 ms / 793 tokens 2.50.460.534 I slot print_timing: id 0 | task 14613 | graphs reused = 14005 2.50.460.535 I slot print_timing: id 0 | task 14613 | graph reallocs = 0 / 0 (same size) / (changed size) 2.50.460.571 I slot release: id 0 | task 14613 | stop processing: n_tokens = 824, truncated = 0 2.50.465.472 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 824, t_last = 170367924 2.50.465.535 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.831 MiB) 2.50.580.206 I slot launch_slot_: id 0 | task 14826 | processing task, is_child = 0 2.52.979.206 I slot print_timing: id 0 | task 14826 | prompt eval time = 219.64 ms / 695 tokens ( 0.32 ms per token, 3164.23 tokens per second) 2.52.979.212 I slot print_timing: id 0 | task 14826 | eval time = 2179.34 ms / 232 tokens ( 9.43 ms per token, 106.00 tokens per second) 2.52.979.213 I slot print_timing: id 0 | task 14826 | total time = 2398.98 ms / 927 tokens 2.52.979.214 I slot print_timing: id 0 | task 14826 | graphs reused = 14234 2.52.979.215 I slot print_timing: id 0 | task 14826 | graph reallocs = 0 / 0 (same size) / (changed size) 2.52.979.253 I slot release: id 0 | task 14826 | stop processing: n_tokens = 958, truncated = 0 2.52.996.191 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 958, t_last = 172886606 2.52.996.262 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.705 MiB) 2.53.099.253 I slot launch_slot_: id 0 | task 15062 | processing task, is_child = 0 2.55.092.462 I slot print_timing: id 0 | task 15062 | prompt eval time = 232.21 ms / 769 tokens ( 0.30 ms per token, 3311.71 tokens per second) 2.55.092.468 I slot print_timing: id 0 | task 15062 | eval time = 1760.98 ms / 191 tokens ( 9.27 ms per token, 107.89 tokens per second) 2.55.092.469 I slot print_timing: id 0 | task 15062 | total time = 1993.19 ms / 960 tokens 2.55.092.470 I slot print_timing: id 0 | task 15062 | graphs reused = 14423 2.55.092.471 I slot print_timing: id 0 | task 15062 | graph reallocs = 0 / 0 (same size) / (changed size) 2.55.092.512 I slot release: id 0 | task 15062 | stop processing: n_tokens = 991, truncated = 0 2.55.113.030 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 991, t_last = 174999864 2.55.113.091 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.176 MiB) 2.55.132.852 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.548 MiB) 2.55.240.088 I slot launch_slot_: id 0 | task 15257 | processing task, is_child = 0 2.56.594.718 I slot print_timing: id 0 | task 15257 | prompt eval time = 195.18 ms / 576 tokens ( 0.34 ms per token, 2951.15 tokens per second) 2.56.594.724 I slot print_timing: id 0 | task 15257 | eval time = 1159.43 ms / 124 tokens ( 9.43 ms per token, 106.09 tokens per second) 2.56.594.725 I slot print_timing: id 0 | task 15257 | total time = 1354.61 ms / 700 tokens 2.56.594.725 I slot print_timing: id 0 | task 15257 | graphs reused = 14545 2.56.594.726 I slot print_timing: id 0 | task 15257 | graph reallocs = 0 / 0 (same size) / (changed size) 2.56.594.765 I slot release: id 0 | task 15257 | stop processing: n_tokens = 731, truncated = 0 2.56.614.740 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 731, t_last = 176502117 2.56.614.792 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.577 MiB) 2.56.686.383 I slot launch_slot_: id 0 | task 15385 | processing task, is_child = 0 2.59.411.775 I slot print_timing: id 0 | task 15385 | prompt eval time = 211.14 ms / 655 tokens ( 0.32 ms per token, 3102.15 tokens per second) 2.59.411.781 I slot print_timing: id 0 | task 15385 | eval time = 2514.23 ms / 275 tokens ( 9.18 ms per token, 108.98 tokens per second) 2.59.411.782 I slot print_timing: id 0 | task 15385 | total time = 2725.37 ms / 930 tokens 2.59.411.783 I slot print_timing: id 0 | task 15385 | graphs reused = 14817 2.59.411.784 I slot print_timing: id 0 | task 15385 | graph reallocs = 0 / 0 (same size) / (changed size) 2.59.411.822 I slot release: id 0 | task 15385 | stop processing: n_tokens = 961, truncated = 0 2.59.435.001 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 961, t_last = 179319175 2.59.435.072 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.673 MiB) 2.59.508.708 I slot launch_slot_: id 0 | task 15664 | processing task, is_child = 0 3.00.818.888 I slot print_timing: id 0 | task 15664 | prompt eval time = 204.21 ms / 621 tokens ( 0.33 ms per token, 3040.96 tokens per second) 3.00.818.894 I slot print_timing: id 0 | task 15664 | eval time = 1105.95 ms / 121 tokens ( 9.22 ms per token, 108.50 tokens per second) 3.00.818.895 I slot print_timing: id 0 | task 15664 | total time = 1310.16 ms / 742 tokens 3.00.818.895 I slot print_timing: id 0 | task 15664 | graphs reused = 14935 3.00.818.896 I slot print_timing: id 0 | task 15664 | graph reallocs = 0 / 0 (same size) / (changed size) 3.00.818.933 I slot release: id 0 | task 15664 | stop processing: n_tokens = 773, truncated = 0 3.00.842.128 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 773, t_last = 180726286 3.00.842.190 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.014 MiB) 3.00.952.095 I slot launch_slot_: id 0 | task 15789 | processing task, is_child = 0 3.02.900.665 I slot print_timing: id 0 | task 15789 | prompt eval time = 225.10 ms / 767 tokens ( 0.29 ms per token, 3407.30 tokens per second) 3.02.900.671 I slot print_timing: id 0 | task 15789 | eval time = 1723.44 ms / 184 tokens ( 9.42 ms per token, 106.18 tokens per second) 3.02.900.672 I slot print_timing: id 0 | task 15789 | total time = 1948.55 ms / 951 tokens 3.02.900.673 I slot print_timing: id 0 | task 15789 | graphs reused = 15117 3.02.900.673 I slot print_timing: id 0 | task 15789 | graph reallocs = 0 / 0 (same size) / (changed size) 3.02.900.716 I slot release: id 0 | task 15789 | stop processing: n_tokens = 982, truncated = 0 3.02.921.301 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 982, t_last = 182808069 3.02.921.364 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.890 MiB) 3.03.025.596 I slot launch_slot_: id 0 | task 15977 | processing task, is_child = 0 3.05.176.989 I slot print_timing: id 0 | task 15977 | prompt eval time = 252.73 ms / 864 tokens ( 0.29 ms per token, 3418.64 tokens per second) 3.05.176.994 I slot print_timing: id 0 | task 15977 | eval time = 1898.64 ms / 203 tokens ( 9.40 ms per token, 106.39 tokens per second) 3.05.176.996 I slot print_timing: id 0 | task 15977 | total time = 2151.37 ms / 1067 tokens 3.05.176.996 I slot print_timing: id 0 | task 15977 | graphs reused = 15317 3.05.176.997 I slot print_timing: id 0 | task 15977 | graph reallocs = 0 / 0 (same size) / (changed size) 3.05.177.042 I slot release: id 0 | task 15977 | stop processing: n_tokens = 1098, truncated = 0 3.05.201.062 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1098, t_last = 185084395 3.05.201.142 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.235 MiB) 3.05.220.585 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.954 MiB) 3.05.331.101 I slot launch_slot_: id 0 | task 16184 | processing task, is_child = 0 3.07.391.592 I slot print_timing: id 0 | task 16184 | prompt eval time = 213.31 ms / 646 tokens ( 0.33 ms per token, 3028.50 tokens per second) 3.07.391.599 I slot print_timing: id 0 | task 16184 | eval time = 1847.16 ms / 202 tokens ( 9.19 ms per token, 108.82 tokens per second) 3.07.391.600 I slot print_timing: id 0 | task 16184 | total time = 2060.47 ms / 848 tokens 3.07.391.602 I slot print_timing: id 0 | task 16184 | graphs reused = 15516 3.07.391.602 I slot print_timing: id 0 | task 16184 | graph reallocs = 0 / 0 (same size) / (changed size) 3.07.391.646 I slot release: id 0 | task 16184 | stop processing: n_tokens = 879, truncated = 0 3.07.410.395 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 879, t_last = 187298998 3.07.410.462 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.330 MiB) 3.07.508.745 I slot launch_slot_: id 0 | task 16390 | processing task, is_child = 0 3.09.794.870 I slot print_timing: id 0 | task 16390 | prompt eval time = 219.09 ms / 720 tokens ( 0.30 ms per token, 3286.29 tokens per second) 3.09.794.876 I slot print_timing: id 0 | task 16390 | eval time = 2067.01 ms / 219 tokens ( 9.48 ms per token, 105.47 tokens per second) 3.09.794.877 I slot print_timing: id 0 | task 16390 | total time = 2286.10 ms / 939 tokens 3.09.794.878 I slot print_timing: id 0 | task 16390 | graphs reused = 15732 3.09.794.879 I slot print_timing: id 0 | task 16390 | graph reallocs = 0 / 0 (same size) / (changed size) 3.09.794.921 I slot release: id 0 | task 16390 | stop processing: n_tokens = 970, truncated = 0 3.09.799.243 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 970, t_last = 189702273 3.09.799.317 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.517 MiB) 3.09.887.231 I slot launch_slot_: id 0 | task 16613 | processing task, is_child = 0 3.12.027.048 I slot print_timing: id 0 | task 16613 | prompt eval time = 177.87 ms / 509 tokens ( 0.35 ms per token, 2861.67 tokens per second) 3.12.027.053 I slot print_timing: id 0 | task 16613 | eval time = 1961.93 ms / 214 tokens ( 9.21 ms per token, 108.57 tokens per second) 3.12.027.055 I slot print_timing: id 0 | task 16613 | total time = 2139.80 ms / 723 tokens 3.12.027.055 I slot print_timing: id 0 | task 16613 | graphs reused = 15944 3.12.027.056 I slot print_timing: id 0 | task 16613 | graph reallocs = 0 / 0 (same size) / (changed size) 3.12.027.089 I slot release: id 0 | task 16613 | stop processing: n_tokens = 754, truncated = 0 3.12.044.282 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 754, t_last = 191934441 3.12.044.342 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.049 MiB) 3.12.138.672 I slot launch_slot_: id 0 | task 16830 | processing task, is_child = 0 3.14.543.954 I slot print_timing: id 0 | task 16830 | prompt eval time = 194.25 ms / 581 tokens ( 0.33 ms per token, 2991.04 tokens per second) 3.14.543.960 I slot print_timing: id 0 | task 16830 | eval time = 2211.02 ms / 242 tokens ( 9.17 ms per token, 109.00 tokens per second) 3.14.543.961 I slot print_timing: id 0 | task 16830 | total time = 2405.26 ms / 823 tokens 3.14.543.961 I slot print_timing: id 0 | task 16830 | graphs reused = 16183 3.14.543.962 I slot print_timing: id 0 | task 16830 | graph reallocs = 0 / 0 (same size) / (changed size) 3.14.544.000 I slot release: id 0 | task 16830 | stop processing: n_tokens = 854, truncated = 0 3.14.561.440 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 854, t_last = 194451352 3.14.561.509 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.891 MiB) 3.14.665.461 I slot launch_slot_: id 0 | task 17076 | processing task, is_child = 0 3.16.940.261 I slot print_timing: id 0 | task 17076 | prompt eval time = 260.28 ms / 925 tokens ( 0.28 ms per token, 3553.81 tokens per second) 3.16.940.266 I slot print_timing: id 0 | task 17076 | eval time = 2014.49 ms / 220 tokens ( 9.20 ms per token, 108.71 tokens per second) 3.16.940.267 I slot print_timing: id 0 | task 17076 | total time = 2274.78 ms / 1145 tokens 3.16.940.268 I slot print_timing: id 0 | task 17076 | graphs reused = 16400 3.16.940.269 I slot print_timing: id 0 | task 17076 | graph reallocs = 0 / 0 (same size) / (changed size) 3.16.940.316 I slot release: id 0 | task 17076 | stop processing: n_tokens = 1176, truncated = 0 3.16.969.814 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1176, t_last = 196847669 3.16.969.886 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.952 MiB) 3.17.048.460 I slot launch_slot_: id 0 | task 17300 | processing task, is_child = 0 3.19.578.633 I slot print_timing: id 0 | task 17300 | prompt eval time = 247.61 ms / 885 tokens ( 0.28 ms per token, 3574.15 tokens per second) 3.19.578.639 I slot print_timing: id 0 | task 17300 | eval time = 2282.54 ms / 245 tokens ( 9.35 ms per token, 106.90 tokens per second) 3.19.578.640 I slot print_timing: id 0 | task 17300 | total time = 2530.15 ms / 1130 tokens 3.19.578.641 I slot print_timing: id 0 | task 17300 | graphs reused = 16642 3.19.578.642 I slot print_timing: id 0 | task 17300 | graph reallocs = 0 / 0 (same size) / (changed size) 3.19.578.688 I slot release: id 0 | task 17300 | stop processing: n_tokens = 1161, truncated = 0 3.19.582.774 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1161, t_last = 199486040 3.19.582.852 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.083 MiB) 3.19.701.036 I slot launch_slot_: id 0 | task 17549 | processing task, is_child = 0 3.21.516.247 I slot print_timing: id 0 | task 17549 | prompt eval time = 152.67 ms / 392 tokens ( 0.39 ms per token, 2567.58 tokens per second) 3.21.516.253 I slot print_timing: id 0 | task 17549 | eval time = 1662.52 ms / 182 tokens ( 9.19 ms per token, 108.87 tokens per second) 3.21.516.254 I slot print_timing: id 0 | task 17549 | total time = 1815.19 ms / 574 tokens 3.21.516.255 I slot print_timing: id 0 | task 17549 | graphs reused = 16821 3.21.516.256 I slot print_timing: id 0 | task 17549 | graph reallocs = 0 / 0 (same size) / (changed size) 3.21.516.286 I slot release: id 0 | task 17549 | stop processing: n_tokens = 605, truncated = 0 3.21.538.443 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 605, t_last = 201423639 3.21.538.498 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 385.279 MiB) 3.21.634.464 I slot launch_slot_: id 0 | task 17734 | processing task, is_child = 0 3.22.679.017 I slot print_timing: id 0 | task 17734 | prompt eval time = 144.30 ms / 331 tokens ( 0.44 ms per token, 2293.82 tokens per second) 3.22.679.023 I slot print_timing: id 0 | task 17734 | eval time = 900.23 ms / 99 tokens ( 9.19 ms per token, 108.86 tokens per second) 3.22.679.024 I slot print_timing: id 0 | task 17734 | total time = 1044.53 ms / 430 tokens 3.22.679.025 I slot print_timing: id 0 | task 17734 | graphs reused = 16918 3.22.679.025 I slot print_timing: id 0 | task 17734 | graph reallocs = 0 / 0 (same size) / (changed size) 3.22.679.053 I slot release: id 0 | task 17734 | stop processing: n_tokens = 461, truncated = 0 3.22.694.178 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 461, t_last = 202586405 3.22.694.216 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.743 MiB) 3.22.775.392 I slot launch_slot_: id 0 | task 17836 | processing task, is_child = 0 3.24.600.432 I slot print_timing: id 0 | task 17836 | prompt eval time = 144.62 ms / 357 tokens ( 0.41 ms per token, 2468.61 tokens per second) 3.24.600.438 I slot print_timing: id 0 | task 17836 | eval time = 1680.40 ms / 184 tokens ( 9.18 ms per token, 108.90 tokens per second) 3.24.600.439 I slot print_timing: id 0 | task 17836 | total time = 1825.02 ms / 541 tokens 3.24.600.440 I slot print_timing: id 0 | task 17836 | graphs reused = 17099 3.24.600.441 I slot print_timing: id 0 | task 17836 | graph reallocs = 0 / 0 (same size) / (changed size) 3.24.600.471 I slot release: id 0 | task 17836 | stop processing: n_tokens = 572, truncated = 0 3.24.621.865 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 572, t_last = 204507824 3.24.621.912 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 377.648 MiB) 3.24.694.952 I slot launch_slot_: id 0 | task 18023 | processing task, is_child = 0 3.25.544.966 I slot print_timing: id 0 | task 18023 | prompt eval time = 144.21 ms / 315 tokens ( 0.46 ms per token, 2184.34 tokens per second) 3.25.544.972 I slot print_timing: id 0 | task 18023 | eval time = 705.79 ms / 78 tokens ( 9.17 ms per token, 109.10 tokens per second) 3.25.544.973 I slot print_timing: id 0 | task 18023 | total time = 850.00 ms / 393 tokens 3.25.544.974 I slot print_timing: id 0 | task 18023 | graphs reused = 17175 3.25.544.975 I slot print_timing: id 0 | task 18023 | graph reallocs = 0 / 0 (same size) / (changed size) 3.25.545.003 I slot release: id 0 | task 18023 | stop processing: n_tokens = 424, truncated = 0 3.25.569.926 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 205452355 3.25.569.971 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.424 MiB) 3.25.666.722 I slot launch_slot_: id 0 | task 18104 | processing task, is_child = 0 3.26.558.867 I slot print_timing: id 0 | task 18104 | prompt eval time = 146.73 ms / 378 tokens ( 0.39 ms per token, 2576.20 tokens per second) 3.26.558.873 I slot print_timing: id 0 | task 18104 | eval time = 745.40 ms / 82 tokens ( 9.20 ms per token, 108.67 tokens per second) 3.26.558.874 I slot print_timing: id 0 | task 18104 | total time = 892.13 ms / 460 tokens 3.26.558.875 I slot print_timing: id 0 | task 18104 | graphs reused = 17255 3.26.558.875 I slot print_timing: id 0 | task 18104 | graph reallocs = 0 / 0 (same size) / (changed size) 3.26.558.906 I slot release: id 0 | task 18104 | stop processing: n_tokens = 491, truncated = 0 3.26.562.626 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 491, t_last = 206466258 3.26.562.667 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.969 MiB) 3.26.666.035 I slot launch_slot_: id 0 | task 18189 | processing task, is_child = 0 3.28.684.848 I slot print_timing: id 0 | task 18189 | prompt eval time = 136.78 ms / 295 tokens ( 0.46 ms per token, 2156.68 tokens per second) 3.28.684.854 I slot print_timing: id 0 | task 18189 | eval time = 1882.01 ms / 206 tokens ( 9.18 ms per token, 108.93 tokens per second) 3.28.684.855 I slot print_timing: id 0 | task 18189 | total time = 2018.79 ms / 501 tokens 3.28.684.856 I slot print_timing: id 0 | task 18189 | graphs reused = 17458 3.28.684.857 I slot print_timing: id 0 | task 18189 | graph reallocs = 0 / 0 (same size) / (changed size) 3.28.684.884 I slot release: id 0 | task 18189 | stop processing: n_tokens = 532, truncated = 0 3.28.706.929 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 532, t_last = 208592237 3.28.706.980 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 324.395 MiB) 3.28.802.513 I slot launch_slot_: id 0 | task 18398 | processing task, is_child = 0 3.31.947.533 I slot print_timing: id 0 | task 18398 | n_gen = 328, tg = 108.89 t/s, tg_3s = 109.22 t/s 3.33.425.894 I slot print_timing: id 0 | task 18398 | prompt eval time = 141.91 ms / 337 tokens ( 0.42 ms per token, 2374.79 tokens per second) 3.33.425.899 I slot print_timing: id 0 | task 18398 | eval time = 4481.45 ms / 489 tokens ( 9.18 ms per token, 108.89 tokens per second) 3.33.425.900 I slot print_timing: id 0 | task 18398 | total time = 4623.36 ms / 826 tokens 3.33.425.901 I slot print_timing: id 0 | task 18398 | graphs reused = 17943 3.33.425.902 I slot print_timing: id 0 | task 18398 | graph reallocs = 0 / 0 (same size) / (changed size) 3.33.425.930 I slot release: id 0 | task 18398 | stop processing: n_tokens = 857, truncated = 0 3.33.440.979 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 857, t_last = 213333282 3.33.441.036 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.993 MiB) 3.33.549.512 I slot launch_slot_: id 0 | task 18890 | processing task, is_child = 0 3.34.717.543 I slot print_timing: id 0 | task 18890 | prompt eval time = 141.86 ms / 325 tokens ( 0.44 ms per token, 2291.04 tokens per second) 3.34.717.549 I slot print_timing: id 0 | task 18890 | eval time = 1026.15 ms / 113 tokens ( 9.16 ms per token, 109.15 tokens per second) 3.34.717.550 I slot print_timing: id 0 | task 18890 | total time = 1168.01 ms / 438 tokens 3.34.717.552 I slot print_timing: id 0 | task 18890 | graphs reused = 18054 3.34.717.553 I slot print_timing: id 0 | task 18890 | graph reallocs = 0 / 0 (same size) / (changed size) 3.34.717.582 I slot release: id 0 | task 18890 | stop processing: n_tokens = 469, truncated = 0 3.34.736.247 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.108 (> 0.100 thold), f_keep = 0.068 3.34.802.613 I slot launch_slot_: id 0 | task 19006 | processing task, is_child = 0 3.35.892.272 I slot print_timing: id 0 | task 19006 | prompt eval time = 128.40 ms / 264 tokens ( 0.49 ms per token, 2056.03 tokens per second) 3.35.892.277 I slot print_timing: id 0 | task 19006 | eval time = 961.24 ms / 106 tokens ( 9.15 ms per token, 109.23 tokens per second) 3.35.892.278 I slot print_timing: id 0 | task 19006 | total time = 1089.64 ms / 370 tokens 3.35.892.279 I slot print_timing: id 0 | task 19006 | graphs reused = 18158 3.35.892.280 I slot print_timing: id 0 | task 19006 | graph reallocs = 0 / 0 (same size) / (changed size) 3.35.892.305 I slot release: id 0 | task 19006 | stop processing: n_tokens = 401, truncated = 0 3.35.920.317 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 401, t_last = 215799658 3.35.920.360 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.016 MiB) 3.36.001.537 I slot launch_slot_: id 0 | task 19115 | processing task, is_child = 0 3.36.336.293 I slot print_timing: id 0 | task 19115 | prompt eval time = 145.97 ms / 331 tokens ( 0.44 ms per token, 2267.59 tokens per second) 3.36.336.299 I slot print_timing: id 0 | task 19115 | eval time = 188.76 ms / 21 tokens ( 9.44 ms per token, 105.95 tokens per second) 3.36.336.300 I slot print_timing: id 0 | task 19115 | total time = 334.74 ms / 352 tokens 3.36.336.301 I slot print_timing: id 0 | task 19115 | graphs reused = 18177 3.36.336.302 I slot print_timing: id 0 | task 19115 | graph reallocs = 0 / 0 (same size) / (changed size) 3.36.336.330 I slot release: id 0 | task 19115 | stop processing: n_tokens = 383, truncated = 0 3.36.361.237 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 383, t_last = 216243682 3.36.361.279 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 377.523 MiB) 3.36.462.443 I slot launch_slot_: id 0 | task 19139 | processing task, is_child = 0 3.38.111.727 I slot print_timing: id 0 | task 19139 | prompt eval time = 140.95 ms / 333 tokens ( 0.42 ms per token, 2362.57 tokens per second) 3.38.111.732 I slot print_timing: id 0 | task 19139 | eval time = 1508.32 ms / 165 tokens ( 9.20 ms per token, 108.73 tokens per second) 3.38.111.733 I slot print_timing: id 0 | task 19139 | total time = 1649.26 ms / 498 tokens 3.38.111.734 I slot print_timing: id 0 | task 19139 | graphs reused = 18339 3.38.111.735 I slot print_timing: id 0 | task 19139 | graph reallocs = 0 / 0 (same size) / (changed size) 3.38.111.761 I slot release: id 0 | task 19139 | stop processing: n_tokens = 529, truncated = 0 3.38.138.627 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 529, t_last = 218019114 3.38.138.677 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.714 MiB) 3.38.231.152 I slot launch_slot_: id 0 | task 19307 | processing task, is_child = 0 3.38.853.111 I slot print_timing: id 0 | task 19307 | prompt eval time = 144.08 ms / 346 tokens ( 0.42 ms per token, 2401.43 tokens per second) 3.38.853.116 I slot print_timing: id 0 | task 19307 | eval time = 477.86 ms / 53 tokens ( 9.19 ms per token, 108.82 tokens per second) 3.38.853.117 I slot print_timing: id 0 | task 19307 | total time = 621.94 ms / 399 tokens 3.38.853.118 I slot print_timing: id 0 | task 19307 | graphs reused = 18390 3.38.853.119 I slot print_timing: id 0 | task 19307 | graph reallocs = 0 / 0 (same size) / (changed size) 3.38.853.148 I slot release: id 0 | task 19307 | stop processing: n_tokens = 430, truncated = 0 3.38.871.428 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 430, t_last = 218760500 3.38.871.468 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.746 MiB) 3.38.965.571 I slot launch_slot_: id 0 | task 19363 | processing task, is_child = 0 3.39.474.828 I slot print_timing: id 0 | task 19363 | prompt eval time = 148.94 ms / 325 tokens ( 0.46 ms per token, 2182.13 tokens per second) 3.39.474.834 I slot print_timing: id 0 | task 19363 | eval time = 360.30 ms / 40 tokens ( 9.24 ms per token, 108.24 tokens per second) 3.39.474.835 I slot print_timing: id 0 | task 19363 | total time = 509.24 ms / 365 tokens 3.39.474.836 I slot print_timing: id 0 | task 19363 | graphs reused = 18428 3.39.474.837 I slot print_timing: id 0 | task 19363 | graph reallocs = 0 / 0 (same size) / (changed size) 3.39.474.865 I slot release: id 0 | task 19363 | stop processing: n_tokens = 396, truncated = 0 3.39.494.558 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 396, t_last = 219382218 3.39.494.601 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.615 MiB) 3.39.562.142 I slot launch_slot_: id 0 | task 19406 | processing task, is_child = 0 3.42.710.270 I slot print_timing: id 0 | task 19406 | n_gen = 330, tg = 109.43 t/s, tg_3s = 109.77 t/s 3.42.874.458 I slot print_timing: id 0 | task 19406 | prompt eval time = 141.71 ms / 322 tokens ( 0.44 ms per token, 2272.33 tokens per second) 3.42.874.464 I slot print_timing: id 0 | task 19406 | eval time = 3170.59 ms / 348 tokens ( 9.14 ms per token, 109.44 tokens per second) 3.42.874.465 I slot print_timing: id 0 | task 19406 | total time = 3312.30 ms / 670 tokens 3.42.874.466 I slot print_timing: id 0 | task 19406 | graphs reused = 18773 3.42.874.467 I slot print_timing: id 0 | task 19406 | graph reallocs = 0 / 0 (same size) / (changed size) 3.42.874.498 I slot release: id 0 | task 19406 | stop processing: n_tokens = 701, truncated = 0 3.42.896.893 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 701, t_last = 222781851 3.42.896.944 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.807 MiB) 3.42.975.861 I slot launch_slot_: id 0 | task 19757 | processing task, is_child = 0 3.46.125.424 I slot print_timing: id 0 | task 19757 | n_gen = 330, tg = 109.40 t/s, tg_3s = 109.73 t/s 3.47.648.987 I slot print_timing: id 0 | task 19757 | prompt eval time = 142.13 ms / 338 tokens ( 0.42 ms per token, 2378.12 tokens per second) 3.47.648.993 I slot print_timing: id 0 | task 19757 | eval time = 4530.97 ms / 496 tokens ( 9.15 ms per token, 109.25 tokens per second) 3.47.648.994 I slot print_timing: id 0 | task 19757 | total time = 4673.10 ms / 834 tokens 3.47.648.994 I slot print_timing: id 0 | task 19757 | graphs reused = 19265 3.47.648.995 I slot print_timing: id 0 | task 19757 | graph reallocs = 0 / 0 (same size) / (changed size) 3.47.649.023 I slot release: id 0 | task 19757 | stop processing: n_tokens = 865, truncated = 0 3.47.670.331 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 865, t_last = 227556376 3.47.733.555 I slot launch_slot_: id 0 | task 20256 | processing task, is_child = 0 3.50.884.840 I slot print_timing: id 0 | task 20256 | n_gen = 327, tg = 108.37 t/s, tg_3s = 108.70 t/s 3.52.890.886 I slot print_timing: id 0 | task 20256 | prompt eval time = 142.96 ms / 347 tokens ( 0.41 ms per token, 2427.27 tokens per second) 3.52.890.891 I slot print_timing: id 0 | task 20256 | eval time = 5014.35 ms / 546 tokens ( 9.20 ms per token, 108.69 tokens per second) 3.52.890.892 I slot print_timing: id 0 | task 20256 | total time = 5157.31 ms / 893 tokens 3.52.890.893 I slot print_timing: id 0 | task 20256 | graphs reused = 19807 3.52.890.894 I slot print_timing: id 0 | task 20256 | graph reallocs = 0 / 0 (same size) / (changed size) 3.52.890.924 I slot release: id 0 | task 20256 | stop processing: n_tokens = 924, truncated = 0 3.52.916.996 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 924, t_last = 232798276 3.52.917.064 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 375.928 MiB) 3.53.004.529 I slot launch_slot_: id 0 | task 20805 | processing task, is_child = 0 3.55.883.509 I slot print_timing: id 0 | task 20805 | prompt eval time = 142.67 ms / 331 tokens ( 0.43 ms per token, 2320.07 tokens per second) 3.55.883.515 I slot print_timing: id 0 | task 20805 | eval time = 2736.29 ms / 299 tokens ( 9.18 ms per token, 108.91 tokens per second) 3.55.883.516 I slot print_timing: id 0 | task 20805 | total time = 2878.96 ms / 630 tokens 3.55.883.517 I slot print_timing: id 0 | task 20805 | graphs reused = 20103 3.55.883.517 I slot print_timing: id 0 | task 20805 | graph reallocs = 0 / 0 (same size) / (changed size) 3.55.883.544 I slot release: id 0 | task 20805 | stop processing: n_tokens = 661, truncated = 0 3.55.900.713 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 661, t_last = 235790897 3.55.900.767 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.464 MiB) 3.55.990.848 I slot launch_slot_: id 0 | task 21107 | processing task, is_child = 0 3.57.130.188 I slot print_timing: id 0 | task 21107 | prompt eval time = 142.06 ms / 345 tokens ( 0.41 ms per token, 2428.50 tokens per second) 3.57.130.194 I slot print_timing: id 0 | task 21107 | eval time = 997.26 ms / 110 tokens ( 9.15 ms per token, 109.30 tokens per second) 3.57.130.195 I slot print_timing: id 0 | task 21107 | total time = 1139.32 ms / 455 tokens 3.57.130.196 I slot print_timing: id 0 | task 21107 | graphs reused = 20211 3.57.130.197 I slot print_timing: id 0 | task 21107 | graph reallocs = 0 / 0 (same size) / (changed size) 3.57.130.226 I slot release: id 0 | task 21107 | stop processing: n_tokens = 486, truncated = 0 3.57.154.304 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 486, t_last = 237037579 3.57.154.353 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.092 MiB) 3.57.247.647 I slot launch_slot_: id 0 | task 21220 | processing task, is_child = 0 3.57.974.890 I slot print_timing: id 0 | task 21220 | prompt eval time = 140.37 ms / 320 tokens ( 0.44 ms per token, 2279.71 tokens per second) 3.57.974.896 I slot print_timing: id 0 | task 21220 | eval time = 586.86 ms / 65 tokens ( 9.17 ms per token, 109.06 tokens per second) 3.57.974.897 I slot print_timing: id 0 | task 21220 | total time = 727.23 ms / 385 tokens 3.57.974.898 I slot print_timing: id 0 | task 21220 | graphs reused = 20274 3.57.974.899 I slot print_timing: id 0 | task 21220 | graph reallocs = 0 / 0 (same size) / (changed size) 3.57.974.926 I slot release: id 0 | task 21220 | stop processing: n_tokens = 416, truncated = 0 3.57.997.615 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 237882279 3.57.997.659 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.243 MiB) 3.58.087.591 I slot launch_slot_: id 0 | task 21288 | processing task, is_child = 0 3.58.529.357 I slot print_timing: id 0 | task 21288 | prompt eval time = 136.55 ms / 297 tokens ( 0.46 ms per token, 2175.06 tokens per second) 3.58.529.362 I slot print_timing: id 0 | task 21288 | eval time = 305.20 ms / 34 tokens ( 9.25 ms per token, 108.13 tokens per second) 3.58.529.363 I slot print_timing: id 0 | task 21288 | total time = 441.75 ms / 331 tokens 3.58.529.365 I slot print_timing: id 0 | task 21288 | graphs reused = 20306 3.58.529.365 I slot print_timing: id 0 | task 21288 | graph reallocs = 0 / 0 (same size) / (changed size) 3.58.529.391 I slot release: id 0 | task 21288 | stop processing: n_tokens = 362, truncated = 0 3.58.533.124 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 362, t_last = 238436744 3.58.533.165 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.089 MiB) 3.58.605.241 I slot launch_slot_: id 0 | task 21325 | processing task, is_child = 0 4.00.263.415 I slot print_timing: id 0 | task 21325 | prompt eval time = 142.60 ms / 343 tokens ( 0.42 ms per token, 2405.38 tokens per second) 4.00.263.421 I slot print_timing: id 0 | task 21325 | eval time = 1515.56 ms / 166 tokens ( 9.19 ms per token, 108.87 tokens per second) 4.00.263.422 I slot print_timing: id 0 | task 21325 | total time = 1658.15 ms / 509 tokens 4.00.263.422 I slot print_timing: id 0 | task 21325 | graphs reused = 20469 4.00.263.423 I slot print_timing: id 0 | task 21325 | graph reallocs = 0 / 0 (same size) / (changed size) 4.00.263.452 I slot release: id 0 | task 21325 | stop processing: n_tokens = 540, truncated = 0 4.00.292.007 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 540, t_last = 240170805 4.00.347.254 I slot launch_slot_: id 0 | task 21494 | processing task, is_child = 0 4.01.520.725 I slot print_timing: id 0 | task 21494 | prompt eval time = 149.92 ms / 371 tokens ( 0.40 ms per token, 2474.69 tokens per second) 4.01.520.731 I slot print_timing: id 0 | task 21494 | eval time = 1023.53 ms / 112 tokens ( 9.22 ms per token, 108.45 tokens per second) 4.01.520.732 I slot print_timing: id 0 | task 21494 | total time = 1173.45 ms / 483 tokens 4.01.520.733 I slot print_timing: id 0 | task 21494 | graphs reused = 20578 4.01.520.734 I slot print_timing: id 0 | task 21494 | graph reallocs = 0 / 0 (same size) / (changed size) 4.01.520.766 I slot release: id 0 | task 21494 | stop processing: n_tokens = 514, truncated = 0 4.01.544.014 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 514, t_last = 241428119 4.01.544.063 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.083 MiB) 4.01.635.620 I slot launch_slot_: id 0 | task 21609 | processing task, is_child = 0 4.02.987.063 I slot print_timing: id 0 | task 21609 | prompt eval time = 137.06 ms / 292 tokens ( 0.47 ms per token, 2130.53 tokens per second) 4.02.987.069 I slot print_timing: id 0 | task 21609 | eval time = 1214.37 ms / 134 tokens ( 9.13 ms per token, 109.52 tokens per second) 4.02.987.070 I slot print_timing: id 0 | task 21609 | total time = 1351.42 ms / 426 tokens 4.02.987.071 I slot print_timing: id 0 | task 21609 | graphs reused = 20710 4.02.987.072 I slot print_timing: id 0 | task 21609 | graph reallocs = 0 / 0 (same size) / (changed size) 4.02.987.098 I slot release: id 0 | task 21609 | stop processing: n_tokens = 457, truncated = 0 4.03.015.930 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 457, t_last = 242894450 4.03.015.981 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.461 MiB) 4.03.112.839 I slot launch_slot_: id 0 | task 21746 | processing task, is_child = 0 4.03.406.814 I slot print_timing: id 0 | task 21746 | prompt eval time = 135.00 ms / 301 tokens ( 0.45 ms per token, 2229.65 tokens per second) 4.03.406.820 I slot print_timing: id 0 | task 21746 | eval time = 158.96 ms / 18 tokens ( 9.35 ms per token, 106.95 tokens per second) 4.03.406.821 I slot print_timing: id 0 | task 21746 | total time = 293.96 ms / 319 tokens 4.03.406.821 I slot print_timing: id 0 | task 21746 | graphs reused = 20726 4.03.406.822 I slot print_timing: id 0 | task 21746 | graph reallocs = 0 / 0 (same size) / (changed size) 4.03.406.849 I slot release: id 0 | task 21746 | stop processing: n_tokens = 350, truncated = 0 4.03.422.311 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 350, t_last = 243314202 4.03.422.355 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.531 MiB) 4.03.492.502 I slot launch_slot_: id 0 | task 21767 | processing task, is_child = 0 4.05.538.879 I slot print_timing: id 0 | task 21767 | prompt eval time = 134.93 ms / 303 tokens ( 0.45 ms per token, 2245.68 tokens per second) 4.05.538.885 I slot print_timing: id 0 | task 21767 | eval time = 1911.43 ms / 210 tokens ( 9.15 ms per token, 109.34 tokens per second) 4.05.538.886 I slot print_timing: id 0 | task 21767 | total time = 2046.36 ms / 513 tokens 4.05.538.886 I slot print_timing: id 0 | task 21767 | graphs reused = 20933 4.05.538.887 I slot print_timing: id 0 | task 21767 | graph reallocs = 0 / 0 (same size) / (changed size) 4.05.538.913 I slot release: id 0 | task 21767 | stop processing: n_tokens = 544, truncated = 0 4.05.562.105 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 544, t_last = 245446266 4.05.562.157 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.062 MiB) 4.05.663.089 I slot launch_slot_: id 0 | task 21980 | processing task, is_child = 0 4.06.538.514 I slot print_timing: id 0 | task 21980 | prompt eval time = 140.77 ms / 321 tokens ( 0.44 ms per token, 2280.28 tokens per second) 4.06.538.520 I slot print_timing: id 0 | task 21980 | eval time = 734.63 ms / 81 tokens ( 9.18 ms per token, 108.90 tokens per second) 4.06.538.521 I slot print_timing: id 0 | task 21980 | total time = 875.41 ms / 402 tokens 4.06.538.521 I slot print_timing: id 0 | task 21980 | graphs reused = 21012 4.06.538.522 I slot print_timing: id 0 | task 21980 | graph reallocs = 0 / 0 (same size) / (changed size) 4.06.538.553 I slot release: id 0 | task 21980 | stop processing: n_tokens = 433, truncated = 0 4.06.542.230 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 433, t_last = 246445906 4.06.542.272 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.424 MiB) 4.06.627.704 I slot launch_slot_: id 0 | task 22064 | processing task, is_child = 0 4.07.671.719 I slot print_timing: id 0 | task 22064 | prompt eval time = 140.83 ms / 322 tokens ( 0.44 ms per token, 2286.41 tokens per second) 4.07.671.724 I slot print_timing: id 0 | task 22064 | eval time = 903.16 ms / 99 tokens ( 9.22 ms per token, 108.51 tokens per second) 4.07.671.725 I slot print_timing: id 0 | task 22064 | total time = 1043.99 ms / 421 tokens 4.07.671.726 I slot print_timing: id 0 | task 22064 | graphs reused = 21109 4.07.671.727 I slot print_timing: id 0 | task 22064 | graph reallocs = 0 / 0 (same size) / (changed size) 4.07.671.757 I slot release: id 0 | task 22064 | stop processing: n_tokens = 452, truncated = 0 4.07.697.831 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 452, t_last = 247579110 4.07.697.877 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.920 MiB) 4.07.770.734 I slot launch_slot_: id 0 | task 22166 | processing task, is_child = 0 4.08.397.344 I slot print_timing: id 0 | task 22166 | prompt eval time = 140.13 ms / 323 tokens ( 0.43 ms per token, 2305.05 tokens per second) 4.08.397.350 I slot print_timing: id 0 | task 22166 | eval time = 486.46 ms / 54 tokens ( 9.18 ms per token, 108.95 tokens per second) 4.08.397.351 I slot print_timing: id 0 | task 22166 | total time = 626.59 ms / 377 tokens 4.08.397.352 I slot print_timing: id 0 | task 22166 | graphs reused = 21161 4.08.397.353 I slot print_timing: id 0 | task 22166 | graph reallocs = 0 / 0 (same size) / (changed size) 4.08.397.379 I slot release: id 0 | task 22166 | stop processing: n_tokens = 408, truncated = 0 4.08.413.817 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 408, t_last = 248304732 4.08.413.860 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.392 MiB) 4.08.486.740 I slot launch_slot_: id 0 | task 22223 | processing task, is_child = 0 4.11.632.652 I slot print_timing: id 0 | task 22223 | n_gen = 330, tg = 109.49 t/s, tg_3s = 109.82 t/s 4.14.638.018 I slot print_timing: id 0 | task 22223 | n_gen = 657, tg = 109.15 t/s, tg_3s = 108.81 t/s 4.15.957.507 I slot print_timing: id 0 | task 22223 | prompt eval time = 141.09 ms / 321 tokens ( 0.44 ms per token, 2275.06 tokens per second) 4.15.957.513 I slot print_timing: id 0 | task 22223 | eval time = 7329.65 ms / 800 tokens ( 9.17 ms per token, 109.01 tokens per second) 4.15.957.514 I slot print_timing: id 0 | task 22223 | total time = 7470.75 ms / 1121 tokens 4.15.957.515 I slot print_timing: id 0 | task 22223 | graphs reused = 21956 4.15.957.515 I slot print_timing: id 0 | task 22223 | graph reallocs = 0 / 0 (same size) / (changed size) 4.15.957.550 I slot release: id 0 | task 22223 | stop processing: n_tokens = 1152, truncated = 0 4.15.961.688 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1152, t_last = 255864903 4.15.961.757 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.763 MiB) 4.16.063.908 I slot launch_slot_: id 0 | task 23026 | processing task, is_child = 0 4.16.494.978 I slot print_timing: id 0 | task 23026 | prompt eval time = 143.72 ms / 322 tokens ( 0.45 ms per token, 2240.48 tokens per second) 4.16.494.984 I slot print_timing: id 0 | task 23026 | eval time = 287.33 ms / 32 tokens ( 9.27 ms per token, 107.89 tokens per second) 4.16.494.985 I slot print_timing: id 0 | task 23026 | total time = 431.05 ms / 354 tokens 4.16.494.987 I slot print_timing: id 0 | task 23026 | graphs reused = 21986 4.16.494.988 I slot print_timing: id 0 | task 23026 | graph reallocs = 0 / 0 (same size) / (changed size) 4.16.495.016 I slot release: id 0 | task 23026 | stop processing: n_tokens = 385, truncated = 0 4.16.516.324 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 385, t_last = 256402369 4.16.516.363 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.859 MiB) 4.16.600.924 I slot launch_slot_: id 0 | task 23061 | processing task, is_child = 0 4.17.156.523 I slot print_timing: id 0 | task 23061 | prompt eval time = 140.94 ms / 337 tokens ( 0.42 ms per token, 2391.17 tokens per second) 4.17.156.529 I slot print_timing: id 0 | task 23061 | eval time = 414.64 ms / 46 tokens ( 9.21 ms per token, 108.53 tokens per second) 4.17.156.530 I slot print_timing: id 0 | task 23061 | total time = 555.58 ms / 383 tokens 4.17.156.531 I slot print_timing: id 0 | task 23061 | graphs reused = 22030 4.17.156.532 I slot print_timing: id 0 | task 23061 | graph reallocs = 0 / 0 (same size) / (changed size) 4.17.156.558 I slot release: id 0 | task 23061 | stop processing: n_tokens = 414, truncated = 0 4.17.171.823 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 257063911 4.17.171.868 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.141 MiB) 4.17.255.922 I slot launch_slot_: id 0 | task 23110 | processing task, is_child = 0 4.17.819.716 I slot print_timing: id 0 | task 23110 | prompt eval time = 140.72 ms / 325 tokens ( 0.43 ms per token, 2309.50 tokens per second) 4.17.819.722 I slot print_timing: id 0 | task 23110 | eval time = 423.05 ms / 47 tokens ( 9.20 ms per token, 108.73 tokens per second) 4.17.819.723 I slot print_timing: id 0 | task 23110 | total time = 563.77 ms / 372 tokens 4.17.819.724 I slot print_timing: id 0 | task 23110 | graphs reused = 22075 4.17.819.724 I slot print_timing: id 0 | task 23110 | graph reallocs = 0 / 0 (same size) / (changed size) 4.17.819.751 I slot release: id 0 | task 23110 | stop processing: n_tokens = 403, truncated = 0 4.17.838.767 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 403, t_last = 257727104 4.17.838.812 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.305 MiB) 4.17.923.846 I slot launch_slot_: id 0 | task 23160 | processing task, is_child = 0 4.19.006.208 I slot print_timing: id 0 | task 23160 | prompt eval time = 140.46 ms / 331 tokens ( 0.42 ms per token, 2356.61 tokens per second) 4.19.006.213 I slot print_timing: id 0 | task 23160 | eval time = 941.89 ms / 104 tokens ( 9.14 ms per token, 109.35 tokens per second) 4.19.006.214 I slot print_timing: id 0 | task 23160 | total time = 1082.34 ms / 435 tokens 4.19.006.215 I slot print_timing: id 0 | task 23160 | graphs reused = 22177 4.19.006.216 I slot print_timing: id 0 | task 23160 | graph reallocs = 0 / 0 (same size) / (changed size) 4.19.006.243 I slot release: id 0 | task 23160 | stop processing: n_tokens = 466, truncated = 0 4.19.021.699 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 466, t_last = 258913596 4.19.021.739 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.171 MiB) 4.19.118.699 I slot launch_slot_: id 0 | task 23267 | processing task, is_child = 0 4.20.063.876 I slot print_timing: id 0 | task 23267 | prompt eval time = 140.64 ms / 336 tokens ( 0.42 ms per token, 2389.08 tokens per second) 4.20.063.882 I slot print_timing: id 0 | task 23267 | eval time = 804.52 ms / 89 tokens ( 9.14 ms per token, 109.38 tokens per second) 4.20.063.883 I slot print_timing: id 0 | task 23267 | total time = 945.16 ms / 425 tokens 4.20.063.884 I slot print_timing: id 0 | task 23267 | graphs reused = 22264 4.20.063.885 I slot print_timing: id 0 | task 23267 | graph reallocs = 0 / 0 (same size) / (changed size) 4.20.063.912 I slot release: id 0 | task 23267 | stop processing: n_tokens = 456, truncated = 0 4.20.086.518 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 456, t_last = 259971265 4.20.086.557 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.044 MiB) 4.20.179.819 I slot launch_slot_: id 0 | task 23359 | processing task, is_child = 0 4.20.580.134 I slot print_timing: id 0 | task 23359 | prompt eval time = 141.15 ms / 349 tokens ( 0.40 ms per token, 2472.58 tokens per second) 4.20.580.138 I slot print_timing: id 0 | task 23359 | eval time = 259.15 ms / 29 tokens ( 9.26 ms per token, 108.05 tokens per second) 4.20.580.139 I slot print_timing: id 0 | task 23359 | total time = 400.30 ms / 378 tokens 4.20.580.141 I slot print_timing: id 0 | task 23359 | graphs reused = 22291 4.20.580.141 I slot print_timing: id 0 | task 23359 | graph reallocs = 0 / 0 (same size) / (changed size) 4.20.580.170 I slot release: id 0 | task 23359 | stop processing: n_tokens = 409, truncated = 0 4.20.603.052 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 260487523 4.20.603.095 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 313.481 MiB) 4.20.693.543 I slot launch_slot_: id 0 | task 23391 | processing task, is_child = 0 4.21.532.643 I slot print_timing: id 0 | task 23391 | prompt eval time = 140.32 ms / 336 tokens ( 0.42 ms per token, 2394.54 tokens per second) 4.21.532.649 I slot print_timing: id 0 | task 23391 | eval time = 698.76 ms / 77 tokens ( 9.19 ms per token, 108.76 tokens per second) 4.21.532.650 I slot print_timing: id 0 | task 23391 | total time = 839.08 ms / 413 tokens 4.21.532.651 I slot print_timing: id 0 | task 23391 | graphs reused = 22366 4.21.532.652 I slot print_timing: id 0 | task 23391 | graph reallocs = 0 / 0 (same size) / (changed size) 4.21.532.681 I slot release: id 0 | task 23391 | stop processing: n_tokens = 444, truncated = 0 4.21.553.682 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 444, t_last = 261440034 4.21.553.727 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.047 MiB) 4.21.644.781 I slot launch_slot_: id 0 | task 23471 | processing task, is_child = 0 4.24.792.285 I slot print_timing: id 0 | task 23471 | n_gen = 330, tg = 109.43 t/s, tg_3s = 109.77 t/s 4.27.800.591 I slot print_timing: id 0 | task 23471 | n_gen = 654, tg = 108.57 t/s, tg_3s = 107.70 t/s 4.28.403.862 I slot print_timing: id 0 | task 23471 | prompt eval time = 141.11 ms / 349 tokens ( 0.40 ms per token, 2473.25 tokens per second) 4.28.403.867 I slot print_timing: id 0 | task 23471 | eval time = 6617.95 ms / 719 tokens ( 9.22 ms per token, 108.49 tokens per second) 4.28.403.868 I slot print_timing: id 0 | task 23471 | total time = 6759.06 ms / 1068 tokens 4.28.403.869 I slot print_timing: id 0 | task 23471 | graphs reused = 23080 4.28.403.870 I slot print_timing: id 0 | task 23471 | graph reallocs = 0 / 0 (same size) / (changed size) 4.28.403.900 I slot release: id 0 | task 23471 | stop processing: n_tokens = 1099, truncated = 0 4.28.419.493 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1099, t_last = 268311252 4.28.419.561 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.951 MiB) 4.28.519.068 I slot launch_slot_: id 0 | task 24193 | processing task, is_child = 0 4.29.477.840 I slot print_timing: id 0 | task 24193 | prompt eval time = 141.71 ms / 349 tokens ( 0.41 ms per token, 2462.81 tokens per second) 4.29.477.846 I slot print_timing: id 0 | task 24193 | eval time = 817.04 ms / 90 tokens ( 9.18 ms per token, 108.93 tokens per second) 4.29.477.847 I slot print_timing: id 0 | task 24193 | total time = 958.75 ms / 439 tokens 4.29.477.848 I slot print_timing: id 0 | task 24193 | graphs reused = 23168 4.29.477.849 I slot print_timing: id 0 | task 24193 | graph reallocs = 0 / 0 (same size) / (changed size) 4.29.477.878 I slot release: id 0 | task 24193 | stop processing: n_tokens = 470, truncated = 0 4.29.506.244 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 269385231 4.29.506.285 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 313.888 MiB) 4.29.577.572 I slot launch_slot_: id 0 | task 24286 | processing task, is_child = 0 4.30.239.566 I slot print_timing: id 0 | task 24286 | prompt eval time = 147.75 ms / 385 tokens ( 0.38 ms per token, 2605.82 tokens per second) 4.30.239.572 I slot print_timing: id 0 | task 24286 | eval time = 514.23 ms / 57 tokens ( 9.18 ms per token, 108.90 tokens per second) 4.30.239.573 I slot print_timing: id 0 | task 24286 | total time = 661.97 ms / 442 tokens 4.30.239.573 I slot print_timing: id 0 | task 24286 | graphs reused = 23223 4.30.239.574 I slot print_timing: id 0 | task 24286 | graph reallocs = 0 / 0 (same size) / (changed size) 4.30.239.603 I slot release: id 0 | task 24286 | stop processing: n_tokens = 473, truncated = 0 4.30.255.035 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 473, t_last = 270146956 4.30.255.081 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.426 MiB) 4.30.319.795 I slot launch_slot_: id 0 | task 24346 | processing task, is_child = 0 4.31.230.488 I slot print_timing: id 0 | task 24346 | prompt eval time = 140.95 ms / 328 tokens ( 0.43 ms per token, 2327.13 tokens per second) 4.31.230.493 I slot print_timing: id 0 | task 24346 | eval time = 769.73 ms / 85 tokens ( 9.16 ms per token, 109.13 tokens per second) 4.31.230.494 I slot print_timing: id 0 | task 24346 | total time = 910.67 ms / 413 tokens 4.31.230.495 I slot print_timing: id 0 | task 24346 | graphs reused = 23306 4.31.230.496 I slot print_timing: id 0 | task 24346 | graph reallocs = 0 / 0 (same size) / (changed size) 4.31.230.524 I slot release: id 0 | task 24346 | stop processing: n_tokens = 444, truncated = 0