/Users/minipro/quantdiff/work/llama-b11869/src/build/bin/llama-server -m /Users/minipro/quantdiff/models/campaign/7f43dd99e7d5/flint-UD-Q2_K_XL.gguf --host 127.0.0.1 --port 8091 -c 16384 -np 4 -ngl 999 -fa on --jinja --seed 1234 --chat-template-kwargs "{\"enable_thinking\": false}" --no-webui -a quant 0.00.046.332 W Setting 'enable_thinking' via --chat-template-kwargs is deprecated. Use --reasoning on / --reasoning off instead. 0.00.046.392 I srv llama_server: initializing ... 0.00.046.397 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.046.483 I srv init_listene: The UI is disabled 0.00.046.484 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.046.525 W srv server_setup: security: no API key is set and CORS allows all origins (see https://github.com/ggml-org/llama.cpp/pull/25655) 0.00.048.184 I srv load_model: loading model '/Users/minipro/quantdiff/models/campaign/7f43dd99e7d5/flint-UD-Q2_K_XL.gguf' 0.00.871.239 I cmn init: llama threadpool init, n_threads = 8 0.00.966.249 I srv load_model: initializing, n_slots = 4, n_ctx_slot = 4096, kv_unified = 'false' 0.00.975.211 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.00.975.221 I srv server_run_i: model loaded 0.00.975.223 I srv server_on_li: listening on http://127.0.0.1:8091 0.30.719.050 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.30.719.108 I slot launch_slot_: id 0 | task 1 | processing task, is_child = 0 0.30.719.109 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.30.719.152 I slot launch_slot_: id 1 | task 0 | processing task, is_child = 0 0.30.719.155 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.30.719.196 I slot launch_slot_: id 2 | task 2 | processing task, is_child = 0 0.30.719.197 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.30.719.233 I slot launch_slot_: id 3 | task 3 | processing task, is_child = 0 0.31.792.385 I slot print_timing: id 0 | task 1 | prompt eval time = 1031.61 ms / 115 tokens ( 8.97 ms per token, 111.48 tokens per second) 0.31.792.387 I slot print_timing: id 0 | task 1 | eval time = 41.53 ms / 2 tokens ( 41.53 ms per token, 24.08 tokens per second) 0.31.792.387 I slot print_timing: id 0 | task 1 | total time = 1073.14 ms / 117 tokens 0.31.792.388 I slot print_timing: id 0 | task 1 | graphs reused = 1 0.31.792.388 I slot print_timing: id 0 | task 1 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.792.408 I slot release: id 0 | task 1 | stop processing: n_tokens = 116, truncated = 0 0.31.792.499 I slot print_timing: id 1 | task 0 | prompt eval time = 1031.77 ms / 102 tokens ( 10.12 ms per token, 98.86 tokens per second) 0.31.792.502 I slot print_timing: id 1 | task 0 | eval time = 41.48 ms / 2 tokens ( 41.48 ms per token, 24.11 tokens per second) 0.31.792.502 I slot print_timing: id 1 | task 0 | total time = 1073.25 ms / 104 tokens 0.31.792.502 I slot print_timing: id 1 | task 0 | graphs reused = 1 0.31.792.503 I slot print_timing: id 1 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.792.514 I slot release: id 1 | task 0 | stop processing: n_tokens = 103, truncated = 0 0.31.792.601 I slot print_timing: id 2 | task 2 | prompt eval time = 1031.96 ms / 122 tokens ( 8.46 ms per token, 118.22 tokens per second) 0.31.792.603 I slot print_timing: id 2 | task 2 | eval time = 41.39 ms / 2 tokens ( 41.39 ms per token, 24.16 tokens per second) 0.31.792.603 I slot print_timing: id 2 | task 2 | total time = 1073.35 ms / 124 tokens 0.31.792.603 I slot print_timing: id 2 | task 2 | graphs reused = 1 0.31.792.604 I slot print_timing: id 2 | task 2 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.792.612 I slot release: id 2 | task 2 | stop processing: n_tokens = 123, truncated = 0 0.31.792.707 I slot print_timing: id 3 | task 3 | prompt eval time = 1032.14 ms / 107 tokens ( 9.65 ms per token, 103.67 tokens per second) 0.31.792.709 I slot print_timing: id 3 | task 3 | eval time = 41.31 ms / 2 tokens ( 41.31 ms per token, 24.21 tokens per second) 0.31.792.710 I slot print_timing: id 3 | task 3 | total time = 1073.45 ms / 109 tokens 0.31.792.710 I slot print_timing: id 3 | task 3 | graphs reused = 1 0.31.792.710 I slot print_timing: id 3 | task 3 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.792.720 I slot release: id 3 | task 3 | stop processing: n_tokens = 108, truncated = 0 0.31.800.845 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.273 (> 0.100 thold), f_keep = 0.233 0.31.802.383 I slot launch_slot_: id 0 | task 7 | processing task, is_child = 0 0.31.806.559 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.193 (> 0.100 thold), f_keep = 0.220 0.31.806.627 I slot launch_slot_: id 2 | task 8 | processing task, is_child = 0 0.31.806.679 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.174 (> 0.100 thold), f_keep = 0.252 0.31.806.734 I slot launch_slot_: id 1 | task 9 | processing task, is_child = 0 0.31.806.756 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.138 (> 0.100 thold), f_keep = 0.241 0.31.806.810 I slot launch_slot_: id 3 | task 10 | processing task, is_child = 0 0.33.320.972 I slot print_timing: id 0 | task 7 | prompt eval time = 1472.85 ms / 99 tokens ( 14.88 ms per token, 67.22 tokens per second) 0.33.320.975 I slot print_timing: id 0 | task 7 | eval time = 41.30 ms / 2 tokens ( 41.30 ms per token, 24.21 tokens per second) 0.33.320.975 I slot print_timing: id 0 | task 7 | total time = 1514.15 ms / 101 tokens 0.33.320.975 I slot print_timing: id 0 | task 7 | graphs reused = 1 0.33.320.976 I slot print_timing: id 0 | task 7 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.320.998 I slot release: id 0 | task 7 | stop processing: n_tokens = 100, truncated = 0 0.33.321.087 I slot print_timing: id 1 | task 9 | prompt eval time = 1472.93 ms / 149 tokens ( 9.89 ms per token, 101.16 tokens per second) 0.33.321.089 I slot print_timing: id 1 | task 9 | eval time = 41.32 ms / 2 tokens ( 41.32 ms per token, 24.20 tokens per second) 0.33.321.090 I slot print_timing: id 1 | task 9 | total time = 1514.25 ms / 151 tokens 0.33.321.090 I slot print_timing: id 1 | task 9 | graphs reused = 1 0.33.321.090 I slot print_timing: id 1 | task 9 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.321.102 I slot release: id 1 | task 9 | stop processing: n_tokens = 150, truncated = 0 0.33.321.185 I slot print_timing: id 2 | task 8 | prompt eval time = 1473.01 ms / 140 tokens ( 10.52 ms per token, 95.04 tokens per second) 0.33.321.186 I slot print_timing: id 2 | task 8 | eval time = 41.32 ms / 2 tokens ( 41.32 ms per token, 24.20 tokens per second) 0.33.321.187 I slot print_timing: id 2 | task 8 | total time = 1514.32 ms / 142 tokens 0.33.321.187 I slot print_timing: id 2 | task 8 | graphs reused = 1 0.33.321.187 I slot print_timing: id 2 | task 8 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.321.196 I slot release: id 2 | task 8 | stop processing: n_tokens = 141, truncated = 0 0.33.321.284 I slot print_timing: id 3 | task 10 | prompt eval time = 1473.09 ms / 189 tokens ( 7.79 ms per token, 128.30 tokens per second) 0.33.321.286 I slot print_timing: id 3 | task 10 | eval time = 41.31 ms / 2 tokens ( 41.31 ms per token, 24.21 tokens per second) 0.33.321.286 I slot print_timing: id 3 | task 10 | total time = 1514.41 ms / 191 tokens 0.33.321.286 I slot print_timing: id 3 | task 10 | graphs reused = 1 0.33.321.287 I slot print_timing: id 3 | task 10 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.321.300 I slot release: id 3 | task 10 | stop processing: n_tokens = 190, truncated = 0 0.33.326.429 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.222 (> 0.100 thold), f_keep = 0.260 0.33.327.488 I slot launch_slot_: id 0 | task 14 | processing task, is_child = 0 0.33.333.482 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.191 0.33.333.554 I slot launch_slot_: id 2 | task 15 | processing task, is_child = 0 0.33.333.605 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.173 0.33.333.680 I slot launch_slot_: id 1 | task 16 | processing task, is_child = 0 0.33.333.708 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.239 (> 0.100 thold), f_keep = 0.137 0.33.333.771 I slot launch_slot_: id 3 | task 17 | processing task, is_child = 0 0.34.454.506 I slot print_timing: id 0 | task 14 | prompt eval time = 1079.33 ms / 117 tokens ( 9.23 ms per token, 108.40 tokens per second) 0.34.454.509 I slot print_timing: id 0 | task 14 | eval time = 41.39 ms / 2 tokens ( 41.39 ms per token, 24.16 tokens per second) 0.34.454.510 I slot print_timing: id 0 | task 14 | total time = 1120.73 ms / 119 tokens 0.34.454.510 I slot print_timing: id 0 | task 14 | graphs reused = 1 0.34.454.511 I slot print_timing: id 0 | task 14 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.454.533 I slot release: id 0 | task 14 | stop processing: n_tokens = 118, truncated = 0 0.34.454.619 I slot print_timing: id 1 | task 16 | prompt eval time = 1079.41 ms / 138 tokens ( 7.82 ms per token, 127.85 tokens per second) 0.34.454.621 I slot print_timing: id 1 | task 16 | eval time = 41.41 ms / 2 tokens ( 41.41 ms per token, 24.15 tokens per second) 0.34.454.621 I slot print_timing: id 1 | task 16 | total time = 1120.82 ms / 140 tokens 0.34.454.621 I slot print_timing: id 1 | task 16 | graphs reused = 1 0.34.454.622 I slot print_timing: id 1 | task 16 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.454.634 I slot release: id 1 | task 16 | stop processing: n_tokens = 139, truncated = 0 0.34.454.723 I slot print_timing: id 2 | task 15 | prompt eval time = 1079.49 ms / 107 tokens ( 10.09 ms per token, 99.12 tokens per second) 0.34.454.728 I slot print_timing: id 2 | task 15 | eval time = 41.41 ms / 2 tokens ( 41.41 ms per token, 24.15 tokens per second) 0.34.454.732 I slot print_timing: id 2 | task 15 | total time = 1120.90 ms / 109 tokens 0.34.454.732 I slot print_timing: id 2 | task 15 | graphs reused = 1 0.34.454.732 I slot print_timing: id 2 | task 15 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.454.739 I slot release: id 2 | task 15 | stop processing: n_tokens = 108, truncated = 0 0.34.454.827 I slot print_timing: id 3 | task 17 | prompt eval time = 1079.57 ms / 109 tokens ( 9.90 ms per token, 100.97 tokens per second) 0.34.454.829 I slot print_timing: id 3 | task 17 | eval time = 41.42 ms / 2 tokens ( 41.42 ms per token, 24.15 tokens per second) 0.34.454.829 I slot print_timing: id 3 | task 17 | total time = 1120.99 ms / 111 tokens 0.34.454.829 I slot print_timing: id 3 | task 17 | graphs reused = 1 0.34.454.829 I slot print_timing: id 3 | task 17 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.454.835 I slot release: id 3 | task 17 | stop processing: n_tokens = 110, truncated = 0 0.34.460.723 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.236 (> 0.100 thold), f_keep = 0.220 0.34.461.925 I slot launch_slot_: id 0 | task 21 | processing task, is_child = 0 0.34.466.567 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.187 0.34.466.633 I slot launch_slot_: id 1 | task 23 | processing task, is_child = 0 0.34.466.679 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.193 (> 0.100 thold), f_keep = 0.241 0.34.466.738 I slot launch_slot_: id 2 | task 22 | processing task, is_child = 0 0.34.466.761 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.150 (> 0.100 thold), f_keep = 0.236 0.34.466.816 I slot launch_slot_: id 3 | task 24 | processing task, is_child = 0 0.35.910.803 I slot print_timing: id 0 | task 21 | prompt eval time = 1403.05 ms / 110 tokens ( 12.76 ms per token, 78.40 tokens per second) 0.35.910.806 I slot print_timing: id 0 | task 21 | eval time = 40.92 ms / 2 tokens ( 40.92 ms per token, 24.44 tokens per second) 0.35.910.806 I slot print_timing: id 0 | task 21 | total time = 1443.97 ms / 112 tokens 0.35.910.807 I slot print_timing: id 0 | task 21 | graphs reused = 1 0.35.910.807 I slot print_timing: id 0 | task 21 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.910.825 I slot release: id 0 | task 21 | stop processing: n_tokens = 111, truncated = 0 0.35.911.014 I slot print_timing: id 2 | task 22 | prompt eval time = 1403.21 ms / 135 tokens ( 10.39 ms per token, 96.21 tokens per second) 0.35.911.015 I slot print_timing: id 2 | task 22 | eval time = 40.94 ms / 2 tokens ( 40.94 ms per token, 24.42 tokens per second) 0.35.911.016 I slot print_timing: id 2 | task 22 | total time = 1444.15 ms / 137 tokens 0.35.911.016 I slot print_timing: id 2 | task 22 | graphs reused = 1 0.35.911.016 I slot print_timing: id 2 | task 22 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.911.032 I slot release: id 2 | task 22 | stop processing: n_tokens = 136, truncated = 0 0.35.911.127 I slot print_timing: id 3 | task 24 | prompt eval time = 1403.30 ms / 173 tokens ( 8.11 ms per token, 123.28 tokens per second) 0.35.911.129 I slot print_timing: id 3 | task 24 | eval time = 40.95 ms / 2 tokens ( 40.95 ms per token, 24.42 tokens per second) 0.35.911.130 I slot print_timing: id 3 | task 24 | total time = 1444.25 ms / 175 tokens 0.35.911.130 I slot print_timing: id 3 | task 24 | graphs reused = 1 0.35.911.130 I slot print_timing: id 3 | task 24 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.911.140 I slot release: id 3 | task 24 | stop processing: n_tokens = 174, truncated = 0 0.35.932.872 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.234 0.35.934.131 I slot launch_slot_: id 0 | task 29 | processing task, is_child = 0 0.35.938.188 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.158 (> 0.100 thold), f_keep = 0.191 0.35.938.279 I slot launch_slot_: id 2 | task 30 | processing task, is_child = 0 0.35.938.309 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.218 (> 0.100 thold), f_keep = 0.149 0.35.938.713 I slot launch_slot_: id 3 | task 31 | processing task, is_child = 0 0.37.126.186 I slot print_timing: id 1 | task 23 | prompt eval time = 1403.13 ms / 128 tokens ( 10.96 ms per token, 91.22 tokens per second) 0.37.126.191 I slot print_timing: id 1 | task 23 | eval time = 1256.21 ms / 4 tokens ( 418.74 ms per token, 2.39 tokens per second) 0.37.126.191 I slot print_timing: id 1 | task 23 | total time = 2659.34 ms / 132 tokens 0.37.126.192 I slot print_timing: id 1 | task 23 | graphs reused = 1 0.37.126.192 I slot print_timing: id 1 | task 23 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.126.214 I slot release: id 1 | task 23 | stop processing: n_tokens = 131, truncated = 0 0.37.222.025 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.226 (> 0.100 thold), f_keep = 0.198 0.37.224.345 I slot launch_slot_: id 1 | task 34 | processing task, is_child = 0 0.37.661.569 I slot print_timing: id 0 | task 29 | prompt eval time = 1283.11 ms / 130 tokens ( 9.87 ms per token, 101.32 tokens per second) 0.37.661.574 I slot print_timing: id 0 | task 29 | eval time = 439.74 ms / 2 tokens ( 439.74 ms per token, 2.27 tokens per second) 0.37.661.574 I slot print_timing: id 0 | task 29 | total time = 1722.84 ms / 132 tokens 0.37.661.575 I slot print_timing: id 0 | task 29 | graphs reused = 1 0.37.661.575 I slot print_timing: id 0 | task 29 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.661.597 I slot release: id 0 | task 29 | stop processing: n_tokens = 131, truncated = 0 0.37.661.699 I slot print_timing: id 2 | task 30 | prompt eval time = 1283.18 ms / 165 tokens ( 7.78 ms per token, 128.59 tokens per second) 0.37.661.703 I slot print_timing: id 2 | task 30 | eval time = 439.77 ms / 2 tokens ( 439.77 ms per token, 2.27 tokens per second) 0.37.661.703 I slot print_timing: id 2 | task 30 | total time = 1722.95 ms / 167 tokens 0.37.661.704 I slot print_timing: id 2 | task 30 | graphs reused = 1 0.37.661.704 I slot print_timing: id 2 | task 30 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.661.715 I slot release: id 2 | task 30 | stop processing: n_tokens = 166, truncated = 0 0.37.661.824 I slot print_timing: id 3 | task 31 | prompt eval time = 1283.25 ms / 119 tokens ( 10.78 ms per token, 92.73 tokens per second) 0.37.661.827 I slot print_timing: id 3 | task 31 | eval time = 439.80 ms / 2 tokens ( 439.80 ms per token, 2.27 tokens per second) 0.37.661.827 I slot print_timing: id 3 | task 31 | total time = 1723.06 ms / 121 tokens 0.37.661.827 I slot print_timing: id 3 | task 31 | graphs reused = 1 0.37.661.828 I slot print_timing: id 3 | task 31 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.661.836 I slot release: id 3 | task 31 | stop processing: n_tokens = 120, truncated = 0 0.37.702.368 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.198 0.37.703.717 I slot launch_slot_: id 0 | task 37 | processing task, is_child = 0 0.37.707.053 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.163 0.37.707.123 I slot launch_slot_: id 2 | task 38 | processing task, is_child = 0 0.37.707.153 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.217 0.37.707.215 I slot launch_slot_: id 3 | task 39 | processing task, is_child = 0 0.38.676.352 I slot print_timing: id 1 | task 34 | prompt eval time = 478.01 ms / 115 tokens ( 4.16 ms per token, 240.58 tokens per second) 0.38.676.355 I slot print_timing: id 1 | task 34 | eval time = 973.98 ms / 2 tokens ( 973.98 ms per token, 1.03 tokens per second) 0.38.676.355 I slot print_timing: id 1 | task 34 | total time = 1452.00 ms / 117 tokens 0.38.676.356 I slot print_timing: id 1 | task 34 | graphs reused = 1 0.38.676.356 I slot print_timing: id 1 | task 34 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.676.374 I slot release: id 1 | task 34 | stop processing: n_tokens = 116, truncated = 0 0.38.772.323 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.233 0.38.773.558 I slot launch_slot_: id 1 | task 42 | processing task, is_child = 0 0.39.196.126 I slot print_timing: id 0 | task 37 | prompt eval time = 1064.69 ms / 104 tokens ( 10.24 ms per token, 97.68 tokens per second) 0.39.196.129 I slot print_timing: id 0 | task 37 | eval time = 424.19 ms / 2 tokens ( 424.19 ms per token, 2.36 tokens per second) 0.39.196.129 I slot print_timing: id 0 | task 37 | total time = 1488.89 ms / 106 tokens 0.39.196.129 I slot print_timing: id 0 | task 37 | graphs reused = 1 0.39.196.130 I slot print_timing: id 0 | task 37 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.196.150 I slot release: id 0 | task 37 | stop processing: n_tokens = 105, truncated = 0 0.39.196.249 I slot print_timing: id 2 | task 38 | prompt eval time = 1064.88 ms / 135 tokens ( 7.89 ms per token, 126.77 tokens per second) 0.39.196.251 I slot print_timing: id 2 | task 38 | eval time = 424.12 ms / 2 tokens ( 424.12 ms per token, 2.36 tokens per second) 0.39.196.252 I slot print_timing: id 2 | task 38 | total time = 1489.00 ms / 137 tokens 0.39.196.252 I slot print_timing: id 2 | task 38 | graphs reused = 1 0.39.196.252 I slot print_timing: id 2 | task 38 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.196.270 I slot release: id 2 | task 38 | stop processing: n_tokens = 136, truncated = 0 0.39.196.375 I slot print_timing: id 3 | task 39 | prompt eval time = 1065.05 ms / 134 tokens ( 7.95 ms per token, 125.82 tokens per second) 0.39.196.376 I slot print_timing: id 3 | task 39 | eval time = 424.06 ms / 2 tokens ( 424.06 ms per token, 2.36 tokens per second) 0.39.196.376 I slot print_timing: id 3 | task 39 | total time = 1489.11 ms / 136 tokens 0.39.196.377 I slot print_timing: id 3 | task 39 | graphs reused = 1 0.39.196.377 I slot print_timing: id 3 | task 39 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.196.386 I slot release: id 3 | task 39 | stop processing: n_tokens = 135, truncated = 0 0.39.237.334 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.248 0.39.238.585 I slot launch_slot_: id 0 | task 45 | processing task, is_child = 0 0.39.242.487 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.193 (> 0.100 thold), f_keep = 0.191 0.39.242.574 I slot launch_slot_: id 2 | task 46 | processing task, is_child = 0 0.39.242.601 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.193 0.39.243.006 I slot launch_slot_: id 3 | task 47 | processing task, is_child = 0 0.40.269.518 I slot print_timing: id 1 | task 42 | prompt eval time = 463.76 ms / 108 tokens ( 4.29 ms per token, 232.88 tokens per second) 0.40.269.524 I slot print_timing: id 1 | task 42 | eval time = 1032.19 ms / 2 tokens ( 1032.19 ms per token, 0.97 tokens per second) 0.40.269.524 I slot print_timing: id 1 | task 42 | total time = 1495.95 ms / 110 tokens 0.40.269.525 I slot print_timing: id 1 | task 42 | graphs reused = 1 0.40.269.525 I slot print_timing: id 1 | task 42 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.269.542 I slot release: id 1 | task 42 | stop processing: n_tokens = 109, truncated = 0 0.40.364.575 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.268 (> 0.100 thold), f_keep = 0.239 0.40.365.887 I slot launch_slot_: id 1 | task 50 | processing task, is_child = 0 0.40.748.271 I slot print_timing: id 0 | task 45 | prompt eval time = 1121.37 ms / 113 tokens ( 9.92 ms per token, 100.77 tokens per second) 0.40.748.273 I slot print_timing: id 0 | task 45 | eval time = 383.89 ms / 2 tokens ( 383.89 ms per token, 2.60 tokens per second) 0.40.748.273 I slot print_timing: id 0 | task 45 | total time = 1505.25 ms / 115 tokens 0.40.748.274 I slot print_timing: id 0 | task 45 | graphs reused = 1 0.40.748.274 I slot print_timing: id 0 | task 45 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.748.290 I slot release: id 0 | task 45 | stop processing: n_tokens = 114, truncated = 0 0.40.748.384 I slot print_timing: id 2 | task 46 | prompt eval time = 1121.44 ms / 135 tokens ( 8.31 ms per token, 120.38 tokens per second) 0.40.748.386 I slot print_timing: id 2 | task 46 | eval time = 383.91 ms / 2 tokens ( 383.91 ms per token, 2.60 tokens per second) 0.40.748.386 I slot print_timing: id 2 | task 46 | total time = 1505.35 ms / 137 tokens 0.40.748.387 I slot print_timing: id 2 | task 46 | graphs reused = 1 0.40.748.387 I slot print_timing: id 2 | task 46 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.748.399 I slot release: id 2 | task 46 | stop processing: n_tokens = 136, truncated = 0 0.40.748.502 I slot print_timing: id 3 | task 47 | prompt eval time = 1121.51 ms / 104 tokens ( 10.78 ms per token, 92.73 tokens per second) 0.40.748.504 I slot print_timing: id 3 | task 47 | eval time = 383.93 ms / 2 tokens ( 383.93 ms per token, 2.60 tokens per second) 0.40.748.504 I slot print_timing: id 3 | task 47 | total time = 1505.45 ms / 106 tokens 0.40.748.504 I slot print_timing: id 3 | task 47 | graphs reused = 1 0.40.748.504 I slot print_timing: id 3 | task 47 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.748.513 I slot release: id 3 | task 47 | stop processing: n_tokens = 105, truncated = 0 0.40.789.526 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.202 (> 0.100 thold), f_keep = 0.228 0.40.790.808 I slot launch_slot_: id 0 | task 53 | processing task, is_child = 0 0.40.793.806 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.286 0.40.793.876 I slot launch_slot_: id 3 | task 54 | processing task, is_child = 0 0.40.793.903 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.274 (> 0.100 thold), f_keep = 0.191 0.40.793.971 I slot launch_slot_: id 2 | task 55 | processing task, is_child = 0 0.41.796.236 I slot print_timing: id 1 | task 50 | prompt eval time = 423.62 ms / 97 tokens ( 4.37 ms per token, 228.98 tokens per second) 0.41.796.241 I slot print_timing: id 1 | task 50 | eval time = 1006.71 ms / 2 tokens ( 1006.71 ms per token, 0.99 tokens per second) 0.41.796.241 I slot print_timing: id 1 | task 50 | total time = 1430.34 ms / 99 tokens 0.41.796.242 I slot print_timing: id 1 | task 50 | graphs reused = 1 0.41.796.242 I slot print_timing: id 1 | task 50 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.796.263 I slot release: id 1 | task 50 | stop processing: n_tokens = 98, truncated = 0 0.41.891.507 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.265 (> 0.100 thold), f_keep = 0.265 0.41.893.188 I slot launch_slot_: id 1 | task 58 | processing task, is_child = 0 0.42.282.629 I slot print_timing: id 0 | task 53 | prompt eval time = 1097.31 ms / 129 tokens ( 8.51 ms per token, 117.56 tokens per second) 0.42.282.631 I slot print_timing: id 0 | task 53 | eval time = 391.34 ms / 2 tokens ( 391.34 ms per token, 2.56 tokens per second) 0.42.282.631 I slot print_timing: id 0 | task 53 | total time = 1488.65 ms / 131 tokens 0.42.282.632 I slot print_timing: id 0 | task 53 | graphs reused = 1 0.42.282.632 I slot print_timing: id 0 | task 53 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.282.654 I slot release: id 0 | task 53 | stop processing: n_tokens = 130, truncated = 0 0.42.282.753 I slot print_timing: id 2 | task 55 | prompt eval time = 1097.40 ms / 95 tokens ( 11.55 ms per token, 86.57 tokens per second) 0.42.282.756 I slot print_timing: id 2 | task 55 | eval time = 391.36 ms / 2 tokens ( 391.36 ms per token, 2.56 tokens per second) 0.42.282.757 I slot print_timing: id 2 | task 55 | total time = 1488.75 ms / 97 tokens 0.42.282.757 I slot print_timing: id 2 | task 55 | graphs reused = 1 0.42.282.757 I slot print_timing: id 2 | task 55 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.282.765 I slot release: id 2 | task 55 | stop processing: n_tokens = 96, truncated = 0 0.42.282.876 I slot print_timing: id 3 | task 54 | prompt eval time = 1097.48 ms / 120 tokens ( 9.15 ms per token, 109.34 tokens per second) 0.42.282.879 I slot print_timing: id 3 | task 54 | eval time = 391.37 ms / 2 tokens ( 391.37 ms per token, 2.56 tokens per second) 0.42.282.879 I slot print_timing: id 3 | task 54 | total time = 1488.86 ms / 122 tokens 0.42.282.879 I slot print_timing: id 3 | task 54 | graphs reused = 1 0.42.282.880 I slot print_timing: id 3 | task 54 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.282.891 I slot release: id 3 | task 54 | stop processing: n_tokens = 121, truncated = 0 0.42.323.994 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.208 (> 0.100 thold), f_keep = 0.200 0.42.325.987 I slot launch_slot_: id 0 | task 61 | processing task, is_child = 0 0.42.329.066 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.158 (> 0.100 thold), f_keep = 0.271 0.42.329.137 I slot launch_slot_: id 2 | task 62 | processing task, is_child = 0 0.42.329.164 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.149 (> 0.100 thold), f_keep = 0.215 0.42.329.237 I slot launch_slot_: id 3 | task 63 | processing task, is_child = 0 0.43.416.275 I slot print_timing: id 1 | task 58 | prompt eval time = 430.80 ms / 98 tokens ( 4.40 ms per token, 227.49 tokens per second) 0.43.416.278 I slot print_timing: id 1 | task 58 | eval time = 1092.28 ms / 2 tokens ( 1092.28 ms per token, 0.92 tokens per second) 0.43.416.278 I slot print_timing: id 1 | task 58 | total time = 1523.07 ms / 100 tokens 0.43.416.279 I slot print_timing: id 1 | task 58 | graphs reused = 1 0.43.416.279 I slot print_timing: id 1 | task 58 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.416.299 I slot release: id 1 | task 58 | stop processing: n_tokens = 99, truncated = 0 0.43.514.125 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.165 (> 0.100 thold), f_keep = 0.263 0.43.514.757 I slot launch_slot_: id 1 | task 66 | processing task, is_child = 0 0.43.993.497 I slot print_timing: id 0 | task 61 | prompt eval time = 1184.68 ms / 125 tokens ( 9.48 ms per token, 105.51 tokens per second) 0.43.993.499 I slot print_timing: id 0 | task 61 | eval time = 479.57 ms / 2 tokens ( 479.57 ms per token, 2.09 tokens per second) 0.43.993.499 I slot print_timing: id 0 | task 61 | total time = 1664.25 ms / 127 tokens 0.43.993.500 I slot print_timing: id 0 | task 61 | graphs reused = 1 0.43.993.500 I slot print_timing: id 0 | task 61 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.993.521 I slot release: id 0 | task 61 | stop processing: n_tokens = 126, truncated = 0 0.43.993.622 I slot print_timing: id 2 | task 62 | prompt eval time = 1184.76 ms / 165 tokens ( 7.18 ms per token, 139.27 tokens per second) 0.43.993.624 I slot print_timing: id 2 | task 62 | eval time = 479.59 ms / 2 tokens ( 479.59 ms per token, 2.09 tokens per second) 0.43.993.624 I slot print_timing: id 2 | task 62 | total time = 1664.35 ms / 167 tokens 0.43.993.624 I slot print_timing: id 2 | task 62 | graphs reused = 1 0.43.993.625 I slot print_timing: id 2 | task 62 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.993.644 I slot release: id 2 | task 62 | stop processing: n_tokens = 166, truncated = 0 0.43.993.758 I slot print_timing: id 3 | task 63 | prompt eval time = 1184.83 ms / 174 tokens ( 6.81 ms per token, 146.86 tokens per second) 0.43.993.759 I slot print_timing: id 3 | task 63 | eval time = 479.64 ms / 2 tokens ( 479.64 ms per token, 2.08 tokens per second) 0.43.993.759 I slot print_timing: id 3 | task 63 | total time = 1664.47 ms / 176 tokens 0.43.993.760 I slot print_timing: id 3 | task 63 | graphs reused = 1 0.43.993.760 I slot print_timing: id 3 | task 63 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.993.772 I slot release: id 3 | task 63 | stop processing: n_tokens = 175, truncated = 0 0.44.035.809 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.186 (> 0.100 thold), f_keep = 0.206 0.44.037.528 I slot launch_slot_: id 0 | task 69 | processing task, is_child = 0 0.44.042.114 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.165 (> 0.100 thold), f_keep = 0.157 0.44.042.184 I slot launch_slot_: id 2 | task 70 | processing task, is_child = 0 0.44.042.214 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.195 (> 0.100 thold), f_keep = 0.149 0.44.042.574 I slot launch_slot_: id 3 | task 71 | processing task, is_child = 0 0.45.156.195 I slot print_timing: id 1 | task 66 | prompt eval time = 521.04 ms / 158 tokens ( 3.30 ms per token, 303.24 tokens per second) 0.45.156.200 I slot print_timing: id 1 | task 66 | eval time = 1120.39 ms / 2 tokens ( 1120.39 ms per token, 0.89 tokens per second) 0.45.156.200 I slot print_timing: id 1 | task 66 | total time = 1641.43 ms / 160 tokens 0.45.156.201 I slot print_timing: id 1 | task 66 | graphs reused = 1 0.45.156.201 I slot print_timing: id 1 | task 66 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.156.221 I slot release: id 1 | task 66 | stop processing: n_tokens = 159, truncated = 0 0.45.252.059 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.164 0.45.253.829 I slot launch_slot_: id 1 | task 74 | processing task, is_child = 0 0.45.678.423 I slot print_timing: id 0 | task 69 | prompt eval time = 1209.28 ms / 140 tokens ( 8.64 ms per token, 115.77 tokens per second) 0.45.678.428 I slot print_timing: id 0 | task 69 | eval time = 426.56 ms / 2 tokens ( 426.56 ms per token, 2.34 tokens per second) 0.45.678.429 I slot print_timing: id 0 | task 69 | total time = 1635.84 ms / 142 tokens 0.45.678.429 I slot print_timing: id 0 | task 69 | graphs reused = 1 0.45.678.430 I slot print_timing: id 0 | task 69 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.678.450 I slot release: id 0 | task 69 | stop processing: n_tokens = 141, truncated = 0 0.45.678.546 I slot print_timing: id 2 | task 70 | prompt eval time = 1209.35 ms / 158 tokens ( 7.65 ms per token, 130.65 tokens per second) 0.45.678.548 I slot print_timing: id 2 | task 70 | eval time = 426.59 ms / 2 tokens ( 426.59 ms per token, 2.34 tokens per second) 0.45.678.549 I slot print_timing: id 2 | task 70 | total time = 1635.94 ms / 160 tokens 0.45.678.549 I slot print_timing: id 2 | task 70 | graphs reused = 1 0.45.678.549 I slot print_timing: id 2 | task 70 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.678.562 I slot release: id 2 | task 70 | stop processing: n_tokens = 159, truncated = 0 0.45.678.666 I slot print_timing: id 3 | task 71 | prompt eval time = 1209.42 ms / 133 tokens ( 9.09 ms per token, 109.97 tokens per second) 0.45.678.667 I slot print_timing: id 3 | task 71 | eval time = 426.61 ms / 2 tokens ( 426.61 ms per token, 2.34 tokens per second) 0.45.678.668 I slot print_timing: id 3 | task 71 | total time = 1636.04 ms / 135 tokens 0.45.678.668 I slot print_timing: id 3 | task 71 | graphs reused = 1 0.45.678.668 I slot print_timing: id 3 | task 71 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.678.676 I slot release: id 3 | task 71 | stop processing: n_tokens = 134, truncated = 0 0.45.719.589 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.273 (> 0.100 thold), f_keep = 0.201 0.45.721.535 I slot launch_slot_: id 3 | task 77 | processing task, is_child = 0 0.45.725.706 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.167 (> 0.100 thold), f_keep = 0.184 0.45.725.783 I slot launch_slot_: id 0 | task 78 | processing task, is_child = 0 0.45.725.812 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.218 (> 0.100 thold), f_keep = 0.164 0.45.725.895 I slot launch_slot_: id 2 | task 79 | processing task, is_child = 0 0.46.732.875 I slot print_timing: id 1 | task 74 | prompt eval time = 465.75 ms / 114 tokens ( 4.09 ms per token, 244.77 tokens per second) 0.46.732.878 I slot print_timing: id 1 | task 74 | eval time = 1013.28 ms / 2 tokens ( 1013.28 ms per token, 0.99 tokens per second) 0.46.732.878 I slot print_timing: id 1 | task 74 | total time = 1479.03 ms / 116 tokens 0.46.732.879 I slot print_timing: id 1 | task 74 | graphs reused = 1 0.46.732.879 I slot print_timing: id 1 | task 74 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.732.896 I slot release: id 1 | task 74 | stop processing: n_tokens = 115, truncated = 0 0.46.828.762 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.235 0.46.830.516 I slot launch_slot_: id 1 | task 82 | processing task, is_child = 0 0.47.306.325 I slot print_timing: id 0 | task 78 | prompt eval time = 1102.67 ms / 156 tokens ( 7.07 ms per token, 141.48 tokens per second) 0.47.306.328 I slot print_timing: id 0 | task 78 | eval time = 477.75 ms / 2 tokens ( 477.75 ms per token, 2.09 tokens per second) 0.47.306.328 I slot print_timing: id 0 | task 78 | total time = 1580.42 ms / 158 tokens 0.47.306.328 I slot print_timing: id 0 | task 78 | graphs reused = 1 0.47.306.329 I slot print_timing: id 0 | task 78 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.306.347 I slot release: id 0 | task 78 | stop processing: n_tokens = 157, truncated = 0 0.47.306.451 I slot print_timing: id 2 | task 79 | prompt eval time = 1102.73 ms / 119 tokens ( 9.27 ms per token, 107.91 tokens per second) 0.47.306.453 I slot print_timing: id 2 | task 79 | eval time = 477.79 ms / 2 tokens ( 477.79 ms per token, 2.09 tokens per second) 0.47.306.454 I slot print_timing: id 2 | task 79 | total time = 1580.52 ms / 121 tokens 0.47.306.454 I slot print_timing: id 2 | task 79 | graphs reused = 1 0.47.306.454 I slot print_timing: id 2 | task 79 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.306.464 I slot release: id 2 | task 79 | stop processing: n_tokens = 120, truncated = 0 0.47.306.563 I slot print_timing: id 3 | task 77 | prompt eval time = 1102.80 ms / 99 tokens ( 11.14 ms per token, 89.77 tokens per second) 0.47.306.565 I slot print_timing: id 3 | task 77 | eval time = 477.81 ms / 2 tokens ( 477.81 ms per token, 2.09 tokens per second) 0.47.306.566 I slot print_timing: id 3 | task 77 | total time = 1580.61 ms / 101 tokens 0.47.306.567 I slot print_timing: id 3 | task 77 | graphs reused = 1 0.47.306.567 I slot print_timing: id 3 | task 77 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.306.578 I slot release: id 3 | task 77 | stop processing: n_tokens = 100, truncated = 0 0.47.348.252 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.165 (> 0.100 thold), f_keep = 0.166 0.47.350.521 I slot launch_slot_: id 0 | task 85 | processing task, is_child = 0 0.47.353.260 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.257 (> 0.100 thold), f_keep = 0.217 0.47.353.331 I slot launch_slot_: id 2 | task 86 | processing task, is_child = 0 0.47.353.357 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.167 (> 0.100 thold), f_keep = 0.260 0.47.353.420 I slot launch_slot_: id 3 | task 87 | processing task, is_child = 0 0.48.530.307 I slot print_timing: id 1 | task 82 | prompt eval time = 517.72 ms / 148 tokens ( 3.50 ms per token, 285.87 tokens per second) 0.48.530.312 I slot print_timing: id 1 | task 82 | eval time = 1182.05 ms / 2 tokens ( 1182.05 ms per token, 0.85 tokens per second) 0.48.530.313 I slot print_timing: id 1 | task 82 | total time = 1699.78 ms / 150 tokens 0.48.530.314 I slot print_timing: id 1 | task 82 | graphs reused = 1 0.48.530.314 I slot print_timing: id 1 | task 82 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.530.333 I slot release: id 1 | task 82 | stop processing: n_tokens = 149, truncated = 0 0.48.627.380 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.267 (> 0.100 thold), f_keep = 0.181 0.48.629.068 I slot launch_slot_: id 1 | task 90 | processing task, is_child = 0 0.49.014.643 I slot print_timing: id 0 | task 85 | prompt eval time = 1273.75 ms / 158 tokens ( 8.06 ms per token, 124.04 tokens per second) 0.49.014.649 I slot print_timing: id 0 | task 85 | eval time = 387.46 ms / 2 tokens ( 387.46 ms per token, 2.58 tokens per second) 0.49.014.649 I slot print_timing: id 0 | task 85 | total time = 1661.22 ms / 160 tokens 0.49.014.649 I slot print_timing: id 0 | task 85 | graphs reused = 1 0.49.014.650 I slot print_timing: id 0 | task 85 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.014.669 I slot release: id 0 | task 85 | stop processing: n_tokens = 159, truncated = 0 0.49.014.766 I slot print_timing: id 2 | task 86 | prompt eval time = 1273.83 ms / 101 tokens ( 12.61 ms per token, 79.29 tokens per second) 0.49.014.769 I slot print_timing: id 2 | task 86 | eval time = 387.48 ms / 2 tokens ( 387.48 ms per token, 2.58 tokens per second) 0.49.014.769 I slot print_timing: id 2 | task 86 | total time = 1661.31 ms / 103 tokens 0.49.014.769 I slot print_timing: id 2 | task 86 | graphs reused = 1 0.49.014.770 I slot print_timing: id 2 | task 86 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.014.778 I slot release: id 2 | task 86 | stop processing: n_tokens = 102, truncated = 0 0.49.014.882 I slot print_timing: id 3 | task 87 | prompt eval time = 1273.90 ms / 156 tokens ( 8.17 ms per token, 122.46 tokens per second) 0.49.014.884 I slot print_timing: id 3 | task 87 | eval time = 387.51 ms / 2 tokens ( 387.51 ms per token, 2.58 tokens per second) 0.49.014.885 I slot print_timing: id 3 | task 87 | total time = 1661.41 ms / 158 tokens 0.49.014.885 I slot print_timing: id 3 | task 87 | graphs reused = 1 0.49.014.886 I slot print_timing: id 3 | task 87 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.014.899 I slot release: id 3 | task 87 | stop processing: n_tokens = 157, truncated = 0 0.49.056.279 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.164 0.49.058.889 I slot launch_slot_: id 0 | task 93 | processing task, is_child = 0 0.49.061.698 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.255 0.49.061.775 I slot launch_slot_: id 2 | task 94 | processing task, is_child = 0 0.49.061.804 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.210 (> 0.100 thold), f_keep = 0.166 0.49.061.870 I slot launch_slot_: id 3 | task 95 | processing task, is_child = 0 0.50.063.383 I slot print_timing: id 1 | task 90 | prompt eval time = 427.20 ms / 101 tokens ( 4.23 ms per token, 236.42 tokens per second) 0.50.063.388 I slot print_timing: id 1 | task 90 | eval time = 1007.11 ms / 2 tokens ( 1007.11 ms per token, 0.99 tokens per second) 0.50.063.389 I slot print_timing: id 1 | task 90 | total time = 1434.30 ms / 103 tokens 0.50.063.389 I slot print_timing: id 1 | task 90 | graphs reused = 1 0.50.063.390 I slot print_timing: id 1 | task 90 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.063.410 I slot release: id 1 | task 90 | stop processing: n_tokens = 102, truncated = 0 0.50.161.129 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.255 0.50.162.243 I slot launch_slot_: id 1 | task 98 | processing task, is_child = 0 0.50.591.285 I slot print_timing: id 0 | task 93 | prompt eval time = 1099.06 ms / 114 tokens ( 9.64 ms per token, 103.73 tokens per second) 0.50.591.290 I slot print_timing: id 0 | task 93 | eval time = 430.34 ms / 2 tokens ( 430.34 ms per token, 2.32 tokens per second) 0.50.591.291 I slot print_timing: id 0 | task 93 | total time = 1529.40 ms / 116 tokens 0.50.591.291 I slot print_timing: id 0 | task 93 | graphs reused = 1 0.50.591.291 I slot print_timing: id 0 | task 93 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.591.311 I slot release: id 0 | task 93 | stop processing: n_tokens = 115, truncated = 0 0.50.591.414 I slot print_timing: id 2 | task 94 | prompt eval time = 1099.13 ms / 134 tokens ( 8.20 ms per token, 121.91 tokens per second) 0.50.591.418 I slot print_timing: id 2 | task 94 | eval time = 430.38 ms / 2 tokens ( 430.38 ms per token, 2.32 tokens per second) 0.50.591.419 I slot print_timing: id 2 | task 94 | total time = 1529.51 ms / 136 tokens 0.50.591.419 I slot print_timing: id 2 | task 94 | graphs reused = 1 0.50.591.419 I slot print_timing: id 2 | task 94 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.591.428 I slot release: id 2 | task 94 | stop processing: n_tokens = 135, truncated = 0 0.50.591.531 I slot print_timing: id 3 | task 95 | prompt eval time = 1099.21 ms / 124 tokens ( 8.86 ms per token, 112.81 tokens per second) 0.50.591.533 I slot print_timing: id 3 | task 95 | eval time = 430.40 ms / 2 tokens ( 430.40 ms per token, 2.32 tokens per second) 0.50.591.534 I slot print_timing: id 3 | task 95 | total time = 1529.62 ms / 126 tokens 0.50.591.534 I slot print_timing: id 3 | task 95 | graphs reused = 1 0.50.591.534 I slot print_timing: id 3 | task 95 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.591.543 I slot release: id 3 | task 95 | stop processing: n_tokens = 125, truncated = 0 0.50.632.539 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.235 0.50.634.205 I slot launch_slot_: id 0 | task 101 | processing task, is_child = 0 0.50.637.471 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.195 (> 0.100 thold), f_keep = 0.193 0.50.637.824 I slot launch_slot_: id 2 | task 102 | processing task, is_child = 0 0.50.637.852 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.208 0.50.637.916 I slot launch_slot_: id 3 | task 103 | processing task, is_child = 0 0.51.688.626 I slot print_timing: id 1 | task 98 | prompt eval time = 470.29 ms / 113 tokens ( 4.16 ms per token, 240.28 tokens per second) 0.51.688.630 I slot print_timing: id 1 | task 98 | eval time = 1056.09 ms / 2 tokens ( 1056.09 ms per token, 0.95 tokens per second) 0.51.688.631 I slot print_timing: id 1 | task 98 | total time = 1526.37 ms / 115 tokens 0.51.688.631 I slot print_timing: id 1 | task 98 | graphs reused = 1 0.51.688.631 I slot print_timing: id 1 | task 98 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.688.651 I slot release: id 1 | task 98 | stop processing: n_tokens = 114, truncated = 0 0.51.784.844 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.217 (> 0.100 thold), f_keep = 0.228 0.51.786.460 I slot launch_slot_: id 1 | task 106 | processing task, is_child = 0 0.52.211.935 I slot print_timing: id 0 | task 101 | prompt eval time = 1146.73 ms / 133 tokens ( 8.62 ms per token, 115.98 tokens per second) 0.52.211.940 I slot print_timing: id 0 | task 101 | eval time = 427.28 ms / 2 tokens ( 427.28 ms per token, 2.34 tokens per second) 0.52.211.941 I slot print_timing: id 0 | task 101 | total time = 1574.01 ms / 135 tokens 0.52.211.941 I slot print_timing: id 0 | task 101 | graphs reused = 1 0.52.211.942 I slot print_timing: id 0 | task 101 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.211.962 I slot release: id 0 | task 101 | stop processing: n_tokens = 134, truncated = 0 0.52.212.062 I slot print_timing: id 2 | task 102 | prompt eval time = 1146.81 ms / 133 tokens ( 8.62 ms per token, 115.97 tokens per second) 0.52.212.064 I slot print_timing: id 2 | task 102 | eval time = 427.31 ms / 2 tokens ( 427.31 ms per token, 2.34 tokens per second) 0.52.212.064 I slot print_timing: id 2 | task 102 | total time = 1574.12 ms / 135 tokens 0.52.212.065 I slot print_timing: id 2 | task 102 | graphs reused = 1 0.52.212.065 I slot print_timing: id 2 | task 102 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.212.076 I slot release: id 2 | task 102 | stop processing: n_tokens = 134, truncated = 0 0.52.212.180 I slot print_timing: id 3 | task 103 | prompt eval time = 1146.88 ms / 113 tokens ( 10.15 ms per token, 98.53 tokens per second) 0.52.212.182 I slot print_timing: id 3 | task 103 | eval time = 427.34 ms / 2 tokens ( 427.34 ms per token, 2.34 tokens per second) 0.52.212.182 I slot print_timing: id 3 | task 103 | total time = 1574.22 ms / 115 tokens 0.52.212.183 I slot print_timing: id 3 | task 103 | graphs reused = 1 0.52.212.183 I slot print_timing: id 3 | task 103 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.212.192 I slot release: id 3 | task 103 | stop processing: n_tokens = 114, truncated = 0 0.52.253.383 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.245 (> 0.100 thold), f_keep = 0.201 0.52.254.877 I slot launch_slot_: id 0 | task 109 | processing task, is_child = 0 0.52.258.411 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.263 (> 0.100 thold), f_keep = 0.194 0.52.258.481 I slot launch_slot_: id 2 | task 110 | processing task, is_child = 0 0.52.258.509 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.228 0.52.258.569 I slot launch_slot_: id 3 | task 111 | processing task, is_child = 0 0.53.192.219 I slot print_timing: id 1 | task 106 | prompt eval time = 466.91 ms / 120 tokens ( 3.89 ms per token, 257.01 tokens per second) 0.53.192.225 I slot print_timing: id 1 | task 106 | eval time = 938.84 ms / 2 tokens ( 938.84 ms per token, 1.07 tokens per second) 0.53.192.226 I slot print_timing: id 1 | task 106 | total time = 1405.75 ms / 122 tokens 0.53.192.226 I slot print_timing: id 1 | task 106 | graphs reused = 1 0.53.192.227 I slot print_timing: id 1 | task 106 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.192.246 I slot release: id 1 | task 106 | stop processing: n_tokens = 121, truncated = 0 0.53.287.997 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.160 (> 0.100 thold), f_keep = 0.215 0.53.289.401 I slot launch_slot_: id 1 | task 114 | processing task, is_child = 0 0.53.772.299 I slot print_timing: id 0 | task 109 | prompt eval time = 1029.21 ms / 110 tokens ( 9.36 ms per token, 106.88 tokens per second) 0.53.772.304 I slot print_timing: id 0 | task 109 | eval time = 484.50 ms / 2 tokens ( 484.50 ms per token, 2.06 tokens per second) 0.53.772.305 I slot print_timing: id 0 | task 109 | total time = 1513.71 ms / 112 tokens 0.53.772.305 I slot print_timing: id 0 | task 109 | graphs reused = 1 0.53.772.305 I slot print_timing: id 0 | task 109 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.772.324 I slot release: id 0 | task 109 | stop processing: n_tokens = 111, truncated = 0 0.53.772.421 I slot print_timing: id 2 | task 110 | prompt eval time = 1029.29 ms / 99 tokens ( 10.40 ms per token, 96.18 tokens per second) 0.53.772.427 I slot print_timing: id 2 | task 110 | eval time = 484.53 ms / 2 tokens ( 484.53 ms per token, 2.06 tokens per second) 0.53.772.427 I slot print_timing: id 2 | task 110 | total time = 1513.82 ms / 101 tokens 0.53.772.427 I slot print_timing: id 2 | task 110 | graphs reused = 1 0.53.772.428 I slot print_timing: id 2 | task 110 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.772.439 I slot release: id 2 | task 110 | stop processing: n_tokens = 100, truncated = 0 0.53.772.544 I slot print_timing: id 3 | task 111 | prompt eval time = 1029.36 ms / 113 tokens ( 9.11 ms per token, 109.78 tokens per second) 0.53.772.549 I slot print_timing: id 3 | task 111 | eval time = 484.55 ms / 2 tokens ( 484.55 ms per token, 2.06 tokens per second) 0.53.772.549 I slot print_timing: id 3 | task 111 | total time = 1513.91 ms / 115 tokens 0.53.772.550 I slot print_timing: id 3 | task 111 | graphs reused = 1 0.53.772.550 I slot print_timing: id 3 | task 111 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.772.560 I slot release: id 3 | task 111 | stop processing: n_tokens = 114, truncated = 0 0.53.815.087 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.243 0.53.816.332 I slot launch_slot_: id 0 | task 117 | processing task, is_child = 0 0.53.819.021 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.213 (> 0.100 thold), f_keep = 0.270 0.53.819.090 I slot launch_slot_: id 2 | task 118 | processing task, is_child = 0 0.53.819.118 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.121 (> 0.100 thold), f_keep = 0.228 0.53.819.182 I slot launch_slot_: id 3 | task 119 | processing task, is_child = 0 0.55.068.782 I slot print_timing: id 1 | task 114 | prompt eval time = 525.67 ms / 162 tokens ( 3.24 ms per token, 308.18 tokens per second) 0.55.068.784 I slot print_timing: id 1 | task 114 | eval time = 1253.69 ms / 2 tokens ( 1253.69 ms per token, 0.80 tokens per second) 0.55.068.786 I slot print_timing: id 1 | task 114 | total time = 1779.37 ms / 164 tokens 0.55.068.786 I slot print_timing: id 1 | task 114 | graphs reused = 1 0.55.068.786 I slot print_timing: id 1 | task 114 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.068.806 I slot release: id 1 | task 114 | stop processing: n_tokens = 163, truncated = 0 0.55.167.129 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.158 (> 0.100 thold), f_keep = 0.160 0.55.169.384 I slot launch_slot_: id 1 | task 122 | processing task, is_child = 0 0.55.662.362 I slot print_timing: id 0 | task 117 | prompt eval time = 1347.74 ms / 107 tokens ( 12.60 ms per token, 79.39 tokens per second) 0.55.662.368 I slot print_timing: id 0 | task 117 | eval time = 495.43 ms / 2 tokens ( 495.43 ms per token, 2.02 tokens per second) 0.55.662.368 I slot print_timing: id 0 | task 117 | total time = 1843.17 ms / 109 tokens 0.55.662.369 I slot print_timing: id 0 | task 117 | graphs reused = 1 0.55.662.369 I slot print_timing: id 0 | task 117 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.662.388 I slot release: id 0 | task 117 | stop processing: n_tokens = 108, truncated = 0 0.55.662.483 I slot print_timing: id 2 | task 118 | prompt eval time = 1347.82 ms / 127 tokens ( 10.61 ms per token, 94.23 tokens per second) 0.55.662.485 I slot print_timing: id 2 | task 118 | eval time = 495.45 ms / 2 tokens ( 495.45 ms per token, 2.02 tokens per second) 0.55.662.486 I slot print_timing: id 2 | task 118 | total time = 1843.27 ms / 129 tokens 0.55.662.486 I slot print_timing: id 2 | task 118 | graphs reused = 1 0.55.662.486 I slot print_timing: id 2 | task 118 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.662.495 I slot release: id 2 | task 118 | stop processing: n_tokens = 128, truncated = 0 0.55.662.598 I slot print_timing: id 3 | task 119 | prompt eval time = 1347.90 ms / 214 tokens ( 6.30 ms per token, 158.77 tokens per second) 0.55.662.599 I slot print_timing: id 3 | task 119 | eval time = 495.47 ms / 2 tokens ( 495.47 ms per token, 2.02 tokens per second) 0.55.662.600 I slot print_timing: id 3 | task 119 | total time = 1843.37 ms / 216 tokens 0.55.662.600 I slot print_timing: id 3 | task 119 | graphs reused = 1 0.55.662.601 I slot print_timing: id 3 | task 119 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.662.613 I slot release: id 3 | task 119 | stop processing: n_tokens = 215, truncated = 0 0.55.705.191 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.218 (> 0.100 thold), f_keep = 0.269 0.55.705.831 I slot launch_slot_: id 0 | task 125 | processing task, is_child = 0 0.55.710.649 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.176 (> 0.100 thold), f_keep = 0.203 0.55.710.739 I slot launch_slot_: id 2 | task 126 | processing task, is_child = 0 0.55.710.774 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.176 (> 0.100 thold), f_keep = 0.121 0.55.711.149 I slot launch_slot_: id 3 | task 127 | processing task, is_child = 0 0.56.715.377 I slot print_timing: id 1 | task 122 | prompt eval time = 535.80 ms / 165 tokens ( 3.25 ms per token, 307.95 tokens per second) 0.56.715.382 I slot print_timing: id 1 | task 122 | eval time = 1010.18 ms / 2 tokens ( 1010.18 ms per token, 0.99 tokens per second) 0.56.715.383 I slot print_timing: id 1 | task 122 | total time = 1545.98 ms / 167 tokens 0.56.715.383 I slot print_timing: id 1 | task 122 | graphs reused = 1 0.56.715.383 I slot print_timing: id 1 | task 122 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.715.405 I slot release: id 1 | task 122 | stop processing: n_tokens = 166, truncated = 0 0.56.812.434 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.122 (> 0.100 thold), f_keep = 0.157 0.56.814.903 I slot launch_slot_: id 1 | task 130 | processing task, is_child = 0 0.57.379.826 I slot print_timing: id 0 | task 125 | prompt eval time = 1101.07 ms / 133 tokens ( 8.28 ms per token, 120.79 tokens per second) 0.57.379.831 I slot print_timing: id 0 | task 125 | eval time = 567.59 ms / 2 tokens ( 567.59 ms per token, 1.76 tokens per second) 0.57.379.832 I slot print_timing: id 0 | task 125 | total time = 1668.66 ms / 135 tokens 0.57.379.832 I slot print_timing: id 0 | task 125 | graphs reused = 1 0.57.379.833 I slot print_timing: id 0 | task 125 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.379.854 I slot release: id 0 | task 125 | stop processing: n_tokens = 134, truncated = 0 0.57.379.951 I slot print_timing: id 2 | task 126 | prompt eval time = 1101.15 ms / 148 tokens ( 7.44 ms per token, 134.41 tokens per second) 0.57.379.956 I slot print_timing: id 2 | task 126 | eval time = 567.62 ms / 2 tokens ( 567.62 ms per token, 1.76 tokens per second) 0.57.379.956 I slot print_timing: id 2 | task 126 | total time = 1668.77 ms / 150 tokens 0.57.379.956 I slot print_timing: id 2 | task 126 | graphs reused = 1 0.57.379.957 I slot print_timing: id 2 | task 126 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.379.966 I slot release: id 2 | task 126 | stop processing: n_tokens = 149, truncated = 0 0.57.380.069 I slot print_timing: id 3 | task 127 | prompt eval time = 1101.23 ms / 148 tokens ( 7.44 ms per token, 134.39 tokens per second) 0.57.380.070 I slot print_timing: id 3 | task 127 | eval time = 567.64 ms / 2 tokens ( 567.64 ms per token, 1.76 tokens per second) 0.57.380.071 I slot print_timing: id 3 | task 127 | total time = 1668.87 ms / 150 tokens 0.57.380.071 I slot print_timing: id 3 | task 127 | graphs reused = 1 0.57.380.071 I slot print_timing: id 3 | task 127 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.380.090 I slot release: id 3 | task 127 | stop processing: n_tokens = 149, truncated = 0 0.57.423.162 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.299 (> 0.100 thold), f_keep = 0.216 0.57.424.629 I slot launch_slot_: id 0 | task 133 | processing task, is_child = 0 0.57.428.207 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.260 (> 0.100 thold), f_keep = 0.181 0.57.428.288 I slot launch_slot_: id 3 | task 134 | processing task, is_child = 0 0.57.428.317 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.148 (> 0.100 thold), f_keep = 0.174 0.57.428.668 I slot launch_slot_: id 2 | task 135 | processing task, is_child = 0 0.58.593.885 I slot print_timing: id 1 | task 130 | prompt eval time = 608.25 ms / 213 tokens ( 2.86 ms per token, 350.18 tokens per second) 0.58.593.891 I slot print_timing: id 1 | task 130 | eval time = 1170.72 ms / 2 tokens ( 1170.72 ms per token, 0.85 tokens per second) 0.58.593.891 I slot print_timing: id 1 | task 130 | total time = 1778.97 ms / 215 tokens 0.58.593.891 I slot print_timing: id 1 | task 130 | graphs reused = 1 0.58.593.892 I slot print_timing: id 1 | task 130 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.593.914 I slot release: id 1 | task 130 | stop processing: n_tokens = 214, truncated = 0 0.58.690.079 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.197 (> 0.100 thold), f_keep = 0.121 0.58.693.150 I slot launch_slot_: id 1 | task 138 | processing task, is_child = 0 0.59.141.435 I slot print_timing: id 0 | task 133 | prompt eval time = 1261.20 ms / 97 tokens ( 13.00 ms per token, 76.91 tokens per second) 0.59.141.440 I slot print_timing: id 0 | task 133 | eval time = 451.56 ms / 2 tokens ( 451.56 ms per token, 2.21 tokens per second) 0.59.141.440 I slot print_timing: id 0 | task 133 | total time = 1712.76 ms / 99 tokens 0.59.141.441 I slot print_timing: id 0 | task 133 | graphs reused = 1 0.59.141.441 I slot print_timing: id 0 | task 133 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.141.463 I slot release: id 0 | task 133 | stop processing: n_tokens = 98, truncated = 0 0.59.141.569 I slot print_timing: id 2 | task 135 | prompt eval time = 1261.28 ms / 176 tokens ( 7.17 ms per token, 139.54 tokens per second) 0.59.141.571 I slot print_timing: id 2 | task 135 | eval time = 451.58 ms / 2 tokens ( 451.58 ms per token, 2.21 tokens per second) 0.59.141.572 I slot print_timing: id 2 | task 135 | total time = 1712.87 ms / 178 tokens 0.59.141.572 I slot print_timing: id 2 | task 135 | graphs reused = 1 0.59.141.573 I slot print_timing: id 2 | task 135 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.141.587 I slot release: id 2 | task 135 | stop processing: n_tokens = 177, truncated = 0 0.59.141.706 I slot print_timing: id 3 | task 134 | prompt eval time = 1261.36 ms / 104 tokens ( 12.13 ms per token, 82.45 tokens per second) 0.59.141.708 I slot print_timing: id 3 | task 134 | eval time = 451.63 ms / 2 tokens ( 451.63 ms per token, 2.21 tokens per second) 0.59.141.708 I slot print_timing: id 3 | task 134 | total time = 1713.00 ms / 106 tokens 0.59.141.708 I slot print_timing: id 3 | task 134 | graphs reused = 1 0.59.141.709 I slot print_timing: id 3 | task 134 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.141.726 I slot release: id 3 | task 134 | stop processing: n_tokens = 105, truncated = 0 0.59.183.133 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.159 (> 0.100 thold), f_keep = 0.265 0.59.183.737 I slot launch_slot_: id 0 | task 141 | processing task, is_child = 0 0.59.186.233 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.245 (> 0.100 thold), f_keep = 0.257 0.59.186.299 I slot launch_slot_: id 3 | task 142 | processing task, is_child = 0 0.59.186.330 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.205 (> 0.100 thold), f_keep = 0.147 0.59.186.398 I slot launch_slot_: id 2 | task 143 | processing task, is_child = 0 1.00.248.128 I slot print_timing: id 1 | task 138 | prompt eval time = 489.97 ms / 132 tokens ( 3.71 ms per token, 269.40 tokens per second) 1.00.248.131 I slot print_timing: id 1 | task 138 | eval time = 1064.99 ms / 2 tokens ( 1064.99 ms per token, 0.94 tokens per second) 1.00.248.131 I slot print_timing: id 1 | task 138 | total time = 1554.97 ms / 134 tokens 1.00.248.132 I slot print_timing: id 1 | task 138 | graphs reused = 1 1.00.248.132 I slot print_timing: id 1 | task 138 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.248.154 I slot release: id 1 | task 138 | stop processing: n_tokens = 133, truncated = 0 1.00.345.543 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.260 (> 0.100 thold), f_keep = 0.195 1.00.347.861 I slot launch_slot_: id 1 | task 146 | processing task, is_child = 0 1.00.738.268 I slot print_timing: id 0 | task 141 | prompt eval time = 1158.92 ms / 164 tokens ( 7.07 ms per token, 141.51 tokens per second) 1.00.738.273 I slot print_timing: id 0 | task 141 | eval time = 392.93 ms / 2 tokens ( 392.93 ms per token, 2.54 tokens per second) 1.00.738.273 I slot print_timing: id 0 | task 141 | total time = 1551.85 ms / 166 tokens 1.00.738.274 I slot print_timing: id 0 | task 141 | graphs reused = 1 1.00.738.274 I slot print_timing: id 0 | task 141 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.738.298 I slot release: id 0 | task 141 | stop processing: n_tokens = 165, truncated = 0 1.00.738.392 I slot print_timing: id 2 | task 143 | prompt eval time = 1158.99 ms / 127 tokens ( 9.13 ms per token, 109.58 tokens per second) 1.00.738.394 I slot print_timing: id 2 | task 143 | eval time = 392.96 ms / 2 tokens ( 392.96 ms per token, 2.54 tokens per second) 1.00.738.394 I slot print_timing: id 2 | task 143 | total time = 1551.95 ms / 129 tokens 1.00.738.394 I slot print_timing: id 2 | task 143 | graphs reused = 1 1.00.738.395 I slot print_timing: id 2 | task 143 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.738.407 I slot release: id 2 | task 143 | stop processing: n_tokens = 128, truncated = 0 1.00.738.502 I slot print_timing: id 3 | task 142 | prompt eval time = 1159.07 ms / 110 tokens ( 10.54 ms per token, 94.90 tokens per second) 1.00.738.504 I slot print_timing: id 3 | task 142 | eval time = 392.96 ms / 2 tokens ( 392.96 ms per token, 2.54 tokens per second) 1.00.738.506 I slot print_timing: id 3 | task 142 | total time = 1552.04 ms / 112 tokens 1.00.738.506 I slot print_timing: id 3 | task 142 | graphs reused = 1 1.00.738.506 I slot print_timing: id 3 | task 142 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.738.516 I slot release: id 3 | task 142 | stop processing: n_tokens = 111, truncated = 0 1.00.779.493 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.210 (> 0.100 thold), f_keep = 0.158 1.00.781.908 I slot launch_slot_: id 0 | task 149 | processing task, is_child = 0 1.00.783.928 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.210 (> 0.100 thold), f_keep = 0.203 1.00.784.002 I slot launch_slot_: id 2 | task 150 | processing task, is_child = 0 1.00.784.029 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.172 (> 0.100 thold), f_keep = 0.234 1.00.784.093 I slot launch_slot_: id 3 | task 151 | processing task, is_child = 0 1.01.875.924 I slot print_timing: id 1 | task 146 | prompt eval time = 431.62 ms / 100 tokens ( 4.32 ms per token, 231.69 tokens per second) 1.01.875.930 I slot print_timing: id 1 | task 146 | eval time = 1096.43 ms / 2 tokens ( 1096.43 ms per token, 0.91 tokens per second) 1.01.875.931 I slot print_timing: id 1 | task 146 | total time = 1528.05 ms / 102 tokens 1.01.875.931 I slot print_timing: id 1 | task 146 | graphs reused = 1 1.01.875.931 I slot print_timing: id 1 | task 146 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.875.949 I slot release: id 1 | task 146 | stop processing: n_tokens = 101, truncated = 0 1.01.972.207 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.243 (> 0.100 thold), f_keep = 0.267 1.01.974.320 I slot launch_slot_: id 1 | task 154 | processing task, is_child = 0 1.02.399.302 I slot print_timing: id 0 | task 149 | prompt eval time = 1187.89 ms / 124 tokens ( 9.58 ms per token, 104.39 tokens per second) 1.02.399.307 I slot print_timing: id 0 | task 149 | eval time = 427.30 ms / 2 tokens ( 427.30 ms per token, 2.34 tokens per second) 1.02.399.308 I slot print_timing: id 0 | task 149 | total time = 1615.19 ms / 126 tokens 1.02.399.308 I slot print_timing: id 0 | task 149 | graphs reused = 1 1.02.399.308 I slot print_timing: id 0 | task 149 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.399.328 I slot release: id 0 | task 149 | stop processing: n_tokens = 125, truncated = 0 1.02.399.421 I slot print_timing: id 2 | task 150 | prompt eval time = 1187.96 ms / 124 tokens ( 9.58 ms per token, 104.38 tokens per second) 1.02.399.423 I slot print_timing: id 2 | task 150 | eval time = 427.33 ms / 2 tokens ( 427.33 ms per token, 2.34 tokens per second) 1.02.399.424 I slot print_timing: id 2 | task 150 | total time = 1615.30 ms / 126 tokens 1.02.399.424 I slot print_timing: id 2 | task 150 | graphs reused = 1 1.02.399.425 I slot print_timing: id 2 | task 150 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.399.433 I slot release: id 2 | task 150 | stop processing: n_tokens = 125, truncated = 0 1.02.399.528 I slot print_timing: id 3 | task 151 | prompt eval time = 1188.06 ms / 151 tokens ( 7.87 ms per token, 127.10 tokens per second) 1.02.399.529 I slot print_timing: id 3 | task 151 | eval time = 427.33 ms / 2 tokens ( 427.33 ms per token, 2.34 tokens per second) 1.02.399.530 I slot print_timing: id 3 | task 151 | total time = 1615.38 ms / 153 tokens 1.02.399.530 I slot print_timing: id 3 | task 151 | graphs reused = 1 1.02.399.530 I slot print_timing: id 3 | task 151 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.399.541 I slot release: id 3 | task 151 | stop processing: n_tokens = 152, truncated = 0 1.02.440.300 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.152 (> 0.100 thold), f_keep = 0.208 1.02.442.169 I slot launch_slot_: id 0 | task 157 | processing task, is_child = 0 1.02.446.045 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.222 (> 0.100 thold), f_keep = 0.208 1.02.446.113 I slot launch_slot_: id 2 | task 158 | processing task, is_child = 0 1.02.446.146 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.171 1.02.446.215 I slot launch_slot_: id 3 | task 159 | processing task, is_child = 0 1.03.700.710 I slot print_timing: id 1 | task 154 | prompt eval time = 465.96 ms / 111 tokens ( 4.20 ms per token, 238.22 tokens per second) 1.03.700.716 I slot print_timing: id 1 | task 154 | eval time = 1260.41 ms / 2 tokens ( 1260.41 ms per token, 0.79 tokens per second) 1.03.700.716 I slot print_timing: id 1 | task 154 | total time = 1726.38 ms / 113 tokens 1.03.700.717 I slot print_timing: id 1 | task 154 | graphs reused = 1 1.03.700.717 I slot print_timing: id 1 | task 154 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.700.733 I slot release: id 1 | task 154 | stop processing: n_tokens = 112, truncated = 0 1.03.798.310 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.161 (> 0.100 thold), f_keep = 0.232 1.03.799.531 I slot launch_slot_: id 1 | task 162 | processing task, is_child = 0 1.04.287.621 I slot print_timing: id 0 | task 157 | prompt eval time = 1351.88 ms / 171 tokens ( 7.91 ms per token, 126.49 tokens per second) 1.04.287.624 I slot print_timing: id 0 | task 157 | eval time = 489.51 ms / 2 tokens ( 489.51 ms per token, 2.04 tokens per second) 1.04.287.624 I slot print_timing: id 0 | task 157 | total time = 1841.39 ms / 173 tokens 1.04.287.625 I slot print_timing: id 0 | task 157 | graphs reused = 1 1.04.287.625 I slot print_timing: id 0 | task 157 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.287.645 I slot release: id 0 | task 157 | stop processing: n_tokens = 172, truncated = 0 1.04.287.743 I slot print_timing: id 2 | task 158 | prompt eval time = 1351.96 ms / 117 tokens ( 11.56 ms per token, 86.54 tokens per second) 1.04.287.745 I slot print_timing: id 2 | task 158 | eval time = 489.54 ms / 2 tokens ( 489.54 ms per token, 2.04 tokens per second) 1.04.287.746 I slot print_timing: id 2 | task 158 | total time = 1841.50 ms / 119 tokens 1.04.287.746 I slot print_timing: id 2 | task 158 | graphs reused = 1 1.04.287.746 I slot print_timing: id 2 | task 158 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.287.757 I slot release: id 2 | task 158 | stop processing: n_tokens = 118, truncated = 0 1.04.287.858 I slot print_timing: id 3 | task 159 | prompt eval time = 1352.03 ms / 167 tokens ( 8.10 ms per token, 123.52 tokens per second) 1.04.287.862 I slot print_timing: id 3 | task 159 | eval time = 489.55 ms / 2 tokens ( 489.55 ms per token, 2.04 tokens per second) 1.04.287.862 I slot print_timing: id 3 | task 159 | total time = 1841.59 ms / 169 tokens 1.04.287.862 I slot print_timing: id 3 | task 159 | graphs reused = 1 1.04.287.863 I slot print_timing: id 3 | task 159 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.287.878 I slot release: id 3 | task 159 | stop processing: n_tokens = 168, truncated = 0 1.04.330.368 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.226 (> 0.100 thold), f_keep = 0.151 1.04.332.719 I slot launch_slot_: id 0 | task 165 | processing task, is_child = 0 1.04.336.049 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.241 (> 0.100 thold), f_keep = 0.220 1.04.336.125 I slot launch_slot_: id 2 | task 166 | processing task, is_child = 0 1.04.336.155 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.236 (> 0.100 thold), f_keep = 0.155 1.04.336.530 I slot launch_slot_: id 3 | task 167 | processing task, is_child = 0 1.05.251.565 I slot print_timing: id 1 | task 162 | prompt eval time = 530.82 ms / 161 tokens ( 3.30 ms per token, 303.30 tokens per second) 1.05.251.571 I slot print_timing: id 1 | task 162 | eval time = 921.19 ms / 2 tokens ( 921.19 ms per token, 1.09 tokens per second) 1.05.251.571 I slot print_timing: id 1 | task 162 | total time = 1452.01 ms / 163 tokens 1.05.251.572 I slot print_timing: id 1 | task 162 | graphs reused = 1 1.05.251.572 I slot print_timing: id 1 | task 162 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.251.595 I slot release: id 1 | task 162 | stop processing: n_tokens = 162, truncated = 0 1.05.347.331 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.245 (> 0.100 thold), f_keep = 0.160 1.05.349.465 I slot launch_slot_: id 1 | task 170 | processing task, is_child = 0 1.05.767.124 I slot print_timing: id 0 | task 165 | prompt eval time = 1010.60 ms / 115 tokens ( 8.79 ms per token, 113.79 tokens per second) 1.05.767.130 I slot print_timing: id 0 | task 165 | eval time = 419.98 ms / 2 tokens ( 419.98 ms per token, 2.38 tokens per second) 1.05.767.130 I slot print_timing: id 0 | task 165 | total time = 1430.58 ms / 117 tokens 1.05.767.130 I slot print_timing: id 0 | task 165 | graphs reused = 1 1.05.767.131 I slot print_timing: id 0 | task 165 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.767.150 I slot release: id 0 | task 165 | stop processing: n_tokens = 116, truncated = 0 1.05.767.246 I slot print_timing: id 2 | task 166 | prompt eval time = 1010.67 ms / 108 tokens ( 9.36 ms per token, 106.86 tokens per second) 1.05.767.248 I slot print_timing: id 2 | task 166 | eval time = 420.01 ms / 2 tokens ( 420.01 ms per token, 2.38 tokens per second) 1.05.767.248 I slot print_timing: id 2 | task 166 | total time = 1430.68 ms / 110 tokens 1.05.767.248 I slot print_timing: id 2 | task 166 | graphs reused = 1 1.05.767.249 I slot print_timing: id 2 | task 166 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.767.258 I slot release: id 2 | task 166 | stop processing: n_tokens = 109, truncated = 0 1.05.767.359 I slot print_timing: id 3 | task 167 | prompt eval time = 1010.75 ms / 110 tokens ( 9.19 ms per token, 108.83 tokens per second) 1.05.767.361 I slot print_timing: id 3 | task 167 | eval time = 420.03 ms / 2 tokens ( 420.03 ms per token, 2.38 tokens per second) 1.05.767.362 I slot print_timing: id 3 | task 167 | total time = 1430.78 ms / 112 tokens 1.05.767.362 I slot print_timing: id 3 | task 167 | graphs reused = 1 1.05.767.362 I slot print_timing: id 3 | task 167 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.767.377 I slot release: id 3 | task 167 | stop processing: n_tokens = 111, truncated = 0 1.05.808.313 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.225 (> 0.100 thold), f_keep = 0.243 1.05.809.289 I slot launch_slot_: id 3 | task 173 | processing task, is_child = 0 1.05.810.498 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.218 (> 0.100 thold), f_keep = 0.224 1.05.810.822 I slot launch_slot_: id 0 | task 174 | processing task, is_child = 0 1.05.810.849 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.195 (> 0.100 thold), f_keep = 0.239 1.05.810.923 I slot launch_slot_: id 2 | task 175 | processing task, is_child = 0 1.06.818.003 I slot print_timing: id 1 | task 170 | prompt eval time = 458.84 ms / 106 tokens ( 4.33 ms per token, 231.02 tokens per second) 1.06.818.008 I slot print_timing: id 1 | task 170 | eval time = 1009.69 ms / 2 tokens ( 1009.69 ms per token, 0.99 tokens per second) 1.06.818.009 I slot print_timing: id 1 | task 170 | total time = 1468.53 ms / 108 tokens 1.06.818.009 I slot print_timing: id 1 | task 170 | graphs reused = 1 1.06.818.009 I slot print_timing: id 1 | task 170 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.818.028 I slot release: id 1 | task 170 | stop processing: n_tokens = 107, truncated = 0 1.06.913.671 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.211 (> 0.100 thold), f_keep = 0.243 1.06.914.377 I slot launch_slot_: id 1 | task 178 | processing task, is_child = 0 1.07.351.550 I slot print_timing: id 0 | task 174 | prompt eval time = 1102.54 ms / 119 tokens ( 9.27 ms per token, 107.93 tokens per second) 1.07.351.552 I slot print_timing: id 0 | task 174 | eval time = 438.08 ms / 2 tokens ( 438.08 ms per token, 2.28 tokens per second) 1.07.351.553 I slot print_timing: id 0 | task 174 | total time = 1540.62 ms / 121 tokens 1.07.351.553 I slot print_timing: id 0 | task 174 | graphs reused = 1 1.07.351.554 I slot print_timing: id 0 | task 174 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.351.571 I slot release: id 0 | task 174 | stop processing: n_tokens = 120, truncated = 0 1.07.351.671 I slot print_timing: id 2 | task 175 | prompt eval time = 1102.62 ms / 133 tokens ( 8.29 ms per token, 120.62 tokens per second) 1.07.351.673 I slot print_timing: id 2 | task 175 | eval time = 438.10 ms / 2 tokens ( 438.10 ms per token, 2.28 tokens per second) 1.07.351.674 I slot print_timing: id 2 | task 175 | total time = 1540.73 ms / 135 tokens 1.07.351.674 I slot print_timing: id 2 | task 175 | graphs reused = 1 1.07.351.674 I slot print_timing: id 2 | task 175 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.351.685 I slot release: id 2 | task 175 | stop processing: n_tokens = 134, truncated = 0 1.07.351.796 I slot print_timing: id 3 | task 173 | prompt eval time = 1102.70 ms / 120 tokens ( 9.19 ms per token, 108.82 tokens per second) 1.07.351.797 I slot print_timing: id 3 | task 173 | eval time = 438.13 ms / 2 tokens ( 438.13 ms per token, 2.28 tokens per second) 1.07.351.798 I slot print_timing: id 3 | task 173 | total time = 1540.83 ms / 122 tokens 1.07.351.798 I slot print_timing: id 3 | task 173 | graphs reused = 1 1.07.351.798 I slot print_timing: id 3 | task 173 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.351.809 I slot release: id 3 | task 173 | stop processing: n_tokens = 121, truncated = 0 1.07.394.275 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.284 (> 0.100 thold), f_keep = 0.223 1.07.396.005 I slot launch_slot_: id 3 | task 181 | processing task, is_child = 0 1.07.399.217 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.217 1.07.399.292 I slot launch_slot_: id 0 | task 182 | processing task, is_child = 0 1.07.399.320 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.215 (> 0.100 thold), f_keep = 0.194 1.07.399.388 I slot launch_slot_: id 2 | task 183 | processing task, is_child = 0 1.08.383.660 I slot print_timing: id 1 | task 178 | prompt eval time = 479.88 ms / 123 tokens ( 3.90 ms per token, 256.31 tokens per second) 1.08.383.665 I slot print_timing: id 1 | task 178 | eval time = 989.38 ms / 2 tokens ( 989.38 ms per token, 1.01 tokens per second) 1.08.383.666 I slot print_timing: id 1 | task 178 | total time = 1469.26 ms / 125 tokens 1.08.383.666 I slot print_timing: id 1 | task 178 | graphs reused = 1 1.08.383.667 I slot print_timing: id 1 | task 178 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.383.688 I slot release: id 1 | task 178 | stop processing: n_tokens = 124, truncated = 0 1.08.479.570 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.179 (> 0.100 thold), f_keep = 0.210 1.08.480.996 I slot launch_slot_: id 1 | task 186 | processing task, is_child = 0 1.08.951.943 I slot print_timing: id 0 | task 182 | prompt eval time = 1079.98 ms / 114 tokens ( 9.47 ms per token, 105.56 tokens per second) 1.08.951.949 I slot print_timing: id 0 | task 182 | eval time = 472.57 ms / 2 tokens ( 472.57 ms per token, 2.12 tokens per second) 1.08.951.949 I slot print_timing: id 0 | task 182 | total time = 1552.55 ms / 116 tokens 1.08.951.950 I slot print_timing: id 0 | task 182 | graphs reused = 1 1.08.951.965 I slot print_timing: id 0 | task 182 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.951.990 I slot release: id 0 | task 182 | stop processing: n_tokens = 115, truncated = 0 1.08.952.092 I slot print_timing: id 2 | task 183 | prompt eval time = 1080.05 ms / 121 tokens ( 8.93 ms per token, 112.03 tokens per second) 1.08.952.093 I slot print_timing: id 2 | task 183 | eval time = 472.62 ms / 2 tokens ( 472.62 ms per token, 2.12 tokens per second) 1.08.952.094 I slot print_timing: id 2 | task 183 | total time = 1552.67 ms / 123 tokens 1.08.952.094 I slot print_timing: id 2 | task 183 | graphs reused = 1 1.08.952.095 I slot print_timing: id 2 | task 183 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.952.105 I slot release: id 2 | task 183 | stop processing: n_tokens = 122, truncated = 0 1.08.952.199 I slot print_timing: id 3 | task 181 | prompt eval time = 1080.12 ms / 95 tokens ( 11.37 ms per token, 87.95 tokens per second) 1.08.952.204 I slot print_timing: id 3 | task 181 | eval time = 472.63 ms / 2 tokens ( 472.63 ms per token, 2.12 tokens per second) 1.08.952.204 I slot print_timing: id 3 | task 181 | total time = 1552.75 ms / 97 tokens 1.08.952.204 I slot print_timing: id 3 | task 181 | graphs reused = 1 1.08.952.205 I slot print_timing: id 3 | task 181 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.952.213 I slot release: id 3 | task 181 | stop processing: n_tokens = 96, truncated = 0 1.08.993.740 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.169 (> 0.100 thold), f_keep = 0.226 1.08.994.991 I slot launch_slot_: id 0 | task 189 | processing task, is_child = 0 1.08.997.542 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.213 1.08.997.617 I slot launch_slot_: id 2 | task 190 | processing task, is_child = 0 1.08.997.643 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.271 1.08.997.719 I slot launch_slot_: id 3 | task 191 | processing task, is_child = 0 1.10.085.576 I slot print_timing: id 1 | task 186 | prompt eval time = 512.73 ms / 145 tokens ( 3.54 ms per token, 282.80 tokens per second) 1.10.085.578 I slot print_timing: id 1 | task 186 | eval time = 1091.83 ms / 2 tokens ( 1091.83 ms per token, 0.92 tokens per second) 1.10.085.580 I slot print_timing: id 1 | task 186 | total time = 1604.57 ms / 147 tokens 1.10.085.580 I slot print_timing: id 1 | task 186 | graphs reused = 1 1.10.085.580 I slot print_timing: id 1 | task 186 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.085.605 I slot release: id 1 | task 186 | stop processing: n_tokens = 146, truncated = 0 1.10.184.870 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.255 (> 0.100 thold), f_keep = 0.178 1.10.187.199 I slot launch_slot_: id 1 | task 194 | processing task, is_child = 0 1.10.599.620 I slot print_timing: id 0 | task 189 | prompt eval time = 1186.94 ms / 154 tokens ( 7.71 ms per token, 129.75 tokens per second) 1.10.599.625 I slot print_timing: id 0 | task 189 | eval time = 414.94 ms / 2 tokens ( 414.94 ms per token, 2.41 tokens per second) 1.10.599.625 I slot print_timing: id 0 | task 189 | total time = 1601.89 ms / 156 tokens 1.10.599.626 I slot print_timing: id 0 | task 189 | graphs reused = 1 1.10.599.626 I slot print_timing: id 0 | task 189 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.599.648 I slot release: id 0 | task 189 | stop processing: n_tokens = 155, truncated = 0 1.10.599.745 I slot print_timing: id 2 | task 190 | prompt eval time = 1187.02 ms / 146 tokens ( 8.13 ms per token, 123.00 tokens per second) 1.10.599.751 I slot print_timing: id 2 | task 190 | eval time = 414.98 ms / 2 tokens ( 414.98 ms per token, 2.41 tokens per second) 1.10.599.751 I slot print_timing: id 2 | task 190 | total time = 1601.99 ms / 148 tokens 1.10.599.752 I slot print_timing: id 2 | task 190 | graphs reused = 1 1.10.599.752 I slot print_timing: id 2 | task 190 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.599.761 I slot release: id 2 | task 190 | stop processing: n_tokens = 147, truncated = 0 1.10.599.858 I slot print_timing: id 3 | task 191 | prompt eval time = 1187.10 ms / 130 tokens ( 9.13 ms per token, 109.51 tokens per second) 1.10.599.859 I slot print_timing: id 3 | task 191 | eval time = 414.99 ms / 2 tokens ( 414.99 ms per token, 2.41 tokens per second) 1.10.599.860 I slot print_timing: id 3 | task 191 | total time = 1602.09 ms / 132 tokens 1.10.599.860 I slot print_timing: id 3 | task 191 | graphs reused = 1 1.10.599.860 I slot print_timing: id 3 | task 191 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.599.871 I slot release: id 3 | task 191 | stop processing: n_tokens = 131, truncated = 0 1.10.640.957 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.168 1.10.643.227 I slot launch_slot_: id 0 | task 197 | processing task, is_child = 0 1.10.646.687 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.202 (> 0.100 thold), f_keep = 0.177 1.10.646.757 I slot launch_slot_: id 2 | task 198 | processing task, is_child = 0 1.10.646.786 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.260 (> 0.100 thold), f_keep = 0.198 1.10.646.855 I slot launch_slot_: id 3 | task 199 | processing task, is_child = 0 1.11.695.292 I slot print_timing: id 1 | task 194 | prompt eval time = 453.75 ms / 102 tokens ( 4.45 ms per token, 224.79 tokens per second) 1.11.695.298 I slot print_timing: id 1 | task 194 | eval time = 1054.33 ms / 2 tokens ( 1054.33 ms per token, 0.95 tokens per second) 1.11.695.298 I slot print_timing: id 1 | task 194 | total time = 1508.08 ms / 104 tokens 1.11.695.299 I slot print_timing: id 1 | task 194 | graphs reused = 1 1.11.695.299 I slot print_timing: id 1 | task 194 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.695.317 I slot release: id 1 | task 194 | stop processing: n_tokens = 103, truncated = 0 1.11.791.554 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.265 (> 0.100 thold), f_keep = 0.262 1.11.792.216 I slot launch_slot_: id 1 | task 202 | processing task, is_child = 0 1.12.202.845 I slot print_timing: id 2 | task 198 | prompt eval time = 1144.57 ms / 129 tokens ( 8.87 ms per token, 112.71 tokens per second) 1.12.202.849 I slot print_timing: id 2 | task 198 | eval time = 411.39 ms / 2 tokens ( 411.39 ms per token, 2.43 tokens per second) 1.12.202.850 I slot print_timing: id 2 | task 198 | total time = 1555.95 ms / 131 tokens 1.12.202.850 I slot print_timing: id 2 | task 198 | graphs reused = 1 1.12.202.851 I slot print_timing: id 2 | task 198 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.202.876 I slot release: id 2 | task 198 | stop processing: n_tokens = 130, truncated = 0 1.12.202.984 I slot print_timing: id 3 | task 199 | prompt eval time = 1144.64 ms / 100 tokens ( 11.45 ms per token, 87.36 tokens per second) 1.12.202.988 I slot print_timing: id 3 | task 199 | eval time = 411.43 ms / 2 tokens ( 411.43 ms per token, 2.43 tokens per second) 1.12.202.989 I slot print_timing: id 3 | task 199 | total time = 1556.08 ms / 102 tokens 1.12.202.989 I slot print_timing: id 3 | task 199 | graphs reused = 1 1.12.202.989 I slot print_timing: id 3 | task 199 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.202.998 I slot release: id 3 | task 199 | stop processing: n_tokens = 101, truncated = 0 1.12.269.513 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.179 (> 0.100 thold), f_keep = 0.200 1.12.271.058 I slot launch_slot_: id 2 | task 205 | processing task, is_child = 0 1.12.272.177 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.257 1.12.272.549 I slot launch_slot_: id 3 | task 206 | processing task, is_child = 0 1.13.029.416 I slot print_timing: id 0 | task 197 | prompt eval time = 1144.49 ms / 138 tokens ( 8.29 ms per token, 120.58 tokens per second) 1.13.029.418 I slot print_timing: id 0 | task 197 | eval time = 1238.05 ms / 4 tokens ( 412.68 ms per token, 2.42 tokens per second) 1.13.029.419 I slot print_timing: id 0 | task 197 | total time = 2382.55 ms / 142 tokens 1.13.029.419 I slot print_timing: id 0 | task 197 | graphs reused = 1 1.13.029.419 I slot print_timing: id 0 | task 197 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.029.442 I slot release: id 0 | task 197 | stop processing: n_tokens = 141, truncated = 0 1.13.029.538 I slot print_timing: id 1 | task 202 | prompt eval time = 477.29 ms / 102 tokens ( 4.68 ms per token, 213.71 tokens per second) 1.13.029.545 I slot print_timing: id 1 | task 202 | eval time = 760.03 ms / 2 tokens ( 760.03 ms per token, 1.32 tokens per second) 1.13.029.546 I slot print_timing: id 1 | task 202 | total time = 1237.32 ms / 104 tokens 1.13.029.546 I slot print_timing: id 1 | task 202 | graphs reused = 1 1.13.029.547 I slot print_timing: id 1 | task 202 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.029.557 I slot release: id 1 | task 202 | stop processing: n_tokens = 103, truncated = 0 1.13.089.300 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.215 (> 0.100 thold), f_keep = 0.184 1.13.091.096 I slot launch_slot_: id 0 | task 210 | processing task, is_child = 0 1.13.091.648 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.226 (> 0.100 thold), f_keep = 0.252 1.13.091.721 I slot launch_slot_: id 1 | task 209 | processing task, is_child = 0 1.13.662.817 I slot print_timing: id 2 | task 205 | prompt eval time = 816.64 ms / 145 tokens ( 5.63 ms per token, 177.56 tokens per second) 1.13.662.823 I slot print_timing: id 2 | task 205 | eval time = 573.61 ms / 2 tokens ( 573.61 ms per token, 1.74 tokens per second) 1.13.662.823 I slot print_timing: id 2 | task 205 | total time = 1390.26 ms / 147 tokens 1.13.662.824 I slot print_timing: id 2 | task 205 | graphs reused = 1 1.13.662.824 I slot print_timing: id 2 | task 205 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.662.842 I slot release: id 2 | task 205 | stop processing: n_tokens = 146, truncated = 0 1.13.662.931 I slot print_timing: id 3 | task 206 | prompt eval time = 816.72 ms / 103 tokens ( 7.93 ms per token, 126.11 tokens per second) 1.13.662.933 I slot print_timing: id 3 | task 206 | eval time = 573.63 ms / 2 tokens ( 573.63 ms per token, 1.74 tokens per second) 1.13.662.933 I slot print_timing: id 3 | task 206 | total time = 1390.35 ms / 105 tokens 1.13.662.933 I slot print_timing: id 3 | task 206 | graphs reused = 1 1.13.662.934 I slot print_timing: id 3 | task 206 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.662.943 I slot release: id 3 | task 206 | stop processing: n_tokens = 104, truncated = 0 1.13.721.218 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.260 1.13.722.453 I slot launch_slot_: id 3 | task 213 | processing task, is_child = 0 1.13.724.035 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.167 (> 0.100 thold), f_keep = 0.178 1.13.724.112 I slot launch_slot_: id 2 | task 214 | processing task, is_child = 0 1.14.511.665 I slot print_timing: id 0 | task 210 | prompt eval time = 629.39 ms / 121 tokens ( 5.20 ms per token, 192.25 tokens per second) 1.14.511.669 I slot print_timing: id 0 | task 210 | eval time = 790.54 ms / 2 tokens ( 790.54 ms per token, 1.26 tokens per second) 1.14.511.669 I slot print_timing: id 0 | task 210 | total time = 1419.93 ms / 123 tokens 1.14.511.670 I slot print_timing: id 0 | task 210 | graphs reused = 1 1.14.511.670 I slot print_timing: id 0 | task 210 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.511.692 I slot release: id 0 | task 210 | stop processing: n_tokens = 122, truncated = 0 1.14.511.796 I slot print_timing: id 1 | task 209 | prompt eval time = 629.47 ms / 115 tokens ( 5.47 ms per token, 182.69 tokens per second) 1.14.511.800 I slot print_timing: id 1 | task 209 | eval time = 790.58 ms / 2 tokens ( 790.58 ms per token, 1.26 tokens per second) 1.14.511.800 I slot print_timing: id 1 | task 209 | total time = 1420.05 ms / 117 tokens 1.14.511.800 I slot print_timing: id 1 | task 209 | graphs reused = 1 1.14.511.801 I slot print_timing: id 1 | task 209 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.511.809 I slot release: id 1 | task 209 | stop processing: n_tokens = 116, truncated = 0 1.14.571.670 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.225 (> 0.100 thold), f_keep = 0.221 1.14.572.958 I slot launch_slot_: id 0 | task 217 | processing task, is_child = 0 1.14.574.441 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.173 (> 0.100 thold), f_keep = 0.224 1.14.574.511 I slot launch_slot_: id 1 | task 218 | processing task, is_child = 0 1.15.280.895 I slot print_timing: id 2 | task 214 | prompt eval time = 847.45 ms / 156 tokens ( 5.43 ms per token, 184.08 tokens per second) 1.15.280.900 I slot print_timing: id 2 | task 214 | eval time = 709.32 ms / 2 tokens ( 709.32 ms per token, 1.41 tokens per second) 1.15.280.901 I slot print_timing: id 2 | task 214 | total time = 1556.77 ms / 158 tokens 1.15.280.901 I slot print_timing: id 2 | task 214 | graphs reused = 1 1.15.280.901 I slot print_timing: id 2 | task 214 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.280.923 I slot release: id 2 | task 214 | stop processing: n_tokens = 157, truncated = 0 1.15.281.017 I slot print_timing: id 3 | task 213 | prompt eval time = 847.52 ms / 107 tokens ( 7.92 ms per token, 126.25 tokens per second) 1.15.281.022 I slot print_timing: id 3 | task 213 | eval time = 709.35 ms / 2 tokens ( 709.35 ms per token, 1.41 tokens per second) 1.15.281.022 I slot print_timing: id 3 | task 213 | total time = 1556.87 ms / 109 tokens 1.15.281.022 I slot print_timing: id 3 | task 213 | graphs reused = 1 1.15.281.023 I slot print_timing: id 3 | task 213 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.281.031 I slot release: id 3 | task 213 | stop processing: n_tokens = 108, truncated = 0 1.15.340.353 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.263 (> 0.100 thold), f_keep = 0.166 1.15.342.495 I slot launch_slot_: id 2 | task 221 | processing task, is_child = 0 1.15.343.552 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.158 (> 0.100 thold), f_keep = 0.241 1.15.343.622 I slot launch_slot_: id 3 | task 222 | processing task, is_child = 0 1.16.145.035 I slot print_timing: id 0 | task 217 | prompt eval time = 765.73 ms / 120 tokens ( 6.38 ms per token, 156.71 tokens per second) 1.16.145.037 I slot print_timing: id 0 | task 217 | eval time = 804.78 ms / 2 tokens ( 804.78 ms per token, 1.24 tokens per second) 1.16.145.038 I slot print_timing: id 0 | task 217 | total time = 1570.51 ms / 122 tokens 1.16.145.038 I slot print_timing: id 0 | task 217 | graphs reused = 1 1.16.145.039 I slot print_timing: id 0 | task 217 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.145.059 I slot release: id 0 | task 217 | stop processing: n_tokens = 121, truncated = 0 1.16.145.158 I slot print_timing: id 1 | task 218 | prompt eval time = 765.80 ms / 150 tokens ( 5.11 ms per token, 195.87 tokens per second) 1.16.145.160 I slot print_timing: id 1 | task 218 | eval time = 804.81 ms / 2 tokens ( 804.81 ms per token, 1.24 tokens per second) 1.16.145.161 I slot print_timing: id 1 | task 218 | total time = 1570.62 ms / 152 tokens 1.16.145.162 I slot print_timing: id 1 | task 218 | graphs reused = 1 1.16.145.162 I slot print_timing: id 1 | task 218 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.145.173 I slot release: id 1 | task 218 | stop processing: n_tokens = 151, truncated = 0 1.16.204.999 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.208 (> 0.100 thold), f_keep = 0.215 1.16.206.398 I slot launch_slot_: id 0 | task 225 | processing task, is_child = 0 1.16.208.395 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.186 (> 0.100 thold), f_keep = 0.179 1.16.208.477 I slot launch_slot_: id 1 | task 226 | processing task, is_child = 0 1.16.889.809 I slot print_timing: id 2 | task 221 | prompt eval time = 861.27 ms / 99 tokens ( 8.70 ms per token, 114.95 tokens per second) 1.16.889.812 I slot print_timing: id 2 | task 221 | eval time = 684.91 ms / 2 tokens ( 684.91 ms per token, 1.46 tokens per second) 1.16.889.812 I slot print_timing: id 2 | task 221 | total time = 1546.18 ms / 101 tokens 1.16.889.813 I slot print_timing: id 2 | task 221 | graphs reused = 1 1.16.889.813 I slot print_timing: id 2 | task 221 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.889.828 I slot release: id 2 | task 221 | stop processing: n_tokens = 100, truncated = 0 1.16.889.918 I slot print_timing: id 3 | task 222 | prompt eval time = 861.34 ms / 165 tokens ( 5.22 ms per token, 191.56 tokens per second) 1.16.889.919 I slot print_timing: id 3 | task 222 | eval time = 684.93 ms / 2 tokens ( 684.93 ms per token, 1.46 tokens per second) 1.16.889.920 I slot print_timing: id 3 | task 222 | total time = 1546.26 ms / 167 tokens 1.16.889.920 I slot print_timing: id 3 | task 222 | graphs reused = 1 1.16.889.920 I slot print_timing: id 3 | task 222 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.889.932 I slot release: id 3 | task 222 | stop processing: n_tokens = 166, truncated = 0 1.16.948.902 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.243 (> 0.100 thold), f_keep = 0.260 1.16.950.504 I slot launch_slot_: id 2 | task 229 | processing task, is_child = 0 1.16.953.027 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.210 (> 0.100 thold), f_keep = 0.157 1.16.953.124 I slot launch_slot_: id 3 | task 230 | processing task, is_child = 0 1.17.584.879 I slot print_timing: id 0 | task 225 | prompt eval time = 740.32 ms / 125 tokens ( 5.92 ms per token, 168.85 tokens per second) 1.17.584.884 I slot print_timing: id 0 | task 225 | eval time = 636.07 ms / 2 tokens ( 636.07 ms per token, 1.57 tokens per second) 1.17.584.884 I slot print_timing: id 0 | task 225 | total time = 1376.39 ms / 127 tokens 1.17.584.885 I slot print_timing: id 0 | task 225 | graphs reused = 1 1.17.584.885 I slot print_timing: id 0 | task 225 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.584.906 I slot release: id 0 | task 225 | stop processing: n_tokens = 126, truncated = 0 1.17.584.998 I slot print_timing: id 1 | task 226 | prompt eval time = 740.39 ms / 145 tokens ( 5.11 ms per token, 195.84 tokens per second) 1.17.585.003 I slot print_timing: id 1 | task 226 | eval time = 636.10 ms / 2 tokens ( 636.10 ms per token, 1.57 tokens per second) 1.17.585.003 I slot print_timing: id 1 | task 226 | total time = 1376.49 ms / 147 tokens 1.17.585.004 I slot print_timing: id 1 | task 226 | graphs reused = 1 1.17.585.004 I slot print_timing: id 1 | task 226 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.585.017 I slot release: id 1 | task 226 | stop processing: n_tokens = 146, truncated = 0 1.17.643.274 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.205 (> 0.100 thold), f_keep = 0.206 1.17.644.692 I slot launch_slot_: id 0 | task 233 | processing task, is_child = 0 1.17.646.844 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.174 (> 0.100 thold), f_keep = 0.178 1.17.646.924 I slot launch_slot_: id 1 | task 234 | processing task, is_child = 0 1.18.331.524 I slot print_timing: id 2 | task 229 | prompt eval time = 690.03 ms / 107 tokens ( 6.45 ms per token, 155.06 tokens per second) 1.18.331.526 I slot print_timing: id 2 | task 229 | eval time = 688.35 ms / 2 tokens ( 688.35 ms per token, 1.45 tokens per second) 1.18.331.527 I slot print_timing: id 2 | task 229 | total time = 1378.39 ms / 109 tokens 1.18.331.527 I slot print_timing: id 2 | task 229 | graphs reused = 1 1.18.331.527 I slot print_timing: id 2 | task 229 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.331.550 I slot release: id 2 | task 229 | stop processing: n_tokens = 108, truncated = 0 1.18.331.646 I slot print_timing: id 3 | task 230 | prompt eval time = 690.10 ms / 124 tokens ( 5.57 ms per token, 179.68 tokens per second) 1.18.331.647 I slot print_timing: id 3 | task 230 | eval time = 688.38 ms / 2 tokens ( 688.38 ms per token, 1.45 tokens per second) 1.18.331.648 I slot print_timing: id 3 | task 230 | total time = 1378.48 ms / 126 tokens 1.18.331.648 I slot print_timing: id 3 | task 230 | graphs reused = 1 1.18.331.648 I slot print_timing: id 3 | task 230 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.331.663 I slot release: id 3 | task 230 | stop processing: n_tokens = 125, truncated = 0 1.18.390.244 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.237 (> 0.100 thold), f_keep = 0.250 1.18.391.804 I slot launch_slot_: id 2 | task 237 | processing task, is_child = 0 1.18.392.966 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.183 (> 0.100 thold), f_keep = 0.208 1.18.393.041 I slot launch_slot_: id 3 | task 238 | processing task, is_child = 0 1.19.076.854 I slot print_timing: id 0 | task 233 | prompt eval time = 743.21 ms / 127 tokens ( 5.85 ms per token, 170.88 tokens per second) 1.19.076.859 I slot print_timing: id 0 | task 233 | eval time = 686.71 ms / 2 tokens ( 686.71 ms per token, 1.46 tokens per second) 1.19.076.860 I slot print_timing: id 0 | task 233 | total time = 1429.92 ms / 129 tokens 1.19.076.860 I slot print_timing: id 0 | task 233 | graphs reused = 1 1.19.076.860 I slot print_timing: id 0 | task 233 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.076.878 I slot release: id 0 | task 233 | stop processing: n_tokens = 128, truncated = 0 1.19.076.975 I slot print_timing: id 1 | task 234 | prompt eval time = 743.28 ms / 149 tokens ( 4.99 ms per token, 200.46 tokens per second) 1.19.076.979 I slot print_timing: id 1 | task 234 | eval time = 686.73 ms / 2 tokens ( 686.73 ms per token, 1.46 tokens per second) 1.19.076.979 I slot print_timing: id 1 | task 234 | total time = 1430.02 ms / 151 tokens 1.19.076.980 I slot print_timing: id 1 | task 234 | graphs reused = 1 1.19.076.980 I slot print_timing: id 1 | task 234 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.076.989 I slot release: id 1 | task 234 | stop processing: n_tokens = 150, truncated = 0 1.19.136.153 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.248 (> 0.100 thold), f_keep = 0.203 1.19.138.451 I slot launch_slot_: id 0 | task 241 | processing task, is_child = 0 1.19.139.971 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.174 (> 0.100 thold), f_keep = 0.173 1.19.140.055 I slot launch_slot_: id 1 | task 242 | processing task, is_child = 0 1.19.902.799 I slot print_timing: id 2 | task 237 | prompt eval time = 743.00 ms / 114 tokens ( 6.52 ms per token, 153.43 tokens per second) 1.19.902.805 I slot print_timing: id 2 | task 237 | eval time = 766.75 ms / 2 tokens ( 766.75 ms per token, 1.30 tokens per second) 1.19.902.805 I slot print_timing: id 2 | task 237 | total time = 1509.75 ms / 116 tokens 1.19.902.806 I slot print_timing: id 2 | task 237 | graphs reused = 1 1.19.902.806 I slot print_timing: id 2 | task 237 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.902.826 I slot release: id 2 | task 237 | stop processing: n_tokens = 115, truncated = 0 1.19.902.918 I slot print_timing: id 3 | task 238 | prompt eval time = 743.08 ms / 142 tokens ( 5.23 ms per token, 191.10 tokens per second) 1.19.902.919 I slot print_timing: id 3 | task 238 | eval time = 766.77 ms / 2 tokens ( 766.77 ms per token, 1.30 tokens per second) 1.19.902.920 I slot print_timing: id 3 | task 238 | total time = 1509.85 ms / 144 tokens 1.19.902.920 I slot print_timing: id 3 | task 238 | graphs reused = 1 1.19.902.920 I slot print_timing: id 3 | task 238 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.902.931 I slot release: id 3 | task 238 | stop processing: n_tokens = 143, truncated = 0 1.19.960.642 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.174 (> 0.100 thold), f_keep = 0.226 1.19.962.041 I slot launch_slot_: id 2 | task 245 | processing task, is_child = 0 1.19.964.136 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.187 (> 0.100 thold), f_keep = 0.182 1.19.964.212 I slot launch_slot_: id 3 | task 246 | processing task, is_child = 0 1.20.631.937 I slot print_timing: id 0 | task 241 | prompt eval time = 820.48 ms / 105 tokens ( 7.81 ms per token, 127.97 tokens per second) 1.20.631.940 I slot print_timing: id 0 | task 241 | eval time = 671.39 ms / 2 tokens ( 671.39 ms per token, 1.49 tokens per second) 1.20.631.940 I slot print_timing: id 0 | task 241 | total time = 1491.87 ms / 107 tokens 1.20.631.941 I slot print_timing: id 0 | task 241 | graphs reused = 1 1.20.631.941 I slot print_timing: id 0 | task 241 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.631.961 I slot release: id 0 | task 241 | stop processing: n_tokens = 106, truncated = 0 1.20.632.055 I slot print_timing: id 1 | task 242 | prompt eval time = 820.55 ms / 149 tokens ( 5.51 ms per token, 181.59 tokens per second) 1.20.632.057 I slot print_timing: id 1 | task 242 | eval time = 671.42 ms / 2 tokens ( 671.42 ms per token, 1.49 tokens per second) 1.20.632.057 I slot print_timing: id 1 | task 242 | total time = 1491.97 ms / 151 tokens 1.20.632.058 I slot print_timing: id 1 | task 242 | graphs reused = 1 1.20.632.058 I slot print_timing: id 1 | task 242 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.632.069 I slot release: id 1 | task 242 | stop processing: n_tokens = 150, truncated = 0 1.20.691.000 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.245 1.20.692.289 I slot launch_slot_: id 0 | task 249 | processing task, is_child = 0 1.20.694.390 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.181 (> 0.100 thold), f_keep = 0.173 1.20.694.471 I slot launch_slot_: id 1 | task 250 | processing task, is_child = 0 1.21.311.578 I slot print_timing: id 2 | task 245 | prompt eval time = 726.68 ms / 149 tokens ( 4.88 ms per token, 205.04 tokens per second) 1.21.311.582 I slot print_timing: id 2 | task 245 | eval time = 620.67 ms / 2 tokens ( 620.67 ms per token, 1.61 tokens per second) 1.21.311.583 I slot print_timing: id 2 | task 245 | total time = 1347.35 ms / 151 tokens 1.21.311.583 I slot print_timing: id 2 | task 245 | graphs reused = 1 1.21.311.584 I slot print_timing: id 2 | task 245 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.311.605 I slot release: id 2 | task 245 | stop processing: n_tokens = 150, truncated = 0 1.21.311.704 I slot print_timing: id 3 | task 246 | prompt eval time = 726.74 ms / 139 tokens ( 5.23 ms per token, 191.26 tokens per second) 1.21.311.708 I slot print_timing: id 3 | task 246 | eval time = 620.71 ms / 2 tokens ( 620.71 ms per token, 1.61 tokens per second) 1.21.311.709 I slot print_timing: id 3 | task 246 | total time = 1347.45 ms / 141 tokens 1.21.311.709 I slot print_timing: id 3 | task 246 | graphs reused = 1 1.21.311.709 I slot print_timing: id 3 | task 246 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.311.719 I slot release: id 3 | task 246 | stop processing: n_tokens = 140, truncated = 0 1.21.371.294 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.245 (> 0.100 thold), f_keep = 0.173 1.21.373.595 I slot launch_slot_: id 2 | task 253 | processing task, is_child = 0 1.21.375.618 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.265 (> 0.100 thold), f_keep = 0.186 1.21.375.697 I slot launch_slot_: id 3 | task 254 | processing task, is_child = 0 1.21.907.103 I slot print_timing: id 0 | task 249 | prompt eval time = 676.72 ms / 143 tokens ( 4.73 ms per token, 211.31 tokens per second) 1.21.907.108 I slot print_timing: id 0 | task 249 | eval time = 535.90 ms / 2 tokens ( 535.90 ms per token, 1.87 tokens per second) 1.21.907.109 I slot print_timing: id 0 | task 249 | total time = 1212.62 ms / 145 tokens 1.21.907.109 I slot print_timing: id 0 | task 249 | graphs reused = 1 1.21.907.109 I slot print_timing: id 0 | task 249 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.907.128 I slot release: id 0 | task 249 | stop processing: n_tokens = 144, truncated = 0 1.21.907.220 I slot print_timing: id 1 | task 250 | prompt eval time = 676.79 ms / 144 tokens ( 4.70 ms per token, 212.77 tokens per second) 1.21.907.225 I slot print_timing: id 1 | task 250 | eval time = 535.93 ms / 2 tokens ( 535.93 ms per token, 1.87 tokens per second) 1.21.907.226 I slot print_timing: id 1 | task 250 | total time = 1212.71 ms / 146 tokens 1.21.907.226 I slot print_timing: id 1 | task 250 | graphs reused = 1 1.21.907.227 I slot print_timing: id 1 | task 250 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.907.237 I slot release: id 1 | task 250 | stop processing: n_tokens = 145, truncated = 0 1.21.964.753 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.280 (> 0.100 thold), f_keep = 0.181 1.21.966.833 I slot launch_slot_: id 0 | task 257 | processing task, is_child = 0 1.21.968.521 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.146 (> 0.100 thold), f_keep = 0.179 1.21.968.618 I slot launch_slot_: id 1 | task 258 | processing task, is_child = 0 1.22.754.049 I slot print_timing: id 2 | task 253 | prompt eval time = 588.93 ms / 106 tokens ( 5.56 ms per token, 179.99 tokens per second) 1.22.754.051 I slot print_timing: id 2 | task 253 | eval time = 789.40 ms / 2 tokens ( 789.40 ms per token, 1.27 tokens per second) 1.22.754.052 I slot print_timing: id 2 | task 253 | total time = 1378.34 ms / 108 tokens 1.22.754.052 I slot print_timing: id 2 | task 253 | graphs reused = 1 1.22.754.053 I slot print_timing: id 2 | task 253 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.754.072 I slot release: id 2 | task 253 | stop processing: n_tokens = 107, truncated = 0 1.22.754.164 I slot print_timing: id 3 | task 254 | prompt eval time = 589.01 ms / 98 tokens ( 6.01 ms per token, 166.38 tokens per second) 1.22.754.168 I slot print_timing: id 3 | task 254 | eval time = 789.42 ms / 2 tokens ( 789.42 ms per token, 1.27 tokens per second) 1.22.754.169 I slot print_timing: id 3 | task 254 | total time = 1378.43 ms / 100 tokens 1.22.754.169 I slot print_timing: id 3 | task 254 | graphs reused = 1 1.22.754.169 I slot print_timing: id 3 | task 254 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.754.177 I slot release: id 3 | task 254 | stop processing: n_tokens = 99, truncated = 0 1.22.813.876 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.243 1.22.815.109 I slot launch_slot_: id 2 | task 261 | processing task, is_child = 0 1.22.815.725 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.255 (> 0.100 thold), f_keep = 0.263 1.22.815.791 I slot launch_slot_: id 3 | task 262 | processing task, is_child = 0 1.23.394.305 I slot print_timing: id 0 | task 257 | prompt eval time = 845.14 ms / 93 tokens ( 9.09 ms per token, 110.04 tokens per second) 1.23.394.307 I slot print_timing: id 0 | task 257 | eval time = 580.53 ms / 2 tokens ( 580.53 ms per token, 1.72 tokens per second) 1.23.394.308 I slot print_timing: id 0 | task 257 | total time = 1425.67 ms / 95 tokens 1.23.394.308 I slot print_timing: id 0 | task 257 | graphs reused = 1 1.23.394.308 I slot print_timing: id 0 | task 257 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.394.325 I slot release: id 0 | task 257 | stop processing: n_tokens = 94, truncated = 0 1.23.394.421 I slot print_timing: id 1 | task 258 | prompt eval time = 845.23 ms / 178 tokens ( 4.75 ms per token, 210.59 tokens per second) 1.23.394.423 I slot print_timing: id 1 | task 258 | eval time = 580.55 ms / 2 tokens ( 580.55 ms per token, 1.72 tokens per second) 1.23.394.423 I slot print_timing: id 1 | task 258 | total time = 1425.77 ms / 180 tokens 1.23.394.423 I slot print_timing: id 1 | task 258 | graphs reused = 1 1.23.394.424 I slot print_timing: id 1 | task 258 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.394.434 I slot release: id 1 | task 258 | stop processing: n_tokens = 179, truncated = 0 1.23.452.516 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.220 (> 0.100 thold), f_keep = 0.277 1.23.453.573 I slot launch_slot_: id 0 | task 265 | processing task, is_child = 0 1.23.456.100 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.176 (> 0.100 thold), f_keep = 0.145 1.23.456.174 I slot launch_slot_: id 1 | task 266 | processing task, is_child = 0 1.24.166.055 I slot print_timing: id 2 | task 261 | prompt eval time = 636.62 ms / 114 tokens ( 5.58 ms per token, 179.07 tokens per second) 1.24.166.060 I slot print_timing: id 2 | task 261 | eval time = 713.63 ms / 2 tokens ( 713.63 ms per token, 1.40 tokens per second) 1.24.166.061 I slot print_timing: id 2 | task 261 | total time = 1350.26 ms / 116 tokens 1.24.166.062 I slot print_timing: id 2 | task 261 | graphs reused = 1 1.24.166.062 I slot print_timing: id 2 | task 261 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.166.084 I slot release: id 2 | task 261 | stop processing: n_tokens = 115, truncated = 0 1.24.166.180 I slot print_timing: id 3 | task 262 | prompt eval time = 636.69 ms / 102 tokens ( 6.24 ms per token, 160.20 tokens per second) 1.24.166.182 I slot print_timing: id 3 | task 262 | eval time = 713.67 ms / 2 tokens ( 713.67 ms per token, 1.40 tokens per second) 1.24.166.182 I slot print_timing: id 3 | task 262 | total time = 1350.36 ms / 104 tokens 1.24.166.182 I slot print_timing: id 3 | task 262 | graphs reused = 1 1.24.166.183 I slot print_timing: id 3 | task 262 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.166.193 I slot release: id 3 | task 262 | stop processing: n_tokens = 103, truncated = 0 1.24.225.599 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.226 (> 0.100 thold), f_keep = 0.226 1.24.227.432 I slot launch_slot_: id 2 | task 269 | processing task, is_child = 0 1.24.228.918 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.214 (> 0.100 thold), f_keep = 0.262 1.24.228.993 I slot launch_slot_: id 3 | task 270 | processing task, is_child = 0 1.24.834.749 I slot print_timing: id 0 | task 265 | prompt eval time = 769.31 ms / 118 tokens ( 6.52 ms per token, 153.38 tokens per second) 1.24.834.756 I slot print_timing: id 0 | task 265 | eval time = 609.25 ms / 2 tokens ( 609.25 ms per token, 1.64 tokens per second) 1.24.834.756 I slot print_timing: id 0 | task 265 | total time = 1378.57 ms / 120 tokens 1.24.834.757 I slot print_timing: id 0 | task 265 | graphs reused = 1 1.24.834.757 I slot print_timing: id 0 | task 265 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.834.776 I slot release: id 0 | task 265 | stop processing: n_tokens = 119, truncated = 0 1.24.834.859 I slot print_timing: id 1 | task 266 | prompt eval time = 769.39 ms / 148 tokens ( 5.20 ms per token, 192.36 tokens per second) 1.24.834.863 I slot print_timing: id 1 | task 266 | eval time = 609.27 ms / 2 tokens ( 609.27 ms per token, 1.64 tokens per second) 1.24.834.864 I slot print_timing: id 1 | task 266 | total time = 1378.66 ms / 150 tokens 1.24.834.864 I slot print_timing: id 1 | task 266 | graphs reused = 1 1.24.834.864 I slot print_timing: id 1 | task 266 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.834.874 I slot release: id 1 | task 266 | stop processing: n_tokens = 149, truncated = 0 1.24.893.932 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.218 1.24.896.058 I slot launch_slot_: id 0 | task 274 | processing task, is_child = 0 1.24.897.614 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.174 1.24.897.690 I slot launch_slot_: id 1 | task 273 | processing task, is_child = 0 1.25.507.443 I slot print_timing: id 2 | task 269 | prompt eval time = 664.83 ms / 115 tokens ( 5.78 ms per token, 172.98 tokens per second) 1.25.507.449 I slot print_timing: id 2 | task 269 | eval time = 613.61 ms / 2 tokens ( 613.61 ms per token, 1.63 tokens per second) 1.25.507.449 I slot print_timing: id 2 | task 269 | total time = 1278.44 ms / 117 tokens 1.25.507.449 I slot print_timing: id 2 | task 269 | graphs reused = 1 1.25.507.450 I slot print_timing: id 2 | task 269 | graph reallocs = 0 / 0 (same size) / (changed size) 1.25.507.468 I slot release: id 2 | task 269 | stop processing: n_tokens = 116, truncated = 0 1.25.507.559 I slot print_timing: id 3 | task 270 | prompt eval time = 664.90 ms / 126 tokens ( 5.28 ms per token, 189.50 tokens per second) 1.25.507.561 I slot print_timing: id 3 | task 270 | eval time = 613.63 ms / 2 tokens ( 613.63 ms per token, 1.63 tokens per second) 1.25.507.562 I slot print_timing: id 3 | task 270 | total time = 1278.53 ms / 128 tokens 1.25.507.562 I slot print_timing: id 3 | task 270 | graphs reused = 1 1.25.507.562 I slot print_timing: id 3 | task 270 | graph reallocs = 0 / 0 (same size) / (changed size) 1.25.507.574 I slot release: id 3 | task 270 | stop processing: n_tokens = 127, truncated = 0 1.25.565.733 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.172 (> 0.100 thold), f_keep = 0.224 1.25.567.773 I slot launch_slot_: id 2 | task 278 | processing task, is_child = 0 1.25.569.118 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.197 (> 0.100 thold), f_keep = 0.205 1.25.569.190 I slot launch_slot_: id 3 | task 277 | processing task, is_child = 0 1.26.260.507 I slot print_timing: id 0 | task 274 | prompt eval time = 667.94 ms / 128 tokens ( 5.22 ms per token, 191.63 tokens per second) 1.26.260.510 I slot print_timing: id 0 | task 274 | eval time = 694.87 ms / 2 tokens ( 694.87 ms per token, 1.44 tokens per second) 1.26.260.510 I slot print_timing: id 0 | task 274 | total time = 1362.81 ms / 130 tokens 1.26.260.511 I slot print_timing: id 0 | task 274 | graphs reused = 1 1.26.260.511 I slot print_timing: id 0 | task 274 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.260.531 I slot release: id 0 | task 274 | stop processing: n_tokens = 129, truncated = 0 1.26.260.626 I slot print_timing: id 1 | task 273 | prompt eval time = 668.01 ms / 113 tokens ( 5.91 ms per token, 169.16 tokens per second) 1.26.260.628 I slot print_timing: id 1 | task 273 | eval time = 694.89 ms / 2 tokens ( 694.89 ms per token, 1.44 tokens per second) 1.26.260.628 I slot print_timing: id 1 | task 273 | total time = 1362.90 ms / 115 tokens 1.26.260.628 I slot print_timing: id 1 | task 273 | graphs reused = 1 1.26.260.629 I slot print_timing: id 1 | task 273 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.260.640 I slot release: id 1 | task 273 | stop processing: n_tokens = 114, truncated = 0 1.26.319.236 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.202 1.26.321.114 I slot launch_slot_: id 0 | task 281 | processing task, is_child = 0 1.26.322.247 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.162 (> 0.100 thold), f_keep = 0.228 1.26.322.317 I slot launch_slot_: id 1 | task 282 | processing task, is_child = 0 1.27.104.686 I slot print_timing: id 2 | task 278 | prompt eval time = 749.94 ms / 151 tokens ( 4.97 ms per token, 201.35 tokens per second) 1.27.104.691 I slot print_timing: id 2 | task 278 | eval time = 785.54 ms / 2 tokens ( 785.54 ms per token, 1.27 tokens per second) 1.27.104.692 I slot print_timing: id 2 | task 278 | total time = 1535.49 ms / 153 tokens 1.27.104.692 I slot print_timing: id 2 | task 278 | graphs reused = 1 1.27.104.693 I slot print_timing: id 2 | task 278 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.104.711 I slot release: id 2 | task 278 | stop processing: n_tokens = 152, truncated = 0 1.27.104.805 I slot print_timing: id 3 | task 277 | prompt eval time = 750.02 ms / 132 tokens ( 5.68 ms per token, 176.00 tokens per second) 1.27.104.807 I slot print_timing: id 3 | task 277 | eval time = 785.57 ms / 2 tokens ( 785.57 ms per token, 1.27 tokens per second) 1.27.104.808 I slot print_timing: id 3 | task 277 | total time = 1535.59 ms / 134 tokens 1.27.104.808 I slot print_timing: id 3 | task 277 | graphs reused = 1 1.27.104.808 I slot print_timing: id 3 | task 277 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.104.822 I slot release: id 3 | task 277 | stop processing: n_tokens = 133, truncated = 0 1.27.163.729 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.149 (> 0.100 thold), f_keep = 0.171 1.27.165.936 I slot launch_slot_: id 2 | task 285 | processing task, is_child = 0 1.27.167.808 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.181 (> 0.100 thold), f_keep = 0.195 1.27.167.882 I slot launch_slot_: id 3 | task 286 | processing task, is_child = 0 1.27.935.855 I slot print_timing: id 0 | task 281 | prompt eval time = 841.31 ms / 113 tokens ( 7.45 ms per token, 134.31 tokens per second) 1.27.935.860 I slot print_timing: id 0 | task 281 | eval time = 772.22 ms / 2 tokens ( 772.22 ms per token, 1.29 tokens per second) 1.27.935.860 I slot print_timing: id 0 | task 281 | total time = 1613.53 ms / 115 tokens 1.27.935.861 I slot print_timing: id 0 | task 281 | graphs reused = 1 1.27.935.861 I slot print_timing: id 0 | task 281 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.935.880 I slot release: id 0 | task 281 | stop processing: n_tokens = 114, truncated = 0 1.27.935.975 I slot print_timing: id 1 | task 282 | prompt eval time = 841.38 ms / 160 tokens ( 5.26 ms per token, 190.16 tokens per second) 1.27.935.977 I slot print_timing: id 1 | task 282 | eval time = 772.25 ms / 2 tokens ( 772.25 ms per token, 1.29 tokens per second) 1.27.935.978 I slot print_timing: id 1 | task 282 | total time = 1613.62 ms / 162 tokens 1.27.935.978 I slot print_timing: id 1 | task 282 | graphs reused = 1 1.27.935.979 I slot print_timing: id 1 | task 282 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.935.991 I slot release: id 1 | task 282 | stop processing: n_tokens = 161, truncated = 0 1.27.995.552 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.206 (> 0.100 thold), f_keep = 0.228 1.27.997.469 I slot launch_slot_: id 0 | task 289 | processing task, is_child = 0 1.27.999.804 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.271 (> 0.100 thold), f_keep = 0.161 1.27.999.891 I slot launch_slot_: id 1 | task 290 | processing task, is_child = 0 1.28.631.071 I slot print_timing: id 2 | task 285 | prompt eval time = 827.53 ms / 175 tokens ( 4.73 ms per token, 211.47 tokens per second) 1.28.631.075 I slot print_timing: id 2 | task 285 | eval time = 635.65 ms / 2 tokens ( 635.65 ms per token, 1.57 tokens per second) 1.28.631.076 I slot print_timing: id 2 | task 285 | total time = 1463.18 ms / 177 tokens 1.28.631.076 I slot print_timing: id 2 | task 285 | graphs reused = 1 1.28.631.077 I slot print_timing: id 2 | task 285 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.631.101 I slot release: id 2 | task 285 | stop processing: n_tokens = 176, truncated = 0 1.28.631.192 I slot print_timing: id 3 | task 286 | prompt eval time = 827.63 ms / 144 tokens ( 5.75 ms per token, 173.99 tokens per second) 1.28.631.194 I slot print_timing: id 3 | task 286 | eval time = 635.64 ms / 2 tokens ( 635.64 ms per token, 1.57 tokens per second) 1.28.631.194 I slot print_timing: id 3 | task 286 | total time = 1463.28 ms / 146 tokens 1.28.631.194 I slot print_timing: id 3 | task 286 | graphs reused = 1 1.28.631.195 I slot print_timing: id 3 | task 286 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.631.207 I slot release: id 3 | task 286 | stop processing: n_tokens = 145, truncated = 0 1.28.689.556 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.226 (> 0.100 thold), f_keep = 0.148 1.28.691.511 I slot launch_slot_: id 2 | task 293 | processing task, is_child = 0 1.28.693.103 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.179 1.28.693.500 I slot launch_slot_: id 3 | task 294 | processing task, is_child = 0 1.29.306.898 I slot print_timing: id 0 | task 289 | prompt eval time = 689.55 ms / 126 tokens ( 5.47 ms per token, 182.73 tokens per second) 1.29.306.900 I slot print_timing: id 0 | task 289 | eval time = 617.45 ms / 2 tokens ( 617.45 ms per token, 1.62 tokens per second) 1.29.306.901 I slot print_timing: id 0 | task 289 | total time = 1307.00 ms / 128 tokens 1.29.306.901 I slot print_timing: id 0 | task 289 | graphs reused = 1 1.29.306.902 I slot print_timing: id 0 | task 289 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.306.924 I slot release: id 0 | task 289 | stop processing: n_tokens = 127, truncated = 0 1.29.307.023 I slot print_timing: id 1 | task 290 | prompt eval time = 689.64 ms / 96 tokens ( 7.18 ms per token, 139.20 tokens per second) 1.29.307.025 I slot print_timing: id 1 | task 290 | eval time = 617.47 ms / 2 tokens ( 617.47 ms per token, 1.62 tokens per second) 1.29.307.026 I slot print_timing: id 1 | task 290 | total time = 1307.11 ms / 98 tokens 1.29.307.026 I slot print_timing: id 1 | task 290 | graphs reused = 1 1.29.307.026 I slot print_timing: id 1 | task 290 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.307.036 I slot release: id 1 | task 290 | stop processing: n_tokens = 97, truncated = 0 1.29.398.056 I slot print_timing: id 2 | task 293 | prompt eval time = 671.76 ms / 115 tokens ( 5.84 ms per token, 171.19 tokens per second) 1.29.398.058 I slot print_timing: id 2 | task 293 | eval time = 32.79 ms / 2 tokens ( 32.79 ms per token, 30.50 tokens per second) 1.29.398.060 I slot print_timing: id 2 | task 293 | total time = 704.54 ms / 117 tokens 1.29.398.060 I slot print_timing: id 2 | task 293 | graphs reused = 1 1.29.398.060 I slot print_timing: id 2 | task 293 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.398.074 I slot release: id 2 | task 293 | stop processing: n_tokens = 116, truncated = 0 1.29.398.156 I slot print_timing: id 3 | task 294 | prompt eval time = 671.83 ms / 128 tokens ( 5.25 ms per token, 190.52 tokens per second) 1.29.398.158 I slot print_timing: id 3 | task 294 | eval time = 32.79 ms / 2 tokens ( 32.79 ms per token, 30.50 tokens per second) 1.29.398.158 I slot print_timing: id 3 | task 294 | total time = 704.62 ms / 130 tokens 1.29.398.158 I slot print_timing: id 3 | task 294 | graphs reused = 1 1.29.398.159 I slot print_timing: id 3 | task 294 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.398.166 I slot release: id 3 | task 294 | stop processing: n_tokens = 129, truncated = 0 1.29.414.330 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 127, t_last = 350908633903 1.29.415.718 I slot launch_slot_: id 0 | task 298 | processing task, is_child = 0 1.29.419.552 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 97, t_last = 350908634015 1.29.419.589 I slot launch_slot_: id 1 | task 299 | processing task, is_child = 0 1.29.419.641 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 116, t_last = 350908725053 1.29.419.675 I slot launch_slot_: id 2 | task 300 | processing task, is_child = 0 1.29.419.700 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 129, t_last = 350908725145 1.29.419.733 I slot launch_slot_: id 3 | task 301 | processing task, is_child = 0 1.32.963.332 I slot print_timing: id 0 | task 298 | prompt processing, n_tokens = 513, progress = 0.50, t = 3.54 s / 144.77 tokens per second 1.33.015.909 I slot print_timing: id 1 | task 299 | prompt processing, n_tokens = 525, progress = 0.50, t = 3.54 s / 148.16 tokens per second 1.33.019.426 I slot print_timing: id 2 | task 300 | prompt processing, n_tokens = 532, progress = 0.51, t = 3.54 s / 150.13 tokens per second 1.33.022.797 I slot print_timing: id 3 | task 301 | prompt processing, n_tokens = 540, progress = 0.51, t = 3.54 s / 152.39 tokens per second 1.36.145.866 I slot print_timing: id 0 | task 298 | prompt processing, n_tokens = 953, progress = 0.93, t = 6.73 s / 141.69 tokens per second 1.36.220.821 I slot print_timing: id 1 | task 299 | prompt processing, n_tokens = 953, progress = 0.92, t = 6.73 s / 141.69 tokens per second 1.36.224.432 I slot print_timing: id 2 | task 300 | prompt processing, n_tokens = 953, progress = 0.91, t = 6.73 s / 141.69 tokens per second 1.36.227.469 I slot print_timing: id 3 | task 301 | prompt processing, n_tokens = 953, progress = 0.90, t = 6.73 s / 141.69 tokens per second 1.37.160.923 I slot print_timing: id 0 | task 298 | prompt processing, n_tokens = 1025, progress = 1.00, t = 7.74 s / 132.41 tokens per second 1.37.214.602 I slot print_timing: id 1 | task 299 | prompt processing, n_tokens = 1037, progress = 1.00, t = 7.74 s / 133.96 tokens per second 1.37.218.336 I slot print_timing: id 2 | task 300 | prompt processing, n_tokens = 1044, progress = 1.00, t = 7.74 s / 134.86 tokens per second 1.37.221.574 I slot print_timing: id 3 | task 301 | prompt processing, n_tokens = 1052, progress = 1.00, t = 7.74 s / 135.90 tokens per second 1.41.384.520 I slot print_timing: id 0 | task 298 | n_gen = 100, tg = 24.40 t/s, tg_3s = 24.64 t/s 1.41.384.696 I slot print_timing: id 1 | task 299 | n_gen = 100, tg = 24.40 t/s, tg_3s = 24.64 t/s 1.41.384.871 I slot print_timing: id 2 | task 300 | n_gen = 100, tg = 24.40 t/s, tg_3s = 24.64 t/s 1.41.385.040 I slot print_timing: id 3 | task 301 | n_gen = 100, tg = 24.40 t/s, tg_3s = 24.64 t/s 1.41.466.333 I slot print_timing: id 0 | task 298 | prompt eval time = 7906.97 ms / 1029 tokens ( 7.68 ms per token, 130.14 tokens per second) 1.41.466.344 I slot print_timing: id 0 | task 298 | eval time = 4139.62 ms / 102 tokens ( 40.99 ms per token, 24.40 tokens per second) 1.41.466.345 I slot print_timing: id 0 | task 298 | total time = 12046.59 ms / 1131 tokens 1.41.466.346 I slot print_timing: id 0 | task 298 | graphs reused = 103 1.41.466.347 I slot print_timing: id 0 | task 298 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.466.430 I slot release: id 0 | task 298 | stop processing: n_tokens = 1130, truncated = 0 1.41.509.637 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.859 1.41.509.667 I slot launch_slot_: id 0 | task 410 | processing task, is_child = 0 1.42.809.421 I slot print_timing: id 1 | task 299 | prompt eval time = 7907.05 ms / 1041 tokens ( 7.60 ms per token, 131.65 tokens per second) 1.42.809.429 I slot print_timing: id 1 | task 299 | eval time = 5482.60 ms / 125 tokens ( 44.21 ms per token, 22.62 tokens per second) 1.42.809.430 I slot print_timing: id 1 | task 299 | total time = 13389.65 ms / 1166 tokens 1.42.809.431 I slot print_timing: id 1 | task 299 | graphs reused = 123 1.42.809.432 I slot print_timing: id 1 | task 299 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.809.500 I slot release: id 1 | task 299 | stop processing: n_tokens = 1165, truncated = 0 1.42.867.391 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.833 1.42.867.418 I slot launch_slot_: id 1 | task 434 | processing task, is_child = 0 1.44.402.582 I slot print_timing: id 2 | task 300 | n_gen = 152, tg = 21.34 t/s, tg_3s = 17.23 t/s 1.44.402.752 I slot print_timing: id 3 | task 301 | n_gen = 152, tg = 21.34 t/s, tg_3s = 17.23 t/s 1.46.534.252 I slot print_timing: id 0 | task 410 | n_gen = 100, tg = 21.74 t/s, tg_3s = 21.96 t/s 1.47.444.518 I slot print_timing: id 2 | task 300 | n_gen = 226, tg = 22.24 t/s, tg_3s = 24.33 t/s 1.47.444.667 I slot print_timing: id 3 | task 301 | n_gen = 226, tg = 22.24 t/s, tg_3s = 24.33 t/s 1.47.485.432 I slot print_timing: id 1 | task 434 | n_gen = 100, tg = 24.34 t/s, tg_3s = 24.58 t/s 1.48.393.802 I slot print_timing: id 2 | task 300 | prompt eval time = 7907.13 ms / 1048 tokens ( 7.54 ms per token, 132.54 tokens per second) 1.48.393.810 I slot print_timing: id 2 | task 300 | eval time = 11066.89 ms / 249 tokens ( 44.62 ms per token, 22.41 tokens per second) 1.48.393.811 I slot print_timing: id 2 | task 300 | total time = 18974.01 ms / 1297 tokens 1.48.393.812 I slot print_timing: id 2 | task 300 | graphs reused = 242 1.48.393.813 I slot print_timing: id 2 | task 300 | graph reallocs = 0 / 0 (same size) / (changed size) 1.48.393.885 I slot release: id 2 | task 300 | stop processing: n_tokens = 1296, truncated = 0 1.48.452.250 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.902 (> 0.100 thold), f_keep = 0.749 1.48.452.280 I slot launch_slot_: id 2 | task 559 | processing task, is_child = 0 1.49.572.624 I slot print_timing: id 0 | task 410 | n_gen = 162, tg = 21.21 t/s, tg_3s = 20.41 t/s 1.50.479.019 I slot print_timing: id 3 | task 301 | n_gen = 288, tg = 21.82 t/s, tg_3s = 20.43 t/s 1.50.519.851 I slot print_timing: id 1 | task 434 | n_gen = 162, tg = 22.67 t/s, tg_3s = 20.43 t/s 1.52.575.869 I slot print_timing: id 0 | task 410 | n_gen = 235, tg = 22.08 t/s, tg_3s = 24.31 t/s 1.53.028.516 I slot print_timing: id 0 | task 410 | prompt eval time = 470.57 ms / 97 tokens ( 4.85 ms per token, 206.13 tokens per second) 1.53.028.522 I slot print_timing: id 0 | task 410 | eval time = 11048.27 ms / 246 tokens ( 45.09 ms per token, 22.18 tokens per second) 1.53.028.523 I slot print_timing: id 0 | task 410 | total time = 11518.84 ms / 343 tokens 1.53.028.524 I slot print_timing: id 0 | task 410 | graphs reused = 339 1.53.028.525 I slot print_timing: id 0 | task 410 | graph reallocs = 0 / 0 (same size) / (changed size) 1.53.028.604 I slot release: id 0 | task 410 | stop processing: n_tokens = 1313, truncated = 0 1.53.071.307 I slot print_timing: id 2 | task 559 | n_gen = 100, tg = 24.23 t/s, tg_3s = 24.47 t/s 1.53.071.464 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.924 (> 0.100 thold), f_keep = 0.740 1.53.071.487 I slot launch_slot_: id 0 | task 661 | processing task, is_child = 0 1.53.510.072 I slot print_timing: id 3 | task 301 | n_gen = 353, tg = 21.75 t/s, tg_3s = 21.44 t/s 1.53.553.598 I slot print_timing: id 1 | task 434 | n_gen = 227, tg = 22.30 t/s, tg_3s = 21.43 t/s 1.56.109.025 I slot print_timing: id 2 | task 559 | n_gen = 165, tg = 23.02 t/s, tg_3s = 21.40 t/s 1.56.520.663 I slot print_timing: id 3 | task 301 | n_gen = 426, tg = 22.14 t/s, tg_3s = 24.25 t/s 1.56.561.422 I slot print_timing: id 1 | task 434 | n_gen = 300, tg = 22.75 t/s, tg_3s = 24.27 t/s 1.57.588.843 I slot print_timing: id 0 | task 661 | n_gen = 100, tg = 24.27 t/s, tg_3s = 24.52 t/s 1.59.122.341 I slot print_timing: id 2 | task 559 | n_gen = 238, tg = 23.38 t/s, tg_3s = 24.23 t/s 1.59.534.863 I slot print_timing: id 3 | task 301 | n_gen = 499, tg = 22.42 t/s, tg_3s = 24.22 t/s 1.59.575.817 I slot print_timing: id 1 | task 434 | n_gen = 373, tg = 23.02 t/s, tg_3s = 24.22 t/s 2.00.606.998 I slot print_timing: id 0 | task 661 | n_gen = 173, tg = 24.24 t/s, tg_3s = 24.19 t/s 2.02.134.684 I slot print_timing: id 2 | task 559 | n_gen = 311, tg = 23.58 t/s, tg_3s = 24.23 t/s 2.02.547.268 I slot print_timing: id 3 | task 301 | n_gen = 572, tg = 22.64 t/s, tg_3s = 24.23 t/s 2.02.588.170 I slot print_timing: id 1 | task 434 | n_gen = 446, tg = 23.21 t/s, tg_3s = 24.23 t/s 2.03.625.619 I slot print_timing: id 0 | task 661 | n_gen = 246, tg = 24.22 t/s, tg_3s = 24.18 t/s 2.04.327.804 I slot print_timing: id 0 | task 661 | prompt eval time = 438.35 ms / 80 tokens ( 5.48 ms per token, 182.50 tokens per second) 2.04.327.812 I slot print_timing: id 0 | task 661 | eval time = 10817.96 ms / 263 tokens ( 41.29 ms per token, 24.22 tokens per second) 2.04.327.813 I slot print_timing: id 0 | task 661 | total time = 11256.31 ms / 343 tokens 2.04.327.814 I slot print_timing: id 0 | task 661 | graphs reused = 600 2.04.327.814 I slot print_timing: id 0 | task 661 | graph reallocs = 0 / 0 (same size) / (changed size) 2.04.327.891 I slot release: id 0 | task 661 | stop processing: n_tokens = 1313, truncated = 0 2.04.371.471 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.899 (> 0.100 thold), f_keep = 0.740 2.04.371.496 I slot launch_slot_: id 0 | task 927 | processing task, is_child = 0 2.04.877.143 I slot print_timing: id 2 | task 559 | prompt eval time = 532.91 ms / 105 tokens ( 5.08 ms per token, 197.03 tokens per second) 2.04.877.148 I slot print_timing: id 2 | task 559 | eval time = 15891.94 ms / 367 tokens ( 43.42 ms per token, 23.03 tokens per second) 2.04.877.148 I slot print_timing: id 2 | task 559 | total time = 16424.86 ms / 472 tokens 2.04.877.149 I slot print_timing: id 2 | task 559 | graphs reused = 601 2.04.877.149 I slot print_timing: id 2 | task 559 | graph reallocs = 0 / 0 (same size) / (changed size) 2.04.877.193 I slot release: id 2 | task 559 | stop processing: n_tokens = 1442, truncated = 0 2.04.930.910 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.877 (> 0.100 thold), f_keep = 0.673 2.04.930.928 I slot launch_slot_: id 2 | task 931 | processing task, is_child = 0 2.05.583.220 I slot print_timing: id 3 | task 301 | n_gen = 623, tg = 22.01 t/s, tg_3s = 16.80 t/s 2.05.624.056 I slot print_timing: id 1 | task 434 | n_gen = 497, tg = 22.34 t/s, tg_3s = 16.80 t/s 2.08.593.464 I slot print_timing: id 3 | task 301 | n_gen = 696, tg = 22.23 t/s, tg_3s = 24.25 t/s 2.08.634.278 I slot print_timing: id 1 | task 434 | n_gen = 570, tg = 22.56 t/s, tg_3s = 24.25 t/s 2.09.459.392 I slot print_timing: id 0 | task 927 | n_gen = 100, tg = 21.60 t/s, tg_3s = 21.82 t/s 2.09.583.657 I slot print_timing: id 2 | task 931 | n_gen = 100, tg = 24.23 t/s, tg_3s = 24.48 t/s 2.11.611.999 I slot print_timing: id 3 | task 301 | n_gen = 769, tg = 22.40 t/s, tg_3s = 24.18 t/s 2.11.653.094 I slot print_timing: id 1 | task 434 | n_gen = 643, tg = 22.74 t/s, tg_3s = 24.18 t/s 2.12.479.209 I slot print_timing: id 0 | task 927 | n_gen = 173, tg = 22.62 t/s, tg_3s = 24.17 t/s 2.12.603.703 I slot print_timing: id 2 | task 931 | n_gen = 173, tg = 24.21 t/s, tg_3s = 24.17 t/s 2.14.346.515 I slot print_timing: id 0 | task 927 | prompt eval time = 505.49 ms / 109 tokens ( 4.64 ms per token, 215.63 tokens per second) 2.14.346.520 I slot print_timing: id 0 | task 927 | eval time = 9469.52 ms / 218 tokens ( 43.64 ms per token, 22.92 tokens per second) 2.14.346.521 I slot print_timing: id 0 | task 927 | total time = 9975.01 ms / 327 tokens 2.14.346.522 I slot print_timing: id 0 | task 927 | graphs reused = 813 2.14.346.522 I slot print_timing: id 0 | task 927 | graph reallocs = 0 / 0 (same size) / (changed size) 2.14.346.596 I slot release: id 0 | task 927 | stop processing: n_tokens = 1297, truncated = 0 2.14.390.118 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.749 2.14.390.145 I slot launch_slot_: id 0 | task 1149 | processing task, is_child = 0 2.14.770.085 I slot print_timing: id 1 | task 434 | n_gen = 710, tg = 22.61 t/s, tg_3s = 21.50 t/s 2.14.770.254 I slot print_timing: id 3 | task 301 | n_gen = 837, tg = 22.33 t/s, tg_3s = 21.53 t/s 2.15.640.843 I slot print_timing: id 2 | task 931 | n_gen = 237, tg = 23.27 t/s, tg_3s = 21.07 t/s 2.17.790.457 I slot print_timing: id 1 | task 434 | n_gen = 782, tg = 22.72 t/s, tg_3s = 23.84 t/s 2.17.790.802 I slot print_timing: id 3 | task 301 | n_gen = 909, tg = 22.44 t/s, tg_3s = 23.84 t/s 2.18.658.863 I slot print_timing: id 2 | task 931 | n_gen = 310, tg = 23.48 t/s, tg_3s = 24.19 t/s 2.18.948.314 I slot print_timing: id 0 | task 1149 | n_gen = 100, tg = 24.16 t/s, tg_3s = 24.40 t/s 2.20.813.909 I slot print_timing: id 1 | task 434 | n_gen = 855, tg = 22.84 t/s, tg_3s = 24.14 t/s 2.20.814.081 I slot print_timing: id 2 | task 931 | prompt eval time = 567.33 ms / 137 tokens ( 4.14 ms per token, 241.48 tokens per second) 2.20.814.085 I slot print_timing: id 2 | task 931 | eval time = 15315.82 ms / 362 tokens ( 42.43 ms per token, 23.57 tokens per second) 2.20.814.087 I slot print_timing: id 2 | task 931 | total time = 15883.15 ms / 499 tokens 2.20.814.088 I slot print_timing: id 2 | task 931 | graphs reused = 957 2.20.814.089 I slot print_timing: id 2 | task 931 | graph reallocs = 0 / 0 (same size) / (changed size) 2.20.814.162 I slot release: id 2 | task 931 | stop processing: n_tokens = 1468, truncated = 0 2.20.814.351 I slot print_timing: id 3 | task 301 | n_gen = 982, tg = 22.56 t/s, tg_3s = 24.14 t/s 2.20.873.168 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.661 2.20.873.204 I slot launch_slot_: id 2 | task 1297 | processing task, is_child = 0 2.21.966.434 I slot print_timing: id 0 | task 1149 | n_gen = 163, tg = 22.77 t/s, tg_3s = 20.87 t/s 2.22.553.172 I slot print_timing: id 3 | task 301 | prompt eval time = 7907.28 ms / 1056 tokens ( 7.49 ms per token, 133.55 tokens per second) 2.22.553.180 I slot print_timing: id 3 | task 301 | eval time = 45226.07 ms / 1014 tokens ( 44.65 ms per token, 22.40 tokens per second) 2.22.553.181 I slot print_timing: id 3 | task 301 | total time = 53133.36 ms / 2070 tokens 2.22.553.182 I slot print_timing: id 3 | task 301 | graphs reused = 984 2.22.553.183 I slot print_timing: id 3 | task 301 | graph reallocs = 0 / 0 (same size) / (changed size) 2.22.553.266 I slot release: id 3 | task 301 | stop processing: n_tokens = 2069, truncated = 0 2.22.596.679 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.469 2.22.618.534 I slot launch_slot_: id 3 | task 1330 | processing task, is_child = 0 2.23.535.945 I slot print_timing: id 1 | task 434 | prompt eval time = 550.45 ms / 104 tokens ( 5.29 ms per token, 188.94 tokens per second) 2.23.535.951 I slot print_timing: id 1 | task 434 | eval time = 40118.07 ms / 901 tokens ( 44.58 ms per token, 22.43 tokens per second) 2.23.535.951 I slot print_timing: id 1 | task 434 | total time = 40668.52 ms / 1005 tokens 2.23.535.952 I slot print_timing: id 1 | task 434 | graphs reused = 994 2.23.535.952 I slot print_timing: id 1 | task 434 | graph reallocs = 0 / 0 (same size) / (changed size) 2.23.536.001 I slot release: id 1 | task 434 | stop processing: n_tokens = 1975, truncated = 0 2.23.590.515 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.492 2.23.611.628 I slot launch_slot_: id 1 | task 1345 | processing task, is_child = 0 2.24.998.444 I slot print_timing: id 0 | task 1149 | n_gen = 217, tg = 21.29 t/s, tg_3s = 17.81 t/s 2.26.232.847 I slot print_timing: id 2 | task 1297 | n_gen = 100, tg = 20.17 t/s, tg_3s = 20.37 t/s 2.27.588.729 I slot print_timing: id 3 | task 1330 | n_gen = 100, tg = 22.17 t/s, tg_3s = 22.40 t/s 2.28.039.550 I slot print_timing: id 0 | task 1149 | n_gen = 291, tg = 21.99 t/s, tg_3s = 24.33 t/s 2.28.121.869 I slot print_timing: id 1 | task 1345 | n_gen = 100, tg = 24.31 t/s, tg_3s = 24.56 t/s 2.29.271.794 I slot print_timing: id 2 | task 1297 | n_gen = 174, tg = 21.77 t/s, tg_3s = 24.35 t/s 2.30.626.695 I slot print_timing: id 3 | task 1330 | n_gen = 174, tg = 23.06 t/s, tg_3s = 24.36 t/s 2.31.078.358 I slot print_timing: id 0 | task 1149 | n_gen = 365, tg = 22.43 t/s, tg_3s = 24.35 t/s 2.31.160.624 I slot print_timing: id 1 | task 1345 | n_gen = 174, tg = 24.33 t/s, tg_3s = 24.35 t/s 2.31.326.172 I slot print_timing: id 2 | task 1297 | prompt eval time = 450.82 ms / 70 tokens ( 6.44 ms per token, 155.27 tokens per second) 2.31.326.177 I slot print_timing: id 2 | task 1297 | eval time = 10002.13 ms / 224 tokens ( 44.85 ms per token, 22.30 tokens per second) 2.31.326.178 I slot print_timing: id 2 | task 1297 | total time = 10452.96 ms / 294 tokens 2.31.326.179 I slot print_timing: id 2 | task 1297 | graphs reused = 1169 2.31.326.180 I slot print_timing: id 2 | task 1297 | graph reallocs = 0 / 0 (same size) / (changed size) 2.31.326.255 I slot release: id 2 | task 1297 | stop processing: n_tokens = 1264, truncated = 0 2.31.384.545 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.768 2.31.384.571 I slot launch_slot_: id 2 | task 1526 | processing task, is_child = 0 2.33.605.409 I slot print_timing: id 0 | task 1149 | prompt eval time = 460.37 ms / 92 tokens ( 5.00 ms per token, 199.84 tokens per second) 2.33.605.417 I slot print_timing: id 0 | task 1149 | eval time = 18754.88 ms / 416 tokens ( 45.19 ms per token, 22.13 tokens per second) 2.33.605.418 I slot print_timing: id 0 | task 1149 | total time = 19215.25 ms / 508 tokens 2.33.605.418 I slot print_timing: id 0 | task 1149 | graphs reused = 1210 2.33.605.419 I slot print_timing: id 0 | task 1149 | graph reallocs = 0 / 0 (same size) / (changed size) 2.33.605.495 I slot release: id 0 | task 1149 | stop processing: n_tokens = 1478, truncated = 0 2.33.648.309 I slot print_timing: id 3 | task 1330 | n_gen = 237, tg = 22.42 t/s, tg_3s = 20.85 t/s 2.33.648.316 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.895 (> 0.100 thold), f_keep = 0.657 2.33.648.338 I slot launch_slot_: id 0 | task 1572 | processing task, is_child = 0 2.34.200.346 I slot print_timing: id 1 | task 1345 | n_gen = 227, tg = 22.27 t/s, tg_3s = 17.44 t/s 2.36.377.852 I slot print_timing: id 2 | task 1526 | n_gen = 100, tg = 21.96 t/s, tg_3s = 22.18 t/s 2.36.665.478 I slot print_timing: id 3 | task 1330 | n_gen = 300, tg = 22.08 t/s, tg_3s = 20.88 t/s 2.37.238.679 I slot print_timing: id 1 | task 1345 | n_gen = 301, tg = 22.75 t/s, tg_3s = 24.36 t/s 2.38.180.916 I slot print_timing: id 1 | task 1345 | prompt eval time = 438.30 ms / 64 tokens ( 6.85 ms per token, 146.02 tokens per second) 2.38.180.924 I slot print_timing: id 1 | task 1345 | eval time = 14130.98 ms / 324 tokens ( 43.75 ms per token, 22.86 tokens per second) 2.38.180.925 I slot print_timing: id 1 | task 1345 | total time = 14569.28 ms / 388 tokens 2.38.180.926 I slot print_timing: id 1 | task 1345 | graphs reused = 1307 2.38.180.927 I slot print_timing: id 1 | task 1345 | graph reallocs = 0 / 0 (same size) / (changed size) 2.38.180.999 I slot release: id 1 | task 1345 | stop processing: n_tokens = 1357, truncated = 0 2.38.238.136 I slot print_timing: id 0 | task 1572 | n_gen = 100, tg = 24.26 t/s, tg_3s = 24.50 t/s 2.38.238.453 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.947 (> 0.100 thold), f_keep = 0.716 2.38.238.477 I slot launch_slot_: id 1 | task 1674 | processing task, is_child = 0 2.39.403.060 I slot print_timing: id 2 | task 1526 | n_gen = 165, tg = 21.77 t/s, tg_3s = 21.49 t/s 2.39.690.119 I slot print_timing: id 3 | task 1330 | n_gen = 365, tg = 21.97 t/s, tg_3s = 21.49 t/s 2.41.247.388 I slot print_timing: id 0 | task 1572 | n_gen = 165, tg = 23.13 t/s, tg_3s = 21.60 t/s 2.41.698.808 I slot print_timing: id 2 | task 1526 | prompt eval time = 484.77 ms / 88 tokens ( 5.51 ms per token, 181.53 tokens per second) 2.41.698.816 I slot print_timing: id 2 | task 1526 | eval time = 9829.46 ms / 221 tokens ( 44.68 ms per token, 22.38 tokens per second) 2.41.698.817 I slot print_timing: id 2 | task 1526 | total time = 10314.23 ms / 309 tokens 2.41.698.817 I slot print_timing: id 2 | task 1526 | graphs reused = 1380 2.41.698.818 I slot print_timing: id 2 | task 1526 | graph reallocs = 0 / 0 (same size) / (changed size) 2.41.698.891 I slot release: id 2 | task 1526 | stop processing: n_tokens = 1279, truncated = 0 2.41.757.258 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.759 2.41.757.283 I slot launch_slot_: id 2 | task 1752 | processing task, is_child = 0 2.42.731.237 I slot print_timing: id 3 | task 1330 | n_gen = 428, tg = 21.78 t/s, tg_3s = 20.72 t/s 2.43.183.052 I slot print_timing: id 1 | task 1674 | n_gen = 100, tg = 21.88 t/s, tg_3s = 22.10 t/s 2.44.254.315 I slot print_timing: id 0 | task 1572 | n_gen = 227, tg = 22.38 t/s, tg_3s = 20.62 t/s 2.45.746.198 I slot print_timing: id 3 | task 1330 | n_gen = 501, tg = 22.10 t/s, tg_3s = 24.21 t/s 2.46.198.199 I slot print_timing: id 1 | task 1674 | n_gen = 173, tg = 22.81 t/s, tg_3s = 24.21 t/s 2.46.363.036 I slot print_timing: id 2 | task 1752 | n_gen = 100, tg = 24.12 t/s, tg_3s = 24.36 t/s 2.47.269.280 I slot print_timing: id 0 | task 1572 | n_gen = 300, tg = 22.80 t/s, tg_3s = 24.21 t/s 2.47.887.641 I slot print_timing: id 1 | task 1674 | prompt eval time = 419.97 ms / 54 tokens ( 7.78 ms per token, 128.58 tokens per second) 2.47.887.648 I slot print_timing: id 1 | task 1674 | eval time = 9229.18 ms / 214 tokens ( 43.33 ms per token, 23.08 tokens per second) 2.47.887.649 I slot print_timing: id 1 | task 1674 | total time = 9649.15 ms / 268 tokens 2.47.887.650 I slot print_timing: id 1 | task 1674 | graphs reused = 1513 2.47.887.651 I slot print_timing: id 1 | task 1674 | graph reallocs = 0 / 0 (same size) / (changed size) 2.47.887.730 I slot release: id 1 | task 1674 | stop processing: n_tokens = 1238, truncated = 0 2.47.945.797 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.784 2.47.945.830 I slot launch_slot_: id 1 | task 1892 | processing task, is_child = 0 2.48.776.801 I slot print_timing: id 3 | task 1330 | n_gen = 565, tg = 21.99 t/s, tg_3s = 21.12 t/s 2.49.393.563 I slot print_timing: id 2 | task 1752 | n_gen = 164, tg = 22.84 t/s, tg_3s = 21.12 t/s 2.50.298.519 I slot print_timing: id 0 | task 1572 | n_gen = 364, tg = 22.49 t/s, tg_3s = 21.13 t/s 2.51.783.796 I slot print_timing: id 3 | task 1330 | n_gen = 638, tg = 22.23 t/s, tg_3s = 24.28 t/s 2.52.031.595 I slot print_timing: id 2 | task 1752 | prompt eval time = 501.12 ms / 96 tokens ( 5.22 ms per token, 191.57 tokens per second) 2.52.031.600 I slot print_timing: id 2 | task 1752 | eval time = 9773.18 ms / 228 tokens ( 43.05 ms per token, 23.23 tokens per second) 2.52.031.602 I slot print_timing: id 2 | task 1752 | total time = 10274.30 ms / 324 tokens 2.52.031.603 I slot print_timing: id 2 | task 1752 | graphs reused = 1600 2.52.031.603 I slot print_timing: id 2 | task 1752 | graph reallocs = 0 / 0 (same size) / (changed size) 2.52.031.680 I slot release: id 2 | task 1752 | stop processing: n_tokens = 1294, truncated = 0 2.52.089.907 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.950 (> 0.100 thold), f_keep = 0.750 2.52.089.932 I slot launch_slot_: id 2 | task 1984 | processing task, is_child = 0 2.52.824.740 I slot print_timing: id 1 | task 1892 | n_gen = 100, tg = 22.33 t/s, tg_3s = 22.56 t/s 2.53.319.705 I slot print_timing: id 0 | task 1572 | n_gen = 429, tg = 22.33 t/s, tg_3s = 21.51 t/s 2.53.609.215 I slot print_timing: id 1 | task 1892 | prompt eval time = 445.93 ms / 66 tokens ( 6.76 ms per token, 148.00 tokens per second) 2.53.609.225 I slot print_timing: id 1 | task 1892 | eval time = 5217.44 ms / 119 tokens ( 44.22 ms per token, 22.62 tokens per second) 2.53.609.226 I slot print_timing: id 1 | task 1892 | total time = 5663.38 ms / 185 tokens 2.53.609.226 I slot print_timing: id 1 | task 1892 | graphs reused = 1626 2.53.609.227 I slot print_timing: id 1 | task 1892 | graph reallocs = 0 / 0 (same size) / (changed size) 2.53.609.296 I slot release: id 1 | task 1892 | stop processing: n_tokens = 1155, truncated = 0 2.53.667.372 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.841 2.53.667.400 I slot launch_slot_: id 1 | task 2015 | processing task, is_child = 0 2.54.813.071 I slot print_timing: id 3 | task 1330 | n_gen = 693, tg = 21.84 t/s, tg_3s = 18.16 t/s 2.56.338.159 I slot print_timing: id 0 | task 1572 | n_gen = 492, tg = 22.14 t/s, tg_3s = 20.87 t/s 2.56.998.848 I slot print_timing: id 2 | task 1984 | n_gen = 100, tg = 21.96 t/s, tg_3s = 22.18 t/s 2.57.245.690 I slot print_timing: id 2 | task 1984 | prompt eval time = 401.15 ms / 51 tokens ( 7.87 ms per token, 127.14 tokens per second) 2.57.245.696 I slot print_timing: id 2 | task 1984 | eval time = 4754.60 ms / 106 tokens ( 45.28 ms per token, 22.08 tokens per second) 2.57.245.698 I slot print_timing: id 2 | task 1984 | total time = 5155.75 ms / 157 tokens 2.57.245.698 I slot print_timing: id 2 | task 1984 | graphs reused = 1700 2.57.245.699 I slot print_timing: id 2 | task 1984 | graph reallocs = 0 / 0 (same size) / (changed size) 2.57.245.770 I slot release: id 2 | task 1984 | stop processing: n_tokens = 1127, truncated = 0 2.57.304.072 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.862 2.57.304.104 I slot launch_slot_: id 2 | task 2094 | processing task, is_child = 0 2.57.830.088 I slot print_timing: id 3 | task 1330 | n_gen = 757, tg = 21.78 t/s, tg_3s = 21.21 t/s 2.58.622.928 I slot print_timing: id 1 | task 2015 | n_gen = 100, tg = 22.10 t/s, tg_3s = 22.32 t/s 2.59.366.492 I slot print_timing: id 0 | task 1572 | n_gen = 556, tg = 22.02 t/s, tg_3s = 21.13 t/s 3.00.854.931 I slot print_timing: id 3 | task 1330 | n_gen = 830, tg = 21.97 t/s, tg_3s = 24.13 t/s 3.01.268.229 I slot print_timing: id 1 | task 2015 | prompt eval time = 474.98 ms / 70 tokens ( 6.79 ms per token, 147.38 tokens per second) 3.01.268.234 I slot print_timing: id 1 | task 2015 | eval time = 7125.84 ms / 164 tokens ( 43.72 ms per token, 22.87 tokens per second) 3.01.268.234 I slot print_timing: id 1 | task 2015 | total time = 7600.82 ms / 234 tokens 3.01.268.235 I slot print_timing: id 1 | task 2015 | graphs reused = 1784 3.01.268.236 I slot print_timing: id 1 | task 2015 | graph reallocs = 0 / 0 (same size) / (changed size) 3.01.268.312 I slot release: id 1 | task 2015 | stop processing: n_tokens = 1204, truncated = 0 3.01.326.558 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.806 3.01.326.584 I slot launch_slot_: id 1 | task 2183 | processing task, is_child = 0 3.02.285.943 I slot print_timing: id 2 | task 2094 | n_gen = 100, tg = 21.79 t/s, tg_3s = 22.01 t/s 3.02.367.421 I slot print_timing: id 0 | task 1572 | n_gen = 618, tg = 21.87 t/s, tg_3s = 20.66 t/s 3.03.619.220 I slot print_timing: id 0 | task 1572 | prompt eval time = 508.54 ms / 115 tokens ( 4.42 ms per token, 226.14 tokens per second) 3.03.619.228 I slot print_timing: id 0 | task 1572 | eval time = 29462.33 ms / 648 tokens ( 45.54 ms per token, 21.96 tokens per second) 3.03.619.229 I slot print_timing: id 0 | task 1572 | total time = 29970.87 ms / 763 tokens 3.03.619.229 I slot print_timing: id 0 | task 1572 | graphs reused = 1826 3.03.619.230 I slot print_timing: id 0 | task 1572 | graph reallocs = 0 / 0 (same size) / (changed size) 3.03.619.306 I slot release: id 0 | task 1572 | stop processing: n_tokens = 1732, truncated = 0 3.03.662.589 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.561 3.03.662.618 I slot launch_slot_: id 0 | task 2230 | processing task, is_child = 0 3.03.951.715 I slot print_timing: id 3 | task 1330 | n_gen = 888, tg = 21.73 t/s, tg_3s = 18.73 t/s 3.05.311.761 I slot print_timing: id 2 | task 2094 | n_gen = 166, tg = 21.80 t/s, tg_3s = 21.81 t/s 3.06.217.071 I slot print_timing: id 1 | task 2183 | n_gen = 100, tg = 22.58 t/s, tg_3s = 22.80 t/s 3.06.258.587 I slot print_timing: id 2 | task 2094 | prompt eval time = 439.33 ms / 63 tokens ( 6.97 ms per token, 143.40 tokens per second) 3.06.258.592 I slot print_timing: id 2 | task 2094 | eval time = 8515.14 ms / 189 tokens ( 45.29 ms per token, 22.08 tokens per second) 3.06.258.593 I slot print_timing: id 2 | task 2094 | total time = 8954.47 ms / 252 tokens 3.06.258.594 I slot print_timing: id 2 | task 2094 | graphs reused = 1880 3.06.258.595 I slot print_timing: id 2 | task 2094 | graph reallocs = 0 / 0 (same size) / (changed size) 3.06.258.666 I slot release: id 2 | task 2094 | stop processing: n_tokens = 1222, truncated = 0 3.06.316.915 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.795 3.06.316.943 I slot launch_slot_: id 2 | task 2288 | processing task, is_child = 0 3.06.953.689 I slot print_timing: id 3 | task 1330 | n_gen = 951, tg = 21.67 t/s, tg_3s = 20.99 t/s 3.08.475.672 I slot print_timing: id 0 | task 2230 | n_gen = 100, tg = 22.28 t/s, tg_3s = 22.50 t/s 3.09.255.109 I slot print_timing: id 1 | task 2183 | n_gen = 165, tg = 22.09 t/s, tg_3s = 21.40 t/s 3.09.965.489 I slot print_timing: id 3 | task 1330 | prompt eval time = 505.59 ms / 88 tokens ( 5.75 ms per token, 174.05 tokens per second) 3.09.965.496 I slot print_timing: id 3 | task 1330 | eval time = 46841.35 ms / 1024 tokens ( 45.79 ms per token, 21.84 tokens per second) 3.09.965.497 I slot print_timing: id 3 | task 1330 | total time = 47346.94 ms / 1112 tokens 3.09.965.498 I slot print_timing: id 3 | task 1330 | graphs reused = 1956 3.09.965.499 I slot print_timing: id 3 | task 1330 | graph reallocs = 0 / 0 (same size) / (changed size) 3.09.965.565 I slot release: id 3 | task 1330 | stop processing: n_tokens = 2063, truncated = 0 3.10.007.615 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.471 3.10.032.276 I slot launch_slot_: id 3 | task 2370 | processing task, is_child = 0 3.11.218.639 I slot print_timing: id 2 | task 2288 | n_gen = 100, tg = 22.11 t/s, tg_3s = 22.33 t/s 3.11.504.999 I slot print_timing: id 0 | task 2230 | n_gen = 164, tg = 21.81 t/s, tg_3s = 21.13 t/s 3.12.083.223 I slot print_timing: id 0 | task 2230 | prompt eval time = 369.36 ms / 56 tokens ( 6.60 ms per token, 151.61 tokens per second) 3.12.083.230 I slot print_timing: id 0 | task 2230 | eval time = 8051.23 ms / 178 tokens ( 45.49 ms per token, 21.98 tokens per second) 3.12.083.231 I slot print_timing: id 0 | task 2230 | total time = 8420.59 ms / 234 tokens 3.12.083.232 I slot print_timing: id 0 | task 2230 | graphs reused = 1993 3.12.083.233 I slot print_timing: id 0 | task 2230 | graph reallocs = 0 / 0 (same size) / (changed size) 3.12.083.305 I slot release: id 0 | task 2230 | stop processing: n_tokens = 1204, truncated = 0 3.12.126.193 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.807 3.12.126.216 I slot launch_slot_: id 0 | task 2413 | processing task, is_child = 0 3.12.509.561 I slot print_timing: id 1 | task 2183 | n_gen = 226, tg = 21.07 t/s, tg_3s = 18.74 t/s 3.14.234.613 I slot print_timing: id 2 | task 2288 | n_gen = 164, tg = 21.75 t/s, tg_3s = 21.22 t/s 3.14.972.736 I slot print_timing: id 3 | task 2370 | n_gen = 100, tg = 22.21 t/s, tg_3s = 22.43 t/s 3.15.301.602 I slot print_timing: id 2 | task 2288 | prompt eval time = 424.16 ms / 63 tokens ( 6.73 ms per token, 148.53 tokens per second) 3.15.301.608 I slot print_timing: id 2 | task 2288 | eval time = 8560.49 ms / 190 tokens ( 45.29 ms per token, 22.08 tokens per second) 3.15.301.609 I slot print_timing: id 2 | task 2288 | total time = 8984.65 ms / 253 tokens 3.15.301.610 I slot print_timing: id 2 | task 2288 | graphs reused = 2059 3.15.301.611 I slot print_timing: id 2 | task 2288 | graph reallocs = 0 / 0 (same size) / (changed size) 3.15.301.686 I slot release: id 2 | task 2288 | stop processing: n_tokens = 1223, truncated = 0 3.15.360.176 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.794 3.15.360.204 I slot launch_slot_: id 2 | task 2483 | processing task, is_child = 0 3.15.766.909 I slot print_timing: id 1 | task 2183 | n_gen = 295, tg = 21.10 t/s, tg_3s = 21.18 t/s 3.16.771.394 I slot print_timing: id 3 | task 2370 | prompt eval time = 482.88 ms / 74 tokens ( 6.53 ms per token, 153.25 tokens per second) 3.16.771.402 I slot print_timing: id 3 | task 2370 | eval time = 6256.22 ms / 133 tokens ( 47.40 ms per token, 21.10 tokens per second) 3.16.771.403 I slot print_timing: id 3 | task 2370 | total time = 6739.11 ms / 207 tokens 3.16.771.403 I slot print_timing: id 3 | task 2370 | graphs reused = 2080 3.16.771.404 I slot print_timing: id 3 | task 2370 | graph reallocs = 0 / 0 (same size) / (changed size) 3.16.771.478 I slot release: id 3 | task 2370 | stop processing: n_tokens = 1158, truncated = 0 3.16.813.821 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.895 (> 0.100 thold), f_keep = 0.839 3.16.813.846 I slot launch_slot_: id 3 | task 2509 | processing task, is_child = 0 3.17.533.987 I slot print_timing: id 0 | task 2413 | n_gen = 100, tg = 20.03 t/s, tg_3s = 20.23 t/s 3.18.770.370 I slot print_timing: id 1 | task 2183 | n_gen = 356, tg = 20.96 t/s, tg_3s = 20.31 t/s 3.20.367.116 I slot print_timing: id 2 | task 2483 | n_gen = 100, tg = 21.97 t/s, tg_3s = 22.19 t/s 3.20.571.707 I slot print_timing: id 0 | task 2413 | n_gen = 174, tg = 21.68 t/s, tg_3s = 24.36 t/s 3.21.398.977 I slot print_timing: id 3 | task 2509 | n_gen = 100, tg = 24.32 t/s, tg_3s = 24.57 t/s 3.21.811.040 I slot print_timing: id 1 | task 2183 | n_gen = 430, tg = 21.47 t/s, tg_3s = 24.34 t/s 3.23.378.716 I slot print_timing: id 2 | task 2483 | n_gen = 173, tg = 22.88 t/s, tg_3s = 24.24 t/s 3.23.591.643 I slot print_timing: id 0 | task 2413 | n_gen = 247, tg = 22.36 t/s, tg_3s = 24.17 t/s 3.24.418.224 I slot print_timing: id 3 | task 2509 | n_gen = 173, tg = 24.26 t/s, tg_3s = 24.18 t/s 3.24.830.321 I slot print_timing: id 1 | task 2183 | n_gen = 503, tg = 21.83 t/s, tg_3s = 24.18 t/s 3.26.397.941 I slot print_timing: id 2 | task 2483 | n_gen = 246, tg = 23.25 t/s, tg_3s = 24.18 t/s 3.26.603.828 I slot print_timing: id 0 | task 2413 | n_gen = 320, tg = 22.77 t/s, tg_3s = 24.23 t/s 3.27.429.008 I slot print_timing: id 3 | task 2509 | n_gen = 246, tg = 24.26 t/s, tg_3s = 24.25 t/s 3.27.841.561 I slot print_timing: id 1 | task 2183 | n_gen = 576, tg = 22.11 t/s, tg_3s = 24.24 t/s 3.29.411.557 I slot print_timing: id 2 | task 2483 | n_gen = 319, tg = 23.47 t/s, tg_3s = 24.22 t/s 3.29.617.652 I slot print_timing: id 0 | task 2413 | n_gen = 393, tg = 23.02 t/s, tg_3s = 24.22 t/s 3.30.443.791 I slot print_timing: id 3 | task 2509 | n_gen = 319, tg = 24.25 t/s, tg_3s = 24.21 t/s 3.30.857.664 I slot print_timing: id 1 | task 2183 | n_gen = 649, tg = 22.33 t/s, tg_3s = 24.20 t/s 3.32.427.658 I slot print_timing: id 2 | task 2483 | n_gen = 392, tg = 23.60 t/s, tg_3s = 24.20 t/s 3.32.633.653 I slot print_timing: id 0 | task 2413 | n_gen = 466, tg = 23.20 t/s, tg_3s = 24.20 t/s 3.33.460.278 I slot print_timing: id 3 | task 2509 | n_gen = 392, tg = 24.24 t/s, tg_3s = 24.20 t/s 3.33.625.236 I slot print_timing: id 1 | task 2183 | prompt eval time = 505.38 ms / 98 tokens ( 5.16 ms per token, 193.92 tokens per second) 3.33.625.244 I slot print_timing: id 1 | task 2183 | eval time = 31793.27 ms / 716 tokens ( 44.47 ms per token, 22.49 tokens per second) 3.33.625.244 I slot print_timing: id 1 | task 2183 | total time = 32298.64 ms / 814 tokens 3.33.625.245 I slot print_timing: id 1 | task 2183 | graphs reused = 2472 3.33.625.246 I slot print_timing: id 1 | task 2183 | graph reallocs = 0 / 0 (same size) / (changed size) 3.33.625.320 I slot release: id 1 | task 2183 | stop processing: n_tokens = 1784, truncated = 0 3.33.683.552 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.544 3.33.683.580 I slot launch_slot_: id 1 | task 2908 | processing task, is_child = 0 3.35.447.635 I slot print_timing: id 2 | task 2483 | n_gen = 456, tg = 23.23 t/s, tg_3s = 21.19 t/s 3.35.653.153 I slot print_timing: id 0 | task 2413 | n_gen = 530, tg = 22.94 t/s, tg_3s = 21.20 t/s 3.36.479.137 I slot print_timing: id 3 | task 2509 | n_gen = 456, tg = 23.76 t/s, tg_3s = 21.20 t/s 3.38.216.529 I slot print_timing: id 1 | task 2908 | n_gen = 100, tg = 24.19 t/s, tg_3s = 24.43 t/s 3.38.464.866 I slot print_timing: id 2 | task 2483 | n_gen = 529, tg = 23.36 t/s, tg_3s = 24.19 t/s 3.38.671.379 I slot print_timing: id 0 | task 2413 | n_gen = 603, tg = 23.08 t/s, tg_3s = 24.19 t/s 3.39.500.038 I slot print_timing: id 3 | task 2509 | n_gen = 529, tg = 23.81 t/s, tg_3s = 24.16 t/s 3.39.996.929 I slot print_timing: id 1 | task 2908 | prompt eval time = 439.73 ms / 64 tokens ( 6.87 ms per token, 145.54 tokens per second) 3.39.996.937 I slot print_timing: id 1 | task 2908 | eval time = 5873.61 ms / 143 tokens ( 41.36 ms per token, 24.18 tokens per second) 3.39.996.938 I slot print_timing: id 1 | task 2908 | total time = 6313.34 ms / 207 tokens 3.39.996.938 I slot print_timing: id 1 | task 2908 | graphs reused = 2613 3.39.996.939 I slot print_timing: id 1 | task 2908 | graph reallocs = 0 / 0 (same size) / (changed size) 3.39.997.010 I slot release: id 1 | task 2908 | stop processing: n_tokens = 1176, truncated = 0 3.40.055.806 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.826 3.40.055.837 I slot launch_slot_: id 1 | task 3054 | processing task, is_child = 0 3.41.477.686 I slot print_timing: id 2 | task 2483 | n_gen = 593, tg = 23.11 t/s, tg_3s = 21.24 t/s 3.41.685.231 I slot print_timing: id 0 | task 2413 | n_gen = 667, tg = 22.89 t/s, tg_3s = 21.24 t/s 3.42.513.959 I slot print_timing: id 3 | task 2509 | n_gen = 593, tg = 23.51 t/s, tg_3s = 21.23 t/s 3.44.509.355 I slot print_timing: id 2 | task 2483 | n_gen = 666, tg = 23.21 t/s, tg_3s = 24.08 t/s 3.44.591.868 I slot print_timing: id 1 | task 3054 | n_gen = 100, tg = 24.08 t/s, tg_3s = 24.32 t/s 3.44.716.105 I slot print_timing: id 0 | task 2413 | n_gen = 740, tg = 23.00 t/s, tg_3s = 24.09 t/s 3.45.006.470 I slot print_timing: id 1 | task 3054 | prompt eval time = 424.42 ms / 57 tokens ( 7.45 ms per token, 134.30 tokens per second) 3.45.006.475 I slot print_timing: id 1 | task 3054 | eval time = 4526.21 ms / 110 tokens ( 41.52 ms per token, 24.08 tokens per second) 3.45.006.477 I slot print_timing: id 1 | task 3054 | total time = 4950.62 ms / 167 tokens 3.45.006.478 I slot print_timing: id 1 | task 3054 | graphs reused = 2720 3.45.006.479 I slot print_timing: id 1 | task 3054 | graph reallocs = 0 / 0 (same size) / (changed size) 3.45.006.554 I slot release: id 1 | task 3054 | stop processing: n_tokens = 1137, truncated = 0 3.45.064.332 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.941 (> 0.100 thold), f_keep = 0.854 3.45.064.360 I slot launch_slot_: id 1 | task 3167 | processing task, is_child = 0 3.45.544.289 I slot print_timing: id 3 | task 2509 | n_gen = 657, tg = 23.25 t/s, tg_3s = 21.12 t/s 3.47.540.343 I slot print_timing: id 2 | task 2483 | n_gen = 730, tg = 23.01 t/s, tg_3s = 21.12 t/s 3.47.747.349 I slot print_timing: id 0 | task 2413 | n_gen = 804, tg = 22.84 t/s, tg_3s = 21.11 t/s 3.48.577.359 I slot print_timing: id 3 | task 2509 | n_gen = 730, tg = 23.33 t/s, tg_3s = 24.07 t/s 3.49.614.856 I slot print_timing: id 1 | task 3167 | n_gen = 100, tg = 24.05 t/s, tg_3s = 24.30 t/s 3.50.569.872 I slot print_timing: id 2 | task 2483 | n_gen = 803, tg = 23.11 t/s, tg_3s = 24.10 t/s 3.50.777.604 I slot print_timing: id 0 | task 2413 | n_gen = 877, tg = 22.94 t/s, tg_3s = 24.09 t/s 3.51.616.399 I slot print_timing: id 3 | task 2509 | n_gen = 803, tg = 23.39 t/s, tg_3s = 24.02 t/s 3.52.617.936 I slot print_timing: id 1 | task 3167 | n_gen = 172, tg = 24.02 t/s, tg_3s = 23.98 t/s 3.52.742.819 I slot print_timing: id 1 | task 3167 | prompt eval time = 434.82 ms / 61 tokens ( 7.13 ms per token, 140.29 tokens per second) 3.52.742.823 I slot print_timing: id 1 | task 3167 | eval time = 7243.63 ms / 175 tokens ( 41.63 ms per token, 24.02 tokens per second) 3.52.742.824 I slot print_timing: id 1 | task 3167 | total time = 7678.45 ms / 236 tokens 3.52.742.825 I slot print_timing: id 1 | task 3167 | graphs reused = 2893 3.52.742.826 I slot print_timing: id 1 | task 3167 | graph reallocs = 0 / 0 (same size) / (changed size) 3.52.742.897 I slot release: id 1 | task 3167 | stop processing: n_tokens = 1206, truncated = 0 3.52.801.789 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.805 3.52.801.818 I slot launch_slot_: id 1 | task 3345 | processing task, is_child = 0 3.53.574.690 I slot print_timing: id 2 | task 2483 | n_gen = 865, tg = 22.91 t/s, tg_3s = 20.63 t/s 3.53.792.142 I slot print_timing: id 0 | task 2413 | n_gen = 939, tg = 22.77 t/s, tg_3s = 20.57 t/s 3.54.627.931 I slot print_timing: id 3 | task 2509 | n_gen = 865, tg = 23.16 t/s, tg_3s = 20.59 t/s 3.56.603.936 I slot print_timing: id 2 | task 2483 | n_gen = 937, tg = 22.97 t/s, tg_3s = 23.77 t/s 3.56.813.602 I slot print_timing: id 0 | task 2413 | n_gen = 1011, tg = 22.84 t/s, tg_3s = 23.83 t/s 3.57.359.898 I slot print_timing: id 0 | task 2413 | prompt eval time = 465.44 ms / 97 tokens ( 4.80 ms per token, 208.40 tokens per second) 3.57.359.903 I slot print_timing: id 0 | task 2413 | eval time = 44768.23 ms / 1024 tokens ( 43.76 ms per token, 22.85 tokens per second) 3.57.359.904 I slot print_timing: id 0 | task 2413 | total time = 45233.67 ms / 1121 tokens 3.57.359.905 I slot print_timing: id 0 | task 2413 | graphs reused = 2988 3.57.359.906 I slot print_timing: id 0 | task 2413 | graph reallocs = 0 / 0 (same size) / (changed size) 3.57.359.983 I slot release: id 0 | task 2413 | stop processing: n_tokens = 2092, truncated = 0 3.57.403.527 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.464 3.57.436.115 I slot launch_slot_: id 0 | task 3446 | processing task, is_child = 0 3.57.794.257 I slot print_timing: id 1 | task 3345 | n_gen = 100, tg = 21.95 t/s, tg_3s = 22.17 t/s 3.57.794.474 I slot print_timing: id 3 | task 2509 | n_gen = 932, tg = 23.01 t/s, tg_3s = 21.16 t/s 3.59.629.484 I slot print_timing: id 2 | task 2483 | n_gen = 1000, tg = 22.82 t/s, tg_3s = 20.82 t/s 4.00.633.594 I slot print_timing: id 2 | task 2483 | prompt eval time = 501.13 ms / 100 tokens ( 5.01 ms per token, 199.55 tokens per second) 4.00.633.599 I slot print_timing: id 2 | task 2483 | eval time = 44772.25 ms / 1024 tokens ( 43.77 ms per token, 22.85 tokens per second) 4.00.633.600 I slot print_timing: id 2 | task 2483 | total time = 45273.38 ms / 1124 tokens 4.00.633.601 I slot print_timing: id 2 | task 2483 | graphs reused = 3053 4.00.633.602 I slot print_timing: id 2 | task 2483 | graph reallocs = 0 / 0 (same size) / (changed size) 4.00.633.667 I slot release: id 2 | task 2483 | stop processing: n_tokens = 2094, truncated = 0 4.00.692.447 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.464 4.00.721.268 I slot launch_slot_: id 2 | task 3516 | processing task, is_child = 0 4.01.103.866 I slot print_timing: id 1 | task 3345 | n_gen = 169, tg = 21.48 t/s, tg_3s = 20.85 t/s 4.01.104.005 I slot print_timing: id 3 | task 2509 | n_gen = 1001, tg = 22.84 t/s, tg_3s = 20.85 t/s 4.02.127.117 I slot print_timing: id 3 | task 2509 | prompt eval time = 514.55 ms / 114 tokens ( 4.51 ms per token, 221.55 tokens per second) 4.02.127.122 I slot print_timing: id 3 | task 2509 | eval time = 44798.71 ms / 1024 tokens ( 43.79 ms per token, 22.84 tokens per second) 4.02.127.123 I slot print_timing: id 3 | task 2509 | total time = 45313.26 ms / 1138 tokens 4.02.127.123 I slot print_timing: id 3 | task 2509 | graphs reused = 3074 4.02.127.124 I slot print_timing: id 3 | task 2509 | graph reallocs = 0 / 0 (same size) / (changed size) 4.02.127.202 I slot release: id 3 | task 2509 | stop processing: n_tokens = 2108, truncated = 0 4.02.170.040 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.461 4.02.200.372 I slot launch_slot_: id 3 | task 3542 | processing task, is_child = 0 4.02.810.007 I slot print_timing: id 0 | task 3446 | n_gen = 100, tg = 20.06 t/s, tg_3s = 20.26 t/s 4.03.345.106 I slot print_timing: id 1 | task 3345 | prompt eval time = 482.04 ms / 73 tokens ( 6.60 ms per token, 151.44 tokens per second) 4.03.345.113 I slot print_timing: id 1 | task 3345 | eval time = 10061.24 ms / 213 tokens ( 47.46 ms per token, 21.07 tokens per second) 4.03.345.114 I slot print_timing: id 1 | task 3345 | total time = 10543.28 ms / 286 tokens 4.03.345.115 I slot print_timing: id 1 | task 3345 | graphs reused = 3091 4.03.345.116 I slot print_timing: id 1 | task 3345 | graph reallocs = 0 / 0 (same size) / (changed size) 4.03.345.189 I slot release: id 1 | task 3345 | stop processing: n_tokens = 1256, truncated = 0 4.03.402.731 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.924 (> 0.100 thold), f_keep = 0.773 4.03.402.762 I slot launch_slot_: id 1 | task 3564 | processing task, is_child = 0 4.05.824.733 I slot print_timing: id 0 | task 3446 | n_gen = 163, tg = 20.38 t/s, tg_3s = 20.90 t/s 4.06.069.927 I slot print_timing: id 2 | task 3516 | n_gen = 100, tg = 20.32 t/s, tg_3s = 20.53 t/s 4.07.097.748 I slot print_timing: id 3 | task 3542 | n_gen = 100, tg = 22.04 t/s, tg_3s = 22.26 t/s 4.07.956.185 I slot print_timing: id 1 | task 3564 | n_gen = 100, tg = 24.38 t/s, tg_3s = 24.63 t/s 4.08.864.066 I slot print_timing: id 0 | task 3446 | n_gen = 237, tg = 21.48 t/s, tg_3s = 24.35 t/s 4.09.110.884 I slot print_timing: id 2 | task 3516 | n_gen = 174, tg = 21.86 t/s, tg_3s = 24.33 t/s 4.10.137.466 I slot print_timing: id 3 | task 3542 | n_gen = 174, tg = 22.97 t/s, tg_3s = 24.34 t/s 4.10.875.163 I slot print_timing: id 0 | task 3446 | prompt eval time = 438.78 ms / 79 tokens ( 5.55 ms per token, 180.04 tokens per second) 4.10.875.168 I slot print_timing: id 0 | task 3446 | eval time = 13000.25 ms / 286 tokens ( 45.61 ms per token, 21.92 tokens per second) 4.10.875.169 I slot print_timing: id 0 | task 3446 | total time = 13439.03 ms / 365 tokens 4.10.875.170 I slot print_timing: id 0 | task 3446 | graphs reused = 3258 4.10.875.171 I slot print_timing: id 0 | task 3446 | graph reallocs = 0 / 0 (same size) / (changed size) 4.10.875.246 I slot release: id 0 | task 3446 | stop processing: n_tokens = 1335, truncated = 0 4.10.918.115 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.896 (> 0.100 thold), f_keep = 0.727 4.10.918.139 I slot launch_slot_: id 0 | task 3738 | processing task, is_child = 0 4.11.331.191 I slot print_timing: id 1 | task 3564 | n_gen = 173, tg = 23.13 t/s, tg_3s = 21.63 t/s 4.12.118.604 I slot print_timing: id 2 | task 3516 | n_gen = 237, tg = 21.61 t/s, tg_3s = 20.95 t/s 4.13.144.220 I slot print_timing: id 3 | task 3542 | n_gen = 237, tg = 22.39 t/s, tg_3s = 20.95 t/s 4.13.554.323 I slot print_timing: id 2 | task 3516 | prompt eval time = 477.32 ms / 91 tokens ( 5.25 ms per token, 190.65 tokens per second) 4.13.554.331 I slot print_timing: id 2 | task 3516 | eval time = 12355.72 ms / 272 tokens ( 45.59 ms per token, 21.93 tokens per second) 4.13.554.331 I slot print_timing: id 2 | task 3516 | total time = 12833.04 ms / 363 tokens 4.13.554.332 I slot print_timing: id 2 | task 3516 | graphs reused = 3310 4.13.554.333 I slot print_timing: id 2 | task 3516 | graph reallocs = 0 / 0 (same size) / (changed size) 4.13.554.404 I slot release: id 2 | task 3516 | stop processing: n_tokens = 1332, truncated = 0 4.13.612.965 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.729 4.13.613.002 I slot launch_slot_: id 2 | task 3794 | processing task, is_child = 0 4.14.367.410 I slot print_timing: id 1 | task 3564 | n_gen = 235, tg = 22.35 t/s, tg_3s = 20.42 t/s 4.15.923.651 I slot print_timing: id 0 | task 3738 | n_gen = 100, tg = 21.94 t/s, tg_3s = 22.16 t/s 4.16.170.669 I slot print_timing: id 3 | task 3542 | n_gen = 300, tg = 22.04 t/s, tg_3s = 20.82 t/s 4.17.398.819 I slot print_timing: id 1 | task 3564 | n_gen = 309, tg = 22.81 t/s, tg_3s = 24.41 t/s 4.18.178.216 I slot print_timing: id 2 | task 3794 | n_gen = 100, tg = 24.36 t/s, tg_3s = 24.61 t/s 4.18.958.185 I slot print_timing: id 0 | task 3738 | n_gen = 174, tg = 22.92 t/s, tg_3s = 24.39 t/s 4.19.205.374 I slot print_timing: id 3 | task 3542 | n_gen = 374, tg = 22.47 t/s, tg_3s = 24.38 t/s 4.20.398.883 I slot print_timing: id 1 | task 3564 | n_gen = 382, tg = 23.09 t/s, tg_3s = 24.33 t/s 4.21.181.647 I slot print_timing: id 2 | task 3794 | n_gen = 173, tg = 24.34 t/s, tg_3s = 24.31 t/s 4.21.963.918 I slot print_timing: id 0 | task 3738 | n_gen = 247, tg = 23.31 t/s, tg_3s = 24.29 t/s 4.22.211.599 I slot print_timing: id 3 | task 3542 | n_gen = 447, tg = 22.75 t/s, tg_3s = 24.28 t/s 4.23.414.967 I slot print_timing: id 1 | task 3564 | n_gen = 455, tg = 23.26 t/s, tg_3s = 24.20 t/s 4.24.200.629 I slot print_timing: id 2 | task 3794 | n_gen = 246, tg = 24.29 t/s, tg_3s = 24.18 t/s 4.24.990.630 I slot print_timing: id 0 | task 3738 | n_gen = 320, tg = 23.49 t/s, tg_3s = 24.12 t/s 4.25.238.831 I slot print_timing: id 3 | task 3542 | n_gen = 520, tg = 22.93 t/s, tg_3s = 24.11 t/s 4.26.438.025 I slot print_timing: id 1 | task 3564 | n_gen = 528, tg = 23.38 t/s, tg_3s = 24.15 t/s 4.27.139.730 I slot print_timing: id 1 | task 3564 | prompt eval time = 493.29 ms / 80 tokens ( 6.17 ms per token, 162.18 tokens per second) 4.27.139.736 I slot print_timing: id 1 | task 3564 | eval time = 23243.67 ms / 545 tokens ( 42.73 ms per token, 23.40 tokens per second) 4.27.139.737 I slot print_timing: id 1 | task 3564 | total time = 23736.96 ms / 625 tokens 4.27.139.737 I slot print_timing: id 1 | task 3564 | graphs reused = 3623 4.27.139.738 I slot print_timing: id 1 | task 3564 | graph reallocs = 0 / 0 (same size) / (changed size) 4.27.139.810 I slot release: id 1 | task 3564 | stop processing: n_tokens = 1595, truncated = 0 4.27.198.179 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.609 4.27.198.207 I slot launch_slot_: id 1 | task 4114 | processing task, is_child = 0 4.27.588.622 I slot print_timing: id 2 | task 3794 | n_gen = 319, tg = 23.60 t/s, tg_3s = 21.55 t/s 4.28.026.932 I slot print_timing: id 0 | task 3738 | n_gen = 383, tg = 22.99 t/s, tg_3s = 20.75 t/s 4.28.274.974 I slot print_timing: id 3 | task 3542 | n_gen = 583, tg = 22.67 t/s, tg_3s = 20.75 t/s 4.30.622.038 I slot print_timing: id 2 | task 3794 | n_gen = 391, tg = 23.63 t/s, tg_3s = 23.74 t/s 4.31.033.006 I slot print_timing: id 0 | task 3738 | n_gen = 456, tg = 23.19 t/s, tg_3s = 24.28 t/s 4.31.280.309 I slot print_timing: id 3 | task 3542 | n_gen = 656, tg = 22.84 t/s, tg_3s = 24.29 t/s 4.31.774.574 I slot print_timing: id 1 | task 4114 | n_gen = 100, tg = 24.23 t/s, tg_3s = 24.48 t/s 4.33.633.320 I slot print_timing: id 2 | task 3794 | n_gen = 464, tg = 23.72 t/s, tg_3s = 24.24 t/s 4.34.046.488 I slot print_timing: id 0 | task 3738 | n_gen = 529, tg = 23.33 t/s, tg_3s = 24.22 t/s 4.34.294.946 I slot print_timing: id 3 | task 3542 | n_gen = 729, tg = 22.97 t/s, tg_3s = 24.22 t/s 4.34.794.233 I slot print_timing: id 1 | task 4114 | n_gen = 173, tg = 24.21 t/s, tg_3s = 24.17 t/s 4.36.668.311 I slot print_timing: id 2 | task 3794 | n_gen = 537, tg = 23.77 t/s, tg_3s = 24.05 t/s 4.37.083.791 I slot print_timing: id 0 | task 3738 | n_gen = 602, tg = 23.41 t/s, tg_3s = 24.03 t/s 4.37.333.116 I slot print_timing: id 3 | task 3542 | n_gen = 802, tg = 23.06 t/s, tg_3s = 24.03 t/s 4.37.830.082 I slot print_timing: id 1 | task 4114 | n_gen = 246, tg = 24.16 t/s, tg_3s = 24.05 t/s 4.37.913.092 I slot print_timing: id 1 | task 4114 | prompt eval time = 491.15 ms / 83 tokens ( 5.92 ms per token, 168.99 tokens per second) 4.37.913.101 I slot print_timing: id 1 | task 4114 | eval time = 10223.73 ms / 248 tokens ( 41.39 ms per token, 24.16 tokens per second) 4.37.913.102 I slot print_timing: id 1 | task 4114 | total time = 10714.88 ms / 331 tokens 4.37.913.103 I slot print_timing: id 1 | task 4114 | graphs reused = 3868 4.37.913.104 I slot print_timing: id 1 | task 4114 | graph reallocs = 0 / 0 (same size) / (changed size) 4.37.913.178 I slot release: id 1 | task 4114 | stop processing: n_tokens = 1301, truncated = 0 4.37.971.207 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.746 4.37.971.235 I slot launch_slot_: id 1 | task 4365 | processing task, is_child = 0 4.39.696.409 I slot print_timing: id 2 | task 3794 | n_gen = 599, tg = 23.38 t/s, tg_3s = 20.47 t/s 4.40.111.351 I slot print_timing: id 0 | task 3738 | n_gen = 664, tg = 23.10 t/s, tg_3s = 20.48 t/s 4.40.360.891 I slot print_timing: id 3 | task 3542 | n_gen = 864, tg = 22.86 t/s, tg_3s = 20.48 t/s 4.42.599.697 I slot print_timing: id 1 | task 4365 | n_gen = 100, tg = 24.05 t/s, tg_3s = 24.29 t/s 4.42.724.999 I slot print_timing: id 2 | task 3794 | n_gen = 672, tg = 23.45 t/s, tg_3s = 24.10 t/s 4.43.140.816 I slot print_timing: id 0 | task 3738 | n_gen = 737, tg = 23.20 t/s, tg_3s = 24.10 t/s 4.43.390.522 I slot print_timing: id 3 | task 3542 | n_gen = 937, tg = 22.95 t/s, tg_3s = 24.10 t/s 4.45.633.397 I slot print_timing: id 1 | task 4365 | n_gen = 173, tg = 24.06 t/s, tg_3s = 24.06 t/s 4.45.758.745 I slot print_timing: id 2 | task 3794 | n_gen = 745, tg = 23.51 t/s, tg_3s = 24.06 t/s 4.46.174.144 I slot print_timing: id 0 | task 3738 | n_gen = 810, tg = 23.27 t/s, tg_3s = 24.07 t/s 4.46.423.690 I slot print_timing: id 3 | task 3542 | n_gen = 1010, tg = 23.03 t/s, tg_3s = 24.07 t/s 4.47.013.484 I slot print_timing: id 3 | task 3542 | prompt eval time = 404.51 ms / 63 tokens ( 6.42 ms per token, 155.74 tokens per second) 4.47.013.491 I slot print_timing: id 3 | task 3542 | eval time = 44408.59 ms / 1024 tokens ( 43.41 ms per token, 23.04 tokens per second) 4.47.013.492 I slot print_timing: id 3 | task 3542 | total time = 44813.10 ms / 1087 tokens 4.47.013.493 I slot print_timing: id 3 | task 3542 | graphs reused = 4071 4.47.013.494 I slot print_timing: id 3 | task 3542 | graph reallocs = 0 / 0 (same size) / (changed size) 4.47.013.570 I slot release: id 3 | task 3542 | stop processing: n_tokens = 2056, truncated = 0 4.47.056.355 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.902 (> 0.100 thold), f_keep = 0.472 4.47.092.083 I slot launch_slot_: id 3 | task 4574 | processing task, is_child = 0 4.48.644.101 I slot print_timing: id 1 | task 4365 | n_gen = 234, tg = 22.93 t/s, tg_3s = 20.26 t/s 4.48.768.015 I slot print_timing: id 2 | task 3794 | n_gen = 806, tg = 23.23 t/s, tg_3s = 20.27 t/s 4.49.180.806 I slot print_timing: id 0 | task 3738 | n_gen = 871, tg = 23.03 t/s, tg_3s = 20.29 t/s 4.51.661.778 I slot print_timing: id 1 | task 4365 | n_gen = 307, tg = 23.22 t/s, tg_3s = 24.19 t/s 4.51.703.518 I slot print_timing: id 3 | task 4574 | n_gen = 100, tg = 24.17 t/s, tg_3s = 24.41 t/s 4.51.785.950 I slot print_timing: id 2 | task 3794 | n_gen = 879, tg = 23.31 t/s, tg_3s = 24.19 t/s 4.52.199.966 I slot print_timing: id 0 | task 3738 | n_gen = 944, tg = 23.12 t/s, tg_3s = 24.18 t/s 4.54.669.572 I slot print_timing: id 1 | task 4365 | n_gen = 379, tg = 23.35 t/s, tg_3s = 23.94 t/s 4.54.711.851 I slot print_timing: id 3 | task 4574 | n_gen = 172, tg = 24.07 t/s, tg_3s = 23.93 t/s 4.54.795.795 I slot print_timing: id 2 | task 3794 | n_gen = 951, tg = 23.35 t/s, tg_3s = 23.92 t/s 4.55.216.246 I slot print_timing: id 0 | task 3738 | n_gen = 1016, tg = 23.17 t/s, tg_3s = 23.87 t/s 4.55.550.791 I slot print_timing: id 0 | task 3738 | prompt eval time = 492.94 ms / 113 tokens ( 4.36 ms per token, 229.24 tokens per second) 4.55.550.799 I slot print_timing: id 0 | task 3738 | eval time = 44139.70 ms / 1024 tokens ( 43.15 ms per token, 23.18 tokens per second) 4.55.550.800 I slot print_timing: id 0 | task 3738 | total time = 44632.64 ms / 1137 tokens 4.55.550.801 I slot print_timing: id 0 | task 3738 | graphs reused = 4260 4.55.550.802 I slot print_timing: id 0 | task 3738 | graph reallocs = 0 / 0 (same size) / (changed size) 4.55.550.875 I slot release: id 0 | task 3738 | stop processing: n_tokens = 2107, truncated = 0 4.55.594.318 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.461 4.55.624.976 I slot launch_slot_: id 0 | task 4769 | processing task, is_child = 0 4.57.686.286 I slot print_timing: id 1 | task 4365 | n_gen = 443, tg = 23.02 t/s, tg_3s = 21.22 t/s 4.57.728.241 I slot print_timing: id 3 | task 4574 | n_gen = 236, tg = 23.22 t/s, tg_3s = 21.22 t/s 4.57.811.555 I slot print_timing: id 2 | task 3794 | n_gen = 1015, tg = 23.21 t/s, tg_3s = 21.22 t/s 4.58.187.600 I slot print_timing: id 2 | task 3794 | prompt eval time = 501.37 ms / 99 tokens ( 5.06 ms per token, 197.46 tokens per second) 4.58.187.608 I slot print_timing: id 2 | task 3794 | eval time = 44073.22 ms / 1024 tokens ( 43.08 ms per token, 23.21 tokens per second) 4.58.187.610 I slot print_timing: id 2 | task 3794 | total time = 44574.59 ms / 1123 tokens 4.58.187.610 I slot print_timing: id 2 | task 3794 | graphs reused = 4311 4.58.187.611 I slot print_timing: id 2 | task 3794 | graph reallocs = 0 / 0 (same size) / (changed size) 4.58.187.687 I slot release: id 2 | task 3794 | stop processing: n_tokens = 2093, truncated = 0 4.58.246.648 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.464 4.58.278.144 I slot launch_slot_: id 2 | task 4825 | processing task, is_child = 0 5.00.559.848 I slot print_timing: id 0 | task 4769 | n_gen = 100, tg = 21.77 t/s, tg_3s = 21.99 t/s 5.00.724.536 I slot print_timing: id 1 | task 4365 | n_gen = 506, tg = 22.71 t/s, tg_3s = 20.74 t/s 5.00.765.906 I slot print_timing: id 3 | task 4574 | n_gen = 299, tg = 22.65 t/s, tg_3s = 20.74 t/s 5.02.697.149 I slot print_timing: id 0 | task 4769 | prompt eval time = 388.05 ms / 65 tokens ( 5.97 ms per token, 167.50 tokens per second) 5.02.697.157 I slot print_timing: id 0 | task 4769 | eval time = 6684.10 ms / 152 tokens ( 44.27 ms per token, 22.59 tokens per second) 5.02.697.159 I slot print_timing: id 0 | task 4769 | total time = 7072.15 ms / 217 tokens 5.02.697.160 I slot print_timing: id 0 | task 4769 | graphs reused = 4405 5.02.697.161 I slot print_timing: id 0 | task 4769 | graph reallocs = 0 / 0 (same size) / (changed size) 5.02.697.235 I slot release: id 0 | task 4769 | stop processing: n_tokens = 1186, truncated = 0 5.02.740.778 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.819 5.02.740.805 I slot launch_slot_: id 0 | task 4925 | processing task, is_child = 0 5.03.141.804 I slot print_timing: id 2 | task 4825 | n_gen = 100, tg = 22.47 t/s, tg_3s = 22.70 t/s 5.03.763.839 I slot print_timing: id 1 | task 4365 | n_gen = 572, tg = 22.59 t/s, tg_3s = 21.72 t/s 5.03.805.282 I slot print_timing: id 3 | task 4574 | n_gen = 365, tg = 22.47 t/s, tg_3s = 21.71 t/s 5.05.827.240 I slot print_timing: id 3 | task 4574 | prompt eval time = 514.80 ms / 108 tokens ( 4.77 ms per token, 209.79 tokens per second) 5.05.827.248 I slot print_timing: id 3 | task 4574 | eval time = 18220.33 ms / 414 tokens ( 44.12 ms per token, 22.67 tokens per second) 5.05.827.249 I slot print_timing: id 3 | task 4574 | total time = 18735.14 ms / 522 tokens 5.05.827.250 I slot print_timing: id 3 | task 4574 | graphs reused = 4470 5.05.827.250 I slot print_timing: id 3 | task 4574 | graph reallocs = 0 / 0 (same size) / (changed size) 5.05.827.334 I slot release: id 3 | task 4574 | stop processing: n_tokens = 1490, truncated = 0 5.05.870.296 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.652 5.05.870.320 I slot launch_slot_: id 3 | task 4994 | processing task, is_child = 0 5.06.200.039 I slot print_timing: id 2 | task 4825 | n_gen = 167, tg = 22.24 t/s, tg_3s = 21.91 t/s 5.06.774.364 I slot print_timing: id 1 | task 4365 | n_gen = 637, tg = 22.48 t/s, tg_3s = 21.59 t/s 5.07.561.869 I slot print_timing: id 0 | task 4925 | n_gen = 100, tg = 22.40 t/s, tg_3s = 22.62 t/s 5.07.971.998 I slot print_timing: id 2 | task 4825 | prompt eval time = 457.80 ms / 71 tokens ( 6.45 ms per token, 155.09 tokens per second) 5.07.972.003 I slot print_timing: id 2 | task 4825 | eval time = 9236.04 ms / 209 tokens ( 44.40 ms per token, 22.52 tokens per second) 5.07.972.004 I slot print_timing: id 2 | task 4825 | total time = 9693.84 ms / 280 tokens 5.07.972.005 I slot print_timing: id 2 | task 4825 | graphs reused = 4510 5.07.972.006 I slot print_timing: id 2 | task 4825 | graph reallocs = 0 / 0 (same size) / (changed size) 5.07.972.086 I slot release: id 2 | task 4825 | stop processing: n_tokens = 1249, truncated = 0 5.08.030.221 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.777 5.08.030.246 I slot launch_slot_: id 2 | task 5039 | processing task, is_child = 0 5.09.810.747 I slot print_timing: id 1 | task 4365 | n_gen = 701, tg = 22.34 t/s, tg_3s = 21.08 t/s 5.10.591.422 I slot print_timing: id 0 | task 4925 | n_gen = 164, tg = 21.88 t/s, tg_3s = 21.13 t/s 5.10.756.089 I slot print_timing: id 3 | task 4994 | n_gen = 100, tg = 22.14 t/s, tg_3s = 22.36 t/s 5.11.828.998 I slot print_timing: id 0 | task 4925 | prompt eval time = 400.84 ms / 67 tokens ( 5.98 ms per token, 167.15 tokens per second) 5.11.829.007 I slot print_timing: id 0 | task 4925 | eval time = 8687.34 ms / 194 tokens ( 45.01 ms per token, 22.22 tokens per second) 5.11.829.008 I slot print_timing: id 0 | task 4925 | total time = 9088.18 ms / 261 tokens 5.11.829.009 I slot print_timing: id 0 | task 4925 | graphs reused = 4589 5.11.829.010 I slot print_timing: id 0 | task 4925 | graph reallocs = 0 / 0 (same size) / (changed size) 5.11.829.079 I slot release: id 0 | task 4925 | stop processing: n_tokens = 1231, truncated = 0 5.11.872.263 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.789 5.11.872.287 I slot launch_slot_: id 0 | task 5124 | processing task, is_child = 0 5.12.820.122 I slot print_timing: id 1 | task 4365 | n_gen = 765, tg = 22.25 t/s, tg_3s = 21.27 t/s 5.12.944.320 I slot print_timing: id 2 | task 5039 | n_gen = 100, tg = 22.24 t/s, tg_3s = 22.46 t/s 5.13.150.858 I slot print_timing: id 3 | task 4994 | prompt eval time = 413.53 ms / 69 tokens ( 5.99 ms per token, 166.86 tokens per second) 5.13.150.866 I slot print_timing: id 3 | task 4994 | eval time = 6867.00 ms / 149 tokens ( 46.40 ms per token, 21.55 tokens per second) 5.13.150.867 I slot print_timing: id 3 | task 4994 | total time = 7280.53 ms / 218 tokens 5.13.150.867 I slot print_timing: id 3 | task 4994 | graphs reused = 4609 5.13.150.868 I slot print_timing: id 3 | task 4994 | graph reallocs = 0 / 0 (same size) / (changed size) 5.13.150.943 I slot release: id 3 | task 4994 | stop processing: n_tokens = 1188, truncated = 0 5.13.193.815 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.817 5.13.193.840 I slot launch_slot_: id 3 | task 5148 | processing task, is_child = 0 5.15.845.479 I slot print_timing: id 1 | task 4365 | n_gen = 829, tg = 22.16 t/s, tg_3s = 21.15 t/s 5.15.969.305 I slot print_timing: id 2 | task 5039 | n_gen = 164, tg = 21.80 t/s, tg_3s = 21.16 t/s 5.16.792.470 I slot print_timing: id 0 | task 5124 | n_gen = 100, tg = 22.15 t/s, tg_3s = 22.37 t/s 5.17.121.769 I slot print_timing: id 2 | task 5039 | prompt eval time = 462.39 ms / 74 tokens ( 6.25 ms per token, 160.04 tokens per second) 5.17.121.777 I slot print_timing: id 2 | task 5039 | eval time = 8629.11 ms / 192 tokens ( 45.18 ms per token, 22.13 tokens per second) 5.17.121.778 I slot print_timing: id 2 | task 5039 | total time = 9091.51 ms / 266 tokens 5.17.121.779 I slot print_timing: id 2 | task 5039 | graphs reused = 4692 5.17.121.780 I slot print_timing: id 2 | task 5039 | graph reallocs = 0 / 0 (same size) / (changed size) 5.17.121.851 I slot release: id 2 | task 5039 | stop processing: n_tokens = 1236, truncated = 0 5.17.180.596 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.786 5.17.180.635 I slot launch_slot_: id 2 | task 5236 | processing task, is_child = 0 5.18.152.539 I slot print_timing: id 3 | task 5148 | n_gen = 100, tg = 22.04 t/s, tg_3s = 22.26 t/s 5.18.851.491 I slot print_timing: id 1 | task 4365 | n_gen = 892, tg = 22.07 t/s, tg_3s = 20.96 t/s 5.19.799.015 I slot print_timing: id 0 | task 5124 | n_gen = 163, tg = 21.67 t/s, tg_3s = 20.95 t/s 5.21.158.544 I slot print_timing: id 3 | task 5148 | n_gen = 173, tg = 22.94 t/s, tg_3s = 24.28 t/s 5.21.734.239 I slot print_timing: id 2 | task 5236 | n_gen = 100, tg = 24.23 t/s, tg_3s = 24.48 t/s 5.21.857.612 I slot print_timing: id 1 | task 4365 | n_gen = 965, tg = 22.23 t/s, tg_3s = 24.28 t/s 5.22.814.320 I slot print_timing: id 0 | task 5124 | n_gen = 236, tg = 22.40 t/s, tg_3s = 24.21 t/s 5.24.192.566 I slot print_timing: id 3 | task 5148 | n_gen = 246, tg = 23.26 t/s, tg_3s = 24.06 t/s 5.24.315.571 I slot print_timing: id 1 | task 4365 | prompt eval time = 511.98 ms / 94 tokens ( 5.45 ms per token, 183.60 tokens per second) 5.24.315.575 I slot print_timing: id 1 | task 4365 | eval time = 45832.34 ms / 1024 tokens ( 44.80 ms per token, 22.32 tokens per second) 5.24.315.576 I slot print_timing: id 1 | task 4365 | total time = 46344.32 ms / 1118 tokens 5.24.315.577 I slot print_timing: id 1 | task 4365 | graphs reused = 4851 5.24.315.578 I slot print_timing: id 1 | task 4365 | graph reallocs = 0 / 0 (same size) / (changed size) 5.24.315.634 I slot release: id 1 | task 4365 | stop processing: n_tokens = 2088, truncated = 0 5.24.368.151 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.465 5.24.391.019 I slot launch_slot_: id 1 | task 5401 | processing task, is_child = 0 5.24.810.594 I slot print_timing: id 2 | task 5236 | n_gen = 165, tg = 22.90 t/s, tg_3s = 21.13 t/s 5.25.843.829 I slot print_timing: id 0 | task 5124 | n_gen = 300, tg = 22.11 t/s, tg_3s = 21.13 t/s 5.26.457.580 I slot print_timing: id 0 | task 5124 | prompt eval time = 450.79 ms / 91 tokens ( 4.95 ms per token, 201.87 tokens per second) 5.26.457.587 I slot print_timing: id 0 | task 5124 | eval time = 14134.49 ms / 315 tokens ( 45.01 ms per token, 22.22 tokens per second) 5.26.457.588 I slot print_timing: id 0 | task 5124 | total time = 14585.28 ms / 406 tokens 5.26.457.589 I slot print_timing: id 0 | task 5124 | graphs reused = 4890 5.26.457.590 I slot print_timing: id 0 | task 5124 | graph reallocs = 0 / 0 (same size) / (changed size) 5.26.457.669 I slot release: id 0 | task 5124 | stop processing: n_tokens = 1376, truncated = 0 5.26.500.566 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.706 5.26.500.594 I slot launch_slot_: id 0 | task 5445 | processing task, is_child = 0 5.27.233.995 I slot print_timing: id 3 | task 5148 | n_gen = 302, tg = 22.18 t/s, tg_3s = 18.41 t/s 5.27.848.947 I slot print_timing: id 2 | task 5236 | n_gen = 230, tg = 22.45 t/s, tg_3s = 21.39 t/s 5.29.242.398 I slot print_timing: id 1 | task 5401 | n_gen = 100, tg = 22.34 t/s, tg_3s = 22.56 t/s 5.30.267.448 I slot print_timing: id 3 | task 5148 | n_gen = 376, tg = 22.58 t/s, tg_3s = 24.39 t/s 5.30.389.968 I slot print_timing: id 2 | task 5236 | prompt eval time = 467.99 ms / 75 tokens ( 6.24 ms per token, 160.26 tokens per second) 5.30.389.973 I slot print_timing: id 2 | task 5236 | eval time = 12741.33 ms / 292 tokens ( 43.78 ms per token, 22.84 tokens per second) 5.30.389.974 I slot print_timing: id 2 | task 5236 | total time = 13209.32 ms / 367 tokens 5.30.389.975 I slot print_timing: id 2 | task 5236 | graphs reused = 4974 5.30.389.976 I slot print_timing: id 2 | task 5236 | graph reallocs = 0 / 0 (same size) / (changed size) 5.30.390.044 I slot release: id 2 | task 5236 | stop processing: n_tokens = 1337, truncated = 0 5.30.448.800 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.726 5.30.448.833 I slot launch_slot_: id 2 | task 5533 | processing task, is_child = 0 5.31.381.102 I slot print_timing: id 0 | task 5445 | n_gen = 100, tg = 22.27 t/s, tg_3s = 22.49 t/s 5.32.076.574 I slot print_timing: id 1 | task 5401 | prompt eval time = 419.48 ms / 57 tokens ( 7.36 ms per token, 135.88 tokens per second) 5.32.076.579 I slot print_timing: id 1 | task 5401 | eval time = 7266.06 ms / 160 tokens ( 45.70 ms per token, 21.88 tokens per second) 5.32.076.580 I slot print_timing: id 1 | task 5401 | total time = 7685.54 ms / 217 tokens 5.32.076.581 I slot print_timing: id 1 | task 5401 | graphs reused = 5002 5.32.076.582 I slot print_timing: id 1 | task 5401 | graph reallocs = 0 / 0 (same size) / (changed size) 5.32.076.650 I slot release: id 1 | task 5401 | stop processing: n_tokens = 1186, truncated = 0 5.32.134.518 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.943 (> 0.100 thold), f_keep = 0.819 5.32.134.546 I slot launch_slot_: id 1 | task 5566 | processing task, is_child = 0 5.33.277.752 I slot print_timing: id 3 | task 5148 | n_gen = 431, tg = 21.92 t/s, tg_3s = 18.27 t/s 5.34.386.494 I slot print_timing: id 0 | task 5445 | n_gen = 164, tg = 21.88 t/s, tg_3s = 21.30 t/s 5.35.338.199 I slot print_timing: id 2 | task 5533 | n_gen = 100, tg = 22.19 t/s, tg_3s = 22.42 t/s 5.36.284.520 I slot print_timing: id 3 | task 5148 | n_gen = 504, tg = 22.23 t/s, tg_3s = 24.28 t/s 5.36.654.305 I slot print_timing: id 1 | task 5566 | n_gen = 100, tg = 24.19 t/s, tg_3s = 24.43 t/s 5.37.399.042 I slot print_timing: id 0 | task 5445 | n_gen = 237, tg = 22.55 t/s, tg_3s = 24.23 t/s 5.38.347.530 I slot print_timing: id 2 | task 5533 | n_gen = 173, tg = 23.03 t/s, tg_3s = 24.26 t/s 5.38.966.792 I slot print_timing: id 3 | task 5148 | prompt eval time = 467.02 ms / 90 tokens ( 5.19 ms per token, 192.71 tokens per second) 5.38.966.800 I slot print_timing: id 3 | task 5148 | eval time = 25305.92 ms / 569 tokens ( 44.55 ms per token, 22.45 tokens per second) 5.38.966.801 I slot print_timing: id 3 | task 5148 | total time = 25772.94 ms / 659 tokens 5.38.966.801 I slot print_timing: id 3 | task 5148 | graphs reused = 5154 5.38.966.802 I slot print_timing: id 3 | task 5148 | graph reallocs = 0 / 0 (same size) / (changed size) 5.38.966.884 I slot release: id 3 | task 5148 | stop processing: n_tokens = 1629, truncated = 0 5.39.009.308 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.596 5.39.009.334 I slot launch_slot_: id 3 | task 5725 | processing task, is_child = 0 5.39.676.924 I slot print_timing: id 1 | task 5566 | n_gen = 164, tg = 22.91 t/s, tg_3s = 21.17 t/s 5.40.422.367 I slot print_timing: id 0 | task 5445 | n_gen = 301, tg = 22.24 t/s, tg_3s = 21.17 t/s 5.41.283.119 I slot print_timing: id 1 | task 5566 | prompt eval time = 426.87 ms / 59 tokens ( 7.24 ms per token, 138.21 tokens per second) 5.41.283.126 I slot print_timing: id 1 | task 5566 | eval time = 8721.69 ms / 203 tokens ( 43.18 ms per token, 23.16 tokens per second) 5.41.283.127 I slot print_timing: id 1 | task 5566 | total time = 9148.56 ms / 262 tokens 5.41.283.128 I slot print_timing: id 1 | task 5566 | graphs reused = 5197 5.41.283.129 I slot print_timing: id 1 | task 5566 | graph reallocs = 0 / 0 (same size) / (changed size) 5.41.283.198 I slot release: id 1 | task 5566 | stop processing: n_tokens = 1232, truncated = 0 5.41.341.118 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.788 5.41.341.145 I slot launch_slot_: id 1 | task 5773 | processing task, is_child = 0 5.41.715.808 I slot print_timing: id 2 | task 5533 | n_gen = 237, tg = 21.77 t/s, tg_3s = 19.00 t/s 5.43.427.306 I slot print_timing: id 0 | task 5445 | n_gen = 364, tg = 22.01 t/s, tg_3s = 20.97 t/s 5.43.961.717 I slot print_timing: id 3 | task 5725 | n_gen = 100, tg = 22.04 t/s, tg_3s = 22.27 t/s 5.44.617.190 I slot print_timing: id 2 | task 5533 | prompt eval time = 428.58 ms / 65 tokens ( 6.59 ms per token, 151.66 tokens per second) 5.44.617.202 I slot print_timing: id 2 | task 5533 | eval time = 13739.76 ms / 306 tokens ( 45.05 ms per token, 22.20 tokens per second) 5.44.617.204 I slot print_timing: id 2 | task 5533 | total time = 14168.35 ms / 371 tokens 5.44.617.204 I slot print_timing: id 2 | task 5533 | graphs reused = 5264 5.44.617.205 I slot print_timing: id 2 | task 5533 | graph reallocs = 0 / 0 (same size) / (changed size) 5.44.617.280 I slot release: id 2 | task 5533 | stop processing: n_tokens = 1341, truncated = 0 5.44.675.382 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.941 (> 0.100 thold), f_keep = 0.724 5.44.675.407 I slot launch_slot_: id 2 | task 5845 | processing task, is_child = 0 5.46.258.895 I slot print_timing: id 1 | task 5773 | n_gen = 100, tg = 22.29 t/s, tg_3s = 22.51 t/s 5.46.463.786 I slot print_timing: id 0 | task 5445 | n_gen = 429, tg = 21.92 t/s, tg_3s = 21.41 t/s 5.46.963.076 I slot print_timing: id 3 | task 5725 | n_gen = 164, tg = 21.76 t/s, tg_3s = 21.32 t/s 5.47.658.845 I slot print_timing: id 1 | task 5773 | prompt eval time = 475.35 ms / 70 tokens ( 6.79 ms per token, 147.26 tokens per second) 5.47.658.852 I slot print_timing: id 1 | task 5773 | eval time = 5842.34 ms / 134 tokens ( 43.93 ms per token, 22.76 tokens per second) 5.47.658.853 I slot print_timing: id 1 | task 5773 | total time = 6317.69 ms / 204 tokens 5.47.658.854 I slot print_timing: id 1 | task 5773 | graphs reused = 5324 5.47.658.855 I slot print_timing: id 1 | task 5773 | graph reallocs = 0 / 0 (same size) / (changed size) 5.47.658.926 I slot release: id 1 | task 5773 | stop processing: n_tokens = 1174, truncated = 0 5.47.716.221 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.899 (> 0.100 thold), f_keep = 0.827 5.47.716.245 I slot launch_slot_: id 1 | task 5911 | processing task, is_child = 0 5.48.383.480 I slot print_timing: id 3 | task 5725 | prompt eval time = 461.21 ms / 86 tokens ( 5.36 ms per token, 186.47 tokens per second) 5.48.383.485 I slot print_timing: id 3 | task 5725 | eval time = 8912.93 ms / 187 tokens ( 47.92 ms per token, 20.87 tokens per second) 5.48.383.486 I slot print_timing: id 3 | task 5725 | total time = 9374.14 ms / 273 tokens 5.48.383.486 I slot print_timing: id 3 | task 5725 | graphs reused = 5326 5.48.383.487 I slot print_timing: id 3 | task 5725 | graph reallocs = 0 / 0 (same size) / (changed size) 5.48.383.530 I slot release: id 3 | task 5725 | stop processing: n_tokens = 1243, truncated = 0 5.48.422.403 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.781 5.48.422.420 I slot launch_slot_: id 3 | task 5918 | processing task, is_child = 0 5.49.482.326 I slot print_timing: id 0 | task 5445 | n_gen = 482, tg = 21.33 t/s, tg_3s = 17.56 t/s 5.50.020.462 I slot print_timing: id 2 | task 5845 | n_gen = 100, tg = 20.12 t/s, tg_3s = 20.33 t/s 5.51.948.649 I slot print_timing: id 2 | task 5845 | prompt eval time = 425.30 ms / 61 tokens ( 6.97 ms per token, 143.43 tokens per second) 5.51.948.656 I slot print_timing: id 2 | task 5845 | eval time = 6847.93 ms / 147 tokens ( 46.90 ms per token, 21.32 tokens per second) 5.51.948.657 I slot print_timing: id 2 | task 5845 | total time = 7273.23 ms / 208 tokens 5.51.948.657 I slot print_timing: id 2 | task 5845 | graphs reused = 5399 5.51.948.658 I slot print_timing: id 2 | task 5845 | graph reallocs = 0 / 0 (same size) / (changed size) 5.51.948.724 I slot release: id 2 | task 5845 | stop processing: n_tokens = 1178, truncated = 0 5.52.006.100 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.824 5.52.006.125 I slot launch_slot_: id 2 | task 5997 | processing task, is_child = 0 5.52.560.401 I slot print_timing: id 0 | task 5445 | n_gen = 545, tg = 21.23 t/s, tg_3s = 20.47 t/s 5.53.188.471 I slot print_timing: id 1 | task 5911 | n_gen = 100, tg = 20.08 t/s, tg_3s = 20.28 t/s 5.53.435.139 I slot print_timing: id 3 | task 5918 | n_gen = 100, tg = 21.67 t/s, tg_3s = 21.89 t/s 5.55.572.987 I slot print_timing: id 0 | task 5445 | n_gen = 618, tg = 21.55 t/s, tg_3s = 24.23 t/s 5.56.191.642 I slot print_timing: id 1 | task 5911 | n_gen = 173, tg = 21.68 t/s, tg_3s = 24.31 t/s 5.56.438.922 I slot print_timing: id 3 | task 5918 | n_gen = 173, tg = 22.71 t/s, tg_3s = 24.30 t/s 5.56.645.048 I slot print_timing: id 2 | task 5997 | n_gen = 100, tg = 24.24 t/s, tg_3s = 24.48 t/s 5.58.458.744 I slot print_timing: id 3 | task 5918 | prompt eval time = 443.50 ms / 78 tokens ( 5.69 ms per token, 175.87 tokens per second) 5.58.458.749 I slot print_timing: id 3 | task 5918 | eval time = 9592.81 ms / 222 tokens ( 43.41 ms per token, 23.04 tokens per second) 5.58.458.750 I slot print_timing: id 3 | task 5918 | total time = 10036.31 ms / 300 tokens 5.58.458.751 I slot print_timing: id 3 | task 5918 | graphs reused = 5541 5.58.458.752 I slot print_timing: id 3 | task 5918 | graph reallocs = 0 / 0 (same size) / (changed size) 5.58.458.826 I slot release: id 3 | task 5918 | stop processing: n_tokens = 1270, truncated = 0 5.58.501.628 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.765 5.58.501.656 I slot launch_slot_: id 3 | task 6144 | processing task, is_child = 0 5.58.876.438 I slot print_timing: id 0 | task 5445 | n_gen = 690, tg = 21.57 t/s, tg_3s = 21.80 t/s 5.59.204.802 I slot print_timing: id 1 | task 5911 | n_gen = 237, tg = 21.56 t/s, tg_3s = 21.24 t/s 5.59.662.137 I slot print_timing: id 2 | task 5997 | n_gen = 164, tg = 22.95 t/s, tg_3s = 21.21 t/s 6.01.893.793 I slot print_timing: id 0 | task 5445 | n_gen = 762, tg = 21.77 t/s, tg_3s = 23.86 t/s 6.02.224.098 I slot print_timing: id 1 | task 5911 | n_gen = 310, tg = 22.13 t/s, tg_3s = 24.18 t/s 6.02.677.559 I slot print_timing: id 2 | task 5997 | n_gen = 237, tg = 23.33 t/s, tg_3s = 24.21 t/s 6.03.049.013 I slot print_timing: id 3 | task 6144 | n_gen = 100, tg = 24.19 t/s, tg_3s = 24.44 t/s 6.04.909.041 I slot print_timing: id 0 | task 5445 | n_gen = 835, tg = 21.96 t/s, tg_3s = 24.21 t/s 6.05.156.822 I slot print_timing: id 0 | task 5445 | prompt eval time = 434.70 ms / 75 tokens ( 5.80 ms per token, 172.53 tokens per second) 6.05.156.829 I slot print_timing: id 0 | task 5445 | eval time = 38221.52 ms / 841 tokens ( 45.50 ms per token, 21.98 tokens per second) 6.05.156.830 I slot print_timing: id 0 | task 5445 | total time = 38656.22 ms / 916 tokens 6.05.156.831 I slot print_timing: id 0 | task 5445 | graphs reused = 5689 6.05.156.832 I slot print_timing: id 0 | task 5445 | graph reallocs = 0 / 0 (same size) / (changed size) 6.05.156.901 I slot release: id 0 | task 5445 | stop processing: n_tokens = 1886, truncated = 0 6.05.200.116 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.515 6.05.200.142 I slot launch_slot_: id 0 | task 6298 | processing task, is_child = 0 6.05.587.006 I slot print_timing: id 1 | task 5911 | n_gen = 383, tg = 22.04 t/s, tg_3s = 21.71 t/s 6.05.711.237 I slot print_timing: id 2 | task 5997 | n_gen = 301, tg = 22.81 t/s, tg_3s = 21.10 t/s 6.06.084.201 I slot print_timing: id 3 | task 6144 | n_gen = 164, tg = 22.87 t/s, tg_3s = 21.09 t/s 6.08.599.729 I slot print_timing: id 1 | task 5911 | n_gen = 455, tg = 22.32 t/s, tg_3s = 23.90 t/s 6.08.729.944 I slot print_timing: id 2 | task 5997 | n_gen = 374, tg = 23.07 t/s, tg_3s = 24.18 t/s 6.09.100.612 I slot print_timing: id 3 | task 6144 | n_gen = 237, tg = 23.27 t/s, tg_3s = 24.20 t/s 6.09.759.513 I slot print_timing: id 0 | task 6298 | n_gen = 100, tg = 24.19 t/s, tg_3s = 24.44 t/s 6.11.615.216 I slot print_timing: id 1 | task 5911 | n_gen = 528, tg = 22.56 t/s, tg_3s = 24.21 t/s 6.11.739.061 I slot print_timing: id 2 | task 5997 | n_gen = 447, tg = 23.26 t/s, tg_3s = 24.26 t/s 6.12.109.731 I slot print_timing: id 3 | task 6144 | n_gen = 310, tg = 23.49 t/s, tg_3s = 24.26 t/s 6.12.768.135 I slot print_timing: id 0 | task 6298 | n_gen = 173, tg = 24.22 t/s, tg_3s = 24.26 t/s 6.14.628.460 I slot print_timing: id 1 | task 5911 | n_gen = 601, tg = 22.75 t/s, tg_3s = 24.23 t/s 6.14.752.896 I slot print_timing: id 2 | task 5997 | n_gen = 520, tg = 23.39 t/s, tg_3s = 24.22 t/s 6.15.126.586 I slot print_timing: id 3 | task 6144 | n_gen = 383, tg = 23.62 t/s, tg_3s = 24.20 t/s 6.15.788.924 I slot print_timing: id 0 | task 6298 | n_gen = 246, tg = 24.21 t/s, tg_3s = 24.17 t/s 6.17.241.193 I slot print_timing: id 3 | task 6144 | prompt eval time = 455.13 ms / 88 tokens ( 5.17 ms per token, 193.35 tokens per second) 6.17.241.201 I slot print_timing: id 3 | task 6144 | eval time = 18284.40 ms / 434 tokens ( 42.23 ms per token, 23.68 tokens per second) 6.17.241.202 I slot print_timing: id 3 | task 6144 | total time = 18739.53 ms / 522 tokens 6.17.241.203 I slot print_timing: id 3 | task 6144 | graphs reused = 5967 6.17.241.204 I slot print_timing: id 3 | task 6144 | graph reallocs = 0 / 0 (same size) / (changed size) 6.17.241.286 I slot release: id 3 | task 6144 | stop processing: n_tokens = 1492, truncated = 0 6.17.283.850 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.952 (> 0.100 thold), f_keep = 0.651 6.17.283.874 I slot launch_slot_: id 3 | task 6582 | processing task, is_child = 0 6.17.647.192 I slot print_timing: id 1 | task 5911 | n_gen = 667, tg = 22.66 t/s, tg_3s = 21.86 t/s 6.17.772.845 I slot print_timing: id 2 | task 5997 | n_gen = 586, tg = 23.20 t/s, tg_3s = 21.85 t/s 6.18.811.538 I slot print_timing: id 0 | task 6298 | n_gen = 312, tg = 23.66 t/s, tg_3s = 21.84 t/s 6.20.676.034 I slot print_timing: id 1 | task 5911 | n_gen = 740, tg = 22.80 t/s, tg_3s = 24.10 t/s 6.20.800.578 I slot print_timing: id 2 | task 5997 | n_gen = 659, tg = 23.30 t/s, tg_3s = 24.11 t/s 6.21.751.361 I slot print_timing: id 3 | task 6582 | n_gen = 100, tg = 24.12 t/s, tg_3s = 24.37 t/s 6.21.833.526 I slot print_timing: id 0 | task 6298 | n_gen = 385, tg = 23.75 t/s, tg_3s = 24.16 t/s 6.22.288.751 I slot print_timing: id 3 | task 6582 | prompt eval time = 363.53 ms / 49 tokens ( 7.42 ms per token, 134.79 tokens per second) 6.22.288.756 I slot print_timing: id 3 | task 6582 | eval time = 4641.34 ms / 113 tokens ( 41.44 ms per token, 24.13 tokens per second) 6.22.288.757 I slot print_timing: id 3 | task 6582 | total time = 5004.87 ms / 162 tokens 6.22.288.758 I slot print_timing: id 3 | task 6582 | graphs reused = 6077 6.22.288.759 I slot print_timing: id 3 | task 6582 | graph reallocs = 0 / 0 (same size) / (changed size) 6.22.288.835 I slot release: id 3 | task 6582 | stop processing: n_tokens = 1132, truncated = 0 6.22.331.954 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.858 6.22.331.980 I slot launch_slot_: id 3 | task 6698 | processing task, is_child = 0 6.23.677.114 I slot print_timing: id 1 | task 5911 | n_gen = 804, tg = 22.67 t/s, tg_3s = 21.33 t/s 6.23.801.242 I slot print_timing: id 2 | task 5997 | n_gen = 723, tg = 23.11 t/s, tg_3s = 21.33 t/s 6.24.873.880 I slot print_timing: id 0 | task 6298 | n_gen = 450, tg = 23.38 t/s, tg_3s = 21.38 t/s 6.26.690.981 I slot print_timing: id 1 | task 5911 | n_gen = 877, tg = 22.79 t/s, tg_3s = 24.22 t/s 6.26.815.196 I slot print_timing: id 2 | task 5997 | n_gen = 796, tg = 23.21 t/s, tg_3s = 24.22 t/s 6.26.856.848 I slot print_timing: id 3 | task 6698 | n_gen = 100, tg = 24.17 t/s, tg_3s = 24.41 t/s 6.27.726.143 I slot print_timing: id 3 | task 6698 | prompt eval time = 428.42 ms / 73 tokens ( 5.87 ms per token, 170.39 tokens per second) 6.27.726.152 I slot print_timing: id 3 | task 6698 | eval time = 4965.74 ms / 121 tokens ( 41.38 ms per token, 24.17 tokens per second) 6.27.726.154 I slot print_timing: id 3 | task 6698 | total time = 5394.16 ms / 194 tokens 6.27.726.155 I slot print_timing: id 3 | task 6698 | graphs reused = 6196 6.27.726.156 I slot print_timing: id 3 | task 6698 | graph reallocs = 0 / 0 (same size) / (changed size) 6.27.726.234 I slot release: id 3 | task 6698 | stop processing: n_tokens = 1164, truncated = 0 6.27.769.284 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.834 6.27.769.309 I slot launch_slot_: id 3 | task 6822 | processing task, is_child = 0 6.28.149.957 I slot print_timing: id 0 | task 6298 | n_gen = 521, tg = 23.13 t/s, tg_3s = 21.67 t/s 6.29.720.797 I slot print_timing: id 1 | task 5911 | n_gen = 941, tg = 22.67 t/s, tg_3s = 21.12 t/s 6.29.845.361 I slot print_timing: id 2 | task 5997 | n_gen = 860, tg = 23.04 t/s, tg_3s = 21.12 t/s 6.31.183.963 I slot print_timing: id 0 | task 6298 | n_gen = 593, tg = 23.20 t/s, tg_3s = 23.73 t/s 6.31.184.140 I slot print_timing: id 1 | task 5911 | prompt eval time = 542.11 ms / 109 tokens ( 4.97 ms per token, 201.07 tokens per second) 6.31.184.146 I slot print_timing: id 1 | task 5911 | eval time = 42925.78 ms / 976 tokens ( 44.03 ms per token, 22.71 tokens per second) 6.31.184.147 I slot print_timing: id 1 | task 5911 | total time = 43467.89 ms / 1085 tokens 6.31.184.148 I slot print_timing: id 1 | task 5911 | graphs reused = 6265 6.31.184.149 I slot print_timing: id 1 | task 5911 | graph reallocs = 0 / 0 (same size) / (changed size) 6.31.184.224 I slot release: id 1 | task 5911 | stop processing: n_tokens = 2055, truncated = 0 6.31.242.707 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.473 6.31.275.989 I slot launch_slot_: id 1 | task 6897 | processing task, is_child = 0 6.32.781.838 I slot print_timing: id 3 | task 6822 | n_gen = 100, tg = 21.75 t/s, tg_3s = 21.97 t/s 6.32.864.188 I slot print_timing: id 2 | task 5997 | n_gen = 922, tg = 22.85 t/s, tg_3s = 20.54 t/s 6.34.193.829 I slot print_timing: id 0 | task 6298 | n_gen = 655, tg = 22.93 t/s, tg_3s = 20.60 t/s 6.35.782.180 I slot print_timing: id 3 | task 6822 | n_gen = 172, tg = 22.64 t/s, tg_3s = 24.00 t/s 6.35.865.782 I slot print_timing: id 1 | task 6897 | n_gen = 100, tg = 24.00 t/s, tg_3s = 24.25 t/s 6.35.865.953 I slot print_timing: id 2 | task 5997 | n_gen = 994, tg = 22.93 t/s, tg_3s = 23.99 t/s 6.37.119.307 I slot print_timing: id 2 | task 5997 | prompt eval time = 554.46 ms / 128 tokens ( 4.33 ms per token, 230.86 tokens per second) 6.37.119.314 I slot print_timing: id 2 | task 5997 | eval time = 44558.72 ms / 1024 tokens ( 43.56 ms per token, 22.96 tokens per second) 6.37.119.315 I slot print_timing: id 2 | task 5997 | total time = 45113.17 ms / 1152 tokens 6.37.119.315 I slot print_timing: id 2 | task 5997 | graphs reused = 6392 6.37.119.316 I slot print_timing: id 2 | task 5997 | graph reallocs = 0 / 0 (same size) / (changed size) 6.37.119.398 I slot release: id 2 | task 5997 | stop processing: n_tokens = 2122, truncated = 0 6.37.178.440 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.458 6.37.212.038 I slot launch_slot_: id 2 | task 7030 | processing task, is_child = 0 6.37.608.536 I slot print_timing: id 0 | task 6298 | n_gen = 727, tg = 22.73 t/s, tg_3s = 21.09 t/s 6.38.786.269 I slot print_timing: id 3 | task 6822 | n_gen = 233, tg = 21.98 t/s, tg_3s = 20.31 t/s 6.38.868.648 I slot print_timing: id 1 | task 6897 | n_gen = 161, tg = 22.45 t/s, tg_3s = 20.31 t/s 6.40.103.590 I slot print_timing: id 3 | task 6822 | prompt eval time = 461.44 ms / 89 tokens ( 5.18 ms per token, 192.88 tokens per second) 6.40.103.597 I slot print_timing: id 3 | task 6822 | eval time = 11872.83 ms / 265 tokens ( 44.97 ms per token, 22.24 tokens per second) 6.40.103.598 I slot print_timing: id 3 | task 6822 | total time = 12334.27 ms / 354 tokens 6.40.103.598 I slot print_timing: id 3 | task 6822 | graphs reused = 6448 6.40.103.599 I slot print_timing: id 3 | task 6822 | graph reallocs = 0 / 0 (same size) / (changed size) 6.40.103.676 I slot release: id 3 | task 6822 | stop processing: n_tokens = 1324, truncated = 0 6.40.146.205 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.733 6.40.146.228 I slot launch_slot_: id 3 | task 7092 | processing task, is_child = 0 6.40.650.182 I slot print_timing: id 0 | task 6298 | n_gen = 790, tg = 22.55 t/s, tg_3s = 20.71 t/s 6.41.887.920 I slot print_timing: id 1 | task 6897 | n_gen = 225, tg = 22.08 t/s, tg_3s = 21.20 t/s 6.42.176.465 I slot print_timing: id 2 | task 7030 | n_gen = 100, tg = 22.13 t/s, tg_3s = 22.36 t/s 6.43.656.773 I slot print_timing: id 0 | task 6298 | n_gen = 863, tg = 22.69 t/s, tg_3s = 24.28 t/s 6.44.688.274 I slot print_timing: id 3 | task 7092 | n_gen = 100, tg = 24.25 t/s, tg_3s = 24.50 t/s 6.44.894.175 I slot print_timing: id 1 | task 6897 | n_gen = 298, tg = 22.58 t/s, tg_3s = 24.28 t/s 6.45.183.230 I slot print_timing: id 2 | task 7030 | n_gen = 173, tg = 23.00 t/s, tg_3s = 24.28 t/s 6.46.666.566 I slot print_timing: id 0 | task 6298 | n_gen = 936, tg = 22.81 t/s, tg_3s = 24.25 t/s 6.47.703.275 I slot print_timing: id 3 | task 7092 | n_gen = 173, tg = 24.24 t/s, tg_3s = 24.21 t/s 6.47.909.904 I slot print_timing: id 1 | task 6897 | n_gen = 371, tg = 22.88 t/s, tg_3s = 24.21 t/s 6.48.199.891 I slot print_timing: id 2 | task 7030 | n_gen = 246, tg = 23.34 t/s, tg_3s = 24.20 t/s 6.48.826.324 I slot print_timing: id 2 | task 7030 | prompt eval time = 491.51 ms / 91 tokens ( 5.40 ms per token, 185.14 tokens per second) 6.48.826.328 I slot print_timing: id 2 | task 7030 | eval time = 11122.76 ms / 261 tokens ( 42.78 ms per token, 23.38 tokens per second) 6.48.826.329 I slot print_timing: id 2 | task 7030 | total time = 11614.27 ms / 352 tokens 6.48.826.330 I slot print_timing: id 2 | task 7030 | graphs reused = 6645 6.48.826.330 I slot print_timing: id 2 | task 7030 | graph reallocs = 0 / 0 (same size) / (changed size) 6.48.826.397 I slot release: id 2 | task 7030 | stop processing: n_tokens = 1321, truncated = 0 6.48.884.633 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.735 6.48.884.660 I slot launch_slot_: id 2 | task 7295 | processing task, is_child = 0 6.49.690.266 I slot print_timing: id 0 | task 6298 | n_gen = 999, tg = 22.67 t/s, tg_3s = 20.84 t/s 6.50.733.341 I slot print_timing: id 0 | task 6298 | prompt eval time = 467.09 ms / 93 tokens ( 5.02 ms per token, 199.11 tokens per second) 6.50.733.349 I slot print_timing: id 0 | task 6298 | eval time = 45066.10 ms / 1024 tokens ( 44.05 ms per token, 22.70 tokens per second) 6.50.733.350 I slot print_timing: id 0 | task 6298 | total time = 45533.19 ms / 1117 tokens 6.50.733.350 I slot print_timing: id 0 | task 6298 | graphs reused = 6677 6.50.733.351 I slot print_timing: id 0 | task 6298 | graph reallocs = 0 / 0 (same size) / (changed size) 6.50.733.424 I slot release: id 0 | task 6298 | stop processing: n_tokens = 2086, truncated = 0 6.50.733.956 I slot print_timing: id 3 | task 7092 | n_gen = 236, tg = 23.20 t/s, tg_3s = 20.79 t/s 6.50.776.713 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.465 6.50.810.785 I slot launch_slot_: id 0 | task 7332 | processing task, is_child = 0 6.51.235.703 I slot print_timing: id 1 | task 6897 | n_gen = 432, tg = 22.11 t/s, tg_3s = 18.34 t/s 6.51.947.922 I slot print_timing: id 3 | task 7092 | prompt eval time = 460.30 ms / 88 tokens ( 5.23 ms per token, 191.18 tokens per second) 6.51.947.927 I slot print_timing: id 3 | task 7092 | eval time = 11341.38 ms / 255 tokens ( 44.65 ms per token, 22.40 tokens per second) 6.51.947.928 I slot print_timing: id 3 | task 7092 | total time = 11801.68 ms / 343 tokens 6.51.947.929 I slot print_timing: id 3 | task 7092 | graphs reused = 6691 6.51.947.930 I slot print_timing: id 3 | task 7092 | graph reallocs = 0 / 0 (same size) / (changed size) 6.51.948.003 I slot release: id 3 | task 7092 | stop processing: n_tokens = 1313, truncated = 0 6.51.990.442 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.876 (> 0.100 thold), f_keep = 0.740 6.51.990.467 I slot launch_slot_: id 3 | task 7352 | processing task, is_child = 0 6.54.274.212 I slot print_timing: id 1 | task 6897 | n_gen = 493, tg = 21.83 t/s, tg_3s = 20.08 t/s 6.54.356.299 I slot print_timing: id 2 | task 7295 | n_gen = 100, tg = 19.79 t/s, tg_3s = 19.99 t/s 6.55.881.706 I slot print_timing: id 0 | task 7332 | n_gen = 100, tg = 21.68 t/s, tg_3s = 21.90 t/s 6.56.620.289 I slot print_timing: id 3 | task 7352 | n_gen = 100, tg = 24.28 t/s, tg_3s = 24.53 t/s 6.57.277.911 I slot print_timing: id 1 | task 6897 | n_gen = 566, tg = 22.13 t/s, tg_3s = 24.30 t/s 6.57.360.074 I slot print_timing: id 2 | task 7295 | n_gen = 173, tg = 21.48 t/s, tg_3s = 24.30 t/s 6.57.768.883 I slot print_timing: id 0 | task 7332 | prompt eval time = 505.10 ms / 85 tokens ( 5.94 ms per token, 168.28 tokens per second) 6.57.768.891 I slot print_timing: id 0 | task 7332 | eval time = 6452.98 ms / 146 tokens ( 44.50 ms per token, 22.47 tokens per second) 6.57.768.892 I slot print_timing: id 0 | task 7332 | total time = 6958.08 ms / 231 tokens 6.57.768.893 I slot print_timing: id 0 | task 7332 | graphs reused = 6816 6.57.768.894 I slot print_timing: id 0 | task 7332 | graph reallocs = 0 / 0 (same size) / (changed size) 6.57.768.964 I slot release: id 0 | task 7332 | stop processing: n_tokens = 1182, truncated = 0 6.57.811.822 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.944 (> 0.100 thold), f_keep = 0.821 6.57.811.846 I slot launch_slot_: id 0 | task 7483 | processing task, is_child = 0 6.59.634.918 I slot print_timing: id 3 | task 7352 | n_gen = 166, tg = 23.27 t/s, tg_3s = 21.89 t/s 7.00.293.491 I slot print_timing: id 1 | task 6897 | n_gen = 632, tg = 22.10 t/s, tg_3s = 21.89 t/s 7.00.376.430 I slot print_timing: id 2 | task 7295 | n_gen = 239, tg = 21.59 t/s, tg_3s = 21.88 t/s 7.01.773.801 I slot print_timing: id 2 | task 7295 | prompt eval time = 468.17 ms / 78 tokens ( 6.00 ms per token, 166.61 tokens per second) 7.01.773.809 I slot print_timing: id 2 | task 7295 | eval time = 12420.96 ms / 273 tokens ( 45.67 ms per token, 21.90 tokens per second) 7.01.773.810 I slot print_timing: id 2 | task 7295 | total time = 12889.13 ms / 351 tokens 7.01.773.811 I slot print_timing: id 2 | task 7295 | graphs reused = 6903 7.01.773.812 I slot print_timing: id 2 | task 7295 | graph reallocs = 0 / 0 (same size) / (changed size) 7.01.773.882 I slot release: id 2 | task 7295 | stop processing: n_tokens = 1321, truncated = 0 7.01.832.559 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.951 (> 0.100 thold), f_keep = 0.735 7.01.832.586 I slot launch_slot_: id 2 | task 7574 | processing task, is_child = 0 7.02.611.667 I slot print_timing: id 0 | task 7483 | n_gen = 100, tg = 22.38 t/s, tg_3s = 22.61 t/s 7.02.653.456 I slot print_timing: id 3 | task 7352 | n_gen = 231, tg = 22.75 t/s, tg_3s = 21.53 t/s 7.03.310.591 I slot print_timing: id 1 | task 6897 | n_gen = 697, tg = 22.05 t/s, tg_3s = 21.54 t/s 7.05.658.183 I slot print_timing: id 0 | task 7483 | n_gen = 174, tg = 23.16 t/s, tg_3s = 24.29 t/s 7.05.658.628 I slot print_timing: id 3 | task 7352 | n_gen = 304, tg = 23.10 t/s, tg_3s = 24.29 t/s 7.05.946.098 I slot print_timing: id 3 | task 7352 | prompt eval time = 552.38 ms / 137 tokens ( 4.03 ms per token, 248.02 tokens per second) 7.05.946.104 I slot print_timing: id 3 | task 7352 | eval time = 13403.24 ms / 311 tokens ( 43.24 ms per token, 23.13 tokens per second) 7.05.946.105 I slot print_timing: id 3 | task 7352 | total time = 13955.62 ms / 448 tokens 7.05.946.106 I slot print_timing: id 3 | task 7352 | graphs reused = 6991 7.05.946.106 I slot print_timing: id 3 | task 7352 | graph reallocs = 0 / 0 (same size) / (changed size) 7.05.946.180 I slot release: id 3 | task 7352 | stop processing: n_tokens = 1418, truncated = 0 7.05.988.622 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.685 7.05.988.647 I slot launch_slot_: id 3 | task 7668 | processing task, is_child = 0 7.06.353.128 I slot print_timing: id 1 | task 6897 | n_gen = 763, tg = 22.02 t/s, tg_3s = 21.69 t/s 7.06.680.502 I slot print_timing: id 2 | task 7574 | n_gen = 100, tg = 22.26 t/s, tg_3s = 22.48 t/s 7.07.300.583 I slot print_timing: id 0 | task 7483 | prompt eval time = 376.62 ms / 58 tokens ( 6.49 ms per token, 154.00 tokens per second) 7.07.300.588 I slot print_timing: id 0 | task 7483 | eval time = 9112.11 ms / 205 tokens ( 44.67 ms per token, 22.39 tokens per second) 7.07.300.589 I slot print_timing: id 0 | task 7483 | total time = 9488.72 ms / 263 tokens 7.07.300.589 I slot print_timing: id 0 | task 7483 | graphs reused = 7011 7.07.300.590 I slot print_timing: id 0 | task 7483 | graph reallocs = 0 / 0 (same size) / (changed size) 7.07.300.660 I slot release: id 0 | task 7483 | stop processing: n_tokens = 1233, truncated = 0 7.07.343.863 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.788 7.07.343.888 I slot launch_slot_: id 0 | task 7693 | processing task, is_child = 0 7.09.383.705 I slot print_timing: id 1 | task 6897 | n_gen = 828, tg = 21.97 t/s, tg_3s = 21.45 t/s 7.09.712.097 I slot print_timing: id 2 | task 7574 | n_gen = 166, tg = 22.06 t/s, tg_3s = 21.77 t/s 7.10.824.172 I slot print_timing: id 3 | task 7668 | n_gen = 100, tg = 22.55 t/s, tg_3s = 22.77 t/s 7.10.988.326 I slot print_timing: id 2 | task 7574 | prompt eval time = 399.59 ms / 50 tokens ( 7.99 ms per token, 125.13 tokens per second) 7.10.988.331 I slot print_timing: id 2 | task 7574 | eval time = 8756.14 ms / 197 tokens ( 44.67 ms per token, 22.38 tokens per second) 7.10.988.332 I slot print_timing: id 2 | task 7574 | total time = 9155.73 ms / 247 tokens 7.10.988.333 I slot print_timing: id 2 | task 7574 | graphs reused = 7090 7.10.988.334 I slot print_timing: id 2 | task 7574 | graph reallocs = 0 / 0 (same size) / (changed size) 7.10.988.405 I slot release: id 2 | task 7574 | stop processing: n_tokens = 1217, truncated = 0 7.11.046.730 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.931 (> 0.100 thold), f_keep = 0.798 7.11.046.755 I slot launch_slot_: id 2 | task 7776 | processing task, is_child = 0 7.12.207.973 I slot print_timing: id 0 | task 7693 | n_gen = 100, tg = 22.10 t/s, tg_3s = 22.33 t/s 7.12.413.745 I slot print_timing: id 1 | task 6897 | n_gen = 892, tg = 21.91 t/s, tg_3s = 21.12 t/s 7.13.399.738 I slot print_timing: id 1 | task 6897 | prompt eval time = 465.37 ms / 70 tokens ( 6.65 ms per token, 150.42 tokens per second) 7.13.399.745 I slot print_timing: id 1 | task 6897 | eval time = 41658.36 ms / 916 tokens ( 45.53 ms per token, 21.96 tokens per second) 7.13.399.746 I slot print_timing: id 1 | task 6897 | total time = 42123.73 ms / 986 tokens 7.13.399.747 I slot print_timing: id 1 | task 6897 | graphs reused = 7135 7.13.399.748 I slot print_timing: id 1 | task 6897 | graph reallocs = 0 / 0 (same size) / (changed size) 7.13.399.825 I slot release: id 1 | task 6897 | stop processing: n_tokens = 1955, truncated = 0 7.13.457.474 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.497 7.13.470.852 I slot launch_slot_: id 1 | task 7826 | processing task, is_child = 0 7.13.910.003 I slot print_timing: id 3 | task 7668 | n_gen = 156, tg = 20.73 t/s, tg_3s = 18.15 t/s 7.15.231.600 I slot print_timing: id 0 | task 7693 | n_gen = 164, tg = 21.73 t/s, tg_3s = 21.17 t/s 7.15.762.339 I slot print_timing: id 0 | task 7693 | prompt eval time = 385.39 ms / 63 tokens ( 6.12 ms per token, 163.47 tokens per second) 7.15.762.344 I slot print_timing: id 0 | task 7693 | eval time = 8033.04 ms / 177 tokens ( 45.64 ms per token, 21.91 tokens per second) 7.15.762.345 I slot print_timing: id 0 | task 7693 | total time = 8418.44 ms / 240 tokens 7.15.762.346 I slot print_timing: id 0 | task 7693 | graphs reused = 7178 7.15.762.347 I slot print_timing: id 0 | task 7693 | graph reallocs = 0 / 0 (same size) / (changed size) 7.15.762.416 I slot release: id 0 | task 7693 | stop processing: n_tokens = 1210, truncated = 0 7.15.805.023 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.802 7.15.805.047 I slot launch_slot_: id 0 | task 7875 | processing task, is_child = 0 7.16.326.107 I slot print_timing: id 2 | task 7776 | n_gen = 100, tg = 20.51 t/s, tg_3s = 20.72 t/s 7.16.946.249 I slot print_timing: id 3 | task 7668 | n_gen = 221, tg = 20.93 t/s, tg_3s = 21.41 t/s 7.18.343.663 I slot print_timing: id 1 | task 7826 | n_gen = 100, tg = 22.33 t/s, tg_3s = 22.55 t/s 7.19.326.607 I slot print_timing: id 2 | task 7776 | n_gen = 173, tg = 21.98 t/s, tg_3s = 24.33 t/s 7.19.983.701 I slot print_timing: id 3 | task 7668 | n_gen = 295, tg = 21.70 t/s, tg_3s = 24.36 t/s 7.20.310.735 I slot print_timing: id 0 | task 7875 | n_gen = 100, tg = 24.33 t/s, tg_3s = 24.58 t/s 7.21.375.149 I slot print_timing: id 1 | task 7826 | n_gen = 174, tg = 23.17 t/s, tg_3s = 24.41 t/s 7.22.359.575 I slot print_timing: id 2 | task 7776 | n_gen = 247, tg = 22.65 t/s, tg_3s = 24.40 t/s 7.23.014.984 I slot print_timing: id 3 | task 7668 | n_gen = 369, tg = 22.19 t/s, tg_3s = 24.41 t/s 7.23.055.505 I slot print_timing: id 0 | task 7875 | prompt eval time = 437.21 ms / 79 tokens ( 5.53 ms per token, 180.69 tokens per second) 7.23.055.509 I slot print_timing: id 0 | task 7875 | eval time = 6813.24 ms / 167 tokens ( 41.04 ms per token, 24.36 tokens per second) 7.23.055.510 I slot print_timing: id 0 | task 7875 | total time = 7250.45 ms / 246 tokens 7.23.055.511 I slot print_timing: id 0 | task 7875 | graphs reused = 7343 7.23.055.512 I slot print_timing: id 0 | task 7875 | graph reallocs = 0 / 0 (same size) / (changed size) 7.23.055.587 I slot release: id 0 | task 7875 | stop processing: n_tokens = 1216, truncated = 0 7.23.098.924 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.799 7.23.098.947 I slot launch_slot_: id 0 | task 8045 | processing task, is_child = 0 7.24.379.224 I slot print_timing: id 1 | task 7826 | n_gen = 238, tg = 22.64 t/s, tg_3s = 21.30 t/s 7.25.365.473 I slot print_timing: id 2 | task 7776 | n_gen = 311, tg = 22.36 t/s, tg_3s = 21.29 t/s 7.26.027.387 I slot print_timing: id 3 | task 7668 | n_gen = 433, tg = 22.05 t/s, tg_3s = 21.25 t/s 7.27.385.307 I slot print_timing: id 1 | task 7826 | n_gen = 311, tg = 23.00 t/s, tg_3s = 24.28 t/s 7.27.631.339 I slot print_timing: id 0 | task 8045 | n_gen = 100, tg = 24.23 t/s, tg_3s = 24.47 t/s 7.28.378.770 I slot print_timing: id 2 | task 7776 | n_gen = 384, tg = 22.69 t/s, tg_3s = 24.23 t/s 7.28.748.990 I slot print_timing: id 3 | task 7668 | prompt eval time = 444.72 ms / 82 tokens ( 5.42 ms per token, 184.39 tokens per second) 7.28.748.998 I slot print_timing: id 3 | task 7668 | eval time = 22315.61 ms / 499 tokens ( 44.81 ms per token, 22.32 tokens per second) 7.28.748.999 I slot print_timing: id 3 | task 7668 | total time = 22760.33 ms / 581 tokens 7.28.749.000 I slot print_timing: id 3 | task 7668 | graphs reused = 7467 7.28.749.001 I slot print_timing: id 3 | task 7668 | graph reallocs = 0 / 0 (same size) / (changed size) 7.28.749.073 I slot release: id 3 | task 7668 | stop processing: n_tokens = 1551, truncated = 0 7.28.791.334 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.626 7.28.791.366 I slot launch_slot_: id 3 | task 8175 | processing task, is_child = 0 7.29.798.181 I slot print_timing: id 1 | task 7826 | prompt eval time = 438.96 ms / 67 tokens ( 6.55 ms per token, 152.63 tokens per second) 7.29.798.187 I slot print_timing: id 1 | task 7826 | eval time = 15888.36 ms / 360 tokens ( 44.26 ms per token, 22.60 tokens per second) 7.29.798.189 I slot print_timing: id 1 | task 7826 | total time = 16327.32 ms / 427 tokens 7.29.798.190 I slot print_timing: id 1 | task 7826 | graphs reused = 7479 7.29.798.191 I slot print_timing: id 1 | task 7826 | graph reallocs = 0 / 0 (same size) / (changed size) 7.29.798.278 I slot release: id 1 | task 7826 | stop processing: n_tokens = 1395, truncated = 0 7.29.859.655 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.696 7.29.859.691 I slot launch_slot_: id 1 | task 8192 | processing task, is_child = 0 7.30.651.497 I slot print_timing: id 0 | task 8045 | n_gen = 153, tg = 21.39 t/s, tg_3s = 17.55 t/s 7.31.389.202 I slot print_timing: id 2 | task 7776 | n_gen = 437, tg = 21.92 t/s, tg_3s = 17.61 t/s 7.33.655.922 I slot print_timing: id 0 | task 8045 | n_gen = 226, tg = 22.25 t/s, tg_3s = 24.30 t/s 7.33.784.924 I slot print_timing: id 3 | task 8175 | n_gen = 100, tg = 21.92 t/s, tg_3s = 22.14 t/s 7.34.402.906 I slot print_timing: id 2 | task 7776 | n_gen = 510, tg = 22.22 t/s, tg_3s = 24.22 t/s 7.34.443.941 I slot print_timing: id 1 | task 8192 | n_gen = 100, tg = 24.24 t/s, tg_3s = 24.49 t/s 7.36.668.103 I slot print_timing: id 0 | task 8045 | n_gen = 299, tg = 22.71 t/s, tg_3s = 24.23 t/s 7.36.792.213 I slot print_timing: id 3 | task 8175 | n_gen = 173, tg = 22.86 t/s, tg_3s = 24.27 t/s 7.37.203.329 I slot print_timing: id 0 | task 8045 | prompt eval time = 446.27 ms / 84 tokens ( 5.31 ms per token, 188.23 tokens per second) 7.37.203.337 I slot print_timing: id 0 | task 8045 | eval time = 13658.10 ms / 312 tokens ( 43.92 ms per token, 22.77 tokens per second) 7.37.203.339 I slot print_timing: id 0 | task 8045 | total time = 14104.37 ms / 396 tokens 7.37.203.339 I slot print_timing: id 0 | task 8045 | graphs reused = 7642 7.37.203.340 I slot print_timing: id 0 | task 8045 | graph reallocs = 0 / 0 (same size) / (changed size) 7.37.203.409 I slot release: id 0 | task 8045 | stop processing: n_tokens = 1366, truncated = 0 7.37.246.705 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.712 7.37.246.730 I slot launch_slot_: id 0 | task 8362 | processing task, is_child = 0 7.37.605.378 I slot print_timing: id 1 | task 8192 | n_gen = 169, tg = 23.19 t/s, tg_3s = 21.83 t/s 7.37.605.504 I slot print_timing: id 2 | task 7776 | n_gen = 580, tg = 22.18 t/s, tg_3s = 21.86 t/s 7.37.944.725 I slot print_timing: id 2 | task 7776 | prompt eval time = 452.85 ms / 72 tokens ( 6.29 ms per token, 158.99 tokens per second) 7.37.944.729 I slot print_timing: id 2 | task 7776 | eval time = 26445.12 ms / 587 tokens ( 45.13 ms per token, 22.16 tokens per second) 7.37.944.730 I slot print_timing: id 2 | task 7776 | total time = 26897.96 ms / 659 tokens 7.37.944.731 I slot print_timing: id 2 | task 7776 | graphs reused = 7648 7.37.944.732 I slot print_timing: id 2 | task 7776 | graph reallocs = 0 / 0 (same size) / (changed size) 7.37.944.809 I slot release: id 2 | task 7776 | stop processing: n_tokens = 1629, truncated = 0 7.38.003.731 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.596 7.38.003.760 I slot launch_slot_: id 2 | task 8372 | processing task, is_child = 0 7.39.794.230 I slot print_timing: id 3 | task 8175 | n_gen = 228, tg = 21.56 t/s, tg_3s = 18.32 t/s 7.40.613.930 I slot print_timing: id 1 | task 8192 | n_gen = 232, tg = 22.53 t/s, tg_3s = 20.94 t/s 7.42.128.550 I slot print_timing: id 0 | task 8362 | n_gen = 100, tg = 22.30 t/s, tg_3s = 22.52 t/s 7.42.497.377 I slot print_timing: id 2 | task 8372 | n_gen = 100, tg = 24.32 t/s, tg_3s = 24.57 t/s 7.42.824.840 I slot print_timing: id 3 | task 8175 | n_gen = 302, tg = 22.20 t/s, tg_3s = 24.42 t/s 7.43.645.505 I slot print_timing: id 1 | task 8192 | n_gen = 306, tg = 22.96 t/s, tg_3s = 24.41 t/s 7.43.768.785 I slot print_timing: id 3 | task 8175 | prompt eval time = 476.43 ms / 101 tokens ( 4.72 ms per token, 212.00 tokens per second) 7.43.768.791 I slot print_timing: id 3 | task 8175 | eval time = 14500.99 ms / 325 tokens ( 44.76 ms per token, 22.34 tokens per second) 7.43.768.792 I slot print_timing: id 3 | task 8175 | total time = 14977.41 ms / 426 tokens 7.43.768.793 I slot print_timing: id 3 | task 8175 | graphs reused = 7776 7.43.768.794 I slot print_timing: id 3 | task 8175 | graph reallocs = 0 / 0 (same size) / (changed size) 7.43.768.869 I slot release: id 3 | task 8175 | stop processing: n_tokens = 1396, truncated = 0 7.43.810.786 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.696 7.43.810.809 I slot launch_slot_: id 3 | task 8506 | processing task, is_child = 0 7.45.152.032 I slot print_timing: id 0 | task 8362 | n_gen = 166, tg = 22.11 t/s, tg_3s = 21.83 t/s 7.45.520.899 I slot print_timing: id 2 | task 8372 | n_gen = 166, tg = 23.26 t/s, tg_3s = 21.83 t/s 7.45.683.941 I slot print_timing: id 1 | task 8192 | prompt eval time = 500.67 ms / 79 tokens ( 6.34 ms per token, 157.79 tokens per second) 7.45.683.945 I slot print_timing: id 1 | task 8192 | eval time = 15323.57 ms / 348 tokens ( 44.16 ms per token, 22.64 tokens per second) 7.45.683.946 I slot print_timing: id 1 | task 8192 | total time = 15824.24 ms / 427 tokens 7.45.683.947 I slot print_timing: id 1 | task 8192 | graphs reused = 7811 7.45.683.949 I slot print_timing: id 1 | task 8192 | graph reallocs = 0 / 0 (same size) / (changed size) 7.45.684.022 I slot release: id 1 | task 8192 | stop processing: n_tokens = 1397, truncated = 0 7.45.741.787 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.695 7.45.741.817 I slot launch_slot_: id 1 | task 8546 | processing task, is_child = 0 7.48.178.112 I slot print_timing: id 0 | task 8362 | n_gen = 229, tg = 21.74 t/s, tg_3s = 20.82 t/s 7.48.553.809 I slot print_timing: id 2 | task 8372 | n_gen = 229, tg = 22.52 t/s, tg_3s = 20.77 t/s 7.48.719.037 I slot print_timing: id 3 | task 8506 | n_gen = 100, tg = 21.95 t/s, tg_3s = 22.17 t/s 7.49.376.076 I slot print_timing: id 0 | task 8362 | prompt eval time = 442.03 ms / 77 tokens ( 5.74 ms per token, 174.20 tokens per second) 7.49.376.083 I slot print_timing: id 0 | task 8362 | eval time = 11687.31 ms / 258 tokens ( 45.48 ms per token, 21.99 tokens per second) 7.49.376.085 I slot print_timing: id 0 | task 8362 | total time = 12129.34 ms / 335 tokens 7.49.376.085 I slot print_timing: id 0 | task 8362 | graphs reused = 7885 7.49.376.086 I slot print_timing: id 0 | task 8362 | graph reallocs = 0 / 0 (same size) / (changed size) 7.49.376.161 I slot release: id 0 | task 8362 | stop processing: n_tokens = 1306, truncated = 0 7.49.419.042 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.879 (> 0.100 thold), f_keep = 0.743 7.49.419.066 I slot launch_slot_: id 0 | task 8626 | processing task, is_child = 0 7.50.787.574 I slot print_timing: id 1 | task 8546 | n_gen = 100, tg = 21.78 t/s, tg_3s = 22.00 t/s 7.51.568.507 I slot print_timing: id 2 | task 8372 | n_gen = 291, tg = 22.07 t/s, tg_3s = 20.57 t/s 7.51.731.489 I slot print_timing: id 3 | task 8506 | n_gen = 162, tg = 21.40 t/s, tg_3s = 20.58 t/s 7.53.818.557 I slot print_timing: id 1 | task 8546 | n_gen = 174, tg = 22.84 t/s, tg_3s = 24.41 t/s 7.54.023.069 I slot print_timing: id 0 | task 8626 | n_gen = 100, tg = 24.37 t/s, tg_3s = 24.61 t/s 7.54.597.483 I slot print_timing: id 2 | task 8372 | n_gen = 365, tg = 22.51 t/s, tg_3s = 24.43 t/s 7.54.761.907 I slot print_timing: id 3 | task 8506 | n_gen = 236, tg = 22.27 t/s, tg_3s = 24.42 t/s 7.56.854.533 I slot print_timing: id 1 | task 8546 | n_gen = 248, tg = 23.28 t/s, tg_3s = 24.37 t/s 7.57.059.923 I slot print_timing: id 0 | task 8626 | n_gen = 174, tg = 24.37 t/s, tg_3s = 24.37 t/s 7.57.266.227 I slot print_timing: id 2 | task 8372 | prompt eval time = 423.53 ms / 62 tokens ( 6.83 ms per token, 146.39 tokens per second) 7.57.266.234 I slot print_timing: id 2 | task 8372 | eval time = 18838.93 ms / 430 tokens ( 43.91 ms per token, 22.77 tokens per second) 7.57.266.235 I slot print_timing: id 2 | task 8372 | total time = 19262.46 ms / 492 tokens 7.57.266.236 I slot print_timing: id 2 | task 8372 | graphs reused = 8063 7.57.266.237 I slot print_timing: id 2 | task 8372 | graph reallocs = 0 / 0 (same size) / (changed size) 7.57.266.306 I slot release: id 2 | task 8372 | stop processing: n_tokens = 1462, truncated = 0 7.57.324.430 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.664 7.57.324.456 I slot launch_slot_: id 2 | task 8808 | processing task, is_child = 0 7.57.811.413 I slot print_timing: id 3 | task 8506 | n_gen = 300, tg = 21.98 t/s, tg_3s = 20.99 t/s 7.59.880.079 I slot print_timing: id 1 | task 8546 | n_gen = 311, tg = 22.73 t/s, tg_3s = 20.82 t/s 8.00.085.444 I slot print_timing: id 0 | task 8626 | n_gen = 237, tg = 23.31 t/s, tg_3s = 20.82 t/s 8.00.824.890 I slot print_timing: id 3 | task 8506 | n_gen = 373, tg = 22.39 t/s, tg_3s = 24.22 t/s 8.01.895.308 I slot print_timing: id 2 | task 8808 | n_gen = 100, tg = 24.24 t/s, tg_3s = 24.49 t/s 8.02.883.032 I slot print_timing: id 1 | task 8546 | n_gen = 384, tg = 23.02 t/s, tg_3s = 24.31 t/s 8.03.088.960 I slot print_timing: id 0 | task 8626 | n_gen = 310, tg = 23.54 t/s, tg_3s = 24.30 t/s 8.03.831.796 I slot print_timing: id 3 | task 8506 | n_gen = 446, tg = 22.68 t/s, tg_3s = 24.28 t/s 8.04.910.051 I slot print_timing: id 2 | task 8808 | n_gen = 173, tg = 24.23 t/s, tg_3s = 24.21 t/s 8.05.899.506 I slot print_timing: id 1 | task 8546 | n_gen = 457, tg = 23.20 t/s, tg_3s = 24.20 t/s 8.06.105.071 I slot print_timing: id 0 | task 8626 | n_gen = 383, tg = 23.66 t/s, tg_3s = 24.20 t/s 8.06.853.127 I slot print_timing: id 3 | task 8506 | n_gen = 519, tg = 22.88 t/s, tg_3s = 24.16 t/s 8.07.929.324 I slot print_timing: id 2 | task 8808 | n_gen = 246, tg = 24.21 t/s, tg_3s = 24.18 t/s 8.08.631.776 I slot print_timing: id 1 | task 8546 | prompt eval time = 500.99 ms / 91 tokens ( 5.51 ms per token, 181.64 tokens per second) 8.08.631.780 I slot print_timing: id 1 | task 8546 | eval time = 22388.96 ms / 523 tokens ( 42.89 ms per token, 23.32 tokens per second) 8.08.631.781 I slot print_timing: id 1 | task 8546 | total time = 22889.95 ms / 614 tokens 8.08.631.782 I slot print_timing: id 1 | task 8546 | graphs reused = 8322 8.08.631.783 I slot print_timing: id 1 | task 8546 | graph reallocs = 0 / 0 (same size) / (changed size) 8.08.631.869 I slot release: id 1 | task 8546 | stop processing: n_tokens = 1584, truncated = 0 8.08.690.062 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.613 8.08.690.091 I slot launch_slot_: id 1 | task 9074 | processing task, is_child = 0 8.09.144.268 I slot print_timing: id 0 | task 8626 | n_gen = 447, tg = 23.25 t/s, tg_3s = 21.06 t/s 8.09.856.640 I slot print_timing: id 3 | task 8506 | n_gen = 582, tg = 22.65 t/s, tg_3s = 20.98 t/s 8.10.969.485 I slot print_timing: id 2 | task 8808 | n_gen = 310, tg = 23.48 t/s, tg_3s = 21.05 t/s 8.11.878.627 I slot print_timing: id 2 | task 8808 | prompt eval time = 486.85 ms / 85 tokens ( 5.73 ms per token, 174.59 tokens per second) 8.11.878.635 I slot print_timing: id 2 | task 8808 | eval time = 14067.31 ms / 332 tokens ( 42.50 ms per token, 23.53 tokens per second) 8.11.878.636 I slot print_timing: id 2 | task 8808 | total time = 14554.16 ms / 417 tokens 8.11.878.637 I slot print_timing: id 2 | task 8808 | graphs reused = 8387 8.11.878.638 I slot print_timing: id 2 | task 8808 | graph reallocs = 0 / 0 (same size) / (changed size) 8.11.878.708 I slot release: id 2 | task 8808 | stop processing: n_tokens = 1387, truncated = 0 8.11.936.394 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.700 8.11.936.423 I slot launch_slot_: id 2 | task 9144 | processing task, is_child = 0 8.12.296.519 I slot print_timing: id 0 | task 8626 | n_gen = 515, tg = 23.01 t/s, tg_3s = 21.57 t/s 8.12.858.000 I slot print_timing: id 3 | task 8506 | n_gen = 645, tg = 22.48 t/s, tg_3s = 20.99 t/s 8.13.642.316 I slot print_timing: id 1 | task 9074 | n_gen = 100, tg = 22.01 t/s, tg_3s = 22.23 t/s 8.15.336.468 I slot print_timing: id 0 | task 8626 | n_gen = 587, tg = 23.09 t/s, tg_3s = 23.68 t/s 8.15.874.507 I slot print_timing: id 3 | task 8506 | n_gen = 718, tg = 22.64 t/s, tg_3s = 24.20 t/s 8.16.494.626 I slot print_timing: id 2 | task 9144 | n_gen = 100, tg = 24.13 t/s, tg_3s = 24.37 t/s 8.16.659.744 I slot print_timing: id 1 | task 9074 | n_gen = 173, tg = 22.89 t/s, tg_3s = 24.19 t/s 8.17.033.666 I slot print_timing: id 1 | task 9074 | prompt eval time = 454.29 ms / 69 tokens ( 6.58 ms per token, 151.89 tokens per second) 8.17.033.672 I slot print_timing: id 1 | task 9074 | eval time = 7889.27 ms / 182 tokens ( 43.59 ms per token, 22.94 tokens per second) 8.17.033.672 I slot print_timing: id 1 | task 9074 | total time = 8343.56 ms / 251 tokens 8.17.033.673 I slot print_timing: id 1 | task 9074 | graphs reused = 8498 8.17.033.674 I slot print_timing: id 1 | task 9074 | graph reallocs = 0 / 0 (same size) / (changed size) 8.17.033.744 I slot release: id 1 | task 9074 | stop processing: n_tokens = 1221, truncated = 0 8.17.092.440 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.795 8.17.092.467 I slot launch_slot_: id 1 | task 9260 | processing task, is_child = 0 8.18.349.883 I slot print_timing: id 0 | task 8626 | n_gen = 649, tg = 22.83 t/s, tg_3s = 20.57 t/s 8.18.888.281 I slot print_timing: id 3 | task 8506 | n_gen = 780, tg = 22.46 t/s, tg_3s = 20.57 t/s 8.19.509.745 I slot print_timing: id 2 | task 9144 | n_gen = 162, tg = 22.62 t/s, tg_3s = 20.56 t/s 8.21.371.802 I slot print_timing: id 0 | task 8626 | n_gen = 722, tg = 22.95 t/s, tg_3s = 24.16 t/s 8.21.703.233 I slot print_timing: id 1 | task 9260 | n_gen = 100, tg = 24.14 t/s, tg_3s = 24.38 t/s 8.21.910.865 I slot print_timing: id 3 | task 8506 | n_gen = 853, tg = 22.60 t/s, tg_3s = 24.15 t/s 8.22.531.482 I slot print_timing: id 2 | task 9144 | n_gen = 235, tg = 23.08 t/s, tg_3s = 24.16 t/s 8.24.395.095 I slot print_timing: id 0 | task 8626 | n_gen = 795, tg = 23.06 t/s, tg_3s = 24.15 t/s 8.24.727.347 I slot print_timing: id 1 | task 9260 | n_gen = 173, tg = 24.14 t/s, tg_3s = 24.14 t/s 8.24.935.248 I slot print_timing: id 3 | task 8506 | n_gen = 926, tg = 22.71 t/s, tg_3s = 24.14 t/s 8.25.557.360 I slot print_timing: id 2 | task 9144 | n_gen = 308, tg = 23.32 t/s, tg_3s = 24.13 t/s 8.26.223.535 I slot print_timing: id 2 | task 9144 | prompt eval time = 455.09 ms / 73 tokens ( 6.23 ms per token, 160.41 tokens per second) 8.26.223.540 I slot print_timing: id 2 | task 9144 | eval time = 13832.01 ms / 324 tokens ( 42.82 ms per token, 23.35 tokens per second) 8.26.223.541 I slot print_timing: id 2 | task 9144 | total time = 14287.10 ms / 397 tokens 8.26.223.542 I slot print_timing: id 2 | task 9144 | graphs reused = 8704 8.26.223.543 I slot print_timing: id 2 | task 9144 | graph reallocs = 0 / 0 (same size) / (changed size) 8.26.223.617 I slot release: id 2 | task 9144 | stop processing: n_tokens = 1367, truncated = 0 8.26.281.309 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.710 8.26.281.336 I slot launch_slot_: id 2 | task 9472 | processing task, is_child = 0 8.27.425.839 I slot print_timing: id 0 | task 8626 | n_gen = 858, tg = 22.87 t/s, tg_3s = 20.79 t/s 8.27.757.071 I slot print_timing: id 1 | task 9260 | n_gen = 236, tg = 23.14 t/s, tg_3s = 20.79 t/s 8.27.964.568 I slot print_timing: id 3 | task 8506 | n_gen = 989, tg = 22.58 t/s, tg_3s = 20.80 t/s 8.29.425.062 I slot print_timing: id 3 | task 8506 | prompt eval time = 398.43 ms / 62 tokens ( 6.43 ms per token, 155.61 tokens per second) 8.29.425.069 I slot print_timing: id 3 | task 8506 | eval time = 45215.82 ms / 1024 tokens ( 44.20 ms per token, 22.62 tokens per second) 8.29.425.070 I slot print_timing: id 3 | task 8506 | total time = 45614.24 ms / 1086 tokens 8.29.425.071 I slot print_timing: id 3 | task 8506 | graphs reused = 8766 8.29.425.072 I slot print_timing: id 3 | task 8506 | graph reallocs = 0 / 0 (same size) / (changed size) 8.29.425.144 I slot release: id 3 | task 8506 | stop processing: n_tokens = 2056, truncated = 0 8.29.468.189 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.472 8.29.504.230 I slot launch_slot_: id 3 | task 9540 | processing task, is_child = 0 8.30.426.312 I slot print_timing: id 0 | task 8626 | n_gen = 920, tg = 22.71 t/s, tg_3s = 20.66 t/s 8.30.797.207 I slot print_timing: id 1 | task 9260 | n_gen = 299, tg = 22.58 t/s, tg_3s = 20.72 t/s 8.31.292.838 I slot print_timing: id 2 | task 9472 | n_gen = 100, tg = 21.79 t/s, tg_3s = 22.01 t/s 8.33.427.715 I slot print_timing: id 0 | task 8626 | n_gen = 992, tg = 22.80 t/s, tg_3s = 23.99 t/s 8.33.802.078 I slot print_timing: id 1 | task 9260 | n_gen = 371, tg = 22.84 t/s, tg_3s = 23.96 t/s 8.34.094.453 I slot print_timing: id 3 | task 9540 | n_gen = 100, tg = 23.95 t/s, tg_3s = 24.19 t/s 8.34.302.600 I slot print_timing: id 2 | task 9472 | n_gen = 172, tg = 22.64 t/s, tg_3s = 23.92 t/s 8.34.761.467 I slot print_timing: id 0 | task 8626 | prompt eval time = 541.09 ms / 134 tokens ( 4.04 ms per token, 247.65 tokens per second) 8.34.761.474 I slot print_timing: id 0 | task 8626 | eval time = 44801.30 ms / 1024 tokens ( 43.79 ms per token, 22.83 tokens per second) 8.34.761.475 I slot print_timing: id 0 | task 8626 | total time = 45342.39 ms / 1158 tokens 8.34.761.476 I slot print_timing: id 0 | task 8626 | graphs reused = 8879 8.34.761.477 I slot print_timing: id 0 | task 8626 | graph reallocs = 0 / 0 (same size) / (changed size) 8.34.761.556 I slot release: id 0 | task 8626 | stop processing: n_tokens = 2128, truncated = 0 8.34.804.271 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.456 8.34.835.126 I slot launch_slot_: id 0 | task 9659 | processing task, is_child = 0 8.35.285.691 I slot print_timing: id 1 | task 9260 | prompt eval time = 509.31 ms / 100 tokens ( 5.09 ms per token, 196.34 tokens per second) 8.35.285.697 I slot print_timing: id 1 | task 9260 | eval time = 17683.91 ms / 397 tokens ( 44.66 ms per token, 22.39 tokens per second) 8.35.285.697 I slot print_timing: id 1 | task 9260 | total time = 18193.22 ms / 497 tokens 8.35.285.698 I slot print_timing: id 1 | task 9260 | graphs reused = 8880 8.35.285.698 I slot print_timing: id 1 | task 9260 | graph reallocs = 0 / 0 (same size) / (changed size) 8.35.285.742 I slot release: id 1 | task 9260 | stop processing: n_tokens = 1467, truncated = 0 8.35.339.591 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.662 8.35.339.614 I slot launch_slot_: id 1 | task 9663 | processing task, is_child = 0 8.35.959.963 I slot print_timing: id 2 | task 9472 | prompt eval time = 467.43 ms / 75 tokens ( 6.23 ms per token, 160.45 tokens per second) 8.35.959.971 I slot print_timing: id 2 | task 9472 | eval time = 9211.19 ms / 192 tokens ( 48.23 ms per token, 20.74 tokens per second) 8.35.959.972 I slot print_timing: id 2 | task 9472 | total time = 9678.62 ms / 267 tokens 8.35.959.973 I slot print_timing: id 2 | task 9472 | graphs reused = 8882 8.35.959.974 I slot print_timing: id 2 | task 9472 | graph reallocs = 0 / 0 (same size) / (changed size) 8.35.960.055 I slot release: id 2 | task 9472 | stop processing: n_tokens = 1237, truncated = 0 8.36.018.722 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.785 8.36.018.750 I slot launch_slot_: id 2 | task 9670 | processing task, is_child = 0 8.37.118.994 I slot print_timing: id 3 | task 9540 | n_gen = 144, tg = 19.98 t/s, tg_3s = 14.55 t/s 8.40.146.126 I slot print_timing: id 0 | task 9659 | n_gen = 100, tg = 20.37 t/s, tg_3s = 20.57 t/s 8.40.146.637 I slot print_timing: id 3 | task 9540 | n_gen = 218, tg = 21.30 t/s, tg_3s = 24.44 t/s 8.40.268.839 I slot print_timing: id 1 | task 9663 | n_gen = 100, tg = 22.32 t/s, tg_3s = 22.54 t/s 8.40.520.239 I slot print_timing: id 2 | task 9670 | n_gen = 100, tg = 24.36 t/s, tg_3s = 24.61 t/s 8.43.179.504 I slot print_timing: id 0 | task 9659 | n_gen = 174, tg = 21.92 t/s, tg_3s = 24.40 t/s 8.43.180.024 I slot print_timing: id 3 | task 9540 | n_gen = 292, tg = 22.01 t/s, tg_3s = 24.40 t/s 8.43.302.944 I slot print_timing: id 1 | task 9663 | n_gen = 174, tg = 23.16 t/s, tg_3s = 24.39 t/s 8.43.548.976 I slot print_timing: id 2 | task 9670 | n_gen = 174, tg = 24.39 t/s, tg_3s = 24.43 t/s 8.43.712.951 I slot print_timing: id 3 | task 9540 | prompt eval time = 456.14 ms / 86 tokens ( 5.30 ms per token, 188.54 tokens per second) 8.43.712.956 I slot print_timing: id 3 | task 9540 | eval time = 13752.56 ms / 305 tokens ( 45.24 ms per token, 22.10 tokens per second) 8.43.712.957 I slot print_timing: id 3 | task 9540 | total time = 14208.71 ms / 391 tokens 8.43.712.957 I slot print_timing: id 3 | task 9540 | graphs reused = 9056 8.43.712.958 I slot print_timing: id 3 | task 9540 | graph reallocs = 0 / 0 (same size) / (changed size) 8.43.713.040 I slot release: id 3 | task 9540 | stop processing: n_tokens = 1360, truncated = 0 8.43.755.399 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.714 8.43.755.430 I slot launch_slot_: id 3 | task 9851 | processing task, is_child = 0 8.45.273.306 I slot print_timing: id 1 | task 9663 | prompt eval time = 492.91 ms / 85 tokens ( 5.80 ms per token, 172.45 tokens per second) 8.45.273.311 I slot print_timing: id 1 | task 9663 | eval time = 9440.78 ms / 213 tokens ( 44.53 ms per token, 22.46 tokens per second) 8.45.273.312 I slot print_timing: id 1 | task 9663 | total time = 9933.68 ms / 298 tokens 8.45.273.312 I slot print_timing: id 1 | task 9663 | graphs reused = 9081 8.45.273.313 I slot print_timing: id 1 | task 9663 | graph reallocs = 0 / 0 (same size) / (changed size) 8.45.273.385 I slot release: id 1 | task 9663 | stop processing: n_tokens = 1268, truncated = 0 8.45.330.819 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.766 8.45.330.846 I slot launch_slot_: id 1 | task 9881 | processing task, is_child = 0 8.46.190.591 I slot print_timing: id 0 | task 9659 | n_gen = 228, tg = 20.82 t/s, tg_3s = 17.93 t/s 8.46.559.283 I slot print_timing: id 2 | task 9670 | n_gen = 228, tg = 22.47 t/s, tg_3s = 17.94 t/s 8.47.542.548 I slot print_timing: id 2 | task 9670 | prompt eval time = 438.05 ms / 69 tokens ( 6.35 ms per token, 157.52 tokens per second) 8.47.542.556 I slot print_timing: id 2 | task 9670 | eval time = 11085.74 ms / 252 tokens ( 44.17 ms per token, 22.64 tokens per second) 8.47.542.557 I slot print_timing: id 2 | task 9670 | total time = 11523.79 ms / 321 tokens 8.47.542.557 I slot print_timing: id 2 | task 9670 | graphs reused = 9121 8.47.542.558 I slot print_timing: id 2 | task 9670 | graph reallocs = 0 / 0 (same size) / (changed size) 8.47.542.632 I slot release: id 2 | task 9670 | stop processing: n_tokens = 1291, truncated = 0 8.47.601.060 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.752 8.47.601.089 I slot launch_slot_: id 2 | task 9927 | processing task, is_child = 0 8.49.065.762 I slot print_timing: id 3 | task 9851 | n_gen = 100, tg = 20.39 t/s, tg_3s = 20.59 t/s 8.49.229.059 I slot print_timing: id 0 | task 9659 | n_gen = 293, tg = 20.94 t/s, tg_3s = 21.39 t/s 8.50.252.160 I slot print_timing: id 1 | task 9881 | n_gen = 100, tg = 22.26 t/s, tg_3s = 22.48 t/s 8.52.095.788 I slot print_timing: id 2 | task 9927 | n_gen = 100, tg = 24.41 t/s, tg_3s = 24.66 t/s 8.52.095.966 I slot print_timing: id 3 | task 9851 | n_gen = 174, tg = 21.94 t/s, tg_3s = 24.42 t/s 8.52.259.388 I slot print_timing: id 0 | task 9659 | n_gen = 367, tg = 21.56 t/s, tg_3s = 24.42 t/s 8.53.285.520 I slot print_timing: id 1 | task 9881 | n_gen = 174, tg = 23.13 t/s, tg_3s = 24.40 t/s 8.55.100.826 I slot print_timing: id 2 | task 9927 | n_gen = 173, tg = 24.36 t/s, tg_3s = 24.29 t/s 8.55.100.997 I slot print_timing: id 3 | task 9851 | n_gen = 247, tg = 22.59 t/s, tg_3s = 24.29 t/s 8.55.264.910 I slot print_timing: id 0 | task 9659 | n_gen = 440, tg = 21.97 t/s, tg_3s = 24.29 t/s 8.55.717.261 I slot print_timing: id 3 | task 9851 | prompt eval time = 454.68 ms / 84 tokens ( 5.41 ms per token, 184.75 tokens per second) 8.55.717.269 I slot print_timing: id 3 | task 9851 | eval time = 11507.14 ms / 262 tokens ( 44.09 ms per token, 22.68 tokens per second) 8.55.717.270 I slot print_timing: id 3 | task 9851 | total time = 11961.82 ms / 346 tokens 8.55.717.271 I slot print_timing: id 3 | task 9851 | graphs reused = 9306 8.55.717.271 I slot print_timing: id 3 | task 9851 | graph reallocs = 0 / 0 (same size) / (changed size) 8.55.717.344 I slot release: id 3 | task 9851 | stop processing: n_tokens = 1316, truncated = 0 8.55.760.111 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.738 8.55.760.136 I slot launch_slot_: id 3 | task 10118 | processing task, is_child = 0 8.56.325.613 I slot print_timing: id 1 | task 9881 | n_gen = 240, tg = 22.72 t/s, tg_3s = 21.71 t/s 8.56.325.700 I slot print_timing: id 2 | task 9927 | prompt eval time = 439.00 ms / 66 tokens ( 6.65 ms per token, 150.34 tokens per second) 8.56.325.702 I slot print_timing: id 2 | task 9927 | eval time = 8285.59 ms / 195 tokens ( 42.71 ms per token, 23.41 tokens per second) 8.56.325.702 I slot print_timing: id 2 | task 9927 | total time = 8724.60 ms / 261 tokens 8.56.325.703 I slot print_timing: id 2 | task 9927 | graphs reused = 9309 8.56.325.703 I slot print_timing: id 2 | task 9927 | graph reallocs = 0 / 0 (same size) / (changed size) 8.56.325.752 I slot release: id 2 | task 9927 | stop processing: n_tokens = 1231, truncated = 0 8.56.379.877 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.882 (> 0.100 thold), f_keep = 0.789 8.56.379.901 I slot launch_slot_: id 2 | task 10126 | processing task, is_child = 0 8.58.294.266 I slot print_timing: id 0 | task 9659 | n_gen = 494, tg = 21.43 t/s, tg_3s = 17.83 t/s 8.59.361.914 I slot print_timing: id 1 | task 9881 | n_gen = 302, tg = 22.20 t/s, tg_3s = 20.42 t/s 9.00.719.393 I slot print_timing: id 3 | task 10118 | n_gen = 100, tg = 21.72 t/s, tg_3s = 21.94 t/s 9.01.007.413 I slot print_timing: id 2 | task 10126 | n_gen = 100, tg = 24.27 t/s, tg_3s = 24.51 t/s 9.01.295.682 I slot print_timing: id 0 | task 9659 | n_gen = 567, tg = 21.76 t/s, tg_3s = 24.32 t/s 9.02.367.233 I slot print_timing: id 1 | task 9881 | n_gen = 375, tg = 22.58 t/s, tg_3s = 24.29 t/s 9.03.731.871 I slot print_timing: id 3 | task 10118 | n_gen = 173, tg = 22.72 t/s, tg_3s = 24.23 t/s 9.04.021.010 I slot print_timing: id 2 | task 10126 | n_gen = 173, tg = 24.25 t/s, tg_3s = 24.22 t/s 9.04.309.757 I slot print_timing: id 0 | task 9659 | n_gen = 640, tg = 22.02 t/s, tg_3s = 24.22 t/s 9.05.383.877 I slot print_timing: id 1 | task 9881 | n_gen = 448, tg = 22.83 t/s, tg_3s = 24.20 t/s 9.05.838.390 I slot print_timing: id 3 | task 10118 | prompt eval time = 400.37 ms / 65 tokens ( 6.16 ms per token, 162.35 tokens per second) 9.05.838.400 I slot print_timing: id 3 | task 10118 | eval time = 9677.88 ms / 224 tokens ( 43.40 ms per token, 23.04 tokens per second) 9.05.838.401 I slot print_timing: id 3 | task 10118 | total time = 10078.24 ms / 289 tokens 9.05.838.402 I slot print_timing: id 3 | task 10118 | graphs reused = 9523 9.05.838.403 I slot print_timing: id 3 | task 10118 | graph reallocs = 0 / 0 (same size) / (changed size) 9.05.838.468 I slot release: id 3 | task 10118 | stop processing: n_tokens = 1259, truncated = 0 9.05.880.834 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.771 9.05.880.860 I slot launch_slot_: id 3 | task 10346 | processing task, is_child = 0 9.07.043.700 I slot print_timing: id 2 | task 10126 | n_gen = 237, tg = 23.33 t/s, tg_3s = 21.17 t/s 9.07.332.000 I slot print_timing: id 0 | task 9659 | n_gen = 704, tg = 21.94 t/s, tg_3s = 21.18 t/s 9.08.407.352 I slot print_timing: id 1 | task 9881 | n_gen = 512, tg = 22.61 t/s, tg_3s = 21.17 t/s 9.10.066.013 I slot print_timing: id 2 | task 10126 | n_gen = 310, tg = 23.52 t/s, tg_3s = 24.15 t/s 9.10.355.110 I slot print_timing: id 0 | task 9659 | n_gen = 777, tg = 22.13 t/s, tg_3s = 24.15 t/s 9.10.438.364 I slot print_timing: id 3 | task 10346 | n_gen = 100, tg = 24.09 t/s, tg_3s = 24.34 t/s 9.11.430.484 I slot print_timing: id 1 | task 9881 | n_gen = 585, tg = 22.79 t/s, tg_3s = 24.15 t/s 9.13.086.059 I slot print_timing: id 2 | task 10126 | n_gen = 383, tg = 23.64 t/s, tg_3s = 24.17 t/s 9.13.375.827 I slot print_timing: id 0 | task 9659 | n_gen = 850, tg = 22.29 t/s, tg_3s = 24.17 t/s 9.13.459.140 I slot print_timing: id 3 | task 10346 | n_gen = 173, tg = 24.12 t/s, tg_3s = 24.17 t/s 9.14.454.389 I slot print_timing: id 1 | task 9881 | n_gen = 658, tg = 22.93 t/s, tg_3s = 24.14 t/s 9.16.110.552 I slot print_timing: id 2 | task 10126 | n_gen = 456, tg = 23.72 t/s, tg_3s = 24.14 t/s 9.16.400.739 I slot print_timing: id 0 | task 9659 | n_gen = 923, tg = 22.42 t/s, tg_3s = 24.13 t/s 9.16.484.063 I slot print_timing: id 3 | task 10346 | n_gen = 246, tg = 24.13 t/s, tg_3s = 24.13 t/s 9.17.480.672 I slot print_timing: id 1 | task 9881 | n_gen = 731, tg = 23.05 t/s, tg_3s = 24.12 t/s 9.18.394.910 I slot print_timing: id 0 | task 9659 | prompt eval time = 450.48 ms / 88 tokens ( 5.12 ms per token, 195.35 tokens per second) 9.18.394.919 I slot print_timing: id 0 | task 9659 | eval time = 43109.29 ms / 971 tokens ( 44.44 ms per token, 22.50 tokens per second) 9.18.394.920 I slot print_timing: id 0 | task 9659 | total time = 43559.77 ms / 1059 tokens 9.18.394.921 I slot print_timing: id 0 | task 9659 | graphs reused = 9812 9.18.394.922 I slot print_timing: id 0 | task 9659 | graph reallocs = 0 / 0 (same size) / (changed size) 9.18.395.000 I slot release: id 0 | task 9659 | stop processing: n_tokens = 2028, truncated = 0 9.18.438.046 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.479 9.18.472.647 I slot launch_slot_: id 0 | task 10641 | processing task, is_child = 0 9.19.128.622 I slot print_timing: id 2 | task 10126 | n_gen = 519, tg = 23.33 t/s, tg_3s = 20.87 t/s 9.19.504.863 I slot print_timing: id 3 | task 10346 | n_gen = 309, tg = 23.38 t/s, tg_3s = 20.86 t/s 9.20.496.589 I slot print_timing: id 1 | task 9881 | n_gen = 794, tg = 22.86 t/s, tg_3s = 20.89 t/s 9.22.150.923 I slot print_timing: id 2 | task 10126 | n_gen = 592, tg = 23.43 t/s, tg_3s = 24.15 t/s 9.22.522.681 I slot print_timing: id 3 | task 10346 | n_gen = 382, tg = 23.53 t/s, tg_3s = 24.19 t/s 9.23.021.447 I slot print_timing: id 0 | task 10641 | n_gen = 100, tg = 24.14 t/s, tg_3s = 24.38 t/s 9.23.521.731 I slot print_timing: id 1 | task 9881 | n_gen = 867, tg = 22.96 t/s, tg_3s = 24.13 t/s 9.25.179.216 I slot print_timing: id 2 | task 10126 | n_gen = 665, tg = 23.50 t/s, tg_3s = 24.11 t/s 9.25.553.277 I slot print_timing: id 3 | task 10346 | n_gen = 455, tg = 23.62 t/s, tg_3s = 24.09 t/s 9.26.049.127 I slot print_timing: id 0 | task 10641 | n_gen = 173, tg = 24.13 t/s, tg_3s = 24.11 t/s 9.26.338.976 I slot print_timing: id 3 | task 10346 | prompt eval time = 448.34 ms / 83 tokens ( 5.40 ms per token, 185.13 tokens per second) 9.26.338.983 I slot print_timing: id 3 | task 10346 | eval time = 20009.77 ms / 474 tokens ( 42.30 ms per token, 23.64 tokens per second) 9.26.338.984 I slot print_timing: id 3 | task 10346 | total time = 20458.11 ms / 557 tokens 9.26.338.985 I slot print_timing: id 3 | task 10346 | graphs reused = 9991 9.26.338.985 I slot print_timing: id 3 | task 10346 | graph reallocs = 0 / 0 (same size) / (changed size) 9.26.339.055 I slot release: id 3 | task 10346 | stop processing: n_tokens = 1527, truncated = 0 9.26.380.988 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.931 (> 0.100 thold), f_keep = 0.636 9.26.381.010 I slot launch_slot_: id 3 | task 10824 | processing task, is_child = 0 9.26.734.887 I slot print_timing: id 1 | task 9881 | n_gen = 937, tg = 22.87 t/s, tg_3s = 21.79 t/s 9.28.185.795 I slot print_timing: id 2 | task 10126 | n_gen = 729, tg = 23.29 t/s, tg_3s = 21.29 t/s 9.28.765.421 I slot print_timing: id 0 | task 10641 | prompt eval time = 447.68 ms / 84 tokens ( 5.33 ms per token, 187.63 tokens per second) 9.28.765.426 I slot print_timing: id 0 | task 10641 | eval time = 9845.08 ms / 230 tokens ( 42.99 ms per token, 23.26 tokens per second) 9.28.765.427 I slot print_timing: id 0 | task 10641 | total time = 10292.76 ms / 314 tokens 9.28.765.428 I slot print_timing: id 0 | task 10641 | graphs reused = 10037 9.28.765.429 I slot print_timing: id 0 | task 10641 | graph reallocs = 0 / 0 (same size) / (changed size) 9.28.765.515 I slot release: id 0 | task 10641 | stop processing: n_tokens = 1282, truncated = 0 9.28.809.150 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.757 9.28.809.174 I slot launch_slot_: id 0 | task 10875 | processing task, is_child = 0 9.29.748.728 I slot print_timing: id 1 | task 9881 | n_gen = 1000, tg = 22.73 t/s, tg_3s = 20.90 t/s 9.30.760.390 I slot print_timing: id 1 | task 9881 | prompt eval time = 473.72 ms / 74 tokens ( 6.40 ms per token, 156.21 tokens per second) 9.30.760.399 I slot print_timing: id 1 | task 9881 | eval time = 44955.82 ms / 1024 tokens ( 43.95 ms per token, 22.76 tokens per second) 9.30.760.400 I slot print_timing: id 1 | task 9881 | total time = 45429.54 ms / 1098 tokens 9.30.760.400 I slot print_timing: id 1 | task 9881 | graphs reused = 10072 9.30.760.401 I slot print_timing: id 1 | task 9881 | graph reallocs = 0 / 0 (same size) / (changed size) 9.30.760.475 I slot release: id 1 | task 9881 | stop processing: n_tokens = 2068, truncated = 0 9.30.818.333 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.470 9.30.854.487 I slot launch_slot_: id 1 | task 10915 | processing task, is_child = 0 9.31.279.465 I slot print_timing: id 2 | task 10126 | n_gen = 785, tg = 22.82 t/s, tg_3s = 18.10 t/s 9.31.700.377 I slot print_timing: id 3 | task 10824 | n_gen = 100, tg = 20.27 t/s, tg_3s = 20.47 t/s 9.33.742.080 I slot print_timing: id 0 | task 10875 | n_gen = 100, tg = 22.06 t/s, tg_3s = 22.28 t/s 9.34.317.793 I slot print_timing: id 2 | task 10126 | n_gen = 859, tg = 22.95 t/s, tg_3s = 24.36 t/s 9.34.728.768 I slot print_timing: id 3 | task 10824 | n_gen = 174, tg = 21.86 t/s, tg_3s = 24.44 t/s 9.35.345.954 I slot print_timing: id 1 | task 10915 | n_gen = 100, tg = 24.34 t/s, tg_3s = 24.59 t/s 9.36.293.625 I slot print_timing: id 3 | task 10824 | prompt eval time = 434.31 ms / 72 tokens ( 6.03 ms per token, 165.78 tokens per second) 9.36.293.631 I slot print_timing: id 3 | task 10824 | eval time = 9478.29 ms / 212 tokens ( 44.92 ms per token, 22.26 tokens per second) 9.36.293.632 I slot print_timing: id 3 | task 10824 | total time = 9912.60 ms / 284 tokens 9.36.293.633 I slot print_timing: id 3 | task 10824 | graphs reused = 10193 9.36.293.634 I slot print_timing: id 3 | task 10824 | graph reallocs = 0 / 0 (same size) / (changed size) 9.36.293.708 I slot release: id 3 | task 10824 | stop processing: n_tokens = 1254, truncated = 0 9.36.336.267 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.774 9.36.336.290 I slot launch_slot_: id 3 | task 11041 | processing task, is_child = 0 9.36.809.696 I slot print_timing: id 0 | task 10875 | n_gen = 165, tg = 21.71 t/s, tg_3s = 21.19 t/s 9.37.340.917 I slot print_timing: id 2 | task 10126 | n_gen = 923, tg = 22.81 t/s, tg_3s = 21.17 t/s 9.37.422.749 I slot print_timing: id 0 | task 10875 | prompt eval time = 445.00 ms / 83 tokens ( 5.36 ms per token, 186.52 tokens per second) 9.37.422.753 I slot print_timing: id 0 | task 10875 | eval time = 8168.56 ms / 180 tokens ( 45.63 ms per token, 21.91 tokens per second) 9.37.422.753 I slot print_timing: id 0 | task 10875 | total time = 8613.57 ms / 263 tokens 9.37.422.754 I slot print_timing: id 0 | task 10875 | graphs reused = 10207 9.37.422.755 I slot print_timing: id 0 | task 10875 | graph reallocs = 0 / 0 (same size) / (changed size) 9.37.422.805 I slot release: id 0 | task 10875 | stop processing: n_tokens = 1233, truncated = 0 9.37.463.402 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.788 9.37.463.425 I slot launch_slot_: id 0 | task 11060 | processing task, is_child = 0 9.38.258.936 I slot print_timing: id 1 | task 10915 | prompt eval time = 424.79 ms / 56 tokens ( 7.59 ms per token, 131.83 tokens per second) 9.38.258.944 I slot print_timing: id 1 | task 10915 | eval time = 6979.64 ms / 154 tokens ( 45.62 ms per token, 21.92 tokens per second) 9.38.258.945 I slot print_timing: id 1 | task 10915 | total time = 7404.43 ms / 210 tokens 9.38.258.946 I slot print_timing: id 1 | task 10915 | graphs reused = 10217 9.38.258.947 I slot print_timing: id 1 | task 10915 | graph reallocs = 0 / 0 (same size) / (changed size) 9.38.259.049 I slot release: id 1 | task 10915 | stop processing: n_tokens = 1179, truncated = 0 9.38.324.186 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.892 (> 0.100 thold), f_keep = 0.824 9.38.324.217 I slot launch_slot_: id 1 | task 11074 | processing task, is_child = 0 9.40.347.818 I slot print_timing: id 2 | task 10126 | n_gen = 976, tg = 22.46 t/s, tg_3s = 17.63 t/s 9.41.721.942 I slot print_timing: id 3 | task 11041 | n_gen = 100, tg = 20.15 t/s, tg_3s = 20.36 t/s 9.42.346.186 I slot print_timing: id 2 | task 10126 | prompt eval time = 547.99 ms / 130 tokens ( 4.22 ms per token, 237.23 tokens per second) 9.42.346.191 I slot print_timing: id 2 | task 10126 | eval time = 45418.28 ms / 1024 tokens ( 44.40 ms per token, 22.52 tokens per second) 9.42.346.193 I slot print_timing: id 2 | task 10126 | total time = 45966.28 ms / 1154 tokens 9.42.346.194 I slot print_timing: id 2 | task 10126 | graphs reused = 10298 9.42.346.194 I slot print_timing: id 2 | task 10126 | graph reallocs = 0 / 0 (same size) / (changed size) 9.42.346.269 I slot release: id 2 | task 10126 | stop processing: n_tokens = 2124, truncated = 0 9.42.404.060 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.457 9.42.438.543 I slot launch_slot_: id 2 | task 11161 | processing task, is_child = 0 9.42.913.269 I slot print_timing: id 0 | task 11060 | n_gen = 100, tg = 19.54 t/s, tg_3s = 19.74 t/s 9.43.453.080 I slot print_timing: id 1 | task 11074 | n_gen = 100, tg = 21.65 t/s, tg_3s = 21.87 t/s 9.44.724.985 I slot print_timing: id 3 | task 11041 | n_gen = 162, tg = 20.34 t/s, tg_3s = 20.65 t/s 9.45.948.823 I slot print_timing: id 0 | task 11060 | n_gen = 174, tg = 21.35 t/s, tg_3s = 24.38 t/s 9.46.478.767 I slot print_timing: id 1 | task 11074 | n_gen = 174, tg = 22.77 t/s, tg_3s = 24.46 t/s 9.46.974.420 I slot print_timing: id 2 | task 11161 | n_gen = 100, tg = 24.38 t/s, tg_3s = 24.62 t/s 9.47.752.475 I slot print_timing: id 1 | task 11074 | prompt eval time = 555.88 ms / 117 tokens ( 4.75 ms per token, 210.48 tokens per second) 9.47.752.482 I slot print_timing: id 1 | task 11074 | eval time = 8872.37 ms / 205 tokens ( 43.49 ms per token, 22.99 tokens per second) 9.47.752.483 I slot print_timing: id 1 | task 11074 | total time = 9428.25 ms / 322 tokens 9.47.752.484 I slot print_timing: id 1 | task 11074 | graphs reused = 10413 9.47.752.485 I slot print_timing: id 1 | task 11074 | graph reallocs = 0 / 0 (same size) / (changed size) 9.47.752.564 I slot release: id 1 | task 11074 | stop processing: n_tokens = 1292, truncated = 0 9.47.752.906 I slot print_timing: id 3 | task 11041 | n_gen = 236, tg = 21.48 t/s, tg_3s = 24.44 t/s 9.47.809.878 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.752 9.47.809.906 I slot launch_slot_: id 1 | task 11283 | processing task, is_child = 0 9.48.953.837 I slot print_timing: id 0 | task 11060 | n_gen = 237, tg = 21.25 t/s, tg_3s = 20.96 t/s 9.49.981.244 I slot print_timing: id 2 | task 11161 | n_gen = 163, tg = 22.92 t/s, tg_3s = 20.95 t/s 9.50.762.243 I slot print_timing: id 3 | task 11041 | n_gen = 299, tg = 21.36 t/s, tg_3s = 20.93 t/s 9.51.705.733 I slot print_timing: id 0 | task 11060 | prompt eval time = 383.89 ms / 57 tokens ( 6.73 ms per token, 148.48 tokens per second) 9.51.705.738 I slot print_timing: id 0 | task 11060 | eval time = 13858.41 ms / 304 tokens ( 45.74 ms per token, 21.86 tokens per second) 9.51.705.741 I slot print_timing: id 0 | task 11060 | total time = 14242.30 ms / 361 tokens 9.51.705.742 I slot print_timing: id 0 | task 11060 | graphs reused = 10495 9.51.705.742 I slot print_timing: id 0 | task 11060 | graph reallocs = 0 / 0 (same size) / (changed size) 9.51.705.816 I slot release: id 0 | task 11060 | stop processing: n_tokens = 1331, truncated = 0 9.51.749.197 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.730 9.51.749.222 I slot launch_slot_: id 0 | task 11370 | processing task, is_child = 0 9.52.776.592 I slot print_timing: id 1 | task 11283 | n_gen = 100, tg = 22.05 t/s, tg_3s = 22.28 t/s 9.53.022.078 I slot print_timing: id 2 | task 11161 | n_gen = 227, tg = 22.36 t/s, tg_3s = 21.05 t/s 9.53.800.868 I slot print_timing: id 3 | task 11041 | n_gen = 363, tg = 21.31 t/s, tg_3s = 21.06 t/s 9.54.375.412 I slot print_timing: id 2 | task 11161 | prompt eval time = 474.94 ms / 87 tokens ( 5.46 ms per token, 183.18 tokens per second) 9.54.375.421 I slot print_timing: id 2 | task 11161 | eval time = 11461.91 ms / 260 tokens ( 44.25 ms per token, 22.60 tokens per second) 9.54.375.422 I slot print_timing: id 2 | task 11161 | total time = 11936.85 ms / 347 tokens 9.54.375.423 I slot print_timing: id 2 | task 11161 | graphs reused = 10547 9.54.375.424 I slot print_timing: id 2 | task 11161 | graph reallocs = 0 / 0 (same size) / (changed size) 9.54.375.496 I slot release: id 2 | task 11161 | stop processing: n_tokens = 1316, truncated = 0 9.54.433.762 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.943 (> 0.100 thold), f_keep = 0.738 9.54.433.790 I slot launch_slot_: id 2 | task 11426 | processing task, is_child = 0 9.55.799.640 I slot print_timing: id 1 | task 11283 | n_gen = 165, tg = 21.83 t/s, tg_3s = 21.50 t/s 9.56.665.149 I slot print_timing: id 0 | task 11370 | n_gen = 100, tg = 22.34 t/s, tg_3s = 22.57 t/s 9.56.829.449 I slot print_timing: id 3 | task 11041 | n_gen = 428, tg = 21.33 t/s, tg_3s = 21.46 t/s 9.58.805.717 I slot print_timing: id 1 | task 11283 | n_gen = 238, tg = 22.53 t/s, tg_3s = 24.28 t/s 9.58.928.441 I slot print_timing: id 2 | task 11426 | n_gen = 100, tg = 24.27 t/s, tg_3s = 24.52 t/s 9.59.668.696 I slot print_timing: id 0 | task 11370 | n_gen = 173, tg = 23.14 t/s, tg_3s = 24.30 t/s 9.59.833.420 I slot print_timing: id 3 | task 11041 | n_gen = 501, tg = 21.72 t/s, tg_3s = 24.30 t/s 10.00.120.806 I slot print_timing: id 2 | task 11426 | prompt eval time = 416.20 ms / 59 tokens ( 7.05 ms per token, 141.76 tokens per second) 10.00.120.814 I slot print_timing: id 2 | task 11426 | eval time = 5270.80 ms / 129 tokens ( 41.18 ms per token, 24.28 tokens per second) 10.00.120.815 I slot print_timing: id 2 | task 11426 | total time = 5687.00 ms / 188 tokens 10.00.120.816 I slot print_timing: id 2 | task 11426 | graphs reused = 10672 10.00.120.817 I slot print_timing: id 2 | task 11426 | graph reallocs = 0 / 0 (same size) / (changed size) 10.00.120.895 I slot release: id 2 | task 11426 | stop processing: n_tokens = 1158, truncated = 0 10.00.179.064 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.839 10.00.179.093 I slot launch_slot_: id 2 | task 11558 | processing task, is_child = 0 10.01.821.445 I slot print_timing: id 1 | task 11283 | n_gen = 301, tg = 22.17 t/s, tg_3s = 20.89 t/s 10.02.686.176 I slot print_timing: id 0 | task 11370 | n_gen = 236, tg = 22.48 t/s, tg_3s = 20.88 t/s 10.02.851.290 I slot print_timing: id 3 | task 11041 | n_gen = 564, tg = 21.62 t/s, tg_3s = 20.88 t/s 10.04.757.910 I slot print_timing: id 2 | task 11558 | n_gen = 100, tg = 24.16 t/s, tg_3s = 24.40 t/s 10.04.840.045 I slot print_timing: id 1 | task 11283 | n_gen = 374, tg = 22.53 t/s, tg_3s = 24.18 t/s 10.05.706.927 I slot print_timing: id 0 | task 11370 | n_gen = 309, tg = 22.86 t/s, tg_3s = 24.17 t/s 10.05.872.303 I slot print_timing: id 3 | task 11041 | n_gen = 637, tg = 21.88 t/s, tg_3s = 24.16 t/s 10.05.994.607 I slot print_timing: id 1 | task 11283 | prompt eval time = 477.37 ms / 78 tokens ( 6.12 ms per token, 163.39 tokens per second) 10.05.994.614 I slot print_timing: id 1 | task 11283 | eval time = 17707.31 ms / 402 tokens ( 44.16 ms per token, 22.65 tokens per second) 10.05.994.615 I slot print_timing: id 1 | task 11283 | total time = 18184.69 ms / 480 tokens 10.05.994.616 I slot print_timing: id 1 | task 11283 | graphs reused = 10800 10.05.994.617 I slot print_timing: id 1 | task 11283 | graph reallocs = 0 / 0 (same size) / (changed size) 10.05.994.689 I slot release: id 1 | task 11283 | stop processing: n_tokens = 1450, truncated = 0 10.06.052.719 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.670 10.06.052.751 I slot launch_slot_: id 1 | task 11691 | processing task, is_child = 0 10.07.772.447 I slot print_timing: id 2 | task 11558 | n_gen = 162, tg = 22.63 t/s, tg_3s = 20.57 t/s 10.08.720.577 I slot print_timing: id 0 | task 11370 | n_gen = 371, tg = 22.44 t/s, tg_3s = 20.57 t/s 10.08.885.657 I slot print_timing: id 3 | task 11041 | n_gen = 699, tg = 21.76 t/s, tg_3s = 20.58 t/s 10.09.008.991 I slot print_timing: id 0 | task 11370 | prompt eval time = 485.21 ms / 101 tokens ( 4.80 ms per token, 208.16 tokens per second) 10.09.008.995 I slot print_timing: id 0 | task 11370 | eval time = 16774.55 ms / 378 tokens ( 44.49 ms per token, 22.47 tokens per second) 10.09.008.996 I slot print_timing: id 0 | task 11370 | total time = 17259.76 ms / 479 tokens 10.09.008.997 I slot print_timing: id 0 | task 11370 | graphs reused = 10858 10.09.008.998 I slot print_timing: id 0 | task 11370 | graph reallocs = 0 / 0 (same size) / (changed size) 10.09.009.071 I slot release: id 0 | task 11370 | stop processing: n_tokens = 1449, truncated = 0 10.09.052.419 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.670 10.09.052.447 I slot launch_slot_: id 0 | task 11754 | processing task, is_child = 0 10.10.808.853 I slot print_timing: id 2 | task 11558 | n_gen = 228, tg = 22.37 t/s, tg_3s = 21.74 t/s 10.10.972.423 I slot print_timing: id 1 | task 11691 | n_gen = 100, tg = 22.44 t/s, tg_3s = 22.67 t/s 10.11.922.338 I slot print_timing: id 3 | task 11041 | n_gen = 765, tg = 21.76 t/s, tg_3s = 21.73 t/s 10.12.293.700 I slot print_timing: id 2 | task 11558 | prompt eval time = 480.36 ms / 85 tokens ( 5.65 ms per token, 176.95 tokens per second) 10.12.293.707 I slot print_timing: id 2 | task 11558 | eval time = 11634.23 ms / 264 tokens ( 44.24 ms per token, 22.61 tokens per second) 10.12.293.710 I slot print_timing: id 2 | task 11558 | total time = 12114.59 ms / 349 tokens 10.12.293.711 I slot print_timing: id 2 | task 11558 | graphs reused = 10926 10.12.293.711 I slot print_timing: id 2 | task 11558 | graph reallocs = 0 / 0 (same size) / (changed size) 10.12.293.788 I slot release: id 2 | task 11558 | stop processing: n_tokens = 1319, truncated = 0 10.12.352.491 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.736 10.12.352.524 I slot launch_slot_: id 2 | task 11827 | processing task, is_child = 0 10.13.907.105 I slot print_timing: id 0 | task 11754 | n_gen = 100, tg = 22.16 t/s, tg_3s = 22.39 t/s 10.13.988.741 I slot print_timing: id 1 | task 11691 | n_gen = 164, tg = 21.94 t/s, tg_3s = 21.22 t/s 10.14.934.382 I slot print_timing: id 3 | task 11041 | n_gen = 829, tg = 21.72 t/s, tg_3s = 21.25 t/s 10.16.866.800 I slot print_timing: id 2 | task 11827 | n_gen = 100, tg = 24.28 t/s, tg_3s = 24.53 t/s 10.16.907.454 I slot print_timing: id 0 | task 11754 | n_gen = 173, tg = 23.03 t/s, tg_3s = 24.33 t/s 10.16.989.517 I slot print_timing: id 1 | task 11691 | n_gen = 237, tg = 22.63 t/s, tg_3s = 24.33 t/s 10.17.939.423 I slot print_timing: id 3 | task 11041 | n_gen = 902, tg = 21.91 t/s, tg_3s = 24.29 t/s 10.18.723.604 I slot print_timing: id 2 | task 11827 | prompt eval time = 436.96 ms / 65 tokens ( 6.72 ms per token, 148.76 tokens per second) 10.18.723.611 I slot print_timing: id 2 | task 11827 | eval time = 5934.11 ms / 145 tokens ( 41.21 ms per token, 24.27 tokens per second) 10.18.723.612 I slot print_timing: id 2 | task 11827 | total time = 6371.07 ms / 210 tokens 10.18.723.613 I slot print_timing: id 2 | task 11827 | graphs reused = 11069 10.18.723.614 I slot print_timing: id 2 | task 11827 | graph reallocs = 0 / 0 (same size) / (changed size) 10.18.723.686 I slot release: id 2 | task 11827 | stop processing: n_tokens = 1180, truncated = 0 10.18.781.845 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.823 10.18.781.870 I slot launch_slot_: id 2 | task 11975 | processing task, is_child = 0 10.19.921.777 I slot print_timing: id 0 | task 11754 | n_gen = 236, tg = 22.42 t/s, tg_3s = 20.90 t/s 10.20.004.225 I slot print_timing: id 1 | task 11691 | n_gen = 300, tg = 22.24 t/s, tg_3s = 20.90 t/s 10.20.953.984 I slot print_timing: id 3 | task 11041 | n_gen = 965, tg = 21.84 t/s, tg_3s = 20.90 t/s 10.22.955.583 I slot print_timing: id 0 | task 11754 | n_gen = 309, tg = 22.79 t/s, tg_3s = 24.06 t/s 10.23.038.967 I slot print_timing: id 1 | task 11691 | n_gen = 373, tg = 22.58 t/s, tg_3s = 24.05 t/s 10.23.164.344 I slot print_timing: id 0 | task 11754 | prompt eval time = 387.39 ms / 62 tokens ( 6.25 ms per token, 160.04 tokens per second) 10.23.164.353 I slot print_timing: id 0 | task 11754 | eval time = 13724.50 ms / 314 tokens ( 43.85 ms per token, 22.81 tokens per second) 10.23.164.354 I slot print_timing: id 0 | task 11754 | total time = 14111.89 ms / 376 tokens 10.23.164.355 I slot print_timing: id 0 | task 11754 | graphs reused = 11161 10.23.164.356 I slot print_timing: id 0 | task 11754 | graph reallocs = 0 / 0 (same size) / (changed size) 10.23.164.426 I slot release: id 0 | task 11754 | stop processing: n_tokens = 1346, truncated = 0 10.23.208.261 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.721 10.23.208.287 I slot launch_slot_: id 0 | task 12073 | processing task, is_child = 0 10.23.749.171 I slot print_timing: id 2 | task 11975 | n_gen = 100, tg = 22.05 t/s, tg_3s = 22.28 t/s 10.23.790.273 I slot print_timing: id 3 | task 11041 | prompt eval time = 473.70 ms / 96 tokens ( 4.93 ms per token, 202.66 tokens per second) 10.23.790.278 I slot print_timing: id 3 | task 11041 | eval time = 46980.28 ms / 1024 tokens ( 45.92 ms per token, 21.78 tokens per second) 10.23.790.279 I slot print_timing: id 3 | task 11041 | total time = 47453.97 ms / 1120 tokens 10.23.790.279 I slot print_timing: id 3 | task 11041 | graphs reused = 11164 10.23.790.280 I slot print_timing: id 3 | task 11041 | graph reallocs = 0 / 0 (same size) / (changed size) 10.23.790.321 I slot release: id 3 | task 11041 | stop processing: n_tokens = 2090, truncated = 0 10.23.829.383 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.465 10.23.863.237 I slot launch_slot_: id 3 | task 12080 | processing task, is_child = 0 10.26.042.938 I slot print_timing: id 1 | task 11691 | n_gen = 428, tg = 21.92 t/s, tg_3s = 18.31 t/s 10.26.780.883 I slot print_timing: id 2 | task 11975 | n_gen = 165, tg = 21.81 t/s, tg_3s = 21.44 t/s 10.28.099.615 I slot print_timing: id 0 | task 12073 | n_gen = 100, tg = 22.32 t/s, tg_3s = 22.54 t/s 10.28.346.732 I slot print_timing: id 3 | task 12080 | n_gen = 100, tg = 24.27 t/s, tg_3s = 24.51 t/s 10.29.045.002 I slot print_timing: id 1 | task 11691 | n_gen = 501, tg = 22.24 t/s, tg_3s = 24.32 t/s 10.29.785.638 I slot print_timing: id 2 | task 11975 | n_gen = 238, tg = 22.52 t/s, tg_3s = 24.29 t/s 10.31.138.668 I slot print_timing: id 0 | task 12073 | n_gen = 174, tg = 23.14 t/s, tg_3s = 24.35 t/s 10.31.385.663 I slot print_timing: id 3 | task 12080 | n_gen = 174, tg = 24.30 t/s, tg_3s = 24.35 t/s 10.32.083.910 I slot print_timing: id 1 | task 11691 | n_gen = 575, tg = 22.49 t/s, tg_3s = 24.35 t/s 10.32.825.653 I slot print_timing: id 2 | task 11975 | n_gen = 312, tg = 22.93 t/s, tg_3s = 24.34 t/s 10.33.773.684 I slot print_timing: id 3 | task 12080 | prompt eval time = 404.29 ms / 68 tokens ( 5.95 ms per token, 168.20 tokens per second) 10.33.773.692 I slot print_timing: id 3 | task 12080 | eval time = 9506.14 ms / 232 tokens ( 41.15 ms per token, 24.30 tokens per second) 10.33.773.694 I slot print_timing: id 3 | task 12080 | total time = 9910.43 ms / 300 tokens 10.33.773.695 I slot print_timing: id 3 | task 12080 | graphs reused = 11392 10.33.773.696 I slot print_timing: id 3 | task 12080 | graph reallocs = 0 / 0 (same size) / (changed size) 10.33.773.766 I slot release: id 3 | task 12080 | stop processing: n_tokens = 1269, truncated = 0 10.33.816.572 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.765 10.33.816.596 I slot launch_slot_: id 3 | task 12315 | processing task, is_child = 0 10.34.191.213 I slot print_timing: id 0 | task 12073 | n_gen = 240, tg = 22.70 t/s, tg_3s = 21.62 t/s 10.35.101.123 I slot print_timing: id 1 | task 11691 | n_gen = 639, tg = 22.35 t/s, tg_3s = 21.21 t/s 10.35.845.668 I slot print_timing: id 2 | task 11975 | n_gen = 376, tg = 22.61 t/s, tg_3s = 21.19 t/s 10.37.203.075 I slot print_timing: id 0 | task 12073 | n_gen = 312, tg = 22.97 t/s, tg_3s = 23.91 t/s 10.38.109.649 I slot print_timing: id 1 | task 11691 | n_gen = 712, tg = 22.54 t/s, tg_3s = 24.26 t/s 10.38.357.497 I slot print_timing: id 3 | task 12315 | n_gen = 100, tg = 24.23 t/s, tg_3s = 24.48 t/s 10.38.858.305 I slot print_timing: id 2 | task 11975 | n_gen = 449, tg = 22.86 t/s, tg_3s = 24.23 t/s 10.39.187.422 I slot print_timing: id 0 | task 12073 | prompt eval time = 454.99 ms / 89 tokens ( 5.11 ms per token, 195.61 tokens per second) 10.39.187.426 I slot print_timing: id 0 | task 12073 | eval time = 15524.14 ms / 360 tokens ( 43.24 ms per token, 23.13 tokens per second) 10.39.187.429 I slot print_timing: id 0 | task 12073 | total time = 15979.12 ms / 449 tokens 10.39.187.429 I slot print_timing: id 0 | task 12073 | graphs reused = 11509 10.39.187.430 I slot print_timing: id 0 | task 12073 | graph reallocs = 0 / 0 (same size) / (changed size) 10.39.187.502 I slot release: id 0 | task 12073 | stop processing: n_tokens = 1419, truncated = 0 10.39.231.014 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.684 10.39.231.038 I slot launch_slot_: id 0 | task 12438 | processing task, is_child = 0 10.41.134.619 I slot print_timing: id 1 | task 11691 | n_gen = 775, tg = 22.39 t/s, tg_3s = 20.83 t/s 10.41.382.751 I slot print_timing: id 3 | task 12315 | n_gen = 163, tg = 22.78 t/s, tg_3s = 20.82 t/s 10.41.877.346 I slot print_timing: id 2 | task 11975 | n_gen = 512, tg = 22.59 t/s, tg_3s = 20.87 t/s 10.42.866.651 I slot print_timing: id 2 | task 11975 | prompt eval time = 478.19 ms / 86 tokens ( 5.56 ms per token, 179.85 tokens per second) 10.42.866.659 I slot print_timing: id 2 | task 11975 | eval time = 23606.58 ms / 536 tokens ( 44.12 ms per token, 22.66 tokens per second) 10.42.866.660 I slot print_timing: id 2 | task 11975 | total time = 24084.77 ms / 622 tokens 10.42.866.661 I slot print_timing: id 2 | task 11975 | graphs reused = 11585 10.42.866.662 I slot print_timing: id 2 | task 11975 | graph reallocs = 0 / 0 (same size) / (changed size) 10.42.866.740 I slot release: id 2 | task 11975 | stop processing: n_tokens = 1592, truncated = 0 10.42.924.799 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.610 10.42.924.827 I slot launch_slot_: id 2 | task 12518 | processing task, is_child = 0 10.44.147.342 I slot print_timing: id 1 | task 11691 | n_gen = 838, tg = 22.27 t/s, tg_3s = 20.91 t/s 10.44.229.532 I slot print_timing: id 0 | task 12438 | n_gen = 100, tg = 21.97 t/s, tg_3s = 22.19 t/s 10.44.394.732 I slot print_timing: id 3 | task 12315 | n_gen = 226, tg = 22.23 t/s, tg_3s = 20.92 t/s 10.47.153.121 I slot print_timing: id 1 | task 11691 | n_gen = 911, tg = 22.42 t/s, tg_3s = 24.29 t/s 10.47.235.378 I slot print_timing: id 0 | task 12438 | n_gen = 173, tg = 22.90 t/s, tg_3s = 24.29 t/s 10.47.400.367 I slot print_timing: id 3 | task 12315 | n_gen = 299, tg = 22.70 t/s, tg_3s = 24.29 t/s 10.47.482.656 I slot print_timing: id 2 | task 12518 | n_gen = 100, tg = 24.22 t/s, tg_3s = 24.47 t/s 10.50.175.040 I slot print_timing: id 1 | task 11691 | n_gen = 984, tg = 22.54 t/s, tg_3s = 24.16 t/s 10.50.258.471 I slot print_timing: id 0 | task 12438 | n_gen = 246, tg = 23.25 t/s, tg_3s = 24.15 t/s 10.50.426.210 I slot print_timing: id 3 | task 12315 | n_gen = 372, tg = 22.97 t/s, tg_3s = 24.13 t/s 10.50.509.605 I slot print_timing: id 2 | task 12518 | n_gen = 173, tg = 24.18 t/s, tg_3s = 24.12 t/s 10.51.848.960 I slot print_timing: id 1 | task 11691 | prompt eval time = 508.01 ms / 101 tokens ( 5.03 ms per token, 198.82 tokens per second) 10.51.848.965 I slot print_timing: id 1 | task 11691 | eval time = 45288.19 ms / 1024 tokens ( 44.27 ms per token, 22.59 tokens per second) 10.51.848.966 I slot print_timing: id 1 | task 11691 | total time = 45796.20 ms / 1125 tokens 10.51.848.966 I slot print_timing: id 1 | task 11691 | graphs reused = 11787 10.51.848.967 I slot print_timing: id 1 | task 11691 | graph reallocs = 0 / 0 (same size) / (changed size) 10.51.849.040 I slot release: id 1 | task 11691 | stop processing: n_tokens = 2095, truncated = 0 10.51.907.076 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.463 10.51.907.355 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 18.695 MiB) 10.51.907.361 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 19.844 MiB) 10.51.907.363 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 24.275 MiB) 10.51.907.365 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 22.798 MiB) 10.51.907.367 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 30.839 MiB) 10.51.907.370 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 19.024 MiB) 10.51.907.372 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 22.470 MiB) 10.51.907.374 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 17.711 MiB) 10.51.907.376 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 21.977 MiB) 10.51.907.378 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 28.213 MiB) 10.51.907.381 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 21.020 MiB) 10.51.949.852 I slot launch_slot_: id 1 | task 12726 | processing task, is_child = 0 10.53.281.180 I slot print_timing: id 0 | task 12438 | n_gen = 307, tg = 22.57 t/s, tg_3s = 20.18 t/s 10.53.281.539 I slot print_timing: id 2 | task 12518 | prompt eval time = 470.46 ms / 93 tokens ( 5.06 ms per token, 197.68 tokens per second) 10.53.281.547 I slot print_timing: id 2 | task 12518 | eval time = 9886.25 ms / 228 tokens ( 43.55 ms per token, 22.96 tokens per second) 10.53.281.548 I slot print_timing: id 2 | task 12518 | total time = 10356.71 ms / 321 tokens 10.53.281.548 I slot print_timing: id 2 | task 12518 | graphs reused = 11805 10.53.281.549 I slot print_timing: id 2 | task 12518 | graph reallocs = 0 / 0 (same size) / (changed size) 10.53.281.622 I slot release: id 2 | task 12518 | stop processing: n_tokens = 1291, truncated = 0 10.53.339.725 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.752 10.53.339.753 I slot launch_slot_: id 2 | task 12750 | processing task, is_child = 0 10.53.702.376 I slot print_timing: id 3 | task 12315 | n_gen = 431, tg = 22.13 t/s, tg_3s = 18.01 t/s 10.56.283.217 I slot print_timing: id 0 | task 12438 | n_gen = 370, tg = 22.28 t/s, tg_3s = 20.99 t/s 10.56.737.394 I slot print_timing: id 3 | task 12315 | n_gen = 503, tg = 22.35 t/s, tg_3s = 23.72 t/s 10.56.942.400 I slot print_timing: id 1 | task 12726 | n_gen = 100, tg = 22.00 t/s, tg_3s = 22.22 t/s 10.57.894.111 I slot print_timing: id 2 | task 12750 | n_gen = 100, tg = 24.16 t/s, tg_3s = 24.41 t/s 10.59.293.590 I slot print_timing: id 0 | task 12438 | n_gen = 443, tg = 22.58 t/s, tg_3s = 24.25 t/s 10.59.747.262 I slot print_timing: id 3 | task 12315 | n_gen = 576, tg = 22.57 t/s, tg_3s = 24.25 t/s 10.59.953.451 I slot print_timing: id 1 | task 12726 | n_gen = 173, tg = 22.90 t/s, tg_3s = 24.24 t/s 11.00.899.683 I slot print_timing: id 2 | task 12750 | n_gen = 173, tg = 24.21 t/s, tg_3s = 24.29 t/s 11.02.301.718 I slot print_timing: id 0 | task 12438 | n_gen = 516, tg = 22.81 t/s, tg_3s = 24.27 t/s 11.02.755.756 I slot print_timing: id 3 | task 12315 | n_gen = 649, tg = 22.75 t/s, tg_3s = 24.26 t/s 11.02.961.297 I slot print_timing: id 1 | task 12726 | n_gen = 246, tg = 23.29 t/s, tg_3s = 24.27 t/s 11.03.209.270 I slot print_timing: id 3 | task 12315 | prompt eval time = 455.61 ms / 87 tokens ( 5.24 ms per token, 190.95 tokens per second) 11.03.209.278 I slot print_timing: id 3 | task 12315 | eval time = 28937.05 ms / 660 tokens ( 43.91 ms per token, 22.77 tokens per second) 11.03.209.279 I slot print_timing: id 3 | task 12315 | total time = 29392.66 ms / 747 tokens 11.03.209.280 I slot print_timing: id 3 | task 12315 | graphs reused = 12031 11.03.209.281 I slot print_timing: id 3 | task 12315 | graph reallocs = 0 / 0 (same size) / (changed size) 11.03.209.357 I slot release: id 3 | task 12315 | stop processing: n_tokens = 1717, truncated = 0 11.03.252.249 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.566 11.03.252.284 I slot launch_slot_: id 3 | task 12982 | processing task, is_child = 0 11.03.940.086 I slot print_timing: id 2 | task 12750 | n_gen = 239, tg = 23.46 t/s, tg_3s = 21.71 t/s 11.05.308.816 I slot print_timing: id 0 | task 12438 | n_gen = 581, tg = 22.67 t/s, tg_3s = 21.62 t/s 11.05.967.428 I slot print_timing: id 1 | task 12726 | n_gen = 311, tg = 22.92 t/s, tg_3s = 21.62 t/s 11.06.957.443 I slot print_timing: id 2 | task 12750 | n_gen = 312, tg = 23.63 t/s, tg_3s = 24.19 t/s 11.07.742.565 I slot print_timing: id 3 | task 12982 | n_gen = 100, tg = 24.20 t/s, tg_3s = 24.44 t/s 11.08.319.699 I slot print_timing: id 0 | task 12438 | n_gen = 654, tg = 22.83 t/s, tg_3s = 24.25 t/s 11.08.980.734 I slot print_timing: id 1 | task 12726 | n_gen = 384, tg = 23.16 t/s, tg_3s = 24.23 t/s 11.09.971.094 I slot print_timing: id 2 | task 12750 | prompt eval time = 456.85 ms / 70 tokens ( 6.53 ms per token, 153.22 tokens per second) 11.09.971.099 I slot print_timing: id 2 | task 12750 | eval time = 16174.48 ms / 385 tokens ( 42.12 ms per token, 23.74 tokens per second) 11.09.971.100 I slot print_timing: id 2 | task 12750 | total time = 16631.33 ms / 455 tokens 11.09.971.100 I slot print_timing: id 2 | task 12750 | graphs reused = 12183 11.09.971.101 I slot print_timing: id 2 | task 12750 | graph reallocs = 0 / 0 (same size) / (changed size) 11.09.971.176 I slot release: id 2 | task 12750 | stop processing: n_tokens = 1425, truncated = 0 11.10.030.222 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.892 (> 0.100 thold), f_keep = 0.681 11.10.030.250 I slot launch_slot_: id 2 | task 13139 | processing task, is_child = 0 11.10.778.719 I slot print_timing: id 3 | task 12982 | n_gen = 162, tg = 22.59 t/s, tg_3s = 20.42 t/s 11.11.319.832 I slot print_timing: id 0 | task 12438 | n_gen = 715, tg = 22.60 t/s, tg_3s = 20.33 t/s 11.11.985.745 I slot print_timing: id 1 | task 12726 | n_gen = 445, tg = 22.72 t/s, tg_3s = 20.30 t/s 11.13.802.226 I slot print_timing: id 3 | task 12982 | n_gen = 235, tg = 23.05 t/s, tg_3s = 24.14 t/s 11.14.338.980 I slot print_timing: id 0 | task 12438 | n_gen = 788, tg = 22.74 t/s, tg_3s = 24.18 t/s 11.14.545.970 I slot print_timing: id 3 | task 12982 | prompt eval time = 399.38 ms / 63 tokens ( 6.34 ms per token, 157.75 tokens per second) 11.14.545.975 I slot print_timing: id 3 | task 12982 | eval time = 10894.30 ms / 253 tokens ( 43.23 ms per token, 23.13 tokens per second) 11.14.545.980 I slot print_timing: id 3 | task 12982 | total time = 11293.68 ms / 316 tokens 11.14.545.981 I slot print_timing: id 3 | task 12982 | graphs reused = 12277 11.14.545.982 I slot print_timing: id 3 | task 12982 | graph reallocs = 0 / 0 (same size) / (changed size) 11.14.546.065 I slot release: id 3 | task 12982 | stop processing: n_tokens = 1286, truncated = 0 11.14.588.656 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.755 11.14.588.683 I slot launch_slot_: id 3 | task 13239 | processing task, is_child = 0 11.14.972.121 I slot print_timing: id 2 | task 13139 | n_gen = 100, tg = 22.49 t/s, tg_3s = 22.72 t/s 11.15.015.951 I slot print_timing: id 1 | task 12726 | n_gen = 511, tg = 22.59 t/s, tg_3s = 21.78 t/s 11.15.798.682 I slot print_timing: id 1 | task 12726 | prompt eval time = 492.76 ms / 86 tokens ( 5.73 ms per token, 174.53 tokens per second) 11.15.798.686 I slot print_timing: id 1 | task 12726 | eval time = 23356.05 ms / 530 tokens ( 44.15 ms per token, 22.65 tokens per second) 11.15.798.687 I slot print_timing: id 1 | task 12726 | total time = 23848.81 ms / 616 tokens 11.15.798.688 I slot print_timing: id 1 | task 12726 | graphs reused = 12296 11.15.798.689 I slot print_timing: id 1 | task 12726 | graph reallocs = 0 / 0 (same size) / (changed size) 11.15.798.763 I slot release: id 1 | task 12726 | stop processing: n_tokens = 1585, truncated = 0 11.15.856.572 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.613 11.15.856.595 I slot launch_slot_: id 1 | task 13263 | processing task, is_child = 0 11.17.378.343 I slot print_timing: id 0 | task 12438 | n_gen = 845, tg = 22.41 t/s, tg_3s = 18.75 t/s 11.17.996.335 I slot print_timing: id 2 | task 13139 | n_gen = 164, tg = 21.95 t/s, tg_3s = 21.16 t/s 11.19.440.165 I slot print_timing: id 3 | task 13239 | n_gen = 100, tg = 22.16 t/s, tg_3s = 22.38 t/s 11.19.976.117 I slot print_timing: id 3 | task 13239 | prompt eval time = 383.57 ms / 56 tokens ( 6.85 ms per token, 145.99 tokens per second) 11.19.976.122 I slot print_timing: id 3 | task 13239 | eval time = 5003.84 ms / 113 tokens ( 44.68 ms per token, 22.38 tokens per second) 11.19.976.123 I slot print_timing: id 3 | task 13239 | total time = 5387.42 ms / 169 tokens 11.19.976.124 I slot print_timing: id 3 | task 13239 | graphs reused = 12384 11.19.976.124 I slot print_timing: id 3 | task 13239 | graph reallocs = 0 / 0 (same size) / (changed size) 11.19.976.201 I slot release: id 3 | task 13239 | stop processing: n_tokens = 1139, truncated = 0 11.20.019.152 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.941 (> 0.100 thold), f_keep = 0.853 11.20.019.176 I slot launch_slot_: id 3 | task 13356 | processing task, is_child = 0 11.20.411.244 I slot print_timing: id 0 | task 12438 | n_gen = 911, tg = 22.37 t/s, tg_3s = 21.76 t/s 11.20.701.272 I slot print_timing: id 1 | task 13263 | n_gen = 100, tg = 22.53 t/s, tg_3s = 22.76 t/s 11.21.033.661 I slot print_timing: id 2 | task 13139 | n_gen = 230, tg = 21.89 t/s, tg_3s = 21.73 t/s 11.23.435.465 I slot print_timing: id 0 | task 12438 | n_gen = 984, tg = 22.49 t/s, tg_3s = 24.14 t/s 11.23.728.841 I slot print_timing: id 1 | task 13263 | n_gen = 173, tg = 23.18 t/s, tg_3s = 24.11 t/s 11.24.062.856 I slot print_timing: id 2 | task 13139 | n_gen = 303, tg = 22.38 t/s, tg_3s = 24.10 t/s 11.24.520.842 I slot print_timing: id 3 | task 13356 | n_gen = 100, tg = 24.09 t/s, tg_3s = 24.33 t/s 11.25.099.372 I slot print_timing: id 0 | task 12438 | prompt eval time = 491.94 ms / 101 tokens ( 4.87 ms per token, 205.31 tokens per second) 11.25.099.376 I slot print_timing: id 0 | task 12438 | eval time = 45376.37 ms / 1024 tokens ( 44.36 ms per token, 22.54 tokens per second) 11.25.099.377 I slot print_timing: id 0 | task 12438 | total time = 45868.31 ms / 1125 tokens 11.25.099.377 I slot print_timing: id 0 | task 12438 | graphs reused = 12495 11.25.099.378 I slot print_timing: id 0 | task 12438 | graph reallocs = 0 / 0 (same size) / (changed size) 11.25.099.447 I slot release: id 0 | task 12438 | stop processing: n_tokens = 2095, truncated = 0 11.25.142.579 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.463 11.25.142.833 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 21.157 MiB) 11.25.142.839 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 26.900 MiB) 11.25.142.841 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 19.352 MiB) 11.25.142.845 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 18.695 MiB) 11.25.142.847 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 16.890 MiB) 11.25.142.849 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 21.977 MiB) 11.25.142.850 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 21.813 MiB) 11.25.142.852 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 17.547 MiB) 11.25.142.854 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 18.367 MiB) 11.25.142.856 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 21.977 MiB) 11.25.142.861 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 20.993 MiB) 11.25.142.863 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 15.413 MiB) 11.25.142.865 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 20.336 MiB) 11.25.142.867 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 26.900 MiB) 11.25.142.869 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 28.377 MiB) 11.25.142.871 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 25.752 MiB) 11.25.182.652 I slot launch_slot_: id 0 | task 13473 | processing task, is_child = 0 11.26.648.793 I slot print_timing: id 3 | task 13356 | prompt eval time = 392.34 ms / 61 tokens ( 6.43 ms per token, 155.48 tokens per second) 11.26.648.800 I slot print_timing: id 3 | task 13356 | eval time = 6237.27 ms / 142 tokens ( 44.24 ms per token, 22.61 tokens per second) 11.26.648.801 I slot print_timing: id 3 | task 13356 | total time = 6629.61 ms / 203 tokens 11.26.648.801 I slot print_timing: id 3 | task 13356 | graphs reused = 12520 11.26.648.802 I slot print_timing: id 3 | task 13356 | graph reallocs = 0 / 0 (same size) / (changed size) 11.26.648.883 I slot release: id 3 | task 13356 | stop processing: n_tokens = 1173, truncated = 0 11.26.691.215 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.828 11.26.691.239 I slot launch_slot_: id 3 | task 13502 | processing task, is_child = 0 11.27.070.598 I slot print_timing: id 1 | task 13263 | n_gen = 236, tg = 21.83 t/s, tg_3s = 18.85 t/s 11.27.070.740 I slot print_timing: id 2 | task 13139 | n_gen = 358, tg = 21.64 t/s, tg_3s = 18.29 t/s 11.29.168.826 I slot print_timing: id 1 | task 13263 | prompt eval time = 450.84 ms / 67 tokens ( 6.73 ms per token, 148.61 tokens per second) 11.29.168.834 I slot print_timing: id 1 | task 13263 | eval time = 12861.38 ms / 286 tokens ( 45.13 ms per token, 22.16 tokens per second) 11.29.168.835 I slot print_timing: id 1 | task 13263 | total time = 13312.22 ms / 353 tokens 11.29.168.836 I slot print_timing: id 1 | task 13263 | graphs reused = 12567 11.29.168.837 I slot print_timing: id 1 | task 13263 | graph reallocs = 0 / 0 (same size) / (changed size) 11.29.168.907 I slot release: id 1 | task 13263 | stop processing: n_tokens = 1323, truncated = 0 11.29.226.505 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.943 (> 0.100 thold), f_keep = 0.734 11.29.226.534 I slot launch_slot_: id 1 | task 13555 | processing task, is_child = 0 11.30.103.961 I slot print_timing: id 2 | task 13139 | n_gen = 422, tg = 21.55 t/s, tg_3s = 21.10 t/s 11.30.435.830 I slot print_timing: id 0 | task 13473 | n_gen = 100, tg = 20.56 t/s, tg_3s = 20.76 t/s 11.31.588.509 I slot print_timing: id 3 | task 13502 | n_gen = 100, tg = 22.31 t/s, tg_3s = 22.53 t/s 11.33.144.809 I slot print_timing: id 2 | task 13139 | n_gen = 496, tg = 21.93 t/s, tg_3s = 24.34 t/s 11.33.471.667 I slot print_timing: id 0 | task 13473 | n_gen = 174, tg = 22.03 t/s, tg_3s = 24.38 t/s 11.33.717.957 I slot print_timing: id 1 | task 13555 | n_gen = 100, tg = 24.35 t/s, tg_3s = 24.60 t/s 11.34.620.446 I slot print_timing: id 3 | task 13502 | n_gen = 174, tg = 23.16 t/s, tg_3s = 24.41 t/s 11.36.184.013 I slot print_timing: id 2 | task 13139 | n_gen = 570, tg = 22.22 t/s, tg_3s = 24.35 t/s 11.36.307.021 I slot print_timing: id 0 | task 13473 | prompt eval time = 437.23 ms / 84 tokens ( 5.21 ms per token, 192.12 tokens per second) 11.36.307.026 I slot print_timing: id 0 | task 13473 | eval time = 10687.12 ms / 243 tokens ( 44.16 ms per token, 22.64 tokens per second) 11.36.307.027 I slot print_timing: id 0 | task 13473 | total time = 11124.35 ms / 327 tokens 11.36.307.028 I slot print_timing: id 0 | task 13473 | graphs reused = 12727 11.36.307.029 I slot print_timing: id 0 | task 13473 | graph reallocs = 0 / 0 (same size) / (changed size) 11.36.307.100 I slot release: id 0 | task 13473 | stop processing: n_tokens = 1296, truncated = 0 11.36.350.447 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.875 (> 0.100 thold), f_keep = 0.749 11.36.350.474 I slot launch_slot_: id 0 | task 13721 | processing task, is_child = 0 11.36.797.854 I slot print_timing: id 1 | task 13555 | n_gen = 165, tg = 22.95 t/s, tg_3s = 21.10 t/s 11.37.628.538 I slot print_timing: id 3 | task 13502 | n_gen = 236, tg = 22.43 t/s, tg_3s = 20.61 t/s 11.37.956.734 I slot print_timing: id 2 | task 13139 | prompt eval time = 540.51 ms / 118 tokens ( 4.58 ms per token, 218.31 tokens per second) 11.37.956.740 I slot print_timing: id 2 | task 13139 | eval time = 27385.97 ms / 602 tokens ( 45.57 ms per token, 21.95 tokens per second) 11.37.956.742 I slot print_timing: id 2 | task 13139 | total time = 27926.47 ms / 720 tokens 11.37.956.742 I slot print_timing: id 2 | task 13139 | graphs reused = 12753 11.37.956.743 I slot print_timing: id 2 | task 13139 | graph reallocs = 0 / 0 (same size) / (changed size) 11.37.956.822 I slot release: id 2 | task 13139 | stop processing: n_tokens = 1690, truncated = 0 11.38.014.852 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.575 11.38.014.887 I slot launch_slot_: id 2 | task 13751 | processing task, is_child = 0 11.39.676.282 I slot print_timing: id 1 | task 13555 | prompt eval time = 426.36 ms / 59 tokens ( 7.23 ms per token, 138.38 tokens per second) 11.39.676.289 I slot print_timing: id 1 | task 13555 | eval time = 10023.38 ms / 224 tokens ( 44.95 ms per token, 22.25 tokens per second) 11.39.676.290 I slot print_timing: id 1 | task 13555 | total time = 10449.74 ms / 283 tokens 11.39.676.290 I slot print_timing: id 1 | task 13555 | graphs reused = 12781 11.39.676.291 I slot print_timing: id 1 | task 13555 | graph reallocs = 0 / 0 (same size) / (changed size) 11.39.676.364 I slot release: id 1 | task 13555 | stop processing: n_tokens = 1253, truncated = 0 11.39.734.175 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.775 11.39.734.204 I slot launch_slot_: id 1 | task 13784 | processing task, is_child = 0 11.40.653.389 I slot print_timing: id 3 | task 13502 | n_gen = 288, tg = 21.25 t/s, tg_3s = 17.19 t/s 11.41.837.976 I slot print_timing: id 0 | task 13721 | n_gen = 100, tg = 19.96 t/s, tg_3s = 20.16 t/s 11.43.025.113 I slot print_timing: id 2 | task 13751 | n_gen = 100, tg = 21.80 t/s, tg_3s = 22.02 t/s 11.43.557.273 I slot print_timing: id 3 | task 13502 | prompt eval time = 459.42 ms / 88 tokens ( 5.22 ms per token, 191.55 tokens per second) 11.43.557.281 I slot print_timing: id 3 | task 13502 | eval time = 16406.61 ms / 359 tokens ( 45.83 ms per token, 21.82 tokens per second) 11.43.557.282 I slot print_timing: id 3 | task 13502 | total time = 16866.02 ms / 447 tokens 11.43.557.283 I slot print_timing: id 3 | task 13502 | graphs reused = 12860 11.43.557.284 I slot print_timing: id 3 | task 13502 | graph reallocs = 0 / 0 (same size) / (changed size) 11.43.557.360 I slot release: id 3 | task 13502 | stop processing: n_tokens = 1417, truncated = 0 11.43.600.078 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.685 11.43.600.106 I slot launch_slot_: id 3 | task 13868 | processing task, is_child = 0 11.44.714.029 I slot print_timing: id 1 | task 13784 | n_gen = 100, tg = 22.31 t/s, tg_3s = 22.54 t/s 11.44.877.795 I slot print_timing: id 0 | task 13721 | n_gen = 165, tg = 20.50 t/s, tg_3s = 21.38 t/s 11.46.030.952 I slot print_timing: id 2 | task 13751 | n_gen = 164, tg = 21.60 t/s, tg_3s = 21.29 t/s 11.47.750.367 I slot print_timing: id 1 | task 13784 | n_gen = 174, tg = 23.15 t/s, tg_3s = 24.37 t/s 11.47.913.912 I slot print_timing: id 0 | task 13721 | n_gen = 239, tg = 21.57 t/s, tg_3s = 24.37 t/s 11.48.119.248 I slot print_timing: id 3 | task 13868 | n_gen = 100, tg = 24.32 t/s, tg_3s = 24.57 t/s 11.49.063.037 I slot print_timing: id 2 | task 13751 | n_gen = 238, tg = 22.40 t/s, tg_3s = 24.41 t/s 11.50.786.290 I slot print_timing: id 1 | task 13784 | n_gen = 248, tg = 23.50 t/s, tg_3s = 24.37 t/s 11.50.950.477 I slot print_timing: id 0 | task 13721 | n_gen = 313, tg = 22.17 t/s, tg_3s = 24.37 t/s 11.51.155.073 I slot print_timing: id 3 | task 13868 | n_gen = 174, tg = 24.35 t/s, tg_3s = 24.38 t/s 11.51.401.675 I slot print_timing: id 3 | task 13868 | prompt eval time = 449.10 ms / 78 tokens ( 5.76 ms per token, 173.68 tokens per second) 11.51.401.682 I slot print_timing: id 3 | task 13868 | eval time = 7352.46 ms / 180 tokens ( 41.08 ms per token, 24.35 tokens per second) 11.51.401.689 I slot print_timing: id 3 | task 13868 | total time = 7801.56 ms / 258 tokens 11.51.401.691 I slot print_timing: id 3 | task 13868 | graphs reused = 13037 11.51.401.699 I slot print_timing: id 3 | task 13868 | graph reallocs = 0 / 0 (same size) / (changed size) 11.51.401.772 I slot release: id 3 | task 13868 | stop processing: n_tokens = 1228, truncated = 0 11.51.444.460 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.899 (> 0.100 thold), f_keep = 0.791 11.51.444.488 I slot launch_slot_: id 3 | task 14051 | processing task, is_child = 0 11.52.079.821 I slot print_timing: id 2 | task 13751 | n_gen = 301, tg = 22.06 t/s, tg_3s = 20.88 t/s 11.53.813.800 I slot print_timing: id 1 | task 13784 | n_gen = 311, tg = 22.90 t/s, tg_3s = 20.81 t/s 11.53.984.561 I slot print_timing: id 0 | task 13721 | n_gen = 376, tg = 21.92 t/s, tg_3s = 20.76 t/s 11.55.014.229 I slot print_timing: id 1 | task 13784 | prompt eval time = 542.42 ms / 112 tokens ( 4.84 ms per token, 206.48 tokens per second) 11.55.014.238 I slot print_timing: id 1 | task 13784 | eval time = 14737.60 ms / 340 tokens ( 43.47 ms per token, 23.00 tokens per second) 11.55.014.239 I slot print_timing: id 1 | task 13784 | total time = 15280.02 ms / 452 tokens 11.55.014.240 I slot print_timing: id 1 | task 13784 | graphs reused = 13109 11.55.014.241 I slot print_timing: id 1 | task 13784 | graph reallocs = 0 / 0 (same size) / (changed size) 11.55.014.323 I slot release: id 1 | task 13784 | stop processing: n_tokens = 1422, truncated = 0 11.55.072.088 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.683 11.55.072.118 I slot launch_slot_: id 1 | task 14129 | processing task, is_child = 0 11.55.449.294 I slot print_timing: id 2 | task 13751 | n_gen = 374, tg = 21.98 t/s, tg_3s = 21.67 t/s 11.56.459.637 I slot print_timing: id 3 | task 14051 | n_gen = 100, tg = 21.98 t/s, tg_3s = 22.20 t/s 11.56.999.812 I slot print_timing: id 0 | task 13721 | n_gen = 439, tg = 21.77 t/s, tg_3s = 20.89 t/s 11.58.479.302 I slot print_timing: id 2 | task 13751 | n_gen = 446, tg = 22.25 t/s, tg_3s = 23.76 t/s 11.59.465.691 I slot print_timing: id 3 | task 14051 | n_gen = 173, tg = 22.90 t/s, tg_3s = 24.28 t/s 11.59.630.602 I slot print_timing: id 1 | task 14129 | n_gen = 100, tg = 24.26 t/s, tg_3s = 24.50 t/s 12.00.003.030 I slot print_timing: id 0 | task 13721 | n_gen = 512, tg = 22.10 t/s, tg_3s = 24.31 t/s 12.01.488.955 I slot print_timing: id 2 | task 13751 | n_gen = 519, tg = 22.52 t/s, tg_3s = 24.26 t/s 12.02.480.290 I slot print_timing: id 3 | task 14051 | n_gen = 246, tg = 23.28 t/s, tg_3s = 24.22 t/s 12.02.645.556 I slot print_timing: id 1 | task 14129 | n_gen = 173, tg = 24.24 t/s, tg_3s = 24.21 t/s 12.03.017.501 I slot print_timing: id 0 | task 13721 | n_gen = 585, tg = 22.34 t/s, tg_3s = 24.22 t/s 12.04.508.284 I slot print_timing: id 2 | task 13751 | n_gen = 592, tg = 22.71 t/s, tg_3s = 24.18 t/s 12.05.499.820 I slot print_timing: id 3 | task 14051 | n_gen = 319, tg = 23.48 t/s, tg_3s = 24.18 t/s 12.05.665.661 I slot print_timing: id 1 | task 14129 | n_gen = 246, tg = 24.22 t/s, tg_3s = 24.17 t/s 12.06.038.752 I slot print_timing: id 0 | task 13721 | n_gen = 658, tg = 22.53 t/s, tg_3s = 24.16 t/s 12.07.535.220 I slot print_timing: id 2 | task 13751 | n_gen = 665, tg = 22.86 t/s, tg_3s = 24.12 t/s 12.08.532.612 I slot print_timing: id 3 | task 14051 | n_gen = 392, tg = 23.59 t/s, tg_3s = 24.07 t/s 12.08.698.146 I slot print_timing: id 1 | task 14129 | n_gen = 319, tg = 24.19 t/s, tg_3s = 24.07 t/s 12.09.071.042 I slot print_timing: id 0 | task 13721 | n_gen = 731, tg = 22.68 t/s, tg_3s = 24.07 t/s 12.10.565.239 I slot print_timing: id 2 | task 13751 | n_gen = 738, tg = 22.97 t/s, tg_3s = 24.09 t/s 12.11.561.472 I slot print_timing: id 3 | task 14051 | n_gen = 465, tg = 23.67 t/s, tg_3s = 24.10 t/s 12.11.727.830 I slot print_timing: id 1 | task 14129 | n_gen = 392, tg = 24.17 t/s, tg_3s = 24.09 t/s 12.12.103.319 I slot print_timing: id 0 | task 13721 | n_gen = 804, tg = 22.80 t/s, tg_3s = 24.07 t/s 12.13.602.250 I slot print_timing: id 2 | task 13751 | n_gen = 811, tg = 23.06 t/s, tg_3s = 24.04 t/s 12.14.601.721 I slot print_timing: id 3 | task 14051 | n_gen = 538, tg = 23.71 t/s, tg_3s = 24.01 t/s 12.14.767.891 I slot print_timing: id 1 | task 14129 | n_gen = 465, tg = 24.14 t/s, tg_3s = 24.01 t/s 12.15.141.795 I slot print_timing: id 0 | task 13721 | n_gen = 877, tg = 22.89 t/s, tg_3s = 24.03 t/s 12.16.643.413 I slot print_timing: id 2 | task 13751 | n_gen = 884, tg = 23.14 t/s, tg_3s = 24.00 t/s 12.17.601.956 I slot print_timing: id 3 | task 14051 | n_gen = 610, tg = 23.75 t/s, tg_3s = 24.00 t/s 12.17.776.398 I slot print_timing: id 1 | task 14129 | n_gen = 537, tg = 24.12 t/s, tg_3s = 23.93 t/s 12.18.155.538 I slot print_timing: id 0 | task 13721 | n_gen = 949, tg = 22.97 t/s, tg_3s = 23.89 t/s 12.19.670.736 I slot print_timing: id 2 | task 13751 | n_gen = 956, tg = 23.19 t/s, tg_3s = 23.78 t/s 12.20.642.890 I slot print_timing: id 3 | task 14051 | n_gen = 682, tg = 23.74 t/s, tg_3s = 23.68 t/s 12.20.812.482 I slot print_timing: id 1 | task 14129 | n_gen = 609, tg = 24.07 t/s, tg_3s = 23.71 t/s 12.21.192.123 I slot print_timing: id 0 | task 13721 | n_gen = 1021, tg = 23.02 t/s, tg_3s = 23.71 t/s 12.21.319.030 I slot print_timing: id 0 | task 13721 | prompt eval time = 527.52 ms / 139 tokens ( 3.80 ms per token, 263.50 tokens per second) 12.21.319.036 I slot print_timing: id 0 | task 13721 | eval time = 44441.03 ms / 1024 tokens ( 43.44 ms per token, 23.02 tokens per second) 12.21.319.037 I slot print_timing: id 0 | task 13721 | total time = 44968.55 ms / 1163 tokens 12.21.319.037 I slot print_timing: id 0 | task 13721 | graphs reused = 13725 12.21.319.038 I slot print_timing: id 0 | task 13721 | graph reallocs = 0 / 0 (same size) / (changed size) 12.21.319.114 I slot release: id 0 | task 13721 | stop processing: n_tokens = 2133, truncated = 0 12.21.362.840 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.455 12.21.363.089 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 21.649 MiB) 12.21.363.095 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 22.798 MiB) 12.21.363.097 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 25.752 MiB) 12.21.363.099 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 18.531 MiB) 12.21.363.101 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 25.423 MiB) 12.21.363.200 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 19.352 MiB) 12.21.363.360 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 24.111 MiB) 12.21.363.608 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 25.752 MiB) 12.21.363.804 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 25.423 MiB) 12.21.364.040 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 18.531 MiB) 12.21.364.258 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 21.813 MiB) 12.21.364.535 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 20.172 MiB) 12.21.364.739 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 18.367 MiB) 12.21.364.943 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 21.649 MiB) 12.21.365.112 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 21.649 MiB) 12.21.365.309 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 18.367 MiB) 12.21.399.885 I slot launch_slot_: id 0 | task 14753 | processing task, is_child = 0 12.22.704.300 I slot print_timing: id 2 | task 13751 | n_gen = 1017, tg = 22.98 t/s, tg_3s = 20.11 t/s 12.22.998.896 I slot print_timing: id 2 | task 13751 | prompt eval time = 468.08 ms / 73 tokens ( 6.41 ms per token, 155.95 tokens per second) 12.22.998.903 I slot print_timing: id 2 | task 13751 | eval time = 44515.92 ms / 1024 tokens ( 43.52 ms per token, 22.98 tokens per second) 12.22.998.904 I slot print_timing: id 2 | task 13751 | total time = 44984.00 ms / 1097 tokens 12.22.998.905 I slot print_timing: id 2 | task 13751 | graphs reused = 13750 12.22.998.906 I slot print_timing: id 2 | task 13751 | graph reallocs = 0 / 0 (same size) / (changed size) 12.22.998.979 I slot release: id 2 | task 13751 | stop processing: n_tokens = 2067, truncated = 0 12.23.057.879 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.470 12.23.058.177 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 19.516 MiB) 12.23.058.185 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 17.875 MiB) 12.23.058.461 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 18.367 MiB) 12.23.058.801 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 26.408 MiB) 12.23.059.083 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 20.665 MiB) 12.23.059.289 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.941 MiB) 12.23.059.479 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 26.900 MiB) 12.23.059.725 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 21.649 MiB) 12.23.059.965 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 24.111 MiB) 12.23.060.189 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 24.111 MiB) 12.23.060.389 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 34.777 MiB) 12.23.060.616 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 28.705 MiB) 12.23.092.764 I slot launch_slot_: id 2 | task 14783 | processing task, is_child = 0 12.23.692.070 I slot print_timing: id 3 | task 14051 | n_gen = 731, tg = 23.00 t/s, tg_3s = 16.07 t/s 12.23.818.388 I slot print_timing: id 1 | task 14129 | n_gen = 657, tg = 23.21 t/s, tg_3s = 15.97 t/s 12.26.544.041 I slot print_timing: id 0 | task 14753 | n_gen = 100, tg = 21.31 t/s, tg_3s = 21.53 t/s 12.26.710.115 I slot print_timing: id 3 | task 14051 | n_gen = 804, tg = 23.10 t/s, tg_3s = 24.19 t/s 12.26.833.814 I slot print_timing: id 1 | task 14129 | n_gen = 730, tg = 23.30 t/s, tg_3s = 24.21 t/s 12.27.783.847 I slot print_timing: id 2 | task 14783 | n_gen = 100, tg = 24.19 t/s, tg_3s = 24.44 t/s 12.29.559.996 I slot print_timing: id 0 | task 14753 | n_gen = 173, tg = 22.45 t/s, tg_3s = 24.20 t/s 12.29.726.475 I slot print_timing: id 3 | task 14051 | n_gen = 877, tg = 23.19 t/s, tg_3s = 24.20 t/s 12.29.850.087 I slot print_timing: id 1 | task 14129 | n_gen = 803, tg = 23.38 t/s, tg_3s = 24.20 t/s 12.30.760.931 I slot print_timing: id 1 | task 14129 | prompt eval time = 477.63 ms / 78 tokens ( 6.12 ms per token, 163.31 tokens per second) 12.30.760.940 I slot print_timing: id 1 | task 14129 | eval time = 35211.18 ms / 825 tokens ( 42.73 ms per token, 23.40 tokens per second) 12.30.760.942 I slot print_timing: id 1 | task 14129 | total time = 35688.81 ms / 903 tokens 12.30.760.943 I slot print_timing: id 1 | task 14129 | graphs reused = 13920 12.30.760.944 I slot print_timing: id 1 | task 14129 | graph reallocs = 0 / 0 (same size) / (changed size) 12.30.761.020 I slot release: id 1 | task 14129 | stop processing: n_tokens = 1873, truncated = 0 12.30.819.348 I slot print_timing: id 2 | task 14783 | n_gen = 173, tg = 24.13 t/s, tg_3s = 24.05 t/s 12.30.819.502 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.518 12.30.819.529 I slot launch_slot_: id 1 | task 14959 | processing task, is_child = 0 12.32.598.623 I slot print_timing: id 0 | task 14753 | n_gen = 237, tg = 22.06 t/s, tg_3s = 21.06 t/s 12.32.764.306 I slot print_timing: id 3 | task 14051 | n_gen = 941, tg = 23.03 t/s, tg_3s = 21.07 t/s 12.33.837.114 I slot print_timing: id 2 | task 14783 | n_gen = 237, tg = 23.26 t/s, tg_3s = 21.21 t/s 12.34.300.012 I slot print_timing: id 0 | task 14753 | prompt eval time = 498.46 ms / 101 tokens ( 4.94 ms per token, 202.62 tokens per second) 12.34.300.020 I slot print_timing: id 0 | task 14753 | eval time = 12401.66 ms / 278 tokens ( 44.77 ms per token, 22.34 tokens per second) 12.34.300.021 I slot print_timing: id 0 | task 14753 | total time = 12900.11 ms / 379 tokens 12.34.300.022 I slot print_timing: id 0 | task 14753 | graphs reused = 13991 12.34.300.023 I slot print_timing: id 0 | task 14753 | graph reallocs = 0 / 0 (same size) / (changed size) 12.34.300.095 I slot release: id 0 | task 14753 | stop processing: n_tokens = 1348, truncated = 0 12.34.344.012 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.924 (> 0.100 thold), f_keep = 0.720 12.34.344.038 I slot launch_slot_: id 0 | task 15036 | processing task, is_child = 0 12.35.728.426 I slot print_timing: id 1 | task 14959 | n_gen = 100, tg = 22.21 t/s, tg_3s = 22.44 t/s 12.35.770.273 I slot print_timing: id 3 | task 14051 | n_gen = 1005, tg = 22.91 t/s, tg_3s = 21.29 t/s 12.36.061.171 I slot print_timing: id 2 | task 14783 | prompt eval time = 599.21 ms / 105 tokens ( 5.71 ms per token, 175.23 tokens per second) 12.36.061.178 I slot print_timing: id 2 | task 14783 | eval time = 12369.17 ms / 282 tokens ( 44.02 ms per token, 22.72 tokens per second) 12.36.061.179 I slot print_timing: id 2 | task 14783 | total time = 12968.38 ms / 387 tokens 12.36.061.180 I slot print_timing: id 2 | task 14783 | graphs reused = 14022 12.36.061.180 I slot print_timing: id 2 | task 14783 | graph reallocs = 0 / 0 (same size) / (changed size) 12.36.061.254 I slot release: id 2 | task 14783 | stop processing: n_tokens = 1338, truncated = 0 12.36.119.641 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.726 12.36.119.667 I slot launch_slot_: id 2 | task 15071 | processing task, is_child = 0 12.36.928.529 I slot print_timing: id 3 | task 14051 | prompt eval time = 510.51 ms / 109 tokens ( 4.68 ms per token, 213.51 tokens per second) 12.36.928.533 I slot print_timing: id 3 | task 14051 | eval time = 44973.52 ms / 1024 tokens ( 43.96 ms per token, 22.75 tokens per second) 12.36.928.535 I slot print_timing: id 3 | task 14051 | total time = 45484.03 ms / 1133 tokens 12.36.928.535 I slot print_timing: id 3 | task 14051 | graphs reused = 14030 12.36.928.536 I slot print_timing: id 3 | task 14051 | graph reallocs = 0 / 0 (same size) / (changed size) 12.36.928.609 I slot release: id 3 | task 14051 | stop processing: n_tokens = 2103, truncated = 0 12.36.970.725 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.462 12.36.970.971 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 21.485 MiB) 12.36.970.976 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 26.736 MiB) 12.36.971.160 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 20.665 MiB) 12.36.971.437 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 17.875 MiB) 12.36.971.673 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 20.172 MiB) 12.36.971.899 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 20.172 MiB) 12.36.999.620 I slot launch_slot_: id 3 | task 15084 | processing task, is_child = 0 12.38.752.312 I slot print_timing: id 1 | task 14959 | n_gen = 155, tg = 20.59 t/s, tg_3s = 18.19 t/s 12.39.609.865 I slot print_timing: id 0 | task 15036 | n_gen = 100, tg = 20.46 t/s, tg_3s = 20.66 t/s 12.41.003.245 I slot print_timing: id 2 | task 15071 | n_gen = 100, tg = 22.22 t/s, tg_3s = 22.45 t/s 12.41.493.010 I slot print_timing: id 3 | task 15084 | n_gen = 100, tg = 24.42 t/s, tg_3s = 24.67 t/s 12.41.778.934 I slot print_timing: id 1 | task 14959 | n_gen = 229, tg = 21.70 t/s, tg_3s = 24.45 t/s 12.42.642.772 I slot print_timing: id 0 | task 15036 | n_gen = 174, tg = 21.98 t/s, tg_3s = 24.40 t/s 12.43.216.399 I slot print_timing: id 0 | task 15036 | prompt eval time = 426.40 ms / 80 tokens ( 5.33 ms per token, 187.62 tokens per second) 12.43.216.409 I slot print_timing: id 0 | task 15036 | eval time = 8445.95 ms / 188 tokens ( 45.17 ms per token, 22.14 tokens per second) 12.43.216.410 I slot print_timing: id 0 | task 15036 | total time = 8872.35 ms / 268 tokens 12.43.216.411 I slot print_timing: id 0 | task 15036 | graphs reused = 14168 12.43.216.411 I slot print_timing: id 0 | task 15036 | graph reallocs = 0 / 0 (same size) / (changed size) 12.43.216.486 I slot release: id 0 | task 15036 | stop processing: n_tokens = 1238, truncated = 0 12.43.259.480 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.879 (> 0.100 thold), f_keep = 0.784 12.43.259.505 I slot launch_slot_: id 0 | task 15229 | processing task, is_child = 0 12.44.003.943 I slot print_timing: id 2 | task 15071 | n_gen = 162, tg = 21.60 t/s, tg_3s = 20.66 t/s 12.44.493.713 I slot print_timing: id 3 | task 15084 | n_gen = 162, tg = 22.82 t/s, tg_3s = 20.66 t/s 12.44.780.321 I slot print_timing: id 1 | task 14959 | n_gen = 291, tg = 21.47 t/s, tg_3s = 20.66 t/s 12.45.025.913 I slot print_timing: id 2 | task 15071 | prompt eval time = 429.03 ms / 68 tokens ( 6.31 ms per token, 158.50 tokens per second) 12.45.025.921 I slot print_timing: id 2 | task 15071 | eval time = 8477.21 ms / 187 tokens ( 45.58 ms per token, 21.94 tokens per second) 12.45.025.921 I slot print_timing: id 2 | task 15071 | total time = 8906.24 ms / 255 tokens 12.45.025.922 I slot print_timing: id 2 | task 15071 | graphs reused = 14198 12.45.025.923 I slot print_timing: id 2 | task 15071 | graph reallocs = 0 / 0 (same size) / (changed size) 12.45.025.993 I slot release: id 2 | task 15071 | stop processing: n_tokens = 1225, truncated = 0 12.45.084.321 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.793 12.45.084.351 I slot launch_slot_: id 2 | task 15263 | processing task, is_child = 0 12.45.552.580 I slot print_timing: id 1 | task 14959 | prompt eval time = 452.09 ms / 68 tokens ( 6.65 ms per token, 150.41 tokens per second) 12.45.552.586 I slot print_timing: id 1 | task 14959 | eval time = 14280.96 ms / 300 tokens ( 47.76 ms per token, 20.94 tokens per second) 12.45.552.587 I slot print_timing: id 1 | task 14959 | total time = 14733.05 ms / 368 tokens 12.45.552.587 I slot print_timing: id 1 | task 14959 | graphs reused = 14198 12.45.552.588 I slot print_timing: id 1 | task 14959 | graph reallocs = 0 / 0 (same size) / (changed size) 12.45.552.633 I slot release: id 1 | task 14959 | stop processing: n_tokens = 1337, truncated = 0 12.45.606.536 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.726 12.45.606.559 I slot launch_slot_: id 1 | task 15267 | processing task, is_child = 0 12.46.898.207 I slot print_timing: id 3 | task 15084 | prompt eval time = 439.19 ms / 77 tokens ( 5.70 ms per token, 175.32 tokens per second) 12.46.898.214 I slot print_timing: id 3 | task 15084 | eval time = 9459.38 ms / 200 tokens ( 47.53 ms per token, 21.04 tokens per second) 12.46.898.215 I slot print_timing: id 3 | task 15084 | total time = 9898.57 ms / 277 tokens 12.46.898.216 I slot print_timing: id 3 | task 15084 | graphs reused = 14216 12.46.898.216 I slot print_timing: id 3 | task 15084 | graph reallocs = 0 / 0 (same size) / (changed size) 12.46.898.288 I slot release: id 3 | task 15084 | stop processing: n_tokens = 1246, truncated = 0 12.46.940.624 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.779 12.46.940.652 I slot launch_slot_: id 3 | task 15290 | processing task, is_child = 0 12.49.035.479 I slot print_timing: id 0 | task 15229 | n_gen = 100, tg = 18.91 t/s, tg_3s = 19.10 t/s 12.50.386.410 I slot print_timing: id 2 | task 15263 | n_gen = 100, tg = 20.48 t/s, tg_3s = 20.69 t/s 12.50.509.345 I slot print_timing: id 1 | task 15267 | n_gen = 100, tg = 22.53 t/s, tg_3s = 22.76 t/s 12.51.246.757 I slot print_timing: id 3 | task 15290 | prompt eval time = 412.76 ms / 63 tokens ( 6.55 ms per token, 152.63 tokens per second) 12.51.246.762 I slot print_timing: id 3 | task 15290 | eval time = 3893.34 ms / 96 tokens ( 40.98 ms per token, 24.40 tokens per second) 12.51.246.763 I slot print_timing: id 3 | task 15290 | total time = 4306.10 ms / 159 tokens 12.51.246.764 I slot print_timing: id 3 | task 15290 | graphs reused = 14309 12.51.246.766 I slot print_timing: id 3 | task 15290 | graph reallocs = 0 / 0 (same size) / (changed size) 12.51.246.833 I slot release: id 3 | task 15290 | stop processing: n_tokens = 1129, truncated = 0 12.51.289.485 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.899 (> 0.100 thold), f_keep = 0.860 12.51.289.508 I slot launch_slot_: id 3 | task 15389 | processing task, is_child = 0 12.52.043.040 I slot print_timing: id 0 | task 15229 | n_gen = 163, tg = 19.65 t/s, tg_3s = 20.95 t/s 12.53.408.066 I slot print_timing: id 2 | task 15263 | n_gen = 163, tg = 20.62 t/s, tg_3s = 20.85 t/s 12.53.530.913 I slot print_timing: id 1 | task 15267 | n_gen = 163, tg = 21.85 t/s, tg_3s = 20.85 t/s 12.55.050.836 I slot print_timing: id 0 | task 15229 | n_gen = 236, tg = 20.89 t/s, tg_3s = 24.27 t/s 12.55.872.611 I slot print_timing: id 3 | task 15389 | n_gen = 100, tg = 24.28 t/s, tg_3s = 24.53 t/s 12.56.447.916 I slot print_timing: id 2 | task 15263 | n_gen = 237, tg = 21.66 t/s, tg_3s = 24.34 t/s 12.56.570.795 I slot print_timing: id 1 | task 15267 | n_gen = 237, tg = 22.57 t/s, tg_3s = 24.34 t/s 12.58.090.105 I slot print_timing: id 0 | task 15229 | n_gen = 310, tg = 21.62 t/s, tg_3s = 24.35 t/s 12.58.418.313 I slot print_timing: id 1 | task 15267 | prompt eval time = 508.92 ms / 92 tokens ( 5.53 ms per token, 180.77 tokens per second) 12.58.418.321 I slot print_timing: id 1 | task 15267 | eval time = 12302.82 ms / 282 tokens ( 43.78 ms per token, 22.84 tokens per second) 12.58.418.322 I slot print_timing: id 1 | task 15267 | total time = 12811.74 ms / 374 tokens 12.58.418.322 I slot print_timing: id 1 | task 15267 | graphs reused = 14468 12.58.418.323 I slot print_timing: id 1 | task 15267 | graph reallocs = 0 / 0 (same size) / (changed size) 12.58.418.399 I slot release: id 1 | task 15267 | stop processing: n_tokens = 1344, truncated = 0 12.58.476.449 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.722 12.58.476.479 I slot launch_slot_: id 1 | task 15554 | processing task, is_child = 0 12.58.908.159 I slot print_timing: id 3 | task 15389 | n_gen = 165, tg = 23.06 t/s, tg_3s = 21.41 t/s 12.59.452.395 I slot print_timing: id 2 | task 15263 | n_gen = 301, tg = 21.58 t/s, tg_3s = 21.30 t/s 13.01.093.465 I slot print_timing: id 0 | task 15229 | n_gen = 374, tg = 21.57 t/s, tg_3s = 21.31 t/s 13.01.551.744 I slot print_timing: id 2 | task 15263 | prompt eval time = 468.42 ms / 79 tokens ( 5.93 ms per token, 168.65 tokens per second) 13.01.551.749 I slot print_timing: id 2 | task 15263 | eval time = 15998.96 ms / 352 tokens ( 45.58 ms per token, 21.94 tokens per second) 13.01.551.751 I slot print_timing: id 2 | task 15263 | total time = 16467.38 ms / 431 tokens 13.01.551.751 I slot print_timing: id 2 | task 15263 | graphs reused = 14530 13.01.551.752 I slot print_timing: id 2 | task 15263 | graph reallocs = 0 / 0 (same size) / (changed size) 13.01.551.824 I slot release: id 2 | task 15263 | stop processing: n_tokens = 1401, truncated = 0 13.01.955.919 I slot print_timing: id 3 | task 15389 | n_gen = 236, tg = 23.13 t/s, tg_3s = 23.30 t/s 13.03.568.136 I slot print_timing: id 1 | task 15554 | n_gen = 100, tg = 21.24 t/s, tg_3s = 21.46 t/s 13.04.138.539 I slot print_timing: id 0 | task 15229 | n_gen = 430, tg = 21.09 t/s, tg_3s = 18.39 t/s 13.05.003.942 I slot print_timing: id 3 | task 15389 | n_gen = 289, tg = 21.80 t/s, tg_3s = 17.39 t/s 13.05.693.388 I slot print_timing: id 3 | task 15389 | prompt eval time = 506.25 ms / 109 tokens ( 4.64 ms per token, 215.31 tokens per second) 13.05.693.397 I slot print_timing: id 3 | task 15389 | eval time = 13897.62 ms / 301 tokens ( 46.33 ms per token, 21.59 tokens per second) 13.05.693.398 I slot print_timing: id 3 | task 15389 | total time = 14403.87 ms / 410 tokens 13.05.693.399 I slot print_timing: id 3 | task 15389 | graphs reused = 14530 13.05.693.400 I slot print_timing: id 3 | task 15389 | graph reallocs = 0 / 0 (same size) / (changed size) 13.05.693.464 I slot release: id 3 | task 15389 | stop processing: n_tokens = 1380, truncated = 0 13.06.167.399 I slot print_timing: id 1 | task 15554 | prompt eval time = 431.47 ms / 65 tokens ( 6.64 ms per token, 150.65 tokens per second) 13.06.167.407 I slot print_timing: id 1 | task 15554 | eval time = 7259.44 ms / 152 tokens ( 48.08 ms per token, 20.80 tokens per second) 13.06.167.408 I slot print_timing: id 1 | task 15554 | total time = 7690.91 ms / 217 tokens 13.06.167.408 I slot print_timing: id 1 | task 15554 | graphs reused = 14544 13.06.167.409 I slot print_timing: id 1 | task 15554 | graph reallocs = 0 / 0 (same size) / (changed size) 13.06.167.477 I slot release: id 1 | task 15554 | stop processing: n_tokens = 1187, truncated = 0 13.07.143.351 I slot print_timing: id 0 | task 15229 | n_gen = 522, tg = 22.32 t/s, tg_3s = 30.62 t/s 13.10.144.054 I slot print_timing: id 0 | task 15229 | n_gen = 676, tg = 25.62 t/s, tg_3s = 51.32 t/s 13.13.151.384 I slot print_timing: id 0 | task 15229 | n_gen = 830, tg = 28.24 t/s, tg_3s = 51.21 t/s 13.16.170.486 I slot print_timing: id 0 | task 15229 | n_gen = 984, tg = 30.37 t/s, tg_3s = 51.01 t/s 13.16.956.344 I slot print_timing: id 0 | task 15229 | prompt eval time = 539.37 ms / 134 tokens ( 4.03 ms per token, 248.44 tokens per second) 13.16.956.350 I slot print_timing: id 0 | task 15229 | eval time = 33157.46 ms / 1024 tokens ( 32.41 ms per token, 30.85 tokens per second) 13.16.956.351 I slot print_timing: id 0 | task 15229 | total time = 33696.83 ms / 1158 tokens 13.16.956.351 I slot print_timing: id 0 | task 15229 | graphs reused = 15093 13.16.956.352 I slot print_timing: id 0 | task 15229 | graph reallocs = 0 / 0 (same size) / (changed size) 13.16.956.402 I slot release: id 0 | task 15229 | stop processing: n_tokens = 2128, truncated = 0 13.16.975.475 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1401, t_last = 351600878803 13.16.975.613 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 24.603 MiB) 13.16.975.616 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 27.885 MiB) 13.16.975.618 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 19.024 MiB) 13.16.975.802 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 27.228 MiB) 13.16.975.968 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 26.244 MiB) 13.16.976.106 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 17.875 MiB) 13.16.976.291 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 18.695 MiB) 13.16.976.466 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 17.547 MiB) 13.16.976.603 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 19.516 MiB) 13.16.976.736 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 19.352 MiB) 13.16.976.858 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 21.649 MiB) 13.16.976.985 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 20.008 MiB) 13.16.992.432 I slot launch_slot_: id 2 | task 16260 | processing task, is_child = 0 13.16.992.577 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 18.531 MiB) 13.16.992.582 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 19.680 MiB) 13.16.992.731 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 23.618 MiB) 13.16.992.836 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 25.095 MiB) 13.16.992.967 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 23.782 MiB) 13.16.993.084 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 21.157 MiB) 13.16.993.196 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 20.993 MiB) 13.16.993.350 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 16.234 MiB) 13.16.993.537 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 22.661 MiB) 13.16.993.699 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 23.618 MiB) 13.16.993.825 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 19.680 MiB) 13.16.993.967 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 18.695 MiB) 13.16.994.109 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 25.423 MiB) 13.16.994.270 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 19.516 MiB) 13.16.994.451 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 24.439 MiB) 13.16.994.593 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 16.070 MiB) 13.17.018.997 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 26.900 MiB) 13.17.019.074 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 20.336 MiB) 13.17.019.184 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 23.618 MiB) 13.17.019.281 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 17.383 MiB) 13.17.019.389 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 20.172 MiB) 13.17.019.499 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 20.665 MiB) 13.17.019.629 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 24.275 MiB) 13.17.019.792 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 18.531 MiB) 13.17.019.901 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 23.126 MiB) 13.17.020.057 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 24.275 MiB) 13.17.020.203 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 24.275 MiB) 13.17.020.314 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 22.634 MiB) 13.17.020.442 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 23.290 MiB) 13.17.039.657 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 23.454 MiB) 13.17.039.729 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 17.219 MiB) 13.17.039.833 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 15.085 MiB) 13.17.039.945 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 29.034 MiB) 13.17.040.063 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 18.531 MiB) 13.17.040.185 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 16.562 MiB) 13.17.040.292 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 19.188 MiB) 13.17.040.435 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 24.111 MiB) 13.17.040.575 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 18.695 MiB) 13.17.040.718 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 20.500 MiB) 13.17.040.825 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 20.829 MiB) 13.17.040.944 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 18.367 MiB) 13.17.041.066 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 24.603 MiB) 13.17.041.199 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 21.485 MiB) 13.17.041.307 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 18.367 MiB) 13.17.041.417 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 26.080 MiB) 13.17.063.013 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1380, t_last = 351605020443 13.17.063.192 I slot launch_slot_: id 3 | task 16261 | processing task, is_child = 0 13.17.063.407 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1187, t_last = 351605494456 13.17.063.524 I slot launch_slot_: id 1 | task 16262 | processing task, is_child = 0 13.17.063.643 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 2128, t_last = 351616283381 13.17.063.798 I slot launch_slot_: id 0 | task 16263 | processing task, is_child = 0 13.21.423.059 I slot print_timing: id 0 | task 16263 | prompt processing, n_tokens = 351, progress = 0.40, t = 4.36 s / 80.52 tokens per second 13.21.554.145 I slot print_timing: id 1 | task 16262 | prompt processing, n_tokens = 336, progress = 0.39, t = 4.36 s / 77.09 tokens per second 13.21.555.382 I slot print_timing: id 2 | task 16260 | prompt processing, n_tokens = 578, progress = 0.84, t = 4.36 s / 132.63 tokens per second 13.21.557.761 I slot print_timing: id 3 | task 16261 | prompt processing, n_tokens = 546, progress = 0.80, t = 4.36 s / 125.30 tokens per second 13.23.630.073 I slot print_timing: id 0 | task 16263 | prompt processing, n_tokens = 768, progress = 0.89, t = 6.57 s / 116.96 tokens per second 13.23.761.426 I slot print_timing: id 1 | task 16262 | prompt processing, n_tokens = 745, progress = 0.87, t = 6.57 s / 113.47 tokens per second 13.23.763.673 I slot print_timing: id 2 | task 16260 | prompt processing, n_tokens = 687, progress = 0.99, t = 6.57 s / 104.64 tokens per second 13.23.766.124 I slot print_timing: id 3 | task 16261 | prompt processing, n_tokens = 679, progress = 0.99, t = 6.56 s / 103.43 tokens per second 13.24.397.156 I slot print_timing: id 0 | task 16263 | prompt processing, n_tokens = 863, progress = 1.00, t = 7.33 s / 117.69 tokens per second 13.24.398.490 I slot print_timing: id 1 | task 16262 | prompt processing, n_tokens = 848, progress = 1.00, t = 7.33 s / 115.65 tokens per second 13.24.490.511 I slot print_timing: id 2 | task 16260 | prompt eval time = 7332.01 ms / 691 tokens ( 10.61 ms per token, 94.24 tokens per second) 13.24.490.514 I slot print_timing: id 2 | task 16260 | eval time = 93.50 ms / 2 tokens ( 93.50 ms per token, 10.70 tokens per second) 13.24.490.515 I slot print_timing: id 2 | task 16260 | total time = 7425.51 ms / 693 tokens 13.24.490.515 I slot print_timing: id 2 | task 16260 | graphs reused = 15093 13.24.490.516 I slot print_timing: id 2 | task 16260 | graph reallocs = 0 / 0 (same size) / (changed size) 13.24.490.549 I slot release: id 2 | task 16260 | stop processing: n_tokens = 692, truncated = 0 13.24.490.640 I slot print_timing: id 3 | task 16261 | prompt eval time = 7331.63 ms / 683 tokens ( 10.73 ms per token, 93.16 tokens per second) 13.24.490.642 I slot print_timing: id 3 | task 16261 | eval time = 93.49 ms / 2 tokens ( 93.49 ms per token, 10.70 tokens per second) 13.24.490.642 I slot print_timing: id 3 | task 16261 | total time = 7425.12 ms / 685 tokens 13.24.490.643 I slot print_timing: id 3 | task 16261 | graphs reused = 15093 13.24.490.643 I slot print_timing: id 3 | task 16261 | graph reallocs = 0 / 0 (same size) / (changed size) 13.24.490.668 I slot release: id 3 | task 16261 | stop processing: n_tokens = 684, truncated = 0 13.24.524.303 I slot print_timing: id 0 | task 16263 | prompt eval time = 7426.50 ms / 867 tokens ( 8.57 ms per token, 116.74 tokens per second) 13.24.524.306 I slot print_timing: id 0 | task 16263 | eval time = 34.00 ms / 2 tokens ( 34.00 ms per token, 29.41 tokens per second) 13.24.524.306 I slot print_timing: id 0 | task 16263 | total time = 7460.50 ms / 869 tokens 13.24.524.306 I slot print_timing: id 0 | task 16263 | graphs reused = 15093 13.24.524.307 I slot print_timing: id 0 | task 16263 | graph reallocs = 0 / 0 (same size) / (changed size) 13.24.524.343 I slot release: id 0 | task 16263 | stop processing: n_tokens = 868, truncated = 0 13.24.524.431 I slot print_timing: id 1 | task 16262 | prompt eval time = 7425.97 ms / 852 tokens ( 8.72 ms per token, 114.73 tokens per second) 13.24.524.433 I slot print_timing: id 1 | task 16262 | eval time = 34.00 ms / 2 tokens ( 34.00 ms per token, 29.41 tokens per second) 13.24.524.433 I slot print_timing: id 1 | task 16262 | total time = 7459.97 ms / 854 tokens 13.24.524.434 I slot print_timing: id 1 | task 16262 | graphs reused = 15093 13.24.524.434 I slot print_timing: id 1 | task 16262 | graph reallocs = 0 / 0 (same size) / (changed size) 13.24.524.470 I slot release: id 1 | task 16262 | stop processing: n_tokens = 853, truncated = 0 13.24.524.473 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 692, t_last = 351623817529 13.24.524.540 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 28.541 MiB) 13.24.524.545 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 23.454 MiB) 13.24.524.546 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 20.500 MiB) 13.24.524.548 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 15.578 MiB) 13.24.524.549 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 18.695 MiB) 13.24.524.551 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 20.829 MiB) 13.24.530.911 I slot launch_slot_: id 2 | task 16271 | processing task, is_child = 0 13.24.530.981 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 237.813 MiB) 13.24.535.024 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 311.095 MiB) 13.24.546.730 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 684, t_last = 351623817647 13.24.546.853 I slot launch_slot_: id 3 | task 16272 | processing task, is_child = 0 13.24.546.979 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 868, t_last = 351623851322 13.24.547.076 I slot launch_slot_: id 0 | task 16273 | processing task, is_child = 0 13.24.547.139 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 853, t_last = 351623851449 13.24.547.235 I slot launch_slot_: id 1 | task 16274 | processing task, is_child = 0 13.28.804.384 I slot print_timing: id 0 | task 16273 | prompt processing, n_tokens = 589, progress = 0.86, t = 4.26 s / 138.36 tokens per second 13.29.040.187 I slot print_timing: id 1 | task 16274 | prompt processing, n_tokens = 589, progress = 0.81, t = 4.26 s / 138.36 tokens per second 13.29.042.601 I slot print_timing: id 2 | task 16271 | prompt processing, n_tokens = 589, progress = 0.81, t = 4.26 s / 138.36 tokens per second 13.29.045.007 I slot print_timing: id 3 | task 16272 | prompt processing, n_tokens = 589, progress = 0.87, t = 4.26 s / 138.37 tokens per second 13.30.168.183 I slot print_timing: id 0 | task 16273 | prompt processing, n_tokens = 682, progress = 0.99, t = 5.62 s / 121.33 tokens per second 13.30.208.167 I slot print_timing: id 1 | task 16274 | prompt processing, n_tokens = 726, progress = 0.99, t = 5.62 s / 129.16 tokens per second 13.30.209.495 I slot print_timing: id 2 | task 16271 | prompt processing, n_tokens = 721, progress = 0.99, t = 5.62 s / 128.28 tokens per second 13.30.210.860 I slot print_timing: id 3 | task 16272 | prompt processing, n_tokens = 676, progress = 0.99, t = 5.62 s / 120.28 tokens per second 13.30.355.284 I slot print_timing: id 0 | task 16273 | prompt eval time = 5765.26 ms / 686 tokens ( 8.40 ms per token, 118.99 tokens per second) 13.30.355.288 I slot print_timing: id 0 | task 16273 | eval time = 42.78 ms / 2 tokens ( 42.78 ms per token, 23.38 tokens per second) 13.30.355.289 I slot print_timing: id 0 | task 16273 | total time = 5808.04 ms / 688 tokens 13.30.355.289 I slot print_timing: id 0 | task 16273 | graphs reused = 15094 13.30.355.290 I slot print_timing: id 0 | task 16273 | graph reallocs = 0 / 0 (same size) / (changed size) 13.30.355.325 I slot release: id 0 | task 16273 | stop processing: n_tokens = 687, truncated = 0 13.30.355.410 I slot print_timing: id 1 | task 16274 | prompt eval time = 5765.24 ms / 730 tokens ( 7.90 ms per token, 126.62 tokens per second) 13.30.355.412 I slot print_timing: id 1 | task 16274 | eval time = 42.81 ms / 2 tokens ( 42.81 ms per token, 23.36 tokens per second) 13.30.355.413 I slot print_timing: id 1 | task 16274 | total time = 5808.05 ms / 732 tokens 13.30.355.413 I slot print_timing: id 1 | task 16274 | graphs reused = 15094 13.30.355.413 I slot print_timing: id 1 | task 16274 | graph reallocs = 0 / 0 (same size) / (changed size) 13.30.355.437 I slot release: id 1 | task 16274 | stop processing: n_tokens = 731, truncated = 0 13.30.355.524 I slot print_timing: id 2 | task 16271 | prompt eval time = 5765.25 ms / 725 tokens ( 7.95 ms per token, 125.75 tokens per second) 13.30.355.530 I slot print_timing: id 2 | task 16271 | eval time = 42.82 ms / 2 tokens ( 42.82 ms per token, 23.36 tokens per second) 13.30.355.530 I slot print_timing: id 2 | task 16271 | total time = 5808.07 ms / 727 tokens 13.30.355.530 I slot print_timing: id 2 | task 16271 | graphs reused = 15094 13.30.355.530 I slot print_timing: id 2 | task 16271 | graph reallocs = 0 / 0 (same size) / (changed size) 13.30.355.553 I slot release: id 2 | task 16271 | stop processing: n_tokens = 726, truncated = 0 13.30.355.641 I slot print_timing: id 3 | task 16272 | prompt eval time = 5765.05 ms / 680 tokens ( 8.48 ms per token, 117.95 tokens per second) 13.30.355.643 I slot print_timing: id 3 | task 16272 | eval time = 42.84 ms / 2 tokens ( 42.84 ms per token, 23.34 tokens per second) 13.30.355.643 I slot print_timing: id 3 | task 16272 | total time = 5807.89 ms / 682 tokens 13.30.355.644 I slot print_timing: id 3 | task 16272 | graphs reused = 15094 13.30.355.644 I slot print_timing: id 3 | task 16272 | graph reallocs = 0 / 0 (same size) / (changed size) 13.30.355.665 I slot release: id 3 | task 16272 | stop processing: n_tokens = 681, truncated = 0 13.30.365.144 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.875 (> 0.100 thold), f_keep = 0.894 13.30.365.252 I slot launch_slot_: id 0 | task 16281 | processing task, is_child = 0 13.30.365.318 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.075 MiB) 13.30.379.284 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.458 MiB) 13.30.386.126 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 731, t_last = 351629682416 13.30.386.241 I slot launch_slot_: id 1 | task 16282 | processing task, is_child = 0 13.30.386.349 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 726, t_last = 351629682532 13.30.386.443 I slot launch_slot_: id 2 | task 16283 | processing task, is_child = 0 13.30.386.495 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 681, t_last = 351629682644 13.30.386.593 I slot launch_slot_: id 3 | task 16284 | processing task, is_child = 0 13.34.302.070 I slot print_timing: id 0 | task 16281 | prompt eval time = 2120.06 ms / 88 tokens ( 24.09 ms per token, 41.51 tokens per second) 13.34.302.073 I slot print_timing: id 0 | task 16281 | eval time = 1795.40 ms / 2 tokens ( 1795.40 ms per token, 0.56 tokens per second) 13.34.302.073 I slot print_timing: id 0 | task 16281 | total time = 3915.47 ms / 90 tokens 13.34.302.074 I slot print_timing: id 0 | task 16281 | graphs reused = 15094 13.34.302.074 I slot print_timing: id 0 | task 16281 | graph reallocs = 0 / 0 (same size) / (changed size) 13.34.302.114 I slot release: id 0 | task 16281 | stop processing: n_tokens = 703, truncated = 0 13.34.302.126 I slot print_timing: id 1 | task 16282 | prompt processing, n_tokens = 344, progress = 0.40, t = 3.91 s / 87.89 tokens per second 13.34.304.885 I slot print_timing: id 2 | task 16283 | prompt processing, n_tokens = 648, progress = 0.84, t = 3.91 s / 165.56 tokens per second 13.34.306.411 I slot print_timing: id 3 | task 16284 | prompt processing, n_tokens = 648, progress = 0.85, t = 3.91 s / 165.56 tokens per second 13.35.121.049 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 703, t_last = 351633629093 13.35.722.273 I slot launch_slot_: id 0 | task 16289 | processing task, is_child = 0 13.35.722.417 I slot print_timing: id 1 | task 16282 | prompt processing, n_tokens = 740, progress = 0.86, t = 4.73 s / 156.34 tokens per second 13.35.724.219 I slot print_timing: id 2 | task 16283 | prompt processing, n_tokens = 767, progress = 0.99, t = 4.73 s / 162.05 tokens per second 13.35.725.595 I slot print_timing: id 3 | task 16284 | prompt processing, n_tokens = 757, progress = 0.99, t = 4.73 s / 159.94 tokens per second 13.36.594.026 I slot print_timing: id 1 | task 16282 | prompt processing, n_tokens = 856, progress = 1.00, t = 6.21 s / 137.94 tokens per second 13.37.186.643 I slot print_timing: id 2 | task 16283 | prompt eval time = 6205.45 ms / 771 tokens ( 8.05 ms per token, 124.25 tokens per second) 13.37.186.649 I slot print_timing: id 2 | task 16283 | eval time = 593.19 ms / 2 tokens ( 593.19 ms per token, 1.69 tokens per second) 13.37.186.649 I slot print_timing: id 2 | task 16283 | total time = 6798.64 ms / 773 tokens 13.37.186.650 I slot print_timing: id 2 | task 16283 | graphs reused = 15094 13.37.186.650 I slot print_timing: id 2 | task 16283 | graph reallocs = 0 / 0 (same size) / (changed size) 13.37.186.688 I slot release: id 2 | task 16283 | stop processing: n_tokens = 772, truncated = 0 13.37.186.782 I slot print_timing: id 3 | task 16284 | prompt eval time = 6205.45 ms / 761 tokens ( 8.15 ms per token, 122.63 tokens per second) 13.37.186.783 I slot print_timing: id 3 | task 16284 | eval time = 593.23 ms / 2 tokens ( 593.23 ms per token, 1.69 tokens per second) 13.37.186.784 I slot print_timing: id 3 | task 16284 | total time = 6798.68 ms / 763 tokens 13.37.186.784 I slot print_timing: id 3 | task 16284 | graphs reused = 15094 13.37.186.784 I slot print_timing: id 3 | task 16284 | graph reallocs = 0 / 0 (same size) / (changed size) 13.37.186.809 I slot release: id 3 | task 16284 | stop processing: n_tokens = 762, truncated = 0 13.37.227.373 I slot print_timing: id 1 | task 16282 | prompt eval time = 6798.66 ms / 860 tokens ( 7.91 ms per token, 126.50 tokens per second) 13.37.227.375 I slot print_timing: id 1 | task 16282 | eval time = 40.81 ms / 2 tokens ( 40.81 ms per token, 24.50 tokens per second) 13.37.227.375 I slot print_timing: id 1 | task 16282 | total time = 6839.47 ms / 862 tokens 13.37.227.376 I slot print_timing: id 1 | task 16282 | graphs reused = 15094 13.37.227.376 I slot print_timing: id 1 | task 16282 | graph reallocs = 0 / 0 (same size) / (changed size) 13.37.227.411 I slot release: id 1 | task 16282 | stop processing: n_tokens = 861, truncated = 0 13.37.227.416 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 772, t_last = 351636513667 13.37.227.488 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.042 MiB) 13.37.234.166 I slot launch_slot_: id 2 | task 16293 | processing task, is_child = 0 13.37.242.509 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.362 MiB) 13.37.248.509 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 762, t_last = 351636513788 13.37.248.623 I slot launch_slot_: id 3 | task 16294 | processing task, is_child = 0 13.37.248.694 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 861, t_last = 351636554390 13.37.248.796 I slot launch_slot_: id 1 | task 16295 | processing task, is_child = 0 13.40.002.820 I slot print_timing: id 0 | task 16289 | prompt processing, n_tokens = 880, progress = 1.00, t = 4.28 s / 205.58 tokens per second 13.41.479.012 I slot print_timing: id 1 | task 16295 | prompt processing, n_tokens = 655, progress = 0.41, t = 4.23 s / 154.88 tokens per second 13.41.480.713 I slot print_timing: id 2 | task 16293 | prompt processing, n_tokens = 403, progress = 0.44, t = 4.23 s / 95.30 tokens per second 13.41.482.242 I slot print_timing: id 3 | task 16294 | prompt processing, n_tokens = 295, progress = 0.36, t = 4.23 s / 69.76 tokens per second 13.44.175.996 I slot print_timing: id 0 | task 16289 | prompt eval time = 5756.69 ms / 884 tokens ( 6.51 ms per token, 153.56 tokens per second) 13.44.176.002 I slot print_timing: id 0 | task 16289 | eval time = 2697.00 ms / 2 tokens ( 2697.00 ms per token, 0.37 tokens per second) 13.44.176.002 I slot print_timing: id 0 | task 16289 | total time = 8453.70 ms / 886 tokens 13.44.176.003 I slot print_timing: id 0 | task 16289 | graphs reused = 15095 13.44.176.003 I slot print_timing: id 0 | task 16289 | graph reallocs = 0 / 0 (same size) / (changed size) 13.44.176.045 I slot release: id 0 | task 16289 | stop processing: n_tokens = 885, truncated = 0 13.44.176.059 I slot print_timing: id 1 | task 16295 | prompt processing, n_tokens = 1097, progress = 0.68, t = 6.93 s / 158.39 tokens per second 13.44.177.784 I slot print_timing: id 2 | task 16293 | prompt processing, n_tokens = 781, progress = 0.85, t = 6.93 s / 112.77 tokens per second 13.44.179.937 I slot print_timing: id 3 | task 16294 | prompt processing, n_tokens = 655, progress = 0.81, t = 6.93 s / 94.57 tokens per second 13.45.730.280 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 885, t_last = 351643503024 13.45.730.364 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.047 MiB) 13.45.849.088 I slot launch_slot_: id 0 | task 16301 | processing task, is_child = 0 13.45.849.219 I slot print_timing: id 1 | task 16295 | prompt processing, n_tokens = 1609, progress = 1.00, t = 8.48 s / 189.73 tokens per second 13.45.851.228 I slot print_timing: id 2 | task 16293 | prompt processing, n_tokens = 915, progress = 1.00, t = 8.48 s / 107.90 tokens per second 13.45.853.000 I slot print_timing: id 3 | task 16294 | prompt processing, n_tokens = 807, progress = 1.00, t = 8.48 s / 95.16 tokens per second 13.46.774.164 I slot print_timing: id 1 | task 16295 | prompt eval time = 9068.70 ms / 1613 tokens ( 5.62 ms per token, 177.86 tokens per second) 13.46.774.169 I slot print_timing: id 1 | task 16295 | eval time = 455.54 ms / 2 tokens ( 455.54 ms per token, 2.20 tokens per second) 13.46.774.169 I slot print_timing: id 1 | task 16295 | total time = 9524.24 ms / 1615 tokens 13.46.774.170 I slot print_timing: id 1 | task 16295 | graphs reused = 15095 13.46.774.170 I slot print_timing: id 1 | task 16295 | graph reallocs = 0 / 0 (same size) / (changed size) 13.46.774.236 I slot release: id 1 | task 16295 | stop processing: n_tokens = 1614, truncated = 0 13.46.774.341 I slot print_timing: id 2 | task 16293 | prompt eval time = 9068.69 ms / 919 tokens ( 9.87 ms per token, 101.34 tokens per second) 13.46.774.343 I slot print_timing: id 2 | task 16293 | eval time = 455.61 ms / 2 tokens ( 455.61 ms per token, 2.19 tokens per second) 13.46.774.344 I slot print_timing: id 2 | task 16293 | total time = 9524.31 ms / 921 tokens 13.46.774.344 I slot print_timing: id 2 | task 16293 | graphs reused = 15095 13.46.774.344 I slot print_timing: id 2 | task 16293 | graph reallocs = 0 / 0 (same size) / (changed size) 13.46.774.374 I slot release: id 2 | task 16293 | stop processing: n_tokens = 920, truncated = 0 13.46.774.503 I slot print_timing: id 3 | task 16294 | prompt eval time = 9068.71 ms / 811 tokens ( 11.18 ms per token, 89.43 tokens per second) 13.46.774.505 I slot print_timing: id 3 | task 16294 | eval time = 455.67 ms / 2 tokens ( 455.67 ms per token, 2.19 tokens per second) 13.46.774.506 I slot print_timing: id 3 | task 16294 | total time = 9524.38 ms / 813 tokens 13.46.774.506 I slot print_timing: id 3 | task 16294 | graphs reused = 15095 13.46.774.507 I slot print_timing: id 3 | task 16294 | graph reallocs = 0 / 0 (same size) / (changed size) 13.46.774.537 I slot release: id 3 | task 16294 | stop processing: n_tokens = 812, truncated = 0 13.47.089.615 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1614, t_last = 351646101216 13.47.773.379 I slot launch_slot_: id 1 | task 16306 | processing task, is_child = 0 13.47.773.468 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 275.911 MiB) 13.47.789.705 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 920, t_last = 351646101353 13.47.789.834 I slot launch_slot_: id 2 | task 16307 | processing task, is_child = 0 13.47.789.896 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 812, t_last = 351646101516 13.47.790.001 I slot launch_slot_: id 3 | task 16308 | processing task, is_child = 0 13.51.472.885 I slot print_timing: id 0 | task 16301 | prompt eval time = 3809.04 ms / 827 tokens ( 4.61 ms per token, 217.11 tokens per second) 13.51.472.888 I slot print_timing: id 0 | task 16301 | eval time = 1814.73 ms / 2 tokens ( 1814.73 ms per token, 0.55 tokens per second) 13.51.472.888 I slot print_timing: id 0 | task 16301 | total time = 5623.78 ms / 829 tokens 13.51.472.889 I slot print_timing: id 0 | task 16301 | graphs reused = 15095 13.51.472.889 I slot print_timing: id 0 | task 16301 | graph reallocs = 0 / 0 (same size) / (changed size) 13.51.472.938 I slot release: id 0 | task 16301 | stop processing: n_tokens = 828, truncated = 0 13.51.472.950 I slot print_timing: id 1 | task 16306 | prompt processing, n_tokens = 527, progress = 0.84, t = 3.68 s / 143.14 tokens per second 13.51.474.605 I slot print_timing: id 2 | task 16307 | prompt processing, n_tokens = 527, progress = 0.81, t = 3.68 s / 143.15 tokens per second 13.51.475.955 I slot print_timing: id 3 | task 16308 | prompt processing, n_tokens = 264, progress = 0.34, t = 3.68 s / 71.71 tokens per second 13.52.334.246 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 828, t_last = 351650799917 13.52.334.339 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 275.008 MiB) 13.52.963.110 I slot launch_slot_: id 0 | task 16313 | processing task, is_child = 0 13.52.963.278 I slot print_timing: id 1 | task 16306 | prompt processing, n_tokens = 623, progress = 0.99, t = 4.54 s / 137.13 tokens per second 13.52.965.205 I slot print_timing: id 2 | task 16307 | prompt processing, n_tokens = 650, progress = 0.99, t = 4.54 s / 143.08 tokens per second 13.52.966.664 I slot print_timing: id 3 | task 16308 | prompt processing, n_tokens = 680, progress = 0.87, t = 4.54 s / 149.69 tokens per second 13.53.753.373 I slot print_timing: id 3 | task 16308 | prompt processing, n_tokens = 776, progress = 0.99, t = 5.96 s / 130.17 tokens per second 13.53.900.774 I slot print_timing: id 1 | task 16306 | prompt eval time = 5961.81 ms / 627 tokens ( 9.51 ms per token, 105.17 tokens per second) 13.53.900.779 I slot print_timing: id 1 | task 16306 | eval time = 147.84 ms / 2 tokens ( 147.84 ms per token, 6.76 tokens per second) 13.53.900.780 I slot print_timing: id 1 | task 16306 | total time = 6109.64 ms / 629 tokens 13.53.900.780 I slot print_timing: id 1 | task 16306 | graphs reused = 15095 13.53.900.781 I slot print_timing: id 1 | task 16306 | graph reallocs = 0 / 0 (same size) / (changed size) 13.53.900.814 I slot release: id 1 | task 16306 | stop processing: n_tokens = 628, truncated = 0 13.53.900.902 I slot print_timing: id 2 | task 16307 | prompt eval time = 5961.74 ms / 654 tokens ( 9.12 ms per token, 109.70 tokens per second) 13.53.900.904 I slot print_timing: id 2 | task 16307 | eval time = 147.86 ms / 2 tokens ( 147.86 ms per token, 6.76 tokens per second) 13.53.900.905 I slot print_timing: id 2 | task 16307 | total time = 6109.60 ms / 656 tokens 13.53.900.905 I slot print_timing: id 2 | task 16307 | graphs reused = 15095 13.53.900.905 I slot print_timing: id 2 | task 16307 | graph reallocs = 0 / 0 (same size) / (changed size) 13.53.900.929 I slot release: id 2 | task 16307 | stop processing: n_tokens = 655, truncated = 0 13.54.668.083 I slot print_timing: id 3 | task 16308 | prompt eval time = 6109.65 ms / 780 tokens ( 7.83 ms per token, 127.67 tokens per second) 13.54.668.086 I slot print_timing: id 3 | task 16308 | eval time = 767.02 ms / 2 tokens ( 767.02 ms per token, 1.30 tokens per second) 13.54.668.086 I slot print_timing: id 3 | task 16308 | total time = 6876.67 ms / 782 tokens 13.54.668.087 I slot print_timing: id 3 | task 16308 | graphs reused = 15095 13.54.668.087 I slot print_timing: id 3 | task 16308 | graph reallocs = 0 / 0 (same size) / (changed size) 13.54.668.127 I slot release: id 3 | task 16308 | stop processing: n_tokens = 781, truncated = 0 13.54.668.136 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.868 (> 0.100 thold), f_keep = 0.879 13.54.668.204 I slot launch_slot_: id 1 | task 16317 | processing task, is_child = 0 13.54.668.287 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.841 MiB) 13.54.687.396 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.871 (> 0.100 thold), f_keep = 0.843 13.54.687.486 I slot launch_slot_: id 2 | task 16318 | processing task, is_child = 0 13.54.687.561 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 781, t_last = 351653995106 13.54.687.668 I slot launch_slot_: id 3 | task 16319 | processing task, is_child = 0 13.56.258.767 I slot print_timing: id 0 | task 16313 | prompt eval time = 3234.70 ms / 631 tokens ( 5.13 ms per token, 195.07 tokens per second) 13.56.258.769 I slot print_timing: id 0 | task 16313 | eval time = 60.94 ms / 2 tokens ( 60.94 ms per token, 16.41 tokens per second) 13.56.258.770 I slot print_timing: id 0 | task 16313 | total time = 3295.63 ms / 633 tokens 13.56.258.770 I slot print_timing: id 0 | task 16313 | graphs reused = 15095 13.56.258.771 I slot print_timing: id 0 | task 16313 | graph reallocs = 0 / 0 (same size) / (changed size) 13.56.258.801 I slot release: id 0 | task 16313 | stop processing: n_tokens = 632, truncated = 0 13.56.258.888 I slot print_timing: id 1 | task 16317 | prompt eval time = 1509.07 ms / 84 tokens ( 17.97 ms per token, 55.66 tokens per second) 13.56.258.889 I slot print_timing: id 1 | task 16317 | eval time = 60.96 ms / 2 tokens ( 60.96 ms per token, 16.40 tokens per second) 13.56.258.890 I slot print_timing: id 1 | task 16317 | total time = 1570.03 ms / 86 tokens 13.56.258.890 I slot print_timing: id 1 | task 16317 | graphs reused = 15095 13.56.258.890 I slot print_timing: id 1 | task 16317 | graph reallocs = 0 / 0 (same size) / (changed size) 13.56.258.910 I slot release: id 1 | task 16317 | stop processing: n_tokens = 637, truncated = 0 13.56.258.996 I slot print_timing: id 2 | task 16318 | prompt eval time = 1508.01 ms / 82 tokens ( 18.39 ms per token, 54.38 tokens per second) 13.56.258.999 I slot print_timing: id 2 | task 16318 | eval time = 60.97 ms / 2 tokens ( 60.97 ms per token, 16.40 tokens per second) 13.56.259.000 I slot print_timing: id 2 | task 16318 | total time = 1568.97 ms / 84 tokens 13.56.259.000 I slot print_timing: id 2 | task 16318 | graphs reused = 15095 13.56.259.000 I slot print_timing: id 2 | task 16318 | graph reallocs = 0 / 0 (same size) / (changed size) 13.56.259.019 I slot release: id 2 | task 16318 | stop processing: n_tokens = 635, truncated = 0 13.57.046.167 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 632, t_last = 351655585780 13.57.046.234 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 275.719 MiB) 13.57.382.944 I slot launch_slot_: id 0 | task 16325 | processing task, is_child = 0 13.57.395.500 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 272.272 MiB) 13.57.400.768 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 351655585890 13.57.400.909 I slot launch_slot_: id 1 | task 16326 | processing task, is_child = 0 13.57.400.976 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 635, t_last = 351655585998 13.57.401.071 I slot launch_slot_: id 2 | task 16327 | processing task, is_child = 0 13.59.059.760 I slot print_timing: id 3 | task 16319 | prompt eval time = 3393.34 ms / 760 tokens ( 4.46 ms per token, 223.97 tokens per second) 13.59.059.765 I slot print_timing: id 3 | task 16319 | eval time = 975.26 ms / 2 tokens ( 975.26 ms per token, 1.03 tokens per second) 13.59.059.766 I slot print_timing: id 3 | task 16319 | total time = 4368.60 ms / 762 tokens 13.59.059.766 I slot print_timing: id 3 | task 16319 | graphs reused = 15095 13.59.059.767 I slot print_timing: id 3 | task 16319 | graph reallocs = 0 / 0 (same size) / (changed size) 13.59.059.805 I slot release: id 3 | task 16319 | stop processing: n_tokens = 761, truncated = 0 13.59.566.087 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 761, t_last = 351658386784 13.59.692.249 I slot launch_slot_: id 3 | task 16331 | processing task, is_child = 0 14.02.085.818 I slot print_timing: id 0 | task 16325 | prompt processing, n_tokens = 741, progress = 0.87, t = 4.68 s / 158.17 tokens per second 14.02.207.821 I slot print_timing: id 1 | task 16326 | prompt processing, n_tokens = 741, progress = 0.85, t = 4.68 s / 158.18 tokens per second 14.02.210.071 I slot print_timing: id 2 | task 16327 | prompt processing, n_tokens = 741, progress = 0.83, t = 4.68 s / 158.18 tokens per second 14.03.574.018 I slot print_timing: id 0 | task 16325 | prompt processing, n_tokens = 848, progress = 1.00, t = 6.17 s / 137.37 tokens per second 14.03.724.256 I slot print_timing: id 1 | task 16326 | prompt processing, n_tokens = 867, progress = 1.00, t = 6.17 s / 140.45 tokens per second 14.03.726.618 I slot print_timing: id 2 | task 16327 | prompt processing, n_tokens = 889, progress = 1.00, t = 6.17 s / 144.02 tokens per second 14.03.727.865 I slot print_timing: id 3 | task 16331 | prompt processing, n_tokens = 298, progress = 0.35, t = 3.88 s / 76.86 tokens per second 14.04.072.079 I slot print_timing: id 3 | task 16331 | prompt processing, n_tokens = 345, progress = 0.40, t = 4.38 s / 78.86 tokens per second 14.04.867.433 I slot print_timing: id 0 | task 16325 | prompt eval time = 6670.79 ms / 852 tokens ( 7.83 ms per token, 127.72 tokens per second) 14.04.867.436 I slot print_timing: id 0 | task 16325 | eval time = 795.56 ms / 2 tokens ( 795.56 ms per token, 1.26 tokens per second) 14.04.867.436 I slot print_timing: id 0 | task 16325 | total time = 7466.35 ms / 854 tokens 14.04.867.437 I slot print_timing: id 0 | task 16325 | graphs reused = 15095 14.04.867.437 I slot print_timing: id 0 | task 16325 | graph reallocs = 0 / 0 (same size) / (changed size) 14.04.867.480 I slot release: id 0 | task 16325 | stop processing: n_tokens = 853, truncated = 0 14.04.867.582 I slot print_timing: id 1 | task 16326 | prompt eval time = 6670.79 ms / 871 tokens ( 7.66 ms per token, 130.57 tokens per second) 14.04.867.583 I slot print_timing: id 1 | task 16326 | eval time = 795.62 ms / 2 tokens ( 795.62 ms per token, 1.26 tokens per second) 14.04.867.583 I slot print_timing: id 1 | task 16326 | total time = 7466.41 ms / 873 tokens 14.04.867.584 I slot print_timing: id 1 | task 16326 | graphs reused = 15095 14.04.867.584 I slot print_timing: id 1 | task 16326 | graph reallocs = 0 / 0 (same size) / (changed size) 14.04.867.605 I slot release: id 1 | task 16326 | stop processing: n_tokens = 872, truncated = 0 14.04.867.728 I slot print_timing: id 2 | task 16327 | prompt eval time = 6670.79 ms / 893 tokens ( 7.47 ms per token, 133.87 tokens per second) 14.04.867.731 I slot print_timing: id 2 | task 16327 | eval time = 795.66 ms / 2 tokens ( 795.66 ms per token, 1.26 tokens per second) 14.04.867.731 I slot print_timing: id 2 | task 16327 | total time = 7466.45 ms / 895 tokens 14.04.867.732 I slot print_timing: id 2 | task 16327 | graphs reused = 15095 14.04.867.732 I slot print_timing: id 2 | task 16327 | graph reallocs = 0 / 0 (same size) / (changed size) 14.04.867.758 I slot release: id 2 | task 16327 | stop processing: n_tokens = 894, truncated = 0 14.04.867.765 I slot print_timing: id 3 | task 16331 | prompt processing, n_tokens = 741, progress = 0.86, t = 5.17 s / 143.31 tokens per second 14.04.875.345 I slot print_timing: id 3 | task 16331 | prompt processing, n_tokens = 857, progress = 1.00, t = 5.18 s / 165.49 tokens per second 14.05.298.129 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.892 (> 0.100 thold), f_keep = 0.898 14.05.298.212 I slot launch_slot_: id 0 | task 16338 | processing task, is_child = 0 14.05.298.287 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 344.980 MiB) 14.05.315.986 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 872, t_last = 351664194584 14.05.316.121 I slot launch_slot_: id 1 | task 16339 | processing task, is_child = 0 14.05.316.187 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 894, t_last = 351664194737 14.05.316.311 I slot launch_slot_: id 2 | task 16340 | processing task, is_child = 0 14.06.316.321 I slot print_timing: id 3 | task 16331 | prompt eval time = 5601.46 ms / 861 tokens ( 6.51 ms per token, 153.71 tokens per second) 14.06.316.323 I slot print_timing: id 3 | task 16331 | eval time = 1018.19 ms / 2 tokens ( 1018.19 ms per token, 0.98 tokens per second) 14.06.316.324 I slot print_timing: id 3 | task 16331 | total time = 6619.66 ms / 863 tokens 14.06.316.324 I slot print_timing: id 3 | task 16331 | graphs reused = 15095 14.06.316.325 I slot print_timing: id 3 | task 16331 | graph reallocs = 0 / 0 (same size) / (changed size) 14.06.316.360 I slot release: id 3 | task 16331 | stop processing: n_tokens = 862, truncated = 0 14.07.136.069 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 862, t_last = 351665643340 14.07.136.156 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 277.005 MiB) 14.07.145.781 I slot launch_slot_: id 3 | task 16343 | processing task, is_child = 0 14.08.641.212 I slot print_timing: id 0 | task 16338 | prompt eval time = 1819.75 ms / 93 tokens ( 19.57 ms per token, 51.11 tokens per second) 14.08.641.217 I slot print_timing: id 0 | task 16338 | eval time = 1505.13 ms / 2 tokens ( 1505.13 ms per token, 0.66 tokens per second) 14.08.641.218 I slot print_timing: id 0 | task 16338 | total time = 3324.88 ms / 95 tokens 14.08.641.218 I slot print_timing: id 0 | task 16338 | graphs reused = 15095 14.08.641.219 I slot print_timing: id 0 | task 16338 | graph reallocs = 0 / 0 (same size) / (changed size) 14.08.641.262 I slot release: id 0 | task 16338 | stop processing: n_tokens = 860, truncated = 0 14.08.641.275 I slot print_timing: id 1 | task 16339 | prompt processing, n_tokens = 390, progress = 0.43, t = 3.32 s / 117.34 tokens per second 14.08.642.359 I slot print_timing: id 2 | task 16340 | prompt processing, n_tokens = 617, progress = 0.83, t = 3.32 s / 185.65 tokens per second 14.09.830.513 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 860, t_last = 351667968241 14.09.830.612 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.276 MiB) 14.10.048.423 I slot launch_slot_: id 0 | task 16346 | processing task, is_child = 0 14.10.048.586 I slot print_timing: id 1 | task 16339 | prompt processing, n_tokens = 686, progress = 0.76, t = 4.51 s / 152.00 tokens per second 14.10.051.049 I slot print_timing: id 2 | task 16340 | prompt processing, n_tokens = 740, progress = 0.99, t = 4.51 s / 163.97 tokens per second 14.11.155.946 I slot print_timing: id 1 | task 16339 | prompt processing, n_tokens = 902, progress = 1.00, t = 5.84 s / 154.50 tokens per second 14.11.157.849 I slot print_timing: id 3 | task 16343 | prompt processing, n_tokens = 281, progress = 0.35, t = 4.01 s / 70.09 tokens per second 14.12.425.647 I slot print_timing: id 2 | task 16340 | prompt eval time = 5838.11 ms / 744 tokens ( 7.85 ms per token, 127.44 tokens per second) 14.12.425.650 I slot print_timing: id 2 | task 16340 | eval time = 1269.98 ms / 2 tokens ( 1269.98 ms per token, 0.79 tokens per second) 14.12.425.651 I slot print_timing: id 2 | task 16340 | total time = 7108.09 ms / 746 tokens 14.12.425.651 I slot print_timing: id 2 | task 16340 | graphs reused = 15095 14.12.425.652 I slot print_timing: id 2 | task 16340 | graph reallocs = 0 / 0 (same size) / (changed size) 14.12.425.685 I slot release: id 2 | task 16340 | stop processing: n_tokens = 745, truncated = 0 14.12.425.707 I slot print_timing: id 3 | task 16343 | prompt processing, n_tokens = 686, progress = 0.86, t = 5.28 s / 129.95 tokens per second 14.13.208.348 I slot print_timing: id 1 | task 16339 | prompt eval time = 7108.08 ms / 906 tokens ( 7.85 ms per token, 127.46 tokens per second) 14.13.208.354 I slot print_timing: id 1 | task 16339 | eval time = 782.82 ms / 2 tokens ( 782.82 ms per token, 1.28 tokens per second) 14.13.208.354 I slot print_timing: id 1 | task 16339 | total time = 7890.90 ms / 908 tokens 14.13.208.355 I slot print_timing: id 1 | task 16339 | graphs reused = 15095 14.13.208.355 I slot print_timing: id 1 | task 16339 | graph reallocs = 0 / 0 (same size) / (changed size) 14.13.208.396 I slot release: id 1 | task 16339 | stop processing: n_tokens = 907, truncated = 0 14.13.208.403 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.890 (> 0.100 thold), f_keep = 0.784 14.13.208.477 I slot launch_slot_: id 1 | task 16350 | processing task, is_child = 0 14.13.223.015 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 745, t_last = 351671752664 14.13.223.150 I slot launch_slot_: id 2 | task 16351 | processing task, is_child = 0 14.13.223.157 I slot print_timing: id 0 | task 16346 | prompt processing, n_tokens = 378, progress = 0.42, t = 3.16 s / 119.63 tokens per second 14.13.225.578 I slot print_timing: id 3 | task 16343 | prompt processing, n_tokens = 793, progress = 0.99, t = 6.06 s / 130.82 tokens per second 14.14.470.646 I slot print_timing: id 0 | task 16346 | prompt processing, n_tokens = 686, progress = 0.77, t = 4.42 s / 155.13 tokens per second 14.15.523.668 I slot print_timing: id 3 | task 16343 | prompt eval time = 7324.28 ms / 797 tokens ( 9.19 ms per token, 108.82 tokens per second) 14.15.523.673 I slot print_timing: id 3 | task 16343 | eval time = 1053.03 ms / 2 tokens ( 1053.03 ms per token, 0.95 tokens per second) 14.15.523.674 I slot print_timing: id 3 | task 16343 | total time = 8377.31 ms / 799 tokens 14.15.523.674 I slot print_timing: id 3 | task 16343 | graphs reused = 15095 14.15.523.675 I slot print_timing: id 3 | task 16343 | graph reallocs = 0 / 0 (same size) / (changed size) 14.15.523.714 I slot release: id 3 | task 16343 | stop processing: n_tokens = 798, truncated = 0 14.15.523.725 I slot print_timing: id 0 | task 16346 | prompt processing, n_tokens = 890, progress = 1.00, t = 5.47 s / 162.56 tokens per second 14.15.921.393 I slot print_timing: id 1 | task 16350 | prompt eval time = 2299.25 ms / 88 tokens ( 26.13 ms per token, 38.27 tokens per second) 14.15.921.396 I slot print_timing: id 1 | task 16350 | eval time = 397.81 ms / 2 tokens ( 397.81 ms per token, 2.51 tokens per second) 14.15.921.397 I slot print_timing: id 1 | task 16350 | total time = 2697.06 ms / 90 tokens 14.15.921.397 I slot print_timing: id 1 | task 16350 | graphs reused = 15095 14.15.921.397 I slot print_timing: id 1 | task 16350 | graph reallocs = 0 / 0 (same size) / (changed size) 14.15.921.431 I slot release: id 1 | task 16350 | stop processing: n_tokens = 800, truncated = 0 14.15.921.439 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.889 14.15.921.517 I slot launch_slot_: id 1 | task 16355 | processing task, is_child = 0 14.15.921.592 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.302 MiB) 14.15.930.773 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 798, t_last = 351674850693 14.15.930.885 I slot launch_slot_: id 3 | task 16356 | processing task, is_child = 0 14.17.304.297 I slot print_timing: id 0 | task 16346 | prompt eval time = 5872.86 ms / 894 tokens ( 6.57 ms per token, 152.23 tokens per second) 14.17.304.299 I slot print_timing: id 0 | task 16346 | eval time = 1382.99 ms / 2 tokens ( 1382.99 ms per token, 0.72 tokens per second) 14.17.304.300 I slot print_timing: id 0 | task 16346 | total time = 7255.85 ms / 896 tokens 14.17.304.300 I slot print_timing: id 0 | task 16346 | graphs reused = 15095 14.17.304.300 I slot print_timing: id 0 | task 16346 | graph reallocs = 0 / 0 (same size) / (changed size) 14.17.304.341 I slot release: id 0 | task 16346 | stop processing: n_tokens = 895, truncated = 0 14.17.306.145 I slot print_timing: id 2 | task 16351 | prompt processing, n_tokens = 686, progress = 0.79, t = 4.08 s / 168.19 tokens per second 14.18.214.792 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 895, t_last = 351676631320 14.18.229.674 I slot launch_slot_: id 0 | task 16359 | processing task, is_child = 0 14.18.229.804 I slot print_timing: id 2 | task 16351 | prompt processing, n_tokens = 859, progress = 1.00, t = 4.99 s / 172.17 tokens per second 14.19.038.760 I slot print_timing: id 1 | task 16355 | prompt eval time = 2283.89 ms / 74 tokens ( 30.86 ms per token, 32.40 tokens per second) 14.19.038.765 I slot print_timing: id 1 | task 16355 | eval time = 823.97 ms / 2 tokens ( 823.97 ms per token, 1.21 tokens per second) 14.19.038.766 I slot print_timing: id 1 | task 16355 | total time = 3107.86 ms / 76 tokens 14.19.038.766 I slot print_timing: id 1 | task 16355 | graphs reused = 15095 14.19.038.767 I slot print_timing: id 1 | task 16355 | graph reallocs = 0 / 0 (same size) / (changed size) 14.19.038.801 I slot release: id 1 | task 16355 | stop processing: n_tokens = 786, truncated = 0 14.19.039.211 I slot print_timing: id 3 | task 16356 | prompt processing, n_tokens = 325, progress = 0.39, t = 3.11 s / 104.65 tokens per second 14.20.114.842 I slot print_timing: id 2 | task 16351 | prompt eval time = 5813.44 ms / 863 tokens ( 6.74 ms per token, 148.45 tokens per second) 14.20.114.845 I slot print_timing: id 2 | task 16351 | eval time = 1075.92 ms / 2 tokens ( 1075.92 ms per token, 0.93 tokens per second) 14.20.114.845 I slot print_timing: id 2 | task 16351 | total time = 6889.36 ms / 865 tokens 14.20.114.846 I slot print_timing: id 2 | task 16351 | graphs reused = 15095 14.20.114.846 I slot print_timing: id 2 | task 16351 | graph reallocs = 0 / 0 (same size) / (changed size) 14.20.114.888 I slot release: id 2 | task 16351 | stop processing: n_tokens = 864, truncated = 0 14.20.114.895 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 786, t_last = 351678365780 14.20.114.972 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.895 MiB) 14.20.126.880 I slot launch_slot_: id 1 | task 16362 | processing task, is_child = 0 14.20.138.713 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 864, t_last = 351679441867 14.20.138.856 I slot launch_slot_: id 2 | task 16363 | processing task, is_child = 0 14.20.139.107 I slot print_timing: id 3 | task 16356 | prompt processing, n_tokens = 678, progress = 0.81, t = 4.18 s / 162.14 tokens per second 14.21.460.351 I slot print_timing: id 3 | task 16356 | prompt processing, n_tokens = 837, progress = 1.00, t = 5.13 s / 163.03 tokens per second 14.23.227.534 I slot print_timing: id 0 | task 16359 | prompt processing, n_tokens = 678, progress = 0.85, t = 5.00 s / 135.66 tokens per second 14.23.229.023 I slot print_timing: id 1 | task 16362 | prompt processing, n_tokens = 202, progress = 0.24, t = 3.09 s / 65.40 tokens per second 14.23.229.035 I slot print_timing: id 2 | task 16363 | prompt processing, n_tokens = 393, progress = 0.33, t = 3.09 s / 127.25 tokens per second 14.24.444.910 I slot print_timing: id 3 | task 16356 | prompt eval time = 7294.37 ms / 841 tokens ( 8.67 ms per token, 115.29 tokens per second) 14.24.444.914 I slot print_timing: id 3 | task 16356 | eval time = 1217.39 ms / 2 tokens ( 1217.39 ms per token, 0.82 tokens per second) 14.24.444.914 I slot print_timing: id 3 | task 16356 | total time = 8511.76 ms / 843 tokens 14.24.444.915 I slot print_timing: id 3 | task 16356 | graphs reused = 15095 14.24.444.915 I slot print_timing: id 3 | task 16356 | graph reallocs = 0 / 0 (same size) / (changed size) 14.24.444.957 I slot release: id 3 | task 16356 | stop processing: n_tokens = 842, truncated = 0 14.24.444.968 I slot print_timing: id 0 | task 16359 | prompt processing, n_tokens = 794, progress = 0.99, t = 6.22 s / 127.75 tokens per second 14.24.446.777 I slot print_timing: id 1 | task 16362 | prompt processing, n_tokens = 313, progress = 0.38, t = 4.31 s / 72.69 tokens per second 14.24.448.506 I slot print_timing: id 2 | task 16363 | prompt processing, n_tokens = 686, progress = 0.57, t = 4.31 s / 159.32 tokens per second 14.26.028.567 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 842, t_last = 351683771936 14.26.028.648 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 345.910 MiB) 14.26.038.142 I slot launch_slot_: id 3 | task 16368 | processing task, is_child = 0 14.26.038.153 I slot print_timing: id 1 | task 16362 | prompt processing, n_tokens = 678, progress = 0.82, t = 5.89 s / 115.12 tokens per second 14.26.040.454 I slot print_timing: id 2 | task 16363 | prompt processing, n_tokens = 1028, progress = 0.86, t = 5.89 s / 174.55 tokens per second 14.27.107.513 I slot print_timing: id 0 | task 16359 | prompt eval time = 7798.87 ms / 798 tokens ( 9.77 ms per token, 102.32 tokens per second) 14.27.107.519 I slot print_timing: id 0 | task 16359 | eval time = 1078.95 ms / 2 tokens ( 1078.95 ms per token, 0.93 tokens per second) 14.27.107.519 I slot print_timing: id 0 | task 16359 | total time = 8877.82 ms / 800 tokens 14.27.107.520 I slot print_timing: id 0 | task 16359 | graphs reused = 15095 14.27.107.520 I slot print_timing: id 0 | task 16359 | graph reallocs = 0 / 0 (same size) / (changed size) 14.27.107.562 I slot release: id 0 | task 16359 | stop processing: n_tokens = 799, truncated = 0 14.27.107.573 I slot print_timing: id 1 | task 16362 | prompt processing, n_tokens = 825, progress = 1.00, t = 6.97 s / 118.39 tokens per second 14.27.109.324 I slot print_timing: id 2 | task 16363 | prompt processing, n_tokens = 1198, progress = 1.00, t = 6.97 s / 171.92 tokens per second 14.27.738.796 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 799, t_last = 351686434541 14.27.752.607 I slot launch_slot_: id 0 | task 16371 | processing task, is_child = 0 14.28.856.400 I slot print_timing: id 1 | task 16362 | prompt eval time = 7599.78 ms / 829 tokens ( 9.17 ms per token, 109.08 tokens per second) 14.28.856.406 I slot print_timing: id 1 | task 16362 | eval time = 1117.74 ms / 2 tokens ( 1117.74 ms per token, 0.89 tokens per second) 14.28.856.406 I slot print_timing: id 1 | task 16362 | total time = 8717.52 ms / 831 tokens 14.28.856.407 I slot print_timing: id 1 | task 16362 | graphs reused = 15095 14.28.856.407 I slot print_timing: id 1 | task 16362 | graph reallocs = 0 / 0 (same size) / (changed size) 14.28.856.442 I slot release: id 1 | task 16362 | stop processing: n_tokens = 830, truncated = 0 14.28.856.536 I slot print_timing: id 2 | task 16363 | prompt eval time = 7599.79 ms / 1202 tokens ( 6.32 ms per token, 158.16 tokens per second) 14.28.856.538 I slot print_timing: id 2 | task 16363 | eval time = 1117.75 ms / 2 tokens ( 1117.75 ms per token, 0.89 tokens per second) 14.28.856.539 I slot print_timing: id 2 | task 16363 | total time = 8717.54 ms / 1204 tokens 14.28.856.539 I slot print_timing: id 2 | task 16363 | graphs reused = 15095 14.28.856.539 I slot print_timing: id 2 | task 16363 | graph reallocs = 0 / 0 (same size) / (changed size) 14.28.856.581 I slot release: id 2 | task 16363 | stop processing: n_tokens = 1203, truncated = 0 14.29.413.131 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 830, t_last = 351688183421 14.29.413.226 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 311.040 MiB) 14.30.099.886 I slot launch_slot_: id 1 | task 16374 | processing task, is_child = 0 14.30.114.368 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.875 14.30.114.444 I slot launch_slot_: id 2 | task 16375 | processing task, is_child = 0 14.30.115.753 I slot print_timing: id 3 | task 16368 | prompt processing, n_tokens = 1028, progress = 0.85, t = 3.37 s / 305.01 tokens per second 14.31.455.896 I slot print_timing: id 0 | task 16371 | prompt processing, n_tokens = 609, progress = 0.54, t = 3.70 s / 164.45 tokens per second 14.31.778.615 I slot print_timing: id 3 | task 16368 | prompt processing, n_tokens = 1204, progress = 1.00, t = 5.41 s / 222.42 tokens per second 14.32.978.957 I slot print_timing: id 0 | task 16371 | prompt processing, n_tokens = 1028, progress = 0.91, t = 5.23 s / 196.71 tokens per second 14.34.155.579 I slot print_timing: id 2 | task 16375 | prompt eval time = 2864.24 ms / 109 tokens ( 26.28 ms per token, 38.06 tokens per second) 14.34.155.583 I slot print_timing: id 2 | task 16375 | eval time = 1176.76 ms / 2 tokens ( 1176.76 ms per token, 0.85 tokens per second) 14.34.155.584 I slot print_timing: id 2 | task 16375 | total time = 4040.99 ms / 111 tokens 14.34.155.585 I slot print_timing: id 2 | task 16375 | graphs reused = 15095 14.34.155.585 I slot print_timing: id 2 | task 16375 | graph reallocs = 0 / 0 (same size) / (changed size) 14.34.155.634 I slot release: id 2 | task 16375 | stop processing: n_tokens = 1163, truncated = 0 14.34.155.788 I slot print_timing: id 3 | task 16368 | prompt eval time = 6936.20 ms / 1208 tokens ( 5.74 ms per token, 174.16 tokens per second) 14.34.155.791 I slot print_timing: id 3 | task 16368 | eval time = 1176.84 ms / 2 tokens ( 1176.84 ms per token, 0.85 tokens per second) 14.34.155.791 I slot print_timing: id 3 | task 16368 | total time = 8113.04 ms / 1210 tokens 14.34.155.791 I slot print_timing: id 3 | task 16368 | graphs reused = 15095 14.34.155.792 I slot print_timing: id 3 | task 16368 | graph reallocs = 0 / 0 (same size) / (changed size) 14.34.155.831 I slot release: id 3 | task 16368 | stop processing: n_tokens = 1209, truncated = 0 14.34.155.839 I slot print_timing: id 0 | task 16371 | prompt processing, n_tokens = 1121, progress = 1.00, t = 6.40 s / 175.08 tokens per second 14.34.157.823 I slot print_timing: id 1 | task 16374 | prompt processing, n_tokens = 593, progress = 0.86, t = 4.04 s / 146.75 tokens per second 14.34.548.999 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1163, t_last = 351693482613 14.34.549.115 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 346.047 MiB) 14.34.560.512 I slot launch_slot_: id 2 | task 16380 | processing task, is_child = 0 14.34.560.606 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 347.087 MiB) 14.34.567.413 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1209, t_last = 351693482810 14.34.567.543 I slot launch_slot_: id 3 | task 16381 | processing task, is_child = 0 14.34.567.550 I slot print_timing: id 1 | task 16374 | prompt processing, n_tokens = 686, progress = 0.99, t = 4.43 s / 154.70 tokens per second 14.35.279.825 I slot print_timing: id 0 | task 16371 | prompt eval time = 6796.38 ms / 1125 tokens ( 6.04 ms per token, 165.53 tokens per second) 14.35.279.827 I slot print_timing: id 0 | task 16371 | eval time = 730.82 ms / 2 tokens ( 730.82 ms per token, 1.37 tokens per second) 14.35.279.828 I slot print_timing: id 0 | task 16371 | total time = 7527.20 ms / 1127 tokens 14.35.279.828 I slot print_timing: id 0 | task 16371 | graphs reused = 15095 14.35.279.828 I slot print_timing: id 0 | task 16371 | graph reallocs = 0 / 0 (same size) / (changed size) 14.35.279.875 I slot release: id 0 | task 16371 | stop processing: n_tokens = 1126, truncated = 0 14.35.975.155 I slot print_timing: id 1 | task 16374 | prompt eval time = 5165.55 ms / 690 tokens ( 7.49 ms per token, 133.58 tokens per second) 14.35.975.158 I slot print_timing: id 1 | task 16374 | eval time = 695.14 ms / 2 tokens ( 695.14 ms per token, 1.44 tokens per second) 14.35.975.159 I slot print_timing: id 1 | task 16374 | total time = 5860.69 ms / 692 tokens 14.35.975.159 I slot print_timing: id 1 | task 16374 | graphs reused = 15095 14.35.975.160 I slot print_timing: id 1 | task 16374 | graph reallocs = 0 / 0 (same size) / (changed size) 14.35.975.192 I slot release: id 1 | task 16374 | stop processing: n_tokens = 691, truncated = 0 14.35.975.206 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1126, t_last = 351694606854 14.35.989.345 I slot launch_slot_: id 0 | task 16384 | processing task, is_child = 0 14.35.997.471 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 691, t_last = 351695302171 14.35.997.588 I slot launch_slot_: id 1 | task 16385 | processing task, is_child = 0 14.39.470.501 I slot print_timing: id 2 | task 16380 | prompt processing, n_tokens = 704, progress = 0.99, t = 4.30 s / 163.61 tokens per second 14.39.473.126 I slot print_timing: id 3 | task 16381 | prompt processing, n_tokens = 661, progress = 0.83, t = 4.30 s / 153.62 tokens per second 14.41.568.932 I slot print_timing: id 0 | task 16384 | prompt processing, n_tokens = 661, progress = 0.86, t = 5.57 s / 118.65 tokens per second 14.41.570.409 I slot print_timing: id 1 | task 16385 | prompt processing, n_tokens = 577, progress = 0.82, t = 5.57 s / 103.57 tokens per second 14.41.572.441 I slot print_timing: id 3 | task 16381 | prompt processing, n_tokens = 797, progress = 1.00, t = 7.00 s / 113.86 tokens per second 14.42.272.445 I slot print_timing: id 2 | task 16380 | prompt eval time = 7000.17 ms / 708 tokens ( 9.89 ms per token, 101.14 tokens per second) 14.42.272.450 I slot print_timing: id 2 | task 16380 | eval time = 703.52 ms / 2 tokens ( 703.52 ms per token, 1.42 tokens per second) 14.42.272.450 I slot print_timing: id 2 | task 16380 | total time = 7703.69 ms / 710 tokens 14.42.272.451 I slot print_timing: id 2 | task 16380 | graphs reused = 15095 14.42.272.451 I slot print_timing: id 2 | task 16380 | graph reallocs = 0 / 0 (same size) / (changed size) 14.42.272.488 I slot release: id 2 | task 16380 | stop processing: n_tokens = 709, truncated = 0 14.42.272.612 I slot print_timing: id 0 | task 16384 | prompt processing, n_tokens = 765, progress = 0.99, t = 6.27 s / 121.92 tokens per second 14.42.274.020 I slot print_timing: id 1 | task 16385 | prompt processing, n_tokens = 698, progress = 0.99, t = 6.27 s / 111.24 tokens per second 14.42.354.982 I slot print_timing: id 3 | task 16381 | prompt eval time = 7703.71 ms / 801 tokens ( 9.62 ms per token, 103.98 tokens per second) 14.42.354.984 I slot print_timing: id 3 | task 16381 | eval time = 82.37 ms / 2 tokens ( 82.37 ms per token, 12.14 tokens per second) 14.42.354.985 I slot print_timing: id 3 | task 16381 | total time = 7786.08 ms / 803 tokens 14.42.354.985 I slot print_timing: id 3 | task 16381 | graphs reused = 15095 14.42.354.985 I slot print_timing: id 3 | task 16381 | graph reallocs = 0 / 0 (same size) / (changed size) 14.42.355.025 I slot release: id 3 | task 16381 | stop processing: n_tokens = 802, truncated = 0 14.42.355.031 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 709, t_last = 351701599467 14.42.355.103 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 275.336 MiB) 14.42.360.080 I slot launch_slot_: id 2 | task 16391 | processing task, is_child = 0 14.42.360.157 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 346.266 MiB) 14.42.365.687 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 802, t_last = 351701682004 14.42.365.821 I slot launch_slot_: id 3 | task 16392 | processing task, is_child = 0 14.42.950.184 I slot print_timing: id 0 | task 16384 | prompt eval time = 6357.19 ms / 769 tokens ( 8.27 ms per token, 120.97 tokens per second) 14.42.950.186 I slot print_timing: id 0 | task 16384 | eval time = 595.39 ms / 2 tokens ( 595.39 ms per token, 1.68 tokens per second) 14.42.950.187 I slot print_timing: id 0 | task 16384 | total time = 6952.59 ms / 771 tokens 14.42.950.188 I slot print_timing: id 0 | task 16384 | graphs reused = 15095 14.42.950.188 I slot print_timing: id 0 | task 16384 | graph reallocs = 0 / 0 (same size) / (changed size) 14.42.950.239 I slot release: id 0 | task 16384 | stop processing: n_tokens = 770, truncated = 0 14.42.950.399 I slot print_timing: id 1 | task 16385 | prompt eval time = 6357.15 ms / 702 tokens ( 9.06 ms per token, 110.43 tokens per second) 14.42.950.401 I slot print_timing: id 1 | task 16385 | eval time = 595.50 ms / 2 tokens ( 595.50 ms per token, 1.68 tokens per second) 14.42.950.402 I slot print_timing: id 1 | task 16385 | total time = 6952.65 ms / 704 tokens 14.42.950.402 I slot print_timing: id 1 | task 16385 | graphs reused = 15095 14.42.950.402 I slot print_timing: id 1 | task 16385 | graph reallocs = 0 / 0 (same size) / (changed size) 14.42.950.428 I slot release: id 1 | task 16385 | stop processing: n_tokens = 703, truncated = 0 14.43.161.111 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.883 (> 0.100 thold), f_keep = 0.856 14.43.161.169 I slot launch_slot_: id 1 | task 16395 | processing task, is_child = 0 14.43.425.972 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 770, t_last = 351702277218 14.43.426.098 I slot launch_slot_: id 0 | task 16396 | processing task, is_child = 0 14.46.759.869 I slot print_timing: id 0 | task 16396 | prompt processing, n_tokens = 194, progress = 0.27, t = 3.33 s / 58.20 tokens per second 14.46.760.405 I slot print_timing: id 2 | task 16391 | prompt processing, n_tokens = 746, progress = 0.99, t = 4.39 s / 169.78 tokens per second 14.46.762.573 I slot print_timing: id 3 | task 16392 | prompt processing, n_tokens = 683, progress = 0.99, t = 4.39 s / 155.45 tokens per second 14.47.557.820 I slot print_timing: id 1 | task 16395 | prompt eval time = 3333.65 ms / 80 tokens ( 41.67 ms per token, 24.00 tokens per second) 14.47.557.826 I slot print_timing: id 1 | task 16395 | eval time = 797.96 ms / 2 tokens ( 797.96 ms per token, 1.25 tokens per second) 14.47.557.826 I slot print_timing: id 1 | task 16395 | total time = 4131.61 ms / 82 tokens 14.47.557.827 I slot print_timing: id 1 | task 16395 | graphs reused = 15095 14.47.557.827 I slot print_timing: id 1 | task 16395 | graph reallocs = 0 / 0 (same size) / (changed size) 14.47.557.860 I slot release: id 1 | task 16395 | stop processing: n_tokens = 683, truncated = 0 14.47.558.115 I slot print_timing: id 0 | task 16396 | prompt processing, n_tokens = 577, progress = 0.81, t = 4.13 s / 139.66 tokens per second 14.48.013.390 I slot print_timing: id 2 | task 16391 | prompt eval time = 5192.14 ms / 750 tokens ( 6.92 ms per token, 144.45 tokens per second) 14.48.013.393 I slot print_timing: id 2 | task 16391 | eval time = 455.42 ms / 2 tokens ( 455.42 ms per token, 2.20 tokens per second) 14.48.013.394 I slot print_timing: id 2 | task 16391 | total time = 5647.56 ms / 752 tokens 14.48.013.394 I slot print_timing: id 2 | task 16391 | graphs reused = 15095 14.48.013.395 I slot print_timing: id 2 | task 16391 | graph reallocs = 0 / 0 (same size) / (changed size) 14.48.013.435 I slot release: id 2 | task 16391 | stop processing: n_tokens = 751, truncated = 0 14.48.013.575 I slot print_timing: id 3 | task 16392 | prompt eval time = 5192.17 ms / 687 tokens ( 7.56 ms per token, 132.31 tokens per second) 14.48.013.577 I slot print_timing: id 3 | task 16392 | eval time = 455.47 ms / 2 tokens ( 455.47 ms per token, 2.20 tokens per second) 14.48.013.578 I slot print_timing: id 3 | task 16392 | total time = 5647.64 ms / 689 tokens 14.48.013.578 I slot print_timing: id 3 | task 16392 | graphs reused = 15095 14.48.013.579 I slot print_timing: id 3 | task 16392 | graph reallocs = 0 / 0 (same size) / (changed size) 14.48.013.605 I slot release: id 3 | task 16392 | stop processing: n_tokens = 688, truncated = 0 14.48.013.611 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 683, t_last = 351706884839 14.48.027.193 I slot launch_slot_: id 1 | task 16401 | processing task, is_child = 0 14.48.027.270 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 257.118 MiB) 14.48.032.481 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 346.950 MiB) 14.48.037.237 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 751, t_last = 351707340414 14.48.037.360 I slot launch_slot_: id 2 | task 16402 | processing task, is_child = 0 14.48.037.418 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 688, t_last = 351707340584 14.48.037.532 I slot launch_slot_: id 3 | task 16403 | processing task, is_child = 0 14.48.037.538 I slot print_timing: id 0 | task 16396 | prompt processing, n_tokens = 706, progress = 0.99, t = 4.59 s / 153.91 tokens per second 14.49.602.805 I slot print_timing: id 0 | task 16396 | prompt eval time = 5485.36 ms / 710 tokens ( 7.73 ms per token, 129.44 tokens per second) 14.49.602.807 I slot print_timing: id 0 | task 16396 | eval time = 691.33 ms / 2 tokens ( 691.33 ms per token, 1.45 tokens per second) 14.49.602.808 I slot print_timing: id 0 | task 16396 | total time = 6176.69 ms / 712 tokens 14.49.602.809 I slot print_timing: id 0 | task 16396 | graphs reused = 15095 14.49.602.809 I slot print_timing: id 0 | task 16396 | graph reallocs = 0 / 0 (same size) / (changed size) 14.49.602.849 I slot release: id 0 | task 16396 | stop processing: n_tokens = 711, truncated = 0 14.49.859.074 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 711, t_last = 351708929828 14.49.901.021 I slot launch_slot_: id 0 | task 16407 | processing task, is_child = 0 14.52.608.669 I slot print_timing: id 1 | task 16401 | prompt processing, n_tokens = 719, progress = 0.87, t = 4.45 s / 161.73 tokens per second 14.52.609.904 I slot print_timing: id 2 | task 16402 | prompt processing, n_tokens = 719, progress = 0.86, t = 4.45 s / 161.73 tokens per second 14.52.612.167 I slot print_timing: id 3 | task 16403 | prompt processing, n_tokens = 719, progress = 0.88, t = 4.45 s / 161.73 tokens per second 14.53.715.854 I slot print_timing: id 0 | task 16407 | prompt processing, n_tokens = 294, progress = 0.36, t = 3.81 s / 77.07 tokens per second 14.53.715.865 I slot print_timing: id 1 | task 16401 | prompt processing, n_tokens = 827, progress = 1.00, t = 5.68 s / 145.67 tokens per second 14.53.756.006 I slot print_timing: id 2 | task 16402 | prompt processing, n_tokens = 832, progress = 1.00, t = 5.68 s / 146.56 tokens per second 14.53.757.854 I slot print_timing: id 3 | task 16403 | prompt processing, n_tokens = 810, progress = 1.00, t = 5.68 s / 142.68 tokens per second 14.53.895.733 I slot print_timing: id 0 | task 16407 | prompt processing, n_tokens = 302, progress = 0.37, t = 3.99 s / 75.61 tokens per second 14.54.715.327 I slot print_timing: id 1 | task 16401 | prompt eval time = 5856.77 ms / 831 tokens ( 7.05 ms per token, 141.89 tokens per second) 14.54.715.329 I slot print_timing: id 1 | task 16401 | eval time = 819.82 ms / 2 tokens ( 819.82 ms per token, 1.22 tokens per second) 14.54.715.330 I slot print_timing: id 1 | task 16401 | total time = 6676.60 ms / 833 tokens 14.54.715.330 I slot print_timing: id 1 | task 16401 | graphs reused = 15095 14.54.715.330 I slot print_timing: id 1 | task 16401 | graph reallocs = 0 / 0 (same size) / (changed size) 14.54.715.367 I slot release: id 1 | task 16401 | stop processing: n_tokens = 832, truncated = 0 14.54.715.464 I slot print_timing: id 2 | task 16402 | prompt eval time = 5856.77 ms / 836 tokens ( 7.01 ms per token, 142.74 tokens per second) 14.54.715.465 I slot print_timing: id 2 | task 16402 | eval time = 819.87 ms / 2 tokens ( 819.87 ms per token, 1.22 tokens per second) 14.54.715.466 I slot print_timing: id 2 | task 16402 | total time = 6676.64 ms / 838 tokens 14.54.715.466 I slot print_timing: id 2 | task 16402 | graphs reused = 15095 14.54.715.467 I slot print_timing: id 2 | task 16402 | graph reallocs = 0 / 0 (same size) / (changed size) 14.54.715.495 I slot release: id 2 | task 16402 | stop processing: n_tokens = 837, truncated = 0 14.54.715.607 I slot print_timing: id 3 | task 16403 | prompt eval time = 5856.79 ms / 814 tokens ( 7.20 ms per token, 138.98 tokens per second) 14.54.715.611 I slot print_timing: id 3 | task 16403 | eval time = 819.88 ms / 2 tokens ( 819.88 ms per token, 1.22 tokens per second) 14.54.715.612 I slot print_timing: id 3 | task 16403 | total time = 6676.68 ms / 816 tokens 14.54.715.612 I slot print_timing: id 3 | task 16403 | graphs reused = 15095 14.54.715.612 I slot print_timing: id 3 | task 16403 | graph reallocs = 0 / 0 (same size) / (changed size) 14.54.715.630 I slot release: id 3 | task 16403 | stop processing: n_tokens = 815, truncated = 0 14.54.715.637 I slot print_timing: id 0 | task 16407 | prompt processing, n_tokens = 719, progress = 0.88, t = 4.81 s / 149.35 tokens per second 14.54.722.924 I slot print_timing: id 0 | task 16407 | prompt processing, n_tokens = 814, progress = 1.00, t = 4.82 s / 168.81 tokens per second 14.55.101.525 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.894 (> 0.100 thold), f_keep = 0.894 14.55.101.602 I slot launch_slot_: id 1 | task 16414 | processing task, is_child = 0 14.55.101.682 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 286.202 MiB) 14.55.118.398 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 837, t_last = 351714042474 14.55.118.527 I slot launch_slot_: id 2 | task 16415 | processing task, is_child = 0 14.55.118.591 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 815, t_last = 351714042609 14.55.118.691 I slot launch_slot_: id 3 | task 16416 | processing task, is_child = 0 14.56.043.544 I slot print_timing: id 0 | task 16407 | prompt eval time = 5200.49 ms / 818 tokens ( 6.36 ms per token, 157.29 tokens per second) 14.56.043.546 I slot print_timing: id 0 | task 16407 | eval time = 942.02 ms / 2 tokens ( 942.02 ms per token, 1.06 tokens per second) 14.56.043.547 I slot print_timing: id 0 | task 16407 | total time = 6142.51 ms / 820 tokens 14.56.043.547 I slot print_timing: id 0 | task 16407 | graphs reused = 15095 14.56.043.548 I slot print_timing: id 0 | task 16407 | graph reallocs = 0 / 0 (same size) / (changed size) 14.56.043.593 I slot release: id 0 | task 16407 | stop processing: n_tokens = 819, truncated = 0 14.56.418.779 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 819, t_last = 351715370572 14.56.418.857 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 326.488 MiB) 14.56.423.609 I slot launch_slot_: id 0 | task 16419 | processing task, is_child = 0 14.58.300.086 I slot print_timing: id 1 | task 16414 | prompt eval time = 1300.07 ms / 88 tokens ( 14.77 ms per token, 67.69 tokens per second) 14.58.300.089 I slot print_timing: id 1 | task 16414 | eval time = 1881.30 ms / 2 tokens ( 1881.30 ms per token, 0.53 tokens per second) 14.58.300.089 I slot print_timing: id 1 | task 16414 | total time = 3181.37 ms / 90 tokens 14.58.300.090 I slot print_timing: id 1 | task 16414 | graphs reused = 15095 14.58.300.090 I slot print_timing: id 1 | task 16414 | graph reallocs = 0 / 0 (same size) / (changed size) 14.58.300.133 I slot release: id 1 | task 16414 | stop processing: n_tokens = 833, truncated = 0 14.58.300.507 I slot print_timing: id 2 | task 16415 | prompt processing, n_tokens = 599, progress = 0.85, t = 3.18 s / 188.36 tokens per second 14.58.302.715 I slot print_timing: id 3 | task 16416 | prompt processing, n_tokens = 599, progress = 0.85, t = 3.18 s / 188.37 tokens per second 14.59.279.270 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 833, t_last = 351717627112 14.59.309.617 I slot launch_slot_: id 1 | task 16422 | processing task, is_child = 0 14.59.309.756 I slot print_timing: id 2 | task 16415 | prompt processing, n_tokens = 700, progress = 0.99, t = 4.16 s / 168.30 tokens per second 14.59.310.995 I slot print_timing: id 3 | task 16416 | prompt processing, n_tokens = 702, progress = 0.99, t = 4.16 s / 168.78 tokens per second 15.00.048.351 I slot print_timing: id 0 | task 16419 | prompt processing, n_tokens = 355, progress = 0.41, t = 3.62 s / 97.95 tokens per second 15.01.291.024 I slot print_timing: id 2 | task 16415 | prompt eval time = 4928.30 ms / 704 tokens ( 7.00 ms per token, 142.85 tokens per second) 15.01.291.030 I slot print_timing: id 2 | task 16415 | eval time = 1242.81 ms / 2 tokens ( 1242.81 ms per token, 0.80 tokens per second) 15.01.291.031 I slot print_timing: id 2 | task 16415 | total time = 6171.11 ms / 706 tokens 15.01.291.031 I slot print_timing: id 2 | task 16415 | graphs reused = 15095 15.01.291.031 I slot print_timing: id 2 | task 16415 | graph reallocs = 0 / 0 (same size) / (changed size) 15.01.291.068 I slot release: id 2 | task 16415 | stop processing: n_tokens = 705, truncated = 0 15.01.291.213 I slot print_timing: id 3 | task 16416 | prompt eval time = 4928.31 ms / 706 tokens ( 6.98 ms per token, 143.25 tokens per second) 15.01.291.215 I slot print_timing: id 3 | task 16416 | eval time = 1242.87 ms / 2 tokens ( 1242.87 ms per token, 0.80 tokens per second) 15.01.291.215 I slot print_timing: id 3 | task 16416 | total time = 6171.18 ms / 708 tokens 15.01.291.215 I slot print_timing: id 3 | task 16416 | graphs reused = 15095 15.01.291.216 I slot print_timing: id 3 | task 16416 | graph reallocs = 0 / 0 (same size) / (changed size) 15.01.291.239 I slot release: id 3 | task 16416 | stop processing: n_tokens = 707, truncated = 0 15.01.291.248 I slot print_timing: id 0 | task 16419 | prompt processing, n_tokens = 733, progress = 0.84, t = 4.87 s / 150.60 tokens per second 15.01.546.559 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 705, t_last = 351720618047 15.01.546.636 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 143.574 MiB) 15.01.925.950 I slot launch_slot_: id 2 | task 16426 | processing task, is_child = 0 15.01.926.016 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.157 MiB) 15.01.930.727 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 707, t_last = 351720618218 15.01.930.841 I slot launch_slot_: id 3 | task 16427 | processing task, is_child = 0 15.01.930.847 I slot print_timing: id 0 | task 16419 | prompt processing, n_tokens = 867, progress = 1.00, t = 5.12 s / 169.24 tokens per second 15.03.338.525 I slot print_timing: id 1 | task 16422 | prompt processing, n_tokens = 733, progress = 0.86, t = 4.03 s / 181.94 tokens per second 15.04.501.433 I slot print_timing: id 0 | task 16419 | prompt eval time = 6914.90 ms / 871 tokens ( 7.94 ms per token, 125.96 tokens per second) 15.04.501.437 I slot print_timing: id 0 | task 16419 | eval time = 1162.91 ms / 2 tokens ( 1162.91 ms per token, 0.86 tokens per second) 15.04.501.438 I slot print_timing: id 0 | task 16419 | total time = 8077.81 ms / 873 tokens 15.04.501.438 I slot print_timing: id 0 | task 16419 | graphs reused = 15095 15.04.501.439 I slot print_timing: id 0 | task 16419 | graph reallocs = 0 / 0 (same size) / (changed size) 15.04.501.488 I slot release: id 0 | task 16419 | stop processing: n_tokens = 872, truncated = 0 15.04.501.499 I slot print_timing: id 1 | task 16422 | prompt processing, n_tokens = 844, progress = 1.00, t = 5.19 s / 162.57 tokens per second 15.04.878.355 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 872, t_last = 351723828467 15.04.878.432 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 161.106 MiB) 15.04.883.884 I slot launch_slot_: id 0 | task 16431 | processing task, is_child = 0 15.06.846.786 I slot print_timing: id 1 | task 16422 | prompt eval time = 5568.71 ms / 848 tokens ( 6.57 ms per token, 152.28 tokens per second) 15.06.846.791 I slot print_timing: id 1 | task 16422 | eval time = 1968.43 ms / 2 tokens ( 1968.43 ms per token, 0.51 tokens per second) 15.06.846.792 I slot print_timing: id 1 | task 16422 | total time = 7537.14 ms / 850 tokens 15.06.846.792 I slot print_timing: id 1 | task 16422 | graphs reused = 15095 15.06.846.792 I slot print_timing: id 1 | task 16422 | graph reallocs = 0 / 0 (same size) / (changed size) 15.06.846.833 I slot release: id 1 | task 16422 | stop processing: n_tokens = 849, truncated = 0 15.06.847.198 I slot print_timing: id 2 | task 16426 | prompt processing, n_tokens = 733, progress = 0.86, t = 4.91 s / 149.18 tokens per second 15.06.849.396 I slot print_timing: id 3 | task 16427 | prompt processing, n_tokens = 685, progress = 0.83, t = 4.91 s / 139.41 tokens per second 15.07.857.161 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 849, t_last = 351726173812 15.07.857.256 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 143.082 MiB) 15.07.943.538 I slot launch_slot_: id 1 | task 16434 | processing task, is_child = 0 15.07.943.666 I slot print_timing: id 2 | task 16426 | prompt processing, n_tokens = 852, progress = 1.00, t = 5.92 s / 143.82 tokens per second 15.07.944.989 I slot print_timing: id 3 | task 16427 | prompt processing, n_tokens = 818, progress = 1.00, t = 5.92 s / 138.08 tokens per second 15.08.427.319 I slot print_timing: id 0 | task 16431 | prompt processing, n_tokens = 274, progress = 0.35, t = 3.54 s / 77.33 tokens per second 15.09.674.428 I slot print_timing: id 2 | task 16426 | prompt eval time = 6494.22 ms / 856 tokens ( 7.59 ms per token, 131.81 tokens per second) 15.09.674.434 I slot print_timing: id 2 | task 16426 | eval time = 1247.21 ms / 2 tokens ( 1247.21 ms per token, 0.80 tokens per second) 15.09.674.435 I slot print_timing: id 2 | task 16426 | total time = 7741.43 ms / 858 tokens 15.09.674.435 I slot print_timing: id 2 | task 16426 | graphs reused = 15095 15.09.674.436 I slot print_timing: id 2 | task 16426 | graph reallocs = 0 / 0 (same size) / (changed size) 15.09.674.473 I slot release: id 2 | task 16426 | stop processing: n_tokens = 857, truncated = 0 15.09.674.615 I slot print_timing: id 3 | task 16427 | prompt eval time = 6494.23 ms / 822 tokens ( 7.90 ms per token, 126.57 tokens per second) 15.09.674.619 I slot print_timing: id 3 | task 16427 | eval time = 1247.30 ms / 2 tokens ( 1247.30 ms per token, 0.80 tokens per second) 15.09.674.619 I slot print_timing: id 3 | task 16427 | total time = 7741.53 ms / 824 tokens 15.09.674.619 I slot print_timing: id 3 | task 16427 | graphs reused = 15095 15.09.674.620 I slot print_timing: id 3 | task 16427 | graph reallocs = 0 / 0 (same size) / (changed size) 15.09.674.659 I slot release: id 3 | task 16427 | stop processing: n_tokens = 823, truncated = 0 15.09.674.666 I slot print_timing: id 0 | task 16431 | prompt processing, n_tokens = 685, progress = 0.87, t = 4.79 s / 142.99 tokens per second 15.09.833.804 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.863 15.09.833.873 I slot launch_slot_: id 3 | task 16438 | processing task, is_child = 0 15.09.833.963 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 146.487 MiB) 15.10.169.334 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 857, t_last = 351729001452 15.10.169.532 I slot launch_slot_: id 2 | task 16439 | processing task, is_child = 0 15.10.169.542 I slot print_timing: id 0 | task 16431 | prompt processing, n_tokens = 786, progress = 0.99, t = 4.95 s / 158.79 tokens per second 15.11.762.959 I slot print_timing: id 1 | task 16434 | prompt processing, n_tokens = 685, progress = 0.86, t = 3.82 s / 179.35 tokens per second 15.12.619.576 I slot print_timing: id 0 | task 16431 | prompt eval time = 6879.06 ms / 790 tokens ( 8.71 ms per token, 114.84 tokens per second) 15.12.619.579 I slot print_timing: id 0 | task 16431 | eval time = 856.62 ms / 2 tokens ( 856.62 ms per token, 1.17 tokens per second) 15.12.619.579 I slot print_timing: id 0 | task 16431 | total time = 7735.68 ms / 792 tokens 15.12.619.580 I slot print_timing: id 0 | task 16431 | graphs reused = 15095 15.12.619.580 I slot print_timing: id 0 | task 16431 | graph reallocs = 0 / 0 (same size) / (changed size) 15.12.619.619 I slot release: id 0 | task 16431 | stop processing: n_tokens = 791, truncated = 0 15.12.619.739 I slot print_timing: id 1 | task 16434 | prompt processing, n_tokens = 795, progress = 0.99, t = 4.68 s / 170.02 tokens per second 15.12.739.481 I slot print_timing: id 3 | task 16438 | prompt eval time = 2446.26 ms / 73 tokens ( 33.51 ms per token, 29.84 tokens per second) 15.12.739.487 I slot print_timing: id 3 | task 16438 | eval time = 119.75 ms / 2 tokens ( 119.75 ms per token, 8.35 tokens per second) 15.12.739.487 I slot print_timing: id 3 | task 16438 | total time = 2566.01 ms / 75 tokens 15.12.739.488 I slot print_timing: id 3 | task 16438 | graphs reused = 15095 15.12.739.488 I slot print_timing: id 3 | task 16438 | graph reallocs = 0 / 0 (same size) / (changed size) 15.12.739.522 I slot release: id 3 | task 16438 | stop processing: n_tokens = 784, truncated = 0 15.12.739.529 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 791, t_last = 351731946598 15.12.739.601 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 146.009 MiB) 15.12.750.745 I slot launch_slot_: id 0 | task 16443 | processing task, is_child = 0 15.12.750.817 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 141.701 MiB) 15.12.755.456 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 784, t_last = 351732066501 15.12.755.573 I slot launch_slot_: id 3 | task 16444 | processing task, is_child = 0 15.14.456.382 I slot print_timing: id 1 | task 16434 | prompt eval time = 4795.83 ms / 799 tokens ( 6.00 ms per token, 166.60 tokens per second) 15.14.456.386 I slot print_timing: id 1 | task 16434 | eval time = 1716.98 ms / 2 tokens ( 1716.98 ms per token, 0.58 tokens per second) 15.14.456.386 I slot print_timing: id 1 | task 16434 | total time = 6512.82 ms / 801 tokens 15.14.456.387 I slot print_timing: id 1 | task 16434 | graphs reused = 15095 15.14.456.387 I slot print_timing: id 1 | task 16434 | graph reallocs = 0 / 0 (same size) / (changed size) 15.14.456.437 I slot release: id 1 | task 16434 | stop processing: n_tokens = 800, truncated = 0 15.14.456.939 I slot print_timing: id 2 | task 16439 | prompt processing, n_tokens = 685, progress = 0.86, t = 4.28 s / 159.94 tokens per second 15.15.460.861 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 800, t_last = 351733783416 15.15.460.945 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 177.788 MiB) 15.15.778.469 I slot launch_slot_: id 1 | task 16447 | processing task, is_child = 0 15.15.778.647 I slot print_timing: id 2 | task 16439 | prompt processing, n_tokens = 791, progress = 0.99, t = 5.29 s / 149.60 tokens per second 15.17.331.912 I slot print_timing: id 0 | task 16443 | prompt processing, n_tokens = 576, progress = 0.53, t = 4.58 s / 125.87 tokens per second 15.17.334.485 I slot print_timing: id 3 | task 16444 | prompt processing, n_tokens = 584, progress = 0.53, t = 4.58 s / 127.64 tokens per second 15.19.270.768 I slot print_timing: id 2 | task 16439 | prompt eval time = 7158.54 ms / 795 tokens ( 9.00 ms per token, 111.06 tokens per second) 15.19.270.771 I slot print_timing: id 2 | task 16439 | eval time = 1938.86 ms / 2 tokens ( 1938.86 ms per token, 0.52 tokens per second) 15.19.270.771 I slot print_timing: id 2 | task 16439 | total time = 9097.41 ms / 797 tokens 15.19.270.772 I slot print_timing: id 2 | task 16439 | graphs reused = 15095 15.19.270.772 I slot print_timing: id 2 | task 16439 | graph reallocs = 0 / 0 (same size) / (changed size) 15.19.270.821 I slot release: id 2 | task 16439 | stop processing: n_tokens = 796, truncated = 0 15.19.270.834 I slot print_timing: id 0 | task 16443 | prompt processing, n_tokens = 940, progress = 0.86, t = 6.52 s / 144.28 tokens per second 15.19.272.511 I slot print_timing: id 1 | task 16447 | prompt processing, n_tokens = 358, progress = 0.31, t = 3.49 s / 102.52 tokens per second 15.19.272.526 I slot print_timing: id 3 | task 16444 | prompt processing, n_tokens = 940, progress = 0.85, t = 6.51 s / 144.30 tokens per second 15.20.354.716 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 796, t_last = 351738597801 15.20.354.816 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 152.942 MiB) 15.20.805.064 I slot launch_slot_: id 2 | task 16451 | processing task, is_child = 0 15.20.805.082 I slot print_timing: id 0 | task 16443 | prompt processing, n_tokens = 1088, progress = 1.00, t = 7.60 s / 143.17 tokens per second 15.20.807.070 I slot print_timing: id 1 | task 16447 | prompt processing, n_tokens = 640, progress = 0.55, t = 4.58 s / 139.85 tokens per second 15.20.808.489 I slot print_timing: id 3 | task 16444 | prompt processing, n_tokens = 1096, progress = 1.00, t = 7.60 s / 144.24 tokens per second 15.22.414.215 I slot print_timing: id 1 | task 16447 | prompt processing, n_tokens = 940, progress = 0.81, t = 6.64 s / 141.66 tokens per second 15.23.931.796 I slot print_timing: id 0 | task 16443 | prompt eval time = 9658.49 ms / 1092 tokens ( 8.84 ms per token, 113.06 tokens per second) 15.23.931.798 I slot print_timing: id 0 | task 16443 | eval time = 1517.72 ms / 2 tokens ( 1517.72 ms per token, 0.66 tokens per second) 15.23.931.799 I slot print_timing: id 0 | task 16443 | total time = 11176.21 ms / 1094 tokens 15.23.931.799 I slot print_timing: id 0 | task 16443 | graphs reused = 15095 15.23.931.800 I slot print_timing: id 0 | task 16443 | graph reallocs = 0 / 0 (same size) / (changed size) 15.23.931.851 I slot release: id 0 | task 16443 | stop processing: n_tokens = 1093, truncated = 0 15.23.932.001 I slot print_timing: id 3 | task 16444 | prompt eval time = 9657.85 ms / 1100 tokens ( 8.78 ms per token, 113.90 tokens per second) 15.23.932.007 I slot print_timing: id 3 | task 16444 | eval time = 1517.79 ms / 2 tokens ( 1517.79 ms per token, 0.66 tokens per second) 15.23.932.007 I slot print_timing: id 3 | task 16444 | total time = 11175.64 ms / 1102 tokens 15.23.932.007 I slot print_timing: id 3 | task 16444 | graphs reused = 15095 15.23.932.008 I slot print_timing: id 3 | task 16444 | graph reallocs = 0 / 0 (same size) / (changed size) 15.23.932.041 I slot release: id 3 | task 16444 | stop processing: n_tokens = 1101, truncated = 0 15.23.932.050 I slot print_timing: id 1 | task 16447 | prompt processing, n_tokens = 1152, progress = 1.00, t = 8.15 s / 141.29 tokens per second 15.23.934.244 I slot print_timing: id 2 | task 16451 | prompt processing, n_tokens = 895, progress = 0.37, t = 3.12 s / 286.55 tokens per second 15.25.825.446 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1093, t_last = 351743258830 15.25.825.543 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.487 MiB) 15.25.841.347 I slot launch_slot_: id 0 | task 16455 | processing task, is_child = 0 15.25.841.436 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 151.984 MiB) 15.25.841.439 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.878 MiB) 15.25.845.855 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1101, t_last = 351743259020 15.25.845.997 I slot launch_slot_: id 3 | task 16456 | processing task, is_child = 0 15.25.846.153 I slot print_timing: id 2 | task 16451 | prompt processing, n_tokens = 1903, progress = 0.79, t = 5.02 s / 379.32 tokens per second 15.27.856.131 I slot print_timing: id 1 | task 16447 | prompt eval time = 10046.93 ms / 1156 tokens ( 8.69 ms per token, 115.06 tokens per second) 15.27.856.136 I slot print_timing: id 1 | task 16447 | eval time = 2030.68 ms / 2 tokens ( 2030.68 ms per token, 0.49 tokens per second) 15.27.856.137 I slot print_timing: id 1 | task 16447 | total time = 12077.62 ms / 1158 tokens 15.27.856.137 I slot print_timing: id 1 | task 16447 | graphs reused = 15095 15.27.856.138 I slot print_timing: id 1 | task 16447 | graph reallocs = 0 / 0 (same size) / (changed size) 15.27.856.192 I slot release: id 1 | task 16447 | stop processing: n_tokens = 1157, truncated = 0 15.27.857.476 I slot print_timing: id 2 | task 16451 | prompt processing, n_tokens = 2137, progress = 0.88, t = 7.05 s / 303.22 tokens per second 15.30.001.183 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1157, t_last = 351747183171 15.30.001.298 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 191.837 MiB) 15.30.584.686 I slot launch_slot_: id 1 | task 16459 | processing task, is_child = 0 15.30.584.710 I slot print_timing: id 0 | task 16455 | prompt processing, n_tokens = 895, progress = 0.38, t = 4.16 s / 215.39 tokens per second 15.30.584.914 I slot print_timing: id 2 | task 16451 | prompt processing, n_tokens = 2415, progress = 1.00, t = 9.19 s / 262.71 tokens per second 15.30.586.537 I slot print_timing: id 3 | task 16456 | prompt processing, n_tokens = 895, progress = 0.35, t = 4.15 s / 215.46 tokens per second 15.34.777.713 I slot print_timing: id 0 | task 16455 | prompt processing, n_tokens = 1817, progress = 0.78, t = 8.93 s / 203.44 tokens per second 15.34.779.432 I slot print_timing: id 1 | task 16459 | prompt processing, n_tokens = 373, progress = 0.15, t = 4.19 s / 88.96 tokens per second 15.34.781.239 I slot print_timing: id 3 | task 16456 | prompt processing, n_tokens = 1644, progress = 0.64, t = 8.93 s / 184.09 tokens per second 15.37.485.155 I slot print_timing: id 2 | task 16451 | prompt eval time = 13969.32 ms / 2419 tokens ( 5.77 ms per token, 173.17 tokens per second) 15.37.485.157 I slot print_timing: id 2 | task 16451 | eval time = 2707.46 ms / 2 tokens ( 2707.46 ms per token, 0.37 tokens per second) 15.37.485.158 I slot print_timing: id 2 | task 16451 | total time = 16676.77 ms / 2421 tokens 15.37.485.158 I slot print_timing: id 2 | task 16451 | graphs reused = 15095 15.37.485.159 I slot print_timing: id 2 | task 16451 | graph reallocs = 0 / 0 (same size) / (changed size) 15.37.485.276 I slot release: id 2 | task 16451 | stop processing: n_tokens = 2420, truncated = 0 15.37.485.296 I slot print_timing: id 0 | task 16455 | prompt processing, n_tokens = 2137, progress = 0.92, t = 11.64 s / 183.61 tokens per second 15.37.487.079 I slot print_timing: id 1 | task 16459 | prompt processing, n_tokens = 895, progress = 0.36, t = 6.90 s / 129.70 tokens per second 15.37.487.107 I slot print_timing: id 3 | task 16456 | prompt processing, n_tokens = 2055, progress = 0.80, t = 11.64 s / 176.58 tokens per second 15.39.924.918 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 2420, t_last = 351756812256 15.39.925.051 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 169.229 MiB) 15.40.262.456 I slot launch_slot_: id 2 | task 16463 | processing task, is_child = 0 15.40.262.468 I slot print_timing: id 0 | task 16455 | prompt processing, n_tokens = 2329, progress = 1.00, t = 14.08 s / 165.42 tokens per second 15.40.263.828 I slot print_timing: id 1 | task 16459 | prompt processing, n_tokens = 1958, progress = 0.79, t = 9.34 s / 209.63 tokens per second 15.40.265.194 I slot print_timing: id 3 | task 16456 | prompt processing, n_tokens = 2137, progress = 0.83, t = 14.08 s / 151.80 tokens per second 15.42.072.810 I slot print_timing: id 1 | task 16459 | prompt processing, n_tokens = 2137, progress = 0.86, t = 11.49 s / 186.02 tokens per second 15.42.075.205 I slot print_timing: id 3 | task 16456 | prompt processing, n_tokens = 2567, progress = 1.00, t = 16.23 s / 158.21 tokens per second 15.43.621.745 I slot print_timing: id 0 | task 16455 | prompt eval time = 16226.79 ms / 2333 tokens ( 6.96 ms per token, 143.77 tokens per second) 15.43.621.750 I slot print_timing: id 0 | task 16455 | eval time = 1548.94 ms / 2 tokens ( 1548.94 ms per token, 0.65 tokens per second) 15.43.621.751 I slot print_timing: id 0 | task 16455 | total time = 17775.73 ms / 2335 tokens 15.43.621.751 I slot print_timing: id 0 | task 16455 | graphs reused = 15095 15.43.621.751 I slot print_timing: id 0 | task 16455 | graph reallocs = 0 / 0 (same size) / (changed size) 15.43.621.848 I slot release: id 0 | task 16455 | stop processing: n_tokens = 2334, truncated = 0 15.43.622.017 I slot print_timing: id 1 | task 16459 | prompt processing, n_tokens = 2470, progress = 1.00, t = 13.04 s / 189.46 tokens per second 15.43.624.594 I slot print_timing: id 2 | task 16463 | prompt processing, n_tokens = 473, progress = 0.29, t = 3.36 s / 140.91 tokens per second 15.45.003.323 I slot print_timing: id 3 | task 16456 | prompt eval time = 17774.73 ms / 2571 tokens ( 6.91 ms per token, 144.64 tokens per second) 15.45.003.325 I slot print_timing: id 3 | task 16456 | eval time = 1381.31 ms / 2 tokens ( 1381.31 ms per token, 0.72 tokens per second) 15.45.003.326 I slot print_timing: id 3 | task 16456 | total time = 19156.04 ms / 2573 tokens 15.45.003.326 I slot print_timing: id 3 | task 16456 | graphs reused = 15095 15.45.003.327 I slot print_timing: id 3 | task 16456 | graph reallocs = 0 / 0 (same size) / (changed size) 15.45.003.433 I slot release: id 3 | task 16456 | stop processing: n_tokens = 2572, truncated = 0 15.45.003.443 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 2334, t_last = 351762948829 15.45.003.579 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 154.993 MiB) 15.45.022.018 I slot launch_slot_: id 0 | task 16467 | processing task, is_child = 0 15.45.022.151 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 156.525 MiB) 15.45.022.154 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 139.622 MiB) 15.45.036.010 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 2572, t_last = 351764330413 15.45.036.189 I slot launch_slot_: id 3 | task 16468 | processing task, is_child = 0 15.45.036.452 I slot print_timing: id 2 | task 16463 | prompt processing, n_tokens = 1106, progress = 0.68, t = 4.74 s / 233.43 tokens per second 15.46.413.994 I slot print_timing: id 1 | task 16459 | prompt eval time = 14418.49 ms / 2474 tokens ( 5.83 ms per token, 171.59 tokens per second) 15.46.413.997 I slot print_timing: id 1 | task 16459 | eval time = 1410.77 ms / 2 tokens ( 1410.77 ms per token, 0.71 tokens per second) 15.46.413.998 I slot print_timing: id 1 | task 16459 | total time = 15829.25 ms / 2476 tokens 15.46.413.998 I slot print_timing: id 1 | task 16459 | graphs reused = 15095 15.46.413.999 I slot print_timing: id 1 | task 16459 | graph reallocs = 0 / 0 (same size) / (changed size) 15.46.414.100 I slot release: id 1 | task 16459 | stop processing: n_tokens = 2475, truncated = 0 15.46.414.642 I slot print_timing: id 2 | task 16463 | prompt processing, n_tokens = 1317, progress = 0.81, t = 6.15 s / 214.18 tokens per second 15.48.227.558 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 2475, t_last = 351765741080 15.48.227.724 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 152.914 MiB) 15.48.305.486 I slot launch_slot_: id 1 | task 16471 | processing task, is_child = 0 15.48.305.501 I slot print_timing: id 0 | task 16467 | prompt processing, n_tokens = 473, progress = 0.28, t = 3.19 s / 148.21 tokens per second 15.48.305.798 I slot print_timing: id 2 | task 16463 | prompt processing, n_tokens = 1618, progress = 1.00, t = 7.96 s / 203.20 tokens per second 15.48.307.118 I slot print_timing: id 3 | task 16468 | prompt processing, n_tokens = 473, progress = 0.25, t = 3.19 s / 148.28 tokens per second 15.51.615.212 I slot print_timing: id 0 | task 16467 | prompt processing, n_tokens = 1170, progress = 0.69, t = 6.58 s / 177.84 tokens per second 15.51.616.836 I slot print_timing: id 1 | task 16471 | prompt processing, n_tokens = 184, progress = 0.11, t = 3.31 s / 55.60 tokens per second 15.51.617.695 I slot print_timing: id 3 | task 16468 | prompt processing, n_tokens = 1317, progress = 0.70, t = 6.58 s / 200.23 tokens per second 15.52.954.989 I slot print_timing: id 2 | task 16463 | prompt eval time = 11350.25 ms / 1622 tokens ( 7.00 ms per token, 142.90 tokens per second) 15.52.954.995 I slot print_timing: id 2 | task 16463 | eval time = 1339.79 ms / 2 tokens ( 1339.79 ms per token, 0.75 tokens per second) 15.52.954.995 I slot print_timing: id 2 | task 16463 | total time = 12690.04 ms / 1624 tokens 15.52.954.996 I slot print_timing: id 2 | task 16463 | graphs reused = 15095 15.52.954.996 I slot print_timing: id 2 | task 16463 | graph reallocs = 0 / 0 (same size) / (changed size) 15.52.955.082 I slot release: id 2 | task 16463 | stop processing: n_tokens = 1623, truncated = 0 15.52.955.095 I slot print_timing: id 0 | task 16467 | prompt processing, n_tokens = 1317, progress = 0.78, t = 7.92 s / 166.32 tokens per second 15.52.956.859 I slot print_timing: id 1 | task 16471 | prompt processing, n_tokens = 473, progress = 0.28, t = 4.65 s / 101.73 tokens per second 15.52.956.881 I slot print_timing: id 3 | task 16468 | prompt processing, n_tokens = 1354, progress = 0.72, t = 7.92 s / 171.02 tokens per second 15.55.125.135 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.761 (> 0.100 thold), f_keep = 0.832 15.55.125.227 I slot launch_slot_: id 2 | task 16475 | processing task, is_child = 0 15.55.125.237 I slot print_timing: id 0 | task 16467 | prompt processing, n_tokens = 1682, progress = 1.00, t = 10.09 s / 166.72 tokens per second 15.56.052.558 I slot print_timing: id 1 | task 16471 | prompt processing, n_tokens = 1176, progress = 0.70, t = 6.82 s / 172.44 tokens per second 15.56.057.188 I slot print_timing: id 3 | task 16468 | prompt processing, n_tokens = 1866, progress = 1.00, t = 10.09 s / 184.98 tokens per second 15.57.434.338 I slot print_timing: id 1 | task 16471 | prompt processing, n_tokens = 1317, progress = 0.78, t = 9.13 s / 144.27 tokens per second 15.58.293.673 I slot print_timing: id 0 | task 16467 | prompt eval time = 12398.03 ms / 1686 tokens ( 7.35 ms per token, 135.99 tokens per second) 15.58.293.679 I slot print_timing: id 0 | task 16467 | eval time = 859.44 ms / 2 tokens ( 859.44 ms per token, 1.16 tokens per second) 15.58.293.679 I slot print_timing: id 0 | task 16467 | total time = 13257.47 ms / 1688 tokens 15.58.293.680 I slot print_timing: id 0 | task 16467 | graphs reused = 15095 15.58.293.680 I slot print_timing: id 0 | task 16467 | graph reallocs = 0 / 0 (same size) / (changed size) 15.58.293.753 I slot release: id 0 | task 16467 | stop processing: n_tokens = 1687, truncated = 0 15.58.293.989 I slot print_timing: id 3 | task 16468 | prompt eval time = 12396.70 ms / 1870 tokens ( 6.63 ms per token, 150.85 tokens per second) 15.58.293.994 I slot print_timing: id 3 | task 16468 | eval time = 859.66 ms / 2 tokens ( 859.66 ms per token, 1.16 tokens per second) 15.58.293.995 I slot print_timing: id 3 | task 16468 | total time = 13256.36 ms / 1872 tokens 15.58.293.995 I slot print_timing: id 3 | task 16468 | graphs reused = 15095 15.58.293.995 I slot print_timing: id 3 | task 16468 | graph reallocs = 0 / 0 (same size) / (changed size) 15.58.294.053 I slot release: id 3 | task 16468 | stop processing: n_tokens = 1871, truncated = 0 15.58.294.063 I slot print_timing: id 1 | task 16471 | prompt processing, n_tokens = 1688, progress = 1.00, t = 9.99 s / 169.00 tokens per second 15.58.358.676 I slot print_timing: id 2 | task 16475 | prompt eval time = 2238.88 ms / 425 tokens ( 5.27 ms per token, 189.83 tokens per second) 15.58.358.680 I slot print_timing: id 2 | task 16475 | eval time = 64.78 ms / 2 tokens ( 64.78 ms per token, 15.44 tokens per second) 15.58.358.681 I slot print_timing: id 2 | task 16475 | total time = 2303.66 ms / 427 tokens 15.58.358.681 I slot print_timing: id 2 | task 16475 | graphs reused = 15095 15.58.358.681 I slot print_timing: id 2 | task 16475 | graph reallocs = 0 / 0 (same size) / (changed size) 15.58.358.748 I slot release: id 2 | task 16475 | stop processing: n_tokens = 1776, truncated = 0 15.58.358.754 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1687, t_last = 351777620734 15.58.358.863 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 137.421 MiB) 15.58.358.868 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 172.359 MiB) 15.58.364.197 I slot launch_slot_: id 0 | task 16479 | processing task, is_child = 0 15.58.364.308 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 174.150 MiB) 15.58.370.180 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 150.932 MiB) 15.58.375.306 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.832 (> 0.100 thold), f_keep = 0.760 15.58.375.369 I slot launch_slot_: id 2 | task 16480 | processing task, is_child = 0 15.58.375.472 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1871, t_last = 351777621033 15.58.375.607 I slot launch_slot_: id 3 | task 16481 | processing task, is_child = 0 15.59.822.719 I slot print_timing: id 1 | task 16471 | prompt eval time = 10053.07 ms / 1692 tokens ( 5.94 ms per token, 168.31 tokens per second) 15.59.822.722 I slot print_timing: id 1 | task 16471 | eval time = 1464.12 ms / 2 tokens ( 1464.12 ms per token, 0.68 tokens per second) 15.59.822.722 I slot print_timing: id 1 | task 16471 | total time = 11517.19 ms / 1694 tokens 15.59.822.723 I slot print_timing: id 1 | task 16471 | graphs reused = 15095 15.59.822.723 I slot print_timing: id 1 | task 16471 | graph reallocs = 0 / 0 (same size) / (changed size) 15.59.822.800 I slot release: id 1 | task 16471 | stop processing: n_tokens = 1693, truncated = 0 16.00.079.070 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1693, t_last = 351779149781 16.00.079.181 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 161.557 MiB) 16.00.079.622 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.663 MiB) 16.00.087.184 I slot launch_slot_: id 1 | task 16484 | processing task, is_child = 0 16.02.003.189 I slot print_timing: id 2 | task 16480 | prompt eval time = 1703.26 ms / 273 tokens ( 6.24 ms per token, 160.28 tokens per second) 16.02.003.195 I slot print_timing: id 2 | task 16480 | eval time = 1924.12 ms / 2 tokens ( 1924.12 ms per token, 0.52 tokens per second) 16.02.003.195 I slot print_timing: id 2 | task 16480 | total time = 3627.38 ms / 275 tokens 16.02.003.196 I slot print_timing: id 2 | task 16480 | graphs reused = 15095 16.02.003.196 I slot print_timing: id 2 | task 16480 | graph reallocs = 0 / 0 (same size) / (changed size) 16.02.003.270 I slot release: id 2 | task 16480 | stop processing: n_tokens = 1624, truncated = 0 16.02.003.284 I slot print_timing: id 0 | task 16479 | prompt processing, n_tokens = 538, progress = 0.84, t = 3.63 s / 148.31 tokens per second 16.02.005.699 I slot print_timing: id 3 | task 16481 | prompt processing, n_tokens = 538, progress = 0.81, t = 3.63 s / 148.37 tokens per second 16.02.595.499 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1624, t_last = 351781330250 16.02.595.622 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 160.600 MiB) 16.02.979.316 I slot launch_slot_: id 2 | task 16487 | processing task, is_child = 0 16.02.979.329 I slot print_timing: id 0 | task 16479 | prompt processing, n_tokens = 634, progress = 0.99, t = 4.22 s / 150.24 tokens per second 16.02.981.332 I slot print_timing: id 3 | task 16481 | prompt processing, n_tokens = 658, progress = 0.99, t = 4.22 s / 155.98 tokens per second 16.04.167.904 I slot print_timing: id 1 | task 16484 | prompt processing, n_tokens = 538, progress = 0.80, t = 4.08 s / 131.86 tokens per second 16.04.707.738 I slot print_timing: id 0 | task 16479 | prompt eval time = 5792.14 ms / 638 tokens ( 9.08 ms per token, 110.15 tokens per second) 16.04.707.743 I slot print_timing: id 0 | task 16479 | eval time = 539.98 ms / 2 tokens ( 539.98 ms per token, 1.85 tokens per second) 16.04.707.744 I slot print_timing: id 0 | task 16479 | total time = 6332.12 ms / 640 tokens 16.04.707.744 I slot print_timing: id 0 | task 16479 | graphs reused = 15095 16.04.707.745 I slot print_timing: id 0 | task 16479 | graph reallocs = 0 / 0 (same size) / (changed size) 16.04.707.783 I slot release: id 0 | task 16479 | stop processing: n_tokens = 639, truncated = 0 16.04.707.941 I slot print_timing: id 3 | task 16481 | prompt eval time = 5790.85 ms / 662 tokens ( 8.75 ms per token, 114.32 tokens per second) 16.04.707.943 I slot print_timing: id 3 | task 16481 | eval time = 540.05 ms / 2 tokens ( 540.05 ms per token, 1.85 tokens per second) 16.04.707.944 I slot print_timing: id 3 | task 16481 | total time = 6330.90 ms / 664 tokens 16.04.707.944 I slot print_timing: id 3 | task 16481 | graphs reused = 15095 16.04.707.944 I slot print_timing: id 3 | task 16481 | graph reallocs = 0 / 0 (same size) / (changed size) 16.04.707.966 I slot release: id 3 | task 16481 | stop processing: n_tokens = 663, truncated = 0 16.04.707.973 I slot print_timing: id 1 | task 16484 | prompt processing, n_tokens = 669, progress = 0.99, t = 4.62 s / 144.80 tokens per second 16.05.513.256 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.862 (> 0.100 thold), f_keep = 0.881 16.05.513.331 I slot launch_slot_: id 0 | task 16491 | processing task, is_child = 0 16.05.513.399 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 195.005 MiB) 16.05.517.907 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 663, t_last = 351784034945 16.05.518.014 I slot launch_slot_: id 3 | task 16492 | processing task, is_child = 0 16.06.392.637 I slot print_timing: id 1 | task 16484 | prompt eval time = 5425.75 ms / 673 tokens ( 8.06 ms per token, 124.04 tokens per second) 16.06.392.640 I slot print_timing: id 1 | task 16484 | eval time = 879.38 ms / 2 tokens ( 879.38 ms per token, 1.14 tokens per second) 16.06.392.640 I slot print_timing: id 1 | task 16484 | total time = 6305.13 ms / 675 tokens 16.06.392.641 I slot print_timing: id 1 | task 16484 | graphs reused = 15095 16.06.392.641 I slot print_timing: id 1 | task 16484 | graph reallocs = 0 / 0 (same size) / (changed size) 16.06.392.677 I slot release: id 1 | task 16484 | stop processing: n_tokens = 674, truncated = 0 16.06.394.194 I slot print_timing: id 2 | task 16487 | prompt processing, n_tokens = 635, progress = 0.99, t = 3.41 s / 186.14 tokens per second 16.06.816.369 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 674, t_last = 351785719656 16.06.816.455 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 152.818 MiB) 16.06.822.824 I slot launch_slot_: id 1 | task 16495 | processing task, is_child = 0 16.07.996.023 I slot print_timing: id 0 | task 16491 | prompt eval time = 1298.22 ms / 90 tokens ( 14.42 ms per token, 69.33 tokens per second) 16.07.996.025 I slot print_timing: id 0 | task 16491 | eval time = 1179.77 ms / 2 tokens ( 1179.77 ms per token, 0.85 tokens per second) 16.07.996.026 I slot print_timing: id 0 | task 16491 | total time = 2477.99 ms / 92 tokens 16.07.996.026 I slot print_timing: id 0 | task 16491 | graphs reused = 15095 16.07.996.027 I slot print_timing: id 0 | task 16491 | graph reallocs = 0 / 0 (same size) / (changed size) 16.07.996.062 I slot release: id 0 | task 16491 | stop processing: n_tokens = 654, truncated = 0 16.07.996.179 I slot print_timing: id 2 | task 16487 | prompt eval time = 3835.21 ms / 639 tokens ( 6.00 ms per token, 166.61 tokens per second) 16.07.996.181 I slot print_timing: id 2 | task 16487 | eval time = 1179.81 ms / 2 tokens ( 1179.81 ms per token, 0.85 tokens per second) 16.07.996.182 I slot print_timing: id 2 | task 16487 | total time = 5015.02 ms / 641 tokens 16.07.996.182 I slot print_timing: id 2 | task 16487 | graphs reused = 15095 16.07.996.182 I slot print_timing: id 2 | task 16487 | graph reallocs = 0 / 0 (same size) / (changed size) 16.07.996.203 I slot release: id 2 | task 16487 | stop processing: n_tokens = 640, truncated = 0 16.08.467.668 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 654, t_last = 351787323041 16.08.467.751 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 152.833 MiB) 16.08.906.084 I slot launch_slot_: id 0 | task 16498 | processing task, is_child = 0 16.08.906.162 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.118 MiB) 16.08.911.039 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 640, t_last = 351787323182 16.08.911.156 I slot launch_slot_: id 2 | task 16499 | processing task, is_child = 0 16.09.886.759 I slot print_timing: id 1 | task 16495 | prompt processing, n_tokens = 441, progress = 0.46, t = 3.06 s / 143.95 tokens per second 16.11.025.435 I slot print_timing: id 3 | task 16492 | prompt eval time = 4366.06 ms / 703 tokens ( 6.21 ms per token, 161.01 tokens per second) 16.11.025.441 I slot print_timing: id 3 | task 16492 | eval time = 1139.01 ms / 2 tokens ( 1139.01 ms per token, 0.88 tokens per second) 16.11.025.441 I slot print_timing: id 3 | task 16492 | total time = 5505.08 ms / 705 tokens 16.11.025.441 I slot print_timing: id 3 | task 16492 | graphs reused = 15095 16.11.025.442 I slot print_timing: id 3 | task 16492 | graph reallocs = 0 / 0 (same size) / (changed size) 16.11.025.484 I slot release: id 3 | task 16492 | stop processing: n_tokens = 704, truncated = 0 16.11.026.034 I slot print_timing: id 1 | task 16495 | prompt processing, n_tokens = 818, progress = 0.85, t = 4.20 s / 194.65 tokens per second 16.12.369.019 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 704, t_last = 351790352463 16.12.369.105 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 195.032 MiB) 16.12.967.387 I slot launch_slot_: id 3 | task 16503 | processing task, is_child = 0 16.12.967.405 I slot print_timing: id 0 | task 16498 | prompt processing, n_tokens = 593, progress = 0.84, t = 3.46 s / 171.49 tokens per second 16.12.969.764 I slot print_timing: id 1 | task 16495 | prompt processing, n_tokens = 953, progress = 1.00, t = 5.55 s / 171.83 tokens per second 16.12.971.019 I slot print_timing: id 2 | task 16499 | prompt processing, n_tokens = 593, progress = 0.85, t = 3.46 s / 171.50 tokens per second 16.14.078.362 I slot print_timing: id 0 | task 16498 | prompt processing, n_tokens = 701, progress = 0.99, t = 5.17 s / 135.67 tokens per second 16.14.079.958 I slot print_timing: id 2 | task 16499 | prompt processing, n_tokens = 697, progress = 0.99, t = 5.17 s / 134.90 tokens per second 16.14.574.047 I slot print_timing: id 1 | task 16495 | prompt eval time = 7255.51 ms / 957 tokens ( 7.58 ms per token, 131.90 tokens per second) 16.14.574.052 I slot print_timing: id 1 | task 16495 | eval time = 495.70 ms / 2 tokens ( 495.70 ms per token, 2.02 tokens per second) 16.14.574.053 I slot print_timing: id 1 | task 16495 | total time = 7751.21 ms / 959 tokens 16.14.574.053 I slot print_timing: id 1 | task 16495 | graphs reused = 15095 16.14.574.054 I slot print_timing: id 1 | task 16495 | graph reallocs = 0 / 0 (same size) / (changed size) 16.14.574.103 I slot release: id 1 | task 16495 | stop processing: n_tokens = 958, truncated = 0 16.15.375.188 I slot print_timing: id 0 | task 16498 | prompt eval time = 5662.79 ms / 705 tokens ( 8.03 ms per token, 124.50 tokens per second) 16.15.375.193 I slot print_timing: id 0 | task 16498 | eval time = 801.23 ms / 2 tokens ( 801.23 ms per token, 1.25 tokens per second) 16.15.375.194 I slot print_timing: id 0 | task 16498 | total time = 6464.02 ms / 707 tokens 16.15.375.194 I slot print_timing: id 0 | task 16498 | graphs reused = 15095 16.15.375.194 I slot print_timing: id 0 | task 16498 | graph reallocs = 0 / 0 (same size) / (changed size) 16.15.375.229 I slot release: id 0 | task 16498 | stop processing: n_tokens = 706, truncated = 0 16.15.375.327 I slot print_timing: id 2 | task 16499 | prompt eval time = 5662.98 ms / 701 tokens ( 8.08 ms per token, 123.79 tokens per second) 16.15.375.329 I slot print_timing: id 2 | task 16499 | eval time = 801.07 ms / 2 tokens ( 801.07 ms per token, 1.25 tokens per second) 16.15.375.330 I slot print_timing: id 2 | task 16499 | total time = 6464.05 ms / 703 tokens 16.15.375.330 I slot print_timing: id 2 | task 16499 | graphs reused = 15095 16.15.375.330 I slot print_timing: id 2 | task 16499 | graph reallocs = 0 / 0 (same size) / (changed size) 16.15.375.354 I slot release: id 2 | task 16499 | stop processing: n_tokens = 702, truncated = 0 16.15.375.360 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 958, t_last = 351793901082 16.15.381.507 I slot launch_slot_: id 1 | task 16507 | processing task, is_child = 0 16.15.381.577 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 159.150 MiB) 16.15.385.249 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 157.318 MiB) 16.15.390.731 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 706, t_last = 351794702208 16.15.390.856 I slot launch_slot_: id 0 | task 16508 | processing task, is_child = 0 16.15.390.914 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 702, t_last = 351794702333 16.15.391.013 I slot launch_slot_: id 2 | task 16509 | processing task, is_child = 0 16.16.314.281 I slot print_timing: id 3 | task 16503 | prompt processing, n_tokens = 747, progress = 0.99, t = 3.17 s / 236.02 tokens per second 16.18.410.369 I slot print_timing: id 3 | task 16503 | prompt eval time = 4513.63 ms / 751 tokens ( 6.01 ms per token, 166.38 tokens per second) 16.18.410.371 I slot print_timing: id 3 | task 16503 | eval time = 924.58 ms / 2 tokens ( 924.58 ms per token, 1.08 tokens per second) 16.18.410.372 I slot print_timing: id 3 | task 16503 | total time = 5438.21 ms / 753 tokens 16.18.410.372 I slot print_timing: id 3 | task 16503 | graphs reused = 15095 16.18.410.373 I slot print_timing: id 3 | task 16503 | graph reallocs = 0 / 0 (same size) / (changed size) 16.18.410.412 I slot release: id 3 | task 16503 | stop processing: n_tokens = 752, truncated = 0 16.18.410.423 I slot print_timing: id 0 | task 16508 | prompt processing, n_tokens = 293, progress = 0.36, t = 3.02 s / 97.05 tokens per second 16.18.411.222 I slot print_timing: id 1 | task 16507 | prompt processing, n_tokens = 640, progress = 0.86, t = 3.02 s / 211.98 tokens per second 16.18.413.783 I slot print_timing: id 2 | task 16509 | prompt processing, n_tokens = 287, progress = 0.36, t = 3.02 s / 95.07 tokens per second 16.19.590.348 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.867 (> 0.100 thold), f_keep = 0.884 16.19.590.439 I slot launch_slot_: id 3 | task 16514 | processing task, is_child = 0 16.19.590.446 I slot print_timing: id 0 | task 16508 | prompt processing, n_tokens = 640, progress = 0.79, t = 4.20 s / 152.41 tokens per second 16.20.150.013 I slot print_timing: id 1 | task 16507 | prompt processing, n_tokens = 741, progress = 0.99, t = 4.20 s / 176.46 tokens per second 16.20.152.254 I slot print_timing: id 2 | task 16509 | prompt processing, n_tokens = 640, progress = 0.80, t = 4.20 s / 152.41 tokens per second 16.21.495.106 I slot print_timing: id 0 | task 16508 | prompt processing, n_tokens = 805, progress = 1.00, t = 6.10 s / 131.88 tokens per second 16.21.496.644 I slot print_timing: id 2 | task 16509 | prompt processing, n_tokens = 799, progress = 1.00, t = 6.10 s / 130.90 tokens per second 16.21.622.993 I slot print_timing: id 1 | task 16507 | prompt eval time = 6103.98 ms / 745 tokens ( 8.19 ms per token, 122.05 tokens per second) 16.21.622.999 I slot print_timing: id 1 | task 16507 | eval time = 127.90 ms / 2 tokens ( 127.90 ms per token, 7.82 tokens per second) 16.21.622.999 I slot print_timing: id 1 | task 16507 | total time = 6231.88 ms / 747 tokens 16.21.622.999 I slot print_timing: id 1 | task 16507 | graphs reused = 15095 16.21.623.000 I slot print_timing: id 1 | task 16507 | graph reallocs = 0 / 0 (same size) / (changed size) 16.21.623.038 I slot release: id 1 | task 16507 | stop processing: n_tokens = 746, truncated = 0 16.21.676.466 I slot print_timing: id 0 | task 16508 | prompt eval time = 6231.86 ms / 809 tokens ( 7.70 ms per token, 129.82 tokens per second) 16.21.676.472 I slot print_timing: id 0 | task 16508 | eval time = 53.59 ms / 2 tokens ( 53.59 ms per token, 18.66 tokens per second) 16.21.676.472 I slot print_timing: id 0 | task 16508 | total time = 6285.44 ms / 811 tokens 16.21.676.473 I slot print_timing: id 0 | task 16508 | graphs reused = 15095 16.21.676.473 I slot print_timing: id 0 | task 16508 | graph reallocs = 0 / 0 (same size) / (changed size) 16.21.676.512 I slot release: id 0 | task 16508 | stop processing: n_tokens = 810, truncated = 0 16.21.676.618 I slot print_timing: id 2 | task 16509 | prompt eval time = 6231.89 ms / 803 tokens ( 7.76 ms per token, 128.85 tokens per second) 16.21.676.621 I slot print_timing: id 2 | task 16509 | eval time = 53.47 ms / 2 tokens ( 53.47 ms per token, 18.70 tokens per second) 16.21.676.621 I slot print_timing: id 2 | task 16509 | total time = 6285.37 ms / 805 tokens 16.21.676.621 I slot print_timing: id 2 | task 16509 | graphs reused = 15095 16.21.676.622 I slot print_timing: id 2 | task 16509 | graph reallocs = 0 / 0 (same size) / (changed size) 16.21.676.646 I slot release: id 2 | task 16509 | stop processing: n_tokens = 804, truncated = 0 16.21.676.732 I slot print_timing: id 3 | task 16514 | prompt eval time = 1469.87 ms / 102 tokens ( 14.41 ms per token, 69.39 tokens per second) 16.21.676.734 I slot print_timing: id 3 | task 16514 | eval time = 53.48 ms / 2 tokens ( 53.48 ms per token, 18.70 tokens per second) 16.21.676.735 I slot print_timing: id 3 | task 16514 | total time = 1523.35 ms / 104 tokens 16.21.676.735 I slot print_timing: id 3 | task 16514 | graphs reused = 15095 16.21.676.735 I slot print_timing: id 3 | task 16514 | graph reallocs = 0 / 0 (same size) / (changed size) 16.21.676.754 I slot release: id 3 | task 16514 | stop processing: n_tokens = 768, truncated = 0 16.21.676.758 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 746, t_last = 351800950017 16.21.676.828 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 153.202 MiB) 16.21.680.997 I slot launch_slot_: id 1 | task 16518 | processing task, is_child = 0 16.21.681.070 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 156.169 MiB) 16.21.684.967 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 184.081 MiB) 16.21.689.122 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 218.062 MiB) 16.21.695.517 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 810, t_last = 351801003491 16.21.695.663 I slot launch_slot_: id 0 | task 16519 | processing task, is_child = 0 16.21.695.783 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 804, t_last = 351801003625 16.21.695.884 I slot launch_slot_: id 2 | task 16520 | processing task, is_child = 0 16.21.695.945 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 768, t_last = 351801003733 16.21.696.039 I slot launch_slot_: id 3 | task 16521 | processing task, is_child = 0 16.26.120.971 I slot print_timing: id 0 | task 16519 | prompt processing, n_tokens = 224, progress = 0.30, t = 4.42 s / 50.62 tokens per second 16.26.237.592 I slot print_timing: id 1 | task 16518 | prompt processing, n_tokens = 507, progress = 0.84, t = 4.42 s / 114.58 tokens per second 16.26.240.208 I slot print_timing: id 2 | task 16520 | prompt processing, n_tokens = 545, progress = 0.82, t = 4.42 s / 123.17 tokens per second 16.26.242.198 I slot print_timing: id 3 | task 16521 | prompt processing, n_tokens = 612, progress = 0.86, t = 4.42 s / 138.32 tokens per second 16.27.721.226 I slot print_timing: id 0 | task 16519 | prompt processing, n_tokens = 612, progress = 0.83, t = 6.03 s / 101.57 tokens per second 16.27.838.318 I slot print_timing: id 1 | task 16518 | prompt processing, n_tokens = 596, progress = 0.99, t = 6.03 s / 98.92 tokens per second 16.27.840.660 I slot print_timing: id 2 | task 16520 | prompt processing, n_tokens = 662, progress = 0.99, t = 6.02 s / 109.88 tokens per second 16.27.841.852 I slot print_timing: id 3 | task 16521 | prompt processing, n_tokens = 711, progress = 0.99, t = 6.02 s / 118.01 tokens per second 16.28.343.355 I slot print_timing: id 0 | task 16519 | prompt processing, n_tokens = 736, progress = 0.99, t = 6.65 s / 110.73 tokens per second 16.28.422.581 I slot print_timing: id 1 | task 16518 | prompt eval time = 6646.99 ms / 600 tokens ( 11.08 ms per token, 90.27 tokens per second) 16.28.422.585 I slot print_timing: id 1 | task 16518 | eval time = 79.43 ms / 2 tokens ( 79.43 ms per token, 12.59 tokens per second) 16.28.422.585 I slot print_timing: id 1 | task 16518 | total time = 6726.42 ms / 602 tokens 16.28.422.585 I slot print_timing: id 1 | task 16518 | graphs reused = 15095 16.28.422.586 I slot print_timing: id 1 | task 16518 | graph reallocs = 0 / 0 (same size) / (changed size) 16.28.422.624 I slot release: id 1 | task 16518 | stop processing: n_tokens = 601, truncated = 0 16.28.422.721 I slot print_timing: id 2 | task 16520 | prompt eval time = 6647.00 ms / 666 tokens ( 9.98 ms per token, 100.20 tokens per second) 16.28.422.724 I slot print_timing: id 2 | task 16520 | eval time = 79.47 ms / 2 tokens ( 79.47 ms per token, 12.58 tokens per second) 16.28.422.725 I slot print_timing: id 2 | task 16520 | total time = 6726.48 ms / 668 tokens 16.28.422.725 I slot print_timing: id 2 | task 16520 | graphs reused = 15095 16.28.422.725 I slot print_timing: id 2 | task 16520 | graph reallocs = 0 / 0 (same size) / (changed size) 16.28.422.753 I slot release: id 2 | task 16520 | stop processing: n_tokens = 667, truncated = 0 16.28.422.863 I slot print_timing: id 3 | task 16521 | prompt eval time = 6646.99 ms / 715 tokens ( 9.30 ms per token, 107.57 tokens per second) 16.28.422.865 I slot print_timing: id 3 | task 16521 | eval time = 79.52 ms / 2 tokens ( 79.52 ms per token, 12.58 tokens per second) 16.28.422.866 I slot print_timing: id 3 | task 16521 | total time = 6726.51 ms / 717 tokens 16.28.422.866 I slot print_timing: id 3 | task 16521 | graphs reused = 15095 16.28.422.866 I slot print_timing: id 3 | task 16521 | graph reallocs = 0 / 0 (same size) / (changed size) 16.28.422.894 I slot release: id 3 | task 16521 | stop processing: n_tokens = 716, truncated = 0 16.28.445.128 I slot print_timing: id 0 | task 16519 | prompt eval time = 6726.45 ms / 740 tokens ( 9.09 ms per token, 110.01 tokens per second) 16.28.445.131 I slot print_timing: id 0 | task 16519 | eval time = 22.63 ms / 2 tokens ( 22.63 ms per token, 44.19 tokens per second) 16.28.445.131 I slot print_timing: id 0 | task 16519 | total time = 6749.08 ms / 742 tokens 16.28.445.132 I slot print_timing: id 0 | task 16519 | graphs reused = 15095 16.28.445.132 I slot print_timing: id 0 | task 16519 | graph reallocs = 0 / 0 (same size) / (changed size) 16.28.445.170 I slot release: id 0 | task 16519 | stop processing: n_tokens = 741, truncated = 0 16.28.445.177 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 601, t_last = 351807749603 16.28.445.244 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 184.245 MiB) 16.28.449.241 I slot launch_slot_: id 1 | task 16529 | processing task, is_child = 0 16.28.449.314 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 181.974 MiB) 16.28.457.424 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 144.299 MiB) 16.28.461.118 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.882 (> 0.100 thold), f_keep = 0.855 16.28.461.191 I slot launch_slot_: id 2 | task 16530 | processing task, is_child = 0 16.28.461.321 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 716, t_last = 351807749873 16.28.461.419 I slot launch_slot_: id 3 | task 16531 | processing task, is_child = 0 16.28.461.477 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 741, t_last = 351807772149 16.28.461.574 I slot launch_slot_: id 0 | task 16532 | processing task, is_child = 0 16.31.983.958 I slot print_timing: id 2 | task 16530 | prompt eval time = 1317.06 ms / 76 tokens ( 17.33 ms per token, 57.70 tokens per second) 16.31.983.960 I slot print_timing: id 2 | task 16530 | eval time = 2205.11 ms / 2 tokens ( 2205.11 ms per token, 0.45 tokens per second) 16.31.983.961 I slot print_timing: id 2 | task 16530 | total time = 3522.17 ms / 78 tokens 16.31.983.961 I slot print_timing: id 2 | task 16530 | graphs reused = 15095 16.31.983.962 I slot print_timing: id 2 | task 16530 | graph reallocs = 0 / 0 (same size) / (changed size) 16.31.984.000 I slot release: id 2 | task 16530 | stop processing: n_tokens = 647, truncated = 0 16.31.984.015 I slot print_timing: id 0 | task 16532 | prompt processing, n_tokens = 522, progress = 0.84, t = 3.52 s / 148.20 tokens per second 16.31.985.621 I slot print_timing: id 1 | task 16529 | prompt processing, n_tokens = 522, progress = 0.84, t = 3.52 s / 148.20 tokens per second 16.31.987.401 I slot print_timing: id 3 | task 16531 | prompt processing, n_tokens = 522, progress = 0.81, t = 3.52 s / 148.26 tokens per second 16.32.483.608 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 647, t_last = 351811310979 16.32.483.683 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 146.022 MiB) 16.32.878.056 I slot launch_slot_: id 2 | task 16537 | processing task, is_child = 0 16.32.878.069 I slot print_timing: id 0 | task 16532 | prompt processing, n_tokens = 618, progress = 0.99, t = 4.02 s / 153.65 tokens per second 16.32.880.580 I slot print_timing: id 1 | task 16529 | prompt processing, n_tokens = 617, progress = 0.99, t = 4.02 s / 153.41 tokens per second 16.32.881.961 I slot print_timing: id 3 | task 16531 | prompt processing, n_tokens = 642, progress = 0.99, t = 4.02 s / 159.67 tokens per second 16.33.412.178 I slot print_timing: id 0 | task 16532 | prompt eval time = 4832.31 ms / 622 tokens ( 7.77 ms per token, 128.72 tokens per second) 16.33.412.180 I slot print_timing: id 0 | task 16532 | eval time = 118.28 ms / 2 tokens ( 118.28 ms per token, 8.45 tokens per second) 16.33.412.181 I slot print_timing: id 0 | task 16532 | total time = 4950.59 ms / 624 tokens 16.33.412.181 I slot print_timing: id 0 | task 16532 | graphs reused = 15095 16.33.412.182 I slot print_timing: id 0 | task 16532 | graph reallocs = 0 / 0 (same size) / (changed size) 16.33.412.213 I slot release: id 0 | task 16532 | stop processing: n_tokens = 623, truncated = 0 16.33.412.303 I slot print_timing: id 1 | task 16529 | prompt eval time = 4832.30 ms / 621 tokens ( 7.78 ms per token, 128.51 tokens per second) 16.33.412.304 I slot print_timing: id 1 | task 16529 | eval time = 118.31 ms / 2 tokens ( 118.31 ms per token, 8.45 tokens per second) 16.33.412.305 I slot print_timing: id 1 | task 16529 | total time = 4950.61 ms / 623 tokens 16.33.412.305 I slot print_timing: id 1 | task 16529 | graphs reused = 15095 16.33.412.306 I slot print_timing: id 1 | task 16529 | graph reallocs = 0 / 0 (same size) / (changed size) 16.33.412.328 I slot release: id 1 | task 16529 | stop processing: n_tokens = 622, truncated = 0 16.33.412.425 I slot print_timing: id 3 | task 16531 | prompt eval time = 4831.20 ms / 646 tokens ( 7.48 ms per token, 133.71 tokens per second) 16.33.412.429 I slot print_timing: id 3 | task 16531 | eval time = 118.32 ms / 2 tokens ( 118.32 ms per token, 8.45 tokens per second) 16.33.412.430 I slot print_timing: id 3 | task 16531 | total time = 4949.52 ms / 648 tokens 16.33.412.430 I slot print_timing: id 3 | task 16531 | graphs reused = 15095 16.33.412.430 I slot print_timing: id 3 | task 16531 | graph reallocs = 0 / 0 (same size) / (changed size) 16.33.412.453 I slot release: id 3 | task 16531 | stop processing: n_tokens = 647, truncated = 0 16.34.186.592 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.877 (> 0.100 thold), f_keep = 0.878 16.34.186.664 I slot launch_slot_: id 0 | task 16542 | processing task, is_child = 0 16.34.186.730 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 155.882 MiB) 16.34.518.042 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 152.819 MiB) 16.34.523.090 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.887 (> 0.100 thold), f_keep = 0.879 16.34.523.172 I slot launch_slot_: id 1 | task 16543 | processing task, is_child = 0 16.34.523.232 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.889 (> 0.100 thold), f_keep = 0.845 16.34.523.277 I slot launch_slot_: id 3 | task 16544 | processing task, is_child = 0 16.35.444.658 I slot print_timing: id 2 | task 16537 | prompt eval time = 2429.74 ms / 617 tokens ( 3.94 ms per token, 253.94 tokens per second) 16.35.444.662 I slot print_timing: id 2 | task 16537 | eval time = 133.03 ms / 2 tokens ( 133.03 ms per token, 7.52 tokens per second) 16.35.444.662 I slot print_timing: id 2 | task 16537 | total time = 2562.77 ms / 619 tokens 16.35.444.663 I slot print_timing: id 2 | task 16537 | graphs reused = 15095 16.35.444.663 I slot print_timing: id 2 | task 16537 | graph reallocs = 0 / 0 (same size) / (changed size) 16.35.444.700 I slot release: id 2 | task 16537 | stop processing: n_tokens = 618, truncated = 0 16.35.498.065 I slot print_timing: id 0 | task 16542 | prompt eval time = 921.20 ms / 77 tokens ( 11.96 ms per token, 83.59 tokens per second) 16.35.498.070 I slot print_timing: id 0 | task 16542 | eval time = 53.58 ms / 2 tokens ( 53.58 ms per token, 18.66 tokens per second) 16.35.498.071 I slot print_timing: id 0 | task 16542 | total time = 974.78 ms / 79 tokens 16.35.498.071 I slot print_timing: id 0 | task 16542 | graphs reused = 15095 16.35.498.072 I slot print_timing: id 0 | task 16542 | graph reallocs = 0 / 0 (same size) / (changed size) 16.35.498.100 I slot release: id 0 | task 16542 | stop processing: n_tokens = 625, truncated = 0 16.35.498.189 I slot print_timing: id 1 | task 16543 | prompt eval time = 920.13 ms / 70 tokens ( 13.14 ms per token, 76.08 tokens per second) 16.35.498.194 I slot print_timing: id 1 | task 16543 | eval time = 53.61 ms / 2 tokens ( 53.61 ms per token, 18.65 tokens per second) 16.35.498.195 I slot print_timing: id 1 | task 16543 | total time = 973.74 ms / 72 tokens 16.35.498.195 I slot print_timing: id 1 | task 16543 | graphs reused = 15095 16.35.498.195 I slot print_timing: id 1 | task 16543 | graph reallocs = 0 / 0 (same size) / (changed size) 16.35.498.217 I slot release: id 1 | task 16543 | stop processing: n_tokens = 618, truncated = 0 16.35.498.307 I slot print_timing: id 3 | task 16544 | prompt eval time = 918.09 ms / 68 tokens ( 13.50 ms per token, 74.07 tokens per second) 16.35.498.308 I slot print_timing: id 3 | task 16544 | eval time = 53.50 ms / 2 tokens ( 53.50 ms per token, 18.69 tokens per second) 16.35.498.310 I slot print_timing: id 3 | task 16544 | total time = 971.59 ms / 70 tokens 16.35.498.310 I slot print_timing: id 3 | task 16544 | graphs reused = 15095 16.35.498.310 I slot print_timing: id 3 | task 16544 | graph reallocs = 0 / 0 (same size) / (changed size) 16.35.498.325 I slot release: id 3 | task 16544 | stop processing: n_tokens = 616, truncated = 0 16.35.498.331 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.879 (> 0.100 thold), f_keep = 0.890 16.35.498.424 I slot launch_slot_: id 1 | task 16548 | processing task, is_child = 0 16.35.498.490 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 181.480 MiB) 16.35.502.908 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 151.547 MiB) 16.35.506.617 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 145.516 MiB) 16.35.513.399 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.834 (> 0.100 thold), f_keep = 0.875 16.35.513.468 I slot launch_slot_: id 0 | task 16549 | processing task, is_child = 0 16.35.513.579 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.885 (> 0.100 thold), f_keep = 0.885 16.35.513.619 I slot launch_slot_: id 2 | task 16551 | processing task, is_child = 0 16.35.513.673 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.877 (> 0.100 thold), f_keep = 0.890 16.35.513.719 I slot launch_slot_: id 3 | task 16550 | processing task, is_child = 0 16.36.607.928 I slot print_timing: id 0 | task 16549 | prompt eval time = 1051.39 ms / 109 tokens ( 9.65 ms per token, 103.67 tokens per second) 16.36.607.931 I slot print_timing: id 0 | task 16549 | eval time = 42.81 ms / 2 tokens ( 42.81 ms per token, 23.36 tokens per second) 16.36.607.931 I slot print_timing: id 0 | task 16549 | total time = 1094.20 ms / 111 tokens 16.36.607.932 I slot print_timing: id 0 | task 16549 | graphs reused = 15095 16.36.607.932 I slot print_timing: id 0 | task 16549 | graph reallocs = 0 / 0 (same size) / (changed size) 16.36.607.967 I slot release: id 0 | task 16549 | stop processing: n_tokens = 657, truncated = 0 16.36.608.054 I slot print_timing: id 1 | task 16548 | prompt eval time = 1050.34 ms / 76 tokens ( 13.82 ms per token, 72.36 tokens per second) 16.36.608.056 I slot print_timing: id 1 | task 16548 | eval time = 42.83 ms / 2 tokens ( 42.83 ms per token, 23.35 tokens per second) 16.36.608.056 I slot print_timing: id 1 | task 16548 | total time = 1093.17 ms / 78 tokens 16.36.608.056 I slot print_timing: id 1 | task 16548 | graphs reused = 15095 16.36.608.057 I slot print_timing: id 1 | task 16548 | graph reallocs = 0 / 0 (same size) / (changed size) 16.36.608.076 I slot release: id 1 | task 16548 | stop processing: n_tokens = 627, truncated = 0 16.36.608.171 I slot print_timing: id 2 | task 16551 | prompt eval time = 1049.30 ms / 71 tokens ( 14.78 ms per token, 67.66 tokens per second) 16.36.608.174 I slot print_timing: id 2 | task 16551 | eval time = 42.80 ms / 2 tokens ( 42.80 ms per token, 23.36 tokens per second) 16.36.608.174 I slot print_timing: id 2 | task 16551 | total time = 1092.11 ms / 73 tokens 16.36.608.174 I slot print_timing: id 2 | task 16551 | graphs reused = 15095 16.36.608.175 I slot print_timing: id 2 | task 16551 | graph reallocs = 0 / 0 (same size) / (changed size) 16.36.608.194 I slot release: id 2 | task 16551 | stop processing: n_tokens = 619, truncated = 0 16.36.608.276 I slot print_timing: id 3 | task 16550 | prompt eval time = 1048.30 ms / 77 tokens ( 13.61 ms per token, 73.45 tokens per second) 16.36.608.278 I slot print_timing: id 3 | task 16550 | eval time = 42.80 ms / 2 tokens ( 42.80 ms per token, 23.36 tokens per second) 16.36.608.279 I slot print_timing: id 3 | task 16550 | total time = 1091.11 ms / 79 tokens 16.36.608.279 I slot print_timing: id 3 | task 16550 | graphs reused = 15095 16.36.608.280 I slot print_timing: id 3 | task 16550 | graph reallocs = 0 / 0 (same size) / (changed size) 16.36.608.303 I slot release: id 3 | task 16550 | stop processing: n_tokens = 626, truncated = 0 16.36.617.613 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 657, t_last = 351815934946 16.36.617.681 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 147.718 MiB) 16.36.623.923 I slot launch_slot_: id 0 | task 16555 | processing task, is_child = 0 16.36.623.988 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 161.352 MiB) 16.36.623.993 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 159.246 MiB) 16.36.629.101 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 159.629 MiB) 16.36.635.214 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 195.976 MiB) 16.36.642.866 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 627, t_last = 351815935055 16.36.643.001 I slot launch_slot_: id 1 | task 16556 | processing task, is_child = 0 16.36.643.107 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 619, t_last = 351815935173 16.36.643.201 I slot launch_slot_: id 2 | task 16557 | processing task, is_child = 0 16.36.643.259 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 626, t_last = 351815935282 16.36.643.354 I slot launch_slot_: id 3 | task 16558 | processing task, is_child = 0 16.39.738.555 I slot print_timing: id 0 | task 16555 | prompt processing, n_tokens = 269, progress = 0.34, t = 3.10 s / 86.91 tokens per second 16.39.804.196 I slot print_timing: id 1 | task 16556 | prompt processing, n_tokens = 280, progress = 0.35, t = 3.10 s / 90.47 tokens per second 16.39.805.169 I slot print_timing: id 2 | task 16557 | prompt processing, n_tokens = 482, progress = 0.48, t = 3.10 s / 155.73 tokens per second 16.39.807.445 I slot print_timing: id 3 | task 16558 | prompt processing, n_tokens = 472, progress = 0.48, t = 3.09 s / 152.51 tokens per second 16.42.642.789 I slot print_timing: id 0 | task 16555 | prompt processing, n_tokens = 677, progress = 0.86, t = 6.00 s / 112.84 tokens per second 16.42.709.493 I slot print_timing: id 1 | task 16556 | prompt processing, n_tokens = 677, progress = 0.85, t = 6.00 s / 112.85 tokens per second 16.42.711.232 I slot print_timing: id 2 | task 16557 | prompt processing, n_tokens = 824, progress = 0.83, t = 6.00 s / 137.35 tokens per second 16.42.712.836 I slot print_timing: id 3 | task 16558 | prompt processing, n_tokens = 824, progress = 0.83, t = 6.00 s / 137.35 tokens per second 16.44.018.752 I slot print_timing: id 0 | task 16555 | prompt processing, n_tokens = 781, progress = 0.99, t = 7.38 s / 105.89 tokens per second 16.44.086.138 I slot print_timing: id 1 | task 16556 | prompt processing, n_tokens = 792, progress = 0.99, t = 7.38 s / 107.39 tokens per second 16.44.088.181 I slot print_timing: id 2 | task 16557 | prompt processing, n_tokens = 994, progress = 1.00, t = 7.38 s / 134.78 tokens per second 16.44.089.622 I slot print_timing: id 3 | task 16558 | prompt processing, n_tokens = 984, progress = 1.00, t = 7.38 s / 133.42 tokens per second 16.44.235.236 I slot print_timing: id 0 | task 16555 | prompt eval time = 7548.77 ms / 785 tokens ( 9.62 ms per token, 103.99 tokens per second) 16.44.235.238 I slot print_timing: id 0 | task 16555 | eval time = 43.10 ms / 2 tokens ( 43.10 ms per token, 23.20 tokens per second) 16.44.235.239 I slot print_timing: id 0 | task 16555 | total time = 7591.87 ms / 787 tokens 16.44.235.239 I slot print_timing: id 0 | task 16555 | graphs reused = 15096 16.44.235.239 I slot print_timing: id 0 | task 16555 | graph reallocs = 0 / 0 (same size) / (changed size) 16.44.235.276 I slot release: id 0 | task 16555 | stop processing: n_tokens = 786, truncated = 0 16.44.235.361 I slot print_timing: id 1 | task 16556 | prompt eval time = 7548.77 ms / 796 tokens ( 9.48 ms per token, 105.45 tokens per second) 16.44.235.363 I slot print_timing: id 1 | task 16556 | eval time = 43.14 ms / 2 tokens ( 43.14 ms per token, 23.18 tokens per second) 16.44.235.363 I slot print_timing: id 1 | task 16556 | total time = 7591.91 ms / 798 tokens 16.44.235.364 I slot print_timing: id 1 | task 16556 | graphs reused = 15096 16.44.235.364 I slot print_timing: id 1 | task 16556 | graph reallocs = 0 / 0 (same size) / (changed size) 16.44.235.387 I slot release: id 1 | task 16556 | stop processing: n_tokens = 797, truncated = 0 16.44.235.490 I slot print_timing: id 2 | task 16557 | prompt eval time = 7548.79 ms / 998 tokens ( 7.56 ms per token, 132.21 tokens per second) 16.44.235.492 I slot print_timing: id 2 | task 16557 | eval time = 43.17 ms / 2 tokens ( 43.17 ms per token, 23.16 tokens per second) 16.44.235.493 I slot print_timing: id 2 | task 16557 | total time = 7591.97 ms / 1000 tokens 16.44.235.493 I slot print_timing: id 2 | task 16557 | graphs reused = 15096 16.44.235.493 I slot print_timing: id 2 | task 16557 | graph reallocs = 0 / 0 (same size) / (changed size) 16.44.235.536 I slot release: id 2 | task 16557 | stop processing: n_tokens = 999, truncated = 0 16.44.235.617 I slot print_timing: id 3 | task 16558 | prompt eval time = 7548.81 ms / 988 tokens ( 7.64 ms per token, 130.88 tokens per second) 16.44.235.619 I slot print_timing: id 3 | task 16558 | eval time = 43.21 ms / 2 tokens ( 43.21 ms per token, 23.14 tokens per second) 16.44.235.619 I slot print_timing: id 3 | task 16558 | total time = 7592.02 ms / 990 tokens 16.44.235.619 I slot print_timing: id 3 | task 16558 | graphs reused = 15096 16.44.235.619 I slot print_timing: id 3 | task 16558 | graph reallocs = 0 / 0 (same size) / (changed size) 16.44.235.645 I slot release: id 3 | task 16558 | stop processing: n_tokens = 989, truncated = 0 16.44.245.628 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.892 16.44.245.749 I slot launch_slot_: id 2 | task 16566 | processing task, is_child = 0 16.44.245.828 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 147.212 MiB) 16.44.249.944 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 147.403 MiB) 16.44.254.061 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 161.762 MiB) 16.44.259.052 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.900 16.44.259.105 I slot launch_slot_: id 3 | task 16567 | processing task, is_child = 0 16.44.259.232 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 786, t_last = 351823562255 16.44.260.945 I slot launch_slot_: id 0 | task 16568 | processing task, is_child = 0 16.44.261.012 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 797, t_last = 351823562366 16.44.261.125 I slot launch_slot_: id 1 | task 16569 | processing task, is_child = 0 16.46.576.433 I slot print_timing: id 2 | task 16566 | prompt eval time = 1797.55 ms / 86 tokens ( 20.90 ms per token, 47.84 tokens per second) 16.46.576.436 I slot print_timing: id 2 | task 16566 | eval time = 515.60 ms / 2 tokens ( 515.60 ms per token, 1.94 tokens per second) 16.46.576.436 I slot print_timing: id 2 | task 16566 | total time = 2313.15 ms / 88 tokens 16.46.576.437 I slot print_timing: id 2 | task 16566 | graphs reused = 15096 16.46.576.437 I slot print_timing: id 2 | task 16566 | graph reallocs = 0 / 0 (same size) / (changed size) 16.46.576.474 I slot release: id 2 | task 16566 | stop processing: n_tokens = 978, truncated = 0 16.46.576.567 I slot print_timing: id 3 | task 16567 | prompt eval time = 1796.37 ms / 96 tokens ( 18.71 ms per token, 53.44 tokens per second) 16.46.576.571 I slot print_timing: id 3 | task 16567 | eval time = 515.62 ms / 2 tokens ( 515.62 ms per token, 1.94 tokens per second) 16.46.576.571 I slot print_timing: id 3 | task 16567 | total time = 2311.99 ms / 98 tokens 16.46.576.572 I slot print_timing: id 3 | task 16567 | graphs reused = 15096 16.46.576.572 I slot print_timing: id 3 | task 16567 | graph reallocs = 0 / 0 (same size) / (changed size) 16.46.576.601 I slot release: id 3 | task 16567 | stop processing: n_tokens = 987, truncated = 0 16.47.294.192 I slot print_timing: id 0 | task 16568 | prompt eval time = 2315.19 ms / 162 tokens ( 14.29 ms per token, 69.97 tokens per second) 16.47.294.195 I slot print_timing: id 0 | task 16568 | eval time = 717.85 ms / 2 tokens ( 717.85 ms per token, 1.39 tokens per second) 16.47.294.195 I slot print_timing: id 0 | task 16568 | total time = 3033.04 ms / 164 tokens 16.47.294.195 I slot print_timing: id 0 | task 16568 | graphs reused = 15096 16.47.294.196 I slot print_timing: id 0 | task 16568 | graph reallocs = 0 / 0 (same size) / (changed size) 16.47.294.242 I slot release: id 0 | task 16568 | stop processing: n_tokens = 986, truncated = 0 16.47.294.251 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.904 16.47.294.334 I slot launch_slot_: id 0 | task 16574 | processing task, is_child = 0 16.47.303.004 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 159.561 MiB) 16.47.303.010 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 160.326 MiB) 16.47.309.090 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.901 (> 0.100 thold), f_keep = 0.911 16.47.309.176 I slot launch_slot_: id 2 | task 16575 | processing task, is_child = 0 16.47.309.254 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.896 (> 0.100 thold), f_keep = 0.903 16.47.309.299 I slot launch_slot_: id 3 | task 16576 | processing task, is_child = 0 16.47.310.520 I slot print_timing: id 1 | task 16569 | prompt processing, n_tokens = 824, progress = 0.83, t = 3.03 s / 271.87 tokens per second 16.48.518.241 I slot print_timing: id 1 | task 16569 | prompt processing, n_tokens = 987, progress = 1.00, t = 4.21 s / 234.18 tokens per second 16.48.671.415 I slot print_timing: id 0 | task 16574 | prompt eval time = 1318.77 ms / 88 tokens ( 14.99 ms per token, 66.73 tokens per second) 16.48.671.417 I slot print_timing: id 0 | task 16574 | eval time = 43.33 ms / 2 tokens ( 43.33 ms per token, 23.08 tokens per second) 16.48.671.418 I slot print_timing: id 0 | task 16574 | total time = 1362.10 ms / 90 tokens 16.48.671.418 I slot print_timing: id 0 | task 16574 | graphs reused = 15096 16.48.671.419 I slot print_timing: id 0 | task 16574 | graph reallocs = 0 / 0 (same size) / (changed size) 16.48.671.462 I slot release: id 0 | task 16574 | stop processing: n_tokens = 980, truncated = 0 16.48.671.556 I slot print_timing: id 1 | task 16569 | prompt eval time = 4365.01 ms / 991 tokens ( 4.40 ms per token, 227.03 tokens per second) 16.48.671.558 I slot print_timing: id 1 | task 16569 | eval time = 43.38 ms / 2 tokens ( 43.38 ms per token, 23.05 tokens per second) 16.48.671.558 I slot print_timing: id 1 | task 16569 | total time = 4408.39 ms / 993 tokens 16.48.671.559 I slot print_timing: id 1 | task 16569 | graphs reused = 15096 16.48.671.559 I slot print_timing: id 1 | task 16569 | graph reallocs = 0 / 0 (same size) / (changed size) 16.48.671.583 I slot release: id 1 | task 16569 | stop processing: n_tokens = 992, truncated = 0 16.48.671.679 I slot print_timing: id 2 | task 16575 | prompt eval time = 1316.63 ms / 98 tokens ( 13.44 ms per token, 74.43 tokens per second) 16.48.671.681 I slot print_timing: id 2 | task 16575 | eval time = 43.32 ms / 2 tokens ( 43.32 ms per token, 23.08 tokens per second) 16.48.671.682 I slot print_timing: id 2 | task 16575 | total time = 1359.96 ms / 100 tokens 16.48.671.682 I slot print_timing: id 2 | task 16575 | graphs reused = 15096 16.48.671.682 I slot print_timing: id 2 | task 16575 | graph reallocs = 0 / 0 (same size) / (changed size) 16.48.671.713 I slot release: id 2 | task 16575 | stop processing: n_tokens = 990, truncated = 0 16.48.671.816 I slot print_timing: id 3 | task 16576 | prompt eval time = 1315.54 ms / 103 tokens ( 12.77 ms per token, 78.29 tokens per second) 16.48.671.820 I slot print_timing: id 3 | task 16576 | eval time = 43.29 ms / 2 tokens ( 43.29 ms per token, 23.10 tokens per second) 16.48.671.821 I slot print_timing: id 3 | task 16576 | total time = 1358.83 ms / 105 tokens 16.48.671.821 I slot print_timing: id 3 | task 16576 | graphs reused = 15096 16.48.671.821 I slot print_timing: id 3 | task 16576 | graph reallocs = 0 / 0 (same size) / (changed size) 16.48.671.843 I slot release: id 3 | task 16576 | stop processing: n_tokens = 995, truncated = 0 16.48.682.138 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.909 16.48.682.193 I slot launch_slot_: id 0 | task 16580 | processing task, is_child = 0 16.48.682.269 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 153.803 MiB) 16.48.686.839 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 190.875 MiB) 16.48.692.726 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 154.665 MiB) 16.48.702.381 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.898 16.48.702.442 I slot launch_slot_: id 1 | task 16581 | processing task, is_child = 0 16.48.702.587 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.900 16.48.702.637 I slot launch_slot_: id 2 | task 16582 | processing task, is_child = 0 16.48.702.704 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.895 16.48.702.740 I slot launch_slot_: id 3 | task 16583 | processing task, is_child = 0 16.49.675.375 I slot print_timing: id 0 | task 16580 | prompt eval time = 929.55 ms / 91 tokens ( 10.21 ms per token, 97.90 tokens per second) 16.49.675.377 I slot print_timing: id 0 | task 16580 | eval time = 43.07 ms / 2 tokens ( 43.07 ms per token, 23.22 tokens per second) 16.49.675.378 I slot print_timing: id 0 | task 16580 | total time = 972.62 ms / 93 tokens 16.49.675.379 I slot print_timing: id 0 | task 16580 | graphs reused = 15096 16.49.675.379 I slot print_timing: id 0 | task 16580 | graph reallocs = 0 / 0 (same size) / (changed size) 16.49.675.415 I slot release: id 0 | task 16580 | stop processing: n_tokens = 983, truncated = 0 16.49.675.499 I slot print_timing: id 1 | task 16581 | prompt eval time = 928.41 ms / 92 tokens ( 10.09 ms per token, 99.09 tokens per second) 16.49.675.502 I slot print_timing: id 1 | task 16581 | eval time = 43.10 ms / 2 tokens ( 43.10 ms per token, 23.20 tokens per second) 16.49.675.502 I slot print_timing: id 1 | task 16581 | total time = 971.52 ms / 94 tokens 16.49.675.502 I slot print_timing: id 1 | task 16581 | graphs reused = 15096 16.49.675.503 I slot print_timing: id 1 | task 16581 | graph reallocs = 0 / 0 (same size) / (changed size) 16.49.675.529 I slot release: id 1 | task 16581 | stop processing: n_tokens = 984, truncated = 0 16.49.675.608 I slot print_timing: id 2 | task 16582 | prompt eval time = 927.38 ms / 99 tokens ( 9.37 ms per token, 106.75 tokens per second) 16.49.675.612 I slot print_timing: id 2 | task 16582 | eval time = 43.10 ms / 2 tokens ( 43.10 ms per token, 23.20 tokens per second) 16.49.675.612 I slot print_timing: id 2 | task 16582 | total time = 970.48 ms / 101 tokens 16.49.675.612 I slot print_timing: id 2 | task 16582 | graphs reused = 15096 16.49.675.613 I slot print_timing: id 2 | task 16582 | graph reallocs = 0 / 0 (same size) / (changed size) 16.49.675.633 I slot release: id 2 | task 16582 | stop processing: n_tokens = 991, truncated = 0 16.49.675.714 I slot print_timing: id 3 | task 16583 | prompt eval time = 926.29 ms / 96 tokens ( 9.65 ms per token, 103.64 tokens per second) 16.49.675.717 I slot print_timing: id 3 | task 16583 | eval time = 43.11 ms / 2 tokens ( 43.11 ms per token, 23.20 tokens per second) 16.49.675.717 I slot print_timing: id 3 | task 16583 | total time = 969.40 ms / 98 tokens 16.49.675.717 I slot print_timing: id 3 | task 16583 | graphs reused = 15096 16.49.675.718 I slot print_timing: id 3 | task 16583 | graph reallocs = 0 / 0 (same size) / (changed size) 16.49.675.742 I slot release: id 3 | task 16583 | stop processing: n_tokens = 988, truncated = 0 16.49.685.347 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 983, t_last = 351829002394 16.49.685.472 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 154.282 MiB) 16.49.685.477 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 181.687 MiB) 16.49.692.012 I slot launch_slot_: id 0 | task 16587 | processing task, is_child = 0 16.49.692.087 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 181.906 MiB) 16.49.697.582 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 183.438 MiB) 16.49.702.855 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 232.003 MiB) 16.49.709.367 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 984, t_last = 351829002508 16.49.709.512 I slot launch_slot_: id 1 | task 16588 | processing task, is_child = 0 16.49.709.653 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.904 (> 0.100 thold), f_keep = 0.899 16.49.709.701 I slot launch_slot_: id 2 | task 16589 | processing task, is_child = 0 16.49.709.772 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.902 16.49.709.810 I slot launch_slot_: id 3 | task 16590 | processing task, is_child = 0 16.51.935.266 I slot print_timing: id 2 | task 16589 | prompt eval time = 1876.33 ms / 95 tokens ( 19.75 ms per token, 50.63 tokens per second) 16.51.935.270 I slot print_timing: id 2 | task 16589 | eval time = 348.86 ms / 2 tokens ( 348.86 ms per token, 2.87 tokens per second) 16.51.935.271 I slot print_timing: id 2 | task 16589 | total time = 2225.19 ms / 97 tokens 16.51.935.271 I slot print_timing: id 2 | task 16589 | graphs reused = 15096 16.51.935.272 I slot print_timing: id 2 | task 16589 | graph reallocs = 0 / 0 (same size) / (changed size) 16.51.935.314 I slot release: id 2 | task 16589 | stop processing: n_tokens = 987, truncated = 0 16.51.935.401 I slot print_timing: id 3 | task 16590 | prompt eval time = 1875.25 ms / 94 tokens ( 19.95 ms per token, 50.13 tokens per second) 16.51.935.403 I slot print_timing: id 3 | task 16590 | eval time = 348.89 ms / 2 tokens ( 348.89 ms per token, 2.87 tokens per second) 16.51.935.403 I slot print_timing: id 3 | task 16590 | total time = 2224.14 ms / 96 tokens 16.51.935.404 I slot print_timing: id 3 | task 16590 | graphs reused = 15096 16.51.935.404 I slot print_timing: id 3 | task 16590 | graph reallocs = 0 / 0 (same size) / (changed size) 16.51.935.433 I slot release: id 3 | task 16590 | stop processing: n_tokens = 986, truncated = 0 16.53.340.843 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 987, t_last = 351831262293 16.53.340.950 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 229.651 MiB) 16.53.416.672 I slot launch_slot_: id 2 | task 16595 | processing task, is_child = 0 16.53.416.759 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 236.161 MiB) 16.53.423.763 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 986, t_last = 351831262412 16.53.423.895 I slot launch_slot_: id 3 | task 16596 | processing task, is_child = 0 16.53.423.903 I slot print_timing: id 0 | task 16587 | prompt processing, n_tokens = 764, progress = 0.86, t = 3.63 s / 210.41 tokens per second 16.53.425.072 I slot print_timing: id 1 | task 16588 | prompt processing, n_tokens = 764, progress = 0.84, t = 3.63 s / 210.42 tokens per second 16.54.510.143 I slot print_timing: id 0 | task 16587 | prompt processing, n_tokens = 889, progress = 1.00, t = 4.80 s / 185.20 tokens per second 16.54.816.234 I slot print_timing: id 1 | task 16588 | prompt processing, n_tokens = 901, progress = 1.00, t = 4.80 s / 187.70 tokens per second 16.56.073.450 I slot print_timing: id 0 | task 16587 | prompt eval time = 5786.31 ms / 893 tokens ( 6.48 ms per token, 154.33 tokens per second) 16.56.073.453 I slot print_timing: id 0 | task 16587 | eval time = 577.33 ms / 2 tokens ( 577.33 ms per token, 1.73 tokens per second) 16.56.073.453 I slot print_timing: id 0 | task 16587 | total time = 6363.63 ms / 895 tokens 16.56.073.454 I slot print_timing: id 0 | task 16587 | graphs reused = 15096 16.56.073.454 I slot print_timing: id 0 | task 16587 | graph reallocs = 0 / 0 (same size) / (changed size) 16.56.073.499 I slot release: id 0 | task 16587 | stop processing: n_tokens = 894, truncated = 0 16.56.073.590 I slot print_timing: id 1 | task 16588 | prompt eval time = 5786.29 ms / 905 tokens ( 6.39 ms per token, 156.40 tokens per second) 16.56.073.593 I slot print_timing: id 1 | task 16588 | eval time = 577.37 ms / 2 tokens ( 577.37 ms per token, 1.73 tokens per second) 16.56.073.594 I slot print_timing: id 1 | task 16588 | total time = 6363.66 ms / 907 tokens 16.56.073.594 I slot print_timing: id 1 | task 16588 | graphs reused = 15096 16.56.073.594 I slot print_timing: id 1 | task 16588 | graph reallocs = 0 / 0 (same size) / (changed size) 16.56.073.626 I slot release: id 1 | task 16588 | stop processing: n_tokens = 906, truncated = 0 16.57.321.845 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.864 (> 0.100 thold), f_keep = 0.883 16.57.321.920 I slot launch_slot_: id 0 | task 16601 | processing task, is_child = 0 16.57.322.009 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 233.508 MiB) 16.57.466.449 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.880 (> 0.100 thold), f_keep = 0.871 16.57.466.532 I slot launch_slot_: id 1 | task 16602 | processing task, is_child = 0 16.57.469.773 I slot print_timing: id 2 | task 16595 | prompt processing, n_tokens = 764, progress = 0.81, t = 3.90 s / 196.12 tokens per second 16.57.470.931 I slot print_timing: id 3 | task 16596 | prompt processing, n_tokens = 764, progress = 0.79, t = 3.90 s / 196.13 tokens per second 16.58.934.518 I slot print_timing: id 2 | task 16595 | prompt processing, n_tokens = 937, progress = 1.00, t = 5.36 s / 174.77 tokens per second 16.58.936.417 I slot print_timing: id 3 | task 16596 | prompt processing, n_tokens = 964, progress = 1.00, t = 5.36 s / 179.81 tokens per second 16.59.081.875 I slot print_timing: id 0 | task 16601 | prompt eval time = 1572.20 ms / 124 tokens ( 12.68 ms per token, 78.87 tokens per second) 16.59.081.878 I slot print_timing: id 0 | task 16601 | eval time = 43.12 ms / 2 tokens ( 43.12 ms per token, 23.19 tokens per second) 16.59.081.879 I slot print_timing: id 0 | task 16601 | total time = 1615.33 ms / 126 tokens 16.59.081.879 I slot print_timing: id 0 | task 16601 | graphs reused = 15096 16.59.081.880 I slot print_timing: id 0 | task 16601 | graph reallocs = 0 / 0 (same size) / (changed size) 16.59.081.929 I slot release: id 0 | task 16601 | stop processing: n_tokens = 914, truncated = 0 16.59.082.017 I slot print_timing: id 1 | task 16602 | prompt eval time = 1570.44 ms / 108 tokens ( 14.54 ms per token, 68.77 tokens per second) 16.59.082.020 I slot print_timing: id 1 | task 16602 | eval time = 43.17 ms / 2 tokens ( 43.17 ms per token, 23.16 tokens per second) 16.59.082.020 I slot print_timing: id 1 | task 16602 | total time = 1613.61 ms / 110 tokens 16.59.082.021 I slot print_timing: id 1 | task 16602 | graphs reused = 15096 16.59.082.021 I slot print_timing: id 1 | task 16602 | graph reallocs = 0 / 0 (same size) / (changed size) 16.59.082.047 I slot release: id 1 | task 16602 | stop processing: n_tokens = 898, truncated = 0 16.59.082.149 I slot print_timing: id 2 | task 16595 | prompt eval time = 5612.72 ms / 941 tokens ( 5.96 ms per token, 167.65 tokens per second) 16.59.082.151 I slot print_timing: id 2 | task 16595 | eval time = 43.21 ms / 2 tokens ( 43.21 ms per token, 23.14 tokens per second) 16.59.082.152 I slot print_timing: id 2 | task 16595 | total time = 5655.93 ms / 943 tokens 16.59.082.152 I slot print_timing: id 2 | task 16595 | graphs reused = 15096 16.59.082.153 I slot print_timing: id 2 | task 16595 | graph reallocs = 0 / 0 (same size) / (changed size) 16.59.082.175 I slot release: id 2 | task 16595 | stop processing: n_tokens = 942, truncated = 0 16.59.082.259 I slot print_timing: id 3 | task 16596 | prompt eval time = 5612.67 ms / 968 tokens ( 5.80 ms per token, 172.47 tokens per second) 16.59.082.260 I slot print_timing: id 3 | task 16596 | eval time = 43.22 ms / 2 tokens ( 43.22 ms per token, 23.14 tokens per second) 16.59.082.261 I slot print_timing: id 3 | task 16596 | total time = 5655.89 ms / 970 tokens 16.59.082.261 I slot print_timing: id 3 | task 16596 | graphs reused = 15096 16.59.082.262 I slot print_timing: id 3 | task 16596 | graph reallocs = 0 / 0 (same size) / (changed size) 16.59.082.292 I slot release: id 3 | task 16596 | stop processing: n_tokens = 969, truncated = 0 16.59.091.149 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 914, t_last = 351838408909 16.59.091.229 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 199.030 MiB) 16.59.096.273 I slot launch_slot_: id 0 | task 16606 | processing task, is_child = 0 16.59.096.344 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 236.540 MiB) 16.59.101.476 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 204.063 MiB) 16.59.106.132 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 199.194 MiB) 16.59.110.713 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 898, t_last = 351838409026 16.59.110.854 I slot launch_slot_: id 1 | task 16607 | processing task, is_child = 0 16.59.110.995 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 942, t_last = 351838409154 16.59.111.113 I slot launch_slot_: id 2 | task 16608 | processing task, is_child = 0 16.59.111.184 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 969, t_last = 351838409271 16.59.111.298 I slot launch_slot_: id 3 | task 16609 | processing task, is_child = 0 17.03.269.050 I slot print_timing: id 0 | task 16606 | prompt processing, n_tokens = 536, progress = 0.85, t = 4.16 s / 128.92 tokens per second 17.03.331.255 I slot print_timing: id 1 | task 16607 | prompt processing, n_tokens = 536, progress = 0.82, t = 4.16 s / 128.92 tokens per second 17.03.333.557 I slot print_timing: id 2 | task 16608 | prompt processing, n_tokens = 536, progress = 0.83, t = 4.16 s / 128.92 tokens per second 17.03.335.315 I slot print_timing: id 3 | task 16609 | prompt processing, n_tokens = 536, progress = 0.77, t = 4.16 s / 128.93 tokens per second 17.04.371.130 I slot print_timing: id 0 | task 16606 | prompt processing, n_tokens = 623, progress = 0.99, t = 5.26 s / 118.45 tokens per second 17.04.630.035 I slot print_timing: id 1 | task 16607 | prompt processing, n_tokens = 648, progress = 0.99, t = 5.26 s / 123.20 tokens per second 17.04.632.607 I slot print_timing: id 2 | task 16608 | prompt processing, n_tokens = 639, progress = 0.99, t = 5.26 s / 121.49 tokens per second 17.04.633.794 I slot print_timing: id 3 | task 16609 | prompt processing, n_tokens = 692, progress = 0.99, t = 5.26 s / 131.57 tokens per second 17.04.778.125 I slot print_timing: id 0 | task 16606 | prompt eval time = 5623.49 ms / 627 tokens ( 8.97 ms per token, 111.50 tokens per second) 17.04.778.127 I slot print_timing: id 0 | task 16606 | eval time = 43.33 ms / 2 tokens ( 43.33 ms per token, 23.08 tokens per second) 17.04.778.127 I slot print_timing: id 0 | task 16606 | total time = 5666.82 ms / 629 tokens 17.04.778.128 I slot print_timing: id 0 | task 16606 | graphs reused = 15097 17.04.778.128 I slot print_timing: id 0 | task 16606 | graph reallocs = 0 / 0 (same size) / (changed size) 17.04.778.165 I slot release: id 0 | task 16606 | stop processing: n_tokens = 628, truncated = 0 17.04.778.248 I slot print_timing: id 1 | task 16607 | prompt eval time = 5623.51 ms / 652 tokens ( 8.63 ms per token, 115.94 tokens per second) 17.04.778.252 I slot print_timing: id 1 | task 16607 | eval time = 43.28 ms / 2 tokens ( 43.28 ms per token, 23.10 tokens per second) 17.04.778.252 I slot print_timing: id 1 | task 16607 | total time = 5666.80 ms / 654 tokens 17.04.778.252 I slot print_timing: id 1 | task 16607 | graphs reused = 15097 17.04.778.253 I slot print_timing: id 1 | task 16607 | graph reallocs = 0 / 0 (same size) / (changed size) 17.04.778.274 I slot release: id 1 | task 16607 | stop processing: n_tokens = 653, truncated = 0 17.04.778.370 I slot print_timing: id 2 | task 16608 | prompt eval time = 5623.57 ms / 643 tokens ( 8.75 ms per token, 114.34 tokens per second) 17.04.778.373 I slot print_timing: id 2 | task 16608 | eval time = 43.23 ms / 2 tokens ( 43.23 ms per token, 23.13 tokens per second) 17.04.778.373 I slot print_timing: id 2 | task 16608 | total time = 5666.80 ms / 645 tokens 17.04.778.373 I slot print_timing: id 2 | task 16608 | graphs reused = 15097 17.04.778.374 I slot print_timing: id 2 | task 16608 | graph reallocs = 0 / 0 (same size) / (changed size) 17.04.778.391 I slot release: id 2 | task 16608 | stop processing: n_tokens = 644, truncated = 0 17.04.778.479 I slot print_timing: id 3 | task 16609 | prompt eval time = 5623.55 ms / 696 tokens ( 8.08 ms per token, 123.77 tokens per second) 17.04.778.482 I slot print_timing: id 3 | task 16609 | eval time = 43.24 ms / 2 tokens ( 43.24 ms per token, 23.13 tokens per second) 17.04.778.483 I slot print_timing: id 3 | task 16609 | total time = 5666.79 ms / 698 tokens 17.04.778.483 I slot print_timing: id 3 | task 16609 | graphs reused = 15097 17.04.778.483 I slot print_timing: id 3 | task 16609 | graph reallocs = 0 / 0 (same size) / (changed size) 17.04.778.501 I slot release: id 3 | task 16609 | stop processing: n_tokens = 697, truncated = 0 17.04.788.005 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.882 (> 0.100 thold), f_keep = 0.862 17.04.788.067 I slot launch_slot_: id 1 | task 16617 | processing task, is_child = 0 17.04.794.864 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 232.382 MiB) 17.04.798.533 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 141.140 MiB) 17.04.802.214 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.889 (> 0.100 thold), f_keep = 0.893 17.04.802.275 I slot launch_slot_: id 0 | task 16616 | processing task, is_child = 0 17.04.802.385 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.871 (> 0.100 thold), f_keep = 0.871 17.04.802.449 I slot launch_slot_: id 2 | task 16618 | processing task, is_child = 0 17.04.802.508 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.858 (> 0.100 thold), f_keep = 0.805 17.04.802.551 I slot launch_slot_: id 3 | task 16619 | processing task, is_child = 0 17.05.807.203 I slot print_timing: id 0 | task 16616 | prompt eval time = 961.64 ms / 70 tokens ( 13.74 ms per token, 72.79 tokens per second) 17.05.807.205 I slot print_timing: id 0 | task 16616 | eval time = 42.99 ms / 2 tokens ( 42.99 ms per token, 23.26 tokens per second) 17.05.807.206 I slot print_timing: id 0 | task 16616 | total time = 1004.64 ms / 72 tokens 17.05.807.206 I slot print_timing: id 0 | task 16616 | graphs reused = 15097 17.05.807.206 I slot print_timing: id 0 | task 16616 | graph reallocs = 0 / 0 (same size) / (changed size) 17.05.807.237 I slot release: id 0 | task 16616 | stop processing: n_tokens = 632, truncated = 0 17.05.807.324 I slot print_timing: id 1 | task 16617 | prompt eval time = 960.58 ms / 75 tokens ( 12.81 ms per token, 78.08 tokens per second) 17.05.807.325 I slot print_timing: id 1 | task 16617 | eval time = 42.99 ms / 2 tokens ( 42.99 ms per token, 23.26 tokens per second) 17.05.807.325 I slot print_timing: id 1 | task 16617 | total time = 1003.58 ms / 77 tokens 17.05.807.326 I slot print_timing: id 1 | task 16617 | graphs reused = 15097 17.05.807.326 I slot print_timing: id 1 | task 16617 | graph reallocs = 0 / 0 (same size) / (changed size) 17.05.807.347 I slot release: id 1 | task 16617 | stop processing: n_tokens = 639, truncated = 0 17.05.807.447 I slot print_timing: id 2 | task 16618 | prompt eval time = 959.47 ms / 83 tokens ( 11.56 ms per token, 86.51 tokens per second) 17.05.807.449 I slot print_timing: id 2 | task 16618 | eval time = 43.00 ms / 2 tokens ( 43.00 ms per token, 23.26 tokens per second) 17.05.807.449 I slot print_timing: id 2 | task 16618 | total time = 1002.47 ms / 85 tokens 17.05.807.449 I slot print_timing: id 2 | task 16618 | graphs reused = 15097 17.05.807.450 I slot print_timing: id 2 | task 16618 | graph reallocs = 0 / 0 (same size) / (changed size) 17.05.807.472 I slot release: id 2 | task 16618 | stop processing: n_tokens = 645, truncated = 0 17.05.807.553 I slot print_timing: id 3 | task 16619 | prompt eval time = 958.47 ms / 93 tokens ( 10.31 ms per token, 97.03 tokens per second) 17.05.807.555 I slot print_timing: id 3 | task 16619 | eval time = 42.98 ms / 2 tokens ( 42.98 ms per token, 23.27 tokens per second) 17.05.807.555 I slot print_timing: id 3 | task 16619 | total time = 1001.45 ms / 95 tokens 17.05.807.555 I slot print_timing: id 3 | task 16619 | graphs reused = 15097 17.05.807.555 I slot print_timing: id 3 | task 16619 | graph reallocs = 0 / 0 (same size) / (changed size) 17.05.807.569 I slot release: id 3 | task 16619 | stop processing: n_tokens = 655, truncated = 0 17.05.816.549 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.870 (> 0.100 thold), f_keep = 0.888 17.05.816.627 I slot launch_slot_: id 0 | task 16623 | processing task, is_child = 0 17.05.816.693 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 142.193 MiB) 17.05.820.985 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 174.328 MiB) 17.05.825.293 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 138.938 MiB) 17.05.829.755 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 639, t_last = 351845134326 17.05.829.883 I slot launch_slot_: id 1 | task 16624 | processing task, is_child = 0 17.05.829.993 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 645, t_last = 351845134451 17.05.830.086 I slot launch_slot_: id 2 | task 16625 | processing task, is_child = 0 17.05.830.142 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 655, t_last = 351845134548 17.05.830.232 I slot launch_slot_: id 3 | task 16626 | processing task, is_child = 0 17.08.077.089 I slot print_timing: id 0 | task 16623 | prompt eval time = 1882.06 ms / 84 tokens ( 22.41 ms per token, 44.63 tokens per second) 17.08.077.092 I slot print_timing: id 0 | task 16623 | eval time = 364.79 ms / 2 tokens ( 364.79 ms per token, 2.74 tokens per second) 17.08.077.092 I slot print_timing: id 0 | task 16623 | total time = 2246.84 ms / 86 tokens 17.08.077.093 I slot print_timing: id 0 | task 16623 | graphs reused = 15097 17.08.077.093 I slot print_timing: id 0 | task 16623 | graph reallocs = 0 / 0 (same size) / (changed size) 17.08.077.130 I slot release: id 0 | task 16623 | stop processing: n_tokens = 646, truncated = 0 17.10.170.134 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 646, t_last = 351847404109 17.10.170.219 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 144.108 MiB) 17.10.295.896 I slot launch_slot_: id 0 | task 16631 | processing task, is_child = 0 17.10.296.020 I slot print_timing: id 1 | task 16624 | prompt processing, n_tokens = 706, progress = 0.85, t = 4.34 s / 162.72 tokens per second 17.10.297.957 I slot print_timing: id 2 | task 16625 | prompt processing, n_tokens = 706, progress = 0.83, t = 4.34 s / 162.73 tokens per second 17.10.299.180 I slot print_timing: id 3 | task 16626 | prompt processing, n_tokens = 706, progress = 0.82, t = 4.34 s / 162.73 tokens per second 17.11.540.987 I slot print_timing: id 1 | task 16624 | prompt processing, n_tokens = 823, progress = 1.00, t = 5.66 s / 145.38 tokens per second 17.11.542.743 I slot print_timing: id 2 | task 16625 | prompt processing, n_tokens = 845, progress = 1.00, t = 5.66 s / 149.27 tokens per second 17.11.545.241 I slot print_timing: id 3 | task 16626 | prompt processing, n_tokens = 852, progress = 1.00, t = 5.66 s / 150.51 tokens per second 17.12.489.713 I slot print_timing: id 1 | task 16624 | prompt eval time = 6276.55 ms / 827 tokens ( 7.59 ms per token, 131.76 tokens per second) 17.12.489.715 I slot print_timing: id 1 | task 16624 | eval time = 381.65 ms / 2 tokens ( 381.65 ms per token, 2.62 tokens per second) 17.12.489.716 I slot print_timing: id 1 | task 16624 | total time = 6658.20 ms / 829 tokens 17.12.489.716 I slot print_timing: id 1 | task 16624 | graphs reused = 15097 17.12.489.717 I slot print_timing: id 1 | task 16624 | graph reallocs = 0 / 0 (same size) / (changed size) 17.12.489.759 I slot release: id 1 | task 16624 | stop processing: n_tokens = 828, truncated = 0 17.12.489.849 I slot print_timing: id 2 | task 16625 | prompt eval time = 6276.60 ms / 849 tokens ( 7.39 ms per token, 135.26 tokens per second) 17.12.489.851 I slot print_timing: id 2 | task 16625 | eval time = 381.64 ms / 2 tokens ( 381.64 ms per token, 2.62 tokens per second) 17.12.489.852 I slot print_timing: id 2 | task 16625 | total time = 6658.24 ms / 851 tokens 17.12.489.852 I slot print_timing: id 2 | task 16625 | graphs reused = 15097 17.12.489.852 I slot print_timing: id 2 | task 16625 | graph reallocs = 0 / 0 (same size) / (changed size) 17.12.489.878 I slot release: id 2 | task 16625 | stop processing: n_tokens = 850, truncated = 0 17.12.489.975 I slot print_timing: id 3 | task 16626 | prompt eval time = 6276.64 ms / 856 tokens ( 7.33 ms per token, 136.38 tokens per second) 17.12.489.977 I slot print_timing: id 3 | task 16626 | eval time = 381.63 ms / 2 tokens ( 381.63 ms per token, 2.62 tokens per second) 17.12.489.977 I slot print_timing: id 3 | task 16626 | total time = 6658.28 ms / 858 tokens 17.12.489.978 I slot print_timing: id 3 | task 16626 | graphs reused = 15097 17.12.489.978 I slot print_timing: id 3 | task 16626 | graph reallocs = 0 / 0 (same size) / (changed size) 17.12.490.003 I slot release: id 3 | task 16626 | stop processing: n_tokens = 857, truncated = 0 17.13.145.473 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 828, t_last = 351851816738 17.13.145.551 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 171.704 MiB) 17.13.679.505 I slot launch_slot_: id 1 | task 16637 | processing task, is_child = 0 17.13.679.585 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 146.829 MiB) 17.13.688.527 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 146.446 MiB) 17.13.696.453 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 850, t_last = 351851816857 17.13.696.603 I slot launch_slot_: id 2 | task 16638 | processing task, is_child = 0 17.13.696.671 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 857, t_last = 351851816982 17.13.696.784 I slot launch_slot_: id 3 | task 16639 | processing task, is_child = 0 17.16.187.546 I slot print_timing: id 0 | task 16631 | prompt eval time = 4756.43 ms / 912 tokens ( 5.22 ms per token, 191.74 tokens per second) 17.16.187.552 I slot print_timing: id 0 | task 16631 | eval time = 1135.19 ms / 2 tokens ( 1135.19 ms per token, 0.88 tokens per second) 17.16.187.553 I slot print_timing: id 0 | task 16631 | total time = 5891.62 ms / 914 tokens 17.16.187.553 I slot print_timing: id 0 | task 16631 | graphs reused = 15097 17.16.187.554 I slot print_timing: id 0 | task 16631 | graph reallocs = 0 / 0 (same size) / (changed size) 17.16.187.605 I slot release: id 0 | task 16631 | stop processing: n_tokens = 913, truncated = 0 17.18.138.977 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 913, t_last = 351855514584 17.18.139.071 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 149.632 MiB) 17.18.537.659 I slot launch_slot_: id 0 | task 16643 | processing task, is_child = 0 17.18.537.815 I slot print_timing: id 1 | task 16637 | prompt processing, n_tokens = 454, progress = 0.47, t = 4.44 s / 102.23 tokens per second 17.18.539.972 I slot print_timing: id 2 | task 16638 | prompt processing, n_tokens = 463, progress = 0.47, t = 4.44 s / 104.26 tokens per second 17.18.541.611 I slot print_timing: id 3 | task 16639 | prompt processing, n_tokens = 1419, progress = 0.73, t = 4.44 s / 319.55 tokens per second 17.21.154.149 I slot print_timing: id 1 | task 16637 | prompt processing, n_tokens = 832, progress = 0.86, t = 7.39 s / 112.53 tokens per second 17.21.155.549 I slot print_timing: id 2 | task 16638 | prompt processing, n_tokens = 832, progress = 0.85, t = 7.39 s / 112.53 tokens per second 17.21.157.557 I slot print_timing: id 3 | task 16639 | prompt processing, n_tokens = 1634, progress = 0.84, t = 7.39 s / 221.01 tokens per second 17.22.735.161 I slot print_timing: id 0 | task 16643 | prompt processing, n_tokens = 598, progress = 0.31, t = 4.20 s / 142.47 tokens per second 17.22.735.186 I slot print_timing: id 1 | task 16637 | prompt processing, n_tokens = 966, progress = 1.00, t = 9.04 s / 106.89 tokens per second 17.23.188.999 I slot print_timing: id 2 | task 16638 | prompt processing, n_tokens = 975, progress = 1.00, t = 9.04 s / 107.89 tokens per second 17.23.191.635 I slot print_timing: id 3 | task 16639 | prompt processing, n_tokens = 1931, progress = 1.00, t = 9.04 s / 213.68 tokens per second 17.24.871.909 I slot print_timing: id 0 | task 16643 | prompt processing, n_tokens = 1431, progress = 0.73, t = 6.33 s / 225.93 tokens per second 17.25.452.079 I slot print_timing: id 1 | task 16637 | prompt eval time = 11173.55 ms / 970 tokens ( 11.52 ms per token, 86.81 tokens per second) 17.25.452.081 I slot print_timing: id 1 | task 16637 | eval time = 580.44 ms / 2 tokens ( 580.44 ms per token, 1.72 tokens per second) 17.25.452.082 I slot print_timing: id 1 | task 16637 | total time = 11753.99 ms / 972 tokens 17.25.452.082 I slot print_timing: id 1 | task 16637 | graphs reused = 15097 17.25.452.083 I slot print_timing: id 1 | task 16637 | graph reallocs = 0 / 0 (same size) / (changed size) 17.25.452.129 I slot release: id 1 | task 16637 | stop processing: n_tokens = 971, truncated = 0 17.25.452.228 I slot print_timing: id 2 | task 16638 | prompt eval time = 11173.57 ms / 979 tokens ( 11.41 ms per token, 87.62 tokens per second) 17.25.452.231 I slot print_timing: id 2 | task 16638 | eval time = 580.46 ms / 2 tokens ( 580.46 ms per token, 1.72 tokens per second) 17.25.452.231 I slot print_timing: id 2 | task 16638 | total time = 11754.03 ms / 981 tokens 17.25.452.231 I slot print_timing: id 2 | task 16638 | graphs reused = 15097 17.25.452.232 I slot print_timing: id 2 | task 16638 | graph reallocs = 0 / 0 (same size) / (changed size) 17.25.452.263 I slot release: id 2 | task 16638 | stop processing: n_tokens = 980, truncated = 0 17.25.452.373 I slot print_timing: id 3 | task 16639 | prompt eval time = 11173.58 ms / 1935 tokens ( 5.77 ms per token, 173.18 tokens per second) 17.25.452.375 I slot print_timing: id 3 | task 16639 | eval time = 580.48 ms / 2 tokens ( 580.48 ms per token, 1.72 tokens per second) 17.25.452.375 I slot print_timing: id 3 | task 16639 | total time = 11754.06 ms / 1937 tokens 17.25.452.376 I slot print_timing: id 3 | task 16639 | graphs reused = 15097 17.25.452.376 I slot print_timing: id 3 | task 16639 | graph reallocs = 0 / 0 (same size) / (changed size) 17.25.452.461 I slot release: id 3 | task 16639 | stop processing: n_tokens = 1936, truncated = 0 17.25.452.470 I slot print_timing: id 0 | task 16643 | prompt processing, n_tokens = 1634, progress = 0.84, t = 6.91 s / 236.32 tokens per second 17.25.461.422 I slot print_timing: id 0 | task 16643 | prompt processing, n_tokens = 1943, progress = 1.00, t = 6.92 s / 280.63 tokens per second 17.26.181.518 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.878 (> 0.100 thold), f_keep = 0.857 17.26.181.600 I slot launch_slot_: id 3 | task 16650 | processing task, is_child = 0 17.26.181.682 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 155.759 MiB) 17.26.181.686 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 155.185 MiB) 17.26.190.564 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 185.720 MiB) 17.26.198.808 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 971, t_last = 351864779108 17.26.198.943 I slot launch_slot_: id 1 | task 16651 | processing task, is_child = 0 17.26.199.014 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 980, t_last = 351864779242 17.26.199.126 I slot launch_slot_: id 2 | task 16652 | processing task, is_child = 0 17.28.076.342 I slot print_timing: id 0 | task 16643 | prompt eval time = 7643.83 ms / 1947 tokens ( 3.93 ms per token, 254.72 tokens per second) 17.28.076.345 I slot print_timing: id 0 | task 16643 | eval time = 1894.83 ms / 2 tokens ( 1894.83 ms per token, 0.53 tokens per second) 17.28.076.346 I slot print_timing: id 0 | task 16643 | total time = 9538.66 ms / 1949 tokens 17.28.076.346 I slot print_timing: id 0 | task 16643 | graphs reused = 15097 17.28.076.347 I slot print_timing: id 0 | task 16643 | graph reallocs = 0 / 0 (same size) / (changed size) 17.28.076.431 I slot release: id 0 | task 16643 | stop processing: n_tokens = 1948, truncated = 0 17.29.013.187 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.836 (> 0.100 thold), f_keep = 0.852 17.29.013.288 I slot launch_slot_: id 0 | task 16655 | processing task, is_child = 0 17.32.761.337 I slot print_timing: id 3 | task 16650 | prompt eval time = 2813.80 ms / 231 tokens ( 12.18 ms per token, 82.10 tokens per second) 17.32.761.344 I slot print_timing: id 3 | task 16650 | eval time = 3748.15 ms / 2 tokens ( 3748.15 ms per token, 0.27 tokens per second) 17.32.761.344 I slot print_timing: id 3 | task 16650 | total time = 6561.95 ms / 233 tokens 17.32.761.345 I slot print_timing: id 3 | task 16650 | graphs reused = 15097 17.32.761.345 I slot print_timing: id 3 | task 16650 | graph reallocs = 0 / 0 (same size) / (changed size) 17.32.761.425 I slot release: id 3 | task 16650 | stop processing: n_tokens = 1892, truncated = 0 17.32.761.440 I slot print_timing: id 0 | task 16655 | prompt processing, n_tokens = 321, progress = 1.00, t = 3.75 s / 85.65 tokens per second 17.32.763.550 I slot print_timing: id 1 | task 16651 | prompt processing, n_tokens = 1397, progress = 0.73, t = 6.56 s / 212.89 tokens per second 17.32.765.674 I slot print_timing: id 2 | task 16652 | prompt processing, n_tokens = 1443, progress = 0.74, t = 6.56 s / 219.90 tokens per second 17.33.841.398 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.866 (> 0.100 thold), f_keep = 0.877 17.33.841.520 I slot launch_slot_: id 3 | task 16658 | processing task, is_child = 0 17.33.841.529 I slot print_timing: id 1 | task 16651 | prompt processing, n_tokens = 1634, progress = 0.85, t = 7.64 s / 213.82 tokens per second 17.33.843.114 I slot print_timing: id 2 | task 16652 | prompt processing, n_tokens = 1634, progress = 0.83, t = 7.64 s / 213.82 tokens per second 17.35.943.034 I slot print_timing: id 0 | task 16655 | prompt eval time = 4828.08 ms / 325 tokens ( 14.86 ms per token, 67.31 tokens per second) 17.35.943.036 I slot print_timing: id 0 | task 16655 | eval time = 2101.65 ms / 2 tokens ( 2101.65 ms per token, 0.48 tokens per second) 17.35.943.036 I slot print_timing: id 0 | task 16655 | total time = 6929.73 ms / 327 tokens 17.35.943.037 I slot print_timing: id 0 | task 16655 | graphs reused = 15097 17.35.943.037 I slot print_timing: id 0 | task 16655 | graph reallocs = 0 / 0 (same size) / (changed size) 17.35.943.121 I slot release: id 0 | task 16655 | stop processing: n_tokens = 1986, truncated = 0 17.35.943.134 I slot print_timing: id 1 | task 16651 | prompt processing, n_tokens = 1909, progress = 1.00, t = 9.74 s / 195.92 tokens per second 17.35.945.181 I slot print_timing: id 2 | task 16652 | prompt processing, n_tokens = 1955, progress = 1.00, t = 9.74 s / 200.64 tokens per second 17.36.034.293 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.832 (> 0.100 thold), f_keep = 0.836 17.36.034.408 I slot launch_slot_: id 0 | task 16661 | processing task, is_child = 0 17.36.792.151 I slot print_timing: id 1 | task 16651 | prompt eval time = 9834.89 ms / 1913 tokens ( 5.14 ms per token, 194.51 tokens per second) 17.36.792.154 I slot print_timing: id 1 | task 16651 | eval time = 758.13 ms / 2 tokens ( 758.13 ms per token, 1.32 tokens per second) 17.36.792.155 I slot print_timing: id 1 | task 16651 | total time = 10593.01 ms / 1915 tokens 17.36.792.155 I slot print_timing: id 1 | task 16651 | graphs reused = 15097 17.36.792.156 I slot print_timing: id 1 | task 16651 | graph reallocs = 0 / 0 (same size) / (changed size) 17.36.792.234 I slot release: id 1 | task 16651 | stop processing: n_tokens = 1914, truncated = 0 17.36.792.329 I slot print_timing: id 2 | task 16652 | prompt eval time = 9834.90 ms / 1959 tokens ( 5.02 ms per token, 199.19 tokens per second) 17.36.792.332 I slot print_timing: id 2 | task 16652 | eval time = 758.17 ms / 2 tokens ( 758.17 ms per token, 1.32 tokens per second) 17.36.792.333 I slot print_timing: id 2 | task 16652 | total time = 10593.07 ms / 1961 tokens 17.36.792.333 I slot print_timing: id 2 | task 16652 | graphs reused = 15097 17.36.792.333 I slot print_timing: id 2 | task 16652 | graph reallocs = 0 / 0 (same size) / (changed size) 17.36.792.382 I slot release: id 2 | task 16652 | stop processing: n_tokens = 1960, truncated = 0 17.36.792.485 I slot print_timing: id 3 | task 16658 | prompt eval time = 2189.69 ms / 257 tokens ( 8.52 ms per token, 117.37 tokens per second) 17.36.792.491 I slot print_timing: id 3 | task 16658 | eval time = 758.20 ms / 2 tokens ( 758.20 ms per token, 1.32 tokens per second) 17.36.792.491 I slot print_timing: id 3 | task 16658 | total time = 2947.88 ms / 259 tokens 17.36.792.491 I slot print_timing: id 3 | task 16658 | graphs reused = 15097 17.36.792.492 I slot print_timing: id 3 | task 16658 | graph reallocs = 0 / 0 (same size) / (changed size) 17.36.792.536 I slot release: id 3 | task 16658 | stop processing: n_tokens = 1917, truncated = 0 17.36.837.796 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.892 (> 0.100 thold), f_keep = 0.867 17.36.837.884 I slot launch_slot_: id 1 | task 16664 | processing task, is_child = 0 17.36.838.006 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 134.590 MiB) 17.36.848.947 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 147.650 MiB) 17.36.848.954 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 140.429 MiB) 17.36.860.178 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.847 17.36.860.252 I slot launch_slot_: id 2 | task 16665 | processing task, is_child = 0 17.36.860.359 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.801 (> 0.100 thold), f_keep = 0.865 17.36.860.403 I slot launch_slot_: id 3 | task 16666 | processing task, is_child = 0 17.38.622.276 I slot print_timing: id 0 | task 16661 | prompt eval time = 803.37 ms / 336 tokens ( 2.39 ms per token, 418.24 tokens per second) 17.38.622.280 I slot print_timing: id 0 | task 16661 | eval time = 1784.48 ms / 2 tokens ( 1784.48 ms per token, 0.56 tokens per second) 17.38.622.280 I slot print_timing: id 0 | task 16661 | total time = 2587.86 ms / 338 tokens 17.38.622.281 I slot print_timing: id 0 | task 16661 | graphs reused = 15097 17.38.622.281 I slot print_timing: id 0 | task 16661 | graph reallocs = 0 / 0 (same size) / (changed size) 17.38.622.364 I slot release: id 0 | task 16661 | stop processing: n_tokens = 1997, truncated = 0 17.38.714.524 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.890 (> 0.100 thold), f_keep = 0.831 17.38.714.632 I slot launch_slot_: id 0 | task 16669 | processing task, is_child = 0 17.39.299.363 I slot print_timing: id 1 | task 16664 | prompt eval time = 1853.89 ms / 201 tokens ( 9.22 ms per token, 108.42 tokens per second) 17.39.299.365 I slot print_timing: id 1 | task 16664 | eval time = 585.06 ms / 2 tokens ( 585.06 ms per token, 1.71 tokens per second) 17.39.299.366 I slot print_timing: id 1 | task 16664 | total time = 2438.95 ms / 203 tokens 17.39.299.366 I slot print_timing: id 1 | task 16664 | graphs reused = 15097 17.39.299.366 I slot print_timing: id 1 | task 16664 | graph reallocs = 0 / 0 (same size) / (changed size) 17.39.299.439 I slot release: id 1 | task 16664 | stop processing: n_tokens = 1862, truncated = 0 17.39.299.550 I slot print_timing: id 2 | task 16665 | prompt eval time = 1852.74 ms / 169 tokens ( 10.96 ms per token, 91.22 tokens per second) 17.39.299.555 I slot print_timing: id 2 | task 16665 | eval time = 585.14 ms / 2 tokens ( 585.14 ms per token, 1.71 tokens per second) 17.39.299.555 I slot print_timing: id 2 | task 16665 | total time = 2437.88 ms / 171 tokens 17.39.299.555 I slot print_timing: id 2 | task 16665 | graphs reused = 15097 17.39.299.556 I slot print_timing: id 2 | task 16665 | graph reallocs = 0 / 0 (same size) / (changed size) 17.39.299.606 I slot release: id 2 | task 16665 | stop processing: n_tokens = 1830, truncated = 0 17.39.299.751 I slot print_timing: id 3 | task 16666 | prompt eval time = 1851.62 ms / 413 tokens ( 4.48 ms per token, 223.05 tokens per second) 17.39.299.755 I slot print_timing: id 3 | task 16666 | eval time = 585.23 ms / 2 tokens ( 585.23 ms per token, 1.71 tokens per second) 17.39.299.756 I slot print_timing: id 3 | task 16666 | total time = 2436.85 ms / 415 tokens 17.39.299.756 I slot print_timing: id 3 | task 16666 | graphs reused = 15097 17.39.299.756 I slot print_timing: id 3 | task 16666 | graph reallocs = 0 / 0 (same size) / (changed size) 17.39.299.811 I slot release: id 3 | task 16666 | stop processing: n_tokens = 2073, truncated = 0 17.39.345.263 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.849 (> 0.100 thold), f_keep = 0.892 17.39.345.323 I slot launch_slot_: id 1 | task 16672 | processing task, is_child = 0 17.39.345.442 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 145.256 MiB) 17.39.356.826 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 174.957 MiB) 17.39.356.831 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 135.643 MiB) 17.39.368.538 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.907 17.39.368.618 I slot launch_slot_: id 2 | task 16673 | processing task, is_child = 0 17.39.368.727 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.864 (> 0.100 thold), f_keep = 0.801 17.39.368.769 I slot launch_slot_: id 3 | task 16674 | processing task, is_child = 0 17.41.111.119 I slot print_timing: id 0 | task 16669 | prompt eval time = 630.62 ms / 206 tokens ( 3.06 ms per token, 326.66 tokens per second) 17.41.111.121 I slot print_timing: id 0 | task 16669 | eval time = 1765.85 ms / 2 tokens ( 1765.85 ms per token, 0.57 tokens per second) 17.41.111.122 I slot print_timing: id 0 | task 16669 | total time = 2396.47 ms / 208 tokens 17.41.111.122 I slot print_timing: id 0 | task 16669 | graphs reused = 15097 17.41.111.123 I slot print_timing: id 0 | task 16669 | graph reallocs = 0 / 0 (same size) / (changed size) 17.41.111.208 I slot release: id 0 | task 16669 | stop processing: n_tokens = 1866, truncated = 0 17.41.201.556 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.864 (> 0.100 thold), f_keep = 0.889 17.41.201.666 I slot launch_slot_: id 0 | task 16677 | processing task, is_child = 0 17.41.869.723 I slot print_timing: id 1 | task 16672 | prompt eval time = 1832.57 ms / 295 tokens ( 6.21 ms per token, 160.98 tokens per second) 17.41.869.725 I slot print_timing: id 1 | task 16672 | eval time = 668.38 ms / 2 tokens ( 668.38 ms per token, 1.50 tokens per second) 17.41.869.727 I slot print_timing: id 1 | task 16672 | total time = 2500.95 ms / 297 tokens 17.41.869.727 I slot print_timing: id 1 | task 16672 | graphs reused = 15097 17.41.869.728 I slot print_timing: id 1 | task 16672 | graph reallocs = 0 / 0 (same size) / (changed size) 17.41.869.803 I slot release: id 1 | task 16672 | stop processing: n_tokens = 1956, truncated = 0 17.41.869.957 I slot print_timing: id 2 | task 16673 | prompt eval time = 1831.43 ms / 169 tokens ( 10.84 ms per token, 92.28 tokens per second) 17.41.869.960 I slot print_timing: id 2 | task 16673 | eval time = 668.52 ms / 2 tokens ( 668.52 ms per token, 1.50 tokens per second) 17.41.869.960 I slot print_timing: id 2 | task 16673 | total time = 2499.95 ms / 171 tokens 17.41.869.961 I slot print_timing: id 2 | task 16673 | graphs reused = 15097 17.41.869.961 I slot print_timing: id 2 | task 16673 | graph reallocs = 0 / 0 (same size) / (changed size) 17.41.870.009 I slot release: id 2 | task 16673 | stop processing: n_tokens = 1829, truncated = 0 17.41.870.145 I slot print_timing: id 3 | task 16674 | prompt eval time = 1830.33 ms / 261 tokens ( 7.01 ms per token, 142.60 tokens per second) 17.41.870.148 I slot print_timing: id 3 | task 16674 | eval time = 668.60 ms / 2 tokens ( 668.60 ms per token, 1.50 tokens per second) 17.41.870.148 I slot print_timing: id 3 | task 16674 | total time = 2498.93 ms / 263 tokens 17.41.870.149 I slot print_timing: id 3 | task 16674 | graphs reused = 15097 17.41.870.149 I slot print_timing: id 3 | task 16674 | graph reallocs = 0 / 0 (same size) / (changed size) 17.41.870.190 I slot release: id 3 | task 16674 | stop processing: n_tokens = 1922, truncated = 0 17.41.915.505 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.843 (> 0.100 thold), f_keep = 0.849 17.41.915.580 I slot launch_slot_: id 1 | task 16680 | processing task, is_child = 0 17.41.915.695 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 138.036 MiB) 17.41.915.703 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 170.868 MiB) 17.41.926.876 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 135.260 MiB) 17.41.926.880 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 172.263 MiB) 17.41.934.159 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.864 17.41.934.240 I slot launch_slot_: id 3 | task 16681 | processing task, is_child = 0 17.41.934.346 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.823 (> 0.100 thold), f_keep = 0.907 17.41.934.391 I slot launch_slot_: id 2 | task 16682 | processing task, is_child = 0 17.43.813.037 I slot print_timing: id 0 | task 16677 | prompt eval time = 713.83 ms / 262 tokens ( 2.72 ms per token, 367.04 tokens per second) 17.43.813.039 I slot print_timing: id 0 | task 16677 | eval time = 1897.53 ms / 2 tokens ( 1897.53 ms per token, 0.53 tokens per second) 17.43.813.039 I slot print_timing: id 0 | task 16677 | total time = 2611.36 ms / 264 tokens 17.43.813.040 I slot print_timing: id 0 | task 16677 | graphs reused = 15097 17.43.813.040 I slot print_timing: id 0 | task 16677 | graph reallocs = 0 / 0 (same size) / (changed size) 17.43.813.115 I slot release: id 0 | task 16677 | stop processing: n_tokens = 1922, truncated = 0 17.43.904.104 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.819 (> 0.100 thold), f_keep = 0.863 17.43.904.202 I slot launch_slot_: id 0 | task 16685 | processing task, is_child = 0 17.44.700.351 I slot print_timing: id 1 | task 16680 | prompt eval time = 1969.50 ms / 308 tokens ( 6.39 ms per token, 156.38 tokens per second) 17.44.700.353 I slot print_timing: id 1 | task 16680 | eval time = 796.45 ms / 2 tokens ( 796.45 ms per token, 1.26 tokens per second) 17.44.700.354 I slot print_timing: id 1 | task 16680 | total time = 2765.95 ms / 310 tokens 17.44.700.354 I slot print_timing: id 1 | task 16680 | graphs reused = 15097 17.44.700.354 I slot print_timing: id 1 | task 16680 | graph reallocs = 0 / 0 (same size) / (changed size) 17.44.700.433 I slot release: id 1 | task 16680 | stop processing: n_tokens = 1969, truncated = 0 17.44.700.532 I slot print_timing: id 2 | task 16682 | prompt eval time = 1968.36 ms / 358 tokens ( 5.50 ms per token, 181.88 tokens per second) 17.44.700.535 I slot print_timing: id 2 | task 16682 | eval time = 796.53 ms / 2 tokens ( 796.53 ms per token, 1.26 tokens per second) 17.44.700.536 I slot print_timing: id 2 | task 16682 | total time = 2764.90 ms / 360 tokens 17.44.700.536 I slot print_timing: id 2 | task 16682 | graphs reused = 15097 17.44.700.536 I slot print_timing: id 2 | task 16682 | graph reallocs = 0 / 0 (same size) / (changed size) 17.44.700.588 I slot release: id 2 | task 16682 | stop processing: n_tokens = 2018, truncated = 0 17.44.700.739 I slot print_timing: id 3 | task 16681 | prompt eval time = 1967.25 ms / 168 tokens ( 11.71 ms per token, 85.40 tokens per second) 17.44.700.741 I slot print_timing: id 3 | task 16681 | eval time = 796.64 ms / 2 tokens ( 796.64 ms per token, 1.26 tokens per second) 17.44.700.741 I slot print_timing: id 3 | task 16681 | total time = 2763.89 ms / 170 tokens 17.44.700.742 I slot print_timing: id 3 | task 16681 | graphs reused = 15097 17.44.700.742 I slot print_timing: id 3 | task 16681 | graph reallocs = 0 / 0 (same size) / (changed size) 17.44.700.784 I slot release: id 3 | task 16681 | stop processing: n_tokens = 1829, truncated = 0 17.44.745.912 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.876 (> 0.100 thold), f_keep = 0.843 17.44.745.971 I slot launch_slot_: id 1 | task 16688 | processing task, is_child = 0 17.44.746.107 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 171.744 MiB) 17.44.753.524 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 205.930 MiB) 17.44.753.531 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 170.362 MiB) 17.44.767.208 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.895 (> 0.100 thold), f_keep = 0.822 17.44.767.279 I slot launch_slot_: id 2 | task 16689 | processing task, is_child = 0 17.44.767.389 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.908 17.44.767.429 I slot launch_slot_: id 3 | task 16690 | processing task, is_child = 0 17.46.440.843 I slot print_timing: id 0 | task 16685 | prompt eval time = 841.69 ms / 366 tokens ( 2.30 ms per token, 434.84 tokens per second) 17.46.440.845 I slot print_timing: id 0 | task 16685 | eval time = 1694.94 ms / 2 tokens ( 1694.94 ms per token, 0.59 tokens per second) 17.46.440.846 I slot print_timing: id 0 | task 16685 | total time = 2536.63 ms / 368 tokens 17.46.440.846 I slot print_timing: id 0 | task 16685 | graphs reused = 15097 17.46.440.847 I slot print_timing: id 0 | task 16685 | graph reallocs = 0 / 0 (same size) / (changed size) 17.46.440.935 I slot release: id 0 | task 16685 | stop processing: n_tokens = 2026, truncated = 0 17.46.532.007 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.819 17.46.532.112 I slot launch_slot_: id 0 | task 16693 | processing task, is_child = 0 17.46.953.366 I slot print_timing: id 1 | task 16688 | prompt eval time = 1764.35 ms / 234 tokens ( 7.54 ms per token, 132.63 tokens per second) 17.46.953.368 I slot print_timing: id 1 | task 16688 | eval time = 421.57 ms / 2 tokens ( 421.57 ms per token, 2.37 tokens per second) 17.46.953.369 I slot print_timing: id 1 | task 16688 | total time = 2185.92 ms / 236 tokens 17.46.953.369 I slot print_timing: id 1 | task 16688 | graphs reused = 15097 17.46.953.370 I slot print_timing: id 1 | task 16688 | graph reallocs = 0 / 0 (same size) / (changed size) 17.46.953.443 I slot release: id 1 | task 16688 | stop processing: n_tokens = 1894, truncated = 0 17.46.953.604 I slot print_timing: id 2 | task 16689 | prompt eval time = 1763.22 ms / 194 tokens ( 9.09 ms per token, 110.03 tokens per second) 17.46.953.607 I slot print_timing: id 2 | task 16689 | eval time = 421.70 ms / 2 tokens ( 421.70 ms per token, 2.37 tokens per second) 17.46.953.607 I slot print_timing: id 2 | task 16689 | total time = 2184.92 ms / 196 tokens 17.46.953.607 I slot print_timing: id 2 | task 16689 | graphs reused = 15097 17.46.953.608 I slot print_timing: id 2 | task 16689 | graph reallocs = 0 / 0 (same size) / (changed size) 17.46.953.656 I slot release: id 2 | task 16689 | stop processing: n_tokens = 1854, truncated = 0 17.46.953.802 I slot print_timing: id 3 | task 16690 | prompt eval time = 1762.11 ms / 217 tokens ( 8.12 ms per token, 123.15 tokens per second) 17.46.953.804 I slot print_timing: id 3 | task 16690 | eval time = 421.80 ms / 2 tokens ( 421.80 ms per token, 2.37 tokens per second) 17.46.953.805 I slot print_timing: id 3 | task 16690 | total time = 2183.90 ms / 219 tokens 17.46.953.805 I slot print_timing: id 3 | task 16690 | graphs reused = 15097 17.46.953.805 I slot print_timing: id 3 | task 16690 | graph reallocs = 0 / 0 (same size) / (changed size) 17.46.953.847 I slot release: id 3 | task 16690 | stop processing: n_tokens = 1878, truncated = 0 17.46.998.827 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1894, t_last = 351886280423 17.46.998.957 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 207.612 MiB) 17.47.011.222 I slot launch_slot_: id 1 | task 16696 | processing task, is_child = 0 17.47.011.341 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 156.196 MiB) 17.47.022.484 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 157.249 MiB) 17.47.022.490 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 211.428 MiB) 17.47.029.322 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.895 17.47.029.391 I slot launch_slot_: id 2 | task 16697 | processing task, is_child = 0 17.47.029.498 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.884 17.47.029.541 I slot launch_slot_: id 3 | task 16698 | processing task, is_child = 0 17.48.601.845 I slot print_timing: id 0 | task 16693 | prompt eval time = 466.71 ms / 108 tokens ( 4.32 ms per token, 231.41 tokens per second) 17.48.601.851 I slot print_timing: id 0 | task 16693 | eval time = 1603.02 ms / 2 tokens ( 1603.02 ms per token, 0.62 tokens per second) 17.48.601.851 I slot print_timing: id 0 | task 16693 | total time = 2069.72 ms / 110 tokens 17.48.601.852 I slot print_timing: id 0 | task 16693 | graphs reused = 15097 17.48.601.852 I slot print_timing: id 0 | task 16693 | graph reallocs = 0 / 0 (same size) / (changed size) 17.48.601.925 I slot release: id 0 | task 16693 | stop processing: n_tokens = 1768, truncated = 0 17.49.183.498 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1768, t_last = 351887928905 17.49.183.632 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 210.991 MiB) 17.49.193.636 I slot launch_slot_: id 0 | task 16701 | processing task, is_child = 0 17.50.586.570 I slot print_timing: id 2 | task 16697 | prompt eval time = 2153.57 ms / 152 tokens ( 14.17 ms per token, 70.58 tokens per second) 17.50.586.574 I slot print_timing: id 2 | task 16697 | eval time = 1403.22 ms / 2 tokens ( 1403.22 ms per token, 0.71 tokens per second) 17.50.586.575 I slot print_timing: id 2 | task 16697 | total time = 3556.79 ms / 154 tokens 17.50.586.575 I slot print_timing: id 2 | task 16697 | graphs reused = 15097 17.50.586.576 I slot print_timing: id 2 | task 16697 | graph reallocs = 0 / 0 (same size) / (changed size) 17.50.586.647 I slot release: id 2 | task 16697 | stop processing: n_tokens = 1812, truncated = 0 17.50.586.813 I slot print_timing: id 3 | task 16698 | prompt eval time = 2152.50 ms / 191 tokens ( 11.27 ms per token, 88.73 tokens per second) 17.50.586.817 I slot print_timing: id 3 | task 16698 | eval time = 1403.32 ms / 2 tokens ( 1403.32 ms per token, 0.71 tokens per second) 17.50.586.817 I slot print_timing: id 3 | task 16698 | total time = 3555.82 ms / 193 tokens 17.50.586.818 I slot print_timing: id 3 | task 16698 | graphs reused = 15097 17.50.586.818 I slot print_timing: id 3 | task 16698 | graph reallocs = 0 / 0 (same size) / (changed size) 17.50.586.863 I slot release: id 3 | task 16698 | stop processing: n_tokens = 1852, truncated = 0 17.50.588.151 I slot print_timing: id 1 | task 16696 | prompt processing, n_tokens = 798, progress = 0.61, t = 3.56 s / 224.35 tokens per second 17.51.355.285 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1812, t_last = 351889913627 17.51.355.434 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 176.258 MiB) 17.51.355.608 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 211.757 MiB) 17.51.810.028 I slot launch_slot_: id 2 | task 16704 | processing task, is_child = 0 17.51.810.159 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 246.285 MiB) 17.51.817.069 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1852, t_last = 351889913842 17.51.817.235 I slot launch_slot_: id 3 | task 16705 | processing task, is_child = 0 17.51.817.259 I slot print_timing: id 1 | task 16696 | prompt processing, n_tokens = 1135, progress = 0.86, t = 4.33 s / 262.38 tokens per second 17.54.273.434 I slot print_timing: id 0 | task 16701 | prompt processing, n_tokens = 989, progress = 0.66, t = 5.08 s / 194.69 tokens per second 17.54.586.214 I slot print_timing: id 1 | task 16696 | prompt processing, n_tokens = 1310, progress = 1.00, t = 7.24 s / 180.84 tokens per second 17.55.999.917 I slot print_timing: id 0 | task 16701 | prompt processing, n_tokens = 1135, progress = 0.75, t = 6.81 s / 166.76 tokens per second 17.56.001.154 I slot print_timing: id 2 | task 16704 | prompt processing, n_tokens = 377, progress = 0.42, t = 4.18 s / 90.16 tokens per second 17.56.001.166 I slot print_timing: id 3 | task 16705 | prompt processing, n_tokens = 515, progress = 0.37, t = 4.18 s / 123.17 tokens per second 17.57.597.532 I slot print_timing: id 1 | task 16696 | prompt eval time = 8970.35 ms / 1314 tokens ( 6.83 ms per token, 146.48 tokens per second) 17.57.597.536 I slot print_timing: id 1 | task 16696 | eval time = 1597.62 ms / 2 tokens ( 1597.62 ms per token, 0.63 tokens per second) 17.57.597.537 I slot print_timing: id 1 | task 16696 | total time = 10567.98 ms / 1316 tokens 17.57.597.537 I slot print_timing: id 1 | task 16696 | graphs reused = 15097 17.57.597.538 I slot print_timing: id 1 | task 16696 | graph reallocs = 0 / 0 (same size) / (changed size) 17.57.597.606 I slot release: id 1 | task 16696 | stop processing: n_tokens = 1315, truncated = 0 17.57.597.620 I slot print_timing: id 0 | task 16701 | prompt processing, n_tokens = 1501, progress = 1.00, t = 8.40 s / 178.61 tokens per second 17.57.599.924 I slot print_timing: id 2 | task 16704 | prompt processing, n_tokens = 387, progress = 0.43, t = 5.78 s / 66.97 tokens per second 17.57.601.914 I slot print_timing: id 3 | task 16705 | prompt processing, n_tokens = 866, progress = 0.63, t = 5.78 s / 149.86 tokens per second 17.59.065.573 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1315, t_last = 351896924586 17.59.065.684 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 245.888 MiB) 17.59.072.399 I slot launch_slot_: id 1 | task 16710 | processing task, is_child = 0 17.59.072.588 I slot print_timing: id 2 | task 16704 | prompt processing, n_tokens = 766, progress = 0.85, t = 7.25 s / 105.70 tokens per second 17.59.073.743 I slot print_timing: id 3 | task 16705 | prompt processing, n_tokens = 1135, progress = 0.82, t = 7.25 s / 156.62 tokens per second 18.00.647.878 I slot print_timing: id 0 | task 16701 | prompt eval time = 9871.92 ms / 1505 tokens ( 6.56 ms per token, 152.45 tokens per second) 18.00.647.883 I slot print_timing: id 0 | task 16701 | eval time = 1582.31 ms / 2 tokens ( 1582.31 ms per token, 0.63 tokens per second) 18.00.647.883 I slot print_timing: id 0 | task 16701 | total time = 11454.23 ms / 1507 tokens 18.00.647.884 I slot print_timing: id 0 | task 16701 | graphs reused = 15097 18.00.647.884 I slot print_timing: id 0 | task 16701 | graph reallocs = 0 / 0 (same size) / (changed size) 18.00.647.951 I slot release: id 0 | task 16701 | stop processing: n_tokens = 1506, truncated = 0 18.00.650.393 I slot print_timing: id 2 | task 16704 | prompt processing, n_tokens = 899, progress = 1.00, t = 8.83 s / 101.82 tokens per second 18.00.652.182 I slot print_timing: id 3 | task 16705 | prompt processing, n_tokens = 1378, progress = 1.00, t = 8.83 s / 156.07 tokens per second 18.01.133.509 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1506, t_last = 351899974930 18.01.133.613 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 211.114 MiB) 18.01.140.135 I slot launch_slot_: id 0 | task 16713 | processing task, is_child = 0 18.02.458.202 I slot print_timing: id 2 | task 16704 | prompt eval time = 9314.93 ms / 903 tokens ( 10.32 ms per token, 96.94 tokens per second) 18.02.458.205 I slot print_timing: id 2 | task 16704 | eval time = 1324.83 ms / 2 tokens ( 1324.83 ms per token, 0.75 tokens per second) 18.02.458.206 I slot print_timing: id 2 | task 16704 | total time = 10639.76 ms / 905 tokens 18.02.458.206 I slot print_timing: id 2 | task 16704 | graphs reused = 15097 18.02.458.206 I slot print_timing: id 2 | task 16704 | graph reallocs = 0 / 0 (same size) / (changed size) 18.02.458.249 I slot release: id 2 | task 16704 | stop processing: n_tokens = 904, truncated = 0 18.02.458.343 I slot print_timing: id 3 | task 16705 | prompt eval time = 9314.89 ms / 1382 tokens ( 6.74 ms per token, 148.36 tokens per second) 18.02.458.345 I slot print_timing: id 3 | task 16705 | eval time = 1324.84 ms / 2 tokens ( 1324.84 ms per token, 0.75 tokens per second) 18.02.458.346 I slot print_timing: id 3 | task 16705 | total time = 10639.72 ms / 1384 tokens 18.02.458.346 I slot print_timing: id 3 | task 16705 | graphs reused = 15097 18.02.458.346 I slot print_timing: id 3 | task 16705 | graph reallocs = 0 / 0 (same size) / (changed size) 18.02.458.397 I slot release: id 3 | task 16705 | stop processing: n_tokens = 1383, truncated = 0 18.02.460.937 I slot print_timing: id 1 | task 16710 | prompt processing, n_tokens = 766, progress = 0.86, t = 3.39 s / 226.25 tokens per second 18.03.045.679 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.876 18.03.045.780 I slot launch_slot_: id 2 | task 16716 | processing task, is_child = 0 18.03.063.879 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1383, t_last = 351901785377 18.03.064.030 I slot launch_slot_: id 3 | task 16717 | processing task, is_child = 0 18.03.064.915 I slot print_timing: id 1 | task 16710 | prompt processing, n_tokens = 887, progress = 1.00, t = 3.97 s / 223.24 tokens per second 18.04.786.427 I slot print_timing: id 0 | task 16713 | prompt processing, n_tokens = 766, progress = 0.87, t = 3.65 s / 210.09 tokens per second 18.05.656.040 I slot print_timing: id 1 | task 16710 | prompt eval time = 5714.01 ms / 891 tokens ( 6.41 ms per token, 155.93 tokens per second) 18.05.656.042 I slot print_timing: id 1 | task 16710 | eval time = 869.61 ms / 2 tokens ( 869.61 ms per token, 1.15 tokens per second) 18.05.656.043 I slot print_timing: id 1 | task 16710 | total time = 6583.62 ms / 893 tokens 18.05.656.043 I slot print_timing: id 1 | task 16710 | graphs reused = 15097 18.05.656.044 I slot print_timing: id 1 | task 16710 | graph reallocs = 0 / 0 (same size) / (changed size) 18.05.656.086 I slot release: id 1 | task 16710 | stop processing: n_tokens = 892, truncated = 0 18.05.656.203 I slot print_timing: id 0 | task 16713 | prompt processing, n_tokens = 877, progress = 1.00, t = 4.52 s / 194.21 tokens per second 18.06.486.984 I slot print_timing: id 2 | task 16716 | prompt eval time = 2590.09 ms / 72 tokens ( 35.97 ms per token, 27.80 tokens per second) 18.06.486.986 I slot print_timing: id 2 | task 16716 | eval time = 830.78 ms / 2 tokens ( 830.78 ms per token, 1.20 tokens per second) 18.06.486.987 I slot print_timing: id 2 | task 16716 | total time = 3420.87 ms / 74 tokens 18.06.486.987 I slot print_timing: id 2 | task 16716 | graphs reused = 15097 18.06.486.988 I slot print_timing: id 2 | task 16716 | graph reallocs = 0 / 0 (same size) / (changed size) 18.06.487.039 I slot release: id 2 | task 16716 | stop processing: n_tokens = 865, truncated = 0 18.06.487.048 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.887 18.06.487.141 I slot launch_slot_: id 1 | task 16721 | processing task, is_child = 0 18.06.487.221 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 211.784 MiB) 18.06.495.177 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.899 (> 0.100 thold), f_keep = 0.914 18.06.495.253 I slot launch_slot_: id 2 | task 16722 | processing task, is_child = 0 18.06.497.571 I slot print_timing: id 3 | task 16717 | prompt processing, n_tokens = 766, progress = 0.86, t = 3.42 s / 224.01 tokens per second 18.07.338.034 I slot print_timing: id 0 | task 16713 | prompt eval time = 5346.73 ms / 881 tokens ( 6.07 ms per token, 164.77 tokens per second) 18.07.338.039 I slot print_timing: id 0 | task 16713 | eval time = 851.15 ms / 2 tokens ( 851.15 ms per token, 1.17 tokens per second) 18.07.338.040 I slot print_timing: id 0 | task 16713 | total time = 6197.88 ms / 883 tokens 18.07.338.040 I slot print_timing: id 0 | task 16713 | graphs reused = 15097 18.07.338.040 I slot print_timing: id 0 | task 16713 | graph reallocs = 0 / 0 (same size) / (changed size) 18.07.338.085 I slot release: id 0 | task 16713 | stop processing: n_tokens = 882, truncated = 0 18.07.341.505 I slot print_timing: id 3 | task 16717 | prompt processing, n_tokens = 882, progress = 1.00, t = 4.27 s / 206.53 tokens per second 18.07.425.958 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 882, t_last = 351906665064 18.07.426.038 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 246.093 MiB) 18.07.432.391 I slot launch_slot_: id 0 | task 16725 | processing task, is_child = 0 18.07.886.749 I slot print_timing: id 1 | task 16721 | prompt eval time = 930.49 ms / 83 tokens ( 11.21 ms per token, 89.20 tokens per second) 18.07.886.751 I slot print_timing: id 1 | task 16721 | eval time = 460.99 ms / 2 tokens ( 460.99 ms per token, 2.17 tokens per second) 18.07.886.751 I slot print_timing: id 1 | task 16721 | total time = 1391.48 ms / 85 tokens 18.07.886.752 I slot print_timing: id 1 | task 16721 | graphs reused = 15097 18.07.886.752 I slot print_timing: id 1 | task 16721 | graph reallocs = 0 / 0 (same size) / (changed size) 18.07.886.794 I slot release: id 1 | task 16721 | stop processing: n_tokens = 875, truncated = 0 18.07.886.940 I slot print_timing: id 2 | task 16722 | prompt eval time = 929.45 ms / 89 tokens ( 10.44 ms per token, 95.76 tokens per second) 18.07.886.946 I slot print_timing: id 2 | task 16722 | eval time = 461.09 ms / 2 tokens ( 461.09 ms per token, 2.17 tokens per second) 18.07.886.947 I slot print_timing: id 2 | task 16722 | total time = 1390.54 ms / 91 tokens 18.07.886.947 I slot print_timing: id 2 | task 16722 | graphs reused = 15097 18.07.886.948 I slot print_timing: id 2 | task 16722 | graph reallocs = 0 / 0 (same size) / (changed size) 18.07.886.972 I slot release: id 2 | task 16722 | stop processing: n_tokens = 881, truncated = 0 18.07.887.117 I slot print_timing: id 3 | task 16717 | prompt eval time = 4358.64 ms / 886 tokens ( 4.92 ms per token, 203.27 tokens per second) 18.07.887.124 I slot print_timing: id 3 | task 16717 | eval time = 461.16 ms / 2 tokens ( 461.16 ms per token, 2.17 tokens per second) 18.07.887.124 I slot print_timing: id 3 | task 16717 | total time = 4819.80 ms / 888 tokens 18.07.887.124 I slot print_timing: id 3 | task 16717 | graphs reused = 15097 18.07.887.124 I slot print_timing: id 3 | task 16717 | graph reallocs = 0 / 0 (same size) / (changed size) 18.07.887.148 I slot release: id 3 | task 16717 | stop processing: n_tokens = 887, truncated = 0 18.08.169.137 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 875, t_last = 351907213773 18.08.169.216 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 211.675 MiB) 18.08.926.215 I slot launch_slot_: id 1 | task 16729 | processing task, is_child = 0 18.08.926.305 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 246.039 MiB) 18.08.934.291 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 169.461 MiB) 18.08.939.791 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 881, t_last = 351907213952 18.08.939.940 I slot launch_slot_: id 2 | task 16730 | processing task, is_child = 0 18.08.940.005 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 887, t_last = 351907214127 18.08.940.114 I slot launch_slot_: id 3 | task 16731 | processing task, is_child = 0 18.10.441.792 I slot print_timing: id 0 | task 16725 | prompt processing, n_tokens = 712, progress = 0.99, t = 3.01 s / 236.59 tokens per second 18.14.519.335 I slot print_timing: id 0 | task 16725 | prompt eval time = 4285.19 ms / 716 tokens ( 5.98 ms per token, 167.09 tokens per second) 18.14.519.342 I slot print_timing: id 0 | task 16725 | eval time = 2801.74 ms / 2 tokens ( 2801.74 ms per token, 0.36 tokens per second) 18.14.519.342 I slot print_timing: id 0 | task 16725 | total time = 7086.93 ms / 718 tokens 18.14.519.343 I slot print_timing: id 0 | task 16725 | graphs reused = 15097 18.14.519.343 I slot print_timing: id 0 | task 16725 | graph reallocs = 0 / 0 (same size) / (changed size) 18.14.519.384 I slot release: id 0 | task 16725 | stop processing: n_tokens = 717, truncated = 0 18.14.519.398 I slot print_timing: id 1 | task 16729 | prompt processing, n_tokens = 987, progress = 0.66, t = 5.58 s / 176.95 tokens per second 18.14.521.093 I slot print_timing: id 2 | task 16730 | prompt processing, n_tokens = 945, progress = 0.65, t = 5.58 s / 169.42 tokens per second 18.14.523.784 I slot print_timing: id 3 | task 16731 | prompt processing, n_tokens = 973, progress = 0.65, t = 5.58 s / 174.46 tokens per second 18.16.246.346 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 717, t_last = 351913846363 18.16.246.429 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 203.934 MiB) 18.16.397.767 I slot launch_slot_: id 0 | task 16736 | processing task, is_child = 0 18.16.397.900 I slot print_timing: id 1 | task 16729 | prompt processing, n_tokens = 1265, progress = 0.84, t = 7.31 s / 173.17 tokens per second 18.16.399.602 I slot print_timing: id 2 | task 16730 | prompt processing, n_tokens = 1265, progress = 0.87, t = 7.30 s / 173.17 tokens per second 18.16.400.737 I slot print_timing: id 3 | task 16731 | prompt processing, n_tokens = 1265, progress = 0.85, t = 7.30 s / 173.19 tokens per second 18.18.719.034 I slot print_timing: id 1 | task 16729 | prompt processing, n_tokens = 1499, progress = 1.00, t = 9.63 s / 155.70 tokens per second 18.18.721.201 I slot print_timing: id 2 | task 16730 | prompt processing, n_tokens = 1457, progress = 1.00, t = 9.63 s / 151.34 tokens per second 18.18.722.541 I slot print_timing: id 3 | task 16731 | prompt processing, n_tokens = 1485, progress = 1.00, t = 9.63 s / 154.26 tokens per second 18.20.191.024 I slot print_timing: id 1 | task 16729 | prompt eval time = 10321.32 ms / 1503 tokens ( 6.87 ms per token, 145.62 tokens per second) 18.20.191.026 I slot print_timing: id 1 | task 16729 | eval time = 928.41 ms / 2 tokens ( 928.41 ms per token, 1.08 tokens per second) 18.20.191.026 I slot print_timing: id 1 | task 16729 | total time = 11249.73 ms / 1505 tokens 18.20.191.027 I slot print_timing: id 1 | task 16729 | graphs reused = 15097 18.20.191.027 I slot print_timing: id 1 | task 16729 | graph reallocs = 0 / 0 (same size) / (changed size) 18.20.191.090 I slot release: id 1 | task 16729 | stop processing: n_tokens = 1504, truncated = 0 18.20.191.188 I slot print_timing: id 2 | task 16730 | prompt eval time = 10321.29 ms / 1461 tokens ( 7.06 ms per token, 141.55 tokens per second) 18.20.191.190 I slot print_timing: id 2 | task 16730 | eval time = 928.47 ms / 2 tokens ( 928.47 ms per token, 1.08 tokens per second) 18.20.191.190 I slot print_timing: id 2 | task 16730 | total time = 11249.76 ms / 1463 tokens 18.20.191.191 I slot print_timing: id 2 | task 16730 | graphs reused = 15097 18.20.191.191 I slot print_timing: id 2 | task 16730 | graph reallocs = 0 / 0 (same size) / (changed size) 18.20.191.231 I slot release: id 2 | task 16730 | stop processing: n_tokens = 1462, truncated = 0 18.20.191.332 I slot print_timing: id 3 | task 16731 | prompt eval time = 10320.66 ms / 1489 tokens ( 6.93 ms per token, 144.27 tokens per second) 18.20.191.334 I slot print_timing: id 3 | task 16731 | eval time = 928.51 ms / 2 tokens ( 928.51 ms per token, 1.08 tokens per second) 18.20.191.335 I slot print_timing: id 3 | task 16731 | total time = 11249.17 ms / 1491 tokens 18.20.191.335 I slot print_timing: id 3 | task 16731 | graphs reused = 15097 18.20.191.335 I slot print_timing: id 3 | task 16731 | graph reallocs = 0 / 0 (same size) / (changed size) 18.20.191.367 I slot release: id 3 | task 16731 | stop processing: n_tokens = 1490, truncated = 0 18.20.191.373 I slot print_timing: id 0 | task 16736 | prompt processing, n_tokens = 989, progress = 0.66, t = 3.79 s / 260.73 tokens per second 18.20.199.721 I slot print_timing: id 0 | task 16736 | prompt processing, n_tokens = 1265, progress = 0.84, t = 3.80 s / 332.73 tokens per second 18.20.826.089 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1504, t_last = 351919518069 18.20.826.204 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 204.317 MiB) 18.21.404.615 I slot launch_slot_: id 1 | task 16742 | processing task, is_child = 0 18.21.404.726 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 172.907 MiB) 18.21.410.536 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 175.492 MiB) 18.21.415.562 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1462, t_last = 351919518210 18.21.415.725 I slot launch_slot_: id 2 | task 16743 | processing task, is_child = 0 18.21.415.817 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.812 (> 0.100 thold), f_keep = 0.866 18.21.415.859 I slot launch_slot_: id 3 | task 16744 | processing task, is_child = 0 18.21.415.865 I slot print_timing: id 0 | task 16736 | prompt processing, n_tokens = 1501, progress = 1.00, t = 4.43 s / 338.96 tokens per second 18.23.204.616 I slot print_timing: id 0 | task 16736 | prompt eval time = 6245.54 ms / 1505 tokens ( 4.15 ms per token, 240.97 tokens per second) 18.23.204.619 I slot print_timing: id 0 | task 16736 | eval time = 561.29 ms / 2 tokens ( 561.29 ms per token, 1.78 tokens per second) 18.23.204.619 I slot print_timing: id 0 | task 16736 | total time = 6806.83 ms / 1507 tokens 18.23.204.620 I slot print_timing: id 0 | task 16736 | graphs reused = 15097 18.23.204.620 I slot print_timing: id 0 | task 16736 | graph reallocs = 0 / 0 (same size) / (changed size) 18.23.204.693 I slot release: id 0 | task 16736 | stop processing: n_tokens = 1506, truncated = 0 18.23.550.514 I slot print_timing: id 3 | task 16744 | prompt eval time = 1787.20 ms / 298 tokens ( 6.00 ms per token, 166.74 tokens per second) 18.23.550.520 I slot print_timing: id 3 | task 16744 | eval time = 345.69 ms / 2 tokens ( 345.69 ms per token, 2.89 tokens per second) 18.23.550.521 I slot print_timing: id 3 | task 16744 | total time = 2132.89 ms / 300 tokens 18.23.550.521 I slot print_timing: id 3 | task 16744 | graphs reused = 15097 18.23.550.521 I slot print_timing: id 3 | task 16744 | graph reallocs = 0 / 0 (same size) / (changed size) 18.23.550.582 I slot release: id 3 | task 16744 | stop processing: n_tokens = 1589, truncated = 0 18.23.550.586 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1506, t_last = 351922531674 18.23.550.690 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 137.995 MiB) 18.23.556.798 I slot launch_slot_: id 0 | task 16748 | processing task, is_child = 0 18.23.556.897 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 139.526 MiB) 18.23.556.900 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 144.600 MiB) 18.23.563.674 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1589, t_last = 351922877561 18.23.563.850 I slot launch_slot_: id 3 | task 16749 | processing task, is_child = 0 18.25.487.550 I slot print_timing: id 1 | task 16742 | prompt processing, n_tokens = 648, progress = 0.83, t = 3.92 s / 165.27 tokens per second 18.25.489.258 I slot print_timing: id 2 | task 16743 | prompt processing, n_tokens = 648, progress = 0.87, t = 3.92 s / 165.28 tokens per second 18.26.458.534 I slot print_timing: id 1 | task 16742 | prompt processing, n_tokens = 774, progress = 0.99, t = 4.97 s / 155.74 tokens per second 18.26.460.445 I slot print_timing: id 2 | task 16743 | prompt processing, n_tokens = 745, progress = 0.99, t = 4.97 s / 149.91 tokens per second 18.27.338.091 I slot print_timing: id 0 | task 16748 | prompt processing, n_tokens = 628, progress = 0.85, t = 3.77 s / 166.40 tokens per second 18.27.339.717 I slot print_timing: id 3 | task 16749 | prompt processing, n_tokens = 247, progress = 0.32, t = 3.77 s / 65.47 tokens per second 18.28.475.782 I slot print_timing: id 1 | task 16742 | prompt eval time = 5920.67 ms / 778 tokens ( 7.61 ms per token, 131.40 tokens per second) 18.28.475.788 I slot print_timing: id 1 | task 16742 | eval time = 1137.85 ms / 2 tokens ( 1137.85 ms per token, 0.88 tokens per second) 18.28.475.789 I slot print_timing: id 1 | task 16742 | total time = 7058.51 ms / 780 tokens 18.28.475.789 I slot print_timing: id 1 | task 16742 | graphs reused = 15097 18.28.475.790 I slot print_timing: id 1 | task 16742 | graph reallocs = 0 / 0 (same size) / (changed size) 18.28.475.833 I slot release: id 1 | task 16742 | stop processing: n_tokens = 779, truncated = 0 18.28.475.927 I slot print_timing: id 2 | task 16743 | prompt eval time = 5920.62 ms / 749 tokens ( 7.90 ms per token, 126.51 tokens per second) 18.28.475.930 I slot print_timing: id 2 | task 16743 | eval time = 1137.85 ms / 2 tokens ( 1137.85 ms per token, 0.88 tokens per second) 18.28.475.930 I slot print_timing: id 2 | task 16743 | total time = 7058.47 ms / 751 tokens 18.28.475.930 I slot print_timing: id 2 | task 16743 | graphs reused = 15097 18.28.475.931 I slot print_timing: id 2 | task 16743 | graph reallocs = 0 / 0 (same size) / (changed size) 18.28.475.953 I slot release: id 2 | task 16743 | stop processing: n_tokens = 750, truncated = 0 18.28.475.961 I slot print_timing: id 0 | task 16748 | prompt processing, n_tokens = 739, progress = 0.99, t = 4.91 s / 150.45 tokens per second 18.28.477.920 I slot print_timing: id 3 | task 16749 | prompt processing, n_tokens = 628, progress = 0.82, t = 4.91 s / 127.89 tokens per second 18.28.944.168 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 779, t_last = 351927802812 18.28.944.245 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 175.080 MiB) 18.28.948.704 I slot launch_slot_: id 1 | task 16755 | processing task, is_child = 0 18.28.948.773 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 174.629 MiB) 18.28.952.514 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 750, t_last = 351927802932 18.28.952.627 I slot launch_slot_: id 2 | task 16756 | processing task, is_child = 0 18.28.952.830 I slot print_timing: id 3 | task 16749 | prompt processing, n_tokens = 759, progress = 0.99, t = 5.38 s / 141.11 tokens per second 18.29.680.575 I slot print_timing: id 0 | task 16748 | prompt eval time = 5380.31 ms / 743 tokens ( 7.24 ms per token, 138.10 tokens per second) 18.29.680.581 I slot print_timing: id 0 | task 16748 | eval time = 736.41 ms / 2 tokens ( 736.41 ms per token, 1.36 tokens per second) 18.29.680.582 I slot print_timing: id 0 | task 16748 | total time = 6116.71 ms / 745 tokens 18.29.680.582 I slot print_timing: id 0 | task 16748 | graphs reused = 15097 18.29.680.583 I slot print_timing: id 0 | task 16748 | graph reallocs = 0 / 0 (same size) / (changed size) 18.29.680.616 I slot release: id 0 | task 16748 | stop processing: n_tokens = 744, truncated = 0 18.30.333.029 I slot print_timing: id 3 | task 16749 | prompt eval time = 6115.52 ms / 763 tokens ( 8.02 ms per token, 124.76 tokens per second) 18.30.333.031 I slot print_timing: id 3 | task 16749 | eval time = 652.30 ms / 2 tokens ( 652.30 ms per token, 1.53 tokens per second) 18.30.333.032 I slot print_timing: id 3 | task 16749 | total time = 6767.82 ms / 765 tokens 18.30.333.032 I slot print_timing: id 3 | task 16749 | graphs reused = 15097 18.30.333.033 I slot print_timing: id 3 | task 16749 | graph reallocs = 0 / 0 (same size) / (changed size) 18.30.333.075 I slot release: id 3 | task 16749 | stop processing: n_tokens = 764, truncated = 0 18.30.333.082 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 744, t_last = 351929007595 18.30.338.470 I slot launch_slot_: id 0 | task 16759 | processing task, is_child = 0 18.30.338.541 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 178.526 MiB) 18.30.342.298 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 764, t_last = 351929660054 18.30.342.404 I slot launch_slot_: id 3 | task 16760 | processing task, is_child = 0 18.33.611.730 I slot print_timing: id 1 | task 16755 | prompt processing, n_tokens = 675, progress = 0.99, t = 4.10 s / 164.49 tokens per second 18.33.613.295 I slot print_timing: id 2 | task 16756 | prompt processing, n_tokens = 628, progress = 0.80, t = 4.10 s / 153.04 tokens per second 18.35.621.050 I slot print_timing: id 0 | task 16759 | prompt processing, n_tokens = 544, progress = 0.83, t = 5.28 s / 103.06 tokens per second 18.35.622.572 I slot print_timing: id 2 | task 16756 | prompt processing, n_tokens = 779, progress = 0.99, t = 6.67 s / 116.82 tokens per second 18.35.624.061 I slot print_timing: id 3 | task 16760 | prompt processing, n_tokens = 495, progress = 0.82, t = 5.28 s / 93.79 tokens per second 18.36.450.106 I slot print_timing: id 1 | task 16755 | prompt eval time = 6668.40 ms / 679 tokens ( 9.82 ms per token, 101.82 tokens per second) 18.36.450.113 I slot print_timing: id 1 | task 16755 | eval time = 829.06 ms / 2 tokens ( 829.06 ms per token, 1.21 tokens per second) 18.36.450.113 I slot print_timing: id 1 | task 16755 | total time = 7497.47 ms / 681 tokens 18.36.450.114 I slot print_timing: id 1 | task 16755 | graphs reused = 15097 18.36.450.114 I slot print_timing: id 1 | task 16755 | graph reallocs = 0 / 0 (same size) / (changed size) 18.36.450.154 I slot release: id 1 | task 16755 | stop processing: n_tokens = 680, truncated = 0 18.36.450.272 I slot print_timing: id 0 | task 16759 | prompt processing, n_tokens = 648, progress = 0.99, t = 6.11 s / 106.10 tokens per second 18.36.452.302 I slot print_timing: id 3 | task 16760 | prompt processing, n_tokens = 599, progress = 0.99, t = 6.11 s / 98.08 tokens per second 18.36.559.903 I slot print_timing: id 2 | task 16756 | prompt eval time = 7497.52 ms / 783 tokens ( 9.58 ms per token, 104.43 tokens per second) 18.36.559.905 I slot print_timing: id 2 | task 16756 | eval time = 109.63 ms / 2 tokens ( 109.63 ms per token, 9.12 tokens per second) 18.36.559.906 I slot print_timing: id 2 | task 16756 | total time = 7607.16 ms / 785 tokens 18.36.559.906 I slot print_timing: id 2 | task 16756 | graphs reused = 15097 18.36.559.906 I slot print_timing: id 2 | task 16756 | graph reallocs = 0 / 0 (same size) / (changed size) 18.36.559.952 I slot release: id 2 | task 16756 | stop processing: n_tokens = 784, truncated = 0 18.36.560.100 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 680, t_last = 351935777133 18.36.560.176 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 173.562 MiB) 18.36.564.239 I slot launch_slot_: id 1 | task 16766 | processing task, is_child = 0 18.36.564.316 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 158.644 MiB) 18.36.568.132 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 784, t_last = 351935886931 18.36.568.246 I slot launch_slot_: id 2 | task 16767 | processing task, is_child = 0 18.37.117.421 I slot print_timing: id 0 | task 16759 | prompt eval time = 6217.41 ms / 652 tokens ( 9.54 ms per token, 104.87 tokens per second) 18.37.117.426 I slot print_timing: id 0 | task 16759 | eval time = 557.60 ms / 2 tokens ( 557.60 ms per token, 1.79 tokens per second) 18.37.117.427 I slot print_timing: id 0 | task 16759 | total time = 6775.01 ms / 654 tokens 18.37.117.427 I slot print_timing: id 0 | task 16759 | graphs reused = 15097 18.37.117.428 I slot print_timing: id 0 | task 16759 | graph reallocs = 0 / 0 (same size) / (changed size) 18.37.117.475 I slot release: id 0 | task 16759 | stop processing: n_tokens = 653, truncated = 0 18.37.117.587 I slot print_timing: id 3 | task 16760 | prompt eval time = 6217.09 ms / 603 tokens ( 10.31 ms per token, 96.99 tokens per second) 18.37.117.589 I slot print_timing: id 3 | task 16760 | eval time = 557.49 ms / 2 tokens ( 557.49 ms per token, 1.79 tokens per second) 18.37.117.589 I slot print_timing: id 3 | task 16760 | total time = 6774.57 ms / 605 tokens 18.37.117.590 I slot print_timing: id 3 | task 16760 | graphs reused = 15097 18.37.117.590 I slot print_timing: id 3 | task 16760 | graph reallocs = 0 / 0 (same size) / (changed size) 18.37.117.619 I slot release: id 3 | task 16760 | stop processing: n_tokens = 604, truncated = 0 18.39.546.176 I slot print_timing: id 1 | task 16766 | prompt eval time = 2944.43 ms / 625 tokens ( 4.71 ms per token, 212.27 tokens per second) 18.39.546.182 I slot print_timing: id 1 | task 16766 | eval time = 33.49 ms / 2 tokens ( 33.49 ms per token, 29.86 tokens per second) 18.39.546.182 I slot print_timing: id 1 | task 16766 | total time = 2977.92 ms / 627 tokens 18.39.546.183 I slot print_timing: id 1 | task 16766 | graphs reused = 15097 18.39.546.183 I slot print_timing: id 1 | task 16766 | graph reallocs = 0 / 0 (same size) / (changed size) 18.39.546.216 I slot release: id 1 | task 16766 | stop processing: n_tokens = 626, truncated = 0 18.39.546.300 I slot print_timing: id 2 | task 16767 | prompt eval time = 2944.42 ms / 591 tokens ( 4.98 ms per token, 200.72 tokens per second) 18.39.546.302 I slot print_timing: id 2 | task 16767 | eval time = 33.52 ms / 2 tokens ( 33.52 ms per token, 29.83 tokens per second) 18.39.546.302 I slot print_timing: id 2 | task 16767 | total time = 2977.94 ms / 593 tokens 18.39.546.302 I slot print_timing: id 2 | task 16767 | graphs reused = 15097 18.39.546.303 I slot print_timing: id 2 | task 16767 | graph reallocs = 0 / 0 (same size) / (changed size) 18.39.546.319 I slot release: id 2 | task 16767 | stop processing: n_tokens = 592, truncated = 0 18.42.585.277 I srv operator(): operator(): cleaning up before exit...