$ /Users/minipro/quantdiff/llama.cpp/llama-b11770/llama-server -m /Users/minipro/quantdiff/models/campaign/fd4730dd8aad/Qwen3.8-27B-UD-Q2_K_XL.gguf --host 127.0.0.1 --port 8089 -c 4096 -np 1 -ngl 999 -fa on --jinja --seed 1234 --no-webui -a quant 0.00.045.232 I srv llama_server: initializing ... 0.00.045.240 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.045.534 I srv init_listene: The UI is disabled 0.00.045.536 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.045.612 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) 0.00.047.367 I srv load_model: loading model '/Users/minipro/quantdiff/models/campaign/fd4730dd8aad/Qwen3.8-27B-UD-Q2_K_XL.gguf' 0.00.550.649 W model has unused tensor blk.64.attn_norm.weight (size = 20480 bytes) -- ignoring 0.00.550.662 W model has unused tensor blk.64.post_attention_norm.weight (size = 20480 bytes) -- ignoring 0.00.550.671 W model has unused tensor blk.64.attn_q.weight (size = 51609600 bytes) -- ignoring 0.00.550.674 W model has unused tensor blk.64.attn_k.weight (size = 5570560 bytes) -- ignoring 0.00.550.676 W model has unused tensor blk.64.attn_v.weight (size = 5570560 bytes) -- ignoring 0.00.550.683 W model has unused tensor blk.64.attn_output.weight (size = 25804800 bytes) -- ignoring 0.00.550.686 W model has unused tensor blk.64.attn_q_norm.weight (size = 1024 bytes) -- ignoring 0.00.550.688 W model has unused tensor blk.64.attn_k_norm.weight (size = 1024 bytes) -- ignoring 0.00.550.690 W model has unused tensor blk.64.ffn_gate.weight (size = 73113600 bytes) -- ignoring 0.00.550.692 W model has unused tensor blk.64.ffn_down.weight (size = 73113600 bytes) -- ignoring 0.00.550.694 W model has unused tensor blk.64.ffn_up.weight (size = 73113600 bytes) -- ignoring 0.00.550.697 W model has unused tensor blk.64.nextn.eh_proj.weight (size = 43008000 bytes) -- ignoring 0.00.550.699 W model has unused tensor blk.64.nextn.enorm.weight (size = 20480 bytes) -- ignoring 0.00.550.702 W model has unused tensor blk.64.nextn.hnorm.weight (size = 20480 bytes) -- ignoring 0.00.550.708 W model has unused tensor blk.64.nextn.shared_head_norm.weight (size = 20480 bytes) -- ignoring 0.01.023.375 I cmn init: llama threadpool init, n_threads = 8 0.01.952.165 I srv load_model: initializing, n_slots = 1, n_ctx_slot = 4096, kv_unified = 'false' 0.01.956.506 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.01.956.534 I srv llama_server: model loaded 0.01.956.539 I srv llama_server: listening on http://127.0.0.1:8089 0.02.007.335 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.02.007.492 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.06.122.153 I slot print_timing: id 0 | task 0 | prompt processing, n_tokens = 364, progress = 0.99, t = 4.11 s / 88.46 tokens per second 0.11.921.877 I slot print_timing: id 0 | task 0 | prompt eval time = 4754.85 ms / 368 tokens ( 12.92 ms per token, 77.39 tokens per second) 0.11.921.882 I slot print_timing: id 0 | task 0 | eval time = 5159.51 ms / 53 tokens ( 99.22 ms per token, 10.08 tokens per second) 0.11.921.882 I slot print_timing: id 0 | task 0 | total time = 9914.36 ms / 421 tokens 0.11.921.883 I slot print_timing: id 0 | task 0 | graphs reused = 52 0.11.921.883 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.11.921.908 I slot release: id 0 | task 0 | stop processing: n_tokens = 420, truncated = 0 0.11.925.925 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 420, t_last = 75443396087 0.11.960.538 I slot launch_slot_: id 0 | task 56 | processing task, is_child = 0 0.15.552.883 I slot print_timing: id 0 | task 56 | prompt processing, n_tokens = 318, progress = 0.99, t = 3.59 s / 88.52 tokens per second 0.20.306.732 I slot print_timing: id 0 | task 56 | prompt eval time = 4200.12 ms / 322 tokens ( 13.04 ms per token, 76.66 tokens per second) 0.20.306.747 I slot print_timing: id 0 | task 56 | eval time = 4146.05 ms / 42 tokens ( 101.12 ms per token, 9.89 tokens per second) 0.20.306.750 I slot print_timing: id 0 | task 56 | total time = 8346.17 ms / 364 tokens 0.20.306.771 I slot print_timing: id 0 | task 56 | graphs reused = 92 0.20.306.773 I slot print_timing: id 0 | task 56 | graph reallocs = 0 / 0 (same size) / (changed size) 0.20.306.877 I slot release: id 0 | task 56 | stop processing: n_tokens = 363, truncated = 0 0.20.319.021 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 363, t_last = 75451781056 0.20.372.415 I slot launch_slot_: id 0 | task 101 | processing task, is_child = 0 0.24.337.738 I slot print_timing: id 0 | task 101 | prompt processing, n_tokens = 361, progress = 0.99, t = 3.97 s / 91.04 tokens per second 0.29.035.496 I slot print_timing: id 0 | task 101 | prompt eval time = 4578.04 ms / 365 tokens ( 12.54 ms per token, 79.73 tokens per second) 0.29.035.509 I slot print_timing: id 0 | task 101 | eval time = 4085.01 ms / 42 tokens ( 99.63 ms per token, 10.04 tokens per second) 0.29.035.511 I slot print_timing: id 0 | task 101 | total time = 8663.05 ms / 407 tokens 0.29.035.513 I slot print_timing: id 0 | task 101 | graphs reused = 132 0.29.035.522 I slot print_timing: id 0 | task 101 | graph reallocs = 0 / 0 (same size) / (changed size) 0.29.035.644 I slot release: id 0 | task 101 | stop processing: n_tokens = 406, truncated = 0 0.29.048.015 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 406, t_last = 75460509823 0.29.105.039 I slot launch_slot_: id 0 | task 146 | processing task, is_child = 0 0.33.395.340 I slot print_timing: id 0 | task 146 | prompt processing, n_tokens = 393, progress = 0.99, t = 4.29 s / 91.60 tokens per second 0.38.179.158 I slot print_timing: id 0 | task 146 | prompt eval time = 4906.71 ms / 397 tokens ( 12.36 ms per token, 80.91 tokens per second) 0.38.179.164 I slot print_timing: id 0 | task 146 | eval time = 4167.40 ms / 43 tokens ( 99.22 ms per token, 10.08 tokens per second) 0.38.179.165 I slot print_timing: id 0 | task 146 | total time = 9074.10 ms / 440 tokens 0.38.179.165 I slot print_timing: id 0 | task 146 | graphs reused = 173 0.38.179.166 I slot print_timing: id 0 | task 146 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.179.192 I slot release: id 0 | task 146 | stop processing: n_tokens = 439, truncated = 0 0.38.182.624 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 0.38.217.073 I slot launch_slot_: id 0 | task 192 | processing task, is_child = 0 0.42.182.118 I slot print_timing: id 0 | task 192 | prompt processing, n_tokens = 379, progress = 0.99, t = 3.97 s / 95.59 tokens per second 0.53.449.167 I slot print_timing: id 0 | task 192 | n_gen = 100, tg = 9.59 t/s, tg_3s = 9.69 t/s 0.56.548.990 I slot print_timing: id 0 | task 192 | n_gen = 129, tg = 9.54 t/s, tg_3s = 9.36 t/s 0.59.641.767 I slot print_timing: id 0 | task 192 | n_gen = 158, tg = 9.51 t/s, tg_3s = 9.38 t/s 1.02.647.919 I slot print_timing: id 0 | task 192 | n_gen = 186, tg = 9.48 t/s, tg_3s = 9.31 t/s 1.03.467.633 I slot print_timing: id 0 | task 192 | prompt eval time = 4910.02 ms / 383 tokens ( 12.82 ms per token, 78.00 tokens per second) 1.03.467.665 I slot print_timing: id 0 | task 192 | eval time = 20340.51 ms / 194 tokens ( 105.39 ms per token, 9.49 tokens per second) 1.03.467.668 I slot print_timing: id 0 | task 192 | total time = 25250.53 ms / 577 tokens 1.03.467.677 I slot print_timing: id 0 | task 192 | graphs reused = 364 1.03.467.679 I slot print_timing: id 0 | task 192 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.467.826 I slot release: id 0 | task 192 | stop processing: n_tokens = 576, truncated = 0 1.03.480.574 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 576, t_last = 75494942005 1.03.539.784 I slot launch_slot_: id 0 | task 389 | processing task, is_child = 0 1.07.518.039 I slot print_timing: id 0 | task 389 | prompt processing, n_tokens = 368, progress = 0.99, t = 3.98 s / 92.50 tokens per second 1.13.868.328 I slot print_timing: id 0 | task 389 | prompt eval time = 4588.24 ms / 372 tokens ( 12.33 ms per token, 81.08 tokens per second) 1.13.868.348 I slot print_timing: id 0 | task 389 | eval time = 5740.25 ms / 55 tokens ( 106.30 ms per token, 9.41 tokens per second) 1.13.868.350 I slot print_timing: id 0 | task 389 | total time = 10328.49 ms / 427 tokens 1.13.868.353 I slot print_timing: id 0 | task 389 | graphs reused = 417 1.13.868.355 I slot print_timing: id 0 | task 389 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.868.468 I slot release: id 0 | task 389 | stop processing: n_tokens = 426, truncated = 0 1.13.880.557 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 75505342647 1.13.939.131 I slot launch_slot_: id 0 | task 447 | processing task, is_child = 0 1.18.594.879 I slot print_timing: id 0 | task 447 | prompt processing, n_tokens = 418, progress = 0.99, t = 4.66 s / 89.78 tokens per second 1.24.866.668 I slot print_timing: id 0 | task 447 | prompt eval time = 5271.44 ms / 422 tokens ( 12.49 ms per token, 80.05 tokens per second) 1.24.866.674 I slot print_timing: id 0 | task 447 | eval time = 5656.07 ms / 55 tokens ( 104.74 ms per token, 9.55 tokens per second) 1.24.866.676 I slot print_timing: id 0 | task 447 | total time = 10927.51 ms / 477 tokens 1.24.866.680 I slot print_timing: id 0 | task 447 | graphs reused = 470 1.24.866.681 I slot print_timing: id 0 | task 447 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.866.762 I slot release: id 0 | task 447 | stop processing: n_tokens = 476, truncated = 0 1.24.878.653 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 476, t_last = 75516340941 1.24.938.002 I slot launch_slot_: id 0 | task 505 | processing task, is_child = 0 1.29.951.529 I slot print_timing: id 0 | task 505 | prompt processing, n_tokens = 466, progress = 0.99, t = 5.01 s / 92.95 tokens per second 1.40.865.088 I slot print_timing: id 0 | task 505 | n_gen = 100, tg = 9.93 t/s, tg_3s = 10.03 t/s 1.43.962.329 I slot print_timing: id 0 | task 505 | n_gen = 129, tg = 9.80 t/s, tg_3s = 9.36 t/s 1.47.054.085 I slot print_timing: id 0 | task 505 | n_gen = 158, tg = 9.72 t/s, tg_3s = 9.38 t/s 1.49.507.113 I slot print_timing: id 0 | task 505 | prompt eval time = 5957.69 ms / 470 tokens ( 12.68 ms per token, 78.89 tokens per second) 1.49.507.124 I slot print_timing: id 0 | task 505 | eval time = 18611.37 ms / 181 tokens ( 103.40 ms per token, 9.67 tokens per second) 1.49.507.127 I slot print_timing: id 0 | task 505 | total time = 24569.06 ms / 651 tokens 1.49.507.129 I slot print_timing: id 0 | task 505 | graphs reused = 648 1.49.507.131 I slot print_timing: id 0 | task 505 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.507.250 I slot release: id 0 | task 505 | stop processing: n_tokens = 650, truncated = 0 1.49.519.075 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 650, t_last = 75540981429 1.49.579.545 I slot launch_slot_: id 0 | task 689 | processing task, is_child = 0 1.53.190.804 I slot print_timing: id 0 | task 689 | prompt processing, n_tokens = 341, progress = 0.99, t = 3.61 s / 94.43 tokens per second 1.58.656.058 I slot print_timing: id 0 | task 689 | prompt eval time = 4224.97 ms / 345 tokens ( 12.25 ms per token, 81.66 tokens per second) 1.58.656.077 I slot print_timing: id 0 | task 689 | eval time = 4851.50 ms / 47 tokens ( 105.47 ms per token, 9.48 tokens per second) 1.58.656.080 I slot print_timing: id 0 | task 689 | total time = 9076.47 ms / 392 tokens 1.58.656.082 I slot print_timing: id 0 | task 689 | graphs reused = 693 1.58.656.084 I slot print_timing: id 0 | task 689 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.656.179 I slot release: id 0 | task 689 | stop processing: n_tokens = 391, truncated = 0 1.58.668.589 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 391, t_last = 75550130358 1.58.729.408 I slot launch_slot_: id 0 | task 739 | processing task, is_child = 0 2.02.690.804 I slot print_timing: id 0 | task 739 | prompt processing, n_tokens = 360, progress = 0.99, t = 3.96 s / 90.88 tokens per second 2.07.596.182 I slot print_timing: id 0 | task 739 | prompt eval time = 4897.46 ms / 364 tokens ( 13.45 ms per token, 74.32 tokens per second) 2.07.596.186 I slot print_timing: id 0 | task 739 | eval time = 3969.30 ms / 41 tokens ( 99.23 ms per token, 10.08 tokens per second) 2.07.596.186 I slot print_timing: id 0 | task 739 | total time = 8866.76 ms / 405 tokens 2.07.596.187 I slot print_timing: id 0 | task 739 | graphs reused = 732 2.07.596.187 I slot print_timing: id 0 | task 739 | graph reallocs = 0 / 0 (same size) / (changed size) 2.07.596.215 I slot release: id 0 | task 739 | stop processing: n_tokens = 404, truncated = 0 2.07.600.544 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 404, t_last = 75559070394 2.07.637.890 I slot launch_slot_: id 0 | task 783 | processing task, is_child = 0 2.11.574.315 I slot print_timing: id 0 | task 783 | prompt processing, n_tokens = 372, progress = 0.99, t = 3.94 s / 94.50 tokens per second 2.18.548.651 I slot print_timing: id 0 | task 783 | prompt eval time = 4544.79 ms / 376 tokens ( 12.09 ms per token, 82.73 tokens per second) 2.18.548.668 I slot print_timing: id 0 | task 783 | eval time = 6365.92 ms / 62 tokens ( 104.36 ms per token, 9.58 tokens per second) 2.18.548.673 I slot print_timing: id 0 | task 783 | total time = 10910.72 ms / 438 tokens 2.18.548.675 I slot print_timing: id 0 | task 783 | graphs reused = 792 2.18.548.677 I slot print_timing: id 0 | task 783 | graph reallocs = 0 / 0 (same size) / (changed size) 2.18.548.828 I slot release: id 0 | task 783 | stop processing: n_tokens = 437, truncated = 0 2.18.561.943 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 75570023007 2.18.622.543 I slot launch_slot_: id 0 | task 848 | processing task, is_child = 0 2.22.931.616 I slot print_timing: id 0 | task 848 | prompt processing, n_tokens = 408, progress = 0.99, t = 4.31 s / 94.68 tokens per second 2.28.325.315 I slot print_timing: id 0 | task 848 | prompt eval time = 4924.11 ms / 412 tokens ( 11.95 ms per token, 83.67 tokens per second) 2.28.325.327 I slot print_timing: id 0 | task 848 | eval time = 4778.61 ms / 47 tokens ( 103.88 ms per token, 9.63 tokens per second) 2.28.325.329 I slot print_timing: id 0 | task 848 | total time = 9702.72 ms / 459 tokens 2.28.325.332 I slot print_timing: id 0 | task 848 | graphs reused = 837 2.28.325.334 I slot print_timing: id 0 | task 848 | graph reallocs = 0 / 0 (same size) / (changed size) 2.28.325.453 I slot release: id 0 | task 848 | stop processing: n_tokens = 458, truncated = 0 2.28.338.049 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 75579799633 2.28.397.175 I slot launch_slot_: id 0 | task 898 | processing task, is_child = 0 2.32.360.181 I slot print_timing: id 0 | task 898 | prompt processing, n_tokens = 372, progress = 0.99, t = 3.96 s / 93.87 tokens per second 2.39.352.525 I slot print_timing: id 0 | task 898 | prompt eval time = 4905.11 ms / 376 tokens ( 13.05 ms per token, 76.65 tokens per second) 2.39.352.528 I slot print_timing: id 0 | task 898 | eval time = 6050.23 ms / 62 tokens ( 99.18 ms per token, 10.08 tokens per second) 2.39.352.528 I slot print_timing: id 0 | task 898 | total time = 10955.33 ms / 438 tokens 2.39.352.529 I slot print_timing: id 0 | task 898 | graphs reused = 897 2.39.352.529 I slot print_timing: id 0 | task 898 | graph reallocs = 0 / 0 (same size) / (changed size) 2.39.352.556 I slot release: id 0 | task 898 | stop processing: n_tokens = 437, truncated = 0 2.39.356.545 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 75590826735 2.39.393.243 I slot launch_slot_: id 0 | task 963 | processing task, is_child = 0 2.43.372.925 I slot print_timing: id 0 | task 963 | prompt processing, n_tokens = 374, progress = 0.99, t = 3.98 s / 93.98 tokens per second 2.49.043.982 I slot print_timing: id 0 | task 963 | prompt eval time = 4590.07 ms / 378 tokens ( 12.14 ms per token, 82.35 tokens per second) 2.49.043.984 I slot print_timing: id 0 | task 963 | eval time = 5060.65 ms / 52 tokens ( 99.23 ms per token, 10.08 tokens per second) 2.49.043.986 I slot print_timing: id 0 | task 963 | total time = 9650.73 ms / 430 tokens 2.49.043.986 I slot print_timing: id 0 | task 963 | graphs reused = 947 2.49.043.987 I slot print_timing: id 0 | task 963 | graph reallocs = 0 / 0 (same size) / (changed size) 2.49.044.015 I slot release: id 0 | task 963 | stop processing: n_tokens = 429, truncated = 0 2.49.047.890 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 429, t_last = 75600518194 2.49.084.478 I slot launch_slot_: id 0 | task 1018 | processing task, is_child = 0 2.53.056.240 I slot print_timing: id 0 | task 1018 | prompt processing, n_tokens = 363, progress = 0.99, t = 3.97 s / 91.40 tokens per second 2.59.676.963 I slot print_timing: id 0 | task 1018 | prompt eval time = 4581.33 ms / 367 tokens ( 12.48 ms per token, 80.11 tokens per second) 2.59.676.969 I slot print_timing: id 0 | task 1018 | eval time = 6011.14 ms / 58 tokens ( 105.46 ms per token, 9.48 tokens per second) 2.59.676.970 I slot print_timing: id 0 | task 1018 | total time = 10592.46 ms / 425 tokens 2.59.676.971 I slot print_timing: id 0 | task 1018 | graphs reused = 1003 2.59.676.972 I slot print_timing: id 0 | task 1018 | graph reallocs = 0 / 0 (same size) / (changed size) 2.59.677.026 I slot release: id 0 | task 1018 | stop processing: n_tokens = 424, truncated = 0 2.59.686.338 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 75611151205 2.59.745.607 I slot launch_slot_: id 0 | task 1079 | processing task, is_child = 0 3.03.354.492 I slot print_timing: id 0 | task 1079 | prompt processing, n_tokens = 343, progress = 0.99, t = 3.61 s / 95.04 tokens per second 3.09.243.028 I slot print_timing: id 0 | task 1079 | prompt eval time = 4224.24 ms / 347 tokens ( 12.17 ms per token, 82.15 tokens per second) 3.09.243.044 I slot print_timing: id 0 | task 1079 | eval time = 5273.15 ms / 51 tokens ( 105.46 ms per token, 9.48 tokens per second) 3.09.243.045 I slot print_timing: id 0 | task 1079 | total time = 9497.39 ms / 398 tokens 3.09.243.046 I slot print_timing: id 0 | task 1079 | graphs reused = 1052 3.09.243.053 I slot print_timing: id 0 | task 1079 | graph reallocs = 0 / 0 (same size) / (changed size) 3.09.243.106 I slot release: id 0 | task 1079 | stop processing: n_tokens = 397, truncated = 0 3.09.254.958 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 397, t_last = 75620717285 3.09.314.696 I slot launch_slot_: id 0 | task 1133 | processing task, is_child = 0 3.13.281.801 I slot print_timing: id 0 | task 1133 | prompt processing, n_tokens = 365, progress = 0.99, t = 3.97 s / 92.01 tokens per second 3.17.865.428 I slot print_timing: id 0 | task 1133 | prompt eval time = 4581.13 ms / 369 tokens ( 12.41 ms per token, 80.55 tokens per second) 3.17.865.431 I slot print_timing: id 0 | task 1133 | eval time = 3969.59 ms / 41 tokens ( 99.24 ms per token, 10.08 tokens per second) 3.17.865.431 I slot print_timing: id 0 | task 1133 | total time = 8550.72 ms / 410 tokens 3.17.865.432 I slot print_timing: id 0 | task 1133 | graphs reused = 1091 3.17.865.432 I slot print_timing: id 0 | task 1133 | graph reallocs = 0 / 0 (same size) / (changed size) 3.17.865.459 I slot release: id 0 | task 1133 | stop processing: n_tokens = 409, truncated = 0 3.17.868.904 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 75629339638 3.17.907.757 I slot launch_slot_: id 0 | task 1177 | processing task, is_child = 0 3.21.865.714 I slot print_timing: id 0 | task 1177 | prompt processing, n_tokens = 348, progress = 0.99, t = 3.96 s / 87.92 tokens per second 3.26.446.533 I slot print_timing: id 0 | task 1177 | prompt eval time = 4566.76 ms / 352 tokens ( 12.97 ms per token, 77.08 tokens per second) 3.26.446.538 I slot print_timing: id 0 | task 1177 | eval time = 3972.00 ms / 41 tokens ( 99.30 ms per token, 10.07 tokens per second) 3.26.446.539 I slot print_timing: id 0 | task 1177 | total time = 8538.76 ms / 393 tokens 3.26.446.539 I slot print_timing: id 0 | task 1177 | graphs reused = 1130 3.26.446.540 I slot print_timing: id 0 | task 1177 | graph reallocs = 0 / 0 (same size) / (changed size) 3.26.446.566 I slot release: id 0 | task 1177 | stop processing: n_tokens = 392, truncated = 0 3.26.450.467 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 392, t_last = 75637920745 3.26.450.492 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 475.138 MiB) 3.26.461.944 I slot launch_slot_: id 0 | task 1221 | processing task, is_child = 0 3.30.418.704 I slot print_timing: id 0 | task 1221 | prompt processing, n_tokens = 345, progress = 0.99, t = 3.96 s / 87.19 tokens per second 3.35.071.002 I slot print_timing: id 0 | task 1221 | prompt eval time = 4564.19 ms / 349 tokens ( 13.08 ms per token, 76.46 tokens per second) 3.35.071.016 I slot print_timing: id 0 | task 1221 | eval time = 4044.83 ms / 40 tokens ( 103.71 ms per token, 9.64 tokens per second) 3.35.071.018 I slot print_timing: id 0 | task 1221 | total time = 8609.02 ms / 389 tokens 3.35.071.021 I slot print_timing: id 0 | task 1221 | graphs reused = 1168 3.35.071.023 I slot print_timing: id 0 | task 1221 | graph reallocs = 0 / 0 (same size) / (changed size) 3.35.071.163 I slot release: id 0 | task 1221 | stop processing: n_tokens = 388, truncated = 0 3.35.083.818 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 388, t_last = 75646545342 3.35.083.885 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 471.575 MiB) 3.35.130.808 I slot launch_slot_: id 0 | task 1264 | processing task, is_child = 0 3.39.102.385 I slot print_timing: id 0 | task 1264 | prompt processing, n_tokens = 380, progress = 0.99, t = 3.97 s / 95.68 tokens per second 3.46.656.042 I slot print_timing: id 0 | task 1264 | prompt eval time = 4912.30 ms / 384 tokens ( 12.79 ms per token, 78.17 tokens per second) 3.46.656.051 I slot print_timing: id 0 | task 1264 | eval time = 6612.89 ms / 63 tokens ( 106.66 ms per token, 9.38 tokens per second) 3.46.656.054 I slot print_timing: id 0 | task 1264 | total time = 11525.19 ms / 447 tokens 3.46.656.057 I slot print_timing: id 0 | task 1264 | graphs reused = 1229 3.46.656.059 I slot print_timing: id 0 | task 1264 | graph reallocs = 0 / 0 (same size) / (changed size) 3.46.656.180 I slot release: id 0 | task 1264 | stop processing: n_tokens = 446, truncated = 0 3.46.668.499 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 446, t_last = 75658130359 3.46.668.564 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 474.263 MiB) 3.46.716.366 I slot launch_slot_: id 0 | task 1330 | processing task, is_child = 0 3.50.290.000 I slot print_timing: id 0 | task 1330 | prompt processing, n_tokens = 352, progress = 0.99, t = 3.57 s / 98.50 tokens per second 3.56.564.659 I slot print_timing: id 0 | task 1330 | prompt eval time = 4185.84 ms / 356 tokens ( 11.76 ms per token, 85.05 tokens per second) 3.56.564.669 I slot print_timing: id 0 | task 1330 | eval time = 5662.42 ms / 54 tokens ( 106.84 ms per token, 9.36 tokens per second) 3.56.564.677 I slot print_timing: id 0 | task 1330 | total time = 9848.26 ms / 410 tokens 3.56.564.679 I slot print_timing: id 0 | task 1330 | graphs reused = 1281 3.56.564.681 I slot print_timing: id 0 | task 1330 | graph reallocs = 0 / 0 (same size) / (changed size) 3.56.564.774 I slot release: id 0 | task 1330 | stop processing: n_tokens = 409, truncated = 0 3.56.577.871 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 75668038953 3.56.577.940 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 476.326 MiB) 3.56.599.115 I slot launch_slot_: id 0 | task 1387 | processing task, is_child = 0 4.00.897.562 I slot print_timing: id 0 | task 1387 | prompt processing, n_tokens = 406, progress = 0.99, t = 4.30 s / 94.45 tokens per second 4.08.680.579 I slot print_timing: id 0 | task 1387 | prompt eval time = 5236.37 ms / 410 tokens ( 12.77 ms per token, 78.30 tokens per second) 4.08.680.584 I slot print_timing: id 0 | task 1387 | eval time = 6845.08 ms / 70 tokens ( 99.20 ms per token, 10.08 tokens per second) 4.08.680.585 I slot print_timing: id 0 | task 1387 | total time = 12081.45 ms / 480 tokens 4.08.680.585 I slot print_timing: id 0 | task 1387 | graphs reused = 1349 4.08.680.586 I slot print_timing: id 0 | task 1387 | graph reallocs = 0 / 0 (same size) / (changed size) 4.08.680.610 I slot release: id 0 | task 1387 | stop processing: n_tokens = 479, truncated = 0 4.08.684.346 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 479, t_last = 75680154789 4.08.684.377 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 484.892 MiB) 4.08.697.995 I slot launch_slot_: id 0 | task 1460 | processing task, is_child = 0 4.12.982.901 I slot print_timing: id 0 | task 1460 | prompt processing, n_tokens = 381, progress = 0.99, t = 4.28 s / 88.92 tokens per second 4.19.285.732 I slot print_timing: id 0 | task 1460 | prompt eval time = 4896.91 ms / 385 tokens ( 12.72 ms per token, 78.62 tokens per second) 4.19.285.742 I slot print_timing: id 0 | task 1460 | eval time = 5690.80 ms / 58 tokens ( 99.84 ms per token, 10.02 tokens per second) 4.19.285.745 I slot print_timing: id 0 | task 1460 | total time = 10587.71 ms / 443 tokens 4.19.285.747 I slot print_timing: id 0 | task 1460 | graphs reused = 1405 4.19.285.749 I slot print_timing: id 0 | task 1460 | graph reallocs = 0 / 0 (same size) / (changed size) 4.19.285.864 I slot release: id 0 | task 1460 | stop processing: n_tokens = 442, truncated = 0 4.19.298.773 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 442, t_last = 75690760043 4.19.298.882 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 475.514 MiB) 4.19.348.432 I slot launch_slot_: id 0 | task 1521 | processing task, is_child = 0 4.23.328.870 I slot print_timing: id 0 | task 1521 | prompt processing, n_tokens = 391, progress = 0.99, t = 3.98 s / 98.23 tokens per second 4.31.701.449 I slot print_timing: id 0 | task 1521 | prompt eval time = 4927.62 ms / 395 tokens ( 12.47 ms per token, 80.16 tokens per second) 4.31.701.461 I slot print_timing: id 0 | task 1521 | eval time = 7425.36 ms / 71 tokens ( 106.08 ms per token, 9.43 tokens per second) 4.31.701.464 I slot print_timing: id 0 | task 1521 | total time = 12352.98 ms / 466 tokens 4.31.701.467 I slot print_timing: id 0 | task 1521 | graphs reused = 1474 4.31.701.469 I slot print_timing: id 0 | task 1521 | graph reallocs = 0 / 0 (same size) / (changed size) 4.31.701.593 I slot release: id 0 | task 1521 | stop processing: n_tokens = 465, truncated = 0 4.31.713.882 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 465, t_last = 75703175772 4.31.713.947 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 478.640 MiB) 4.31.747.254 I slot launch_slot_: id 0 | task 1595 | processing task, is_child = 0 4.36.067.355 I slot print_timing: id 0 | task 1595 | prompt processing, n_tokens = 426, progress = 0.99, t = 4.32 s / 98.61 tokens per second 4.43.520.708 I slot print_timing: id 0 | task 1595 | prompt eval time = 5280.69 ms / 430 tokens ( 12.28 ms per token, 81.43 tokens per second) 4.43.520.725 I slot print_timing: id 0 | task 1595 | eval time = 6492.73 ms / 62 tokens ( 106.44 ms per token, 9.40 tokens per second) 4.43.520.728 I slot print_timing: id 0 | task 1595 | total time = 11773.42 ms / 492 tokens 4.43.520.739 I slot print_timing: id 0 | task 1595 | graphs reused = 1534 4.43.520.741 I slot print_timing: id 0 | task 1595 | graph reallocs = 0 / 0 (same size) / (changed size) 4.43.520.879 I slot release: id 0 | task 1595 | stop processing: n_tokens = 491, truncated = 0 4.43.533.573 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 491, t_last = 75714995058 4.43.533.657 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 489.519 MiB) 4.43.566.036 I slot launch_slot_: id 0 | task 1660 | processing task, is_child = 0 4.47.539.905 I slot print_timing: id 0 | task 1660 | prompt processing, n_tokens = 388, progress = 0.99, t = 3.97 s / 97.64 tokens per second 4.54.937.233 I slot print_timing: id 0 | task 1660 | prompt eval time = 4918.63 ms / 392 tokens ( 12.55 ms per token, 79.70 tokens per second) 4.54.937.241 I slot print_timing: id 0 | task 1660 | eval time = 6452.54 ms / 62 tokens ( 105.78 ms per token, 9.45 tokens per second) 4.54.937.242 I slot print_timing: id 0 | task 1660 | total time = 11371.17 ms / 454 tokens 4.54.937.243 I slot print_timing: id 0 | task 1660 | graphs reused = 1594 4.54.937.244 I slot print_timing: id 0 | task 1660 | graph reallocs = 0 / 0 (same size) / (changed size) 4.54.937.301 I slot release: id 0 | task 1660 | stop processing: n_tokens = 453, truncated = 0 4.54.948.360 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 453, t_last = 75726411480 4.54.948.442 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 473.325 MiB) 4.55.009.069 I slot launch_slot_: id 0 | task 1725 | processing task, is_child = 0 4.58.968.575 I slot print_timing: id 0 | task 1725 | prompt processing, n_tokens = 346, progress = 0.99, t = 3.96 s / 87.39 tokens per second 5.06.739.400 I slot print_timing: id 0 | task 1725 | prompt eval time = 4567.84 ms / 350 tokens ( 13.05 ms per token, 76.62 tokens per second) 5.06.739.415 I slot print_timing: id 0 | task 1725 | eval time = 7162.44 ms / 70 tokens ( 103.80 ms per token, 9.63 tokens per second) 5.06.739.418 I slot print_timing: id 0 | task 1725 | total time = 11730.28 ms / 420 tokens 5.06.739.420 I slot print_timing: id 0 | task 1725 | graphs reused = 1662 5.06.739.422 I slot print_timing: id 0 | task 1725 | graph reallocs = 0 / 0 (same size) / (changed size) 5.06.739.536 I slot release: id 0 | task 1725 | stop processing: n_tokens = 419, truncated = 0 5.06.751.660 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 75738213715 5.06.751.727 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 474.138 MiB) 5.06.785.836 I slot launch_slot_: id 0 | task 1798 | processing task, is_child = 0 5.10.760.005 I slot print_timing: id 0 | task 1798 | prompt processing, n_tokens = 376, progress = 0.99, t = 3.97 s / 94.61 tokens per second 5.17.327.538 I slot print_timing: id 0 | task 1798 | prompt eval time = 4587.25 ms / 380 tokens ( 12.07 ms per token, 82.84 tokens per second) 5.17.327.540 I slot print_timing: id 0 | task 1798 | eval time = 5954.44 ms / 61 tokens ( 99.24 ms per token, 10.08 tokens per second) 5.17.327.541 I slot print_timing: id 0 | task 1798 | total time = 10541.69 ms / 441 tokens 5.17.327.541 I slot print_timing: id 0 | task 1798 | graphs reused = 1721 5.17.327.542 I slot print_timing: id 0 | task 1798 | graph reallocs = 0 / 0 (same size) / (changed size) 5.17.327.568 I slot release: id 0 | task 1798 | stop processing: n_tokens = 440, truncated = 0 5.17.332.032 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 440, t_last = 75748801747 5.17.332.061 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 476.201 MiB) 5.17.369.302 I slot launch_slot_: id 0 | task 1862 | processing task, is_child = 0 5.21.654.414 I slot print_timing: id 0 | task 1862 | prompt processing, n_tokens = 406, progress = 0.99, t = 4.29 s / 94.75 tokens per second 5.30.461.049 I slot print_timing: id 0 | task 1862 | prompt eval time = 5237.33 ms / 410 tokens ( 12.77 ms per token, 78.28 tokens per second) 5.30.461.055 I slot print_timing: id 0 | task 1862 | eval time = 7854.40 ms / 80 tokens ( 99.42 ms per token, 10.06 tokens per second) 5.30.461.056 I slot print_timing: id 0 | task 1862 | total time = 13091.74 ms / 490 tokens 5.30.461.056 I slot print_timing: id 0 | task 1862 | graphs reused = 1799 5.30.461.057 I slot print_timing: id 0 | task 1862 | graph reallocs = 0 / 0 (same size) / (changed size) 5.30.461.085 I slot release: id 0 | task 1862 | stop processing: n_tokens = 489, truncated = 0 5.30.464.974 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 489, t_last = 75761935264 5.30.465.004 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 477.514 MiB) 5.30.511.937 I slot launch_slot_: id 0 | task 1945 | processing task, is_child = 0 5.34.797.658 I slot print_timing: id 0 | task 1945 | prompt processing, n_tokens = 383, progress = 0.99, t = 4.29 s / 89.37 tokens per second 5.42.341.958 I slot print_timing: id 0 | task 1945 | prompt eval time = 4897.64 ms / 387 tokens ( 12.66 ms per token, 79.02 tokens per second) 5.42.341.971 I slot print_timing: id 0 | task 1945 | eval time = 6932.35 ms / 68 tokens ( 103.47 ms per token, 9.66 tokens per second) 5.42.341.974 I slot print_timing: id 0 | task 1945 | total time = 11829.99 ms / 455 tokens 5.42.341.977 I slot print_timing: id 0 | task 1945 | graphs reused = 1865 5.42.341.979 I slot print_timing: id 0 | task 1945 | graph reallocs = 0 / 0 (same size) / (changed size) 5.42.342.109 I slot release: id 0 | task 1945 | stop processing: n_tokens = 454, truncated = 0 5.42.354.104 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 454, t_last = 75773816288 5.42.354.170 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 476.201 MiB) 5.42.387.707 I slot launch_slot_: id 0 | task 2016 | processing task, is_child = 0 5.46.349.595 I slot print_timing: id 0 | task 2016 | prompt processing, n_tokens = 354, progress = 0.99, t = 3.96 s / 89.35 tokens per second 5.52.754.069 I slot print_timing: id 0 | task 2016 | prompt eval time = 4571.76 ms / 358 tokens ( 12.77 ms per token, 78.31 tokens per second) 5.52.754.082 I slot print_timing: id 0 | task 2016 | eval time = 5794.57 ms / 59 tokens ( 99.91 ms per token, 10.01 tokens per second) 5.52.754.084 I slot print_timing: id 0 | task 2016 | total time = 10366.33 ms / 417 tokens 5.52.754.086 I slot print_timing: id 0 | task 2016 | graphs reused = 1922 5.52.754.088 I slot print_timing: id 0 | task 2016 | graph reallocs = 0 / 0 (same size) / (changed size) 5.52.754.217 I slot release: id 0 | task 2016 | stop processing: n_tokens = 416, truncated = 0 5.52.767.545 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 75784228396 5.52.767.617 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 475.701 MiB) 5.52.801.252 I slot launch_slot_: id 0 | task 2078 | processing task, is_child = 0 5.56.769.905 I slot print_timing: id 0 | task 2078 | prompt processing, n_tokens = 355, progress = 0.99, t = 3.97 s / 89.45 tokens per second 6.00.234.662 I slot print_timing: id 0 | task 2078 | prompt eval time = 4576.01 ms / 359 tokens ( 12.75 ms per token, 78.45 tokens per second) 6.00.234.675 I slot print_timing: id 0 | task 2078 | eval time = 2857.37 ms / 29 tokens ( 102.05 ms per token, 9.80 tokens per second) 6.00.234.678 I slot print_timing: id 0 | task 2078 | total time = 7433.38 ms / 388 tokens 6.00.234.680 I slot print_timing: id 0 | task 2078 | graphs reused = 1949 6.00.234.682 I slot print_timing: id 0 | task 2078 | graph reallocs = 0 / 0 (same size) / (changed size) 6.00.234.777 I slot release: id 0 | task 2078 | stop processing: n_tokens = 387, truncated = 0 6.00.246.484 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 387, t_last = 75791708956 6.00.246.558 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 475.388 MiB) 6.00.288.092 I slot launch_slot_: id 0 | task 2110 | processing task, is_child = 0 6.04.578.781 I slot print_timing: id 0 | task 2110 | prompt processing, n_tokens = 383, progress = 0.99, t = 4.29 s / 89.26 tokens per second 6.11.450.069 I slot print_timing: id 0 | task 2110 | prompt eval time = 4900.66 ms / 387 tokens ( 12.66 ms per token, 78.97 tokens per second) 6.11.450.085 I slot print_timing: id 0 | task 2110 | eval time = 6261.26 ms / 61 tokens ( 104.35 ms per token, 9.58 tokens per second) 6.11.450.088 I slot print_timing: id 0 | task 2110 | total time = 11161.92 ms / 448 tokens 6.11.450.091 I slot print_timing: id 0 | task 2110 | graphs reused = 2008 6.11.450.093 I slot print_timing: id 0 | task 2110 | graph reallocs = 0 / 0 (same size) / (changed size) 6.11.450.213 I slot release: id 0 | task 2110 | stop processing: n_tokens = 447, truncated = 0 6.11.462.219 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 75802924392 6.11.462.290 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 473.700 MiB) 6.11.525.693 I slot launch_slot_: id 0 | task 2174 | processing task, is_child = 0 6.15.827.031 I slot print_timing: id 0 | task 2174 | prompt processing, n_tokens = 406, progress = 0.99, t = 4.30 s / 94.39 tokens per second 6.22.828.540 I slot print_timing: id 0 | task 2174 | prompt eval time = 4915.46 ms / 410 tokens ( 11.99 ms per token, 83.41 tokens per second) 6.22.828.554 I slot print_timing: id 0 | task 2174 | eval time = 6387.35 ms / 61 tokens ( 106.46 ms per token, 9.39 tokens per second) 6.22.828.563 I slot print_timing: id 0 | task 2174 | total time = 11302.81 ms / 471 tokens 6.22.828.565 I slot print_timing: id 0 | task 2174 | graphs reused = 2067 6.22.828.567 I slot print_timing: id 0 | task 2174 | graph reallocs = 0 / 0 (same size) / (changed size) 6.22.828.689 I slot release: id 0 | task 2174 | stop processing: n_tokens = 470, truncated = 0 6.22.840.896 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 75814302868 6.22.840.988 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 474.451 MiB) 6.22.914.087 I slot launch_slot_: id 0 | task 2238 | processing task, is_child = 0 6.26.892.963 I slot print_timing: id 0 | task 2238 | prompt processing, n_tokens = 347, progress = 0.99, t = 3.98 s / 87.21 tokens per second 6.32.717.036 I slot print_timing: id 0 | task 2238 | prompt eval time = 4586.32 ms / 351 tokens ( 13.07 ms per token, 76.53 tokens per second) 6.32.717.054 I slot print_timing: id 0 | task 2238 | eval time = 5216.58 ms / 50 tokens ( 106.46 ms per token, 9.39 tokens per second) 6.32.717.057 I slot print_timing: id 0 | task 2238 | total time = 9802.90 ms / 401 tokens 6.32.717.060 I slot print_timing: id 0 | task 2238 | graphs reused = 2115 6.32.717.062 I slot print_timing: id 0 | task 2238 | graph reallocs = 0 / 0 (same size) / (changed size) 6.32.717.187 I slot release: id 0 | task 2238 | stop processing: n_tokens = 400, truncated = 0 6.32.730.300 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 75824191367 6.32.730.365 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 473.388 MiB) 6.32.751.109 I slot launch_slot_: id 0 | task 2291 | processing task, is_child = 0 6.37.068.099 I slot print_timing: id 0 | task 2291 | prompt processing, n_tokens = 389, progress = 0.99, t = 4.32 s / 90.11 tokens per second 6.48.244.825 I slot print_timing: id 0 | task 2291 | n_gen = 100, tg = 9.38 t/s, tg_3s = 9.47 t/s 6.51.325.776 I slot print_timing: id 0 | task 2291 | n_gen = 129, tg = 9.39 t/s, tg_3s = 9.41 t/s 6.54.432.167 I slot print_timing: id 0 | task 2291 | n_gen = 158, tg = 9.38 t/s, tg_3s = 9.34 t/s 6.57.519.908 I slot print_timing: id 0 | task 2291 | n_gen = 187, tg = 9.38 t/s, tg_3s = 9.39 t/s 7.00.600.703 I slot print_timing: id 0 | task 2291 | n_gen = 216, tg = 9.38 t/s, tg_3s = 9.41 t/s 7.01.454.791 I slot print_timing: id 0 | task 2291 | prompt eval time = 4938.58 ms / 393 tokens ( 12.57 ms per token, 79.58 tokens per second) 7.01.454.813 I slot print_timing: id 0 | task 2291 | eval time = 23765.07 ms / 224 tokens ( 106.57 ms per token, 9.38 tokens per second) 7.01.454.815 I slot print_timing: id 0 | task 2291 | total time = 28703.65 ms / 617 tokens 7.01.454.817 I slot print_timing: id 0 | task 2291 | graphs reused = 2336 7.01.454.819 I slot print_timing: id 0 | task 2291 | graph reallocs = 0 / 0 (same size) / (changed size) 7.01.454.966 I slot release: id 0 | task 2291 | stop processing: n_tokens = 616, truncated = 0 7.01.467.648 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 616, t_last = 75852929145 7.01.467.741 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 473.138 MiB) 7.01.522.915 I slot launch_slot_: id 0 | task 2518 | processing task, is_child = 0 7.05.123.597 I slot print_timing: id 0 | task 2518 | prompt processing, n_tokens = 317, progress = 0.99, t = 3.60 s / 88.04 tokens per second 7.11.386.457 I slot print_timing: id 0 | task 2518 | prompt eval time = 4210.05 ms / 321 tokens ( 13.12 ms per token, 76.25 tokens per second) 7.11.386.474 I slot print_timing: id 0 | task 2518 | eval time = 5653.46 ms / 57 tokens ( 100.95 ms per token, 9.91 tokens per second) 7.11.386.476 I slot print_timing: id 0 | task 2518 | total time = 9863.51 ms / 378 tokens 7.11.386.481 I slot print_timing: id 0 | task 2518 | graphs reused = 2391 7.11.386.493 I slot print_timing: id 0 | task 2518 | graph reallocs = 0 / 0 (same size) / (changed size) 7.11.386.593 I slot release: id 0 | task 2518 | stop processing: n_tokens = 377, truncated = 0 7.11.398.231 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 377, t_last = 75862860773 7.11.398.300 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 476.764 MiB) 7.11.425.019 I slot launch_slot_: id 0 | task 2578 | processing task, is_child = 0 7.15.030.033 I slot print_timing: id 0 | task 2578 | prompt processing, n_tokens = 326, progress = 0.99, t = 3.60 s / 90.43 tokens per second 7.26.167.292 I slot print_timing: id 0 | task 2578 | n_gen = 100, tg = 9.40 t/s, tg_3s = 9.50 t/s 7.28.290.367 I slot print_timing: id 0 | task 2578 | prompt eval time = 4214.04 ms / 330 tokens ( 12.77 ms per token, 78.31 tokens per second) 7.28.290.381 I slot print_timing: id 0 | task 2578 | eval time = 12651.27 ms / 120 tokens ( 106.31 ms per token, 9.41 tokens per second) 7.28.290.387 I slot print_timing: id 0 | task 2578 | total time = 16865.32 ms / 450 tokens 7.28.290.389 I slot print_timing: id 0 | task 2578 | graphs reused = 2509 7.28.290.391 I slot print_timing: id 0 | task 2578 | graph reallocs = 0 / 0 (same size) / (changed size) 7.28.290.488 I slot release: id 0 | task 2578 | stop processing: n_tokens = 449, truncated = 0 7.28.301.801 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 449, t_last = 75879764667 7.28.301.869 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 474.451 MiB) 7.28.350.654 I slot launch_slot_: id 0 | task 2701 | processing task, is_child = 0 7.31.968.675 I slot print_timing: id 0 | task 2701 | prompt processing, n_tokens = 337, progress = 0.99, t = 3.62 s / 93.15 tokens per second 7.35.654.493 I slot print_timing: id 0 | task 2701 | prompt eval time = 4226.73 ms / 341 tokens ( 12.40 ms per token, 80.68 tokens per second) 7.35.654.499 I slot print_timing: id 0 | task 2701 | eval time = 3077.09 ms / 32 tokens ( 99.26 ms per token, 10.07 tokens per second) 7.35.654.499 I slot print_timing: id 0 | task 2701 | total time = 7303.83 ms / 373 tokens 7.35.654.500 I slot print_timing: id 0 | task 2701 | graphs reused = 2539 7.35.654.500 I slot print_timing: id 0 | task 2701 | graph reallocs = 0 / 0 (same size) / (changed size) 7.35.654.525 I slot release: id 0 | task 2701 | stop processing: n_tokens = 372, truncated = 0 7.35.658.233 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 372, t_last = 75887128704 7.35.658.258 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 478.827 MiB) 7.35.675.502 I slot launch_slot_: id 0 | task 2736 | processing task, is_child = 0 7.39.888.637 I slot print_timing: id 0 | task 2736 | prompt processing, n_tokens = 334, progress = 0.99, t = 4.21 s / 79.28 tokens per second 7.45.024.956 I slot print_timing: id 0 | task 2736 | prompt eval time = 4683.27 ms / 338 tokens ( 13.86 ms per token, 72.17 tokens per second) 7.45.024.959 I slot print_timing: id 0 | task 2736 | eval time = 4666.17 ms / 48 tokens ( 99.28 ms per token, 10.07 tokens per second) 7.45.024.960 I slot print_timing: id 0 | task 2736 | total time = 9349.44 ms / 386 tokens 7.45.024.960 I slot print_timing: id 0 | task 2736 | graphs reused = 2585 7.45.024.961 I slot print_timing: id 0 | task 2736 | graph reallocs = 0 / 0 (same size) / (changed size) 7.45.024.986 I slot release: id 0 | task 2736 | stop processing: n_tokens = 385, truncated = 0 7.45.028.961 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 385, t_last = 75896499166 7.45.028.989 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 476.514 MiB) 7.45.042.917 I slot launch_slot_: id 0 | task 2787 | processing task, is_child = 0 7.49.023.094 I slot print_timing: id 0 | task 2787 | prompt processing, n_tokens = 391, progress = 0.99, t = 3.98 s / 98.24 tokens per second 7.55.429.194 I slot print_timing: id 0 | task 2787 | prompt eval time = 4926.05 ms / 395 tokens ( 12.47 ms per token, 80.19 tokens per second) 7.55.429.197 I slot print_timing: id 0 | task 2787 | eval time = 5460.22 ms / 56 tokens ( 99.28 ms per token, 10.07 tokens per second) 7.55.429.198 I slot print_timing: id 0 | task 2787 | total time = 10386.26 ms / 451 tokens 7.55.429.198 I slot print_timing: id 0 | task 2787 | graphs reused = 2639 7.55.429.199 I slot print_timing: id 0 | task 2787 | graph reallocs = 0 / 0 (same size) / (changed size) 7.55.429.225 I slot release: id 0 | task 2787 | stop processing: n_tokens = 450, truncated = 0 7.55.433.411 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 450, t_last = 75906903404 7.55.433.441 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 477.952 MiB) 7.55.455.760 I slot launch_slot_: id 0 | task 2846 | processing task, is_child = 0 8.01.132.892 I slot print_timing: id 0 | task 2846 | prompt processing, n_tokens = 524, progress = 0.99, t = 5.68 s / 92.30 tokens per second 8.10.691.995 I slot print_timing: id 0 | task 2846 | prompt eval time = 6636.11 ms / 528 tokens ( 12.57 ms per token, 79.56 tokens per second) 8.10.692.006 I slot print_timing: id 0 | task 2846 | eval time = 8600.07 ms / 83 tokens ( 104.88 ms per token, 9.53 tokens per second) 8.10.692.009 I slot print_timing: id 0 | task 2846 | total time = 15236.18 ms / 611 tokens 8.10.692.011 I slot print_timing: id 0 | task 2846 | graphs reused = 2720 8.10.692.013 I slot print_timing: id 0 | task 2846 | graph reallocs = 0 / 0 (same size) / (changed size) 8.10.692.152 I slot release: id 0 | task 2846 | stop processing: n_tokens = 610, truncated = 0 8.10.703.898 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 610, t_last = 75922166331 8.10.703.986 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 479.578 MiB) 8.10.704.016 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 477.202 MiB) 8.10.759.012 I slot launch_slot_: id 0 | task 2933 | processing task, is_child = 0 8.14.370.354 I slot print_timing: id 0 | task 2933 | prompt processing, n_tokens = 327, progress = 0.99, t = 3.61 s / 90.55 tokens per second 8.19.416.312 I slot print_timing: id 0 | task 2933 | prompt eval time = 4222.31 ms / 331 tokens ( 12.76 ms per token, 78.39 tokens per second) 8.19.416.329 I slot print_timing: id 0 | task 2933 | eval time = 4434.96 ms / 45 tokens ( 100.79 ms per token, 9.92 tokens per second) 8.19.416.331 I slot print_timing: id 0 | task 2933 | total time = 8657.27 ms / 376 tokens 8.19.416.333 I slot print_timing: id 0 | task 2933 | graphs reused = 2763 8.19.416.335 I slot print_timing: id 0 | task 2933 | graph reallocs = 0 / 0 (same size) / (changed size) 8.19.416.490 I slot release: id 0 | task 2933 | stop processing: n_tokens = 387, truncated = 0 8.19.428.708 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 387, t_last = 75930890669 8.19.428.779 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 475.076 MiB) 8.19.498.671 I slot launch_slot_: id 0 | task 2981 | processing task, is_child = 0 8.23.488.478 I slot print_timing: id 0 | task 2981 | prompt processing, n_tokens = 358, progress = 0.99, t = 3.99 s / 89.73 tokens per second 8.29.396.198 I slot print_timing: id 0 | task 2981 | prompt eval time = 4599.21 ms / 362 tokens ( 12.70 ms per token, 78.71 tokens per second) 8.29.396.215 I slot print_timing: id 0 | task 2981 | eval time = 5298.29 ms / 53 tokens ( 101.89 ms per token, 9.81 tokens per second) 8.29.396.228 I slot print_timing: id 0 | task 2981 | total time = 9897.49 ms / 415 tokens 8.29.396.238 I slot print_timing: id 0 | task 2981 | graphs reused = 2814 8.29.396.241 I slot print_timing: id 0 | task 2981 | graph reallocs = 0 / 0 (same size) / (changed size) 8.29.396.336 I slot release: id 0 | task 2981 | stop processing: n_tokens = 426, truncated = 0 8.29.408.183 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 75940870516 8.29.408.252 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 476.389 MiB) 8.29.455.692 I slot launch_slot_: id 0 | task 3037 | processing task, is_child = 0 8.33.769.472 I slot print_timing: id 0 | task 3037 | prompt processing, n_tokens = 415, progress = 0.99, t = 4.31 s / 96.20 tokens per second 8.41.773.119 I slot print_timing: id 0 | task 3037 | prompt eval time = 5253.62 ms / 419 tokens ( 12.54 ms per token, 79.75 tokens per second) 8.41.773.133 I slot print_timing: id 0 | task 3037 | eval time = 7063.76 ms / 69 tokens ( 103.88 ms per token, 9.63 tokens per second) 8.41.773.137 I slot print_timing: id 0 | task 3037 | total time = 12317.38 ms / 488 tokens 8.41.773.140 I slot print_timing: id 0 | task 3037 | graphs reused = 2881 8.41.773.142 I slot print_timing: id 0 | task 3037 | graph reallocs = 0 / 0 (same size) / (changed size) 8.41.773.394 I slot release: id 0 | task 3037 | stop processing: n_tokens = 499, truncated = 0 8.41.786.691 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 499, t_last = 75953247574 8.41.786.773 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 479.452 MiB) 8.41.786.817 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 477.264 MiB) 8.41.876.991 I slot launch_slot_: id 0 | task 3109 | processing task, is_child = 0 8.46.560.168 I slot print_timing: id 0 | task 3109 | prompt processing, n_tokens = 419, progress = 0.99, t = 4.68 s / 89.47 tokens per second 8.51.629.516 I slot print_timing: id 0 | task 3109 | prompt eval time = 5299.44 ms / 423 tokens ( 12.53 ms per token, 79.82 tokens per second) 8.51.629.532 I slot print_timing: id 0 | task 3109 | eval time = 4453.06 ms / 44 tokens ( 103.56 ms per token, 9.66 tokens per second) 8.51.629.534 I slot print_timing: id 0 | task 3109 | total time = 9752.49 ms / 467 tokens 8.51.629.536 I slot print_timing: id 0 | task 3109 | graphs reused = 2923 8.51.629.538 I slot print_timing: id 0 | task 3109 | graph reallocs = 0 / 0 (same size) / (changed size) 8.51.629.642 I slot release: id 0 | task 3109 | stop processing: n_tokens = 478, truncated = 0 8.51.641.481 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 478, t_last = 75963103821 8.51.641.565 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 474.888 MiB) 8.51.723.838 I slot launch_slot_: id 0 | task 3156 | processing task, is_child = 0 8.55.325.062 I slot print_timing: id 0 | task 3156 | prompt processing, n_tokens = 337, progress = 0.99, t = 3.60 s / 93.58 tokens per second 9.00.102.315 I slot print_timing: id 0 | task 3156 | prompt eval time = 4208.67 ms / 341 tokens ( 12.34 ms per token, 81.02 tokens per second) 9.00.102.320 I slot print_timing: id 0 | task 3156 | eval time = 4169.78 ms / 43 tokens ( 99.28 ms per token, 10.07 tokens per second) 9.00.102.320 I slot print_timing: id 0 | task 3156 | total time = 8378.45 ms / 384 tokens 9.00.102.321 I slot print_timing: id 0 | task 3156 | graphs reused = 2964 9.00.102.321 I slot print_timing: id 0 | task 3156 | graph reallocs = 0 / 0 (same size) / (changed size) 9.00.102.349 I slot release: id 0 | task 3156 | stop processing: n_tokens = 395, truncated = 0 9.00.106.433 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 395, t_last = 75971576528 9.00.106.458 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 473.075 MiB) 9.00.150.716 I slot launch_slot_: id 0 | task 3202 | processing task, is_child = 0 9.04.120.128 I slot print_timing: id 0 | task 3202 | prompt processing, n_tokens = 352, progress = 0.99, t = 3.97 s / 88.68 tokens per second 9.09.439.482 I slot print_timing: id 0 | task 3202 | prompt eval time = 4579.14 ms / 356 tokens ( 12.86 ms per token, 77.74 tokens per second) 9.09.439.492 I slot print_timing: id 0 | task 3202 | eval time = 4709.59 ms / 47 tokens ( 102.38 ms per token, 9.77 tokens per second) 9.09.439.494 I slot print_timing: id 0 | task 3202 | total time = 9288.73 ms / 403 tokens 9.09.439.497 I slot print_timing: id 0 | task 3202 | graphs reused = 3009 9.09.439.499 I slot print_timing: id 0 | task 3202 | graph reallocs = 0 / 0 (same size) / (changed size) 9.09.439.624 I slot release: id 0 | task 3202 | stop processing: n_tokens = 414, truncated = 0 9.09.451.228 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 75980913803 9.09.451.299 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 476.826 MiB) 9.09.451.304 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 478.265 MiB) 9.09.532.581 I slot launch_slot_: id 0 | task 3252 | processing task, is_child = 0 9.13.522.728 I slot print_timing: id 0 | task 3252 | prompt processing, n_tokens = 358, progress = 0.99, t = 3.99 s / 89.72 tokens per second 9.18.401.923 I slot print_timing: id 0 | task 3252 | prompt eval time = 4597.73 ms / 362 tokens ( 12.70 ms per token, 78.73 tokens per second) 9.18.401.925 I slot print_timing: id 0 | task 3252 | eval time = 4271.60 ms / 44 tokens ( 99.34 ms per token, 10.07 tokens per second) 9.18.401.926 I slot print_timing: id 0 | task 3252 | total time = 8869.32 ms / 406 tokens 9.18.401.927 I slot print_timing: id 0 | task 3252 | graphs reused = 3051 9.18.401.927 I slot print_timing: id 0 | task 3252 | graph reallocs = 0 / 0 (same size) / (changed size) 9.18.401.952 I slot release: id 0 | task 3252 | stop processing: n_tokens = 417, truncated = 0 9.18.406.097 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 417, t_last = 75989876131 9.18.406.127 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 473.888 MiB) 9.18.444.138 I slot launch_slot_: id 0 | task 3299 | processing task, is_child = 0 9.22.737.385 I slot print_timing: id 0 | task 3299 | prompt processing, n_tokens = 387, progress = 0.99, t = 4.29 s / 90.14 tokens per second 9.30.001.526 I slot print_timing: id 0 | task 3299 | prompt eval time = 4909.44 ms / 391 tokens ( 12.56 ms per token, 79.64 tokens per second) 9.30.001.532 I slot print_timing: id 0 | task 3299 | eval time = 6647.94 ms / 68 tokens ( 99.22 ms per token, 10.08 tokens per second) 9.30.001.533 I slot print_timing: id 0 | task 3299 | total time = 11557.38 ms / 459 tokens 9.30.001.533 I slot print_timing: id 0 | task 3299 | graphs reused = 3117 9.30.001.533 I slot print_timing: id 0 | task 3299 | graph reallocs = 0 / 0 (same size) / (changed size) 9.30.001.563 I slot release: id 0 | task 3299 | stop processing: n_tokens = 470, truncated = 0 9.30.005.498 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 76001475742 9.30.005.526 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 487.393 MiB) 9.30.039.043 I slot launch_slot_: id 0 | task 3370 | processing task, is_child = 0 9.33.660.178 I slot print_timing: id 0 | task 3370 | prompt processing, n_tokens = 339, progress = 0.99, t = 3.62 s / 93.62 tokens per second 9.39.533.520 I slot print_timing: id 0 | task 3370 | prompt eval time = 4231.68 ms / 343 tokens ( 12.34 ms per token, 81.06 tokens per second) 9.39.533.523 I slot print_timing: id 0 | task 3370 | eval time = 5262.78 ms / 54 tokens ( 99.30 ms per token, 10.07 tokens per second) 9.39.533.524 I slot print_timing: id 0 | task 3370 | total time = 9494.47 ms / 397 tokens 9.39.533.525 I slot print_timing: id 0 | task 3370 | graphs reused = 3169 9.39.533.525 I slot print_timing: id 0 | task 3370 | graph reallocs = 0 / 0 (same size) / (changed size) 9.39.533.552 I slot release: id 0 | task 3370 | stop processing: n_tokens = 408, truncated = 0 9.39.537.682 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 408, t_last = 76011007731 9.39.537.712 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 472.450 MiB) 9.39.573.080 I slot launch_slot_: id 0 | task 3427 | processing task, is_child = 0 9.43.877.349 I slot print_timing: id 0 | task 3427 | prompt processing, n_tokens = 397, progress = 0.99, t = 4.30 s / 92.23 tokens per second 9.48.977.948 I slot print_timing: id 0 | task 3427 | prompt eval time = 4916.58 ms / 401 tokens ( 12.26 ms per token, 81.56 tokens per second) 9.48.977.961 I slot print_timing: id 0 | task 3427 | eval time = 4488.25 ms / 46 tokens ( 99.74 ms per token, 10.03 tokens per second) 9.48.977.964 I slot print_timing: id 0 | task 3427 | total time = 9404.83 ms / 447 tokens 9.48.977.966 I slot print_timing: id 0 | task 3427 | graphs reused = 3213 9.48.977.968 I slot print_timing: id 0 | task 3427 | graph reallocs = 0 / 0 (same size) / (changed size) 9.48.978.121 I slot release: id 0 | task 3427 | stop processing: n_tokens = 458, truncated = 0 9.48.990.739 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 76020452300 9.48.990.805 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 476.952 MiB) 9.48.990.823 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 472.137 MiB) 9.49.073.110 I slot launch_slot_: id 0 | task 3476 | processing task, is_child = 0 9.53.065.290 I slot print_timing: id 0 | task 3476 | prompt processing, n_tokens = 351, progress = 0.99, t = 3.99 s / 87.92 tokens per second 10.00.324.916 I slot print_timing: id 0 | task 3476 | prompt eval time = 4600.64 ms / 355 tokens ( 12.96 ms per token, 77.16 tokens per second) 10.00.324.922 I slot print_timing: id 0 | task 3476 | eval time = 6651.15 ms / 68 tokens ( 99.27 ms per token, 10.07 tokens per second) 10.00.324.922 I slot print_timing: id 0 | task 3476 | total time = 11251.79 ms / 423 tokens 10.00.324.923 I slot print_timing: id 0 | task 3476 | graphs reused = 3279 10.00.324.923 I slot print_timing: id 0 | task 3476 | graph reallocs = 0 / 0 (same size) / (changed size) 10.00.324.948 I slot release: id 0 | task 3476 | stop processing: n_tokens = 434, truncated = 0 10.00.329.224 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 434, t_last = 76031799127 10.00.329.252 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 472.950 MiB) 10.00.361.755 I slot launch_slot_: id 0 | task 3547 | processing task, is_child = 0 10.04.326.123 I slot print_timing: id 0 | task 3547 | prompt processing, n_tokens = 347, progress = 0.99, t = 3.96 s / 87.53 tokens per second 10.10.515.987 I slot print_timing: id 0 | task 3547 | prompt eval time = 4574.17 ms / 351 tokens ( 13.03 ms per token, 76.74 tokens per second) 10.10.515.990 I slot print_timing: id 0 | task 3547 | eval time = 5580.05 ms / 57 tokens ( 99.64 ms per token, 10.04 tokens per second) 10.10.515.990 I slot print_timing: id 0 | task 3547 | total time = 10154.22 ms / 408 tokens 10.10.515.991 I slot print_timing: id 0 | task 3547 | graphs reused = 3334 10.10.515.991 I slot print_timing: id 0 | task 3547 | graph reallocs = 0 / 0 (same size) / (changed size) 10.10.516.014 I slot release: id 0 | task 3547 | stop processing: n_tokens = 419, truncated = 0 10.10.520.646 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 76041990193 10.10.520.689 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 477.014 MiB) 10.10.550.725 I slot launch_slot_: id 0 | task 3607 | processing task, is_child = 0 10.15.581.595 I slot print_timing: id 0 | task 3607 | prompt processing, n_tokens = 471, progress = 0.99, t = 5.03 s / 93.62 tokens per second 10.25.866.194 I slot print_timing: id 0 | task 3607 | prompt eval time = 5974.52 ms / 475 tokens ( 12.58 ms per token, 79.50 tokens per second) 10.25.866.206 I slot print_timing: id 0 | task 3607 | eval time = 9340.92 ms / 93 tokens ( 101.53 ms per token, 9.85 tokens per second) 10.25.866.209 I slot print_timing: id 0 | task 3607 | total time = 15315.44 ms / 568 tokens 10.25.866.211 I slot print_timing: id 0 | task 3607 | graphs reused = 3424 10.25.866.213 I slot print_timing: id 0 | task 3607 | graph reallocs = 0 / 0 (same size) / (changed size) 10.25.866.330 I slot release: id 0 | task 3607 | stop processing: n_tokens = 579, truncated = 0 10.25.879.000 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 579, t_last = 76057340509 10.25.879.103 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 636.644 MiB) 10.25.907.465 I slot launch_slot_: id 0 | task 3703 | processing task, is_child = 0 10.30.587.341 I slot print_timing: id 0 | task 3703 | prompt processing, n_tokens = 436, progress = 0.99, t = 4.68 s / 93.17 tokens per second 10.41.161.288 I slot print_timing: id 0 | task 3703 | prompt eval time = 5618.31 ms / 440 tokens ( 12.77 ms per token, 78.32 tokens per second) 10.41.161.300 I slot print_timing: id 0 | task 3703 | eval time = 9635.46 ms / 92 tokens ( 105.88 ms per token, 9.44 tokens per second) 10.41.161.302 I slot print_timing: id 0 | task 3703 | total time = 15253.77 ms / 532 tokens 10.41.161.305 I slot print_timing: id 0 | task 3703 | graphs reused = 3513 10.41.161.307 I slot print_timing: id 0 | task 3703 | graph reallocs = 0 / 0 (same size) / (changed size) 10.41.161.428 I slot release: id 0 | task 3703 | stop processing: n_tokens = 543, truncated = 0 10.41.175.582 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 543, t_last = 76072635607 10.41.175.674 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 622.701 MiB) 10.41.210.284 I slot launch_slot_: id 0 | task 3798 | processing task, is_child = 0 10.44.850.270 I slot print_timing: id 0 | task 3798 | prompt processing, n_tokens = 341, progress = 0.99, t = 3.64 s / 93.68 tokens per second 10.51.181.175 I slot print_timing: id 0 | task 3798 | prompt eval time = 4263.34 ms / 345 tokens ( 12.36 ms per token, 80.92 tokens per second) 10.51.181.178 I slot print_timing: id 0 | task 3798 | eval time = 5707.53 ms / 55 tokens ( 105.70 ms per token, 9.46 tokens per second) 10.51.181.179 I slot print_timing: id 0 | task 3798 | total time = 9970.88 ms / 400 tokens 10.51.181.179 I slot print_timing: id 0 | task 3798 | graphs reused = 3566 10.51.181.180 I slot print_timing: id 0 | task 3798 | graph reallocs = 0 / 0 (same size) / (changed size) 10.51.181.203 I slot release: id 0 | task 3798 | stop processing: n_tokens = 411, truncated = 0 10.51.185.868 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 76082655382 10.51.185.905 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 625.140 MiB) 10.51.207.591 I slot launch_slot_: id 0 | task 3856 | processing task, is_child = 0 10.55.499.932 I slot print_timing: id 0 | task 3856 | prompt processing, n_tokens = 378, progress = 0.99, t = 4.29 s / 88.06 tokens per second 11.01.758.891 I slot print_timing: id 0 | task 3856 | prompt eval time = 4903.65 ms / 382 tokens ( 12.84 ms per token, 77.90 tokens per second) 11.01.758.902 I slot print_timing: id 0 | task 3856 | eval time = 5647.63 ms / 55 tokens ( 104.59 ms per token, 9.56 tokens per second) 11.01.758.904 I slot print_timing: id 0 | task 3856 | total time = 10551.27 ms / 437 tokens 11.01.758.906 I slot print_timing: id 0 | task 3856 | graphs reused = 3619 11.01.758.908 I slot print_timing: id 0 | task 3856 | graph reallocs = 0 / 0 (same size) / (changed size) 11.01.758.986 I slot release: id 0 | task 3856 | stop processing: n_tokens = 448, truncated = 0 11.01.770.306 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 76093233165 11.01.770.375 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 629.704 MiB) 11.01.821.451 I slot launch_slot_: id 0 | task 3914 | processing task, is_child = 0 11.05.442.340 I slot print_timing: id 0 | task 3914 | prompt processing, n_tokens = 333, progress = 0.99, t = 3.62 s / 91.97 tokens per second 11.10.420.551 I slot print_timing: id 0 | task 3914 | prompt eval time = 4230.15 ms / 337 tokens ( 12.55 ms per token, 79.67 tokens per second) 11.10.420.557 I slot print_timing: id 0 | task 3914 | eval time = 4368.94 ms / 45 tokens ( 99.29 ms per token, 10.07 tokens per second) 11.10.420.557 I slot print_timing: id 0 | task 3914 | total time = 8599.08 ms / 382 tokens 11.10.420.558 I slot print_timing: id 0 | task 3914 | graphs reused = 3662 11.10.420.558 I slot print_timing: id 0 | task 3914 | graph reallocs = 0 / 0 (same size) / (changed size) 11.10.420.583 I slot release: id 0 | task 3914 | stop processing: n_tokens = 393, truncated = 0 11.10.425.279 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 76101894762 11.10.425.305 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 628.391 MiB) 11.10.473.219 I slot launch_slot_: id 0 | task 3962 | processing task, is_child = 0 11.14.774.579 I slot print_timing: id 0 | task 3962 | prompt processing, n_tokens = 398, progress = 0.99, t = 4.30 s / 92.53 tokens per second 11.22.631.003 I slot print_timing: id 0 | task 3962 | prompt eval time = 4912.54 ms / 402 tokens ( 12.22 ms per token, 81.83 tokens per second) 11.22.631.017 I slot print_timing: id 0 | task 3962 | eval time = 7245.21 ms / 70 tokens ( 105.00 ms per token, 9.52 tokens per second) 11.22.631.020 I slot print_timing: id 0 | task 3962 | total time = 12157.75 ms / 472 tokens 11.22.631.023 I slot print_timing: id 0 | task 3962 | graphs reused = 3730 11.22.631.025 I slot print_timing: id 0 | task 3962 | graph reallocs = 0 / 0 (same size) / (changed size) 11.22.631.160 I slot release: id 0 | task 3962 | stop processing: n_tokens = 483, truncated = 0 11.22.645.677 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 483, t_last = 76114105339 11.22.645.747 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 623.201 MiB) 11.22.677.079 I slot launch_slot_: id 0 | task 4035 | processing task, is_child = 0 11.28.840.627 I slot print_timing: id 0 | task 4035 | prompt processing, n_tokens = 545, progress = 0.99, t = 6.16 s / 88.42 tokens per second 11.35.337.362 I slot print_timing: id 0 | task 4035 | prompt eval time = 7101.05 ms / 549 tokens ( 12.93 ms per token, 77.31 tokens per second) 11.35.337.368 I slot print_timing: id 0 | task 4035 | eval time = 5559.22 ms / 57 tokens ( 99.27 ms per token, 10.07 tokens per second) 11.35.337.368 I slot print_timing: id 0 | task 4035 | total time = 12660.27 ms / 606 tokens 11.35.337.369 I slot print_timing: id 0 | task 4035 | graphs reused = 3785 11.35.337.369 I slot print_timing: id 0 | task 4035 | graph reallocs = 0 / 0 (same size) / (changed size) 11.35.337.432 I slot release: id 0 | task 4035 | stop processing: n_tokens = 617, truncated = 0 11.35.342.940 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 617, t_last = 76126811611 11.35.342.973 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 624.389 MiB) 11.35.342.976 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 624.577 MiB) 11.35.394.990 I slot launch_slot_: id 0 | task 4096 | processing task, is_child = 0 11.42.247.678 I slot print_timing: id 0 | task 4096 | prompt processing, n_tokens = 612, progress = 0.99, t = 6.85 s / 89.31 tokens per second 11.49.000.777 I slot print_timing: id 0 | task 4096 | prompt eval time = 7806.32 ms / 616 tokens ( 12.67 ms per token, 78.91 tokens per second) 11.49.000.805 I slot print_timing: id 0 | task 4096 | eval time = 5799.42 ms / 58 tokens ( 101.74 ms per token, 9.83 tokens per second) 11.49.000.808 I slot print_timing: id 0 | task 4096 | total time = 13605.75 ms / 674 tokens 11.49.000.810 I slot print_timing: id 0 | task 4096 | graphs reused = 3841 11.49.000.812 I slot print_timing: id 0 | task 4096 | graph reallocs = 0 / 0 (same size) / (changed size) 11.49.000.993 I slot release: id 0 | task 4096 | stop processing: n_tokens = 685, truncated = 0 11.49.016.168 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 685, t_last = 76140475172 11.49.016.249 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 627.891 MiB) 11.49.107.261 I slot launch_slot_: id 0 | task 4158 | processing task, is_child = 0 11.56.346.806 I slot print_timing: id 0 | task 4158 | prompt processing, n_tokens = 661, progress = 0.99, t = 7.24 s / 91.30 tokens per second 12.03.642.778 I slot print_timing: id 0 | task 4158 | prompt eval time = 8188.42 ms / 665 tokens ( 12.31 ms per token, 81.21 tokens per second) 12.03.642.789 I slot print_timing: id 0 | task 4158 | eval time = 6347.05 ms / 61 tokens ( 105.78 ms per token, 9.45 tokens per second) 12.03.642.792 I slot print_timing: id 0 | task 4158 | total time = 14535.47 ms / 726 tokens 12.03.642.794 I slot print_timing: id 0 | task 4158 | graphs reused = 3900 12.03.642.796 I slot print_timing: id 0 | task 4158 | graph reallocs = 0 / 0 (same size) / (changed size) 12.03.642.992 I slot release: id 0 | task 4158 | stop processing: n_tokens = 737, truncated = 0 12.03.657.089 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 737, t_last = 76155117172 12.03.657.180 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 624.014 MiB) 12.03.751.206 I slot launch_slot_: id 0 | task 4223 | processing task, is_child = 0 12.11.313.565 I slot print_timing: id 0 | task 4223 | prompt processing, n_tokens = 641, progress = 0.99, t = 7.56 s / 84.76 tokens per second 12.17.659.414 I slot print_timing: id 0 | task 4223 | prompt eval time = 8179.43 ms / 645 tokens ( 12.68 ms per token, 78.86 tokens per second) 12.17.659.427 I slot print_timing: id 0 | task 4223 | eval time = 5728.75 ms / 55 tokens ( 106.09 ms per token, 9.43 tokens per second) 12.17.659.430 I slot print_timing: id 0 | task 4223 | total time = 13908.18 ms / 700 tokens 12.17.659.435 I slot print_timing: id 0 | task 4223 | graphs reused = 3953 12.17.659.437 I slot print_timing: id 0 | task 4223 | graph reallocs = 0 / 0 (same size) / (changed size) 12.17.659.599 I slot release: id 0 | task 4223 | stop processing: n_tokens = 711, truncated = 0 12.17.672.861 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 711, t_last = 76169133778 12.17.672.955 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 627.140 MiB) 12.17.754.096 I slot launch_slot_: id 0 | task 4282 | processing task, is_child = 0 12.22.795.012 I slot print_timing: id 0 | task 4282 | prompt processing, n_tokens = 470, progress = 0.99, t = 5.04 s / 93.24 tokens per second 12.28.842.597 I slot print_timing: id 0 | task 4282 | prompt eval time = 5655.94 ms / 474 tokens ( 11.93 ms per token, 83.81 tokens per second) 12.28.842.612 I slot print_timing: id 0 | task 4282 | eval time = 5432.53 ms / 52 tokens ( 106.52 ms per token, 9.39 tokens per second) 12.28.842.615 I slot print_timing: id 0 | task 4282 | total time = 11088.47 ms / 526 tokens 12.28.842.617 I slot print_timing: id 0 | task 4282 | graphs reused = 4002 12.28.842.619 I slot print_timing: id 0 | task 4282 | graph reallocs = 0 / 0 (same size) / (changed size) 12.28.842.759 I slot release: id 0 | task 4282 | stop processing: n_tokens = 537, truncated = 0 12.28.857.231 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 537, t_last = 76180316938 12.28.857.307 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 625.640 MiB) 12.28.883.726 I slot launch_slot_: id 0 | task 4337 | processing task, is_child = 0 12.36.084.817 I slot print_timing: id 0 | task 4337 | prompt processing, n_tokens = 613, progress = 0.99, t = 7.20 s / 85.13 tokens per second 12.40.772.271 I slot print_timing: id 0 | task 4337 | prompt eval time = 7815.90 ms / 617 tokens ( 12.67 ms per token, 78.94 tokens per second) 12.40.772.274 I slot print_timing: id 0 | task 4337 | eval time = 4072.63 ms / 42 tokens ( 99.33 ms per token, 10.07 tokens per second) 12.40.772.274 I slot print_timing: id 0 | task 4337 | total time = 11888.53 ms / 659 tokens 12.40.772.275 I slot print_timing: id 0 | task 4337 | graphs reused = 4042 12.40.772.275 I slot print_timing: id 0 | task 4337 | graph reallocs = 0 / 0 (same size) / (changed size) 12.40.772.313 I slot release: id 0 | task 4337 | stop processing: n_tokens = 670, truncated = 0 12.40.776.956 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 670, t_last = 76192246492 12.40.776.995 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 624.702 MiB) 12.40.777.003 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 634.706 MiB) 12.40.815.792 I slot launch_slot_: id 0 | task 4383 | processing task, is_child = 0 12.47.686.046 I slot print_timing: id 0 | task 4383 | prompt processing, n_tokens = 597, progress = 0.99, t = 6.87 s / 86.90 tokens per second 12.52.970.576 I slot print_timing: id 0 | task 4383 | prompt eval time = 7486.41 ms / 601 tokens ( 12.46 ms per token, 80.28 tokens per second) 12.52.970.578 I slot print_timing: id 0 | task 4383 | eval time = 4668.36 ms / 48 tokens ( 99.33 ms per token, 10.07 tokens per second) 12.52.970.579 I slot print_timing: id 0 | task 4383 | total time = 12154.77 ms / 649 tokens 12.52.970.579 I slot print_timing: id 0 | task 4383 | graphs reused = 4088 12.52.970.580 I slot print_timing: id 0 | task 4383 | graph reallocs = 0 / 0 (same size) / (changed size) 12.52.970.623 I slot release: id 0 | task 4383 | stop processing: n_tokens = 660, truncated = 0 12.52.975.474 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 660, t_last = 76204444802 12.52.975.515 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 632.455 MiB) 12.53.018.236 I slot launch_slot_: id 0 | task 4435 | processing task, is_child = 0 12.59.174.289 I slot print_timing: id 0 | task 4435 | prompt processing, n_tokens = 529, progress = 0.99, t = 6.16 s / 85.93 tokens per second 13.04.356.912 I slot print_timing: id 0 | task 4435 | prompt eval time = 6770.55 ms / 533 tokens ( 12.70 ms per token, 78.72 tokens per second) 13.04.356.917 I slot print_timing: id 0 | task 4435 | eval time = 4568.11 ms / 47 tokens ( 99.31 ms per token, 10.07 tokens per second) 13.04.356.918 I slot print_timing: id 0 | task 4435 | total time = 11338.66 ms / 580 tokens 13.04.356.918 I slot print_timing: id 0 | task 4435 | graphs reused = 4133 13.04.356.921 I slot print_timing: id 0 | task 4435 | graph reallocs = 0 / 0 (same size) / (changed size) 13.04.356.958 I slot release: id 0 | task 4435 | stop processing: n_tokens = 591, truncated = 0 13.04.361.426 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 591, t_last = 76215831137 13.04.361.460 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 624.202 MiB) 13.04.380.090 I slot launch_slot_: id 0 | task 4486 | processing task, is_child = 0 13.09.759.571 I slot print_timing: id 0 | task 4486 | prompt processing, n_tokens = 476, progress = 0.99, t = 5.38 s / 88.48 tokens per second 13.15.650.460 I slot print_timing: id 0 | task 4486 | prompt eval time = 5987.76 ms / 480 tokens ( 12.47 ms per token, 80.16 tokens per second) 13.15.650.474 I slot print_timing: id 0 | task 4486 | eval time = 5282.57 ms / 52 tokens ( 103.58 ms per token, 9.65 tokens per second) 13.15.650.477 I slot print_timing: id 0 | task 4486 | total time = 11270.33 ms / 532 tokens 13.15.650.479 I slot print_timing: id 0 | task 4486 | graphs reused = 4182 13.15.650.481 I slot print_timing: id 0 | task 4486 | graph reallocs = 0 / 0 (same size) / (changed size) 13.15.650.720 I slot release: id 0 | task 4486 | stop processing: n_tokens = 560, truncated = 0 13.15.665.359 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 76227124899 13.15.665.432 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 626.515 MiB) 13.15.665.438 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 623.076 MiB) 13.15.694.820 I slot launch_slot_: id 0 | task 4541 | processing task, is_child = 0 13.22.218.647 I slot print_timing: id 0 | task 4541 | prompt processing, n_tokens = 563, progress = 0.99, t = 6.52 s / 86.30 tokens per second 13.27.206.870 I slot print_timing: id 0 | task 4541 | prompt eval time = 7145.99 ms / 567 tokens ( 12.60 ms per token, 79.35 tokens per second) 13.27.206.897 I slot print_timing: id 0 | task 4541 | eval time = 4366.03 ms / 42 tokens ( 106.49 ms per token, 9.39 tokens per second) 13.27.206.900 I slot print_timing: id 0 | task 4541 | total time = 11512.02 ms / 609 tokens 13.27.206.902 I slot print_timing: id 0 | task 4541 | graphs reused = 4222 13.27.206.904 I slot print_timing: id 0 | task 4541 | graph reallocs = 0 / 0 (same size) / (changed size) 13.27.207.095 I slot release: id 0 | task 4541 | stop processing: n_tokens = 637, truncated = 0 13.27.221.182 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 76238681274 13.27.221.262 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 628.703 MiB) 13.27.308.639 I slot launch_slot_: id 0 | task 4587 | processing task, is_child = 0 13.32.710.642 I slot print_timing: id 0 | task 4587 | prompt processing, n_tokens = 502, progress = 0.99, t = 5.40 s / 92.93 tokens per second 13.39.570.926 I slot print_timing: id 0 | task 4587 | prompt eval time = 6014.56 ms / 506 tokens ( 11.89 ms per token, 84.13 tokens per second) 13.39.570.942 I slot print_timing: id 0 | task 4587 | eval time = 6247.69 ms / 63 tokens ( 100.77 ms per token, 9.92 tokens per second) 13.39.570.945 I slot print_timing: id 0 | task 4587 | total time = 12262.25 ms / 569 tokens 13.39.570.947 I slot print_timing: id 0 | task 4587 | graphs reused = 4283 13.39.570.949 I slot print_timing: id 0 | task 4587 | graph reallocs = 0 / 0 (same size) / (changed size) 13.39.571.142 I slot release: id 0 | task 4587 | stop processing: n_tokens = 597, truncated = 0 13.39.584.782 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 597, t_last = 76251045322 13.39.584.864 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 786.708 MiB) 13.39.617.651 I slot launch_slot_: id 0 | task 4653 | processing task, is_child = 0 13.44.309.233 I slot print_timing: id 0 | task 4653 | prompt processing, n_tokens = 432, progress = 0.99, t = 4.69 s / 92.08 tokens per second 13.48.789.406 I slot print_timing: id 0 | task 4653 | prompt eval time = 5300.53 ms / 436 tokens ( 12.16 ms per token, 82.26 tokens per second) 13.48.789.412 I slot print_timing: id 0 | task 4653 | eval time = 3871.21 ms / 40 tokens ( 99.26 ms per token, 10.07 tokens per second) 13.48.789.413 I slot print_timing: id 0 | task 4653 | total time = 9171.74 ms / 476 tokens 13.48.789.413 I slot print_timing: id 0 | task 4653 | graphs reused = 4321 13.48.789.413 I slot print_timing: id 0 | task 4653 | graph reallocs = 0 / 0 (same size) / (changed size) 13.48.789.445 I slot release: id 0 | task 4653 | stop processing: n_tokens = 504, truncated = 0 13.48.794.015 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 76260263624 13.48.794.044 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 790.959 MiB) 13.48.815.027 I slot launch_slot_: id 0 | task 4696 | processing task, is_child = 0 13.54.725.130 I slot print_timing: id 0 | task 4696 | prompt processing, n_tokens = 515, progress = 0.99, t = 5.91 s / 87.14 tokens per second 14.01.630.140 I slot print_timing: id 0 | task 4696 | prompt eval time = 6524.97 ms / 519 tokens ( 12.57 ms per token, 79.54 tokens per second) 14.01.630.152 I slot print_timing: id 0 | task 4696 | eval time = 6290.12 ms / 62 tokens ( 103.12 ms per token, 9.70 tokens per second) 14.01.630.155 I slot print_timing: id 0 | task 4696 | total time = 12815.09 ms / 581 tokens 14.01.630.157 I slot print_timing: id 0 | task 4696 | graphs reused = 4381 14.01.630.159 I slot print_timing: id 0 | task 4696 | graph reallocs = 0 / 0 (same size) / (changed size) 14.01.630.384 I slot release: id 0 | task 4696 | stop processing: n_tokens = 609, truncated = 0 14.01.643.586 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 609, t_last = 76273104564 14.01.643.665 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 794.210 MiB) 14.01.725.321 I slot launch_slot_: id 0 | task 4762 | processing task, is_child = 0 14.06.776.580 I slot print_timing: id 0 | task 4762 | prompt processing, n_tokens = 461, progress = 0.99, t = 5.05 s / 91.26 tokens per second 14.11.855.583 I slot print_timing: id 0 | task 4762 | prompt eval time = 5660.84 ms / 465 tokens ( 12.17 ms per token, 82.14 tokens per second) 14.11.855.589 I slot print_timing: id 0 | task 4762 | eval time = 4469.41 ms / 46 tokens ( 99.32 ms per token, 10.07 tokens per second) 14.11.855.589 I slot print_timing: id 0 | task 4762 | total time = 10130.25 ms / 511 tokens 14.11.855.590 I slot print_timing: id 0 | task 4762 | graphs reused = 4424 14.11.855.590 I slot print_timing: id 0 | task 4762 | graph reallocs = 0 / 0 (same size) / (changed size) 14.11.855.644 I slot release: id 0 | task 4762 | stop processing: n_tokens = 542, truncated = 0 14.11.860.172 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 542, t_last = 76283329823 14.11.860.210 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 792.585 MiB) 14.11.901.220 I slot launch_slot_: id 0 | task 4811 | processing task, is_child = 0 14.16.577.301 I slot print_timing: id 0 | task 4811 | prompt processing, n_tokens = 427, progress = 0.99, t = 4.68 s / 91.32 tokens per second 14.21.234.854 I slot print_timing: id 0 | task 4811 | prompt eval time = 5287.94 ms / 431 tokens ( 12.27 ms per token, 81.51 tokens per second) 14.21.234.857 I slot print_timing: id 0 | task 4811 | eval time = 4045.68 ms / 41 tokens ( 101.14 ms per token, 9.89 tokens per second) 14.21.234.858 I slot print_timing: id 0 | task 4811 | total time = 9333.62 ms / 472 tokens 14.21.234.858 I slot print_timing: id 0 | task 4811 | graphs reused = 4463 14.21.234.859 I slot print_timing: id 0 | task 4811 | graph reallocs = 0 / 0 (same size) / (changed size) 14.21.234.904 I slot release: id 0 | task 4811 | stop processing: n_tokens = 503, truncated = 0 14.21.241.454 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 503, t_last = 76292709083 14.21.241.497 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 632.080 MiB) 14.21.241.500 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 790.021 MiB) 14.21.365.324 I slot launch_slot_: id 0 | task 4855 | processing task, is_child = 0 14.26.687.941 I slot print_timing: id 0 | task 4855 | prompt processing, n_tokens = 453, progress = 0.99, t = 5.32 s / 85.11 tokens per second 14.31.579.421 I slot print_timing: id 0 | task 4855 | prompt eval time = 5934.94 ms / 457 tokens ( 12.99 ms per token, 77.00 tokens per second) 14.31.579.424 I slot print_timing: id 0 | task 4855 | eval time = 4279.15 ms / 44 tokens ( 99.52 ms per token, 10.05 tokens per second) 14.31.579.425 I slot print_timing: id 0 | task 4855 | total time = 10214.08 ms / 501 tokens 14.31.579.425 I slot print_timing: id 0 | task 4855 | graphs reused = 4504 14.31.579.426 I slot print_timing: id 0 | task 4855 | graph reallocs = 0 / 0 (same size) / (changed size) 14.31.579.480 I slot release: id 0 | task 4855 | stop processing: n_tokens = 532, truncated = 0 14.31.585.539 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 532, t_last = 76303053660 14.31.585.569 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 789.396 MiB) 14.31.682.463 I slot launch_slot_: id 0 | task 4902 | processing task, is_child = 0 14.36.378.129 I slot print_timing: id 0 | task 4902 | prompt processing, n_tokens = 435, progress = 0.99, t = 4.70 s / 92.64 tokens per second 14.41.068.619 I slot print_timing: id 0 | task 4902 | prompt eval time = 5309.44 ms / 439 tokens ( 12.09 ms per token, 82.68 tokens per second) 14.41.068.625 I slot print_timing: id 0 | task 4902 | eval time = 4076.70 ms / 42 tokens ( 99.43 ms per token, 10.06 tokens per second) 14.41.068.626 I slot print_timing: id 0 | task 4902 | total time = 9386.14 ms / 481 tokens 14.41.068.626 I slot print_timing: id 0 | task 4902 | graphs reused = 4544 14.41.068.627 I slot print_timing: id 0 | task 4902 | graph reallocs = 0 / 0 (same size) / (changed size) 14.41.068.669 I slot release: id 0 | task 4902 | stop processing: n_tokens = 512, truncated = 0 14.41.074.245 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 512, t_last = 76312542848 14.41.074.283 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 785.082 MiB) 14.41.194.751 I slot launch_slot_: id 0 | task 4947 | processing task, is_child = 0 14.47.768.644 I slot print_timing: id 0 | task 4947 | prompt processing, n_tokens = 602, progress = 0.99, t = 6.57 s / 91.57 tokens per second 14.54.183.582 I slot print_timing: id 0 | task 4947 | prompt eval time = 7516.50 ms / 606 tokens ( 12.40 ms per token, 80.62 tokens per second) 14.54.183.587 I slot print_timing: id 0 | task 4947 | eval time = 5472.32 ms / 56 tokens ( 99.50 ms per token, 10.05 tokens per second) 14.54.183.587 I slot print_timing: id 0 | task 4947 | total time = 12988.82 ms / 662 tokens 14.54.183.588 I slot print_timing: id 0 | task 4947 | graphs reused = 4598 14.54.183.588 I slot print_timing: id 0 | task 4947 | graph reallocs = 0 / 0 (same size) / (changed size) 14.54.183.636 I slot release: id 0 | task 4947 | stop processing: n_tokens = 693, truncated = 0 14.54.188.301 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 76325657815 14.54.188.335 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 783.144 MiB) 14.54.188.343 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 937.584 MiB) 14.54.325.952 I slot launch_slot_: id 0 | task 5007 | processing task, is_child = 0 14.59.366.822 I slot print_timing: id 0 | task 5007 | prompt processing, n_tokens = 473, progress = 0.99, t = 5.04 s / 93.83 tokens per second 15.04.284.612 I slot print_timing: id 0 | task 5007 | prompt eval time = 5979.33 ms / 477 tokens ( 12.54 ms per token, 79.77 tokens per second) 15.04.284.615 I slot print_timing: id 0 | task 5007 | eval time = 3979.32 ms / 41 tokens ( 99.48 ms per token, 10.05 tokens per second) 15.04.284.615 I slot print_timing: id 0 | task 5007 | total time = 9958.64 ms / 518 tokens 15.04.284.616 I slot print_timing: id 0 | task 5007 | graphs reused = 4636 15.04.284.616 I slot print_timing: id 0 | task 5007 | graph reallocs = 0 / 0 (same size) / (changed size) 15.04.284.652 I slot release: id 0 | task 5007 | stop processing: n_tokens = 549, truncated = 0 15.04.290.208 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 76335758831 15.04.290.238 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 785.457 MiB) 15.04.361.373 I slot launch_slot_: id 0 | task 5051 | processing task, is_child = 0 15.08.345.096 I slot print_timing: id 0 | task 5051 | prompt processing, n_tokens = 782, progress = 0.93, t = 3.98 s / 196.30 tokens per second 15.13.731.706 I slot print_timing: id 0 | task 5051 | prompt processing, n_tokens = 841, progress = 1.00, t = 9.37 s / 89.75 tokens per second 15.20.607.823 I slot print_timing: id 0 | task 5051 | prompt eval time = 10369.74 ms / 845 tokens ( 12.27 ms per token, 81.49 tokens per second) 15.20.607.825 I slot print_timing: id 0 | task 5051 | eval time = 5876.70 ms / 60 tokens ( 99.61 ms per token, 10.04 tokens per second) 15.20.607.826 I slot print_timing: id 0 | task 5051 | total time = 16246.44 ms / 905 tokens 15.20.607.826 I slot print_timing: id 0 | task 5051 | graphs reused = 4694 15.20.607.827 I slot print_timing: id 0 | task 5051 | graph reallocs = 0 / 0 (same size) / (changed size) 15.20.607.911 I slot release: id 0 | task 5051 | stop processing: n_tokens = 936, truncated = 0 15.20.612.555 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 936, t_last = 76352082090 15.20.612.599 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 779.643 MiB) 15.20.729.221 I slot launch_slot_: id 0 | task 5115 | processing task, is_child = 0 15.25.797.508 I slot print_timing: id 0 | task 5115 | prompt processing, n_tokens = 455, progress = 0.99, t = 5.07 s / 89.77 tokens per second 15.30.915.837 I slot print_timing: id 0 | task 5115 | prompt eval time = 6007.70 ms / 459 tokens ( 13.09 ms per token, 76.40 tokens per second) 15.30.915.842 I slot print_timing: id 0 | task 5115 | eval time = 4178.89 ms / 43 tokens ( 99.50 ms per token, 10.05 tokens per second) 15.30.915.843 I slot print_timing: id 0 | task 5115 | total time = 10186.60 ms / 502 tokens 15.30.915.843 I slot print_timing: id 0 | task 5115 | graphs reused = 4734 15.30.915.844 I slot print_timing: id 0 | task 5115 | graph reallocs = 0 / 0 (same size) / (changed size) 15.30.915.885 I slot release: id 0 | task 5115 | stop processing: n_tokens = 533, truncated = 0 15.30.921.559 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 533, t_last = 76362390064 15.30.921.592 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 935.834 MiB) 15.30.995.524 I slot launch_slot_: id 0 | task 5161 | processing task, is_child = 0 15.38.265.553 I slot print_timing: id 0 | task 5161 | prompt processing, n_tokens = 666, progress = 0.99, t = 7.27 s / 91.61 tokens per second 15.43.786.974 I slot print_timing: id 0 | task 5161 | prompt eval time = 8211.11 ms / 670 tokens ( 12.26 ms per token, 81.60 tokens per second) 15.43.786.979 I slot print_timing: id 0 | task 5161 | eval time = 4580.32 ms / 47 tokens ( 99.57 ms per token, 10.04 tokens per second) 15.43.786.980 I slot print_timing: id 0 | task 5161 | total time = 12791.43 ms / 717 tokens 15.43.786.980 I slot print_timing: id 0 | task 5161 | graphs reused = 4779 15.43.786.980 I slot print_timing: id 0 | task 5161 | graph reallocs = 0 / 0 (same size) / (changed size) 15.43.787.039 I slot release: id 0 | task 5161 | stop processing: n_tokens = 748, truncated = 0 15.43.792.557 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 748, t_last = 76375261219 15.43.792.593 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 931.645 MiB) 15.43.906.244 I slot launch_slot_: id 0 | task 5212 | processing task, is_child = 0 15.47.172.317 I slot print_timing: id 0 | task 5212 | prompt processing, n_tokens = 731, progress = 0.95, t = 3.27 s / 223.82 tokens per second 15.52.570.341 I slot print_timing: id 0 | task 5212 | prompt processing, n_tokens = 771, progress = 1.00, t = 8.66 s / 88.99 tokens per second 15.59.711.731 I slot print_timing: id 0 | task 5212 | prompt eval time = 9611.09 ms / 775 tokens ( 12.40 ms per token, 80.64 tokens per second) 15.59.711.733 I slot print_timing: id 0 | task 5212 | eval time = 6194.38 ms / 63 tokens ( 99.91 ms per token, 10.01 tokens per second) 15.59.711.734 I slot print_timing: id 0 | task 5212 | total time = 15805.47 ms / 838 tokens 15.59.711.734 I slot print_timing: id 0 | task 5212 | graphs reused = 4840 15.59.711.735 I slot print_timing: id 0 | task 5212 | graph reallocs = 0 / 0 (same size) / (changed size) 15.59.711.795 I slot release: id 0 | task 5212 | stop processing: n_tokens = 869, truncated = 0 15.59.716.839 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 869, t_last = 76391185974 15.59.716.882 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 929.206 MiB) 15.59.869.143 I slot launch_slot_: id 0 | task 5279 | processing task, is_child = 0 16.06.062.000 I slot print_timing: id 0 | task 5279 | prompt processing, n_tokens = 569, progress = 0.99, t = 6.19 s / 91.88 tokens per second 16.13.968.496 I slot print_timing: id 0 | task 5279 | prompt eval time = 7136.22 ms / 573 tokens ( 12.45 ms per token, 80.29 tokens per second) 16.13.968.499 I slot print_timing: id 0 | task 5279 | eval time = 6963.12 ms / 71 tokens ( 99.47 ms per token, 10.05 tokens per second) 16.13.968.500 I slot print_timing: id 0 | task 5279 | total time = 14099.34 ms / 644 tokens 16.13.968.500 I slot print_timing: id 0 | task 5279 | graphs reused = 4909 16.13.968.501 I slot print_timing: id 0 | task 5279 | graph reallocs = 0 / 0 (same size) / (changed size) 16.13.968.545 I slot release: id 0 | task 5279 | stop processing: n_tokens = 675, truncated = 0 16.13.973.447 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 675, t_last = 76405442724 16.13.973.485 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 931.019 MiB) 16.13.973.490 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 929.769 MiB) 16.14.025.019 I slot launch_slot_: id 0 | task 5354 | processing task, is_child = 0 16.19.044.362 I slot print_timing: id 0 | task 5354 | prompt processing, n_tokens = 457, progress = 0.99, t = 5.02 s / 91.05 tokens per second 16.26.250.938 I slot print_timing: id 0 | task 5354 | prompt eval time = 5961.28 ms / 461 tokens ( 12.93 ms per token, 77.33 tokens per second) 16.26.250.943 I slot print_timing: id 0 | task 5354 | eval time = 6264.63 ms / 64 tokens ( 99.44 ms per token, 10.06 tokens per second) 16.26.250.944 I slot print_timing: id 0 | task 5354 | total time = 12225.91 ms / 525 tokens 16.26.250.944 I slot print_timing: id 0 | task 5354 | graphs reused = 4970 16.26.250.945 I slot print_timing: id 0 | task 5354 | graph reallocs = 0 / 0 (same size) / (changed size) 16.26.250.972 I slot release: id 0 | task 5354 | stop processing: n_tokens = 556, truncated = 0 16.26.255.980 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 556, t_last = 76417725151 16.26.256.010 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1090.712 MiB) 16.26.288.758 I slot launch_slot_: id 0 | task 5421 | processing task, is_child = 0 16.33.180.127 I slot print_timing: id 0 | task 5421 | prompt processing, n_tokens = 605, progress = 0.99, t = 6.89 s / 87.79 tokens per second 16.43.648.811 I slot print_timing: id 0 | task 5421 | n_gen = 100, tg = 10.05 t/s, tg_3s = 10.15 t/s 16.45.952.353 I slot print_timing: id 0 | task 5421 | prompt eval time = 7504.55 ms / 609 tokens ( 12.32 ms per token, 81.15 tokens per second) 16.45.952.356 I slot print_timing: id 0 | task 5421 | eval time = 12159.03 ms / 123 tokens ( 99.66 ms per token, 10.03 tokens per second) 16.45.952.357 I slot print_timing: id 0 | task 5421 | total time = 19663.58 ms / 732 tokens 16.45.952.358 I slot print_timing: id 0 | task 5421 | graphs reused = 5091 16.45.952.358 I slot print_timing: id 0 | task 5421 | graph reallocs = 0 / 0 (same size) / (changed size) 16.45.952.403 I slot release: id 0 | task 5421 | stop processing: n_tokens = 763, truncated = 0 16.45.958.916 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 763, t_last = 76437426582 16.45.958.972 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 932.082 MiB) 16.46.010.015 I slot launch_slot_: id 0 | task 5548 | processing task, is_child = 0 16.49.279.345 I slot print_timing: id 0 | task 5548 | prompt processing, n_tokens = 758, progress = 0.96, t = 3.27 s / 231.85 tokens per second 16.55.013.446 I slot print_timing: id 0 | task 5548 | prompt processing, n_tokens = 787, progress = 1.00, t = 9.00 s / 87.41 tokens per second 17.01.612.044 I slot print_timing: id 0 | task 5548 | prompt eval time = 9623.09 ms / 791 tokens ( 12.17 ms per token, 82.20 tokens per second) 17.01.612.049 I slot print_timing: id 0 | task 5548 | eval time = 5978.92 ms / 61 tokens ( 99.65 ms per token, 10.04 tokens per second) 17.01.612.049 I slot print_timing: id 0 | task 5548 | total time = 15602.01 ms / 852 tokens 17.01.612.050 I slot print_timing: id 0 | task 5548 | graphs reused = 5150 17.01.612.050 I slot print_timing: id 0 | task 5548 | graph reallocs = 0 / 0 (same size) / (changed size) 17.01.612.097 I slot release: id 0 | task 5548 | stop processing: n_tokens = 883, truncated = 0 17.01.617.032 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 883, t_last = 76453086276 17.01.617.073 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1105.905 MiB) 17.01.665.015 I slot launch_slot_: id 0 | task 5613 | processing task, is_child = 0 17.07.827.822 I slot print_timing: id 0 | task 5613 | prompt processing, n_tokens = 529, progress = 0.99, t = 6.16 s / 85.84 tokens per second 17.13.914.593 I slot print_timing: id 0 | task 5613 | prompt eval time = 6778.02 ms / 533 tokens ( 12.72 ms per token, 78.64 tokens per second) 17.13.914.598 I slot print_timing: id 0 | task 5613 | eval time = 5471.54 ms / 56 tokens ( 99.48 ms per token, 10.05 tokens per second) 17.13.914.600 I slot print_timing: id 0 | task 5613 | total time = 12249.57 ms / 589 tokens 17.13.914.600 I slot print_timing: id 0 | task 5613 | graphs reused = 5204 17.13.914.601 I slot print_timing: id 0 | task 5613 | graph reallocs = 0 / 0 (same size) / (changed size) 17.13.914.641 I slot release: id 0 | task 5613 | stop processing: n_tokens = 677, truncated = 0 17.13.919.684 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 677, t_last = 76465388821 17.13.949.878 I slot launch_slot_: id 0 | task 5673 | processing task, is_child = 0 17.20.125.002 I slot print_timing: id 0 | task 5673 | prompt processing, n_tokens = 562, progress = 0.99, t = 6.18 s / 91.01 tokens per second 17.25.551.812 I slot print_timing: id 0 | task 5673 | prompt eval time = 7113.66 ms / 566 tokens ( 12.57 ms per token, 79.57 tokens per second) 17.25.551.818 I slot print_timing: id 0 | task 5673 | eval time = 4488.25 ms / 46 tokens ( 99.74 ms per token, 10.03 tokens per second) 17.25.551.818 I slot print_timing: id 0 | task 5673 | total time = 11601.91 ms / 612 tokens 17.25.551.819 I slot print_timing: id 0 | task 5673 | graphs reused = 5248 17.25.551.819 I slot print_timing: id 0 | task 5673 | graph reallocs = 0 / 0 (same size) / (changed size) 17.25.551.876 I slot release: id 0 | task 5673 | stop processing: n_tokens = 643, truncated = 0 17.25.556.917 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 643, t_last = 76477026055 17.25.556.958 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 931.082 MiB) 17.25.585.200 I slot launch_slot_: id 0 | task 5723 | processing task, is_child = 0 17.30.602.636 I slot print_timing: id 0 | task 5723 | prompt processing, n_tokens = 439, progress = 0.99, t = 5.02 s / 87.50 tokens per second 17.35.393.756 I slot print_timing: id 0 | task 5723 | prompt eval time = 5627.74 ms / 443 tokens ( 12.70 ms per token, 78.72 tokens per second) 17.35.393.762 I slot print_timing: id 0 | task 5723 | eval time = 4180.81 ms / 43 tokens ( 99.54 ms per token, 10.05 tokens per second) 17.35.393.762 I slot print_timing: id 0 | task 5723 | total time = 9808.55 ms / 486 tokens 17.35.393.763 I slot print_timing: id 0 | task 5723 | graphs reused = 5288 17.35.393.763 I slot print_timing: id 0 | task 5723 | graph reallocs = 0 / 0 (same size) / (changed size) 17.35.393.801 I slot release: id 0 | task 5723 | stop processing: n_tokens = 517, truncated = 0 17.35.398.804 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 517, t_last = 76486867980 17.35.398.833 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1094.150 MiB) 17.35.425.365 I slot launch_slot_: id 0 | task 5769 | processing task, is_child = 0 17.40.468.473 I slot print_timing: id 0 | task 5769 | prompt processing, n_tokens = 483, progress = 0.99, t = 5.04 s / 95.77 tokens per second 17.47.771.647 I slot print_timing: id 0 | task 5769 | prompt eval time = 5985.53 ms / 487 tokens ( 12.29 ms per token, 81.36 tokens per second) 17.47.771.651 I slot print_timing: id 0 | task 5769 | eval time = 6360.74 ms / 65 tokens ( 99.39 ms per token, 10.06 tokens per second) 17.47.771.651 I slot print_timing: id 0 | task 5769 | total time = 12346.27 ms / 552 tokens 17.47.771.652 I slot print_timing: id 0 | task 5769 | graphs reused = 5351 17.47.771.652 I slot print_timing: id 0 | task 5769 | graph reallocs = 0 / 0 (same size) / (changed size) 17.47.771.698 I slot release: id 0 | task 5769 | stop processing: n_tokens = 583, truncated = 0 17.47.777.182 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 583, t_last = 76499245877 17.47.777.221 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1101.716 MiB) 17.47.813.445 I slot launch_slot_: id 0 | task 5837 | processing task, is_child = 0 17.53.211.307 I slot print_timing: id 0 | task 5837 | prompt processing, n_tokens = 503, progress = 0.99, t = 5.40 s / 93.19 tokens per second 17.58.398.637 I slot print_timing: id 0 | task 5837 | prompt eval time = 6013.52 ms / 507 tokens ( 11.86 ms per token, 84.31 tokens per second) 17.58.398.642 I slot print_timing: id 0 | task 5837 | eval time = 4571.66 ms / 47 tokens ( 99.38 ms per token, 10.06 tokens per second) 17.58.398.643 I slot print_timing: id 0 | task 5837 | total time = 10585.18 ms / 554 tokens 17.58.398.643 I slot print_timing: id 0 | task 5837 | graphs reused = 5396 17.58.398.644 I slot print_timing: id 0 | task 5837 | graph reallocs = 0 / 0 (same size) / (changed size) 17.58.398.684 I slot release: id 0 | task 5837 | stop processing: n_tokens = 585, truncated = 0 17.58.404.234 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 585, t_last = 76509872863 17.58.404.265 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 932.520 MiB) 17.58.426.293 I slot launch_slot_: id 0 | task 5887 | processing task, is_child = 0 18.05.661.882 I slot print_timing: id 0 | task 5887 | prompt processing, n_tokens = 629, progress = 0.99, t = 7.24 s / 86.93 tokens per second 18.12.742.485 I slot print_timing: id 0 | task 5887 | prompt eval time = 7847.00 ms / 633 tokens ( 12.40 ms per token, 80.67 tokens per second) 18.12.742.491 I slot print_timing: id 0 | task 5887 | eval time = 6469.18 ms / 66 tokens ( 99.53 ms per token, 10.05 tokens per second) 18.12.742.491 I slot print_timing: id 0 | task 5887 | total time = 14316.18 ms / 699 tokens 18.12.742.492 I slot print_timing: id 0 | task 5887 | graphs reused = 5460 18.12.742.492 I slot print_timing: id 0 | task 5887 | graph reallocs = 0 / 0 (same size) / (changed size) 18.12.742.530 I slot release: id 0 | task 5887 | stop processing: n_tokens = 730, truncated = 0 18.12.747.499 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 730, t_last = 76524216709 18.12.747.534 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1095.088 MiB) 18.12.774.596 I slot launch_slot_: id 0 | task 5957 | processing task, is_child = 0 18.19.284.403 I slot print_timing: id 0 | task 5957 | prompt processing, n_tokens = 567, progress = 0.99, t = 6.51 s / 87.10 tokens per second 18.24.472.146 I slot print_timing: id 0 | task 5957 | prompt eval time = 7122.60 ms / 571 tokens ( 12.47 ms per token, 80.17 tokens per second) 18.24.472.149 I slot print_timing: id 0 | task 5957 | eval time = 4574.94 ms / 47 tokens ( 99.46 ms per token, 10.05 tokens per second) 18.24.472.150 I slot print_timing: id 0 | task 5957 | total time = 11697.54 ms / 618 tokens 18.24.472.150 I slot print_timing: id 0 | task 5957 | graphs reused = 5505 18.24.472.151 I slot print_timing: id 0 | task 5957 | graph reallocs = 0 / 0 (same size) / (changed size) 18.24.472.187 I slot release: id 0 | task 5957 | stop processing: n_tokens = 649, truncated = 0 18.24.478.120 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 649, t_last = 76535946366 18.24.478.153 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1102.591 MiB) 18.24.503.030 I slot launch_slot_: id 0 | task 6008 | processing task, is_child = 0 18.27.777.818 I slot print_timing: id 0 | task 6008 | prompt processing, n_tokens = 775, progress = 0.97, t = 3.27 s / 236.66 tokens per second 18.33.521.063 I slot print_timing: id 0 | task 6008 | prompt processing, n_tokens = 794, progress = 1.00, t = 9.02 s / 88.05 tokens per second 18.38.420.176 I slot print_timing: id 0 | task 6008 | prompt eval time = 9633.07 ms / 798 tokens ( 12.07 ms per token, 82.84 tokens per second) 18.38.420.178 I slot print_timing: id 0 | task 6008 | eval time = 4284.06 ms / 44 tokens ( 99.63 ms per token, 10.04 tokens per second) 18.38.420.179 I slot print_timing: id 0 | task 6008 | total time = 13917.13 ms / 842 tokens 18.38.420.179 I slot print_timing: id 0 | task 6008 | graphs reused = 5547 18.38.420.180 I slot print_timing: id 0 | task 6008 | graph reallocs = 0 / 0 (same size) / (changed size) 18.38.420.230 I slot release: id 0 | task 6008 | stop processing: n_tokens = 873, truncated = 0 18.38.425.186 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 873, t_last = 76549894409 18.38.425.229 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1239.337 MiB) 18.38.462.404 I slot launch_slot_: id 0 | task 6056 | processing task, is_child = 0 18.44.970.598 I slot print_timing: id 0 | task 6056 | prompt processing, n_tokens = 568, progress = 0.99, t = 6.51 s / 87.27 tokens per second 18.49.763.067 I slot print_timing: id 0 | task 6056 | prompt eval time = 7123.15 ms / 572 tokens ( 12.45 ms per token, 80.30 tokens per second) 18.49.763.073 I slot print_timing: id 0 | task 6056 | eval time = 4177.51 ms / 43 tokens ( 99.46 ms per token, 10.05 tokens per second) 18.49.763.074 I slot print_timing: id 0 | task 6056 | total time = 11300.65 ms / 615 tokens 18.49.763.074 I slot print_timing: id 0 | task 6056 | graphs reused = 5588 18.49.763.075 I slot print_timing: id 0 | task 6056 | graph reallocs = 0 / 0 (same size) / (changed size) 18.49.763.107 I slot release: id 0 | task 6056 | stop processing: n_tokens = 646, truncated = 0 18.49.767.947 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 646, t_last = 76561237286 18.49.767.979 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1087.585 MiB) 18.49.793.187 I slot launch_slot_: id 0 | task 6103 | processing task, is_child = 0 18.56.989.252 I slot print_timing: id 0 | task 6103 | prompt processing, n_tokens = 609, progress = 0.99, t = 7.20 s / 84.63 tokens per second 19.02.389.884 I slot print_timing: id 0 | task 6103 | prompt eval time = 7810.85 ms / 613 tokens ( 12.74 ms per token, 78.48 tokens per second) 19.02.389.890 I slot print_timing: id 0 | task 6103 | eval time = 4785.83 ms / 49 tokens ( 99.70 ms per token, 10.03 tokens per second) 19.02.389.890 I slot print_timing: id 0 | task 6103 | total time = 12596.69 ms / 662 tokens 19.02.389.891 I slot print_timing: id 0 | task 6103 | graphs reused = 5635 19.02.389.891 I slot print_timing: id 0 | task 6103 | graph reallocs = 0 / 0 (same size) / (changed size) 19.02.389.933 I slot release: id 0 | task 6103 | stop processing: n_tokens = 693, truncated = 0 19.02.395.390 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 76573864112 19.02.395.425 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 930.081 MiB) 19.02.420.973 I slot launch_slot_: id 0 | task 6156 | processing task, is_child = 0 19.08.937.301 I slot print_timing: id 0 | task 6156 | prompt processing, n_tokens = 576, progress = 0.99, t = 6.52 s / 88.39 tokens per second 19.15.817.401 I slot print_timing: id 0 | task 6156 | prompt eval time = 7127.02 ms / 580 tokens ( 12.29 ms per token, 81.38 tokens per second) 19.15.817.407 I slot print_timing: id 0 | task 6156 | eval time = 6269.40 ms / 64 tokens ( 99.51 ms per token, 10.05 tokens per second) 19.15.817.407 I slot print_timing: id 0 | task 6156 | total time = 13396.42 ms / 644 tokens 19.15.817.408 I slot print_timing: id 0 | task 6156 | graphs reused = 5697 19.15.817.408 I slot print_timing: id 0 | task 6156 | graph reallocs = 0 / 0 (same size) / (changed size) 19.15.817.456 I slot release: id 0 | task 6156 | stop processing: n_tokens = 675, truncated = 0 19.15.822.738 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 675, t_last = 76587291635 19.15.822.772 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 934.208 MiB) 19.15.848.131 I slot launch_slot_: id 0 | task 6224 | processing task, is_child = 0 19.24.136.259 I slot print_timing: id 0 | task 6224 | prompt processing, n_tokens = 712, progress = 0.99, t = 8.29 s / 85.91 tokens per second 19.29.636.585 I slot print_timing: id 0 | task 6224 | prompt eval time = 8900.98 ms / 716 tokens ( 12.43 ms per token, 80.44 tokens per second) 19.29.636.590 I slot print_timing: id 0 | task 6224 | eval time = 4887.46 ms / 50 tokens ( 99.74 ms per token, 10.03 tokens per second) 19.29.636.591 I slot print_timing: id 0 | task 6224 | total time = 13788.44 ms / 766 tokens 19.29.636.591 I slot print_timing: id 0 | task 6224 | graphs reused = 5744 19.29.636.592 I slot print_timing: id 0 | task 6224 | graph reallocs = 0 / 0 (same size) / (changed size) 19.29.636.626 I slot release: id 0 | task 6224 | stop processing: n_tokens = 797, truncated = 0 19.29.642.066 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 797, t_last = 76601110805 19.29.642.104 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 934.333 MiB) 19.29.678.637 I slot launch_slot_: id 0 | task 6278 | processing task, is_child = 0 19.32.950.713 I slot print_timing: id 0 | task 6278 | prompt processing, n_tokens = 755, progress = 0.95, t = 3.27 s / 230.74 tokens per second 19.38.350.746 I slot print_timing: id 0 | task 6278 | prompt processing, n_tokens = 795, progress = 1.00, t = 8.67 s / 91.67 tokens per second 19.49.161.863 I slot print_timing: id 0 | task 6278 | n_gen = 100, tg = 10.04 t/s, tg_3s = 10.14 t/s 19.49.360.906 I slot print_timing: id 0 | task 6278 | prompt eval time = 9617.94 ms / 799 tokens ( 12.04 ms per token, 83.07 tokens per second) 19.49.360.911 I slot print_timing: id 0 | task 6278 | eval time = 10064.32 ms / 102 tokens ( 99.65 ms per token, 10.04 tokens per second) 19.49.360.912 I slot print_timing: id 0 | task 6278 | total time = 19682.26 ms / 901 tokens 19.49.360.912 I slot print_timing: id 0 | task 6278 | graphs reused = 5844 19.49.360.913 I slot print_timing: id 0 | task 6278 | graph reallocs = 0 / 0 (same size) / (changed size) 19.49.360.951 I slot release: id 0 | task 6278 | stop processing: n_tokens = 932, truncated = 0 19.49.365.101 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 932, t_last = 76620835130 19.49.365.142 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1093.025 MiB) 19.49.404.311 I slot launch_slot_: id 0 | task 6384 | processing task, is_child = 0 19.53.027.952 I slot print_timing: id 0 | task 6384 | prompt processing, n_tokens = 357, progress = 0.99, t = 3.62 s / 98.52 tokens per second 20.03.809.791 I slot print_timing: id 0 | task 6384 | n_gen = 100, tg = 10.06 t/s, tg_3s = 10.16 t/s 20.06.891.608 I slot print_timing: id 0 | task 6384 | n_gen = 131, tg = 10.06 t/s, tg_3s = 10.06 t/s 20.07.487.937 I slot print_timing: id 0 | task 6384 | prompt eval time = 4566.39 ms / 361 tokens ( 12.65 ms per token, 79.06 tokens per second) 20.07.487.943 I slot print_timing: id 0 | task 6384 | eval time = 13517.22 ms / 137 tokens ( 99.39 ms per token, 10.06 tokens per second) 20.07.487.943 I slot print_timing: id 0 | task 6384 | total time = 18083.61 ms / 498 tokens 20.07.487.944 I slot print_timing: id 0 | task 6384 | graphs reused = 5978 20.07.487.944 I slot print_timing: id 0 | task 6384 | graph reallocs = 0 / 0 (same size) / (changed size) 20.07.487.971 I slot release: id 0 | task 6384 | stop processing: n_tokens = 529, truncated = 0 20.07.493.305 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 529, t_last = 76638962150 20.07.493.346 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1087.961 MiB) 20.07.516.472 I slot launch_slot_: id 0 | task 6524 | processing task, is_child = 0 20.11.488.954 I slot print_timing: id 0 | task 6524 | prompt processing, n_tokens = 377, progress = 0.99, t = 3.97 s / 94.90 tokens per second 20.22.280.018 I slot print_timing: id 0 | task 6524 | n_gen = 100, tg = 10.06 t/s, tg_3s = 10.16 t/s 20.23.077.989 I slot print_timing: id 0 | task 6524 | prompt eval time = 4922.70 ms / 381 tokens ( 12.92 ms per token, 77.40 tokens per second) 20.23.077.991 I slot print_timing: id 0 | task 6524 | eval time = 10638.81 ms / 108 tokens ( 99.43 ms per token, 10.06 tokens per second) 20.23.077.992 I slot print_timing: id 0 | task 6524 | total time = 15561.51 ms / 489 tokens 20.23.077.992 I slot print_timing: id 0 | task 6524 | graphs reused = 6083 20.23.077.993 I slot print_timing: id 0 | task 6524 | graph reallocs = 0 / 0 (same size) / (changed size) 20.23.078.032 I slot release: id 0 | task 6524 | stop processing: n_tokens = 520, truncated = 0 20.23.083.052 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 76654552211 20.23.083.088 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1101.966 MiB) 20.23.105.328 I slot launch_slot_: id 0 | task 6635 | processing task, is_child = 0 20.26.692.214 I slot print_timing: id 0 | task 6635 | prompt processing, n_tokens = 361, progress = 0.99, t = 3.59 s / 100.64 tokens per second 20.37.477.826 I slot print_timing: id 0 | task 6635 | n_gen = 100, tg = 10.06 t/s, tg_3s = 10.16 t/s 20.39.865.864 I slot print_timing: id 0 | task 6635 | prompt eval time = 4530.56 ms / 365 tokens ( 12.41 ms per token, 80.56 tokens per second) 20.39.865.867 I slot print_timing: id 0 | task 6635 | eval time = 12229.97 ms / 124 tokens ( 99.43 ms per token, 10.06 tokens per second) 20.39.865.868 I slot print_timing: id 0 | task 6635 | total time = 16760.53 ms / 489 tokens 20.39.865.868 I slot print_timing: id 0 | task 6635 | graphs reused = 6204 20.39.865.869 I slot print_timing: id 0 | task 6635 | graph reallocs = 0 / 0 (same size) / (changed size) 20.39.865.904 I slot release: id 0 | task 6635 | stop processing: n_tokens = 520, truncated = 0 20.39.870.597 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 76671340083 20.39.870.625 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1087.773 MiB) 20.39.892.688 I slot launch_slot_: id 0 | task 6762 | processing task, is_child = 0 20.43.494.847 I slot print_timing: id 0 | task 6762 | prompt processing, n_tokens = 329, progress = 0.99, t = 3.60 s / 91.33 tokens per second 20.54.286.714 I slot print_timing: id 0 | task 6762 | n_gen = 100, tg = 10.05 t/s, tg_3s = 10.15 t/s 20.54.982.756 I slot print_timing: id 0 | task 6762 | prompt eval time = 4545.36 ms / 333 tokens ( 13.65 ms per token, 73.26 tokens per second) 20.54.982.761 I slot print_timing: id 0 | task 6762 | eval time = 10544.70 ms / 107 tokens ( 99.48 ms per token, 10.05 tokens per second) 20.54.982.761 I slot print_timing: id 0 | task 6762 | total time = 15090.06 ms / 440 tokens 20.54.982.762 I slot print_timing: id 0 | task 6762 | graphs reused = 6309 20.54.982.762 I slot print_timing: id 0 | task 6762 | graph reallocs = 0 / 0 (same size) / (changed size) 20.54.982.789 I slot release: id 0 | task 6762 | stop processing: n_tokens = 471, truncated = 0 20.54.987.875 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 471, t_last = 76686456968 20.55.017.421 I slot launch_slot_: id 0 | task 6872 | processing task, is_child = 0 20.59.315.922 I slot print_timing: id 0 | task 6872 | prompt processing, n_tokens = 399, progress = 0.99, t = 4.30 s / 92.82 tokens per second 21.10.101.884 I slot print_timing: id 0 | task 6872 | n_gen = 100, tg = 10.05 t/s, tg_3s = 10.15 t/s 21.13.181.817 I slot print_timing: id 0 | task 6872 | n_gen = 131, tg = 10.06 t/s, tg_3s = 10.07 t/s 21.16.263.136 I slot print_timing: id 0 | task 6872 | n_gen = 162, tg = 10.06 t/s, tg_3s = 10.06 t/s 21.19.343.394 I slot print_timing: id 0 | task 6872 | n_gen = 193, tg = 10.06 t/s, tg_3s = 10.06 t/s 21.19.542.065 I slot print_timing: id 0 | task 6872 | prompt eval time = 5236.62 ms / 403 tokens ( 12.99 ms per token, 76.96 tokens per second) 21.19.542.070 I slot print_timing: id 0 | task 6872 | eval time = 19288.01 ms / 195 tokens ( 99.42 ms per token, 10.06 tokens per second) 21.19.542.070 I slot print_timing: id 0 | task 6872 | total time = 24524.63 ms / 598 tokens 21.19.542.071 I slot print_timing: id 0 | task 6872 | graphs reused = 6501 21.19.542.071 I slot print_timing: id 0 | task 6872 | graph reallocs = 0 / 0 (same size) / (changed size) 21.19.542.097 I slot release: id 0 | task 6872 | stop processing: n_tokens = 629, truncated = 0 21.19.546.512 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 629, t_last = 76711016277 21.19.546.549 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1090.712 MiB) 21.19.568.963 I slot launch_slot_: id 0 | task 7070 | processing task, is_child = 0 21.23.540.653 I slot print_timing: id 0 | task 7070 | prompt processing, n_tokens = 407, progress = 0.99, t = 3.97 s / 102.48 tokens per second 21.34.696.873 I slot print_timing: id 0 | task 7070 | n_gen = 100, tg = 10.06 t/s, tg_3s = 10.16 t/s 21.37.776.913 I slot print_timing: id 0 | task 7070 | n_gen = 131, tg = 10.06 t/s, tg_3s = 10.06 t/s 21.40.857.361 I slot print_timing: id 0 | task 7070 | n_gen = 162, tg = 10.06 t/s, tg_3s = 10.06 t/s 21.43.142.742 I slot print_timing: id 0 | task 7070 | prompt eval time = 5289.44 ms / 411 tokens ( 12.87 ms per token, 77.70 tokens per second) 21.43.142.747 I slot print_timing: id 0 | task 7070 | eval time = 18284.33 ms / 185 tokens ( 99.37 ms per token, 10.06 tokens per second) 21.43.142.748 I slot print_timing: id 0 | task 7070 | total time = 23573.77 ms / 596 tokens 21.43.142.748 I slot print_timing: id 0 | task 7070 | graphs reused = 6683 21.43.142.749 I slot print_timing: id 0 | task 7070 | graph reallocs = 0 / 0 (same size) / (changed size) 21.43.142.774 I slot release: id 0 | task 7070 | stop processing: n_tokens = 627, truncated = 0 21.43.147.711 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 627, t_last = 76734616953 21.43.147.743 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1089.586 MiB) 21.43.169.971 I slot launch_slot_: id 0 | task 7258 | processing task, is_child = 0 21.47.834.465 I slot print_timing: id 0 | task 7258 | prompt processing, n_tokens = 486, progress = 0.99, t = 4.66 s / 104.19 tokens per second 21.59.326.008 I slot print_timing: id 0 | task 7258 | n_gen = 100, tg = 10.06 t/s, tg_3s = 10.16 t/s 22.02.407.427 I slot print_timing: id 0 | task 7258 | n_gen = 131, tg = 10.06 t/s, tg_3s = 10.06 t/s 22.05.492.066 I slot print_timing: id 0 | task 7258 | n_gen = 162, tg = 10.06 t/s, tg_3s = 10.05 t/s 22.08.575.781 I slot print_timing: id 0 | task 7258 | n_gen = 193, tg = 10.06 t/s, tg_3s = 10.05 t/s 22.11.661.821 I slot print_timing: id 0 | task 7258 | n_gen = 224, tg = 10.05 t/s, tg_3s = 10.05 t/s 22.11.761.230 I slot print_timing: id 0 | task 7258 | prompt eval time = 6313.23 ms / 490 tokens ( 12.88 ms per token, 77.61 tokens per second) 22.11.761.232 I slot print_timing: id 0 | task 7258 | eval time = 22278.02 ms / 225 tokens ( 99.46 ms per token, 10.05 tokens per second) 22.11.761.233 I slot print_timing: id 0 | task 7258 | total time = 28591.25 ms / 715 tokens 22.11.761.233 I slot print_timing: id 0 | task 7258 | graphs reused = 6906 22.11.761.234 I slot print_timing: id 0 | task 7258 | graph reallocs = 0 / 0 (same size) / (changed size) 22.11.761.265 I slot release: id 0 | task 7258 | stop processing: n_tokens = 746, truncated = 0 22.11.766.400 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 746, t_last = 76763235444 22.11.766.440 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1097.214 MiB) 22.11.788.967 I slot launch_slot_: id 0 | task 7486 | processing task, is_child = 0 22.15.054.885 I slot print_timing: id 0 | task 7486 | prompt processing, n_tokens = 340, progress = 0.99, t = 3.27 s / 104.11 tokens per second 22.20.438.569 I slot print_timing: id 0 | task 7486 | prompt eval time = 4573.23 ms / 344 tokens ( 13.29 ms per token, 75.22 tokens per second) 22.20.438.574 I slot print_timing: id 0 | task 7486 | eval time = 4076.36 ms / 42 tokens ( 99.42 ms per token, 10.06 tokens per second) 22.20.438.574 I slot print_timing: id 0 | task 7486 | total time = 8649.59 ms / 386 tokens 22.20.438.575 I slot print_timing: id 0 | task 7486 | graphs reused = 6946 22.20.438.575 I slot print_timing: id 0 | task 7486 | graph reallocs = 0 / 0 (same size) / (changed size) 22.20.438.600 I slot release: id 0 | task 7486 | stop processing: n_tokens = 417, truncated = 0 22.20.442.825 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 417, t_last = 76771912779 22.20.442.853 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1105.655 MiB) 22.20.468.105 I slot launch_slot_: id 0 | task 7531 | processing task, is_child = 0 22.23.729.503 I slot print_timing: id 0 | task 7531 | prompt processing, n_tokens = 343, progress = 0.99, t = 3.26 s / 105.17 tokens per second 22.34.877.653 I slot print_timing: id 0 | task 7531 | n_gen = 100, tg = 10.06 t/s, tg_3s = 10.17 t/s 22.37.977.137 I slot print_timing: id 0 | task 7531 | n_gen = 131, tg = 10.05 t/s, tg_3s = 10.00 t/s 22.41.030.976 I slot print_timing: id 0 | task 7531 | n_gen = 159, tg = 9.88 t/s, tg_3s = 9.17 t/s 22.42.340.668 I slot print_timing: id 0 | task 7531 | prompt eval time = 4572.94 ms / 347 tokens ( 13.18 ms per token, 75.88 tokens per second) 22.42.340.694 I slot print_timing: id 0 | task 7531 | eval time = 17299.59 ms / 171 tokens ( 101.76 ms per token, 9.83 tokens per second) 22.42.340.696 I slot print_timing: id 0 | task 7531 | total time = 21872.53 ms / 518 tokens 22.42.340.698 I slot print_timing: id 0 | task 7531 | graphs reused = 7114 22.42.340.700 I slot print_timing: id 0 | task 7531 | graph reallocs = 0 / 0 (same size) / (changed size) 22.42.340.816 I slot release: id 0 | task 7531 | stop processing: n_tokens = 549, truncated = 0 22.42.352.932 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 76793814995 22.42.353.027 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 930.832 MiB) 22.42.387.877 I slot launch_slot_: id 0 | task 7705 | processing task, is_child = 0 22.46.004.145 I slot print_timing: id 0 | task 7705 | prompt processing, n_tokens = 397, progress = 0.99, t = 3.62 s / 109.78 tokens per second 22.57.169.732 I slot print_timing: id 0 | task 7705 | n_gen = 100, tg = 10.06 t/s, tg_3s = 10.16 t/s 22.59.753.366 I slot print_timing: id 0 | task 7705 | prompt eval time = 4941.10 ms / 401 tokens ( 12.32 ms per token, 81.16 tokens per second) 22.59.753.372 I slot print_timing: id 0 | task 7705 | eval time = 12424.38 ms / 126 tokens ( 99.40 ms per token, 10.06 tokens per second) 22.59.753.372 I slot print_timing: id 0 | task 7705 | total time = 17365.48 ms / 527 tokens 22.59.753.373 I slot print_timing: id 0 | task 7705 | graphs reused = 7237 22.59.753.373 I slot print_timing: id 0 | task 7705 | graph reallocs = 0 / 0 (same size) / (changed size) 22.59.753.399 I slot release: id 0 | task 7705 | stop processing: n_tokens = 558, truncated = 0 22.59.758.054 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 76811227578 22.59.758.084 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 930.269 MiB) 22.59.780.826 I slot launch_slot_: id 0 | task 7834 | processing task, is_child = 0 23.03.763.206 I slot print_timing: id 0 | task 7834 | prompt processing, n_tokens = 452, progress = 0.99, t = 3.98 s / 113.50 tokens per second 23.15.277.481 I slot print_timing: id 0 | task 7834 | n_gen = 100, tg = 10.04 t/s, tg_3s = 10.15 t/s 23.16.768.068 I slot print_timing: id 0 | task 7834 | prompt eval time = 5639.94 ms / 456 tokens ( 12.37 ms per token, 80.85 tokens per second) 23.16.768.071 I slot print_timing: id 0 | task 7834 | eval time = 11347.29 ms / 115 tokens ( 99.54 ms per token, 10.05 tokens per second) 23.16.768.071 I slot print_timing: id 0 | task 7834 | total time = 16987.23 ms / 571 tokens 23.16.768.071 I slot print_timing: id 0 | task 7834 | graphs reused = 7349 23.16.768.072 I slot print_timing: id 0 | task 7834 | graph reallocs = 0 / 0 (same size) / (changed size) 23.16.768.102 I slot release: id 0 | task 7834 | stop processing: n_tokens = 602, truncated = 0 23.16.773.181 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 23.16.773.221 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 930.269 MiB) 23.16.797.242 I slot launch_slot_: id 0 | task 7952 | processing task, is_child = 0 23.20.407.034 I slot print_timing: id 0 | task 7952 | prompt processing, n_tokens = 402, progress = 0.99, t = 3.61 s / 111.36 tokens per second 23.31.889.960 I slot print_timing: id 0 | task 7952 | n_gen = 100, tg = 10.06 t/s, tg_3s = 10.16 t/s 23.33.082.362 I slot print_timing: id 0 | task 7952 | prompt eval time = 5252.83 ms / 406 tokens ( 12.94 ms per token, 77.29 tokens per second) 23.33.082.364 I slot print_timing: id 0 | task 7952 | eval time = 11032.28 ms / 112 tokens ( 99.39 ms per token, 10.06 tokens per second) 23.33.082.365 I slot print_timing: id 0 | task 7952 | total time = 16285.11 ms / 518 tokens 23.33.082.365 I slot print_timing: id 0 | task 7952 | graphs reused = 7458 23.33.082.366 I slot print_timing: id 0 | task 7952 | graph reallocs = 0 / 0 (same size) / (changed size) 23.33.082.392 I slot release: id 0 | task 7952 | stop processing: n_tokens = 549, truncated = 0 23.33.087.471 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 76844556571 23.33.087.510 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 927.205 MiB) 23.33.112.731 I slot launch_slot_: id 0 | task 8067 | processing task, is_child = 0 23.36.730.335 I slot print_timing: id 0 | task 8067 | prompt processing, n_tokens = 402, progress = 0.99, t = 3.62 s / 111.12 tokens per second 23.47.901.029 I slot print_timing: id 0 | task 8067 | n_gen = 100, tg = 10.05 t/s, tg_3s = 10.16 t/s 23.50.982.808 I slot print_timing: id 0 | task 8067 | n_gen = 131, tg = 10.06 t/s, tg_3s = 10.06 t/s 23.54.063.278 I slot print_timing: id 0 | task 8067 | n_gen = 162, tg = 10.06 t/s, tg_3s = 10.06 t/s 23.55.752.759 I slot print_timing: id 0 | task 8067 | prompt eval time = 4942.43 ms / 406 tokens ( 12.17 ms per token, 82.15 tokens per second) 23.55.752.761 I slot print_timing: id 0 | task 8067 | eval time = 17697.59 ms / 179 tokens ( 99.42 ms per token, 10.06 tokens per second) 23.55.752.762 I slot print_timing: id 0 | task 8067 | total time = 22640.01 ms / 585 tokens 23.55.752.763 I slot print_timing: id 0 | task 8067 | graphs reused = 7634 23.55.752.763 I slot print_timing: id 0 | task 8067 | graph reallocs = 0 / 0 (same size) / (changed size) 23.55.752.788 I slot release: id 0 | task 8067 | stop processing: n_tokens = 616, truncated = 0 23.55.757.462 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 616, t_last = 76867226967 23.55.757.499 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 937.084 MiB) 23.55.780.747 I slot launch_slot_: id 0 | task 8249 | processing task, is_child = 0 23.59.751.609 I slot print_timing: id 0 | task 8249 | prompt processing, n_tokens = 440, progress = 0.99, t = 3.97 s / 110.81 tokens per second 24.11.251.528 I slot print_timing: id 0 | task 8249 | n_gen = 100, tg = 10.06 t/s, tg_3s = 10.16 t/s 24.14.332.713 I slot print_timing: id 0 | task 8249 | n_gen = 131, tg = 10.06 t/s, tg_3s = 10.06 t/s 24.15.624.403 I slot print_timing: id 0 | task 8249 | prompt eval time = 5629.34 ms / 444 tokens ( 12.68 ms per token, 78.87 tokens per second) 24.15.624.407 I slot print_timing: id 0 | task 8249 | eval time = 14214.31 ms / 144 tokens ( 99.40 ms per token, 10.06 tokens per second) 24.15.624.407 I slot print_timing: id 0 | task 8249 | total time = 19843.65 ms / 588 tokens 24.15.624.408 I slot print_timing: id 0 | task 8249 | graphs reused = 7775 24.15.624.408 I slot print_timing: id 0 | task 8249 | graph reallocs = 0 / 0 (same size) / (changed size) 24.15.624.448 I slot release: id 0 | task 8249 | stop processing: n_tokens = 619, truncated = 0 24.15.628.614 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 619, t_last = 76887098627 24.15.628.646 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 936.959 MiB) 24.15.650.772 I slot launch_slot_: id 0 | task 8396 | processing task, is_child = 0 24.19.262.271 I slot print_timing: id 0 | task 8396 | prompt processing, n_tokens = 368, progress = 0.99, t = 3.61 s / 101.90 tokens per second 24.30.409.734 I slot print_timing: id 0 | task 8396 | n_gen = 100, tg = 10.06 t/s, tg_3s = 10.16 t/s 24.30.707.749 I slot print_timing: id 0 | task 8396 | prompt eval time = 4921.10 ms / 372 tokens ( 13.23 ms per token, 75.59 tokens per second) 24.30.707.753 I slot print_timing: id 0 | task 8396 | eval time = 10135.87 ms / 103 tokens ( 99.37 ms per token, 10.06 tokens per second) 24.30.707.753 I slot print_timing: id 0 | task 8396 | total time = 15056.97 ms / 475 tokens 24.30.707.754 I slot print_timing: id 0 | task 8396 | graphs reused = 7876 24.30.707.754 I slot print_timing: id 0 | task 8396 | graph reallocs = 0 / 0 (same size) / (changed size) 24.30.707.786 I slot release: id 0 | task 8396 | stop processing: n_tokens = 506, truncated = 0 24.30.712.875 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 506, t_last = 76902181965 24.30.712.911 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 944.399 MiB) 24.30.734.911 I slot launch_slot_: id 0 | task 8502 | processing task, is_child = 0 24.34.705.344 I slot print_timing: id 0 | task 8502 | prompt processing, n_tokens = 450, progress = 0.99, t = 3.97 s / 113.34 tokens per second 24.46.212.766 I slot print_timing: id 0 | task 8502 | n_gen = 100, tg = 10.07 t/s, tg_3s = 10.17 t/s 24.49.295.094 I slot print_timing: id 0 | task 8502 | n_gen = 131, tg = 10.06 t/s, tg_3s = 10.06 t/s 24.52.376.154 I slot print_timing: id 0 | task 8502 | n_gen = 162, tg = 10.06 t/s, tg_3s = 10.06 t/s 24.55.458.723 I slot print_timing: id 0 | task 8502 | n_gen = 193, tg = 10.06 t/s, tg_3s = 10.06 t/s 24.58.542.231 I slot print_timing: id 0 | task 8502 | n_gen = 224, tg = 10.06 t/s, tg_3s = 10.05 t/s 24.59.140.163 I slot print_timing: id 0 | task 8502 | prompt eval time = 5641.88 ms / 454 tokens ( 12.43 ms per token, 80.47 tokens per second) 24.59.140.165 I slot print_timing: id 0 | task 8502 | eval time = 22763.36 ms / 230 tokens ( 99.40 ms per token, 10.06 tokens per second) 24.59.140.165 I slot print_timing: id 0 | task 8502 | total time = 28405.24 ms / 684 tokens 24.59.140.166 I slot print_timing: id 0 | task 8502 | graphs reused = 8103 24.59.140.166 I slot print_timing: id 0 | task 8502 | graph reallocs = 0 / 0 (same size) / (changed size) 24.59.140.193 I slot release: id 0 | task 8502 | stop processing: n_tokens = 715, truncated = 0 24.59.145.198 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 715, t_last = 76930614372 24.59.145.244 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 923.829 MiB) 24.59.167.162 I slot launch_slot_: id 0 | task 8735 | processing task, is_child = 0 25.02.777.389 I slot print_timing: id 0 | task 8735 | prompt processing, n_tokens = 350, progress = 0.99, t = 3.61 s / 96.95 tokens per second 25.13.569.834 I slot print_timing: id 0 | task 8735 | n_gen = 100, tg = 10.06 t/s, tg_3s = 10.16 t/s 25.16.655.863 I slot print_timing: id 0 | task 8735 | n_gen = 131, tg = 10.06 t/s, tg_3s = 10.05 t/s 25.19.737.167 I slot print_timing: id 0 | task 8735 | n_gen = 162, tg = 10.06 t/s, tg_3s = 10.06 t/s 25.22.817.778 I slot print_timing: id 0 | task 8735 | n_gen = 193, tg = 10.06 t/s, tg_3s = 10.06 t/s 25.25.897.316 I slot print_timing: id 0 | task 8735 | n_gen = 224, tg = 10.06 t/s, tg_3s = 10.07 t/s 25.28.382.454 I slot print_timing: id 0 | task 8735 | prompt eval time = 4561.38 ms / 354 tokens ( 12.89 ms per token, 77.61 tokens per second) 25.28.382.460 I slot print_timing: id 0 | task 8735 | eval time = 24653.90 ms / 249 tokens ( 99.41 ms per token, 10.06 tokens per second) 25.28.382.460 I slot print_timing: id 0 | task 8735 | total time = 29215.28 ms / 603 tokens 25.28.382.461 I slot print_timing: id 0 | task 8735 | graphs reused = 8349 25.28.382.461 I slot print_timing: id 0 | task 8735 | graph reallocs = 0 / 0 (same size) / (changed size) 25.28.382.487 I slot release: id 0 | task 8735 | stop processing: n_tokens = 634, truncated = 0 25.28.387.408 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 634, t_last = 76959856666 25.28.387.459 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 932.082 MiB) 25.28.411.755 I slot launch_slot_: id 0 | task 8987 | processing task, is_child = 0 25.32.015.245 I slot print_timing: id 0 | task 8987 | prompt processing, n_tokens = 330, progress = 0.99, t = 3.60 s / 91.58 tokens per second 25.42.791.974 I slot print_timing: id 0 | task 8987 | n_gen = 100, tg = 10.06 t/s, tg_3s = 10.17 t/s 25.45.870.808 I slot print_timing: id 0 | task 8987 | n_gen = 131, tg = 10.06 t/s, tg_3s = 10.07 t/s 25.46.765.100 I slot print_timing: id 0 | task 8987 | prompt eval time = 4542.85 ms / 334 tokens ( 13.60 ms per token, 73.52 tokens per second) 25.46.765.106 I slot print_timing: id 0 | task 8987 | eval time = 13810.48 ms / 140 tokens ( 99.36 ms per token, 10.06 tokens per second) 25.46.765.106 I slot print_timing: id 0 | task 8987 | total time = 18353.33 ms / 474 tokens 25.46.765.107 I slot print_timing: id 0 | task 8987 | graphs reused = 8487 25.46.765.107 I slot print_timing: id 0 | task 8987 | graph reallocs = 0 / 0 (same size) / (changed size) 25.46.765.136 I slot release: id 0 | task 8987 | stop processing: n_tokens = 505, truncated = 0 25.46.769.665 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 505, t_last = 76978239315 25.46.769.697 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 932.645 MiB) 25.46.791.525 I slot launch_slot_: id 0 | task 9130 | processing task, is_child = 0 25.50.777.824 I slot print_timing: id 0 | task 9130 | prompt processing, n_tokens = 422, progress = 0.99, t = 3.99 s / 105.86 tokens per second 26.01.936.313 I slot print_timing: id 0 | task 9130 | n_gen = 100, tg = 10.06 t/s, tg_3s = 10.16 t/s 26.05.016.279 I slot print_timing: id 0 | task 9130 | n_gen = 131, tg = 10.06 t/s, tg_3s = 10.07 t/s 26.08.097.324 I slot print_timing: id 0 | task 9130 | n_gen = 162, tg = 10.06 t/s, tg_3s = 10.06 t/s 26.09.389.448 I slot print_timing: id 0 | task 9130 | prompt eval time = 5304.21 ms / 426 tokens ( 12.45 ms per token, 80.31 tokens per second) 26.09.389.451 I slot print_timing: id 0 | task 9130 | eval time = 17293.70 ms / 175 tokens ( 99.39 ms per token, 10.06 tokens per second) 26.09.389.451 I slot print_timing: id 0 | task 9130 | total time = 22597.91 ms / 601 tokens 26.09.389.452 I slot print_timing: id 0 | task 9130 | graphs reused = 8659 26.09.389.452 I slot print_timing: id 0 | task 9130 | graph reallocs = 0 / 0 (same size) / (changed size) 26.09.389.482 I slot release: id 0 | task 9130 | stop processing: n_tokens = 632, truncated = 0 26.09.393.609 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 632, t_last = 77000863661 26.09.393.656 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 935.396 MiB) 26.09.415.806 I slot launch_slot_: id 0 | task 9308 | processing task, is_child = 0 26.13.034.650 I slot print_timing: id 0 | task 9308 | prompt processing, n_tokens = 362, progress = 0.99, t = 3.62 s / 100.03 tokens per second 26.23.826.316 I slot print_timing: id 0 | task 9308 | n_gen = 100, tg = 10.06 t/s, tg_3s = 10.16 t/s 26.25.518.103 I slot print_timing: id 0 | task 9308 | prompt eval time = 4571.30 ms / 366 tokens ( 12.49 ms per token, 80.06 tokens per second) 26.25.518.105 I slot print_timing: id 0 | task 9308 | eval time = 11530.99 ms / 117 tokens ( 99.41 ms per token, 10.06 tokens per second) 26.25.518.106 I slot print_timing: id 0 | task 9308 | total time = 16102.29 ms / 483 tokens 26.25.518.106 I slot print_timing: id 0 | task 9308 | graphs reused = 8773 26.25.518.107 I slot print_timing: id 0 | task 9308 | graph reallocs = 0 / 0 (same size) / (changed size) 26.25.518.135 I slot release: id 0 | task 9308 | stop processing: n_tokens = 514, truncated = 0 26.25.522.545 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 514, t_last = 77016992314 26.25.522.576 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 932.082 MiB) 26.25.544.152 I slot launch_slot_: id 0 | task 9428 | processing task, is_child = 0 26.29.171.172 I slot print_timing: id 0 | task 9428 | prompt processing, n_tokens = 458, progress = 0.99, t = 3.63 s / 126.27 tokens per second 26.41.019.439 I slot print_timing: id 0 | task 9428 | n_gen = 100, tg = 10.06 t/s, tg_3s = 10.16 t/s 26.44.100.552 I slot print_timing: id 0 | task 9428 | n_gen = 131, tg = 10.06 t/s, tg_3s = 10.06 t/s 26.47.182.297 I slot print_timing: id 0 | task 9428 | n_gen = 162, tg = 10.06 t/s, tg_3s = 10.06 t/s 26.50.262.575 I slot print_timing: id 0 | task 9428 | n_gen = 193, tg = 10.06 t/s, tg_3s = 10.06 t/s 26.53.346.101 I slot print_timing: id 0 | task 9428 | n_gen = 224, tg = 10.06 t/s, tg_3s = 10.05 t/s 26.56.431.573 I slot print_timing: id 0 | task 9428 | n_gen = 255, tg = 10.06 t/s, tg_3s = 10.05 t/s 26.56.929.416 I slot print_timing: id 0 | task 9428 | prompt eval time = 5637.19 ms / 462 tokens ( 12.20 ms per token, 81.96 tokens per second) 26.56.929.422 I slot print_timing: id 0 | task 9428 | eval time = 25748.07 ms / 260 tokens ( 99.41 ms per token, 10.06 tokens per second) 26.56.929.423 I slot print_timing: id 0 | task 9428 | total time = 31385.25 ms / 722 tokens 26.56.929.423 I slot print_timing: id 0 | task 9428 | graphs reused = 9030 26.56.929.424 I slot print_timing: id 0 | task 9428 | graph reallocs = 0 / 0 (same size) / (changed size) 26.56.929.464 I slot release: id 0 | task 9428 | stop processing: n_tokens = 753, truncated = 0 26.56.934.530 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 753, t_last = 77048403643 26.56.934.575 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 936.271 MiB) 26.56.956.979 I slot launch_slot_: id 0 | task 9691 | processing task, is_child = 0 27.00.227.014 I slot print_timing: id 0 | task 9691 | prompt processing, n_tokens = 392, progress = 0.99, t = 3.27 s / 119.88 tokens per second 27.11.724.323 I slot print_timing: id 0 | task 9691 | n_gen = 100, tg = 10.06 t/s, tg_3s = 10.16 t/s 27.14.802.218 I slot print_timing: id 0 | task 9691 | n_gen = 131, tg = 10.06 t/s, tg_3s = 10.07 t/s 27.17.285.361 I slot print_timing: id 0 | task 9691 | prompt eval time = 4926.80 ms / 396 tokens ( 12.44 ms per token, 80.38 tokens per second) 27.17.285.364 I slot print_timing: id 0 | task 9691 | eval time = 15401.57 ms / 156 tokens ( 99.36 ms per token, 10.06 tokens per second) 27.17.285.365 I slot print_timing: id 0 | task 9691 | total time = 20328.37 ms / 552 tokens 27.17.285.365 I slot print_timing: id 0 | task 9691 | graphs reused = 9183 27.17.285.366 I slot print_timing: id 0 | task 9691 | graph reallocs = 0 / 0 (same size) / (changed size) 27.17.285.396 I slot release: id 0 | task 9691 | stop processing: n_tokens = 583, truncated = 0 27.17.289.284 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 583, t_last = 77068759575 27.17.289.317 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 936.459 MiB) 27.17.311.362 I slot launch_slot_: id 0 | task 9850 | processing task, is_child = 0 27.21.604.241 I slot print_timing: id 0 | task 9850 | prompt processing, n_tokens = 454, progress = 0.99, t = 4.29 s / 105.76 tokens per second 27.33.092.538 I slot print_timing: id 0 | task 9850 | n_gen = 100, tg = 10.06 t/s, tg_3s = 10.16 t/s 27.36.171.654 I slot print_timing: id 0 | task 9850 | n_gen = 131, tg = 10.06 t/s, tg_3s = 10.07 t/s 27.39.251.389 I slot print_timing: id 0 | task 9850 | n_gen = 162, tg = 10.06 t/s, tg_3s = 10.07 t/s 27.41.040.726 I slot print_timing: id 0 | task 9850 | prompt eval time = 5940.77 ms / 458 tokens ( 12.97 ms per token, 77.09 tokens per second) 27.41.040.731 I slot print_timing: id 0 | task 9850 | eval time = 17788.59 ms / 180 tokens ( 99.38 ms per token, 10.06 tokens per second) 27.41.040.732 I slot print_timing: id 0 | task 9850 | total time = 23729.35 ms / 638 tokens 27.41.040.732 I slot print_timing: id 0 | task 9850 | graphs reused = 9360 27.41.040.733 I slot print_timing: id 0 | task 9850 | graph reallocs = 0 / 0 (same size) / (changed size) 27.41.040.763 I slot release: id 0 | task 9850 | stop processing: n_tokens = 669, truncated = 0 27.41.045.572 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 669, t_last = 77092514942 27.41.045.609 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 929.394 MiB) 27.41.068.686 I slot launch_slot_: id 0 | task 10033 | processing task, is_child = 0 27.44.680.184 I slot print_timing: id 0 | task 10033 | prompt processing, n_tokens = 454, progress = 0.99, t = 3.61 s / 125.71 tokens per second 27.55.860.913 I slot print_timing: id 0 | task 10033 | prompt eval time = 5629.81 ms / 458 tokens ( 12.29 ms per token, 81.35 tokens per second) 27.55.860.916 I slot print_timing: id 0 | task 10033 | eval time = 9162.40 ms / 93 tokens ( 99.59 ms per token, 10.04 tokens per second) 27.55.860.916 I slot print_timing: id 0 | task 10033 | total time = 14792.22 ms / 551 tokens 27.55.860.917 I slot print_timing: id 0 | task 10033 | graphs reused = 9450 27.55.860.917 I slot print_timing: id 0 | task 10033 | graph reallocs = 0 / 0 (same size) / (changed size) 27.55.860.944 I slot release: id 0 | task 10033 | stop processing: n_tokens = 582, truncated = 0 27.55.865.950 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 582, t_last = 77107335123 27.55.865.981 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 942.461 MiB) 27.55.887.637 I slot launch_slot_: id 0 | task 10129 | processing task, is_child = 0 27.59.870.902 I slot print_timing: id 0 | task 10129 | prompt processing, n_tokens = 448, progress = 0.99, t = 3.98 s / 112.47 tokens per second 28.11.366.246 I slot print_timing: id 0 | task 10129 | n_gen = 100, tg = 10.06 t/s, tg_3s = 10.16 t/s 28.14.445.453 I slot print_timing: id 0 | task 10129 | n_gen = 131, tg = 10.06 t/s, tg_3s = 10.07 t/s 28.17.526.245 I slot print_timing: id 0 | task 10129 | n_gen = 162, tg = 10.06 t/s, tg_3s = 10.06 t/s 28.20.607.362 I slot print_timing: id 0 | task 10129 | n_gen = 193, tg = 10.06 t/s, tg_3s = 10.06 t/s 28.23.690.664 I slot print_timing: id 0 | task 10129 | n_gen = 224, tg = 10.06 t/s, tg_3s = 10.05 t/s 28.26.776.441 I slot print_timing: id 0 | task 10129 | n_gen = 255, tg = 10.06 t/s, tg_3s = 10.05 t/s 28.29.864.527 I slot print_timing: id 0 | task 10129 | n_gen = 286, tg = 10.06 t/s, tg_3s = 10.04 t/s 28.32.551.180 I slot print_timing: id 0 | task 10129 | prompt eval time = 5634.81 ms / 452 tokens ( 12.47 ms per token, 80.22 tokens per second) 28.32.551.182 I slot print_timing: id 0 | task 10129 | eval time = 31028.72 ms / 313 tokens ( 99.45 ms per token, 10.06 tokens per second) 28.32.551.183 I slot print_timing: id 0 | task 10129 | total time = 36663.52 ms / 765 tokens 28.32.551.183 I slot print_timing: id 0 | task 10129 | graphs reused = 9759 28.32.551.184 I slot print_timing: id 0 | task 10129 | graph reallocs = 0 / 0 (same size) / (changed size) 28.32.551.215 I slot release: id 0 | task 10129 | stop processing: n_tokens = 796, truncated = 0 28.32.555.635 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 796, t_last = 77144025394 28.32.555.676 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 937.397 MiB) 28.32.578.107 I slot launch_slot_: id 0 | task 10445 | processing task, is_child = 0 28.36.185.648 I slot print_timing: id 0 | task 10445 | prompt processing, n_tokens = 400, progress = 0.99, t = 3.61 s / 110.88 tokens per second 28.47.688.667 I slot print_timing: id 0 | task 10445 | n_gen = 100, tg = 10.04 t/s, tg_3s = 10.14 t/s 28.49.675.591 I slot print_timing: id 0 | task 10445 | prompt eval time = 5253.36 ms / 404 tokens ( 13.00 ms per token, 76.90 tokens per second) 28.49.675.594 I slot print_timing: id 0 | task 10445 | eval time = 11844.11 ms / 120 tokens ( 99.53 ms per token, 10.05 tokens per second) 28.49.675.594 I slot print_timing: id 0 | task 10445 | total time = 17097.47 ms / 524 tokens 28.49.675.595 I slot print_timing: id 0 | task 10445 | graphs reused = 9876 28.49.675.595 I slot print_timing: id 0 | task 10445 | graph reallocs = 0 / 0 (same size) / (changed size) 28.49.675.620 I slot release: id 0 | task 10445 | stop processing: n_tokens = 555, truncated = 0 28.49.680.042 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 555, t_last = 77161149799 28.49.680.073 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 929.331 MiB) 28.49.702.087 I slot launch_slot_: id 0 | task 10568 | processing task, is_child = 0 28.53.309.380 I slot print_timing: id 0 | task 10568 | prompt processing, n_tokens = 341, progress = 0.99, t = 3.61 s / 94.53 tokens per second 29.04.093.965 I slot print_timing: id 0 | task 10568 | n_gen = 100, tg = 10.06 t/s, tg_3s = 10.16 t/s 29.04.689.793 I slot print_timing: id 0 | task 10568 | prompt eval time = 4551.41 ms / 345 tokens ( 13.19 ms per token, 75.80 tokens per second) 29.04.689.798 I slot print_timing: id 0 | task 10568 | eval time = 10436.29 ms / 106 tokens ( 99.39 ms per token, 10.06 tokens per second) 29.04.689.799 I slot print_timing: id 0 | task 10568 | total time = 14987.70 ms / 451 tokens 29.04.689.799 I slot print_timing: id 0 | task 10568 | graphs reused = 9980 29.04.689.800 I slot print_timing: id 0 | task 10568 | graph reallocs = 0 / 0 (same size) / (changed size) 29.04.689.824 I slot release: id 0 | task 10568 | stop processing: n_tokens = 482, truncated = 0 29.04.694.727 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 482, t_last = 77176164003 29.04.694.763 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 937.272 MiB) 29.04.716.333 I slot launch_slot_: id 0 | task 10677 | processing task, is_child = 0 29.08.320.340 I slot print_timing: id 0 | task 10677 | prompt processing, n_tokens = 426, progress = 0.99, t = 3.60 s / 118.20 tokens per second 29.20.169.985 I slot print_timing: id 0 | task 10677 | n_gen = 100, tg = 10.06 t/s, tg_3s = 10.16 t/s 29.21.957.995 I slot print_timing: id 0 | task 10677 | prompt eval time = 5612.35 ms / 430 tokens ( 13.05 ms per token, 76.62 tokens per second) 29.21.958.000 I slot print_timing: id 0 | task 10677 | eval time = 11629.30 ms / 118 tokens ( 99.40 ms per token, 10.06 tokens per second) 29.21.958.001 I slot print_timing: id 0 | task 10677 | total time = 17241.65 ms / 548 tokens 29.21.958.001 I slot print_timing: id 0 | task 10677 | graphs reused = 10095 29.21.958.002 I slot print_timing: id 0 | task 10677 | graph reallocs = 0 / 0 (same size) / (changed size) 29.21.958.028 I slot release: id 0 | task 10677 | stop processing: n_tokens = 579, truncated = 0 29.21.962.198 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 579, t_last = 77193432207 29.21.962.228 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 929.894 MiB) 29.21.983.847 I slot launch_slot_: id 0 | task 10798 | processing task, is_child = 0 29.25.249.774 I slot print_timing: id 0 | task 10798 | prompt processing, n_tokens = 312, progress = 0.99, t = 3.27 s / 95.53 tokens per second 29.34.555.372 I slot print_timing: id 0 | task 10798 | prompt eval time = 4207.89 ms / 316 tokens ( 13.32 ms per token, 75.10 tokens per second) 29.34.555.375 I slot print_timing: id 0 | task 10798 | eval time = 8363.62 ms / 85 tokens ( 99.57 ms per token, 10.04 tokens per second) 29.34.555.375 I slot print_timing: id 0 | task 10798 | total time = 12571.51 ms / 401 tokens 29.34.555.376 I slot print_timing: id 0 | task 10798 | graphs reused = 10178 29.34.555.376 I slot print_timing: id 0 | task 10798 | graph reallocs = 0 / 0 (same size) / (changed size) 29.34.555.407 I slot release: id 0 | task 10798 | stop processing: n_tokens = 432, truncated = 0 29.34.560.075 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 432, t_last = 77206029586 29.34.560.105 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 944.837 MiB) 29.34.584.124 I slot launch_slot_: id 0 | task 10886 | processing task, is_child = 0 29.38.183.730 I slot print_timing: id 0 | task 10886 | prompt processing, n_tokens = 350, progress = 0.99, t = 3.60 s / 97.23 tokens per second 29.49.636.026 I slot print_timing: id 0 | task 10886 | n_gen = 100, tg = 9.44 t/s, tg_3s = 9.53 t/s 29.52.572.537 I slot print_timing: id 0 | task 10886 | prompt eval time = 4559.49 ms / 354 tokens ( 12.88 ms per token, 77.64 tokens per second) 29.52.572.552 I slot print_timing: id 0 | task 10886 | eval time = 13428.89 ms / 127 tokens ( 106.58 ms per token, 9.38 tokens per second) 29.52.572.560 I slot print_timing: id 0 | task 10886 | total time = 17988.38 ms / 481 tokens 29.52.572.562 I slot print_timing: id 0 | task 10886 | graphs reused = 10303 29.52.572.564 I slot print_timing: id 0 | task 10886 | graph reallocs = 0 / 0 (same size) / (changed size) 29.52.572.676 I slot release: id 0 | task 10886 | stop processing: n_tokens = 512, truncated = 0 29.52.585.333 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 512, t_last = 77224046856 29.52.585.406 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 934.208 MiB) 29.52.620.933 I slot launch_slot_: id 0 | task 11016 | processing task, is_child = 0 29.57.295.223 I slot print_timing: id 0 | task 11016 | prompt processing, n_tokens = 434, progress = 0.99, t = 4.67 s / 92.85 tokens per second 30.07.886.590 I slot print_timing: id 0 | task 11016 | prompt eval time = 5619.85 ms / 438 tokens ( 12.83 ms per token, 77.94 tokens per second) 30.07.886.593 I slot print_timing: id 0 | task 11016 | eval time = 9645.79 ms / 98 tokens ( 99.44 ms per token, 10.06 tokens per second) 30.07.886.594 I slot print_timing: id 0 | task 11016 | total time = 15265.64 ms / 536 tokens 30.07.886.594 I slot print_timing: id 0 | task 11016 | graphs reused = 10398 30.07.886.594 I slot print_timing: id 0 | task 11016 | graph reallocs = 0 / 0 (same size) / (changed size) 30.07.886.624 I slot release: id 0 | task 11016 | stop processing: n_tokens = 567, truncated = 0 30.07.891.453 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 567, t_last = 77239360803 30.07.891.489 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 939.585 MiB) 30.07.913.285 I slot launch_slot_: id 0 | task 11117 | processing task, is_child = 0 30.12.933.450 I slot print_timing: id 0 | task 11117 | prompt processing, n_tokens = 453, progress = 0.99, t = 5.02 s / 90.24 tokens per second 30.20.735.238 I slot print_timing: id 0 | task 11117 | prompt eval time = 5959.93 ms / 457 tokens ( 13.04 ms per token, 76.68 tokens per second) 30.20.735.247 I slot print_timing: id 0 | task 11117 | eval time = 6862.01 ms / 70 tokens ( 99.45 ms per token, 10.06 tokens per second) 30.20.735.248 I slot print_timing: id 0 | task 11117 | total time = 12821.94 ms / 527 tokens 30.20.735.248 I slot print_timing: id 0 | task 11117 | graphs reused = 10465 30.20.735.249 I slot print_timing: id 0 | task 11117 | graph reallocs = 0 / 0 (same size) / (changed size) 30.20.735.278 I slot release: id 0 | task 11117 | stop processing: n_tokens = 558, truncated = 0 30.20.740.369 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 77252209457 30.20.740.402 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 934.145 MiB) 30.20.762.083 I slot launch_slot_: id 0 | task 11190 | processing task, is_child = 0 30.25.441.558 I slot print_timing: id 0 | task 11190 | prompt processing, n_tokens = 469, progress = 0.99, t = 4.68 s / 100.23 tokens per second 30.36.397.483 I slot print_timing: id 0 | task 11190 | prompt eval time = 5988.23 ms / 473 tokens ( 12.66 ms per token, 78.99 tokens per second) 30.36.397.491 I slot print_timing: id 0 | task 11190 | eval time = 9647.16 ms / 98 tokens ( 99.46 ms per token, 10.05 tokens per second) 30.36.397.491 I slot print_timing: id 0 | task 11190 | total time = 15635.39 ms / 571 tokens 30.36.397.492 I slot print_timing: id 0 | task 11190 | graphs reused = 10560 30.36.397.492 I slot print_timing: id 0 | task 11190 | graph reallocs = 0 / 0 (same size) / (changed size) 30.36.397.534 I slot release: id 0 | task 11190 | stop processing: n_tokens = 602, truncated = 0 30.36.402.193 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 602, t_last = 77267871713 30.36.402.224 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 947.525 MiB) 30.36.424.284 I slot launch_slot_: id 0 | task 11291 | processing task, is_child = 0 30.41.447.024 I slot print_timing: id 0 | task 11291 | prompt processing, n_tokens = 472, progress = 0.99, t = 5.02 s / 93.97 tokens per second 30.44.989.449 I slot print_timing: id 0 | task 11291 | prompt eval time = 5973.05 ms / 476 tokens ( 12.55 ms per token, 79.69 tokens per second) 30.44.989.454 I slot print_timing: id 0 | task 11291 | eval time = 2592.11 ms / 27 tokens ( 99.70 ms per token, 10.03 tokens per second) 30.44.989.455 I slot print_timing: id 0 | task 11291 | total time = 8565.16 ms / 503 tokens 30.44.989.456 I slot print_timing: id 0 | task 11291 | graphs reused = 10584 30.44.989.456 I slot print_timing: id 0 | task 11291 | graph reallocs = 0 / 0 (same size) / (changed size) 30.44.989.489 I slot release: id 0 | task 11291 | stop processing: n_tokens = 534, truncated = 0 30.44.994.021 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 534, t_last = 77276463668 30.44.994.058 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 932.457 MiB) 30.45.016.110 I slot launch_slot_: id 0 | task 11321 | processing task, is_child = 0 30.49.682.485 I slot print_timing: id 0 | task 11321 | prompt processing, n_tokens = 462, progress = 0.99, t = 4.67 s / 99.01 tokens per second 31.00.839.939 I slot print_timing: id 0 | task 11321 | n_gen = 100, tg = 10.06 t/s, tg_3s = 10.16 t/s 31.01.536.143 I slot print_timing: id 0 | task 11321 | prompt eval time = 5982.73 ms / 466 tokens ( 12.84 ms per token, 77.89 tokens per second) 31.01.536.147 I slot print_timing: id 0 | task 11321 | eval time = 10537.29 ms / 107 tokens ( 99.41 ms per token, 10.06 tokens per second) 31.01.536.148 I slot print_timing: id 0 | task 11321 | total time = 16520.02 ms / 573 tokens 31.01.536.148 I slot print_timing: id 0 | task 11321 | graphs reused = 10688 31.01.536.149 I slot print_timing: id 0 | task 11321 | graph reallocs = 0 / 0 (same size) / (changed size) 31.01.536.188 I slot release: id 0 | task 11321 | stop processing: n_tokens = 604, truncated = 0 31.01.540.931 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 604, t_last = 77293010367 31.01.540.965 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 927.893 MiB) 31.01.563.894 I slot launch_slot_: id 0 | task 11431 | processing task, is_child = 0 31.05.875.356 I slot print_timing: id 0 | task 11431 | prompt processing, n_tokens = 411, progress = 0.99, t = 4.31 s / 95.33 tokens per second 31.14.469.068 I slot print_timing: id 0 | task 11431 | prompt eval time = 5250.82 ms / 415 tokens ( 12.65 ms per token, 79.04 tokens per second) 31.14.469.074 I slot print_timing: id 0 | task 11431 | eval time = 7654.35 ms / 78 tokens ( 99.41 ms per token, 10.06 tokens per second) 31.14.469.075 I slot print_timing: id 0 | task 11431 | total time = 12905.16 ms / 493 tokens 31.14.469.075 I slot print_timing: id 0 | task 11431 | graphs reused = 10763 31.14.469.076 I slot print_timing: id 0 | task 11431 | graph reallocs = 0 / 0 (same size) / (changed size) 31.14.469.102 I slot release: id 0 | task 11431 | stop processing: n_tokens = 524, truncated = 0 31.14.473.190 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 524, t_last = 77305943281 31.14.473.219 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 933.958 MiB) 31.14.494.711 I slot launch_slot_: id 0 | task 11512 | processing task, is_child = 0 31.18.115.165 I slot print_timing: id 0 | task 11512 | prompt processing, n_tokens = 348, progress = 0.99, t = 3.62 s / 96.12 tokens per second 31.25.319.609 I slot print_timing: id 0 | task 11512 | prompt eval time = 4559.06 ms / 352 tokens ( 12.95 ms per token, 77.21 tokens per second) 31.25.319.612 I slot print_timing: id 0 | task 11512 | eval time = 6265.83 ms / 64 tokens ( 99.46 ms per token, 10.05 tokens per second) 31.25.319.612 I slot print_timing: id 0 | task 11512 | total time = 10824.88 ms / 416 tokens 31.25.319.613 I slot print_timing: id 0 | task 11512 | graphs reused = 10825 31.25.319.613 I slot print_timing: id 0 | task 11512 | graph reallocs = 0 / 0 (same size) / (changed size) 31.25.319.642 I slot release: id 0 | task 11512 | stop processing: n_tokens = 447, truncated = 0 31.25.324.683 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 77316793821 31.25.324.716 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 924.767 MiB) 31.25.347.020 I slot launch_slot_: id 0 | task 11579 | processing task, is_child = 0 31.31.500.799 I slot print_timing: id 0 | task 11579 | prompt processing, n_tokens = 546, progress = 0.99, t = 6.15 s / 88.73 tokens per second 31.42.296.042 I slot print_timing: id 0 | task 11579 | n_gen = 100, tg = 10.05 t/s, tg_3s = 10.16 t/s 31.45.379.918 I slot print_timing: id 0 | task 11579 | n_gen = 131, tg = 10.05 t/s, tg_3s = 10.05 t/s 31.48.466.032 I slot print_timing: id 0 | task 11579 | n_gen = 162, tg = 10.05 t/s, tg_3s = 10.04 t/s 31.48.565.582 I slot print_timing: id 0 | task 11579 | prompt eval time = 7101.93 ms / 550 tokens ( 12.91 ms per token, 77.44 tokens per second) 31.48.565.585 I slot print_timing: id 0 | task 11579 | eval time = 16116.62 ms / 163 tokens ( 99.49 ms per token, 10.05 tokens per second) 31.48.565.585 I slot print_timing: id 0 | task 11579 | total time = 23218.55 ms / 713 tokens 31.48.565.586 I slot print_timing: id 0 | task 11579 | graphs reused = 10986 31.48.565.586 I slot print_timing: id 0 | task 11579 | graph reallocs = 0 / 0 (same size) / (changed size) 31.48.565.615 I slot release: id 0 | task 11579 | stop processing: n_tokens = 744, truncated = 0 31.48.571.508 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 744, t_last = 77340039794 31.48.571.550 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 929.769 MiB) 31.48.596.755 I slot launch_slot_: id 0 | task 11746 | processing task, is_child = 0 31.55.452.438 I slot print_timing: id 0 | task 11746 | prompt processing, n_tokens = 768, progress = 1.00, t = 6.86 s / 112.02 tokens per second 32.07.690.355 I slot print_timing: id 0 | task 11746 | n_gen = 100, tg = 10.04 t/s, tg_3s = 10.14 t/s 32.10.775.778 I slot print_timing: id 0 | task 11746 | n_gen = 131, tg = 10.04 t/s, tg_3s = 10.05 t/s 32.13.863.706 I slot print_timing: id 0 | task 11746 | n_gen = 162, tg = 10.04 t/s, tg_3s = 10.04 t/s 32.16.951.900 I slot print_timing: id 0 | task 11746 | n_gen = 193, tg = 10.04 t/s, tg_3s = 10.04 t/s 32.20.044.417 I slot print_timing: id 0 | task 11746 | n_gen = 224, tg = 10.04 t/s, tg_3s = 10.02 t/s 32.22.834.393 I slot print_timing: id 0 | task 11746 | prompt eval time = 9233.82 ms / 772 tokens ( 11.96 ms per token, 83.61 tokens per second) 32.22.834.398 I slot print_timing: id 0 | task 11746 | eval time = 25003.81 ms / 252 tokens ( 99.62 ms per token, 10.04 tokens per second) 32.22.834.399 I slot print_timing: id 0 | task 11746 | total time = 34237.63 ms / 1024 tokens 32.22.834.399 I slot print_timing: id 0 | task 11746 | graphs reused = 11235 32.22.834.400 I slot print_timing: id 0 | task 11746 | graph reallocs = 0 / 0 (same size) / (changed size) 32.22.834.449 I slot release: id 0 | task 11746 | stop processing: n_tokens = 1055, truncated = 0 32.22.840.228 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1055, t_last = 77374308628 32.22.840.284 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 933.208 MiB) 32.22.881.086 I slot launch_slot_: id 0 | task 12002 | processing task, is_child = 0 32.29.738.849 I slot print_timing: id 0 | task 12002 | prompt processing, n_tokens = 679, progress = 0.99, t = 6.86 s / 99.01 tokens per second 32.41.252.839 I slot print_timing: id 0 | task 12002 | n_gen = 100, tg = 10.04 t/s, tg_3s = 10.14 t/s 32.44.338.220 I slot print_timing: id 0 | task 12002 | n_gen = 131, tg = 10.04 t/s, tg_3s = 10.05 t/s 32.47.424.524 I slot print_timing: id 0 | task 12002 | n_gen = 162, tg = 10.04 t/s, tg_3s = 10.04 t/s 32.50.510.711 I slot print_timing: id 0 | task 12002 | n_gen = 193, tg = 10.04 t/s, tg_3s = 10.04 t/s 32.51.306.903 I slot print_timing: id 0 | task 12002 | prompt eval time = 8513.02 ms / 683 tokens ( 12.46 ms per token, 80.23 tokens per second) 32.51.306.909 I slot print_timing: id 0 | task 12002 | eval time = 19912.79 ms / 201 tokens ( 99.56 ms per token, 10.04 tokens per second) 32.51.306.909 I slot print_timing: id 0 | task 12002 | total time = 28425.81 ms / 884 tokens 32.51.306.910 I slot print_timing: id 0 | task 12002 | graphs reused = 11433 32.51.306.910 I slot print_timing: id 0 | task 12002 | graph reallocs = 0 / 0 (same size) / (changed size) 32.51.306.942 I slot release: id 0 | task 12002 | stop processing: n_tokens = 915, truncated = 0 32.51.312.256 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 915, t_last = 77402781121 32.51.312.297 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 932.645 MiB) 32.51.338.560 I slot launch_slot_: id 0 | task 12207 | processing task, is_child = 0 32.56.787.210 I slot print_timing: id 0 | task 12207 | prompt processing, n_tokens = 575, progress = 0.99, t = 5.45 s / 105.53 tokens per second 33.08.300.388 I slot print_timing: id 0 | task 12207 | n_gen = 100, tg = 10.06 t/s, tg_3s = 10.16 t/s 33.11.385.331 I slot print_timing: id 0 | task 12207 | n_gen = 131, tg = 10.05 t/s, tg_3s = 10.05 t/s 33.14.474.862 I slot print_timing: id 0 | task 12207 | n_gen = 162, tg = 10.05 t/s, tg_3s = 10.03 t/s 33.17.559.785 I slot print_timing: id 0 | task 12207 | n_gen = 193, tg = 10.05 t/s, tg_3s = 10.05 t/s 33.20.644.248 I slot print_timing: id 0 | task 12207 | n_gen = 224, tg = 10.05 t/s, tg_3s = 10.05 t/s 33.22.535.920 I slot print_timing: id 0 | task 12207 | prompt eval time = 7117.52 ms / 579 tokens ( 12.29 ms per token, 81.35 tokens per second) 33.22.535.922 I slot print_timing: id 0 | task 12207 | eval time = 24079.83 ms / 243 tokens ( 99.50 ms per token, 10.05 tokens per second) 33.22.535.923 I slot print_timing: id 0 | task 12207 | total time = 31197.35 ms / 822 tokens 33.22.535.923 I slot print_timing: id 0 | task 12207 | graphs reused = 11673 33.22.535.924 I slot print_timing: id 0 | task 12207 | graph reallocs = 0 / 0 (same size) / (changed size) 33.22.535.958 I slot release: id 0 | task 12207 | stop processing: n_tokens = 853, truncated = 0 33.22.540.755 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 853, t_last = 77434010137 33.22.540.794 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 935.396 MiB) 33.22.566.455 I slot launch_slot_: id 0 | task 12454 | processing task, is_child = 0 33.27.941.038 I slot print_timing: id 0 | task 12454 | prompt processing, n_tokens = 496, progress = 0.99, t = 5.37 s / 92.29 tokens per second 33.38.733.187 I slot print_timing: id 0 | task 12454 | n_gen = 100, tg = 10.06 t/s, tg_3s = 10.16 t/s 33.39.329.295 I slot print_timing: id 0 | task 12454 | prompt eval time = 6326.05 ms / 500 tokens ( 12.65 ms per token, 79.04 tokens per second) 33.39.329.297 I slot print_timing: id 0 | task 12454 | eval time = 10436.78 ms / 106 tokens ( 99.40 ms per token, 10.06 tokens per second) 33.39.329.298 I slot print_timing: id 0 | task 12454 | total time = 16762.83 ms / 606 tokens 33.39.329.298 I slot print_timing: id 0 | task 12454 | graphs reused = 11777 33.39.329.299 I slot print_timing: id 0 | task 12454 | graph reallocs = 0 / 0 (same size) / (changed size) 33.39.329.327 I slot release: id 0 | task 12454 | stop processing: n_tokens = 637, truncated = 0 33.39.334.541 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 77450803506 33.39.334.577 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 931.144 MiB) 33.39.368.857 I slot launch_slot_: id 0 | task 12563 | processing task, is_child = 0 33.42.618.397 I slot print_timing: id 0 | task 12563 | prompt processing, n_tokens = 613, progress = 0.80, t = 3.25 s / 188.64 tokens per second 33.46.909.696 I slot print_timing: id 0 | task 12563 | prompt processing, n_tokens = 772, progress = 1.00, t = 7.54 s / 102.38 tokens per second 33.58.802.989 I slot print_timing: id 0 | task 12563 | n_gen = 100, tg = 10.04 t/s, tg_3s = 10.14 t/s 34.01.889.606 I slot print_timing: id 0 | task 12563 | n_gen = 131, tg = 10.04 t/s, tg_3s = 10.04 t/s 34.04.977.675 I slot print_timing: id 0 | task 12563 | n_gen = 162, tg = 10.04 t/s, tg_3s = 10.04 t/s 34.08.063.122 I slot print_timing: id 0 | task 12563 | n_gen = 193, tg = 10.04 t/s, tg_3s = 10.05 t/s 34.09.657.986 I slot print_timing: id 0 | task 12563 | prompt eval time = 9575.33 ms / 776 tokens ( 12.34 ms per token, 81.04 tokens per second) 34.09.657.992 I slot print_timing: id 0 | task 12563 | eval time = 20713.79 ms / 209 tokens ( 99.59 ms per token, 10.04 tokens per second) 34.09.657.992 I slot print_timing: id 0 | task 12563 | total time = 30289.12 ms / 985 tokens 34.09.657.993 I slot print_timing: id 0 | task 12563 | graphs reused = 11984 34.09.657.993 I slot print_timing: id 0 | task 12563 | graph reallocs = 0 / 0 (same size) / (changed size) 34.09.658.029 I slot release: id 0 | task 12563 | stop processing: n_tokens = 1016, truncated = 0 34.09.663.219 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1016, t_last = 77481132209 34.09.663.263 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 935.521 MiB) 34.09.663.270 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 930.519 MiB) 34.09.702.853 I slot launch_slot_: id 0 | task 12776 | processing task, is_child = 0 34.14.728.209 I slot print_timing: id 0 | task 12776 | prompt processing, n_tokens = 500, progress = 0.99, t = 5.03 s / 99.50 tokens per second 34.25.881.828 I slot print_timing: id 0 | task 12776 | n_gen = 100, tg = 10.06 t/s, tg_3s = 10.16 t/s 34.28.963.140 I slot print_timing: id 0 | task 12776 | n_gen = 131, tg = 10.06 t/s, tg_3s = 10.06 t/s 34.32.046.567 I slot print_timing: id 0 | task 12776 | n_gen = 162, tg = 10.06 t/s, tg_3s = 10.05 t/s 34.35.132.149 I slot print_timing: id 0 | task 12776 | n_gen = 193, tg = 10.06 t/s, tg_3s = 10.05 t/s 34.35.530.475 I slot print_timing: id 0 | task 12776 | prompt eval time = 6338.20 ms / 504 tokens ( 12.58 ms per token, 79.52 tokens per second) 34.35.530.484 I slot print_timing: id 0 | task 12776 | eval time = 19489.41 ms / 197 tokens ( 99.44 ms per token, 10.06 tokens per second) 34.35.530.485 I slot print_timing: id 0 | task 12776 | total time = 25827.61 ms / 701 tokens 34.35.530.485 I slot print_timing: id 0 | task 12776 | graphs reused = 12179 34.35.530.486 I slot print_timing: id 0 | task 12776 | graph reallocs = 0 / 0 (same size) / (changed size) 34.35.530.524 I slot release: id 0 | task 12776 | stop processing: n_tokens = 732, truncated = 0 34.35.535.342 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 732, t_last = 77507004703 34.35.535.380 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 925.705 MiB) 34.35.569.596 I slot launch_slot_: id 0 | task 12976 | processing task, is_child = 0 34.41.716.993 I slot print_timing: id 0 | task 12976 | prompt processing, n_tokens = 629, progress = 0.99, t = 6.15 s / 102.32 tokens per second 34.53.236.627 I slot print_timing: id 0 | task 12976 | n_gen = 100, tg = 10.04 t/s, tg_3s = 10.15 t/s 34.56.325.294 I slot print_timing: id 0 | task 12976 | n_gen = 131, tg = 10.04 t/s, tg_3s = 10.04 t/s 34.57.121.381 I slot print_timing: id 0 | task 12976 | prompt eval time = 7810.00 ms / 633 tokens ( 12.34 ms per token, 81.05 tokens per second) 34.57.121.387 I slot print_timing: id 0 | task 12976 | eval time = 13741.77 ms / 139 tokens ( 99.58 ms per token, 10.04 tokens per second) 34.57.121.387 I slot print_timing: id 0 | task 12976 | total time = 21551.77 ms / 772 tokens 34.57.121.388 I slot print_timing: id 0 | task 12976 | graphs reused = 12315 34.57.121.388 I slot print_timing: id 0 | task 12976 | graph reallocs = 0 / 0 (same size) / (changed size) 34.57.121.425 I slot release: id 0 | task 12976 | stop processing: n_tokens = 803, truncated = 0 34.57.125.713 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 803, t_last = 77528595604 34.57.125.754 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1093.900 MiB) 34.57.151.267 I slot launch_slot_: id 0 | task 13119 | processing task, is_child = 0 35.01.131.575 I slot print_timing: id 0 | task 13119 | prompt processing, n_tokens = 391, progress = 0.99, t = 3.98 s / 98.23 tokens per second 35.08.445.779 I slot print_timing: id 0 | task 13119 | prompt eval time = 4932.02 ms / 395 tokens ( 12.49 ms per token, 80.09 tokens per second) 35.08.445.784 I slot print_timing: id 0 | task 13119 | eval time = 6362.48 ms / 65 tokens ( 99.41 ms per token, 10.06 tokens per second) 35.08.445.785 I slot print_timing: id 0 | task 13119 | total time = 11294.50 ms / 460 tokens 35.08.445.785 I slot print_timing: id 0 | task 13119 | graphs reused = 12378 35.08.445.785 I slot print_timing: id 0 | task 13119 | graph reallocs = 0 / 0 (same size) / (changed size) 35.08.445.815 I slot release: id 0 | task 13119 | stop processing: n_tokens = 491, truncated = 0 35.08.451.030 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 491, t_last = 77539919994 35.08.451.065 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1113.345 MiB) 35.08.473.096 I slot launch_slot_: id 0 | task 13187 | processing task, is_child = 0 35.14.293.597 I slot print_timing: id 0 | task 13187 | prompt processing, n_tokens = 580, progress = 0.99, t = 5.82 s / 99.65 tokens per second 35.25.803.314 I slot print_timing: id 0 | task 13187 | n_gen = 100, tg = 10.05 t/s, tg_3s = 10.15 t/s 35.28.888.781 I slot print_timing: id 0 | task 13187 | n_gen = 131, tg = 10.05 t/s, tg_3s = 10.05 t/s 35.31.978.959 I slot print_timing: id 0 | task 13187 | n_gen = 162, tg = 10.04 t/s, tg_3s = 10.03 t/s 35.35.062.945 I slot print_timing: id 0 | task 13187 | n_gen = 193, tg = 10.05 t/s, tg_3s = 10.05 t/s 35.36.854.664 I slot print_timing: id 0 | task 13187 | prompt eval time = 7477.85 ms / 584 tokens ( 12.80 ms per token, 78.10 tokens per second) 35.36.854.669 I slot print_timing: id 0 | task 13187 | eval time = 20903.71 ms / 211 tokens ( 99.54 ms per token, 10.05 tokens per second) 35.36.854.669 I slot print_timing: id 0 | task 13187 | total time = 28381.56 ms / 795 tokens 35.36.854.670 I slot print_timing: id 0 | task 13187 | graphs reused = 12586 35.36.854.670 I slot print_timing: id 0 | task 13187 | graph reallocs = 0 / 0 (same size) / (changed size) 35.36.854.714 I slot release: id 0 | task 13187 | stop processing: n_tokens = 826, truncated = 0 35.36.860.467 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 826, t_last = 77568328893 35.36.860.505 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1104.592 MiB) 35.36.885.814 I slot launch_slot_: id 0 | task 13402 | processing task, is_child = 0 35.43.054.542 I slot print_timing: id 0 | task 13402 | prompt processing, n_tokens = 691, progress = 0.99, t = 6.17 s / 112.02 tokens per second 35.55.284.144 I slot print_timing: id 0 | task 13402 | n_gen = 100, tg = 10.04 t/s, tg_3s = 10.14 t/s 35.58.369.945 I slot print_timing: id 0 | task 13402 | n_gen = 131, tg = 10.04 t/s, tg_3s = 10.05 t/s 36.01.455.836 I slot print_timing: id 0 | task 13402 | n_gen = 162, tg = 10.04 t/s, tg_3s = 10.05 t/s 36.04.540.466 I slot print_timing: id 0 | task 13402 | n_gen = 193, tg = 10.04 t/s, tg_3s = 10.05 t/s 36.07.627.373 I slot print_timing: id 0 | task 13402 | n_gen = 224, tg = 10.04 t/s, tg_3s = 10.04 t/s 36.09.917.546 I slot print_timing: id 0 | task 13402 | prompt eval time = 8537.13 ms / 695 tokens ( 12.28 ms per token, 81.41 tokens per second) 36.09.917.550 I slot print_timing: id 0 | task 13402 | eval time = 24494.59 ms / 247 tokens ( 99.57 ms per token, 10.04 tokens per second) 36.09.917.551 I slot print_timing: id 0 | task 13402 | total time = 33031.72 ms / 942 tokens 36.09.917.551 I slot print_timing: id 0 | task 13402 | graphs reused = 12830 36.09.917.552 I slot print_timing: id 0 | task 13402 | graph reallocs = 0 / 0 (same size) / (changed size) 36.09.917.586 I slot release: id 0 | task 13402 | stop processing: n_tokens = 973, truncated = 0 36.09.922.796 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 973, t_last = 77601391765 36.09.922.839 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1100.715 MiB) 36.09.959.344 I slot launch_slot_: id 0 | task 13653 | processing task, is_child = 0 36.17.524.125 I slot print_timing: id 0 | task 13653 | prompt processing, n_tokens = 765, progress = 1.00, t = 7.56 s / 101.13 tokens per second 36.29.052.659 I slot print_timing: id 0 | task 13653 | n_gen = 100, tg = 10.05 t/s, tg_3s = 10.15 t/s 36.32.138.577 I slot print_timing: id 0 | task 13653 | n_gen = 131, tg = 10.05 t/s, tg_3s = 10.05 t/s 36.35.226.478 I slot print_timing: id 0 | task 13653 | n_gen = 162, tg = 10.04 t/s, tg_3s = 10.04 t/s 36.38.115.847 I slot print_timing: id 0 | task 13653 | prompt eval time = 9237.67 ms / 769 tokens ( 12.01 ms per token, 83.25 tokens per second) 36.38.115.853 I slot print_timing: id 0 | task 13653 | eval time = 18918.81 ms / 191 tokens ( 99.57 ms per token, 10.04 tokens per second) 36.38.115.854 I slot print_timing: id 0 | task 13653 | total time = 28156.49 ms / 960 tokens 36.38.115.854 I slot print_timing: id 0 | task 13653 | graphs reused = 13019 36.38.115.855 I slot print_timing: id 0 | task 13653 | graph reallocs = 0 / 0 (same size) / (changed size) 36.38.115.895 I slot release: id 0 | task 13653 | stop processing: n_tokens = 991, truncated = 0 36.38.121.312 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 991, t_last = 77629590074 36.38.121.356 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 937.584 MiB) 36.38.160.659 I slot launch_slot_: id 0 | task 13848 | processing task, is_child = 0 36.43.971.572 I slot print_timing: id 0 | task 13848 | prompt processing, n_tokens = 572, progress = 0.99, t = 5.81 s / 98.44 tokens per second 36.55.132.316 I slot print_timing: id 0 | task 13848 | n_gen = 100, tg = 10.05 t/s, tg_3s = 10.16 t/s 36.58.216.394 I slot print_timing: id 0 | task 13848 | n_gen = 131, tg = 10.05 t/s, tg_3s = 10.05 t/s 37.01.302.566 I slot print_timing: id 0 | task 13848 | n_gen = 162, tg = 10.05 t/s, tg_3s = 10.04 t/s 37.04.288.287 I slot print_timing: id 0 | task 13848 | prompt eval time = 7125.51 ms / 576 tokens ( 12.37 ms per token, 80.84 tokens per second) 37.04.288.291 I slot print_timing: id 0 | task 13848 | eval time = 19002.10 ms / 192 tokens ( 99.49 ms per token, 10.05 tokens per second) 37.04.288.292 I slot print_timing: id 0 | task 13848 | total time = 26127.62 ms / 768 tokens 37.04.288.292 I slot print_timing: id 0 | task 13848 | graphs reused = 13208 37.04.288.293 I slot print_timing: id 0 | task 13848 | graph reallocs = 0 / 0 (same size) / (changed size) 37.04.288.333 I slot release: id 0 | task 13848 | stop processing: n_tokens = 799, truncated = 0 37.04.293.858 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 799, t_last = 77655762512 37.04.293.900 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1110.907 MiB) 37.04.319.167 I slot launch_slot_: id 0 | task 14044 | processing task, is_child = 0 37.10.459.923 I slot print_timing: id 0 | task 14044 | prompt processing, n_tokens = 651, progress = 0.99, t = 6.14 s / 106.01 tokens per second 37.22.326.695 I slot print_timing: id 0 | task 14044 | n_gen = 100, tg = 10.05 t/s, tg_3s = 10.15 t/s 37.25.411.255 I slot print_timing: id 0 | task 14044 | n_gen = 131, tg = 10.05 t/s, tg_3s = 10.05 t/s 37.28.498.714 I slot print_timing: id 0 | task 14044 | n_gen = 162, tg = 10.05 t/s, tg_3s = 10.04 t/s 37.31.583.734 I slot print_timing: id 0 | task 14044 | n_gen = 193, tg = 10.05 t/s, tg_3s = 10.05 t/s 37.34.670.701 I slot print_timing: id 0 | task 14044 | n_gen = 224, tg = 10.05 t/s, tg_3s = 10.04 t/s 37.37.758.223 I slot print_timing: id 0 | task 14044 | n_gen = 255, tg = 10.04 t/s, tg_3s = 10.04 t/s 37.40.846.670 I slot print_timing: id 0 | task 14044 | n_gen = 286, tg = 10.04 t/s, tg_3s = 10.04 t/s 37.41.543.317 I slot print_timing: id 0 | task 14044 | prompt eval time = 8152.33 ms / 655 tokens ( 12.45 ms per token, 80.35 tokens per second) 37.41.543.321 I slot print_timing: id 0 | task 14044 | eval time = 29071.81 ms / 293 tokens ( 99.56 ms per token, 10.04 tokens per second) 37.41.543.321 I slot print_timing: id 0 | task 14044 | total time = 37224.13 ms / 948 tokens 37.41.543.322 I slot print_timing: id 0 | task 14044 | graphs reused = 13498 37.41.543.322 I slot print_timing: id 0 | task 14044 | graph reallocs = 0 / 0 (same size) / (changed size) 37.41.543.357 I slot release: id 0 | task 14044 | stop processing: n_tokens = 979, truncated = 0 37.41.548.467 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 979, t_last = 77693017536 37.41.548.514 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 943.524 MiB) 37.41.577.261 I slot launch_slot_: id 0 | task 14341 | processing task, is_child = 0 37.47.726.968 I slot print_timing: id 0 | task 14341 | prompt processing, n_tokens = 617, progress = 0.99, t = 6.15 s / 100.33 tokens per second 37.59.235.926 I slot print_timing: id 0 | task 14341 | n_gen = 100, tg = 10.05 t/s, tg_3s = 10.15 t/s 38.01.329.658 I slot print_timing: id 0 | task 14341 | prompt eval time = 7808.05 ms / 621 tokens ( 12.57 ms per token, 79.53 tokens per second) 38.01.329.660 I slot print_timing: id 0 | task 14341 | eval time = 11944.33 ms / 121 tokens ( 99.54 ms per token, 10.05 tokens per second) 38.01.329.661 I slot print_timing: id 0 | task 14341 | total time = 19752.39 ms / 742 tokens 38.01.329.661 I slot print_timing: id 0 | task 14341 | graphs reused = 13616 38.01.329.662 I slot print_timing: id 0 | task 14341 | graph reallocs = 0 / 0 (same size) / (changed size) 38.01.329.702 I slot release: id 0 | task 14341 | stop processing: n_tokens = 773, truncated = 0 38.01.334.935 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 773, t_last = 77712803881 38.01.334.978 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1097.589 MiB) 38.01.362.070 I slot launch_slot_: id 0 | task 14466 | processing task, is_child = 0 38.08.576.246 I slot print_timing: id 0 | task 14466 | prompt processing, n_tokens = 763, progress = 0.99, t = 7.21 s / 105.76 tokens per second 38.20.443.955 I slot print_timing: id 0 | task 14466 | n_gen = 100, tg = 10.04 t/s, tg_3s = 10.14 t/s 38.23.530.918 I slot print_timing: id 0 | task 14466 | n_gen = 131, tg = 10.04 t/s, tg_3s = 10.04 t/s 38.26.536.017 I slot print_timing: id 0 | task 14466 | n_gen = 161, tg = 10.03 t/s, tg_3s = 9.98 t/s 38.29.624.368 I slot print_timing: id 0 | task 14466 | n_gen = 192, tg = 10.03 t/s, tg_3s = 10.04 t/s 38.30.122.758 I slot print_timing: id 0 | task 14466 | prompt eval time = 9223.85 ms / 767 tokens ( 12.03 ms per token, 83.15 tokens per second) 38.30.122.763 I slot print_timing: id 0 | task 14466 | eval time = 19536.82 ms / 197 tokens ( 99.68 ms per token, 10.03 tokens per second) 38.30.122.764 I slot print_timing: id 0 | task 14466 | total time = 28760.68 ms / 964 tokens 38.30.122.765 I slot print_timing: id 0 | task 14466 | graphs reused = 13811 38.30.122.765 I slot print_timing: id 0 | task 14466 | graph reallocs = 0 / 0 (same size) / (changed size) 38.30.122.808 I slot release: id 0 | task 14466 | stop processing: n_tokens = 995, truncated = 0 38.30.128.230 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 995, t_last = 77741596987 38.30.128.276 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 928.456 MiB) 38.30.167.776 I slot launch_slot_: id 0 | task 14667 | processing task, is_child = 0 38.34.149.021 I slot print_timing: id 0 | task 14667 | prompt processing, n_tokens = 686, progress = 0.80, t = 3.98 s / 172.31 tokens per second 38.38.131.513 I slot print_timing: id 0 | task 14667 | prompt processing, n_tokens = 860, progress = 1.00, t = 7.96 s / 107.99 tokens per second 38.50.369.823 I slot print_timing: id 0 | task 14667 | n_gen = 100, tg = 10.04 t/s, tg_3s = 10.14 t/s 38.53.462.234 I slot print_timing: id 0 | task 14667 | n_gen = 131, tg = 10.03 t/s, tg_3s = 10.02 t/s 38.56.465.873 I slot print_timing: id 0 | task 14667 | n_gen = 161, tg = 10.02 t/s, tg_3s = 9.99 t/s 38.59.554.331 I slot print_timing: id 0 | task 14667 | n_gen = 192, tg = 10.03 t/s, tg_3s = 10.04 t/s 39.02.644.726 I slot print_timing: id 0 | task 14667 | prompt eval time = 10337.29 ms / 864 tokens ( 11.96 ms per token, 83.58 tokens per second) 39.02.644.728 I slot print_timing: id 0 | task 14667 | eval time = 22139.65 ms / 223 tokens ( 99.73 ms per token, 10.03 tokens per second) 39.02.644.729 I slot print_timing: id 0 | task 14667 | total time = 32476.94 ms / 1087 tokens 39.02.644.729 I slot print_timing: id 0 | task 14667 | graphs reused = 14031 39.02.644.730 I slot print_timing: id 0 | task 14667 | graph reallocs = 0 / 0 (same size) / (changed size) 39.02.644.768 I slot release: id 0 | task 14667 | stop processing: n_tokens = 1118, truncated = 0 39.02.649.734 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1118, t_last = 77774118947 39.02.649.785 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1099.027 MiB) 39.02.689.982 I slot launch_slot_: id 0 | task 14894 | processing task, is_child = 0 39.09.182.339 I slot print_timing: id 0 | task 14894 | prompt processing, n_tokens = 642, progress = 0.99, t = 6.49 s / 98.89 tokens per second 39.20.708.051 I slot print_timing: id 0 | task 14894 | n_gen = 100, tg = 10.04 t/s, tg_3s = 10.14 t/s 39.23.793.062 I slot print_timing: id 0 | task 14894 | n_gen = 131, tg = 10.04 t/s, tg_3s = 10.05 t/s 39.25.783.107 I slot print_timing: id 0 | task 14894 | prompt eval time = 8156.73 ms / 646 tokens ( 12.63 ms per token, 79.20 tokens per second) 39.25.783.112 I slot print_timing: id 0 | task 14894 | eval time = 14936.38 ms / 151 tokens ( 99.58 ms per token, 10.04 tokens per second) 39.25.783.112 I slot print_timing: id 0 | task 14894 | total time = 23093.11 ms / 797 tokens 39.25.783.113 I slot print_timing: id 0 | task 14894 | graphs reused = 14179 39.25.783.113 I slot print_timing: id 0 | task 14894 | graph reallocs = 0 / 0 (same size) / (changed size) 39.25.783.148 I slot release: id 0 | task 14894 | stop processing: n_tokens = 828, truncated = 0 39.25.788.359 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 828, t_last = 77797257327 39.25.788.397 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1108.218 MiB) 39.25.813.841 I slot launch_slot_: id 0 | task 15049 | processing task, is_child = 0 39.32.678.933 I slot print_timing: id 0 | task 15049 | prompt processing, n_tokens = 716, progress = 0.99, t = 6.87 s / 104.30 tokens per second 39.44.553.166 I slot print_timing: id 0 | task 15049 | n_gen = 100, tg = 10.04 t/s, tg_3s = 10.14 t/s 39.47.555.770 I slot print_timing: id 0 | task 15049 | n_gen = 130, tg = 10.03 t/s, tg_3s = 9.99 t/s 39.50.642.459 I slot print_timing: id 0 | task 15049 | n_gen = 161, tg = 10.03 t/s, tg_3s = 10.04 t/s 39.53.730.002 I slot print_timing: id 0 | task 15049 | n_gen = 192, tg = 10.03 t/s, tg_3s = 10.04 t/s 39.56.718.795 I slot print_timing: id 0 | task 15049 | prompt eval time = 8876.58 ms / 720 tokens ( 12.33 ms per token, 81.11 tokens per second) 39.56.718.800 I slot print_timing: id 0 | task 15049 | eval time = 22028.36 ms / 222 tokens ( 99.68 ms per token, 10.03 tokens per second) 39.56.718.801 I slot print_timing: id 0 | task 15049 | total time = 30904.94 ms / 942 tokens 39.56.718.801 I slot print_timing: id 0 | task 15049 | graphs reused = 14398 39.56.718.802 I slot print_timing: id 0 | task 15049 | graph reallocs = 0 / 0 (same size) / (changed size) 39.56.718.834 I slot release: id 0 | task 15049 | stop processing: n_tokens = 973, truncated = 0 39.56.723.580 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 973, t_last = 77828193013 39.56.723.634 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1109.343 MiB) 39.56.749.617 I slot launch_slot_: id 0 | task 15275 | processing task, is_child = 0 40.01.432.367 I slot print_timing: id 0 | task 15275 | prompt processing, n_tokens = 505, progress = 0.99, t = 4.68 s / 107.84 tokens per second 40.12.925.450 I slot print_timing: id 0 | task 15275 | n_gen = 100, tg = 10.06 t/s, tg_3s = 10.16 t/s 40.16.007.229 I slot print_timing: id 0 | task 15275 | n_gen = 131, tg = 10.06 t/s, tg_3s = 10.06 t/s 40.19.091.747 I slot print_timing: id 0 | task 15275 | n_gen = 162, tg = 10.06 t/s, tg_3s = 10.05 t/s 40.22.177.295 I slot print_timing: id 0 | task 15275 | n_gen = 193, tg = 10.05 t/s, tg_3s = 10.05 t/s 40.24.267.668 I slot print_timing: id 0 | task 15275 | prompt eval time = 6330.71 ms / 509 tokens ( 12.44 ms per token, 80.40 tokens per second) 40.24.267.670 I slot print_timing: id 0 | task 15275 | eval time = 21187.33 ms / 214 tokens ( 99.47 ms per token, 10.05 tokens per second) 40.24.267.672 I slot print_timing: id 0 | task 15275 | total time = 27518.03 ms / 723 tokens 40.24.267.672 I slot print_timing: id 0 | task 15275 | graphs reused = 14610 40.24.267.673 I slot print_timing: id 0 | task 15275 | graph reallocs = 0 / 0 (same size) / (changed size) 40.24.267.704 I slot release: id 0 | task 15275 | stop processing: n_tokens = 754, truncated = 0 40.24.272.727 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 754, t_last = 77855741883 40.24.272.770 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1097.339 MiB) 40.24.295.530 I slot launch_slot_: id 0 | task 15492 | processing task, is_child = 0 40.30.105.793 I slot print_timing: id 0 | task 15492 | prompt processing, n_tokens = 577, progress = 0.99, t = 5.81 s / 99.31 tokens per second 40.41.601.546 I slot print_timing: id 0 | task 15492 | n_gen = 100, tg = 10.05 t/s, tg_3s = 10.16 t/s 40.44.686.535 I slot print_timing: id 0 | task 15492 | n_gen = 131, tg = 10.05 t/s, tg_3s = 10.05 t/s 40.47.775.619 I slot print_timing: id 0 | task 15492 | n_gen = 162, tg = 10.05 t/s, tg_3s = 10.04 t/s 40.50.860.948 I slot print_timing: id 0 | task 15492 | n_gen = 193, tg = 10.05 t/s, tg_3s = 10.05 t/s 40.53.947.078 I slot print_timing: id 0 | task 15492 | n_gen = 224, tg = 10.05 t/s, tg_3s = 10.04 t/s 40.55.739.472 I slot print_timing: id 0 | task 15492 | prompt eval time = 7459.93 ms / 581 tokens ( 12.84 ms per token, 77.88 tokens per second) 40.55.739.477 I slot print_timing: id 0 | task 15492 | eval time = 23984.00 ms / 242 tokens ( 99.52 ms per token, 10.05 tokens per second) 40.55.739.478 I slot print_timing: id 0 | task 15492 | total time = 31443.93 ms / 823 tokens 40.55.739.478 I slot print_timing: id 0 | task 15492 | graphs reused = 14849 40.55.739.479 I slot print_timing: id 0 | task 15492 | graph reallocs = 0 / 0 (same size) / (changed size) 40.55.739.513 I slot release: id 0 | task 15492 | stop processing: n_tokens = 854, truncated = 0 40.55.745.404 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 854, t_last = 77887213692 40.55.745.445 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1108.593 MiB) 40.55.770.702 I slot launch_slot_: id 0 | task 15738 | processing task, is_child = 0 41.00.454.469 I slot print_timing: id 0 | task 15738 | prompt processing, n_tokens = 741, progress = 0.81, t = 4.68 s / 158.21 tokens per second 41.04.435.301 I slot print_timing: id 0 | task 15738 | prompt processing, n_tokens = 921, progress = 1.00, t = 8.66 s / 106.29 tokens per second 41.16.688.213 I slot print_timing: id 0 | task 15738 | n_gen = 100, tg = 10.03 t/s, tg_3s = 10.13 t/s 41.19.777.919 I slot print_timing: id 0 | task 15738 | n_gen = 131, tg = 10.03 t/s, tg_3s = 10.03 t/s 41.22.869.689 I slot print_timing: id 0 | task 15738 | n_gen = 162, tg = 10.03 t/s, tg_3s = 10.03 t/s 41.25.963.764 I slot print_timing: id 0 | task 15738 | n_gen = 193, tg = 10.03 t/s, tg_3s = 10.02 t/s 41.29.054.611 I slot print_timing: id 0 | task 15738 | n_gen = 224, tg = 10.03 t/s, tg_3s = 10.03 t/s 41.30.949.058 I slot print_timing: id 0 | task 15738 | prompt eval time = 11045.55 ms / 925 tokens ( 11.94 ms per token, 83.74 tokens per second) 41.30.949.063 I slot print_timing: id 0 | task 15738 | eval time = 24132.79 ms / 243 tokens ( 99.72 ms per token, 10.03 tokens per second) 41.30.949.064 I slot print_timing: id 0 | task 15738 | total time = 35178.34 ms / 1168 tokens 41.30.949.064 I slot print_timing: id 0 | task 15738 | graphs reused = 15089 41.30.949.065 I slot print_timing: id 0 | task 15738 | graph reallocs = 0 / 0 (same size) / (changed size) 41.30.949.117 I slot release: id 0 | task 15738 | stop processing: n_tokens = 1199, truncated = 0 41.30.954.448 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1199, t_last = 77922423296 41.30.954.497 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1095.713 MiB) 41.30.994.941 I slot launch_slot_: id 0 | task 15985 | processing task, is_child = 0 41.35.296.394 I slot print_timing: id 0 | task 15985 | prompt processing, n_tokens = 743, progress = 0.85, t = 4.30 s / 172.73 tokens per second 41.39.611.217 I slot print_timing: id 0 | task 15985 | prompt processing, n_tokens = 881, progress = 1.00, t = 8.62 s / 102.25 tokens per second 41.51.505.329 I slot print_timing: id 0 | task 15985 | n_gen = 100, tg = 10.03 t/s, tg_3s = 10.13 t/s 41.54.610.890 I slot print_timing: id 0 | task 15985 | n_gen = 131, tg = 10.02 t/s, tg_3s = 9.98 t/s 41.57.700.831 I slot print_timing: id 0 | task 15985 | n_gen = 162, tg = 10.02 t/s, tg_3s = 10.03 t/s 42.00.791.897 I slot print_timing: id 0 | task 15985 | n_gen = 193, tg = 10.02 t/s, tg_3s = 10.03 t/s 42.03.882.818 I slot print_timing: id 0 | task 15985 | n_gen = 224, tg = 10.02 t/s, tg_3s = 10.03 t/s 42.06.972.219 I slot print_timing: id 0 | task 15985 | n_gen = 255, tg = 10.02 t/s, tg_3s = 10.03 t/s 42.07.570.499 I slot print_timing: id 0 | task 15985 | prompt eval time = 10636.18 ms / 885 tokens ( 12.02 ms per token, 83.21 tokens per second) 42.07.570.504 I slot print_timing: id 0 | task 15985 | eval time = 25939.37 ms / 261 tokens ( 99.77 ms per token, 10.02 tokens per second) 42.07.570.505 I slot print_timing: id 0 | task 15985 | total time = 36575.55 ms / 1146 tokens 42.07.570.505 I slot print_timing: id 0 | task 15985 | graphs reused = 15347 42.07.570.506 I slot print_timing: id 0 | task 15985 | graph reallocs = 0 / 0 (same size) / (changed size) 42.07.570.545 I slot release: id 0 | task 15985 | stop processing: n_tokens = 1177, truncated = 0 42.07.575.759 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1177, t_last = 77959044724 42.07.575.816 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1109.594 MiB) 42.07.616.917 I slot launch_slot_: id 0 | task 16250 | processing task, is_child = 0 42.11.920.742 I slot print_timing: id 0 | task 16250 | prompt processing, n_tokens = 388, progress = 0.99, t = 4.30 s / 90.15 tokens per second 42.16.806.803 I slot print_timing: id 0 | task 16250 | prompt eval time = 4914.38 ms / 392 tokens ( 12.54 ms per token, 79.77 tokens per second) 42.16.806.806 I slot print_timing: id 0 | task 16250 | eval time = 4275.50 ms / 44 tokens ( 99.43 ms per token, 10.06 tokens per second) 42.16.806.806 I slot print_timing: id 0 | task 16250 | total time = 9189.87 ms / 436 tokens 42.16.806.807 I slot print_timing: id 0 | task 16250 | graphs reused = 15389 42.16.806.807 I slot print_timing: id 0 | task 16250 | graph reallocs = 0 / 0 (same size) / (changed size) 42.16.806.833 I slot release: id 0 | task 16250 | stop processing: n_tokens = 467, truncated = 0 42.16.811.880 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 467, t_last = 77968281012 42.16.811.913 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1117.284 MiB) 42.16.836.956 I slot launch_slot_: id 0 | task 16297 | processing task, is_child = 0 42.20.452.775 I slot print_timing: id 0 | task 16297 | prompt processing, n_tokens = 327, progress = 0.99, t = 3.62 s / 90.44 tokens per second 42.26.808.537 I slot print_timing: id 0 | task 16297 | prompt eval time = 4105.33 ms / 331 tokens ( 12.40 ms per token, 80.63 tokens per second) 42.26.808.542 I slot print_timing: id 0 | task 16297 | eval time = 5866.24 ms / 60 tokens ( 99.43 ms per token, 10.06 tokens per second) 42.26.808.542 I slot print_timing: id 0 | task 16297 | total time = 9971.57 ms / 391 tokens 42.26.808.543 I slot print_timing: id 0 | task 16297 | graphs reused = 15447 42.26.808.543 I slot print_timing: id 0 | task 16297 | graph reallocs = 0 / 0 (same size) / (changed size) 42.26.808.569 I slot release: id 0 | task 16297 | stop processing: n_tokens = 422, truncated = 0 42.26.813.011 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 422, t_last = 77978282748 42.26.813.045 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1099.152 MiB) 42.26.835.559 I slot launch_slot_: id 0 | task 16360 | processing task, is_child = 0 42.30.797.374 I slot print_timing: id 0 | task 16360 | prompt processing, n_tokens = 353, progress = 0.99, t = 3.96 s / 89.10 tokens per second 42.41.265.940 I slot print_timing: id 0 | task 16360 | n_gen = 100, tg = 10.05 t/s, tg_3s = 10.15 t/s 42.41.365.322 I slot print_timing: id 0 | task 16360 | prompt eval time = 4576.03 ms / 357 tokens ( 12.82 ms per token, 78.02 tokens per second) 42.41.365.324 I slot print_timing: id 0 | task 16360 | eval time = 9953.72 ms / 101 tokens ( 99.54 ms per token, 10.05 tokens per second) 42.41.365.325 I slot print_timing: id 0 | task 16360 | total time = 14529.75 ms / 458 tokens 42.41.365.325 I slot print_timing: id 0 | task 16360 | graphs reused = 15546 42.41.365.325 I slot print_timing: id 0 | task 16360 | graph reallocs = 0 / 0 (same size) / (changed size) 42.41.365.352 I slot release: id 0 | task 16360 | stop processing: n_tokens = 489, truncated = 0 42.41.369.296 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 489, t_last = 77992839531 42.41.412.659 I slot launch_slot_: id 0 | task 16464 | processing task, is_child = 0 42.45.015.514 I slot print_timing: id 0 | task 16464 | prompt processing, n_tokens = 311, progress = 0.99, t = 3.60 s / 86.32 tokens per second 42.55.348.929 I slot print_timing: id 0 | task 16464 | n_gen = 100, tg = 10.06 t/s, tg_3s = 10.16 t/s 42.57.437.393 I slot print_timing: id 0 | task 16464 | prompt eval time = 4095.50 ms / 315 tokens ( 13.00 ms per token, 76.91 tokens per second) 42.57.437.398 I slot print_timing: id 0 | task 16464 | eval time = 11929.22 ms / 121 tokens ( 99.41 ms per token, 10.06 tokens per second) 42.57.437.399 I slot print_timing: id 0 | task 16464 | total time = 16024.72 ms / 436 tokens 42.57.437.399 I slot print_timing: id 0 | task 16464 | graphs reused = 15665 42.57.437.400 I slot print_timing: id 0 | task 16464 | graph reallocs = 0 / 0 (same size) / (changed size) 42.57.437.426 I slot release: id 0 | task 16464 | stop processing: n_tokens = 467, truncated = 0 42.57.441.847 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 467, t_last = 78008911605 42.57.441.873 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1108.218 MiB) 42.57.464.416 I slot launch_slot_: id 0 | task 16588 | processing task, is_child = 0 43.01.442.164 I slot print_timing: id 0 | task 16588 | prompt processing, n_tokens = 374, progress = 0.99, t = 3.98 s / 94.02 tokens per second 43.08.248.973 I slot print_timing: id 0 | task 16588 | prompt eval time = 4921.85 ms / 378 tokens ( 13.02 ms per token, 76.80 tokens per second) 43.08.248.976 I slot print_timing: id 0 | task 16588 | eval time = 5862.69 ms / 60 tokens ( 99.37 ms per token, 10.06 tokens per second) 43.08.248.977 I slot print_timing: id 0 | task 16588 | total time = 10784.55 ms / 438 tokens 43.08.248.977 I slot print_timing: id 0 | task 16588 | graphs reused = 15723 43.08.248.978 I slot print_timing: id 0 | task 16588 | graph reallocs = 0 / 0 (same size) / (changed size) 43.08.249.008 I slot release: id 0 | task 16588 | stop processing: n_tokens = 469, truncated = 0 43.08.253.862 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 469, t_last = 78019723187 43.08.253.897 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 944.899 MiB) 43.08.276.029 I slot launch_slot_: id 0 | task 16651 | processing task, is_child = 0 43.11.541.557 I slot print_timing: id 0 | task 16651 | prompt processing, n_tokens = 291, progress = 0.99, t = 3.27 s / 89.11 tokens per second 43.14.836.630 I slot print_timing: id 0 | task 16651 | prompt eval time = 3875.82 ms / 295 tokens ( 13.14 ms per token, 76.11 tokens per second) 43.14.836.636 I slot print_timing: id 0 | task 16651 | eval time = 2684.77 ms / 28 tokens ( 99.44 ms per token, 10.06 tokens per second) 43.14.836.636 I slot print_timing: id 0 | task 16651 | total time = 6560.59 ms / 323 tokens 43.14.836.636 I slot print_timing: id 0 | task 16651 | graphs reused = 15749 43.14.836.637 I slot print_timing: id 0 | task 16651 | graph reallocs = 0 / 0 (same size) / (changed size) 43.14.836.659 I slot release: id 0 | task 16651 | stop processing: n_tokens = 354, truncated = 0 43.14.841.287 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 354, t_last = 78026310838 43.14.841.317 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1100.778 MiB) 43.14.867.091 I slot launch_slot_: id 0 | task 16682 | processing task, is_child = 0 43.18.488.896 I slot print_timing: id 0 | task 16682 | prompt processing, n_tokens = 333, progress = 0.99, t = 3.62 s / 91.94 tokens per second 43.26.535.407 I slot print_timing: id 0 | task 16682 | prompt eval time = 4114.78 ms / 337 tokens ( 12.21 ms per token, 81.90 tokens per second) 43.26.535.413 I slot print_timing: id 0 | task 16682 | eval time = 7553.53 ms / 77 tokens ( 99.39 ms per token, 10.06 tokens per second) 43.26.535.413 I slot print_timing: id 0 | task 16682 | total time = 11668.31 ms / 414 tokens 43.26.535.414 I slot print_timing: id 0 | task 16682 | graphs reused = 15824 43.26.535.414 I slot print_timing: id 0 | task 16682 | graph reallocs = 0 / 0 (same size) / (changed size) 43.26.535.440 I slot release: id 0 | task 16682 | stop processing: n_tokens = 445, truncated = 0 43.26.540.204 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 445, t_last = 78038009619 43.26.540.237 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1122.348 MiB) 43.26.562.448 I slot launch_slot_: id 0 | task 16762 | processing task, is_child = 0 43.30.169.239 I slot print_timing: id 0 | task 16762 | prompt processing, n_tokens = 321, progress = 0.99, t = 3.61 s / 89.00 tokens per second 43.40.625.898 I slot print_timing: id 0 | task 16762 | n_gen = 100, tg = 10.06 t/s, tg_3s = 10.16 t/s 43.43.012.649 I slot print_timing: id 0 | task 16762 | prompt eval time = 4218.41 ms / 325 tokens ( 12.98 ms per token, 77.04 tokens per second) 43.43.012.655 I slot print_timing: id 0 | task 16762 | eval time = 12231.78 ms / 124 tokens ( 99.45 ms per token, 10.06 tokens per second) 43.43.012.655 I slot print_timing: id 0 | task 16762 | total time = 16450.19 ms / 449 tokens 43.43.012.656 I slot print_timing: id 0 | task 16762 | graphs reused = 15946 43.43.012.656 I slot print_timing: id 0 | task 16762 | graph reallocs = 0 / 0 (same size) / (changed size) 43.43.012.683 I slot release: id 0 | task 16762 | stop processing: n_tokens = 480, truncated = 0 43.43.017.118 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.108 (> 0.100 thold), f_keep = 0.067 43.43.017.148 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1120.973 MiB) 43.43.038.614 I slot launch_slot_: id 0 | task 16889 | processing task, is_child = 0 43.52.106.946 I slot print_timing: id 0 | task 16889 | prompt eval time = 3507.44 ms / 264 tokens ( 13.29 ms per token, 75.27 tokens per second) 43.52.106.952 I slot print_timing: id 0 | task 16889 | eval time = 5560.88 ms / 57 tokens ( 99.30 ms per token, 10.07 tokens per second) 43.52.106.952 I slot print_timing: id 0 | task 16889 | total time = 9068.32 ms / 321 tokens 43.52.106.953 I slot print_timing: id 0 | task 16889 | graphs reused = 16001 43.52.106.953 I slot print_timing: id 0 | task 16889 | graph reallocs = 0 / 0 (same size) / (changed size) 43.52.106.986 I slot release: id 0 | task 16889 | stop processing: n_tokens = 352, truncated = 0 43.52.111.193 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 352, t_last = 78063581165 43.52.111.221 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 926.955 MiB) 43.52.136.601 I slot launch_slot_: id 0 | task 16949 | processing task, is_child = 0 43.55.744.868 I slot print_timing: id 0 | task 16949 | prompt processing, n_tokens = 327, progress = 0.99, t = 3.61 s / 90.63 tokens per second 44.00.926.137 I slot print_timing: id 0 | task 16949 | prompt eval time = 4218.77 ms / 331 tokens ( 12.75 ms per token, 78.46 tokens per second) 44.00.926.160 I slot print_timing: id 0 | task 16949 | eval time = 4570.74 ms / 45 tokens ( 103.88 ms per token, 9.63 tokens per second) 44.00.926.162 I slot print_timing: id 0 | task 16949 | total time = 8789.51 ms / 376 tokens 44.00.926.167 I slot print_timing: id 0 | task 16949 | graphs reused = 16044 44.00.926.172 I slot print_timing: id 0 | task 16949 | graph reallocs = 0 / 0 (same size) / (changed size) 44.00.926.279 I slot release: id 0 | task 16949 | stop processing: n_tokens = 407, truncated = 0 44.00.938.300 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 407, t_last = 78072400458 44.00.938.365 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 924.142 MiB) 44.00.974.462 I slot launch_slot_: id 0 | task 16997 | processing task, is_child = 0 44.04.593.161 I slot print_timing: id 0 | task 16997 | prompt processing, n_tokens = 329, progress = 0.99, t = 3.62 s / 90.92 tokens per second 44.14.545.816 I slot print_timing: id 0 | task 16997 | prompt eval time = 4227.81 ms / 333 tokens ( 12.70 ms per token, 78.76 tokens per second) 44.14.545.821 I slot print_timing: id 0 | task 16997 | eval time = 9343.53 ms / 95 tokens ( 99.40 ms per token, 10.06 tokens per second) 44.14.545.822 I slot print_timing: id 0 | task 16997 | total time = 13571.34 ms / 428 tokens 44.14.545.822 I slot print_timing: id 0 | task 16997 | graphs reused = 16137 44.14.545.823 I slot print_timing: id 0 | task 16997 | graph reallocs = 0 / 0 (same size) / (changed size) 44.14.545.850 I slot release: id 0 | task 16997 | stop processing: n_tokens = 459, truncated = 0 44.14.550.588 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 459, t_last = 78086020029 44.14.550.625 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 928.331 MiB) 44.14.572.330 I slot launch_slot_: id 0 | task 17095 | processing task, is_child = 0 44.18.178.963 I slot print_timing: id 0 | task 17095 | prompt processing, n_tokens = 342, progress = 0.99, t = 3.61 s / 94.83 tokens per second 44.24.294.480 I slot print_timing: id 0 | task 17095 | prompt eval time = 4553.99 ms / 346 tokens ( 13.16 ms per token, 75.98 tokens per second) 44.24.294.486 I slot print_timing: id 0 | task 17095 | eval time = 5168.15 ms / 53 tokens ( 99.39 ms per token, 10.06 tokens per second) 44.24.294.486 I slot print_timing: id 0 | task 17095 | total time = 9722.14 ms / 399 tokens 44.24.294.487 I slot print_timing: id 0 | task 17095 | graphs reused = 16188 44.24.294.487 I slot print_timing: id 0 | task 17095 | graph reallocs = 0 / 0 (same size) / (changed size) 44.24.294.513 I slot release: id 0 | task 17095 | stop processing: n_tokens = 430, truncated = 0 44.24.299.422 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 430, t_last = 78095768692 44.24.299.460 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 926.955 MiB) 44.24.321.274 I slot launch_slot_: id 0 | task 17151 | processing task, is_child = 0 44.27.930.981 I slot print_timing: id 0 | task 17151 | prompt processing, n_tokens = 321, progress = 0.99, t = 3.61 s / 88.93 tokens per second 44.32.302.368 I slot print_timing: id 0 | task 17151 | prompt eval time = 4103.35 ms / 325 tokens ( 12.63 ms per token, 79.20 tokens per second) 44.32.302.374 I slot print_timing: id 0 | task 17151 | eval time = 3877.74 ms / 40 tokens ( 99.43 ms per token, 10.06 tokens per second) 44.32.302.374 I slot print_timing: id 0 | task 17151 | total time = 7981.08 ms / 365 tokens 44.32.302.375 I slot print_timing: id 0 | task 17151 | graphs reused = 16226 44.32.302.375 I slot print_timing: id 0 | task 17151 | graph reallocs = 0 / 0 (same size) / (changed size) 44.32.302.402 I slot release: id 0 | task 17151 | stop processing: n_tokens = 396, truncated = 0 44.32.306.884 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 396, t_last = 78103776581 44.32.306.921 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 927.080 MiB) 44.32.329.897 I slot launch_slot_: id 0 | task 17194 | processing task, is_child = 0 44.35.937.400 I slot print_timing: id 0 | task 17194 | prompt processing, n_tokens = 318, progress = 0.99, t = 3.61 s / 88.15 tokens per second 44.46.398.140 I slot print_timing: id 0 | task 17194 | n_gen = 100, tg = 10.05 t/s, tg_3s = 10.15 t/s 44.49.487.118 I slot print_timing: id 0 | task 17194 | n_gen = 131, tg = 10.05 t/s, tg_3s = 10.04 t/s 44.52.574.885 I slot print_timing: id 0 | task 17194 | n_gen = 162, tg = 10.04 t/s, tg_3s = 10.04 t/s 44.55.661.144 I slot print_timing: id 0 | task 17194 | n_gen = 193, tg = 10.04 t/s, tg_3s = 10.04 t/s 44.58.744.258 I slot print_timing: id 0 | task 17194 | n_gen = 224, tg = 10.05 t/s, tg_3s = 10.05 t/s 45.01.833.563 I slot print_timing: id 0 | task 17194 | n_gen = 255, tg = 10.04 t/s, tg_3s = 10.03 t/s 45.04.915.687 I slot print_timing: id 0 | task 17194 | n_gen = 286, tg = 10.05 t/s, tg_3s = 10.06 t/s 45.07.999.286 I slot print_timing: id 0 | task 17194 | n_gen = 317, tg = 10.05 t/s, tg_3s = 10.05 t/s 45.11.083.970 I slot print_timing: id 0 | task 17194 | n_gen = 348, tg = 10.05 t/s, tg_3s = 10.05 t/s 45.12.775.713 I slot print_timing: id 0 | task 17194 | prompt eval time = 4215.79 ms / 322 tokens ( 13.09 ms per token, 76.38 tokens per second) 45.12.775.715 I slot print_timing: id 0 | task 17194 | eval time = 36230.02 ms / 365 tokens ( 99.53 ms per token, 10.05 tokens per second) 45.12.775.716 I slot print_timing: id 0 | task 17194 | total time = 40445.81 ms / 687 tokens 45.12.775.716 I slot print_timing: id 0 | task 17194 | graphs reused = 16588 45.12.775.717 I slot print_timing: id 0 | task 17194 | graph reallocs = 0 / 0 (same size) / (changed size) 45.12.775.743 I slot release: id 0 | task 17194 | stop processing: n_tokens = 718, truncated = 0 45.12.780.595 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 718, t_last = 78144249922 45.12.780.640 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 919.890 MiB) 45.12.803.088 I slot launch_slot_: id 0 | task 17562 | processing task, is_child = 0 45.16.422.817 I slot print_timing: id 0 | task 17562 | prompt processing, n_tokens = 334, progress = 0.99, t = 3.62 s / 92.27 tokens per second 45.26.887.940 I slot print_timing: id 0 | task 17562 | n_gen = 100, tg = 10.05 t/s, tg_3s = 10.15 t/s 45.29.974.885 I slot print_timing: id 0 | task 17562 | n_gen = 131, tg = 10.04 t/s, tg_3s = 10.04 t/s 45.33.063.981 I slot print_timing: id 0 | task 17562 | n_gen = 162, tg = 10.04 t/s, tg_3s = 10.04 t/s 45.36.149.516 I slot print_timing: id 0 | task 17562 | n_gen = 193, tg = 10.04 t/s, tg_3s = 10.05 t/s 45.39.229.079 I slot print_timing: id 0 | task 17562 | n_gen = 224, tg = 10.05 t/s, tg_3s = 10.07 t/s 45.42.315.471 I slot print_timing: id 0 | task 17562 | n_gen = 255, tg = 10.05 t/s, tg_3s = 10.04 t/s 45.45.397.740 I slot print_timing: id 0 | task 17562 | n_gen = 286, tg = 10.05 t/s, tg_3s = 10.06 t/s 45.48.485.701 I slot print_timing: id 0 | task 17562 | n_gen = 317, tg = 10.05 t/s, tg_3s = 10.04 t/s 45.51.573.601 I slot print_timing: id 0 | task 17562 | n_gen = 348, tg = 10.05 t/s, tg_3s = 10.04 t/s 45.54.663.399 I slot print_timing: id 0 | task 17562 | n_gen = 379, tg = 10.05 t/s, tg_3s = 10.03 t/s 45.57.752.628 I slot print_timing: id 0 | task 17562 | n_gen = 410, tg = 10.04 t/s, tg_3s = 10.03 t/s 46.00.842.250 I slot print_timing: id 0 | task 17562 | n_gen = 441, tg = 10.04 t/s, tg_3s = 10.03 t/s 46.03.934.707 I slot print_timing: id 0 | task 17562 | n_gen = 472, tg = 10.04 t/s, tg_3s = 10.02 t/s 46.07.023.037 I slot print_timing: id 0 | task 17562 | n_gen = 503, tg = 10.04 t/s, tg_3s = 10.04 t/s 46.10.109.918 I slot print_timing: id 0 | task 17562 | n_gen = 534, tg = 10.04 t/s, tg_3s = 10.04 t/s 46.13.199.875 I slot print_timing: id 0 | task 17562 | n_gen = 565, tg = 10.04 t/s, tg_3s = 10.03 t/s 46.16.288.197 I slot print_timing: id 0 | task 17562 | n_gen = 596, tg = 10.04 t/s, tg_3s = 10.04 t/s 46.19.375.803 I slot print_timing: id 0 | task 17562 | n_gen = 627, tg = 10.04 t/s, tg_3s = 10.04 t/s 46.21.469.544 I slot print_timing: id 0 | task 17562 | prompt eval time = 4229.84 ms / 338 tokens ( 12.51 ms per token, 79.91 tokens per second) 46.21.469.549 I slot print_timing: id 0 | task 17562 | eval time = 64436.61 ms / 648 tokens ( 99.59 ms per token, 10.04 tokens per second) 46.21.469.550 I slot print_timing: id 0 | task 17562 | total time = 68666.45 ms / 986 tokens 46.21.469.550 I slot print_timing: id 0 | task 17562 | graphs reused = 17232 46.21.469.550 I slot print_timing: id 0 | task 17562 | graph reallocs = 0 / 0 (same size) / (changed size) 46.21.469.574 I slot release: id 0 | task 17562 | stop processing: n_tokens = 1017, truncated = 0 46.21.474.022 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1017, t_last = 78212943753 46.21.474.067 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 925.580 MiB) 46.21.498.838 I slot launch_slot_: id 0 | task 18213 | processing task, is_child = 0 46.25.121.107 I slot print_timing: id 0 | task 18213 | prompt processing, n_tokens = 343, progress = 0.99, t = 3.62 s / 94.69 tokens per second 46.35.580.301 I slot print_timing: id 0 | task 18213 | n_gen = 100, tg = 10.05 t/s, tg_3s = 10.15 t/s 46.38.660.304 I slot print_timing: id 0 | task 18213 | n_gen = 131, tg = 10.05 t/s, tg_3s = 10.06 t/s 46.41.750.174 I slot print_timing: id 0 | task 18213 | n_gen = 162, tg = 10.05 t/s, tg_3s = 10.03 t/s 46.44.836.352 I slot print_timing: id 0 | task 18213 | n_gen = 193, tg = 10.05 t/s, tg_3s = 10.04 t/s 46.47.923.153 I slot print_timing: id 0 | task 18213 | n_gen = 224, tg = 10.05 t/s, tg_3s = 10.04 t/s 46.51.006.929 I slot print_timing: id 0 | task 18213 | n_gen = 255, tg = 10.05 t/s, tg_3s = 10.05 t/s 46.54.092.538 I slot print_timing: id 0 | task 18213 | n_gen = 286, tg = 10.05 t/s, tg_3s = 10.05 t/s 46.57.175.280 I slot print_timing: id 0 | task 18213 | n_gen = 317, tg = 10.05 t/s, tg_3s = 10.06 t/s 47.00.259.134 I slot print_timing: id 0 | task 18213 | n_gen = 348, tg = 10.05 t/s, tg_3s = 10.05 t/s 47.03.343.003 I slot print_timing: id 0 | task 18213 | n_gen = 379, tg = 10.05 t/s, tg_3s = 10.05 t/s 47.06.431.286 I slot print_timing: id 0 | task 18213 | n_gen = 410, tg = 10.05 t/s, tg_3s = 10.04 t/s 47.09.516.166 I slot print_timing: id 0 | task 18213 | n_gen = 441, tg = 10.05 t/s, tg_3s = 10.05 t/s 47.12.601.461 I slot print_timing: id 0 | task 18213 | n_gen = 472, tg = 10.05 t/s, tg_3s = 10.05 t/s 47.15.687.035 I slot print_timing: id 0 | task 18213 | n_gen = 503, tg = 10.05 t/s, tg_3s = 10.05 t/s 47.18.773.371 I slot print_timing: id 0 | task 18213 | n_gen = 534, tg = 10.05 t/s, tg_3s = 10.04 t/s 47.21.860.534 I slot print_timing: id 0 | task 18213 | n_gen = 565, tg = 10.05 t/s, tg_3s = 10.04 t/s 47.24.948.325 I slot print_timing: id 0 | task 18213 | n_gen = 596, tg = 10.05 t/s, tg_3s = 10.04 t/s 47.28.036.208 I slot print_timing: id 0 | task 18213 | n_gen = 627, tg = 10.05 t/s, tg_3s = 10.04 t/s 47.31.127.127 I slot print_timing: id 0 | task 18213 | n_gen = 658, tg = 10.05 t/s, tg_3s = 10.03 t/s 47.34.216.249 I slot print_timing: id 0 | task 18213 | n_gen = 689, tg = 10.05 t/s, tg_3s = 10.04 t/s 47.37.306.744 I slot print_timing: id 0 | task 18213 | n_gen = 720, tg = 10.05 t/s, tg_3s = 10.03 t/s 47.40.401.368 I slot print_timing: id 0 | task 18213 | n_gen = 751, tg = 10.04 t/s, tg_3s = 10.02 t/s 47.43.492.642 I slot print_timing: id 0 | task 18213 | n_gen = 782, tg = 10.04 t/s, tg_3s = 10.03 t/s 47.46.583.812 I slot print_timing: id 0 | task 18213 | n_gen = 813, tg = 10.04 t/s, tg_3s = 10.03 t/s 47.49.674.565 I slot print_timing: id 0 | task 18213 | n_gen = 844, tg = 10.04 t/s, tg_3s = 10.03 t/s 47.52.765.388 I slot print_timing: id 0 | task 18213 | n_gen = 875, tg = 10.04 t/s, tg_3s = 10.03 t/s 47.55.860.086 I slot print_timing: id 0 | task 18213 | n_gen = 906, tg = 10.04 t/s, tg_3s = 10.02 t/s 47.58.952.971 I slot print_timing: id 0 | task 18213 | n_gen = 937, tg = 10.04 t/s, tg_3s = 10.02 t/s 48.02.046.972 I slot print_timing: id 0 | task 18213 | n_gen = 968, tg = 10.04 t/s, tg_3s = 10.02 t/s 48.05.142.516 I slot print_timing: id 0 | task 18213 | n_gen = 999, tg = 10.04 t/s, tg_3s = 10.01 t/s 48.07.641.101 I slot print_timing: id 0 | task 18213 | prompt eval time = 4231.72 ms / 347 tokens ( 12.20 ms per token, 82.00 tokens per second) 48.07.641.107 I slot print_timing: id 0 | task 18213 | eval time = 101910.53 ms / 1024 tokens ( 99.62 ms per token, 10.04 tokens per second) 48.07.641.108 I slot print_timing: id 0 | task 18213 | total time = 106142.25 ms / 1371 tokens 48.07.641.108 I slot print_timing: id 0 | task 18213 | graphs reused = 18250 48.07.641.109 I slot print_timing: id 0 | task 18213 | graph reallocs = 0 / 0 (same size) / (changed size) 48.07.641.134 I slot release: id 0 | task 18213 | stop processing: n_tokens = 1402, truncated = 0 48.07.646.095 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1402, t_last = 78319115313 48.07.646.159 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 927.768 MiB) 48.07.684.632 I slot launch_slot_: id 0 | task 19240 | processing task, is_child = 0 48.11.294.041 I slot print_timing: id 0 | task 19240 | prompt processing, n_tokens = 327, progress = 0.99, t = 3.61 s / 90.60 tokens per second 48.15.879.398 I slot print_timing: id 0 | task 19240 | prompt eval time = 4219.36 ms / 331 tokens ( 12.75 ms per token, 78.45 tokens per second) 48.15.879.403 I slot print_timing: id 0 | task 19240 | eval time = 3975.39 ms / 41 tokens ( 99.38 ms per token, 10.06 tokens per second) 48.15.879.403 I slot print_timing: id 0 | task 19240 | total time = 8194.75 ms / 372 tokens 48.15.879.404 I slot print_timing: id 0 | task 19240 | graphs reused = 18289 48.15.879.404 I slot print_timing: id 0 | task 19240 | graph reallocs = 0 / 0 (same size) / (changed size) 48.15.879.429 I slot release: id 0 | task 19240 | stop processing: n_tokens = 403, truncated = 0 48.15.884.413 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 403, t_last = 78327353608 48.15.884.447 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 919.765 MiB) 48.15.911.364 I slot launch_slot_: id 0 | task 19284 | processing task, is_child = 0 48.19.493.612 I slot print_timing: id 0 | task 19284 | prompt processing, n_tokens = 341, progress = 0.99, t = 3.58 s / 95.19 tokens per second 48.24.493.929 I slot print_timing: id 0 | task 19284 | prompt eval time = 4192.27 ms / 345 tokens ( 12.15 ms per token, 82.29 tokens per second) 48.24.493.935 I slot print_timing: id 0 | task 19284 | eval time = 4390.28 ms / 45 tokens ( 99.78 ms per token, 10.02 tokens per second) 48.24.493.935 I slot print_timing: id 0 | task 19284 | total time = 8582.56 ms / 390 tokens 48.24.493.936 I slot print_timing: id 0 | task 19284 | graphs reused = 18332 48.24.493.936 I slot print_timing: id 0 | task 19284 | graph reallocs = 0 / 0 (same size) / (changed size) 48.24.493.960 I slot release: id 0 | task 19284 | stop processing: n_tokens = 421, truncated = 0 48.24.498.044 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 421, t_last = 78335968139 48.24.498.070 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 923.204 MiB) 48.24.519.544 I slot launch_slot_: id 0 | task 19332 | processing task, is_child = 0 48.28.122.537 I slot print_timing: id 0 | task 19332 | prompt processing, n_tokens = 316, progress = 0.99, t = 3.60 s / 87.71 tokens per second 48.38.577.755 I slot print_timing: id 0 | task 19332 | n_gen = 100, tg = 10.06 t/s, tg_3s = 10.16 t/s 48.41.657.878 I slot print_timing: id 0 | task 19332 | n_gen = 131, tg = 10.06 t/s, tg_3s = 10.06 t/s 48.44.744.044 I slot print_timing: id 0 | task 19332 | n_gen = 162, tg = 10.06 t/s, tg_3s = 10.04 t/s 48.47.824.487 I slot print_timing: id 0 | task 19332 | n_gen = 193, tg = 10.06 t/s, tg_3s = 10.06 t/s 48.50.011.517 I slot print_timing: id 0 | task 19332 | prompt eval time = 4215.91 ms / 320 tokens ( 13.17 ms per token, 75.90 tokens per second) 48.50.011.523 I slot print_timing: id 0 | task 19332 | eval time = 21276.05 ms / 215 tokens ( 99.42 ms per token, 10.06 tokens per second) 48.50.011.523 I slot print_timing: id 0 | task 19332 | total time = 25491.96 ms / 535 tokens 48.50.011.524 I slot print_timing: id 0 | task 19332 | graphs reused = 18544 48.50.011.524 I slot print_timing: id 0 | task 19332 | graph reallocs = 0 / 0 (same size) / (changed size) 48.50.011.547 I slot release: id 0 | task 19332 | stop processing: n_tokens = 566, truncated = 0 48.50.016.036 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 566, t_last = 78361485726 48.50.016.074 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 926.455 MiB) 48.50.039.117 I slot launch_slot_: id 0 | task 19550 | processing task, is_child = 0 48.53.308.819 I slot print_timing: id 0 | task 19550 | prompt processing, n_tokens = 293, progress = 0.99, t = 3.27 s / 89.61 tokens per second 48.57.078.450 I slot print_timing: id 0 | task 19550 | prompt eval time = 3759.09 ms / 297 tokens ( 12.66 ms per token, 79.01 tokens per second) 48.57.078.455 I slot print_timing: id 0 | task 19550 | eval time = 3280.23 ms / 34 tokens ( 99.40 ms per token, 10.06 tokens per second) 48.57.078.455 I slot print_timing: id 0 | task 19550 | total time = 7039.32 ms / 331 tokens 48.57.078.456 I slot print_timing: id 0 | task 19550 | graphs reused = 18576 48.57.078.456 I slot print_timing: id 0 | task 19550 | graph reallocs = 0 / 0 (same size) / (changed size) 48.57.078.477 I slot release: id 0 | task 19550 | stop processing: n_tokens = 362, truncated = 0 48.57.082.926 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 362, t_last = 78368552656 48.57.082.954 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 924.642 MiB) 48.57.109.426 I slot launch_slot_: id 0 | task 19587 | processing task, is_child = 0 49.00.730.758 I slot print_timing: id 0 | task 19587 | prompt processing, n_tokens = 339, progress = 0.99, t = 3.62 s / 93.61 tokens per second 49.11.187.142 I slot print_timing: id 0 | task 19587 | n_gen = 100, tg = 10.05 t/s, tg_3s = 10.16 t/s 49.14.271.861 I slot print_timing: id 0 | task 19587 | n_gen = 131, tg = 10.05 t/s, tg_3s = 10.05 t/s 49.17.354.395 I slot print_timing: id 0 | task 19587 | n_gen = 162, tg = 10.05 t/s, tg_3s = 10.06 t/s 49.20.236.509 I slot print_timing: id 0 | task 19587 | prompt eval time = 4231.21 ms / 343 tokens ( 12.34 ms per token, 81.06 tokens per second) 49.20.236.511 I slot print_timing: id 0 | task 19587 | eval time = 18895.86 ms / 191 tokens ( 99.45 ms per token, 10.06 tokens per second) 49.20.236.511 I slot print_timing: id 0 | task 19587 | total time = 23127.07 ms / 534 tokens 49.20.236.512 I slot print_timing: id 0 | task 19587 | graphs reused = 18764 49.20.236.512 I slot print_timing: id 0 | task 19587 | graph reallocs = 0 / 0 (same size) / (changed size) 49.20.236.541 I slot release: id 0 | task 19587 | stop processing: n_tokens = 565, truncated = 0 49.20.241.087 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 565, t_last = 78391710720 49.20.241.118 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 922.516 MiB) 49.20.262.887 I slot launch_slot_: id 0 | task 19781 | processing task, is_child = 0 49.24.251.947 I slot print_timing: id 0 | task 19781 | prompt processing, n_tokens = 367, progress = 0.99, t = 3.99 s / 92.00 tokens per second 49.34.711.386 I slot print_timing: id 0 | task 19781 | n_gen = 100, tg = 10.05 t/s, tg_3s = 10.15 t/s 49.37.799.268 I slot print_timing: id 0 | task 19781 | n_gen = 131, tg = 10.05 t/s, tg_3s = 10.04 t/s 49.40.881.685 I slot print_timing: id 0 | task 19781 | n_gen = 162, tg = 10.05 t/s, tg_3s = 10.06 t/s 49.43.965.333 I slot print_timing: id 0 | task 19781 | n_gen = 193, tg = 10.05 t/s, tg_3s = 10.05 t/s 49.44.462.341 I slot print_timing: id 0 | task 19781 | prompt eval time = 4600.06 ms / 371 tokens ( 12.40 ms per token, 80.65 tokens per second) 49.44.462.346 I slot print_timing: id 0 | task 19781 | eval time = 19599.38 ms / 198 tokens ( 99.49 ms per token, 10.05 tokens per second) 49.44.462.347 I slot print_timing: id 0 | task 19781 | total time = 24199.44 ms / 569 tokens 49.44.462.347 I slot print_timing: id 0 | task 19781 | graphs reused = 18959 49.44.462.348 I slot print_timing: id 0 | task 19781 | graph reallocs = 0 / 0 (same size) / (changed size) 49.44.462.373 I slot release: id 0 | task 19781 | stop processing: n_tokens = 600, truncated = 0 49.44.467.033 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 600, t_last = 78415936552 49.44.467.072 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 942.649 MiB) 49.44.489.904 I slot launch_slot_: id 0 | task 19982 | processing task, is_child = 0 49.47.751.082 I slot print_timing: id 0 | task 19982 | prompt processing, n_tokens = 288, progress = 0.99, t = 3.26 s / 88.31 tokens per second 49.58.207.255 I slot print_timing: id 0 | task 19982 | n_gen = 100, tg = 10.06 t/s, tg_3s = 10.16 t/s 50.01.287.049 I slot print_timing: id 0 | task 19982 | n_gen = 131, tg = 10.06 t/s, tg_3s = 10.07 t/s 50.04.366.956 I slot print_timing: id 0 | task 19982 | n_gen = 162, tg = 10.06 t/s, tg_3s = 10.07 t/s 50.07.050.158 I slot print_timing: id 0 | task 19982 | prompt eval time = 3872.05 ms / 292 tokens ( 13.26 ms per token, 75.41 tokens per second) 50.07.050.160 I slot print_timing: id 0 | task 19982 | eval time = 18688.20 ms / 189 tokens ( 99.41 ms per token, 10.06 tokens per second) 50.07.050.161 I slot print_timing: id 0 | task 19982 | total time = 22560.24 ms / 481 tokens 50.07.050.161 I slot print_timing: id 0 | task 19982 | graphs reused = 19146 50.07.050.162 I slot print_timing: id 0 | task 19982 | graph reallocs = 0 / 0 (same size) / (changed size) 50.07.050.184 I slot release: id 0 | task 19982 | stop processing: n_tokens = 512, truncated = 0 50.07.054.675 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 512, t_last = 78438524363 50.07.054.706 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 961.343 MiB) 50.07.076.679 I slot launch_slot_: id 0 | task 20174 | processing task, is_child = 0 50.10.346.301 I slot print_timing: id 0 | task 20174 | prompt processing, n_tokens = 297, progress = 0.99, t = 3.27 s / 90.84 tokens per second 50.16.907.263 I slot print_timing: id 0 | task 20174 | prompt eval time = 3762.49 ms / 301 tokens ( 12.50 ms per token, 80.00 tokens per second) 50.16.907.269 I slot print_timing: id 0 | task 20174 | eval time = 6068.08 ms / 62 tokens ( 99.48 ms per token, 10.05 tokens per second) 50.16.907.270 I slot print_timing: id 0 | task 20174 | total time = 9830.57 ms / 363 tokens 50.16.907.270 I slot print_timing: id 0 | task 20174 | graphs reused = 19206 50.16.907.271 I slot print_timing: id 0 | task 20174 | graph reallocs = 0 / 0 (same size) / (changed size) 50.16.907.296 I slot release: id 0 | task 20174 | stop processing: n_tokens = 394, truncated = 0 50.16.911.528 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 394, t_last = 78448381475 50.16.911.557 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 985.414 MiB) 50.16.934.290 I slot launch_slot_: id 0 | task 20239 | processing task, is_child = 0 50.20.207.056 I slot print_timing: id 0 | task 20239 | prompt processing, n_tokens = 299, progress = 0.99, t = 3.27 s / 91.36 tokens per second 50.24.892.628 I slot print_timing: id 0 | task 20239 | prompt eval time = 3881.62 ms / 303 tokens ( 12.81 ms per token, 78.06 tokens per second) 50.24.892.632 I slot print_timing: id 0 | task 20239 | eval time = 4076.70 ms / 42 tokens ( 99.43 ms per token, 10.06 tokens per second) 50.24.892.632 I slot print_timing: id 0 | task 20239 | total time = 7958.33 ms / 345 tokens 50.24.892.632 I slot print_timing: id 0 | task 20239 | graphs reused = 19246 50.24.892.633 I slot print_timing: id 0 | task 20239 | graph reallocs = 0 / 0 (same size) / (changed size) 50.24.892.658 I slot release: id 0 | task 20239 | stop processing: n_tokens = 376, truncated = 0 50.24.897.108 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 376, t_last = 78456366837 50.24.897.140 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 922.954 MiB) 50.24.919.827 I slot launch_slot_: id 0 | task 20284 | processing task, is_child = 0 50.28.526.398 I slot print_timing: id 0 | task 20284 | prompt processing, n_tokens = 317, progress = 0.99, t = 3.61 s / 87.90 tokens per second 50.37.086.683 I slot print_timing: id 0 | task 20284 | prompt eval time = 4217.07 ms / 321 tokens ( 13.14 ms per token, 76.12 tokens per second) 50.37.086.689 I slot print_timing: id 0 | task 20284 | eval time = 7949.78 ms / 81 tokens ( 99.37 ms per token, 10.06 tokens per second) 50.37.086.689 I slot print_timing: id 0 | task 20284 | total time = 12166.85 ms / 402 tokens 50.37.086.690 I slot print_timing: id 0 | task 20284 | graphs reused = 19325 50.37.086.690 I slot print_timing: id 0 | task 20284 | graph reallocs = 0 / 0 (same size) / (changed size) 50.37.086.713 I slot release: id 0 | task 20284 | stop processing: n_tokens = 433, truncated = 0 50.37.090.985 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 433, t_last = 78468560892 50.37.091.010 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 924.079 MiB) 50.37.112.650 I slot launch_slot_: id 0 | task 20368 | processing task, is_child = 0 50.40.721.451 I slot print_timing: id 0 | task 20368 | prompt processing, n_tokens = 318, progress = 0.99, t = 3.61 s / 88.12 tokens per second 50.45.911.782 I slot print_timing: id 0 | task 20368 | prompt eval time = 4219.80 ms / 322 tokens ( 13.10 ms per token, 76.31 tokens per second) 50.45.911.787 I slot print_timing: id 0 | task 20368 | eval time = 4579.32 ms / 47 tokens ( 99.55 ms per token, 10.05 tokens per second) 50.45.911.788 I slot print_timing: id 0 | task 20368 | total time = 8799.12 ms / 369 tokens 50.45.911.788 I slot print_timing: id 0 | task 20368 | graphs reused = 19370 50.45.911.789 I slot print_timing: id 0 | task 20368 | graph reallocs = 0 / 0 (same size) / (changed size) 50.45.911.812 I slot release: id 0 | task 20368 | stop processing: n_tokens = 400, truncated = 0 50.45.916.081 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 78477385991 50.45.916.105 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 933.145 MiB) 50.45.938.191 I slot launch_slot_: id 0 | task 20418 | processing task, is_child = 0 50.49.547.418 I slot print_timing: id 0 | task 20418 | prompt processing, n_tokens = 319, progress = 0.99, t = 3.61 s / 88.38 tokens per second 50.54.631.188 I slot print_timing: id 0 | task 20418 | prompt eval time = 4220.06 ms / 323 tokens ( 13.07 ms per token, 76.54 tokens per second) 50.54.631.191 I slot print_timing: id 0 | task 20418 | eval time = 4472.93 ms / 46 tokens ( 99.40 ms per token, 10.06 tokens per second) 50.54.631.192 I slot print_timing: id 0 | task 20418 | total time = 8692.99 ms / 369 tokens 50.54.631.192 I slot print_timing: id 0 | task 20418 | graphs reused = 19414 50.54.631.193 I slot print_timing: id 0 | task 20418 | graph reallocs = 0 / 0 (same size) / (changed size) 50.54.631.230 I slot release: id 0 | task 20418 | stop processing: n_tokens = 400, truncated = 0 50.54.635.691 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 78486105410 50.54.635.717 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 920.390 MiB) 50.54.657.184 I slot launch_slot_: id 0 | task 20467 | processing task, is_child = 0 50.58.264.716 I slot print_timing: id 0 | task 20467 | prompt processing, n_tokens = 317, progress = 0.99, t = 3.61 s / 87.87 tokens per second 51.08.605.428 I slot print_timing: id 0 | task 20467 | n_gen = 100, tg = 10.05 t/s, tg_3s = 10.15 t/s 51.11.686.215 I slot print_timing: id 0 | task 20467 | n_gen = 131, tg = 10.06 t/s, tg_3s = 10.06 t/s 51.14.769.098 I slot print_timing: id 0 | task 20467 | n_gen = 162, tg = 10.06 t/s, tg_3s = 10.06 t/s 51.17.848.656 I slot print_timing: id 0 | task 20467 | n_gen = 193, tg = 10.06 t/s, tg_3s = 10.07 t/s 51.20.932.666 I slot print_timing: id 0 | task 20467 | n_gen = 224, tg = 10.06 t/s, tg_3s = 10.05 t/s 51.24.014.183 I slot print_timing: id 0 | task 20467 | n_gen = 255, tg = 10.06 t/s, tg_3s = 10.06 t/s 51.27.097.594 I slot print_timing: id 0 | task 20467 | n_gen = 286, tg = 10.06 t/s, tg_3s = 10.05 t/s 51.30.184.188 I slot print_timing: id 0 | task 20467 | n_gen = 317, tg = 10.06 t/s, tg_3s = 10.04 t/s 51.33.270.323 I slot print_timing: id 0 | task 20467 | n_gen = 348, tg = 10.05 t/s, tg_3s = 10.04 t/s 51.36.353.845 I slot print_timing: id 0 | task 20467 | n_gen = 379, tg = 10.05 t/s, tg_3s = 10.05 t/s 51.36.553.070 I slot print_timing: id 0 | task 20467 | prompt eval time = 4100.50 ms / 321 tokens ( 12.77 ms per token, 78.28 tokens per second) 51.36.553.076 I slot print_timing: id 0 | task 20467 | eval time = 37795.38 ms / 381 tokens ( 99.46 ms per token, 10.05 tokens per second) 51.36.553.076 I slot print_timing: id 0 | task 20467 | total time = 41895.88 ms / 702 tokens 51.36.553.077 I slot print_timing: id 0 | task 20467 | graphs reused = 19792 51.36.553.077 I slot print_timing: id 0 | task 20467 | graph reallocs = 0 / 0 (same size) / (changed size) 51.36.553.104 I slot release: id 0 | task 20467 | stop processing: n_tokens = 733, truncated = 0 51.36.557.387 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 733, t_last = 78528027283 51.36.557.424 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 933.083 MiB) 51.36.579.346 I slot launch_slot_: id 0 | task 20851 | processing task, is_child = 0 51.40.191.605 I slot print_timing: id 0 | task 20851 | prompt processing, n_tokens = 318, progress = 0.99, t = 3.61 s / 88.03 tokens per second 51.47.535.380 I slot print_timing: id 0 | task 20851 | prompt eval time = 4098.93 ms / 322 tokens ( 12.73 ms per token, 78.56 tokens per second) 51.47.535.383 I slot print_timing: id 0 | task 20851 | eval time = 6857.09 ms / 70 tokens ( 99.38 ms per token, 10.06 tokens per second) 51.47.535.384 I slot print_timing: id 0 | task 20851 | total time = 10956.02 ms / 392 tokens 51.47.535.384 I slot print_timing: id 0 | task 20851 | graphs reused = 19860 51.47.535.385 I slot print_timing: id 0 | task 20851 | graph reallocs = 0 / 0 (same size) / (changed size) 51.47.535.408 I slot release: id 0 | task 20851 | stop processing: n_tokens = 423, truncated = 0 51.47.540.248 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 423, t_last = 78539009587 51.47.540.278 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 935.271 MiB) 51.47.564.697 I slot launch_slot_: id 0 | task 20924 | processing task, is_child = 0 51.51.183.651 I slot print_timing: id 0 | task 20924 | prompt processing, n_tokens = 333, progress = 0.99, t = 3.62 s / 92.02 tokens per second 51.56.266.549 I slot print_timing: id 0 | task 20924 | prompt eval time = 4227.61 ms / 337 tokens ( 12.54 ms per token, 79.71 tokens per second) 51.56.266.555 I slot print_timing: id 0 | task 20924 | eval time = 4474.23 ms / 46 tokens ( 99.43 ms per token, 10.06 tokens per second) 51.56.266.555 I slot print_timing: id 0 | task 20924 | total time = 8701.84 ms / 383 tokens 51.56.266.556 I slot print_timing: id 0 | task 20924 | graphs reused = 19904 51.56.266.556 I slot print_timing: id 0 | task 20924 | graph reallocs = 0 / 0 (same size) / (changed size) 51.56.266.582 I slot release: id 0 | task 20924 | stop processing: n_tokens = 414, truncated = 0 51.56.270.786 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 78547740761 51.56.270.819 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 929.769 MiB) 51.56.293.084 I slot launch_slot_: id 0 | task 20973 | processing task, is_child = 0 51.59.901.932 I slot print_timing: id 0 | task 20973 | prompt processing, n_tokens = 321, progress = 0.99, t = 3.61 s / 88.95 tokens per second 52.05.086.280 I slot print_timing: id 0 | task 20973 | prompt eval time = 4219.04 ms / 325 tokens ( 12.98 ms per token, 77.03 tokens per second) 52.05.086.282 I slot print_timing: id 0 | task 20973 | eval time = 4574.14 ms / 47 tokens ( 99.44 ms per token, 10.06 tokens per second) 52.05.086.283 I slot print_timing: id 0 | task 20973 | total time = 8793.18 ms / 372 tokens 52.05.086.283 I slot print_timing: id 0 | task 20973 | graphs reused = 19949 52.05.086.284 I slot print_timing: id 0 | task 20973 | graph reallocs = 0 / 0 (same size) / (changed size) 52.05.086.310 I slot release: id 0 | task 20973 | stop processing: n_tokens = 403, truncated = 0 52.05.090.949 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 403, t_last = 78556560489 52.05.090.980 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 922.391 MiB) 52.05.112.683 I slot launch_slot_: id 0 | task 21023 | processing task, is_child = 0 52.08.724.306 I slot print_timing: id 0 | task 21023 | prompt processing, n_tokens = 327, progress = 0.99, t = 3.61 s / 90.54 tokens per second 52.19.631.465 I slot print_timing: id 0 | task 21023 | n_gen = 100, tg = 9.61 t/s, tg_3s = 9.71 t/s 52.22.711.441 I slot print_timing: id 0 | task 21023 | n_gen = 131, tg = 9.72 t/s, tg_3s = 10.07 t/s 52.24.700.549 I slot print_timing: id 0 | task 21023 | prompt eval time = 4221.84 ms / 331 tokens ( 12.75 ms per token, 78.40 tokens per second) 52.24.700.552 I slot print_timing: id 0 | task 21023 | eval time = 15366.01 ms / 151 tokens ( 102.44 ms per token, 9.76 tokens per second) 52.24.700.553 I slot print_timing: id 0 | task 21023 | total time = 19587.85 ms / 482 tokens 52.24.700.553 I slot print_timing: id 0 | task 21023 | graphs reused = 20097 52.24.700.554 I slot print_timing: id 0 | task 21023 | graph reallocs = 0 / 0 (same size) / (changed size) 52.24.700.578 I slot release: id 0 | task 21023 | stop processing: n_tokens = 513, truncated = 0 52.24.704.594 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 513, t_last = 78576174757 52.24.704.622 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 921.266 MiB) 52.24.726.468 I slot launch_slot_: id 0 | task 21177 | processing task, is_child = 0 52.28.349.095 I slot print_timing: id 0 | task 21177 | prompt processing, n_tokens = 332, progress = 0.99, t = 3.62 s / 91.65 tokens per second 52.38.673.519 I slot print_timing: id 0 | task 21177 | n_gen = 100, tg = 10.06 t/s, tg_3s = 10.17 t/s 52.38.772.621 I slot print_timing: id 0 | task 21177 | prompt eval time = 4110.21 ms / 336 tokens ( 12.23 ms per token, 81.75 tokens per second) 52.38.772.625 I slot print_timing: id 0 | task 21177 | eval time = 9935.94 ms / 101 tokens ( 99.36 ms per token, 10.06 tokens per second) 52.38.772.626 I slot print_timing: id 0 | task 21177 | total time = 14046.14 ms / 437 tokens 52.38.772.626 I slot print_timing: id 0 | task 21177 | graphs reused = 20196 52.38.772.627 I slot print_timing: id 0 | task 21177 | graph reallocs = 0 / 0 (same size) / (changed size) 52.38.772.654 I slot release: id 0 | task 21177 | stop processing: n_tokens = 468, truncated = 0 52.38.777.187 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 468, t_last = 78590246833 52.38.777.223 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 924.830 MiB) 52.38.799.999 I slot launch_slot_: id 0 | task 21281 | processing task, is_child = 0 52.42.762.645 I slot print_timing: id 0 | task 21281 | prompt processing, n_tokens = 345, progress = 0.99, t = 3.96 s / 87.06 tokens per second 52.44.965.742 I slot print_timing: id 0 | task 21281 | prompt eval time = 4573.13 ms / 349 tokens ( 13.10 ms per token, 76.32 tokens per second) 52.44.965.744 I slot print_timing: id 0 | task 21281 | eval time = 1592.60 ms / 17 tokens ( 99.54 ms per token, 10.05 tokens per second) 52.44.965.745 I slot print_timing: id 0 | task 21281 | total time = 6165.73 ms / 366 tokens 52.44.965.745 I slot print_timing: id 0 | task 21281 | graphs reused = 20211 52.44.965.745 I slot print_timing: id 0 | task 21281 | graph reallocs = 0 / 0 (same size) / (changed size) 52.44.965.780 I slot release: id 0 | task 21281 | stop processing: n_tokens = 397, truncated = 0 52.44.970.072 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 397, t_last = 78596439959 52.44.970.098 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 922.766 MiB) 52.44.995.779 I slot launch_slot_: id 0 | task 21301 | processing task, is_child = 0 52.48.615.323 I slot print_timing: id 0 | task 21301 | prompt processing, n_tokens = 332, progress = 0.99, t = 3.62 s / 91.72 tokens per second 52.58.946.112 I slot print_timing: id 0 | task 21301 | n_gen = 100, tg = 10.06 t/s, tg_3s = 10.16 t/s 53.02.028.797 I slot print_timing: id 0 | task 21301 | n_gen = 131, tg = 10.06 t/s, tg_3s = 10.06 t/s 53.05.114.546 I slot print_timing: id 0 | task 21301 | n_gen = 162, tg = 10.06 t/s, tg_3s = 10.05 t/s 53.08.197.795 I slot print_timing: id 0 | task 21301 | n_gen = 193, tg = 10.06 t/s, tg_3s = 10.05 t/s 53.11.282.377 I slot print_timing: id 0 | task 21301 | n_gen = 224, tg = 10.05 t/s, tg_3s = 10.05 t/s 53.14.364.065 I slot print_timing: id 0 | task 21301 | n_gen = 255, tg = 10.06 t/s, tg_3s = 10.06 t/s 53.17.447.938 I slot print_timing: id 0 | task 21301 | n_gen = 286, tg = 10.06 t/s, tg_3s = 10.05 t/s 53.20.534.252 I slot print_timing: id 0 | task 21301 | n_gen = 317, tg = 10.05 t/s, tg_3s = 10.04 t/s 53.23.621.083 I slot print_timing: id 0 | task 21301 | n_gen = 348, tg = 10.05 t/s, tg_3s = 10.04 t/s 53.26.707.471 I slot print_timing: id 0 | task 21301 | n_gen = 379, tg = 10.05 t/s, tg_3s = 10.04 t/s 53.29.797.731 I slot print_timing: id 0 | task 21301 | n_gen = 410, tg = 10.05 t/s, tg_3s = 10.03 t/s 53.32.885.151 I slot print_timing: id 0 | task 21301 | n_gen = 441, tg = 10.05 t/s, tg_3s = 10.04 t/s 53.35.970.491 I slot print_timing: id 0 | task 21301 | n_gen = 472, tg = 10.05 t/s, tg_3s = 10.05 t/s 53.39.056.666 I slot print_timing: id 0 | task 21301 | n_gen = 503, tg = 10.05 t/s, tg_3s = 10.04 t/s 53.42.147.172 I slot print_timing: id 0 | task 21301 | n_gen = 534, tg = 10.05 t/s, tg_3s = 10.03 t/s 53.45.235.211 I slot print_timing: id 0 | task 21301 | n_gen = 565, tg = 10.05 t/s, tg_3s = 10.04 t/s 53.48.324.422 I slot print_timing: id 0 | task 21301 | n_gen = 596, tg = 10.05 t/s, tg_3s = 10.03 t/s 53.51.414.183 I slot print_timing: id 0 | task 21301 | n_gen = 627, tg = 10.05 t/s, tg_3s = 10.03 t/s 53.54.509.699 I slot print_timing: id 0 | task 21301 | n_gen = 658, tg = 10.05 t/s, tg_3s = 10.01 t/s 53.57.600.008 I slot print_timing: id 0 | task 21301 | n_gen = 689, tg = 10.04 t/s, tg_3s = 10.03 t/s 54.00.691.244 I slot print_timing: id 0 | task 21301 | n_gen = 720, tg = 10.04 t/s, tg_3s = 10.03 t/s 54.03.780.822 I slot print_timing: id 0 | task 21301 | n_gen = 751, tg = 10.04 t/s, tg_3s = 10.03 t/s 54.06.871.952 I slot print_timing: id 0 | task 21301 | n_gen = 782, tg = 10.04 t/s, tg_3s = 10.03 t/s 54.09.964.640 I slot print_timing: id 0 | task 21301 | n_gen = 813, tg = 10.04 t/s, tg_3s = 10.02 t/s 54.13.056.541 I slot print_timing: id 0 | task 21301 | n_gen = 844, tg = 10.04 t/s, tg_3s = 10.03 t/s 54.16.149.068 I slot print_timing: id 0 | task 21301 | n_gen = 875, tg = 10.04 t/s, tg_3s = 10.02 t/s 54.18.846.400 I slot print_timing: id 0 | task 21301 | prompt eval time = 4108.35 ms / 336 tokens ( 12.23 ms per token, 81.78 tokens per second) 54.18.846.404 I slot print_timing: id 0 | task 21301 | eval time = 89742.26 ms / 902 tokens ( 99.60 ms per token, 10.04 tokens per second) 54.18.846.404 I slot print_timing: id 0 | task 21301 | total time = 93850.61 ms / 1238 tokens 54.18.846.405 I slot print_timing: id 0 | task 21301 | graphs reused = 21108 54.18.846.405 I slot print_timing: id 0 | task 21301 | graph reallocs = 0 / 0 (same size) / (changed size) 54.18.846.429 I slot release: id 0 | task 21301 | stop processing: n_tokens = 1269, truncated = 0 54.18.851.409 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1269, t_last = 78690320608 54.18.851.472 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 922.766 MiB) 54.18.876.100 I slot launch_slot_: id 0 | task 22206 | processing task, is_child = 0 54.22.847.895 I slot print_timing: id 0 | task 22206 | prompt processing, n_tokens = 345, progress = 0.99, t = 3.97 s / 86.86 tokens per second 54.33.187.519 I slot print_timing: id 0 | task 22206 | n_gen = 100, tg = 10.05 t/s, tg_3s = 10.16 t/s 54.36.270.717 I slot print_timing: id 0 | task 22206 | n_gen = 131, tg = 10.05 t/s, tg_3s = 10.05 t/s 54.39.353.771 I slot print_timing: id 0 | task 22206 | n_gen = 162, tg = 10.05 t/s, tg_3s = 10.05 t/s 54.42.438.365 I slot print_timing: id 0 | task 22206 | n_gen = 193, tg = 10.05 t/s, tg_3s = 10.05 t/s 54.45.518.972 I slot print_timing: id 0 | task 22206 | n_gen = 224, tg = 10.05 t/s, tg_3s = 10.06 t/s 54.48.604.579 I slot print_timing: id 0 | task 22206 | n_gen = 255, tg = 10.05 t/s, tg_3s = 10.05 t/s 54.51.692.045 I slot print_timing: id 0 | task 22206 | n_gen = 286, tg = 10.05 t/s, tg_3s = 10.04 t/s 54.54.784.525 I slot print_timing: id 0 | task 22206 | n_gen = 317, tg = 10.05 t/s, tg_3s = 10.02 t/s 54.57.873.846 I slot print_timing: id 0 | task 22206 | n_gen = 348, tg = 10.05 t/s, tg_3s = 10.03 t/s 55.00.954.400 I slot print_timing: id 0 | task 22206 | n_gen = 379, tg = 10.05 t/s, tg_3s = 10.06 t/s 55.04.045.004 I slot print_timing: id 0 | task 22206 | n_gen = 410, tg = 10.05 t/s, tg_3s = 10.03 t/s 55.07.133.058 I slot print_timing: id 0 | task 22206 | n_gen = 441, tg = 10.05 t/s, tg_3s = 10.04 t/s 55.10.219.939 I slot print_timing: id 0 | task 22206 | n_gen = 472, tg = 10.05 t/s, tg_3s = 10.04 t/s 55.12.213.348 I slot print_timing: id 0 | task 22206 | prompt eval time = 4464.50 ms / 349 tokens ( 12.79 ms per token, 78.17 tokens per second) 55.12.213.352 I slot print_timing: id 0 | task 22206 | eval time = 48872.74 ms / 492 tokens ( 99.54 ms per token, 10.05 tokens per second) 55.12.213.353 I slot print_timing: id 0 | task 22206 | total time = 53337.24 ms / 841 tokens 55.12.213.353 I slot print_timing: id 0 | task 22206 | graphs reused = 21596 55.12.213.354 I slot print_timing: id 0 | task 22206 | graph reallocs = 0 / 0 (same size) / (changed size) 55.12.213.379 I slot release: id 0 | task 22206 | stop processing: n_tokens = 872, truncated = 0 55.12.218.252 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 872, t_last = 78743687558 55.12.218.295 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 943.586 MiB) 55.12.240.641 I slot launch_slot_: id 0 | task 22701 | processing task, is_child = 0 55.16.211.184 I slot print_timing: id 0 | task 22701 | prompt processing, n_tokens = 345, progress = 0.99, t = 3.97 s / 86.89 tokens per second 55.26.545.896 I slot print_timing: id 0 | task 22701 | n_gen = 100, tg = 10.06 t/s, tg_3s = 10.16 t/s 55.29.325.990 I slot print_timing: id 0 | task 22701 | prompt eval time = 4462.90 ms / 349 tokens ( 12.79 ms per token, 78.20 tokens per second) 55.29.325.992 I slot print_timing: id 0 | task 22701 | eval time = 12622.44 ms / 128 tokens ( 99.39 ms per token, 10.06 tokens per second) 55.29.325.993 I slot print_timing: id 0 | task 22701 | total time = 17085.34 ms / 477 tokens 55.29.325.993 I slot print_timing: id 0 | task 22701 | graphs reused = 21722 55.29.325.994 I slot print_timing: id 0 | task 22701 | graph reallocs = 0 / 0 (same size) / (changed size) 55.29.326.022 I slot release: id 0 | task 22701 | stop processing: n_tokens = 508, truncated = 0 55.29.330.368 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 508, t_last = 78760800201 55.29.330.401 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 924.204 MiB) 55.29.353.318 I slot launch_slot_: id 0 | task 22832 | processing task, is_child = 0 55.33.652.289 I slot print_timing: id 0 | task 22832 | prompt processing, n_tokens = 381, progress = 0.99, t = 4.30 s / 88.63 tokens per second 55.44.102.639 I slot print_timing: id 0 | task 22832 | n_gen = 100, tg = 10.06 t/s, tg_3s = 10.16 t/s 55.47.184.447 I slot print_timing: id 0 | task 22832 | n_gen = 131, tg = 10.06 t/s, tg_3s = 10.06 t/s 55.48.776.404 I slot print_timing: id 0 | task 22832 | prompt eval time = 4909.98 ms / 385 tokens ( 12.75 ms per token, 78.41 tokens per second) 55.48.776.409 I slot print_timing: id 0 | task 22832 | eval time = 14513.09 ms / 147 tokens ( 99.40 ms per token, 10.06 tokens per second) 55.48.776.410 I slot print_timing: id 0 | task 22832 | total time = 19423.07 ms / 532 tokens 55.48.776.410 I slot print_timing: id 0 | task 22832 | graphs reused = 21866 55.48.776.411 I slot print_timing: id 0 | task 22832 | graph reallocs = 0 / 0 (same size) / (changed size) 55.48.776.438 I slot release: id 0 | task 22832 | stop processing: n_tokens = 563, truncated = 0 55.48.780.915 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 563, t_last = 78780250617 55.48.780.949 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 923.642 MiB) 55.48.804.091 I slot launch_slot_: id 0 | task 22982 | processing task, is_child = 0 55.52.411.678 I slot print_timing: id 0 | task 22982 | prompt processing, n_tokens = 324, progress = 0.99, t = 3.61 s / 89.81 tokens per second 55.58.585.228 I slot print_timing: id 0 | task 22982 | prompt eval time = 4217.90 ms / 328 tokens ( 12.86 ms per token, 77.76 tokens per second) 55.58.585.233 I slot print_timing: id 0 | task 22982 | eval time = 5563.22 ms / 57 tokens ( 99.34 ms per token, 10.07 tokens per second) 55.58.585.234 I slot print_timing: id 0 | task 22982 | total time = 9781.12 ms / 385 tokens 55.58.585.234 I slot print_timing: id 0 | task 22982 | graphs reused = 21921 55.58.585.234 I slot print_timing: id 0 | task 22982 | graph reallocs = 0 / 0 (same size) / (changed size) 55.58.585.258 I slot release: id 0 | task 22982 | stop processing: n_tokens = 416, truncated = 0 55.58.820.236 I srv operator(): operator(): cleaning up before exit...