$ /Users/minipro/quantdiff/llama.cpp/llama-b11770/llama-server -m /Users/minipro/quantdiff/models/campaign/8c2a45ff85e7/Qwen3.8-27B-UD-Q3_K_XL.gguf --host 127.0.0.1 --port 8089 -c 4096 -np 1 -ngl 999 -fa on --jinja --seed 1234 --no-webui -a quant 0.00.044.646 I srv llama_server: initializing ... 0.00.044.652 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.044.740 I srv init_listene: The UI is disabled 0.00.044.741 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.044.776 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) 0.00.046.463 I srv load_model: loading model '/Users/minipro/quantdiff/models/campaign/8c2a45ff85e7/Qwen3.8-27B-UD-Q3_K_XL.gguf' 0.00.558.323 W model has unused tensor blk.64.attn_norm.weight (size = 20480 bytes) -- ignoring 0.00.558.335 W model has unused tensor blk.64.post_attention_norm.weight (size = 20480 bytes) -- ignoring 0.00.558.342 W model has unused tensor blk.64.attn_q.weight (size = 51609600 bytes) -- ignoring 0.00.558.345 W model has unused tensor blk.64.attn_k.weight (size = 5570560 bytes) -- ignoring 0.00.558.347 W model has unused tensor blk.64.attn_v.weight (size = 5570560 bytes) -- ignoring 0.00.558.355 W model has unused tensor blk.64.attn_output.weight (size = 25804800 bytes) -- ignoring 0.00.558.357 W model has unused tensor blk.64.attn_q_norm.weight (size = 1024 bytes) -- ignoring 0.00.558.359 W model has unused tensor blk.64.attn_k_norm.weight (size = 1024 bytes) -- ignoring 0.00.558.361 W model has unused tensor blk.64.ffn_gate.weight (size = 73113600 bytes) -- ignoring 0.00.558.363 W model has unused tensor blk.64.ffn_down.weight (size = 73113600 bytes) -- ignoring 0.00.558.365 W model has unused tensor blk.64.ffn_up.weight (size = 73113600 bytes) -- ignoring 0.00.558.369 W model has unused tensor blk.64.nextn.eh_proj.weight (size = 43008000 bytes) -- ignoring 0.00.558.371 W model has unused tensor blk.64.nextn.enorm.weight (size = 20480 bytes) -- ignoring 0.00.558.373 W model has unused tensor blk.64.nextn.hnorm.weight (size = 20480 bytes) -- ignoring 0.00.558.380 W model has unused tensor blk.64.nextn.shared_head_norm.weight (size = 20480 bytes) -- ignoring 0.01.157.151 I cmn init: llama threadpool init, n_threads = 8 0.01.741.343 I srv load_model: initializing, n_slots = 1, n_ctx_slot = 4096, kv_unified = 'false' 0.01.745.213 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.01.745.233 I srv llama_server: model loaded 0.01.745.236 I srv llama_server: listening on http://127.0.0.1:8089 0.02.026.177 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.02.026.397 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.06.063.551 I slot print_timing: id 0 | task 0 | prompt processing, n_tokens = 364, progress = 0.99, t = 4.04 s / 90.16 tokens per second 0.10.739.915 I slot print_timing: id 0 | task 0 | prompt eval time = 4685.24 ms / 368 tokens ( 12.73 ms per token, 78.54 tokens per second) 0.10.739.944 I slot print_timing: id 0 | task 0 | eval time = 4028.24 ms / 41 tokens ( 100.71 ms per token, 9.93 tokens per second) 0.10.739.947 I slot print_timing: id 0 | task 0 | total time = 8713.48 ms / 409 tokens 0.10.739.949 I slot print_timing: id 0 | task 0 | graphs reused = 40 0.10.739.951 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.10.740.098 I slot release: id 0 | task 0 | stop processing: n_tokens = 408, truncated = 0 0.10.753.499 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 408, t_last = 83228839736 0.10.808.789 I slot launch_slot_: id 0 | task 44 | processing task, is_child = 0 0.14.408.193 I slot print_timing: id 0 | task 44 | prompt processing, n_tokens = 318, progress = 0.99, t = 3.60 s / 88.35 tokens per second 0.19.296.028 I slot print_timing: id 0 | task 44 | prompt eval time = 4201.36 ms / 322 tokens ( 13.05 ms per token, 76.64 tokens per second) 0.19.296.055 I slot print_timing: id 0 | task 44 | eval time = 4285.84 ms / 42 tokens ( 104.53 ms per token, 9.57 tokens per second) 0.19.296.061 I slot print_timing: id 0 | task 44 | total time = 8487.20 ms / 364 tokens 0.19.296.065 I slot print_timing: id 0 | task 44 | graphs reused = 80 0.19.296.073 I slot print_timing: id 0 | task 44 | graph reallocs = 0 / 0 (same size) / (changed size) 0.19.296.236 I slot release: id 0 | task 44 | stop processing: n_tokens = 363, truncated = 0 0.19.308.520 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 363, t_last = 83237395873 0.19.364.207 I slot launch_slot_: id 0 | task 89 | processing task, is_child = 0 0.23.339.871 I slot print_timing: id 0 | task 89 | prompt processing, n_tokens = 361, progress = 0.99, t = 3.98 s / 90.80 tokens per second 0.28.096.293 I slot print_timing: id 0 | task 89 | prompt eval time = 4581.31 ms / 365 tokens ( 12.55 ms per token, 79.67 tokens per second) 0.28.096.306 I slot print_timing: id 0 | task 89 | eval time = 4150.75 ms / 42 tokens ( 101.24 ms per token, 9.88 tokens per second) 0.28.096.309 I slot print_timing: id 0 | task 89 | total time = 8732.06 ms / 407 tokens 0.28.096.311 I slot print_timing: id 0 | task 89 | graphs reused = 120 0.28.096.313 I slot print_timing: id 0 | task 89 | graph reallocs = 0 / 0 (same size) / (changed size) 0.28.096.433 I slot release: id 0 | task 89 | stop processing: n_tokens = 406, truncated = 0 0.28.108.212 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 406, t_last = 83246196070 0.28.168.003 I slot launch_slot_: id 0 | task 134 | processing task, is_child = 0 0.32.465.691 I slot print_timing: id 0 | task 134 | prompt processing, n_tokens = 393, progress = 0.99, t = 4.30 s / 91.44 tokens per second 0.37.189.096 I slot print_timing: id 0 | task 134 | prompt eval time = 4904.55 ms / 397 tokens ( 12.35 ms per token, 80.95 tokens per second) 0.37.189.098 I slot print_timing: id 0 | task 134 | eval time = 4116.52 ms / 43 tokens ( 98.01 ms per token, 10.20 tokens per second) 0.37.189.098 I slot print_timing: id 0 | task 134 | total time = 9021.08 ms / 440 tokens 0.37.189.099 I slot print_timing: id 0 | task 134 | graphs reused = 161 0.37.189.099 I slot print_timing: id 0 | task 134 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.189.124 I slot release: id 0 | task 134 | stop processing: n_tokens = 439, truncated = 0 0.37.193.571 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.117 (> 0.100 thold), f_keep = 0.103 0.37.230.335 I slot launch_slot_: id 0 | task 180 | processing task, is_child = 0 0.41.204.796 I slot print_timing: id 0 | task 180 | prompt processing, n_tokens = 379, progress = 0.99, t = 3.97 s / 95.36 tokens per second 0.47.771.144 I slot print_timing: id 0 | task 180 | prompt eval time = 4914.94 ms / 383 tokens ( 12.83 ms per token, 77.93 tokens per second) 0.47.771.166 I slot print_timing: id 0 | task 180 | eval time = 5625.84 ms / 55 tokens ( 104.18 ms per token, 9.60 tokens per second) 0.47.771.168 I slot print_timing: id 0 | task 180 | total time = 10540.78 ms / 438 tokens 0.47.771.171 I slot print_timing: id 0 | task 180 | graphs reused = 214 0.47.771.173 I slot print_timing: id 0 | task 180 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.771.267 I slot release: id 0 | task 180 | stop processing: n_tokens = 437, truncated = 0 0.47.783.029 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 83265870904 0.47.839.310 I slot launch_slot_: id 0 | task 238 | processing task, is_child = 0 0.51.825.194 I slot print_timing: id 0 | task 238 | prompt processing, n_tokens = 368, progress = 0.99, t = 3.99 s / 92.33 tokens per second 0.57.891.607 I slot print_timing: id 0 | task 238 | prompt eval time = 4588.94 ms / 372 tokens ( 12.34 ms per token, 81.06 tokens per second) 0.57.891.620 I slot print_timing: id 0 | task 238 | eval time = 5463.32 ms / 55 tokens ( 101.17 ms per token, 9.88 tokens per second) 0.57.891.623 I slot print_timing: id 0 | task 238 | total time = 10052.26 ms / 427 tokens 0.57.891.625 I slot print_timing: id 0 | task 238 | graphs reused = 267 0.57.891.627 I slot print_timing: id 0 | task 238 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.891.714 I slot release: id 0 | task 238 | stop processing: n_tokens = 426, truncated = 0 0.57.903.894 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 83275991352 0.57.959.646 I slot launch_slot_: id 0 | task 296 | processing task, is_child = 0 1.02.623.881 I slot print_timing: id 0 | task 296 | prompt processing, n_tokens = 418, progress = 0.99, t = 4.66 s / 89.62 tokens per second 1.08.903.874 I slot print_timing: id 0 | task 296 | prompt eval time = 5271.93 ms / 422 tokens ( 12.49 ms per token, 80.05 tokens per second) 1.08.903.888 I slot print_timing: id 0 | task 296 | eval time = 5672.27 ms / 55 tokens ( 105.04 ms per token, 9.52 tokens per second) 1.08.903.891 I slot print_timing: id 0 | task 296 | total time = 10944.20 ms / 477 tokens 1.08.903.893 I slot print_timing: id 0 | task 296 | graphs reused = 320 1.08.903.895 I slot print_timing: id 0 | task 296 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.904.038 I slot release: id 0 | task 296 | stop processing: n_tokens = 476, truncated = 0 1.08.916.535 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 476, t_last = 83287003676 1.08.974.599 I slot launch_slot_: id 0 | task 354 | processing task, is_child = 0 1.13.997.125 I slot print_timing: id 0 | task 354 | prompt processing, n_tokens = 466, progress = 0.99, t = 5.02 s / 92.78 tokens per second 1.22.047.798 I slot print_timing: id 0 | task 354 | prompt eval time = 5961.32 ms / 470 tokens ( 12.68 ms per token, 78.84 tokens per second) 1.22.047.811 I slot print_timing: id 0 | task 354 | eval time = 7111.85 ms / 72 tokens ( 100.17 ms per token, 9.98 tokens per second) 1.22.047.814 I slot print_timing: id 0 | task 354 | total time = 13073.17 ms / 542 tokens 1.22.047.816 I slot print_timing: id 0 | task 354 | graphs reused = 389 1.22.047.818 I slot print_timing: id 0 | task 354 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.047.914 I slot release: id 0 | task 354 | stop processing: n_tokens = 541, truncated = 0 1.22.059.856 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 541, t_last = 83300147552 1.22.120.066 I slot launch_slot_: id 0 | task 429 | processing task, is_child = 0 1.25.736.859 I slot print_timing: id 0 | task 429 | prompt processing, n_tokens = 341, progress = 0.99, t = 3.62 s / 94.28 tokens per second 1.30.854.109 I slot print_timing: id 0 | task 429 | prompt eval time = 4223.88 ms / 345 tokens ( 12.24 ms per token, 81.68 tokens per second) 1.30.854.121 I slot print_timing: id 0 | task 429 | eval time = 4510.12 ms / 47 tokens ( 98.05 ms per token, 10.20 tokens per second) 1.30.854.124 I slot print_timing: id 0 | task 429 | total time = 8734.00 ms / 392 tokens 1.30.854.126 I slot print_timing: id 0 | task 429 | graphs reused = 434 1.30.854.128 I slot print_timing: id 0 | task 429 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.854.251 I slot release: id 0 | task 429 | stop processing: n_tokens = 391, truncated = 0 1.30.863.380 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 391, t_last = 83308953888 1.30.921.425 I slot launch_slot_: id 0 | task 479 | processing task, is_child = 0 1.34.892.583 I slot print_timing: id 0 | task 479 | prompt processing, n_tokens = 360, progress = 0.99, t = 3.97 s / 90.65 tokens per second 1.39.978.688 I slot print_timing: id 0 | task 479 | prompt eval time = 4901.13 ms / 364 tokens ( 13.46 ms per token, 74.27 tokens per second) 1.39.978.702 I slot print_timing: id 0 | task 479 | eval time = 4156.10 ms / 41 tokens ( 103.90 ms per token, 9.62 tokens per second) 1.39.978.705 I slot print_timing: id 0 | task 479 | total time = 9057.23 ms / 405 tokens 1.39.978.708 I slot print_timing: id 0 | task 479 | graphs reused = 473 1.39.978.710 I slot print_timing: id 0 | task 479 | graph reallocs = 0 / 0 (same size) / (changed size) 1.39.978.826 I slot release: id 0 | task 479 | stop processing: n_tokens = 404, truncated = 0 1.39.990.900 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 404, t_last = 83318078463 1.40.051.114 I slot launch_slot_: id 0 | task 523 | processing task, is_child = 0 1.43.984.269 I slot print_timing: id 0 | task 523 | prompt processing, n_tokens = 372, progress = 0.99, t = 3.93 s / 94.58 tokens per second 1.50.577.837 I slot print_timing: id 0 | task 523 | prompt eval time = 4535.15 ms / 376 tokens ( 12.06 ms per token, 82.91 tokens per second) 1.50.577.842 I slot print_timing: id 0 | task 523 | eval time = 5991.56 ms / 62 tokens ( 98.22 ms per token, 10.18 tokens per second) 1.50.577.843 I slot print_timing: id 0 | task 523 | total time = 10526.71 ms / 438 tokens 1.50.577.843 I slot print_timing: id 0 | task 523 | graphs reused = 533 1.50.577.844 I slot print_timing: id 0 | task 523 | graph reallocs = 0 / 0 (same size) / (changed size) 1.50.577.874 I slot release: id 0 | task 523 | stop processing: n_tokens = 437, truncated = 0 1.50.581.956 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 83328677511 1.50.618.442 I slot launch_slot_: id 0 | task 588 | processing task, is_child = 0 1.54.927.633 I slot print_timing: id 0 | task 588 | prompt processing, n_tokens = 408, progress = 0.99, t = 4.31 s / 94.68 tokens per second 2.00.044.638 I slot print_timing: id 0 | task 588 | prompt eval time = 4915.85 ms / 412 tokens ( 11.93 ms per token, 83.81 tokens per second) 2.00.044.647 I slot print_timing: id 0 | task 588 | eval time = 4510.34 ms / 47 tokens ( 98.05 ms per token, 10.20 tokens per second) 2.00.044.647 I slot print_timing: id 0 | task 588 | total time = 9426.19 ms / 459 tokens 2.00.044.647 I slot print_timing: id 0 | task 588 | graphs reused = 578 2.00.044.648 I slot print_timing: id 0 | task 588 | graph reallocs = 0 / 0 (same size) / (changed size) 2.00.044.677 I slot release: id 0 | task 588 | stop processing: n_tokens = 458, truncated = 0 2.00.048.598 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 83338144314 2.00.085.772 I slot launch_slot_: id 0 | task 638 | processing task, is_child = 0 2.04.054.641 I slot print_timing: id 0 | task 638 | prompt processing, n_tokens = 372, progress = 0.99, t = 3.97 s / 93.73 tokens per second 2.11.391.467 I slot print_timing: id 0 | task 638 | prompt eval time = 4906.43 ms / 376 tokens ( 13.05 ms per token, 76.63 tokens per second) 2.11.391.479 I slot print_timing: id 0 | task 638 | eval time = 6399.22 ms / 62 tokens ( 104.91 ms per token, 9.53 tokens per second) 2.11.391.482 I slot print_timing: id 0 | task 638 | total time = 11305.66 ms / 438 tokens 2.11.391.484 I slot print_timing: id 0 | task 638 | graphs reused = 638 2.11.391.486 I slot print_timing: id 0 | task 638 | graph reallocs = 0 / 0 (same size) / (changed size) 2.11.391.591 I slot release: id 0 | task 638 | stop processing: n_tokens = 437, truncated = 0 2.11.403.295 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 83349491229 2.11.462.077 I slot launch_slot_: id 0 | task 703 | processing task, is_child = 0 2.15.448.776 I slot print_timing: id 0 | task 703 | prompt processing, n_tokens = 374, progress = 0.99, t = 3.99 s / 93.81 tokens per second 2.21.358.506 I slot print_timing: id 0 | task 703 | prompt eval time = 4589.16 ms / 378 tokens ( 12.14 ms per token, 82.37 tokens per second) 2.21.358.526 I slot print_timing: id 0 | task 703 | eval time = 5307.23 ms / 52 tokens ( 104.06 ms per token, 9.61 tokens per second) 2.21.358.529 I slot print_timing: id 0 | task 703 | total time = 9896.40 ms / 430 tokens 2.21.358.531 I slot print_timing: id 0 | task 703 | graphs reused = 688 2.21.358.533 I slot print_timing: id 0 | task 703 | graph reallocs = 0 / 0 (same size) / (changed size) 2.21.358.637 I slot release: id 0 | task 703 | stop processing: n_tokens = 429, truncated = 0 2.21.369.895 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 429, t_last = 83359458274 2.21.430.991 I slot launch_slot_: id 0 | task 758 | processing task, is_child = 0 2.25.408.288 I slot print_timing: id 0 | task 758 | prompt processing, n_tokens = 363, progress = 0.99, t = 3.98 s / 91.27 tokens per second 2.31.610.196 I slot print_timing: id 0 | task 758 | prompt eval time = 4580.19 ms / 367 tokens ( 12.48 ms per token, 80.13 tokens per second) 2.31.610.201 I slot print_timing: id 0 | task 758 | eval time = 5599.00 ms / 58 tokens ( 98.23 ms per token, 10.18 tokens per second) 2.31.610.202 I slot print_timing: id 0 | task 758 | total time = 10179.19 ms / 425 tokens 2.31.610.202 I slot print_timing: id 0 | task 758 | graphs reused = 744 2.31.610.203 I slot print_timing: id 0 | task 758 | graph reallocs = 0 / 0 (same size) / (changed size) 2.31.610.228 I slot release: id 0 | task 758 | stop processing: n_tokens = 424, truncated = 0 2.31.614.214 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 83369709865 2.31.653.016 I slot launch_slot_: id 0 | task 819 | processing task, is_child = 0 2.35.270.827 I slot print_timing: id 0 | task 819 | prompt processing, n_tokens = 343, progress = 0.99, t = 3.62 s / 94.81 tokens per second 2.40.781.028 I slot print_timing: id 0 | task 819 | prompt eval time = 4224.61 ms / 347 tokens ( 12.17 ms per token, 82.14 tokens per second) 2.40.781.031 I slot print_timing: id 0 | task 819 | eval time = 4903.39 ms / 51 tokens ( 98.07 ms per token, 10.20 tokens per second) 2.40.781.032 I slot print_timing: id 0 | task 819 | total time = 9128.00 ms / 398 tokens 2.40.781.032 I slot print_timing: id 0 | task 819 | graphs reused = 793 2.40.781.033 I slot print_timing: id 0 | task 819 | graph reallocs = 0 / 0 (same size) / (changed size) 2.40.781.059 I slot release: id 0 | task 819 | stop processing: n_tokens = 397, truncated = 0 2.40.785.368 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 397, t_last = 83378880696 2.40.822.772 I slot launch_slot_: id 0 | task 873 | processing task, is_child = 0 2.44.796.602 I slot print_timing: id 0 | task 873 | prompt processing, n_tokens = 365, progress = 0.99, t = 3.97 s / 91.85 tokens per second 2.49.583.905 I slot print_timing: id 0 | task 873 | prompt eval time = 4579.52 ms / 369 tokens ( 12.41 ms per token, 80.58 tokens per second) 2.49.583.915 I slot print_timing: id 0 | task 873 | eval time = 4181.58 ms / 41 tokens ( 104.54 ms per token, 9.57 tokens per second) 2.49.583.918 I slot print_timing: id 0 | task 873 | total time = 8761.10 ms / 410 tokens 2.49.583.921 I slot print_timing: id 0 | task 873 | graphs reused = 832 2.49.583.923 I slot print_timing: id 0 | task 873 | graph reallocs = 0 / 0 (same size) / (changed size) 2.49.584.038 I slot release: id 0 | task 873 | stop processing: n_tokens = 409, truncated = 0 2.49.595.599 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 83387683675 2.49.664.331 I slot launch_slot_: id 0 | task 917 | processing task, is_child = 0 2.53.627.110 I slot print_timing: id 0 | task 917 | prompt processing, n_tokens = 348, progress = 0.99, t = 3.96 s / 87.82 tokens per second 2.58.326.304 I slot print_timing: id 0 | task 917 | prompt eval time = 4565.72 ms / 352 tokens ( 12.97 ms per token, 77.10 tokens per second) 2.58.326.318 I slot print_timing: id 0 | task 917 | eval time = 4096.21 ms / 41 tokens ( 102.41 ms per token, 9.77 tokens per second) 2.58.326.321 I slot print_timing: id 0 | task 917 | total time = 8661.93 ms / 393 tokens 2.58.326.323 I slot print_timing: id 0 | task 917 | graphs reused = 871 2.58.326.325 I slot print_timing: id 0 | task 917 | graph reallocs = 0 / 0 (same size) / (changed size) 2.58.326.424 I slot release: id 0 | task 917 | stop processing: n_tokens = 392, truncated = 0 2.58.339.110 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 392, t_last = 83396426061 2.58.339.198 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 474.388 MiB) 2.58.360.513 I slot launch_slot_: id 0 | task 961 | processing task, is_child = 0 3.02.340.795 I slot print_timing: id 0 | task 961 | prompt processing, n_tokens = 345, progress = 0.99, t = 3.98 s / 86.68 tokens per second 3.06.776.184 I slot print_timing: id 0 | task 961 | prompt eval time = 4593.49 ms / 349 tokens ( 13.16 ms per token, 75.98 tokens per second) 3.06.776.189 I slot print_timing: id 0 | task 961 | eval time = 3822.17 ms / 40 tokens ( 98.00 ms per token, 10.20 tokens per second) 3.06.776.190 I slot print_timing: id 0 | task 961 | total time = 8415.66 ms / 389 tokens 3.06.776.190 I slot print_timing: id 0 | task 961 | graphs reused = 909 3.06.776.190 I slot print_timing: id 0 | task 961 | graph reallocs = 0 / 0 (same size) / (changed size) 3.06.776.215 I slot release: id 0 | task 961 | stop processing: n_tokens = 388, truncated = 0 3.06.780.319 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 388, t_last = 83404875852 3.06.780.346 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 471.575 MiB) 3.06.820.204 I slot launch_slot_: id 0 | task 1004 | processing task, is_child = 0 3.10.803.230 I slot print_timing: id 0 | task 1004 | prompt processing, n_tokens = 380, progress = 0.99, t = 3.98 s / 95.41 tokens per second 3.17.827.413 I slot print_timing: id 0 | task 1004 | prompt eval time = 4919.31 ms / 384 tokens ( 12.81 ms per token, 78.06 tokens per second) 3.17.827.416 I slot print_timing: id 0 | task 1004 | eval time = 6087.88 ms / 63 tokens ( 98.19 ms per token, 10.18 tokens per second) 3.17.827.416 I slot print_timing: id 0 | task 1004 | total time = 11007.19 ms / 447 tokens 3.17.827.416 I slot print_timing: id 0 | task 1004 | graphs reused = 970 3.17.827.417 I slot print_timing: id 0 | task 1004 | graph reallocs = 0 / 0 (same size) / (changed size) 3.17.827.443 I slot release: id 0 | task 1004 | stop processing: n_tokens = 446, truncated = 0 3.17.834.011 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 446, t_last = 83415927080 3.17.834.050 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 474.263 MiB) 3.17.875.450 I slot launch_slot_: id 0 | task 1070 | processing task, is_child = 0 3.21.452.072 I slot print_timing: id 0 | task 1070 | prompt processing, n_tokens = 352, progress = 0.99, t = 3.58 s / 98.42 tokens per second 3.27.611.985 I slot print_timing: id 0 | task 1070 | prompt eval time = 4180.52 ms / 356 tokens ( 11.74 ms per token, 85.16 tokens per second) 3.27.612.000 I slot print_timing: id 0 | task 1070 | eval time = 5555.96 ms / 54 tokens ( 104.83 ms per token, 9.54 tokens per second) 3.27.612.003 I slot print_timing: id 0 | task 1070 | total time = 9736.48 ms / 410 tokens 3.27.612.006 I slot print_timing: id 0 | task 1070 | graphs reused = 1022 3.27.612.008 I slot print_timing: id 0 | task 1070 | graph reallocs = 0 / 0 (same size) / (changed size) 3.27.612.120 I slot release: id 0 | task 1070 | stop processing: n_tokens = 409, truncated = 0 3.27.633.426 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 83425711757 3.27.633.502 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 476.326 MiB) 3.27.652.110 I slot launch_slot_: id 0 | task 1127 | processing task, is_child = 0 3.31.955.505 I slot print_timing: id 0 | task 1127 | prompt processing, n_tokens = 406, progress = 0.99, t = 4.30 s / 94.34 tokens per second 3.39.737.142 I slot print_timing: id 0 | task 1127 | prompt eval time = 5235.79 ms / 410 tokens ( 12.77 ms per token, 78.31 tokens per second) 3.39.737.164 I slot print_timing: id 0 | task 1127 | eval time = 6849.21 ms / 70 tokens ( 99.26 ms per token, 10.07 tokens per second) 3.39.737.171 I slot print_timing: id 0 | task 1127 | total time = 12085.01 ms / 480 tokens 3.39.737.173 I slot print_timing: id 0 | task 1127 | graphs reused = 1090 3.39.737.176 I slot print_timing: id 0 | task 1127 | graph reallocs = 0 / 0 (same size) / (changed size) 3.39.737.291 I slot release: id 0 | task 1127 | stop processing: n_tokens = 479, truncated = 0 3.39.749.153 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 479, t_last = 83437836929 3.39.749.224 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 476.201 MiB) 3.39.827.027 I slot launch_slot_: id 0 | task 1200 | processing task, is_child = 0 3.44.126.844 I slot print_timing: id 0 | task 1200 | prompt processing, n_tokens = 381, progress = 0.99, t = 4.30 s / 88.61 tokens per second 3.51.316.691 I slot print_timing: id 0 | task 1200 | prompt eval time = 4904.44 ms / 385 tokens ( 12.74 ms per token, 78.50 tokens per second) 3.51.316.705 I slot print_timing: id 0 | task 1200 | eval time = 6585.19 ms / 66 tokens ( 101.31 ms per token, 9.87 tokens per second) 3.51.316.707 I slot print_timing: id 0 | task 1200 | total time = 11489.63 ms / 451 tokens 3.51.316.710 I slot print_timing: id 0 | task 1200 | graphs reused = 1154 3.51.316.712 I slot print_timing: id 0 | task 1200 | graph reallocs = 0 / 0 (same size) / (changed size) 3.51.316.845 I slot release: id 0 | task 1200 | stop processing: n_tokens = 450, truncated = 0 3.51.329.608 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 450, t_last = 83449416483 3.51.329.676 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 475.514 MiB) 3.51.406.410 I slot launch_slot_: id 0 | task 1269 | processing task, is_child = 0 3.55.405.626 I slot print_timing: id 0 | task 1269 | prompt processing, n_tokens = 391, progress = 0.99, t = 4.00 s / 97.77 tokens per second 4.03.403.307 I slot print_timing: id 0 | task 1269 | prompt eval time = 4939.62 ms / 395 tokens ( 12.51 ms per token, 79.97 tokens per second) 4.03.403.323 I slot print_timing: id 0 | task 1269 | eval time = 7057.23 ms / 71 tokens ( 100.82 ms per token, 9.92 tokens per second) 4.03.403.326 I slot print_timing: id 0 | task 1269 | total time = 11996.85 ms / 466 tokens 4.03.403.328 I slot print_timing: id 0 | task 1269 | graphs reused = 1223 4.03.403.330 I slot print_timing: id 0 | task 1269 | graph reallocs = 0 / 0 (same size) / (changed size) 4.03.403.456 I slot release: id 0 | task 1269 | stop processing: n_tokens = 465, truncated = 0 4.03.416.331 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 465, t_last = 83461503093 4.03.416.398 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 478.640 MiB) 4.03.478.138 I slot launch_slot_: id 0 | task 1343 | processing task, is_child = 0 4.07.810.529 I slot print_timing: id 0 | task 1343 | prompt processing, n_tokens = 426, progress = 0.99, t = 4.33 s / 98.33 tokens per second 4.14.846.375 I slot print_timing: id 0 | task 1343 | prompt eval time = 5274.59 ms / 430 tokens ( 12.27 ms per token, 81.52 tokens per second) 4.14.846.383 I slot print_timing: id 0 | task 1343 | eval time = 6093.62 ms / 62 tokens ( 99.90 ms per token, 10.01 tokens per second) 4.14.846.390 I slot print_timing: id 0 | task 1343 | total time = 11368.22 ms / 492 tokens 4.14.846.395 I slot print_timing: id 0 | task 1343 | graphs reused = 1283 4.14.846.396 I slot print_timing: id 0 | task 1343 | graph reallocs = 0 / 0 (same size) / (changed size) 4.14.846.457 I slot release: id 0 | task 1343 | stop processing: n_tokens = 491, truncated = 0 4.14.856.131 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 491, t_last = 83472946094 4.14.856.211 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 482.704 MiB) 4.14.911.897 I slot launch_slot_: id 0 | task 1408 | processing task, is_child = 0 4.18.894.386 I slot print_timing: id 0 | task 1408 | prompt processing, n_tokens = 388, progress = 0.99, t = 3.98 s / 97.43 tokens per second 4.25.811.297 I slot print_timing: id 0 | task 1408 | prompt eval time = 4922.52 ms / 392 tokens ( 12.56 ms per token, 79.63 tokens per second) 4.25.811.303 I slot print_timing: id 0 | task 1408 | eval time = 5976.86 ms / 62 tokens ( 97.98 ms per token, 10.21 tokens per second) 4.25.811.303 I slot print_timing: id 0 | task 1408 | total time = 10899.38 ms / 454 tokens 4.25.811.304 I slot print_timing: id 0 | task 1408 | graphs reused = 1343 4.25.811.304 I slot print_timing: id 0 | task 1408 | graph reallocs = 0 / 0 (same size) / (changed size) 4.25.811.329 I slot release: id 0 | task 1408 | stop processing: n_tokens = 453, truncated = 0 4.25.815.526 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 453, t_last = 83483910966 4.25.815.554 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 473.325 MiB) 4.25.869.105 I slot launch_slot_: id 0 | task 1473 | processing task, is_child = 0 4.29.834.204 I slot print_timing: id 0 | task 1473 | prompt processing, n_tokens = 346, progress = 0.99, t = 3.97 s / 87.26 tokens per second 4.35.328.635 I slot print_timing: id 0 | task 1473 | prompt eval time = 4565.87 ms / 350 tokens ( 13.05 ms per token, 76.66 tokens per second) 4.35.328.650 I slot print_timing: id 0 | task 1473 | eval time = 4893.62 ms / 49 tokens ( 101.95 ms per token, 9.81 tokens per second) 4.35.328.653 I slot print_timing: id 0 | task 1473 | total time = 9459.49 ms / 399 tokens 4.35.328.655 I slot print_timing: id 0 | task 1473 | graphs reused = 1390 4.35.328.657 I slot print_timing: id 0 | task 1473 | graph reallocs = 0 / 0 (same size) / (changed size) 4.35.328.769 I slot release: id 0 | task 1473 | stop processing: n_tokens = 398, truncated = 0 4.35.340.839 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 398, t_last = 83493428407 4.35.340.901 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 474.138 MiB) 4.35.398.051 I slot launch_slot_: id 0 | task 1525 | processing task, is_child = 0 4.39.384.170 I slot print_timing: id 0 | task 1525 | prompt processing, n_tokens = 376, progress = 0.99, t = 3.99 s / 94.33 tokens per second 4.45.872.867 I slot print_timing: id 0 | task 1525 | prompt eval time = 4589.91 ms / 380 tokens ( 12.08 ms per token, 82.79 tokens per second) 4.45.872.876 I slot print_timing: id 0 | task 1525 | eval time = 5884.89 ms / 61 tokens ( 98.08 ms per token, 10.20 tokens per second) 4.45.872.877 I slot print_timing: id 0 | task 1525 | total time = 10474.80 ms / 441 tokens 4.45.872.877 I slot print_timing: id 0 | task 1525 | graphs reused = 1449 4.45.872.878 I slot print_timing: id 0 | task 1525 | graph reallocs = 0 / 0 (same size) / (changed size) 4.45.872.907 I slot release: id 0 | task 1525 | stop processing: n_tokens = 440, truncated = 0 4.45.877.336 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 440, t_last = 83503972544 4.45.877.368 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 476.201 MiB) 4.45.934.886 I slot launch_slot_: id 0 | task 1589 | processing task, is_child = 0 4.50.227.759 I slot print_timing: id 0 | task 1589 | prompt processing, n_tokens = 406, progress = 0.99, t = 4.29 s / 94.58 tokens per second 4.58.940.733 I slot print_timing: id 0 | task 1589 | prompt eval time = 5237.60 ms / 410 tokens ( 12.77 ms per token, 78.28 tokens per second) 4.58.940.745 I slot print_timing: id 0 | task 1589 | eval time = 7768.22 ms / 80 tokens ( 98.33 ms per token, 10.17 tokens per second) 4.58.940.746 I slot print_timing: id 0 | task 1589 | total time = 13005.82 ms / 490 tokens 4.58.940.747 I slot print_timing: id 0 | task 1589 | graphs reused = 1527 4.58.940.748 I slot print_timing: id 0 | task 1589 | graph reallocs = 0 / 0 (same size) / (changed size) 4.58.940.813 I slot release: id 0 | task 1589 | stop processing: n_tokens = 489, truncated = 0 4.58.952.528 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 489, t_last = 83517040451 4.58.952.611 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 477.514 MiB) 4.59.051.243 I slot launch_slot_: id 0 | task 1672 | processing task, is_child = 0 5.03.357.629 I slot print_timing: id 0 | task 1672 | prompt processing, n_tokens = 383, progress = 0.99, t = 4.31 s / 88.94 tokens per second 5.10.531.098 I slot print_timing: id 0 | task 1672 | prompt eval time = 4912.16 ms / 387 tokens ( 12.69 ms per token, 78.78 tokens per second) 5.10.531.101 I slot print_timing: id 0 | task 1672 | eval time = 6567.67 ms / 68 tokens ( 98.02 ms per token, 10.20 tokens per second) 5.10.531.102 I slot print_timing: id 0 | task 1672 | total time = 11479.84 ms / 455 tokens 5.10.531.102 I slot print_timing: id 0 | task 1672 | graphs reused = 1593 5.10.531.102 I slot print_timing: id 0 | task 1672 | graph reallocs = 0 / 0 (same size) / (changed size) 5.10.531.133 I slot release: id 0 | task 1672 | stop processing: n_tokens = 454, truncated = 0 5.10.535.592 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 454, t_last = 83528630770 5.10.535.629 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 476.201 MiB) 5.10.581.220 I slot launch_slot_: id 0 | task 1743 | processing task, is_child = 0 5.14.556.829 I slot print_timing: id 0 | task 1743 | prompt processing, n_tokens = 354, progress = 0.99, t = 3.98 s / 89.04 tokens per second 5.20.863.912 I slot print_timing: id 0 | task 1743 | prompt eval time = 4576.07 ms / 358 tokens ( 12.78 ms per token, 78.23 tokens per second) 5.20.863.917 I slot print_timing: id 0 | task 1743 | eval time = 5706.61 ms / 59 tokens ( 98.39 ms per token, 10.16 tokens per second) 5.20.863.918 I slot print_timing: id 0 | task 1743 | total time = 10282.68 ms / 417 tokens 5.20.863.919 I slot print_timing: id 0 | task 1743 | graphs reused = 1650 5.20.863.920 I slot print_timing: id 0 | task 1743 | graph reallocs = 0 / 0 (same size) / (changed size) 5.20.863.959 I slot release: id 0 | task 1743 | stop processing: n_tokens = 416, truncated = 0 5.20.871.299 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 83538963596 5.20.871.372 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 475.701 MiB) 5.20.926.957 I slot launch_slot_: id 0 | task 1805 | processing task, is_child = 0 5.24.903.090 I slot print_timing: id 0 | task 1805 | prompt processing, n_tokens = 355, progress = 0.99, t = 3.98 s / 89.28 tokens per second 5.28.249.955 I slot print_timing: id 0 | task 1805 | prompt eval time = 4577.19 ms / 359 tokens ( 12.75 ms per token, 78.43 tokens per second) 5.28.249.960 I slot print_timing: id 0 | task 1805 | eval time = 2745.79 ms / 29 tokens ( 98.06 ms per token, 10.20 tokens per second) 5.28.249.961 I slot print_timing: id 0 | task 1805 | total time = 7322.98 ms / 388 tokens 5.28.249.961 I slot print_timing: id 0 | task 1805 | graphs reused = 1677 5.28.249.962 I slot print_timing: id 0 | task 1805 | graph reallocs = 0 / 0 (same size) / (changed size) 5.28.249.986 I slot release: id 0 | task 1805 | stop processing: n_tokens = 387, truncated = 0 5.28.254.053 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 387, t_last = 83546349623 5.28.254.080 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 475.388 MiB) 5.28.309.300 I slot launch_slot_: id 0 | task 1837 | processing task, is_child = 0 5.32.603.280 I slot print_timing: id 0 | task 1837 | prompt processing, n_tokens = 383, progress = 0.99, t = 4.29 s / 89.19 tokens per second 5.39.272.706 I slot print_timing: id 0 | task 1837 | prompt eval time = 4894.88 ms / 387 tokens ( 12.65 ms per token, 79.06 tokens per second) 5.39.272.727 I slot print_timing: id 0 | task 1837 | eval time = 6068.50 ms / 61 tokens ( 101.14 ms per token, 9.89 tokens per second) 5.39.272.729 I slot print_timing: id 0 | task 1837 | total time = 10963.38 ms / 448 tokens 5.39.272.732 I slot print_timing: id 0 | task 1837 | graphs reused = 1736 5.39.272.734 I slot print_timing: id 0 | task 1837 | graph reallocs = 0 / 0 (same size) / (changed size) 5.39.272.847 I slot release: id 0 | task 1837 | stop processing: n_tokens = 447, truncated = 0 5.39.285.240 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 83557372484 5.39.285.306 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 473.700 MiB) 5.39.426.227 I slot launch_slot_: id 0 | task 1901 | processing task, is_child = 0 5.43.743.638 I slot print_timing: id 0 | task 1901 | prompt processing, n_tokens = 406, progress = 0.99, t = 4.32 s / 94.04 tokens per second 5.50.488.362 I slot print_timing: id 0 | task 1901 | prompt eval time = 4924.46 ms / 410 tokens ( 12.01 ms per token, 83.26 tokens per second) 5.50.488.373 I slot print_timing: id 0 | task 1901 | eval time = 6137.64 ms / 61 tokens ( 102.29 ms per token, 9.78 tokens per second) 5.50.488.376 I slot print_timing: id 0 | task 1901 | total time = 11062.10 ms / 471 tokens 5.50.488.381 I slot print_timing: id 0 | task 1901 | graphs reused = 1795 5.50.488.383 I slot print_timing: id 0 | task 1901 | graph reallocs = 0 / 0 (same size) / (changed size) 5.50.488.517 I slot release: id 0 | task 1901 | stop processing: n_tokens = 470, truncated = 0 5.50.501.955 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 83568588154 5.50.502.026 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 474.451 MiB) 5.50.668.733 I slot launch_slot_: id 0 | task 1965 | processing task, is_child = 0 5.54.644.848 I slot print_timing: id 0 | task 1965 | prompt processing, n_tokens = 347, progress = 0.99, t = 3.98 s / 87.27 tokens per second 6.00.249.078 I slot print_timing: id 0 | task 1965 | prompt eval time = 4576.55 ms / 351 tokens ( 13.04 ms per token, 76.70 tokens per second) 6.00.249.100 I slot print_timing: id 0 | task 1965 | eval time = 5003.76 ms / 50 tokens ( 102.12 ms per token, 9.79 tokens per second) 6.00.249.103 I slot print_timing: id 0 | task 1965 | total time = 9580.31 ms / 401 tokens 6.00.249.105 I slot print_timing: id 0 | task 1965 | graphs reused = 1843 6.00.249.107 I slot print_timing: id 0 | task 1965 | graph reallocs = 0 / 0 (same size) / (changed size) 6.00.249.220 I slot release: id 0 | task 1965 | stop processing: n_tokens = 400, truncated = 0 6.00.261.382 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 83578348857 6.00.261.446 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 473.388 MiB) 6.00.283.179 I slot launch_slot_: id 0 | task 2018 | processing task, is_child = 0 6.04.588.579 I slot print_timing: id 0 | task 2018 | prompt processing, n_tokens = 389, progress = 0.99, t = 4.31 s / 90.35 tokens per second 6.14.984.407 I slot print_timing: id 0 | task 2018 | n_gen = 100, tg = 10.11 t/s, tg_3s = 10.21 t/s 6.18.046.497 I slot print_timing: id 0 | task 2018 | n_gen = 129, tg = 9.95 t/s, tg_3s = 9.47 t/s 6.21.093.446 I slot print_timing: id 0 | task 2018 | n_gen = 158, tg = 9.87 t/s, tg_3s = 9.52 t/s 6.24.151.993 I slot print_timing: id 0 | task 2018 | n_gen = 187, tg = 9.81 t/s, tg_3s = 9.48 t/s 6.27.198.637 I slot print_timing: id 0 | task 2018 | n_gen = 216, tg = 9.77 t/s, tg_3s = 9.52 t/s 6.28.045.256 I slot print_timing: id 0 | task 2018 | prompt eval time = 4904.90 ms / 393 tokens ( 12.48 ms per token, 80.12 tokens per second) 6.28.045.269 I slot print_timing: id 0 | task 2018 | eval time = 22857.15 ms / 224 tokens ( 102.50 ms per token, 9.76 tokens per second) 6.28.045.277 I slot print_timing: id 0 | task 2018 | total time = 27762.04 ms / 617 tokens 6.28.045.279 I slot print_timing: id 0 | task 2018 | graphs reused = 2064 6.28.045.281 I slot print_timing: id 0 | task 2018 | graph reallocs = 0 / 0 (same size) / (changed size) 6.28.045.403 I slot release: id 0 | task 2018 | stop processing: n_tokens = 616, truncated = 0 6.28.057.375 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 616, t_last = 83606145040 6.28.057.451 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 473.138 MiB) 6.28.113.858 I slot launch_slot_: id 0 | task 2245 | processing task, is_child = 0 6.31.734.688 I slot print_timing: id 0 | task 2245 | prompt processing, n_tokens = 317, progress = 0.99, t = 3.62 s / 87.55 tokens per second 6.35.613.582 I slot print_timing: id 0 | task 2245 | prompt eval time = 4235.59 ms / 321 tokens ( 13.19 ms per token, 75.79 tokens per second) 6.35.613.593 I slot print_timing: id 0 | task 2245 | eval time = 3264.11 ms / 32 tokens ( 105.29 ms per token, 9.50 tokens per second) 6.35.613.605 I slot print_timing: id 0 | task 2245 | total time = 7499.70 ms / 353 tokens 6.35.613.610 I slot print_timing: id 0 | task 2245 | graphs reused = 2094 6.35.613.612 I slot print_timing: id 0 | task 2245 | graph reallocs = 0 / 0 (same size) / (changed size) 6.35.613.741 I slot release: id 0 | task 2245 | stop processing: n_tokens = 352, truncated = 0 6.35.625.502 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 352, t_last = 83613713378 6.35.625.566 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 476.764 MiB) 6.35.652.593 I slot launch_slot_: id 0 | task 2280 | processing task, is_child = 0 6.39.262.070 I slot print_timing: id 0 | task 2280 | prompt processing, n_tokens = 326, progress = 0.99, t = 3.61 s / 90.32 tokens per second 6.47.363.625 I slot print_timing: id 0 | task 2280 | prompt eval time = 4210.19 ms / 330 tokens ( 12.76 ms per token, 78.38 tokens per second) 6.47.363.653 I slot print_timing: id 0 | task 2280 | eval time = 7500.81 ms / 75 tokens ( 101.36 ms per token, 9.87 tokens per second) 6.47.363.656 I slot print_timing: id 0 | task 2280 | total time = 11711.00 ms / 405 tokens 6.47.363.658 I slot print_timing: id 0 | task 2280 | graphs reused = 2167 6.47.363.660 I slot print_timing: id 0 | task 2280 | graph reallocs = 0 / 0 (same size) / (changed size) 6.47.363.764 I slot release: id 0 | task 2280 | stop processing: n_tokens = 404, truncated = 0 6.47.375.338 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 404, t_last = 83625463402 6.47.375.421 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 474.451 MiB) 6.47.416.199 I slot launch_slot_: id 0 | task 2358 | processing task, is_child = 0 6.51.040.303 I slot print_timing: id 0 | task 2358 | prompt processing, n_tokens = 337, progress = 0.99, t = 3.62 s / 92.99 tokens per second 6.54.911.492 I slot print_timing: id 0 | task 2358 | prompt eval time = 4225.61 ms / 341 tokens ( 12.39 ms per token, 80.70 tokens per second) 6.54.911.505 I slot print_timing: id 0 | task 2358 | eval time = 3269.65 ms / 32 tokens ( 105.47 ms per token, 9.48 tokens per second) 6.54.911.510 I slot print_timing: id 0 | task 2358 | total time = 7495.26 ms / 373 tokens 6.54.911.516 I slot print_timing: id 0 | task 2358 | graphs reused = 2197 6.54.911.523 I slot print_timing: id 0 | task 2358 | graph reallocs = 0 / 0 (same size) / (changed size) 6.54.911.634 I slot release: id 0 | task 2358 | stop processing: n_tokens = 372, truncated = 0 6.54.922.849 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 372, t_last = 83633011271 6.54.922.909 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 478.827 MiB) 6.54.969.345 I slot launch_slot_: id 0 | task 2393 | processing task, is_child = 0 6.58.812.021 I slot print_timing: id 0 | task 2393 | prompt processing, n_tokens = 334, progress = 0.99, t = 3.84 s / 86.92 tokens per second 7.04.107.849 I slot print_timing: id 0 | task 2393 | prompt eval time = 4288.12 ms / 338 tokens ( 12.69 ms per token, 78.82 tokens per second) 7.04.107.860 I slot print_timing: id 0 | task 2393 | eval time = 4850.35 ms / 48 tokens ( 103.20 ms per token, 9.69 tokens per second) 7.04.107.863 I slot print_timing: id 0 | task 2393 | total time = 9138.46 ms / 386 tokens 7.04.107.865 I slot print_timing: id 0 | task 2393 | graphs reused = 2243 7.04.107.867 I slot print_timing: id 0 | task 2393 | graph reallocs = 0 / 0 (same size) / (changed size) 7.04.107.963 I slot release: id 0 | task 2393 | stop processing: n_tokens = 385, truncated = 0 7.04.120.607 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 385, t_last = 83642207600 7.04.120.675 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 477.014 MiB) 7.04.208.240 I slot launch_slot_: id 0 | task 2444 | processing task, is_child = 0 7.08.207.996 I slot print_timing: id 0 | task 2444 | prompt processing, n_tokens = 391, progress = 0.99, t = 4.00 s / 97.76 tokens per second 7.14.542.713 I slot print_timing: id 0 | task 2444 | prompt eval time = 4942.13 ms / 395 tokens ( 12.51 ms per token, 79.93 tokens per second) 7.14.542.718 I slot print_timing: id 0 | task 2444 | eval time = 5392.33 ms / 56 tokens ( 98.04 ms per token, 10.20 tokens per second) 7.14.542.719 I slot print_timing: id 0 | task 2444 | total time = 10334.46 ms / 451 tokens 7.14.542.719 I slot print_timing: id 0 | task 2444 | graphs reused = 2297 7.14.542.720 I slot print_timing: id 0 | task 2444 | graph reallocs = 0 / 0 (same size) / (changed size) 7.14.542.746 I slot release: id 0 | task 2444 | stop processing: n_tokens = 450, truncated = 0 7.14.546.898 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 450, t_last = 83652642383 7.14.546.926 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 477.952 MiB) 7.14.598.822 I slot launch_slot_: id 0 | task 2503 | processing task, is_child = 0 7.20.263.786 I slot print_timing: id 0 | task 2503 | prompt processing, n_tokens = 524, progress = 0.99, t = 5.66 s / 92.50 tokens per second 7.29.756.245 I slot print_timing: id 0 | task 2503 | prompt eval time = 6621.18 ms / 528 tokens ( 12.54 ms per token, 79.74 tokens per second) 7.29.756.257 I slot print_timing: id 0 | task 2503 | eval time = 8536.22 ms / 83 tokens ( 104.10 ms per token, 9.61 tokens per second) 7.29.756.260 I slot print_timing: id 0 | task 2503 | total time = 15157.39 ms / 611 tokens 7.29.756.262 I slot print_timing: id 0 | task 2503 | graphs reused = 2378 7.29.756.264 I slot print_timing: id 0 | task 2503 | graph reallocs = 0 / 0 (same size) / (changed size) 7.29.756.413 I slot release: id 0 | task 2503 | stop processing: n_tokens = 610, truncated = 0 7.29.768.610 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 610, t_last = 83667856051 7.29.768.692 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 479.578 MiB) 7.29.768.727 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 477.202 MiB) 7.29.910.535 I slot launch_slot_: id 0 | task 2590 | processing task, is_child = 0 7.33.540.003 I slot print_timing: id 0 | task 2590 | prompt processing, n_tokens = 327, progress = 0.99, t = 3.63 s / 90.10 tokens per second 7.38.463.990 I slot print_timing: id 0 | task 2590 | prompt eval time = 4233.48 ms / 331 tokens ( 12.79 ms per token, 78.19 tokens per second) 7.38.463.993 I slot print_timing: id 0 | task 2590 | eval time = 4319.96 ms / 45 tokens ( 98.18 ms per token, 10.19 tokens per second) 7.38.463.993 I slot print_timing: id 0 | task 2590 | total time = 8553.44 ms / 376 tokens 7.38.463.994 I slot print_timing: id 0 | task 2590 | graphs reused = 2421 7.38.463.994 I slot print_timing: id 0 | task 2590 | graph reallocs = 0 / 0 (same size) / (changed size) 7.38.464.021 I slot release: id 0 | task 2590 | stop processing: n_tokens = 387, truncated = 0 7.38.467.597 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 387, t_last = 83676563658 7.38.467.626 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 473.763 MiB) 7.38.555.300 I slot launch_slot_: id 0 | task 2638 | processing task, is_child = 0 7.42.548.503 I slot print_timing: id 0 | task 2638 | prompt processing, n_tokens = 358, progress = 0.99, t = 3.99 s / 89.65 tokens per second 7.48.288.653 I slot print_timing: id 0 | task 2638 | prompt eval time = 4594.07 ms / 362 tokens ( 12.69 ms per token, 78.80 tokens per second) 7.48.288.670 I slot print_timing: id 0 | task 2638 | eval time = 5139.24 ms / 53 tokens ( 98.83 ms per token, 10.12 tokens per second) 7.48.288.673 I slot print_timing: id 0 | task 2638 | total time = 9733.31 ms / 415 tokens 7.48.288.675 I slot print_timing: id 0 | task 2638 | graphs reused = 2472 7.48.288.678 I slot print_timing: id 0 | task 2638 | graph reallocs = 0 / 0 (same size) / (changed size) 7.48.288.794 I slot release: id 0 | task 2638 | stop processing: n_tokens = 426, truncated = 0 7.48.300.729 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 83686388431 7.48.300.796 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 476.389 MiB) 7.48.413.684 I slot launch_slot_: id 0 | task 2694 | processing task, is_child = 0 7.52.743.392 I slot print_timing: id 0 | task 2694 | prompt processing, n_tokens = 415, progress = 0.99, t = 4.33 s / 95.85 tokens per second 8.00.780.487 I slot print_timing: id 0 | task 2694 | prompt eval time = 5263.64 ms / 419 tokens ( 12.56 ms per token, 79.60 tokens per second) 8.00.780.492 I slot print_timing: id 0 | task 2694 | eval time = 7103.13 ms / 69 tokens ( 104.46 ms per token, 9.57 tokens per second) 8.00.780.495 I slot print_timing: id 0 | task 2694 | total time = 12366.77 ms / 488 tokens 8.00.780.496 I slot print_timing: id 0 | task 2694 | graphs reused = 2539 8.00.780.506 I slot print_timing: id 0 | task 2694 | graph reallocs = 0 / 0 (same size) / (changed size) 8.00.780.579 I slot release: id 0 | task 2694 | stop processing: n_tokens = 499, truncated = 0 8.00.791.997 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 499, t_last = 83698880216 8.00.792.089 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 479.452 MiB) 8.00.792.097 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 477.264 MiB) 8.00.916.267 I slot launch_slot_: id 0 | task 2766 | processing task, is_child = 0 8.05.604.151 I slot print_timing: id 0 | task 2766 | prompt processing, n_tokens = 419, progress = 0.99, t = 4.69 s / 89.38 tokens per second 8.15.651.523 I slot print_timing: id 0 | task 2766 | prompt eval time = 5295.54 ms / 423 tokens ( 12.52 ms per token, 79.88 tokens per second) 8.15.651.526 I slot print_timing: id 0 | task 2766 | eval time = 9439.71 ms / 97 tokens ( 98.33 ms per token, 10.17 tokens per second) 8.15.651.527 I slot print_timing: id 0 | task 2766 | total time = 14735.24 ms / 520 tokens 8.15.651.527 I slot print_timing: id 0 | task 2766 | graphs reused = 2633 8.15.651.528 I slot print_timing: id 0 | task 2766 | graph reallocs = 0 / 0 (same size) / (changed size) 8.15.651.559 I slot release: id 0 | task 2766 | stop processing: n_tokens = 531, truncated = 0 8.15.655.312 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 531, t_last = 83713751196 8.15.655.348 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 474.888 MiB) 8.15.745.694 I slot launch_slot_: id 0 | task 2866 | processing task, is_child = 0 8.19.335.002 I slot print_timing: id 0 | task 2866 | prompt processing, n_tokens = 337, progress = 0.99, t = 3.59 s / 93.89 tokens per second 8.24.388.121 I slot print_timing: id 0 | task 2866 | prompt eval time = 4204.79 ms / 341 tokens ( 12.33 ms per token, 81.10 tokens per second) 8.24.388.130 I slot print_timing: id 0 | task 2866 | eval time = 4437.59 ms / 43 tokens ( 105.66 ms per token, 9.46 tokens per second) 8.24.388.132 I slot print_timing: id 0 | task 2866 | total time = 8642.38 ms / 384 tokens 8.24.388.134 I slot print_timing: id 0 | task 2866 | graphs reused = 2674 8.24.388.136 I slot print_timing: id 0 | task 2866 | graph reallocs = 0 / 0 (same size) / (changed size) 8.24.388.515 I slot release: id 0 | task 2866 | stop processing: n_tokens = 395, truncated = 0 8.24.402.565 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 395, t_last = 83722488152 8.24.402.654 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 473.075 MiB) 8.24.539.453 I slot launch_slot_: id 0 | task 2912 | processing task, is_child = 0 8.28.522.340 I slot print_timing: id 0 | task 2912 | prompt processing, n_tokens = 352, progress = 0.99, t = 3.98 s / 88.38 tokens per second 8.33.898.588 I slot print_timing: id 0 | task 2912 | prompt eval time = 4586.20 ms / 356 tokens ( 12.88 ms per token, 77.62 tokens per second) 8.33.898.603 I slot print_timing: id 0 | task 2912 | eval time = 4772.91 ms / 47 tokens ( 103.76 ms per token, 9.64 tokens per second) 8.33.898.606 I slot print_timing: id 0 | task 2912 | total time = 9359.11 ms / 403 tokens 8.33.898.608 I slot print_timing: id 0 | task 2912 | graphs reused = 2719 8.33.898.610 I slot print_timing: id 0 | task 2912 | graph reallocs = 0 / 0 (same size) / (changed size) 8.33.898.763 I slot release: id 0 | task 2912 | stop processing: n_tokens = 414, truncated = 0 8.33.911.736 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 83731998400 8.33.911.814 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 476.826 MiB) 8.33.911.821 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 478.265 MiB) 8.34.065.523 I slot launch_slot_: id 0 | task 2962 | processing task, is_child = 0 8.38.062.324 I slot print_timing: id 0 | task 2962 | prompt processing, n_tokens = 358, progress = 0.99, t = 4.00 s / 89.57 tokens per second 8.42.885.879 I slot print_timing: id 0 | task 2962 | prompt eval time = 4597.76 ms / 362 tokens ( 12.70 ms per token, 78.73 tokens per second) 8.42.885.882 I slot print_timing: id 0 | task 2962 | eval time = 4222.58 ms / 44 tokens ( 98.20 ms per token, 10.18 tokens per second) 8.42.885.882 I slot print_timing: id 0 | task 2962 | total time = 8820.34 ms / 406 tokens 8.42.885.882 I slot print_timing: id 0 | task 2962 | graphs reused = 2761 8.42.885.883 I slot print_timing: id 0 | task 2962 | graph reallocs = 0 / 0 (same size) / (changed size) 8.42.885.929 I slot release: id 0 | task 2962 | stop processing: n_tokens = 417, truncated = 0 8.42.890.642 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 417, t_last = 83740985566 8.42.890.671 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 473.888 MiB) 8.42.991.732 I slot launch_slot_: id 0 | task 3009 | processing task, is_child = 0 8.47.300.180 I slot print_timing: id 0 | task 3009 | prompt processing, n_tokens = 387, progress = 0.99, t = 4.31 s / 89.82 tokens per second 8.54.900.755 I slot print_timing: id 0 | task 3009 | prompt eval time = 4917.10 ms / 391 tokens ( 12.58 ms per token, 79.52 tokens per second) 8.54.900.778 I slot print_timing: id 0 | task 3009 | eval time = 6991.88 ms / 68 tokens ( 104.36 ms per token, 9.58 tokens per second) 8.54.900.781 I slot print_timing: id 0 | task 3009 | total time = 11908.98 ms / 459 tokens 8.54.900.783 I slot print_timing: id 0 | task 3009 | graphs reused = 2827 8.54.900.785 I slot print_timing: id 0 | task 3009 | graph reallocs = 0 / 0 (same size) / (changed size) 8.54.901.007 I slot release: id 0 | task 3009 | stop processing: n_tokens = 470, truncated = 0 8.54.914.084 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 83753000645 8.54.914.159 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 487.393 MiB) 8.55.031.922 I slot launch_slot_: id 0 | task 3080 | processing task, is_child = 0 8.58.670.810 I slot print_timing: id 0 | task 3080 | prompt processing, n_tokens = 339, progress = 0.99, t = 3.64 s / 93.16 tokens per second 9.06.634.428 I slot print_timing: id 0 | task 3080 | prompt eval time = 4242.24 ms / 343 tokens ( 12.37 ms per token, 80.85 tokens per second) 9.06.634.446 I slot print_timing: id 0 | task 3080 | eval time = 7360.23 ms / 75 tokens ( 99.46 ms per token, 10.05 tokens per second) 9.06.634.458 I slot print_timing: id 0 | task 3080 | total time = 11602.47 ms / 418 tokens 9.06.634.460 I slot print_timing: id 0 | task 3080 | graphs reused = 2900 9.06.634.465 I slot print_timing: id 0 | task 3080 | graph reallocs = 0 / 0 (same size) / (changed size) 9.06.634.599 I slot release: id 0 | task 3080 | stop processing: n_tokens = 429, truncated = 0 9.06.647.370 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 429, t_last = 83764734236 9.06.647.443 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 470.887 MiB) 9.06.780.850 I slot launch_slot_: id 0 | task 3158 | processing task, is_child = 0 9.11.102.647 I slot print_timing: id 0 | task 3158 | prompt processing, n_tokens = 397, progress = 0.99, t = 4.32 s / 91.86 tokens per second 9.16.280.947 I slot print_timing: id 0 | task 3158 | prompt eval time = 4928.15 ms / 401 tokens ( 12.29 ms per token, 81.37 tokens per second) 9.16.280.961 I slot print_timing: id 0 | task 3158 | eval time = 4571.91 ms / 46 tokens ( 101.60 ms per token, 9.84 tokens per second) 9.16.280.963 I slot print_timing: id 0 | task 3158 | total time = 9500.06 ms / 447 tokens 9.16.280.965 I slot print_timing: id 0 | task 3158 | graphs reused = 2944 9.16.280.967 I slot print_timing: id 0 | task 3158 | graph reallocs = 0 / 0 (same size) / (changed size) 9.16.281.303 I slot release: id 0 | task 3158 | stop processing: n_tokens = 458, truncated = 0 9.16.294.592 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 83774380941 9.16.294.680 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 474.138 MiB) 9.16.294.693 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 472.137 MiB) 9.16.320.520 I slot launch_slot_: id 0 | task 3207 | processing task, is_child = 0 9.20.306.185 I slot print_timing: id 0 | task 3207 | prompt processing, n_tokens = 351, progress = 0.99, t = 3.99 s / 88.07 tokens per second 9.27.913.216 I slot print_timing: id 0 | task 3207 | prompt eval time = 4587.05 ms / 355 tokens ( 12.92 ms per token, 77.39 tokens per second) 9.27.913.226 I slot print_timing: id 0 | task 3207 | eval time = 7005.60 ms / 68 tokens ( 104.56 ms per token, 9.56 tokens per second) 9.27.913.229 I slot print_timing: id 0 | task 3207 | total time = 11592.65 ms / 423 tokens 9.27.913.237 I slot print_timing: id 0 | task 3207 | graphs reused = 3010 9.27.913.239 I slot print_timing: id 0 | task 3207 | graph reallocs = 0 / 0 (same size) / (changed size) 9.27.913.420 I slot release: id 0 | task 3207 | stop processing: n_tokens = 434, truncated = 0 9.27.926.637 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 434, t_last = 83786013057 9.27.926.703 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 472.950 MiB) 9.28.017.592 I slot launch_slot_: id 0 | task 3278 | processing task, is_child = 0 9.32.000.197 I slot print_timing: id 0 | task 3278 | prompt processing, n_tokens = 347, progress = 0.99, t = 3.98 s / 87.13 tokens per second 9.38.338.216 I slot print_timing: id 0 | task 3278 | prompt eval time = 4586.64 ms / 351 tokens ( 13.07 ms per token, 76.53 tokens per second) 9.38.338.228 I slot print_timing: id 0 | task 3278 | eval time = 5733.93 ms / 57 tokens ( 102.39 ms per token, 9.77 tokens per second) 9.38.338.231 I slot print_timing: id 0 | task 3278 | total time = 10320.58 ms / 408 tokens 9.38.338.238 I slot print_timing: id 0 | task 3278 | graphs reused = 3065 9.38.338.240 I slot print_timing: id 0 | task 3278 | graph reallocs = 0 / 0 (same size) / (changed size) 9.38.338.423 I slot release: id 0 | task 3278 | stop processing: n_tokens = 419, truncated = 0 9.38.351.458 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 83796438060 9.38.351.528 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 477.014 MiB) 9.38.449.065 I slot launch_slot_: id 0 | task 3338 | processing task, is_child = 0 9.43.528.616 I slot print_timing: id 0 | task 3338 | prompt processing, n_tokens = 471, progress = 0.99, t = 5.08 s / 92.73 tokens per second 9.54.207.227 I slot print_timing: id 0 | task 3338 | prompt eval time = 6030.58 ms / 475 tokens ( 12.70 ms per token, 78.77 tokens per second) 9.54.207.235 I slot print_timing: id 0 | task 3338 | eval time = 9727.54 ms / 93 tokens ( 105.73 ms per token, 9.46 tokens per second) 9.54.207.237 I slot print_timing: id 0 | task 3338 | total time = 15758.13 ms / 568 tokens 9.54.207.239 I slot print_timing: id 0 | task 3338 | graphs reused = 3155 9.54.207.240 I slot print_timing: id 0 | task 3338 | graph reallocs = 0 / 0 (same size) / (changed size) 9.54.207.394 I slot release: id 0 | task 3338 | stop processing: n_tokens = 579, truncated = 0 9.54.220.744 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 579, t_last = 83812307032 9.54.220.824 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 636.644 MiB) 9.54.333.875 I slot launch_slot_: id 0 | task 3434 | processing task, is_child = 0 9.59.027.844 I slot print_timing: id 0 | task 3434 | prompt processing, n_tokens = 436, progress = 0.99, t = 4.69 s / 92.89 tokens per second 10.10.235.247 I slot print_timing: id 0 | task 3434 | n_gen = 100, tg = 9.64 t/s, tg_3s = 9.73 t/s 10.10.871.412 I slot print_timing: id 0 | task 3434 | prompt eval time = 5627.11 ms / 440 tokens ( 12.79 ms per token, 78.19 tokens per second) 10.10.871.418 I slot print_timing: id 0 | task 3434 | eval time = 10910.41 ms / 106 tokens ( 103.91 ms per token, 9.62 tokens per second) 10.10.871.419 I slot print_timing: id 0 | task 3434 | total time = 16537.51 ms / 546 tokens 10.10.871.421 I slot print_timing: id 0 | task 3434 | graphs reused = 3258 10.10.871.422 I slot print_timing: id 0 | task 3434 | graph reallocs = 0 / 0 (same size) / (changed size) 10.10.871.564 I slot release: id 0 | task 3434 | stop processing: n_tokens = 557, truncated = 0 10.10.883.401 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 557, t_last = 83828971201 10.10.883.487 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 622.701 MiB) 10.10.999.432 I slot launch_slot_: id 0 | task 3543 | processing task, is_child = 0 10.14.638.801 I slot print_timing: id 0 | task 3543 | prompt processing, n_tokens = 341, progress = 0.99, t = 3.64 s / 93.70 tokens per second 10.20.637.067 I slot print_timing: id 0 | task 3543 | prompt eval time = 4241.38 ms / 345 tokens ( 12.29 ms per token, 81.34 tokens per second) 10.20.637.072 I slot print_timing: id 0 | task 3543 | eval time = 5396.22 ms / 55 tokens ( 99.93 ms per token, 10.01 tokens per second) 10.20.637.074 I slot print_timing: id 0 | task 3543 | total time = 9637.60 ms / 400 tokens 10.20.637.075 I slot print_timing: id 0 | task 3543 | graphs reused = 3311 10.20.637.076 I slot print_timing: id 0 | task 3543 | graph reallocs = 0 / 0 (same size) / (changed size) 10.20.637.150 I slot release: id 0 | task 3543 | stop processing: n_tokens = 411, truncated = 0 10.20.648.313 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 83838736787 10.20.648.381 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 625.140 MiB) 10.20.753.761 I slot launch_slot_: id 0 | task 3601 | processing task, is_child = 0 10.25.053.870 I slot print_timing: id 0 | task 3601 | prompt processing, n_tokens = 378, progress = 0.99, t = 4.30 s / 87.91 tokens per second 10.30.952.610 I slot print_timing: id 0 | task 3601 | prompt eval time = 4904.87 ms / 382 tokens ( 12.84 ms per token, 77.88 tokens per second) 10.30.952.616 I slot print_timing: id 0 | task 3601 | eval time = 5293.96 ms / 55 tokens ( 98.04 ms per token, 10.20 tokens per second) 10.30.952.616 I slot print_timing: id 0 | task 3601 | total time = 10198.83 ms / 437 tokens 10.30.952.617 I slot print_timing: id 0 | task 3601 | graphs reused = 3364 10.30.952.617 I slot print_timing: id 0 | task 3601 | graph reallocs = 0 / 0 (same size) / (changed size) 10.30.952.664 I slot release: id 0 | task 3601 | stop processing: n_tokens = 448, truncated = 0 10.30.956.938 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 83849052301 10.30.956.972 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 629.704 MiB) 10.31.001.542 I slot launch_slot_: id 0 | task 3659 | processing task, is_child = 0 10.34.625.081 I slot print_timing: id 0 | task 3659 | prompt processing, n_tokens = 333, progress = 0.99, t = 3.62 s / 91.90 tokens per second 10.39.838.516 I slot print_timing: id 0 | task 3659 | prompt eval time = 4225.61 ms / 337 tokens ( 12.54 ms per token, 79.75 tokens per second) 10.39.838.531 I slot print_timing: id 0 | task 3659 | eval time = 4611.34 ms / 45 tokens ( 104.80 ms per token, 9.54 tokens per second) 10.39.838.533 I slot print_timing: id 0 | task 3659 | total time = 8836.95 ms / 382 tokens 10.39.838.542 I slot print_timing: id 0 | task 3659 | graphs reused = 3407 10.39.838.554 I slot print_timing: id 0 | task 3659 | graph reallocs = 0 / 0 (same size) / (changed size) 10.39.838.796 I slot release: id 0 | task 3659 | stop processing: n_tokens = 393, truncated = 0 10.39.852.858 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 83857938433 10.39.852.921 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 631.705 MiB) 10.39.959.810 I slot launch_slot_: id 0 | task 3707 | processing task, is_child = 0 10.44.281.729 I slot print_timing: id 0 | task 3707 | prompt processing, n_tokens = 398, progress = 0.99, t = 4.32 s / 92.09 tokens per second 10.51.664.829 I slot print_timing: id 0 | task 3707 | prompt eval time = 4927.15 ms / 402 tokens ( 12.26 ms per token, 81.59 tokens per second) 10.51.664.835 I slot print_timing: id 0 | task 3707 | eval time = 6777.85 ms / 70 tokens ( 98.23 ms per token, 10.18 tokens per second) 10.51.664.836 I slot print_timing: id 0 | task 3707 | total time = 11705.00 ms / 472 tokens 10.51.664.837 I slot print_timing: id 0 | task 3707 | graphs reused = 3475 10.51.664.837 I slot print_timing: id 0 | task 3707 | graph reallocs = 0 / 0 (same size) / (changed size) 10.51.664.892 I slot release: id 0 | task 3707 | stop processing: n_tokens = 483, truncated = 0 10.51.669.824 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 483, t_last = 83869764529 10.51.669.855 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 623.201 MiB) 10.51.750.172 I slot launch_slot_: id 0 | task 3780 | processing task, is_child = 0 10.57.938.701 I slot print_timing: id 0 | task 3780 | prompt processing, n_tokens = 545, progress = 0.99, t = 6.19 s / 88.07 tokens per second 11.07.596.623 I slot print_timing: id 0 | task 3780 | prompt eval time = 7120.19 ms / 549 tokens ( 12.97 ms per token, 77.10 tokens per second) 11.07.596.630 I slot print_timing: id 0 | task 3780 | eval time = 8726.23 ms / 84 tokens ( 105.14 ms per token, 9.51 tokens per second) 11.07.596.632 I slot print_timing: id 0 | task 3780 | total time = 15846.42 ms / 633 tokens 11.07.596.633 I slot print_timing: id 0 | task 3780 | graphs reused = 3557 11.07.596.634 I slot print_timing: id 0 | task 3780 | graph reallocs = 0 / 0 (same size) / (changed size) 11.07.596.784 I slot release: id 0 | task 3780 | stop processing: n_tokens = 644, truncated = 0 11.07.608.449 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 644, t_last = 83885696422 11.07.608.536 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 624.389 MiB) 11.07.608.548 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 624.577 MiB) 11.07.806.072 I slot launch_slot_: id 0 | task 3868 | processing task, is_child = 0 11.14.681.100 I slot print_timing: id 0 | task 3868 | prompt processing, n_tokens = 612, progress = 0.99, t = 6.88 s / 89.02 tokens per second 11.21.342.765 I slot print_timing: id 0 | task 3868 | prompt eval time = 7826.74 ms / 616 tokens ( 12.71 ms per token, 78.70 tokens per second) 11.21.342.776 I slot print_timing: id 0 | task 3868 | eval time = 5709.90 ms / 58 tokens ( 100.17 ms per token, 9.98 tokens per second) 11.21.342.778 I slot print_timing: id 0 | task 3868 | total time = 13536.64 ms / 674 tokens 11.21.342.780 I slot print_timing: id 0 | task 3868 | graphs reused = 3613 11.21.342.782 I slot print_timing: id 0 | task 3868 | graph reallocs = 0 / 0 (same size) / (changed size) 11.21.342.957 I slot release: id 0 | task 3868 | stop processing: n_tokens = 685, truncated = 0 11.21.358.175 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 685, t_last = 83899442594 11.21.358.262 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 627.891 MiB) 11.21.570.341 I slot launch_slot_: id 0 | task 3930 | processing task, is_child = 0 11.28.828.835 I slot print_timing: id 0 | task 3930 | prompt processing, n_tokens = 661, progress = 0.99, t = 7.26 s / 91.07 tokens per second 11.35.664.890 I slot print_timing: id 0 | task 3930 | prompt eval time = 8202.81 ms / 665 tokens ( 12.34 ms per token, 81.07 tokens per second) 11.35.664.892 I slot print_timing: id 0 | task 3930 | eval time = 5891.73 ms / 61 tokens ( 98.20 ms per token, 10.18 tokens per second) 11.35.664.900 I slot print_timing: id 0 | task 3930 | total time = 14094.54 ms / 726 tokens 11.35.664.904 I slot print_timing: id 0 | task 3930 | graphs reused = 3672 11.35.664.905 I slot print_timing: id 0 | task 3930 | graph reallocs = 0 / 0 (same size) / (changed size) 11.35.664.961 I slot release: id 0 | task 3930 | stop processing: n_tokens = 737, truncated = 0 11.35.669.661 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 737, t_last = 83913764598 11.35.669.703 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 625.327 MiB) 11.35.794.367 I slot launch_slot_: id 0 | task 3995 | processing task, is_child = 0 11.43.367.319 I slot print_timing: id 0 | task 3995 | prompt processing, n_tokens = 641, progress = 0.99, t = 7.57 s / 84.64 tokens per second 11.49.283.081 I slot print_timing: id 0 | task 3995 | prompt eval time = 8182.70 ms / 645 tokens ( 12.69 ms per token, 78.82 tokens per second) 11.49.283.084 I slot print_timing: id 0 | task 3995 | eval time = 5306.00 ms / 55 tokens ( 98.26 ms per token, 10.18 tokens per second) 11.49.283.084 I slot print_timing: id 0 | task 3995 | total time = 13488.70 ms / 700 tokens 11.49.283.085 I slot print_timing: id 0 | task 3995 | graphs reused = 3725 11.49.283.085 I slot print_timing: id 0 | task 3995 | graph reallocs = 0 / 0 (same size) / (changed size) 11.49.283.134 I slot release: id 0 | task 3995 | stop processing: n_tokens = 711, truncated = 0 11.49.287.337 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 711, t_last = 83927382771 11.49.287.373 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 627.140 MiB) 11.49.397.117 I slot launch_slot_: id 0 | task 4054 | processing task, is_child = 0 11.54.456.672 I slot print_timing: id 0 | task 4054 | prompt processing, n_tokens = 470, progress = 0.99, t = 5.06 s / 92.89 tokens per second 12.02.320.672 I slot print_timing: id 0 | task 4054 | prompt eval time = 5666.05 ms / 474 tokens ( 11.95 ms per token, 83.66 tokens per second) 12.02.320.675 I slot print_timing: id 0 | task 4054 | eval time = 7257.49 ms / 75 tokens ( 98.07 ms per token, 10.20 tokens per second) 12.02.320.675 I slot print_timing: id 0 | task 4054 | total time = 12923.54 ms / 549 tokens 12.02.320.676 I slot print_timing: id 0 | task 4054 | graphs reused = 3797 12.02.320.676 I slot print_timing: id 0 | task 4054 | graph reallocs = 0 / 0 (same size) / (changed size) 12.02.320.734 I slot release: id 0 | task 4054 | stop processing: n_tokens = 560, truncated = 0 12.02.326.932 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 83940420371 12.02.326.969 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 625.640 MiB) 12.02.326.976 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 624.702 MiB) 12.02.429.364 I slot launch_slot_: id 0 | task 4132 | processing task, is_child = 0 12.09.641.493 I slot print_timing: id 0 | task 4132 | prompt processing, n_tokens = 613, progress = 0.99, t = 7.21 s / 85.00 tokens per second 12.14.271.577 I slot print_timing: id 0 | task 4132 | prompt eval time = 7819.94 ms / 617 tokens ( 12.67 ms per token, 78.90 tokens per second) 12.14.271.581 I slot print_timing: id 0 | task 4132 | eval time = 4022.27 ms / 42 tokens ( 98.10 ms per token, 10.19 tokens per second) 12.14.271.581 I slot print_timing: id 0 | task 4132 | total time = 11842.20 ms / 659 tokens 12.14.271.582 I slot print_timing: id 0 | task 4132 | graphs reused = 3837 12.14.271.582 I slot print_timing: id 0 | task 4132 | graph reallocs = 0 / 0 (same size) / (changed size) 12.14.271.625 I slot release: id 0 | task 4132 | stop processing: n_tokens = 670, truncated = 0 12.14.276.089 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 670, t_last = 83952371262 12.14.276.123 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 634.706 MiB) 12.14.431.925 I slot launch_slot_: id 0 | task 4178 | processing task, is_child = 0 12.21.326.560 I slot print_timing: id 0 | task 4178 | prompt processing, n_tokens = 597, progress = 0.99, t = 6.89 s / 86.59 tokens per second 12.31.701.138 I slot print_timing: id 0 | task 4178 | n_gen = 100, tg = 10.14 t/s, tg_3s = 10.24 t/s 12.34.757.218 I slot print_timing: id 0 | task 4178 | n_gen = 129, tg = 9.98 t/s, tg_3s = 9.49 t/s 12.35.498.734 I slot print_timing: id 0 | task 4178 | prompt eval time = 7504.78 ms / 601 tokens ( 12.49 ms per token, 80.08 tokens per second) 12.35.498.744 I slot print_timing: id 0 | task 4178 | eval time = 13561.99 ms / 136 tokens ( 100.46 ms per token, 9.95 tokens per second) 12.35.498.747 I slot print_timing: id 0 | task 4178 | total time = 21066.77 ms / 737 tokens 12.35.498.749 I slot print_timing: id 0 | task 4178 | graphs reused = 3971 12.35.498.751 I slot print_timing: id 0 | task 4178 | graph reallocs = 0 / 0 (same size) / (changed size) 12.35.498.950 I slot release: id 0 | task 4178 | stop processing: n_tokens = 748, truncated = 0 12.35.512.995 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 748, t_last = 83973598587 12.35.513.083 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 633.330 MiB) 12.35.672.201 I slot launch_slot_: id 0 | task 4318 | processing task, is_child = 0 12.41.853.298 I slot print_timing: id 0 | task 4318 | prompt processing, n_tokens = 529, progress = 0.99, t = 6.18 s / 85.58 tokens per second 12.47.155.477 I slot print_timing: id 0 | task 4318 | prompt eval time = 6788.61 ms / 533 tokens ( 12.74 ms per token, 78.51 tokens per second) 12.47.155.503 I slot print_timing: id 0 | task 4318 | eval time = 4694.62 ms / 47 tokens ( 102.06 ms per token, 9.80 tokens per second) 12.47.155.519 I slot print_timing: id 0 | task 4318 | total time = 11483.24 ms / 580 tokens 12.47.155.524 I slot print_timing: id 0 | task 4318 | graphs reused = 4016 12.47.155.526 I slot print_timing: id 0 | task 4318 | graph reallocs = 0 / 0 (same size) / (changed size) 12.47.155.734 I slot release: id 0 | task 4318 | stop processing: n_tokens = 591, truncated = 0 12.47.168.800 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 591, t_last = 83985255372 12.47.168.873 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 624.202 MiB) 12.47.292.320 I slot launch_slot_: id 0 | task 4369 | processing task, is_child = 0 12.52.698.214 I slot print_timing: id 0 | task 4369 | prompt processing, n_tokens = 476, progress = 0.99, t = 5.41 s / 88.05 tokens per second 12.58.304.671 I slot print_timing: id 0 | task 4369 | prompt eval time = 6008.36 ms / 480 tokens ( 12.52 ms per token, 79.89 tokens per second) 12.58.304.674 I slot print_timing: id 0 | task 4369 | eval time = 5003.97 ms / 52 tokens ( 98.12 ms per token, 10.19 tokens per second) 12.58.304.674 I slot print_timing: id 0 | task 4369 | total time = 11012.33 ms / 532 tokens 12.58.304.685 I slot print_timing: id 0 | task 4369 | graphs reused = 4065 12.58.304.686 I slot print_timing: id 0 | task 4369 | graph reallocs = 0 / 0 (same size) / (changed size) 12.58.304.717 I slot release: id 0 | task 4369 | stop processing: n_tokens = 560, truncated = 0 12.58.309.138 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 83996404355 12.58.309.172 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 626.515 MiB) 12.58.309.184 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 623.076 MiB) 12.58.412.345 I slot launch_slot_: id 0 | task 4424 | processing task, is_child = 0 13.04.955.838 I slot print_timing: id 0 | task 4424 | prompt processing, n_tokens = 563, progress = 0.99, t = 6.54 s / 86.04 tokens per second 13.09.586.812 I slot print_timing: id 0 | task 4424 | prompt eval time = 7149.60 ms / 567 tokens ( 12.61 ms per token, 79.31 tokens per second) 13.09.586.815 I slot print_timing: id 0 | task 4424 | eval time = 4024.85 ms / 42 tokens ( 98.17 ms per token, 10.19 tokens per second) 13.09.586.816 I slot print_timing: id 0 | task 4424 | total time = 11174.45 ms / 609 tokens 13.09.586.816 I slot print_timing: id 0 | task 4424 | graphs reused = 4105 13.09.586.817 I slot print_timing: id 0 | task 4424 | graph reallocs = 0 / 0 (same size) / (changed size) 13.09.586.856 I slot release: id 0 | task 4424 | stop processing: n_tokens = 637, truncated = 0 13.09.591.349 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 84007686493 13.09.591.386 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 628.703 MiB) 13.09.795.452 I slot launch_slot_: id 0 | task 4470 | processing task, is_child = 0 13.15.237.969 I slot print_timing: id 0 | task 4470 | prompt processing, n_tokens = 502, progress = 0.99, t = 5.44 s / 92.24 tokens per second 13.22.407.361 I slot print_timing: id 0 | task 4470 | prompt eval time = 6061.67 ms / 506 tokens ( 11.98 ms per token, 83.48 tokens per second) 13.22.407.370 I slot print_timing: id 0 | task 4470 | eval time = 6550.21 ms / 63 tokens ( 105.65 ms per token, 9.47 tokens per second) 13.22.407.371 I slot print_timing: id 0 | task 4470 | total time = 12611.88 ms / 569 tokens 13.22.407.373 I slot print_timing: id 0 | task 4470 | graphs reused = 4166 13.22.407.374 I slot print_timing: id 0 | task 4470 | graph reallocs = 0 / 0 (same size) / (changed size) 13.22.407.458 I slot release: id 0 | task 4470 | stop processing: n_tokens = 597, truncated = 0 13.22.420.188 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 597, t_last = 84020507095 13.22.420.274 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 788.396 MiB) 13.22.565.281 I slot launch_slot_: id 0 | task 4536 | processing task, is_child = 0 13.27.290.546 I slot print_timing: id 0 | task 4536 | prompt processing, n_tokens = 432, progress = 0.99, t = 4.73 s / 91.42 tokens per second 13.32.012.300 I slot print_timing: id 0 | task 4536 | prompt eval time = 5339.90 ms / 436 tokens ( 12.25 ms per token, 81.65 tokens per second) 13.32.012.310 I slot print_timing: id 0 | task 4536 | eval time = 4107.08 ms / 40 tokens ( 105.31 ms per token, 9.50 tokens per second) 13.32.012.313 I slot print_timing: id 0 | task 4536 | total time = 9446.98 ms / 476 tokens 13.32.012.315 I slot print_timing: id 0 | task 4536 | graphs reused = 4204 13.32.012.317 I slot print_timing: id 0 | task 4536 | graph reallocs = 0 / 0 (same size) / (changed size) 13.32.012.428 I slot release: id 0 | task 4536 | stop processing: n_tokens = 504, truncated = 0 13.32.025.627 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 84030112065 13.32.025.697 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 790.959 MiB) 13.32.147.712 I slot launch_slot_: id 0 | task 4579 | processing task, is_child = 0 13.38.067.418 I slot print_timing: id 0 | task 4579 | prompt processing, n_tokens = 515, progress = 0.99, t = 5.92 s / 87.00 tokens per second 13.44.823.887 I slot print_timing: id 0 | task 4579 | prompt eval time = 6527.86 ms / 519 tokens ( 12.58 ms per token, 79.51 tokens per second) 13.44.823.900 I slot print_timing: id 0 | task 4579 | eval time = 6148.28 ms / 62 tokens ( 100.79 ms per token, 9.92 tokens per second) 13.44.823.903 I slot print_timing: id 0 | task 4579 | total time = 12676.14 ms / 581 tokens 13.44.823.906 I slot print_timing: id 0 | task 4579 | graphs reused = 4264 13.44.823.908 I slot print_timing: id 0 | task 4579 | graph reallocs = 0 / 0 (same size) / (changed size) 13.44.824.110 I slot release: id 0 | task 4579 | stop processing: n_tokens = 609, truncated = 0 13.44.837.049 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 609, t_last = 84042923747 13.44.837.129 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 794.210 MiB) 13.44.992.761 I slot launch_slot_: id 0 | task 4645 | processing task, is_child = 0 13.50.054.239 I slot print_timing: id 0 | task 4645 | prompt processing, n_tokens = 461, progress = 0.99, t = 5.06 s / 91.08 tokens per second 13.55.071.788 I slot print_timing: id 0 | task 4645 | prompt eval time = 5662.58 ms / 465 tokens ( 12.18 ms per token, 82.12 tokens per second) 13.55.071.794 I slot print_timing: id 0 | task 4645 | eval time = 4416.43 ms / 46 tokens ( 98.14 ms per token, 10.19 tokens per second) 13.55.071.794 I slot print_timing: id 0 | task 4645 | total time = 10079.01 ms / 511 tokens 13.55.071.795 I slot print_timing: id 0 | task 4645 | graphs reused = 4307 13.55.071.795 I slot print_timing: id 0 | task 4645 | graph reallocs = 0 / 0 (same size) / (changed size) 13.55.071.836 I slot release: id 0 | task 4645 | stop processing: n_tokens = 542, truncated = 0 13.55.076.377 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 542, t_last = 84053171474 13.55.076.408 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 792.585 MiB) 13.55.134.810 I slot launch_slot_: id 0 | task 4694 | processing task, is_child = 0 13.59.822.785 I slot print_timing: id 0 | task 4694 | prompt processing, n_tokens = 427, progress = 0.99, t = 4.69 s / 91.08 tokens per second 14.04.351.451 I slot print_timing: id 0 | task 4694 | prompt eval time = 5292.94 ms / 431 tokens ( 12.28 ms per token, 81.43 tokens per second) 14.04.351.454 I slot print_timing: id 0 | task 4694 | eval time = 3923.68 ms / 41 tokens ( 98.09 ms per token, 10.19 tokens per second) 14.04.351.455 I slot print_timing: id 0 | task 4694 | total time = 9216.61 ms / 472 tokens 14.04.351.456 I slot print_timing: id 0 | task 4694 | graphs reused = 4346 14.04.351.456 I slot print_timing: id 0 | task 4694 | graph reallocs = 0 / 0 (same size) / (changed size) 14.04.351.502 I slot release: id 0 | task 4694 | stop processing: n_tokens = 503, truncated = 0 14.04.355.953 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 503, t_last = 84062451139 14.04.355.989 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 633.518 MiB) 14.04.356.002 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 790.021 MiB) 14.04.489.311 I slot launch_slot_: id 0 | task 4738 | processing task, is_child = 0 14.09.532.886 I slot print_timing: id 0 | task 4738 | prompt processing, n_tokens = 453, progress = 0.99, t = 5.04 s / 89.82 tokens per second 14.14.357.187 I slot print_timing: id 0 | task 4738 | prompt eval time = 5647.79 ms / 457 tokens ( 12.36 ms per token, 80.92 tokens per second) 14.14.357.190 I slot print_timing: id 0 | task 4738 | eval time = 4220.07 ms / 44 tokens ( 98.14 ms per token, 10.19 tokens per second) 14.14.357.190 I slot print_timing: id 0 | task 4738 | total time = 9867.86 ms / 501 tokens 14.14.357.191 I slot print_timing: id 0 | task 4738 | graphs reused = 4387 14.14.357.191 I slot print_timing: id 0 | task 4738 | graph reallocs = 0 / 0 (same size) / (changed size) 14.14.357.229 I slot release: id 0 | task 4738 | stop processing: n_tokens = 532, truncated = 0 14.14.361.463 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 532, t_last = 84072456866 14.14.361.498 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 794.898 MiB) 14.14.478.329 I slot launch_slot_: id 0 | task 4785 | processing task, is_child = 0 14.19.184.150 I slot print_timing: id 0 | task 4785 | prompt processing, n_tokens = 435, progress = 0.99, t = 4.71 s / 92.44 tokens per second 14.23.807.785 I slot print_timing: id 0 | task 4785 | prompt eval time = 5309.35 ms / 439 tokens ( 12.09 ms per token, 82.68 tokens per second) 14.23.807.791 I slot print_timing: id 0 | task 4785 | eval time = 4020.10 ms / 42 tokens ( 98.05 ms per token, 10.20 tokens per second) 14.23.807.791 I slot print_timing: id 0 | task 4785 | total time = 9329.44 ms / 481 tokens 14.23.807.792 I slot print_timing: id 0 | task 4785 | graphs reused = 4427 14.23.807.792 I slot print_timing: id 0 | task 4785 | graph reallocs = 0 / 0 (same size) / (changed size) 14.23.807.830 I slot release: id 0 | task 4785 | stop processing: n_tokens = 512, truncated = 0 14.23.812.470 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 512, t_last = 84081907467 14.23.812.499 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 785.082 MiB) 14.23.917.882 I slot launch_slot_: id 0 | task 4830 | processing task, is_child = 0 14.30.495.103 I slot print_timing: id 0 | task 4830 | prompt processing, n_tokens = 602, progress = 0.99, t = 6.58 s / 91.53 tokens per second 14.36.905.606 I slot print_timing: id 0 | task 4830 | prompt eval time = 7514.20 ms / 606 tokens ( 12.40 ms per token, 80.65 tokens per second) 14.36.905.619 I slot print_timing: id 0 | task 4830 | eval time = 5473.49 ms / 56 tokens ( 99.52 ms per token, 10.05 tokens per second) 14.36.905.632 I slot print_timing: id 0 | task 4830 | total time = 12987.69 ms / 662 tokens 14.36.905.634 I slot print_timing: id 0 | task 4830 | graphs reused = 4481 14.36.905.643 I slot print_timing: id 0 | task 4830 | graph reallocs = 0 / 0 (same size) / (changed size) 14.36.905.905 I slot release: id 0 | task 4830 | stop processing: n_tokens = 693, truncated = 0 14.36.919.114 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 84095005543 14.36.919.206 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 783.144 MiB) 14.36.919.254 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 937.584 MiB) 14.37.132.525 I slot launch_slot_: id 0 | task 4890 | processing task, is_child = 0 14.42.188.834 I slot print_timing: id 0 | task 4890 | prompt processing, n_tokens = 473, progress = 0.99, t = 5.06 s / 93.55 tokens per second 14.47.039.672 I slot print_timing: id 0 | task 4890 | prompt eval time = 5985.76 ms / 477 tokens ( 12.55 ms per token, 79.69 tokens per second) 14.47.039.677 I slot print_timing: id 0 | task 4890 | eval time = 3921.37 ms / 41 tokens ( 98.03 ms per token, 10.20 tokens per second) 14.47.039.678 I slot print_timing: id 0 | task 4890 | total time = 9907.13 ms / 518 tokens 14.47.039.679 I slot print_timing: id 0 | task 4890 | graphs reused = 4519 14.47.039.679 I slot print_timing: id 0 | task 4890 | graph reallocs = 0 / 0 (same size) / (changed size) 14.47.039.729 I slot release: id 0 | task 4890 | stop processing: n_tokens = 549, truncated = 0 14.47.045.214 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 84105139366 14.47.045.243 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 785.457 MiB) 14.47.183.225 I slot launch_slot_: id 0 | task 4934 | processing task, is_child = 0 14.51.172.372 I slot print_timing: id 0 | task 4934 | prompt processing, n_tokens = 782, progress = 0.93, t = 3.99 s / 196.03 tokens per second 14.56.581.266 I slot print_timing: id 0 | task 4934 | prompt processing, n_tokens = 841, progress = 1.00, t = 9.40 s / 89.49 tokens per second 15.08.016.672 I slot print_timing: id 0 | task 4934 | n_gen = 100, tg = 9.47 t/s, tg_3s = 9.56 t/s 15.11.086.179 I slot print_timing: id 0 | task 4934 | n_gen = 129, tg = 9.46 t/s, tg_3s = 9.45 t/s 15.14.145.165 I slot print_timing: id 0 | task 4934 | n_gen = 158, tg = 9.47 t/s, tg_3s = 9.48 t/s 15.17.206.005 I slot print_timing: id 0 | task 4934 | n_gen = 187, tg = 9.47 t/s, tg_3s = 9.47 t/s 15.17.412.881 I slot print_timing: id 0 | task 4934 | prompt eval time = 10376.15 ms / 845 tokens ( 12.28 ms per token, 81.44 tokens per second) 15.17.412.890 I slot print_timing: id 0 | task 4934 | eval time = 19853.48 ms / 189 tokens ( 105.60 ms per token, 9.47 tokens per second) 15.17.412.891 I slot print_timing: id 0 | task 4934 | total time = 30229.62 ms / 1034 tokens 15.17.412.892 I slot print_timing: id 0 | task 4934 | graphs reused = 4705 15.17.412.893 I slot print_timing: id 0 | task 4934 | graph reallocs = 0 / 0 (same size) / (changed size) 15.17.413.036 I slot release: id 0 | task 4934 | stop processing: n_tokens = 1065, truncated = 0 15.17.425.455 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1065, t_last = 84135512674 15.17.425.575 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 779.643 MiB) 15.17.638.039 I slot launch_slot_: id 0 | task 5127 | processing task, is_child = 0 15.22.690.714 I slot print_timing: id 0 | task 5127 | prompt processing, n_tokens = 455, progress = 0.99, t = 5.05 s / 90.05 tokens per second 15.28.055.056 I slot print_timing: id 0 | task 5127 | prompt eval time = 6002.17 ms / 459 tokens ( 13.08 ms per token, 76.47 tokens per second) 15.28.055.075 I slot print_timing: id 0 | task 5127 | eval time = 4414.78 ms / 43 tokens ( 105.11 ms per token, 9.51 tokens per second) 15.28.055.077 I slot print_timing: id 0 | task 5127 | total time = 10416.95 ms / 502 tokens 15.28.055.123 I slot print_timing: id 0 | task 5127 | graphs reused = 4745 15.28.055.141 I slot print_timing: id 0 | task 5127 | graph reallocs = 0 / 0 (same size) / (changed size) 15.28.055.576 I slot release: id 0 | task 5127 | stop processing: n_tokens = 533, truncated = 0 15.28.072.417 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 533, t_last = 84146155213 15.28.072.500 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 935.834 MiB) 15.28.214.028 I slot launch_slot_: id 0 | task 5173 | processing task, is_child = 0 15.35.477.838 I slot print_timing: id 0 | task 5173 | prompt processing, n_tokens = 666, progress = 0.99, t = 7.26 s / 91.69 tokens per second 15.41.290.692 I slot print_timing: id 0 | task 5173 | prompt eval time = 8221.71 ms / 670 tokens ( 12.27 ms per token, 81.49 tokens per second) 15.41.290.705 I slot print_timing: id 0 | task 5173 | eval time = 4854.92 ms / 47 tokens ( 105.54 ms per token, 9.47 tokens per second) 15.41.290.708 I slot print_timing: id 0 | task 5173 | total time = 13076.63 ms / 717 tokens 15.41.290.710 I slot print_timing: id 0 | task 5173 | graphs reused = 4790 15.41.290.712 I slot print_timing: id 0 | task 5173 | graph reallocs = 0 / 0 (same size) / (changed size) 15.41.291.063 I slot release: id 0 | task 5173 | stop processing: n_tokens = 748, truncated = 0 15.41.306.850 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 748, t_last = 84159390700 15.41.306.939 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 931.645 MiB) 15.41.494.381 I slot launch_slot_: id 0 | task 5224 | processing task, is_child = 0 15.44.760.104 I slot print_timing: id 0 | task 5224 | prompt processing, n_tokens = 731, progress = 0.95, t = 3.27 s / 223.84 tokens per second 15.50.168.274 I slot print_timing: id 0 | task 5224 | prompt processing, n_tokens = 771, progress = 1.00, t = 8.67 s / 88.89 tokens per second 15.57.474.404 I slot print_timing: id 0 | task 5224 | prompt eval time = 9612.28 ms / 775 tokens ( 12.40 ms per token, 80.63 tokens per second) 15.57.474.410 I slot print_timing: id 0 | task 5224 | eval time = 6367.73 ms / 63 tokens ( 102.71 ms per token, 9.74 tokens per second) 15.57.474.410 I slot print_timing: id 0 | task 5224 | total time = 15980.01 ms / 838 tokens 15.57.474.411 I slot print_timing: id 0 | task 5224 | graphs reused = 4851 15.57.474.411 I slot print_timing: id 0 | task 5224 | graph reallocs = 0 / 0 (same size) / (changed size) 15.57.474.500 I slot release: id 0 | task 5224 | stop processing: n_tokens = 869, truncated = 0 15.57.480.342 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 869, t_last = 84175574137 15.57.480.383 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 929.206 MiB) 15.57.693.384 I slot launch_slot_: id 0 | task 5291 | processing task, is_child = 0 16.03.891.215 I slot print_timing: id 0 | task 5291 | prompt processing, n_tokens = 569, progress = 0.99, t = 6.20 s / 91.81 tokens per second 16.11.697.227 I slot print_timing: id 0 | task 5291 | prompt eval time = 7134.35 ms / 573 tokens ( 12.45 ms per token, 80.32 tokens per second) 16.11.697.232 I slot print_timing: id 0 | task 5291 | eval time = 6869.48 ms / 71 tokens ( 98.14 ms per token, 10.19 tokens per second) 16.11.697.233 I slot print_timing: id 0 | task 5291 | total time = 14003.83 ms / 644 tokens 16.11.697.233 I slot print_timing: id 0 | task 5291 | graphs reused = 4920 16.11.697.234 I slot print_timing: id 0 | task 5291 | graph reallocs = 0 / 0 (same size) / (changed size) 16.11.697.296 I slot release: id 0 | task 5291 | stop processing: n_tokens = 675, truncated = 0 16.11.702.059 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 675, t_last = 84189796933 16.11.702.094 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 931.019 MiB) 16.11.702.108 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 929.769 MiB) 16.11.878.058 I slot launch_slot_: id 0 | task 5366 | processing task, is_child = 0 16.16.919.072 I slot print_timing: id 0 | task 5366 | prompt processing, n_tokens = 457, progress = 0.99, t = 5.04 s / 90.66 tokens per second 16.24.040.651 I slot print_timing: id 0 | task 5366 | prompt eval time = 5975.91 ms / 461 tokens ( 12.96 ms per token, 77.14 tokens per second) 16.24.040.665 I slot print_timing: id 0 | task 5366 | eval time = 6186.65 ms / 64 tokens ( 98.20 ms per token, 10.18 tokens per second) 16.24.040.667 I slot print_timing: id 0 | task 5366 | total time = 12162.56 ms / 525 tokens 16.24.040.670 I slot print_timing: id 0 | task 5366 | graphs reused = 4981 16.24.040.675 I slot print_timing: id 0 | task 5366 | graph reallocs = 0 / 0 (same size) / (changed size) 16.24.040.874 I slot release: id 0 | task 5366 | stop processing: n_tokens = 556, truncated = 0 16.24.055.901 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 556, t_last = 84202140512 16.24.055.983 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1090.712 MiB) 16.24.218.675 I slot launch_slot_: id 0 | task 5433 | processing task, is_child = 0 16.31.139.915 I slot print_timing: id 0 | task 5433 | prompt processing, n_tokens = 605, progress = 0.99, t = 6.92 s / 87.41 tokens per second 16.42.193.571 I slot print_timing: id 0 | task 5433 | n_gen = 100, tg = 9.50 t/s, tg_3s = 9.59 t/s 16.42.405.941 I slot print_timing: id 0 | task 5433 | prompt eval time = 7551.42 ms / 609 tokens ( 12.40 ms per token, 80.65 tokens per second) 16.42.405.945 I slot print_timing: id 0 | task 5433 | eval time = 10635.83 ms / 102 tokens ( 105.31 ms per token, 9.50 tokens per second) 16.42.405.947 I slot print_timing: id 0 | task 5433 | total time = 18187.25 ms / 711 tokens 16.42.405.948 I slot print_timing: id 0 | task 5433 | graphs reused = 5081 16.42.405.949 I slot print_timing: id 0 | task 5433 | graph reallocs = 0 / 0 (same size) / (changed size) 16.42.406.101 I slot release: id 0 | task 5433 | stop processing: n_tokens = 742, truncated = 0 16.42.421.461 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 742, t_last = 84220505738 16.42.421.558 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 932.082 MiB) 16.42.708.492 I slot launch_slot_: id 0 | task 5539 | processing task, is_child = 0 16.45.990.918 I slot print_timing: id 0 | task 5539 | prompt processing, n_tokens = 758, progress = 0.96, t = 3.28 s / 230.93 tokens per second 16.51.786.536 I slot print_timing: id 0 | task 5539 | prompt processing, n_tokens = 787, progress = 1.00, t = 9.08 s / 86.69 tokens per second 16.58.290.349 I slot print_timing: id 0 | task 5539 | prompt eval time = 9687.33 ms / 791 tokens ( 12.25 ms per token, 81.65 tokens per second) 16.58.290.352 I slot print_timing: id 0 | task 5539 | eval time = 5894.51 ms / 61 tokens ( 98.24 ms per token, 10.18 tokens per second) 16.58.290.352 I slot print_timing: id 0 | task 5539 | total time = 15581.84 ms / 852 tokens 16.58.290.358 I slot print_timing: id 0 | task 5539 | graphs reused = 5140 16.58.290.359 I slot print_timing: id 0 | task 5539 | graph reallocs = 0 / 0 (same size) / (changed size) 16.58.290.428 I slot release: id 0 | task 5539 | stop processing: n_tokens = 883, truncated = 0 16.58.294.860 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 883, t_last = 84236390066 16.58.294.902 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1113.970 MiB) 16.58.441.061 I slot launch_slot_: id 0 | task 5604 | processing task, is_child = 0 17.04.642.436 I slot print_timing: id 0 | task 5604 | prompt processing, n_tokens = 529, progress = 0.99, t = 6.20 s / 85.30 tokens per second 17.10.645.700 I slot print_timing: id 0 | task 5604 | prompt eval time = 6809.41 ms / 533 tokens ( 12.78 ms per token, 78.27 tokens per second) 17.10.645.702 I slot print_timing: id 0 | task 5604 | eval time = 5395.21 ms / 56 tokens ( 98.09 ms per token, 10.19 tokens per second) 17.10.645.704 I slot print_timing: id 0 | task 5604 | total time = 12204.62 ms / 589 tokens 17.10.645.704 I slot print_timing: id 0 | task 5604 | graphs reused = 5194 17.10.645.704 I slot print_timing: id 0 | task 5604 | graph reallocs = 0 / 0 (same size) / (changed size) 17.10.645.758 I slot release: id 0 | task 5604 | stop processing: n_tokens = 677, truncated = 0 17.10.650.416 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 677, t_last = 84248745396 17.10.810.812 I slot launch_slot_: id 0 | task 5664 | processing task, is_child = 0 17.17.006.388 I slot print_timing: id 0 | task 5664 | prompt processing, n_tokens = 562, progress = 0.99, t = 6.20 s / 90.71 tokens per second 17.22.368.396 I slot print_timing: id 0 | task 5664 | prompt eval time = 7127.36 ms / 566 tokens ( 12.59 ms per token, 79.41 tokens per second) 17.22.368.399 I slot print_timing: id 0 | task 5664 | eval time = 4430.21 ms / 46 tokens ( 98.45 ms per token, 10.16 tokens per second) 17.22.368.399 I slot print_timing: id 0 | task 5664 | total time = 11557.57 ms / 612 tokens 17.22.368.400 I slot print_timing: id 0 | task 5664 | graphs reused = 5238 17.22.368.400 I slot print_timing: id 0 | task 5664 | graph reallocs = 0 / 0 (same size) / (changed size) 17.22.368.457 I slot release: id 0 | task 5664 | stop processing: n_tokens = 643, truncated = 0 17.22.372.530 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 643, t_last = 84260468094 17.22.372.572 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 931.082 MiB) 17.22.527.603 I slot launch_slot_: id 0 | task 5714 | processing task, is_child = 0 17.27.571.968 I slot print_timing: id 0 | task 5714 | prompt processing, n_tokens = 439, progress = 0.99, t = 5.04 s / 87.03 tokens per second 17.32.297.742 I slot print_timing: id 0 | task 5714 | prompt eval time = 5646.53 ms / 443 tokens ( 12.75 ms per token, 78.46 tokens per second) 17.32.297.745 I slot print_timing: id 0 | task 5714 | eval time = 4123.60 ms / 43 tokens ( 98.18 ms per token, 10.19 tokens per second) 17.32.297.745 I slot print_timing: id 0 | task 5714 | total time = 9770.13 ms / 486 tokens 17.32.297.746 I slot print_timing: id 0 | task 5714 | graphs reused = 5278 17.32.297.746 I slot print_timing: id 0 | task 5714 | graph reallocs = 0 / 0 (same size) / (changed size) 17.32.297.786 I slot release: id 0 | task 5714 | stop processing: n_tokens = 517, truncated = 0 17.32.302.234 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 517, t_last = 84270397423 17.32.302.263 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1094.150 MiB) 17.32.430.415 I slot launch_slot_: id 0 | task 5760 | processing task, is_child = 0 17.37.493.271 I slot print_timing: id 0 | task 5760 | prompt processing, n_tokens = 483, progress = 0.99, t = 5.06 s / 95.40 tokens per second 17.44.705.584 I slot print_timing: id 0 | task 5760 | prompt eval time = 5999.31 ms / 487 tokens ( 12.32 ms per token, 81.18 tokens per second) 17.44.705.587 I slot print_timing: id 0 | task 5760 | eval time = 6275.84 ms / 65 tokens ( 98.06 ms per token, 10.20 tokens per second) 17.44.705.587 I slot print_timing: id 0 | task 5760 | total time = 12275.15 ms / 552 tokens 17.44.705.588 I slot print_timing: id 0 | task 5760 | graphs reused = 5341 17.44.705.588 I slot print_timing: id 0 | task 5760 | graph reallocs = 0 / 0 (same size) / (changed size) 17.44.705.634 I slot release: id 0 | task 5760 | stop processing: n_tokens = 583, truncated = 0 17.44.710.374 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 583, t_last = 84282805271 17.44.710.412 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1101.716 MiB) 17.44.840.829 I slot launch_slot_: id 0 | task 5828 | processing task, is_child = 0 17.50.256.400 I slot print_timing: id 0 | task 5828 | prompt processing, n_tokens = 503, progress = 0.99, t = 5.42 s / 92.88 tokens per second 17.55.375.776 I slot print_timing: id 0 | task 5828 | prompt eval time = 6022.98 ms / 507 tokens ( 11.88 ms per token, 84.18 tokens per second) 17.55.375.779 I slot print_timing: id 0 | task 5828 | eval time = 4511.96 ms / 47 tokens ( 98.09 ms per token, 10.20 tokens per second) 17.55.375.779 I slot print_timing: id 0 | task 5828 | total time = 10534.93 ms / 554 tokens 17.55.375.779 I slot print_timing: id 0 | task 5828 | graphs reused = 5386 17.55.375.780 I slot print_timing: id 0 | task 5828 | graph reallocs = 0 / 0 (same size) / (changed size) 17.55.375.827 I slot release: id 0 | task 5828 | stop processing: n_tokens = 585, truncated = 0 17.55.381.258 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 585, t_last = 84293475464 17.55.381.293 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 932.520 MiB) 17.55.474.548 I slot launch_slot_: id 0 | task 5878 | processing task, is_child = 0 18.02.754.516 I slot print_timing: id 0 | task 5878 | prompt processing, n_tokens = 629, progress = 0.99, t = 7.28 s / 86.40 tokens per second 18.11.510.730 I slot print_timing: id 0 | task 5878 | prompt eval time = 7881.54 ms / 633 tokens ( 12.45 ms per token, 80.31 tokens per second) 18.11.510.736 I slot print_timing: id 0 | task 5878 | eval time = 8154.63 ms / 84 tokens ( 98.25 ms per token, 10.18 tokens per second) 18.11.510.736 I slot print_timing: id 0 | task 5878 | total time = 16036.17 ms / 717 tokens 18.11.510.737 I slot print_timing: id 0 | task 5878 | graphs reused = 5468 18.11.510.737 I slot print_timing: id 0 | task 5878 | graph reallocs = 0 / 0 (same size) / (changed size) 18.11.510.798 I slot release: id 0 | task 5878 | stop processing: n_tokens = 748, truncated = 0 18.11.515.192 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 748, t_last = 84309610435 18.11.515.229 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1093.775 MiB) 18.11.587.221 I slot launch_slot_: id 0 | task 5966 | processing task, is_child = 0 18.18.104.655 I slot print_timing: id 0 | task 5966 | prompt processing, n_tokens = 567, progress = 0.99, t = 6.52 s / 87.00 tokens per second 18.23.227.557 I slot print_timing: id 0 | task 5966 | prompt eval time = 7122.31 ms / 571 tokens ( 12.47 ms per token, 80.17 tokens per second) 18.23.227.563 I slot print_timing: id 0 | task 5966 | eval time = 4518.02 ms / 47 tokens ( 98.22 ms per token, 10.18 tokens per second) 18.23.227.564 I slot print_timing: id 0 | task 5966 | total time = 11640.33 ms / 618 tokens 18.23.227.564 I slot print_timing: id 0 | task 5966 | graphs reused = 5513 18.23.227.565 I slot print_timing: id 0 | task 5966 | graph reallocs = 0 / 0 (same size) / (changed size) 18.23.227.609 I slot release: id 0 | task 5966 | stop processing: n_tokens = 649, truncated = 0 18.23.233.637 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 649, t_last = 84321327246 18.23.233.670 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1102.591 MiB) 18.23.260.818 I slot launch_slot_: id 0 | task 6017 | processing task, is_child = 0 18.26.536.057 I slot print_timing: id 0 | task 6017 | prompt processing, n_tokens = 775, progress = 0.97, t = 3.28 s / 236.63 tokens per second 18.32.287.351 I slot print_timing: id 0 | task 6017 | prompt processing, n_tokens = 794, progress = 1.00, t = 9.03 s / 87.96 tokens per second 18.37.124.209 I slot print_timing: id 0 | task 6017 | prompt eval time = 9635.01 ms / 798 tokens ( 12.07 ms per token, 82.82 tokens per second) 18.37.124.211 I slot print_timing: id 0 | task 6017 | eval time = 4228.37 ms / 44 tokens ( 98.33 ms per token, 10.17 tokens per second) 18.37.124.211 I slot print_timing: id 0 | task 6017 | total time = 13863.38 ms / 842 tokens 18.37.124.212 I slot print_timing: id 0 | task 6017 | graphs reused = 5555 18.37.124.212 I slot print_timing: id 0 | task 6017 | graph reallocs = 0 / 0 (same size) / (changed size) 18.37.124.280 I slot release: id 0 | task 6017 | stop processing: n_tokens = 873, truncated = 0 18.37.128.786 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 873, t_last = 84335223918 18.37.128.826 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1239.337 MiB) 18.37.155.368 I slot launch_slot_: id 0 | task 6065 | processing task, is_child = 0 18.43.674.916 I slot print_timing: id 0 | task 6065 | prompt processing, n_tokens = 568, progress = 0.99, t = 6.52 s / 87.12 tokens per second 18.48.408.536 I slot print_timing: id 0 | task 6065 | prompt eval time = 7126.54 ms / 572 tokens ( 12.46 ms per token, 80.26 tokens per second) 18.48.408.542 I slot print_timing: id 0 | task 6065 | eval time = 4126.62 ms / 43 tokens ( 98.25 ms per token, 10.18 tokens per second) 18.48.408.542 I slot print_timing: id 0 | task 6065 | total time = 11253.16 ms / 615 tokens 18.48.408.543 I slot print_timing: id 0 | task 6065 | graphs reused = 5596 18.48.408.543 I slot print_timing: id 0 | task 6065 | graph reallocs = 0 / 0 (same size) / (changed size) 18.48.408.582 I slot release: id 0 | task 6065 | stop processing: n_tokens = 646, truncated = 0 18.48.413.304 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 646, t_last = 84346508219 18.48.413.337 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1087.585 MiB) 18.48.446.135 I slot launch_slot_: id 0 | task 6112 | processing task, is_child = 0 18.55.646.992 I slot print_timing: id 0 | task 6112 | prompt processing, n_tokens = 609, progress = 0.99, t = 7.20 s / 84.57 tokens per second 19.00.969.200 I slot print_timing: id 0 | task 6112 | prompt eval time = 7806.55 ms / 613 tokens ( 12.73 ms per token, 78.52 tokens per second) 19.00.969.203 I slot print_timing: id 0 | task 6112 | eval time = 4716.51 ms / 49 tokens ( 98.26 ms per token, 10.18 tokens per second) 19.00.969.204 I slot print_timing: id 0 | task 6112 | total time = 12523.06 ms / 662 tokens 19.00.969.205 I slot print_timing: id 0 | task 6112 | graphs reused = 5643 19.00.969.205 I slot print_timing: id 0 | task 6112 | graph reallocs = 0 / 0 (same size) / (changed size) 19.00.969.258 I slot release: id 0 | task 6112 | stop processing: n_tokens = 693, truncated = 0 19.00.974.916 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 84359068895 19.00.974.957 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 930.081 MiB) 19.01.011.797 I slot launch_slot_: id 0 | task 6165 | processing task, is_child = 0 19.07.534.149 I slot print_timing: id 0 | task 6165 | prompt processing, n_tokens = 576, progress = 0.99, t = 6.52 s / 88.31 tokens per second 19.14.373.750 I slot print_timing: id 0 | task 6165 | prompt eval time = 7126.09 ms / 580 tokens ( 12.29 ms per token, 81.39 tokens per second) 19.14.373.757 I slot print_timing: id 0 | task 6165 | eval time = 6235.85 ms / 64 tokens ( 98.98 ms per token, 10.10 tokens per second) 19.14.373.757 I slot print_timing: id 0 | task 6165 | total time = 13361.94 ms / 644 tokens 19.14.373.758 I slot print_timing: id 0 | task 6165 | graphs reused = 5705 19.14.373.758 I slot print_timing: id 0 | task 6165 | graph reallocs = 0 / 0 (same size) / (changed size) 19.14.373.837 I slot release: id 0 | task 6165 | stop processing: n_tokens = 675, truncated = 0 19.14.381.431 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 675, t_last = 84372473474 19.14.381.469 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 934.208 MiB) 19.14.483.965 I slot launch_slot_: id 0 | task 6233 | processing task, is_child = 0 19.22.810.343 I slot print_timing: id 0 | task 6233 | prompt processing, n_tokens = 712, progress = 0.99, t = 8.33 s / 85.51 tokens per second 19.30.203.954 I slot print_timing: id 0 | task 6233 | prompt eval time = 8929.25 ms / 716 tokens ( 12.47 ms per token, 80.19 tokens per second) 19.30.203.960 I slot print_timing: id 0 | task 6233 | eval time = 6790.73 ms / 70 tokens ( 98.42 ms per token, 10.16 tokens per second) 19.30.203.960 I slot print_timing: id 0 | task 6233 | total time = 15719.98 ms / 786 tokens 19.30.203.960 I slot print_timing: id 0 | task 6233 | graphs reused = 5772 19.30.203.961 I slot print_timing: id 0 | task 6233 | graph reallocs = 0 / 0 (same size) / (changed size) 19.30.204.015 I slot release: id 0 | task 6233 | stop processing: n_tokens = 817, truncated = 0 19.30.211.050 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 817, t_last = 84388303652 19.30.211.091 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 934.333 MiB) 19.30.311.909 I slot launch_slot_: id 0 | task 6307 | processing task, is_child = 0 19.33.597.920 I slot print_timing: id 0 | task 6307 | prompt processing, n_tokens = 755, progress = 0.95, t = 3.29 s / 229.76 tokens per second 19.39.005.703 I slot print_timing: id 0 | task 6307 | prompt processing, n_tokens = 795, progress = 1.00, t = 8.69 s / 91.44 tokens per second 19.49.687.627 I slot print_timing: id 0 | task 6307 | n_gen = 100, tg = 10.16 t/s, tg_3s = 10.27 t/s 19.51.853.115 I slot print_timing: id 0 | task 6307 | prompt eval time = 9633.89 ms / 799 tokens ( 12.06 ms per token, 82.94 tokens per second) 19.51.853.118 I slot print_timing: id 0 | task 6307 | eval time = 11907.30 ms / 122 tokens ( 98.41 ms per token, 10.16 tokens per second) 19.51.853.119 I slot print_timing: id 0 | task 6307 | total time = 21541.19 ms / 921 tokens 19.51.853.119 I slot print_timing: id 0 | task 6307 | graphs reused = 5892 19.51.853.120 I slot print_timing: id 0 | task 6307 | graph reallocs = 0 / 0 (same size) / (changed size) 19.51.853.172 I slot release: id 0 | task 6307 | stop processing: n_tokens = 952, truncated = 0 19.51.858.326 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 952, t_last = 84409952809 19.51.858.369 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1094.150 MiB) 19.51.910.887 I slot launch_slot_: id 0 | task 6433 | processing task, is_child = 0 19.55.540.636 I slot print_timing: id 0 | task 6433 | prompt processing, n_tokens = 357, progress = 0.99, t = 3.63 s / 98.35 tokens per second 20.06.193.879 I slot print_timing: id 0 | task 6433 | n_gen = 100, tg = 10.19 t/s, tg_3s = 10.29 t/s 20.07.371.353 I slot print_timing: id 0 | task 6433 | prompt eval time = 4566.65 ms / 361 tokens ( 12.65 ms per token, 79.05 tokens per second) 20.07.371.359 I slot print_timing: id 0 | task 6433 | eval time = 10893.81 ms / 112 tokens ( 98.14 ms per token, 10.19 tokens per second) 20.07.371.359 I slot print_timing: id 0 | task 6433 | total time = 15460.45 ms / 473 tokens 20.07.371.360 I slot print_timing: id 0 | task 6433 | graphs reused = 6002 20.07.371.360 I slot print_timing: id 0 | task 6433 | graph reallocs = 0 / 0 (same size) / (changed size) 20.07.371.406 I slot release: id 0 | task 6433 | stop processing: n_tokens = 504, truncated = 0 20.07.375.857 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 84425471043 20.07.375.885 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1087.961 MiB) 20.07.444.221 I slot launch_slot_: id 0 | task 6548 | processing task, is_child = 0 20.11.440.088 I slot print_timing: id 0 | task 6548 | prompt processing, n_tokens = 377, progress = 0.99, t = 4.00 s / 94.35 tokens per second 20.22.104.587 I slot print_timing: id 0 | task 6548 | n_gen = 100, tg = 10.19 t/s, tg_3s = 10.29 t/s 20.22.892.369 I slot print_timing: id 0 | task 6548 | prompt eval time = 4941.52 ms / 381 tokens ( 12.97 ms per token, 77.10 tokens per second) 20.22.892.374 I slot print_timing: id 0 | task 6548 | eval time = 10506.62 ms / 108 tokens ( 98.19 ms per token, 10.18 tokens per second) 20.22.892.374 I slot print_timing: id 0 | task 6548 | total time = 15448.13 ms / 489 tokens 20.22.892.374 I slot print_timing: id 0 | task 6548 | graphs reused = 6107 20.22.892.375 I slot print_timing: id 0 | task 6548 | graph reallocs = 0 / 0 (same size) / (changed size) 20.22.892.424 I slot release: id 0 | task 6548 | stop processing: n_tokens = 520, truncated = 0 20.22.897.618 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 84440992061 20.22.897.649 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1101.966 MiB) 20.22.920.893 I slot launch_slot_: id 0 | task 6659 | processing task, is_child = 0 20.26.503.704 I slot print_timing: id 0 | task 6659 | prompt processing, n_tokens = 361, progress = 0.99, t = 3.58 s / 100.76 tokens per second 20.37.155.866 I slot print_timing: id 0 | task 6659 | n_gen = 100, tg = 10.19 t/s, tg_3s = 10.29 t/s 20.39.514.466 I slot print_timing: id 0 | task 6659 | prompt eval time = 4520.94 ms / 365 tokens ( 12.39 ms per token, 80.74 tokens per second) 20.39.514.469 I slot print_timing: id 0 | task 6659 | eval time = 12072.62 ms / 124 tokens ( 98.15 ms per token, 10.19 tokens per second) 20.39.514.469 I slot print_timing: id 0 | task 6659 | total time = 16593.56 ms / 489 tokens 20.39.514.470 I slot print_timing: id 0 | task 6659 | graphs reused = 6228 20.39.514.470 I slot print_timing: id 0 | task 6659 | graph reallocs = 0 / 0 (same size) / (changed size) 20.39.514.513 I slot release: id 0 | task 6659 | stop processing: n_tokens = 520, truncated = 0 20.39.519.336 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 84457614150 20.39.519.372 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1087.773 MiB) 20.39.595.126 I slot launch_slot_: id 0 | task 6786 | processing task, is_child = 0 20.43.202.378 I slot print_timing: id 0 | task 6786 | prompt processing, n_tokens = 329, progress = 0.99, t = 3.61 s / 91.21 tokens per second 20.53.858.120 I slot print_timing: id 0 | task 6786 | n_gen = 100, tg = 10.19 t/s, tg_3s = 10.29 t/s 20.54.544.615 I slot print_timing: id 0 | task 6786 | prompt eval time = 4544.03 ms / 333 tokens ( 13.65 ms per token, 73.28 tokens per second) 20.54.544.621 I slot print_timing: id 0 | task 6786 | eval time = 10405.45 ms / 107 tokens ( 98.16 ms per token, 10.19 tokens per second) 20.54.544.621 I slot print_timing: id 0 | task 6786 | total time = 14949.48 ms / 440 tokens 20.54.544.622 I slot print_timing: id 0 | task 6786 | graphs reused = 6333 20.54.544.622 I slot print_timing: id 0 | task 6786 | graph reallocs = 0 / 0 (same size) / (changed size) 20.54.544.658 I slot release: id 0 | task 6786 | stop processing: n_tokens = 471, truncated = 0 20.54.548.884 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 471, t_last = 84472644295 20.54.624.359 I slot launch_slot_: id 0 | task 6896 | processing task, is_child = 0 20.58.932.241 I slot print_timing: id 0 | task 6896 | prompt processing, n_tokens = 399, progress = 0.99, t = 4.31 s / 92.62 tokens per second 21.09.584.433 I slot print_timing: id 0 | task 6896 | n_gen = 100, tg = 10.18 t/s, tg_3s = 10.29 t/s 21.12.624.035 I slot print_timing: id 0 | task 6896 | n_gen = 131, tg = 10.19 t/s, tg_3s = 10.20 t/s 21.14.880.741 I slot print_timing: id 0 | task 6896 | prompt eval time = 5239.55 ms / 403 tokens ( 13.00 ms per token, 76.91 tokens per second) 21.14.880.744 I slot print_timing: id 0 | task 6896 | eval time = 15016.82 ms / 154 tokens ( 98.15 ms per token, 10.19 tokens per second) 21.14.880.744 I slot print_timing: id 0 | task 6896 | total time = 20256.37 ms / 557 tokens 21.14.880.745 I slot print_timing: id 0 | task 6896 | graphs reused = 6484 21.14.880.745 I slot print_timing: id 0 | task 6896 | graph reallocs = 0 / 0 (same size) / (changed size) 21.14.880.771 I slot release: id 0 | task 6896 | stop processing: n_tokens = 588, truncated = 0 21.14.885.756 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 588, t_last = 84492980408 21.14.885.794 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1090.712 MiB) 21.14.983.532 I slot launch_slot_: id 0 | task 7053 | processing task, is_child = 0 21.18.975.851 I slot print_timing: id 0 | task 7053 | prompt processing, n_tokens = 407, progress = 0.99, t = 3.99 s / 101.95 tokens per second 21.30.010.230 I slot print_timing: id 0 | task 7053 | n_gen = 100, tg = 10.18 t/s, tg_3s = 10.29 t/s 21.33.052.156 I slot print_timing: id 0 | task 7053 | n_gen = 131, tg = 10.19 t/s, tg_3s = 10.19 t/s 21.36.094.180 I slot print_timing: id 0 | task 7053 | n_gen = 162, tg = 10.19 t/s, tg_3s = 10.19 t/s 21.39.137.846 I slot print_timing: id 0 | task 7053 | n_gen = 193, tg = 10.19 t/s, tg_3s = 10.19 t/s 21.40.021.336 I slot print_timing: id 0 | task 7053 | prompt eval time = 5305.60 ms / 411 tokens ( 12.91 ms per token, 77.47 tokens per second) 21.40.021.339 I slot print_timing: id 0 | task 7053 | eval time = 19732.19 ms / 202 tokens ( 98.17 ms per token, 10.19 tokens per second) 21.40.021.339 I slot print_timing: id 0 | task 7053 | total time = 25037.79 ms / 613 tokens 21.40.021.339 I slot print_timing: id 0 | task 7053 | graphs reused = 6683 21.40.021.340 I slot print_timing: id 0 | task 7053 | graph reallocs = 0 / 0 (same size) / (changed size) 21.40.021.365 I slot release: id 0 | task 7053 | stop processing: n_tokens = 644, truncated = 0 21.40.026.281 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 644, t_last = 84518121002 21.40.026.315 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1089.586 MiB) 21.40.062.231 I slot launch_slot_: id 0 | task 7258 | processing task, is_child = 0 21.44.732.797 I slot print_timing: id 0 | task 7258 | prompt processing, n_tokens = 486, progress = 0.99, t = 4.67 s / 104.06 tokens per second 21.56.094.668 I slot print_timing: id 0 | task 7258 | n_gen = 100, tg = 10.19 t/s, tg_3s = 10.29 t/s 21.59.136.384 I slot print_timing: id 0 | task 7258 | n_gen = 131, tg = 10.19 t/s, tg_3s = 10.19 t/s 22.02.183.560 I slot print_timing: id 0 | task 7258 | n_gen = 162, tg = 10.18 t/s, tg_3s = 10.17 t/s 22.05.228.397 I slot print_timing: id 0 | task 7258 | n_gen = 193, tg = 10.18 t/s, tg_3s = 10.18 t/s 22.08.274.175 I slot print_timing: id 0 | task 7258 | n_gen = 224, tg = 10.18 t/s, tg_3s = 10.18 t/s 22.09.453.613 I slot print_timing: id 0 | task 7258 | prompt eval time = 6312.84 ms / 490 tokens ( 12.88 ms per token, 77.62 tokens per second) 22.09.453.618 I slot print_timing: id 0 | task 7258 | eval time = 23078.52 ms / 236 tokens ( 98.21 ms per token, 10.18 tokens per second) 22.09.453.620 I slot print_timing: id 0 | task 7258 | total time = 29391.37 ms / 726 tokens 22.09.453.620 I slot print_timing: id 0 | task 7258 | graphs reused = 6917 22.09.453.621 I slot print_timing: id 0 | task 7258 | graph reallocs = 0 / 0 (same size) / (changed size) 22.09.453.664 I slot release: id 0 | task 7258 | stop processing: n_tokens = 757, truncated = 0 22.09.458.649 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 757, t_last = 84547553301 22.09.458.689 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1098.464 MiB) 22.09.484.989 I slot launch_slot_: id 0 | task 7497 | processing task, is_child = 0 22.12.754.349 I slot print_timing: id 0 | task 7497 | prompt processing, n_tokens = 340, progress = 0.99, t = 3.27 s / 104.00 tokens per second 22.23.780.974 I slot print_timing: id 0 | task 7497 | n_gen = 100, tg = 10.18 t/s, tg_3s = 10.29 t/s 22.26.821.895 I slot print_timing: id 0 | task 7497 | n_gen = 131, tg = 10.19 t/s, tg_3s = 10.19 t/s 22.29.866.752 I slot print_timing: id 0 | task 7497 | n_gen = 162, tg = 10.18 t/s, tg_3s = 10.18 t/s 22.32.908.630 I slot print_timing: id 0 | task 7497 | n_gen = 193, tg = 10.19 t/s, tg_3s = 10.19 t/s 22.35.950.546 I slot print_timing: id 0 | task 7497 | n_gen = 224, tg = 10.19 t/s, tg_3s = 10.19 t/s 22.38.992.342 I slot print_timing: id 0 | task 7497 | n_gen = 255, tg = 10.19 t/s, tg_3s = 10.19 t/s 22.41.053.761 I slot print_timing: id 0 | task 7497 | prompt eval time = 4573.88 ms / 344 tokens ( 13.30 ms per token, 75.21 tokens per second) 22.41.053.763 I slot print_timing: id 0 | task 7497 | eval time = 26994.89 ms / 276 tokens ( 98.16 ms per token, 10.19 tokens per second) 22.41.053.764 I slot print_timing: id 0 | task 7497 | total time = 31568.76 ms / 620 tokens 22.41.053.764 I slot print_timing: id 0 | task 7497 | graphs reused = 7190 22.41.053.765 I slot print_timing: id 0 | task 7497 | graph reallocs = 0 / 0 (same size) / (changed size) 22.41.053.789 I slot release: id 0 | task 7497 | stop processing: n_tokens = 651, truncated = 0 22.41.058.456 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 651, t_last = 84579153426 22.41.058.496 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1106.905 MiB) 22.41.081.263 I slot launch_slot_: id 0 | task 7776 | processing task, is_child = 0 22.44.346.522 I slot print_timing: id 0 | task 7776 | prompt processing, n_tokens = 343, progress = 0.99, t = 3.27 s / 105.05 tokens per second 22.55.371.740 I slot print_timing: id 0 | task 7776 | n_gen = 100, tg = 10.19 t/s, tg_3s = 10.29 t/s 22.58.411.440 I slot print_timing: id 0 | task 7776 | n_gen = 131, tg = 10.19 t/s, tg_3s = 10.20 t/s 23.01.456.324 I slot print_timing: id 0 | task 7776 | n_gen = 162, tg = 10.19 t/s, tg_3s = 10.18 t/s 23.04.497.828 I slot print_timing: id 0 | task 7776 | n_gen = 193, tg = 10.19 t/s, tg_3s = 10.19 t/s 23.07.539.604 I slot print_timing: id 0 | task 7776 | n_gen = 224, tg = 10.19 t/s, tg_3s = 10.19 t/s 23.07.834.076 I slot print_timing: id 0 | task 7776 | prompt eval time = 4576.87 ms / 347 tokens ( 13.19 ms per token, 75.82 tokens per second) 23.07.834.078 I slot print_timing: id 0 | task 7776 | eval time = 22175.93 ms / 227 tokens ( 98.12 ms per token, 10.19 tokens per second) 23.07.834.079 I slot print_timing: id 0 | task 7776 | total time = 26752.80 ms / 574 tokens 23.07.834.079 I slot print_timing: id 0 | task 7776 | graphs reused = 7414 23.07.834.079 I slot print_timing: id 0 | task 7776 | graph reallocs = 0 / 0 (same size) / (changed size) 23.07.834.108 I slot release: id 0 | task 7776 | stop processing: n_tokens = 605, truncated = 0 23.07.838.714 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 605, t_last = 84605933745 23.07.838.746 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 929.269 MiB) 23.07.865.994 I slot launch_slot_: id 0 | task 8006 | processing task, is_child = 0 23.11.484.998 I slot print_timing: id 0 | task 8006 | prompt processing, n_tokens = 397, progress = 0.99, t = 3.62 s / 109.70 tokens per second 23.22.531.008 I slot print_timing: id 0 | task 8006 | n_gen = 100, tg = 10.18 t/s, tg_3s = 10.29 t/s 23.25.571.609 I slot print_timing: id 0 | task 8006 | n_gen = 131, tg = 10.19 t/s, tg_3s = 10.20 t/s 23.26.748.228 I slot print_timing: id 0 | task 8006 | prompt eval time = 4942.53 ms / 401 tokens ( 12.33 ms per token, 81.13 tokens per second) 23.26.748.231 I slot print_timing: id 0 | task 8006 | eval time = 13939.68 ms / 143 tokens ( 98.17 ms per token, 10.19 tokens per second) 23.26.748.232 I slot print_timing: id 0 | task 8006 | total time = 18882.22 ms / 544 tokens 23.26.748.232 I slot print_timing: id 0 | task 8006 | graphs reused = 7554 23.26.748.233 I slot print_timing: id 0 | task 8006 | graph reallocs = 0 / 0 (same size) / (changed size) 23.26.748.268 I slot release: id 0 | task 8006 | stop processing: n_tokens = 575, truncated = 0 23.26.753.497 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 575, t_last = 84624847905 23.26.753.546 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 930.269 MiB) 23.26.775.479 I slot launch_slot_: id 0 | task 8152 | processing task, is_child = 0 23.30.764.701 I slot print_timing: id 0 | task 8152 | prompt processing, n_tokens = 452, progress = 0.99, t = 3.99 s / 113.31 tokens per second 23.42.136.465 I slot print_timing: id 0 | task 8152 | n_gen = 100, tg = 10.18 t/s, tg_3s = 10.29 t/s 23.45.196.862 I slot print_timing: id 0 | task 8152 | n_gen = 131, tg = 10.17 t/s, tg_3s = 10.13 t/s 23.48.238.439 I slot print_timing: id 0 | task 8152 | n_gen = 162, tg = 10.18 t/s, tg_3s = 10.19 t/s 23.51.295.348 I slot print_timing: id 0 | task 8152 | n_gen = 193, tg = 10.17 t/s, tg_3s = 10.14 t/s 23.53.164.222 I slot print_timing: id 0 | task 8152 | prompt eval time = 5639.97 ms / 456 tokens ( 12.37 ms per token, 80.85 tokens per second) 23.53.164.229 I slot print_timing: id 0 | task 8152 | eval time = 20748.76 ms / 212 tokens ( 98.34 ms per token, 10.17 tokens per second) 23.53.164.229 I slot print_timing: id 0 | task 8152 | total time = 26388.73 ms / 668 tokens 23.53.164.229 I slot print_timing: id 0 | task 8152 | graphs reused = 7763 23.53.164.230 I slot print_timing: id 0 | task 8152 | graph reallocs = 0 / 0 (same size) / (changed size) 23.53.164.268 I slot release: id 0 | task 8152 | stop processing: n_tokens = 699, truncated = 0 23.53.168.638 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.107 (> 0.100 thold), f_keep = 0.067 23.53.168.676 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 930.269 MiB) 23.53.202.203 I slot launch_slot_: id 0 | task 8367 | processing task, is_child = 0 23.56.817.299 I slot print_timing: id 0 | task 8367 | prompt processing, n_tokens = 402, progress = 0.99, t = 3.62 s / 111.20 tokens per second 24.08.176.157 I slot print_timing: id 0 | task 8367 | n_gen = 100, tg = 10.19 t/s, tg_3s = 10.29 t/s 24.10.825.135 I slot print_timing: id 0 | task 8367 | prompt eval time = 5257.74 ms / 406 tokens ( 12.95 ms per token, 77.22 tokens per second) 24.10.825.140 I slot print_timing: id 0 | task 8367 | eval time = 12365.17 ms / 127 tokens ( 98.14 ms per token, 10.19 tokens per second) 24.10.825.141 I slot print_timing: id 0 | task 8367 | total time = 17622.92 ms / 533 tokens 24.10.825.141 I slot print_timing: id 0 | task 8367 | graphs reused = 7887 24.10.825.142 I slot print_timing: id 0 | task 8367 | graph reallocs = 0 / 0 (same size) / (changed size) 24.10.825.170 I slot release: id 0 | task 8367 | stop processing: n_tokens = 564, truncated = 0 24.10.829.608 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 564, t_last = 84668924807 24.10.829.638 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 927.205 MiB) 24.10.857.121 I slot launch_slot_: id 0 | task 8497 | processing task, is_child = 0 24.14.482.266 I slot print_timing: id 0 | task 8497 | prompt processing, n_tokens = 402, progress = 0.99, t = 3.63 s / 110.89 tokens per second 24.25.521.340 I slot print_timing: id 0 | task 8497 | n_gen = 100, tg = 10.19 t/s, tg_3s = 10.29 t/s 24.28.563.194 I slot print_timing: id 0 | task 8497 | n_gen = 131, tg = 10.19 t/s, tg_3s = 10.19 t/s 24.31.605.436 I slot print_timing: id 0 | task 8497 | n_gen = 162, tg = 10.19 t/s, tg_3s = 10.19 t/s 24.33.273.668 I slot print_timing: id 0 | task 8497 | prompt eval time = 4946.46 ms / 406 tokens ( 12.18 ms per token, 82.08 tokens per second) 24.33.273.673 I slot print_timing: id 0 | task 8497 | eval time = 17470.08 ms / 179 tokens ( 98.15 ms per token, 10.19 tokens per second) 24.33.273.674 I slot print_timing: id 0 | task 8497 | total time = 22416.54 ms / 585 tokens 24.33.273.674 I slot print_timing: id 0 | task 8497 | graphs reused = 8063 24.33.273.675 I slot print_timing: id 0 | task 8497 | graph reallocs = 0 / 0 (same size) / (changed size) 24.33.273.713 I slot release: id 0 | task 8497 | stop processing: n_tokens = 616, truncated = 0 24.33.278.971 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 616, t_last = 84691373350 24.33.279.011 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 934.521 MiB) 24.33.312.242 I slot launch_slot_: id 0 | task 8679 | processing task, is_child = 0 24.37.287.509 I slot print_timing: id 0 | task 8679 | prompt processing, n_tokens = 440, progress = 0.99, t = 3.98 s / 110.68 tokens per second 24.48.653.685 I slot print_timing: id 0 | task 8679 | n_gen = 100, tg = 10.19 t/s, tg_3s = 10.29 t/s 24.51.696.039 I slot print_timing: id 0 | task 8679 | n_gen = 131, tg = 10.19 t/s, tg_3s = 10.19 t/s 24.52.972.021 I slot print_timing: id 0 | task 8679 | prompt eval time = 5626.30 ms / 444 tokens ( 12.67 ms per token, 78.92 tokens per second) 24.52.972.024 I slot print_timing: id 0 | task 8679 | eval time = 14033.47 ms / 144 tokens ( 98.14 ms per token, 10.19 tokens per second) 24.52.972.024 I slot print_timing: id 0 | task 8679 | total time = 19659.77 ms / 588 tokens 24.52.972.025 I slot print_timing: id 0 | task 8679 | graphs reused = 8204 24.52.972.025 I slot print_timing: id 0 | task 8679 | graph reallocs = 0 / 0 (same size) / (changed size) 24.52.972.067 I slot release: id 0 | task 8679 | stop processing: n_tokens = 619, truncated = 0 24.52.977.005 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 619, t_last = 84711071704 24.52.977.047 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 938.022 MiB) 24.53.001.399 I slot launch_slot_: id 0 | task 8826 | processing task, is_child = 0 24.56.616.760 I slot print_timing: id 0 | task 8826 | prompt processing, n_tokens = 368, progress = 0.99, t = 3.62 s / 101.79 tokens per second 25.07.636.282 I slot print_timing: id 0 | task 8826 | n_gen = 100, tg = 10.19 t/s, tg_3s = 10.29 t/s 25.07.930.791 I slot print_timing: id 0 | task 8826 | prompt eval time = 4919.90 ms / 372 tokens ( 13.23 ms per token, 75.61 tokens per second) 25.07.930.796 I slot print_timing: id 0 | task 8826 | eval time = 10009.48 ms / 103 tokens ( 98.13 ms per token, 10.19 tokens per second) 25.07.930.796 I slot print_timing: id 0 | task 8826 | total time = 14929.38 ms / 475 tokens 25.07.930.801 I slot print_timing: id 0 | task 8826 | graphs reused = 8305 25.07.930.803 I slot print_timing: id 0 | task 8826 | graph reallocs = 0 / 0 (same size) / (changed size) 25.07.930.832 I slot release: id 0 | task 8826 | stop processing: n_tokens = 506, truncated = 0 25.07.935.887 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 506, t_last = 84726030469 25.07.935.920 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 945.087 MiB) 25.07.958.405 I slot launch_slot_: id 0 | task 8932 | processing task, is_child = 0 25.11.933.665 I slot print_timing: id 0 | task 8932 | prompt processing, n_tokens = 450, progress = 0.99, t = 3.98 s / 113.20 tokens per second 25.23.316.283 I slot print_timing: id 0 | task 8932 | n_gen = 100, tg = 10.19 t/s, tg_3s = 10.29 t/s 25.26.358.068 I slot print_timing: id 0 | task 8932 | n_gen = 131, tg = 10.19 t/s, tg_3s = 10.19 t/s 25.29.400.498 I slot print_timing: id 0 | task 8932 | n_gen = 162, tg = 10.19 t/s, tg_3s = 10.19 t/s 25.32.443.853 I slot print_timing: id 0 | task 8932 | n_gen = 193, tg = 10.19 t/s, tg_3s = 10.19 t/s 25.35.489.182 I slot print_timing: id 0 | task 8932 | n_gen = 224, tg = 10.19 t/s, tg_3s = 10.18 t/s 25.36.078.888 I slot print_timing: id 0 | task 8932 | prompt eval time = 5639.48 ms / 454 tokens ( 12.42 ms per token, 80.50 tokens per second) 25.36.078.893 I slot print_timing: id 0 | task 8932 | eval time = 22480.99 ms / 230 tokens ( 98.17 ms per token, 10.19 tokens per second) 25.36.078.893 I slot print_timing: id 0 | task 8932 | total time = 28120.47 ms / 684 tokens 25.36.078.894 I slot print_timing: id 0 | task 8932 | graphs reused = 8532 25.36.078.894 I slot print_timing: id 0 | task 8932 | graph reallocs = 0 / 0 (same size) / (changed size) 25.36.078.934 I slot release: id 0 | task 8932 | stop processing: n_tokens = 715, truncated = 0 25.36.083.641 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 715, t_last = 84754178572 25.36.083.680 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 938.460 MiB) 25.36.108.447 I slot launch_slot_: id 0 | task 9165 | processing task, is_child = 0 25.39.722.660 I slot print_timing: id 0 | task 9165 | prompt processing, n_tokens = 350, progress = 0.99, t = 3.61 s / 96.84 tokens per second 25.50.383.760 I slot print_timing: id 0 | task 9165 | n_gen = 100, tg = 10.19 t/s, tg_3s = 10.29 t/s 25.53.427.788 I slot print_timing: id 0 | task 9165 | n_gen = 131, tg = 10.19 t/s, tg_3s = 10.18 t/s 25.56.470.310 I slot print_timing: id 0 | task 9165 | n_gen = 162, tg = 10.19 t/s, tg_3s = 10.19 t/s 25.59.512.391 I slot print_timing: id 0 | task 9165 | n_gen = 193, tg = 10.19 t/s, tg_3s = 10.19 t/s 26.02.553.836 I slot print_timing: id 0 | task 9165 | n_gen = 224, tg = 10.19 t/s, tg_3s = 10.19 t/s 26.02.750.420 I slot print_timing: id 0 | task 9165 | prompt eval time = 4559.24 ms / 354 tokens ( 12.88 ms per token, 77.64 tokens per second) 26.02.750.425 I slot print_timing: id 0 | task 9165 | eval time = 22082.73 ms / 226 tokens ( 98.15 ms per token, 10.19 tokens per second) 26.02.750.426 I slot print_timing: id 0 | task 9165 | total time = 26641.96 ms / 580 tokens 26.02.750.426 I slot print_timing: id 0 | task 9165 | graphs reused = 8755 26.02.750.426 I slot print_timing: id 0 | task 9165 | graph reallocs = 0 / 0 (same size) / (changed size) 26.02.750.468 I slot release: id 0 | task 9165 | stop processing: n_tokens = 611, truncated = 0 26.02.754.916 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 611, t_last = 84780850105 26.02.754.952 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 935.583 MiB) 26.02.777.875 I slot launch_slot_: id 0 | task 9394 | processing task, is_child = 0 26.06.389.298 I slot print_timing: id 0 | task 9394 | prompt processing, n_tokens = 330, progress = 0.99, t = 3.61 s / 91.38 tokens per second 26.17.037.172 I slot print_timing: id 0 | task 9394 | n_gen = 100, tg = 10.19 t/s, tg_3s = 10.29 t/s 26.20.077.652 I slot print_timing: id 0 | task 9394 | n_gen = 131, tg = 10.19 t/s, tg_3s = 10.20 t/s 26.20.959.819 I slot print_timing: id 0 | task 9394 | prompt eval time = 4544.19 ms / 334 tokens ( 13.61 ms per token, 73.50 tokens per second) 26.20.959.824 I slot print_timing: id 0 | task 9394 | eval time = 13637.74 ms / 140 tokens ( 98.11 ms per token, 10.19 tokens per second) 26.20.959.824 I slot print_timing: id 0 | task 9394 | total time = 18181.93 ms / 474 tokens 26.20.959.824 I slot print_timing: id 0 | task 9394 | graphs reused = 8893 26.20.959.825 I slot print_timing: id 0 | task 9394 | graph reallocs = 0 / 0 (same size) / (changed size) 26.20.959.848 I slot release: id 0 | task 9394 | stop processing: n_tokens = 505, truncated = 0 26.20.964.581 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 505, t_last = 84799059485 26.20.964.609 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 933.708 MiB) 26.20.987.013 I slot launch_slot_: id 0 | task 9537 | processing task, is_child = 0 26.24.976.994 I slot print_timing: id 0 | task 9537 | prompt processing, n_tokens = 422, progress = 0.99, t = 3.99 s / 105.77 tokens per second 26.36.004.310 I slot print_timing: id 0 | task 9537 | n_gen = 100, tg = 10.19 t/s, tg_3s = 10.30 t/s 26.39.045.587 I slot print_timing: id 0 | task 9537 | n_gen = 131, tg = 10.19 t/s, tg_3s = 10.19 t/s 26.42.086.452 I slot print_timing: id 0 | task 9537 | n_gen = 162, tg = 10.19 t/s, tg_3s = 10.19 t/s 26.43.361.897 I slot print_timing: id 0 | task 9537 | prompt eval time = 5305.80 ms / 426 tokens ( 12.45 ms per token, 80.29 tokens per second) 26.43.361.901 I slot print_timing: id 0 | task 9537 | eval time = 17069.07 ms / 175 tokens ( 98.10 ms per token, 10.19 tokens per second) 26.43.361.902 I slot print_timing: id 0 | task 9537 | total time = 22374.87 ms / 601 tokens 26.43.361.902 I slot print_timing: id 0 | task 9537 | graphs reused = 9065 26.43.361.903 I slot print_timing: id 0 | task 9537 | graph reallocs = 0 / 0 (same size) / (changed size) 26.43.361.942 I slot release: id 0 | task 9537 | stop processing: n_tokens = 632, truncated = 0 26.43.366.702 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 632, t_last = 84821461579 26.43.366.737 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 941.461 MiB) 26.43.389.068 I slot launch_slot_: id 0 | task 9715 | processing task, is_child = 0 26.47.011.432 I slot print_timing: id 0 | task 9715 | prompt processing, n_tokens = 362, progress = 0.99, t = 3.62 s / 99.94 tokens per second 26.57.669.873 I slot print_timing: id 0 | task 9715 | n_gen = 100, tg = 10.19 t/s, tg_3s = 10.30 t/s 27.00.712.593 I slot print_timing: id 0 | task 9715 | n_gen = 131, tg = 10.19 t/s, tg_3s = 10.19 t/s 27.02.967.795 I slot print_timing: id 0 | task 9715 | prompt eval time = 4567.52 ms / 366 tokens ( 12.48 ms per token, 80.13 tokens per second) 27.02.967.801 I slot print_timing: id 0 | task 9715 | eval time = 15011.20 ms / 154 tokens ( 98.11 ms per token, 10.19 tokens per second) 27.02.967.801 I slot print_timing: id 0 | task 9715 | total time = 19578.72 ms / 520 tokens 27.02.967.801 I slot print_timing: id 0 | task 9715 | graphs reused = 9216 27.02.967.802 I slot print_timing: id 0 | task 9715 | graph reallocs = 0 / 0 (same size) / (changed size) 27.02.967.842 I slot release: id 0 | task 9715 | stop processing: n_tokens = 551, truncated = 0 27.02.972.224 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 551, t_last = 84841067479 27.02.972.259 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 933.020 MiB) 27.02.995.499 I slot launch_slot_: id 0 | task 9872 | processing task, is_child = 0 27.06.625.315 I slot print_timing: id 0 | task 9872 | prompt processing, n_tokens = 458, progress = 0.99, t = 3.63 s / 126.18 tokens per second 27.18.352.751 I slot print_timing: id 0 | task 9872 | n_gen = 100, tg = 10.18 t/s, tg_3s = 10.29 t/s 27.21.394.346 I slot print_timing: id 0 | task 9872 | n_gen = 131, tg = 10.19 t/s, tg_3s = 10.19 t/s 27.24.436.492 I slot print_timing: id 0 | task 9872 | n_gen = 162, tg = 10.19 t/s, tg_3s = 10.19 t/s 27.27.479.652 I slot print_timing: id 0 | task 9872 | n_gen = 193, tg = 10.19 t/s, tg_3s = 10.19 t/s 27.30.526.317 I slot print_timing: id 0 | task 9872 | n_gen = 224, tg = 10.19 t/s, tg_3s = 10.18 t/s 27.33.572.020 I slot print_timing: id 0 | task 9872 | n_gen = 255, tg = 10.18 t/s, tg_3s = 10.18 t/s 27.36.620.428 I slot print_timing: id 0 | task 9872 | n_gen = 286, tg = 10.18 t/s, tg_3s = 10.17 t/s 27.39.666.294 I slot print_timing: id 0 | task 9872 | n_gen = 317, tg = 10.18 t/s, tg_3s = 10.18 t/s 27.42.711.283 I slot print_timing: id 0 | task 9872 | n_gen = 348, tg = 10.18 t/s, tg_3s = 10.18 t/s 27.43.300.800 I slot print_timing: id 0 | task 9872 | prompt eval time = 5636.40 ms / 462 tokens ( 12.20 ms per token, 81.97 tokens per second) 27.43.300.805 I slot print_timing: id 0 | task 9872 | eval time = 34668.89 ms / 354 tokens ( 98.21 ms per token, 10.18 tokens per second) 27.43.300.805 I slot print_timing: id 0 | task 9872 | total time = 40305.29 ms / 816 tokens 27.43.300.806 I slot print_timing: id 0 | task 9872 | graphs reused = 9566 27.43.300.806 I slot print_timing: id 0 | task 9872 | graph reallocs = 0 / 0 (same size) / (changed size) 27.43.300.833 I slot release: id 0 | task 9872 | stop processing: n_tokens = 847, truncated = 0 27.43.305.512 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 847, t_last = 84881400470 27.43.305.556 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 936.271 MiB) 27.43.328.664 I slot launch_slot_: id 0 | task 10229 | processing task, is_child = 0 27.46.604.667 I slot print_timing: id 0 | task 10229 | prompt processing, n_tokens = 392, progress = 0.99, t = 3.28 s / 119.66 tokens per second 27.57.968.784 I slot print_timing: id 0 | task 10229 | n_gen = 100, tg = 10.19 t/s, tg_3s = 10.29 t/s 28.01.010.355 I slot print_timing: id 0 | task 10229 | n_gen = 131, tg = 10.19 t/s, tg_3s = 10.19 t/s 28.01.794.763 I slot print_timing: id 0 | task 10229 | prompt eval time = 4925.66 ms / 396 tokens ( 12.44 ms per token, 80.40 tokens per second) 28.01.794.765 I slot print_timing: id 0 | task 10229 | eval time = 13540.43 ms / 139 tokens ( 98.12 ms per token, 10.19 tokens per second) 28.01.794.766 I slot print_timing: id 0 | task 10229 | total time = 18466.09 ms / 535 tokens 28.01.794.766 I slot print_timing: id 0 | task 10229 | graphs reused = 9702 28.01.794.767 I slot print_timing: id 0 | task 10229 | graph reallocs = 0 / 0 (same size) / (changed size) 28.01.794.803 I slot release: id 0 | task 10229 | stop processing: n_tokens = 566, truncated = 0 28.01.798.775 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 566, t_last = 84899894440 28.01.798.809 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 936.459 MiB) 28.01.820.685 I slot launch_slot_: id 0 | task 10371 | processing task, is_child = 0 28.06.119.666 I slot print_timing: id 0 | task 10371 | prompt processing, n_tokens = 454, progress = 0.99, t = 4.30 s / 105.61 tokens per second 28.17.481.423 I slot print_timing: id 0 | task 10371 | n_gen = 100, tg = 10.18 t/s, tg_3s = 10.28 t/s 28.20.524.337 I slot print_timing: id 0 | task 10371 | n_gen = 131, tg = 10.18 t/s, tg_3s = 10.19 t/s 28.23.566.875 I slot print_timing: id 0 | task 10371 | n_gen = 162, tg = 10.18 t/s, tg_3s = 10.19 t/s 28.25.726.696 I slot print_timing: id 0 | task 10371 | prompt eval time = 5936.51 ms / 458 tokens ( 12.96 ms per token, 77.15 tokens per second) 28.25.726.700 I slot print_timing: id 0 | task 10371 | eval time = 17969.49 ms / 184 tokens ( 98.19 ms per token, 10.18 tokens per second) 28.25.726.700 I slot print_timing: id 0 | task 10371 | total time = 23906.00 ms / 642 tokens 28.25.726.701 I slot print_timing: id 0 | task 10371 | graphs reused = 9883 28.25.726.701 I slot print_timing: id 0 | task 10371 | graph reallocs = 0 / 0 (same size) / (changed size) 28.25.726.739 I slot release: id 0 | task 10371 | stop processing: n_tokens = 673, truncated = 0 28.25.731.285 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 673, t_last = 84923826376 28.25.731.319 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 929.394 MiB) 28.25.755.058 I slot launch_slot_: id 0 | task 10558 | processing task, is_child = 0 28.29.372.269 I slot print_timing: id 0 | task 10558 | prompt processing, n_tokens = 454, progress = 0.99, t = 3.62 s / 125.51 tokens per second 28.41.113.962 I slot print_timing: id 0 | task 10558 | n_gen = 100, tg = 10.18 t/s, tg_3s = 10.28 t/s 28.43.385.015 I slot print_timing: id 0 | task 10558 | prompt eval time = 5631.11 ms / 458 tokens ( 12.30 ms per token, 81.33 tokens per second) 28.43.385.020 I slot print_timing: id 0 | task 10558 | eval time = 11998.83 ms / 123 tokens ( 98.35 ms per token, 10.17 tokens per second) 28.43.385.020 I slot print_timing: id 0 | task 10558 | total time = 17629.94 ms / 581 tokens 28.43.385.021 I slot print_timing: id 0 | task 10558 | graphs reused = 10003 28.43.385.021 I slot print_timing: id 0 | task 10558 | graph reallocs = 0 / 0 (same size) / (changed size) 28.43.385.048 I slot release: id 0 | task 10558 | stop processing: n_tokens = 612, truncated = 0 28.43.390.103 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 612, t_last = 84941484685 28.43.390.143 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 942.461 MiB) 28.43.412.574 I slot launch_slot_: id 0 | task 10684 | processing task, is_child = 0 28.47.403.459 I slot print_timing: id 0 | task 10684 | prompt processing, n_tokens = 448, progress = 0.99, t = 3.99 s / 112.26 tokens per second 28.58.777.192 I slot print_timing: id 0 | task 10684 | n_gen = 100, tg = 10.18 t/s, tg_3s = 10.28 t/s 29.01.819.317 I slot print_timing: id 0 | task 10684 | n_gen = 131, tg = 10.18 t/s, tg_3s = 10.19 t/s 29.04.861.152 I slot print_timing: id 0 | task 10684 | n_gen = 162, tg = 10.18 t/s, tg_3s = 10.19 t/s 29.07.904.780 I slot print_timing: id 0 | task 10684 | n_gen = 193, tg = 10.18 t/s, tg_3s = 10.19 t/s 29.10.951.901 I slot print_timing: id 0 | task 10684 | n_gen = 224, tg = 10.18 t/s, tg_3s = 10.17 t/s 29.13.605.878 I slot print_timing: id 0 | task 10684 | prompt eval time = 5637.59 ms / 452 tokens ( 12.47 ms per token, 80.18 tokens per second) 29.13.605.881 I slot print_timing: id 0 | task 10684 | eval time = 24555.71 ms / 251 tokens ( 98.22 ms per token, 10.18 tokens per second) 29.13.605.882 I slot print_timing: id 0 | task 10684 | total time = 30193.29 ms / 703 tokens 29.13.605.882 I slot print_timing: id 0 | task 10684 | graphs reused = 10251 29.13.605.883 I slot print_timing: id 0 | task 10684 | graph reallocs = 0 / 0 (same size) / (changed size) 29.13.605.911 I slot release: id 0 | task 10684 | stop processing: n_tokens = 734, truncated = 0 29.13.610.359 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 734, t_last = 84971705548 29.13.610.400 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 935.959 MiB) 29.13.633.310 I slot launch_slot_: id 0 | task 10938 | processing task, is_child = 0 29.17.248.004 I slot print_timing: id 0 | task 10938 | prompt processing, n_tokens = 400, progress = 0.99, t = 3.61 s / 110.66 tokens per second 29.28.604.405 I slot print_timing: id 0 | task 10938 | n_gen = 100, tg = 10.19 t/s, tg_3s = 10.29 t/s 29.30.566.550 I slot print_timing: id 0 | task 10938 | prompt eval time = 5254.42 ms / 404 tokens ( 13.01 ms per token, 76.89 tokens per second) 29.30.566.552 I slot print_timing: id 0 | task 10938 | eval time = 11678.81 ms / 120 tokens ( 98.14 ms per token, 10.19 tokens per second) 29.30.566.553 I slot print_timing: id 0 | task 10938 | total time = 16933.22 ms / 524 tokens 29.30.566.553 I slot print_timing: id 0 | task 10938 | graphs reused = 10368 29.30.566.553 I slot print_timing: id 0 | task 10938 | graph reallocs = 0 / 0 (same size) / (changed size) 29.30.566.581 I slot release: id 0 | task 10938 | stop processing: n_tokens = 555, truncated = 0 29.30.571.313 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 555, t_last = 84988666218 29.30.571.342 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 929.331 MiB) 29.30.592.965 I slot launch_slot_: id 0 | task 11061 | processing task, is_child = 0 29.34.207.870 I slot print_timing: id 0 | task 11061 | prompt processing, n_tokens = 341, progress = 0.99, t = 3.61 s / 94.33 tokens per second 29.44.868.126 I slot print_timing: id 0 | task 11061 | n_gen = 100, tg = 10.18 t/s, tg_3s = 10.29 t/s 29.45.456.557 I slot print_timing: id 0 | task 11061 | prompt eval time = 4553.48 ms / 345 tokens ( 13.20 ms per token, 75.77 tokens per second) 29.45.456.563 I slot print_timing: id 0 | task 11061 | eval time = 10310.10 ms / 106 tokens ( 98.19 ms per token, 10.18 tokens per second) 29.45.456.563 I slot print_timing: id 0 | task 11061 | total time = 14863.58 ms / 451 tokens 29.45.456.564 I slot print_timing: id 0 | task 11061 | graphs reused = 10472 29.45.456.564 I slot print_timing: id 0 | task 11061 | graph reallocs = 0 / 0 (same size) / (changed size) 29.45.456.588 I slot release: id 0 | task 11061 | stop processing: n_tokens = 482, truncated = 0 29.45.461.354 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 482, t_last = 85003556225 29.45.461.388 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 937.272 MiB) 29.45.482.961 I slot launch_slot_: id 0 | task 11170 | processing task, is_child = 0 29.49.090.436 I slot print_timing: id 0 | task 11170 | prompt processing, n_tokens = 426, progress = 0.99, t = 3.61 s / 118.09 tokens per second 30.00.229.415 I slot print_timing: id 0 | task 11170 | prompt eval time = 5611.58 ms / 430 tokens ( 13.05 ms per token, 76.63 tokens per second) 30.00.229.420 I slot print_timing: id 0 | task 11170 | eval time = 9134.86 ms / 94 tokens ( 98.22 ms per token, 10.18 tokens per second) 30.00.229.421 I slot print_timing: id 0 | task 11170 | total time = 14746.44 ms / 524 tokens 30.00.229.422 I slot print_timing: id 0 | task 11170 | graphs reused = 10563 30.00.229.422 I slot print_timing: id 0 | task 11170 | graph reallocs = 0 / 0 (same size) / (changed size) 30.00.229.447 I slot release: id 0 | task 11170 | stop processing: n_tokens = 555, truncated = 0 30.00.234.028 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 555, t_last = 85018329084 30.00.234.057 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 932.207 MiB) 30.00.255.686 I slot launch_slot_: id 0 | task 11267 | processing task, is_child = 0 30.03.527.397 I slot print_timing: id 0 | task 11267 | prompt processing, n_tokens = 312, progress = 0.99, t = 3.27 s / 95.36 tokens per second 30.12.724.827 I slot print_timing: id 0 | task 11267 | prompt eval time = 4208.40 ms / 316 tokens ( 13.32 ms per token, 75.09 tokens per second) 30.12.724.832 I slot print_timing: id 0 | task 11267 | eval time = 8260.73 ms / 85 tokens ( 98.34 ms per token, 10.17 tokens per second) 30.12.724.833 I slot print_timing: id 0 | task 11267 | total time = 12469.13 ms / 401 tokens 30.12.724.833 I slot print_timing: id 0 | task 11267 | graphs reused = 10646 30.12.724.834 I slot print_timing: id 0 | task 11267 | graph reallocs = 0 / 0 (same size) / (changed size) 30.12.724.859 I slot release: id 0 | task 11267 | stop processing: n_tokens = 432, truncated = 0 30.12.729.242 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 432, t_last = 85030824496 30.12.729.273 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 950.714 MiB) 30.12.763.666 I slot launch_slot_: id 0 | task 11355 | processing task, is_child = 0 30.16.368.793 I slot print_timing: id 0 | task 11355 | prompt processing, n_tokens = 350, progress = 0.99, t = 3.61 s / 97.08 tokens per second 30.27.036.202 I slot print_timing: id 0 | task 11355 | n_gen = 100, tg = 10.19 t/s, tg_3s = 10.30 t/s 30.27.723.133 I slot print_timing: id 0 | task 11355 | prompt eval time = 4560.29 ms / 354 tokens ( 12.88 ms per token, 77.63 tokens per second) 30.27.723.139 I slot print_timing: id 0 | task 11355 | eval time = 10399.17 ms / 107 tokens ( 98.11 ms per token, 10.19 tokens per second) 30.27.723.140 I slot print_timing: id 0 | task 11355 | total time = 14959.46 ms / 461 tokens 30.27.723.140 I slot print_timing: id 0 | task 11355 | graphs reused = 10751 30.27.723.141 I slot print_timing: id 0 | task 11355 | graph reallocs = 0 / 0 (same size) / (changed size) 30.27.723.165 I slot release: id 0 | task 11355 | stop processing: n_tokens = 492, truncated = 0 30.27.728.066 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 492, t_last = 85045822802 30.27.728.098 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 933.145 MiB) 30.27.750.521 I slot launch_slot_: id 0 | task 11465 | processing task, is_child = 0 30.32.428.172 I slot print_timing: id 0 | task 11465 | prompt processing, n_tokens = 434, progress = 0.99, t = 4.68 s / 92.78 tokens per second 30.42.892.882 I slot print_timing: id 0 | task 11465 | prompt eval time = 5619.69 ms / 438 tokens ( 12.83 ms per token, 77.94 tokens per second) 30.42.892.884 I slot print_timing: id 0 | task 11465 | eval time = 9522.65 ms / 98 tokens ( 98.17 ms per token, 10.19 tokens per second) 30.42.892.885 I slot print_timing: id 0 | task 11465 | total time = 15142.35 ms / 536 tokens 30.42.892.885 I slot print_timing: id 0 | task 11465 | graphs reused = 10846 30.42.892.885 I slot print_timing: id 0 | task 11465 | graph reallocs = 0 / 0 (same size) / (changed size) 30.42.892.913 I slot release: id 0 | task 11465 | stop processing: n_tokens = 567, truncated = 0 30.42.897.273 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 567, t_last = 85060992550 30.42.897.311 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 939.835 MiB) 30.42.919.449 I slot launch_slot_: id 0 | task 11566 | processing task, is_child = 0 30.47.948.589 I slot print_timing: id 0 | task 11566 | prompt processing, n_tokens = 453, progress = 0.99, t = 5.03 s / 90.08 tokens per second 30.55.655.166 I slot print_timing: id 0 | task 11566 | prompt eval time = 5960.24 ms / 457 tokens ( 13.04 ms per token, 76.67 tokens per second) 30.55.655.170 I slot print_timing: id 0 | task 11566 | eval time = 6775.47 ms / 70 tokens ( 98.20 ms per token, 10.18 tokens per second) 30.55.655.171 I slot print_timing: id 0 | task 11566 | total time = 12735.71 ms / 527 tokens 30.55.655.171 I slot print_timing: id 0 | task 11566 | graphs reused = 10913 30.55.655.172 I slot print_timing: id 0 | task 11566 | graph reallocs = 0 / 0 (same size) / (changed size) 30.55.655.213 I slot release: id 0 | task 11566 | stop processing: n_tokens = 558, truncated = 0 30.55.659.430 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 85073754850 30.55.659.461 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 936.021 MiB) 30.55.681.428 I slot launch_slot_: id 0 | task 11639 | processing task, is_child = 0 31.00.369.242 I slot print_timing: id 0 | task 11639 | prompt processing, n_tokens = 469, progress = 0.99, t = 4.69 s / 100.05 tokens per second 31.11.310.660 I slot print_timing: id 0 | task 11639 | prompt eval time = 5993.21 ms / 473 tokens ( 12.67 ms per token, 78.92 tokens per second) 31.11.310.666 I slot print_timing: id 0 | task 11639 | eval time = 9636.01 ms / 98 tokens ( 99.34 ms per token, 10.07 tokens per second) 31.11.310.666 I slot print_timing: id 0 | task 11639 | total time = 15629.22 ms / 571 tokens 31.11.310.667 I slot print_timing: id 0 | task 11639 | graphs reused = 11008 31.11.310.667 I slot print_timing: id 0 | task 11639 | graph reallocs = 0 / 0 (same size) / (changed size) 31.11.310.700 I slot release: id 0 | task 11639 | stop processing: n_tokens = 602, truncated = 0 31.11.315.793 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 602, t_last = 85089410337 31.11.315.825 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 943.649 MiB) 31.11.338.002 I slot launch_slot_: id 0 | task 11740 | processing task, is_child = 0 31.16.370.539 I slot print_timing: id 0 | task 11740 | prompt processing, n_tokens = 472, progress = 0.99, t = 5.03 s / 93.79 tokens per second 31.19.875.124 I slot print_timing: id 0 | task 11740 | prompt eval time = 5977.00 ms / 476 tokens ( 12.56 ms per token, 79.64 tokens per second) 31.19.875.130 I slot print_timing: id 0 | task 11740 | eval time = 2560.11 ms / 27 tokens ( 98.47 ms per token, 10.16 tokens per second) 31.19.875.130 I slot print_timing: id 0 | task 11740 | total time = 8537.11 ms / 503 tokens 31.19.875.131 I slot print_timing: id 0 | task 11740 | graphs reused = 11032 31.19.875.131 I slot print_timing: id 0 | task 11740 | graph reallocs = 0 / 0 (same size) / (changed size) 31.19.875.171 I slot release: id 0 | task 11740 | stop processing: n_tokens = 534, truncated = 0 31.19.880.075 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 534, t_last = 85097974808 31.19.880.108 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 932.457 MiB) 31.19.901.639 I slot launch_slot_: id 0 | task 11770 | processing task, is_child = 0 31.24.574.389 I slot print_timing: id 0 | task 11770 | prompt processing, n_tokens = 462, progress = 0.99, t = 4.67 s / 98.87 tokens per second 31.35.605.165 I slot print_timing: id 0 | task 11770 | n_gen = 100, tg = 10.19 t/s, tg_3s = 10.29 t/s 31.36.291.563 I slot print_timing: id 0 | task 11770 | prompt eval time = 5986.10 ms / 466 tokens ( 12.85 ms per token, 77.85 tokens per second) 31.36.291.568 I slot print_timing: id 0 | task 11770 | eval time = 10403.82 ms / 107 tokens ( 98.15 ms per token, 10.19 tokens per second) 31.36.291.569 I slot print_timing: id 0 | task 11770 | total time = 16389.91 ms / 573 tokens 31.36.291.569 I slot print_timing: id 0 | task 11770 | graphs reused = 11136 31.36.291.569 I slot print_timing: id 0 | task 11770 | graph reallocs = 0 / 0 (same size) / (changed size) 31.36.291.608 I slot release: id 0 | task 11770 | stop processing: n_tokens = 604, truncated = 0 31.36.295.451 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 604, t_last = 85114391245 31.36.295.483 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 927.893 MiB) 31.36.317.241 I slot launch_slot_: id 0 | task 11880 | processing task, is_child = 0 31.40.636.842 I slot print_timing: id 0 | task 11880 | prompt processing, n_tokens = 411, progress = 0.99, t = 4.32 s / 95.15 tokens per second 31.49.131.195 I slot print_timing: id 0 | task 11880 | prompt eval time = 5253.48 ms / 415 tokens ( 12.66 ms per token, 79.00 tokens per second) 31.49.131.198 I slot print_timing: id 0 | task 11880 | eval time = 7560.46 ms / 78 tokens ( 98.19 ms per token, 10.18 tokens per second) 31.49.131.199 I slot print_timing: id 0 | task 11880 | total time = 12813.94 ms / 493 tokens 31.49.131.199 I slot print_timing: id 0 | task 11880 | graphs reused = 11211 31.49.131.199 I slot print_timing: id 0 | task 11880 | graph reallocs = 0 / 0 (same size) / (changed size) 31.49.131.226 I slot release: id 0 | task 11880 | stop processing: n_tokens = 524, truncated = 0 31.49.136.100 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 524, t_last = 85127230863 31.49.136.146 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 932.457 MiB) 31.49.159.791 I slot launch_slot_: id 0 | task 11961 | processing task, is_child = 0 31.52.786.010 I slot print_timing: id 0 | task 11961 | prompt processing, n_tokens = 348, progress = 0.99, t = 3.63 s / 95.97 tokens per second 32.03.441.029 I slot print_timing: id 0 | task 11961 | n_gen = 100, tg = 10.18 t/s, tg_3s = 10.29 t/s 32.04.225.849 I slot print_timing: id 0 | task 11961 | prompt eval time = 4559.16 ms / 352 tokens ( 12.95 ms per token, 77.21 tokens per second) 32.04.225.855 I slot print_timing: id 0 | task 11961 | eval time = 10506.89 ms / 108 tokens ( 98.20 ms per token, 10.18 tokens per second) 32.04.225.855 I slot print_timing: id 0 | task 11961 | total time = 15066.05 ms / 460 tokens 32.04.225.856 I slot print_timing: id 0 | task 11961 | graphs reused = 11317 32.04.225.856 I slot print_timing: id 0 | task 11961 | graph reallocs = 0 / 0 (same size) / (changed size) 32.04.225.882 I slot release: id 0 | task 11961 | stop processing: n_tokens = 491, truncated = 0 32.04.230.964 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 491, t_last = 85142325519 32.04.231.004 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 924.767 MiB) 32.04.252.495 I slot launch_slot_: id 0 | task 12072 | processing task, is_child = 0 32.10.416.967 I slot print_timing: id 0 | task 12072 | prompt processing, n_tokens = 546, progress = 0.99, t = 6.16 s / 88.57 tokens per second 32.21.080.368 I slot print_timing: id 0 | task 12072 | n_gen = 100, tg = 10.18 t/s, tg_3s = 10.29 t/s 32.24.126.327 I slot print_timing: id 0 | task 12072 | n_gen = 131, tg = 10.18 t/s, tg_3s = 10.18 t/s 32.26.582.962 I slot print_timing: id 0 | task 12072 | prompt eval time = 7106.19 ms / 550 tokens ( 12.92 ms per token, 77.40 tokens per second) 32.26.582.964 I slot print_timing: id 0 | task 12072 | eval time = 15224.27 ms / 156 tokens ( 98.22 ms per token, 10.18 tokens per second) 32.26.582.964 I slot print_timing: id 0 | task 12072 | total time = 22330.46 ms / 706 tokens 32.26.582.965 I slot print_timing: id 0 | task 12072 | graphs reused = 11471 32.26.582.965 I slot print_timing: id 0 | task 12072 | graph reallocs = 0 / 0 (same size) / (changed size) 32.26.582.997 I slot release: id 0 | task 12072 | stop processing: n_tokens = 737, truncated = 0 32.26.588.173 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 737, t_last = 85164682634 32.26.588.210 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 928.518 MiB) 32.26.613.959 I slot launch_slot_: id 0 | task 12232 | processing task, is_child = 0 32.33.469.657 I slot print_timing: id 0 | task 12232 | prompt processing, n_tokens = 768, progress = 1.00, t = 6.86 s / 112.02 tokens per second 32.45.583.665 I slot print_timing: id 0 | task 12232 | n_gen = 100, tg = 10.17 t/s, tg_3s = 10.27 t/s 32.48.632.266 I slot print_timing: id 0 | task 12232 | n_gen = 131, tg = 10.17 t/s, tg_3s = 10.17 t/s 32.51.681.142 I slot print_timing: id 0 | task 12232 | n_gen = 162, tg = 10.17 t/s, tg_3s = 10.17 t/s 32.54.731.297 I slot print_timing: id 0 | task 12232 | n_gen = 193, tg = 10.17 t/s, tg_3s = 10.16 t/s 32.57.785.624 I slot print_timing: id 0 | task 12232 | n_gen = 224, tg = 10.16 t/s, tg_3s = 10.15 t/s 32.57.982.395 I slot print_timing: id 0 | task 12232 | prompt eval time = 9232.42 ms / 772 tokens ( 11.96 ms per token, 83.62 tokens per second) 32.57.982.397 I slot print_timing: id 0 | task 12232 | eval time = 22136.01 ms / 226 tokens ( 98.38 ms per token, 10.16 tokens per second) 32.57.982.398 I slot print_timing: id 0 | task 12232 | total time = 31368.43 ms / 998 tokens 32.57.982.398 I slot print_timing: id 0 | task 12232 | graphs reused = 11694 32.57.982.399 I slot print_timing: id 0 | task 12232 | graph reallocs = 0 / 0 (same size) / (changed size) 32.57.982.457 I slot release: id 0 | task 12232 | stop processing: n_tokens = 1029, truncated = 0 32.57.987.883 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1029, t_last = 85196082094 32.57.987.927 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 933.208 MiB) 32.58.013.737 I slot launch_slot_: id 0 | task 12462 | processing task, is_child = 0 33.04.885.087 I slot print_timing: id 0 | task 12462 | prompt processing, n_tokens = 679, progress = 0.99, t = 6.87 s / 98.82 tokens per second 33.16.274.780 I slot print_timing: id 0 | task 12462 | n_gen = 100, tg = 10.17 t/s, tg_3s = 10.27 t/s 33.19.321.455 I slot print_timing: id 0 | task 12462 | n_gen = 131, tg = 10.17 t/s, tg_3s = 10.18 t/s 33.22.369.188 I slot print_timing: id 0 | task 12462 | n_gen = 162, tg = 10.17 t/s, tg_3s = 10.17 t/s 33.25.421.260 I slot print_timing: id 0 | task 12462 | n_gen = 193, tg = 10.17 t/s, tg_3s = 10.16 t/s 33.26.208.060 I slot print_timing: id 0 | task 12462 | prompt eval time = 8524.51 ms / 683 tokens ( 12.48 ms per token, 80.12 tokens per second) 33.26.208.063 I slot print_timing: id 0 | task 12462 | eval time = 19669.80 ms / 201 tokens ( 98.35 ms per token, 10.17 tokens per second) 33.26.208.064 I slot print_timing: id 0 | task 12462 | total time = 28194.31 ms / 884 tokens 33.26.208.064 I slot print_timing: id 0 | task 12462 | graphs reused = 11892 33.26.208.065 I slot print_timing: id 0 | task 12462 | graph reallocs = 0 / 0 (same size) / (changed size) 33.26.208.102 I slot release: id 0 | task 12462 | stop processing: n_tokens = 915, truncated = 0 33.26.213.096 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 915, t_last = 85224307739 33.26.213.141 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 932.645 MiB) 33.26.239.922 I slot launch_slot_: id 0 | task 12667 | processing task, is_child = 0 33.31.699.572 I slot print_timing: id 0 | task 12667 | prompt processing, n_tokens = 575, progress = 0.99, t = 5.46 s / 105.32 tokens per second 33.43.087.402 I slot print_timing: id 0 | task 12667 | n_gen = 100, tg = 10.18 t/s, tg_3s = 10.28 t/s 33.46.133.422 I slot print_timing: id 0 | task 12667 | n_gen = 131, tg = 10.18 t/s, tg_3s = 10.18 t/s 33.49.183.450 I slot print_timing: id 0 | task 12667 | n_gen = 162, tg = 10.18 t/s, tg_3s = 10.16 t/s 33.52.230.224 I slot print_timing: id 0 | task 12667 | n_gen = 193, tg = 10.18 t/s, tg_3s = 10.17 t/s 33.55.278.485 I slot print_timing: id 0 | task 12667 | n_gen = 224, tg = 10.17 t/s, tg_3s = 10.17 t/s 33.56.950.176 I slot print_timing: id 0 | task 12667 | prompt eval time = 7121.62 ms / 579 tokens ( 12.30 ms per token, 81.30 tokens per second) 33.56.950.182 I slot print_timing: id 0 | task 12667 | eval time = 23588.62 ms / 241 tokens ( 98.29 ms per token, 10.17 tokens per second) 33.56.950.183 I slot print_timing: id 0 | task 12667 | total time = 30710.24 ms / 820 tokens 33.56.950.183 I slot print_timing: id 0 | task 12667 | graphs reused = 12130 33.56.950.184 I slot print_timing: id 0 | task 12667 | graph reallocs = 0 / 0 (same size) / (changed size) 33.56.950.225 I slot release: id 0 | task 12667 | stop processing: n_tokens = 851, truncated = 0 33.56.955.042 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 851, t_last = 85255049862 33.56.955.090 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 935.396 MiB) 33.57.005.488 I slot launch_slot_: id 0 | task 12912 | processing task, is_child = 0 34.02.386.936 I slot print_timing: id 0 | task 12912 | prompt processing, n_tokens = 496, progress = 0.99, t = 5.38 s / 92.17 tokens per second 34.13.050.467 I slot print_timing: id 0 | task 12912 | n_gen = 100, tg = 10.19 t/s, tg_3s = 10.29 t/s 34.16.092.909 I slot print_timing: id 0 | task 12912 | n_gen = 131, tg = 10.19 t/s, tg_3s = 10.19 t/s 34.17.467.122 I slot print_timing: id 0 | task 12912 | prompt eval time = 6326.86 ms / 500 tokens ( 12.65 ms per token, 79.03 tokens per second) 34.17.467.127 I slot print_timing: id 0 | task 12912 | eval time = 14134.76 ms / 145 tokens ( 98.16 ms per token, 10.19 tokens per second) 34.17.467.128 I slot print_timing: id 0 | task 12912 | total time = 20461.62 ms / 645 tokens 34.17.467.128 I slot print_timing: id 0 | task 12912 | graphs reused = 12273 34.17.467.128 I slot print_timing: id 0 | task 12912 | graph reallocs = 0 / 0 (same size) / (changed size) 34.17.467.165 I slot release: id 0 | task 12912 | stop processing: n_tokens = 676, truncated = 0 34.17.472.414 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 676, t_last = 85275566802 34.17.472.451 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 931.144 MiB) 34.17.518.559 I slot launch_slot_: id 0 | task 13060 | processing task, is_child = 0 34.20.773.708 I slot print_timing: id 0 | task 13060 | prompt processing, n_tokens = 613, progress = 0.80, t = 3.26 s / 188.32 tokens per second 34.25.067.153 I slot print_timing: id 0 | task 13060 | prompt processing, n_tokens = 772, progress = 1.00, t = 7.55 s / 102.27 tokens per second 34.36.834.237 I slot print_timing: id 0 | task 13060 | n_gen = 100, tg = 10.17 t/s, tg_3s = 10.27 t/s 34.39.883.567 I slot print_timing: id 0 | task 13060 | n_gen = 131, tg = 10.17 t/s, tg_3s = 10.17 t/s 34.42.932.893 I slot print_timing: id 0 | task 13060 | n_gen = 162, tg = 10.17 t/s, tg_3s = 10.17 t/s 34.45.983.103 I slot print_timing: id 0 | task 13060 | n_gen = 193, tg = 10.17 t/s, tg_3s = 10.16 t/s 34.48.938.635 I slot print_timing: id 0 | task 13060 | prompt eval time = 9582.47 ms / 776 tokens ( 12.35 ms per token, 80.98 tokens per second) 34.48.938.637 I slot print_timing: id 0 | task 13060 | eval time = 21837.59 ms / 223 tokens ( 98.37 ms per token, 10.17 tokens per second) 34.48.938.638 I slot print_timing: id 0 | task 13060 | total time = 31420.07 ms / 999 tokens 34.48.938.639 I slot print_timing: id 0 | task 13060 | graphs reused = 12493 34.48.938.640 I slot print_timing: id 0 | task 13060 | graph reallocs = 0 / 0 (same size) / (changed size) 34.48.938.678 I slot release: id 0 | task 13060 | stop processing: n_tokens = 1030, truncated = 0 34.48.943.813 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1030, t_last = 85307038315 34.48.943.865 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 935.521 MiB) 34.48.943.869 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 930.519 MiB) 34.48.994.913 I slot launch_slot_: id 0 | task 13287 | processing task, is_child = 0 34.54.026.369 I slot print_timing: id 0 | task 13287 | prompt processing, n_tokens = 500, progress = 0.99, t = 5.03 s / 99.38 tokens per second 35.05.055.919 I slot print_timing: id 0 | task 13287 | n_gen = 100, tg = 10.19 t/s, tg_3s = 10.29 t/s 35.08.097.310 I slot print_timing: id 0 | task 13287 | n_gen = 131, tg = 10.19 t/s, tg_3s = 10.19 t/s 35.11.142.313 I slot print_timing: id 0 | task 13287 | n_gen = 162, tg = 10.19 t/s, tg_3s = 10.18 t/s 35.14.188.824 I slot print_timing: id 0 | task 13287 | n_gen = 193, tg = 10.18 t/s, tg_3s = 10.18 t/s 35.14.581.920 I slot print_timing: id 0 | task 13287 | prompt eval time = 6341.32 ms / 504 tokens ( 12.58 ms per token, 79.48 tokens per second) 35.14.581.926 I slot print_timing: id 0 | task 13287 | eval time = 19245.68 ms / 197 tokens ( 98.19 ms per token, 10.18 tokens per second) 35.14.581.926 I slot print_timing: id 0 | task 13287 | total time = 25587.00 ms / 701 tokens 35.14.581.926 I slot print_timing: id 0 | task 13287 | graphs reused = 12688 35.14.581.927 I slot print_timing: id 0 | task 13287 | graph reallocs = 0 / 0 (same size) / (changed size) 35.14.581.958 I slot release: id 0 | task 13287 | stop processing: n_tokens = 732, truncated = 0 35.14.587.082 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 732, t_last = 85332681595 35.14.587.118 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 928.456 MiB) 35.14.609.611 I slot launch_slot_: id 0 | task 13487 | processing task, is_child = 0 35.20.768.848 I slot print_timing: id 0 | task 13487 | prompt processing, n_tokens = 629, progress = 0.99, t = 6.16 s / 102.12 tokens per second 35.32.163.941 I slot print_timing: id 0 | task 13487 | n_gen = 100, tg = 10.17 t/s, tg_3s = 10.27 t/s 35.35.213.112 I slot print_timing: id 0 | task 13487 | n_gen = 131, tg = 10.17 t/s, tg_3s = 10.17 t/s 35.38.260.495 I slot print_timing: id 0 | task 13487 | n_gen = 162, tg = 10.17 t/s, tg_3s = 10.17 t/s 35.40.325.606 I slot print_timing: id 0 | task 13487 | prompt eval time = 7818.60 ms / 633 tokens ( 12.35 ms per token, 80.96 tokens per second) 35.40.325.612 I slot print_timing: id 0 | task 13487 | eval time = 17897.38 ms / 183 tokens ( 98.34 ms per token, 10.17 tokens per second) 35.40.325.613 I slot print_timing: id 0 | task 13487 | total time = 25715.99 ms / 816 tokens 35.40.325.613 I slot print_timing: id 0 | task 13487 | graphs reused = 12868 35.40.325.614 I slot print_timing: id 0 | task 13487 | graph reallocs = 0 / 0 (same size) / (changed size) 35.40.325.650 I slot release: id 0 | task 13487 | stop processing: n_tokens = 847, truncated = 0 35.40.330.344 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 847, t_last = 85358425287 35.40.330.387 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1093.463 MiB) 35.40.382.127 I slot launch_slot_: id 0 | task 13674 | processing task, is_child = 0 35.44.370.339 I slot print_timing: id 0 | task 13674 | prompt processing, n_tokens = 391, progress = 0.99, t = 3.99 s / 98.04 tokens per second 35.54.055.055 I slot print_timing: id 0 | task 13674 | prompt eval time = 4934.49 ms / 395 tokens ( 12.49 ms per token, 80.05 tokens per second) 35.54.055.061 I slot print_timing: id 0 | task 13674 | eval time = 8738.42 ms / 90 tokens ( 98.18 ms per token, 10.18 tokens per second) 35.54.055.062 I slot print_timing: id 0 | task 13674 | total time = 13672.92 ms / 485 tokens 35.54.055.062 I slot print_timing: id 0 | task 13674 | graphs reused = 12955 35.54.055.063 I slot print_timing: id 0 | task 13674 | graph reallocs = 0 / 0 (same size) / (changed size) 35.54.055.106 I slot release: id 0 | task 13674 | stop processing: n_tokens = 516, truncated = 0 35.54.059.907 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 516, t_last = 85372154743 35.54.059.938 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1111.719 MiB) 35.54.081.972 I slot launch_slot_: id 0 | task 13767 | processing task, is_child = 0 35.59.913.158 I slot print_timing: id 0 | task 13767 | prompt processing, n_tokens = 580, progress = 0.99, t = 5.83 s / 99.47 tokens per second 36.11.282.446 I slot print_timing: id 0 | task 13767 | n_gen = 100, tg = 10.17 t/s, tg_3s = 10.28 t/s 36.14.327.904 I slot print_timing: id 0 | task 13767 | n_gen = 131, tg = 10.18 t/s, tg_3s = 10.18 t/s 36.17.382.692 I slot print_timing: id 0 | task 13767 | n_gen = 162, tg = 10.17 t/s, tg_3s = 10.15 t/s 36.20.429.573 I slot print_timing: id 0 | task 13767 | n_gen = 193, tg = 10.17 t/s, tg_3s = 10.17 t/s 36.23.476.392 I slot print_timing: id 0 | task 13767 | n_gen = 224, tg = 10.17 t/s, tg_3s = 10.17 t/s 36.23.966.837 I slot print_timing: id 0 | task 13767 | prompt eval time = 7470.51 ms / 584 tokens ( 12.79 ms per token, 78.17 tokens per second) 36.23.966.841 I slot print_timing: id 0 | task 13767 | eval time = 22414.35 ms / 229 tokens ( 98.31 ms per token, 10.17 tokens per second) 36.23.966.841 I slot print_timing: id 0 | task 13767 | total time = 29884.86 ms / 813 tokens 36.23.966.842 I slot print_timing: id 0 | task 13767 | graphs reused = 13181 36.23.966.842 I slot print_timing: id 0 | task 13767 | graph reallocs = 0 / 0 (same size) / (changed size) 36.23.966.892 I slot release: id 0 | task 13767 | stop processing: n_tokens = 844, truncated = 0 36.23.971.983 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 844, t_last = 85402066529 36.23.972.024 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1104.592 MiB) 36.23.997.645 I slot launch_slot_: id 0 | task 14000 | processing task, is_child = 0 36.30.180.101 I slot print_timing: id 0 | task 14000 | prompt processing, n_tokens = 691, progress = 0.99, t = 6.18 s / 111.77 tokens per second 36.42.281.802 I slot print_timing: id 0 | task 14000 | n_gen = 100, tg = 10.17 t/s, tg_3s = 10.27 t/s 36.45.327.985 I slot print_timing: id 0 | task 14000 | n_gen = 131, tg = 10.17 t/s, tg_3s = 10.18 t/s 36.48.373.796 I slot print_timing: id 0 | task 14000 | n_gen = 162, tg = 10.17 t/s, tg_3s = 10.18 t/s 36.51.421.871 I slot print_timing: id 0 | task 14000 | n_gen = 193, tg = 10.17 t/s, tg_3s = 10.17 t/s 36.54.469.618 I slot print_timing: id 0 | task 14000 | n_gen = 224, tg = 10.17 t/s, tg_3s = 10.17 t/s 36.57.517.259 I slot print_timing: id 0 | task 14000 | n_gen = 255, tg = 10.17 t/s, tg_3s = 10.17 t/s 36.57.910.071 I slot print_timing: id 0 | task 14000 | prompt eval time = 8548.59 ms / 695 tokens ( 12.30 ms per token, 81.30 tokens per second) 36.57.910.076 I slot print_timing: id 0 | task 14000 | eval time = 25363.82 ms / 259 tokens ( 98.31 ms per token, 10.17 tokens per second) 36.57.910.077 I slot print_timing: id 0 | task 14000 | total time = 33912.42 ms / 954 tokens 36.57.910.077 I slot print_timing: id 0 | task 14000 | graphs reused = 13437 36.57.910.077 I slot print_timing: id 0 | task 14000 | graph reallocs = 0 / 0 (same size) / (changed size) 36.57.910.111 I slot release: id 0 | task 14000 | stop processing: n_tokens = 985, truncated = 0 36.57.915.446 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 985, t_last = 85436009748 36.57.915.489 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1100.590 MiB) 36.57.941.534 I slot launch_slot_: id 0 | task 14263 | processing task, is_child = 0 37.05.518.215 I slot print_timing: id 0 | task 14263 | prompt processing, n_tokens = 765, progress = 1.00, t = 7.58 s / 100.97 tokens per second 37.15.448.927 I slot print_timing: id 0 | task 14263 | prompt eval time = 9243.64 ms / 769 tokens ( 12.02 ms per token, 83.19 tokens per second) 37.15.448.932 I slot print_timing: id 0 | task 14263 | eval time = 8263.74 ms / 85 tokens ( 98.38 ms per token, 10.16 tokens per second) 37.15.448.932 I slot print_timing: id 0 | task 14263 | total time = 17507.38 ms / 854 tokens 37.15.448.933 I slot print_timing: id 0 | task 14263 | graphs reused = 13520 37.15.448.933 I slot print_timing: id 0 | task 14263 | graph reallocs = 0 / 0 (same size) / (changed size) 37.15.448.969 I slot release: id 0 | task 14263 | stop processing: n_tokens = 885, truncated = 0 37.15.454.184 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 885, t_last = 85453548606 37.15.454.231 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 940.023 MiB) 37.15.505.872 I slot launch_slot_: id 0 | task 14352 | processing task, is_child = 0 37.21.330.132 I slot print_timing: id 0 | task 14352 | prompt processing, n_tokens = 572, progress = 0.99, t = 5.82 s / 98.21 tokens per second 37.32.367.687 I slot print_timing: id 0 | task 14352 | n_gen = 100, tg = 10.18 t/s, tg_3s = 10.28 t/s 37.35.413.319 I slot print_timing: id 0 | task 14352 | n_gen = 131, tg = 10.18 t/s, tg_3s = 10.18 t/s 37.37.772.774 I slot print_timing: id 0 | task 14352 | prompt eval time = 7137.19 ms / 576 tokens ( 12.39 ms per token, 80.70 tokens per second) 37.37.772.776 I slot print_timing: id 0 | task 14352 | eval time = 15129.69 ms / 155 tokens ( 98.24 ms per token, 10.18 tokens per second) 37.37.772.776 I slot print_timing: id 0 | task 14352 | total time = 22266.88 ms / 731 tokens 37.37.772.776 I slot print_timing: id 0 | task 14352 | graphs reused = 13673 37.37.772.777 I slot print_timing: id 0 | task 14352 | graph reallocs = 0 / 0 (same size) / (changed size) 37.37.772.819 I slot release: id 0 | task 14352 | stop processing: n_tokens = 762, truncated = 0 37.37.778.531 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 762, t_last = 85475872456 37.37.778.579 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1111.782 MiB) 37.37.803.974 I slot launch_slot_: id 0 | task 14511 | processing task, is_child = 0 37.43.955.689 I slot print_timing: id 0 | task 14511 | prompt processing, n_tokens = 651, progress = 0.99, t = 6.15 s / 105.82 tokens per second 37.54.914.953 I slot print_timing: id 0 | task 14511 | prompt eval time = 8158.33 ms / 655 tokens ( 12.46 ms per token, 80.29 tokens per second) 37.54.914.958 I slot print_timing: id 0 | task 14511 | eval time = 8952.64 ms / 92 tokens ( 98.38 ms per token, 10.16 tokens per second) 37.54.914.958 I slot print_timing: id 0 | task 14511 | total time = 17110.96 ms / 747 tokens 37.54.914.959 I slot print_timing: id 0 | task 14511 | graphs reused = 13762 37.54.914.959 I slot print_timing: id 0 | task 14511 | graph reallocs = 0 / 0 (same size) / (changed size) 37.54.914.995 I slot release: id 0 | task 14511 | stop processing: n_tokens = 778, truncated = 0 37.54.920.199 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 778, t_last = 85493014632 37.54.920.240 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 943.524 MiB) 37.54.946.458 I slot launch_slot_: id 0 | task 14607 | processing task, is_child = 0 38.01.104.026 I slot print_timing: id 0 | task 14607 | prompt processing, n_tokens = 617, progress = 0.99, t = 6.16 s / 100.20 tokens per second 38.12.490.498 I slot print_timing: id 0 | task 14607 | n_gen = 100, tg = 10.17 t/s, tg_3s = 10.28 t/s 38.15.541.153 I slot print_timing: id 0 | task 14607 | n_gen = 131, tg = 10.17 t/s, tg_3s = 10.16 t/s 38.16.229.547 I slot print_timing: id 0 | task 14607 | prompt eval time = 7812.54 ms / 621 tokens ( 12.58 ms per token, 79.49 tokens per second) 38.16.229.552 I slot print_timing: id 0 | task 14607 | eval time = 13470.54 ms / 138 tokens ( 98.33 ms per token, 10.17 tokens per second) 38.16.229.552 I slot print_timing: id 0 | task 14607 | total time = 21283.08 ms / 759 tokens 38.16.229.553 I slot print_timing: id 0 | task 14607 | graphs reused = 13897 38.16.229.553 I slot print_timing: id 0 | task 14607 | graph reallocs = 0 / 0 (same size) / (changed size) 38.16.229.594 I slot release: id 0 | task 14607 | stop processing: n_tokens = 790, truncated = 0 38.16.234.996 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 790, t_last = 85514329231 38.16.235.036 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1100.340 MiB) 38.16.260.734 I slot launch_slot_: id 0 | task 14749 | processing task, is_child = 0 38.23.483.635 I slot print_timing: id 0 | task 14749 | prompt processing, n_tokens = 763, progress = 0.99, t = 7.22 s / 105.64 tokens per second 38.35.241.421 I slot print_timing: id 0 | task 14749 | n_gen = 100, tg = 10.17 t/s, tg_3s = 10.27 t/s 38.38.290.046 I slot print_timing: id 0 | task 14749 | n_gen = 131, tg = 10.17 t/s, tg_3s = 10.17 t/s 38.41.356.763 I slot print_timing: id 0 | task 14749 | n_gen = 162, tg = 10.16 t/s, tg_3s = 10.11 t/s 38.44.407.356 I slot print_timing: id 0 | task 14749 | n_gen = 193, tg = 10.16 t/s, tg_3s = 10.16 t/s 38.45.391.472 I slot print_timing: id 0 | task 14749 | prompt eval time = 9244.73 ms / 767 tokens ( 12.05 ms per token, 82.97 tokens per second) 38.45.391.478 I slot print_timing: id 0 | task 14749 | eval time = 19886.00 ms / 203 tokens ( 98.45 ms per token, 10.16 tokens per second) 38.45.391.478 I slot print_timing: id 0 | task 14749 | total time = 29130.73 ms / 970 tokens 38.45.391.479 I slot print_timing: id 0 | task 14749 | graphs reused = 14098 38.45.391.479 I slot print_timing: id 0 | task 14749 | graph reallocs = 0 / 0 (same size) / (changed size) 38.45.391.522 I slot release: id 0 | task 14749 | stop processing: n_tokens = 1001, truncated = 0 38.45.397.233 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1001, t_last = 85543491159 38.45.397.276 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 930.019 MiB) 38.45.434.417 I slot launch_slot_: id 0 | task 14956 | processing task, is_child = 0 38.49.424.761 I slot print_timing: id 0 | task 14956 | prompt processing, n_tokens = 686, progress = 0.80, t = 3.99 s / 171.92 tokens per second 38.53.412.379 I slot print_timing: id 0 | task 14956 | prompt processing, n_tokens = 860, progress = 1.00, t = 7.98 s / 107.80 tokens per second 39.05.523.704 I slot print_timing: id 0 | task 14956 | n_gen = 100, tg = 10.16 t/s, tg_3s = 10.27 t/s 39.08.577.891 I slot print_timing: id 0 | task 14956 | n_gen = 131, tg = 10.16 t/s, tg_3s = 10.15 t/s 39.11.643.042 I slot print_timing: id 0 | task 14956 | n_gen = 162, tg = 10.15 t/s, tg_3s = 10.11 t/s 39.14.694.024 I slot print_timing: id 0 | task 14956 | n_gen = 193, tg = 10.15 t/s, tg_3s = 10.16 t/s 39.17.351.096 I slot print_timing: id 0 | task 14956 | prompt eval time = 10349.56 ms / 864 tokens ( 11.98 ms per token, 83.48 tokens per second) 39.17.351.099 I slot print_timing: id 0 | task 14956 | eval time = 21567.11 ms / 220 tokens ( 98.48 ms per token, 10.15 tokens per second) 39.17.351.099 I slot print_timing: id 0 | task 14956 | total time = 31916.67 ms / 1084 tokens 39.17.351.100 I slot print_timing: id 0 | task 14956 | graphs reused = 14315 39.17.351.100 I slot print_timing: id 0 | task 14956 | graph reallocs = 0 / 0 (same size) / (changed size) 39.17.351.142 I slot release: id 0 | task 14956 | stop processing: n_tokens = 1115, truncated = 0 39.17.357.101 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1115, t_last = 85575450780 39.17.357.157 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1100.153 MiB) 39.17.397.704 I slot launch_slot_: id 0 | task 15180 | processing task, is_child = 0 39.23.902.247 I slot print_timing: id 0 | task 15180 | prompt processing, n_tokens = 642, progress = 0.99, t = 6.50 s / 98.70 tokens per second 39.35.297.410 I slot print_timing: id 0 | task 15180 | n_gen = 100, tg = 10.17 t/s, tg_3s = 10.27 t/s 39.38.147.900 I slot print_timing: id 0 | task 15180 | prompt eval time = 8163.82 ms / 646 tokens ( 12.64 ms per token, 79.13 tokens per second) 39.38.147.906 I slot print_timing: id 0 | task 15180 | eval time = 12586.36 ms / 129 tokens ( 98.33 ms per token, 10.17 tokens per second) 39.38.147.906 I slot print_timing: id 0 | task 15180 | total time = 20750.18 ms / 775 tokens 39.38.147.906 I slot print_timing: id 0 | task 15180 | graphs reused = 14441 39.38.147.907 I slot print_timing: id 0 | task 15180 | graph reallocs = 0 / 0 (same size) / (changed size) 39.38.147.945 I slot release: id 0 | task 15180 | stop processing: n_tokens = 806, truncated = 0 39.38.153.108 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 806, t_last = 85596247582 39.38.153.146 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1108.968 MiB) 39.38.178.789 I slot launch_slot_: id 0 | task 15313 | processing task, is_child = 0 39.45.050.564 I slot print_timing: id 0 | task 15313 | prompt processing, n_tokens = 716, progress = 0.99, t = 6.87 s / 104.19 tokens per second 39.56.799.269 I slot print_timing: id 0 | task 15313 | n_gen = 100, tg = 10.17 t/s, tg_3s = 10.27 t/s 39.59.846.699 I slot print_timing: id 0 | task 15313 | n_gen = 131, tg = 10.17 t/s, tg_3s = 10.17 t/s 40.02.908.041 I slot print_timing: id 0 | task 15313 | n_gen = 162, tg = 10.16 t/s, tg_3s = 10.13 t/s 40.05.971.881 I slot print_timing: id 0 | task 15313 | n_gen = 193, tg = 10.15 t/s, tg_3s = 10.12 t/s 40.09.023.119 I slot print_timing: id 0 | task 15313 | n_gen = 224, tg = 10.15 t/s, tg_3s = 10.16 t/s 40.10.892.769 I slot print_timing: id 0 | task 15313 | prompt eval time = 8881.77 ms / 720 tokens ( 12.34 ms per token, 81.06 tokens per second) 40.10.892.771 I slot print_timing: id 0 | task 15313 | eval time = 23832.20 ms / 243 tokens ( 98.48 ms per token, 10.15 tokens per second) 40.10.892.772 I slot print_timing: id 0 | task 15313 | total time = 32713.97 ms / 963 tokens 40.10.892.772 I slot print_timing: id 0 | task 15313 | graphs reused = 14681 40.10.892.772 I slot print_timing: id 0 | task 15313 | graph reallocs = 0 / 0 (same size) / (changed size) 40.10.892.811 I slot release: id 0 | task 15313 | stop processing: n_tokens = 994, truncated = 0 40.10.897.459 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 994, t_last = 85628992448 40.10.897.520 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1102.716 MiB) 40.10.923.685 I slot launch_slot_: id 0 | task 15560 | processing task, is_child = 0 40.15.613.339 I slot print_timing: id 0 | task 15560 | prompt processing, n_tokens = 505, progress = 0.99, t = 4.69 s / 107.68 tokens per second 40.26.974.061 I slot print_timing: id 0 | task 15560 | n_gen = 100, tg = 10.18 t/s, tg_3s = 10.29 t/s 40.30.017.244 I slot print_timing: id 0 | task 15560 | n_gen = 131, tg = 10.19 t/s, tg_3s = 10.19 t/s 40.33.062.935 I slot print_timing: id 0 | task 15560 | n_gen = 162, tg = 10.18 t/s, tg_3s = 10.18 t/s 40.36.110.382 I slot print_timing: id 0 | task 15560 | n_gen = 193, tg = 10.18 t/s, tg_3s = 10.17 t/s 40.38.174.951 I slot print_timing: id 0 | task 15560 | prompt eval time = 6330.10 ms / 509 tokens ( 12.44 ms per token, 80.41 tokens per second) 40.38.174.953 I slot print_timing: id 0 | task 15560 | eval time = 20921.16 ms / 214 tokens ( 98.22 ms per token, 10.18 tokens per second) 40.38.174.955 I slot print_timing: id 0 | task 15560 | total time = 27251.25 ms / 723 tokens 40.38.174.955 I slot print_timing: id 0 | task 15560 | graphs reused = 14893 40.38.174.955 I slot print_timing: id 0 | task 15560 | graph reallocs = 0 / 0 (same size) / (changed size) 40.38.174.987 I slot release: id 0 | task 15560 | stop processing: n_tokens = 754, truncated = 0 40.38.180.704 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 754, t_last = 85656274625 40.38.180.751 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1095.026 MiB) 40.38.202.882 I slot launch_slot_: id 0 | task 15777 | processing task, is_child = 0 40.44.023.024 I slot print_timing: id 0 | task 15777 | prompt processing, n_tokens = 577, progress = 0.99, t = 5.82 s / 99.14 tokens per second 40.55.386.253 I slot print_timing: id 0 | task 15777 | n_gen = 100, tg = 10.18 t/s, tg_3s = 10.29 t/s 40.58.432.134 I slot print_timing: id 0 | task 15777 | n_gen = 131, tg = 10.18 t/s, tg_3s = 10.18 t/s 41.01.485.040 I slot print_timing: id 0 | task 15777 | n_gen = 162, tg = 10.18 t/s, tg_3s = 10.15 t/s 41.04.532.807 I slot print_timing: id 0 | task 15777 | n_gen = 193, tg = 10.18 t/s, tg_3s = 10.17 t/s 41.07.579.005 I slot print_timing: id 0 | task 15777 | n_gen = 224, tg = 10.18 t/s, tg_3s = 10.18 t/s 41.09.348.429 I slot print_timing: id 0 | task 15777 | prompt eval time = 7462.42 ms / 581 tokens ( 12.84 ms per token, 77.86 tokens per second) 41.09.348.432 I slot print_timing: id 0 | task 15777 | eval time = 23683.12 ms / 242 tokens ( 98.27 ms per token, 10.18 tokens per second) 41.09.348.432 I slot print_timing: id 0 | task 15777 | total time = 31145.54 ms / 823 tokens 41.09.348.433 I slot print_timing: id 0 | task 15777 | graphs reused = 15132 41.09.348.433 I slot print_timing: id 0 | task 15777 | graph reallocs = 0 / 0 (same size) / (changed size) 41.09.348.467 I slot release: id 0 | task 15777 | stop processing: n_tokens = 854, truncated = 0 41.09.354.655 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 854, t_last = 85687448104 41.09.354.696 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1096.026 MiB) 41.09.380.405 I slot launch_slot_: id 0 | task 16023 | processing task, is_child = 0 41.14.069.880 I slot print_timing: id 0 | task 16023 | prompt processing, n_tokens = 741, progress = 0.81, t = 4.69 s / 158.01 tokens per second 41.18.057.166 I slot print_timing: id 0 | task 16023 | prompt processing, n_tokens = 921, progress = 1.00, t = 8.68 s / 106.15 tokens per second 41.30.182.213 I slot print_timing: id 0 | task 16023 | n_gen = 100, tg = 10.16 t/s, tg_3s = 10.26 t/s 41.33.237.308 I slot print_timing: id 0 | task 16023 | n_gen = 131, tg = 10.15 t/s, tg_3s = 10.15 t/s 41.36.291.318 I slot print_timing: id 0 | task 16023 | n_gen = 162, tg = 10.15 t/s, tg_3s = 10.15 t/s 41.39.343.627 I slot print_timing: id 0 | task 16023 | n_gen = 193, tg = 10.15 t/s, tg_3s = 10.16 t/s 41.42.395.236 I slot print_timing: id 0 | task 16023 | n_gen = 224, tg = 10.15 t/s, tg_3s = 10.16 t/s 41.43.872.066 I slot print_timing: id 0 | task 16023 | prompt eval time = 11054.63 ms / 925 tokens ( 11.95 ms per token, 83.68 tokens per second) 41.43.872.071 I slot print_timing: id 0 | task 16023 | eval time = 23437.02 ms / 239 tokens ( 98.47 ms per token, 10.15 tokens per second) 41.43.872.072 I slot print_timing: id 0 | task 16023 | total time = 34491.65 ms / 1164 tokens 41.43.872.072 I slot print_timing: id 0 | task 16023 | graphs reused = 15368 41.43.872.073 I slot print_timing: id 0 | task 16023 | graph reallocs = 0 / 0 (same size) / (changed size) 41.43.872.126 I slot release: id 0 | task 16023 | stop processing: n_tokens = 1195, truncated = 0 41.43.878.379 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1195, t_last = 85721971763 41.43.878.431 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1096.776 MiB) 41.43.919.289 I slot launch_slot_: id 0 | task 16266 | processing task, is_child = 0 41.48.226.799 I slot print_timing: id 0 | task 16266 | prompt processing, n_tokens = 743, progress = 0.85, t = 4.31 s / 172.49 tokens per second 41.52.547.771 I slot print_timing: id 0 | task 16266 | prompt processing, n_tokens = 881, progress = 1.00, t = 8.63 s / 102.10 tokens per second 42.04.301.435 I slot print_timing: id 0 | task 16266 | n_gen = 100, tg = 10.16 t/s, tg_3s = 10.27 t/s 42.07.355.920 I slot print_timing: id 0 | task 16266 | n_gen = 131, tg = 10.16 t/s, tg_3s = 10.15 t/s 42.10.420.694 I slot print_timing: id 0 | task 16266 | n_gen = 162, tg = 10.15 t/s, tg_3s = 10.11 t/s 42.13.472.039 I slot print_timing: id 0 | task 16266 | n_gen = 193, tg = 10.15 t/s, tg_3s = 10.16 t/s 42.16.525.103 I slot print_timing: id 0 | task 16266 | n_gen = 224, tg = 10.15 t/s, tg_3s = 10.15 t/s 42.19.578.912 I slot print_timing: id 0 | task 16266 | n_gen = 255, tg = 10.15 t/s, tg_3s = 10.15 t/s 42.21.056.230 I slot print_timing: id 0 | task 16266 | prompt eval time = 10642.34 ms / 885 tokens ( 12.03 ms per token, 83.16 tokens per second) 42.21.056.232 I slot print_timing: id 0 | task 16266 | eval time = 26494.59 ms / 270 tokens ( 98.49 ms per token, 10.15 tokens per second) 42.21.056.233 I slot print_timing: id 0 | task 16266 | total time = 37136.93 ms / 1155 tokens 42.21.056.234 I slot print_timing: id 0 | task 16266 | graphs reused = 15635 42.21.056.234 I slot print_timing: id 0 | task 16266 | graph reallocs = 0 / 0 (same size) / (changed size) 42.21.056.278 I slot release: id 0 | task 16266 | stop processing: n_tokens = 1186, truncated = 0 42.21.061.123 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1186, t_last = 85759155915 42.21.061.177 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1109.969 MiB) 42.21.102.430 I slot launch_slot_: id 0 | task 16540 | processing task, is_child = 0 42.25.409.294 I slot print_timing: id 0 | task 16540 | prompt processing, n_tokens = 388, progress = 0.99, t = 4.31 s / 90.09 tokens per second 42.35.734.104 I slot print_timing: id 0 | task 16540 | n_gen = 100, tg = 10.18 t/s, tg_3s = 10.29 t/s 42.38.774.438 I slot print_timing: id 0 | task 16540 | n_gen = 131, tg = 10.19 t/s, tg_3s = 10.20 t/s 42.41.816.907 I slot print_timing: id 0 | task 16540 | n_gen = 162, tg = 10.19 t/s, tg_3s = 10.19 t/s 42.42.899.478 I slot print_timing: id 0 | task 16540 | prompt eval time = 4911.19 ms / 392 tokens ( 12.53 ms per token, 79.82 tokens per second) 42.42.899.480 I slot print_timing: id 0 | task 16540 | eval time = 16885.84 ms / 173 tokens ( 98.17 ms per token, 10.19 tokens per second) 42.42.899.480 I slot print_timing: id 0 | task 16540 | total time = 21797.04 ms / 565 tokens 42.42.899.481 I slot print_timing: id 0 | task 16540 | graphs reused = 15805 42.42.899.481 I slot print_timing: id 0 | task 16540 | graph reallocs = 0 / 0 (same size) / (changed size) 42.42.899.507 I slot release: id 0 | task 16540 | stop processing: n_tokens = 596, truncated = 0 42.42.903.841 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 596, t_last = 85780999144 42.42.903.873 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1117.096 MiB) 42.42.926.078 I slot launch_slot_: id 0 | task 16716 | processing task, is_child = 0 42.46.545.760 I slot print_timing: id 0 | task 16716 | prompt processing, n_tokens = 327, progress = 0.99, t = 3.62 s / 90.34 tokens per second 42.56.737.677 I slot print_timing: id 0 | task 16716 | n_gen = 100, tg = 10.18 t/s, tg_3s = 10.28 t/s 42.59.793.204 I slot print_timing: id 0 | task 16716 | n_gen = 131, tg = 10.17 t/s, tg_3s = 10.15 t/s 43.02.741.191 I slot print_timing: id 0 | task 16716 | prompt eval time = 4083.08 ms / 331 tokens ( 12.34 ms per token, 81.07 tokens per second) 43.02.741.197 I slot print_timing: id 0 | task 16716 | eval time = 15732.02 ms / 161 tokens ( 98.33 ms per token, 10.17 tokens per second) 43.02.741.197 I slot print_timing: id 0 | task 16716 | total time = 19815.10 ms / 492 tokens 43.02.741.198 I slot print_timing: id 0 | task 16716 | graphs reused = 15963 43.02.741.198 I slot print_timing: id 0 | task 16716 | graph reallocs = 0 / 0 (same size) / (changed size) 43.02.741.225 I slot release: id 0 | task 16716 | stop processing: n_tokens = 523, truncated = 0 43.02.745.501 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 523, t_last = 85800840862 43.02.745.530 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1097.777 MiB) 43.02.767.475 I slot launch_slot_: id 0 | task 16880 | processing task, is_child = 0 43.06.737.316 I slot print_timing: id 0 | task 16880 | prompt processing, n_tokens = 353, progress = 0.99, t = 3.97 s / 88.92 tokens per second 43.17.064.656 I slot print_timing: id 0 | task 16880 | n_gen = 100, tg = 10.18 t/s, tg_3s = 10.29 t/s 43.20.109.577 I slot print_timing: id 0 | task 16880 | n_gen = 131, tg = 10.18 t/s, tg_3s = 10.18 t/s 43.21.977.018 I slot print_timing: id 0 | task 16880 | prompt eval time = 4575.33 ms / 357 tokens ( 12.82 ms per token, 78.03 tokens per second) 43.21.977.020 I slot print_timing: id 0 | task 16880 | eval time = 14634.20 ms / 150 tokens ( 98.22 ms per token, 10.18 tokens per second) 43.21.977.021 I slot print_timing: id 0 | task 16880 | total time = 19209.53 ms / 507 tokens 43.21.977.021 I slot print_timing: id 0 | task 16880 | graphs reused = 16110 43.21.977.022 I slot print_timing: id 0 | task 16880 | graph reallocs = 0 / 0 (same size) / (changed size) 43.21.977.046 I slot release: id 0 | task 16880 | stop processing: n_tokens = 538, truncated = 0 43.21.981.880 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 538, t_last = 85820076683 43.21.981.917 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1109.531 MiB) 43.22.004.440 I slot launch_slot_: id 0 | task 17033 | processing task, is_child = 0 43.25.611.886 I slot print_timing: id 0 | task 17033 | prompt processing, n_tokens = 311, progress = 0.99, t = 3.61 s / 86.21 tokens per second 43.35.794.219 I slot print_timing: id 0 | task 17033 | n_gen = 100, tg = 10.19 t/s, tg_3s = 10.29 t/s 43.36.971.920 I slot print_timing: id 0 | task 17033 | prompt eval time = 4072.35 ms / 315 tokens ( 12.93 ms per token, 77.35 tokens per second) 43.36.971.922 I slot print_timing: id 0 | task 17033 | eval time = 10895.12 ms / 112 tokens ( 98.15 ms per token, 10.19 tokens per second) 43.36.971.923 I slot print_timing: id 0 | task 17033 | total time = 14967.47 ms / 427 tokens 43.36.971.923 I slot print_timing: id 0 | task 17033 | graphs reused = 16220 43.36.971.924 I slot print_timing: id 0 | task 17033 | graph reallocs = 0 / 0 (same size) / (changed size) 43.36.971.946 I slot release: id 0 | task 17033 | stop processing: n_tokens = 458, truncated = 0 43.36.976.130 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 85835071583 43.37.033.799 I slot launch_slot_: id 0 | task 17148 | processing task, is_child = 0 43.41.018.073 I slot print_timing: id 0 | task 17148 | prompt processing, n_tokens = 374, progress = 0.99, t = 3.98 s / 93.87 tokens per second 43.47.745.642 I slot print_timing: id 0 | task 17148 | prompt eval time = 4921.36 ms / 378 tokens ( 13.02 ms per token, 76.81 tokens per second) 43.47.745.645 I slot print_timing: id 0 | task 17148 | eval time = 5790.48 ms / 60 tokens ( 98.14 ms per token, 10.19 tokens per second) 43.47.745.646 I slot print_timing: id 0 | task 17148 | total time = 10711.83 ms / 438 tokens 43.47.745.646 I slot print_timing: id 0 | task 17148 | graphs reused = 16278 43.47.745.647 I slot print_timing: id 0 | task 17148 | graph reallocs = 0 / 0 (same size) / (changed size) 43.47.745.672 I slot release: id 0 | task 17148 | stop processing: n_tokens = 469, truncated = 0 43.47.750.366 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 469, t_last = 85845845309 43.47.750.401 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 944.899 MiB) 43.47.772.304 I slot launch_slot_: id 0 | task 17211 | processing task, is_child = 0 43.51.042.635 I slot print_timing: id 0 | task 17211 | prompt processing, n_tokens = 291, progress = 0.99, t = 3.27 s / 88.98 tokens per second 43.54.295.701 I slot print_timing: id 0 | task 17211 | prompt eval time = 3873.59 ms / 295 tokens ( 13.13 ms per token, 76.16 tokens per second) 43.54.295.706 I slot print_timing: id 0 | task 17211 | eval time = 2649.80 ms / 28 tokens ( 98.14 ms per token, 10.19 tokens per second) 43.54.295.706 I slot print_timing: id 0 | task 17211 | total time = 6523.39 ms / 323 tokens 43.54.295.707 I slot print_timing: id 0 | task 17211 | graphs reused = 16304 43.54.295.707 I slot print_timing: id 0 | task 17211 | graph reallocs = 0 / 0 (same size) / (changed size) 43.54.295.732 I slot release: id 0 | task 17211 | stop processing: n_tokens = 354, truncated = 0 43.54.300.367 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 354, t_last = 85852395370 43.54.300.397 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1100.778 MiB) 43.54.326.913 I slot launch_slot_: id 0 | task 17242 | processing task, is_child = 0 43.57.953.956 I slot print_timing: id 0 | task 17242 | prompt processing, n_tokens = 333, progress = 0.99, t = 3.63 s / 91.81 tokens per second 44.06.377.400 I slot print_timing: id 0 | task 17242 | prompt eval time = 4092.28 ms / 337 tokens ( 12.14 ms per token, 82.35 tokens per second) 44.06.377.403 I slot print_timing: id 0 | task 17242 | eval time = 7958.18 ms / 82 tokens ( 98.25 ms per token, 10.18 tokens per second) 44.06.377.403 I slot print_timing: id 0 | task 17242 | total time = 12050.46 ms / 419 tokens 44.06.377.403 I slot print_timing: id 0 | task 17242 | graphs reused = 16384 44.06.377.404 I slot print_timing: id 0 | task 17242 | graph reallocs = 0 / 0 (same size) / (changed size) 44.06.377.432 I slot release: id 0 | task 17242 | stop processing: n_tokens = 450, truncated = 0 44.06.382.327 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 450, t_last = 85864477069 44.06.382.357 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1122.098 MiB) 44.06.405.048 I slot launch_slot_: id 0 | task 17327 | processing task, is_child = 0 44.10.018.031 I slot print_timing: id 0 | task 17327 | prompt processing, n_tokens = 321, progress = 0.99, t = 3.61 s / 88.85 tokens per second 44.20.348.170 I slot print_timing: id 0 | task 17327 | n_gen = 100, tg = 10.18 t/s, tg_3s = 10.28 t/s 44.23.395.636 I slot print_timing: id 0 | task 17327 | n_gen = 131, tg = 10.18 t/s, tg_3s = 10.17 t/s 44.24.670.722 I slot print_timing: id 0 | task 17327 | prompt eval time = 4218.06 ms / 325 tokens ( 12.98 ms per token, 77.05 tokens per second) 44.24.670.728 I slot print_timing: id 0 | task 17327 | eval time = 14047.61 ms / 144 tokens ( 98.24 ms per token, 10.18 tokens per second) 44.24.670.729 I slot print_timing: id 0 | task 17327 | total time = 18265.67 ms / 469 tokens 44.24.670.730 I slot print_timing: id 0 | task 17327 | graphs reused = 16526 44.24.670.730 I slot print_timing: id 0 | task 17327 | graph reallocs = 0 / 0 (same size) / (changed size) 44.24.670.754 I slot release: id 0 | task 17327 | stop processing: n_tokens = 500, truncated = 0 44.24.675.396 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.108 (> 0.100 thold), f_keep = 0.064 44.24.675.431 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1121.535 MiB) 44.24.697.655 I slot launch_slot_: id 0 | task 17474 | processing task, is_child = 0 44.37.326.178 I slot print_timing: id 0 | task 17474 | prompt eval time = 3504.31 ms / 264 tokens ( 13.27 ms per token, 75.34 tokens per second) 44.37.326.183 I slot print_timing: id 0 | task 17474 | eval time = 9124.20 ms / 94 tokens ( 98.11 ms per token, 10.19 tokens per second) 44.37.326.183 I slot print_timing: id 0 | task 17474 | total time = 12628.51 ms / 358 tokens 44.37.326.184 I slot print_timing: id 0 | task 17474 | graphs reused = 16618 44.37.326.184 I slot print_timing: id 0 | task 17474 | graph reallocs = 0 / 0 (same size) / (changed size) 44.37.326.205 I slot release: id 0 | task 17474 | stop processing: n_tokens = 389, truncated = 0 44.37.330.587 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 389, t_last = 85895425842 44.37.330.620 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 935.021 MiB) 44.37.357.801 I slot launch_slot_: id 0 | task 17571 | processing task, is_child = 0 44.40.973.011 I slot print_timing: id 0 | task 17571 | prompt processing, n_tokens = 327, progress = 0.99, t = 3.62 s / 90.45 tokens per second 44.43.157.522 I slot print_timing: id 0 | task 17571 | prompt eval time = 4219.53 ms / 331 tokens ( 12.75 ms per token, 78.44 tokens per second) 44.43.157.525 I slot print_timing: id 0 | task 17571 | eval time = 1580.18 ms / 17 tokens ( 98.76 ms per token, 10.13 tokens per second) 44.43.157.526 I slot print_timing: id 0 | task 17571 | total time = 5799.71 ms / 348 tokens 44.43.157.526 I slot print_timing: id 0 | task 17571 | graphs reused = 16633 44.43.157.527 I slot print_timing: id 0 | task 17571 | graph reallocs = 0 / 0 (same size) / (changed size) 44.43.157.550 I slot release: id 0 | task 17571 | stop processing: n_tokens = 379, truncated = 0 44.43.162.415 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 379, t_last = 85901257187 44.43.162.446 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 930.457 MiB) 44.43.188.423 I slot launch_slot_: id 0 | task 17591 | processing task, is_child = 0 44.46.809.023 I slot print_timing: id 0 | task 17591 | prompt processing, n_tokens = 329, progress = 0.99, t = 3.62 s / 90.87 tokens per second 44.57.133.565 I slot print_timing: id 0 | task 17591 | n_gen = 100, tg = 10.18 t/s, tg_3s = 10.28 t/s 45.00.176.786 I slot print_timing: id 0 | task 17591 | n_gen = 131, tg = 10.18 t/s, tg_3s = 10.19 t/s 45.02.337.305 I slot print_timing: id 0 | task 17591 | prompt eval time = 4221.40 ms / 333 tokens ( 12.68 ms per token, 78.88 tokens per second) 45.02.337.310 I slot print_timing: id 0 | task 17591 | eval time = 14927.47 ms / 153 tokens ( 98.21 ms per token, 10.18 tokens per second) 45.02.337.310 I slot print_timing: id 0 | task 17591 | total time = 19148.87 ms / 486 tokens 45.02.337.311 I slot print_timing: id 0 | task 17591 | graphs reused = 16783 45.02.337.311 I slot print_timing: id 0 | task 17591 | graph reallocs = 0 / 0 (same size) / (changed size) 45.02.337.336 I slot release: id 0 | task 17591 | stop processing: n_tokens = 517, truncated = 0 45.02.341.985 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 517, t_last = 85920436973 45.02.342.017 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 931.394 MiB) 45.02.364.681 I slot launch_slot_: id 0 | task 17747 | processing task, is_child = 0 45.05.976.560 I slot print_timing: id 0 | task 17747 | prompt processing, n_tokens = 342, progress = 0.99, t = 3.61 s / 94.69 tokens per second 45.16.636.762 I slot print_timing: id 0 | task 17747 | n_gen = 100, tg = 10.19 t/s, tg_3s = 10.29 t/s 45.19.683.163 I slot print_timing: id 0 | task 17747 | n_gen = 131, tg = 10.18 t/s, tg_3s = 10.18 t/s 45.22.729.636 I slot print_timing: id 0 | task 17747 | n_gen = 162, tg = 10.18 t/s, tg_3s = 10.18 t/s 45.25.774.570 I slot print_timing: id 0 | task 17747 | n_gen = 193, tg = 10.18 t/s, tg_3s = 10.18 t/s 45.28.819.516 I slot print_timing: id 0 | task 17747 | n_gen = 224, tg = 10.18 t/s, tg_3s = 10.18 t/s 45.31.865.635 I slot print_timing: id 0 | task 17747 | n_gen = 255, tg = 10.18 t/s, tg_3s = 10.18 t/s 45.34.911.534 I slot print_timing: id 0 | task 17747 | n_gen = 286, tg = 10.18 t/s, tg_3s = 10.18 t/s 45.37.957.077 I slot print_timing: id 0 | task 17747 | n_gen = 317, tg = 10.18 t/s, tg_3s = 10.18 t/s 45.41.001.392 I slot print_timing: id 0 | task 17747 | n_gen = 348, tg = 10.18 t/s, tg_3s = 10.18 t/s 45.44.047.552 I slot print_timing: id 0 | task 17747 | n_gen = 379, tg = 10.18 t/s, tg_3s = 10.18 t/s 45.47.096.469 I slot print_timing: id 0 | task 17747 | n_gen = 410, tg = 10.18 t/s, tg_3s = 10.17 t/s 45.50.144.894 I slot print_timing: id 0 | task 17747 | n_gen = 441, tg = 10.18 t/s, tg_3s = 10.17 t/s 45.50.243.161 I slot print_timing: id 0 | task 17747 | prompt eval time = 4553.89 ms / 346 tokens ( 13.16 ms per token, 75.98 tokens per second) 45.50.243.166 I slot print_timing: id 0 | task 17747 | eval time = 43324.58 ms / 442 tokens ( 98.24 ms per token, 10.18 tokens per second) 45.50.243.167 I slot print_timing: id 0 | task 17747 | total time = 47878.47 ms / 788 tokens 45.50.243.167 I slot print_timing: id 0 | task 17747 | graphs reused = 17221 45.50.243.168 I slot print_timing: id 0 | task 17747 | graph reallocs = 0 / 0 (same size) / (changed size) 45.50.243.194 I slot release: id 0 | task 17747 | stop processing: n_tokens = 819, truncated = 0 45.50.247.330 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 819, t_last = 85968342831 45.50.247.369 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 926.393 MiB) 45.50.275.955 I slot launch_slot_: id 0 | task 18192 | processing task, is_child = 0 45.53.890.845 I slot print_timing: id 0 | task 18192 | prompt processing, n_tokens = 321, progress = 0.99, t = 3.61 s / 88.80 tokens per second 45.59.069.086 I slot print_timing: id 0 | task 18192 | prompt eval time = 4080.70 ms / 325 tokens ( 12.56 ms per token, 79.64 tokens per second) 45.59.069.089 I slot print_timing: id 0 | task 18192 | eval time = 4712.42 ms / 49 tokens ( 98.18 ms per token, 10.19 tokens per second) 45.59.069.089 I slot print_timing: id 0 | task 18192 | total time = 8793.12 ms / 374 tokens 45.59.069.090 I slot print_timing: id 0 | task 18192 | graphs reused = 17268 45.59.069.090 I slot print_timing: id 0 | task 18192 | graph reallocs = 0 / 0 (same size) / (changed size) 45.59.069.114 I slot release: id 0 | task 18192 | stop processing: n_tokens = 405, truncated = 0 45.59.073.683 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 405, t_last = 85977168751 45.59.073.713 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 927.080 MiB) 45.59.096.264 I slot launch_slot_: id 0 | task 18244 | processing task, is_child = 0 46.02.708.166 I slot print_timing: id 0 | task 18244 | prompt processing, n_tokens = 318, progress = 0.99, t = 3.61 s / 88.04 tokens per second 46.13.045.726 I slot print_timing: id 0 | task 18244 | n_gen = 100, tg = 10.17 t/s, tg_3s = 10.27 t/s 46.16.091.379 I slot print_timing: id 0 | task 18244 | n_gen = 131, tg = 10.17 t/s, tg_3s = 10.18 t/s 46.19.142.475 I slot print_timing: id 0 | task 18244 | n_gen = 162, tg = 10.17 t/s, tg_3s = 10.16 t/s 46.22.188.134 I slot print_timing: id 0 | task 18244 | n_gen = 193, tg = 10.17 t/s, tg_3s = 10.18 t/s 46.25.238.968 I slot print_timing: id 0 | task 18244 | n_gen = 224, tg = 10.17 t/s, tg_3s = 10.16 t/s 46.28.291.508 I slot print_timing: id 0 | task 18244 | n_gen = 255, tg = 10.17 t/s, tg_3s = 10.16 t/s 46.31.341.015 I slot print_timing: id 0 | task 18244 | n_gen = 286, tg = 10.17 t/s, tg_3s = 10.17 t/s 46.32.420.020 I slot print_timing: id 0 | task 18244 | prompt eval time = 4214.05 ms / 322 tokens ( 13.09 ms per token, 76.41 tokens per second) 46.32.420.025 I slot print_timing: id 0 | task 18244 | eval time = 29109.69 ms / 297 tokens ( 98.34 ms per token, 10.17 tokens per second) 46.32.420.026 I slot print_timing: id 0 | task 18244 | total time = 33323.75 ms / 619 tokens 46.32.420.027 I slot print_timing: id 0 | task 18244 | graphs reused = 17562 46.32.420.027 I slot print_timing: id 0 | task 18244 | graph reallocs = 0 / 0 (same size) / (changed size) 46.32.420.050 I slot release: id 0 | task 18244 | stop processing: n_tokens = 650, truncated = 0 46.32.424.483 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 650, t_last = 86010519687 46.32.424.516 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 919.890 MiB) 46.32.446.725 I slot launch_slot_: id 0 | task 18544 | processing task, is_child = 0 46.36.072.550 I slot print_timing: id 0 | task 18544 | prompt processing, n_tokens = 334, progress = 0.99, t = 3.63 s / 92.12 tokens per second 46.46.407.592 I slot print_timing: id 0 | task 18544 | n_gen = 100, tg = 10.17 t/s, tg_3s = 10.27 t/s 46.49.460.966 I slot print_timing: id 0 | task 18544 | n_gen = 131, tg = 10.17 t/s, tg_3s = 10.15 t/s 46.52.511.993 I slot print_timing: id 0 | task 18544 | n_gen = 162, tg = 10.17 t/s, tg_3s = 10.16 t/s 46.55.557.920 I slot print_timing: id 0 | task 18544 | n_gen = 193, tg = 10.17 t/s, tg_3s = 10.18 t/s 46.58.604.636 I slot print_timing: id 0 | task 18544 | n_gen = 224, tg = 10.17 t/s, tg_3s = 10.17 t/s 47.01.650.906 I slot print_timing: id 0 | task 18544 | n_gen = 255, tg = 10.17 t/s, tg_3s = 10.18 t/s 47.04.698.813 I slot print_timing: id 0 | task 18544 | n_gen = 286, tg = 10.17 t/s, tg_3s = 10.17 t/s 47.07.748.795 I slot print_timing: id 0 | task 18544 | n_gen = 317, tg = 10.17 t/s, tg_3s = 10.16 t/s 47.10.800.475 I slot print_timing: id 0 | task 18544 | n_gen = 348, tg = 10.17 t/s, tg_3s = 10.16 t/s 47.13.851.738 I slot print_timing: id 0 | task 18544 | n_gen = 379, tg = 10.17 t/s, tg_3s = 10.16 t/s 47.16.911.430 I slot print_timing: id 0 | task 18544 | n_gen = 410, tg = 10.16 t/s, tg_3s = 10.13 t/s 47.19.961.664 I slot print_timing: id 0 | task 18544 | n_gen = 441, tg = 10.16 t/s, tg_3s = 10.16 t/s 47.23.014.361 I slot print_timing: id 0 | task 18544 | n_gen = 472, tg = 10.16 t/s, tg_3s = 10.15 t/s 47.26.067.914 I slot print_timing: id 0 | task 18544 | n_gen = 503, tg = 10.16 t/s, tg_3s = 10.15 t/s 47.29.116.905 I slot print_timing: id 0 | task 18544 | n_gen = 534, tg = 10.16 t/s, tg_3s = 10.17 t/s 47.30.989.857 I slot print_timing: id 0 | task 18544 | prompt eval time = 4227.97 ms / 338 tokens ( 12.51 ms per token, 79.94 tokens per second) 47.30.989.862 I slot print_timing: id 0 | task 18544 | eval time = 54315.15 ms / 553 tokens ( 98.40 ms per token, 10.16 tokens per second) 47.30.989.862 I slot print_timing: id 0 | task 18544 | total time = 58543.12 ms / 891 tokens 47.30.989.863 I slot print_timing: id 0 | task 18544 | graphs reused = 18111 47.30.989.863 I slot print_timing: id 0 | task 18544 | graph reallocs = 0 / 0 (same size) / (changed size) 47.30.989.891 I slot release: id 0 | task 18544 | stop processing: n_tokens = 922, truncated = 0 47.30.994.511 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 922, t_last = 86069089528 47.30.994.560 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 925.892 MiB) 47.31.023.134 I slot launch_slot_: id 0 | task 19100 | processing task, is_child = 0 47.34.653.122 I slot print_timing: id 0 | task 19100 | prompt processing, n_tokens = 343, progress = 0.99, t = 3.63 s / 94.49 tokens per second 47.44.988.761 I slot print_timing: id 0 | task 19100 | n_gen = 100, tg = 10.17 t/s, tg_3s = 10.27 t/s 47.48.037.198 I slot print_timing: id 0 | task 19100 | n_gen = 131, tg = 10.17 t/s, tg_3s = 10.17 t/s 47.51.087.928 I slot print_timing: id 0 | task 19100 | n_gen = 162, tg = 10.17 t/s, tg_3s = 10.16 t/s 47.54.137.262 I slot print_timing: id 0 | task 19100 | n_gen = 193, tg = 10.17 t/s, tg_3s = 10.17 t/s 47.57.182.348 I slot print_timing: id 0 | task 19100 | n_gen = 224, tg = 10.17 t/s, tg_3s = 10.18 t/s 48.00.227.817 I slot print_timing: id 0 | task 19100 | n_gen = 255, tg = 10.17 t/s, tg_3s = 10.18 t/s 48.03.271.456 I slot print_timing: id 0 | task 19100 | n_gen = 286, tg = 10.17 t/s, tg_3s = 10.19 t/s 48.06.319.910 I slot print_timing: id 0 | task 19100 | n_gen = 317, tg = 10.17 t/s, tg_3s = 10.17 t/s 48.09.373.440 I slot print_timing: id 0 | task 19100 | n_gen = 348, tg = 10.17 t/s, tg_3s = 10.15 t/s 48.12.428.508 I slot print_timing: id 0 | task 19100 | n_gen = 379, tg = 10.17 t/s, tg_3s = 10.15 t/s 48.15.478.773 I slot print_timing: id 0 | task 19100 | n_gen = 410, tg = 10.17 t/s, tg_3s = 10.16 t/s 48.18.531.613 I slot print_timing: id 0 | task 19100 | n_gen = 441, tg = 10.17 t/s, tg_3s = 10.15 t/s 48.21.586.552 I slot print_timing: id 0 | task 19100 | n_gen = 472, tg = 10.17 t/s, tg_3s = 10.15 t/s 48.24.636.069 I slot print_timing: id 0 | task 19100 | n_gen = 503, tg = 10.17 t/s, tg_3s = 10.17 t/s 48.27.684.965 I slot print_timing: id 0 | task 19100 | n_gen = 534, tg = 10.17 t/s, tg_3s = 10.17 t/s 48.30.740.837 I slot print_timing: id 0 | task 19100 | n_gen = 565, tg = 10.16 t/s, tg_3s = 10.14 t/s 48.33.794.123 I slot print_timing: id 0 | task 19100 | n_gen = 596, tg = 10.16 t/s, tg_3s = 10.15 t/s 48.36.853.112 I slot print_timing: id 0 | task 19100 | n_gen = 627, tg = 10.16 t/s, tg_3s = 10.13 t/s 48.39.910.589 I slot print_timing: id 0 | task 19100 | n_gen = 658, tg = 10.16 t/s, tg_3s = 10.14 t/s 48.42.961.997 I slot print_timing: id 0 | task 19100 | n_gen = 689, tg = 10.16 t/s, tg_3s = 10.16 t/s 48.46.016.567 I slot print_timing: id 0 | task 19100 | n_gen = 720, tg = 10.16 t/s, tg_3s = 10.15 t/s 48.49.068.010 I slot print_timing: id 0 | task 19100 | n_gen = 751, tg = 10.16 t/s, tg_3s = 10.16 t/s 48.52.122.684 I slot print_timing: id 0 | task 19100 | n_gen = 782, tg = 10.16 t/s, tg_3s = 10.15 t/s 48.55.176.592 I slot print_timing: id 0 | task 19100 | n_gen = 813, tg = 10.16 t/s, tg_3s = 10.15 t/s 48.58.229.598 I slot print_timing: id 0 | task 19100 | n_gen = 844, tg = 10.16 t/s, tg_3s = 10.15 t/s 49.01.283.733 I slot print_timing: id 0 | task 19100 | n_gen = 875, tg = 10.16 t/s, tg_3s = 10.15 t/s 49.01.382.209 I slot print_timing: id 0 | task 19100 | prompt eval time = 4231.65 ms / 347 tokens ( 12.19 ms per token, 82.00 tokens per second) 49.01.382.214 I slot print_timing: id 0 | task 19100 | eval time = 86127.41 ms / 876 tokens ( 98.43 ms per token, 10.16 tokens per second) 49.01.382.215 I slot print_timing: id 0 | task 19100 | total time = 90359.07 ms / 1223 tokens 49.01.382.216 I slot print_timing: id 0 | task 19100 | graphs reused = 18982 49.01.382.216 I slot print_timing: id 0 | task 19100 | graph reallocs = 0 / 0 (same size) / (changed size) 49.01.382.240 I slot release: id 0 | task 19100 | stop processing: n_tokens = 1254, truncated = 0 49.01.387.206 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1254, t_last = 86159481877 49.01.387.277 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 929.019 MiB) 49.01.425.853 I slot launch_slot_: id 0 | task 19979 | processing task, is_child = 0 49.05.043.373 I slot print_timing: id 0 | task 19979 | prompt processing, n_tokens = 327, progress = 0.99, t = 3.62 s / 90.39 tokens per second 49.11.043.943 I slot print_timing: id 0 | task 19979 | prompt eval time = 4219.17 ms / 331 tokens ( 12.75 ms per token, 78.45 tokens per second) 49.11.043.949 I slot print_timing: id 0 | task 19979 | eval time = 5398.91 ms / 56 tokens ( 98.16 ms per token, 10.19 tokens per second) 49.11.043.949 I slot print_timing: id 0 | task 19979 | total time = 9618.08 ms / 387 tokens 49.11.043.949 I slot print_timing: id 0 | task 19979 | graphs reused = 19036 49.11.043.950 I slot print_timing: id 0 | task 19979 | graph reallocs = 0 / 0 (same size) / (changed size) 49.11.043.973 I slot release: id 0 | task 19979 | stop processing: n_tokens = 418, truncated = 0 49.11.048.864 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 418, t_last = 86169143610 49.11.048.898 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 922.079 MiB) 49.11.075.756 I slot launch_slot_: id 0 | task 20038 | processing task, is_child = 0 49.14.655.227 I slot print_timing: id 0 | task 20038 | prompt processing, n_tokens = 341, progress = 0.99, t = 3.58 s / 95.27 tokens per second 49.24.974.713 I slot print_timing: id 0 | task 20038 | n_gen = 100, tg = 10.19 t/s, tg_3s = 10.29 t/s 49.28.019.834 I slot print_timing: id 0 | task 20038 | n_gen = 131, tg = 10.19 t/s, tg_3s = 10.18 t/s 49.31.064.793 I slot print_timing: id 0 | task 20038 | n_gen = 162, tg = 10.18 t/s, tg_3s = 10.18 t/s 49.33.916.536 I slot print_timing: id 0 | task 20038 | prompt eval time = 4180.47 ms / 345 tokens ( 12.12 ms per token, 82.53 tokens per second) 49.33.916.538 I slot print_timing: id 0 | task 20038 | eval time = 18660.30 ms / 191 tokens ( 98.21 ms per token, 10.18 tokens per second) 49.33.916.538 I slot print_timing: id 0 | task 20038 | total time = 22840.77 ms / 536 tokens 49.33.916.539 I slot print_timing: id 0 | task 20038 | graphs reused = 19224 49.33.916.539 I slot print_timing: id 0 | task 20038 | graph reallocs = 0 / 0 (same size) / (changed size) 49.33.916.565 I slot release: id 0 | task 20038 | stop processing: n_tokens = 567, truncated = 0 49.33.921.227 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 567, t_last = 86192016202 49.33.921.258 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 921.453 MiB) 49.33.943.538 I slot launch_slot_: id 0 | task 20232 | processing task, is_child = 0 49.37.553.039 I slot print_timing: id 0 | task 20232 | prompt processing, n_tokens = 316, progress = 0.99, t = 3.61 s / 87.55 tokens per second 49.47.886.779 I slot print_timing: id 0 | task 20232 | n_gen = 100, tg = 10.18 t/s, tg_3s = 10.28 t/s 49.48.673.263 I slot print_timing: id 0 | task 20232 | prompt eval time = 4214.76 ms / 320 tokens ( 13.17 ms per token, 75.92 tokens per second) 49.48.673.266 I slot print_timing: id 0 | task 20232 | eval time = 10514.95 ms / 108 tokens ( 98.27 ms per token, 10.18 tokens per second) 49.48.673.266 I slot print_timing: id 0 | task 20232 | total time = 14729.71 ms / 428 tokens 49.48.673.266 I slot print_timing: id 0 | task 20232 | graphs reused = 19330 49.48.673.267 I slot print_timing: id 0 | task 20232 | graph reallocs = 0 / 0 (same size) / (changed size) 49.48.673.290 I slot release: id 0 | task 20232 | stop processing: n_tokens = 459, truncated = 0 49.48.677.405 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 459, t_last = 86206772927 49.48.677.435 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 930.081 MiB) 49.48.698.982 I slot launch_slot_: id 0 | task 20343 | processing task, is_child = 0 49.51.974.199 I slot print_timing: id 0 | task 20343 | prompt processing, n_tokens = 293, progress = 0.99, t = 3.28 s / 89.46 tokens per second 49.55.675.454 I slot print_timing: id 0 | task 20343 | prompt eval time = 3737.43 ms / 297 tokens ( 12.58 ms per token, 79.47 tokens per second) 49.55.675.460 I slot print_timing: id 0 | task 20343 | eval time = 3239.03 ms / 34 tokens ( 98.15 ms per token, 10.19 tokens per second) 49.55.675.460 I slot print_timing: id 0 | task 20343 | total time = 6976.46 ms / 331 tokens 49.55.675.461 I slot print_timing: id 0 | task 20343 | graphs reused = 19362 49.55.675.462 I slot print_timing: id 0 | task 20343 | graph reallocs = 0 / 0 (same size) / (changed size) 49.55.675.487 I slot release: id 0 | task 20343 | stop processing: n_tokens = 362, truncated = 0 49.55.679.823 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 362, t_last = 86213775124 49.55.679.847 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 948.963 MiB) 49.55.705.496 I slot launch_slot_: id 0 | task 20380 | processing task, is_child = 0 49.59.333.488 I slot print_timing: id 0 | task 20380 | prompt processing, n_tokens = 339, progress = 0.99, t = 3.63 s / 93.44 tokens per second 50.09.660.105 I slot print_timing: id 0 | task 20380 | n_gen = 100, tg = 10.18 t/s, tg_3s = 10.28 t/s 50.12.707.305 I slot print_timing: id 0 | task 20380 | n_gen = 131, tg = 10.18 t/s, tg_3s = 10.17 t/s 50.15.759.700 I slot print_timing: id 0 | task 20380 | n_gen = 162, tg = 10.17 t/s, tg_3s = 10.16 t/s 50.18.316.398 I slot print_timing: id 0 | task 20380 | prompt eval time = 4227.76 ms / 343 tokens ( 12.33 ms per token, 81.13 tokens per second) 50.18.316.400 I slot print_timing: id 0 | task 20380 | eval time = 18383.13 ms / 188 tokens ( 98.31 ms per token, 10.17 tokens per second) 50.18.316.400 I slot print_timing: id 0 | task 20380 | total time = 22610.89 ms / 531 tokens 50.18.316.401 I slot print_timing: id 0 | task 20380 | graphs reused = 19547 50.18.316.401 I slot print_timing: id 0 | task 20380 | graph reallocs = 0 / 0 (same size) / (changed size) 50.18.316.427 I slot release: id 0 | task 20380 | stop processing: n_tokens = 562, truncated = 0 50.18.321.217 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 562, t_last = 86236416064 50.18.321.256 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 923.079 MiB) 50.18.344.028 I slot launch_slot_: id 0 | task 20571 | processing task, is_child = 0 50.22.340.839 I slot print_timing: id 0 | task 20571 | prompt processing, n_tokens = 367, progress = 0.99, t = 4.00 s / 91.82 tokens per second 50.32.665.513 I slot print_timing: id 0 | task 20571 | n_gen = 100, tg = 10.18 t/s, tg_3s = 10.28 t/s 50.35.717.210 I slot print_timing: id 0 | task 20571 | n_gen = 131, tg = 10.18 t/s, tg_3s = 10.16 t/s 50.38.760.185 I slot print_timing: id 0 | task 20571 | n_gen = 162, tg = 10.18 t/s, tg_3s = 10.19 t/s 50.40.135.606 I slot print_timing: id 0 | task 20571 | prompt eval time = 4598.12 ms / 371 tokens ( 12.39 ms per token, 80.69 tokens per second) 50.40.135.609 I slot print_timing: id 0 | task 20571 | eval time = 17193.45 ms / 176 tokens ( 98.25 ms per token, 10.18 tokens per second) 50.40.135.610 I slot print_timing: id 0 | task 20571 | total time = 21791.56 ms / 547 tokens 50.40.135.610 I slot print_timing: id 0 | task 20571 | graphs reused = 19720 50.40.135.611 I slot print_timing: id 0 | task 20571 | graph reallocs = 0 / 0 (same size) / (changed size) 50.40.135.642 I slot release: id 0 | task 20571 | stop processing: n_tokens = 578, truncated = 0 50.40.140.248 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 578, t_last = 86258235279 50.40.140.288 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 938.397 MiB) 50.40.162.937 I slot launch_slot_: id 0 | task 20750 | processing task, is_child = 0 50.43.430.285 I slot print_timing: id 0 | task 20750 | prompt processing, n_tokens = 288, progress = 0.99, t = 3.27 s / 88.15 tokens per second 50.53.753.198 I slot print_timing: id 0 | task 20750 | n_gen = 100, tg = 10.19 t/s, tg_3s = 10.29 t/s 50.56.793.391 I slot print_timing: id 0 | task 20750 | n_gen = 131, tg = 10.19 t/s, tg_3s = 10.20 t/s 50.59.834.638 I slot print_timing: id 0 | task 20750 | n_gen = 162, tg = 10.19 t/s, tg_3s = 10.19 t/s 51.02.880.567 I slot print_timing: id 0 | task 20750 | n_gen = 193, tg = 10.19 t/s, tg_3s = 10.18 t/s 51.05.924.594 I slot print_timing: id 0 | task 20750 | n_gen = 224, tg = 10.19 t/s, tg_3s = 10.18 t/s 51.07.397.528 I slot print_timing: id 0 | task 20750 | prompt eval time = 3871.05 ms / 292 tokens ( 13.26 ms per token, 75.43 tokens per second) 51.07.397.533 I slot print_timing: id 0 | task 20750 | eval time = 23363.53 ms / 239 tokens ( 98.17 ms per token, 10.19 tokens per second) 51.07.397.534 I slot print_timing: id 0 | task 20750 | total time = 27234.58 ms / 531 tokens 51.07.397.534 I slot print_timing: id 0 | task 20750 | graphs reused = 19956 51.07.397.535 I slot print_timing: id 0 | task 20750 | graph reallocs = 0 / 0 (same size) / (changed size) 51.07.397.556 I slot release: id 0 | task 20750 | stop processing: n_tokens = 562, truncated = 0 51.07.402.196 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 562, t_last = 86285497193 51.07.402.237 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 955.403 MiB) 51.07.424.924 I slot launch_slot_: id 0 | task 20992 | processing task, is_child = 0 51.10.703.526 I slot print_timing: id 0 | task 20992 | prompt processing, n_tokens = 297, progress = 0.99, t = 3.28 s / 90.59 tokens per second 51.20.595.331 I slot print_timing: id 0 | task 20992 | prompt eval time = 3743.54 ms / 301 tokens ( 12.44 ms per token, 80.41 tokens per second) 51.20.595.333 I slot print_timing: id 0 | task 20992 | eval time = 9426.86 ms / 97 tokens ( 98.20 ms per token, 10.18 tokens per second) 51.20.595.334 I slot print_timing: id 0 | task 20992 | total time = 13170.39 ms / 398 tokens 51.20.595.334 I slot print_timing: id 0 | task 20992 | graphs reused = 20051 51.20.595.335 I slot print_timing: id 0 | task 20992 | graph reallocs = 0 / 0 (same size) / (changed size) 51.20.595.361 I slot release: id 0 | task 20992 | stop processing: n_tokens = 429, truncated = 0 51.20.599.814 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 429, t_last = 86298694998 51.20.599.843 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 976.161 MiB) 51.20.621.384 I slot launch_slot_: id 0 | task 21092 | processing task, is_child = 0 51.23.898.100 I slot print_timing: id 0 | task 21092 | prompt processing, n_tokens = 299, progress = 0.99, t = 3.28 s / 91.25 tokens per second 51.34.220.148 I slot print_timing: id 0 | task 21092 | n_gen = 100, tg = 10.19 t/s, tg_3s = 10.29 t/s 51.37.265.069 I slot print_timing: id 0 | task 21092 | n_gen = 131, tg = 10.18 t/s, tg_3s = 10.18 t/s 51.40.307.195 I slot print_timing: id 0 | task 21092 | n_gen = 162, tg = 10.19 t/s, tg_3s = 10.19 t/s 51.42.175.527 I slot print_timing: id 0 | task 21092 | prompt eval time = 3878.78 ms / 303 tokens ( 12.80 ms per token, 78.12 tokens per second) 51.42.175.530 I slot print_timing: id 0 | task 21092 | eval time = 17675.36 ms / 181 tokens ( 98.20 ms per token, 10.18 tokens per second) 51.42.175.531 I slot print_timing: id 0 | task 21092 | total time = 21554.13 ms / 484 tokens 51.42.175.531 I slot print_timing: id 0 | task 21092 | graphs reused = 20229 51.42.175.532 I slot print_timing: id 0 | task 21092 | graph reallocs = 0 / 0 (same size) / (changed size) 51.42.175.554 I slot release: id 0 | task 21092 | stop processing: n_tokens = 515, truncated = 0 51.42.179.890 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 515, t_last = 86320275191 51.42.179.919 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 923.892 MiB) 51.42.203.028 I slot launch_slot_: id 0 | task 21276 | processing task, is_child = 0 51.45.816.365 I slot print_timing: id 0 | task 21276 | prompt processing, n_tokens = 317, progress = 0.99, t = 3.61 s / 87.73 tokens per second 51.56.139.682 I slot print_timing: id 0 | task 21276 | n_gen = 100, tg = 10.18 t/s, tg_3s = 10.28 t/s 51.59.181.976 I slot print_timing: id 0 | task 21276 | n_gen = 131, tg = 10.18 t/s, tg_3s = 10.19 t/s 52.00.750.887 I slot print_timing: id 0 | task 21276 | prompt eval time = 4213.73 ms / 321 tokens ( 13.13 ms per token, 76.18 tokens per second) 52.00.750.892 I slot print_timing: id 0 | task 21276 | eval time = 14334.12 ms / 147 tokens ( 98.18 ms per token, 10.19 tokens per second) 52.00.750.892 I slot print_timing: id 0 | task 21276 | total time = 18547.85 ms / 468 tokens 52.00.750.893 I slot print_timing: id 0 | task 21276 | graphs reused = 20374 52.00.750.893 I slot print_timing: id 0 | task 21276 | graph reallocs = 0 / 0 (same size) / (changed size) 52.00.750.917 I slot release: id 0 | task 21276 | stop processing: n_tokens = 499, truncated = 0 52.00.755.822 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 499, t_last = 86338850554 52.00.755.857 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 933.208 MiB) 52.00.777.999 I slot launch_slot_: id 0 | task 21426 | processing task, is_child = 0 52.04.391.348 I slot print_timing: id 0 | task 21426 | prompt processing, n_tokens = 318, progress = 0.99, t = 3.61 s / 88.01 tokens per second 52.09.905.778 I slot print_timing: id 0 | task 21426 | prompt eval time = 4216.00 ms / 322 tokens ( 13.09 ms per token, 76.38 tokens per second) 52.09.905.781 I slot print_timing: id 0 | task 21426 | eval time = 4911.76 ms / 51 tokens ( 98.24 ms per token, 10.18 tokens per second) 52.09.905.782 I slot print_timing: id 0 | task 21426 | total time = 9127.76 ms / 373 tokens 52.09.905.782 I slot print_timing: id 0 | task 21426 | graphs reused = 20423 52.09.905.783 I slot print_timing: id 0 | task 21426 | graph reallocs = 0 / 0 (same size) / (changed size) 52.09.905.805 I slot release: id 0 | task 21426 | stop processing: n_tokens = 404, truncated = 0 52.09.909.984 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 404, t_last = 86348005442 52.09.910.010 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 926.455 MiB) 52.09.936.605 I slot launch_slot_: id 0 | task 21480 | processing task, is_child = 0 52.13.547.438 I slot print_timing: id 0 | task 21480 | prompt processing, n_tokens = 319, progress = 0.99, t = 3.61 s / 88.35 tokens per second 52.23.880.120 I slot print_timing: id 0 | task 21480 | n_gen = 100, tg = 10.17 t/s, tg_3s = 10.28 t/s 52.26.934.168 I slot print_timing: id 0 | task 21480 | n_gen = 131, tg = 10.17 t/s, tg_3s = 10.15 t/s 52.29.981.433 I slot print_timing: id 0 | task 21480 | n_gen = 162, tg = 10.17 t/s, tg_3s = 10.17 t/s 52.33.025.565 I slot print_timing: id 0 | task 21480 | n_gen = 193, tg = 10.17 t/s, tg_3s = 10.18 t/s 52.34.693.236 I slot print_timing: id 0 | task 21480 | prompt eval time = 4213.51 ms / 323 tokens ( 13.04 ms per token, 76.66 tokens per second) 52.34.693.240 I slot print_timing: id 0 | task 21480 | eval time = 20543.11 ms / 210 tokens ( 98.29 ms per token, 10.17 tokens per second) 52.34.693.240 I slot print_timing: id 0 | task 21480 | total time = 24756.62 ms / 533 tokens 52.34.693.240 I slot print_timing: id 0 | task 21480 | graphs reused = 20630 52.34.693.241 I slot print_timing: id 0 | task 21480 | graph reallocs = 0 / 0 (same size) / (changed size) 52.34.693.268 I slot release: id 0 | task 21480 | stop processing: n_tokens = 564, truncated = 0 52.34.698.099 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 564, t_last = 86372792905 52.34.698.140 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 920.390 MiB) 52.34.719.861 I slot launch_slot_: id 0 | task 21693 | processing task, is_child = 0 52.38.333.509 I slot print_timing: id 0 | task 21693 | prompt processing, n_tokens = 317, progress = 0.99, t = 3.61 s / 87.72 tokens per second 52.48.525.012 I slot print_timing: id 0 | task 21693 | n_gen = 100, tg = 10.18 t/s, tg_3s = 10.28 t/s 52.51.569.868 I slot print_timing: id 0 | task 21693 | n_gen = 131, tg = 10.18 t/s, tg_3s = 10.18 t/s 52.54.618.530 I slot print_timing: id 0 | task 21693 | n_gen = 162, tg = 10.18 t/s, tg_3s = 10.17 t/s 52.57.665.308 I slot print_timing: id 0 | task 21693 | n_gen = 193, tg = 10.18 t/s, tg_3s = 10.17 t/s 53.00.712.920 I slot print_timing: id 0 | task 21693 | n_gen = 224, tg = 10.18 t/s, tg_3s = 10.17 t/s 53.03.756.489 I slot print_timing: id 0 | task 21693 | n_gen = 255, tg = 10.18 t/s, tg_3s = 10.19 t/s 53.06.799.138 I slot print_timing: id 0 | task 21693 | n_gen = 286, tg = 10.18 t/s, tg_3s = 10.19 t/s 53.09.848.917 I slot print_timing: id 0 | task 21693 | n_gen = 317, tg = 10.18 t/s, tg_3s = 10.16 t/s 53.12.897.084 I slot print_timing: id 0 | task 21693 | n_gen = 348, tg = 10.18 t/s, tg_3s = 10.17 t/s 53.15.946.575 I slot print_timing: id 0 | task 21693 | n_gen = 379, tg = 10.18 t/s, tg_3s = 10.17 t/s 53.18.995.089 I slot print_timing: id 0 | task 21693 | n_gen = 410, tg = 10.18 t/s, tg_3s = 10.17 t/s 53.22.044.631 I slot print_timing: id 0 | task 21693 | n_gen = 441, tg = 10.17 t/s, tg_3s = 10.17 t/s 53.25.096.401 I slot print_timing: id 0 | task 21693 | n_gen = 472, tg = 10.17 t/s, tg_3s = 10.16 t/s 53.28.144.444 I slot print_timing: id 0 | task 21693 | n_gen = 503, tg = 10.17 t/s, tg_3s = 10.17 t/s 53.31.198.473 I slot print_timing: id 0 | task 21693 | n_gen = 534, tg = 10.17 t/s, tg_3s = 10.15 t/s 53.34.250.582 I slot print_timing: id 0 | task 21693 | n_gen = 565, tg = 10.17 t/s, tg_3s = 10.16 t/s 53.37.305.686 I slot print_timing: id 0 | task 21693 | n_gen = 596, tg = 10.17 t/s, tg_3s = 10.15 t/s 53.40.359.093 I slot print_timing: id 0 | task 21693 | n_gen = 627, tg = 10.17 t/s, tg_3s = 10.15 t/s 53.43.412.724 I slot print_timing: id 0 | task 21693 | n_gen = 658, tg = 10.17 t/s, tg_3s = 10.15 t/s 53.46.470.913 I slot print_timing: id 0 | task 21693 | n_gen = 689, tg = 10.17 t/s, tg_3s = 10.14 t/s 53.49.526.565 I slot print_timing: id 0 | task 21693 | n_gen = 720, tg = 10.17 t/s, tg_3s = 10.15 t/s 53.52.580.011 I slot print_timing: id 0 | task 21693 | n_gen = 751, tg = 10.17 t/s, tg_3s = 10.15 t/s 53.55.638.084 I slot print_timing: id 0 | task 21693 | n_gen = 782, tg = 10.16 t/s, tg_3s = 10.14 t/s 53.58.693.567 I slot print_timing: id 0 | task 21693 | n_gen = 813, tg = 10.16 t/s, tg_3s = 10.15 t/s 54.01.751.766 I slot print_timing: id 0 | task 21693 | n_gen = 844, tg = 10.16 t/s, tg_3s = 10.14 t/s 54.04.805.503 I slot print_timing: id 0 | task 21693 | n_gen = 875, tg = 10.16 t/s, tg_3s = 10.15 t/s 54.07.866.170 I slot print_timing: id 0 | task 21693 | n_gen = 906, tg = 10.16 t/s, tg_3s = 10.13 t/s 54.10.921.779 I slot print_timing: id 0 | task 21693 | n_gen = 937, tg = 10.16 t/s, tg_3s = 10.15 t/s 54.12.701.130 I slot print_timing: id 0 | task 21693 | prompt eval time = 4079.33 ms / 321 tokens ( 12.71 ms per token, 78.69 tokens per second) 54.12.701.135 I slot print_timing: id 0 | task 21693 | eval time = 93901.93 ms / 955 tokens ( 98.43 ms per token, 10.16 tokens per second) 54.12.701.136 I slot print_timing: id 0 | task 21693 | total time = 97981.26 ms / 1276 tokens 54.12.701.136 I slot print_timing: id 0 | task 21693 | graphs reused = 21579 54.12.701.137 I slot print_timing: id 0 | task 21693 | graph reallocs = 0 / 0 (same size) / (changed size) 54.12.701.163 I slot release: id 0 | task 21693 | stop processing: n_tokens = 1307, truncated = 0 54.12.706.003 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1307, t_last = 86470800801 54.12.706.067 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 932.895 MiB) 54.12.745.397 I slot launch_slot_: id 0 | task 22651 | processing task, is_child = 0 54.16.359.962 I slot print_timing: id 0 | task 22651 | prompt processing, n_tokens = 318, progress = 0.99, t = 3.61 s / 87.98 tokens per second 54.26.548.268 I slot print_timing: id 0 | task 22651 | n_gen = 100, tg = 10.18 t/s, tg_3s = 10.28 t/s 54.29.594.862 I slot print_timing: id 0 | task 22651 | n_gen = 131, tg = 10.18 t/s, tg_3s = 10.18 t/s 54.32.646.316 I slot print_timing: id 0 | task 22651 | n_gen = 162, tg = 10.17 t/s, tg_3s = 10.16 t/s 54.35.690.041 I slot print_timing: id 0 | task 22651 | n_gen = 193, tg = 10.18 t/s, tg_3s = 10.18 t/s 54.35.886.389 I slot print_timing: id 0 | task 22651 | prompt eval time = 4076.08 ms / 322 tokens ( 12.66 ms per token, 79.00 tokens per second) 54.35.886.394 I slot print_timing: id 0 | task 22651 | eval time = 19064.91 ms / 195 tokens ( 98.27 ms per token, 10.18 tokens per second) 54.35.886.395 I slot print_timing: id 0 | task 22651 | total time = 23140.98 ms / 517 tokens 54.35.886.395 I slot print_timing: id 0 | task 22651 | graphs reused = 21771 54.35.886.396 I slot print_timing: id 0 | task 22651 | graph reallocs = 0 / 0 (same size) / (changed size) 54.35.886.421 I slot release: id 0 | task 22651 | stop processing: n_tokens = 548, truncated = 0 54.35.890.772 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 548, t_last = 86493986058 54.35.890.804 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 933.895 MiB) 54.35.912.830 I slot launch_slot_: id 0 | task 22849 | processing task, is_child = 0 54.39.536.868 I slot print_timing: id 0 | task 22849 | prompt processing, n_tokens = 333, progress = 0.99, t = 3.62 s / 91.89 tokens per second 54.44.555.823 I slot print_timing: id 0 | task 22849 | prompt eval time = 4225.26 ms / 337 tokens ( 12.54 ms per token, 79.76 tokens per second) 54.44.555.825 I slot print_timing: id 0 | task 22849 | eval time = 4417.72 ms / 46 tokens ( 98.17 ms per token, 10.19 tokens per second) 54.44.555.826 I slot print_timing: id 0 | task 22849 | total time = 8642.98 ms / 383 tokens 54.44.555.826 I slot print_timing: id 0 | task 22849 | graphs reused = 21815 54.44.555.827 I slot print_timing: id 0 | task 22849 | graph reallocs = 0 / 0 (same size) / (changed size) 54.44.555.856 I slot release: id 0 | task 22849 | stop processing: n_tokens = 414, truncated = 0 54.44.559.573 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 86502655493 54.44.559.602 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 932.895 MiB) 54.44.581.981 I slot launch_slot_: id 0 | task 22898 | processing task, is_child = 0 54.48.196.525 I slot print_timing: id 0 | task 22898 | prompt processing, n_tokens = 321, progress = 0.99, t = 3.61 s / 88.81 tokens per second 54.53.312.958 I slot print_timing: id 0 | task 22898 | prompt eval time = 4217.62 ms / 325 tokens ( 12.98 ms per token, 77.06 tokens per second) 54.53.312.963 I slot print_timing: id 0 | task 22898 | eval time = 4513.35 ms / 47 tokens ( 98.12 ms per token, 10.19 tokens per second) 54.53.312.963 I slot print_timing: id 0 | task 22898 | total time = 8730.97 ms / 372 tokens 54.53.312.964 I slot print_timing: id 0 | task 22898 | graphs reused = 21860 54.53.312.964 I slot print_timing: id 0 | task 22898 | graph reallocs = 0 / 0 (same size) / (changed size) 54.53.312.987 I slot release: id 0 | task 22898 | stop processing: n_tokens = 403, truncated = 0 54.53.317.442 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 403, t_last = 86511412624 54.53.317.468 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 924.579 MiB) 54.53.339.175 I slot launch_slot_: id 0 | task 22948 | processing task, is_child = 0 54.56.954.959 I slot print_timing: id 0 | task 22948 | prompt processing, n_tokens = 327, progress = 0.99, t = 3.62 s / 90.44 tokens per second 55.07.273.644 I slot print_timing: id 0 | task 22948 | n_gen = 100, tg = 10.19 t/s, tg_3s = 10.29 t/s 55.10.317.374 I slot print_timing: id 0 | task 22948 | n_gen = 131, tg = 10.19 t/s, tg_3s = 10.18 t/s 55.11.987.666 I slot print_timing: id 0 | task 22948 | prompt eval time = 4216.70 ms / 331 tokens ( 12.74 ms per token, 78.50 tokens per second) 55.11.987.671 I slot print_timing: id 0 | task 22948 | eval time = 14431.78 ms / 148 tokens ( 98.18 ms per token, 10.19 tokens per second) 55.11.987.671 I slot print_timing: id 0 | task 22948 | total time = 18648.48 ms / 479 tokens 55.11.987.672 I slot print_timing: id 0 | task 22948 | graphs reused = 22006 55.11.987.672 I slot print_timing: id 0 | task 22948 | graph reallocs = 0 / 0 (same size) / (changed size) 55.11.987.699 I slot release: id 0 | task 22948 | stop processing: n_tokens = 510, truncated = 0 55.11.992.392 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 510, t_last = 86530087336 55.11.992.421 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 929.956 MiB) 55.12.014.467 I slot launch_slot_: id 0 | task 23099 | processing task, is_child = 0 55.15.641.111 I slot print_timing: id 0 | task 23099 | prompt processing, n_tokens = 332, progress = 0.99, t = 3.63 s / 91.55 tokens per second 55.25.816.568 I slot print_timing: id 0 | task 23099 | n_gen = 100, tg = 10.19 t/s, tg_3s = 10.29 t/s 55.28.862.200 I slot print_timing: id 0 | task 23099 | n_gen = 131, tg = 10.19 t/s, tg_3s = 10.18 t/s 55.31.124.434 I slot print_timing: id 0 | task 23099 | prompt eval time = 4086.91 ms / 336 tokens ( 12.16 ms per token, 82.21 tokens per second) 55.31.124.437 I slot print_timing: id 0 | task 23099 | eval time = 15023.05 ms / 154 tokens ( 98.19 ms per token, 10.18 tokens per second) 55.31.124.437 I slot print_timing: id 0 | task 23099 | total time = 19109.96 ms / 490 tokens 55.31.124.438 I slot print_timing: id 0 | task 23099 | graphs reused = 22157 55.31.124.438 I slot print_timing: id 0 | task 23099 | graph reallocs = 0 / 0 (same size) / (changed size) 55.31.124.461 I slot release: id 0 | task 23099 | stop processing: n_tokens = 521, truncated = 0 55.31.128.406 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 521, t_last = 86549224098 55.31.128.439 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 928.956 MiB) 55.31.149.959 I slot launch_slot_: id 0 | task 23256 | processing task, is_child = 0 55.35.119.680 I slot print_timing: id 0 | task 23256 | prompt processing, n_tokens = 345, progress = 0.99, t = 3.97 s / 86.91 tokens per second 55.37.494.136 I slot print_timing: id 0 | task 23256 | prompt eval time = 4574.25 ms / 349 tokens ( 13.11 ms per token, 76.30 tokens per second) 55.37.494.138 I slot print_timing: id 0 | task 23256 | eval time = 1769.92 ms / 19 tokens ( 98.33 ms per token, 10.17 tokens per second) 55.37.494.139 I slot print_timing: id 0 | task 23256 | total time = 6344.17 ms / 368 tokens 55.37.494.139 I slot print_timing: id 0 | task 23256 | graphs reused = 22174 55.37.494.140 I slot print_timing: id 0 | task 23256 | graph reallocs = 0 / 0 (same size) / (changed size) 55.37.494.165 I slot release: id 0 | task 23256 | stop processing: n_tokens = 399, truncated = 0 55.37.498.839 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 399, t_last = 86555593802 55.37.498.867 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 923.016 MiB) 55.37.520.573 I slot launch_slot_: id 0 | task 23278 | processing task, is_child = 0 55.41.148.016 I slot print_timing: id 0 | task 23278 | prompt processing, n_tokens = 332, progress = 0.99, t = 3.63 s / 91.52 tokens per second 55.51.328.824 I slot print_timing: id 0 | task 23278 | n_gen = 100, tg = 10.19 t/s, tg_3s = 10.29 t/s 55.54.372.349 I slot print_timing: id 0 | task 23278 | n_gen = 131, tg = 10.19 t/s, tg_3s = 10.19 t/s 55.57.416.678 I slot print_timing: id 0 | task 23278 | n_gen = 162, tg = 10.19 t/s, tg_3s = 10.18 t/s 56.00.462.630 I slot print_timing: id 0 | task 23278 | n_gen = 193, tg = 10.18 t/s, tg_3s = 10.18 t/s 56.03.507.988 I slot print_timing: id 0 | task 23278 | n_gen = 224, tg = 10.18 t/s, tg_3s = 10.18 t/s 56.06.557.848 I slot print_timing: id 0 | task 23278 | n_gen = 255, tg = 10.18 t/s, tg_3s = 10.16 t/s 56.09.600.784 I slot print_timing: id 0 | task 23278 | n_gen = 286, tg = 10.18 t/s, tg_3s = 10.19 t/s 56.12.651.328 I slot print_timing: id 0 | task 23278 | n_gen = 317, tg = 10.18 t/s, tg_3s = 10.16 t/s 56.15.699.445 I slot print_timing: id 0 | task 23278 | n_gen = 348, tg = 10.18 t/s, tg_3s = 10.17 t/s 56.18.749.179 I slot print_timing: id 0 | task 23278 | n_gen = 379, tg = 10.18 t/s, tg_3s = 10.16 t/s 56.21.797.879 I slot print_timing: id 0 | task 23278 | n_gen = 410, tg = 10.18 t/s, tg_3s = 10.17 t/s 56.24.848.224 I slot print_timing: id 0 | task 23278 | n_gen = 441, tg = 10.18 t/s, tg_3s = 10.16 t/s 56.27.896.916 I slot print_timing: id 0 | task 23278 | n_gen = 472, tg = 10.18 t/s, tg_3s = 10.17 t/s 56.30.948.375 I slot print_timing: id 0 | task 23278 | n_gen = 503, tg = 10.17 t/s, tg_3s = 10.16 t/s 56.33.995.782 I slot print_timing: id 0 | task 23278 | n_gen = 534, tg = 10.17 t/s, tg_3s = 10.17 t/s 56.37.050.826 I slot print_timing: id 0 | task 23278 | n_gen = 565, tg = 10.17 t/s, tg_3s = 10.15 t/s 56.40.101.073 I slot print_timing: id 0 | task 23278 | n_gen = 596, tg = 10.17 t/s, tg_3s = 10.16 t/s 56.43.156.601 I slot print_timing: id 0 | task 23278 | n_gen = 627, tg = 10.17 t/s, tg_3s = 10.15 t/s 56.46.212.715 I slot print_timing: id 0 | task 23278 | n_gen = 658, tg = 10.17 t/s, tg_3s = 10.14 t/s 56.49.265.899 I slot print_timing: id 0 | task 23278 | n_gen = 689, tg = 10.17 t/s, tg_3s = 10.15 t/s 56.52.316.982 I slot print_timing: id 0 | task 23278 | n_gen = 720, tg = 10.17 t/s, tg_3s = 10.16 t/s 56.55.373.910 I slot print_timing: id 0 | task 23278 | n_gen = 751, tg = 10.17 t/s, tg_3s = 10.14 t/s 56.58.428.202 I slot print_timing: id 0 | task 23278 | n_gen = 782, tg = 10.17 t/s, tg_3s = 10.15 t/s 57.01.483.411 I slot print_timing: id 0 | task 23278 | n_gen = 813, tg = 10.17 t/s, tg_3s = 10.15 t/s 57.04.537.797 I slot print_timing: id 0 | task 23278 | n_gen = 844, tg = 10.17 t/s, tg_3s = 10.15 t/s 57.07.591.493 I slot print_timing: id 0 | task 23278 | n_gen = 875, tg = 10.16 t/s, tg_3s = 10.15 t/s 57.10.648.486 I slot print_timing: id 0 | task 23278 | n_gen = 906, tg = 10.16 t/s, tg_3s = 10.14 t/s 57.13.706.971 I slot print_timing: id 0 | task 23278 | n_gen = 937, tg = 10.16 t/s, tg_3s = 10.14 t/s 57.16.765.275 I slot print_timing: id 0 | task 23278 | n_gen = 968, tg = 10.16 t/s, tg_3s = 10.14 t/s 57.19.824.733 I slot print_timing: id 0 | task 23278 | n_gen = 999, tg = 10.16 t/s, tg_3s = 10.13 t/s 57.22.290.490 I slot print_timing: id 0 | task 23278 | prompt eval time = 4089.59 ms / 336 tokens ( 12.17 ms per token, 82.16 tokens per second) 57.22.290.493 I slot print_timing: id 0 | task 23278 | eval time = 100680.32 ms / 1024 tokens ( 98.42 ms per token, 10.16 tokens per second) 57.22.290.494 I slot print_timing: id 0 | task 23278 | total time = 104769.91 ms / 1360 tokens 57.22.290.494 I slot print_timing: id 0 | task 23278 | graphs reused = 23192 57.22.290.494 I slot print_timing: id 0 | task 23278 | graph reallocs = 0 / 0 (same size) / (changed size) 57.22.290.518 I slot release: id 0 | task 23278 | stop processing: n_tokens = 1391, truncated = 0 57.22.295.741 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1391, t_last = 86660390155 57.22.295.809 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 933.020 MiB) 57.22.335.734 I slot launch_slot_: id 0 | task 24305 | processing task, is_child = 0 57.26.313.190 I slot print_timing: id 0 | task 24305 | prompt processing, n_tokens = 345, progress = 0.99, t = 3.98 s / 86.74 tokens per second 57.36.505.328 I slot print_timing: id 0 | task 24305 | n_gen = 100, tg = 10.18 t/s, tg_3s = 10.28 t/s 57.39.551.290 I slot print_timing: id 0 | task 24305 | n_gen = 131, tg = 10.18 t/s, tg_3s = 10.18 t/s 57.42.600.144 I slot print_timing: id 0 | task 24305 | n_gen = 162, tg = 10.18 t/s, tg_3s = 10.17 t/s 57.45.644.125 I slot print_timing: id 0 | task 24305 | n_gen = 193, tg = 10.18 t/s, tg_3s = 10.18 t/s 57.48.687.888 I slot print_timing: id 0 | task 24305 | n_gen = 224, tg = 10.18 t/s, tg_3s = 10.18 t/s 57.51.733.316 I slot print_timing: id 0 | task 24305 | n_gen = 255, tg = 10.18 t/s, tg_3s = 10.18 t/s 57.54.782.625 I slot print_timing: id 0 | task 24305 | n_gen = 286, tg = 10.18 t/s, tg_3s = 10.17 t/s 57.57.832.246 I slot print_timing: id 0 | task 24305 | n_gen = 317, tg = 10.18 t/s, tg_3s = 10.17 t/s 58.00.885.610 I slot print_timing: id 0 | task 24305 | n_gen = 348, tg = 10.17 t/s, tg_3s = 10.15 t/s 58.03.938.943 I slot print_timing: id 0 | task 24305 | n_gen = 379, tg = 10.17 t/s, tg_3s = 10.15 t/s 58.06.992.798 I slot print_timing: id 0 | task 24305 | n_gen = 410, tg = 10.17 t/s, tg_3s = 10.15 t/s 58.10.040.997 I slot print_timing: id 0 | task 24305 | n_gen = 441, tg = 10.17 t/s, tg_3s = 10.17 t/s 58.13.092.019 I slot print_timing: id 0 | task 24305 | n_gen = 472, tg = 10.17 t/s, tg_3s = 10.16 t/s 58.16.144.412 I slot print_timing: id 0 | task 24305 | n_gen = 503, tg = 10.17 t/s, tg_3s = 10.16 t/s 58.19.198.211 I slot print_timing: id 0 | task 24305 | n_gen = 534, tg = 10.17 t/s, tg_3s = 10.15 t/s 58.22.246.799 I slot print_timing: id 0 | task 24305 | n_gen = 565, tg = 10.17 t/s, tg_3s = 10.17 t/s 58.25.301.375 I slot print_timing: id 0 | task 24305 | n_gen = 596, tg = 10.17 t/s, tg_3s = 10.15 t/s 58.28.355.187 I slot print_timing: id 0 | task 24305 | n_gen = 627, tg = 10.17 t/s, tg_3s = 10.15 t/s 58.31.409.513 I slot print_timing: id 0 | task 24305 | n_gen = 658, tg = 10.17 t/s, tg_3s = 10.15 t/s 58.34.460.332 I slot print_timing: id 0 | task 24305 | n_gen = 689, tg = 10.17 t/s, tg_3s = 10.16 t/s 58.37.513.914 I slot print_timing: id 0 | task 24305 | n_gen = 720, tg = 10.16 t/s, tg_3s = 10.15 t/s 58.40.572.058 I slot print_timing: id 0 | task 24305 | n_gen = 751, tg = 10.16 t/s, tg_3s = 10.14 t/s 58.42.346.121 I slot print_timing: id 0 | task 24305 | prompt eval time = 4442.99 ms / 349 tokens ( 12.73 ms per token, 78.55 tokens per second) 58.42.346.126 I slot print_timing: id 0 | task 24305 | eval time = 75567.37 ms / 769 tokens ( 98.40 ms per token, 10.16 tokens per second) 58.42.346.126 I slot print_timing: id 0 | task 24305 | total time = 80010.36 ms / 1118 tokens 58.42.346.127 I slot print_timing: id 0 | task 24305 | graphs reused = 23956 58.42.346.127 I slot print_timing: id 0 | task 24305 | graph reallocs = 0 / 0 (same size) / (changed size) 58.42.346.152 I slot release: id 0 | task 24305 | stop processing: n_tokens = 1149, truncated = 0 58.42.350.927 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1149, t_last = 86740445789 58.42.350.987 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 979.475 MiB) 58.42.374.681 I slot launch_slot_: id 0 | task 25077 | processing task, is_child = 0 58.46.352.422 I slot print_timing: id 0 | task 25077 | prompt processing, n_tokens = 345, progress = 0.99, t = 3.98 s / 86.73 tokens per second 58.52.513.581 I slot print_timing: id 0 | task 25077 | prompt eval time = 4444.33 ms / 349 tokens ( 12.73 ms per token, 78.53 tokens per second) 58.52.513.584 I slot print_timing: id 0 | task 25077 | eval time = 5694.56 ms / 59 tokens ( 98.18 ms per token, 10.19 tokens per second) 58.52.513.585 I slot print_timing: id 0 | task 25077 | total time = 10138.89 ms / 408 tokens 58.52.513.585 I slot print_timing: id 0 | task 25077 | graphs reused = 24013 58.52.513.586 I slot print_timing: id 0 | task 25077 | graph reallocs = 0 / 0 (same size) / (changed size) 58.52.513.610 I slot release: id 0 | task 25077 | stop processing: n_tokens = 439, truncated = 0 58.52.518.183 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 439, t_last = 86750613247 58.52.518.215 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 932.020 MiB) 58.52.542.118 I slot launch_slot_: id 0 | task 25139 | processing task, is_child = 0 58.56.845.560 I slot print_timing: id 0 | task 25139 | prompt processing, n_tokens = 381, progress = 0.99, t = 4.30 s / 88.53 tokens per second 59.07.175.594 I slot print_timing: id 0 | task 25139 | n_gen = 100, tg = 10.18 t/s, tg_3s = 10.28 t/s 59.10.217.877 I slot print_timing: id 0 | task 25139 | n_gen = 131, tg = 10.18 t/s, tg_3s = 10.19 t/s 59.13.264.093 I slot print_timing: id 0 | task 25139 | n_gen = 162, tg = 10.18 t/s, tg_3s = 10.18 t/s 59.13.460.548 I slot print_timing: id 0 | task 25139 | prompt eval time = 4907.58 ms / 385 tokens ( 12.75 ms per token, 78.45 tokens per second) 59.13.460.554 I slot print_timing: id 0 | task 25139 | eval time = 16010.84 ms / 164 tokens ( 98.23 ms per token, 10.18 tokens per second) 59.13.460.555 I slot print_timing: id 0 | task 25139 | total time = 20918.42 ms / 549 tokens 59.13.460.555 I slot print_timing: id 0 | task 25139 | graphs reused = 24174 59.13.460.556 I slot print_timing: id 0 | task 25139 | graph reallocs = 0 / 0 (same size) / (changed size) 59.13.460.583 I slot release: id 0 | task 25139 | stop processing: n_tokens = 580, truncated = 0 59.13.465.423 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 580, t_last = 86771560220 59.13.465.460 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 923.642 MiB) 59.13.488.069 I slot launch_slot_: id 0 | task 25306 | processing task, is_child = 0 59.17.100.586 I slot print_timing: id 0 | task 25306 | prompt processing, n_tokens = 324, progress = 0.99, t = 3.61 s / 89.69 tokens per second 59.23.197.444 I slot print_timing: id 0 | task 25306 | prompt eval time = 4214.21 ms / 328 tokens ( 12.85 ms per token, 77.83 tokens per second) 59.23.197.450 I slot print_timing: id 0 | task 25306 | eval time = 5495.16 ms / 57 tokens ( 98.13 ms per token, 10.19 tokens per second) 59.23.197.451 I slot print_timing: id 0 | task 25306 | total time = 9709.36 ms / 385 tokens 59.23.197.451 I slot print_timing: id 0 | task 25306 | graphs reused = 24229 59.23.197.452 I slot print_timing: id 0 | task 25306 | graph reallocs = 0 / 0 (same size) / (changed size) 59.23.197.474 I slot release: id 0 | task 25306 | stop processing: n_tokens = 416, truncated = 0 59.23.507.879 I srv operator(): operator(): cleaning up before exit...