$ /Users/minipro/quantdiff/llama.cpp/llama-b11770/llama-server -m /Users/minipro/quantdiff/models/campaign/322e194ff797/Qwen3.8-27B-UD-Q4_K_M.gguf --host 127.0.0.1 --port 8089 -c 4096 -np 1 -ngl 999 -fa on --jinja --seed 1234 --no-webui -a quant 0.00.045.653 I srv llama_server: initializing ... 0.00.045.658 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.045.750 I srv init_listene: The UI is disabled 0.00.045.751 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.045.790 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) 0.00.047.452 I srv load_model: loading model '/Users/minipro/quantdiff/models/campaign/322e194ff797/Qwen3.8-27B-UD-Q4_K_M.gguf' 0.00.552.676 W model has unused tensor blk.64.attn_norm.weight (size = 20480 bytes) -- ignoring 0.00.552.684 W model has unused tensor blk.64.post_attention_norm.weight (size = 20480 bytes) -- ignoring 0.00.552.691 W model has unused tensor blk.64.attn_q.weight (size = 51609600 bytes) -- ignoring 0.00.552.694 W model has unused tensor blk.64.attn_k.weight (size = 5570560 bytes) -- ignoring 0.00.552.696 W model has unused tensor blk.64.attn_v.weight (size = 5570560 bytes) -- ignoring 0.00.552.704 W model has unused tensor blk.64.attn_output.weight (size = 25804800 bytes) -- ignoring 0.00.552.706 W model has unused tensor blk.64.attn_q_norm.weight (size = 1024 bytes) -- ignoring 0.00.552.709 W model has unused tensor blk.64.attn_k_norm.weight (size = 1024 bytes) -- ignoring 0.00.552.711 W model has unused tensor blk.64.ffn_gate.weight (size = 73113600 bytes) -- ignoring 0.00.552.713 W model has unused tensor blk.64.ffn_down.weight (size = 73113600 bytes) -- ignoring 0.00.552.715 W model has unused tensor blk.64.ffn_up.weight (size = 73113600 bytes) -- ignoring 0.00.552.718 W model has unused tensor blk.64.nextn.eh_proj.weight (size = 43008000 bytes) -- ignoring 0.00.552.720 W model has unused tensor blk.64.nextn.enorm.weight (size = 20480 bytes) -- ignoring 0.00.552.722 W model has unused tensor blk.64.nextn.hnorm.weight (size = 20480 bytes) -- ignoring 0.00.552.729 W model has unused tensor blk.64.nextn.shared_head_norm.weight (size = 20480 bytes) -- ignoring 0.01.287.351 I cmn init: llama threadpool init, n_threads = 8 0.01.854.302 I srv load_model: initializing, n_slots = 1, n_ctx_slot = 4096, kv_unified = 'false' 0.01.858.190 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.01.858.212 I srv llama_server: model loaded 0.01.858.218 I srv llama_server: listening on http://127.0.0.1:8089 0.02.023.198 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.02.023.434 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.06.059.594 I slot print_timing: id 0 | task 0 | prompt processing, n_tokens = 364, progress = 0.99, t = 4.04 s / 90.19 tokens per second 0.12.530.723 I slot print_timing: id 0 | task 0 | prompt eval time = 4689.07 ms / 368 tokens ( 12.74 ms per token, 78.48 tokens per second) 0.12.530.738 I slot print_timing: id 0 | task 0 | eval time = 5818.18 ms / 53 tokens ( 111.89 ms per token, 8.94 tokens per second) 0.12.530.750 I slot print_timing: id 0 | task 0 | total time = 10507.25 ms / 421 tokens 0.12.530.752 I slot print_timing: id 0 | task 0 | graphs reused = 52 0.12.530.755 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.12.530.857 I slot release: id 0 | task 0 | stop processing: n_tokens = 420, truncated = 0 0.12.543.760 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 420, t_last = 90729828501 0.12.599.952 I slot launch_slot_: id 0 | task 56 | processing task, is_child = 0 0.16.237.577 I slot print_timing: id 0 | task 56 | prompt processing, n_tokens = 318, progress = 0.99, t = 3.64 s / 87.42 tokens per second 0.21.153.805 I slot print_timing: id 0 | task 56 | prompt eval time = 4246.06 ms / 322 tokens ( 13.19 ms per token, 75.84 tokens per second) 0.21.153.810 I slot print_timing: id 0 | task 56 | eval time = 4307.78 ms / 42 tokens ( 105.07 ms per token, 9.52 tokens per second) 0.21.153.811 I slot print_timing: id 0 | task 56 | total time = 8553.84 ms / 364 tokens 0.21.153.811 I slot print_timing: id 0 | task 56 | graphs reused = 92 0.21.153.812 I slot print_timing: id 0 | task 56 | graph reallocs = 0 / 0 (same size) / (changed size) 0.21.153.841 I slot release: id 0 | task 56 | stop processing: n_tokens = 363, truncated = 0 0.21.157.521 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 363, t_last = 90738451484 0.21.191.200 I slot launch_slot_: id 0 | task 101 | processing task, is_child = 0 0.25.199.450 I slot print_timing: id 0 | task 101 | prompt processing, n_tokens = 361, progress = 0.99, t = 4.01 s / 90.06 tokens per second 0.30.128.352 I slot print_timing: id 0 | task 101 | prompt eval time = 4621.21 ms / 365 tokens ( 12.66 ms per token, 78.98 tokens per second) 0.30.128.354 I slot print_timing: id 0 | task 101 | eval time = 4315.93 ms / 42 tokens ( 105.27 ms per token, 9.50 tokens per second) 0.30.128.355 I slot print_timing: id 0 | task 101 | total time = 8937.14 ms / 407 tokens 0.30.128.356 I slot print_timing: id 0 | task 101 | graphs reused = 132 0.30.128.356 I slot print_timing: id 0 | task 101 | graph reallocs = 0 / 0 (same size) / (changed size) 0.30.128.382 I slot release: id 0 | task 101 | stop processing: n_tokens = 406, truncated = 0 0.30.132.575 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 406, t_last = 90747426025 0.30.166.839 I slot launch_slot_: id 0 | task 146 | processing task, is_child = 0 0.34.501.069 I slot print_timing: id 0 | task 146 | prompt processing, n_tokens = 393, progress = 0.99, t = 4.33 s / 90.67 tokens per second 0.39.534.995 I slot print_timing: id 0 | task 146 | prompt eval time = 4949.05 ms / 397 tokens ( 12.47 ms per token, 80.22 tokens per second) 0.39.535.002 I slot print_timing: id 0 | task 146 | eval time = 4419.10 ms / 43 tokens ( 105.22 ms per token, 9.50 tokens per second) 0.39.535.003 I slot print_timing: id 0 | task 146 | total time = 9368.15 ms / 440 tokens 0.39.535.003 I slot print_timing: id 0 | task 146 | graphs reused = 173 0.39.535.004 I slot print_timing: id 0 | task 146 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.535.028 I slot release: id 0 | task 146 | stop processing: n_tokens = 439, truncated = 0 0.39.538.897 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 0.39.572.966 I slot launch_slot_: id 0 | task 192 | processing task, is_child = 0 0.43.582.906 I slot print_timing: id 0 | task 192 | prompt processing, n_tokens = 379, progress = 0.99, t = 4.01 s / 94.52 tokens per second 0.50.208.012 I slot print_timing: id 0 | task 192 | prompt eval time = 4959.99 ms / 383 tokens ( 12.95 ms per token, 77.22 tokens per second) 0.50.208.016 I slot print_timing: id 0 | task 192 | eval time = 5675.05 ms / 55 tokens ( 105.09 ms per token, 9.52 tokens per second) 0.50.208.017 I slot print_timing: id 0 | task 192 | total time = 10635.03 ms / 438 tokens 0.50.208.017 I slot print_timing: id 0 | task 192 | graphs reused = 226 0.50.208.018 I slot print_timing: id 0 | task 192 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.208.045 I slot release: id 0 | task 192 | stop processing: n_tokens = 437, truncated = 0 0.50.212.280 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 90767505688 0.50.247.283 I slot launch_slot_: id 0 | task 250 | processing task, is_child = 0 0.54.289.931 I slot print_timing: id 0 | task 250 | prompt processing, n_tokens = 368, progress = 0.99, t = 4.04 s / 91.03 tokens per second 1.00.998.254 I slot print_timing: id 0 | task 250 | prompt eval time = 4665.15 ms / 372 tokens ( 12.54 ms per token, 79.74 tokens per second) 1.00.998.267 I slot print_timing: id 0 | task 250 | eval time = 6085.80 ms / 55 tokens ( 112.70 ms per token, 8.87 tokens per second) 1.00.998.270 I slot print_timing: id 0 | task 250 | total time = 10750.95 ms / 427 tokens 1.00.998.272 I slot print_timing: id 0 | task 250 | graphs reused = 279 1.00.998.274 I slot print_timing: id 0 | task 250 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.998.372 I slot release: id 0 | task 250 | stop processing: n_tokens = 426, truncated = 0 1.01.010.259 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 90778296015 1.01.068.207 I slot launch_slot_: id 0 | task 308 | processing task, is_child = 0 1.05.778.361 I slot print_timing: id 0 | task 308 | prompt processing, n_tokens = 418, progress = 0.99, t = 4.71 s / 88.74 tokens per second 1.12.464.508 I slot print_timing: id 0 | task 308 | prompt eval time = 5322.91 ms / 422 tokens ( 12.61 ms per token, 79.28 tokens per second) 1.12.464.529 I slot print_timing: id 0 | task 308 | eval time = 6073.34 ms / 55 tokens ( 112.47 ms per token, 8.89 tokens per second) 1.12.464.531 I slot print_timing: id 0 | task 308 | total time = 11396.25 ms / 477 tokens 1.12.464.533 I slot print_timing: id 0 | task 308 | graphs reused = 332 1.12.464.536 I slot print_timing: id 0 | task 308 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.464.730 I slot release: id 0 | task 308 | stop processing: n_tokens = 476, truncated = 0 1.12.477.415 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 476, t_last = 90789762374 1.12.532.860 I slot launch_slot_: id 0 | task 366 | processing task, is_child = 0 1.17.605.232 I slot print_timing: id 0 | task 366 | prompt processing, n_tokens = 466, progress = 0.99, t = 5.07 s / 91.87 tokens per second 1.26.524.327 I slot print_timing: id 0 | task 366 | prompt eval time = 6019.69 ms / 470 tokens ( 12.81 ms per token, 78.08 tokens per second) 1.26.524.343 I slot print_timing: id 0 | task 366 | eval time = 7971.76 ms / 72 tokens ( 112.28 ms per token, 8.91 tokens per second) 1.26.524.346 I slot print_timing: id 0 | task 366 | total time = 13991.44 ms / 542 tokens 1.26.524.348 I slot print_timing: id 0 | task 366 | graphs reused = 401 1.26.524.350 I slot print_timing: id 0 | task 366 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.524.468 I slot release: id 0 | task 366 | stop processing: n_tokens = 541, truncated = 0 1.26.536.587 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 541, t_last = 90803822111 1.26.592.222 I slot launch_slot_: id 0 | task 441 | processing task, is_child = 0 1.30.241.333 I slot print_timing: id 0 | task 441 | prompt processing, n_tokens = 341, progress = 0.99, t = 3.65 s / 93.45 tokens per second 1.35.813.367 I slot print_timing: id 0 | task 441 | prompt eval time = 4263.53 ms / 345 tokens ( 12.36 ms per token, 80.92 tokens per second) 1.35.813.384 I slot print_timing: id 0 | task 441 | eval time = 4957.59 ms / 47 tokens ( 107.77 ms per token, 9.28 tokens per second) 1.35.813.387 I slot print_timing: id 0 | task 441 | total time = 9221.12 ms / 392 tokens 1.35.813.389 I slot print_timing: id 0 | task 441 | graphs reused = 446 1.35.813.391 I slot print_timing: id 0 | task 441 | graph reallocs = 0 / 0 (same size) / (changed size) 1.35.813.500 I slot release: id 0 | task 441 | stop processing: n_tokens = 391, truncated = 0 1.35.826.058 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 391, t_last = 90813111144 1.35.883.334 I slot launch_slot_: id 0 | task 491 | processing task, is_child = 0 1.39.888.819 I slot print_timing: id 0 | task 491 | prompt processing, n_tokens = 360, progress = 0.99, t = 4.01 s / 89.88 tokens per second 1.45.033.054 I slot print_timing: id 0 | task 491 | prompt eval time = 4946.25 ms / 364 tokens ( 13.59 ms per token, 73.59 tokens per second) 1.45.033.059 I slot print_timing: id 0 | task 491 | eval time = 4203.46 ms / 41 tokens ( 105.09 ms per token, 9.52 tokens per second) 1.45.033.060 I slot print_timing: id 0 | task 491 | total time = 9149.71 ms / 405 tokens 1.45.033.060 I slot print_timing: id 0 | task 491 | graphs reused = 485 1.45.033.061 I slot print_timing: id 0 | task 491 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.033.084 I slot release: id 0 | task 491 | stop processing: n_tokens = 404, truncated = 0 1.45.038.078 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 404, t_last = 90822330728 1.45.072.453 I slot launch_slot_: id 0 | task 535 | processing task, is_child = 0 1.49.056.299 I slot print_timing: id 0 | task 535 | prompt processing, n_tokens = 372, progress = 0.99, t = 3.98 s / 93.38 tokens per second 1.56.275.267 I slot print_timing: id 0 | task 535 | prompt eval time = 4591.99 ms / 376 tokens ( 12.21 ms per token, 81.88 tokens per second) 1.56.275.277 I slot print_timing: id 0 | task 535 | eval time = 6610.81 ms / 62 tokens ( 108.37 ms per token, 9.23 tokens per second) 1.56.275.279 I slot print_timing: id 0 | task 535 | total time = 11202.80 ms / 438 tokens 1.56.275.280 I slot print_timing: id 0 | task 535 | graphs reused = 545 1.56.275.281 I slot print_timing: id 0 | task 535 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.275.336 I slot release: id 0 | task 535 | stop processing: n_tokens = 437, truncated = 0 1.56.285.617 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 90833572979 1.56.342.495 I slot launch_slot_: id 0 | task 600 | processing task, is_child = 0 2.00.693.008 I slot print_timing: id 0 | task 600 | prompt processing, n_tokens = 408, progress = 0.99, t = 4.35 s / 93.78 tokens per second 2.06.143.248 I slot print_timing: id 0 | task 600 | prompt eval time = 4963.80 ms / 412 tokens ( 12.05 ms per token, 83.00 tokens per second) 2.06.143.251 I slot print_timing: id 0 | task 600 | eval time = 4836.93 ms / 47 tokens ( 105.15 ms per token, 9.51 tokens per second) 2.06.143.252 I slot print_timing: id 0 | task 600 | total time = 9800.74 ms / 459 tokens 2.06.143.252 I slot print_timing: id 0 | task 600 | graphs reused = 590 2.06.143.253 I slot print_timing: id 0 | task 600 | graph reallocs = 0 / 0 (same size) / (changed size) 2.06.143.281 I slot release: id 0 | task 600 | stop processing: n_tokens = 458, truncated = 0 2.06.146.929 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 90843440924 2.06.190.549 I slot launch_slot_: id 0 | task 650 | processing task, is_child = 0 2.10.213.591 I slot print_timing: id 0 | task 650 | prompt processing, n_tokens = 372, progress = 0.99, t = 4.02 s / 92.47 tokens per second 2.18.005.904 I slot print_timing: id 0 | task 650 | prompt eval time = 4983.90 ms / 376 tokens ( 13.26 ms per token, 75.44 tokens per second) 2.18.005.918 I slot print_timing: id 0 | task 650 | eval time = 6831.41 ms / 62 tokens ( 111.99 ms per token, 8.93 tokens per second) 2.18.005.920 I slot print_timing: id 0 | task 650 | total time = 11815.32 ms / 438 tokens 2.18.005.923 I slot print_timing: id 0 | task 650 | graphs reused = 650 2.18.005.925 I slot print_timing: id 0 | task 650 | graph reallocs = 0 / 0 (same size) / (changed size) 2.18.006.048 I slot release: id 0 | task 650 | stop processing: n_tokens = 437, truncated = 0 2.18.018.007 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 90855303692 2.18.200.013 I slot launch_slot_: id 0 | task 715 | processing task, is_child = 0 2.22.257.079 I slot print_timing: id 0 | task 715 | prompt processing, n_tokens = 374, progress = 0.99, t = 4.06 s / 92.19 tokens per second 2.28.610.457 I slot print_timing: id 0 | task 715 | prompt eval time = 4680.47 ms / 378 tokens ( 12.38 ms per token, 80.76 tokens per second) 2.28.610.474 I slot print_timing: id 0 | task 715 | eval time = 5729.95 ms / 52 tokens ( 112.35 ms per token, 8.90 tokens per second) 2.28.610.477 I slot print_timing: id 0 | task 715 | total time = 10410.42 ms / 430 tokens 2.28.610.485 I slot print_timing: id 0 | task 715 | graphs reused = 700 2.28.610.487 I slot print_timing: id 0 | task 715 | graph reallocs = 0 / 0 (same size) / (changed size) 2.28.610.591 I slot release: id 0 | task 715 | stop processing: n_tokens = 429, truncated = 0 2.28.622.743 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 429, t_last = 90865908234 2.28.761.771 I slot launch_slot_: id 0 | task 770 | processing task, is_child = 0 2.32.796.448 I slot print_timing: id 0 | task 770 | prompt processing, n_tokens = 363, progress = 0.99, t = 4.03 s / 89.97 tokens per second 2.39.769.761 I slot print_timing: id 0 | task 770 | prompt eval time = 4644.01 ms / 367 tokens ( 12.65 ms per token, 79.03 tokens per second) 2.39.769.763 I slot print_timing: id 0 | task 770 | eval time = 6363.96 ms / 58 tokens ( 111.65 ms per token, 8.96 tokens per second) 2.39.769.764 I slot print_timing: id 0 | task 770 | total time = 11007.97 ms / 425 tokens 2.39.769.764 I slot print_timing: id 0 | task 770 | graphs reused = 756 2.39.769.765 I slot print_timing: id 0 | task 770 | graph reallocs = 0 / 0 (same size) / (changed size) 2.39.769.788 I slot release: id 0 | task 770 | stop processing: n_tokens = 424, truncated = 0 2.39.773.991 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 90877067431 2.39.844.744 I slot launch_slot_: id 0 | task 831 | processing task, is_child = 0 2.43.497.476 I slot print_timing: id 0 | task 831 | prompt processing, n_tokens = 343, progress = 0.99, t = 3.65 s / 93.90 tokens per second 2.49.600.030 I slot print_timing: id 0 | task 831 | prompt eval time = 4265.98 ms / 347 tokens ( 12.29 ms per token, 81.34 tokens per second) 2.49.600.042 I slot print_timing: id 0 | task 831 | eval time = 5489.28 ms / 51 tokens ( 109.79 ms per token, 9.11 tokens per second) 2.49.600.044 I slot print_timing: id 0 | task 831 | total time = 9755.25 ms / 398 tokens 2.49.600.046 I slot print_timing: id 0 | task 831 | graphs reused = 805 2.49.600.048 I slot print_timing: id 0 | task 831 | graph reallocs = 0 / 0 (same size) / (changed size) 2.49.600.193 I slot release: id 0 | task 831 | stop processing: n_tokens = 397, truncated = 0 2.49.612.929 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 397, t_last = 90886897836 2.49.691.491 I slot launch_slot_: id 0 | task 885 | processing task, is_child = 0 2.53.721.414 I slot print_timing: id 0 | task 885 | prompt processing, n_tokens = 365, progress = 0.99, t = 4.03 s / 90.57 tokens per second 2.58.539.228 I slot print_timing: id 0 | task 885 | prompt eval time = 4643.21 ms / 369 tokens ( 12.58 ms per token, 79.47 tokens per second) 2.58.539.233 I slot print_timing: id 0 | task 885 | eval time = 4204.52 ms / 41 tokens ( 105.11 ms per token, 9.51 tokens per second) 2.58.539.234 I slot print_timing: id 0 | task 885 | total time = 8847.72 ms / 410 tokens 2.58.539.234 I slot print_timing: id 0 | task 885 | graphs reused = 844 2.58.539.235 I slot print_timing: id 0 | task 885 | graph reallocs = 0 / 0 (same size) / (changed size) 2.58.539.263 I slot release: id 0 | task 885 | stop processing: n_tokens = 409, truncated = 0 2.58.543.575 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 90895836906 2.58.598.792 I slot launch_slot_: id 0 | task 929 | processing task, is_child = 0 3.02.602.628 I slot print_timing: id 0 | task 929 | prompt processing, n_tokens = 348, progress = 0.99, t = 4.00 s / 86.92 tokens per second 3.07.550.986 I slot print_timing: id 0 | task 929 | prompt eval time = 4612.77 ms / 352 tokens ( 13.10 ms per token, 76.31 tokens per second) 3.07.551.014 I slot print_timing: id 0 | task 929 | eval time = 4339.40 ms / 41 tokens ( 108.48 ms per token, 9.22 tokens per second) 3.07.551.017 I slot print_timing: id 0 | task 929 | total time = 8952.17 ms / 393 tokens 3.07.551.019 I slot print_timing: id 0 | task 929 | graphs reused = 883 3.07.551.021 I slot print_timing: id 0 | task 929 | graph reallocs = 0 / 0 (same size) / (changed size) 3.07.551.127 I slot release: id 0 | task 929 | stop processing: n_tokens = 392, truncated = 0 3.07.563.568 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 392, t_last = 90904848771 3.07.563.642 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 475.138 MiB) 3.07.585.910 I slot launch_slot_: id 0 | task 973 | processing task, is_child = 0 3.11.593.220 I slot print_timing: id 0 | task 973 | prompt processing, n_tokens = 345, progress = 0.99, t = 4.01 s / 86.09 tokens per second 3.16.298.572 I slot print_timing: id 0 | task 973 | prompt eval time = 4614.05 ms / 349 tokens ( 13.22 ms per token, 75.64 tokens per second) 3.16.298.579 I slot print_timing: id 0 | task 973 | eval time = 4098.60 ms / 40 tokens ( 105.09 ms per token, 9.52 tokens per second) 3.16.298.579 I slot print_timing: id 0 | task 973 | total time = 8712.65 ms / 389 tokens 3.16.298.580 I slot print_timing: id 0 | task 973 | graphs reused = 921 3.16.298.580 I slot print_timing: id 0 | task 973 | graph reallocs = 0 / 0 (same size) / (changed size) 3.16.298.607 I slot release: id 0 | task 973 | stop processing: n_tokens = 388, truncated = 0 3.16.302.831 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 388, t_last = 90913596250 3.16.302.859 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 471.575 MiB) 3.16.335.690 I slot launch_slot_: id 0 | task 1016 | processing task, is_child = 0 3.20.358.985 I slot print_timing: id 0 | task 1016 | prompt processing, n_tokens = 380, progress = 0.99, t = 4.02 s / 94.45 tokens per second 3.27.824.692 I slot print_timing: id 0 | task 1016 | prompt eval time = 4968.60 ms / 384 tokens ( 12.94 ms per token, 77.29 tokens per second) 3.27.824.695 I slot print_timing: id 0 | task 1016 | eval time = 6520.39 ms / 63 tokens ( 105.17 ms per token, 9.51 tokens per second) 3.27.824.696 I slot print_timing: id 0 | task 1016 | total time = 11488.99 ms / 447 tokens 3.27.824.696 I slot print_timing: id 0 | task 1016 | graphs reused = 982 3.27.824.697 I slot print_timing: id 0 | task 1016 | graph reallocs = 0 / 0 (same size) / (changed size) 3.27.824.725 I slot release: id 0 | task 1016 | stop processing: n_tokens = 446, truncated = 0 3.27.828.072 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 446, t_last = 90925122368 3.27.828.107 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 474.263 MiB) 3.27.863.668 I slot launch_slot_: id 0 | task 1082 | processing task, is_child = 0 3.31.487.724 I slot print_timing: id 0 | task 1082 | prompt processing, n_tokens = 352, progress = 0.99, t = 3.62 s / 97.13 tokens per second 3.38.053.427 I slot print_timing: id 0 | task 1082 | prompt eval time = 4235.17 ms / 356 tokens ( 11.90 ms per token, 84.06 tokens per second) 3.38.053.453 I slot print_timing: id 0 | task 1082 | eval time = 5954.56 ms / 54 tokens ( 112.35 ms per token, 8.90 tokens per second) 3.38.053.456 I slot print_timing: id 0 | task 1082 | total time = 10189.73 ms / 410 tokens 3.38.053.458 I slot print_timing: id 0 | task 1082 | graphs reused = 1034 3.38.053.460 I slot print_timing: id 0 | task 1082 | graph reallocs = 0 / 0 (same size) / (changed size) 3.38.053.581 I slot release: id 0 | task 1082 | stop processing: n_tokens = 409, truncated = 0 3.38.066.690 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 90935351224 3.38.066.759 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 476.326 MiB) 3.38.117.585 I slot launch_slot_: id 0 | task 1139 | processing task, is_child = 0 3.42.464.848 I slot print_timing: id 0 | task 1139 | prompt processing, n_tokens = 406, progress = 0.99, t = 4.35 s / 93.39 tokens per second 3.51.117.069 I slot print_timing: id 0 | task 1139 | prompt eval time = 5290.23 ms / 410 tokens ( 12.90 ms per token, 77.50 tokens per second) 3.51.117.076 I slot print_timing: id 0 | task 1139 | eval time = 7709.23 ms / 70 tokens ( 111.73 ms per token, 8.95 tokens per second) 3.51.117.077 I slot print_timing: id 0 | task 1139 | total time = 12999.45 ms / 480 tokens 3.51.117.078 I slot print_timing: id 0 | task 1139 | graphs reused = 1102 3.51.117.079 I slot print_timing: id 0 | task 1139 | graph reallocs = 0 / 0 (same size) / (changed size) 3.51.117.187 I slot release: id 0 | task 1139 | stop processing: n_tokens = 479, truncated = 0 3.51.128.329 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 479, t_last = 90948414830 3.51.128.400 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 476.201 MiB) 3.51.211.726 I slot launch_slot_: id 0 | task 1212 | processing task, is_child = 0 3.55.559.726 I slot print_timing: id 0 | task 1212 | prompt processing, n_tokens = 381, progress = 0.99, t = 4.35 s / 87.63 tokens per second 4.02.396.032 I slot print_timing: id 0 | task 1212 | prompt eval time = 4959.10 ms / 385 tokens ( 12.88 ms per token, 77.64 tokens per second) 4.02.396.039 I slot print_timing: id 0 | task 1212 | eval time = 6225.16 ms / 58 tokens ( 109.21 ms per token, 9.16 tokens per second) 4.02.396.041 I slot print_timing: id 0 | task 1212 | total time = 11184.27 ms / 443 tokens 4.02.396.042 I slot print_timing: id 0 | task 1212 | graphs reused = 1158 4.02.396.043 I slot print_timing: id 0 | task 1212 | graph reallocs = 0 / 0 (same size) / (changed size) 4.02.396.096 I slot release: id 0 | task 1212 | stop processing: n_tokens = 442, truncated = 0 4.02.407.897 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 442, t_last = 90959693739 4.02.407.982 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 475.514 MiB) 4.02.517.370 I slot launch_slot_: id 0 | task 1273 | processing task, is_child = 0 4.06.544.448 I slot print_timing: id 0 | task 1273 | prompt processing, n_tokens = 391, progress = 0.99, t = 4.03 s / 97.09 tokens per second 4.15.182.508 I slot print_timing: id 0 | task 1273 | prompt eval time = 4975.09 ms / 395 tokens ( 12.60 ms per token, 79.40 tokens per second) 4.15.182.530 I slot print_timing: id 0 | task 1273 | eval time = 7690.01 ms / 71 tokens ( 109.86 ms per token, 9.10 tokens per second) 4.15.182.533 I slot print_timing: id 0 | task 1273 | total time = 12665.10 ms / 466 tokens 4.15.182.535 I slot print_timing: id 0 | task 1273 | graphs reused = 1227 4.15.182.537 I slot print_timing: id 0 | task 1273 | graph reallocs = 0 / 0 (same size) / (changed size) 4.15.182.652 I slot release: id 0 | task 1273 | stop processing: n_tokens = 465, truncated = 0 4.15.195.567 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 465, t_last = 90972480296 4.15.195.654 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 478.640 MiB) 4.15.325.653 I slot launch_slot_: id 0 | task 1347 | processing task, is_child = 0 4.19.697.751 I slot print_timing: id 0 | task 1347 | prompt processing, n_tokens = 426, progress = 0.99, t = 4.37 s / 97.44 tokens per second 4.27.317.551 I slot print_timing: id 0 | task 1347 | prompt eval time = 5322.85 ms / 430 tokens ( 12.38 ms per token, 80.78 tokens per second) 4.27.317.562 I slot print_timing: id 0 | task 1347 | eval time = 6669.01 ms / 62 tokens ( 109.33 ms per token, 9.15 tokens per second) 4.27.317.565 I slot print_timing: id 0 | task 1347 | total time = 11991.87 ms / 492 tokens 4.27.317.567 I slot print_timing: id 0 | task 1347 | graphs reused = 1287 4.27.317.569 I slot print_timing: id 0 | task 1347 | graph reallocs = 0 / 0 (same size) / (changed size) 4.27.317.697 I slot release: id 0 | task 1347 | stop processing: n_tokens = 491, truncated = 0 4.27.330.063 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 491, t_last = 90984615340 4.27.330.147 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 482.704 MiB) 4.27.461.219 I slot launch_slot_: id 0 | task 1412 | processing task, is_child = 0 4.31.487.120 I slot print_timing: id 0 | task 1412 | prompt processing, n_tokens = 388, progress = 0.99, t = 4.03 s / 96.38 tokens per second 4.39.146.627 I slot print_timing: id 0 | task 1412 | prompt eval time = 4974.69 ms / 392 tokens ( 12.69 ms per token, 78.80 tokens per second) 4.39.146.660 I slot print_timing: id 0 | task 1412 | eval time = 6710.66 ms / 62 tokens ( 110.01 ms per token, 9.09 tokens per second) 4.39.146.664 I slot print_timing: id 0 | task 1412 | total time = 11685.35 ms / 454 tokens 4.39.146.666 I slot print_timing: id 0 | task 1412 | graphs reused = 1347 4.39.146.671 I slot print_timing: id 0 | task 1412 | graph reallocs = 0 / 0 (same size) / (changed size) 4.39.146.832 I slot release: id 0 | task 1412 | stop processing: n_tokens = 453, truncated = 0 4.39.157.629 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 453, t_last = 90996444476 4.39.157.707 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 473.325 MiB) 4.39.312.091 I slot launch_slot_: id 0 | task 1477 | processing task, is_child = 0 4.43.331.392 I slot print_timing: id 0 | task 1477 | prompt processing, n_tokens = 346, progress = 0.99, t = 4.02 s / 86.09 tokens per second 4.49.153.005 I slot print_timing: id 0 | task 1477 | prompt eval time = 4627.48 ms / 350 tokens ( 13.22 ms per token, 75.64 tokens per second) 4.49.153.015 I slot print_timing: id 0 | task 1477 | eval time = 5213.35 ms / 49 tokens ( 108.61 ms per token, 9.21 tokens per second) 4.49.153.024 I slot print_timing: id 0 | task 1477 | total time = 9840.83 ms / 399 tokens 4.49.153.026 I slot print_timing: id 0 | task 1477 | graphs reused = 1394 4.49.153.028 I slot print_timing: id 0 | task 1477 | graph reallocs = 0 / 0 (same size) / (changed size) 4.49.153.372 I slot release: id 0 | task 1477 | stop processing: n_tokens = 398, truncated = 0 4.49.168.404 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 398, t_last = 91006451015 4.49.168.477 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 474.138 MiB) 4.49.291.728 I slot launch_slot_: id 0 | task 1529 | processing task, is_child = 0 4.53.332.611 I slot print_timing: id 0 | task 1529 | prompt processing, n_tokens = 376, progress = 0.99, t = 4.04 s / 93.05 tokens per second 5.00.372.058 I slot print_timing: id 0 | task 1529 | prompt eval time = 4653.27 ms / 380 tokens ( 12.25 ms per token, 81.66 tokens per second) 5.00.372.067 I slot print_timing: id 0 | task 1529 | eval time = 6427.01 ms / 61 tokens ( 107.12 ms per token, 9.34 tokens per second) 5.00.372.070 I slot print_timing: id 0 | task 1529 | total time = 11080.28 ms / 441 tokens 5.00.372.073 I slot print_timing: id 0 | task 1529 | graphs reused = 1453 5.00.372.075 I slot print_timing: id 0 | task 1529 | graph reallocs = 0 / 0 (same size) / (changed size) 5.00.372.229 I slot release: id 0 | task 1529 | stop processing: n_tokens = 440, truncated = 0 5.00.384.309 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 440, t_last = 91017669873 5.00.384.376 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 476.201 MiB) 5.00.531.567 I slot launch_slot_: id 0 | task 1593 | processing task, is_child = 0 5.04.866.763 I slot print_timing: id 0 | task 1593 | prompt processing, n_tokens = 406, progress = 0.99, t = 4.34 s / 93.65 tokens per second 5.14.718.161 I slot print_timing: id 0 | task 1593 | prompt eval time = 5290.19 ms / 410 tokens ( 12.90 ms per token, 77.50 tokens per second) 5.14.718.175 I slot print_timing: id 0 | task 1593 | eval time = 8896.38 ms / 80 tokens ( 112.61 ms per token, 8.88 tokens per second) 5.14.718.178 I slot print_timing: id 0 | task 1593 | total time = 14186.57 ms / 490 tokens 5.14.718.180 I slot print_timing: id 0 | task 1593 | graphs reused = 1531 5.14.718.182 I slot print_timing: id 0 | task 1593 | graph reallocs = 0 / 0 (same size) / (changed size) 5.14.718.316 I slot release: id 0 | task 1593 | stop processing: n_tokens = 489, truncated = 0 5.14.731.822 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 489, t_last = 91032015959 5.14.731.894 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 477.514 MiB) 5.14.875.632 I slot launch_slot_: id 0 | task 1676 | processing task, is_child = 0 5.19.225.241 I slot print_timing: id 0 | task 1676 | prompt processing, n_tokens = 383, progress = 0.99, t = 4.35 s / 88.05 tokens per second 5.27.171.947 I slot print_timing: id 0 | task 1676 | prompt eval time = 4962.02 ms / 387 tokens ( 12.82 ms per token, 77.99 tokens per second) 5.27.171.957 I slot print_timing: id 0 | task 1676 | eval time = 7334.27 ms / 68 tokens ( 109.47 ms per token, 9.14 tokens per second) 5.27.171.958 I slot print_timing: id 0 | task 1676 | total time = 12296.29 ms / 455 tokens 5.27.171.959 I slot print_timing: id 0 | task 1676 | graphs reused = 1597 5.27.171.960 I slot print_timing: id 0 | task 1676 | graph reallocs = 0 / 0 (same size) / (changed size) 5.27.172.256 I slot release: id 0 | task 1676 | stop processing: n_tokens = 454, truncated = 0 5.27.187.172 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 454, t_last = 91044469900 5.27.187.253 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 476.201 MiB) 5.27.290.001 I slot launch_slot_: id 0 | task 1747 | processing task, is_child = 0 5.31.304.681 I slot print_timing: id 0 | task 1747 | prompt processing, n_tokens = 354, progress = 0.99, t = 4.01 s / 88.18 tokens per second 5.38.321.180 I slot print_timing: id 0 | task 1747 | prompt eval time = 4623.11 ms / 358 tokens ( 12.91 ms per token, 77.44 tokens per second) 5.38.321.188 I slot print_timing: id 0 | task 1747 | eval time = 6408.05 ms / 59 tokens ( 110.48 ms per token, 9.05 tokens per second) 5.38.321.189 I slot print_timing: id 0 | task 1747 | total time = 11031.15 ms / 417 tokens 5.38.321.190 I slot print_timing: id 0 | task 1747 | graphs reused = 1654 5.38.321.191 I slot print_timing: id 0 | task 1747 | graph reallocs = 0 / 0 (same size) / (changed size) 5.38.321.314 I slot release: id 0 | task 1747 | stop processing: n_tokens = 416, truncated = 0 5.38.333.988 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 91055618957 5.38.334.058 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 475.701 MiB) 5.38.455.300 I slot launch_slot_: id 0 | task 1809 | processing task, is_child = 0 5.42.472.790 I slot print_timing: id 0 | task 1809 | prompt processing, n_tokens = 355, progress = 0.99, t = 4.02 s / 88.36 tokens per second 5.48.950.085 I slot print_timing: id 0 | task 1809 | prompt eval time = 4624.40 ms / 359 tokens ( 12.88 ms per token, 77.63 tokens per second) 5.48.950.111 I slot print_timing: id 0 | task 1809 | eval time = 5870.35 ms / 56 tokens ( 106.73 ms per token, 9.37 tokens per second) 5.48.950.131 I slot print_timing: id 0 | task 1809 | total time = 10494.75 ms / 415 tokens 5.48.950.146 I slot print_timing: id 0 | task 1809 | graphs reused = 1708 5.48.950.148 I slot print_timing: id 0 | task 1809 | graph reallocs = 0 / 0 (same size) / (changed size) 5.48.950.326 I slot release: id 0 | task 1809 | stop processing: n_tokens = 414, truncated = 0 5.48.962.770 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 91066247970 5.48.962.837 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 475.388 MiB) 5.49.049.060 I slot launch_slot_: id 0 | task 1868 | processing task, is_child = 0 5.53.411.396 I slot print_timing: id 0 | task 1868 | prompt processing, n_tokens = 383, progress = 0.99, t = 4.36 s / 87.80 tokens per second 6.00.326.922 I slot print_timing: id 0 | task 1868 | prompt eval time = 4970.08 ms / 387 tokens ( 12.84 ms per token, 77.87 tokens per second) 6.00.326.924 I slot print_timing: id 0 | task 1868 | eval time = 6307.76 ms / 61 tokens ( 105.13 ms per token, 9.51 tokens per second) 6.00.326.925 I slot print_timing: id 0 | task 1868 | total time = 11277.85 ms / 448 tokens 6.00.326.925 I slot print_timing: id 0 | task 1868 | graphs reused = 1767 6.00.326.926 I slot print_timing: id 0 | task 1868 | graph reallocs = 0 / 0 (same size) / (changed size) 6.00.326.993 I slot release: id 0 | task 1868 | stop processing: n_tokens = 447, truncated = 0 6.00.331.194 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 91077624636 6.00.331.222 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 473.700 MiB) 6.00.418.071 I slot launch_slot_: id 0 | task 1932 | processing task, is_child = 0 6.04.770.265 I slot print_timing: id 0 | task 1932 | prompt processing, n_tokens = 406, progress = 0.99, t = 4.35 s / 93.29 tokens per second 6.11.696.599 I slot print_timing: id 0 | task 1932 | prompt eval time = 4963.49 ms / 410 tokens ( 12.11 ms per token, 82.60 tokens per second) 6.11.696.602 I slot print_timing: id 0 | task 1932 | eval time = 6315.02 ms / 61 tokens ( 105.25 ms per token, 9.50 tokens per second) 6.11.696.602 I slot print_timing: id 0 | task 1932 | total time = 11278.51 ms / 471 tokens 6.11.696.603 I slot print_timing: id 0 | task 1932 | graphs reused = 1826 6.11.696.603 I slot print_timing: id 0 | task 1932 | graph reallocs = 0 / 0 (same size) / (changed size) 6.11.696.661 I slot release: id 0 | task 1932 | stop processing: n_tokens = 470, truncated = 0 6.11.701.017 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 91088994304 6.11.701.049 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 474.451 MiB) 6.11.825.392 I slot launch_slot_: id 0 | task 1996 | processing task, is_child = 0 6.15.848.883 I slot print_timing: id 0 | task 1996 | prompt processing, n_tokens = 347, progress = 0.99, t = 4.02 s / 86.24 tokens per second 6.21.939.353 I slot print_timing: id 0 | task 1996 | prompt eval time = 4631.56 ms / 351 tokens ( 13.20 ms per token, 75.78 tokens per second) 6.21.939.370 I slot print_timing: id 0 | task 1996 | eval time = 5482.35 ms / 50 tokens ( 111.88 ms per token, 8.94 tokens per second) 6.21.939.373 I slot print_timing: id 0 | task 1996 | total time = 10113.92 ms / 401 tokens 6.21.939.375 I slot print_timing: id 0 | task 1996 | graphs reused = 1874 6.21.939.384 I slot print_timing: id 0 | task 1996 | graph reallocs = 0 / 0 (same size) / (changed size) 6.21.939.688 I slot release: id 0 | task 1996 | stop processing: n_tokens = 400, truncated = 0 6.21.954.181 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 91099237331 6.21.954.248 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 473.388 MiB) 6.22.076.920 I slot launch_slot_: id 0 | task 2049 | processing task, is_child = 0 6.26.451.686 I slot print_timing: id 0 | task 2049 | prompt processing, n_tokens = 389, progress = 0.99, t = 4.37 s / 88.92 tokens per second 6.38.207.783 I slot print_timing: id 0 | task 2049 | n_gen = 100, tg = 8.89 t/s, tg_3s = 8.98 t/s 6.41.221.514 I slot print_timing: id 0 | task 2049 | n_gen = 127, tg = 8.91 t/s, tg_3s = 8.96 t/s 6.44.247.071 I slot print_timing: id 0 | task 2049 | n_gen = 154, tg = 8.91 t/s, tg_3s = 8.92 t/s 6.47.336.650 I slot print_timing: id 0 | task 2049 | n_gen = 182, tg = 8.93 t/s, tg_3s = 9.06 t/s 6.50.383.582 I slot print_timing: id 0 | task 2049 | n_gen = 211, tg = 9.01 t/s, tg_3s = 9.52 t/s 6.51.749.520 I slot print_timing: id 0 | task 2049 | prompt eval time = 4997.18 ms / 393 tokens ( 12.72 ms per token, 78.64 tokens per second) 6.51.749.523 I slot print_timing: id 0 | task 2049 | eval time = 24675.40 ms / 224 tokens ( 110.65 ms per token, 9.04 tokens per second) 6.51.749.524 I slot print_timing: id 0 | task 2049 | total time = 29672.58 ms / 617 tokens 6.51.749.524 I slot print_timing: id 0 | task 2049 | graphs reused = 2095 6.51.749.524 I slot print_timing: id 0 | task 2049 | graph reallocs = 0 / 0 (same size) / (changed size) 6.51.749.584 I slot release: id 0 | task 2049 | stop processing: n_tokens = 616, truncated = 0 6.51.753.844 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 616, t_last = 91129047227 6.51.753.879 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 473.138 MiB) 6.51.846.384 I slot launch_slot_: id 0 | task 2276 | processing task, is_child = 0 6.55.501.619 I slot print_timing: id 0 | task 2276 | prompt processing, n_tokens = 317, progress = 0.99, t = 3.66 s / 86.73 tokens per second 6.59.367.488 I slot print_timing: id 0 | task 2276 | prompt eval time = 4262.98 ms / 321 tokens ( 13.28 ms per token, 75.30 tokens per second) 6.59.367.494 I slot print_timing: id 0 | task 2276 | eval time = 3258.11 ms / 32 tokens ( 105.10 ms per token, 9.51 tokens per second) 6.59.367.495 I slot print_timing: id 0 | task 2276 | total time = 7521.09 ms / 353 tokens 6.59.367.495 I slot print_timing: id 0 | task 2276 | graphs reused = 2125 6.59.367.496 I slot print_timing: id 0 | task 2276 | graph reallocs = 0 / 0 (same size) / (changed size) 6.59.367.522 I slot release: id 0 | task 2276 | stop processing: n_tokens = 352, truncated = 0 6.59.371.391 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 352, t_last = 91136665165 6.59.371.420 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 476.764 MiB) 6.59.454.913 I slot launch_slot_: id 0 | task 2311 | processing task, is_child = 0 7.03.097.918 I slot print_timing: id 0 | task 2311 | prompt processing, n_tokens = 326, progress = 0.99, t = 3.64 s / 89.49 tokens per second 7.11.701.694 I slot print_timing: id 0 | task 2311 | prompt eval time = 4250.14 ms / 330 tokens ( 12.88 ms per token, 77.64 tokens per second) 7.11.701.701 I slot print_timing: id 0 | task 2311 | eval time = 7996.62 ms / 77 tokens ( 105.22 ms per token, 9.50 tokens per second) 7.11.701.703 I slot print_timing: id 0 | task 2311 | total time = 12246.76 ms / 407 tokens 7.11.701.703 I slot print_timing: id 0 | task 2311 | graphs reused = 2200 7.11.701.704 I slot print_timing: id 0 | task 2311 | graph reallocs = 0 / 0 (same size) / (changed size) 7.11.701.729 I slot release: id 0 | task 2311 | stop processing: n_tokens = 406, truncated = 0 7.11.706.234 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 406, t_last = 91148999372 7.11.706.261 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 474.451 MiB) 7.11.718.473 I slot launch_slot_: id 0 | task 2391 | processing task, is_child = 0 7.15.380.296 I slot print_timing: id 0 | task 2391 | prompt processing, n_tokens = 337, progress = 0.99, t = 3.66 s / 92.03 tokens per second 7.19.251.282 I slot print_timing: id 0 | task 2391 | prompt eval time = 4271.05 ms / 341 tokens ( 12.53 ms per token, 79.84 tokens per second) 7.19.251.287 I slot print_timing: id 0 | task 2391 | eval time = 3261.75 ms / 32 tokens ( 105.22 ms per token, 9.50 tokens per second) 7.19.251.288 I slot print_timing: id 0 | task 2391 | total time = 7532.80 ms / 373 tokens 7.19.251.289 I slot print_timing: id 0 | task 2391 | graphs reused = 2230 7.19.251.289 I slot print_timing: id 0 | task 2391 | graph reallocs = 0 / 0 (same size) / (changed size) 7.19.251.347 I slot release: id 0 | task 2391 | stop processing: n_tokens = 372, truncated = 0 7.19.255.353 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 372, t_last = 91156548990 7.19.255.383 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 478.827 MiB) 7.19.281.363 I slot launch_slot_: id 0 | task 2426 | processing task, is_child = 0 7.23.207.173 I slot print_timing: id 0 | task 2426 | prompt processing, n_tokens = 334, progress = 0.99, t = 3.93 s / 85.08 tokens per second 7.28.866.568 I slot print_timing: id 0 | task 2426 | prompt eval time = 4394.99 ms / 338 tokens ( 13.00 ms per token, 76.91 tokens per second) 7.28.866.589 I slot print_timing: id 0 | task 2426 | eval time = 5190.16 ms / 48 tokens ( 110.43 ms per token, 9.06 tokens per second) 7.28.866.591 I slot print_timing: id 0 | task 2426 | total time = 9585.16 ms / 386 tokens 7.28.866.597 I slot print_timing: id 0 | task 2426 | graphs reused = 2276 7.28.866.598 I slot print_timing: id 0 | task 2426 | graph reallocs = 0 / 0 (same size) / (changed size) 7.28.866.867 I slot release: id 0 | task 2426 | stop processing: n_tokens = 385, truncated = 0 7.28.879.335 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 385, t_last = 91166164510 7.28.879.401 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 476.514 MiB) 7.29.009.877 I slot launch_slot_: id 0 | task 2477 | processing task, is_child = 0 7.33.067.997 I slot print_timing: id 0 | task 2477 | prompt processing, n_tokens = 391, progress = 0.99, t = 4.06 s / 96.35 tokens per second 7.40.236.096 I slot print_timing: id 0 | task 2477 | prompt eval time = 5023.37 ms / 395 tokens ( 12.72 ms per token, 78.63 tokens per second) 7.40.236.119 I slot print_timing: id 0 | task 2477 | eval time = 6202.82 ms / 56 tokens ( 112.78 ms per token, 8.87 tokens per second) 7.40.236.122 I slot print_timing: id 0 | task 2477 | total time = 11226.19 ms / 451 tokens 7.40.236.127 I slot print_timing: id 0 | task 2477 | graphs reused = 2330 7.40.236.135 I slot print_timing: id 0 | task 2477 | graph reallocs = 0 / 0 (same size) / (changed size) 7.40.236.353 I slot release: id 0 | task 2477 | stop processing: n_tokens = 450, truncated = 0 7.40.250.771 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 450, t_last = 91177533997 7.40.250.838 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 477.952 MiB) 7.40.352.625 I slot launch_slot_: id 0 | task 2536 | processing task, is_child = 0 7.46.117.792 I slot print_timing: id 0 | task 2536 | prompt processing, n_tokens = 524, progress = 0.99, t = 5.77 s / 90.89 tokens per second 7.56.188.190 I slot print_timing: id 0 | task 2536 | prompt eval time = 6729.13 ms / 528 tokens ( 12.74 ms per token, 78.46 tokens per second) 7.56.188.203 I slot print_timing: id 0 | task 2536 | eval time = 9106.39 ms / 83 tokens ( 111.05 ms per token, 9.00 tokens per second) 7.56.188.206 I slot print_timing: id 0 | task 2536 | total time = 15835.53 ms / 611 tokens 7.56.188.209 I slot print_timing: id 0 | task 2536 | graphs reused = 2411 7.56.188.211 I slot print_timing: id 0 | task 2536 | graph reallocs = 0 / 0 (same size) / (changed size) 7.56.188.549 I slot release: id 0 | task 2536 | stop processing: n_tokens = 610, truncated = 0 7.56.200.584 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 610, t_last = 91193486192 7.56.200.668 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 479.578 MiB) 7.56.200.685 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 477.202 MiB) 7.56.364.996 I slot launch_slot_: id 0 | task 2623 | processing task, is_child = 0 8.00.022.654 I slot print_timing: id 0 | task 2623 | prompt processing, n_tokens = 327, progress = 0.99, t = 3.66 s / 89.40 tokens per second 8.05.527.237 I slot print_timing: id 0 | task 2623 | prompt eval time = 4270.54 ms / 331 tokens ( 12.90 ms per token, 77.51 tokens per second) 8.05.527.249 I slot print_timing: id 0 | task 2623 | eval time = 4891.65 ms / 45 tokens ( 111.17 ms per token, 8.99 tokens per second) 8.05.527.252 I slot print_timing: id 0 | task 2623 | total time = 9162.19 ms / 376 tokens 8.05.527.254 I slot print_timing: id 0 | task 2623 | graphs reused = 2454 8.05.527.256 I slot print_timing: id 0 | task 2623 | graph reallocs = 0 / 0 (same size) / (changed size) 8.05.527.468 I slot release: id 0 | task 2623 | stop processing: n_tokens = 387, truncated = 0 8.05.540.147 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 387, t_last = 91202825111 8.05.540.215 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 473.763 MiB) 8.05.666.706 I slot launch_slot_: id 0 | task 2671 | processing task, is_child = 0 8.09.695.386 I slot print_timing: id 0 | task 2671 | prompt processing, n_tokens = 358, progress = 0.99, t = 4.03 s / 88.86 tokens per second 8.15.861.309 I slot print_timing: id 0 | task 2671 | prompt eval time = 4635.72 ms / 362 tokens ( 12.81 ms per token, 78.09 tokens per second) 8.15.861.315 I slot print_timing: id 0 | task 2671 | eval time = 5558.86 ms / 53 tokens ( 106.90 ms per token, 9.35 tokens per second) 8.15.861.316 I slot print_timing: id 0 | task 2671 | total time = 10194.58 ms / 415 tokens 8.15.861.320 I slot print_timing: id 0 | task 2671 | graphs reused = 2505 8.15.861.341 I slot print_timing: id 0 | task 2671 | graph reallocs = 0 / 0 (same size) / (changed size) 8.15.861.460 I slot release: id 0 | task 2671 | stop processing: n_tokens = 426, truncated = 0 8.15.874.545 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 91213159103 8.15.874.629 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 476.389 MiB) 8.16.015.523 I slot launch_slot_: id 0 | task 2727 | processing task, is_child = 0 8.20.381.827 I slot print_timing: id 0 | task 2727 | prompt processing, n_tokens = 415, progress = 0.99, t = 4.37 s / 95.05 tokens per second 8.28.476.785 I slot print_timing: id 0 | task 2727 | prompt eval time = 5310.42 ms / 419 tokens ( 12.67 ms per token, 78.90 tokens per second) 8.28.476.791 I slot print_timing: id 0 | task 2727 | eval time = 7150.83 ms / 69 tokens ( 105.16 ms per token, 9.51 tokens per second) 8.28.476.791 I slot print_timing: id 0 | task 2727 | total time = 12461.25 ms / 488 tokens 8.28.476.792 I slot print_timing: id 0 | task 2727 | graphs reused = 2572 8.28.476.792 I slot print_timing: id 0 | task 2727 | graph reallocs = 0 / 0 (same size) / (changed size) 8.28.476.879 I slot release: id 0 | task 2727 | stop processing: n_tokens = 499, truncated = 0 8.28.481.864 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 499, t_last = 91225774523 8.28.481.898 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 479.452 MiB) 8.28.481.910 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 477.264 MiB) 8.28.581.735 I slot launch_slot_: id 0 | task 2799 | processing task, is_child = 0 8.33.322.985 I slot print_timing: id 0 | task 2799 | prompt processing, n_tokens = 419, progress = 0.99, t = 4.74 s / 88.37 tokens per second 8.38.458.964 I slot print_timing: id 0 | task 2799 | prompt eval time = 5355.53 ms / 423 tokens ( 12.66 ms per token, 78.98 tokens per second) 8.38.458.971 I slot print_timing: id 0 | task 2799 | eval time = 4521.68 ms / 44 tokens ( 105.16 ms per token, 9.51 tokens per second) 8.38.458.972 I slot print_timing: id 0 | task 2799 | total time = 9877.21 ms / 467 tokens 8.38.458.974 I slot print_timing: id 0 | task 2799 | graphs reused = 2614 8.38.458.975 I slot print_timing: id 0 | task 2799 | graph reallocs = 0 / 0 (same size) / (changed size) 8.38.459.115 I slot release: id 0 | task 2799 | stop processing: n_tokens = 478, truncated = 0 8.38.467.291 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 478, t_last = 91235756758 8.38.467.358 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 474.888 MiB) 8.38.621.822 I slot launch_slot_: id 0 | task 2846 | processing task, is_child = 0 8.42.264.144 I slot print_timing: id 0 | task 2846 | prompt processing, n_tokens = 337, progress = 0.99, t = 3.64 s / 92.52 tokens per second 8.47.288.344 I slot print_timing: id 0 | task 2846 | prompt eval time = 4250.50 ms / 341 tokens ( 12.46 ms per token, 80.23 tokens per second) 8.47.288.347 I slot print_timing: id 0 | task 2846 | eval time = 4416.00 ms / 43 tokens ( 105.14 ms per token, 9.51 tokens per second) 8.47.288.347 I slot print_timing: id 0 | task 2846 | total time = 8666.51 ms / 384 tokens 8.47.288.348 I slot print_timing: id 0 | task 2846 | graphs reused = 2655 8.47.288.348 I slot print_timing: id 0 | task 2846 | graph reallocs = 0 / 0 (same size) / (changed size) 8.47.288.399 I slot release: id 0 | task 2846 | stop processing: n_tokens = 395, truncated = 0 8.47.292.531 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 395, t_last = 91244586042 8.47.292.560 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 474.763 MiB) 8.47.396.122 I slot launch_slot_: id 0 | task 2892 | processing task, is_child = 0 8.51.429.798 I slot print_timing: id 0 | task 2892 | prompt processing, n_tokens = 352, progress = 0.99, t = 4.03 s / 87.27 tokens per second 8.56.961.205 I slot print_timing: id 0 | task 2892 | prompt eval time = 4643.83 ms / 356 tokens ( 13.04 ms per token, 76.66 tokens per second) 8.56.961.216 I slot print_timing: id 0 | task 2892 | eval time = 4921.21 ms / 47 tokens ( 106.98 ms per token, 9.35 tokens per second) 8.56.961.225 I slot print_timing: id 0 | task 2892 | total time = 9565.05 ms / 403 tokens 8.56.961.227 I slot print_timing: id 0 | task 2892 | graphs reused = 2700 8.56.961.229 I slot print_timing: id 0 | task 2892 | graph reallocs = 0 / 0 (same size) / (changed size) 8.56.961.340 I slot release: id 0 | task 2892 | stop processing: n_tokens = 414, truncated = 0 8.56.975.348 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 91254258984 8.56.975.429 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 476.826 MiB) 8.56.975.457 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 478.265 MiB) 8.57.124.673 I slot launch_slot_: id 0 | task 2942 | processing task, is_child = 0 9.01.162.211 I slot print_timing: id 0 | task 2942 | prompt processing, n_tokens = 358, progress = 0.99, t = 4.04 s / 88.67 tokens per second 9.06.508.481 I slot print_timing: id 0 | task 2942 | prompt eval time = 4646.62 ms / 362 tokens ( 12.84 ms per token, 77.91 tokens per second) 9.06.508.485 I slot print_timing: id 0 | task 2942 | eval time = 4737.17 ms / 46 tokens ( 105.27 ms per token, 9.50 tokens per second) 9.06.508.487 I slot print_timing: id 0 | task 2942 | total time = 9383.80 ms / 408 tokens 9.06.508.487 I slot print_timing: id 0 | task 2942 | graphs reused = 2744 9.06.508.488 I slot print_timing: id 0 | task 2942 | graph reallocs = 0 / 0 (same size) / (changed size) 9.06.508.540 I slot release: id 0 | task 2942 | stop processing: n_tokens = 419, truncated = 0 9.06.512.852 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 91263806183 9.06.512.881 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 473.888 MiB) 9.06.630.408 I slot launch_slot_: id 0 | task 2991 | processing task, is_child = 0 9.10.980.582 I slot print_timing: id 0 | task 2991 | prompt processing, n_tokens = 387, progress = 0.99, t = 4.35 s / 88.96 tokens per second 9.19.018.009 I slot print_timing: id 0 | task 2991 | prompt eval time = 4965.56 ms / 391 tokens ( 12.70 ms per token, 78.74 tokens per second) 9.19.018.027 I slot print_timing: id 0 | task 2991 | eval time = 7421.99 ms / 68 tokens ( 110.78 ms per token, 9.03 tokens per second) 9.19.018.029 I slot print_timing: id 0 | task 2991 | total time = 12387.55 ms / 459 tokens 9.19.018.032 I slot print_timing: id 0 | task 2991 | graphs reused = 2810 9.19.018.034 I slot print_timing: id 0 | task 2991 | graph reallocs = 0 / 0 (same size) / (changed size) 9.19.018.313 I slot release: id 0 | task 2991 | stop processing: n_tokens = 470, truncated = 0 9.19.030.658 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 91276315956 9.19.030.727 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 487.393 MiB) 9.19.148.741 I slot launch_slot_: id 0 | task 3062 | processing task, is_child = 0 9.22.816.322 I slot print_timing: id 0 | task 3062 | prompt processing, n_tokens = 339, progress = 0.99, t = 3.67 s / 92.43 tokens per second 9.29.350.841 I slot print_timing: id 0 | task 3062 | prompt eval time = 4277.81 ms / 343 tokens ( 12.47 ms per token, 80.18 tokens per second) 9.29.350.854 I slot print_timing: id 0 | task 3062 | eval time = 5924.26 ms / 54 tokens ( 111.78 ms per token, 8.95 tokens per second) 9.29.350.867 I slot print_timing: id 0 | task 3062 | total time = 10202.07 ms / 397 tokens 9.29.350.869 I slot print_timing: id 0 | task 3062 | graphs reused = 2862 9.29.350.871 I slot print_timing: id 0 | task 3062 | graph reallocs = 0 / 0 (same size) / (changed size) 9.29.350.967 I slot release: id 0 | task 3062 | stop processing: n_tokens = 408, truncated = 0 9.29.363.790 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 408, t_last = 91286648610 9.29.363.854 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 470.887 MiB) 9.29.506.839 I slot launch_slot_: id 0 | task 3119 | processing task, is_child = 0 9.33.860.704 I slot print_timing: id 0 | task 3119 | prompt processing, n_tokens = 397, progress = 0.99, t = 4.35 s / 91.18 tokens per second 9.39.286.474 I slot print_timing: id 0 | task 3119 | prompt eval time = 4966.32 ms / 401 tokens ( 12.38 ms per token, 80.74 tokens per second) 9.39.286.487 I slot print_timing: id 0 | task 3119 | eval time = 4813.27 ms / 46 tokens ( 106.96 ms per token, 9.35 tokens per second) 9.39.286.490 I slot print_timing: id 0 | task 3119 | total time = 9779.59 ms / 447 tokens 9.39.286.493 I slot print_timing: id 0 | task 3119 | graphs reused = 2906 9.39.286.495 I slot print_timing: id 0 | task 3119 | graph reallocs = 0 / 0 (same size) / (changed size) 9.39.286.812 I slot release: id 0 | task 3119 | stop processing: n_tokens = 458, truncated = 0 9.39.301.942 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 91296584455 9.39.302.029 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 474.263 MiB) 9.39.302.082 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 472.137 MiB) 9.39.454.653 I slot launch_slot_: id 0 | task 3168 | processing task, is_child = 0 9.43.485.608 I slot print_timing: id 0 | task 3168 | prompt processing, n_tokens = 351, progress = 0.99, t = 4.03 s / 87.08 tokens per second 9.51.488.062 I slot print_timing: id 0 | task 3168 | prompt eval time = 4640.43 ms / 355 tokens ( 13.07 ms per token, 76.50 tokens per second) 9.51.488.074 I slot print_timing: id 0 | task 3168 | eval time = 7392.95 ms / 68 tokens ( 110.34 ms per token, 9.06 tokens per second) 9.51.488.077 I slot print_timing: id 0 | task 3168 | total time = 12033.38 ms / 423 tokens 9.51.488.079 I slot print_timing: id 0 | task 3168 | graphs reused = 2972 9.51.488.081 I slot print_timing: id 0 | task 3168 | graph reallocs = 0 / 0 (same size) / (changed size) 9.51.488.278 I slot release: id 0 | task 3168 | stop processing: n_tokens = 434, truncated = 0 9.51.501.033 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 434, t_last = 91308785921 9.51.501.105 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 472.950 MiB) 9.51.650.791 I slot launch_slot_: id 0 | task 3239 | processing task, is_child = 0 9.55.674.213 I slot print_timing: id 0 | task 3239 | prompt processing, n_tokens = 347, progress = 0.99, t = 4.02 s / 86.25 tokens per second 10.02.194.328 I slot print_timing: id 0 | task 3239 | prompt eval time = 4633.45 ms / 351 tokens ( 13.20 ms per token, 75.75 tokens per second) 10.02.194.331 I slot print_timing: id 0 | task 3239 | eval time = 5910.07 ms / 57 tokens ( 105.54 ms per token, 9.48 tokens per second) 10.02.194.332 I slot print_timing: id 0 | task 3239 | total time = 10543.52 ms / 408 tokens 10.02.194.332 I slot print_timing: id 0 | task 3239 | graphs reused = 3027 10.02.194.333 I slot print_timing: id 0 | task 3239 | graph reallocs = 0 / 0 (same size) / (changed size) 10.02.194.386 I slot release: id 0 | task 3239 | stop processing: n_tokens = 419, truncated = 0 10.02.199.146 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 91319492029 10.02.199.177 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 477.014 MiB) 10.02.279.920 I slot launch_slot_: id 0 | task 3299 | processing task, is_child = 0 10.07.387.200 I slot print_timing: id 0 | task 3299 | prompt processing, n_tokens = 471, progress = 0.99, t = 5.11 s / 92.22 tokens per second 10.18.020.549 I slot print_timing: id 0 | task 3299 | prompt eval time = 6051.56 ms / 475 tokens ( 12.74 ms per token, 78.49 tokens per second) 10.18.020.552 I slot print_timing: id 0 | task 3299 | eval time = 9689.05 ms / 93 tokens ( 105.32 ms per token, 9.50 tokens per second) 10.18.020.552 I slot print_timing: id 0 | task 3299 | total time = 15740.61 ms / 568 tokens 10.18.020.553 I slot print_timing: id 0 | task 3299 | graphs reused = 3117 10.18.020.553 I slot print_timing: id 0 | task 3299 | graph reallocs = 0 / 0 (same size) / (changed size) 10.18.020.597 I slot release: id 0 | task 3299 | stop processing: n_tokens = 579, truncated = 0 10.18.025.544 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 579, t_last = 91335318240 10.18.025.574 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 636.644 MiB) 10.18.118.848 I slot launch_slot_: id 0 | task 3395 | processing task, is_child = 0 10.22.861.813 I slot print_timing: id 0 | task 3395 | prompt processing, n_tokens = 436, progress = 0.99, t = 4.74 s / 91.93 tokens per second 10.34.400.356 I slot print_timing: id 0 | task 3395 | n_gen = 100, tg = 9.34 t/s, tg_3s = 9.44 t/s 10.35.077.368 I slot print_timing: id 0 | task 3395 | prompt eval time = 5686.73 ms / 440 tokens ( 12.92 ms per token, 77.37 tokens per second) 10.35.077.375 I slot print_timing: id 0 | task 3395 | eval time = 11271.77 ms / 106 tokens ( 107.35 ms per token, 9.32 tokens per second) 10.35.077.376 I slot print_timing: id 0 | task 3395 | total time = 16958.50 ms / 546 tokens 10.35.077.377 I slot print_timing: id 0 | task 3395 | graphs reused = 3220 10.35.077.378 I slot print_timing: id 0 | task 3395 | graph reallocs = 0 / 0 (same size) / (changed size) 10.35.077.485 I slot release: id 0 | task 3395 | stop processing: n_tokens = 557, truncated = 0 10.35.089.302 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 557, t_last = 91352375128 10.35.089.378 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 622.701 MiB) 10.35.203.676 I slot launch_slot_: id 0 | task 3504 | processing task, is_child = 0 10.38.878.367 I slot print_timing: id 0 | task 3504 | prompt processing, n_tokens = 341, progress = 0.99, t = 3.67 s / 92.80 tokens per second 10.45.457.735 I slot print_timing: id 0 | task 3504 | prompt eval time = 4283.77 ms / 345 tokens ( 12.42 ms per token, 80.54 tokens per second) 10.45.457.758 I slot print_timing: id 0 | task 3504 | eval time = 5970.25 ms / 55 tokens ( 110.56 ms per token, 9.04 tokens per second) 10.45.457.761 I slot print_timing: id 0 | task 3504 | total time = 10254.03 ms / 400 tokens 10.45.457.763 I slot print_timing: id 0 | task 3504 | graphs reused = 3273 10.45.457.765 I slot print_timing: id 0 | task 3504 | graph reallocs = 0 / 0 (same size) / (changed size) 10.45.457.947 I slot release: id 0 | task 3504 | stop processing: n_tokens = 411, truncated = 0 10.45.470.290 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 91362755590 10.45.470.357 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 625.140 MiB) 10.45.612.197 I slot launch_slot_: id 0 | task 3562 | processing task, is_child = 0 10.49.958.280 I slot print_timing: id 0 | task 3562 | prompt processing, n_tokens = 378, progress = 0.99, t = 4.35 s / 86.98 tokens per second 10.56.250.541 I slot print_timing: id 0 | task 3562 | prompt eval time = 4958.98 ms / 382 tokens ( 12.98 ms per token, 77.03 tokens per second) 10.56.250.544 I slot print_timing: id 0 | task 3562 | eval time = 5679.34 ms / 55 tokens ( 105.17 ms per token, 9.51 tokens per second) 10.56.250.545 I slot print_timing: id 0 | task 3562 | total time = 10638.33 ms / 437 tokens 10.56.250.545 I slot print_timing: id 0 | task 3562 | graphs reused = 3326 10.56.250.546 I slot print_timing: id 0 | task 3562 | graph reallocs = 0 / 0 (same size) / (changed size) 10.56.250.592 I slot release: id 0 | task 3562 | stop processing: n_tokens = 448, truncated = 0 10.56.255.181 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 91373548235 10.56.255.215 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 629.704 MiB) 10.56.350.665 I slot launch_slot_: id 0 | task 3620 | processing task, is_child = 0 11.00.024.871 I slot print_timing: id 0 | task 3620 | prompt processing, n_tokens = 333, progress = 0.99, t = 3.67 s / 90.63 tokens per second 11.05.501.279 I slot print_timing: id 0 | task 3620 | prompt eval time = 4282.18 ms / 337 tokens ( 12.71 ms per token, 78.70 tokens per second) 11.05.501.298 I slot print_timing: id 0 | task 3620 | eval time = 4868.40 ms / 45 tokens ( 110.65 ms per token, 9.04 tokens per second) 11.05.501.301 I slot print_timing: id 0 | task 3620 | total time = 9150.58 ms / 382 tokens 11.05.501.304 I slot print_timing: id 0 | task 3620 | graphs reused = 3369 11.05.501.306 I slot print_timing: id 0 | task 3620 | graph reallocs = 0 / 0 (same size) / (changed size) 11.05.501.589 I slot release: id 0 | task 3620 | stop processing: n_tokens = 393, truncated = 0 11.05.515.073 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 91382799233 11.05.515.141 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 628.391 MiB) 11.05.680.685 I slot launch_slot_: id 0 | task 3668 | processing task, is_child = 0 11.10.052.106 I slot print_timing: id 0 | task 3668 | prompt processing, n_tokens = 398, progress = 0.99, t = 4.37 s / 91.05 tokens per second 11.18.164.145 I slot print_timing: id 0 | task 3668 | prompt eval time = 4983.95 ms / 402 tokens ( 12.40 ms per token, 80.66 tokens per second) 11.18.164.158 I slot print_timing: id 0 | task 3668 | eval time = 7499.44 ms / 70 tokens ( 108.69 ms per token, 9.20 tokens per second) 11.18.164.161 I slot print_timing: id 0 | task 3668 | total time = 12483.39 ms / 472 tokens 11.18.164.163 I slot print_timing: id 0 | task 3668 | graphs reused = 3437 11.18.164.165 I slot print_timing: id 0 | task 3668 | graph reallocs = 0 / 0 (same size) / (changed size) 11.18.164.445 I slot release: id 0 | task 3668 | stop processing: n_tokens = 483, truncated = 0 11.18.179.589 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 483, t_last = 91395462089 11.18.179.662 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 623.201 MiB) 11.18.300.886 I slot launch_slot_: id 0 | task 3741 | processing task, is_child = 0 11.24.544.858 I slot print_timing: id 0 | task 3741 | prompt processing, n_tokens = 545, progress = 0.99, t = 6.24 s / 87.28 tokens per second 11.31.399.987 I slot print_timing: id 0 | task 3741 | prompt eval time = 7188.10 ms / 549 tokens ( 13.09 ms per token, 76.38 tokens per second) 11.31.400.001 I slot print_timing: id 0 | task 3741 | eval time = 5910.95 ms / 57 tokens ( 105.55 ms per token, 9.47 tokens per second) 11.31.400.006 I slot print_timing: id 0 | task 3741 | total time = 13099.06 ms / 606 tokens 11.31.400.008 I slot print_timing: id 0 | task 3741 | graphs reused = 3492 11.31.400.010 I slot print_timing: id 0 | task 3741 | graph reallocs = 0 / 0 (same size) / (changed size) 11.31.400.267 I slot release: id 0 | task 3741 | stop processing: n_tokens = 617, truncated = 0 11.31.415.546 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 617, t_last = 91408697911 11.31.415.643 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 624.389 MiB) 11.31.415.657 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 624.702 MiB) 11.31.628.089 I slot launch_slot_: id 0 | task 3802 | processing task, is_child = 0 11.38.568.264 I slot print_timing: id 0 | task 3802 | prompt processing, n_tokens = 612, progress = 0.99, t = 6.94 s / 88.18 tokens per second 11.45.532.943 I slot print_timing: id 0 | task 3802 | prompt eval time = 7904.61 ms / 616 tokens ( 12.83 ms per token, 77.93 tokens per second) 11.45.532.946 I slot print_timing: id 0 | task 3802 | eval time = 6000.23 ms / 58 tokens ( 105.27 ms per token, 9.50 tokens per second) 11.45.532.946 I slot print_timing: id 0 | task 3802 | total time = 13904.84 ms / 674 tokens 11.45.532.947 I slot print_timing: id 0 | task 3802 | graphs reused = 3548 11.45.532.948 I slot print_timing: id 0 | task 3802 | graph reallocs = 0 / 0 (same size) / (changed size) 11.45.533.013 I slot release: id 0 | task 3802 | stop processing: n_tokens = 685, truncated = 0 11.45.538.716 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 685, t_last = 91422830657 11.45.538.754 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 627.891 MiB) 11.45.736.382 I slot launch_slot_: id 0 | task 3864 | processing task, is_child = 0 11.53.097.307 I slot print_timing: id 0 | task 3864 | prompt processing, n_tokens = 661, progress = 0.99, t = 7.36 s / 89.80 tokens per second 12.00.826.504 I slot print_timing: id 0 | task 3864 | prompt eval time = 8334.68 ms / 665 tokens ( 12.53 ms per token, 79.79 tokens per second) 12.00.826.531 I slot print_timing: id 0 | task 3864 | eval time = 6755.43 ms / 61 tokens ( 112.59 ms per token, 8.88 tokens per second) 12.00.826.535 I slot print_timing: id 0 | task 3864 | total time = 15090.10 ms / 726 tokens 12.00.826.536 I slot print_timing: id 0 | task 3864 | graphs reused = 3607 12.00.826.549 I slot print_timing: id 0 | task 3864 | graph reallocs = 0 / 0 (same size) / (changed size) 12.00.826.728 I slot release: id 0 | task 3864 | stop processing: n_tokens = 737, truncated = 0 12.00.843.221 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 737, t_last = 91438124371 12.00.843.312 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 624.014 MiB) 12.00.983.464 I slot launch_slot_: id 0 | task 3929 | processing task, is_child = 0 12.08.635.809 I slot print_timing: id 0 | task 3929 | prompt processing, n_tokens = 641, progress = 0.99, t = 7.65 s / 83.77 tokens per second 12.15.087.767 I slot print_timing: id 0 | task 3929 | prompt eval time = 8268.60 ms / 645 tokens ( 12.82 ms per token, 78.01 tokens per second) 12.15.087.791 I slot print_timing: id 0 | task 3929 | eval time = 5835.67 ms / 55 tokens ( 108.07 ms per token, 9.25 tokens per second) 12.15.087.794 I slot print_timing: id 0 | task 3929 | total time = 14104.27 ms / 700 tokens 12.15.087.796 I slot print_timing: id 0 | task 3929 | graphs reused = 3660 12.15.087.798 I slot print_timing: id 0 | task 3929 | graph reallocs = 0 / 0 (same size) / (changed size) 12.15.088.057 I slot release: id 0 | task 3929 | stop processing: n_tokens = 711, truncated = 0 12.15.103.122 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 711, t_last = 91452385700 12.15.103.217 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 627.140 MiB) 12.15.246.738 I slot launch_slot_: id 0 | task 3988 | processing task, is_child = 0 12.20.349.644 I slot print_timing: id 0 | task 3988 | prompt processing, n_tokens = 470, progress = 0.99, t = 5.10 s / 92.10 tokens per second 12.26.348.866 I slot print_timing: id 0 | task 3988 | prompt eval time = 5717.84 ms / 474 tokens ( 12.06 ms per token, 82.90 tokens per second) 12.26.348.879 I slot print_timing: id 0 | task 3988 | eval time = 5384.25 ms / 52 tokens ( 105.57 ms per token, 9.47 tokens per second) 12.26.348.881 I slot print_timing: id 0 | task 3988 | total time = 11102.09 ms / 526 tokens 12.26.348.883 I slot print_timing: id 0 | task 3988 | graphs reused = 3709 12.26.348.885 I slot print_timing: id 0 | task 3988 | graph reallocs = 0 / 0 (same size) / (changed size) 12.26.349.094 I slot release: id 0 | task 3988 | stop processing: n_tokens = 537, truncated = 0 12.26.362.889 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 537, t_last = 91463646738 12.26.362.963 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 625.640 MiB) 12.26.493.315 I slot launch_slot_: id 0 | task 4043 | processing task, is_child = 0 12.33.770.172 I slot print_timing: id 0 | task 4043 | prompt processing, n_tokens = 613, progress = 0.99, t = 7.28 s / 84.24 tokens per second 12.38.700.188 I slot print_timing: id 0 | task 4043 | prompt eval time = 7891.88 ms / 617 tokens ( 12.79 ms per token, 78.18 tokens per second) 12.38.700.194 I slot print_timing: id 0 | task 4043 | eval time = 4314.98 ms / 42 tokens ( 105.24 ms per token, 9.50 tokens per second) 12.38.700.194 I slot print_timing: id 0 | task 4043 | total time = 12206.86 ms / 659 tokens 12.38.700.195 I slot print_timing: id 0 | task 4043 | graphs reused = 3749 12.38.700.195 I slot print_timing: id 0 | task 4043 | graph reallocs = 0 / 0 (same size) / (changed size) 12.38.700.267 I slot release: id 0 | task 4043 | stop processing: n_tokens = 670, truncated = 0 12.38.705.653 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 670, t_last = 91475997910 12.38.705.691 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 624.702 MiB) 12.38.705.699 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 634.706 MiB) 12.38.830.366 I slot launch_slot_: id 0 | task 4089 | processing task, is_child = 0 12.45.799.947 I slot print_timing: id 0 | task 4089 | prompt processing, n_tokens = 597, progress = 0.99, t = 6.97 s / 85.66 tokens per second 12.51.360.695 I slot print_timing: id 0 | task 4089 | prompt eval time = 7585.40 ms / 601 tokens ( 12.62 ms per token, 79.23 tokens per second) 12.51.360.698 I slot print_timing: id 0 | task 4089 | eval time = 4944.91 ms / 48 tokens ( 105.21 ms per token, 9.50 tokens per second) 12.51.360.699 I slot print_timing: id 0 | task 4089 | total time = 12530.31 ms / 649 tokens 12.51.360.700 I slot print_timing: id 0 | task 4089 | graphs reused = 3795 12.51.360.700 I slot print_timing: id 0 | task 4089 | graph reallocs = 0 / 0 (same size) / (changed size) 12.51.360.765 I slot release: id 0 | task 4089 | stop processing: n_tokens = 660, truncated = 0 12.51.365.284 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 660, t_last = 91488658408 12.51.365.324 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 633.330 MiB) 12.51.495.718 I slot launch_slot_: id 0 | task 4141 | processing task, is_child = 0 12.57.732.242 I slot print_timing: id 0 | task 4141 | prompt processing, n_tokens = 529, progress = 0.99, t = 6.24 s / 84.82 tokens per second 13.03.505.794 I slot print_timing: id 0 | task 4141 | prompt eval time = 6848.46 ms / 533 tokens ( 12.85 ms per token, 77.83 tokens per second) 13.03.505.812 I slot print_timing: id 0 | task 4141 | eval time = 5161.56 ms / 47 tokens ( 112.21 ms per token, 8.91 tokens per second) 13.03.505.819 I slot print_timing: id 0 | task 4141 | total time = 12010.03 ms / 580 tokens 13.03.505.822 I slot print_timing: id 0 | task 4141 | graphs reused = 3840 13.03.505.824 I slot print_timing: id 0 | task 4141 | graph reallocs = 0 / 0 (same size) / (changed size) 13.03.506.027 I slot release: id 0 | task 4141 | stop processing: n_tokens = 591, truncated = 0 13.03.519.384 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 591, t_last = 91500803671 13.03.519.459 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 624.202 MiB) 13.03.655.561 I slot launch_slot_: id 0 | task 4192 | processing task, is_child = 0 13.09.111.694 I slot print_timing: id 0 | task 4192 | prompt processing, n_tokens = 476, progress = 0.99, t = 5.46 s / 87.24 tokens per second 13.15.427.113 I slot print_timing: id 0 | task 4192 | prompt eval time = 6063.75 ms / 480 tokens ( 12.63 ms per token, 79.16 tokens per second) 13.15.427.125 I slot print_timing: id 0 | task 4192 | eval time = 5707.77 ms / 52 tokens ( 111.92 ms per token, 8.94 tokens per second) 13.15.427.128 I slot print_timing: id 0 | task 4192 | total time = 11771.52 ms / 532 tokens 13.15.427.130 I slot print_timing: id 0 | task 4192 | graphs reused = 3889 13.15.427.211 I slot print_timing: id 0 | task 4192 | graph reallocs = 0 / 0 (same size) / (changed size) 13.15.427.395 I slot release: id 0 | task 4192 | stop processing: n_tokens = 560, truncated = 0 13.15.441.387 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 91512725038 13.15.441.461 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 626.515 MiB) 13.15.441.494 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 623.076 MiB) 13.15.593.351 I slot launch_slot_: id 0 | task 4247 | processing task, is_child = 0 13.22.189.827 I slot print_timing: id 0 | task 4247 | prompt processing, n_tokens = 563, progress = 0.99, t = 6.60 s / 85.35 tokens per second 13.27.442.621 I slot print_timing: id 0 | task 4247 | prompt eval time = 7226.60 ms / 567 tokens ( 12.75 ms per token, 78.46 tokens per second) 13.27.442.640 I slot print_timing: id 0 | task 4247 | eval time = 4622.63 ms / 42 tokens ( 112.75 ms per token, 8.87 tokens per second) 13.27.442.643 I slot print_timing: id 0 | task 4247 | total time = 11849.23 ms / 609 tokens 13.27.442.646 I slot print_timing: id 0 | task 4247 | graphs reused = 3929 13.27.442.648 I slot print_timing: id 0 | task 4247 | graph reallocs = 0 / 0 (same size) / (changed size) 13.27.442.954 I slot release: id 0 | task 4247 | stop processing: n_tokens = 637, truncated = 0 13.27.456.073 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 91524740598 13.27.456.153 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 628.703 MiB) 13.27.719.492 I slot launch_slot_: id 0 | task 4293 | processing task, is_child = 0 13.33.203.133 I slot print_timing: id 0 | task 4293 | prompt processing, n_tokens = 502, progress = 0.99, t = 5.48 s / 91.55 tokens per second 13.40.346.845 I slot print_timing: id 0 | task 4293 | prompt eval time = 6096.34 ms / 506 tokens ( 12.05 ms per token, 83.00 tokens per second) 13.40.346.848 I slot print_timing: id 0 | task 4293 | eval time = 6531.01 ms / 63 tokens ( 105.34 ms per token, 9.49 tokens per second) 13.40.346.849 I slot print_timing: id 0 | task 4293 | total time = 12627.34 ms / 569 tokens 13.40.346.849 I slot print_timing: id 0 | task 4293 | graphs reused = 3990 13.40.346.850 I slot print_timing: id 0 | task 4293 | graph reallocs = 0 / 0 (same size) / (changed size) 13.40.346.891 I slot release: id 0 | task 4293 | stop processing: n_tokens = 597, truncated = 0 13.40.351.510 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 597, t_last = 91537644534 13.40.351.542 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 786.708 MiB) 13.40.458.753 I slot launch_slot_: id 0 | task 4359 | processing task, is_child = 0 13.45.196.803 I slot print_timing: id 0 | task 4359 | prompt processing, n_tokens = 432, progress = 0.99, t = 4.74 s / 91.18 tokens per second 13.49.906.705 I slot print_timing: id 0 | task 4359 | prompt eval time = 5344.65 ms / 436 tokens ( 12.26 ms per token, 81.58 tokens per second) 13.49.906.708 I slot print_timing: id 0 | task 4359 | eval time = 4103.29 ms / 40 tokens ( 105.21 ms per token, 9.50 tokens per second) 13.49.906.708 I slot print_timing: id 0 | task 4359 | total time = 9447.94 ms / 476 tokens 13.49.906.709 I slot print_timing: id 0 | task 4359 | graphs reused = 4028 13.49.906.709 I slot print_timing: id 0 | task 4359 | graph reallocs = 0 / 0 (same size) / (changed size) 13.49.906.738 I slot release: id 0 | task 4359 | stop processing: n_tokens = 504, truncated = 0 13.49.911.700 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 91547204381 13.49.911.733 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 790.959 MiB) 13.50.000.995 I slot launch_slot_: id 0 | task 4402 | processing task, is_child = 0 13.55.990.687 I slot print_timing: id 0 | task 4402 | prompt processing, n_tokens = 515, progress = 0.99, t = 5.99 s / 85.98 tokens per second 14.03.218.887 I slot print_timing: id 0 | task 4402 | prompt eval time = 6603.77 ms / 519 tokens ( 12.72 ms per token, 78.59 tokens per second) 14.03.218.907 I slot print_timing: id 0 | task 4402 | eval time = 6614.09 ms / 62 tokens ( 108.43 ms per token, 9.22 tokens per second) 14.03.218.909 I slot print_timing: id 0 | task 4402 | total time = 13217.86 ms / 581 tokens 14.03.218.911 I slot print_timing: id 0 | task 4402 | graphs reused = 4088 14.03.218.913 I slot print_timing: id 0 | task 4402 | graph reallocs = 0 / 0 (same size) / (changed size) 14.03.219.143 I slot release: id 0 | task 4402 | stop processing: n_tokens = 609, truncated = 0 14.03.232.383 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 609, t_last = 91560516787 14.03.232.471 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 794.210 MiB) 14.03.294.695 I slot launch_slot_: id 0 | task 4468 | processing task, is_child = 0 14.08.395.490 I slot print_timing: id 0 | task 4468 | prompt processing, n_tokens = 461, progress = 0.99, t = 5.10 s / 90.38 tokens per second 14.14.083.331 I slot print_timing: id 0 | task 4468 | prompt eval time = 5709.36 ms / 465 tokens ( 12.28 ms per token, 81.45 tokens per second) 14.14.083.348 I slot print_timing: id 0 | task 4468 | eval time = 5079.23 ms / 46 tokens ( 112.87 ms per token, 8.86 tokens per second) 14.14.083.356 I slot print_timing: id 0 | task 4468 | total time = 10788.60 ms / 511 tokens 14.14.083.358 I slot print_timing: id 0 | task 4468 | graphs reused = 4131 14.14.083.360 I slot print_timing: id 0 | task 4468 | graph reallocs = 0 / 0 (same size) / (changed size) 14.14.083.651 I slot release: id 0 | task 4468 | stop processing: n_tokens = 542, truncated = 0 14.14.096.904 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 542, t_last = 91571381295 14.14.096.978 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 792.585 MiB) 14.14.261.127 I slot launch_slot_: id 0 | task 4517 | processing task, is_child = 0 14.19.018.360 I slot print_timing: id 0 | task 4517 | prompt processing, n_tokens = 427, progress = 0.99, t = 4.76 s / 89.76 tokens per second 14.24.132.728 I slot print_timing: id 0 | task 4517 | prompt eval time = 5382.53 ms / 431 tokens ( 12.49 ms per token, 80.07 tokens per second) 14.24.132.741 I slot print_timing: id 0 | task 4517 | eval time = 4489.03 ms / 41 tokens ( 112.23 ms per token, 8.91 tokens per second) 14.24.132.743 I slot print_timing: id 0 | task 4517 | total time = 9871.56 ms / 472 tokens 14.24.132.746 I slot print_timing: id 0 | task 4517 | graphs reused = 4170 14.24.132.748 I slot print_timing: id 0 | task 4517 | graph reallocs = 0 / 0 (same size) / (changed size) 14.24.132.905 I slot release: id 0 | task 4517 | stop processing: n_tokens = 503, truncated = 0 14.24.146.505 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 503, t_last = 91581430549 14.24.146.594 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 632.080 MiB) 14.24.146.604 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 790.021 MiB) 14.24.333.077 I slot launch_slot_: id 0 | task 4561 | processing task, is_child = 0 14.29.426.049 I slot print_timing: id 0 | task 4561 | prompt processing, n_tokens = 453, progress = 0.99, t = 5.09 s / 88.95 tokens per second 14.34.699.766 I slot print_timing: id 0 | task 4561 | prompt eval time = 5701.33 ms / 457 tokens ( 12.48 ms per token, 80.16 tokens per second) 14.34.699.783 I slot print_timing: id 0 | task 4561 | eval time = 4665.30 ms / 44 tokens ( 108.50 ms per token, 9.22 tokens per second) 14.34.699.786 I slot print_timing: id 0 | task 4561 | total time = 10366.63 ms / 501 tokens 14.34.699.788 I slot print_timing: id 0 | task 4561 | graphs reused = 4211 14.34.699.790 I slot print_timing: id 0 | task 4561 | graph reallocs = 0 / 0 (same size) / (changed size) 14.34.700.033 I slot release: id 0 | task 4561 | stop processing: n_tokens = 532, truncated = 0 14.34.712.989 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 532, t_last = 91591997677 14.34.713.085 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 789.396 MiB) 14.34.909.135 I slot launch_slot_: id 0 | task 4608 | processing task, is_child = 0 14.39.659.152 I slot print_timing: id 0 | task 4608 | prompt processing, n_tokens = 435, progress = 0.99, t = 4.75 s / 91.58 tokens per second 14.44.579.886 I slot print_timing: id 0 | task 4608 | prompt eval time = 5360.32 ms / 439 tokens ( 12.21 ms per token, 81.90 tokens per second) 14.44.579.891 I slot print_timing: id 0 | task 4608 | eval time = 4310.42 ms / 42 tokens ( 105.13 ms per token, 9.51 tokens per second) 14.44.579.892 I slot print_timing: id 0 | task 4608 | total time = 9670.74 ms / 481 tokens 14.44.579.892 I slot print_timing: id 0 | task 4608 | graphs reused = 4251 14.44.579.893 I slot print_timing: id 0 | task 4608 | graph reallocs = 0 / 0 (same size) / (changed size) 14.44.579.939 I slot release: id 0 | task 4608 | stop processing: n_tokens = 512, truncated = 0 14.44.584.572 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 512, t_last = 91601877582 14.44.584.602 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 785.082 MiB) 14.44.691.069 I slot launch_slot_: id 0 | task 4653 | processing task, is_child = 0 14.51.330.025 I slot print_timing: id 0 | task 4653 | prompt processing, n_tokens = 602, progress = 0.99, t = 6.64 s / 90.68 tokens per second 14.58.063.348 I slot print_timing: id 0 | task 4653 | prompt eval time = 7585.25 ms / 606 tokens ( 12.52 ms per token, 79.89 tokens per second) 14.58.063.351 I slot print_timing: id 0 | task 4653 | eval time = 5787.02 ms / 56 tokens ( 105.22 ms per token, 9.50 tokens per second) 14.58.063.352 I slot print_timing: id 0 | task 4653 | total time = 13372.26 ms / 662 tokens 14.58.063.352 I slot print_timing: id 0 | task 4653 | graphs reused = 4305 14.58.063.353 I slot print_timing: id 0 | task 4653 | graph reallocs = 0 / 0 (same size) / (changed size) 14.58.063.417 I slot release: id 0 | task 4653 | stop processing: n_tokens = 693, truncated = 0 14.58.068.393 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 91615361060 14.58.068.433 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 783.144 MiB) 14.58.068.451 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 937.584 MiB) 14.58.279.411 I slot launch_slot_: id 0 | task 4713 | processing task, is_child = 0 15.03.386.961 I slot print_timing: id 0 | task 4713 | prompt processing, n_tokens = 473, progress = 0.99, t = 5.11 s / 92.61 tokens per second 15.08.536.500 I slot print_timing: id 0 | task 4713 | prompt eval time = 6047.98 ms / 477 tokens ( 12.68 ms per token, 78.87 tokens per second) 15.08.536.506 I slot print_timing: id 0 | task 4713 | eval time = 4209.09 ms / 41 tokens ( 105.23 ms per token, 9.50 tokens per second) 15.08.536.506 I slot print_timing: id 0 | task 4713 | total time = 10257.07 ms / 518 tokens 15.08.536.507 I slot print_timing: id 0 | task 4713 | graphs reused = 4343 15.08.536.507 I slot print_timing: id 0 | task 4713 | graph reallocs = 0 / 0 (same size) / (changed size) 15.08.536.563 I slot release: id 0 | task 4713 | stop processing: n_tokens = 549, truncated = 0 15.08.543.580 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 91625834206 15.08.543.610 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 785.457 MiB) 15.08.685.705 I slot launch_slot_: id 0 | task 4757 | processing task, is_child = 0 15.12.712.343 I slot print_timing: id 0 | task 4757 | prompt processing, n_tokens = 782, progress = 0.93, t = 4.03 s / 194.21 tokens per second 15.18.160.920 I slot print_timing: id 0 | task 4757 | prompt processing, n_tokens = 841, progress = 1.00, t = 9.48 s / 88.76 tokens per second 15.25.527.497 I slot print_timing: id 0 | task 4757 | prompt eval time = 10447.83 ms / 845 tokens ( 12.36 ms per token, 80.88 tokens per second) 15.25.527.514 I slot print_timing: id 0 | task 4757 | eval time = 6393.93 ms / 60 tokens ( 108.37 ms per token, 9.23 tokens per second) 15.25.527.517 I slot print_timing: id 0 | task 4757 | total time = 16841.75 ms / 905 tokens 15.25.527.520 I slot print_timing: id 0 | task 4757 | graphs reused = 4401 15.25.527.522 I slot print_timing: id 0 | task 4757 | graph reallocs = 0 / 0 (same size) / (changed size) 15.25.527.982 I slot release: id 0 | task 4757 | stop processing: n_tokens = 936, truncated = 0 15.25.541.736 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 936, t_last = 91642825625 15.25.541.844 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 779.643 MiB) 15.25.792.933 I slot launch_slot_: id 0 | task 4821 | processing task, is_child = 0 15.30.882.923 I slot print_timing: id 0 | task 4821 | prompt processing, n_tokens = 455, progress = 0.99, t = 5.09 s / 89.39 tokens per second 15.36.246.856 I slot print_timing: id 0 | task 4821 | prompt eval time = 6032.45 ms / 459 tokens ( 13.14 ms per token, 76.09 tokens per second) 15.36.246.859 I slot print_timing: id 0 | task 4821 | eval time = 4421.45 ms / 43 tokens ( 105.27 ms per token, 9.50 tokens per second) 15.36.246.860 I slot print_timing: id 0 | task 4821 | total time = 10453.90 ms / 502 tokens 15.36.246.860 I slot print_timing: id 0 | task 4821 | graphs reused = 4441 15.36.246.861 I slot print_timing: id 0 | task 4821 | graph reallocs = 0 / 0 (same size) / (changed size) 15.36.246.924 I slot release: id 0 | task 4821 | stop processing: n_tokens = 533, truncated = 0 15.36.253.979 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 533, t_last = 91653544567 15.36.254.018 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 935.834 MiB) 15.36.346.610 I slot launch_slot_: id 0 | task 4867 | processing task, is_child = 0 15.43.693.485 I slot print_timing: id 0 | task 4867 | prompt processing, n_tokens = 666, progress = 0.99, t = 7.35 s / 90.65 tokens per second 15.49.767.565 I slot print_timing: id 0 | task 4867 | prompt eval time = 8292.04 ms / 670 tokens ( 12.38 ms per token, 80.80 tokens per second) 15.49.767.585 I slot print_timing: id 0 | task 4867 | eval time = 5128.88 ms / 47 tokens ( 111.50 ms per token, 8.97 tokens per second) 15.49.767.588 I slot print_timing: id 0 | task 4867 | total time = 13420.92 ms / 717 tokens 15.49.767.590 I slot print_timing: id 0 | task 4867 | graphs reused = 4486 15.49.767.598 I slot print_timing: id 0 | task 4867 | graph reallocs = 0 / 0 (same size) / (changed size) 15.49.767.913 I slot release: id 0 | task 4867 | stop processing: n_tokens = 748, truncated = 0 15.49.783.518 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 748, t_last = 91667065556 15.49.783.613 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 931.645 MiB) 15.50.025.116 I slot launch_slot_: id 0 | task 4918 | processing task, is_child = 0 15.53.331.752 I slot print_timing: id 0 | task 4918 | prompt processing, n_tokens = 731, progress = 0.95, t = 3.31 s / 221.07 tokens per second 15.58.794.851 I slot print_timing: id 0 | task 4918 | prompt processing, n_tokens = 771, progress = 1.00, t = 8.77 s / 87.92 tokens per second 16.06.584.955 I slot print_timing: id 0 | task 4918 | prompt eval time = 9717.53 ms / 775 tokens ( 12.54 ms per token, 79.75 tokens per second) 16.06.584.961 I slot print_timing: id 0 | task 4918 | eval time = 6842.29 ms / 63 tokens ( 110.36 ms per token, 9.06 tokens per second) 16.06.584.961 I slot print_timing: id 0 | task 4918 | total time = 16559.82 ms / 838 tokens 16.06.584.962 I slot print_timing: id 0 | task 4918 | graphs reused = 4547 16.06.584.962 I slot print_timing: id 0 | task 4918 | graph reallocs = 0 / 0 (same size) / (changed size) 16.06.585.067 I slot release: id 0 | task 4918 | stop processing: n_tokens = 869, truncated = 0 16.06.590.596 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 869, t_last = 91683882711 16.06.590.641 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 929.206 MiB) 16.06.842.076 I slot launch_slot_: id 0 | task 4985 | processing task, is_child = 0 16.13.127.442 I slot print_timing: id 0 | task 4985 | prompt processing, n_tokens = 569, progress = 0.99, t = 6.29 s / 90.53 tokens per second 16.21.436.567 I slot print_timing: id 0 | task 4985 | prompt eval time = 7232.82 ms / 573 tokens ( 12.62 ms per token, 79.22 tokens per second) 16.21.436.569 I slot print_timing: id 0 | task 4985 | eval time = 7361.66 ms / 71 tokens ( 105.17 ms per token, 9.51 tokens per second) 16.21.436.570 I slot print_timing: id 0 | task 4985 | total time = 14594.48 ms / 644 tokens 16.21.436.570 I slot print_timing: id 0 | task 4985 | graphs reused = 4616 16.21.436.571 I slot print_timing: id 0 | task 4985 | graph reallocs = 0 / 0 (same size) / (changed size) 16.21.436.671 I slot release: id 0 | task 4985 | stop processing: n_tokens = 675, truncated = 0 16.21.441.959 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 675, t_last = 91698734315 16.21.441.997 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 931.019 MiB) 16.21.442.018 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 929.769 MiB) 16.21.602.467 I slot launch_slot_: id 0 | task 5060 | processing task, is_child = 0 16.26.685.231 I slot print_timing: id 0 | task 5060 | prompt processing, n_tokens = 457, progress = 0.99, t = 5.08 s / 89.91 tokens per second 16.34.599.212 I slot print_timing: id 0 | task 5060 | prompt eval time = 6026.91 ms / 461 tokens ( 13.07 ms per token, 76.49 tokens per second) 16.34.599.232 I slot print_timing: id 0 | task 5060 | eval time = 6969.80 ms / 64 tokens ( 110.63 ms per token, 9.04 tokens per second) 16.34.599.235 I slot print_timing: id 0 | task 5060 | total time = 12996.70 ms / 525 tokens 16.34.599.246 I slot print_timing: id 0 | task 5060 | graphs reused = 4677 16.34.599.248 I slot print_timing: id 0 | task 5060 | graph reallocs = 0 / 0 (same size) / (changed size) 16.34.599.482 I slot release: id 0 | task 5060 | stop processing: n_tokens = 556, truncated = 0 16.34.615.718 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 556, t_last = 91711897125 16.34.615.796 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1090.712 MiB) 16.34.830.227 I slot launch_slot_: id 0 | task 5127 | processing task, is_child = 0 16.41.817.475 I slot print_timing: id 0 | task 5127 | prompt processing, n_tokens = 605, progress = 0.99, t = 6.99 s / 86.59 tokens per second 16.52.860.071 I slot print_timing: id 0 | task 5127 | n_gen = 100, tg = 9.49 t/s, tg_3s = 9.59 t/s 16.55.926.905 I slot print_timing: id 0 | task 5127 | n_gen = 129, tg = 9.48 t/s, tg_3s = 9.46 t/s 16.58.980.456 I slot print_timing: id 0 | task 5127 | n_gen = 158, tg = 9.49 t/s, tg_3s = 9.50 t/s 17.02.036.823 I slot print_timing: id 0 | task 5127 | n_gen = 187, tg = 9.49 t/s, tg_3s = 9.49 t/s 17.05.105.494 I slot print_timing: id 0 | task 5127 | n_gen = 216, tg = 9.48 t/s, tg_3s = 9.45 t/s 17.05.421.441 I slot print_timing: id 0 | task 5127 | prompt eval time = 7601.33 ms / 609 tokens ( 12.48 ms per token, 80.12 tokens per second) 17.05.421.444 I slot print_timing: id 0 | task 5127 | eval time = 22989.87 ms / 219 tokens ( 105.46 ms per token, 9.48 tokens per second) 17.05.421.444 I slot print_timing: id 0 | task 5127 | total time = 30591.20 ms / 828 tokens 17.05.421.445 I slot print_timing: id 0 | task 5127 | graphs reused = 4893 17.05.421.445 I slot print_timing: id 0 | task 5127 | graph reallocs = 0 / 0 (same size) / (changed size) 17.05.421.508 I slot release: id 0 | task 5127 | stop processing: n_tokens = 859, truncated = 0 17.05.427.672 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 859, t_last = 91742719151 17.05.427.721 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 932.082 MiB) 17.05.616.654 I slot launch_slot_: id 0 | task 5350 | processing task, is_child = 0 17.08.960.468 I slot print_timing: id 0 | task 5350 | prompt processing, n_tokens = 758, progress = 0.96, t = 3.34 s / 226.69 tokens per second 17.14.765.456 I slot print_timing: id 0 | task 5350 | prompt processing, n_tokens = 787, progress = 1.00, t = 9.15 s / 86.02 tokens per second 17.22.110.480 I slot print_timing: id 0 | task 5350 | prompt eval time = 9767.02 ms / 791 tokens ( 12.35 ms per token, 80.99 tokens per second) 17.22.110.484 I slot print_timing: id 0 | task 5350 | eval time = 6726.77 ms / 61 tokens ( 112.11 ms per token, 8.92 tokens per second) 17.22.110.485 I slot print_timing: id 0 | task 5350 | total time = 16493.80 ms / 852 tokens 17.22.110.486 I slot print_timing: id 0 | task 5350 | graphs reused = 4952 17.22.110.529 I slot print_timing: id 0 | task 5350 | graph reallocs = 0 / 0 (same size) / (changed size) 17.22.110.639 I slot release: id 0 | task 5350 | stop processing: n_tokens = 883, truncated = 0 17.22.124.008 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 883, t_last = 91759408282 17.22.124.117 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1105.905 MiB) 17.22.334.332 I slot launch_slot_: id 0 | task 5415 | processing task, is_child = 0 17.28.602.922 I slot print_timing: id 0 | task 5415 | prompt processing, n_tokens = 529, progress = 0.99, t = 6.27 s / 84.39 tokens per second 17.35.320.055 I slot print_timing: id 0 | task 5415 | prompt eval time = 6883.27 ms / 533 tokens ( 12.91 ms per token, 77.43 tokens per second) 17.35.320.065 I slot print_timing: id 0 | task 5415 | eval time = 6102.43 ms / 56 tokens ( 110.95 ms per token, 9.01 tokens per second) 17.35.320.067 I slot print_timing: id 0 | task 5415 | total time = 12985.69 ms / 589 tokens 17.35.320.069 I slot print_timing: id 0 | task 5415 | graphs reused = 5006 17.35.320.071 I slot print_timing: id 0 | task 5415 | graph reallocs = 0 / 0 (same size) / (changed size) 17.35.320.385 I slot release: id 0 | task 5415 | stop processing: n_tokens = 677, truncated = 0 17.35.334.604 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 677, t_last = 91772618029 17.35.516.757 I slot launch_slot_: id 0 | task 5475 | processing task, is_child = 0 17.41.771.058 I slot print_timing: id 0 | task 5475 | prompt processing, n_tokens = 562, progress = 0.99, t = 6.25 s / 89.86 tokens per second 17.47.460.547 I slot print_timing: id 0 | task 5475 | prompt eval time = 7196.16 ms / 566 tokens ( 12.71 ms per token, 78.65 tokens per second) 17.47.460.552 I slot print_timing: id 0 | task 5475 | eval time = 4747.62 ms / 46 tokens ( 105.50 ms per token, 9.48 tokens per second) 17.47.460.552 I slot print_timing: id 0 | task 5475 | total time = 11943.78 ms / 612 tokens 17.47.460.553 I slot print_timing: id 0 | task 5475 | graphs reused = 5050 17.47.460.553 I slot print_timing: id 0 | task 5475 | graph reallocs = 0 / 0 (same size) / (changed size) 17.47.460.612 I slot release: id 0 | task 5475 | stop processing: n_tokens = 643, truncated = 0 17.47.464.914 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 643, t_last = 91784758255 17.47.464.948 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 931.082 MiB) 17.47.589.906 I slot launch_slot_: id 0 | task 5525 | processing task, is_child = 0 17.52.679.358 I slot print_timing: id 0 | task 5525 | prompt processing, n_tokens = 439, progress = 0.99, t = 5.09 s / 86.26 tokens per second 17.57.709.053 I slot print_timing: id 0 | task 5525 | prompt eval time = 5698.35 ms / 443 tokens ( 12.86 ms per token, 77.74 tokens per second) 17.57.709.058 I slot print_timing: id 0 | task 5525 | eval time = 4420.79 ms / 43 tokens ( 105.26 ms per token, 9.50 tokens per second) 17.57.709.059 I slot print_timing: id 0 | task 5525 | total time = 10119.13 ms / 486 tokens 17.57.709.059 I slot print_timing: id 0 | task 5525 | graphs reused = 5090 17.57.709.060 I slot print_timing: id 0 | task 5525 | graph reallocs = 0 / 0 (same size) / (changed size) 17.57.709.102 I slot release: id 0 | task 5525 | stop processing: n_tokens = 517, truncated = 0 17.57.713.643 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 517, t_last = 91795006745 17.57.713.673 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1094.150 MiB) 17.57.846.853 I slot launch_slot_: id 0 | task 5571 | processing task, is_child = 0 18.02.959.243 I slot print_timing: id 0 | task 5571 | prompt processing, n_tokens = 483, progress = 0.99, t = 5.11 s / 94.48 tokens per second 18.10.639.395 I slot print_timing: id 0 | task 5571 | prompt eval time = 6057.84 ms / 487 tokens ( 12.44 ms per token, 80.39 tokens per second) 18.10.639.398 I slot print_timing: id 0 | task 5571 | eval time = 6734.68 ms / 65 tokens ( 105.23 ms per token, 9.50 tokens per second) 18.10.639.398 I slot print_timing: id 0 | task 5571 | total time = 12792.53 ms / 552 tokens 18.10.639.399 I slot print_timing: id 0 | task 5571 | graphs reused = 5153 18.10.639.399 I slot print_timing: id 0 | task 5571 | graph reallocs = 0 / 0 (same size) / (changed size) 18.10.639.451 I slot release: id 0 | task 5571 | stop processing: n_tokens = 583, truncated = 0 18.10.644.261 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 583, t_last = 91807937094 18.10.644.293 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1101.716 MiB) 18.10.775.574 I slot launch_slot_: id 0 | task 5639 | processing task, is_child = 0 18.16.251.719 I slot print_timing: id 0 | task 5639 | prompt processing, n_tokens = 503, progress = 0.99, t = 5.48 s / 91.85 tokens per second 18.21.703.475 I slot print_timing: id 0 | task 5639 | prompt eval time = 6091.09 ms / 507 tokens ( 12.01 ms per token, 83.24 tokens per second) 18.21.703.480 I slot print_timing: id 0 | task 5639 | eval time = 4836.80 ms / 47 tokens ( 105.15 ms per token, 9.51 tokens per second) 18.21.703.480 I slot print_timing: id 0 | task 5639 | total time = 10927.88 ms / 554 tokens 18.21.703.481 I slot print_timing: id 0 | task 5639 | graphs reused = 5198 18.21.703.481 I slot print_timing: id 0 | task 5639 | graph reallocs = 0 / 0 (same size) / (changed size) 18.21.703.541 I slot release: id 0 | task 5639 | stop processing: n_tokens = 585, truncated = 0 18.21.708.245 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 585, t_last = 91819001184 18.21.708.276 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 932.520 MiB) 18.21.814.016 I slot launch_slot_: id 0 | task 5689 | processing task, is_child = 0 18.29.129.618 I slot print_timing: id 0 | task 5689 | prompt processing, n_tokens = 629, progress = 0.99, t = 7.32 s / 85.98 tokens per second 18.37.085.905 I slot print_timing: id 0 | task 5689 | prompt eval time = 7942.14 ms / 633 tokens ( 12.55 ms per token, 79.70 tokens per second) 18.37.085.917 I slot print_timing: id 0 | task 5689 | eval time = 7329.71 ms / 66 tokens ( 112.76 ms per token, 8.87 tokens per second) 18.37.085.919 I slot print_timing: id 0 | task 5689 | total time = 15271.85 ms / 699 tokens 18.37.085.922 I slot print_timing: id 0 | task 5689 | graphs reused = 5262 18.37.085.924 I slot print_timing: id 0 | task 5689 | graph reallocs = 0 / 0 (same size) / (changed size) 18.37.086.192 I slot release: id 0 | task 5689 | stop processing: n_tokens = 730, truncated = 0 18.37.099.934 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 730, t_last = 91834383836 18.37.100.047 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1101.090 MiB) 18.37.156.625 I slot launch_slot_: id 0 | task 5759 | processing task, is_child = 0 18.43.751.031 I slot print_timing: id 0 | task 5759 | prompt processing, n_tokens = 567, progress = 0.99, t = 6.59 s / 85.98 tokens per second 18.49.463.080 I slot print_timing: id 0 | task 5759 | prompt eval time = 7207.18 ms / 571 tokens ( 12.62 ms per token, 79.23 tokens per second) 18.49.463.093 I slot print_timing: id 0 | task 5759 | eval time = 5099.22 ms / 47 tokens ( 110.85 ms per token, 9.02 tokens per second) 18.49.463.096 I slot print_timing: id 0 | task 5759 | total time = 12306.40 ms / 618 tokens 18.49.463.098 I slot print_timing: id 0 | task 5759 | graphs reused = 5307 18.49.463.100 I slot print_timing: id 0 | task 5759 | graph reallocs = 0 / 0 (same size) / (changed size) 18.49.463.412 I slot release: id 0 | task 5759 | stop processing: n_tokens = 649, truncated = 0 18.49.479.063 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 649, t_last = 91846761055 18.49.479.154 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1102.591 MiB) 18.49.562.976 I slot launch_slot_: id 0 | task 5810 | processing task, is_child = 0 18.52.887.937 I slot print_timing: id 0 | task 5810 | prompt processing, n_tokens = 775, progress = 0.97, t = 3.32 s / 233.09 tokens per second 18.58.704.521 I slot print_timing: id 0 | task 5810 | prompt processing, n_tokens = 794, progress = 1.00, t = 9.14 s / 86.86 tokens per second 19.04.056.196 I slot print_timing: id 0 | task 5810 | prompt eval time = 9754.72 ms / 798 tokens ( 12.22 ms per token, 81.81 tokens per second) 19.04.056.210 I slot print_timing: id 0 | task 5810 | eval time = 4738.47 ms / 44 tokens ( 110.20 ms per token, 9.07 tokens per second) 19.04.056.219 I slot print_timing: id 0 | task 5810 | total time = 14493.18 ms / 842 tokens 19.04.056.221 I slot print_timing: id 0 | task 5810 | graphs reused = 5349 19.04.056.228 I slot print_timing: id 0 | task 5810 | graph reallocs = 0 / 0 (same size) / (changed size) 19.04.056.539 I slot release: id 0 | task 5810 | stop processing: n_tokens = 873, truncated = 0 19.04.069.957 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 873, t_last = 91861354183 19.04.070.054 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1239.337 MiB) 19.04.194.986 I slot launch_slot_: id 0 | task 5858 | processing task, is_child = 0 19.10.796.855 I slot print_timing: id 0 | task 5858 | prompt processing, n_tokens = 568, progress = 0.99, t = 6.60 s / 86.04 tokens per second 19.15.826.531 I slot print_timing: id 0 | task 5858 | prompt eval time = 7214.39 ms / 572 tokens ( 12.61 ms per token, 79.29 tokens per second) 19.15.826.534 I slot print_timing: id 0 | task 5858 | eval time = 4417.14 ms / 43 tokens ( 105.17 ms per token, 9.51 tokens per second) 19.15.826.534 I slot print_timing: id 0 | task 5858 | total time = 11631.53 ms / 615 tokens 19.15.826.535 I slot print_timing: id 0 | task 5858 | graphs reused = 5390 19.15.826.535 I slot print_timing: id 0 | task 5858 | graph reallocs = 0 / 0 (same size) / (changed size) 19.15.826.576 I slot release: id 0 | task 5858 | stop processing: n_tokens = 646, truncated = 0 19.15.831.615 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 646, t_last = 91873124219 19.15.831.648 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1087.585 MiB) 19.15.943.076 I slot launch_slot_: id 0 | task 5905 | processing task, is_child = 0 19.23.235.325 I slot print_timing: id 0 | task 5905 | prompt processing, n_tokens = 609, progress = 0.99, t = 7.29 s / 83.51 tokens per second 19.29.266.255 I slot print_timing: id 0 | task 5905 | prompt eval time = 7917.93 ms / 613 tokens ( 12.92 ms per token, 77.42 tokens per second) 19.29.266.264 I slot print_timing: id 0 | task 5905 | eval time = 5405.23 ms / 49 tokens ( 112.61 ms per token, 8.88 tokens per second) 19.29.266.266 I slot print_timing: id 0 | task 5905 | total time = 13323.16 ms / 662 tokens 19.29.266.267 I slot print_timing: id 0 | task 5905 | graphs reused = 5437 19.29.266.268 I slot print_timing: id 0 | task 5905 | graph reallocs = 0 / 0 (same size) / (changed size) 19.29.266.351 I slot release: id 0 | task 5905 | stop processing: n_tokens = 693, truncated = 0 19.29.277.464 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 91886563995 19.29.277.560 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 930.081 MiB) 19.29.486.343 I slot launch_slot_: id 0 | task 5958 | processing task, is_child = 0 19.36.090.787 I slot print_timing: id 0 | task 5958 | prompt processing, n_tokens = 576, progress = 0.99, t = 6.60 s / 87.21 tokens per second 19.43.641.262 I slot print_timing: id 0 | task 5958 | prompt eval time = 7215.52 ms / 580 tokens ( 12.44 ms per token, 80.38 tokens per second) 19.43.641.278 I slot print_timing: id 0 | task 5958 | eval time = 6939.36 ms / 64 tokens ( 110.15 ms per token, 9.08 tokens per second) 19.43.641.285 I slot print_timing: id 0 | task 5958 | total time = 14154.88 ms / 644 tokens 19.43.641.294 I slot print_timing: id 0 | task 5958 | graphs reused = 5499 19.43.641.296 I slot print_timing: id 0 | task 5958 | graph reallocs = 0 / 0 (same size) / (changed size) 19.43.641.615 I slot release: id 0 | task 5958 | stop processing: n_tokens = 675, truncated = 0 19.43.659.762 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 675, t_last = 91900939258 19.43.659.845 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 934.208 MiB) 19.43.858.165 I slot launch_slot_: id 0 | task 6026 | processing task, is_child = 0 19.52.264.221 I slot print_timing: id 0 | task 6026 | prompt processing, n_tokens = 712, progress = 0.99, t = 8.41 s / 84.70 tokens per second 19.58.358.466 I slot print_timing: id 0 | task 6026 | prompt eval time = 9017.57 ms / 716 tokens ( 12.59 ms per token, 79.40 tokens per second) 19.58.358.479 I slot print_timing: id 0 | task 6026 | eval time = 5482.70 ms / 50 tokens ( 111.89 ms per token, 8.94 tokens per second) 19.58.358.482 I slot print_timing: id 0 | task 6026 | total time = 14500.27 ms / 766 tokens 19.58.358.484 I slot print_timing: id 0 | task 6026 | graphs reused = 5546 19.58.358.486 I slot print_timing: id 0 | task 6026 | graph reallocs = 0 / 0 (same size) / (changed size) 19.58.358.877 I slot release: id 0 | task 6026 | stop processing: n_tokens = 797, truncated = 0 19.58.374.012 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 797, t_last = 91915656521 19.58.374.125 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 934.333 MiB) 19.58.567.747 I slot launch_slot_: id 0 | task 6080 | processing task, is_child = 0 20.01.889.214 I slot print_timing: id 0 | task 6080 | prompt processing, n_tokens = 755, progress = 0.95, t = 3.32 s / 227.31 tokens per second 20.07.356.356 I slot print_timing: id 0 | task 6080 | prompt processing, n_tokens = 795, progress = 1.00, t = 8.79 s / 90.46 tokens per second 20.19.176.091 I slot print_timing: id 0 | task 6080 | n_gen = 100, tg = 9.11 t/s, tg_3s = 9.20 t/s 20.19.402.419 I slot print_timing: id 0 | task 6080 | prompt eval time = 9737.18 ms / 799 tokens ( 12.19 ms per token, 82.06 tokens per second) 20.19.402.430 I slot print_timing: id 0 | task 6080 | eval time = 11097.38 ms / 102 tokens ( 109.88 ms per token, 9.10 tokens per second) 20.19.402.433 I slot print_timing: id 0 | task 6080 | total time = 20834.57 ms / 901 tokens 20.19.402.435 I slot print_timing: id 0 | task 6080 | graphs reused = 5646 20.19.402.437 I slot print_timing: id 0 | task 6080 | graph reallocs = 0 / 0 (same size) / (changed size) 20.19.402.859 I slot release: id 0 | task 6080 | stop processing: n_tokens = 932, truncated = 0 20.19.415.591 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 932, t_last = 91936700502 20.19.415.692 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1093.025 MiB) 20.19.656.399 I slot launch_slot_: id 0 | task 6186 | processing task, is_child = 0 20.23.336.011 I slot print_timing: id 0 | task 6186 | prompt processing, n_tokens = 357, progress = 0.99, t = 3.68 s / 97.02 tokens per second 20.34.686.010 I slot print_timing: id 0 | task 6186 | n_gen = 100, tg = 9.51 t/s, tg_3s = 9.61 t/s 20.35.947.310 I slot print_timing: id 0 | task 6186 | prompt eval time = 4624.29 ms / 361 tokens ( 12.81 ms per token, 78.07 tokens per second) 20.35.947.315 I slot print_timing: id 0 | task 6186 | eval time = 11666.61 ms / 112 tokens ( 105.10 ms per token, 9.51 tokens per second) 20.35.947.316 I slot print_timing: id 0 | task 6186 | total time = 16290.90 ms / 473 tokens 20.35.947.316 I slot print_timing: id 0 | task 6186 | graphs reused = 5756 20.35.947.317 I slot print_timing: id 0 | task 6186 | graph reallocs = 0 / 0 (same size) / (changed size) 20.35.947.361 I slot release: id 0 | task 6186 | stop processing: n_tokens = 504, truncated = 0 20.35.951.799 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 91953245004 20.35.951.829 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1087.961 MiB) 20.36.166.038 I slot launch_slot_: id 0 | task 6301 | processing task, is_child = 0 20.40.199.860 I slot print_timing: id 0 | task 6301 | prompt processing, n_tokens = 377, progress = 0.99, t = 4.03 s / 93.46 tokens per second 20.51.784.283 I slot print_timing: id 0 | task 6301 | n_gen = 100, tg = 9.32 t/s, tg_3s = 9.42 t/s 20.52.629.132 I slot print_timing: id 0 | task 6301 | prompt eval time = 4999.50 ms / 381 tokens ( 13.12 ms per token, 76.21 tokens per second) 20.52.629.134 I slot print_timing: id 0 | task 6301 | eval time = 11463.58 ms / 108 tokens ( 107.14 ms per token, 9.33 tokens per second) 20.52.629.134 I slot print_timing: id 0 | task 6301 | total time = 16463.08 ms / 489 tokens 20.52.629.135 I slot print_timing: id 0 | task 6301 | graphs reused = 5861 20.52.629.135 I slot print_timing: id 0 | task 6301 | graph reallocs = 0 / 0 (same size) / (changed size) 20.52.629.310 I slot release: id 0 | task 6301 | stop processing: n_tokens = 520, truncated = 0 20.52.639.007 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 91969926953 20.52.639.047 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1101.966 MiB) 20.52.804.895 I slot launch_slot_: id 0 | task 6412 | processing task, is_child = 0 20.56.451.256 I slot print_timing: id 0 | task 6412 | prompt processing, n_tokens = 361, progress = 0.99, t = 3.65 s / 99.00 tokens per second 21.07.820.084 I slot print_timing: id 0 | task 6412 | n_gen = 100, tg = 9.50 t/s, tg_3s = 9.60 t/s 21.10.347.222 I slot print_timing: id 0 | task 6412 | prompt eval time = 4594.19 ms / 365 tokens ( 12.59 ms per token, 79.45 tokens per second) 21.10.347.227 I slot print_timing: id 0 | task 6412 | eval time = 12948.12 ms / 124 tokens ( 105.27 ms per token, 9.50 tokens per second) 21.10.347.228 I slot print_timing: id 0 | task 6412 | total time = 17542.31 ms / 489 tokens 21.10.347.228 I slot print_timing: id 0 | task 6412 | graphs reused = 5982 21.10.347.229 I slot print_timing: id 0 | task 6412 | graph reallocs = 0 / 0 (same size) / (changed size) 21.10.347.290 I slot release: id 0 | task 6412 | stop processing: n_tokens = 520, truncated = 0 21.10.352.102 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 91987644933 21.10.352.132 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1087.773 MiB) 21.10.483.405 I slot launch_slot_: id 0 | task 6539 | processing task, is_child = 0 21.14.127.130 I slot print_timing: id 0 | task 6539 | prompt processing, n_tokens = 329, progress = 0.99, t = 3.64 s / 90.29 tokens per second 21.25.494.471 I slot print_timing: id 0 | task 6539 | n_gen = 100, tg = 9.50 t/s, tg_3s = 9.59 t/s 21.26.231.116 I slot print_timing: id 0 | task 6539 | prompt eval time = 4586.20 ms / 333 tokens ( 13.77 ms per token, 72.61 tokens per second) 21.26.231.121 I slot print_timing: id 0 | task 6539 | eval time = 11161.50 ms / 107 tokens ( 105.30 ms per token, 9.50 tokens per second) 21.26.231.122 I slot print_timing: id 0 | task 6539 | total time = 15747.70 ms / 440 tokens 21.26.231.122 I slot print_timing: id 0 | task 6539 | graphs reused = 6087 21.26.231.123 I slot print_timing: id 0 | task 6539 | graph reallocs = 0 / 0 (same size) / (changed size) 21.26.231.175 I slot release: id 0 | task 6539 | stop processing: n_tokens = 471, truncated = 0 21.26.237.142 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 471, t_last = 92003528818 21.26.316.329 I slot launch_slot_: id 0 | task 6649 | processing task, is_child = 0 21.30.676.571 I slot print_timing: id 0 | task 6649 | prompt processing, n_tokens = 399, progress = 0.99, t = 4.36 s / 91.51 tokens per second 21.42.045.824 I slot print_timing: id 0 | task 6649 | n_gen = 100, tg = 9.49 t/s, tg_3s = 9.59 t/s 21.45.096.945 I slot print_timing: id 0 | task 6649 | n_gen = 129, tg = 9.50 t/s, tg_3s = 9.50 t/s 21.48.146.262 I slot print_timing: id 0 | task 6649 | n_gen = 158, tg = 9.50 t/s, tg_3s = 9.51 t/s 21.50.250.004 I slot print_timing: id 0 | task 6649 | prompt eval time = 5302.38 ms / 403 tokens ( 13.16 ms per token, 76.00 tokens per second) 21.50.250.006 I slot print_timing: id 0 | task 6649 | eval time = 18631.28 ms / 178 tokens ( 105.26 ms per token, 9.50 tokens per second) 21.50.250.007 I slot print_timing: id 0 | task 6649 | total time = 23933.66 ms / 581 tokens 21.50.250.007 I slot print_timing: id 0 | task 6649 | graphs reused = 6262 21.50.250.008 I slot print_timing: id 0 | task 6649 | graph reallocs = 0 / 0 (same size) / (changed size) 21.50.250.052 I slot release: id 0 | task 6649 | stop processing: n_tokens = 612, truncated = 0 21.50.255.379 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 612, t_last = 92027547695 21.50.255.422 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1090.712 MiB) 21.50.390.454 I slot launch_slot_: id 0 | task 6830 | processing task, is_child = 0 21.54.416.060 I slot print_timing: id 0 | task 6830 | prompt processing, n_tokens = 407, progress = 0.99, t = 4.03 s / 101.10 tokens per second 22.06.158.973 I slot print_timing: id 0 | task 6830 | n_gen = 100, tg = 9.50 t/s, tg_3s = 9.60 t/s 22.09.210.452 I slot print_timing: id 0 | task 6830 | n_gen = 129, tg = 9.50 t/s, tg_3s = 9.50 t/s 22.12.260.100 I slot print_timing: id 0 | task 6830 | n_gen = 158, tg = 9.50 t/s, tg_3s = 9.51 t/s 22.15.101.322 I slot print_timing: id 0 | task 6830 | prompt eval time = 5351.77 ms / 411 tokens ( 13.02 ms per token, 76.80 tokens per second) 22.15.101.325 I slot print_timing: id 0 | task 6830 | eval time = 19359.07 ms / 185 tokens ( 105.21 ms per token, 9.50 tokens per second) 22.15.101.325 I slot print_timing: id 0 | task 6830 | total time = 24710.85 ms / 596 tokens 22.15.101.326 I slot print_timing: id 0 | task 6830 | graphs reused = 6444 22.15.101.326 I slot print_timing: id 0 | task 6830 | graph reallocs = 0 / 0 (same size) / (changed size) 22.15.101.375 I slot release: id 0 | task 6830 | stop processing: n_tokens = 627, truncated = 0 22.15.106.847 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 627, t_last = 92052399018 22.15.106.882 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1089.586 MiB) 22.15.271.980 I slot launch_slot_: id 0 | task 7018 | processing task, is_child = 0 22.20.005.199 I slot print_timing: id 0 | task 7018 | prompt processing, n_tokens = 486, progress = 0.99, t = 4.73 s / 102.68 tokens per second 22.32.076.013 I slot print_timing: id 0 | task 7018 | n_gen = 100, tg = 9.50 t/s, tg_3s = 9.60 t/s 22.35.127.593 I slot print_timing: id 0 | task 7018 | n_gen = 129, tg = 9.50 t/s, tg_3s = 9.50 t/s 22.38.183.249 I slot print_timing: id 0 | task 7018 | n_gen = 158, tg = 9.50 t/s, tg_3s = 9.49 t/s 22.41.238.365 I slot print_timing: id 0 | task 7018 | n_gen = 187, tg = 9.50 t/s, tg_3s = 9.49 t/s 22.44.292.899 I slot print_timing: id 0 | task 7018 | n_gen = 216, tg = 9.50 t/s, tg_3s = 9.49 t/s 22.45.240.679 I slot print_timing: id 0 | task 7018 | prompt eval time = 6386.35 ms / 490 tokens ( 13.03 ms per token, 76.73 tokens per second) 22.45.240.685 I slot print_timing: id 0 | task 7018 | eval time = 23582.34 ms / 225 tokens ( 105.28 ms per token, 9.50 tokens per second) 22.45.240.685 I slot print_timing: id 0 | task 7018 | total time = 29968.69 ms / 715 tokens 22.45.240.686 I slot print_timing: id 0 | task 7018 | graphs reused = 6667 22.45.240.686 I slot print_timing: id 0 | task 7018 | graph reallocs = 0 / 0 (same size) / (changed size) 22.45.240.740 I slot release: id 0 | task 7018 | stop processing: n_tokens = 746, truncated = 0 22.45.245.129 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 746, t_last = 92082538383 22.45.245.168 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1097.214 MiB) 22.45.377.844 I slot launch_slot_: id 0 | task 7246 | processing task, is_child = 0 22.48.694.105 I slot print_timing: id 0 | task 7246 | prompt processing, n_tokens = 340, progress = 0.99, t = 3.32 s / 102.53 tokens per second 23.00.421.383 I slot print_timing: id 0 | task 7246 | n_gen = 100, tg = 9.51 t/s, tg_3s = 9.61 t/s 23.03.471.352 I slot print_timing: id 0 | task 7246 | n_gen = 129, tg = 9.51 t/s, tg_3s = 9.51 t/s 23.06.524.765 I slot print_timing: id 0 | task 7246 | n_gen = 158, tg = 9.51 t/s, tg_3s = 9.50 t/s 23.07.892.297 I slot print_timing: id 0 | task 7246 | prompt eval time = 4632.47 ms / 344 tokens ( 13.47 ms per token, 74.26 tokens per second) 23.07.892.304 I slot print_timing: id 0 | task 7246 | eval time = 17881.97 ms / 171 tokens ( 105.19 ms per token, 9.51 tokens per second) 23.07.892.304 I slot print_timing: id 0 | task 7246 | total time = 22514.44 ms / 515 tokens 23.07.892.305 I slot print_timing: id 0 | task 7246 | graphs reused = 6835 23.07.892.305 I slot print_timing: id 0 | task 7246 | graph reallocs = 0 / 0 (same size) / (changed size) 23.07.892.344 I slot release: id 0 | task 7246 | stop processing: n_tokens = 546, truncated = 0 23.07.896.582 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 546, t_last = 92105189987 23.07.896.616 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1105.655 MiB) 23.08.057.293 I slot launch_slot_: id 0 | task 7420 | processing task, is_child = 0 23.11.370.445 I slot print_timing: id 0 | task 7420 | prompt processing, n_tokens = 343, progress = 0.99, t = 3.31 s / 103.53 tokens per second 23.23.105.733 I slot print_timing: id 0 | task 7420 | n_gen = 100, tg = 9.51 t/s, tg_3s = 9.60 t/s 23.26.155.048 I slot print_timing: id 0 | task 7420 | n_gen = 129, tg = 9.51 t/s, tg_3s = 9.51 t/s 23.29.207.905 I slot print_timing: id 0 | task 7420 | n_gen = 158, tg = 9.51 t/s, tg_3s = 9.50 t/s 23.30.575.108 I slot print_timing: id 0 | task 7420 | prompt eval time = 4636.57 ms / 347 tokens ( 13.36 ms per token, 74.84 tokens per second) 23.30.575.110 I slot print_timing: id 0 | task 7420 | eval time = 17881.23 ms / 171 tokens ( 105.18 ms per token, 9.51 tokens per second) 23.30.575.111 I slot print_timing: id 0 | task 7420 | total time = 22517.80 ms / 518 tokens 23.30.575.111 I slot print_timing: id 0 | task 7420 | graphs reused = 7003 23.30.575.112 I slot print_timing: id 0 | task 7420 | graph reallocs = 0 / 0 (same size) / (changed size) 23.30.575.136 I slot release: id 0 | task 7420 | stop processing: n_tokens = 549, truncated = 0 23.30.580.394 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 92127872779 23.30.580.431 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 929.269 MiB) 23.30.737.258 I slot launch_slot_: id 0 | task 7594 | processing task, is_child = 0 23.34.397.317 I slot print_timing: id 0 | task 7594 | prompt processing, n_tokens = 397, progress = 0.99, t = 3.66 s / 108.47 tokens per second 23.46.152.539 I slot print_timing: id 0 | task 7594 | n_gen = 100, tg = 9.50 t/s, tg_3s = 9.60 t/s 23.48.887.020 I slot print_timing: id 0 | task 7594 | prompt eval time = 4999.62 ms / 401 tokens ( 12.47 ms per token, 80.21 tokens per second) 23.48.887.025 I slot print_timing: id 0 | task 7594 | eval time = 13150.13 ms / 126 tokens ( 105.20 ms per token, 9.51 tokens per second) 23.48.887.026 I slot print_timing: id 0 | task 7594 | total time = 18149.75 ms / 527 tokens 23.48.887.026 I slot print_timing: id 0 | task 7594 | graphs reused = 7126 23.48.887.027 I slot print_timing: id 0 | task 7594 | graph reallocs = 0 / 0 (same size) / (changed size) 23.48.887.069 I slot release: id 0 | task 7594 | stop processing: n_tokens = 558, truncated = 0 23.48.892.709 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 92146184712 23.48.892.757 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 930.269 MiB) 23.48.920.183 I slot launch_slot_: id 0 | task 7723 | processing task, is_child = 0 23.52.949.905 I slot print_timing: id 0 | task 7723 | prompt processing, n_tokens = 452, progress = 0.99, t = 4.03 s / 112.17 tokens per second 24.05.060.425 I slot print_timing: id 0 | task 7723 | n_gen = 100, tg = 9.47 t/s, tg_3s = 9.57 t/s 24.06.638.857 I slot print_timing: id 0 | task 7723 | prompt eval time = 5689.47 ms / 456 tokens ( 12.48 ms per token, 80.15 tokens per second) 24.06.638.861 I slot print_timing: id 0 | task 7723 | eval time = 12029.19 ms / 115 tokens ( 105.52 ms per token, 9.48 tokens per second) 24.06.638.862 I slot print_timing: id 0 | task 7723 | total time = 17718.66 ms / 571 tokens 24.06.638.862 I slot print_timing: id 0 | task 7723 | graphs reused = 7238 24.06.638.862 I slot print_timing: id 0 | task 7723 | graph reallocs = 0 / 0 (same size) / (changed size) 24.06.638.900 I slot release: id 0 | task 7723 | stop processing: n_tokens = 602, truncated = 0 24.06.643.733 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.107 (> 0.100 thold), f_keep = 0.078 24.06.643.763 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 930.269 MiB) 24.06.679.587 I slot launch_slot_: id 0 | task 7841 | processing task, is_child = 0 24.10.329.999 I slot print_timing: id 0 | task 7841 | prompt processing, n_tokens = 402, progress = 0.99, t = 3.65 s / 110.12 tokens per second 24.22.395.927 I slot print_timing: id 0 | task 7841 | n_gen = 100, tg = 9.50 t/s, tg_3s = 9.60 t/s 24.23.658.175 I slot print_timing: id 0 | task 7841 | prompt eval time = 5298.88 ms / 406 tokens ( 13.05 ms per token, 76.62 tokens per second) 24.23.658.178 I slot print_timing: id 0 | task 7841 | eval time = 11679.69 ms / 112 tokens ( 105.22 ms per token, 9.50 tokens per second) 24.23.658.178 I slot print_timing: id 0 | task 7841 | total time = 16978.57 ms / 518 tokens 24.23.658.179 I slot print_timing: id 0 | task 7841 | graphs reused = 7347 24.23.658.179 I slot print_timing: id 0 | task 7841 | graph reallocs = 0 / 0 (same size) / (changed size) 24.23.658.231 I slot release: id 0 | task 7841 | stop processing: n_tokens = 549, truncated = 0 24.23.662.679 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 92180955874 24.23.662.710 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 927.205 MiB) 24.23.708.352 I slot launch_slot_: id 0 | task 7956 | processing task, is_child = 0 24.27.374.546 I slot print_timing: id 0 | task 7956 | prompt processing, n_tokens = 402, progress = 0.99, t = 3.67 s / 109.65 tokens per second 24.39.131.432 I slot print_timing: id 0 | task 7956 | n_gen = 100, tg = 9.50 t/s, tg_3s = 9.60 t/s 24.42.183.307 I slot print_timing: id 0 | task 7956 | n_gen = 129, tg = 9.50 t/s, tg_3s = 9.50 t/s 24.45.228.496 I slot print_timing: id 0 | task 7956 | n_gen = 158, tg = 9.51 t/s, tg_3s = 9.52 t/s 24.47.436.480 I slot print_timing: id 0 | task 7956 | prompt eval time = 5002.86 ms / 406 tokens ( 12.32 ms per token, 81.15 tokens per second) 24.47.436.486 I slot print_timing: id 0 | task 7956 | eval time = 18725.26 ms / 179 tokens ( 105.20 ms per token, 9.51 tokens per second) 24.47.436.486 I slot print_timing: id 0 | task 7956 | total time = 23728.12 ms / 585 tokens 24.47.436.487 I slot print_timing: id 0 | task 7956 | graphs reused = 7523 24.47.436.487 I slot print_timing: id 0 | task 7956 | graph reallocs = 0 / 0 (same size) / (changed size) 24.47.436.516 I slot release: id 0 | task 7956 | stop processing: n_tokens = 616, truncated = 0 24.47.441.785 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 616, t_last = 92204734159 24.47.441.825 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 936.021 MiB) 24.47.474.026 I slot launch_slot_: id 0 | task 8138 | processing task, is_child = 0 24.51.492.397 I slot print_timing: id 0 | task 8138 | prompt processing, n_tokens = 440, progress = 0.99, t = 4.02 s / 109.50 tokens per second 25.03.574.871 I slot print_timing: id 0 | task 8138 | n_gen = 100, tg = 9.50 t/s, tg_3s = 9.60 t/s 25.06.625.273 I slot print_timing: id 0 | task 8138 | n_gen = 129, tg = 9.50 t/s, tg_3s = 9.51 t/s 25.08.203.763 I slot print_timing: id 0 | task 8138 | prompt eval time = 5681.38 ms / 444 tokens ( 12.80 ms per token, 78.15 tokens per second) 25.08.203.766 I slot print_timing: id 0 | task 8138 | eval time = 15048.35 ms / 144 tokens ( 105.23 ms per token, 9.50 tokens per second) 25.08.203.767 I slot print_timing: id 0 | task 8138 | total time = 20729.72 ms / 588 tokens 25.08.203.767 I slot print_timing: id 0 | task 8138 | graphs reused = 7664 25.08.203.767 I slot print_timing: id 0 | task 8138 | graph reallocs = 0 / 0 (same size) / (changed size) 25.08.203.818 I slot release: id 0 | task 8138 | stop processing: n_tokens = 619, truncated = 0 25.08.208.299 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 619, t_last = 92225501461 25.08.208.333 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 936.959 MiB) 25.08.252.326 I slot launch_slot_: id 0 | task 8285 | processing task, is_child = 0 25.11.903.144 I slot print_timing: id 0 | task 8285 | prompt processing, n_tokens = 368, progress = 0.99, t = 3.65 s / 100.80 tokens per second 25.23.634.127 I slot print_timing: id 0 | task 8285 | n_gen = 100, tg = 9.51 t/s, tg_3s = 9.60 t/s 25.23.949.806 I slot print_timing: id 0 | task 8285 | prompt eval time = 4967.58 ms / 372 tokens ( 13.35 ms per token, 74.89 tokens per second) 25.23.949.812 I slot print_timing: id 0 | task 8285 | eval time = 10729.89 ms / 103 tokens ( 105.20 ms per token, 9.51 tokens per second) 25.23.949.812 I slot print_timing: id 0 | task 8285 | total time = 15697.47 ms / 475 tokens 25.23.949.813 I slot print_timing: id 0 | task 8285 | graphs reused = 7765 25.23.949.813 I slot print_timing: id 0 | task 8285 | graph reallocs = 0 / 0 (same size) / (changed size) 25.23.949.843 I slot release: id 0 | task 8285 | stop processing: n_tokens = 506, truncated = 0 25.23.955.217 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 506, t_last = 92241247486 25.23.955.253 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 944.399 MiB) 25.23.993.602 I slot launch_slot_: id 0 | task 8391 | processing task, is_child = 0 25.28.008.492 I slot print_timing: id 0 | task 8391 | prompt processing, n_tokens = 450, progress = 0.99, t = 4.01 s / 112.08 tokens per second 25.40.101.477 I slot print_timing: id 0 | task 8391 | n_gen = 100, tg = 9.50 t/s, tg_3s = 9.60 t/s 25.43.150.835 I slot print_timing: id 0 | task 8391 | n_gen = 129, tg = 9.51 t/s, tg_3s = 9.51 t/s 25.46.202.178 I slot print_timing: id 0 | task 8391 | n_gen = 158, tg = 9.51 t/s, tg_3s = 9.50 t/s 25.49.253.602 I slot print_timing: id 0 | task 8391 | n_gen = 187, tg = 9.50 t/s, tg_3s = 9.50 t/s 25.52.305.987 I slot print_timing: id 0 | task 8391 | n_gen = 216, tg = 9.50 t/s, tg_3s = 9.50 t/s 25.53.780.584 I slot print_timing: id 0 | task 8391 | prompt eval time = 5691.31 ms / 454 tokens ( 12.54 ms per token, 79.77 tokens per second) 25.53.780.589 I slot print_timing: id 0 | task 8391 | eval time = 24095.66 ms / 230 tokens ( 105.22 ms per token, 9.50 tokens per second) 25.53.780.590 I slot print_timing: id 0 | task 8391 | total time = 29786.97 ms / 684 tokens 25.53.780.590 I slot print_timing: id 0 | task 8391 | graphs reused = 7992 25.53.780.591 I slot print_timing: id 0 | task 8391 | graph reallocs = 0 / 0 (same size) / (changed size) 25.53.780.643 I slot release: id 0 | task 8391 | stop processing: n_tokens = 715, truncated = 0 25.53.785.277 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 715, t_last = 92271078286 25.53.785.311 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 931.895 MiB) 25.53.841.051 I slot launch_slot_: id 0 | task 8624 | processing task, is_child = 0 25.57.492.633 I slot print_timing: id 0 | task 8624 | prompt processing, n_tokens = 350, progress = 0.99, t = 3.65 s / 95.85 tokens per second 26.08.863.874 I slot print_timing: id 0 | task 8624 | n_gen = 100, tg = 9.50 t/s, tg_3s = 9.60 t/s 26.11.918.279 I slot print_timing: id 0 | task 8624 | n_gen = 129, tg = 9.50 t/s, tg_3s = 9.49 t/s 26.14.968.688 I slot print_timing: id 0 | task 8624 | n_gen = 158, tg = 9.50 t/s, tg_3s = 9.51 t/s 26.17.988.518 I slot print_timing: id 0 | task 8624 | n_gen = 185, tg = 9.42 t/s, tg_3s = 8.94 t/s 26.21.091.915 I slot print_timing: id 0 | task 8624 | n_gen = 212, tg = 9.32 t/s, tg_3s = 8.70 t/s 26.24.168.776 I slot print_timing: id 0 | task 8624 | n_gen = 239, tg = 9.25 t/s, tg_3s = 8.78 t/s 26.25.080.724 I slot print_timing: id 0 | task 8624 | prompt eval time = 4604.96 ms / 354 tokens ( 13.01 ms per token, 76.87 tokens per second) 26.25.080.743 I slot print_timing: id 0 | task 8624 | eval time = 26634.68 ms / 247 tokens ( 108.27 ms per token, 9.24 tokens per second) 26.25.080.745 I slot print_timing: id 0 | task 8624 | total time = 31239.64 ms / 601 tokens 26.25.080.747 I slot print_timing: id 0 | task 8624 | graphs reused = 8236 26.25.080.749 I slot print_timing: id 0 | task 8624 | graph reallocs = 0 / 0 (same size) / (changed size) 26.25.081.072 I slot release: id 0 | task 8624 | stop processing: n_tokens = 632, truncated = 0 26.25.094.660 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 632, t_last = 92302378716 26.25.094.761 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 932.082 MiB) 26.25.195.551 I slot launch_slot_: id 0 | task 8874 | processing task, is_child = 0 26.28.850.967 I slot print_timing: id 0 | task 8874 | prompt processing, n_tokens = 330, progress = 0.99, t = 3.66 s / 90.28 tokens per second 26.40.204.794 I slot print_timing: id 0 | task 8874 | n_gen = 100, tg = 9.51 t/s, tg_3s = 9.60 t/s 26.43.253.685 I slot print_timing: id 0 | task 8874 | n_gen = 129, tg = 9.51 t/s, tg_3s = 9.51 t/s 26.44.410.390 I slot print_timing: id 0 | task 8874 | prompt eval time = 4596.97 ms / 334 tokens ( 13.76 ms per token, 72.66 tokens per second) 26.44.410.392 I slot print_timing: id 0 | task 8874 | eval time = 14617.85 ms / 140 tokens ( 105.16 ms per token, 9.51 tokens per second) 26.44.410.393 I slot print_timing: id 0 | task 8874 | total time = 19214.82 ms / 474 tokens 26.44.410.393 I slot print_timing: id 0 | task 8874 | graphs reused = 8374 26.44.410.394 I slot print_timing: id 0 | task 8874 | graph reallocs = 0 / 0 (same size) / (changed size) 26.44.410.420 I slot release: id 0 | task 8874 | stop processing: n_tokens = 505, truncated = 0 26.44.415.334 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 505, t_last = 92321708063 26.44.415.363 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 932.645 MiB) 26.44.437.386 I slot launch_slot_: id 0 | task 9017 | processing task, is_child = 0 26.48.468.314 I slot print_timing: id 0 | task 9017 | prompt processing, n_tokens = 422, progress = 0.99, t = 4.03 s / 104.69 tokens per second 27.00.215.984 I slot print_timing: id 0 | task 9017 | n_gen = 100, tg = 9.50 t/s, tg_3s = 9.60 t/s 27.03.265.362 I slot print_timing: id 0 | task 9017 | n_gen = 129, tg = 9.50 t/s, tg_3s = 9.51 t/s 27.06.316.374 I slot print_timing: id 0 | task 9017 | n_gen = 158, tg = 9.50 t/s, tg_3s = 9.51 t/s 27.08.105.127 I slot print_timing: id 0 | task 9017 | prompt eval time = 5359.11 ms / 426 tokens ( 12.58 ms per token, 79.49 tokens per second) 27.08.105.132 I slot print_timing: id 0 | task 9017 | eval time = 18308.62 ms / 175 tokens ( 105.22 ms per token, 9.50 tokens per second) 27.08.105.133 I slot print_timing: id 0 | task 9017 | total time = 23667.73 ms / 601 tokens 27.08.105.133 I slot print_timing: id 0 | task 9017 | graphs reused = 8546 27.08.105.134 I slot print_timing: id 0 | task 9017 | graph reallocs = 0 / 0 (same size) / (changed size) 27.08.105.170 I slot release: id 0 | task 9017 | stop processing: n_tokens = 632, truncated = 0 27.08.109.458 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 632, t_last = 92345402813 27.08.109.490 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 935.396 MiB) 27.08.132.444 I slot launch_slot_: id 0 | task 9195 | processing task, is_child = 0 27.11.792.852 I slot print_timing: id 0 | task 9195 | prompt processing, n_tokens = 362, progress = 0.99, t = 3.66 s / 98.90 tokens per second 27.23.165.709 I slot print_timing: id 0 | task 9195 | n_gen = 100, tg = 9.50 t/s, tg_3s = 9.60 t/s 27.24.956.655 I slot print_timing: id 0 | task 9195 | prompt eval time = 4614.44 ms / 366 tokens ( 12.61 ms per token, 79.32 tokens per second) 27.24.956.660 I slot print_timing: id 0 | task 9195 | eval time = 12209.76 ms / 117 tokens ( 105.26 ms per token, 9.50 tokens per second) 27.24.956.660 I slot print_timing: id 0 | task 9195 | total time = 16824.20 ms / 483 tokens 27.24.956.661 I slot print_timing: id 0 | task 9195 | graphs reused = 8660 27.24.956.661 I slot print_timing: id 0 | task 9195 | graph reallocs = 0 / 0 (same size) / (changed size) 27.24.956.718 I slot release: id 0 | task 9195 | stop processing: n_tokens = 514, truncated = 0 27.24.961.608 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 514, t_last = 92362254361 27.24.961.637 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 932.082 MiB) 27.24.983.479 I slot launch_slot_: id 0 | task 9315 | processing task, is_child = 0 27.28.651.010 I slot print_timing: id 0 | task 9315 | prompt processing, n_tokens = 458, progress = 0.99, t = 3.67 s / 124.88 tokens per second 27.41.098.061 I slot print_timing: id 0 | task 9315 | n_gen = 100, tg = 9.50 t/s, tg_3s = 9.59 t/s 27.44.150.107 I slot print_timing: id 0 | task 9315 | n_gen = 129, tg = 9.50 t/s, tg_3s = 9.50 t/s 27.47.202.269 I slot print_timing: id 0 | task 9315 | n_gen = 158, tg = 9.50 t/s, tg_3s = 9.50 t/s 27.50.255.352 I slot print_timing: id 0 | task 9315 | n_gen = 187, tg = 9.50 t/s, tg_3s = 9.50 t/s 27.53.308.620 I slot print_timing: id 0 | task 9315 | n_gen = 216, tg = 9.50 t/s, tg_3s = 9.50 t/s 27.56.363.953 I slot print_timing: id 0 | task 9315 | n_gen = 245, tg = 9.50 t/s, tg_3s = 9.49 t/s 27.58.259.576 I slot print_timing: id 0 | task 9315 | prompt eval time = 5691.89 ms / 462 tokens ( 12.32 ms per token, 81.17 tokens per second) 27.58.259.581 I slot print_timing: id 0 | task 9315 | eval time = 27584.19 ms / 263 tokens ( 105.28 ms per token, 9.50 tokens per second) 27.58.259.581 I slot print_timing: id 0 | task 9315 | total time = 33276.08 ms / 725 tokens 27.58.259.582 I slot print_timing: id 0 | task 9315 | graphs reused = 8920 27.58.259.582 I slot print_timing: id 0 | task 9315 | graph reallocs = 0 / 0 (same size) / (changed size) 27.58.259.630 I slot release: id 0 | task 9315 | stop processing: n_tokens = 756, truncated = 0 27.58.264.597 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 756, t_last = 92395557273 27.58.264.632 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 936.271 MiB) 27.58.288.590 I slot launch_slot_: id 0 | task 9581 | processing task, is_child = 0 28.01.598.613 I slot print_timing: id 0 | task 9581 | prompt processing, n_tokens = 392, progress = 0.99, t = 3.31 s / 118.43 tokens per second 28.13.681.710 I slot print_timing: id 0 | task 9581 | n_gen = 100, tg = 9.50 t/s, tg_3s = 9.60 t/s 28.16.730.485 I slot print_timing: id 0 | task 9581 | n_gen = 129, tg = 9.50 t/s, tg_3s = 9.51 t/s 28.18.939.626 I slot print_timing: id 0 | task 9581 | prompt eval time = 4975.18 ms / 396 tokens ( 12.56 ms per token, 79.60 tokens per second) 28.18.939.631 I slot print_timing: id 0 | task 9581 | eval time = 15675.85 ms / 150 tokens ( 105.21 ms per token, 9.51 tokens per second) 28.18.939.632 I slot print_timing: id 0 | task 9581 | total time = 20651.02 ms / 546 tokens 28.18.939.632 I slot print_timing: id 0 | task 9581 | graphs reused = 9067 28.18.939.633 I slot print_timing: id 0 | task 9581 | graph reallocs = 0 / 0 (same size) / (changed size) 28.18.939.667 I slot release: id 0 | task 9581 | stop processing: n_tokens = 577, truncated = 0 28.18.945.067 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 577, t_last = 92416237310 28.18.945.104 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 936.459 MiB) 28.18.967.776 I slot launch_slot_: id 0 | task 9734 | processing task, is_child = 0 28.23.308.146 I slot print_timing: id 0 | task 9734 | prompt processing, n_tokens = 454, progress = 0.99, t = 4.34 s / 104.60 tokens per second 28.35.376.969 I slot print_timing: id 0 | task 9734 | n_gen = 100, tg = 9.50 t/s, tg_3s = 9.60 t/s 28.38.426.978 I slot print_timing: id 0 | task 9734 | n_gen = 129, tg = 9.50 t/s, tg_3s = 9.51 t/s 28.41.480.279 I slot print_timing: id 0 | task 9734 | n_gen = 158, tg = 9.50 t/s, tg_3s = 9.50 t/s 28.41.796.562 I slot print_timing: id 0 | task 9734 | prompt eval time = 5989.45 ms / 458 tokens ( 13.08 ms per token, 76.47 tokens per second) 28.41.796.565 I slot print_timing: id 0 | task 9734 | eval time = 16839.33 ms / 161 tokens ( 105.25 ms per token, 9.50 tokens per second) 28.41.796.565 I slot print_timing: id 0 | task 9734 | total time = 22828.77 ms / 619 tokens 28.41.796.566 I slot print_timing: id 0 | task 9734 | graphs reused = 9225 28.41.796.566 I slot print_timing: id 0 | task 9734 | graph reallocs = 0 / 0 (same size) / (changed size) 28.41.796.610 I slot release: id 0 | task 9734 | stop processing: n_tokens = 650, truncated = 0 28.41.801.951 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 650, t_last = 92439094253 28.41.801.993 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 929.394 MiB) 28.41.824.289 I slot launch_slot_: id 0 | task 9898 | processing task, is_child = 0 28.45.475.074 I slot print_timing: id 0 | task 9898 | prompt processing, n_tokens = 454, progress = 0.99, t = 3.65 s / 124.36 tokens per second 28.54.575.236 I slot print_timing: id 0 | task 9898 | prompt eval time = 5684.03 ms / 458 tokens ( 12.41 ms per token, 80.58 tokens per second) 28.54.575.241 I slot print_timing: id 0 | task 9898 | eval time = 7066.90 ms / 68 tokens ( 105.48 ms per token, 9.48 tokens per second) 28.54.575.242 I slot print_timing: id 0 | task 9898 | total time = 12750.93 ms / 526 tokens 28.54.575.243 I slot print_timing: id 0 | task 9898 | graphs reused = 9290 28.54.575.243 I slot print_timing: id 0 | task 9898 | graph reallocs = 0 / 0 (same size) / (changed size) 28.54.575.272 I slot release: id 0 | task 9898 | stop processing: n_tokens = 557, truncated = 0 28.54.580.051 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 557, t_last = 92451872915 28.54.580.081 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 942.461 MiB) 28.54.602.191 I slot launch_slot_: id 0 | task 9969 | processing task, is_child = 0 28.58.631.331 I slot print_timing: id 0 | task 9969 | prompt processing, n_tokens = 448, progress = 0.99, t = 4.03 s / 111.19 tokens per second 29.10.711.394 I slot print_timing: id 0 | task 9969 | n_gen = 100, tg = 9.50 t/s, tg_3s = 9.59 t/s 29.13.762.237 I slot print_timing: id 0 | task 9969 | n_gen = 129, tg = 9.50 t/s, tg_3s = 9.51 t/s 29.16.811.632 I slot print_timing: id 0 | task 9969 | n_gen = 158, tg = 9.50 t/s, tg_3s = 9.51 t/s 29.19.862.271 I slot print_timing: id 0 | task 9969 | n_gen = 187, tg = 9.50 t/s, tg_3s = 9.51 t/s 29.22.915.192 I slot print_timing: id 0 | task 9969 | n_gen = 216, tg = 9.50 t/s, tg_3s = 9.50 t/s 29.25.652.414 I slot print_timing: id 0 | task 9969 | prompt eval time = 5685.23 ms / 452 tokens ( 12.58 ms per token, 79.50 tokens per second) 29.25.652.416 I slot print_timing: id 0 | task 9969 | eval time = 25364.98 ms / 242 tokens ( 105.25 ms per token, 9.50 tokens per second) 29.25.652.417 I slot print_timing: id 0 | task 9969 | total time = 31050.21 ms / 694 tokens 29.25.652.417 I slot print_timing: id 0 | task 9969 | graphs reused = 9529 29.25.652.418 I slot print_timing: id 0 | task 9969 | graph reallocs = 0 / 0 (same size) / (changed size) 29.25.652.445 I slot release: id 0 | task 9969 | stop processing: n_tokens = 725, truncated = 0 29.25.656.334 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 725, t_last = 92482950088 29.25.656.370 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 937.272 MiB) 29.25.679.873 I slot launch_slot_: id 0 | task 10214 | processing task, is_child = 0 29.29.330.140 I slot print_timing: id 0 | task 10214 | prompt processing, n_tokens = 400, progress = 0.99, t = 3.65 s / 109.58 tokens per second 29.41.397.730 I slot print_timing: id 0 | task 10214 | n_gen = 100, tg = 9.50 t/s, tg_3s = 9.60 t/s 29.44.447.525 I slot print_timing: id 0 | task 10214 | n_gen = 129, tg = 9.50 t/s, tg_3s = 9.51 t/s 29.44.657.898 I slot print_timing: id 0 | task 10214 | prompt eval time = 5298.82 ms / 404 tokens ( 13.12 ms per token, 76.24 tokens per second) 29.44.657.905 I slot print_timing: id 0 | task 10214 | eval time = 13679.19 ms / 131 tokens ( 105.22 ms per token, 9.50 tokens per second) 29.44.657.905 I slot print_timing: id 0 | task 10214 | total time = 18978.01 ms / 535 tokens 29.44.657.906 I slot print_timing: id 0 | task 10214 | graphs reused = 9657 29.44.657.906 I slot print_timing: id 0 | task 10214 | graph reallocs = 0 / 0 (same size) / (changed size) 29.44.657.932 I slot release: id 0 | task 10214 | stop processing: n_tokens = 566, truncated = 0 29.44.662.456 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 566, t_last = 92501955575 29.44.662.487 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 929.331 MiB) 29.44.684.745 I slot launch_slot_: id 0 | task 10348 | processing task, is_child = 0 29.48.335.202 I slot print_timing: id 0 | task 10348 | prompt processing, n_tokens = 341, progress = 0.99, t = 3.65 s / 93.41 tokens per second 29.59.702.232 I slot print_timing: id 0 | task 10348 | n_gen = 100, tg = 9.50 t/s, tg_3s = 9.60 t/s 30.00.333.292 I slot print_timing: id 0 | task 10348 | prompt eval time = 4598.41 ms / 345 tokens ( 13.33 ms per token, 75.03 tokens per second) 30.00.333.299 I slot print_timing: id 0 | task 10348 | eval time = 11050.13 ms / 106 tokens ( 105.24 ms per token, 9.50 tokens per second) 30.00.333.300 I slot print_timing: id 0 | task 10348 | total time = 15648.54 ms / 451 tokens 30.00.333.300 I slot print_timing: id 0 | task 10348 | graphs reused = 9761 30.00.333.301 I slot print_timing: id 0 | task 10348 | graph reallocs = 0 / 0 (same size) / (changed size) 30.00.333.337 I slot release: id 0 | task 10348 | stop processing: n_tokens = 482, truncated = 0 30.00.337.751 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 482, t_last = 92517630980 30.00.337.778 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 937.272 MiB) 30.00.390.112 I slot launch_slot_: id 0 | task 10457 | processing task, is_child = 0 30.04.032.771 I slot print_timing: id 0 | task 10457 | prompt processing, n_tokens = 426, progress = 0.99, t = 3.64 s / 116.95 tokens per second 30.16.474.055 I slot print_timing: id 0 | task 10457 | n_gen = 100, tg = 9.50 t/s, tg_3s = 9.60 t/s 30.18.367.235 I slot print_timing: id 0 | task 10457 | prompt eval time = 5663.30 ms / 430 tokens ( 13.17 ms per token, 75.93 tokens per second) 30.18.367.240 I slot print_timing: id 0 | task 10457 | eval time = 12313.81 ms / 118 tokens ( 105.25 ms per token, 9.50 tokens per second) 30.18.367.241 I slot print_timing: id 0 | task 10457 | total time = 17977.11 ms / 548 tokens 30.18.367.241 I slot print_timing: id 0 | task 10457 | graphs reused = 9876 30.18.367.242 I slot print_timing: id 0 | task 10457 | graph reallocs = 0 / 0 (same size) / (changed size) 30.18.367.272 I slot release: id 0 | task 10457 | stop processing: n_tokens = 579, truncated = 0 30.18.371.366 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 579, t_last = 92535664915 30.18.371.396 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 929.894 MiB) 30.18.393.921 I slot launch_slot_: id 0 | task 10578 | processing task, is_child = 0 30.21.698.478 I slot print_timing: id 0 | task 10578 | prompt processing, n_tokens = 312, progress = 0.99, t = 3.30 s / 94.42 tokens per second 30.31.500.494 I slot print_timing: id 0 | task 10578 | prompt eval time = 4252.80 ms / 316 tokens ( 13.46 ms per token, 74.30 tokens per second) 30.31.500.496 I slot print_timing: id 0 | task 10578 | eval time = 8853.76 ms / 85 tokens ( 105.40 ms per token, 9.49 tokens per second) 30.31.500.497 I slot print_timing: id 0 | task 10578 | total time = 13106.56 ms / 401 tokens 30.31.500.497 I slot print_timing: id 0 | task 10578 | graphs reused = 9959 30.31.500.498 I slot print_timing: id 0 | task 10578 | graph reallocs = 0 / 0 (same size) / (changed size) 30.31.500.520 I slot release: id 0 | task 10578 | stop processing: n_tokens = 432, truncated = 0 30.31.505.346 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 432, t_last = 92548798163 30.31.505.383 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 945.024 MiB) 30.31.540.006 I slot launch_slot_: id 0 | task 10666 | processing task, is_child = 0 30.35.180.292 I slot print_timing: id 0 | task 10666 | prompt processing, n_tokens = 350, progress = 0.99, t = 3.64 s / 96.15 tokens per second 30.46.557.756 I slot print_timing: id 0 | task 10666 | n_gen = 100, tg = 9.51 t/s, tg_3s = 9.60 t/s 30.47.293.795 I slot print_timing: id 0 | task 10666 | prompt eval time = 4604.71 ms / 354 tokens ( 13.01 ms per token, 76.88 tokens per second) 30.47.293.800 I slot print_timing: id 0 | task 10666 | eval time = 11149.07 ms / 107 tokens ( 105.18 ms per token, 9.51 tokens per second) 30.47.293.801 I slot print_timing: id 0 | task 10666 | total time = 15753.78 ms / 461 tokens 30.47.293.801 I slot print_timing: id 0 | task 10666 | graphs reused = 10064 30.47.293.802 I slot print_timing: id 0 | task 10666 | graph reallocs = 0 / 0 (same size) / (changed size) 30.47.293.829 I slot release: id 0 | task 10666 | stop processing: n_tokens = 492, truncated = 0 30.47.298.492 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 492, t_last = 92564591472 30.47.298.520 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 933.833 MiB) 30.47.320.390 I slot launch_slot_: id 0 | task 10776 | processing task, is_child = 0 30.52.046.426 I slot print_timing: id 0 | task 10776 | prompt processing, n_tokens = 434, progress = 0.99, t = 4.73 s / 91.83 tokens per second 31.03.418.839 I slot print_timing: id 0 | task 10776 | n_gen = 100, tg = 9.50 t/s, tg_3s = 9.59 t/s 31.04.154.253 I slot print_timing: id 0 | task 10776 | prompt eval time = 5676.34 ms / 438 tokens ( 12.96 ms per token, 77.16 tokens per second) 31.04.154.259 I slot print_timing: id 0 | task 10776 | eval time = 11157.51 ms / 107 tokens ( 105.26 ms per token, 9.50 tokens per second) 31.04.154.260 I slot print_timing: id 0 | task 10776 | total time = 16833.85 ms / 545 tokens 31.04.154.260 I slot print_timing: id 0 | task 10776 | graphs reused = 10168 31.04.154.261 I slot print_timing: id 0 | task 10776 | graph reallocs = 0 / 0 (same size) / (changed size) 31.04.154.296 I slot release: id 0 | task 10776 | stop processing: n_tokens = 576, truncated = 0 31.04.159.688 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 576, t_last = 92581451940 31.04.159.728 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 938.397 MiB) 31.04.184.174 I slot launch_slot_: id 0 | task 10886 | processing task, is_child = 0 31.09.262.293 I slot print_timing: id 0 | task 10886 | prompt processing, n_tokens = 453, progress = 0.99, t = 5.08 s / 89.21 tokens per second 31.17.463.938 I slot print_timing: id 0 | task 10886 | prompt eval time = 6018.91 ms / 457 tokens ( 13.17 ms per token, 75.93 tokens per second) 31.17.463.944 I slot print_timing: id 0 | task 10886 | eval time = 7260.84 ms / 70 tokens ( 105.23 ms per token, 9.50 tokens per second) 31.17.463.945 I slot print_timing: id 0 | task 10886 | total time = 13279.75 ms / 527 tokens 31.17.463.945 I slot print_timing: id 0 | task 10886 | graphs reused = 10235 31.17.463.946 I slot print_timing: id 0 | task 10886 | graph reallocs = 0 / 0 (same size) / (changed size) 31.17.463.982 I slot release: id 0 | task 10886 | stop processing: n_tokens = 558, truncated = 0 31.17.469.079 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 92594761625 31.17.469.115 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 932.582 MiB) 31.17.491.703 I slot launch_slot_: id 0 | task 10959 | processing task, is_child = 0 31.22.224.570 I slot print_timing: id 0 | task 10959 | prompt processing, n_tokens = 469, progress = 0.99, t = 4.73 s / 99.09 tokens per second 31.33.752.392 I slot print_timing: id 0 | task 10959 | prompt eval time = 6049.76 ms / 473 tokens ( 12.79 ms per token, 78.18 tokens per second) 31.33.752.394 I slot print_timing: id 0 | task 10959 | eval time = 10210.91 ms / 98 tokens ( 105.27 ms per token, 9.50 tokens per second) 31.33.752.396 I slot print_timing: id 0 | task 10959 | total time = 16260.67 ms / 571 tokens 31.33.752.396 I slot print_timing: id 0 | task 10959 | graphs reused = 10330 31.33.752.397 I slot print_timing: id 0 | task 10959 | graph reallocs = 0 / 0 (same size) / (changed size) 31.33.752.430 I slot release: id 0 | task 10959 | stop processing: n_tokens = 602, truncated = 0 31.33.757.407 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 602, t_last = 92611050073 31.33.757.448 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 943.086 MiB) 31.33.780.443 I slot launch_slot_: id 0 | task 11060 | processing task, is_child = 0 31.38.867.637 I slot print_timing: id 0 | task 11060 | prompt processing, n_tokens = 472, progress = 0.99, t = 5.09 s / 92.78 tokens per second 31.42.565.194 I slot print_timing: id 0 | task 11060 | prompt eval time = 6041.87 ms / 476 tokens ( 12.69 ms per token, 78.78 tokens per second) 31.42.565.199 I slot print_timing: id 0 | task 11060 | eval time = 2742.87 ms / 27 tokens ( 105.49 ms per token, 9.48 tokens per second) 31.42.565.199 I slot print_timing: id 0 | task 11060 | total time = 8784.74 ms / 503 tokens 31.42.565.200 I slot print_timing: id 0 | task 11060 | graphs reused = 10354 31.42.565.200 I slot print_timing: id 0 | task 11060 | graph reallocs = 0 / 0 (same size) / (changed size) 31.42.565.243 I slot release: id 0 | task 11060 | stop processing: n_tokens = 534, truncated = 0 31.42.570.324 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 534, t_last = 92619862886 31.42.570.361 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 933.145 MiB) 31.42.592.469 I slot launch_slot_: id 0 | task 11090 | processing task, is_child = 0 31.47.310.160 I slot print_timing: id 0 | task 11090 | prompt processing, n_tokens = 462, progress = 0.99, t = 4.72 s / 97.93 tokens per second 31.59.054.602 I slot print_timing: id 0 | task 11090 | n_gen = 100, tg = 9.50 t/s, tg_3s = 9.60 t/s 31.59.791.406 I slot print_timing: id 0 | task 11090 | prompt eval time = 6044.00 ms / 466 tokens ( 12.97 ms per token, 77.10 tokens per second) 31.59.791.408 I slot print_timing: id 0 | task 11090 | eval time = 11154.93 ms / 107 tokens ( 105.24 ms per token, 9.50 tokens per second) 31.59.791.409 I slot print_timing: id 0 | task 11090 | total time = 17198.93 ms / 573 tokens 31.59.791.409 I slot print_timing: id 0 | task 11090 | graphs reused = 10458 31.59.791.410 I slot print_timing: id 0 | task 11090 | graph reallocs = 0 / 0 (same size) / (changed size) 31.59.791.448 I slot release: id 0 | task 11090 | stop processing: n_tokens = 604, truncated = 0 31.59.795.981 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 604, t_last = 92637089091 31.59.796.015 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 927.893 MiB) 31.59.818.100 I slot launch_slot_: id 0 | task 11200 | processing task, is_child = 0 32.04.178.639 I slot print_timing: id 0 | task 11200 | prompt processing, n_tokens = 411, progress = 0.99, t = 4.36 s / 94.25 tokens per second 32.13.225.552 I slot print_timing: id 0 | task 11200 | prompt eval time = 5303.01 ms / 415 tokens ( 12.78 ms per token, 78.26 tokens per second) 32.13.225.558 I slot print_timing: id 0 | task 11200 | eval time = 8104.43 ms / 78 tokens ( 105.25 ms per token, 9.50 tokens per second) 32.13.225.558 I slot print_timing: id 0 | task 11200 | total time = 13407.44 ms / 493 tokens 32.13.225.559 I slot print_timing: id 0 | task 11200 | graphs reused = 10533 32.13.225.559 I slot print_timing: id 0 | task 11200 | graph reallocs = 0 / 0 (same size) / (changed size) 32.13.225.587 I slot release: id 0 | task 11200 | stop processing: n_tokens = 524, truncated = 0 32.13.230.101 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 524, t_last = 92650523230 32.13.230.133 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 933.958 MiB) 32.13.252.093 I slot launch_slot_: id 0 | task 11281 | processing task, is_child = 0 32.16.913.870 I slot print_timing: id 0 | task 11281 | prompt processing, n_tokens = 348, progress = 0.99, t = 3.66 s / 95.04 tokens per second 32.28.279.574 I slot print_timing: id 0 | task 11281 | n_gen = 100, tg = 9.50 t/s, tg_3s = 9.59 t/s 32.31.331.462 I slot print_timing: id 0 | task 11281 | n_gen = 129, tg = 9.50 t/s, tg_3s = 9.50 t/s 32.32.596.063 I slot print_timing: id 0 | task 11281 | prompt eval time = 4603.68 ms / 352 tokens ( 13.08 ms per token, 76.46 tokens per second) 32.32.596.068 I slot print_timing: id 0 | task 11281 | eval time = 14740.28 ms / 141 tokens ( 105.29 ms per token, 9.50 tokens per second) 32.32.596.069 I slot print_timing: id 0 | task 11281 | total time = 19343.96 ms / 493 tokens 32.32.596.069 I slot print_timing: id 0 | task 11281 | graphs reused = 10671 32.32.596.070 I slot print_timing: id 0 | task 11281 | graph reallocs = 0 / 0 (same size) / (changed size) 32.32.596.106 I slot release: id 0 | task 11281 | stop processing: n_tokens = 524, truncated = 0 32.32.601.028 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 524, t_last = 92669893749 32.32.601.061 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 924.767 MiB) 32.32.622.983 I slot launch_slot_: id 0 | task 11425 | processing task, is_child = 0 32.38.855.024 I slot print_timing: id 0 | task 11425 | prompt processing, n_tokens = 546, progress = 0.99, t = 6.23 s / 87.61 tokens per second 32.50.226.482 I slot print_timing: id 0 | task 11425 | n_gen = 100, tg = 9.50 t/s, tg_3s = 9.60 t/s 32.53.280.670 I slot print_timing: id 0 | task 11425 | n_gen = 129, tg = 9.50 t/s, tg_3s = 9.50 t/s 32.53.702.287 I slot print_timing: id 0 | task 11425 | prompt eval time = 7184.56 ms / 550 tokens ( 13.06 ms per token, 76.55 tokens per second) 32.53.702.292 I slot print_timing: id 0 | task 11425 | eval time = 13894.74 ms / 133 tokens ( 105.26 ms per token, 9.50 tokens per second) 32.53.702.292 I slot print_timing: id 0 | task 11425 | total time = 21079.29 ms / 683 tokens 32.53.702.293 I slot print_timing: id 0 | task 11425 | graphs reused = 10802 32.53.702.293 I slot print_timing: id 0 | task 11425 | graph reallocs = 0 / 0 (same size) / (changed size) 32.53.702.337 I slot release: id 0 | task 11425 | stop processing: n_tokens = 714, truncated = 0 32.53.708.269 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 714, t_last = 92690999980 32.53.708.312 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 928.518 MiB) 32.53.756.470 I slot launch_slot_: id 0 | task 11562 | processing task, is_child = 0 33.00.678.148 I slot print_timing: id 0 | task 11562 | prompt processing, n_tokens = 768, progress = 1.00, t = 6.92 s / 110.96 tokens per second 33.13.515.297 I slot print_timing: id 0 | task 11562 | n_gen = 100, tg = 9.49 t/s, tg_3s = 9.58 t/s 33.16.570.133 I slot print_timing: id 0 | task 11562 | n_gen = 129, tg = 9.49 t/s, tg_3s = 9.49 t/s 33.19.626.174 I slot print_timing: id 0 | task 11562 | n_gen = 158, tg = 9.49 t/s, tg_3s = 9.49 t/s 33.22.682.874 I slot print_timing: id 0 | task 11562 | n_gen = 187, tg = 9.49 t/s, tg_3s = 9.49 t/s 33.25.741.468 I slot print_timing: id 0 | task 11562 | n_gen = 216, tg = 9.49 t/s, tg_3s = 9.48 t/s 33.28.802.520 I slot print_timing: id 0 | task 11562 | n_gen = 245, tg = 9.49 t/s, tg_3s = 9.47 t/s 33.29.118.969 I slot print_timing: id 0 | task 11562 | prompt eval time = 9323.71 ms / 772 tokens ( 12.08 ms per token, 82.80 tokens per second) 33.29.118.972 I slot print_timing: id 0 | task 11562 | eval time = 26038.78 ms / 248 tokens ( 105.42 ms per token, 9.49 tokens per second) 33.29.118.973 I slot print_timing: id 0 | task 11562 | total time = 35362.49 ms / 1020 tokens 33.29.118.973 I slot print_timing: id 0 | task 11562 | graphs reused = 11047 33.29.118.974 I slot print_timing: id 0 | task 11562 | graph reallocs = 0 / 0 (same size) / (changed size) 33.29.119.018 I slot release: id 0 | task 11562 | stop processing: n_tokens = 1051, truncated = 0 33.29.124.546 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1051, t_last = 92726416661 33.29.124.595 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 933.770 MiB) 33.29.176.365 I slot launch_slot_: id 0 | task 11814 | processing task, is_child = 0 33.36.115.725 I slot print_timing: id 0 | task 11814 | prompt processing, n_tokens = 679, progress = 0.99, t = 6.94 s / 97.85 tokens per second 33.48.215.780 I slot print_timing: id 0 | task 11814 | n_gen = 100, tg = 9.49 t/s, tg_3s = 9.58 t/s 33.51.270.295 I slot print_timing: id 0 | task 11814 | n_gen = 129, tg = 9.49 t/s, tg_3s = 9.49 t/s 33.54.324.293 I slot print_timing: id 0 | task 11814 | n_gen = 158, tg = 9.49 t/s, tg_3s = 9.50 t/s 33.56.750.953 I slot print_timing: id 0 | task 11814 | prompt eval time = 8603.52 ms / 683 tokens ( 12.60 ms per token, 79.39 tokens per second) 33.56.750.955 I slot print_timing: id 0 | task 11814 | eval time = 18971.06 ms / 181 tokens ( 105.39 ms per token, 9.49 tokens per second) 33.56.750.955 I slot print_timing: id 0 | task 11814 | total time = 27574.58 ms / 864 tokens 33.56.750.956 I slot print_timing: id 0 | task 11814 | graphs reused = 11225 33.56.750.956 I slot print_timing: id 0 | task 11814 | graph reallocs = 0 / 0 (same size) / (changed size) 33.56.750.991 I slot release: id 0 | task 11814 | stop processing: n_tokens = 895, truncated = 0 33.56.756.223 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 895, t_last = 92754048634 33.56.756.270 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 932.645 MiB) 33.56.784.229 I slot launch_slot_: id 0 | task 11999 | processing task, is_child = 0 34.02.297.317 I slot print_timing: id 0 | task 11999 | prompt processing, n_tokens = 575, progress = 0.99, t = 5.51 s / 104.30 tokens per second 34.14.401.442 I slot print_timing: id 0 | task 11999 | n_gen = 100, tg = 9.49 t/s, tg_3s = 9.59 t/s 34.17.456.090 I slot print_timing: id 0 | task 11999 | n_gen = 129, tg = 9.49 t/s, tg_3s = 9.49 t/s 34.20.510.377 I slot print_timing: id 0 | task 11999 | n_gen = 158, tg = 9.49 t/s, tg_3s = 9.49 t/s 34.23.567.972 I slot print_timing: id 0 | task 11999 | n_gen = 187, tg = 9.49 t/s, tg_3s = 9.48 t/s 34.26.624.676 I slot print_timing: id 0 | task 11999 | n_gen = 216, tg = 9.49 t/s, tg_3s = 9.49 t/s 34.29.678.912 I slot print_timing: id 0 | task 11999 | n_gen = 245, tg = 9.49 t/s, tg_3s = 9.50 t/s 34.31.152.940 I slot print_timing: id 0 | task 11999 | prompt eval time = 7189.27 ms / 579 tokens ( 12.42 ms per token, 80.54 tokens per second) 34.31.152.943 I slot print_timing: id 0 | task 11999 | eval time = 27179.42 ms / 259 tokens ( 105.35 ms per token, 9.49 tokens per second) 34.31.152.944 I slot print_timing: id 0 | task 11999 | total time = 34368.70 ms / 838 tokens 34.31.152.944 I slot print_timing: id 0 | task 11999 | graphs reused = 11481 34.31.152.945 I slot print_timing: id 0 | task 11999 | graph reallocs = 0 / 0 (same size) / (changed size) 34.31.152.983 I slot release: id 0 | task 11999 | stop processing: n_tokens = 869, truncated = 0 34.31.158.048 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 869, t_last = 92788450626 34.31.158.088 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 935.396 MiB) 34.31.207.750 I slot launch_slot_: id 0 | task 12262 | processing task, is_child = 0 34.36.647.454 I slot print_timing: id 0 | task 12262 | prompt processing, n_tokens = 496, progress = 0.99, t = 5.44 s / 91.18 tokens per second 34.48.021.871 I slot print_timing: id 0 | task 12262 | n_gen = 100, tg = 9.50 t/s, tg_3s = 9.60 t/s 34.48.653.479 I slot print_timing: id 0 | task 12262 | prompt eval time = 6395.41 ms / 500 tokens ( 12.79 ms per token, 78.18 tokens per second) 34.48.653.481 I slot print_timing: id 0 | task 12262 | eval time = 11050.31 ms / 106 tokens ( 105.24 ms per token, 9.50 tokens per second) 34.48.653.482 I slot print_timing: id 0 | task 12262 | total time = 17445.72 ms / 606 tokens 34.48.653.482 I slot print_timing: id 0 | task 12262 | graphs reused = 11585 34.48.653.483 I slot print_timing: id 0 | task 12262 | graph reallocs = 0 / 0 (same size) / (changed size) 34.48.653.513 I slot release: id 0 | task 12262 | stop processing: n_tokens = 637, truncated = 0 34.48.658.686 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 92805951156 34.48.658.722 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 931.144 MiB) 34.48.681.197 I slot launch_slot_: id 0 | task 12371 | processing task, is_child = 0 34.51.969.115 I slot print_timing: id 0 | task 12371 | prompt processing, n_tokens = 613, progress = 0.80, t = 3.29 s / 186.44 tokens per second 34.56.308.367 I slot print_timing: id 0 | task 12371 | prompt processing, n_tokens = 772, progress = 1.00, t = 7.63 s / 101.22 tokens per second 35.08.798.172 I slot print_timing: id 0 | task 12371 | n_gen = 100, tg = 9.49 t/s, tg_3s = 9.58 t/s 35.11.856.061 I slot print_timing: id 0 | task 12371 | n_gen = 129, tg = 9.48 t/s, tg_3s = 9.48 t/s 35.14.913.031 I slot print_timing: id 0 | task 12371 | n_gen = 158, tg = 9.49 t/s, tg_3s = 9.49 t/s 35.17.968.812 I slot print_timing: id 0 | task 12371 | n_gen = 187, tg = 9.49 t/s, tg_3s = 9.49 t/s 35.21.028.117 I slot print_timing: id 0 | task 12371 | n_gen = 216, tg = 9.49 t/s, tg_3s = 9.48 t/s 35.21.558.475 I slot print_timing: id 0 | task 12371 | prompt eval time = 9679.81 ms / 776 tokens ( 12.47 ms per token, 80.17 tokens per second) 35.21.558.477 I slot print_timing: id 0 | task 12371 | eval time = 23197.45 ms / 221 tokens ( 105.44 ms per token, 9.48 tokens per second) 35.21.558.478 I slot print_timing: id 0 | task 12371 | total time = 32877.27 ms / 997 tokens 35.21.558.478 I slot print_timing: id 0 | task 12371 | graphs reused = 11803 35.21.558.479 I slot print_timing: id 0 | task 12371 | graph reallocs = 0 / 0 (same size) / (changed size) 35.21.558.516 I slot release: id 0 | task 12371 | stop processing: n_tokens = 1028, truncated = 0 35.21.563.836 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1028, t_last = 92838856159 35.21.563.897 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 935.521 MiB) 35.21.563.905 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 930.519 MiB) 35.21.615.492 I slot launch_slot_: id 0 | task 12596 | processing task, is_child = 0 35.26.700.411 I slot print_timing: id 0 | task 12596 | prompt processing, n_tokens = 500, progress = 0.99, t = 5.08 s / 98.33 tokens per second 35.38.438.058 I slot print_timing: id 0 | task 12596 | n_gen = 100, tg = 9.50 t/s, tg_3s = 9.60 t/s 35.41.488.694 I slot print_timing: id 0 | task 12596 | n_gen = 129, tg = 9.50 t/s, tg_3s = 9.51 t/s 35.44.541.926 I slot print_timing: id 0 | task 12596 | n_gen = 158, tg = 9.50 t/s, tg_3s = 9.50 t/s 35.47.597.229 I slot print_timing: id 0 | task 12596 | n_gen = 187, tg = 9.50 t/s, tg_3s = 9.49 t/s 35.48.650.092 I slot print_timing: id 0 | task 12596 | prompt eval time = 6406.59 ms / 504 tokens ( 12.71 ms per token, 78.67 tokens per second) 35.48.650.097 I slot print_timing: id 0 | task 12596 | eval time = 20628.00 ms / 197 tokens ( 105.24 ms per token, 9.50 tokens per second) 35.48.650.098 I slot print_timing: id 0 | task 12596 | total time = 27034.59 ms / 701 tokens 35.48.650.098 I slot print_timing: id 0 | task 12596 | graphs reused = 11998 35.48.650.099 I slot print_timing: id 0 | task 12596 | graph reallocs = 0 / 0 (same size) / (changed size) 35.48.650.126 I slot release: id 0 | task 12596 | stop processing: n_tokens = 732, truncated = 0 35.48.655.375 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 732, t_last = 92865947769 35.48.655.414 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 930.519 MiB) 35.48.678.843 I slot launch_slot_: id 0 | task 12796 | processing task, is_child = 0 35.54.898.061 I slot print_timing: id 0 | task 12796 | prompt processing, n_tokens = 629, progress = 0.99, t = 6.22 s / 101.14 tokens per second 36.06.999.169 I slot print_timing: id 0 | task 12796 | n_gen = 100, tg = 9.49 t/s, tg_3s = 9.59 t/s 36.10.058.553 I slot print_timing: id 0 | task 12796 | n_gen = 129, tg = 9.49 t/s, tg_3s = 9.48 t/s 36.13.113.093 I slot print_timing: id 0 | task 12796 | n_gen = 158, tg = 9.49 t/s, tg_3s = 9.49 t/s 36.16.168.308 I slot print_timing: id 0 | task 12796 | n_gen = 187, tg = 9.49 t/s, tg_3s = 9.49 t/s 36.18.275.395 I slot print_timing: id 0 | task 12796 | prompt eval time = 7892.87 ms / 633 tokens ( 12.47 ms per token, 80.20 tokens per second) 36.18.275.398 I slot print_timing: id 0 | task 12796 | eval time = 21703.67 ms / 207 tokens ( 105.36 ms per token, 9.49 tokens per second) 36.18.275.399 I slot print_timing: id 0 | task 12796 | total time = 29596.54 ms / 840 tokens 36.18.275.399 I slot print_timing: id 0 | task 12796 | graphs reused = 12202 36.18.275.400 I slot print_timing: id 0 | task 12796 | graph reallocs = 0 / 0 (same size) / (changed size) 36.18.275.439 I slot release: id 0 | task 12796 | stop processing: n_tokens = 871, truncated = 0 36.18.280.250 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 871, t_last = 92895573082 36.18.280.295 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1092.025 MiB) 36.18.319.075 I slot launch_slot_: id 0 | task 13007 | processing task, is_child = 0 36.22.347.153 I slot print_timing: id 0 | task 13007 | prompt processing, n_tokens = 391, progress = 0.99, t = 4.03 s / 97.07 tokens per second 36.31.829.955 I slot print_timing: id 0 | task 13007 | prompt eval time = 4982.95 ms / 395 tokens ( 12.62 ms per token, 79.27 tokens per second) 36.31.829.960 I slot print_timing: id 0 | task 13007 | eval time = 8527.92 ms / 82 tokens ( 105.28 ms per token, 9.50 tokens per second) 36.31.829.961 I slot print_timing: id 0 | task 13007 | total time = 13510.87 ms / 477 tokens 36.31.829.962 I slot print_timing: id 0 | task 13007 | graphs reused = 12282 36.31.829.962 I slot print_timing: id 0 | task 13007 | graph reallocs = 0 / 0 (same size) / (changed size) 36.31.830.004 I slot release: id 0 | task 13007 | stop processing: n_tokens = 508, truncated = 0 36.31.835.007 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 508, t_last = 92909127647 36.31.835.040 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1113.095 MiB) 36.31.857.342 I slot launch_slot_: id 0 | task 13092 | processing task, is_child = 0 36.37.747.786 I slot print_timing: id 0 | task 13092 | prompt processing, n_tokens = 580, progress = 0.99, t = 5.89 s / 98.46 tokens per second 36.49.835.303 I slot print_timing: id 0 | task 13092 | n_gen = 100, tg = 9.49 t/s, tg_3s = 9.58 t/s 36.52.891.016 I slot print_timing: id 0 | task 13092 | n_gen = 129, tg = 9.49 t/s, tg_3s = 9.49 t/s 36.55.952.863 I slot print_timing: id 0 | task 13092 | n_gen = 158, tg = 9.48 t/s, tg_3s = 9.47 t/s 36.59.005.432 I slot print_timing: id 0 | task 13092 | n_gen = 187, tg = 9.49 t/s, tg_3s = 9.50 t/s 37.02.061.422 I slot print_timing: id 0 | task 13092 | n_gen = 216, tg = 9.49 t/s, tg_3s = 9.49 t/s 37.02.588.391 I slot print_timing: id 0 | task 13092 | prompt eval time = 7541.71 ms / 584 tokens ( 12.91 ms per token, 77.44 tokens per second) 37.02.588.397 I slot print_timing: id 0 | task 13092 | eval time = 23189.33 ms / 221 tokens ( 105.41 ms per token, 9.49 tokens per second) 37.02.588.397 I slot print_timing: id 0 | task 13092 | total time = 30731.04 ms / 805 tokens 37.02.588.398 I slot print_timing: id 0 | task 13092 | graphs reused = 12500 37.02.588.398 I slot print_timing: id 0 | task 13092 | graph reallocs = 0 / 0 (same size) / (changed size) 37.02.588.447 I slot release: id 0 | task 13092 | stop processing: n_tokens = 836, truncated = 0 37.02.593.405 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 836, t_last = 92939886090 37.02.593.448 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1103.341 MiB) 37.02.618.894 I slot launch_slot_: id 0 | task 13317 | processing task, is_child = 0 37.08.863.669 I slot print_timing: id 0 | task 13317 | prompt processing, n_tokens = 691, progress = 0.99, t = 6.24 s / 110.65 tokens per second 37.21.693.036 I slot print_timing: id 0 | task 13317 | n_gen = 100, tg = 9.48 t/s, tg_3s = 9.58 t/s 37.24.750.467 I slot print_timing: id 0 | task 13317 | n_gen = 129, tg = 9.48 t/s, tg_3s = 9.49 t/s 37.27.805.385 I slot print_timing: id 0 | task 13317 | n_gen = 158, tg = 9.48 t/s, tg_3s = 9.49 t/s 37.30.861.177 I slot print_timing: id 0 | task 13317 | n_gen = 187, tg = 9.49 t/s, tg_3s = 9.49 t/s 37.33.916.613 I slot print_timing: id 0 | task 13317 | n_gen = 216, tg = 9.49 t/s, tg_3s = 9.49 t/s 37.36.972.987 I slot print_timing: id 0 | task 13317 | n_gen = 245, tg = 9.49 t/s, tg_3s = 9.49 t/s 37.38.554.737 I slot print_timing: id 0 | task 13317 | prompt eval time = 8633.77 ms / 695 tokens ( 12.42 ms per token, 80.50 tokens per second) 37.38.554.740 I slot print_timing: id 0 | task 13317 | eval time = 27302.06 ms / 260 tokens ( 105.41 ms per token, 9.49 tokens per second) 37.38.554.740 I slot print_timing: id 0 | task 13317 | total time = 35935.83 ms / 955 tokens 37.38.554.741 I slot print_timing: id 0 | task 13317 | graphs reused = 12757 37.38.554.741 I slot print_timing: id 0 | task 13317 | graph reallocs = 0 / 0 (same size) / (changed size) 37.38.554.777 I slot release: id 0 | task 13317 | stop processing: n_tokens = 986, truncated = 0 37.38.560.006 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 986, t_last = 92975852420 37.38.560.048 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1101.716 MiB) 37.38.590.550 I slot launch_slot_: id 0 | task 13581 | processing task, is_child = 0 37.46.240.830 I slot print_timing: id 0 | task 13581 | prompt processing, n_tokens = 765, progress = 1.00, t = 7.65 s / 100.00 tokens per second 37.57.309.755 I slot print_timing: id 0 | task 13581 | prompt eval time = 9333.18 ms / 769 tokens ( 12.14 ms per token, 82.39 tokens per second) 37.57.309.760 I slot print_timing: id 0 | task 13581 | eval time = 9386.01 ms / 90 tokens ( 105.46 ms per token, 9.48 tokens per second) 37.57.309.761 I slot print_timing: id 0 | task 13581 | total time = 18719.19 ms / 859 tokens 37.57.309.761 I slot print_timing: id 0 | task 13581 | graphs reused = 12845 37.57.309.762 I slot print_timing: id 0 | task 13581 | graph reallocs = 0 / 0 (same size) / (changed size) 37.57.309.812 I slot release: id 0 | task 13581 | stop processing: n_tokens = 890, truncated = 0 37.57.315.417 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 890, t_last = 92994607455 37.57.315.470 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 937.584 MiB) 37.57.356.933 I slot launch_slot_: id 0 | task 13675 | processing task, is_child = 0 38.03.241.139 I slot print_timing: id 0 | task 13675 | prompt processing, n_tokens = 572, progress = 0.99, t = 5.88 s / 97.21 tokens per second 38.14.986.762 I slot print_timing: id 0 | task 13675 | n_gen = 100, tg = 9.50 t/s, tg_3s = 9.60 t/s 38.18.067.192 I slot print_timing: id 0 | task 13675 | n_gen = 128, tg = 9.41 t/s, tg_3s = 9.09 t/s 38.21.121.624 I slot print_timing: id 0 | task 13675 | n_gen = 157, tg = 9.42 t/s, tg_3s = 9.49 t/s 38.21.226.900 I slot print_timing: id 0 | task 13675 | prompt eval time = 7209.20 ms / 576 tokens ( 12.52 ms per token, 79.90 tokens per second) 38.21.226.906 I slot print_timing: id 0 | task 13675 | eval time = 16660.75 ms / 158 tokens ( 106.12 ms per token, 9.42 tokens per second) 38.21.226.906 I slot print_timing: id 0 | task 13675 | total time = 23869.96 ms / 734 tokens 38.21.226.907 I slot print_timing: id 0 | task 13675 | graphs reused = 13001 38.21.226.907 I slot print_timing: id 0 | task 13675 | graph reallocs = 0 / 0 (same size) / (changed size) 38.21.226.948 I slot release: id 0 | task 13675 | stop processing: n_tokens = 765, truncated = 0 38.21.232.539 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 765, t_last = 93018524592 38.21.232.581 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1111.657 MiB) 38.21.257.936 I slot launch_slot_: id 0 | task 13837 | processing task, is_child = 0 38.27.468.373 I slot print_timing: id 0 | task 13837 | prompt processing, n_tokens = 651, progress = 0.99, t = 6.21 s / 104.82 tokens per second 38.39.084.495 I slot print_timing: id 0 | task 13837 | prompt eval time = 8236.25 ms / 655 tokens ( 12.57 ms per token, 79.53 tokens per second) 38.39.084.500 I slot print_timing: id 0 | task 13837 | eval time = 9590.30 ms / 92 tokens ( 105.39 ms per token, 9.49 tokens per second) 38.39.084.501 I slot print_timing: id 0 | task 13837 | total time = 17826.55 ms / 747 tokens 38.39.084.501 I slot print_timing: id 0 | task 13837 | graphs reused = 13090 38.39.084.501 I slot print_timing: id 0 | task 13837 | graph reallocs = 0 / 0 (same size) / (changed size) 38.39.084.539 I slot release: id 0 | task 13837 | stop processing: n_tokens = 778, truncated = 0 38.39.089.485 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 778, t_last = 93036382182 38.39.089.522 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 943.524 MiB) 38.39.115.145 I slot launch_slot_: id 0 | task 13933 | processing task, is_child = 0 38.45.329.083 I slot print_timing: id 0 | task 13933 | prompt processing, n_tokens = 617, progress = 0.99, t = 6.21 s / 99.29 tokens per second 38.57.420.663 I slot print_timing: id 0 | task 13933 | n_gen = 100, tg = 9.50 t/s, tg_3s = 9.59 t/s 39.00.477.788 I slot print_timing: id 0 | task 13933 | n_gen = 129, tg = 9.49 t/s, tg_3s = 9.49 t/s 39.01.425.494 I slot print_timing: id 0 | task 13933 | prompt eval time = 7879.60 ms / 621 tokens ( 12.69 ms per token, 78.81 tokens per second) 39.01.425.500 I slot print_timing: id 0 | task 13933 | eval time = 14430.74 ms / 138 tokens ( 105.33 ms per token, 9.49 tokens per second) 39.01.425.501 I slot print_timing: id 0 | task 13933 | total time = 22310.34 ms / 759 tokens 39.01.425.501 I slot print_timing: id 0 | task 13933 | graphs reused = 13225 39.01.425.502 I slot print_timing: id 0 | task 13933 | graph reallocs = 0 / 0 (same size) / (changed size) 39.01.425.545 I slot release: id 0 | task 13933 | stop processing: n_tokens = 790, truncated = 0 39.01.431.036 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 790, t_last = 93058723188 39.01.431.075 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1101.841 MiB) 39.01.458.961 I slot launch_slot_: id 0 | task 14075 | processing task, is_child = 0 39.08.750.057 I slot print_timing: id 0 | task 14075 | prompt processing, n_tokens = 763, progress = 0.99, t = 7.29 s / 104.65 tokens per second 39.21.202.810 I slot print_timing: id 0 | task 14075 | n_gen = 100, tg = 9.49 t/s, tg_3s = 9.59 t/s 39.24.258.810 I slot print_timing: id 0 | task 14075 | n_gen = 129, tg = 9.49 t/s, tg_3s = 9.49 t/s 39.27.331.382 I slot print_timing: id 0 | task 14075 | n_gen = 158, tg = 9.48 t/s, tg_3s = 9.44 t/s 39.30.386.258 I slot print_timing: id 0 | task 14075 | n_gen = 187, tg = 9.48 t/s, tg_3s = 9.49 t/s 39.32.073.296 I slot print_timing: id 0 | task 14075 | prompt eval time = 9315.69 ms / 767 tokens ( 12.15 ms per token, 82.33 tokens per second) 39.32.073.302 I slot print_timing: id 0 | task 14075 | eval time = 21298.63 ms / 203 tokens ( 105.44 ms per token, 9.48 tokens per second) 39.32.073.303 I slot print_timing: id 0 | task 14075 | total time = 30614.33 ms / 970 tokens 39.32.073.303 I slot print_timing: id 0 | task 14075 | graphs reused = 13426 39.32.073.304 I slot print_timing: id 0 | task 14075 | graph reallocs = 0 / 0 (same size) / (changed size) 39.32.073.345 I slot release: id 0 | task 14075 | stop processing: n_tokens = 1001, truncated = 0 39.32.079.457 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1001, t_last = 93089370989 39.32.079.507 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 929.519 MiB) 39.32.105.710 I slot launch_slot_: id 0 | task 14282 | processing task, is_child = 0 39.36.139.554 I slot print_timing: id 0 | task 14282 | prompt processing, n_tokens = 686, progress = 0.80, t = 4.03 s / 170.06 tokens per second 39.40.166.345 I slot print_timing: id 0 | task 14282 | prompt processing, n_tokens = 860, progress = 1.00, t = 8.06 s / 106.69 tokens per second 39.52.993.350 I slot print_timing: id 0 | task 14282 | n_gen = 100, tg = 9.49 t/s, tg_3s = 9.58 t/s 39.56.051.302 I slot print_timing: id 0 | task 14282 | n_gen = 129, tg = 9.49 t/s, tg_3s = 9.48 t/s 39.59.128.369 I slot print_timing: id 0 | task 14282 | n_gen = 158, tg = 9.48 t/s, tg_3s = 9.42 t/s 40.02.187.233 I slot print_timing: id 0 | task 14282 | n_gen = 187, tg = 9.48 t/s, tg_3s = 9.48 t/s 40.05.244.940 I slot print_timing: id 0 | task 14282 | n_gen = 216, tg = 9.48 t/s, tg_3s = 9.48 t/s 40.05.772.340 I slot print_timing: id 0 | task 14282 | prompt eval time = 10453.09 ms / 864 tokens ( 12.10 ms per token, 82.66 tokens per second) 40.05.772.345 I slot print_timing: id 0 | task 14282 | eval time = 23213.53 ms / 221 tokens ( 105.52 ms per token, 9.48 tokens per second) 40.05.772.346 I slot print_timing: id 0 | task 14282 | total time = 33666.62 ms / 1085 tokens 40.05.772.346 I slot print_timing: id 0 | task 14282 | graphs reused = 13644 40.05.772.347 I slot print_timing: id 0 | task 14282 | graph reallocs = 0 / 0 (same size) / (changed size) 40.05.772.383 I slot release: id 0 | task 14282 | stop processing: n_tokens = 1116, truncated = 0 40.05.777.562 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1116, t_last = 93123070026 40.05.777.610 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1099.652 MiB) 40.05.819.266 I slot launch_slot_: id 0 | task 14507 | processing task, is_child = 0 40.12.390.061 I slot print_timing: id 0 | task 14507 | prompt processing, n_tokens = 642, progress = 0.99, t = 6.57 s / 97.71 tokens per second 40.24.492.053 I slot print_timing: id 0 | task 14507 | n_gen = 100, tg = 9.49 t/s, tg_3s = 9.59 t/s 40.27.546.960 I slot print_timing: id 0 | task 14507 | prompt eval time = 8240.93 ms / 646 tokens ( 12.76 ms per token, 78.39 tokens per second) 40.27.546.964 I slot print_timing: id 0 | task 14507 | eval time = 13486.75 ms / 129 tokens ( 105.37 ms per token, 9.49 tokens per second) 40.27.546.965 I slot print_timing: id 0 | task 14507 | total time = 21727.68 ms / 775 tokens 40.27.546.965 I slot print_timing: id 0 | task 14507 | graphs reused = 13770 40.27.546.966 I slot print_timing: id 0 | task 14507 | graph reallocs = 0 / 0 (same size) / (changed size) 40.27.547.002 I slot release: id 0 | task 14507 | stop processing: n_tokens = 806, truncated = 0 40.27.553.257 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 806, t_last = 93144844645 40.27.553.305 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1109.031 MiB) 40.27.580.026 I slot launch_slot_: id 0 | task 14640 | processing task, is_child = 0 40.34.522.649 I slot print_timing: id 0 | task 14640 | prompt processing, n_tokens = 716, progress = 0.99, t = 6.94 s / 103.13 tokens per second 40.46.989.055 I slot print_timing: id 0 | task 14640 | n_gen = 100, tg = 9.48 t/s, tg_3s = 9.58 t/s 40.50.059.263 I slot print_timing: id 0 | task 14640 | n_gen = 129, tg = 9.48 t/s, tg_3s = 9.45 t/s 40.53.114.247 I slot print_timing: id 0 | task 14640 | n_gen = 158, tg = 9.48 t/s, tg_3s = 9.49 t/s 40.56.182.880 I slot print_timing: id 0 | task 14640 | n_gen = 187, tg = 9.47 t/s, tg_3s = 9.45 t/s 40.59.240.963 I slot print_timing: id 0 | task 14640 | n_gen = 216, tg = 9.48 t/s, tg_3s = 9.48 t/s 40.59.873.307 I slot print_timing: id 0 | task 14640 | prompt eval time = 8971.13 ms / 720 tokens ( 12.46 ms per token, 80.26 tokens per second) 40.59.873.314 I slot print_timing: id 0 | task 14640 | eval time = 23322.14 ms / 222 tokens ( 105.53 ms per token, 9.48 tokens per second) 40.59.873.315 I slot print_timing: id 0 | task 14640 | total time = 32293.27 ms / 942 tokens 40.59.873.315 I slot print_timing: id 0 | task 14640 | graphs reused = 13989 40.59.873.316 I slot print_timing: id 0 | task 14640 | graph reallocs = 0 / 0 (same size) / (changed size) 40.59.873.350 I slot release: id 0 | task 14640 | stop processing: n_tokens = 973, truncated = 0 40.59.877.909 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 973, t_last = 93177170993 40.59.877.951 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1103.029 MiB) 40.59.903.920 I slot launch_slot_: id 0 | task 14866 | processing task, is_child = 0 41.04.641.596 I slot print_timing: id 0 | task 14866 | prompt processing, n_tokens = 505, progress = 0.99, t = 4.74 s / 106.59 tokens per second 41.16.710.705 I slot print_timing: id 0 | task 14866 | n_gen = 100, tg = 9.50 t/s, tg_3s = 9.60 t/s 41.19.760.707 I slot print_timing: id 0 | task 14866 | n_gen = 129, tg = 9.50 t/s, tg_3s = 9.51 t/s 41.22.814.714 I slot print_timing: id 0 | task 14866 | n_gen = 158, tg = 9.50 t/s, tg_3s = 9.50 t/s 41.25.869.333 I slot print_timing: id 0 | task 14866 | n_gen = 187, tg = 9.50 t/s, tg_3s = 9.49 t/s 41.28.714.784 I slot print_timing: id 0 | task 14866 | prompt eval time = 6386.77 ms / 509 tokens ( 12.55 ms per token, 79.70 tokens per second) 41.28.714.786 I slot print_timing: id 0 | task 14866 | eval time = 22424.08 ms / 214 tokens ( 105.28 ms per token, 9.50 tokens per second) 41.28.714.787 I slot print_timing: id 0 | task 14866 | total time = 28810.85 ms / 723 tokens 41.28.714.787 I slot print_timing: id 0 | task 14866 | graphs reused = 14201 41.28.714.788 I slot print_timing: id 0 | task 14866 | graph reallocs = 0 / 0 (same size) / (changed size) 41.28.714.818 I slot release: id 0 | task 14866 | stop processing: n_tokens = 754, truncated = 0 41.28.719.504 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 754, t_last = 93206012461 41.28.719.542 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1095.213 MiB) 41.28.741.731 I slot launch_slot_: id 0 | task 15083 | processing task, is_child = 0 41.34.625.253 I slot print_timing: id 0 | task 15083 | prompt processing, n_tokens = 577, progress = 0.99, t = 5.88 s / 98.07 tokens per second 41.46.709.175 I slot print_timing: id 0 | task 15083 | n_gen = 100, tg = 9.49 t/s, tg_3s = 9.59 t/s 41.49.764.253 I slot print_timing: id 0 | task 15083 | n_gen = 129, tg = 9.49 t/s, tg_3s = 9.49 t/s 41.52.824.554 I slot print_timing: id 0 | task 15083 | n_gen = 158, tg = 9.49 t/s, tg_3s = 9.48 t/s 41.55.879.094 I slot print_timing: id 0 | task 15083 | n_gen = 187, tg = 9.49 t/s, tg_3s = 9.49 t/s 41.58.934.987 I slot print_timing: id 0 | task 15083 | n_gen = 216, tg = 9.49 t/s, tg_3s = 9.49 t/s 42.01.674.977 I slot print_timing: id 0 | task 15083 | prompt eval time = 7539.71 ms / 581 tokens ( 12.98 ms per token, 77.06 tokens per second) 42.01.674.980 I slot print_timing: id 0 | task 15083 | eval time = 25393.52 ms / 242 tokens ( 105.37 ms per token, 9.49 tokens per second) 42.01.674.980 I slot print_timing: id 0 | task 15083 | total time = 32933.23 ms / 823 tokens 42.01.674.981 I slot print_timing: id 0 | task 15083 | graphs reused = 14440 42.01.674.981 I slot print_timing: id 0 | task 15083 | graph reallocs = 0 / 0 (same size) / (changed size) 42.01.675.021 I slot release: id 0 | task 15083 | stop processing: n_tokens = 854, truncated = 0 42.01.680.802 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 854, t_last = 93238972664 42.01.680.845 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1096.026 MiB) 42.01.706.810 I slot launch_slot_: id 0 | task 15329 | processing task, is_child = 0 42.06.444.010 I slot print_timing: id 0 | task 15329 | prompt processing, n_tokens = 741, progress = 0.81, t = 4.74 s / 156.42 tokens per second 42.10.468.439 I slot print_timing: id 0 | task 15329 | prompt processing, n_tokens = 921, progress = 1.00, t = 8.76 s / 105.12 tokens per second 42.23.315.816 I slot print_timing: id 0 | task 15329 | n_gen = 100, tg = 9.48 t/s, tg_3s = 9.57 t/s 42.26.378.579 I slot print_timing: id 0 | task 15329 | n_gen = 129, tg = 9.48 t/s, tg_3s = 9.47 t/s 42.29.440.870 I slot print_timing: id 0 | task 15329 | n_gen = 158, tg = 9.47 t/s, tg_3s = 9.47 t/s 42.32.501.096 I slot print_timing: id 0 | task 15329 | n_gen = 187, tg = 9.47 t/s, tg_3s = 9.48 t/s 42.35.560.162 I slot print_timing: id 0 | task 15329 | n_gen = 216, tg = 9.48 t/s, tg_3s = 9.48 t/s 42.37.881.203 I slot print_timing: id 0 | task 15329 | prompt eval time = 11162.75 ms / 925 tokens ( 12.07 ms per token, 82.86 tokens per second) 42.37.881.205 I slot print_timing: id 0 | task 15329 | eval time = 25011.63 ms / 238 tokens ( 105.53 ms per token, 9.48 tokens per second) 42.37.881.205 I slot print_timing: id 0 | task 15329 | total time = 36174.38 ms / 1163 tokens 42.37.881.206 I slot print_timing: id 0 | task 15329 | graphs reused = 14675 42.37.881.206 I slot print_timing: id 0 | task 15329 | graph reallocs = 0 / 0 (same size) / (changed size) 42.37.881.263 I slot release: id 0 | task 15329 | stop processing: n_tokens = 1194, truncated = 0 42.37.886.442 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1194, t_last = 93275178906 42.37.886.491 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1096.776 MiB) 42.37.941.359 I slot launch_slot_: id 0 | task 15571 | processing task, is_child = 0 42.42.293.694 I slot print_timing: id 0 | task 15571 | prompt processing, n_tokens = 743, progress = 0.85, t = 4.35 s / 170.71 tokens per second 42.46.656.800 I slot print_timing: id 0 | task 15571 | prompt processing, n_tokens = 881, progress = 1.00, t = 8.72 s / 101.09 tokens per second 42.59.131.716 I slot print_timing: id 0 | task 15571 | n_gen = 100, tg = 9.48 t/s, tg_3s = 9.58 t/s 43.02.206.843 I slot print_timing: id 0 | task 15571 | n_gen = 129, tg = 9.47 t/s, tg_3s = 9.43 t/s 43.05.266.483 I slot print_timing: id 0 | task 15571 | n_gen = 158, tg = 9.47 t/s, tg_3s = 9.48 t/s 43.08.326.087 I slot print_timing: id 0 | task 15571 | n_gen = 187, tg = 9.47 t/s, tg_3s = 9.48 t/s 43.11.386.543 I slot print_timing: id 0 | task 15571 | n_gen = 216, tg = 9.47 t/s, tg_3s = 9.48 t/s 43.14.446.934 I slot print_timing: id 0 | task 15571 | prompt eval time = 10750.78 ms / 885 tokens ( 12.15 ms per token, 82.32 tokens per second) 43.14.446.937 I slot print_timing: id 0 | task 15571 | eval time = 25754.78 ms / 245 tokens ( 105.55 ms per token, 9.47 tokens per second) 43.14.446.937 I slot print_timing: id 0 | task 15571 | total time = 36505.56 ms / 1130 tokens 43.14.446.938 I slot print_timing: id 0 | task 15571 | graphs reused = 14917 43.14.446.938 I slot print_timing: id 0 | task 15571 | graph reallocs = 0 / 0 (same size) / (changed size) 43.14.446.980 I slot release: id 0 | task 15571 | stop processing: n_tokens = 1161, truncated = 0 43.14.451.769 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1161, t_last = 93311744623 43.14.451.819 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1109.969 MiB) 43.14.504.923 I slot launch_slot_: id 0 | task 15820 | processing task, is_child = 0 43.18.856.168 I slot print_timing: id 0 | task 15820 | prompt processing, n_tokens = 388, progress = 0.99, t = 4.35 s / 89.17 tokens per second 43.29.892.561 I slot print_timing: id 0 | task 15820 | n_gen = 100, tg = 9.50 t/s, tg_3s = 9.59 t/s 43.32.942.016 I slot print_timing: id 0 | task 15820 | n_gen = 129, tg = 9.50 t/s, tg_3s = 9.51 t/s 43.35.993.158 I slot print_timing: id 0 | task 15820 | n_gen = 158, tg = 9.50 t/s, tg_3s = 9.50 t/s 43.39.043.848 I slot print_timing: id 0 | task 15820 | n_gen = 187, tg = 9.50 t/s, tg_3s = 9.51 t/s 43.42.092.967 I slot print_timing: id 0 | task 15820 | n_gen = 216, tg = 9.50 t/s, tg_3s = 9.51 t/s 43.45.146.059 I slot print_timing: id 0 | task 15820 | n_gen = 245, tg = 9.50 t/s, tg_3s = 9.50 t/s 43.48.203.744 I slot print_timing: id 0 | task 15820 | n_gen = 274, tg = 9.50 t/s, tg_3s = 9.48 t/s 43.51.262.216 I slot print_timing: id 0 | task 15820 | n_gen = 303, tg = 9.50 t/s, tg_3s = 9.48 t/s 43.52.106.489 I slot print_timing: id 0 | task 15820 | prompt eval time = 4961.62 ms / 392 tokens ( 12.66 ms per token, 79.01 tokens per second) 43.52.106.494 I slot print_timing: id 0 | task 15820 | eval time = 32639.94 ms / 311 tokens ( 105.29 ms per token, 9.50 tokens per second) 43.52.106.495 I slot print_timing: id 0 | task 15820 | total time = 37601.56 ms / 703 tokens 43.52.106.496 I slot print_timing: id 0 | task 15820 | graphs reused = 15225 43.52.106.496 I slot print_timing: id 0 | task 15820 | graph reallocs = 0 / 0 (same size) / (changed size) 43.52.106.523 I slot release: id 0 | task 15820 | stop processing: n_tokens = 734, truncated = 0 43.52.111.104 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 734, t_last = 93349404166 43.52.111.140 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1117.159 MiB) 43.52.133.606 I slot launch_slot_: id 0 | task 16134 | processing task, is_child = 0 43.55.792.626 I slot print_timing: id 0 | task 16134 | prompt processing, n_tokens = 327, progress = 0.99, t = 3.66 s / 89.37 tokens per second 44.06.741.241 I slot print_timing: id 0 | task 16134 | n_gen = 100, tg = 9.47 t/s, tg_3s = 9.57 t/s 44.08.111.857 I slot print_timing: id 0 | task 16134 | prompt eval time = 4156.20 ms / 331 tokens ( 12.56 ms per token, 79.64 tokens per second) 44.08.111.863 I slot print_timing: id 0 | task 16134 | eval time = 11822.04 ms / 113 tokens ( 105.55 ms per token, 9.47 tokens per second) 44.08.111.863 I slot print_timing: id 0 | task 16134 | total time = 15978.24 ms / 444 tokens 44.08.111.864 I slot print_timing: id 0 | task 16134 | graphs reused = 15336 44.08.111.864 I slot print_timing: id 0 | task 16134 | graph reallocs = 0 / 0 (same size) / (changed size) 44.08.111.888 I slot release: id 0 | task 16134 | stop processing: n_tokens = 475, truncated = 0 44.08.116.079 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 475, t_last = 93365409531 44.08.116.111 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1097.777 MiB) 44.08.137.946 I slot launch_slot_: id 0 | task 16250 | processing task, is_child = 0 44.12.147.228 I slot print_timing: id 0 | task 16250 | prompt processing, n_tokens = 353, progress = 0.99, t = 4.01 s / 88.05 tokens per second 44.18.458.326 I slot print_timing: id 0 | task 16250 | prompt eval time = 4621.49 ms / 357 tokens ( 12.95 ms per token, 77.25 tokens per second) 44.18.458.331 I slot print_timing: id 0 | task 16250 | eval time = 5698.88 ms / 55 tokens ( 105.53 ms per token, 9.48 tokens per second) 44.18.458.332 I slot print_timing: id 0 | task 16250 | total time = 10320.37 ms / 412 tokens 44.18.458.332 I slot print_timing: id 0 | task 16250 | graphs reused = 15389 44.18.458.333 I slot print_timing: id 0 | task 16250 | graph reallocs = 0 / 0 (same size) / (changed size) 44.18.458.360 I slot release: id 0 | task 16250 | stop processing: n_tokens = 443, truncated = 0 44.18.462.645 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 443, t_last = 93375756003 44.18.462.672 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1108.218 MiB) 44.18.489.669 I slot launch_slot_: id 0 | task 16308 | processing task, is_child = 0 44.22.131.128 I slot print_timing: id 0 | task 16308 | prompt processing, n_tokens = 311, progress = 0.99, t = 3.64 s / 85.41 tokens per second 44.33.069.854 I slot print_timing: id 0 | task 16308 | n_gen = 100, tg = 9.48 t/s, tg_3s = 9.58 t/s 44.33.176.501 I slot print_timing: id 0 | task 16308 | prompt eval time = 4141.92 ms / 315 tokens ( 13.15 ms per token, 76.05 tokens per second) 44.33.176.503 I slot print_timing: id 0 | task 16308 | eval time = 10544.90 ms / 101 tokens ( 105.45 ms per token, 9.48 tokens per second) 44.33.176.504 I slot print_timing: id 0 | task 16308 | total time = 14686.82 ms / 416 tokens 44.33.176.504 I slot print_timing: id 0 | task 16308 | graphs reused = 15488 44.33.176.505 I slot print_timing: id 0 | task 16308 | graph reallocs = 0 / 0 (same size) / (changed size) 44.33.176.531 I slot release: id 0 | task 16308 | stop processing: n_tokens = 447, truncated = 0 44.33.180.867 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 93390474174 44.33.203.949 I slot launch_slot_: id 0 | task 16412 | processing task, is_child = 0 44.37.225.952 I slot print_timing: id 0 | task 16412 | prompt processing, n_tokens = 374, progress = 0.99, t = 4.02 s / 92.99 tokens per second 44.44.380.658 I slot print_timing: id 0 | task 16412 | prompt eval time = 4969.52 ms / 378 tokens ( 13.15 ms per token, 76.06 tokens per second) 44.44.380.662 I slot print_timing: id 0 | task 16412 | eval time = 6207.18 ms / 60 tokens ( 105.21 ms per token, 9.51 tokens per second) 44.44.380.662 I slot print_timing: id 0 | task 16412 | total time = 11176.70 ms / 438 tokens 44.44.380.662 I slot print_timing: id 0 | task 16412 | graphs reused = 15546 44.44.380.663 I slot print_timing: id 0 | task 16412 | graph reallocs = 0 / 0 (same size) / (changed size) 44.44.380.688 I slot release: id 0 | task 16412 | stop processing: n_tokens = 469, truncated = 0 44.44.384.608 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 469, t_last = 93401678331 44.44.384.639 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 944.899 MiB) 44.44.406.311 I slot launch_slot_: id 0 | task 16475 | processing task, is_child = 0 44.47.710.466 I slot print_timing: id 0 | task 16475 | prompt processing, n_tokens = 291, progress = 0.99, t = 3.30 s / 88.07 tokens per second 44.51.159.407 I slot print_timing: id 0 | task 16475 | prompt eval time = 3912.78 ms / 295 tokens ( 13.26 ms per token, 75.39 tokens per second) 44.51.159.409 I slot print_timing: id 0 | task 16475 | eval time = 2840.30 ms / 28 tokens ( 105.20 ms per token, 9.51 tokens per second) 44.51.159.410 I slot print_timing: id 0 | task 16475 | total time = 6753.08 ms / 323 tokens 44.51.159.410 I slot print_timing: id 0 | task 16475 | graphs reused = 15572 44.51.159.411 I slot print_timing: id 0 | task 16475 | graph reallocs = 0 / 0 (same size) / (changed size) 44.51.159.433 I slot release: id 0 | task 16475 | stop processing: n_tokens = 354, truncated = 0 44.51.163.869 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 354, t_last = 93408457076 44.51.163.894 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1100.778 MiB) 44.51.190.166 I slot launch_slot_: id 0 | task 16506 | processing task, is_child = 0 44.54.854.163 I slot print_timing: id 0 | task 16506 | prompt processing, n_tokens = 333, progress = 0.99, t = 3.66 s / 90.88 tokens per second 45.00.090.712 I slot print_timing: id 0 | task 16506 | prompt eval time = 4162.43 ms / 337 tokens ( 12.35 ms per token, 80.96 tokens per second) 45.00.090.717 I slot print_timing: id 0 | task 16506 | eval time = 4738.10 ms / 46 tokens ( 105.29 ms per token, 9.50 tokens per second) 45.00.090.718 I slot print_timing: id 0 | task 16506 | total time = 8900.53 ms / 383 tokens 45.00.090.718 I slot print_timing: id 0 | task 16506 | graphs reused = 15616 45.00.090.719 I slot print_timing: id 0 | task 16506 | graph reallocs = 0 / 0 (same size) / (changed size) 45.00.090.744 I slot release: id 0 | task 16506 | stop processing: n_tokens = 414, truncated = 0 45.00.095.158 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 93417388387 45.00.095.186 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1122.036 MiB) 45.00.118.854 I slot launch_slot_: id 0 | task 16555 | processing task, is_child = 0 45.03.767.285 I slot print_timing: id 0 | task 16555 | prompt processing, n_tokens = 321, progress = 0.99, t = 3.65 s / 87.98 tokens per second 45.14.812.993 I slot print_timing: id 0 | task 16555 | n_gen = 100, tg = 9.49 t/s, tg_3s = 9.58 t/s 45.17.871.562 I slot print_timing: id 0 | task 16555 | n_gen = 129, tg = 9.49 t/s, tg_3s = 9.48 t/s 45.20.190.979 I slot print_timing: id 0 | task 16555 | prompt eval time = 4260.32 ms / 325 tokens ( 13.11 ms per token, 76.29 tokens per second) 45.20.190.985 I slot print_timing: id 0 | task 16555 | eval time = 15811.80 ms / 151 tokens ( 105.41 ms per token, 9.49 tokens per second) 45.20.190.986 I slot print_timing: id 0 | task 16555 | total time = 20072.11 ms / 476 tokens 45.20.190.986 I slot print_timing: id 0 | task 16555 | graphs reused = 15765 45.20.190.986 I slot print_timing: id 0 | task 16555 | graph reallocs = 0 / 0 (same size) / (changed size) 45.20.191.015 I slot release: id 0 | task 16555 | stop processing: n_tokens = 507, truncated = 0 45.20.195.616 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.108 (> 0.100 thold), f_keep = 0.063 45.20.195.650 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1119.972 MiB) 45.20.218.265 I slot launch_slot_: id 0 | task 16709 | processing task, is_child = 0 45.34.186.896 I slot print_timing: id 0 | task 16709 | n_gen = 100, tg = 9.49 t/s, tg_3s = 9.59 t/s 45.37.241.209 I slot print_timing: id 0 | task 16709 | n_gen = 129, tg = 9.49 t/s, tg_3s = 9.49 t/s 45.40.292.948 I slot print_timing: id 0 | task 16709 | n_gen = 158, tg = 9.49 t/s, tg_3s = 9.50 t/s 45.43.343.280 I slot print_timing: id 0 | task 16709 | n_gen = 187, tg = 9.50 t/s, tg_3s = 9.51 t/s 45.46.400.914 I slot print_timing: id 0 | task 16709 | n_gen = 216, tg = 9.49 t/s, tg_3s = 9.48 t/s 45.49.458.692 I slot print_timing: id 0 | task 16709 | n_gen = 245, tg = 9.49 t/s, tg_3s = 9.48 t/s 45.52.509.282 I slot print_timing: id 0 | task 16709 | n_gen = 274, tg = 9.49 t/s, tg_3s = 9.51 t/s 45.55.560.572 I slot print_timing: id 0 | task 16709 | n_gen = 303, tg = 9.50 t/s, tg_3s = 9.50 t/s 45.56.401.924 I slot print_timing: id 0 | task 16709 | prompt eval time = 3538.66 ms / 264 tokens ( 13.40 ms per token, 74.60 tokens per second) 45.56.401.930 I slot print_timing: id 0 | task 16709 | eval time = 32644.98 ms / 311 tokens ( 105.31 ms per token, 9.50 tokens per second) 45.56.401.930 I slot print_timing: id 0 | task 16709 | total time = 36183.65 ms / 575 tokens 45.56.401.931 I slot print_timing: id 0 | task 16709 | graphs reused = 16073 45.56.401.931 I slot print_timing: id 0 | task 16709 | graph reallocs = 0 / 0 (same size) / (changed size) 45.56.401.964 I slot release: id 0 | task 16709 | stop processing: n_tokens = 606, truncated = 0 45.56.406.784 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 606, t_last = 93473699607 45.56.406.819 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 943.649 MiB) 45.56.428.622 I slot launch_slot_: id 0 | task 17023 | processing task, is_child = 0 46.00.079.917 I slot print_timing: id 0 | task 17023 | prompt processing, n_tokens = 327, progress = 0.99, t = 3.65 s / 89.56 tokens per second 46.08.500.875 I slot print_timing: id 0 | task 17023 | prompt eval time = 4260.62 ms / 331 tokens ( 12.87 ms per token, 77.69 tokens per second) 46.08.500.881 I slot print_timing: id 0 | task 17023 | eval time = 7811.63 ms / 75 tokens ( 105.56 ms per token, 9.47 tokens per second) 46.08.500.881 I slot print_timing: id 0 | task 17023 | total time = 12072.24 ms / 406 tokens 46.08.500.882 I slot print_timing: id 0 | task 17023 | graphs reused = 16146 46.08.500.882 I slot print_timing: id 0 | task 17023 | graph reallocs = 0 / 0 (same size) / (changed size) 46.08.500.908 I slot release: id 0 | task 17023 | stop processing: n_tokens = 437, truncated = 0 46.08.505.573 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 93485798551 46.08.505.605 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 927.456 MiB) 46.08.528.237 I slot launch_slot_: id 0 | task 17101 | processing task, is_child = 0 46.12.186.872 I slot print_timing: id 0 | task 17101 | prompt processing, n_tokens = 329, progress = 0.99, t = 3.66 s / 89.92 tokens per second 46.23.226.433 I slot print_timing: id 0 | task 17101 | n_gen = 100, tg = 9.49 t/s, tg_3s = 9.59 t/s 46.24.494.242 I slot print_timing: id 0 | task 17101 | prompt eval time = 4266.16 ms / 333 tokens ( 12.81 ms per token, 78.06 tokens per second) 46.24.494.244 I slot print_timing: id 0 | task 17101 | eval time = 11699.83 ms / 112 tokens ( 105.40 ms per token, 9.49 tokens per second) 46.24.494.245 I slot print_timing: id 0 | task 17101 | total time = 15965.99 ms / 445 tokens 46.24.494.245 I slot print_timing: id 0 | task 17101 | graphs reused = 16256 46.24.494.246 I slot print_timing: id 0 | task 17101 | graph reallocs = 0 / 0 (same size) / (changed size) 46.24.494.270 I slot release: id 0 | task 17101 | stop processing: n_tokens = 476, truncated = 0 46.24.498.423 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 476, t_last = 93501791913 46.24.498.455 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 925.455 MiB) 46.24.521.200 I slot launch_slot_: id 0 | task 17216 | processing task, is_child = 0 46.28.169.301 I slot print_timing: id 0 | task 17216 | prompt processing, n_tokens = 342, progress = 0.99, t = 3.65 s / 93.75 tokens per second 46.34.591.099 I slot print_timing: id 0 | task 17216 | prompt eval time = 4597.08 ms / 346 tokens ( 13.29 ms per token, 75.27 tokens per second) 46.34.591.104 I slot print_timing: id 0 | task 17216 | eval time = 5472.81 ms / 53 tokens ( 105.25 ms per token, 9.50 tokens per second) 46.34.591.105 I slot print_timing: id 0 | task 17216 | total time = 10069.89 ms / 399 tokens 46.34.591.105 I slot print_timing: id 0 | task 17216 | graphs reused = 16307 46.34.591.106 I slot print_timing: id 0 | task 17216 | graph reallocs = 0 / 0 (same size) / (changed size) 46.34.591.129 I slot release: id 0 | task 17216 | stop processing: n_tokens = 430, truncated = 0 46.34.595.636 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 430, t_last = 93511888772 46.34.595.670 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 925.705 MiB) 46.34.622.278 I slot launch_slot_: id 0 | task 17272 | processing task, is_child = 0 46.38.272.874 I slot print_timing: id 0 | task 17272 | prompt processing, n_tokens = 321, progress = 0.99, t = 3.65 s / 87.93 tokens per second 46.43.721.612 I slot print_timing: id 0 | task 17272 | prompt eval time = 4150.50 ms / 325 tokens ( 12.77 ms per token, 78.30 tokens per second) 46.43.721.618 I slot print_timing: id 0 | task 17272 | eval time = 4948.82 ms / 48 tokens ( 105.29 ms per token, 9.50 tokens per second) 46.43.721.619 I slot print_timing: id 0 | task 17272 | total time = 9099.32 ms / 373 tokens 46.43.721.619 I slot print_timing: id 0 | task 17272 | graphs reused = 16353 46.43.721.620 I slot print_timing: id 0 | task 17272 | graph reallocs = 0 / 0 (same size) / (changed size) 46.43.721.643 I slot release: id 0 | task 17272 | stop processing: n_tokens = 404, truncated = 0 46.43.725.933 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 404, t_last = 93521019286 46.43.725.958 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 927.080 MiB) 46.43.747.791 I slot launch_slot_: id 0 | task 17323 | processing task, is_child = 0 46.47.393.966 I slot print_timing: id 0 | task 17323 | prompt processing, n_tokens = 318, progress = 0.99, t = 3.65 s / 87.22 tokens per second 46.58.434.034 I slot print_timing: id 0 | task 17323 | n_gen = 100, tg = 9.49 t/s, tg_3s = 9.59 t/s 47.01.494.630 I slot print_timing: id 0 | task 17323 | n_gen = 129, tg = 9.49 t/s, tg_3s = 9.48 t/s 47.04.553.073 I slot print_timing: id 0 | task 17323 | n_gen = 158, tg = 9.49 t/s, tg_3s = 9.48 t/s 47.07.617.900 I slot print_timing: id 0 | task 17323 | n_gen = 187, tg = 9.48 t/s, tg_3s = 9.46 t/s 47.10.675.399 I slot print_timing: id 0 | task 17323 | n_gen = 216, tg = 9.48 t/s, tg_3s = 9.48 t/s 47.13.736.005 I slot print_timing: id 0 | task 17323 | n_gen = 245, tg = 9.48 t/s, tg_3s = 9.48 t/s 47.16.791.324 I slot print_timing: id 0 | task 17323 | n_gen = 274, tg = 9.48 t/s, tg_3s = 9.49 t/s 47.19.853.752 I slot print_timing: id 0 | task 17323 | n_gen = 303, tg = 9.48 t/s, tg_3s = 9.47 t/s 47.22.911.623 I slot print_timing: id 0 | task 17323 | n_gen = 332, tg = 9.48 t/s, tg_3s = 9.48 t/s 47.24.810.460 I slot print_timing: id 0 | task 17323 | prompt eval time = 4254.08 ms / 322 tokens ( 13.21 ms per token, 75.69 tokens per second) 47.24.810.465 I slot print_timing: id 0 | task 17323 | eval time = 36808.57 ms / 350 tokens ( 105.47 ms per token, 9.48 tokens per second) 47.24.810.465 I slot print_timing: id 0 | task 17323 | total time = 41062.65 ms / 672 tokens 47.24.810.466 I slot print_timing: id 0 | task 17323 | graphs reused = 16700 47.24.810.466 I slot print_timing: id 0 | task 17323 | graph reallocs = 0 / 0 (same size) / (changed size) 47.24.810.493 I slot release: id 0 | task 17323 | stop processing: n_tokens = 703, truncated = 0 47.24.815.149 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 703, t_last = 93562108136 47.24.815.183 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 919.890 MiB) 47.24.844.503 I slot launch_slot_: id 0 | task 17676 | processing task, is_child = 0 47.28.505.144 I slot print_timing: id 0 | task 17676 | prompt processing, n_tokens = 334, progress = 0.99, t = 3.66 s / 91.24 tokens per second 47.39.555.552 I slot print_timing: id 0 | task 17676 | n_gen = 100, tg = 9.48 t/s, tg_3s = 9.58 t/s 47.42.611.381 I slot print_timing: id 0 | task 17676 | n_gen = 129, tg = 9.48 t/s, tg_3s = 9.49 t/s 47.45.672.771 I slot print_timing: id 0 | task 17676 | n_gen = 158, tg = 9.48 t/s, tg_3s = 9.47 t/s 47.48.727.846 I slot print_timing: id 0 | task 17676 | n_gen = 187, tg = 9.48 t/s, tg_3s = 9.49 t/s 47.51.782.277 I slot print_timing: id 0 | task 17676 | n_gen = 216, tg = 9.49 t/s, tg_3s = 9.49 t/s 47.54.836.887 I slot print_timing: id 0 | task 17676 | n_gen = 245, tg = 9.49 t/s, tg_3s = 9.49 t/s 47.57.889.801 I slot print_timing: id 0 | task 17676 | n_gen = 274, tg = 9.49 t/s, tg_3s = 9.50 t/s 48.00.945.447 I slot print_timing: id 0 | task 17676 | n_gen = 303, tg = 9.49 t/s, tg_3s = 9.49 t/s 48.04.005.630 I slot print_timing: id 0 | task 17676 | n_gen = 332, tg = 9.49 t/s, tg_3s = 9.48 t/s 48.07.062.264 I slot print_timing: id 0 | task 17676 | n_gen = 361, tg = 9.49 t/s, tg_3s = 9.49 t/s 48.10.123.660 I slot print_timing: id 0 | task 17676 | n_gen = 390, tg = 9.49 t/s, tg_3s = 9.47 t/s 48.13.190.959 I slot print_timing: id 0 | task 17676 | n_gen = 419, tg = 9.48 t/s, tg_3s = 9.45 t/s 48.16.253.543 I slot print_timing: id 0 | task 17676 | n_gen = 448, tg = 9.48 t/s, tg_3s = 9.47 t/s 48.19.311.564 I slot print_timing: id 0 | task 17676 | n_gen = 477, tg = 9.48 t/s, tg_3s = 9.48 t/s 48.22.367.748 I slot print_timing: id 0 | task 17676 | n_gen = 506, tg = 9.48 t/s, tg_3s = 9.49 t/s 48.25.427.828 I slot print_timing: id 0 | task 17676 | n_gen = 535, tg = 9.48 t/s, tg_3s = 9.48 t/s 48.28.494.659 I slot print_timing: id 0 | task 17676 | n_gen = 564, tg = 9.48 t/s, tg_3s = 9.46 t/s 48.31.559.206 I slot print_timing: id 0 | task 17676 | n_gen = 593, tg = 9.48 t/s, tg_3s = 9.46 t/s 48.34.625.101 I slot print_timing: id 0 | task 17676 | n_gen = 622, tg = 9.48 t/s, tg_3s = 9.46 t/s 48.37.683.728 I slot print_timing: id 0 | task 17676 | n_gen = 651, tg = 9.48 t/s, tg_3s = 9.48 t/s 48.40.749.860 I slot print_timing: id 0 | task 17676 | n_gen = 680, tg = 9.48 t/s, tg_3s = 9.46 t/s 48.43.809.449 I slot print_timing: id 0 | task 17676 | n_gen = 709, tg = 9.48 t/s, tg_3s = 9.48 t/s 48.44.020.439 I slot print_timing: id 0 | task 17676 | prompt eval time = 4271.28 ms / 338 tokens ( 12.64 ms per token, 79.13 tokens per second) 48.44.020.445 I slot print_timing: id 0 | task 17676 | eval time = 74904.65 ms / 711 tokens ( 105.50 ms per token, 9.48 tokens per second) 48.44.020.446 I slot print_timing: id 0 | task 17676 | total time = 79175.93 ms / 1049 tokens 48.44.020.446 I slot print_timing: id 0 | task 17676 | graphs reused = 17406 48.44.020.447 I slot print_timing: id 0 | task 17676 | graph reallocs = 0 / 0 (same size) / (changed size) 48.44.020.472 I slot release: id 0 | task 17676 | stop processing: n_tokens = 1080, truncated = 0 48.44.025.548 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1080, t_last = 93641318115 48.44.025.614 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 923.642 MiB) 48.44.049.777 I slot launch_slot_: id 0 | task 18390 | processing task, is_child = 0 48.47.716.094 I slot print_timing: id 0 | task 18390 | prompt processing, n_tokens = 343, progress = 0.99, t = 3.67 s / 93.55 tokens per second 48.58.754.812 I slot print_timing: id 0 | task 18390 | n_gen = 100, tg = 9.49 t/s, tg_3s = 9.59 t/s 49.01.808.930 I slot print_timing: id 0 | task 18390 | n_gen = 129, tg = 9.49 t/s, tg_3s = 9.50 t/s 49.04.865.486 I slot print_timing: id 0 | task 18390 | n_gen = 158, tg = 9.49 t/s, tg_3s = 9.49 t/s 49.07.920.055 I slot print_timing: id 0 | task 18390 | n_gen = 187, tg = 9.49 t/s, tg_3s = 9.49 t/s 49.10.977.985 I slot print_timing: id 0 | task 18390 | n_gen = 216, tg = 9.49 t/s, tg_3s = 9.48 t/s 49.14.036.138 I slot print_timing: id 0 | task 18390 | n_gen = 245, tg = 9.49 t/s, tg_3s = 9.48 t/s 49.17.096.279 I slot print_timing: id 0 | task 18390 | n_gen = 274, tg = 9.49 t/s, tg_3s = 9.48 t/s 49.20.152.198 I slot print_timing: id 0 | task 18390 | n_gen = 303, tg = 9.49 t/s, tg_3s = 9.49 t/s 49.23.215.773 I slot print_timing: id 0 | task 18390 | n_gen = 332, tg = 9.49 t/s, tg_3s = 9.47 t/s 49.26.275.602 I slot print_timing: id 0 | task 18390 | n_gen = 361, tg = 9.49 t/s, tg_3s = 9.48 t/s 49.29.336.374 I slot print_timing: id 0 | task 18390 | n_gen = 390, tg = 9.49 t/s, tg_3s = 9.47 t/s 49.32.402.391 I slot print_timing: id 0 | task 18390 | n_gen = 419, tg = 9.48 t/s, tg_3s = 9.46 t/s 49.35.458.847 I slot print_timing: id 0 | task 18390 | n_gen = 448, tg = 9.48 t/s, tg_3s = 9.49 t/s 49.38.516.055 I slot print_timing: id 0 | task 18390 | n_gen = 477, tg = 9.48 t/s, tg_3s = 9.49 t/s 49.41.577.307 I slot print_timing: id 0 | task 18390 | n_gen = 506, tg = 9.48 t/s, tg_3s = 9.47 t/s 49.44.633.083 I slot print_timing: id 0 | task 18390 | n_gen = 535, tg = 9.48 t/s, tg_3s = 9.49 t/s 49.47.691.738 I slot print_timing: id 0 | task 18390 | n_gen = 564, tg = 9.48 t/s, tg_3s = 9.48 t/s 49.50.750.353 I slot print_timing: id 0 | task 18390 | n_gen = 593, tg = 9.48 t/s, tg_3s = 9.48 t/s 49.53.811.730 I slot print_timing: id 0 | task 18390 | n_gen = 622, tg = 9.48 t/s, tg_3s = 9.47 t/s 49.56.874.758 I slot print_timing: id 0 | task 18390 | n_gen = 651, tg = 9.48 t/s, tg_3s = 9.47 t/s 49.59.936.056 I slot print_timing: id 0 | task 18390 | n_gen = 680, tg = 9.48 t/s, tg_3s = 9.47 t/s 50.02.997.586 I slot print_timing: id 0 | task 18390 | n_gen = 709, tg = 9.48 t/s, tg_3s = 9.47 t/s 50.06.056.197 I slot print_timing: id 0 | task 18390 | n_gen = 738, tg = 9.48 t/s, tg_3s = 9.48 t/s 50.09.122.011 I slot print_timing: id 0 | task 18390 | n_gen = 767, tg = 9.48 t/s, tg_3s = 9.46 t/s 50.12.181.601 I slot print_timing: id 0 | task 18390 | n_gen = 796, tg = 9.48 t/s, tg_3s = 9.48 t/s 50.15.245.364 I slot print_timing: id 0 | task 18390 | n_gen = 825, tg = 9.48 t/s, tg_3s = 9.47 t/s 50.15.878.286 I slot print_timing: id 0 | task 18390 | prompt eval time = 4274.98 ms / 347 tokens ( 12.32 ms per token, 81.17 tokens per second) 50.15.878.291 I slot print_timing: id 0 | task 18390 | eval time = 87553.52 ms / 831 tokens ( 105.49 ms per token, 9.48 tokens per second) 50.15.878.292 I slot print_timing: id 0 | task 18390 | total time = 91828.50 ms / 1178 tokens 50.15.878.292 I slot print_timing: id 0 | task 18390 | graphs reused = 18232 50.15.878.293 I slot print_timing: id 0 | task 18390 | graph reallocs = 0 / 0 (same size) / (changed size) 50.15.878.316 I slot release: id 0 | task 18390 | stop processing: n_tokens = 1209, truncated = 0 50.15.883.292 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1209, t_last = 93733175959 50.15.883.354 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 929.456 MiB) 50.15.922.173 I slot launch_slot_: id 0 | task 19224 | processing task, is_child = 0 50.19.573.534 I slot print_timing: id 0 | task 19224 | prompt processing, n_tokens = 327, progress = 0.99, t = 3.65 s / 89.56 tokens per second 50.25.968.004 I slot print_timing: id 0 | task 19224 | prompt eval time = 4259.33 ms / 331 tokens ( 12.87 ms per token, 77.71 tokens per second) 50.25.968.010 I slot print_timing: id 0 | task 19224 | eval time = 5786.48 ms / 56 tokens ( 105.21 ms per token, 9.50 tokens per second) 50.25.968.011 I slot print_timing: id 0 | task 19224 | total time = 10045.82 ms / 387 tokens 50.25.968.011 I slot print_timing: id 0 | task 19224 | graphs reused = 18286 50.25.968.011 I slot print_timing: id 0 | task 19224 | graph reallocs = 0 / 0 (same size) / (changed size) 50.25.968.034 I slot release: id 0 | task 19224 | stop processing: n_tokens = 418, truncated = 0 50.25.972.178 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 418, t_last = 93743265677 50.25.972.203 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 935.646 MiB) 50.25.993.813 I slot launch_slot_: id 0 | task 19283 | processing task, is_child = 0 50.29.621.983 I slot print_timing: id 0 | task 19283 | prompt processing, n_tokens = 341, progress = 0.99, t = 3.63 s / 93.99 tokens per second 50.40.655.493 I slot print_timing: id 0 | task 19283 | n_gen = 100, tg = 9.50 t/s, tg_3s = 9.59 t/s 50.43.706.764 I slot print_timing: id 0 | task 19283 | n_gen = 129, tg = 9.50 t/s, tg_3s = 9.50 t/s 50.44.971.200 I slot print_timing: id 0 | task 19283 | prompt eval time = 4235.65 ms / 345 tokens ( 12.28 ms per token, 81.45 tokens per second) 50.44.971.203 I slot print_timing: id 0 | task 19283 | eval time = 14741.72 ms / 141 tokens ( 105.30 ms per token, 9.50 tokens per second) 50.44.971.204 I slot print_timing: id 0 | task 19283 | total time = 18977.37 ms / 486 tokens 50.44.971.204 I slot print_timing: id 0 | task 19283 | graphs reused = 18424 50.44.971.205 I slot print_timing: id 0 | task 19283 | graph reallocs = 0 / 0 (same size) / (changed size) 50.44.971.230 I slot release: id 0 | task 19283 | stop processing: n_tokens = 517, truncated = 0 50.44.975.734 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 517, t_last = 93762268873 50.44.975.764 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 925.080 MiB) 50.44.998.953 I slot launch_slot_: id 0 | task 19427 | processing task, is_child = 0 50.48.642.587 I slot print_timing: id 0 | task 19427 | prompt processing, n_tokens = 316, progress = 0.99, t = 3.64 s / 86.73 tokens per second 50.59.681.854 I slot print_timing: id 0 | task 19427 | n_gen = 100, tg = 9.49 t/s, tg_3s = 9.59 t/s 51.01.369.121 I slot print_timing: id 0 | task 19427 | prompt eval time = 4254.93 ms / 320 tokens ( 13.30 ms per token, 75.21 tokens per second) 51.01.369.124 I slot print_timing: id 0 | task 19427 | eval time = 12115.23 ms / 116 tokens ( 105.35 ms per token, 9.49 tokens per second) 51.01.369.124 I slot print_timing: id 0 | task 19427 | total time = 16370.16 ms / 436 tokens 51.01.369.125 I slot print_timing: id 0 | task 19427 | graphs reused = 18538 51.01.369.125 I slot print_timing: id 0 | task 19427 | graph reallocs = 0 / 0 (same size) / (changed size) 51.01.369.155 I slot release: id 0 | task 19427 | stop processing: n_tokens = 467, truncated = 0 51.01.373.933 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 467, t_last = 93778666798 51.01.373.966 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 927.518 MiB) 51.01.396.218 I slot launch_slot_: id 0 | task 19546 | processing task, is_child = 0 51.04.703.041 I slot print_timing: id 0 | task 19546 | prompt processing, n_tokens = 293, progress = 0.99, t = 3.31 s / 88.61 tokens per second 51.08.671.909 I slot print_timing: id 0 | task 19546 | prompt eval time = 3803.45 ms / 297 tokens ( 12.81 ms per token, 78.09 tokens per second) 51.08.671.915 I slot print_timing: id 0 | task 19546 | eval time = 3472.23 ms / 34 tokens ( 105.22 ms per token, 9.50 tokens per second) 51.08.671.915 I slot print_timing: id 0 | task 19546 | total time = 7275.68 ms / 331 tokens 51.08.671.915 I slot print_timing: id 0 | task 19546 | graphs reused = 18570 51.08.671.916 I slot print_timing: id 0 | task 19546 | graph reallocs = 0 / 0 (same size) / (changed size) 51.08.671.941 I slot release: id 0 | task 19546 | stop processing: n_tokens = 362, truncated = 0 51.08.676.506 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 362, t_last = 93785969584 51.08.676.533 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 924.642 MiB) 51.08.701.320 I slot launch_slot_: id 0 | task 19583 | processing task, is_child = 0 51.12.366.603 I slot print_timing: id 0 | task 19583 | prompt processing, n_tokens = 339, progress = 0.99, t = 3.67 s / 92.49 tokens per second 51.23.399.023 I slot print_timing: id 0 | task 19583 | n_gen = 100, tg = 9.50 t/s, tg_3s = 9.59 t/s 51.26.451.016 I slot print_timing: id 0 | task 19583 | n_gen = 129, tg = 9.50 t/s, tg_3s = 9.50 t/s 51.29.507.726 I slot print_timing: id 0 | task 19583 | n_gen = 158, tg = 9.50 t/s, tg_3s = 9.49 t/s 51.32.561.994 I slot print_timing: id 0 | task 19583 | n_gen = 187, tg = 9.50 t/s, tg_3s = 9.49 t/s 51.35.621.186 I slot print_timing: id 0 | task 19583 | n_gen = 216, tg = 9.49 t/s, tg_3s = 9.48 t/s 51.38.680.561 I slot print_timing: id 0 | task 19583 | n_gen = 245, tg = 9.49 t/s, tg_3s = 9.48 t/s 51.41.737.329 I slot print_timing: id 0 | task 19583 | n_gen = 274, tg = 9.49 t/s, tg_3s = 9.49 t/s 51.42.686.634 I slot print_timing: id 0 | task 19583 | prompt eval time = 4272.74 ms / 343 tokens ( 12.46 ms per token, 80.28 tokens per second) 51.42.686.639 I slot print_timing: id 0 | task 19583 | eval time = 29712.56 ms / 283 tokens ( 105.36 ms per token, 9.49 tokens per second) 51.42.686.639 I slot print_timing: id 0 | task 19583 | total time = 33985.30 ms / 626 tokens 51.42.686.640 I slot print_timing: id 0 | task 19583 | graphs reused = 18850 51.42.686.640 I slot print_timing: id 0 | task 19583 | graph reallocs = 0 / 0 (same size) / (changed size) 51.42.686.665 I slot release: id 0 | task 19583 | stop processing: n_tokens = 657, truncated = 0 51.42.691.069 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 657, t_last = 93819984308 51.42.691.104 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 923.016 MiB) 51.42.713.846 I slot launch_slot_: id 0 | task 19869 | processing task, is_child = 0 51.46.749.248 I slot print_timing: id 0 | task 19869 | prompt processing, n_tokens = 367, progress = 0.99, t = 4.04 s / 90.95 tokens per second 51.57.786.695 I slot print_timing: id 0 | task 19869 | n_gen = 100, tg = 9.49 t/s, tg_3s = 9.59 t/s 52.00.843.347 I slot print_timing: id 0 | task 19869 | n_gen = 129, tg = 9.49 t/s, tg_3s = 9.49 t/s 52.03.896.274 I slot print_timing: id 0 | task 19869 | n_gen = 158, tg = 9.49 t/s, tg_3s = 9.50 t/s 52.06.950.228 I slot print_timing: id 0 | task 19869 | n_gen = 187, tg = 9.49 t/s, tg_3s = 9.50 t/s 52.08.323.090 I slot print_timing: id 0 | task 19869 | prompt eval time = 4645.56 ms / 371 tokens ( 12.52 ms per token, 79.86 tokens per second) 52.08.323.093 I slot print_timing: id 0 | task 19869 | eval time = 20963.67 ms / 200 tokens ( 105.35 ms per token, 9.49 tokens per second) 52.08.323.093 I slot print_timing: id 0 | task 19869 | total time = 25609.23 ms / 571 tokens 52.08.323.093 I slot print_timing: id 0 | task 19869 | graphs reused = 19047 52.08.323.094 I slot print_timing: id 0 | task 19869 | graph reallocs = 0 / 0 (same size) / (changed size) 52.08.323.119 I slot release: id 0 | task 19869 | stop processing: n_tokens = 602, truncated = 0 52.08.327.784 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 602, t_last = 93845620762 52.08.327.821 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 941.711 MiB) 52.08.351.075 I slot launch_slot_: id 0 | task 20072 | processing task, is_child = 0 52.11.650.000 I slot print_timing: id 0 | task 20072 | prompt processing, n_tokens = 288, progress = 0.99, t = 3.30 s / 87.30 tokens per second 52.22.683.409 I slot print_timing: id 0 | task 20072 | n_gen = 100, tg = 9.50 t/s, tg_3s = 9.59 t/s 52.25.736.969 I slot print_timing: id 0 | task 20072 | n_gen = 129, tg = 9.50 t/s, tg_3s = 9.50 t/s 52.28.828.381 I slot print_timing: id 0 | task 20072 | n_gen = 158, tg = 9.48 t/s, tg_3s = 9.38 t/s 52.31.879.567 I slot print_timing: id 0 | task 20072 | n_gen = 187, tg = 9.48 t/s, tg_3s = 9.50 t/s 52.32.832.138 I slot print_timing: id 0 | task 20072 | prompt eval time = 3909.22 ms / 292 tokens ( 13.39 ms per token, 74.70 tokens per second) 52.32.832.143 I slot print_timing: id 0 | task 20072 | eval time = 20571.83 ms / 196 tokens ( 105.50 ms per token, 9.48 tokens per second) 52.32.832.144 I slot print_timing: id 0 | task 20072 | total time = 24481.05 ms / 488 tokens 52.32.832.144 I slot print_timing: id 0 | task 20072 | graphs reused = 19240 52.32.832.145 I slot print_timing: id 0 | task 20072 | graph reallocs = 0 / 0 (same size) / (changed size) 52.32.832.169 I slot release: id 0 | task 20072 | stop processing: n_tokens = 519, truncated = 0 52.32.837.166 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 519, t_last = 93870129812 52.32.837.207 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 965.282 MiB) 52.32.861.416 I slot launch_slot_: id 0 | task 20271 | processing task, is_child = 0 52.36.170.058 I slot print_timing: id 0 | task 20271 | prompt processing, n_tokens = 297, progress = 0.99, t = 3.31 s / 89.77 tokens per second 52.44.461.847 I slot print_timing: id 0 | task 20271 | prompt eval time = 3809.09 ms / 301 tokens ( 12.65 ms per token, 79.02 tokens per second) 52.44.461.853 I slot print_timing: id 0 | task 20271 | eval time = 7791.33 ms / 75 tokens ( 105.29 ms per token, 9.50 tokens per second) 52.44.461.854 I slot print_timing: id 0 | task 20271 | total time = 11600.42 ms / 376 tokens 52.44.461.854 I slot print_timing: id 0 | task 20271 | graphs reused = 19313 52.44.461.854 I slot print_timing: id 0 | task 20271 | graph reallocs = 0 / 0 (same size) / (changed size) 52.44.461.878 I slot release: id 0 | task 20271 | stop processing: n_tokens = 407, truncated = 0 52.44.466.625 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 407, t_last = 93881759521 52.44.466.658 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 973.347 MiB) 52.44.489.831 I slot launch_slot_: id 0 | task 20349 | processing task, is_child = 0 52.47.798.950 I slot print_timing: id 0 | task 20349 | prompt processing, n_tokens = 299, progress = 0.99, t = 3.31 s / 90.36 tokens per second 52.58.835.311 I slot print_timing: id 0 | task 20349 | n_gen = 100, tg = 9.49 t/s, tg_3s = 9.59 t/s 53.01.890.519 I slot print_timing: id 0 | task 20349 | n_gen = 129, tg = 9.49 t/s, tg_3s = 9.49 t/s 53.04.947.019 I slot print_timing: id 0 | task 20349 | n_gen = 158, tg = 9.49 t/s, tg_3s = 9.49 t/s 53.08.007.312 I slot print_timing: id 0 | task 20349 | n_gen = 187, tg = 9.49 t/s, tg_3s = 9.48 t/s 53.11.059.559 I slot print_timing: id 0 | task 20349 | n_gen = 216, tg = 9.49 t/s, tg_3s = 9.50 t/s 53.12.534.053 I slot print_timing: id 0 | task 20349 | prompt eval time = 3917.28 ms / 303 tokens ( 12.93 ms per token, 77.35 tokens per second) 53.12.534.058 I slot print_timing: id 0 | task 20349 | eval time = 24126.94 ms / 230 tokens ( 105.36 ms per token, 9.49 tokens per second) 53.12.534.058 I slot print_timing: id 0 | task 20349 | total time = 28044.21 ms / 533 tokens 53.12.534.059 I slot print_timing: id 0 | task 20349 | graphs reused = 19540 53.12.534.059 I slot print_timing: id 0 | task 20349 | graph reallocs = 0 / 0 (same size) / (changed size) 53.12.534.082 I slot release: id 0 | task 20349 | stop processing: n_tokens = 564, truncated = 0 53.12.538.176 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 564, t_last = 93909831725 53.12.538.206 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 923.892 MiB) 53.12.560.023 I slot launch_slot_: id 0 | task 20582 | processing task, is_child = 0 53.16.208.759 I slot print_timing: id 0 | task 20582 | prompt processing, n_tokens = 317, progress = 0.99, t = 3.65 s / 86.88 tokens per second 53.27.242.271 I slot print_timing: id 0 | task 20582 | n_gen = 100, tg = 9.50 t/s, tg_3s = 9.59 t/s 53.28.727.967 I slot print_timing: id 0 | task 20582 | prompt eval time = 4256.95 ms / 321 tokens ( 13.26 ms per token, 75.41 tokens per second) 53.28.727.973 I slot print_timing: id 0 | task 20582 | eval time = 11910.99 ms / 114 tokens ( 105.41 ms per token, 9.49 tokens per second) 53.28.727.974 I slot print_timing: id 0 | task 20582 | total time = 16167.94 ms / 435 tokens 53.28.727.974 I slot print_timing: id 0 | task 20582 | graphs reused = 19652 53.28.727.974 I slot print_timing: id 0 | task 20582 | graph reallocs = 0 / 0 (same size) / (changed size) 53.28.727.997 I slot release: id 0 | task 20582 | stop processing: n_tokens = 466, truncated = 0 53.28.732.520 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 466, t_last = 93926025640 53.28.732.549 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 930.081 MiB) 53.28.754.468 I slot launch_slot_: id 0 | task 20699 | processing task, is_child = 0 53.32.404.950 I slot print_timing: id 0 | task 20699 | prompt processing, n_tokens = 318, progress = 0.99, t = 3.65 s / 87.11 tokens per second 53.38.385.447 I slot print_timing: id 0 | task 20699 | prompt eval time = 4260.78 ms / 322 tokens ( 13.23 ms per token, 75.57 tokens per second) 53.38.385.453 I slot print_timing: id 0 | task 20699 | eval time = 5370.18 ms / 52 tokens ( 105.30 ms per token, 9.50 tokens per second) 53.38.385.453 I slot print_timing: id 0 | task 20699 | total time = 9630.97 ms / 374 tokens 53.38.385.454 I slot print_timing: id 0 | task 20699 | graphs reused = 19702 53.38.385.454 I slot print_timing: id 0 | task 20699 | graph reallocs = 0 / 0 (same size) / (changed size) 53.38.385.478 I slot release: id 0 | task 20699 | stop processing: n_tokens = 405, truncated = 0 53.38.389.949 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 405, t_last = 93935683122 53.38.389.984 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 926.955 MiB) 53.38.411.597 I slot launch_slot_: id 0 | task 20754 | processing task, is_child = 0 53.42.060.680 I slot print_timing: id 0 | task 20754 | prompt processing, n_tokens = 319, progress = 0.99, t = 3.65 s / 87.42 tokens per second 53.53.092.553 I slot print_timing: id 0 | task 20754 | n_gen = 100, tg = 9.50 t/s, tg_3s = 9.59 t/s 53.56.147.206 I slot print_timing: id 0 | task 20754 | n_gen = 129, tg = 9.50 t/s, tg_3s = 9.49 t/s 53.59.201.175 I slot print_timing: id 0 | task 20754 | n_gen = 158, tg = 9.50 t/s, tg_3s = 9.50 t/s 54.02.258.200 I slot print_timing: id 0 | task 20754 | n_gen = 187, tg = 9.50 t/s, tg_3s = 9.49 t/s 54.05.312.694 I slot print_timing: id 0 | task 20754 | n_gen = 216, tg = 9.50 t/s, tg_3s = 9.49 t/s 54.08.364.301 I slot print_timing: id 0 | task 20754 | n_gen = 245, tg = 9.50 t/s, tg_3s = 9.50 t/s 54.11.423.427 I slot print_timing: id 0 | task 20754 | n_gen = 274, tg = 9.49 t/s, tg_3s = 9.48 t/s 54.14.478.878 I slot print_timing: id 0 | task 20754 | n_gen = 303, tg = 9.49 t/s, tg_3s = 9.49 t/s 54.15.005.263 I slot print_timing: id 0 | task 20754 | prompt eval time = 4257.94 ms / 323 tokens ( 13.18 ms per token, 75.86 tokens per second) 54.15.005.269 I slot print_timing: id 0 | task 20754 | eval time = 32335.72 ms / 308 tokens ( 105.33 ms per token, 9.49 tokens per second) 54.15.005.269 I slot print_timing: id 0 | task 20754 | total time = 36593.66 ms / 631 tokens 54.15.005.270 I slot print_timing: id 0 | task 20754 | graphs reused = 20007 54.15.005.270 I slot print_timing: id 0 | task 20754 | graph reallocs = 0 / 0 (same size) / (changed size) 54.15.005.299 I slot release: id 0 | task 20754 | stop processing: n_tokens = 662, truncated = 0 54.15.010.783 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 662, t_last = 93972302942 54.15.010.830 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 920.390 MiB) 54.15.035.037 I slot launch_slot_: id 0 | task 21065 | processing task, is_child = 0 54.18.681.148 I slot print_timing: id 0 | task 21065 | prompt processing, n_tokens = 317, progress = 0.99, t = 3.65 s / 86.94 tokens per second 54.29.616.727 I slot print_timing: id 0 | task 21065 | n_gen = 100, tg = 9.49 t/s, tg_3s = 9.58 t/s 54.32.665.834 I slot print_timing: id 0 | task 21065 | n_gen = 129, tg = 9.49 t/s, tg_3s = 9.51 t/s 54.35.737.397 I slot print_timing: id 0 | task 21065 | n_gen = 158, tg = 9.48 t/s, tg_3s = 9.44 t/s 54.38.793.911 I slot print_timing: id 0 | task 21065 | n_gen = 187, tg = 9.48 t/s, tg_3s = 9.49 t/s 54.41.854.921 I slot print_timing: id 0 | task 21065 | n_gen = 216, tg = 9.48 t/s, tg_3s = 9.47 t/s 54.44.917.061 I slot print_timing: id 0 | task 21065 | n_gen = 245, tg = 9.48 t/s, tg_3s = 9.47 t/s 54.47.971.995 I slot print_timing: id 0 | task 21065 | n_gen = 274, tg = 9.48 t/s, tg_3s = 9.49 t/s 54.51.028.545 I slot print_timing: id 0 | task 21065 | n_gen = 303, tg = 9.48 t/s, tg_3s = 9.49 t/s 54.54.088.867 I slot print_timing: id 0 | task 21065 | n_gen = 332, tg = 9.48 t/s, tg_3s = 9.48 t/s 54.57.147.919 I slot print_timing: id 0 | task 21065 | n_gen = 361, tg = 9.48 t/s, tg_3s = 9.48 t/s 55.00.210.371 I slot print_timing: id 0 | task 21065 | n_gen = 390, tg = 9.48 t/s, tg_3s = 9.47 t/s 55.03.272.354 I slot print_timing: id 0 | task 21065 | n_gen = 419, tg = 9.48 t/s, tg_3s = 9.47 t/s 55.06.331.639 I slot print_timing: id 0 | task 21065 | n_gen = 448, tg = 9.48 t/s, tg_3s = 9.48 t/s 55.09.394.235 I slot print_timing: id 0 | task 21065 | n_gen = 477, tg = 9.48 t/s, tg_3s = 9.47 t/s 55.12.454.274 I slot print_timing: id 0 | task 21065 | n_gen = 506, tg = 9.48 t/s, tg_3s = 9.48 t/s 55.15.518.901 I slot print_timing: id 0 | task 21065 | n_gen = 535, tg = 9.48 t/s, tg_3s = 9.46 t/s 55.18.580.711 I slot print_timing: id 0 | task 21065 | n_gen = 564, tg = 9.48 t/s, tg_3s = 9.47 t/s 55.21.639.751 I slot print_timing: id 0 | task 21065 | n_gen = 593, tg = 9.48 t/s, tg_3s = 9.48 t/s 55.24.702.486 I slot print_timing: id 0 | task 21065 | n_gen = 622, tg = 9.48 t/s, tg_3s = 9.47 t/s 55.27.763.355 I slot print_timing: id 0 | task 21065 | n_gen = 651, tg = 9.48 t/s, tg_3s = 9.47 t/s 55.30.831.502 I slot print_timing: id 0 | task 21065 | n_gen = 680, tg = 9.48 t/s, tg_3s = 9.45 t/s 55.33.900.425 I slot print_timing: id 0 | task 21065 | n_gen = 709, tg = 9.48 t/s, tg_3s = 9.45 t/s 55.36.968.479 I slot print_timing: id 0 | task 21065 | n_gen = 738, tg = 9.47 t/s, tg_3s = 9.45 t/s 55.40.034.509 I slot print_timing: id 0 | task 21065 | n_gen = 767, tg = 9.47 t/s, tg_3s = 9.46 t/s 55.43.095.546 I slot print_timing: id 0 | task 21065 | n_gen = 796, tg = 9.47 t/s, tg_3s = 9.47 t/s 55.45.208.183 I slot print_timing: id 0 | task 21065 | prompt eval time = 4144.99 ms / 321 tokens ( 12.91 ms per token, 77.44 tokens per second) 55.45.208.189 I slot print_timing: id 0 | task 21065 | eval time = 86028.14 ms / 816 tokens ( 105.56 ms per token, 9.47 tokens per second) 55.45.208.190 I slot print_timing: id 0 | task 21065 | total time = 90173.13 ms / 1137 tokens 55.45.208.190 I slot print_timing: id 0 | task 21065 | graphs reused = 20818 55.45.208.191 I slot print_timing: id 0 | task 21065 | graph reallocs = 0 / 0 (same size) / (changed size) 55.45.208.215 I slot release: id 0 | task 21065 | stop processing: n_tokens = 1168, truncated = 0 55.45.213.666 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1168, t_last = 94062505858 55.45.213.718 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 938.835 MiB) 55.45.239.527 I slot launch_slot_: id 0 | task 21884 | processing task, is_child = 0 55.48.887.704 I slot print_timing: id 0 | task 21884 | prompt processing, n_tokens = 318, progress = 0.99, t = 3.65 s / 87.17 tokens per second 55.59.821.934 I slot print_timing: id 0 | task 21884 | n_gen = 100, tg = 9.48 t/s, tg_3s = 9.58 t/s 56.02.875.600 I slot print_timing: id 0 | task 21884 | n_gen = 129, tg = 9.49 t/s, tg_3s = 9.50 t/s 56.05.821.513 I slot print_timing: id 0 | task 21884 | prompt eval time = 4143.60 ms / 322 tokens ( 12.87 ms per token, 77.71 tokens per second) 56.05.821.519 I slot print_timing: id 0 | task 21884 | eval time = 16438.37 ms / 157 tokens ( 105.37 ms per token, 9.49 tokens per second) 56.05.821.519 I slot print_timing: id 0 | task 21884 | total time = 20581.97 ms / 479 tokens 56.05.821.520 I slot print_timing: id 0 | task 21884 | graphs reused = 20973 56.05.821.520 I slot print_timing: id 0 | task 21884 | graph reallocs = 0 / 0 (same size) / (changed size) 56.05.821.543 I slot release: id 0 | task 21884 | stop processing: n_tokens = 510, truncated = 0 56.05.825.474 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 510, t_last = 94083119186 56.05.825.502 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 935.396 MiB) 56.05.847.401 I slot launch_slot_: id 0 | task 22044 | processing task, is_child = 0 56.09.506.668 I slot print_timing: id 0 | task 22044 | prompt processing, n_tokens = 333, progress = 0.99, t = 3.66 s / 91.00 tokens per second 56.14.850.594 I slot print_timing: id 0 | task 22044 | prompt eval time = 4266.85 ms / 337 tokens ( 12.66 ms per token, 78.98 tokens per second) 56.14.850.596 I slot print_timing: id 0 | task 22044 | eval time = 4736.32 ms / 46 tokens ( 105.25 ms per token, 9.50 tokens per second) 56.14.850.596 I slot print_timing: id 0 | task 22044 | total time = 9003.18 ms / 383 tokens 56.14.850.597 I slot print_timing: id 0 | task 22044 | graphs reused = 21017 56.14.850.597 I slot print_timing: id 0 | task 22044 | graph reallocs = 0 / 0 (same size) / (changed size) 56.14.850.628 I slot release: id 0 | task 22044 | stop processing: n_tokens = 414, truncated = 0 56.14.854.809 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 94092148272 56.14.854.835 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 930.207 MiB) 56.14.876.625 I slot launch_slot_: id 0 | task 22093 | processing task, is_child = 0 56.18.526.418 I slot print_timing: id 0 | task 22093 | prompt processing, n_tokens = 321, progress = 0.99, t = 3.65 s / 87.95 tokens per second 56.23.976.331 I slot print_timing: id 0 | task 22093 | prompt eval time = 4260.07 ms / 325 tokens ( 13.11 ms per token, 76.29 tokens per second) 56.23.976.336 I slot print_timing: id 0 | task 22093 | eval time = 4839.62 ms / 47 tokens ( 105.21 ms per token, 9.50 tokens per second) 56.23.976.337 I slot print_timing: id 0 | task 22093 | total time = 9099.69 ms / 372 tokens 56.23.976.337 I slot print_timing: id 0 | task 22093 | graphs reused = 21062 56.23.976.338 I slot print_timing: id 0 | task 22093 | graph reallocs = 0 / 0 (same size) / (changed size) 56.23.976.361 I slot release: id 0 | task 22093 | stop processing: n_tokens = 403, truncated = 0 56.23.980.721 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 403, t_last = 94101274004 56.23.980.747 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 923.204 MiB) 56.24.002.061 I slot launch_slot_: id 0 | task 22143 | processing task, is_child = 0 56.27.655.307 I slot print_timing: id 0 | task 22143 | prompt processing, n_tokens = 327, progress = 0.99, t = 3.65 s / 89.51 tokens per second 56.38.691.171 I slot print_timing: id 0 | task 22143 | n_gen = 100, tg = 9.49 t/s, tg_3s = 9.59 t/s 56.41.743.210 I slot print_timing: id 0 | task 22143 | n_gen = 129, tg = 9.50 t/s, tg_3s = 9.50 t/s 56.44.800.929 I slot print_timing: id 0 | task 22143 | n_gen = 158, tg = 9.49 t/s, tg_3s = 9.48 t/s 56.46.168.450 I slot print_timing: id 0 | task 22143 | prompt eval time = 4262.04 ms / 331 tokens ( 12.88 ms per token, 77.66 tokens per second) 56.46.168.456 I slot print_timing: id 0 | task 22143 | eval time = 17904.34 ms / 171 tokens ( 105.32 ms per token, 9.49 tokens per second) 56.46.168.456 I slot print_timing: id 0 | task 22143 | total time = 22166.38 ms / 502 tokens 56.46.168.457 I slot print_timing: id 0 | task 22143 | graphs reused = 21230 56.46.168.457 I slot print_timing: id 0 | task 22143 | graph reallocs = 0 / 0 (same size) / (changed size) 56.46.168.483 I slot release: id 0 | task 22143 | stop processing: n_tokens = 533, truncated = 0 56.46.172.799 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 533, t_last = 94123466126 56.46.172.828 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 933.020 MiB) 56.46.194.441 I slot launch_slot_: id 0 | task 22317 | processing task, is_child = 0 56.49.859.879 I slot print_timing: id 0 | task 22317 | prompt processing, n_tokens = 332, progress = 0.99, t = 3.67 s / 90.58 tokens per second 57.00.776.386 I slot print_timing: id 0 | task 22317 | n_gen = 100, tg = 9.50 t/s, tg_3s = 9.60 t/s 57.03.298.949 I slot print_timing: id 0 | task 22317 | prompt eval time = 4159.92 ms / 336 tokens ( 12.38 ms per token, 80.77 tokens per second) 57.03.298.955 I slot print_timing: id 0 | task 22317 | eval time = 12944.58 ms / 124 tokens ( 105.24 ms per token, 9.50 tokens per second) 57.03.298.955 I slot print_timing: id 0 | task 22317 | total time = 17104.50 ms / 460 tokens 57.03.298.956 I slot print_timing: id 0 | task 22317 | graphs reused = 21352 57.03.298.956 I slot print_timing: id 0 | task 22317 | graph reallocs = 0 / 0 (same size) / (changed size) 57.03.298.980 I slot release: id 0 | task 22317 | stop processing: n_tokens = 491, truncated = 0 57.03.303.967 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 491, t_last = 94140596623 57.03.304.001 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 926.893 MiB) 57.03.327.198 I slot launch_slot_: id 0 | task 22444 | processing task, is_child = 0 57.07.336.069 I slot print_timing: id 0 | task 22444 | prompt processing, n_tokens = 345, progress = 0.99, t = 4.01 s / 86.06 tokens per second 57.11.000.641 I slot print_timing: id 0 | task 22444 | prompt eval time = 4619.67 ms / 349 tokens ( 13.24 ms per token, 75.55 tokens per second) 57.11.000.644 I slot print_timing: id 0 | task 22444 | eval time = 3053.76 ms / 30 tokens ( 105.30 ms per token, 9.50 tokens per second) 57.11.000.644 I slot print_timing: id 0 | task 22444 | total time = 7673.43 ms / 379 tokens 57.11.000.645 I slot print_timing: id 0 | task 22444 | graphs reused = 21380 57.11.000.645 I slot print_timing: id 0 | task 22444 | graph reallocs = 0 / 0 (same size) / (changed size) 57.11.000.669 I slot release: id 0 | task 22444 | stop processing: n_tokens = 410, truncated = 0 57.11.005.730 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 410, t_last = 94148298312 57.11.005.767 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 923.079 MiB) 57.11.028.745 I slot launch_slot_: id 0 | task 22477 | processing task, is_child = 0 57.14.688.904 I slot print_timing: id 0 | task 22477 | prompt processing, n_tokens = 332, progress = 0.99, t = 3.66 s / 90.71 tokens per second 57.25.610.051 I slot print_timing: id 0 | task 22477 | n_gen = 100, tg = 9.50 t/s, tg_3s = 9.59 t/s 57.28.662.038 I slot print_timing: id 0 | task 22477 | n_gen = 129, tg = 9.50 t/s, tg_3s = 9.50 t/s 57.31.716.095 I slot print_timing: id 0 | task 22477 | n_gen = 158, tg = 9.50 t/s, tg_3s = 9.50 t/s 57.34.772.356 I slot print_timing: id 0 | task 22477 | n_gen = 187, tg = 9.50 t/s, tg_3s = 9.49 t/s 57.37.839.779 I slot print_timing: id 0 | task 22477 | n_gen = 216, tg = 9.49 t/s, tg_3s = 9.45 t/s 57.40.894.993 I slot print_timing: id 0 | task 22477 | n_gen = 245, tg = 9.49 t/s, tg_3s = 9.49 t/s 57.43.952.925 I slot print_timing: id 0 | task 22477 | n_gen = 274, tg = 9.49 t/s, tg_3s = 9.48 t/s 57.47.016.265 I slot print_timing: id 0 | task 22477 | n_gen = 303, tg = 9.49 t/s, tg_3s = 9.47 t/s 57.50.074.159 I slot print_timing: id 0 | task 22477 | n_gen = 332, tg = 9.49 t/s, tg_3s = 9.48 t/s 57.53.130.505 I slot print_timing: id 0 | task 22477 | n_gen = 361, tg = 9.49 t/s, tg_3s = 9.49 t/s 57.56.200.536 I slot print_timing: id 0 | task 22477 | n_gen = 390, tg = 9.48 t/s, tg_3s = 9.45 t/s 57.59.262.313 I slot print_timing: id 0 | task 22477 | n_gen = 419, tg = 9.48 t/s, tg_3s = 9.47 t/s 58.02.326.482 I slot print_timing: id 0 | task 22477 | n_gen = 448, tg = 9.48 t/s, tg_3s = 9.46 t/s 58.05.389.570 I slot print_timing: id 0 | task 22477 | n_gen = 477, tg = 9.48 t/s, tg_3s = 9.47 t/s 58.08.451.324 I slot print_timing: id 0 | task 22477 | n_gen = 506, tg = 9.48 t/s, tg_3s = 9.47 t/s 58.11.516.738 I slot print_timing: id 0 | task 22477 | n_gen = 535, tg = 9.48 t/s, tg_3s = 9.46 t/s 58.14.574.883 I slot print_timing: id 0 | task 22477 | n_gen = 564, tg = 9.48 t/s, tg_3s = 9.48 t/s 58.17.636.301 I slot print_timing: id 0 | task 22477 | n_gen = 593, tg = 9.48 t/s, tg_3s = 9.47 t/s 58.20.698.415 I slot print_timing: id 0 | task 22477 | n_gen = 622, tg = 9.48 t/s, tg_3s = 9.47 t/s 58.23.759.539 I slot print_timing: id 0 | task 22477 | n_gen = 651, tg = 9.48 t/s, tg_3s = 9.47 t/s 58.26.822.368 I slot print_timing: id 0 | task 22477 | n_gen = 680, tg = 9.48 t/s, tg_3s = 9.47 t/s 58.29.893.822 I slot print_timing: id 0 | task 22477 | n_gen = 709, tg = 9.48 t/s, tg_3s = 9.44 t/s 58.32.958.189 I slot print_timing: id 0 | task 22477 | n_gen = 738, tg = 9.48 t/s, tg_3s = 9.46 t/s 58.36.020.031 I slot print_timing: id 0 | task 22477 | n_gen = 767, tg = 9.48 t/s, tg_3s = 9.47 t/s 58.39.087.097 I slot print_timing: id 0 | task 22477 | n_gen = 796, tg = 9.48 t/s, tg_3s = 9.46 t/s 58.42.149.683 I slot print_timing: id 0 | task 22477 | n_gen = 825, tg = 9.48 t/s, tg_3s = 9.47 t/s 58.45.218.714 I slot print_timing: id 0 | task 22477 | n_gen = 854, tg = 9.47 t/s, tg_3s = 9.45 t/s 58.48.280.164 I slot print_timing: id 0 | task 22477 | n_gen = 883, tg = 9.47 t/s, tg_3s = 9.47 t/s 58.51.342.662 I slot print_timing: id 0 | task 22477 | n_gen = 912, tg = 9.47 t/s, tg_3s = 9.47 t/s 58.54.412.906 I slot print_timing: id 0 | task 22477 | n_gen = 941, tg = 9.47 t/s, tg_3s = 9.45 t/s 58.57.476.932 I slot print_timing: id 0 | task 22477 | n_gen = 970, tg = 9.47 t/s, tg_3s = 9.46 t/s 59.00.549.099 I slot print_timing: id 0 | task 22477 | n_gen = 999, tg = 9.47 t/s, tg_3s = 9.44 t/s 59.03.197.894 I slot print_timing: id 0 | task 22477 | prompt eval time = 4157.10 ms / 336 tokens ( 12.37 ms per token, 80.83 tokens per second) 59.03.197.896 I slot print_timing: id 0 | task 22477 | eval time = 108012.04 ms / 1024 tokens ( 105.58 ms per token, 9.47 tokens per second) 59.03.197.897 I slot print_timing: id 0 | task 22477 | total time = 112169.13 ms / 1360 tokens 59.03.197.897 I slot print_timing: id 0 | task 22477 | graphs reused = 22398 59.03.197.898 I slot print_timing: id 0 | task 22477 | graph reallocs = 0 / 0 (same size) / (changed size) 59.03.197.921 I slot release: id 0 | task 22477 | stop processing: n_tokens = 1391, truncated = 0 59.03.203.177 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1391, t_last = 94260495565 59.03.203.243 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 939.147 MiB) 59.03.254.588 I slot launch_slot_: id 0 | task 23504 | processing task, is_child = 0 59.07.270.552 I slot print_timing: id 0 | task 23504 | prompt processing, n_tokens = 345, progress = 0.99, t = 4.02 s / 85.91 tokens per second 59.18.198.214 I slot print_timing: id 0 | task 23504 | n_gen = 100, tg = 9.49 t/s, tg_3s = 9.59 t/s 59.21.252.529 I slot print_timing: id 0 | task 23504 | n_gen = 129, tg = 9.49 t/s, tg_3s = 9.49 t/s 59.24.315.039 I slot print_timing: id 0 | task 23504 | n_gen = 158, tg = 9.49 t/s, tg_3s = 9.47 t/s 59.27.368.961 I slot print_timing: id 0 | task 23504 | n_gen = 187, tg = 9.49 t/s, tg_3s = 9.50 t/s 59.30.423.969 I slot print_timing: id 0 | task 23504 | n_gen = 216, tg = 9.49 t/s, tg_3s = 9.49 t/s 59.33.478.592 I slot print_timing: id 0 | task 23504 | n_gen = 245, tg = 9.49 t/s, tg_3s = 9.49 t/s 59.36.536.255 I slot print_timing: id 0 | task 23504 | n_gen = 274, tg = 9.49 t/s, tg_3s = 9.48 t/s 59.39.599.093 I slot print_timing: id 0 | task 23504 | n_gen = 303, tg = 9.49 t/s, tg_3s = 9.47 t/s 59.42.658.799 I slot print_timing: id 0 | task 23504 | n_gen = 332, tg = 9.49 t/s, tg_3s = 9.48 t/s 59.45.718.953 I slot print_timing: id 0 | task 23504 | n_gen = 361, tg = 9.49 t/s, tg_3s = 9.48 t/s 59.48.781.864 I slot print_timing: id 0 | task 23504 | n_gen = 390, tg = 9.48 t/s, tg_3s = 9.47 t/s 59.51.847.855 I slot print_timing: id 0 | task 23504 | n_gen = 419, tg = 9.48 t/s, tg_3s = 9.46 t/s 59.54.806.654 I slot print_timing: id 0 | task 23504 | prompt eval time = 4514.44 ms / 349 tokens ( 12.94 ms per token, 77.31 tokens per second) 59.54.806.656 I slot print_timing: id 0 | task 23504 | eval time = 47037.61 ms / 447 tokens ( 105.47 ms per token, 9.48 tokens per second) 59.54.806.657 I slot print_timing: id 0 | task 23504 | total time = 51552.05 ms / 796 tokens 59.54.806.657 I slot print_timing: id 0 | task 23504 | graphs reused = 22841 59.54.806.658 I slot print_timing: id 0 | task 23504 | graph reallocs = 0 / 0 (same size) / (changed size) 59.54.806.684 I slot release: id 0 | task 23504 | stop processing: n_tokens = 827, truncated = 0 59.54.811.033 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 827, t_last = 94312104327 59.54.811.071 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 970.784 MiB) 59.54.833.594 I slot launch_slot_: id 0 | task 23954 | processing task, is_child = 0 59.58.850.014 I slot print_timing: id 0 | task 23954 | prompt processing, n_tokens = 345, progress = 0.99, t = 4.02 s / 85.90 tokens per second 60.09.777.393 I slot print_timing: id 0 | task 23954 | n_gen = 100, tg = 9.49 t/s, tg_3s = 9.59 t/s 60.11.671.123 I slot print_timing: id 0 | task 23954 | prompt eval time = 4515.47 ms / 349 tokens ( 12.94 ms per token, 77.29 tokens per second) 60.11.671.126 I slot print_timing: id 0 | task 23954 | eval time = 12322.04 ms / 118 tokens ( 105.32 ms per token, 9.50 tokens per second) 60.11.671.126 I slot print_timing: id 0 | task 23954 | total time = 16837.51 ms / 467 tokens 60.11.671.127 I slot print_timing: id 0 | task 23954 | graphs reused = 22957 60.11.671.127 I slot print_timing: id 0 | task 23954 | graph reallocs = 0 / 0 (same size) / (changed size) 60.11.671.151 I slot release: id 0 | task 23954 | stop processing: n_tokens = 498, truncated = 0 60.11.676.219 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 498, t_last = 94328968794 60.11.676.256 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 929.644 MiB) 60.11.699.390 I slot launch_slot_: id 0 | task 24075 | processing task, is_child = 0 60.16.045.054 I slot print_timing: id 0 | task 24075 | prompt processing, n_tokens = 381, progress = 0.99, t = 4.35 s / 87.67 tokens per second 60.27.077.060 I slot print_timing: id 0 | task 24075 | n_gen = 100, tg = 9.50 t/s, tg_3s = 9.60 t/s 60.30.127.840 I slot print_timing: id 0 | task 24075 | n_gen = 129, tg = 9.50 t/s, tg_3s = 9.51 t/s 60.30.552.957 I slot print_timing: id 0 | task 24075 | prompt eval time = 4956.39 ms / 385 tokens ( 12.87 ms per token, 77.68 tokens per second) 60.30.552.963 I slot print_timing: id 0 | task 24075 | eval time = 13897.17 ms / 133 tokens ( 105.28 ms per token, 9.50 tokens per second) 60.30.552.963 I slot print_timing: id 0 | task 24075 | total time = 18853.56 ms / 518 tokens 60.30.552.964 I slot print_timing: id 0 | task 24075 | graphs reused = 23087 60.30.552.964 I slot print_timing: id 0 | task 24075 | graph reallocs = 0 / 0 (same size) / (changed size) 60.30.552.993 I slot release: id 0 | task 24075 | stop processing: n_tokens = 549, truncated = 0 60.30.557.439 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 94347850636 60.30.557.472 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 923.642 MiB) 60.30.580.096 I slot launch_slot_: id 0 | task 24211 | processing task, is_child = 0 60.34.228.651 I slot print_timing: id 0 | task 24211 | prompt processing, n_tokens = 324, progress = 0.99, t = 3.65 s / 88.80 tokens per second 60.40.719.106 I slot print_timing: id 0 | task 24211 | prompt eval time = 4256.54 ms / 328 tokens ( 12.98 ms per token, 77.06 tokens per second) 60.40.719.112 I slot print_timing: id 0 | task 24211 | eval time = 5882.46 ms / 57 tokens ( 105.04 ms per token, 9.52 tokens per second) 60.40.719.112 I slot print_timing: id 0 | task 24211 | total time = 10139.00 ms / 385 tokens 60.40.719.113 I slot print_timing: id 0 | task 24211 | graphs reused = 23142 60.40.719.113 I slot print_timing: id 0 | task 24211 | graph reallocs = 0 / 0 (same size) / (changed size) 60.40.719.136 I slot release: id 0 | task 24211 | stop processing: n_tokens = 416, truncated = 0 60.41.098.333 I srv operator(): operator(): cleaning up before exit...