$ C:\quantdiff\llama.cpp\bin\llama-server.exe -m C:\quantdiff\dl\campaign\b6f76e74f862\Ornith-1.5-9B-Q6_K.gguf --host 127.0.0.1 --port 8089 -c 4096 -np 1 -ngl 999 -fa on --jinja --seed 1234 --no-webui -a quant 0.00.104.295 I srv llama_server: initializing ... 0.00.104.299 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.104.411 I srv init_listene: The UI is disabled 0.00.104.413 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.104.489 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) 0.00.107.272 I srv load_model: loading model 'C:\quantdiff\dl\campaign\b6f76e74f862\Ornith-1.5-9B-Q6_K.gguf' 0.01.020.191 W model has unused tensor blk.32.attn_norm.weight (size = 16384 bytes) -- ignoring 0.01.020.206 W model has unused tensor blk.32.post_attention_norm.weight (size = 16384 bytes) -- ignoring 0.01.020.232 W model has unused tensor blk.32.attn_q.weight (size = 27525120 bytes) -- ignoring 0.01.020.242 W model has unused tensor blk.32.attn_k.weight (size = 3440640 bytes) -- ignoring 0.01.020.251 W model has unused tensor blk.32.attn_v.weight (size = 3440640 bytes) -- ignoring 0.01.020.284 W model has unused tensor blk.32.attn_output.weight (size = 13762560 bytes) -- ignoring 0.01.020.295 W model has unused tensor blk.32.attn_q_norm.weight (size = 1024 bytes) -- ignoring 0.01.020.304 W model has unused tensor blk.32.attn_k_norm.weight (size = 1024 bytes) -- ignoring 0.01.020.313 W model has unused tensor blk.32.ffn_gate.weight (size = 41287680 bytes) -- ignoring 0.01.020.322 W model has unused tensor blk.32.ffn_down.weight (size = 41287680 bytes) -- ignoring 0.01.020.331 W model has unused tensor blk.32.ffn_up.weight (size = 41287680 bytes) -- ignoring 0.01.020.342 W model has unused tensor blk.32.nextn.eh_proj.weight (size = 27525120 bytes) -- ignoring 0.01.020.353 W model has unused tensor blk.32.nextn.enorm.weight (size = 16384 bytes) -- ignoring 0.01.020.362 W model has unused tensor blk.32.nextn.hnorm.weight (size = 16384 bytes) -- ignoring 0.01.020.392 W model has unused tensor blk.32.nextn.shared_head_norm.weight (size = 16384 bytes) -- ignoring 0.03.379.692 I cmn init: llama threadpool init, n_threads = 8 0.03.464.365 I srv load_model: initializing, n_slots = 1, n_ctx_slot = 4096, kv_unified = 'false' 0.03.469.756 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.03.469.779 I srv llama_server: model loaded 0.03.469.782 I srv llama_server: listening on http://127.0.0.1:8089 0.04.627.737 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.04.627.895 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.05.704.365 I slot print_timing: id 0 | task 0 | prompt eval time = 160.53 ms / 368 tokens ( 0.44 ms per token, 2292.34 tokens per second) 0.05.704.370 I slot print_timing: id 0 | task 0 | eval time = 915.91 ms / 72 tokens ( 12.90 ms per token, 77.52 tokens per second) 0.05.704.371 I slot print_timing: id 0 | task 0 | total time = 1076.45 ms / 440 tokens 0.05.704.378 I slot print_timing: id 0 | task 0 | graphs reused = 71 0.05.704.378 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.704.420 I slot release: id 0 | task 0 | stop processing: n_tokens = 439, truncated = 0 0.05.745.875 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 439, t_last = 5602143 0.05.770.676 I slot launch_slot_: id 0 | task 75 | processing task, is_child = 0 0.06.626.528 I slot print_timing: id 0 | task 75 | prompt eval time = 140.08 ms / 322 tokens ( 0.44 ms per token, 2298.64 tokens per second) 0.06.626.535 I slot print_timing: id 0 | task 75 | eval time = 715.75 ms / 59 tokens ( 12.34 ms per token, 81.03 tokens per second) 0.06.626.536 I slot print_timing: id 0 | task 75 | total time = 855.83 ms / 381 tokens 0.06.626.537 I slot print_timing: id 0 | task 75 | graphs reused = 128 0.06.626.537 I slot print_timing: id 0 | task 75 | graph reallocs = 0 / 0 (same size) / (changed size) 0.06.626.563 I slot release: id 0 | task 75 | stop processing: n_tokens = 380, truncated = 0 0.06.631.256 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 380, t_last = 6524285 0.06.654.585 I slot launch_slot_: id 0 | task 137 | processing task, is_child = 0 0.07.297.313 I slot print_timing: id 0 | task 137 | prompt eval time = 137.55 ms / 365 tokens ( 0.38 ms per token, 2653.60 tokens per second) 0.07.297.319 I slot print_timing: id 0 | task 137 | eval time = 505.16 ms / 42 tokens ( 12.32 ms per token, 81.16 tokens per second) 0.07.297.320 I slot print_timing: id 0 | task 137 | total time = 642.71 ms / 407 tokens 0.07.297.320 I slot print_timing: id 0 | task 137 | graphs reused = 168 0.07.297.321 I slot print_timing: id 0 | task 137 | graph reallocs = 0 / 0 (same size) / (changed size) 0.07.297.349 I slot release: id 0 | task 137 | stop processing: n_tokens = 406, truncated = 0 0.07.321.337 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 406, t_last = 7195072 0.07.345.560 I slot launch_slot_: id 0 | task 182 | processing task, is_child = 0 0.08.339.522 I slot print_timing: id 0 | task 182 | prompt eval time = 150.62 ms / 397 tokens ( 0.38 ms per token, 2635.82 tokens per second) 0.08.339.527 I slot print_timing: id 0 | task 182 | eval time = 843.32 ms / 67 tokens ( 12.78 ms per token, 78.26 tokens per second) 0.08.339.528 I slot print_timing: id 0 | task 182 | total time = 993.94 ms / 464 tokens 0.08.339.529 I slot print_timing: id 0 | task 182 | graphs reused = 233 0.08.339.530 I slot print_timing: id 0 | task 182 | graph reallocs = 0 / 0 (same size) / (changed size) 0.08.339.560 I slot release: id 0 | task 182 | stop processing: n_tokens = 463, truncated = 0 0.08.366.615 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.117 (> 0.100 thold), f_keep = 0.097 0.08.390.500 I slot launch_slot_: id 0 | task 252 | processing task, is_child = 0 0.09.417.146 I slot print_timing: id 0 | task 252 | prompt eval time = 145.48 ms / 383 tokens ( 0.38 ms per token, 2632.59 tokens per second) 0.09.417.152 I slot print_timing: id 0 | task 252 | eval time = 881.15 ms / 70 tokens ( 12.77 ms per token, 78.31 tokens per second) 0.09.417.153 I slot print_timing: id 0 | task 252 | total time = 1026.63 ms / 453 tokens 0.09.417.154 I slot print_timing: id 0 | task 252 | graphs reused = 301 0.09.417.155 I slot print_timing: id 0 | task 252 | graph reallocs = 0 / 0 (same size) / (changed size) 0.09.417.182 I slot release: id 0 | task 252 | stop processing: n_tokens = 452, truncated = 0 0.09.444.863 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 452, t_last = 9314905 0.09.469.199 I slot launch_slot_: id 0 | task 325 | processing task, is_child = 0 0.10.282.238 I slot print_timing: id 0 | task 325 | prompt eval time = 144.74 ms / 372 tokens ( 0.39 ms per token, 2570.16 tokens per second) 0.10.282.243 I slot print_timing: id 0 | task 325 | eval time = 668.28 ms / 55 tokens ( 12.38 ms per token, 80.80 tokens per second) 0.10.282.244 I slot print_timing: id 0 | task 325 | total time = 813.02 ms / 427 tokens 0.10.282.245 I slot print_timing: id 0 | task 325 | graphs reused = 354 0.10.282.246 I slot print_timing: id 0 | task 325 | graph reallocs = 0 / 0 (same size) / (changed size) 0.10.282.276 I slot release: id 0 | task 325 | stop processing: n_tokens = 426, truncated = 0 0.10.287.210 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 10179998 0.10.311.632 I slot launch_slot_: id 0 | task 383 | processing task, is_child = 0 0.11.312.170 I slot print_timing: id 0 | task 383 | prompt eval time = 163.50 ms / 422 tokens ( 0.39 ms per token, 2581.04 tokens per second) 0.11.312.176 I slot print_timing: id 0 | task 383 | eval time = 837.02 ms / 69 tokens ( 12.31 ms per token, 81.24 tokens per second) 0.11.312.177 I slot print_timing: id 0 | task 383 | total time = 1000.52 ms / 491 tokens 0.11.312.178 I slot print_timing: id 0 | task 383 | graphs reused = 421 0.11.312.179 I slot print_timing: id 0 | task 383 | graph reallocs = 0 / 0 (same size) / (changed size) 0.11.312.210 I slot release: id 0 | task 383 | stop processing: n_tokens = 490, truncated = 0 0.11.341.920 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 490, t_last = 11209932 0.11.366.262 I slot launch_slot_: id 0 | task 455 | processing task, is_child = 0 0.12.622.037 I slot print_timing: id 0 | task 455 | prompt eval time = 167.71 ms / 470 tokens ( 0.36 ms per token, 2802.47 tokens per second) 0.12.622.044 I slot print_timing: id 0 | task 455 | eval time = 1088.05 ms / 89 tokens ( 12.36 ms per token, 80.88 tokens per second) 0.12.622.045 I slot print_timing: id 0 | task 455 | total time = 1255.76 ms / 559 tokens 0.12.622.045 I slot print_timing: id 0 | task 455 | graphs reused = 507 0.12.622.046 I slot print_timing: id 0 | task 455 | graph reallocs = 0 / 0 (same size) / (changed size) 0.12.622.085 I slot release: id 0 | task 455 | stop processing: n_tokens = 558, truncated = 0 0.12.653.569 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 12519807 0.12.678.579 I slot launch_slot_: id 0 | task 547 | processing task, is_child = 0 0.13.676.217 I slot print_timing: id 0 | task 547 | prompt eval time = 136.03 ms / 345 tokens ( 0.39 ms per token, 2536.24 tokens per second) 0.13.676.224 I slot print_timing: id 0 | task 547 | eval time = 861.59 ms / 71 tokens ( 12.31 ms per token, 81.24 tokens per second) 0.13.676.225 I slot print_timing: id 0 | task 547 | total time = 997.62 ms / 416 tokens 0.13.676.225 I slot print_timing: id 0 | task 547 | graphs reused = 576 0.13.676.226 I slot print_timing: id 0 | task 547 | graph reallocs = 0 / 0 (same size) / (changed size) 0.13.676.253 I slot release: id 0 | task 547 | stop processing: n_tokens = 415, truncated = 0 0.13.716.896 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 415, t_last = 13573976 0.13.741.319 I slot launch_slot_: id 0 | task 621 | processing task, is_child = 0 0.14.374.991 I slot print_timing: id 0 | task 621 | prompt eval time = 138.93 ms / 364 tokens ( 0.38 ms per token, 2620.04 tokens per second) 0.14.375.000 I slot print_timing: id 0 | task 621 | eval time = 494.73 ms / 41 tokens ( 12.37 ms per token, 80.85 tokens per second) 0.14.375.002 I slot print_timing: id 0 | task 621 | total time = 633.65 ms / 405 tokens 0.14.375.003 I slot print_timing: id 0 | task 621 | graphs reused = 615 0.14.375.004 I slot print_timing: id 0 | task 621 | graph reallocs = 0 / 0 (same size) / (changed size) 0.14.375.034 I slot release: id 0 | task 621 | stop processing: n_tokens = 404, truncated = 0 0.14.403.173 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 404, t_last = 14272756 0.14.427.359 I slot launch_slot_: id 0 | task 665 | processing task, is_child = 0 0.15.581.501 I slot print_timing: id 0 | task 665 | prompt eval time = 145.50 ms / 376 tokens ( 0.39 ms per token, 2584.23 tokens per second) 0.15.581.508 I slot print_timing: id 0 | task 665 | eval time = 1008.62 ms / 80 tokens ( 12.77 ms per token, 78.32 tokens per second) 0.15.581.509 I slot print_timing: id 0 | task 665 | total time = 1154.12 ms / 456 tokens 0.15.581.510 I slot print_timing: id 0 | task 665 | graphs reused = 693 0.15.581.511 I slot print_timing: id 0 | task 665 | graph reallocs = 0 / 0 (same size) / (changed size) 0.15.581.540 I slot release: id 0 | task 665 | stop processing: n_tokens = 455, truncated = 0 0.15.605.944 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 455, t_last = 15479262 0.15.632.710 I slot launch_slot_: id 0 | task 748 | processing task, is_child = 0 0.16.629.708 I slot print_timing: id 0 | task 748 | prompt eval time = 146.94 ms / 412 tokens ( 0.36 ms per token, 2803.94 tokens per second) 0.16.629.714 I slot print_timing: id 0 | task 748 | eval time = 850.04 ms / 70 tokens ( 12.32 ms per token, 81.17 tokens per second) 0.16.629.715 I slot print_timing: id 0 | task 748 | total time = 996.98 ms / 482 tokens 0.16.629.716 I slot print_timing: id 0 | task 748 | graphs reused = 761 0.16.629.717 I slot print_timing: id 0 | task 748 | graph reallocs = 0 / 0 (same size) / (changed size) 0.16.629.749 I slot release: id 0 | task 748 | stop processing: n_tokens = 481, truncated = 0 0.16.634.744 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 481, t_last = 16527472 0.16.659.606 I slot launch_slot_: id 0 | task 821 | processing task, is_child = 0 0.17.549.781 I slot print_timing: id 0 | task 821 | prompt eval time = 140.30 ms / 376 tokens ( 0.37 ms per token, 2679.99 tokens per second) 0.17.549.787 I slot print_timing: id 0 | task 821 | eval time = 749.86 ms / 62 tokens ( 12.29 ms per token, 81.35 tokens per second) 0.17.549.788 I slot print_timing: id 0 | task 821 | total time = 890.16 ms / 438 tokens 0.17.549.789 I slot print_timing: id 0 | task 821 | graphs reused = 821 0.17.549.790 I slot print_timing: id 0 | task 821 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.549.816 I slot release: id 0 | task 821 | stop processing: n_tokens = 437, truncated = 0 0.17.574.802 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 17447539 0.17.599.530 I slot launch_slot_: id 0 | task 886 | processing task, is_child = 0 0.18.590.412 I slot print_timing: id 0 | task 886 | prompt eval time = 143.66 ms / 378 tokens ( 0.38 ms per token, 2631.29 tokens per second) 0.18.590.418 I slot print_timing: id 0 | task 886 | eval time = 847.21 ms / 70 tokens ( 12.28 ms per token, 81.44 tokens per second) 0.18.590.419 I slot print_timing: id 0 | task 886 | total time = 990.86 ms / 448 tokens 0.18.590.420 I slot print_timing: id 0 | task 886 | graphs reused = 889 0.18.590.421 I slot print_timing: id 0 | task 886 | graph reallocs = 0 / 0 (same size) / (changed size) 0.18.590.449 I slot release: id 0 | task 886 | stop processing: n_tokens = 447, truncated = 0 0.18.620.733 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 18488171 0.18.645.027 I slot launch_slot_: id 0 | task 959 | processing task, is_child = 0 0.19.537.153 I slot print_timing: id 0 | task 959 | prompt eval time = 144.53 ms / 367 tokens ( 0.39 ms per token, 2539.30 tokens per second) 0.19.537.159 I slot print_timing: id 0 | task 959 | eval time = 747.58 ms / 62 tokens ( 12.26 ms per token, 81.60 tokens per second) 0.19.537.160 I slot print_timing: id 0 | task 959 | total time = 892.11 ms / 429 tokens 0.19.537.161 I slot print_timing: id 0 | task 959 | graphs reused = 949 0.19.537.162 I slot print_timing: id 0 | task 959 | graph reallocs = 0 / 0 (same size) / (changed size) 0.19.537.189 I slot release: id 0 | task 959 | stop processing: n_tokens = 428, truncated = 0 0.19.554.791 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 428, t_last = 19434911 0.19.578.509 I slot launch_slot_: id 0 | task 1024 | processing task, is_child = 0 0.20.659.122 I slot print_timing: id 0 | task 1024 | prompt eval time = 136.05 ms / 347 tokens ( 0.39 ms per token, 2550.50 tokens per second) 0.20.659.128 I slot print_timing: id 0 | task 1024 | eval time = 944.54 ms / 78 tokens ( 12.27 ms per token, 81.52 tokens per second) 0.20.659.129 I slot print_timing: id 0 | task 1024 | total time = 1080.60 ms / 425 tokens 0.20.659.130 I slot print_timing: id 0 | task 1024 | graphs reused = 1025 0.20.659.131 I slot print_timing: id 0 | task 1024 | graph reallocs = 0 / 0 (same size) / (changed size) 0.20.659.158 I slot release: id 0 | task 1024 | stop processing: n_tokens = 424, truncated = 0 0.20.687.083 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 20556881 0.20.712.375 I slot launch_slot_: id 0 | task 1105 | processing task, is_child = 0 0.21.746.837 I slot print_timing: id 0 | task 1105 | prompt eval time = 137.41 ms / 369 tokens ( 0.37 ms per token, 2685.32 tokens per second) 0.21.746.843 I slot print_timing: id 0 | task 1105 | eval time = 897.03 ms / 74 tokens ( 12.29 ms per token, 81.38 tokens per second) 0.21.746.844 I slot print_timing: id 0 | task 1105 | total time = 1034.44 ms / 443 tokens 0.21.746.845 I slot print_timing: id 0 | task 1105 | graphs reused = 1097 0.21.746.846 I slot print_timing: id 0 | task 1105 | graph reallocs = 0 / 0 (same size) / (changed size) 0.21.746.875 I slot release: id 0 | task 1105 | stop processing: n_tokens = 442, truncated = 0 0.21.751.473 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 442, t_last = 21644597 0.21.776.176 I slot launch_slot_: id 0 | task 1182 | processing task, is_child = 0 0.22.406.477 I slot print_timing: id 0 | task 1182 | prompt eval time = 136.01 ms / 352 tokens ( 0.39 ms per token, 2587.99 tokens per second) 0.22.406.482 I slot print_timing: id 0 | task 1182 | eval time = 494.27 ms / 41 tokens ( 12.36 ms per token, 80.93 tokens per second) 0.22.406.483 I slot print_timing: id 0 | task 1182 | total time = 630.28 ms / 393 tokens 0.22.406.485 I slot print_timing: id 0 | task 1182 | graphs reused = 1136 0.22.406.485 I slot print_timing: id 0 | task 1182 | graph reallocs = 0 / 0 (same size) / (changed size) 0.22.406.512 I slot release: id 0 | task 1182 | stop processing: n_tokens = 392, truncated = 0 0.22.411.198 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 392, t_last = 22304235 0.22.435.205 I slot launch_slot_: id 0 | task 1226 | processing task, is_child = 0 0.23.227.276 I slot print_timing: id 0 | task 1226 | prompt eval time = 138.54 ms / 349 tokens ( 0.40 ms per token, 2519.06 tokens per second) 0.23.227.282 I slot print_timing: id 0 | task 1226 | eval time = 653.51 ms / 54 tokens ( 12.33 ms per token, 81.10 tokens per second) 0.23.227.283 I slot print_timing: id 0 | task 1226 | total time = 792.06 ms / 403 tokens 0.23.227.284 I slot print_timing: id 0 | task 1226 | graphs reused = 1188 0.23.227.285 I slot print_timing: id 0 | task 1226 | graph reallocs = 0 / 0 (same size) / (changed size) 0.23.227.311 I slot release: id 0 | task 1226 | stop processing: n_tokens = 402, truncated = 0 0.23.242.500 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 402, t_last = 23125034 0.23.266.510 I slot launch_slot_: id 0 | task 1283 | processing task, is_child = 0 0.24.188.510 I slot print_timing: id 0 | task 1283 | prompt eval time = 147.00 ms / 384 tokens ( 0.38 ms per token, 2612.30 tokens per second) 0.24.188.516 I slot print_timing: id 0 | task 1283 | eval time = 774.99 ms / 63 tokens ( 12.50 ms per token, 80.00 tokens per second) 0.24.188.517 I slot print_timing: id 0 | task 1283 | total time = 921.98 ms / 447 tokens 0.24.188.518 I slot print_timing: id 0 | task 1283 | graphs reused = 1249 0.24.188.519 I slot print_timing: id 0 | task 1283 | graph reallocs = 0 / 0 (same size) / (changed size) 0.24.188.548 I slot release: id 0 | task 1283 | stop processing: n_tokens = 446, truncated = 0 0.24.207.651 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 446, t_last = 24086270 0.24.233.248 I slot launch_slot_: id 0 | task 1349 | processing task, is_child = 0 0.25.359.544 I slot print_timing: id 0 | task 1349 | prompt eval time = 143.40 ms / 356 tokens ( 0.40 ms per token, 2482.57 tokens per second) 0.25.359.550 I slot print_timing: id 0 | task 1349 | eval time = 982.88 ms / 79 tokens ( 12.60 ms per token, 79.36 tokens per second) 0.25.359.551 I slot print_timing: id 0 | task 1349 | total time = 1126.28 ms / 435 tokens 0.25.359.552 I slot print_timing: id 0 | task 1349 | graphs reused = 1326 0.25.359.553 I slot print_timing: id 0 | task 1349 | graph reallocs = 0 / 0 (same size) / (changed size) 0.25.359.580 I slot release: id 0 | task 1349 | stop processing: n_tokens = 434, truncated = 0 0.25.388.284 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 434, t_last = 25257303 0.25.412.134 I slot launch_slot_: id 0 | task 1431 | processing task, is_child = 0 0.26.421.320 I slot print_timing: id 0 | task 1431 | prompt eval time = 147.96 ms / 410 tokens ( 0.36 ms per token, 2770.98 tokens per second) 0.26.421.325 I slot print_timing: id 0 | task 1431 | eval time = 861.21 ms / 70 tokens ( 12.48 ms per token, 80.12 tokens per second) 0.26.421.327 I slot print_timing: id 0 | task 1431 | total time = 1009.17 ms / 480 tokens 0.26.421.328 I slot print_timing: id 0 | task 1431 | graphs reused = 1394 0.26.421.328 I slot print_timing: id 0 | task 1431 | graph reallocs = 0 / 0 (same size) / (changed size) 0.26.421.358 I slot release: id 0 | task 1431 | stop processing: n_tokens = 479, truncated = 0 0.26.426.204 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 479, t_last = 26319080 0.26.450.957 I slot launch_slot_: id 0 | task 1504 | processing task, is_child = 0 0.27.336.231 I slot print_timing: id 0 | task 1504 | prompt eval time = 149.85 ms / 385 tokens ( 0.39 ms per token, 2569.17 tokens per second) 0.27.336.237 I slot print_timing: id 0 | task 1504 | eval time = 735.40 ms / 58 tokens ( 12.90 ms per token, 77.51 tokens per second) 0.27.336.239 I slot print_timing: id 0 | task 1504 | total time = 885.25 ms / 443 tokens 0.27.336.239 I slot print_timing: id 0 | task 1504 | graphs reused = 1450 0.27.336.240 I slot print_timing: id 0 | task 1504 | graph reallocs = 0 / 0 (same size) / (changed size) 0.27.336.268 I slot release: id 0 | task 1504 | stop processing: n_tokens = 442, truncated = 0 0.27.356.376 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 442, t_last = 27233991 0.27.381.122 I slot launch_slot_: id 0 | task 1565 | processing task, is_child = 0 0.28.703.744 I slot print_timing: id 0 | task 1565 | prompt eval time = 152.48 ms / 395 tokens ( 0.39 ms per token, 2590.55 tokens per second) 0.28.703.750 I slot print_timing: id 0 | task 1565 | eval time = 1170.12 ms / 92 tokens ( 12.86 ms per token, 77.77 tokens per second) 0.28.703.751 I slot print_timing: id 0 | task 1565 | total time = 1322.60 ms / 487 tokens 0.28.703.752 I slot print_timing: id 0 | task 1565 | graphs reused = 1540 0.28.703.753 I slot print_timing: id 0 | task 1565 | graph reallocs = 0 / 0 (same size) / (changed size) 0.28.703.785 I slot release: id 0 | task 1565 | stop processing: n_tokens = 486, truncated = 0 0.28.720.622 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 486, t_last = 28601507 0.28.746.283 I slot launch_slot_: id 0 | task 1660 | processing task, is_child = 0 0.29.929.485 I slot print_timing: id 0 | task 1660 | prompt eval time = 154.35 ms / 430 tokens ( 0.36 ms per token, 2785.79 tokens per second) 0.29.929.491 I slot print_timing: id 0 | task 1660 | eval time = 1028.82 ms / 84 tokens ( 12.40 ms per token, 80.67 tokens per second) 0.29.929.492 I slot print_timing: id 0 | task 1660 | total time = 1183.18 ms / 514 tokens 0.29.929.493 I slot print_timing: id 0 | task 1660 | graphs reused = 1621 0.29.929.494 I slot print_timing: id 0 | task 1660 | graph reallocs = 0 / 0 (same size) / (changed size) 0.29.929.528 I slot release: id 0 | task 1660 | stop processing: n_tokens = 513, truncated = 0 0.29.951.433 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 513, t_last = 29827251 0.29.976.526 I slot launch_slot_: id 0 | task 1747 | processing task, is_child = 0 0.30.896.415 I slot print_timing: id 0 | task 1747 | prompt eval time = 149.84 ms / 392 tokens ( 0.38 ms per token, 2616.12 tokens per second) 0.30.896.420 I slot print_timing: id 0 | task 1747 | eval time = 770.03 ms / 62 tokens ( 12.62 ms per token, 79.22 tokens per second) 0.30.896.421 I slot print_timing: id 0 | task 1747 | total time = 919.87 ms / 454 tokens 0.30.896.422 I slot print_timing: id 0 | task 1747 | graphs reused = 1681 0.30.896.423 I slot print_timing: id 0 | task 1747 | graph reallocs = 0 / 0 (same size) / (changed size) 0.30.896.450 I slot release: id 0 | task 1747 | stop processing: n_tokens = 453, truncated = 0 0.30.916.771 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 453, t_last = 30794172 0.30.942.963 I slot launch_slot_: id 0 | task 1812 | processing task, is_child = 0 0.31.969.738 I slot print_timing: id 0 | task 1812 | prompt eval time = 140.62 ms / 350 tokens ( 0.40 ms per token, 2489.00 tokens per second) 0.31.969.744 I slot print_timing: id 0 | task 1812 | eval time = 886.13 ms / 70 tokens ( 12.84 ms per token, 77.87 tokens per second) 0.31.969.746 I slot print_timing: id 0 | task 1812 | total time = 1026.75 ms / 420 tokens 0.31.969.746 I slot print_timing: id 0 | task 1812 | graphs reused = 1749 0.31.969.747 I slot print_timing: id 0 | task 1812 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.969.779 I slot release: id 0 | task 1812 | stop processing: n_tokens = 419, truncated = 0 0.31.974.834 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 31867501 0.31.999.547 I slot launch_slot_: id 0 | task 1885 | processing task, is_child = 0 0.33.099.093 I slot print_timing: id 0 | task 1885 | prompt eval time = 151.21 ms / 380 tokens ( 0.40 ms per token, 2513.14 tokens per second) 0.33.099.100 I slot print_timing: id 0 | task 1885 | eval time = 948.32 ms / 75 tokens ( 12.82 ms per token, 78.03 tokens per second) 0.33.099.101 I slot print_timing: id 0 | task 1885 | total time = 1099.53 ms / 455 tokens 0.33.099.102 I slot print_timing: id 0 | task 1885 | graphs reused = 1822 0.33.099.103 I slot print_timing: id 0 | task 1885 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.099.132 I slot release: id 0 | task 1885 | stop processing: n_tokens = 454, truncated = 0 0.33.104.585 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 454, t_last = 32996854 0.33.129.376 I slot launch_slot_: id 0 | task 1963 | processing task, is_child = 0 0.34.253.546 I slot print_timing: id 0 | task 1963 | prompt eval time = 151.46 ms / 410 tokens ( 0.37 ms per token, 2706.91 tokens per second) 0.34.253.551 I slot print_timing: id 0 | task 1963 | eval time = 972.68 ms / 80 tokens ( 12.31 ms per token, 81.22 tokens per second) 0.34.253.552 I slot print_timing: id 0 | task 1963 | total time = 1124.15 ms / 490 tokens 0.34.253.553 I slot print_timing: id 0 | task 1963 | graphs reused = 1900 0.34.253.554 I slot print_timing: id 0 | task 1963 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.253.582 I slot release: id 0 | task 1963 | stop processing: n_tokens = 489, truncated = 0 0.34.274.088 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 489, t_last = 34151304 0.34.298.348 I slot launch_slot_: id 0 | task 2046 | processing task, is_child = 0 0.35.302.094 I slot print_timing: id 0 | task 2046 | prompt eval time = 146.21 ms / 387 tokens ( 0.38 ms per token, 2646.95 tokens per second) 0.35.302.099 I slot print_timing: id 0 | task 2046 | eval time = 857.51 ms / 68 tokens ( 12.80 ms per token, 78.13 tokens per second) 0.35.302.100 I slot print_timing: id 0 | task 2046 | total time = 1003.72 ms / 455 tokens 0.35.302.101 I slot print_timing: id 0 | task 2046 | graphs reused = 1966 0.35.302.102 I slot print_timing: id 0 | task 2046 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.302.131 I slot release: id 0 | task 2046 | stop processing: n_tokens = 454, truncated = 0 0.35.334.916 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 454, t_last = 35199854 0.35.359.806 I slot launch_slot_: id 0 | task 2117 | processing task, is_child = 0 0.36.501.767 I slot print_timing: id 0 | task 2117 | prompt eval time = 140.17 ms / 358 tokens ( 0.39 ms per token, 2554.01 tokens per second) 0.36.501.773 I slot print_timing: id 0 | task 2117 | eval time = 1001.77 ms / 79 tokens ( 12.84 ms per token, 77.86 tokens per second) 0.36.501.774 I slot print_timing: id 0 | task 2117 | total time = 1141.94 ms / 437 tokens 0.36.501.775 I slot print_timing: id 0 | task 2117 | graphs reused = 2043 0.36.501.775 I slot print_timing: id 0 | task 2117 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.501.805 I slot release: id 0 | task 2117 | stop processing: n_tokens = 436, truncated = 0 0.36.517.250 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 436, t_last = 36399527 0.36.541.605 I slot launch_slot_: id 0 | task 2199 | processing task, is_child = 0 0.37.569.674 I slot print_timing: id 0 | task 2199 | prompt eval time = 141.01 ms / 359 tokens ( 0.39 ms per token, 2545.99 tokens per second) 0.37.569.680 I slot print_timing: id 0 | task 2199 | eval time = 887.04 ms / 72 tokens ( 12.49 ms per token, 80.04 tokens per second) 0.37.569.681 I slot print_timing: id 0 | task 2199 | total time = 1028.05 ms / 431 tokens 0.37.569.682 I slot print_timing: id 0 | task 2199 | graphs reused = 2113 0.37.569.683 I slot print_timing: id 0 | task 2199 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.569.710 I slot release: id 0 | task 2199 | stop processing: n_tokens = 430, truncated = 0 0.37.587.179 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 430, t_last = 37467432 0.37.611.887 I slot launch_slot_: id 0 | task 2274 | processing task, is_child = 0 0.38.753.433 I slot print_timing: id 0 | task 2274 | prompt eval time = 145.85 ms / 387 tokens ( 0.38 ms per token, 2653.36 tokens per second) 0.38.753.438 I slot print_timing: id 0 | task 2274 | eval time = 995.67 ms / 81 tokens ( 12.45 ms per token, 80.35 tokens per second) 0.38.753.439 I slot print_timing: id 0 | task 2274 | total time = 1141.53 ms / 468 tokens 0.38.753.440 I slot print_timing: id 0 | task 2274 | graphs reused = 2192 0.38.753.441 I slot print_timing: id 0 | task 2274 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.753.470 I slot release: id 0 | task 2274 | stop processing: n_tokens = 467, truncated = 0 0.38.772.365 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 467, t_last = 38651192 0.38.797.205 I slot launch_slot_: id 0 | task 2358 | processing task, is_child = 0 0.39.999.676 I slot print_timing: id 0 | task 2358 | prompt eval time = 150.72 ms / 410 tokens ( 0.37 ms per token, 2720.33 tokens per second) 0.39.999.683 I slot print_timing: id 0 | task 2358 | eval time = 1051.73 ms / 85 tokens ( 12.52 ms per token, 79.87 tokens per second) 0.39.999.684 I slot print_timing: id 0 | task 2358 | total time = 1202.45 ms / 495 tokens 0.39.999.685 I slot print_timing: id 0 | task 2358 | graphs reused = 2275 0.39.999.686 I slot print_timing: id 0 | task 2358 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.999.724 I slot release: id 0 | task 2358 | stop processing: n_tokens = 494, truncated = 0 0.40.043.979 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 494, t_last = 39897447 0.40.070.123 I slot launch_slot_: id 0 | task 2446 | processing task, is_child = 0 0.41.067.773 I slot print_timing: id 0 | task 2446 | prompt eval time = 141.41 ms / 351 tokens ( 0.40 ms per token, 2482.21 tokens per second) 0.41.067.778 I slot print_timing: id 0 | task 2446 | eval time = 856.22 ms / 67 tokens ( 12.97 ms per token, 77.08 tokens per second) 0.41.067.779 I slot print_timing: id 0 | task 2446 | total time = 997.63 ms / 418 tokens 0.41.067.780 I slot print_timing: id 0 | task 2446 | graphs reused = 2340 0.41.067.781 I slot print_timing: id 0 | task 2446 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.067.811 I slot release: id 0 | task 2446 | stop processing: n_tokens = 417, truncated = 0 0.41.101.663 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 417, t_last = 40965533 0.41.127.644 I slot launch_slot_: id 0 | task 2516 | processing task, is_child = 0 0.44.278.357 I slot print_timing: id 0 | task 2516 | n_gen = 239, tg = 79.33 t/s, tg_3s = 79.66 t/s 0.44.329.116 I slot print_timing: id 0 | task 2516 | prompt eval time = 150.41 ms / 393 tokens ( 0.38 ms per token, 2612.79 tokens per second) 0.44.329.121 I slot print_timing: id 0 | task 2516 | eval time = 3051.04 ms / 243 tokens ( 12.61 ms per token, 79.32 tokens per second) 0.44.329.122 I slot print_timing: id 0 | task 2516 | total time = 3201.45 ms / 636 tokens 0.44.329.123 I slot print_timing: id 0 | task 2516 | graphs reused = 2580 0.44.329.124 I slot print_timing: id 0 | task 2516 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.329.154 I slot release: id 0 | task 2516 | stop processing: n_tokens = 635, truncated = 0 0.44.359.066 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 635, t_last = 44226876 0.44.384.687 I slot launch_slot_: id 0 | task 2762 | processing task, is_child = 0 0.44.897.112 I slot print_timing: id 0 | task 2762 | prompt eval time = 138.77 ms / 321 tokens ( 0.43 ms per token, 2313.18 tokens per second) 0.44.897.119 I slot print_timing: id 0 | task 2762 | eval time = 373.63 ms / 30 tokens ( 12.88 ms per token, 77.62 tokens per second) 0.44.897.120 I slot print_timing: id 0 | task 2762 | total time = 512.40 ms / 351 tokens 0.44.897.121 I slot print_timing: id 0 | task 2762 | graphs reused = 2608 0.44.897.122 I slot print_timing: id 0 | task 2762 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.897.152 I slot release: id 0 | task 2762 | stop processing: n_tokens = 350, truncated = 0 0.44.935.244 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 350, t_last = 44794874 0.44.959.489 I slot launch_slot_: id 0 | task 2795 | processing task, is_child = 0 0.46.611.052 I slot print_timing: id 0 | task 2795 | prompt eval time = 139.06 ms / 330 tokens ( 0.42 ms per token, 2373.09 tokens per second) 0.46.611.058 I slot print_timing: id 0 | task 2795 | eval time = 1512.48 ms / 121 tokens ( 12.60 ms per token, 79.34 tokens per second) 0.46.611.059 I slot print_timing: id 0 | task 2795 | total time = 1651.54 ms / 451 tokens 0.46.611.060 I slot print_timing: id 0 | task 2795 | graphs reused = 2727 0.46.611.061 I slot print_timing: id 0 | task 2795 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.611.093 I slot release: id 0 | task 2795 | stop processing: n_tokens = 450, truncated = 0 0.46.648.808 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 450, t_last = 46508816 0.46.673.678 I slot launch_slot_: id 0 | task 2919 | processing task, is_child = 0 0.47.541.871 I slot print_timing: id 0 | task 2919 | prompt eval time = 136.59 ms / 341 tokens ( 0.40 ms per token, 2496.49 tokens per second) 0.47.541.877 I slot print_timing: id 0 | task 2919 | eval time = 731.58 ms / 60 tokens ( 12.40 ms per token, 80.65 tokens per second) 0.47.541.878 I slot print_timing: id 0 | task 2919 | total time = 868.17 ms / 401 tokens 0.47.541.879 I slot print_timing: id 0 | task 2919 | graphs reused = 2785 0.47.541.880 I slot print_timing: id 0 | task 2919 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.541.908 I slot release: id 0 | task 2919 | stop processing: n_tokens = 400, truncated = 0 0.47.566.283 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 47439630 0.47.590.024 I slot launch_slot_: id 0 | task 2982 | processing task, is_child = 0 0.48.488.112 I slot print_timing: id 0 | task 2982 | prompt eval time = 137.92 ms / 338 tokens ( 0.41 ms per token, 2450.68 tokens per second) 0.48.488.118 I slot print_timing: id 0 | task 2982 | eval time = 760.15 ms / 60 tokens ( 12.88 ms per token, 77.62 tokens per second) 0.48.488.119 I slot print_timing: id 0 | task 2982 | total time = 898.07 ms / 398 tokens 0.48.488.120 I slot print_timing: id 0 | task 2982 | graphs reused = 2843 0.48.488.121 I slot print_timing: id 0 | task 2982 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.488.149 I slot release: id 0 | task 2982 | stop processing: n_tokens = 397, truncated = 0 0.48.517.846 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 397, t_last = 48385871 0.48.542.022 I slot launch_slot_: id 0 | task 3045 | processing task, is_child = 0 0.49.402.314 I slot print_timing: id 0 | task 3045 | prompt eval time = 154.24 ms / 395 tokens ( 0.39 ms per token, 2560.88 tokens per second) 0.49.402.320 I slot print_timing: id 0 | task 3045 | eval time = 706.03 ms / 56 tokens ( 12.84 ms per token, 77.90 tokens per second) 0.49.402.321 I slot print_timing: id 0 | task 3045 | total time = 860.27 ms / 451 tokens 0.49.402.322 I slot print_timing: id 0 | task 3045 | graphs reused = 2897 0.49.402.322 I slot print_timing: id 0 | task 3045 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.402.351 I slot release: id 0 | task 3045 | stop processing: n_tokens = 450, truncated = 0 0.49.432.313 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 450, t_last = 49300074 0.49.456.708 I slot launch_slot_: id 0 | task 3104 | processing task, is_child = 0 0.50.698.885 I slot print_timing: id 0 | task 3104 | prompt eval time = 211.89 ms / 528 tokens ( 0.40 ms per token, 2491.89 tokens per second) 0.50.698.890 I slot print_timing: id 0 | task 3104 | eval time = 1030.27 ms / 83 tokens ( 12.56 ms per token, 79.59 tokens per second) 0.50.698.891 I slot print_timing: id 0 | task 3104 | total time = 1242.16 ms / 611 tokens 0.50.698.892 I slot print_timing: id 0 | task 3104 | graphs reused = 2978 0.50.698.893 I slot print_timing: id 0 | task 3104 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.698.928 I slot release: id 0 | task 3104 | stop processing: n_tokens = 610, truncated = 0 0.50.713.583 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 610, t_last = 50596650 0.50.745.879 I slot launch_slot_: id 0 | task 3191 | processing task, is_child = 0 0.51.647.482 I slot print_timing: id 0 | task 3191 | prompt eval time = 155.23 ms / 331 tokens ( 0.47 ms per token, 2132.31 tokens per second) 0.51.647.488 I slot print_timing: id 0 | task 3191 | eval time = 746.35 ms / 61 tokens ( 12.44 ms per token, 80.39 tokens per second) 0.51.647.489 I slot print_timing: id 0 | task 3191 | total time = 901.59 ms / 392 tokens 0.51.647.491 I slot print_timing: id 0 | task 3191 | graphs reused = 3037 0.51.647.492 I slot print_timing: id 0 | task 3191 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.647.520 I slot release: id 0 | task 3191 | stop processing: n_tokens = 403, truncated = 0 0.51.683.714 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 403, t_last = 51545243 0.51.712.793 I slot launch_slot_: id 0 | task 3255 | processing task, is_child = 0 0.52.768.391 I slot print_timing: id 0 | task 3255 | prompt eval time = 167.51 ms / 362 tokens ( 0.46 ms per token, 2161.04 tokens per second) 0.52.768.398 I slot print_timing: id 0 | task 3255 | eval time = 888.07 ms / 70 tokens ( 12.87 ms per token, 77.70 tokens per second) 0.52.768.399 I slot print_timing: id 0 | task 3255 | total time = 1055.58 ms / 432 tokens 0.52.768.400 I slot print_timing: id 0 | task 3255 | graphs reused = 3105 0.52.768.401 I slot print_timing: id 0 | task 3255 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.768.430 I slot release: id 0 | task 3255 | stop processing: n_tokens = 443, truncated = 0 0.52.791.057 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 443, t_last = 52666152 0.52.821.202 I slot launch_slot_: id 0 | task 3328 | processing task, is_child = 0 0.54.005.806 I slot print_timing: id 0 | task 3328 | prompt eval time = 172.22 ms / 419 tokens ( 0.41 ms per token, 2432.96 tokens per second) 0.54.005.812 I slot print_timing: id 0 | task 3328 | eval time = 1012.37 ms / 80 tokens ( 12.81 ms per token, 78.04 tokens per second) 0.54.005.813 I slot print_timing: id 0 | task 3328 | total time = 1184.58 ms / 499 tokens 0.54.005.814 I slot print_timing: id 0 | task 3328 | graphs reused = 3183 0.54.005.815 I slot print_timing: id 0 | task 3328 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.005.845 I slot release: id 0 | task 3328 | stop processing: n_tokens = 510, truncated = 0 0.54.025.730 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 510, t_last = 53903567 0.54.055.585 I slot launch_slot_: id 0 | task 3411 | processing task, is_child = 0 0.54.769.649 I slot print_timing: id 0 | task 3411 | prompt eval time = 183.34 ms / 423 tokens ( 0.43 ms per token, 2307.21 tokens per second) 0.54.769.655 I slot print_timing: id 0 | task 3411 | eval time = 530.71 ms / 44 tokens ( 12.34 ms per token, 81.02 tokens per second) 0.54.769.656 I slot print_timing: id 0 | task 3411 | total time = 714.05 ms / 467 tokens 0.54.769.658 I slot print_timing: id 0 | task 3411 | graphs reused = 3225 0.54.769.658 I slot print_timing: id 0 | task 3411 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.769.689 I slot release: id 0 | task 3411 | stop processing: n_tokens = 478, truncated = 0 0.54.785.961 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 478, t_last = 54667412 0.54.815.907 I slot launch_slot_: id 0 | task 3458 | processing task, is_child = 0 0.55.490.364 I slot print_timing: id 0 | task 3458 | prompt eval time = 155.89 ms / 341 tokens ( 0.46 ms per token, 2187.41 tokens per second) 0.55.490.370 I slot print_timing: id 0 | task 3458 | eval time = 518.55 ms / 43 tokens ( 12.35 ms per token, 81.00 tokens per second) 0.55.490.371 I slot print_timing: id 0 | task 3458 | total time = 674.44 ms / 384 tokens 0.55.490.372 I slot print_timing: id 0 | task 3458 | graphs reused = 3266 0.55.490.373 I slot print_timing: id 0 | task 3458 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.490.403 I slot release: id 0 | task 3458 | stop processing: n_tokens = 395, truncated = 0 0.55.530.989 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 395, t_last = 55388125 0.55.560.022 I slot launch_slot_: id 0 | task 3504 | processing task, is_child = 0 0.56.551.375 I slot print_timing: id 0 | task 3504 | prompt eval time = 160.49 ms / 356 tokens ( 0.45 ms per token, 2218.23 tokens per second) 0.56.551.381 I slot print_timing: id 0 | task 3504 | eval time = 830.85 ms / 66 tokens ( 12.78 ms per token, 78.23 tokens per second) 0.56.551.382 I slot print_timing: id 0 | task 3504 | total time = 991.34 ms / 422 tokens 0.56.551.383 I slot print_timing: id 0 | task 3504 | graphs reused = 3330 0.56.551.383 I slot print_timing: id 0 | task 3504 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.551.412 I slot release: id 0 | task 3504 | stop processing: n_tokens = 433, truncated = 0 0.56.592.114 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 433, t_last = 56449134 0.56.592.162 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.481 MiB) 0.56.625.849 I slot launch_slot_: id 0 | task 3573 | processing task, is_child = 0 0.57.554.922 I slot print_timing: id 0 | task 3573 | prompt eval time = 168.88 ms / 362 tokens ( 0.47 ms per token, 2143.52 tokens per second) 0.57.554.928 I slot print_timing: id 0 | task 3573 | eval time = 760.17 ms / 60 tokens ( 12.88 ms per token, 77.61 tokens per second) 0.57.554.929 I slot print_timing: id 0 | task 3573 | total time = 929.05 ms / 422 tokens 0.57.554.930 I slot print_timing: id 0 | task 3573 | graphs reused = 3388 0.57.554.930 I slot print_timing: id 0 | task 3573 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.554.960 I slot release: id 0 | task 3573 | stop processing: n_tokens = 433, truncated = 0 0.57.577.937 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 433, t_last = 57452682 0.57.577.981 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.636 MiB) 0.57.610.063 I slot launch_slot_: id 0 | task 3636 | processing task, is_child = 0 0.58.863.085 I slot print_timing: id 0 | task 3636 | prompt eval time = 169.80 ms / 391 tokens ( 0.43 ms per token, 2302.75 tokens per second) 0.58.863.090 I slot print_timing: id 0 | task 3636 | eval time = 1083.21 ms / 88 tokens ( 12.45 ms per token, 80.32 tokens per second) 0.58.863.091 I slot print_timing: id 0 | task 3636 | total time = 1253.00 ms / 479 tokens 0.58.863.092 I slot print_timing: id 0 | task 3636 | graphs reused = 3474 0.58.863.093 I slot print_timing: id 0 | task 3636 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.863.122 I slot release: id 0 | task 3636 | stop processing: n_tokens = 490, truncated = 0 0.58.885.507 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 490, t_last = 58760844 0.58.885.555 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.449 MiB) 0.58.888.374 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.231 MiB) 0.58.922.710 I slot launch_slot_: id 0 | task 3727 | processing task, is_child = 0 0.59.737.201 I slot print_timing: id 0 | task 3727 | prompt eval time = 155.71 ms / 343 tokens ( 0.45 ms per token, 2202.84 tokens per second) 0.59.737.207 I slot print_timing: id 0 | task 3727 | eval time = 658.77 ms / 54 tokens ( 12.43 ms per token, 80.45 tokens per second) 0.59.737.208 I slot print_timing: id 0 | task 3727 | total time = 814.47 ms / 397 tokens 0.59.737.208 I slot print_timing: id 0 | task 3727 | graphs reused = 3526 0.59.737.209 I slot print_timing: id 0 | task 3727 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.737.236 I slot release: id 0 | task 3727 | stop processing: n_tokens = 408, truncated = 0 0.59.777.304 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 408, t_last = 59634958 0.59.777.351 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.887 MiB) 0.59.810.604 I slot launch_slot_: id 0 | task 3784 | processing task, is_child = 0 1.00.556.717 I slot print_timing: id 0 | task 3784 | prompt eval time = 169.05 ms / 401 tokens ( 0.42 ms per token, 2372.07 tokens per second) 1.00.556.724 I slot print_timing: id 0 | task 3784 | eval time = 577.04 ms / 46 tokens ( 12.82 ms per token, 77.98 tokens per second) 1.00.556.725 I slot print_timing: id 0 | task 3784 | total time = 746.09 ms / 447 tokens 1.00.556.726 I slot print_timing: id 0 | task 3784 | graphs reused = 3570 1.00.556.727 I slot print_timing: id 0 | task 3784 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.556.762 I slot release: id 0 | task 3784 | stop processing: n_tokens = 458, truncated = 0 1.00.573.093 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 60454484 1.00.573.149 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.074 MiB) 1.00.607.239 I slot launch_slot_: id 0 | task 3833 | processing task, is_child = 0 1.01.628.336 I slot print_timing: id 0 | task 3833 | prompt eval time = 160.37 ms / 355 tokens ( 0.45 ms per token, 2213.69 tokens per second) 1.01.628.342 I slot print_timing: id 0 | task 3833 | eval time = 860.71 ms / 68 tokens ( 12.85 ms per token, 77.84 tokens per second) 1.01.628.343 I slot print_timing: id 0 | task 3833 | total time = 1021.08 ms / 423 tokens 1.01.628.345 I slot print_timing: id 0 | task 3833 | graphs reused = 3636 1.01.628.346 I slot print_timing: id 0 | task 3833 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.628.372 I slot release: id 0 | task 3833 | stop processing: n_tokens = 434, truncated = 0 1.01.633.087 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 434, t_last = 61526095 1.01.633.139 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.076 MiB) 1.01.667.899 I slot launch_slot_: id 0 | task 3904 | processing task, is_child = 0 1.02.793.798 I slot print_timing: id 0 | task 3904 | prompt eval time = 159.86 ms / 351 tokens ( 0.46 ms per token, 2195.71 tokens per second) 1.02.793.804 I slot print_timing: id 0 | task 3904 | eval time = 966.02 ms / 76 tokens ( 12.88 ms per token, 77.64 tokens per second) 1.02.793.805 I slot print_timing: id 0 | task 3904 | total time = 1125.88 ms / 427 tokens 1.02.793.806 I slot print_timing: id 0 | task 3904 | graphs reused = 3710 1.02.793.807 I slot print_timing: id 0 | task 3904 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.793.834 I slot release: id 0 | task 3904 | stop processing: n_tokens = 438, truncated = 0 1.02.820.085 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 438, t_last = 62691556 1.02.820.137 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 168.202 MiB) 1.02.822.920 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.730 MiB) 1.02.859.632 I slot launch_slot_: id 0 | task 3983 | processing task, is_child = 0 1.04.459.033 I slot print_timing: id 0 | task 3983 | prompt eval time = 186.76 ms / 475 tokens ( 0.39 ms per token, 2543.32 tokens per second) 1.04.459.039 I slot print_timing: id 0 | task 3983 | eval time = 1412.62 ms / 113 tokens ( 12.61 ms per token, 79.29 tokens per second) 1.04.459.041 I slot print_timing: id 0 | task 3983 | total time = 1599.38 ms / 588 tokens 1.04.459.042 I slot print_timing: id 0 | task 3983 | graphs reused = 3820 1.04.459.043 I slot print_timing: id 0 | task 3983 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.459.078 I slot release: id 0 | task 3983 | stop processing: n_tokens = 599, truncated = 0 1.04.492.626 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 599, t_last = 64356800 1.04.492.688 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.386 MiB) 1.04.530.639 I slot launch_slot_: id 0 | task 4099 | processing task, is_child = 0 1.06.431.060 I slot print_timing: id 0 | task 4099 | prompt eval time = 188.72 ms / 440 tokens ( 0.43 ms per token, 2331.50 tokens per second) 1.06.431.066 I slot print_timing: id 0 | task 4099 | eval time = 1711.68 ms / 135 tokens ( 12.77 ms per token, 78.29 tokens per second) 1.06.431.068 I slot print_timing: id 0 | task 4099 | total time = 1900.40 ms / 575 tokens 1.06.431.068 I slot print_timing: id 0 | task 4099 | graphs reused = 3952 1.06.431.069 I slot print_timing: id 0 | task 4099 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.431.099 I slot release: id 0 | task 4099 | stop processing: n_tokens = 586, truncated = 0 1.06.459.579 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 586, t_last = 66328822 1.06.459.636 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.981 MiB) 1.06.494.736 I slot launch_slot_: id 0 | task 4237 | processing task, is_child = 0 1.07.524.387 I slot print_timing: id 0 | task 4237 | prompt eval time = 154.95 ms / 345 tokens ( 0.45 ms per token, 2226.55 tokens per second) 1.07.524.393 I slot print_timing: id 0 | task 4237 | eval time = 874.69 ms / 72 tokens ( 12.32 ms per token, 81.17 tokens per second) 1.07.524.394 I slot print_timing: id 0 | task 4237 | total time = 1029.63 ms / 417 tokens 1.07.524.395 I slot print_timing: id 0 | task 4237 | graphs reused = 4022 1.07.524.396 I slot print_timing: id 0 | task 4237 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.524.423 I slot release: id 0 | task 4237 | stop processing: n_tokens = 428, truncated = 0 1.07.567.286 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 428, t_last = 67422145 1.07.567.334 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.794 MiB) 1.07.570.100 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 1.07.603.703 I slot launch_slot_: id 0 | task 4312 | processing task, is_child = 0 1.08.740.987 I slot print_timing: id 0 | task 4312 | prompt eval time = 164.78 ms / 382 tokens ( 0.43 ms per token, 2318.17 tokens per second) 1.08.740.992 I slot print_timing: id 0 | task 4312 | eval time = 972.48 ms / 77 tokens ( 12.80 ms per token, 78.15 tokens per second) 1.08.740.993 I slot print_timing: id 0 | task 4312 | total time = 1137.26 ms / 459 tokens 1.08.740.994 I slot print_timing: id 0 | task 4312 | graphs reused = 4097 1.08.740.995 I slot print_timing: id 0 | task 4312 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.741.027 I slot release: id 0 | task 4312 | stop processing: n_tokens = 470, truncated = 0 1.08.757.751 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 68638749 1.08.757.797 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.731 MiB) 1.08.791.931 I slot launch_slot_: id 0 | task 4392 | processing task, is_child = 0 1.09.517.191 I slot print_timing: id 0 | task 4392 | prompt eval time = 159.50 ms / 337 tokens ( 0.47 ms per token, 2112.84 tokens per second) 1.09.517.196 I slot print_timing: id 0 | task 4392 | eval time = 565.74 ms / 45 tokens ( 12.86 ms per token, 77.77 tokens per second) 1.09.517.198 I slot print_timing: id 0 | task 4392 | total time = 725.24 ms / 382 tokens 1.09.517.199 I slot print_timing: id 0 | task 4392 | graphs reused = 4140 1.09.517.200 I slot print_timing: id 0 | task 4392 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.517.228 I slot release: id 0 | task 4392 | stop processing: n_tokens = 393, truncated = 0 1.09.522.341 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 69414950 1.09.522.387 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.137 MiB) 1.09.554.987 I slot launch_slot_: id 0 | task 4440 | processing task, is_child = 0 1.10.599.357 I slot print_timing: id 0 | task 4440 | prompt eval time = 171.33 ms / 402 tokens ( 0.43 ms per token, 2346.38 tokens per second) 1.10.599.363 I slot print_timing: id 0 | task 4440 | eval time = 873.02 ms / 70 tokens ( 12.65 ms per token, 79.04 tokens per second) 1.10.599.364 I slot print_timing: id 0 | task 4440 | total time = 1044.35 ms / 472 tokens 1.10.599.365 I slot print_timing: id 0 | task 4440 | graphs reused = 4208 1.10.599.365 I slot print_timing: id 0 | task 4440 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.599.395 I slot release: id 0 | task 4440 | stop processing: n_tokens = 483, truncated = 0 1.10.604.774 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 483, t_last = 70497117 1.10.604.824 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.012 MiB) 1.10.607.593 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.575 MiB) 1.10.643.236 I slot launch_slot_: id 0 | task 4513 | processing task, is_child = 0 1.11.866.141 I slot print_timing: id 0 | task 4513 | prompt eval time = 211.44 ms / 549 tokens ( 0.39 ms per token, 2596.51 tokens per second) 1.11.866.147 I slot print_timing: id 0 | task 4513 | eval time = 1011.45 ms / 83 tokens ( 12.33 ms per token, 81.07 tokens per second) 1.11.866.148 I slot print_timing: id 0 | task 4513 | total time = 1222.89 ms / 632 tokens 1.11.866.149 I slot print_timing: id 0 | task 4513 | graphs reused = 4289 1.11.866.150 I slot print_timing: id 0 | task 4513 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.866.182 I slot release: id 0 | task 4513 | stop processing: n_tokens = 643, truncated = 0 1.11.906.978 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 643, t_last = 71763905 1.11.907.044 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.011 MiB) 1.11.947.134 I slot launch_slot_: id 0 | task 4600 | processing task, is_child = 0 1.13.103.818 I slot print_timing: id 0 | task 4600 | prompt eval time = 236.69 ms / 616 tokens ( 0.38 ms per token, 2602.59 tokens per second) 1.13.103.824 I slot print_timing: id 0 | task 4600 | eval time = 919.98 ms / 73 tokens ( 12.78 ms per token, 78.26 tokens per second) 1.13.103.825 I slot print_timing: id 0 | task 4600 | total time = 1156.66 ms / 689 tokens 1.13.103.826 I slot print_timing: id 0 | task 4600 | graphs reused = 4360 1.13.103.827 I slot print_timing: id 0 | task 4600 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.103.862 I slot release: id 0 | task 4600 | stop processing: n_tokens = 700, truncated = 0 1.13.140.223 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 700, t_last = 73001585 1.13.140.289 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.324 MiB) 1.13.142.992 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.700 MiB) 1.13.184.336 I slot launch_slot_: id 0 | task 4677 | processing task, is_child = 0 1.14.474.793 I slot print_timing: id 0 | task 4677 | prompt eval time = 258.81 ms / 665 tokens ( 0.39 ms per token, 2569.40 tokens per second) 1.14.474.800 I slot print_timing: id 0 | task 4677 | eval time = 1031.62 ms / 80 tokens ( 13.06 ms per token, 76.58 tokens per second) 1.14.474.801 I slot print_timing: id 0 | task 4677 | total time = 1290.44 ms / 745 tokens 1.14.474.803 I slot print_timing: id 0 | task 4677 | graphs reused = 4438 1.14.474.804 I slot print_timing: id 0 | task 4677 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.474.843 I slot release: id 0 | task 4677 | stop processing: n_tokens = 756, truncated = 0 1.14.490.733 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 756, t_last = 74372565 1.14.490.809 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.324 MiB) 1.14.493.840 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.732 MiB) 1.14.539.487 I slot launch_slot_: id 0 | task 4761 | processing task, is_child = 0 1.15.456.250 I slot print_timing: id 0 | task 4761 | prompt eval time = 242.73 ms / 645 tokens ( 0.38 ms per token, 2657.31 tokens per second) 1.15.456.256 I slot print_timing: id 0 | task 4761 | eval time = 674.02 ms / 55 tokens ( 12.48 ms per token, 80.12 tokens per second) 1.15.456.257 I slot print_timing: id 0 | task 4761 | total time = 916.74 ms / 700 tokens 1.15.456.258 I slot print_timing: id 0 | task 4761 | graphs reused = 4491 1.15.456.258 I slot print_timing: id 0 | task 4761 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.456.294 I slot release: id 0 | task 4761 | stop processing: n_tokens = 711, truncated = 0 1.15.461.576 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 711, t_last = 75354016 1.15.461.651 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.575 MiB) 1.15.508.329 I slot launch_slot_: id 0 | task 4820 | processing task, is_child = 0 1.16.648.466 I slot print_timing: id 0 | task 4820 | prompt eval time = 189.43 ms / 474 tokens ( 0.40 ms per token, 2502.20 tokens per second) 1.16.648.472 I slot print_timing: id 0 | task 4820 | eval time = 950.68 ms / 75 tokens ( 12.85 ms per token, 77.84 tokens per second) 1.16.648.473 I slot print_timing: id 0 | task 4820 | total time = 1140.11 ms / 549 tokens 1.16.648.474 I slot print_timing: id 0 | task 4820 | graphs reused = 4563 1.16.648.474 I slot print_timing: id 0 | task 4820 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.648.506 I slot release: id 0 | task 4820 | stop processing: n_tokens = 560, truncated = 0 1.16.681.258 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 76546229 1.16.681.310 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.951 MiB) 1.16.684.003 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.795 MiB) 1.16.725.605 I slot launch_slot_: id 0 | task 4898 | processing task, is_child = 0 1.17.668.836 I slot print_timing: id 0 | task 4898 | prompt eval time = 236.22 ms / 617 tokens ( 0.38 ms per token, 2611.98 tokens per second) 1.17.668.842 I slot print_timing: id 0 | task 4898 | eval time = 706.99 ms / 55 tokens ( 13.09 ms per token, 76.38 tokens per second) 1.17.668.843 I slot print_timing: id 0 | task 4898 | total time = 943.20 ms / 672 tokens 1.17.668.845 I slot print_timing: id 0 | task 4898 | graphs reused = 4616 1.17.668.846 I slot print_timing: id 0 | task 4898 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.668.885 I slot release: id 0 | task 4898 | stop processing: n_tokens = 683, truncated = 0 1.17.710.562 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 683, t_last = 77566607 1.17.710.629 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.919 MiB) 1.17.756.222 I slot launch_slot_: id 0 | task 4957 | processing task, is_child = 0 1.18.890.247 I slot print_timing: id 0 | task 4957 | prompt eval time = 234.06 ms / 601 tokens ( 0.39 ms per token, 2567.68 tokens per second) 1.18.890.253 I slot print_timing: id 0 | task 4957 | eval time = 899.94 ms / 72 tokens ( 12.68 ms per token, 78.89 tokens per second) 1.18.890.254 I slot print_timing: id 0 | task 4957 | total time = 1134.00 ms / 673 tokens 1.18.890.255 I slot print_timing: id 0 | task 4957 | graphs reused = 4686 1.18.890.256 I slot print_timing: id 0 | task 4957 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.890.292 I slot release: id 0 | task 4957 | stop processing: n_tokens = 684, truncated = 0 1.18.925.893 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 684, t_last = 78788014 1.18.925.959 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.855 MiB) 1.18.928.785 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.950 MiB) 1.18.977.538 I slot launch_slot_: id 0 | task 5033 | processing task, is_child = 0 1.19.763.376 I slot print_timing: id 0 | task 5033 | prompt eval time = 214.05 ms / 533 tokens ( 0.40 ms per token, 2490.04 tokens per second) 1.19.763.382 I slot print_timing: id 0 | task 5033 | eval time = 571.76 ms / 47 tokens ( 12.43 ms per token, 80.45 tokens per second) 1.19.763.383 I slot print_timing: id 0 | task 5033 | total time = 785.81 ms / 580 tokens 1.19.763.384 I slot print_timing: id 0 | task 5033 | graphs reused = 4731 1.19.763.385 I slot print_timing: id 0 | task 5033 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.763.431 I slot release: id 0 | task 5033 | stop processing: n_tokens = 591, truncated = 0 1.19.769.515 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 591, t_last = 79661154 1.19.769.571 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.044 MiB) 1.19.772.395 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.950 MiB) 1.19.819.387 I slot launch_slot_: id 0 | task 5084 | processing task, is_child = 0 1.20.913.191 I slot print_timing: id 0 | task 5084 | prompt eval time = 198.73 ms / 480 tokens ( 0.41 ms per token, 2415.37 tokens per second) 1.20.913.197 I slot print_timing: id 0 | task 5084 | eval time = 895.06 ms / 71 tokens ( 12.79 ms per token, 78.21 tokens per second) 1.20.913.199 I slot print_timing: id 0 | task 5084 | total time = 1093.78 ms / 551 tokens 1.20.913.200 I slot print_timing: id 0 | task 5084 | graphs reused = 4799 1.20.913.201 I slot print_timing: id 0 | task 5084 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.913.233 I slot release: id 0 | task 5084 | stop processing: n_tokens = 579, truncated = 0 1.20.918.586 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 579, t_last = 80810956 1.20.918.643 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.387 MiB) 1.20.956.713 I slot launch_slot_: id 0 | task 5158 | processing task, is_child = 0 1.21.889.985 I slot print_timing: id 0 | task 5158 | prompt eval time = 219.18 ms / 567 tokens ( 0.39 ms per token, 2586.91 tokens per second) 1.21.889.991 I slot print_timing: id 0 | task 5158 | eval time = 714.07 ms / 57 tokens ( 12.75 ms per token, 78.42 tokens per second) 1.21.889.992 I slot print_timing: id 0 | task 5158 | total time = 933.25 ms / 624 tokens 1.21.889.993 I slot print_timing: id 0 | task 5158 | graphs reused = 4854 1.21.889.994 I slot print_timing: id 0 | task 5158 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.890.026 I slot release: id 0 | task 5158 | stop processing: n_tokens = 652, truncated = 0 1.21.917.481 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 652, t_last = 81787749 1.21.917.542 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.199 MiB) 1.21.920.244 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.356 MiB) 1.21.976.503 I slot launch_slot_: id 0 | task 5219 | processing task, is_child = 0 1.24.194.489 I slot print_timing: id 0 | task 5219 | prompt eval time = 201.25 ms / 506 tokens ( 0.40 ms per token, 2514.26 tokens per second) 1.24.194.494 I slot print_timing: id 0 | task 5219 | eval time = 2016.71 ms / 164 tokens ( 12.37 ms per token, 80.82 tokens per second) 1.24.194.495 I slot print_timing: id 0 | task 5219 | total time = 2217.97 ms / 670 tokens 1.24.194.496 I slot print_timing: id 0 | task 5219 | graphs reused = 5016 1.24.194.497 I slot print_timing: id 0 | task 5219 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.194.529 I slot release: id 0 | task 5219 | stop processing: n_tokens = 698, truncated = 0 1.24.230.793 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 698, t_last = 84092251 1.24.230.857 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.201 MiB) 1.24.233.678 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.793 MiB) 1.24.285.292 I slot launch_slot_: id 0 | task 5386 | processing task, is_child = 0 1.24.971.472 I slot print_timing: id 0 | task 5386 | prompt eval time = 186.36 ms / 436 tokens ( 0.43 ms per token, 2339.55 tokens per second) 1.24.971.478 I slot print_timing: id 0 | task 5386 | eval time = 499.80 ms / 40 tokens ( 12.82 ms per token, 78.03 tokens per second) 1.24.971.479 I slot print_timing: id 0 | task 5386 | total time = 686.16 ms / 476 tokens 1.24.971.480 I slot print_timing: id 0 | task 5386 | graphs reused = 5054 1.24.971.481 I slot print_timing: id 0 | task 5386 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.971.511 I slot release: id 0 | task 5386 | stop processing: n_tokens = 504, truncated = 0 1.24.976.636 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 84869233 1.24.976.689 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 170.610 MiB) 1.25.015.734 I slot launch_slot_: id 0 | task 5429 | processing task, is_child = 0 1.26.012.716 I slot print_timing: id 0 | task 5429 | prompt eval time = 213.70 ms / 519 tokens ( 0.41 ms per token, 2428.67 tokens per second) 1.26.012.722 I slot print_timing: id 0 | task 5429 | eval time = 783.27 ms / 62 tokens ( 12.84 ms per token, 77.88 tokens per second) 1.26.012.724 I slot print_timing: id 0 | task 5429 | total time = 996.96 ms / 581 tokens 1.26.012.724 I slot print_timing: id 0 | task 5429 | graphs reused = 5114 1.26.012.725 I slot print_timing: id 0 | task 5429 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.012.759 I slot release: id 0 | task 5429 | stop processing: n_tokens = 609, truncated = 0 1.26.018.012 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 609, t_last = 85910481 1.26.018.072 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 161.697 MiB) 1.26.020.926 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.825 MiB) 1.26.070.893 I slot launch_slot_: id 0 | task 5495 | processing task, is_child = 0 1.26.830.894 I slot print_timing: id 0 | task 5495 | prompt eval time = 187.42 ms / 465 tokens ( 0.40 ms per token, 2481.01 tokens per second) 1.26.830.899 I slot print_timing: id 0 | task 5495 | eval time = 572.56 ms / 46 tokens ( 12.72 ms per token, 78.59 tokens per second) 1.26.830.900 I slot print_timing: id 0 | task 5495 | total time = 759.98 ms / 511 tokens 1.26.830.901 I slot print_timing: id 0 | task 5495 | graphs reused = 5157 1.26.830.902 I slot print_timing: id 0 | task 5495 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.830.932 I slot release: id 0 | task 5495 | stop processing: n_tokens = 542, truncated = 0 1.26.864.018 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 542, t_last = 86728654 1.26.864.064 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.261 MiB) 1.26.866.736 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.167 MiB) 1.26.915.778 I slot launch_slot_: id 0 | task 5544 | processing task, is_child = 0 1.27.814.070 I slot print_timing: id 0 | task 5544 | prompt eval time = 180.88 ms / 431 tokens ( 0.42 ms per token, 2382.77 tokens per second) 1.27.814.075 I slot print_timing: id 0 | task 5544 | eval time = 717.39 ms / 59 tokens ( 12.37 ms per token, 80.85 tokens per second) 1.27.814.076 I slot print_timing: id 0 | task 5544 | total time = 898.27 ms / 490 tokens 1.27.814.077 I slot print_timing: id 0 | task 5544 | graphs reused = 5213 1.27.814.078 I slot print_timing: id 0 | task 5544 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.814.108 I slot release: id 0 | task 5544 | stop processing: n_tokens = 521, truncated = 0 1.27.842.804 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 521, t_last = 87711830 1.27.842.856 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.825 MiB) 1.27.845.713 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 220.079 MiB) 1.27.891.072 I slot launch_slot_: id 0 | task 5606 | processing task, is_child = 0 1.28.863.963 I slot print_timing: id 0 | task 5606 | prompt eval time = 181.01 ms / 457 tokens ( 0.40 ms per token, 2524.72 tokens per second) 1.28.863.968 I slot print_timing: id 0 | task 5606 | eval time = 791.86 ms / 63 tokens ( 12.77 ms per token, 78.30 tokens per second) 1.28.863.969 I slot print_timing: id 0 | task 5606 | total time = 972.87 ms / 520 tokens 1.28.863.970 I slot print_timing: id 0 | task 5606 | graphs reused = 5273 1.28.863.971 I slot print_timing: id 0 | task 5606 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.864.000 I slot release: id 0 | task 5606 | stop processing: n_tokens = 551, truncated = 0 1.28.893.311 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 551, t_last = 88761723 1.28.893.365 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.605 MiB) 1.28.896.942 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.856 MiB) 1.28.943.371 I slot launch_slot_: id 0 | task 5672 | processing task, is_child = 0 1.29.653.286 I slot print_timing: id 0 | task 5672 | prompt eval time = 186.09 ms / 439 tokens ( 0.42 ms per token, 2359.05 tokens per second) 1.29.653.292 I slot print_timing: id 0 | task 5672 | eval time = 523.80 ms / 42 tokens ( 12.78 ms per token, 78.27 tokens per second) 1.29.653.293 I slot print_timing: id 0 | task 5672 | total time = 709.90 ms / 481 tokens 1.29.653.294 I slot print_timing: id 0 | task 5672 | graphs reused = 5313 1.29.653.295 I slot print_timing: id 0 | task 5672 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.653.325 I slot release: id 0 | task 5672 | stop processing: n_tokens = 512, truncated = 0 1.29.672.706 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 512, t_last = 89551048 1.29.672.759 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.952 MiB) 1.29.725.606 I slot launch_slot_: id 0 | task 5717 | processing task, is_child = 0 1.30.829.578 I slot print_timing: id 0 | task 5717 | prompt eval time = 228.80 ms / 606 tokens ( 0.38 ms per token, 2648.64 tokens per second) 1.30.829.583 I slot print_timing: id 0 | task 5717 | eval time = 875.15 ms / 70 tokens ( 12.68 ms per token, 78.84 tokens per second) 1.30.829.585 I slot print_timing: id 0 | task 5717 | total time = 1103.95 ms / 676 tokens 1.30.829.585 I slot print_timing: id 0 | task 5717 | graphs reused = 5381 1.30.829.586 I slot print_timing: id 0 | task 5717 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.829.622 I slot release: id 0 | task 5717 | stop processing: n_tokens = 707, truncated = 0 1.30.843.980 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 707, t_last = 90727344 1.30.844.033 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.951 MiB) 1.30.847.412 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.355 MiB) 1.30.913.771 I slot launch_slot_: id 0 | task 5791 | processing task, is_child = 0 1.31.743.405 I slot print_timing: id 0 | task 5791 | prompt eval time = 184.92 ms / 477 tokens ( 0.39 ms per token, 2579.51 tokens per second) 1.31.743.411 I slot print_timing: id 0 | task 5791 | eval time = 644.69 ms / 53 tokens ( 12.40 ms per token, 80.66 tokens per second) 1.31.743.412 I slot print_timing: id 0 | task 5791 | total time = 829.61 ms / 530 tokens 1.31.743.413 I slot print_timing: id 0 | task 5791 | graphs reused = 5431 1.31.743.414 I slot print_timing: id 0 | task 5791 | graph reallocs = 0 / 0 (same size) / (changed size) 1.31.743.447 I slot release: id 0 | task 5791 | stop processing: n_tokens = 561, truncated = 0 1.31.781.996 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 561, t_last = 91641169 1.31.782.052 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.544 MiB) 1.31.835.665 I slot launch_slot_: id 0 | task 5847 | processing task, is_child = 0 1.33.016.682 I slot print_timing: id 0 | task 5847 | prompt eval time = 279.45 ms / 845 tokens ( 0.33 ms per token, 3023.79 tokens per second) 1.33.016.688 I slot print_timing: id 0 | task 5847 | eval time = 901.55 ms / 72 tokens ( 12.70 ms per token, 78.75 tokens per second) 1.33.016.689 I slot print_timing: id 0 | task 5847 | total time = 1181.00 ms / 917 tokens 1.33.016.690 I slot print_timing: id 0 | task 5847 | graphs reused = 5501 1.33.016.690 I slot print_timing: id 0 | task 5847 | graph reallocs = 0 / 0 (same size) / (changed size) 1.33.016.735 I slot release: id 0 | task 5847 | stop processing: n_tokens = 948, truncated = 0 1.33.021.649 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 948, t_last = 92914457 1.33.021.722 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.544 MiB) 1.33.025.244 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.326 MiB) 1.33.093.474 I slot launch_slot_: id 0 | task 5923 | processing task, is_child = 0 1.33.938.341 I slot print_timing: id 0 | task 5923 | prompt eval time = 190.69 ms / 459 tokens ( 0.42 ms per token, 2407.09 tokens per second) 1.33.938.347 I slot print_timing: id 0 | task 5923 | eval time = 654.16 ms / 52 tokens ( 12.83 ms per token, 77.96 tokens per second) 1.33.938.348 I slot print_timing: id 0 | task 5923 | total time = 844.85 ms / 511 tokens 1.33.938.349 I slot print_timing: id 0 | task 5923 | graphs reused = 5550 1.33.938.350 I slot print_timing: id 0 | task 5923 | graph reallocs = 0 / 0 (same size) / (changed size) 1.33.938.381 I slot release: id 0 | task 5923 | stop processing: n_tokens = 542, truncated = 0 1.33.977.496 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 542, t_last = 93836104 1.33.977.551 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.762 MiB) 1.34.032.914 I slot launch_slot_: id 0 | task 5978 | processing task, is_child = 0 1.34.891.955 I slot print_timing: id 0 | task 5978 | prompt eval time = 246.20 ms / 670 tokens ( 0.37 ms per token, 2721.39 tokens per second) 1.34.891.961 I slot print_timing: id 0 | task 5978 | eval time = 612.82 ms / 47 tokens ( 13.32 ms per token, 75.06 tokens per second) 1.34.891.962 I slot print_timing: id 0 | task 5978 | total time = 859.02 ms / 717 tokens 1.34.891.963 I slot print_timing: id 0 | task 5978 | graphs reused = 5595 1.34.891.964 I slot print_timing: id 0 | task 5978 | graph reallocs = 0 / 0 (same size) / (changed size) 1.34.892.002 I slot release: id 0 | task 5978 | stop processing: n_tokens = 748, truncated = 0 1.34.936.108 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 748, t_last = 94789725 1.34.936.169 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.325 MiB) 1.34.939.752 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.575 MiB) 1.35.006.498 I slot launch_slot_: id 0 | task 6029 | processing task, is_child = 0 1.36.280.929 I slot print_timing: id 0 | task 6029 | prompt eval time = 267.58 ms / 775 tokens ( 0.35 ms per token, 2896.29 tokens per second) 1.36.280.935 I slot print_timing: id 0 | task 6029 | eval time = 1006.83 ms / 83 tokens ( 12.28 ms per token, 81.44 tokens per second) 1.36.280.936 I slot print_timing: id 0 | task 6029 | total time = 1274.41 ms / 858 tokens 1.36.280.937 I slot print_timing: id 0 | task 6029 | graphs reused = 5676 1.36.280.937 I slot print_timing: id 0 | task 6029 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.280.979 I slot release: id 0 | task 6029 | stop processing: n_tokens = 889, truncated = 0 1.36.307.515 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 889, t_last = 96178701 1.36.307.574 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.700 MiB) 1.36.311.065 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 219.735 MiB) 1.36.380.226 I slot launch_slot_: id 0 | task 6116 | processing task, is_child = 0 1.37.629.600 I slot print_timing: id 0 | task 6116 | prompt eval time = 220.59 ms / 573 tokens ( 0.38 ms per token, 2597.59 tokens per second) 1.37.629.607 I slot print_timing: id 0 | task 6116 | eval time = 1028.77 ms / 82 tokens ( 12.70 ms per token, 78.74 tokens per second) 1.37.629.608 I slot print_timing: id 0 | task 6116 | total time = 1249.35 ms / 655 tokens 1.37.629.609 I slot print_timing: id 0 | task 6116 | graphs reused = 5756 1.37.629.609 I slot print_timing: id 0 | task 6116 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.629.646 I slot release: id 0 | task 6116 | stop processing: n_tokens = 686, truncated = 0 1.37.653.707 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 686, t_last = 97527368 1.37.653.768 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 219.328 MiB) 1.37.657.367 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.387 MiB) 1.37.720.986 I slot launch_slot_: id 0 | task 6202 | processing task, is_child = 0 1.38.882.328 I slot print_timing: id 0 | task 6202 | prompt eval time = 189.89 ms / 461 tokens ( 0.41 ms per token, 2427.72 tokens per second) 1.38.882.333 I slot print_timing: id 0 | task 6202 | eval time = 971.43 ms / 77 tokens ( 12.78 ms per token, 78.24 tokens per second) 1.38.882.335 I slot print_timing: id 0 | task 6202 | total time = 1161.32 ms / 538 tokens 1.38.882.335 I slot print_timing: id 0 | task 6202 | graphs reused = 5830 1.38.882.336 I slot print_timing: id 0 | task 6202 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.882.366 I slot release: id 0 | task 6202 | stop processing: n_tokens = 569, truncated = 0 1.38.887.962 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 569, t_last = 98780089 1.38.888.016 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.701 MiB) 1.38.938.807 I slot launch_slot_: id 0 | task 6282 | processing task, is_child = 0 1.39.930.482 I slot print_timing: id 0 | task 6282 | prompt eval time = 223.35 ms / 609 tokens ( 0.37 ms per token, 2726.63 tokens per second) 1.39.930.487 I slot print_timing: id 0 | task 6282 | eval time = 768.30 ms / 61 tokens ( 12.81 ms per token, 78.09 tokens per second) 1.39.930.488 I slot print_timing: id 0 | task 6282 | total time = 991.65 ms / 670 tokens 1.39.930.489 I slot print_timing: id 0 | task 6282 | graphs reused = 5889 1.39.930.490 I slot print_timing: id 0 | task 6282 | graph reallocs = 0 / 0 (same size) / (changed size) 1.39.930.525 I slot release: id 0 | task 6282 | stop processing: n_tokens = 701, truncated = 0 1.39.959.130 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 701, t_last = 99828247 1.39.959.188 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.293 MiB) 1.39.962.763 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.107 MiB) 1.40.029.778 I slot launch_slot_: id 0 | task 6347 | processing task, is_child = 0 1.41.267.124 I slot print_timing: id 0 | task 6347 | prompt eval time = 268.54 ms / 791 tokens ( 0.34 ms per token, 2945.57 tokens per second) 1.41.267.130 I slot print_timing: id 0 | task 6347 | eval time = 968.79 ms / 80 tokens ( 12.26 ms per token, 81.55 tokens per second) 1.41.267.131 I slot print_timing: id 0 | task 6347 | total time = 1237.33 ms / 871 tokens 1.41.267.132 I slot print_timing: id 0 | task 6347 | graphs reused = 5967 1.41.267.133 I slot print_timing: id 0 | task 6347 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.267.173 I slot release: id 0 | task 6347 | stop processing: n_tokens = 902, truncated = 0 1.41.288.225 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 902, t_last = 101164896 1.41.288.298 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 271.362 MiB) 1.41.366.531 I slot launch_slot_: id 0 | task 6431 | processing task, is_child = 0 1.42.469.023 I slot print_timing: id 0 | task 6431 | prompt eval time = 207.15 ms / 533 tokens ( 0.39 ms per token, 2573.08 tokens per second) 1.42.469.029 I slot print_timing: id 0 | task 6431 | eval time = 895.33 ms / 74 tokens ( 12.26 ms per token, 81.53 tokens per second) 1.42.469.031 I slot print_timing: id 0 | task 6431 | total time = 1102.47 ms / 607 tokens 1.42.469.031 I slot print_timing: id 0 | task 6431 | graphs reused = 6039 1.42.469.032 I slot print_timing: id 0 | task 6431 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.469.070 I slot release: id 0 | task 6431 | stop processing: n_tokens = 695, truncated = 0 1.42.474.345 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 695, t_last = 102366792 1.42.474.396 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.144 MiB) 1.42.533.719 I slot launch_slot_: id 0 | task 6509 | processing task, is_child = 0 1.43.597.737 I slot print_timing: id 0 | task 6509 | prompt eval time = 215.92 ms / 566 tokens ( 0.38 ms per token, 2621.29 tokens per second) 1.43.597.743 I slot print_timing: id 0 | task 6509 | eval time = 848.07 ms / 68 tokens ( 12.66 ms per token, 79.00 tokens per second) 1.43.597.744 I slot print_timing: id 0 | task 6509 | total time = 1064.00 ms / 634 tokens 1.43.597.745 I slot print_timing: id 0 | task 6509 | graphs reused = 6105 1.43.597.746 I slot print_timing: id 0 | task 6509 | graph reallocs = 0 / 0 (same size) / (changed size) 1.43.597.781 I slot release: id 0 | task 6509 | stop processing: n_tokens = 665, truncated = 0 1.43.641.288 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 665, t_last = 103495503 1.43.641.342 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.895 MiB) 1.43.694.114 I slot launch_slot_: id 0 | task 6581 | processing task, is_child = 0 1.44.508.723 I slot print_timing: id 0 | task 6581 | prompt eval time = 181.56 ms / 443 tokens ( 0.41 ms per token, 2439.96 tokens per second) 1.44.508.728 I slot print_timing: id 0 | task 6581 | eval time = 633.03 ms / 52 tokens ( 12.41 ms per token, 80.57 tokens per second) 1.44.508.729 I slot print_timing: id 0 | task 6581 | total time = 814.59 ms / 495 tokens 1.44.508.730 I slot print_timing: id 0 | task 6581 | graphs reused = 6154 1.44.508.731 I slot print_timing: id 0 | task 6581 | graph reallocs = 0 / 0 (same size) / (changed size) 1.44.508.764 I slot release: id 0 | task 6581 | stop processing: n_tokens = 526, truncated = 0 1.44.513.824 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 526, t_last = 104406487 1.44.513.877 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.488 MiB) 1.44.562.052 I slot launch_slot_: id 0 | task 6636 | processing task, is_child = 0 1.45.921.884 I slot print_timing: id 0 | task 6636 | prompt eval time = 185.06 ms / 487 tokens ( 0.38 ms per token, 2631.61 tokens per second) 1.45.921.889 I slot print_timing: id 0 | task 6636 | eval time = 1174.75 ms / 96 tokens ( 12.37 ms per token, 80.87 tokens per second) 1.45.921.890 I slot print_timing: id 0 | task 6636 | total time = 1359.81 ms / 583 tokens 1.45.921.891 I slot print_timing: id 0 | task 6636 | graphs reused = 6248 1.45.921.892 I slot print_timing: id 0 | task 6636 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.921.924 I slot release: id 0 | task 6636 | stop processing: n_tokens = 614, truncated = 0 1.45.938.958 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 614, t_last = 105819646 1.45.939.017 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 218.515 MiB) 1.45.942.792 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 272.612 MiB) 1.45.996.527 I slot launch_slot_: id 0 | task 6735 | processing task, is_child = 0 1.47.013.708 I slot print_timing: id 0 | task 6735 | prompt eval time = 194.60 ms / 507 tokens ( 0.38 ms per token, 2605.32 tokens per second) 1.47.013.713 I slot print_timing: id 0 | task 6735 | eval time = 822.56 ms / 68 tokens ( 12.28 ms per token, 81.45 tokens per second) 1.47.013.714 I slot print_timing: id 0 | task 6735 | total time = 1017.16 ms / 575 tokens 1.47.013.715 I slot print_timing: id 0 | task 6735 | graphs reused = 6314 1.47.013.716 I slot print_timing: id 0 | task 6735 | graph reallocs = 0 / 0 (same size) / (changed size) 1.47.013.750 I slot release: id 0 | task 6735 | stop processing: n_tokens = 606, truncated = 0 1.47.019.311 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 606, t_last = 106911472 1.47.019.396 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 272.644 MiB) 1.47.069.244 I slot launch_slot_: id 0 | task 6806 | processing task, is_child = 0 1.48.093.014 I slot print_timing: id 0 | task 6806 | prompt eval time = 225.81 ms / 633 tokens ( 0.36 ms per token, 2803.18 tokens per second) 1.48.093.019 I slot print_timing: id 0 | task 6806 | eval time = 797.93 ms / 66 tokens ( 12.28 ms per token, 81.46 tokens per second) 1.48.093.020 I slot print_timing: id 0 | task 6806 | total time = 1023.75 ms / 699 tokens 1.48.093.021 I slot print_timing: id 0 | task 6806 | graphs reused = 6378 1.48.093.022 I slot print_timing: id 0 | task 6806 | graph reallocs = 0 / 0 (same size) / (changed size) 1.48.093.059 I slot release: id 0 | task 6806 | stop processing: n_tokens = 730, truncated = 0 1.48.133.586 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 730, t_last = 107990781 1.48.133.646 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 269.735 MiB) 1.48.188.735 I slot launch_slot_: id 0 | task 6876 | processing task, is_child = 0 1.49.115.279 I slot print_timing: id 0 | task 6876 | prompt eval time = 213.62 ms / 571 tokens ( 0.37 ms per token, 2672.95 tokens per second) 1.49.115.284 I slot print_timing: id 0 | task 6876 | eval time = 712.90 ms / 59 tokens ( 12.29 ms per token, 81.36 tokens per second) 1.49.115.285 I slot print_timing: id 0 | task 6876 | total time = 926.52 ms / 630 tokens 1.49.115.286 I slot print_timing: id 0 | task 6876 | graphs reused = 6435 1.49.115.286 I slot print_timing: id 0 | task 6876 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.115.320 I slot release: id 0 | task 6876 | stop processing: n_tokens = 661, truncated = 0 1.49.161.288 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 661, t_last = 109013042 1.49.161.345 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 269.360 MiB) 1.49.213.597 I slot launch_slot_: id 0 | task 6939 | processing task, is_child = 0 1.50.278.525 I slot print_timing: id 0 | task 6939 | prompt eval time = 267.38 ms / 798 tokens ( 0.34 ms per token, 2984.57 tokens per second) 1.50.278.531 I slot print_timing: id 0 | task 6939 | eval time = 797.53 ms / 66 tokens ( 12.27 ms per token, 81.50 tokens per second) 1.50.278.533 I slot print_timing: id 0 | task 6939 | total time = 1064.91 ms / 864 tokens 1.50.278.534 I slot print_timing: id 0 | task 6939 | graphs reused = 6499 1.50.278.535 I slot print_timing: id 0 | task 6939 | graph reallocs = 0 / 0 (same size) / (changed size) 1.50.278.579 I slot release: id 0 | task 6939 | stop processing: n_tokens = 895, truncated = 0 1.50.300.650 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 895, t_last = 110176301 1.50.300.707 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.894 MiB) 1.50.305.860 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.082 MiB) 1.50.362.181 I slot launch_slot_: id 0 | task 7009 | processing task, is_child = 0 1.51.338.224 I slot print_timing: id 0 | task 7009 | prompt eval time = 214.44 ms / 572 tokens ( 0.37 ms per token, 2667.44 tokens per second) 1.51.338.229 I slot print_timing: id 0 | task 7009 | eval time = 761.59 ms / 63 tokens ( 12.28 ms per token, 81.41 tokens per second) 1.51.338.230 I slot print_timing: id 0 | task 7009 | total time = 976.03 ms / 635 tokens 1.51.338.231 I slot print_timing: id 0 | task 7009 | graphs reused = 6560 1.51.338.232 I slot print_timing: id 0 | task 7009 | graph reallocs = 0 / 0 (same size) / (changed size) 1.51.338.267 I slot release: id 0 | task 7009 | stop processing: n_tokens = 666, truncated = 0 1.51.373.733 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 666, t_last = 111235989 1.51.373.791 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 267.015 MiB) 1.51.424.861 I slot launch_slot_: id 0 | task 7076 | processing task, is_child = 0 1.52.692.057 I slot print_timing: id 0 | task 7076 | prompt eval time = 223.65 ms / 613 tokens ( 0.36 ms per token, 2740.90 tokens per second) 1.52.692.071 I slot print_timing: id 0 | task 7076 | eval time = 1043.53 ms / 86 tokens ( 12.28 ms per token, 81.45 tokens per second) 1.52.692.072 I slot print_timing: id 0 | task 7076 | total time = 1267.18 ms / 699 tokens 1.52.692.073 I slot print_timing: id 0 | task 7076 | graphs reused = 6644 1.52.692.075 I slot print_timing: id 0 | task 7076 | graph reallocs = 0 / 0 (same size) / (changed size) 1.52.692.111 I slot release: id 0 | task 7076 | stop processing: n_tokens = 730, truncated = 0 1.52.714.226 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 730, t_last = 112589833 1.52.714.284 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.549 MiB) 1.52.768.378 I slot launch_slot_: id 0 | task 7166 | processing task, is_child = 0 1.53.962.841 I slot print_timing: id 0 | task 7166 | prompt eval time = 213.40 ms / 580 tokens ( 0.37 ms per token, 2717.89 tokens per second) 1.53.962.847 I slot print_timing: id 0 | task 7166 | eval time = 981.04 ms / 81 tokens ( 12.26 ms per token, 81.55 tokens per second) 1.53.962.848 I slot print_timing: id 0 | task 7166 | total time = 1194.44 ms / 661 tokens 1.53.962.848 I slot print_timing: id 0 | task 7166 | graphs reused = 6723 1.53.962.850 I slot print_timing: id 0 | task 7166 | graph reallocs = 0 / 0 (same size) / (changed size) 1.53.962.885 I slot release: id 0 | task 7166 | stop processing: n_tokens = 692, truncated = 0 1.53.968.637 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 692, t_last = 113860608 1.53.968.694 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.454 MiB) 1.54.020.286 I slot launch_slot_: id 0 | task 7251 | processing task, is_child = 0 1.55.127.979 I slot print_timing: id 0 | task 7251 | prompt eval time = 255.89 ms / 716 tokens ( 0.36 ms per token, 2798.09 tokens per second) 1.55.127.985 I slot print_timing: id 0 | task 7251 | eval time = 851.79 ms / 70 tokens ( 12.34 ms per token, 81.01 tokens per second) 1.55.127.986 I slot print_timing: id 0 | task 7251 | total time = 1107.67 ms / 786 tokens 1.55.127.987 I slot print_timing: id 0 | task 7251 | graphs reused = 6790 1.55.127.988 I slot print_timing: id 0 | task 7251 | graph reallocs = 0 / 0 (same size) / (changed size) 1.55.128.026 I slot release: id 0 | task 7251 | stop processing: n_tokens = 817, truncated = 0 1.55.157.382 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 817, t_last = 115025749 1.55.157.446 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.797 MiB) 1.55.162.694 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.735 MiB) 1.55.218.654 I slot launch_slot_: id 0 | task 7325 | processing task, is_child = 0 1.56.874.827 I slot print_timing: id 0 | task 7325 | prompt eval time = 269.06 ms / 799 tokens ( 0.34 ms per token, 2969.65 tokens per second) 1.56.874.832 I slot print_timing: id 0 | task 7325 | eval time = 1387.10 ms / 114 tokens ( 12.28 ms per token, 81.47 tokens per second) 1.56.874.834 I slot print_timing: id 0 | task 7325 | total time = 1656.15 ms / 913 tokens 1.56.874.834 I slot print_timing: id 0 | task 7325 | graphs reused = 6902 1.56.874.835 I slot print_timing: id 0 | task 7325 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.874.877 I slot release: id 0 | task 7325 | stop processing: n_tokens = 944, truncated = 0 1.56.890.414 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 944, t_last = 116772599 1.56.890.484 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.515 MiB) 1.56.944.737 I slot launch_slot_: id 0 | task 7443 | processing task, is_child = 0 1.58.671.673 I slot print_timing: id 0 | task 7443 | prompt eval time = 156.24 ms / 361 tokens ( 0.43 ms per token, 2310.58 tokens per second) 1.58.671.679 I slot print_timing: id 0 | task 7443 | eval time = 1570.68 ms / 129 tokens ( 12.27 ms per token, 81.49 tokens per second) 1.58.671.680 I slot print_timing: id 0 | task 7443 | total time = 1726.92 ms / 490 tokens 1.58.671.681 I slot print_timing: id 0 | task 7443 | graphs reused = 7028 1.58.671.682 I slot print_timing: id 0 | task 7443 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.671.711 I slot release: id 0 | task 7443 | stop processing: n_tokens = 521, truncated = 0 1.58.709.475 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 521, t_last = 118569433 1.58.709.529 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.864 MiB) 1.58.759.685 I slot launch_slot_: id 0 | task 7575 | processing task, is_child = 0 2.00.393.186 I slot print_timing: id 0 | task 7575 | prompt eval time = 159.19 ms / 381 tokens ( 0.42 ms per token, 2393.44 tokens per second) 2.00.393.192 I slot print_timing: id 0 | task 7575 | eval time = 1474.30 ms / 121 tokens ( 12.29 ms per token, 81.39 tokens per second) 2.00.393.193 I slot print_timing: id 0 | task 7575 | total time = 1633.48 ms / 502 tokens 2.00.393.193 I slot print_timing: id 0 | task 7575 | graphs reused = 7146 2.00.393.194 I slot print_timing: id 0 | task 7575 | graph reallocs = 0 / 0 (same size) / (changed size) 2.00.393.224 I slot release: id 0 | task 7575 | stop processing: n_tokens = 533, truncated = 0 2.00.437.161 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 533, t_last = 120290946 2.00.437.210 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.048 MiB) 2.00.484.961 I slot launch_slot_: id 0 | task 7699 | processing task, is_child = 0 2.02.285.375 I slot print_timing: id 0 | task 7699 | prompt eval time = 156.87 ms / 365 tokens ( 0.43 ms per token, 2326.78 tokens per second) 2.02.285.381 I slot print_timing: id 0 | task 7699 | eval time = 1643.53 ms / 135 tokens ( 12.27 ms per token, 81.53 tokens per second) 2.02.285.382 I slot print_timing: id 0 | task 7699 | total time = 1800.39 ms / 500 tokens 2.02.285.384 I slot print_timing: id 0 | task 7699 | graphs reused = 7278 2.02.285.385 I slot print_timing: id 0 | task 7699 | graph reallocs = 0 / 0 (same size) / (changed size) 2.02.285.413 I slot release: id 0 | task 7699 | stop processing: n_tokens = 531, truncated = 0 2.02.304.887 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 531, t_last = 122183135 2.02.304.937 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.401 MiB) 2.02.355.460 I slot launch_slot_: id 0 | task 7837 | processing task, is_child = 0 2.04.161.776 I slot print_timing: id 0 | task 7837 | prompt eval time = 154.00 ms / 333 tokens ( 0.46 ms per token, 2162.38 tokens per second) 2.04.161.782 I slot print_timing: id 0 | task 7837 | eval time = 1652.30 ms / 136 tokens ( 12.24 ms per token, 81.70 tokens per second) 2.04.161.783 I slot print_timing: id 0 | task 7837 | total time = 1806.30 ms / 469 tokens 2.04.161.784 I slot print_timing: id 0 | task 7837 | graphs reused = 7412 2.04.161.785 I slot print_timing: id 0 | task 7837 | graph reallocs = 0 / 0 (same size) / (changed size) 2.04.161.812 I slot release: id 0 | task 7837 | stop processing: n_tokens = 500, truncated = 0 2.04.185.169 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 500, t_last = 124059535 2.04.225.504 I slot launch_slot_: id 0 | task 7976 | processing task, is_child = 0 2.06.598.264 I slot print_timing: id 0 | task 7976 | prompt eval time = 168.24 ms / 403 tokens ( 0.42 ms per token, 2395.46 tokens per second) 2.06.598.269 I slot print_timing: id 0 | task 7976 | eval time = 2204.50 ms / 181 tokens ( 12.25 ms per token, 81.65 tokens per second) 2.06.598.270 I slot print_timing: id 0 | task 7976 | total time = 2372.74 ms / 584 tokens 2.06.598.271 I slot print_timing: id 0 | task 7976 | graphs reused = 7590 2.06.598.271 I slot print_timing: id 0 | task 7976 | graph reallocs = 0 / 0 (same size) / (changed size) 2.06.598.302 I slot release: id 0 | task 7976 | stop processing: n_tokens = 615, truncated = 0 2.06.603.319 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 615, t_last = 126496025 2.06.603.507 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.454 MiB) 2.06.651.365 I slot launch_slot_: id 0 | task 8160 | processing task, is_child = 0 2.09.252.408 I slot print_timing: id 0 | task 8160 | prompt eval time = 164.15 ms / 411 tokens ( 0.40 ms per token, 2503.85 tokens per second) 2.09.252.413 I slot print_timing: id 0 | task 8160 | eval time = 2436.88 ms / 200 tokens ( 12.25 ms per token, 81.66 tokens per second) 2.09.252.415 I slot print_timing: id 0 | task 8160 | total time = 2601.02 ms / 611 tokens 2.09.252.416 I slot print_timing: id 0 | task 8160 | graphs reused = 7787 2.09.252.417 I slot print_timing: id 0 | task 8160 | graph reallocs = 0 / 0 (same size) / (changed size) 2.09.252.447 I slot release: id 0 | task 8160 | stop processing: n_tokens = 642, truncated = 0 2.09.257.644 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 642, t_last = 129150169 2.09.257.698 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 375.146 MiB) 2.09.311.182 I slot launch_slot_: id 0 | task 8363 | processing task, is_child = 0 2.12.380.203 I slot print_timing: id 0 | task 8363 | prompt eval time = 194.97 ms / 490 tokens ( 0.40 ms per token, 2513.19 tokens per second) 2.12.380.209 I slot print_timing: id 0 | task 8363 | eval time = 2874.03 ms / 236 tokens ( 12.23 ms per token, 81.77 tokens per second) 2.12.380.210 I slot print_timing: id 0 | task 8363 | total time = 3069.00 ms / 726 tokens 2.12.380.210 I slot print_timing: id 0 | task 8363 | graphs reused = 8021 2.12.380.211 I slot print_timing: id 0 | task 8363 | graph reallocs = 0 / 0 (same size) / (changed size) 2.12.380.243 I slot release: id 0 | task 8363 | stop processing: n_tokens = 757, truncated = 0 2.12.421.027 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 757, t_last = 132277966 2.12.421.087 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.556 MiB) 2.12.477.633 I slot launch_slot_: id 0 | task 8602 | processing task, is_child = 0 2.14.898.624 I slot print_timing: id 0 | task 8602 | prompt eval time = 155.19 ms / 344 tokens ( 0.45 ms per token, 2216.68 tokens per second) 2.14.898.630 I slot print_timing: id 0 | task 8602 | eval time = 2265.79 ms / 186 tokens ( 12.25 ms per token, 81.65 tokens per second) 2.14.898.631 I slot print_timing: id 0 | task 8602 | total time = 2420.97 ms / 530 tokens 2.14.898.632 I slot print_timing: id 0 | task 8602 | graphs reused = 8204 2.14.898.632 I slot print_timing: id 0 | task 8602 | graph reallocs = 0 / 0 (same size) / (changed size) 2.14.898.660 I slot release: id 0 | task 8602 | stop processing: n_tokens = 561, truncated = 0 2.14.924.308 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 561, t_last = 134796383 2.14.924.359 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.298 MiB) 2.14.972.402 I slot launch_slot_: id 0 | task 8791 | processing task, is_child = 0 2.17.406.324 I slot print_timing: id 0 | task 8791 | prompt eval time = 155.44 ms / 347 tokens ( 0.45 ms per token, 2232.32 tokens per second) 2.17.406.330 I slot print_timing: id 0 | task 8791 | eval time = 2278.46 ms / 187 tokens ( 12.25 ms per token, 81.63 tokens per second) 2.17.406.331 I slot print_timing: id 0 | task 8791 | total time = 2433.91 ms / 534 tokens 2.17.406.332 I slot print_timing: id 0 | task 8791 | graphs reused = 8388 2.17.406.332 I slot print_timing: id 0 | task 8791 | graph reallocs = 0 / 0 (same size) / (changed size) 2.17.406.359 I slot release: id 0 | task 8791 | stop processing: n_tokens = 565, truncated = 0 2.17.443.568 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 565, t_last = 137304082 2.17.443.611 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.677 MiB) 2.17.495.042 I slot launch_slot_: id 0 | task 8981 | processing task, is_child = 0 2.19.309.014 I slot print_timing: id 0 | task 8981 | prompt eval time = 166.16 ms / 401 tokens ( 0.41 ms per token, 2413.39 tokens per second) 2.19.309.019 I slot print_timing: id 0 | task 8981 | eval time = 1647.80 ms / 135 tokens ( 12.30 ms per token, 81.32 tokens per second) 2.19.309.021 I slot print_timing: id 0 | task 8981 | total time = 1813.95 ms / 536 tokens 2.19.309.022 I slot print_timing: id 0 | task 8981 | graphs reused = 8520 2.19.309.022 I slot print_timing: id 0 | task 8981 | graph reallocs = 0 / 0 (same size) / (changed size) 2.19.309.053 I slot release: id 0 | task 8981 | stop processing: n_tokens = 567, truncated = 0 2.19.329.141 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 567, t_last = 139206775 2.19.329.192 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.962 MiB) 2.19.378.762 I slot launch_slot_: id 0 | task 9119 | processing task, is_child = 0 2.21.207.283 I slot print_timing: id 0 | task 9119 | prompt eval time = 178.77 ms / 456 tokens ( 0.39 ms per token, 2550.71 tokens per second) 2.21.207.288 I slot print_timing: id 0 | task 9119 | eval time = 1649.72 ms / 129 tokens ( 12.89 ms per token, 77.59 tokens per second) 2.21.207.289 I slot print_timing: id 0 | task 9119 | total time = 1828.50 ms / 585 tokens 2.21.207.290 I slot print_timing: id 0 | task 9119 | graphs reused = 8646 2.21.207.291 I slot print_timing: id 0 | task 9119 | graph reallocs = 0 / 0 (same size) / (changed size) 2.21.207.322 I slot release: id 0 | task 9119 | stop processing: n_tokens = 616, truncated = 0 2.21.230.831 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.107 (> 0.100 thold), f_keep = 0.076 2.21.230.879 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 423.739 MiB) 2.21.293.168 I slot launch_slot_: id 0 | task 9251 | processing task, is_child = 0 2.23.061.239 I slot print_timing: id 0 | task 9251 | prompt eval time = 173.41 ms / 406 tokens ( 0.43 ms per token, 2341.33 tokens per second) 2.23.061.245 I slot print_timing: id 0 | task 9251 | eval time = 1594.65 ms / 127 tokens ( 12.66 ms per token, 79.01 tokens per second) 2.23.061.246 I slot print_timing: id 0 | task 9251 | total time = 1768.05 ms / 533 tokens 2.23.061.247 I slot print_timing: id 0 | task 9251 | graphs reused = 8770 2.23.061.248 I slot print_timing: id 0 | task 9251 | graph reallocs = 0 / 0 (same size) / (changed size) 2.23.061.278 I slot release: id 0 | task 9251 | stop processing: n_tokens = 564, truncated = 0 2.23.077.429 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 564, t_last = 142959001 2.23.117.593 I slot launch_slot_: id 0 | task 9381 | processing task, is_child = 0 2.25.829.342 I slot print_timing: id 0 | task 9381 | prompt eval time = 166.63 ms / 406 tokens ( 0.41 ms per token, 2436.55 tokens per second) 2.25.829.347 I slot print_timing: id 0 | task 9381 | eval time = 2545.10 ms / 202 tokens ( 12.66 ms per token, 78.98 tokens per second) 2.25.829.348 I slot print_timing: id 0 | task 9381 | total time = 2711.73 ms / 608 tokens 2.25.829.349 I slot print_timing: id 0 | task 9381 | graphs reused = 8969 2.25.829.350 I slot print_timing: id 0 | task 9381 | graph reallocs = 0 / 0 (same size) / (changed size) 2.25.829.381 I slot release: id 0 | task 9381 | stop processing: n_tokens = 639, truncated = 0 2.25.834.216 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 639, t_last = 145727103 2.25.834.275 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 372.551 MiB) 2.25.884.091 I slot launch_slot_: id 0 | task 9586 | processing task, is_child = 0 2.27.972.386 I slot print_timing: id 0 | task 9586 | prompt eval time = 177.39 ms / 444 tokens ( 0.40 ms per token, 2502.90 tokens per second) 2.27.972.391 I slot print_timing: id 0 | task 9586 | eval time = 1910.88 ms / 155 tokens ( 12.41 ms per token, 80.59 tokens per second) 2.27.972.393 I slot print_timing: id 0 | task 9586 | total time = 2088.28 ms / 599 tokens 2.27.972.393 I slot print_timing: id 0 | task 9586 | graphs reused = 9121 2.27.972.394 I slot print_timing: id 0 | task 9586 | graph reallocs = 0 / 0 (same size) / (changed size) 2.27.972.423 I slot release: id 0 | task 9586 | stop processing: n_tokens = 630, truncated = 0 2.27.992.811 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 630, t_last = 147870146 2.27.992.870 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.953 MiB) 2.28.042.437 I slot launch_slot_: id 0 | task 9744 | processing task, is_child = 0 2.29.729.104 I slot print_timing: id 0 | task 9744 | prompt eval time = 164.95 ms / 372 tokens ( 0.44 ms per token, 2255.28 tokens per second) 2.29.729.109 I slot print_timing: id 0 | task 9744 | eval time = 1521.70 ms / 120 tokens ( 12.79 ms per token, 78.20 tokens per second) 2.29.729.110 I slot print_timing: id 0 | task 9744 | total time = 1686.65 ms / 492 tokens 2.29.729.111 I slot print_timing: id 0 | task 9744 | graphs reused = 9238 2.29.729.112 I slot print_timing: id 0 | task 9744 | graph reallocs = 0 / 0 (same size) / (changed size) 2.29.729.141 I slot release: id 0 | task 9744 | stop processing: n_tokens = 523, truncated = 0 2.29.756.536 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 523, t_last = 149626863 2.29.756.581 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.705 MiB) 2.29.811.324 I slot launch_slot_: id 0 | task 9867 | processing task, is_child = 0 2.32.999.689 I slot print_timing: id 0 | task 9867 | n_gen = 242, tg = 80.06 t/s, tg_3s = 80.39 t/s 2.33.229.356 I slot print_timing: id 0 | task 9867 | prompt eval time = 178.18 ms / 454 tokens ( 0.39 ms per token, 2548.03 tokens per second) 2.33.229.362 I slot print_timing: id 0 | task 9867 | eval time = 3239.84 ms / 260 tokens ( 12.51 ms per token, 79.94 tokens per second) 2.33.229.363 I slot print_timing: id 0 | task 9867 | total time = 3418.01 ms / 714 tokens 2.33.229.364 I slot print_timing: id 0 | task 9867 | graphs reused = 9495 2.33.229.365 I slot print_timing: id 0 | task 9867 | graph reallocs = 0 / 0 (same size) / (changed size) 2.33.229.396 I slot release: id 0 | task 9867 | stop processing: n_tokens = 745, truncated = 0 2.33.253.482 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 745, t_last = 153127118 2.33.253.544 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.455 MiB) 2.33.304.974 I slot launch_slot_: id 0 | task 10130 | processing task, is_child = 0 2.35.138.879 I slot print_timing: id 0 | task 10130 | prompt eval time = 162.26 ms / 354 tokens ( 0.46 ms per token, 2181.70 tokens per second) 2.35.138.885 I slot print_timing: id 0 | task 10130 | eval time = 1671.62 ms / 133 tokens ( 12.66 ms per token, 78.97 tokens per second) 2.35.138.886 I slot print_timing: id 0 | task 10130 | total time = 1833.88 ms / 487 tokens 2.35.138.887 I slot print_timing: id 0 | task 10130 | graphs reused = 9625 2.35.138.887 I slot print_timing: id 0 | task 10130 | graph reallocs = 0 / 0 (same size) / (changed size) 2.35.138.919 I slot release: id 0 | task 10130 | stop processing: n_tokens = 518, truncated = 0 2.35.175.329 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 518, t_last = 155036641 2.35.175.378 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.583 MiB) 2.35.225.120 I slot launch_slot_: id 0 | task 10266 | processing task, is_child = 0 2.37.392.737 I slot print_timing: id 0 | task 10266 | prompt eval time = 164.21 ms / 334 tokens ( 0.49 ms per token, 2034.01 tokens per second) 2.37.392.743 I slot print_timing: id 0 | task 10266 | eval time = 2003.39 ms / 160 tokens ( 12.60 ms per token, 79.37 tokens per second) 2.37.392.744 I slot print_timing: id 0 | task 10266 | total time = 2167.60 ms / 494 tokens 2.37.392.745 I slot print_timing: id 0 | task 10266 | graphs reused = 9782 2.37.392.746 I slot print_timing: id 0 | task 10266 | graph reallocs = 0 / 0 (same size) / (changed size) 2.37.392.775 I slot release: id 0 | task 10266 | stop processing: n_tokens = 525, truncated = 0 2.37.417.256 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 525, t_last = 157290498 2.37.417.308 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 372.426 MiB) 2.37.465.623 I slot launch_slot_: id 0 | task 10429 | processing task, is_child = 0 2.40.035.828 I slot print_timing: id 0 | task 10429 | prompt eval time = 178.31 ms / 426 tokens ( 0.42 ms per token, 2389.08 tokens per second) 2.40.035.834 I slot print_timing: id 0 | task 10429 | eval time = 2391.88 ms / 192 tokens ( 12.52 ms per token, 79.85 tokens per second) 2.40.035.835 I slot print_timing: id 0 | task 10429 | total time = 2570.19 ms / 618 tokens 2.40.035.836 I slot print_timing: id 0 | task 10429 | graphs reused = 9971 2.40.035.837 I slot print_timing: id 0 | task 10429 | graph reallocs = 0 / 0 (same size) / (changed size) 2.40.035.868 I slot release: id 0 | task 10429 | stop processing: n_tokens = 649, truncated = 0 2.40.059.103 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 649, t_last = 159933590 2.40.059.158 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.743 MiB) 2.40.110.855 I slot launch_slot_: id 0 | task 10624 | processing task, is_child = 0 2.42.094.510 I slot print_timing: id 0 | task 10624 | prompt eval time = 162.64 ms / 366 tokens ( 0.44 ms per token, 2250.34 tokens per second) 2.42.094.515 I slot print_timing: id 0 | task 10624 | eval time = 1820.99 ms / 144 tokens ( 12.73 ms per token, 78.53 tokens per second) 2.42.094.517 I slot print_timing: id 0 | task 10624 | total time = 1983.63 ms / 510 tokens 2.42.094.518 I slot print_timing: id 0 | task 10624 | graphs reused = 10112 2.42.094.519 I slot print_timing: id 0 | task 10624 | graph reallocs = 0 / 0 (same size) / (changed size) 2.42.094.549 I slot release: id 0 | task 10624 | stop processing: n_tokens = 541, truncated = 0 2.42.099.412 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 541, t_last = 161992271 2.42.099.454 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 372.582 MiB) 2.42.146.752 I slot launch_slot_: id 0 | task 10771 | processing task, is_child = 0 2.45.347.683 I slot print_timing: id 0 | task 10771 | n_gen = 242, tg = 80.07 t/s, tg_3s = 80.41 t/s 2.45.849.248 I slot print_timing: id 0 | task 10771 | prompt eval time = 191.16 ms / 462 tokens ( 0.41 ms per token, 2416.87 tokens per second) 2.45.849.254 I slot print_timing: id 0 | task 10771 | eval time = 3511.32 ms / 281 tokens ( 12.54 ms per token, 79.74 tokens per second) 2.45.849.255 I slot print_timing: id 0 | task 10771 | total time = 3702.48 ms / 743 tokens 2.45.849.256 I slot print_timing: id 0 | task 10771 | graphs reused = 10389 2.45.849.257 I slot print_timing: id 0 | task 10771 | graph reallocs = 0 / 0 (same size) / (changed size) 2.45.849.288 I slot release: id 0 | task 10771 | stop processing: n_tokens = 774, truncated = 0 2.45.865.585 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 774, t_last = 165747011 2.45.865.647 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.583 MiB) 2.45.916.423 I slot launch_slot_: id 0 | task 11055 | processing task, is_child = 0 2.48.012.981 I slot print_timing: id 0 | task 11055 | prompt eval time = 169.57 ms / 396 tokens ( 0.43 ms per token, 2335.26 tokens per second) 2.48.012.986 I slot print_timing: id 0 | task 11055 | eval time = 1926.96 ms / 155 tokens ( 12.51 ms per token, 79.92 tokens per second) 2.48.012.987 I slot print_timing: id 0 | task 11055 | total time = 2096.54 ms / 551 tokens 2.48.012.988 I slot print_timing: id 0 | task 11055 | graphs reused = 10541 2.48.012.989 I slot print_timing: id 0 | task 11055 | graph reallocs = 0 / 0 (same size) / (changed size) 2.48.013.019 I slot release: id 0 | task 11055 | stop processing: n_tokens = 582, truncated = 0 2.48.017.974 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 582, t_last = 167910741 2.48.057.984 I slot launch_slot_: id 0 | task 11213 | processing task, is_child = 0 2.50.463.351 I slot print_timing: id 0 | task 11213 | prompt eval time = 178.40 ms / 458 tokens ( 0.39 ms per token, 2567.22 tokens per second) 2.50.463.356 I slot print_timing: id 0 | task 11213 | eval time = 2226.94 ms / 175 tokens ( 12.80 ms per token, 78.13 tokens per second) 2.50.463.358 I slot print_timing: id 0 | task 11213 | total time = 2405.35 ms / 633 tokens 2.50.463.358 I slot print_timing: id 0 | task 11213 | graphs reused = 10713 2.50.463.360 I slot print_timing: id 0 | task 11213 | graph reallocs = 0 / 0 (same size) / (changed size) 2.50.463.392 I slot release: id 0 | task 11213 | stop processing: n_tokens = 664, truncated = 0 2.50.477.857 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 664, t_last = 170361115 2.50.477.906 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.395 MiB) 2.50.524.885 I slot launch_slot_: id 0 | task 11391 | processing task, is_child = 0 2.53.063.867 I slot print_timing: id 0 | task 11391 | prompt eval time = 187.94 ms / 458 tokens ( 0.41 ms per token, 2436.88 tokens per second) 2.53.063.872 I slot print_timing: id 0 | task 11391 | eval time = 2351.02 ms / 188 tokens ( 12.57 ms per token, 79.54 tokens per second) 2.53.063.873 I slot print_timing: id 0 | task 11391 | total time = 2538.96 ms / 646 tokens 2.53.063.874 I slot print_timing: id 0 | task 11391 | graphs reused = 10898 2.53.063.875 I slot print_timing: id 0 | task 11391 | graph reallocs = 0 / 0 (same size) / (changed size) 2.53.063.907 I slot release: id 0 | task 11391 | stop processing: n_tokens = 677, truncated = 0 2.53.080.910 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 677, t_last = 172961629 2.53.080.967 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 377.304 MiB) 2.53.132.106 I slot launch_slot_: id 0 | task 11582 | processing task, is_child = 0 2.56.275.678 I slot print_timing: id 0 | task 11582 | prompt eval time = 188.22 ms / 452 tokens ( 0.42 ms per token, 2401.46 tokens per second) 2.56.275.684 I slot print_timing: id 0 | task 11582 | eval time = 2955.33 ms / 234 tokens ( 12.68 ms per token, 78.84 tokens per second) 2.56.275.685 I slot print_timing: id 0 | task 11582 | total time = 3143.55 ms / 686 tokens 2.56.275.686 I slot print_timing: id 0 | task 11582 | graphs reused = 11129 2.56.275.687 I slot print_timing: id 0 | task 11582 | graph reallocs = 0 / 0 (same size) / (changed size) 2.56.275.719 I slot release: id 0 | task 11582 | stop processing: n_tokens = 717, truncated = 0 2.56.280.547 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 717, t_last = 176173441 2.56.280.598 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.276 MiB) 2.56.329.665 I slot launch_slot_: id 0 | task 11819 | processing task, is_child = 0 2.58.206.326 I slot print_timing: id 0 | task 11819 | prompt eval time = 167.98 ms / 404 tokens ( 0.42 ms per token, 2405.05 tokens per second) 2.58.206.332 I slot print_timing: id 0 | task 11819 | eval time = 1708.66 ms / 135 tokens ( 12.75 ms per token, 78.42 tokens per second) 2.58.206.333 I slot print_timing: id 0 | task 11819 | total time = 1876.64 ms / 539 tokens 2.58.206.334 I slot print_timing: id 0 | task 11819 | graphs reused = 11261 2.58.206.334 I slot print_timing: id 0 | task 11819 | graph reallocs = 0 / 0 (same size) / (changed size) 2.58.206.364 I slot release: id 0 | task 11819 | stop processing: n_tokens = 570, truncated = 0 2.58.230.655 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 570, t_last = 178104087 2.58.230.709 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.797 MiB) 2.58.287.448 I slot launch_slot_: id 0 | task 11957 | processing task, is_child = 0 2.59.970.160 I slot print_timing: id 0 | task 11957 | prompt eval time = 160.19 ms / 345 tokens ( 0.46 ms per token, 2153.64 tokens per second) 2.59.970.165 I slot print_timing: id 0 | task 11957 | eval time = 1522.50 ms / 123 tokens ( 12.48 ms per token, 80.13 tokens per second) 2.59.970.166 I slot print_timing: id 0 | task 11957 | total time = 1682.69 ms / 468 tokens 2.59.970.168 I slot print_timing: id 0 | task 11957 | graphs reused = 11382 2.59.970.168 I slot print_timing: id 0 | task 11957 | graph reallocs = 0 / 0 (same size) / (changed size) 2.59.970.198 I slot release: id 0 | task 11957 | stop processing: n_tokens = 499, truncated = 0 2.59.994.671 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 499, t_last = 179867920 2.59.994.720 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.172 MiB) 3.00.042.587 I slot launch_slot_: id 0 | task 12083 | processing task, is_child = 0 3.01.700.402 I slot print_timing: id 0 | task 12083 | prompt eval time = 182.67 ms / 430 tokens ( 0.42 ms per token, 2354.00 tokens per second) 3.01.700.407 I slot print_timing: id 0 | task 12083 | eval time = 1475.13 ms / 118 tokens ( 12.61 ms per token, 79.32 tokens per second) 3.01.700.409 I slot print_timing: id 0 | task 12083 | total time = 1657.80 ms / 548 tokens 3.01.700.409 I slot print_timing: id 0 | task 12083 | graphs reused = 11497 3.01.700.410 I slot print_timing: id 0 | task 12083 | graph reallocs = 0 / 0 (same size) / (changed size) 3.01.700.440 I slot release: id 0 | task 12083 | stop processing: n_tokens = 579, truncated = 0 3.01.715.077 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 579, t_last = 181598163 3.01.715.129 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.110 MiB) 3.01.765.100 I slot launch_slot_: id 0 | task 12204 | processing task, is_child = 0 3.02.988.213 I slot print_timing: id 0 | task 12204 | prompt eval time = 152.83 ms / 316 tokens ( 0.48 ms per token, 2067.68 tokens per second) 3.02.988.219 I slot print_timing: id 0 | task 12204 | eval time = 1070.26 ms / 85 tokens ( 12.74 ms per token, 78.49 tokens per second) 3.02.988.219 I slot print_timing: id 0 | task 12204 | total time = 1223.09 ms / 401 tokens 3.02.988.220 I slot print_timing: id 0 | task 12204 | graphs reused = 11580 3.02.988.221 I slot print_timing: id 0 | task 12204 | graph reallocs = 0 / 0 (same size) / (changed size) 3.02.988.250 I slot release: id 0 | task 12204 | stop processing: n_tokens = 432, truncated = 0 3.03.015.544 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 432, t_last = 182885972 3.03.015.591 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.140 MiB) 3.03.059.876 I slot launch_slot_: id 0 | task 12292 | processing task, is_child = 0 3.04.743.618 I slot print_timing: id 0 | task 12292 | prompt eval time = 162.51 ms / 354 tokens ( 0.46 ms per token, 2178.27 tokens per second) 3.04.743.624 I slot print_timing: id 0 | task 12292 | eval time = 1521.21 ms / 125 tokens ( 12.27 ms per token, 81.51 tokens per second) 3.04.743.625 I slot print_timing: id 0 | task 12292 | total time = 1683.72 ms / 479 tokens 3.04.743.626 I slot print_timing: id 0 | task 12292 | graphs reused = 11703 3.04.743.626 I slot print_timing: id 0 | task 12292 | graph reallocs = 0 / 0 (same size) / (changed size) 3.04.743.656 I slot release: id 0 | task 12292 | stop processing: n_tokens = 510, truncated = 0 3.04.767.650 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 510, t_last = 184641378 3.04.767.698 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.736 MiB) 3.04.815.397 I slot launch_slot_: id 0 | task 12420 | processing task, is_child = 0 3.06.450.312 I slot print_timing: id 0 | task 12420 | prompt eval time = 189.75 ms / 438 tokens ( 0.43 ms per token, 2308.26 tokens per second) 3.06.450.318 I slot print_timing: id 0 | task 12420 | eval time = 1445.14 ms / 114 tokens ( 12.79 ms per token, 78.19 tokens per second) 3.06.450.318 I slot print_timing: id 0 | task 12420 | total time = 1634.89 ms / 552 tokens 3.06.450.319 I slot print_timing: id 0 | task 12420 | graphs reused = 11814 3.06.450.320 I slot print_timing: id 0 | task 12420 | graph reallocs = 0 / 0 (same size) / (changed size) 3.06.450.351 I slot release: id 0 | task 12420 | stop processing: n_tokens = 583, truncated = 0 3.06.482.707 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 583, t_last = 186348073 3.06.482.761 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.581 MiB) 3.06.535.030 I slot launch_slot_: id 0 | task 12537 | processing task, is_child = 0 3.07.968.227 I slot print_timing: id 0 | task 12537 | prompt eval time = 188.28 ms / 457 tokens ( 0.41 ms per token, 2427.17 tokens per second) 3.07.968.232 I slot print_timing: id 0 | task 12537 | eval time = 1244.89 ms / 100 tokens ( 12.57 ms per token, 79.52 tokens per second) 3.07.968.233 I slot print_timing: id 0 | task 12537 | total time = 1433.18 ms / 557 tokens 3.07.968.234 I slot print_timing: id 0 | task 12537 | graphs reused = 11911 3.07.968.234 I slot print_timing: id 0 | task 12537 | graph reallocs = 0 / 0 (same size) / (changed size) 3.07.968.264 I slot release: id 0 | task 12537 | stop processing: n_tokens = 588, truncated = 0 3.07.999.735 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 588, t_last = 187865987 3.07.999.788 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.177 MiB) 3.08.054.856 I slot launch_slot_: id 0 | task 12640 | processing task, is_child = 0 3.09.658.271 I slot print_timing: id 0 | task 12640 | prompt eval time = 191.89 ms / 473 tokens ( 0.41 ms per token, 2464.90 tokens per second) 3.09.658.277 I slot print_timing: id 0 | task 12640 | eval time = 1411.50 ms / 112 tokens ( 12.72 ms per token, 78.64 tokens per second) 3.09.658.278 I slot print_timing: id 0 | task 12640 | total time = 1603.39 ms / 585 tokens 3.09.658.279 I slot print_timing: id 0 | task 12640 | graphs reused = 12020 3.09.658.280 I slot print_timing: id 0 | task 12640 | graph reallocs = 0 / 0 (same size) / (changed size) 3.09.658.312 I slot release: id 0 | task 12640 | stop processing: n_tokens = 616, truncated = 0 3.09.701.618 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 616, t_last = 189556034 3.09.701.675 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.048 MiB) 3.09.750.157 I slot launch_slot_: id 0 | task 12755 | processing task, is_child = 0 3.10.574.753 I slot print_timing: id 0 | task 12755 | prompt eval time = 190.34 ms / 476 tokens ( 0.40 ms per token, 2500.77 tokens per second) 3.10.574.759 I slot print_timing: id 0 | task 12755 | eval time = 634.24 ms / 50 tokens ( 12.94 ms per token, 77.26 tokens per second) 3.10.574.759 I slot print_timing: id 0 | task 12755 | total time = 824.58 ms / 526 tokens 3.10.574.760 I slot print_timing: id 0 | task 12755 | graphs reused = 12067 3.10.574.761 I slot print_timing: id 0 | task 12755 | graph reallocs = 0 / 0 (same size) / (changed size) 3.10.574.794 I slot release: id 0 | task 12755 | stop processing: n_tokens = 557, truncated = 0 3.10.579.685 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 557, t_last = 190472516 3.10.579.731 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.173 MiB) 3.10.630.266 I slot launch_slot_: id 0 | task 12808 | processing task, is_child = 0 3.12.289.399 I slot print_timing: id 0 | task 12808 | prompt eval time = 195.72 ms / 466 tokens ( 0.42 ms per token, 2380.92 tokens per second) 3.12.289.406 I slot print_timing: id 0 | task 12808 | eval time = 1463.39 ms / 118 tokens ( 12.51 ms per token, 79.95 tokens per second) 3.12.289.407 I slot print_timing: id 0 | task 12808 | total time = 1659.11 ms / 584 tokens 3.12.289.407 I slot print_timing: id 0 | task 12808 | graphs reused = 12182 3.12.289.408 I slot print_timing: id 0 | task 12808 | graph reallocs = 0 / 0 (same size) / (changed size) 3.12.289.438 I slot release: id 0 | task 12808 | stop processing: n_tokens = 615, truncated = 0 3.12.294.512 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 615, t_last = 192187160 3.12.294.567 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.235 MiB) 3.12.343.490 I slot launch_slot_: id 0 | task 12929 | processing task, is_child = 0 3.13.757.577 I slot print_timing: id 0 | task 12929 | prompt eval time = 165.47 ms / 415 tokens ( 0.40 ms per token, 2507.95 tokens per second) 3.13.757.582 I slot print_timing: id 0 | task 12929 | eval time = 1248.59 ms / 100 tokens ( 12.61 ms per token, 79.29 tokens per second) 3.13.757.583 I slot print_timing: id 0 | task 12929 | total time = 1414.07 ms / 515 tokens 3.13.757.584 I slot print_timing: id 0 | task 12929 | graphs reused = 12279 3.13.757.585 I slot print_timing: id 0 | task 12929 | graph reallocs = 0 / 0 (same size) / (changed size) 3.13.757.616 I slot release: id 0 | task 12929 | stop processing: n_tokens = 546, truncated = 0 3.13.775.712 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 546, t_last = 193655338 3.13.775.764 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.768 MiB) 3.13.830.845 I slot launch_slot_: id 0 | task 13032 | processing task, is_child = 0 3.15.148.917 I slot print_timing: id 0 | task 13032 | prompt eval time = 159.49 ms / 352 tokens ( 0.45 ms per token, 2207.03 tokens per second) 3.15.148.924 I slot print_timing: id 0 | task 13032 | eval time = 1158.56 ms / 92 tokens ( 12.73 ms per token, 78.55 tokens per second) 3.15.148.925 I slot print_timing: id 0 | task 13032 | total time = 1318.05 ms / 444 tokens 3.15.148.926 I slot print_timing: id 0 | task 13032 | graphs reused = 12369 3.15.148.926 I slot print_timing: id 0 | task 13032 | graph reallocs = 0 / 0 (same size) / (changed size) 3.15.148.956 I slot release: id 0 | task 13032 | stop processing: n_tokens = 475, truncated = 0 3.15.182.541 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 475, t_last = 195046678 3.15.182.595 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.142 MiB) 3.15.228.027 I slot launch_slot_: id 0 | task 13127 | processing task, is_child = 0 3.17.423.801 I slot print_timing: id 0 | task 13127 | prompt eval time = 219.09 ms / 550 tokens ( 0.40 ms per token, 2510.37 tokens per second) 3.17.423.806 I slot print_timing: id 0 | task 13127 | eval time = 1976.66 ms / 161 tokens ( 12.35 ms per token, 80.94 tokens per second) 3.17.423.807 I slot print_timing: id 0 | task 13127 | total time = 2195.75 ms / 711 tokens 3.17.423.809 I slot print_timing: id 0 | task 13127 | graphs reused = 12528 3.17.423.810 I slot print_timing: id 0 | task 13127 | graph reallocs = 0 / 0 (same size) / (changed size) 3.17.423.848 I slot release: id 0 | task 13127 | stop processing: n_tokens = 742, truncated = 0 3.17.429.984 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 742, t_last = 197321570 3.17.430.041 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.487 MiB) 3.17.484.557 I slot launch_slot_: id 0 | task 13292 | processing task, is_child = 0 3.20.755.066 I slot print_timing: id 0 | task 13292 | n_gen = 241, tg = 79.73 t/s, tg_3s = 80.07 t/s 3.20.865.031 I slot print_timing: id 0 | task 13292 | prompt eval time = 260.49 ms / 772 tokens ( 0.34 ms per token, 2963.66 tokens per second) 3.20.865.036 I slot print_timing: id 0 | task 13292 | eval time = 3119.97 ms / 250 tokens ( 12.53 ms per token, 79.81 tokens per second) 3.20.865.037 I slot print_timing: id 0 | task 13292 | total time = 3380.46 ms / 1022 tokens 3.20.865.038 I slot print_timing: id 0 | task 13292 | graphs reused = 12775 3.20.865.039 I slot print_timing: id 0 | task 13292 | graph reallocs = 0 / 0 (same size) / (changed size) 3.20.865.078 I slot release: id 0 | task 13292 | stop processing: n_tokens = 1053, truncated = 0 3.20.889.474 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1053, t_last = 200762801 3.20.889.549 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.206 MiB) 3.20.947.069 I slot launch_slot_: id 0 | task 13546 | processing task, is_child = 0 3.23.725.583 I slot print_timing: id 0 | task 13546 | prompt eval time = 250.32 ms / 683 tokens ( 0.37 ms per token, 2728.45 tokens per second) 3.23.725.589 I slot print_timing: id 0 | task 13546 | eval time = 2528.17 ms / 200 tokens ( 12.70 ms per token, 78.71 tokens per second) 3.23.725.590 I slot print_timing: id 0 | task 13546 | total time = 2778.49 ms / 883 tokens 3.23.725.591 I slot print_timing: id 0 | task 13546 | graphs reused = 12972 3.23.725.591 I slot print_timing: id 0 | task 13546 | graph reallocs = 0 / 0 (same size) / (changed size) 3.23.725.631 I slot release: id 0 | task 13546 | stop processing: n_tokens = 914, truncated = 0 3.23.751.832 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 914, t_last = 203623354 3.23.751.896 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.859 MiB) 3.23.816.717 I slot launch_slot_: id 0 | task 13750 | processing task, is_child = 0 3.27.047.867 I slot print_timing: id 0 | task 13750 | n_gen = 241, tg = 79.71 t/s, tg_3s = 80.04 t/s 3.27.124.138 I slot print_timing: id 0 | task 13750 | prompt eval time = 220.24 ms / 579 tokens ( 0.38 ms per token, 2628.99 tokens per second) 3.27.124.143 I slot print_timing: id 0 | task 13750 | eval time = 3087.16 ms / 247 tokens ( 12.55 ms per token, 79.68 tokens per second) 3.27.124.144 I slot print_timing: id 0 | task 13750 | total time = 3307.40 ms / 826 tokens 3.27.124.145 I slot print_timing: id 0 | task 13750 | graphs reused = 13216 3.27.124.146 I slot print_timing: id 0 | task 13750 | graph reallocs = 0 / 0 (same size) / (changed size) 3.27.124.181 I slot release: id 0 | task 13750 | stop processing: n_tokens = 857, truncated = 0 3.27.151.141 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 857, t_last = 207021903 3.27.151.202 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 324.802 MiB) 3.27.156.634 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.703 MiB) 3.27.218.897 I slot launch_slot_: id 0 | task 14001 | processing task, is_child = 0 3.29.147.293 I slot print_timing: id 0 | task 14001 | prompt eval time = 207.65 ms / 500 tokens ( 0.42 ms per token, 2407.92 tokens per second) 3.29.147.299 I slot print_timing: id 0 | task 14001 | eval time = 1720.73 ms / 140 tokens ( 12.38 ms per token, 80.78 tokens per second) 3.29.147.300 I slot print_timing: id 0 | task 14001 | total time = 1928.38 ms / 640 tokens 3.29.147.301 I slot print_timing: id 0 | task 14001 | graphs reused = 13354 3.29.147.302 I slot print_timing: id 0 | task 14001 | graph reallocs = 0 / 0 (same size) / (changed size) 3.29.147.336 I slot release: id 0 | task 14001 | stop processing: n_tokens = 671, truncated = 0 3.29.175.952 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 671, t_last = 209045058 3.29.176.011 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.922 MiB) 3.29.224.619 I slot launch_slot_: id 0 | task 14144 | processing task, is_child = 0 3.32.438.747 I slot print_timing: id 0 | task 14144 | prompt eval time = 268.59 ms / 776 tokens ( 0.35 ms per token, 2889.12 tokens per second) 3.32.438.753 I slot print_timing: id 0 | task 14144 | eval time = 2945.51 ms / 234 tokens ( 12.64 ms per token, 79.10 tokens per second) 3.32.438.754 I slot print_timing: id 0 | task 14144 | total time = 3214.11 ms / 1010 tokens 3.32.438.755 I slot print_timing: id 0 | task 14144 | graphs reused = 13585 3.32.438.755 I slot print_timing: id 0 | task 14144 | graph reallocs = 0 / 0 (same size) / (changed size) 3.32.438.795 I slot release: id 0 | task 14144 | stop processing: n_tokens = 1041, truncated = 0 3.32.464.034 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1041, t_last = 212336518 3.32.464.108 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.800 MiB) 3.32.522.866 I slot launch_slot_: id 0 | task 14382 | processing task, is_child = 0 3.35.623.561 I slot print_timing: id 0 | task 14382 | prompt eval time = 192.64 ms / 504 tokens ( 0.38 ms per token, 2616.32 tokens per second) 3.35.623.567 I slot print_timing: id 0 | task 14382 | eval time = 2908.04 ms / 232 tokens ( 12.59 ms per token, 79.44 tokens per second) 3.35.623.568 I slot print_timing: id 0 | task 14382 | total time = 3100.67 ms / 736 tokens 3.35.623.569 I slot print_timing: id 0 | task 14382 | graphs reused = 13815 3.35.623.570 I slot print_timing: id 0 | task 14382 | graph reallocs = 0 / 0 (same size) / (changed size) 3.35.623.603 I slot release: id 0 | task 14382 | stop processing: n_tokens = 767, truncated = 0 3.35.640.161 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 767, t_last = 215521326 3.35.640.226 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.422 MiB) 3.35.688.945 I slot launch_slot_: id 0 | task 14617 | processing task, is_child = 0 3.38.778.310 I slot print_timing: id 0 | task 14617 | prompt eval time = 236.09 ms / 633 tokens ( 0.37 ms per token, 2681.14 tokens per second) 3.38.778.315 I slot print_timing: id 0 | task 14617 | eval time = 2853.25 ms / 230 tokens ( 12.46 ms per token, 80.26 tokens per second) 3.38.778.316 I slot print_timing: id 0 | task 14617 | total time = 3089.35 ms / 863 tokens 3.38.778.317 I slot print_timing: id 0 | task 14617 | graphs reused = 14042 3.38.778.318 I slot print_timing: id 0 | task 14617 | graph reallocs = 0 / 0 (same size) / (changed size) 3.38.778.354 I slot release: id 0 | task 14617 | stop processing: n_tokens = 894, truncated = 0 3.38.817.604 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 894, t_last = 218676076 3.38.817.674 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.709 MiB) 3.38.872.337 I slot launch_slot_: id 0 | task 14851 | processing task, is_child = 0 3.40.960.742 I slot print_timing: id 0 | task 14851 | prompt eval time = 173.36 ms / 395 tokens ( 0.44 ms per token, 2278.46 tokens per second) 3.40.960.747 I slot print_timing: id 0 | task 14851 | eval time = 1915.02 ms / 153 tokens ( 12.60 ms per token, 79.37 tokens per second) 3.40.960.748 I slot print_timing: id 0 | task 14851 | total time = 2088.38 ms / 548 tokens 3.40.960.749 I slot print_timing: id 0 | task 14851 | graphs reused = 14192 3.40.960.750 I slot print_timing: id 0 | task 14851 | graph reallocs = 0 / 0 (same size) / (changed size) 3.40.960.785 I slot release: id 0 | task 14851 | stop processing: n_tokens = 579, truncated = 0 3.40.966.185 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 579, t_last = 220858507 3.40.966.242 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.704 MiB) 3.41.012.208 I slot launch_slot_: id 0 | task 15007 | processing task, is_child = 0 3.44.106.439 I slot print_timing: id 0 | task 15007 | prompt eval time = 218.14 ms / 584 tokens ( 0.37 ms per token, 2677.16 tokens per second) 3.44.106.445 I slot print_timing: id 0 | task 15007 | eval time = 2876.07 ms / 228 tokens ( 12.67 ms per token, 78.93 tokens per second) 3.44.106.446 I slot print_timing: id 0 | task 15007 | total time = 3094.21 ms / 812 tokens 3.44.106.447 I slot print_timing: id 0 | task 15007 | graphs reused = 14417 3.44.106.448 I slot print_timing: id 0 | task 15007 | graph reallocs = 0 / 0 (same size) / (changed size) 3.44.106.484 I slot release: id 0 | task 15007 | stop processing: n_tokens = 843, truncated = 0 3.44.127.497 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 843, t_last = 224004207 3.44.127.566 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 322.269 MiB) 3.44.180.028 I slot launch_slot_: id 0 | task 15239 | processing task, is_child = 0 3.47.441.531 I slot print_timing: id 0 | task 15239 | n_gen = 241, tg = 79.90 t/s, tg_3s = 80.23 t/s 3.47.606.175 I slot print_timing: id 0 | task 15239 | prompt eval time = 257.70 ms / 695 tokens ( 0.37 ms per token, 2696.89 tokens per second) 3.47.606.181 I slot print_timing: id 0 | task 15239 | eval time = 3168.42 ms / 254 tokens ( 12.52 ms per token, 79.85 tokens per second) 3.47.606.182 I slot print_timing: id 0 | task 15239 | total time = 3426.13 ms / 949 tokens 3.47.606.184 I slot print_timing: id 0 | task 15239 | graphs reused = 14668 3.47.606.185 I slot print_timing: id 0 | task 15239 | graph reallocs = 0 / 0 (same size) / (changed size) 3.47.606.224 I slot release: id 0 | task 15239 | stop processing: n_tokens = 980, truncated = 0 3.47.636.286 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 980, t_last = 227503946 3.47.636.349 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 322.675 MiB) 3.47.693.455 I slot launch_slot_: id 0 | task 15497 | processing task, is_child = 0 3.50.548.442 I slot print_timing: id 0 | task 15497 | prompt eval time = 269.46 ms / 769 tokens ( 0.35 ms per token, 2853.90 tokens per second) 3.50.548.447 I slot print_timing: id 0 | task 15497 | eval time = 2585.51 ms / 209 tokens ( 12.43 ms per token, 80.45 tokens per second) 3.50.548.448 I slot print_timing: id 0 | task 15497 | total time = 2854.97 ms / 978 tokens 3.50.548.449 I slot print_timing: id 0 | task 15497 | graphs reused = 14875 3.50.548.450 I slot print_timing: id 0 | task 15497 | graph reallocs = 0 / 0 (same size) / (changed size) 3.50.548.490 I slot release: id 0 | task 15497 | stop processing: n_tokens = 1009, truncated = 0 3.50.569.991 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1009, t_last = 230446213 3.50.570.063 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.926 MiB) 3.50.575.368 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.329 MiB) 3.50.635.864 I slot launch_slot_: id 0 | task 15710 | processing task, is_child = 0 3.52.949.620 I slot print_timing: id 0 | task 15710 | prompt eval time = 218.45 ms / 576 tokens ( 0.38 ms per token, 2636.81 tokens per second) 3.52.949.626 I slot print_timing: id 0 | task 15710 | eval time = 2095.29 ms / 167 tokens ( 12.62 ms per token, 79.23 tokens per second) 3.52.949.627 I slot print_timing: id 0 | task 15710 | total time = 2313.74 ms / 743 tokens 3.52.949.628 I slot print_timing: id 0 | task 15710 | graphs reused = 15039 3.52.949.629 I slot print_timing: id 0 | task 15710 | graph reallocs = 0 / 0 (same size) / (changed size) 3.52.949.666 I slot release: id 0 | task 15710 | stop processing: n_tokens = 774, truncated = 0 3.52.965.416 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 774, t_last = 232847388 3.52.965.478 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.109 MiB) 3.53.019.942 I slot launch_slot_: id 0 | task 15881 | processing task, is_child = 0 3.56.261.202 I slot print_timing: id 0 | task 15881 | n_gen = 239, tg = 79.22 t/s, tg_3s = 79.55 t/s 3.56.998.710 I slot print_timing: id 0 | task 15881 | prompt eval time = 236.92 ms / 655 tokens ( 0.36 ms per token, 2764.65 tokens per second) 3.56.998.716 I slot print_timing: id 0 | task 15881 | eval time = 3741.83 ms / 299 tokens ( 12.56 ms per token, 79.64 tokens per second) 3.56.998.717 I slot print_timing: id 0 | task 15881 | total time = 3978.75 ms / 954 tokens 3.56.998.718 I slot print_timing: id 0 | task 15881 | graphs reused = 15335 3.56.998.718 I slot print_timing: id 0 | task 15881 | graph reallocs = 0 / 0 (same size) / (changed size) 3.56.998.755 I slot release: id 0 | task 15881 | stop processing: n_tokens = 985, truncated = 0 3.57.039.927 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 985, t_last = 236896478 3.57.039.998 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.611 MiB) 3.57.097.025 I slot launch_slot_: id 0 | task 16184 | processing task, is_child = 0 3.59.096.798 I slot print_timing: id 0 | task 16184 | prompt eval time = 225.90 ms / 621 tokens ( 0.36 ms per token, 2749.04 tokens per second) 3.59.096.804 I slot print_timing: id 0 | task 16184 | eval time = 1773.86 ms / 142 tokens ( 12.58 ms per token, 79.49 tokens per second) 3.59.096.806 I slot print_timing: id 0 | task 16184 | total time = 1999.75 ms / 763 tokens 3.59.096.807 I slot print_timing: id 0 | task 16184 | graphs reused = 15474 3.59.096.808 I slot print_timing: id 0 | task 16184 | graph reallocs = 0 / 0 (same size) / (changed size) 3.59.096.845 I slot release: id 0 | task 16184 | stop processing: n_tokens = 794, truncated = 0 3.59.115.906 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 794, t_last = 238994567 3.59.115.972 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.014 MiB) 3.59.167.870 I slot launch_slot_: id 0 | task 16330 | processing task, is_child = 0 4.01.547.787 I slot print_timing: id 0 | task 16330 | prompt eval time = 272.27 ms / 767 tokens ( 0.35 ms per token, 2817.02 tokens per second) 4.01.547.792 I slot print_timing: id 0 | task 16330 | eval time = 2107.62 ms / 170 tokens ( 12.47 ms per token, 80.19 tokens per second) 4.01.547.794 I slot print_timing: id 0 | task 16330 | total time = 2379.90 ms / 937 tokens 4.01.547.795 I slot print_timing: id 0 | task 16330 | graphs reused = 15642 4.01.547.796 I slot print_timing: id 0 | task 16330 | graph reallocs = 0 / 0 (same size) / (changed size) 4.01.547.837 I slot release: id 0 | task 16330 | stop processing: n_tokens = 968, truncated = 0 4.01.583.937 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 968, t_last = 241445560 4.01.583.997 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.453 MiB) 4.01.639.609 I slot launch_slot_: id 0 | task 16504 | processing task, is_child = 0 4.04.733.462 I slot print_timing: id 0 | task 16504 | prompt eval time = 287.86 ms / 864 tokens ( 0.33 ms per token, 3001.47 tokens per second) 4.04.733.467 I slot print_timing: id 0 | task 16504 | eval time = 2805.97 ms / 222 tokens ( 12.70 ms per token, 78.76 tokens per second) 4.04.733.469 I slot print_timing: id 0 | task 16504 | total time = 3093.83 ms / 1086 tokens 4.04.733.469 I slot print_timing: id 0 | task 16504 | graphs reused = 15861 4.04.733.470 I slot print_timing: id 0 | task 16504 | graph reallocs = 0 / 0 (same size) / (changed size) 4.04.733.514 I slot release: id 0 | task 16504 | stop processing: n_tokens = 1117, truncated = 0 4.04.739.177 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1117, t_last = 244631236 4.04.739.255 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.736 MiB) 4.04.744.492 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.892 MiB) 4.04.814.342 I slot launch_slot_: id 0 | task 16730 | processing task, is_child = 0 4.07.018.478 I slot print_timing: id 0 | task 16730 | prompt eval time = 241.09 ms / 646 tokens ( 0.37 ms per token, 2679.54 tokens per second) 4.07.018.484 I slot print_timing: id 0 | task 16730 | eval time = 1963.03 ms / 158 tokens ( 12.50 ms per token, 79.98 tokens per second) 4.07.018.485 I slot print_timing: id 0 | task 16730 | total time = 2204.12 ms / 804 tokens 4.07.018.486 I slot print_timing: id 0 | task 16730 | graphs reused = 16016 4.07.018.487 I slot print_timing: id 0 | task 16730 | graph reallocs = 0 / 0 (same size) / (changed size) 4.07.018.525 I slot release: id 0 | task 16730 | stop processing: n_tokens = 835, truncated = 0 4.07.040.227 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 835, t_last = 246916248 4.07.040.291 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.768 MiB) 4.07.095.547 I slot launch_slot_: id 0 | task 16892 | processing task, is_child = 0 4.10.334.404 I slot print_timing: id 0 | task 16892 | prompt eval time = 254.62 ms / 720 tokens ( 0.35 ms per token, 2827.77 tokens per second) 4.10.334.409 I slot print_timing: id 0 | task 16892 | eval time = 2984.22 ms / 240 tokens ( 12.49 ms per token, 80.09 tokens per second) 4.10.334.410 I slot print_timing: id 0 | task 16892 | total time = 3238.84 ms / 960 tokens 4.10.334.411 I slot print_timing: id 0 | task 16892 | graphs reused = 16253 4.10.334.412 I slot print_timing: id 0 | task 16892 | graph reallocs = 0 / 0 (same size) / (changed size) 4.10.334.452 I slot release: id 0 | task 16892 | stop processing: n_tokens = 991, truncated = 0 4.10.353.570 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 991, t_last = 250232174 4.10.353.643 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.923 MiB) 4.10.412.704 I slot launch_slot_: id 0 | task 17136 | processing task, is_child = 0 4.13.522.206 I slot print_timing: id 0 | task 17136 | prompt eval time = 202.23 ms / 509 tokens ( 0.40 ms per token, 2516.89 tokens per second) 4.13.522.211 I slot print_timing: id 0 | task 17136 | eval time = 2907.25 ms / 232 tokens ( 12.59 ms per token, 79.46 tokens per second) 4.13.522.212 I slot print_timing: id 0 | task 17136 | total time = 3109.48 ms / 741 tokens 4.13.522.213 I slot print_timing: id 0 | task 17136 | graphs reused = 16482 4.13.522.214 I slot print_timing: id 0 | task 17136 | graph reallocs = 0 / 0 (same size) / (changed size) 4.13.522.246 I slot release: id 0 | task 17136 | stop processing: n_tokens = 772, truncated = 0 4.13.567.909 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 772, t_last = 253419969 4.13.567.969 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.736 MiB) 4.13.617.601 I slot launch_slot_: id 0 | task 17371 | processing task, is_child = 0 4.16.845.975 I slot print_timing: id 0 | task 17371 | n_gen = 239, tg = 79.05 t/s, tg_3s = 79.38 t/s 4.17.187.740 I slot print_timing: id 0 | task 17371 | prompt eval time = 217.59 ms / 581 tokens ( 0.37 ms per token, 2670.17 tokens per second) 4.17.187.746 I slot print_timing: id 0 | task 17371 | eval time = 3352.53 ms / 267 tokens ( 12.60 ms per token, 79.34 tokens per second) 4.17.187.747 I slot print_timing: id 0 | task 17371 | total time = 3570.12 ms / 848 tokens 4.17.187.747 I slot print_timing: id 0 | task 17371 | graphs reused = 16746 4.17.187.748 I slot print_timing: id 0 | task 17371 | graph reallocs = 0 / 0 (same size) / (changed size) 4.17.187.785 I slot release: id 0 | task 17371 | stop processing: n_tokens = 879, truncated = 0 4.17.204.355 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 879, t_last = 257085507 4.17.204.426 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.579 MiB) 4.17.269.840 I slot launch_slot_: id 0 | task 17642 | processing task, is_child = 0 4.20.568.834 I slot print_timing: id 0 | task 17642 | n_gen = 239, tg = 79.31 t/s, tg_3s = 79.65 t/s 4.20.581.798 I slot print_timing: id 0 | task 17642 | prompt eval time = 298.25 ms / 925 tokens ( 0.32 ms per token, 3101.48 tokens per second) 4.20.581.803 I slot print_timing: id 0 | task 17642 | eval time = 3013.70 ms / 240 tokens ( 12.61 ms per token, 79.30 tokens per second) 4.20.581.803 I slot print_timing: id 0 | task 17642 | total time = 3311.94 ms / 1165 tokens 4.20.581.804 I slot print_timing: id 0 | task 17642 | graphs reused = 16983 4.20.581.805 I slot print_timing: id 0 | task 17642 | graph reallocs = 0 / 0 (same size) / (changed size) 4.20.581.851 I slot release: id 0 | task 17642 | stop processing: n_tokens = 1196, truncated = 0 4.20.604.808 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1196, t_last = 260479573 4.20.604.890 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.358 MiB) 4.20.659.612 I slot launch_slot_: id 0 | task 17886 | processing task, is_child = 0 4.23.951.575 I slot print_timing: id 0 | task 17886 | n_gen = 241, tg = 79.92 t/s, tg_3s = 80.25 t/s 4.24.204.796 I slot print_timing: id 0 | task 17886 | prompt eval time = 288.89 ms / 885 tokens ( 0.33 ms per token, 3063.48 tokens per second) 4.24.204.802 I slot print_timing: id 0 | task 17886 | eval time = 3256.28 ms / 261 tokens ( 12.52 ms per token, 79.85 tokens per second) 4.24.204.803 I slot print_timing: id 0 | task 17886 | total time = 3545.16 ms / 1146 tokens 4.24.204.804 I slot print_timing: id 0 | task 17886 | graphs reused = 17241 4.24.204.805 I slot print_timing: id 0 | task 17886 | graph reallocs = 0 / 0 (same size) / (changed size) 4.24.204.851 I slot release: id 0 | task 17886 | stop processing: n_tokens = 1177, truncated = 0 4.24.247.115 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1177, t_last = 264102573 4.24.247.198 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.959 MiB) 4.24.304.862 I slot launch_slot_: id 0 | task 18151 | processing task, is_child = 0 4.25.817.380 I slot print_timing: id 0 | task 18151 | prompt eval time = 168.79 ms / 392 tokens ( 0.43 ms per token, 2322.44 tokens per second) 4.25.817.386 I slot print_timing: id 0 | task 18151 | eval time = 1343.71 ms / 109 tokens ( 12.44 ms per token, 80.37 tokens per second) 4.25.817.387 I slot print_timing: id 0 | task 18151 | total time = 1512.50 ms / 501 tokens 4.25.817.387 I slot print_timing: id 0 | task 18151 | graphs reused = 17347 4.25.817.389 I slot print_timing: id 0 | task 18151 | graph reallocs = 0 / 0 (same size) / (changed size) 4.25.817.420 I slot release: id 0 | task 18151 | stop processing: n_tokens = 532, truncated = 0 4.25.855.277 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 532, t_last = 265715143 4.25.855.331 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 384.685 MiB) 4.25.906.028 I slot launch_slot_: id 0 | task 18263 | processing task, is_child = 0 4.28.404.854 I slot print_timing: id 0 | task 18263 | prompt eval time = 153.01 ms / 331 tokens ( 0.46 ms per token, 2163.27 tokens per second) 4.28.404.860 I slot print_timing: id 0 | task 18263 | eval time = 2345.80 ms / 186 tokens ( 12.68 ms per token, 78.86 tokens per second) 4.28.404.861 I slot print_timing: id 0 | task 18263 | total time = 2498.81 ms / 517 tokens 4.28.404.862 I slot print_timing: id 0 | task 18263 | graphs reused = 17530 4.28.404.862 I slot print_timing: id 0 | task 18263 | graph reallocs = 0 / 0 (same size) / (changed size) 4.28.404.889 I slot release: id 0 | task 18263 | stop processing: n_tokens = 548, truncated = 0 4.28.409.430 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 548, t_last = 268302612 4.28.409.481 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 380.338 MiB) 4.28.466.093 I slot launch_slot_: id 0 | task 18452 | processing task, is_child = 0 4.29.460.253 I slot print_timing: id 0 | task 18452 | prompt eval time = 159.58 ms / 357 tokens ( 0.45 ms per token, 2237.09 tokens per second) 4.29.460.262 I slot print_timing: id 0 | task 18452 | eval time = 834.56 ms / 68 tokens ( 12.46 ms per token, 80.28 tokens per second) 4.29.460.263 I slot print_timing: id 0 | task 18452 | total time = 994.14 ms / 425 tokens 4.29.460.264 I slot print_timing: id 0 | task 18452 | graphs reused = 17596 4.29.460.265 I slot print_timing: id 0 | task 18452 | graph reallocs = 0 / 0 (same size) / (changed size) 4.29.460.293 I slot release: id 0 | task 18452 | stop processing: n_tokens = 456, truncated = 0 4.29.492.386 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 456, t_last = 269358015 4.29.492.433 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.555 MiB) 4.29.548.076 I slot launch_slot_: id 0 | task 18523 | processing task, is_child = 0 4.31.098.258 I slot print_timing: id 0 | task 18523 | prompt eval time = 151.35 ms / 315 tokens ( 0.48 ms per token, 2081.21 tokens per second) 4.31.098.263 I slot print_timing: id 0 | task 18523 | eval time = 1398.81 ms / 113 tokens ( 12.49 ms per token, 80.07 tokens per second) 4.31.098.264 I slot print_timing: id 0 | task 18523 | total time = 1550.16 ms / 428 tokens 4.31.098.265 I slot print_timing: id 0 | task 18523 | graphs reused = 17707 4.31.098.266 I slot print_timing: id 0 | task 18523 | graph reallocs = 0 / 0 (same size) / (changed size) 4.31.098.294 I slot release: id 0 | task 18523 | stop processing: n_tokens = 459, truncated = 0 4.31.121.993 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 459, t_last = 270996016 4.31.122.040 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 322.488 MiB) 4.31.170.049 I slot launch_slot_: id 0 | task 18639 | processing task, is_child = 0 4.32.492.724 I slot print_timing: id 0 | task 18639 | prompt eval time = 159.99 ms / 378 tokens ( 0.42 ms per token, 2362.69 tokens per second) 4.32.492.729 I slot print_timing: id 0 | task 18639 | eval time = 1162.67 ms / 92 tokens ( 12.78 ms per token, 78.27 tokens per second) 4.32.492.730 I slot print_timing: id 0 | task 18639 | total time = 1322.65 ms / 470 tokens 4.32.492.731 I slot print_timing: id 0 | task 18639 | graphs reused = 17797 4.32.492.732 I slot print_timing: id 0 | task 18639 | graph reallocs = 0 / 0 (same size) / (changed size) 4.32.492.763 I slot release: id 0 | task 18639 | stop processing: n_tokens = 501, truncated = 0 4.32.512.474 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 501, t_last = 272390485 4.32.512.524 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 384.309 MiB) 4.32.564.000 I slot launch_slot_: id 0 | task 18734 | processing task, is_child = 0 4.33.488.568 I slot print_timing: id 0 | task 18734 | prompt eval time = 149.65 ms / 295 tokens ( 0.51 ms per token, 1971.25 tokens per second) 4.33.488.573 I slot print_timing: id 0 | task 18734 | eval time = 774.90 ms / 63 tokens ( 12.50 ms per token, 80.01 tokens per second) 4.33.488.574 I slot print_timing: id 0 | task 18734 | total time = 924.55 ms / 358 tokens 4.33.488.575 I slot print_timing: id 0 | task 18734 | graphs reused = 17858 4.33.488.576 I slot print_timing: id 0 | task 18734 | graph reallocs = 0 / 0 (same size) / (changed size) 4.33.488.602 I slot release: id 0 | task 18734 | stop processing: n_tokens = 389, truncated = 0 4.33.513.533 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 389, t_last = 273386325 4.33.513.576 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.490 MiB) 4.33.559.637 I slot launch_slot_: id 0 | task 18800 | processing task, is_child = 0 4.36.721.266 I slot print_timing: id 0 | task 18800 | n_gen = 240, tg = 79.43 t/s, tg_3s = 79.76 t/s 4.38.287.023 I slot print_timing: id 0 | task 18800 | prompt eval time = 152.65 ms / 337 tokens ( 0.45 ms per token, 2207.66 tokens per second) 4.38.287.029 I slot print_timing: id 0 | task 18800 | eval time = 4574.72 ms / 367 tokens ( 12.50 ms per token, 80.00 tokens per second) 4.38.287.030 I slot print_timing: id 0 | task 18800 | total time = 4727.37 ms / 704 tokens 4.38.287.031 I slot print_timing: id 0 | task 18800 | graphs reused = 18222 4.38.287.031 I slot print_timing: id 0 | task 18800 | graph reallocs = 0 / 0 (same size) / (changed size) 4.38.287.060 I slot release: id 0 | task 18800 | stop processing: n_tokens = 735, truncated = 0 4.38.314.396 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 735, t_last = 278184783 4.38.314.456 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.712 MiB) 4.38.364.245 I slot launch_slot_: id 0 | task 19170 | processing task, is_child = 0 4.40.342.956 I slot print_timing: id 0 | task 19170 | prompt eval time = 152.43 ms / 325 tokens ( 0.47 ms per token, 2132.18 tokens per second) 4.40.342.961 I slot print_timing: id 0 | task 19170 | eval time = 1826.27 ms / 148 tokens ( 12.42 ms per token, 80.49 tokens per second) 4.40.342.962 I slot print_timing: id 0 | task 19170 | total time = 1978.69 ms / 473 tokens 4.40.342.963 I slot print_timing: id 0 | task 19170 | graphs reused = 18368 4.40.342.964 I slot print_timing: id 0 | task 19170 | graph reallocs = 0 / 0 (same size) / (changed size) 4.40.342.992 I slot release: id 0 | task 19170 | stop processing: n_tokens = 504, truncated = 0 4.40.358.995 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.108 (> 0.100 thold), f_keep = 0.063 4.40.398.694 I slot launch_slot_: id 0 | task 19321 | processing task, is_child = 0 4.41.525.457 I slot print_timing: id 0 | task 19321 | prompt eval time = 135.08 ms / 264 tokens ( 0.51 ms per token, 1954.40 tokens per second) 4.41.525.463 I slot print_timing: id 0 | task 19321 | eval time = 991.66 ms / 82 tokens ( 12.24 ms per token, 81.68 tokens per second) 4.41.525.464 I slot print_timing: id 0 | task 19321 | total time = 1126.74 ms / 346 tokens 4.41.525.465 I slot print_timing: id 0 | task 19321 | graphs reused = 18448 4.41.525.466 I slot print_timing: id 0 | task 19321 | graph reallocs = 0 / 0 (same size) / (changed size) 4.41.525.492 I slot release: id 0 | task 19321 | stop processing: n_tokens = 377, truncated = 0 4.41.529.980 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 377, t_last = 281423214 4.41.530.022 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.611 MiB) 4.41.574.998 I slot launch_slot_: id 0 | task 19406 | processing task, is_child = 0 4.43.181.319 I slot print_timing: id 0 | task 19406 | prompt eval time = 152.27 ms / 331 tokens ( 0.46 ms per token, 2173.76 tokens per second) 4.43.181.325 I slot print_timing: id 0 | task 19406 | eval time = 1454.03 ms / 120 tokens ( 12.22 ms per token, 81.84 tokens per second) 4.43.181.326 I slot print_timing: id 0 | task 19406 | total time = 1606.30 ms / 451 tokens 4.43.181.327 I slot print_timing: id 0 | task 19406 | graphs reused = 18566 4.43.181.327 I slot print_timing: id 0 | task 19406 | graph reallocs = 0 / 0 (same size) / (changed size) 4.43.181.355 I slot release: id 0 | task 19406 | stop processing: n_tokens = 482, truncated = 0 4.43.223.086 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 482, t_last = 283079077 4.43.223.134 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.117 MiB) 4.43.281.974 I slot launch_slot_: id 0 | task 19529 | processing task, is_child = 0 4.45.654.045 I slot print_timing: id 0 | task 19529 | prompt eval time = 152.69 ms / 333 tokens ( 0.46 ms per token, 2180.95 tokens per second) 4.45.654.051 I slot print_timing: id 0 | task 19529 | eval time = 2219.36 ms / 181 tokens ( 12.33 ms per token, 81.10 tokens per second) 4.45.654.052 I slot print_timing: id 0 | task 19529 | total time = 2372.05 ms / 514 tokens 4.45.654.053 I slot print_timing: id 0 | task 19529 | graphs reused = 18744 4.45.654.054 I slot print_timing: id 0 | task 19529 | graph reallocs = 0 / 0 (same size) / (changed size) 4.45.654.086 I slot release: id 0 | task 19529 | stop processing: n_tokens = 545, truncated = 0 4.45.675.093 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 545, t_last = 285551808 4.45.675.146 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.402 MiB) 4.45.725.716 I slot launch_slot_: id 0 | task 19713 | processing task, is_child = 0 4.47.612.182 I slot print_timing: id 0 | task 19713 | prompt eval time = 156.22 ms / 346 tokens ( 0.45 ms per token, 2214.90 tokens per second) 4.47.612.188 I slot print_timing: id 0 | task 19713 | eval time = 1730.23 ms / 142 tokens ( 12.27 ms per token, 81.49 tokens per second) 4.47.612.189 I slot print_timing: id 0 | task 19713 | total time = 1886.45 ms / 488 tokens 4.47.612.189 I slot print_timing: id 0 | task 19713 | graphs reused = 18883 4.47.612.190 I slot print_timing: id 0 | task 19713 | graph reallocs = 0 / 0 (same size) / (changed size) 4.47.612.217 I slot release: id 0 | task 19713 | stop processing: n_tokens = 519, truncated = 0 4.47.649.335 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 519, t_last = 287509940 4.47.649.385 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 383.309 MiB) 4.47.702.979 I slot launch_slot_: id 0 | task 19858 | processing task, is_child = 0 4.49.154.165 I slot print_timing: id 0 | task 19858 | prompt eval time = 151.34 ms / 325 tokens ( 0.47 ms per token, 2147.54 tokens per second) 4.49.154.171 I slot print_timing: id 0 | task 19858 | eval time = 1299.83 ms / 107 tokens ( 12.26 ms per token, 81.55 tokens per second) 4.49.154.172 I slot print_timing: id 0 | task 19858 | total time = 1451.17 ms / 432 tokens 4.49.154.173 I slot print_timing: id 0 | task 19858 | graphs reused = 18988 4.49.154.174 I slot print_timing: id 0 | task 19858 | graph reallocs = 0 / 0 (same size) / (changed size) 4.49.154.203 I slot release: id 0 | task 19858 | stop processing: n_tokens = 463, truncated = 0 4.49.170.505 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 463, t_last = 289051925 4.49.170.551 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 375.959 MiB) 4.49.219.099 I slot launch_slot_: id 0 | task 19968 | processing task, is_child = 0 4.50.748.839 I slot print_timing: id 0 | task 19968 | prompt eval time = 152.63 ms / 322 tokens ( 0.47 ms per token, 2109.72 tokens per second) 4.50.748.845 I slot print_timing: id 0 | task 19968 | eval time = 1377.10 ms / 113 tokens ( 12.30 ms per token, 81.33 tokens per second) 4.50.748.846 I slot print_timing: id 0 | task 19968 | total time = 1529.72 ms / 435 tokens 4.50.748.847 I slot print_timing: id 0 | task 19968 | graphs reused = 19099 4.50.748.848 I slot print_timing: id 0 | task 19968 | graph reallocs = 0 / 0 (same size) / (changed size) 4.50.748.876 I slot release: id 0 | task 19968 | stop processing: n_tokens = 466, truncated = 0 4.50.783.293 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 466, t_last = 290646599 4.50.783.341 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.558 MiB) 4.50.833.653 I slot launch_slot_: id 0 | task 20084 | processing task, is_child = 0 4.53.988.042 I slot print_timing: id 0 | task 20084 | n_gen = 246, tg = 81.63 t/s, tg_3s = 81.96 t/s 4.55.637.578 I slot print_timing: id 0 | task 20084 | prompt eval time = 152.85 ms / 338 tokens ( 0.45 ms per token, 2211.38 tokens per second) 4.55.637.583 I slot print_timing: id 0 | task 20084 | eval time = 4651.06 ms / 381 tokens ( 12.24 ms per token, 81.70 tokens per second) 4.55.637.584 I slot print_timing: id 0 | task 20084 | total time = 4803.91 ms / 719 tokens 4.55.637.585 I slot print_timing: id 0 | task 20084 | graphs reused = 19477 4.55.637.586 I slot print_timing: id 0 | task 20084 | graph reallocs = 0 / 0 (same size) / (changed size) 4.55.637.614 I slot release: id 0 | task 20084 | stop processing: n_tokens = 750, truncated = 0 4.55.651.807 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 750, t_last = 295535336 4.55.692.735 I slot launch_slot_: id 0 | task 20468 | processing task, is_child = 0 4.58.849.286 I slot print_timing: id 0 | task 20468 | n_gen = 246, tg = 81.61 t/s, tg_3s = 81.94 t/s 5.00.435.717 I slot print_timing: id 0 | task 20468 | prompt eval time = 154.27 ms / 347 tokens ( 0.44 ms per token, 2249.26 tokens per second) 5.00.435.722 I slot print_timing: id 0 | task 20468 | eval time = 4588.69 ms / 376 tokens ( 12.24 ms per token, 81.72 tokens per second) 5.00.435.724 I slot print_timing: id 0 | task 20468 | total time = 4742.96 ms / 723 tokens 5.00.435.724 I slot print_timing: id 0 | task 20468 | graphs reused = 19850 5.00.435.725 I slot print_timing: id 0 | task 20468 | graph reallocs = 0 / 0 (same size) / (changed size) 5.00.435.754 I slot release: id 0 | task 20468 | stop processing: n_tokens = 754, truncated = 0 5.00.473.612 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 754, t_last = 300333476 5.00.473.675 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 376.585 MiB) 5.00.520.761 I slot launch_slot_: id 0 | task 20847 | processing task, is_child = 0 5.03.683.611 I slot print_timing: id 0 | task 20847 | n_gen = 247, tg = 81.74 t/s, tg_3s = 82.07 t/s 5.04.513.814 I slot print_timing: id 0 | task 20847 | prompt eval time = 153.39 ms / 331 tokens ( 0.46 ms per token, 2157.88 tokens per second) 5.04.513.820 I slot print_timing: id 0 | task 20847 | eval time = 3839.64 ms / 315 tokens ( 12.23 ms per token, 81.78 tokens per second) 5.04.513.821 I slot print_timing: id 0 | task 20847 | total time = 3993.04 ms / 646 tokens 5.04.513.822 I slot print_timing: id 0 | task 20847 | graphs reused = 20162 5.04.513.823 I slot print_timing: id 0 | task 20847 | graph reallocs = 0 / 0 (same size) / (changed size) 5.04.513.849 I slot release: id 0 | task 20847 | stop processing: n_tokens = 677, truncated = 0 5.04.551.012 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 677, t_last = 304411572 5.04.551.068 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.026 MiB) 5.04.600.697 I slot launch_slot_: id 0 | task 21165 | processing task, is_child = 0 5.07.757.345 I slot print_timing: id 0 | task 21165 | n_gen = 246, tg = 81.59 t/s, tg_3s = 81.92 t/s 5.08.417.446 I slot print_timing: id 0 | task 21165 | prompt eval time = 153.66 ms / 345 tokens ( 0.45 ms per token, 2245.23 tokens per second) 5.08.417.451 I slot print_timing: id 0 | task 21165 | eval time = 3663.07 ms / 300 tokens ( 12.25 ms per token, 81.63 tokens per second) 5.08.417.452 I slot print_timing: id 0 | task 21165 | total time = 3816.73 ms / 645 tokens 5.08.417.453 I slot print_timing: id 0 | task 21165 | graphs reused = 20459 5.08.417.454 I slot print_timing: id 0 | task 21165 | graph reallocs = 0 / 0 (same size) / (changed size) 5.08.417.482 I slot release: id 0 | task 21165 | stop processing: n_tokens = 676, truncated = 0 5.08.457.956 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 676, t_last = 308315204 5.08.458.011 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.686 MiB) 5.08.519.672 I slot launch_slot_: id 0 | task 21468 | processing task, is_child = 0 5.10.417.857 I slot print_timing: id 0 | task 21468 | prompt eval time = 151.70 ms / 320 tokens ( 0.47 ms per token, 2109.40 tokens per second) 5.10.417.863 I slot print_timing: id 0 | task 21468 | eval time = 1746.46 ms / 144 tokens ( 12.21 ms per token, 81.88 tokens per second) 5.10.417.864 I slot print_timing: id 0 | task 21468 | total time = 1898.16 ms / 464 tokens 5.10.417.865 I slot print_timing: id 0 | task 21468 | graphs reused = 20601 5.10.417.865 I slot print_timing: id 0 | task 21468 | graph reallocs = 0 / 0 (same size) / (changed size) 5.10.417.892 I slot release: id 0 | task 21468 | stop processing: n_tokens = 495, truncated = 0 5.10.456.774 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 495, t_last = 310315614 5.10.456.822 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 377.867 MiB) 5.10.505.885 I slot launch_slot_: id 0 | task 21615 | processing task, is_child = 0 5.11.361.731 I slot print_timing: id 0 | task 21615 | prompt eval time = 144.79 ms / 297 tokens ( 0.49 ms per token, 2051.18 tokens per second) 5.11.361.737 I slot print_timing: id 0 | task 21615 | eval time = 711.03 ms / 59 tokens ( 12.26 ms per token, 81.57 tokens per second) 5.11.361.738 I slot print_timing: id 0 | task 21615 | total time = 855.83 ms / 356 tokens 5.11.361.739 I slot print_timing: id 0 | task 21615 | graphs reused = 20658 5.11.361.740 I slot print_timing: id 0 | task 21615 | graph reallocs = 0 / 0 (same size) / (changed size) 5.11.361.767 I slot release: id 0 | task 21615 | stop processing: n_tokens = 387, truncated = 0 5.11.377.845 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 387, t_last = 311259490 5.11.377.887 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.746 MiB) 5.11.428.623 I slot launch_slot_: id 0 | task 21677 | processing task, is_child = 0 5.14.593.941 I slot print_timing: id 0 | task 21677 | n_gen = 244, tg = 80.67 t/s, tg_3s = 81.00 t/s 5.14.720.647 I slot print_timing: id 0 | task 21677 | prompt eval time = 153.00 ms / 343 tokens ( 0.45 ms per token, 2241.76 tokens per second) 5.14.720.653 I slot print_timing: id 0 | task 21677 | eval time = 3139.00 ms / 254 tokens ( 12.41 ms per token, 80.60 tokens per second) 5.14.720.654 I slot print_timing: id 0 | task 21677 | total time = 3292.01 ms / 597 tokens 5.14.720.655 I slot print_timing: id 0 | task 21677 | graphs reused = 20909 5.14.720.656 I slot print_timing: id 0 | task 21677 | graph reallocs = 0 / 0 (same size) / (changed size) 5.14.720.683 I slot release: id 0 | task 21677 | stop processing: n_tokens = 628, truncated = 0 5.14.725.444 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 628, t_last = 314618406 5.14.766.074 I slot launch_slot_: id 0 | task 21934 | processing task, is_child = 0 5.17.346.614 I slot print_timing: id 0 | task 21934 | prompt eval time = 167.84 ms / 371 tokens ( 0.45 ms per token, 2210.44 tokens per second) 5.17.346.620 I slot print_timing: id 0 | task 21934 | eval time = 2412.68 ms / 195 tokens ( 12.44 ms per token, 80.41 tokens per second) 5.17.346.621 I slot print_timing: id 0 | task 21934 | total time = 2580.52 ms / 566 tokens 5.17.346.623 I slot print_timing: id 0 | task 21934 | graphs reused = 21101 5.17.346.624 I slot print_timing: id 0 | task 21934 | graph reallocs = 0 / 0 (same size) / (changed size) 5.17.346.654 I slot release: id 0 | task 21934 | stop processing: n_tokens = 597, truncated = 0 5.17.391.668 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 597, t_last = 317244377 5.17.391.723 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.646 MiB) 5.17.441.334 I slot launch_slot_: id 0 | task 22132 | processing task, is_child = 0 5.19.990.801 I slot print_timing: id 0 | task 22132 | prompt eval time = 149.34 ms / 292 tokens ( 0.51 ms per token, 1955.28 tokens per second) 5.19.990.807 I slot print_timing: id 0 | task 22132 | eval time = 2400.11 ms / 190 tokens ( 12.70 ms per token, 78.75 tokens per second) 5.19.990.808 I slot print_timing: id 0 | task 22132 | total time = 2549.45 ms / 482 tokens 5.19.990.809 I slot print_timing: id 0 | task 22132 | graphs reused = 21288 5.19.990.810 I slot print_timing: id 0 | task 22132 | graph reallocs = 0 / 0 (same size) / (changed size) 5.19.990.835 I slot release: id 0 | task 22132 | stop processing: n_tokens = 513, truncated = 0 5.19.995.379 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 513, t_last = 319888558 5.19.995.427 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.243 MiB) 5.20.051.886 I slot launch_slot_: id 0 | task 22325 | processing task, is_child = 0 5.21.522.284 I slot print_timing: id 0 | task 22325 | prompt eval time = 145.55 ms / 301 tokens ( 0.48 ms per token, 2068.03 tokens per second) 5.21.522.290 I slot print_timing: id 0 | task 22325 | eval time = 1324.83 ms / 108 tokens ( 12.38 ms per token, 80.77 tokens per second) 5.21.522.291 I slot print_timing: id 0 | task 22325 | total time = 1470.38 ms / 409 tokens 5.21.522.292 I slot print_timing: id 0 | task 22325 | graphs reused = 21394 5.21.522.293 I slot print_timing: id 0 | task 22325 | graph reallocs = 0 / 0 (same size) / (changed size) 5.21.522.323 I slot release: id 0 | task 22325 | stop processing: n_tokens = 440, truncated = 0 5.21.561.616 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 440, t_last = 321420045 5.21.561.662 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 389.157 MiB) 5.21.607.632 I slot launch_slot_: id 0 | task 22436 | processing task, is_child = 0 5.23.720.228 I slot print_timing: id 0 | task 22436 | prompt eval time = 149.11 ms / 303 tokens ( 0.49 ms per token, 2032.06 tokens per second) 5.23.720.233 I slot print_timing: id 0 | task 22436 | eval time = 1963.47 ms / 155 tokens ( 12.75 ms per token, 78.43 tokens per second) 5.23.720.235 I slot print_timing: id 0 | task 22436 | total time = 2112.58 ms / 458 tokens 5.23.720.236 I slot print_timing: id 0 | task 22436 | graphs reused = 21547 5.23.720.237 I slot print_timing: id 0 | task 22436 | graph reallocs = 0 / 0 (same size) / (changed size) 5.23.720.263 I slot release: id 0 | task 22436 | stop processing: n_tokens = 489, truncated = 0 5.23.724.813 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 489, t_last = 323617986 5.23.724.860 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.562 MiB) 5.23.774.100 I slot launch_slot_: id 0 | task 22594 | processing task, is_child = 0 5.26.552.363 I slot print_timing: id 0 | task 22594 | prompt eval time = 156.36 ms / 321 tokens ( 0.49 ms per token, 2052.99 tokens per second) 5.26.552.369 I slot print_timing: id 0 | task 22594 | eval time = 2621.89 ms / 210 tokens ( 12.54 ms per token, 79.71 tokens per second) 5.26.552.370 I slot print_timing: id 0 | task 22594 | total time = 2778.24 ms / 531 tokens 5.26.552.371 I slot print_timing: id 0 | task 22594 | graphs reused = 21754 5.26.552.371 I slot print_timing: id 0 | task 22594 | graph reallocs = 0 / 0 (same size) / (changed size) 5.26.552.400 I slot release: id 0 | task 22594 | stop processing: n_tokens = 562, truncated = 0 5.26.556.950 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 562, t_last = 326450123 5.26.557.001 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.141 MiB) 5.26.606.708 I slot launch_slot_: id 0 | task 22807 | processing task, is_child = 0 5.27.442.110 I slot print_timing: id 0 | task 22807 | prompt eval time = 156.06 ms / 322 tokens ( 0.48 ms per token, 2063.34 tokens per second) 5.27.442.116 I slot print_timing: id 0 | task 22807 | eval time = 679.32 ms / 54 tokens ( 12.82 ms per token, 78.02 tokens per second) 5.27.442.117 I slot print_timing: id 0 | task 22807 | total time = 835.38 ms / 376 tokens 5.27.442.118 I slot print_timing: id 0 | task 22807 | graphs reused = 21806 5.27.442.118 I slot print_timing: id 0 | task 22807 | graph reallocs = 0 / 0 (same size) / (changed size) 5.27.442.148 I slot release: id 0 | task 22807 | stop processing: n_tokens = 407, truncated = 0 5.27.478.615 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 407, t_last = 327339871 5.27.478.662 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.641 MiB) 5.27.533.070 I slot launch_slot_: id 0 | task 22864 | processing task, is_child = 0 5.29.072.280 I slot print_timing: id 0 | task 22864 | prompt eval time = 158.91 ms / 323 tokens ( 0.49 ms per token, 2032.65 tokens per second) 5.29.072.285 I slot print_timing: id 0 | task 22864 | eval time = 1380.28 ms / 113 tokens ( 12.32 ms per token, 81.14 tokens per second) 5.29.072.286 I slot print_timing: id 0 | task 22864 | total time = 1539.19 ms / 436 tokens 5.29.072.287 I slot print_timing: id 0 | task 22864 | graphs reused = 21917 5.29.072.288 I slot print_timing: id 0 | task 22864 | graph reallocs = 0 / 0 (same size) / (changed size) 5.29.072.319 I slot release: id 0 | task 22864 | stop processing: n_tokens = 467, truncated = 0 5.29.096.606 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 467, t_last = 328970042 5.29.096.652 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.764 MiB) 5.29.150.894 I slot launch_slot_: id 0 | task 22980 | processing task, is_child = 0 5.32.044.347 I slot print_timing: id 0 | task 22980 | prompt eval time = 152.31 ms / 321 tokens ( 0.47 ms per token, 2107.59 tokens per second) 5.32.044.356 I slot print_timing: id 0 | task 22980 | eval time = 2741.12 ms / 217 tokens ( 12.69 ms per token, 78.80 tokens per second) 5.32.044.357 I slot print_timing: id 0 | task 22980 | total time = 2893.43 ms / 538 tokens 5.32.044.357 I slot print_timing: id 0 | task 22980 | graphs reused = 22131 5.32.044.358 I slot print_timing: id 0 | task 22980 | graph reallocs = 0 / 0 (same size) / (changed size) 5.32.044.387 I slot release: id 0 | task 22980 | stop processing: n_tokens = 569, truncated = 0 5.32.073.110 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 569, t_last = 331942109 5.32.073.163 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.858 MiB) 5.32.121.844 I slot launch_slot_: id 0 | task 23200 | processing task, is_child = 0 5.33.394.445 I slot print_timing: id 0 | task 23200 | prompt eval time = 152.69 ms / 322 tokens ( 0.47 ms per token, 2108.79 tokens per second) 5.33.394.451 I slot print_timing: id 0 | task 23200 | eval time = 1119.89 ms / 92 tokens ( 12.31 ms per token, 81.26 tokens per second) 5.33.394.452 I slot print_timing: id 0 | task 23200 | total time = 1272.58 ms / 414 tokens 5.33.394.453 I slot print_timing: id 0 | task 23200 | graphs reused = 22221 5.33.394.454 I slot print_timing: id 0 | task 23200 | graph reallocs = 0 / 0 (same size) / (changed size) 5.33.394.483 I slot release: id 0 | task 23200 | stop processing: n_tokens = 445, truncated = 0 5.33.411.258 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 445, t_last = 333292206 5.33.411.303 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.171 MiB) 5.33.461.237 I slot launch_slot_: id 0 | task 23295 | processing task, is_child = 0 5.34.358.521 I slot print_timing: id 0 | task 23295 | prompt eval time = 157.15 ms / 337 tokens ( 0.47 ms per token, 2144.39 tokens per second) 5.34.358.527 I slot print_timing: id 0 | task 23295 | eval time = 740.11 ms / 59 tokens ( 12.76 ms per token, 78.37 tokens per second) 5.34.358.528 I slot print_timing: id 0 | task 23295 | total time = 897.26 ms / 396 tokens 5.34.358.529 I slot print_timing: id 0 | task 23295 | graphs reused = 22278 5.34.358.530 I slot print_timing: id 0 | task 23295 | graph reallocs = 0 / 0 (same size) / (changed size) 5.34.358.562 I slot release: id 0 | task 23295 | stop processing: n_tokens = 427, truncated = 0 5.34.380.773 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 427, t_last = 334256285 5.34.380.820 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 313.669 MiB) 5.34.427.866 I slot launch_slot_: id 0 | task 23357 | processing task, is_child = 0 5.35.418.279 I slot print_timing: id 0 | task 23357 | prompt eval time = 156.80 ms / 325 tokens ( 0.48 ms per token, 2072.66 tokens per second) 5.35.418.285 I slot print_timing: id 0 | task 23357 | eval time = 833.59 ms / 66 tokens ( 12.82 ms per token, 77.98 tokens per second) 5.35.418.286 I slot print_timing: id 0 | task 23357 | total time = 990.39 ms / 391 tokens 5.35.418.287 I slot print_timing: id 0 | task 23357 | graphs reused = 22342 5.35.418.288 I slot print_timing: id 0 | task 23357 | graph reallocs = 0 / 0 (same size) / (changed size) 5.35.418.316 I slot release: id 0 | task 23357 | stop processing: n_tokens = 422, truncated = 0 5.35.455.609 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 422, t_last = 335316039 5.35.455.656 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 324.489 MiB) 5.35.503.516 I slot launch_slot_: id 0 | task 23426 | processing task, is_child = 0 5.37.856.984 I slot print_timing: id 0 | task 23426 | prompt eval time = 157.03 ms / 331 tokens ( 0.47 ms per token, 2107.82 tokens per second) 5.37.856.990 I slot print_timing: id 0 | task 23426 | eval time = 2196.42 ms / 177 tokens ( 12.48 ms per token, 80.13 tokens per second) 5.37.856.991 I slot print_timing: id 0 | task 23426 | total time = 2353.45 ms / 508 tokens 5.37.856.991 I slot print_timing: id 0 | task 23426 | graphs reused = 22516 5.37.856.992 I slot print_timing: id 0 | task 23426 | graph reallocs = 0 / 0 (same size) / (changed size) 5.37.857.021 I slot release: id 0 | task 23426 | stop processing: n_tokens = 539, truncated = 0 5.37.890.066 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 539, t_last = 337754744 5.37.890.111 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.265 MiB) 5.37.934.956 I slot launch_slot_: id 0 | task 23606 | processing task, is_child = 0 5.40.090.961 I slot print_timing: id 0 | task 23606 | prompt eval time = 156.12 ms / 336 tokens ( 0.46 ms per token, 2152.26 tokens per second) 5.40.090.967 I slot print_timing: id 0 | task 23606 | eval time = 1999.87 ms / 158 tokens ( 12.74 ms per token, 78.50 tokens per second) 5.40.090.969 I slot print_timing: id 0 | task 23606 | total time = 2155.99 ms / 494 tokens 5.40.090.969 I slot print_timing: id 0 | task 23606 | graphs reused = 22671 5.40.090.970 I slot print_timing: id 0 | task 23606 | graph reallocs = 0 / 0 (same size) / (changed size) 5.40.091.000 I slot release: id 0 | task 23606 | stop processing: n_tokens = 525, truncated = 0 5.40.124.948 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 525, t_last = 339988722 5.40.124.999 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 313.294 MiB) 5.40.170.394 I slot launch_slot_: id 0 | task 23767 | processing task, is_child = 0 5.40.917.487 I slot print_timing: id 0 | task 23767 | prompt eval time = 154.33 ms / 349 tokens ( 0.44 ms per token, 2261.45 tokens per second) 5.40.917.493 I slot print_timing: id 0 | task 23767 | eval time = 592.75 ms / 48 tokens ( 12.61 ms per token, 79.29 tokens per second) 5.40.917.494 I slot print_timing: id 0 | task 23767 | total time = 747.07 ms / 397 tokens 5.40.917.494 I slot print_timing: id 0 | task 23767 | graphs reused = 22717 5.40.917.496 I slot print_timing: id 0 | task 23767 | graph reallocs = 0 / 0 (same size) / (changed size) 5.40.917.528 I slot release: id 0 | task 23767 | stop processing: n_tokens = 428, truncated = 0 5.40.935.219 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 428, t_last = 340815250 5.40.935.258 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.577 MiB) 5.40.980.840 I slot launch_slot_: id 0 | task 23818 | processing task, is_child = 0 5.44.139.355 I slot print_timing: id 0 | task 23818 | n_gen = 237, tg = 78.52 t/s, tg_3s = 78.85 t/s 5.46.820.633 I slot print_timing: id 0 | task 23818 | prompt eval time = 152.93 ms / 336 tokens ( 0.46 ms per token, 2197.08 tokens per second) 5.46.820.639 I slot print_timing: id 0 | task 23818 | eval time = 5686.84 ms / 451 tokens ( 12.64 ms per token, 79.13 tokens per second) 5.46.820.640 I slot print_timing: id 0 | task 23818 | total time = 5839.77 ms / 787 tokens 5.46.820.641 I slot print_timing: id 0 | task 23818 | graphs reused = 23164 5.46.820.642 I slot print_timing: id 0 | task 23818 | graph reallocs = 0 / 0 (same size) / (changed size) 5.46.820.673 I slot release: id 0 | task 23818 | stop processing: n_tokens = 818, truncated = 0 5.46.835.172 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 818, t_last = 346718395 5.46.835.238 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.547 MiB) 5.46.886.474 I slot launch_slot_: id 0 | task 24272 | processing task, is_child = 0 5.50.048.668 I slot print_timing: id 0 | task 24272 | n_gen = 242, tg = 80.18 t/s, tg_3s = 80.51 t/s 5.50.300.833 I slot print_timing: id 0 | task 24272 | prompt eval time = 156.47 ms / 349 tokens ( 0.45 ms per token, 2230.46 tokens per second) 5.50.300.838 I slot print_timing: id 0 | task 24272 | eval time = 3257.87 ms / 262 tokens ( 12.48 ms per token, 80.11 tokens per second) 5.50.300.839 I slot print_timing: id 0 | task 24272 | total time = 3414.34 ms / 611 tokens 5.50.300.840 I slot print_timing: id 0 | task 24272 | graphs reused = 23423 5.50.300.841 I slot print_timing: id 0 | task 24272 | graph reallocs = 0 / 0 (same size) / (changed size) 5.50.300.872 I slot release: id 0 | task 24272 | stop processing: n_tokens = 642, truncated = 0 5.50.305.486 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 642, t_last = 350198594 5.50.305.541 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.734 MiB) 5.50.358.914 I slot launch_slot_: id 0 | task 24537 | processing task, is_child = 0 5.51.422.431 I slot print_timing: id 0 | task 24537 | prompt eval time = 157.39 ms / 349 tokens ( 0.45 ms per token, 2217.42 tokens per second) 5.51.422.437 I slot print_timing: id 0 | task 24537 | eval time = 906.11 ms / 72 tokens ( 12.76 ms per token, 78.36 tokens per second) 5.51.422.438 I slot print_timing: id 0 | task 24537 | total time = 1063.49 ms / 421 tokens 5.51.422.440 I slot print_timing: id 0 | task 24537 | graphs reused = 23493 5.51.422.440 I slot print_timing: id 0 | task 24537 | graph reallocs = 0 / 0 (same size) / (changed size) 5.51.422.470 I slot release: id 0 | task 24537 | stop processing: n_tokens = 452, truncated = 0 5.51.451.799 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 452, t_last = 351320192 5.51.451.847 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.983 MiB) 5.51.499.471 I slot launch_slot_: id 0 | task 24612 | processing task, is_child = 0 5.53.912.510 I slot print_timing: id 0 | task 24612 | prompt eval time = 167.34 ms / 385 tokens ( 0.43 ms per token, 2300.69 tokens per second) 5.53.912.515 I slot print_timing: id 0 | task 24612 | eval time = 2245.68 ms / 182 tokens ( 12.41 ms per token, 80.60 tokens per second) 5.53.912.516 I slot print_timing: id 0 | task 24612 | total time = 2413.02 ms / 567 tokens 5.53.912.517 I slot print_timing: id 0 | task 24612 | graphs reused = 23672 5.53.912.518 I slot print_timing: id 0 | task 24612 | graph reallocs = 0 / 0 (same size) / (changed size) 5.53.912.547 I slot release: id 0 | task 24612 | stop processing: n_tokens = 598, truncated = 0 5.53.936.230 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 598, t_last = 353810269 5.53.936.282 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.077 MiB) 5.53.987.082 I slot launch_slot_: id 0 | task 24797 | processing task, is_child = 0 5.55.051.023 I slot print_timing: id 0 | task 24797 | prompt eval time = 157.19 ms / 328 tokens ( 0.48 ms per token, 2086.66 tokens per second) 5.55.051.029 I slot print_timing: id 0 | task 24797 | eval time = 906.73 ms / 72 tokens ( 12.77 ms per token, 78.30 tokens per second) 5.55.051.030 I slot print_timing: id 0 | task 24797 | total time = 1063.92 ms / 400 tokens 5.55.051.031 I slot print_timing: id 0 | task 24797 | graphs reused = 23742 5.55.051.032 I slot print_timing: id 0 | task 24797 | graph reallocs = 0 / 0 (same size) / (changed size) 5.55.051.059 I slot release: id 0 | task 24797 | stop processing: n_tokens = 431, truncated = 0