$ /Users/minipro/quantdiff/llama.cpp/llama-b11770/llama-server -m /Users/minipro/quantdiff/models/campaign/cc1b0bde185f/Spark-X2.6-4B-IQ3_XXS.gguf --host 127.0.0.1 --port 8089 -c 4096 -np 1 -ngl 999 -fa on --jinja --seed 1234 --no-webui -a quant 0.00.042.917 I srv llama_server: initializing ... 0.00.042.924 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.043.009 I srv init_listene: The UI is disabled 0.00.043.010 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.043.047 W srv llama_server: security: no API key is set and CORS allows all origins (see https://github.com/ggml-org/llama.cpp/pull/25655) 0.00.044.722 I srv load_model: loading model '/Users/minipro/quantdiff/models/campaign/cc1b0bde185f/Spark-X2.6-4B-IQ3_XXS.gguf' 0.00.363.885 I cmn init: llama threadpool init, n_threads = 8 0.00.449.226 I srv load_model: initializing, n_slots = 1, n_ctx_slot = 4096, kv_unified = 'false' 0.00.456.610 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.00.456.621 I srv llama_server: model loaded 0.00.456.623 I srv llama_server: listening on http://127.0.0.1:8089 0.02.022.563 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.02.022.793 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.05.497.533 I slot print_timing: id 0 | task 0 | n_gen = 150, tg = 49.37 t/s, tg_3s = 49.71 t/s 0.07.935.246 I slot print_timing: id 0 | task 0 | prompt eval time = 456.98 ms / 172 tokens ( 2.66 ms per token, 376.39 tokens per second) 0.07.935.253 I slot print_timing: id 0 | task 0 | eval time = 5455.46 ms / 269 tokens ( 20.36 ms per token, 49.13 tokens per second) 0.07.935.253 I slot print_timing: id 0 | task 0 | total time = 5912.44 ms / 441 tokens 0.07.935.254 I slot print_timing: id 0 | task 0 | graphs reused = 267 0.07.935.254 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.07.935.280 I slot release: id 0 | task 0 | stop processing: n_tokens = 440, truncated = 0 0.07.939.162 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.236 (> 0.100 thold), f_keep = 0.068 0.07.948.213 I slot launch_slot_: id 0 | task 272 | processing task, is_child = 0 0.08.730.305 I slot print_timing: id 0 | task 272 | prompt eval time = 355.48 ms / 127 tokens ( 2.80 ms per token, 357.26 tokens per second) 0.08.730.310 I slot print_timing: id 0 | task 272 | eval time = 426.60 ms / 22 tokens ( 20.31 ms per token, 49.23 tokens per second) 0.08.730.311 I slot print_timing: id 0 | task 272 | total time = 782.08 ms / 149 tokens 0.08.730.312 I slot print_timing: id 0 | task 272 | graphs reused = 287 0.08.730.312 I slot print_timing: id 0 | task 272 | graph reallocs = 0 / 0 (same size) / (changed size) 0.08.730.327 I slot release: id 0 | task 272 | stop processing: n_tokens = 148, truncated = 0 0.08.734.526 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.203 0.08.738.510 I slot launch_slot_: id 0 | task 297 | processing task, is_child = 0 0.11.272.826 I slot print_timing: id 0 | task 297 | prompt eval time = 410.24 ms / 171 tokens ( 2.40 ms per token, 416.83 tokens per second) 0.11.272.829 I slot print_timing: id 0 | task 297 | eval time = 2124.07 ms / 106 tokens ( 20.23 ms per token, 49.43 tokens per second) 0.11.272.830 I slot print_timing: id 0 | task 297 | total time = 2534.31 ms / 277 tokens 0.11.272.830 I slot print_timing: id 0 | task 297 | graphs reused = 390 0.11.272.831 I slot print_timing: id 0 | task 297 | graph reallocs = 0 / 0 (same size) / (changed size) 0.11.272.850 I slot release: id 0 | task 297 | stop processing: n_tokens = 276, truncated = 0 0.11.276.979 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.147 (> 0.100 thold), f_keep = 0.109 0.11.283.673 I slot launch_slot_: id 0 | task 406 | processing task, is_child = 0 0.14.762.694 I slot print_timing: id 0 | task 406 | n_gen = 149, tg = 49.25 t/s, tg_3s = 49.58 t/s 0.15.028.707 I slot print_timing: id 0 | task 406 | prompt eval time = 473.89 ms / 204 tokens ( 2.32 ms per token, 430.48 tokens per second) 0.15.028.710 I slot print_timing: id 0 | task 406 | eval time = 3271.14 ms / 162 tokens ( 20.32 ms per token, 49.22 tokens per second) 0.15.028.711 I slot print_timing: id 0 | task 406 | total time = 3745.02 ms / 366 tokens 0.15.028.712 I slot print_timing: id 0 | task 406 | graphs reused = 549 0.15.028.712 I slot print_timing: id 0 | task 406 | graph reallocs = 0 / 0 (same size) / (changed size) 0.15.028.742 I slot release: id 0 | task 406 | stop processing: n_tokens = 365, truncated = 0 0.15.032.871 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.118 0.15.041.165 I slot launch_slot_: id 0 | task 571 | processing task, is_child = 0 0.18.501.840 I slot print_timing: id 0 | task 571 | n_gen = 149, tg = 49.32 t/s, tg_3s = 49.66 t/s 0.19.832.767 I slot print_timing: id 0 | task 571 | prompt eval time = 460.12 ms / 187 tokens ( 2.46 ms per token, 406.42 tokens per second) 0.19.832.770 I slot print_timing: id 0 | task 571 | eval time = 4331.47 ms / 214 tokens ( 20.34 ms per token, 49.17 tokens per second) 0.19.832.771 I slot print_timing: id 0 | task 571 | total time = 4791.59 ms / 401 tokens 0.19.832.771 I slot print_timing: id 0 | task 571 | graphs reused = 760 0.19.832.772 I slot print_timing: id 0 | task 571 | graph reallocs = 0 / 0 (same size) / (changed size) 0.19.832.790 I slot release: id 0 | task 571 | stop processing: n_tokens = 400, truncated = 0 0.19.836.984 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.075 0.19.844.889 I slot launch_slot_: id 0 | task 788 | processing task, is_child = 0 0.20.847.168 I slot print_timing: id 0 | task 788 | prompt eval time = 381.39 ms / 171 tokens ( 2.23 ms per token, 448.36 tokens per second) 0.20.847.174 I slot print_timing: id 0 | task 788 | eval time = 620.88 ms / 31 tokens ( 20.70 ms per token, 48.32 tokens per second) 0.20.847.175 I slot print_timing: id 0 | task 788 | total time = 1002.27 ms / 202 tokens 0.20.847.175 I slot print_timing: id 0 | task 788 | graphs reused = 789 0.20.847.176 I slot print_timing: id 0 | task 788 | graph reallocs = 0 / 0 (same size) / (changed size) 0.20.847.192 I slot release: id 0 | task 788 | stop processing: n_tokens = 201, truncated = 0 0.20.851.251 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.136 (> 0.100 thold), f_keep = 0.149 0.20.856.925 I slot launch_slot_: id 0 | task 822 | processing task, is_child = 0 0.21.909.859 I slot print_timing: id 0 | task 822 | prompt eval time = 523.10 ms / 221 tokens ( 2.37 ms per token, 422.48 tokens per second) 0.21.909.866 I slot print_timing: id 0 | task 822 | eval time = 529.83 ms / 27 tokens ( 20.38 ms per token, 49.07 tokens per second) 0.21.909.867 I slot print_timing: id 0 | task 822 | total time = 1052.93 ms / 248 tokens 0.21.909.868 I slot print_timing: id 0 | task 822 | graphs reused = 814 0.21.909.868 I slot print_timing: id 0 | task 822 | graph reallocs = 0 / 0 (same size) / (changed size) 0.21.909.886 I slot release: id 0 | task 822 | stop processing: n_tokens = 247, truncated = 0 0.21.914.048 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.111 (> 0.100 thold), f_keep = 0.121 0.21.920.944 I slot launch_slot_: id 0 | task 852 | processing task, is_child = 0 0.25.551.900 I slot print_timing: id 0 | task 852 | n_gen = 148, tg = 48.96 t/s, tg_3s = 49.29 t/s 0.28.168.606 I slot print_timing: id 0 | task 852 | prompt eval time = 628.51 ms / 270 tokens ( 2.33 ms per token, 429.58 tokens per second) 0.28.168.609 I slot print_timing: id 0 | task 852 | eval time = 5619.14 ms / 275 tokens ( 20.51 ms per token, 48.76 tokens per second) 0.28.168.610 I slot print_timing: id 0 | task 852 | total time = 6247.65 ms / 545 tokens 0.28.168.611 I slot print_timing: id 0 | task 852 | graphs reused = 1086 0.28.168.611 I slot print_timing: id 0 | task 852 | graph reallocs = 0 / 0 (same size) / (changed size) 0.28.168.637 I slot release: id 0 | task 852 | stop processing: n_tokens = 544, truncated = 0 0.28.173.073 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.055 0.28.184.695 I slot launch_slot_: id 0 | task 1130 | processing task, is_child = 0 0.29.091.862 I slot print_timing: id 0 | task 1130 | prompt eval time = 359.45 ms / 150 tokens ( 2.40 ms per token, 417.31 tokens per second) 0.29.091.868 I slot print_timing: id 0 | task 1130 | eval time = 547.71 ms / 28 tokens ( 20.29 ms per token, 49.30 tokens per second) 0.29.091.869 I slot print_timing: id 0 | task 1130 | total time = 907.16 ms / 178 tokens 0.29.091.870 I slot print_timing: id 0 | task 1130 | graphs reused = 1112 0.29.091.874 I slot print_timing: id 0 | task 1130 | graph reallocs = 0 / 0 (same size) / (changed size) 0.29.091.895 I slot release: id 0 | task 1130 | stop processing: n_tokens = 177, truncated = 0 0.29.096.413 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.180 (> 0.100 thold), f_keep = 0.169 0.29.098.032 I slot launch_slot_: id 0 | task 1161 | processing task, is_child = 0 0.31.669.999 I slot print_timing: id 0 | task 1161 | prompt eval time = 409.19 ms / 167 tokens ( 2.45 ms per token, 408.12 tokens per second) 0.31.670.007 I slot print_timing: id 0 | task 1161 | eval time = 2162.76 ms / 108 tokens ( 20.21 ms per token, 49.47 tokens per second) 0.31.670.008 I slot print_timing: id 0 | task 1161 | total time = 2571.95 ms / 275 tokens 0.31.670.009 I slot print_timing: id 0 | task 1161 | graphs reused = 1217 0.31.670.009 I slot print_timing: id 0 | task 1161 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.670.026 I slot release: id 0 | task 1161 | stop processing: n_tokens = 274, truncated = 0 0.31.674.095 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.109 0.31.679.715 I slot launch_slot_: id 0 | task 1272 | processing task, is_child = 0 0.35.066.123 I slot print_timing: id 0 | task 1272 | n_gen = 150, tg = 49.54 t/s, tg_3s = 49.87 t/s 0.37.835.257 I slot print_timing: id 0 | task 1272 | prompt eval time = 378.68 ms / 171 tokens ( 2.21 ms per token, 451.57 tokens per second) 0.37.835.262 I slot print_timing: id 0 | task 1272 | eval time = 5776.85 ms / 284 tokens ( 20.41 ms per token, 48.99 tokens per second) 0.37.835.263 I slot print_timing: id 0 | task 1272 | total time = 6155.53 ms / 455 tokens 0.37.835.264 I slot print_timing: id 0 | task 1272 | graphs reused = 1498 0.37.835.264 I slot print_timing: id 0 | task 1272 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.835.283 I slot release: id 0 | task 1272 | stop processing: n_tokens = 454, truncated = 0 0.37.839.422 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.140 (> 0.100 thold), f_keep = 0.066 0.37.849.166 I slot launch_slot_: id 0 | task 1559 | processing task, is_child = 0 0.39.865.974 I slot print_timing: id 0 | task 1559 | prompt eval time = 475.07 ms / 214 tokens ( 2.22 ms per token, 450.46 tokens per second) 0.39.865.984 I slot print_timing: id 0 | task 1559 | eval time = 1541.73 ms / 77 tokens ( 20.29 ms per token, 49.30 tokens per second) 0.39.865.984 I slot print_timing: id 0 | task 1559 | total time = 2016.80 ms / 291 tokens 0.39.865.985 I slot print_timing: id 0 | task 1559 | graphs reused = 1572 0.39.865.986 I slot print_timing: id 0 | task 1559 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.866.008 I slot release: id 0 | task 1559 | stop processing: n_tokens = 290, truncated = 0 0.39.870.006 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.164 (> 0.100 thold), f_keep = 0.103 0.39.877.393 I slot launch_slot_: id 0 | task 1639 | processing task, is_child = 0 0.41.086.956 I slot print_timing: id 0 | task 1639 | prompt eval time = 459.35 ms / 183 tokens ( 2.51 ms per token, 398.39 tokens per second) 0.41.086.959 I slot print_timing: id 0 | task 1639 | eval time = 750.20 ms / 38 tokens ( 20.28 ms per token, 49.32 tokens per second) 0.41.086.960 I slot print_timing: id 0 | task 1639 | total time = 1209.55 ms / 221 tokens 0.41.086.961 I slot print_timing: id 0 | task 1639 | graphs reused = 1608 0.41.086.961 I slot print_timing: id 0 | task 1639 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.086.980 I slot release: id 0 | task 1639 | stop processing: n_tokens = 220, truncated = 0 0.41.091.026 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.164 (> 0.100 thold), f_keep = 0.136 0.41.094.766 I slot launch_slot_: id 0 | task 1680 | processing task, is_child = 0 0.42.034.881 I slot print_timing: id 0 | task 1680 | prompt eval time = 472.98 ms / 183 tokens ( 2.58 ms per token, 386.91 tokens per second) 0.42.034.887 I slot print_timing: id 0 | task 1680 | eval time = 467.12 ms / 24 tokens ( 20.31 ms per token, 49.24 tokens per second) 0.42.034.888 I slot print_timing: id 0 | task 1680 | total time = 940.11 ms / 207 tokens 0.42.034.888 I slot print_timing: id 0 | task 1680 | graphs reused = 1630 0.42.034.889 I slot print_timing: id 0 | task 1680 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.034.907 I slot release: id 0 | task 1680 | stop processing: n_tokens = 206, truncated = 0 0.42.038.731 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.176 (> 0.100 thold), f_keep = 0.146 0.42.044.607 I slot launch_slot_: id 0 | task 1707 | processing task, is_child = 0 0.43.146.696 I slot print_timing: id 0 | task 1707 | prompt eval time = 411.94 ms / 170 tokens ( 2.42 ms per token, 412.68 tokens per second) 0.43.146.702 I slot print_timing: id 0 | task 1707 | eval time = 690.14 ms / 35 tokens ( 20.30 ms per token, 49.27 tokens per second) 0.43.146.703 I slot print_timing: id 0 | task 1707 | total time = 1102.08 ms / 205 tokens 0.43.146.703 I slot print_timing: id 0 | task 1707 | graphs reused = 1663 0.43.146.704 I slot print_timing: id 0 | task 1707 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.146.722 I slot release: id 0 | task 1707 | stop processing: n_tokens = 204, truncated = 0 0.43.150.484 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.147 0.43.156.232 I slot launch_slot_: id 0 | task 1745 | processing task, is_child = 0 0.44.020.813 I slot print_timing: id 0 | task 1745 | prompt eval time = 358.23 ms / 150 tokens ( 2.39 ms per token, 418.73 tokens per second) 0.44.020.816 I slot print_timing: id 0 | task 1745 | eval time = 506.34 ms / 26 tokens ( 20.25 ms per token, 49.37 tokens per second) 0.44.020.817 I slot print_timing: id 0 | task 1745 | total time = 864.57 ms / 176 tokens 0.44.020.817 I slot print_timing: id 0 | task 1745 | graphs reused = 1687 0.44.020.818 I slot print_timing: id 0 | task 1745 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.020.836 I slot release: id 0 | task 1745 | stop processing: n_tokens = 175, truncated = 0 0.44.024.728 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.172 (> 0.100 thold), f_keep = 0.171 0.44.028.691 I slot launch_slot_: id 0 | task 1774 | processing task, is_child = 0 0.45.430.488 I slot print_timing: id 0 | task 1774 | prompt eval time = 410.51 ms / 174 tokens ( 2.36 ms per token, 423.86 tokens per second) 0.45.430.493 I slot print_timing: id 0 | task 1774 | eval time = 991.28 ms / 50 tokens ( 20.23 ms per token, 49.43 tokens per second) 0.45.430.495 I slot print_timing: id 0 | task 1774 | total time = 1401.78 ms / 224 tokens 0.45.430.495 I slot print_timing: id 0 | task 1774 | graphs reused = 1735 0.45.430.496 I slot print_timing: id 0 | task 1774 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.430.517 I slot release: id 0 | task 1774 | stop processing: n_tokens = 223, truncated = 0 0.45.434.479 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.192 (> 0.100 thold), f_keep = 0.135 0.45.440.327 I slot launch_slot_: id 0 | task 1827 | processing task, is_child = 0 0.46.236.822 I slot print_timing: id 0 | task 1827 | prompt eval time = 410.76 ms / 156 tokens ( 2.63 ms per token, 379.78 tokens per second) 0.46.236.829 I slot print_timing: id 0 | task 1827 | eval time = 385.72 ms / 20 tokens ( 20.30 ms per token, 49.26 tokens per second) 0.46.236.829 I slot print_timing: id 0 | task 1827 | total time = 796.49 ms / 176 tokens 0.46.236.830 I slot print_timing: id 0 | task 1827 | graphs reused = 1753 0.46.236.831 I slot print_timing: id 0 | task 1827 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.236.850 I slot release: id 0 | task 1827 | stop processing: n_tokens = 175, truncated = 0 0.46.240.903 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.197 (> 0.100 thold), f_keep = 0.171 0.46.245.849 I slot launch_slot_: id 0 | task 1850 | processing task, is_child = 0 0.46.968.819 I slot print_timing: id 0 | task 1850 | prompt eval time = 377.52 ms / 152 tokens ( 2.48 ms per token, 402.63 tokens per second) 0.46.968.823 I slot print_timing: id 0 | task 1850 | eval time = 345.44 ms / 18 tokens ( 20.32 ms per token, 49.21 tokens per second) 0.46.968.823 I slot print_timing: id 0 | task 1850 | total time = 722.96 ms / 170 tokens 0.46.968.824 I slot print_timing: id 0 | task 1850 | graphs reused = 1769 0.46.968.824 I slot print_timing: id 0 | task 1850 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.968.842 I slot release: id 0 | task 1850 | stop processing: n_tokens = 169, truncated = 0 0.46.972.955 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.160 (> 0.100 thold), f_keep = 0.178 0.46.977.844 I slot launch_slot_: id 0 | task 1871 | processing task, is_child = 0 0.48.209.357 I slot print_timing: id 0 | task 1871 | prompt eval time = 460.04 ms / 187 tokens ( 2.46 ms per token, 406.48 tokens per second) 0.48.209.360 I slot print_timing: id 0 | task 1871 | eval time = 771.46 ms / 39 tokens ( 20.30 ms per token, 49.26 tokens per second) 0.48.209.361 I slot print_timing: id 0 | task 1871 | total time = 1231.50 ms / 226 tokens 0.48.209.362 I slot print_timing: id 0 | task 1871 | graphs reused = 1806 0.48.209.363 I slot print_timing: id 0 | task 1871 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.209.380 I slot release: id 0 | task 1871 | stop processing: n_tokens = 225, truncated = 0 0.48.213.045 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.133 0.48.218.268 I slot launch_slot_: id 0 | task 1913 | processing task, is_child = 0 0.51.070.694 I slot print_timing: id 0 | task 1913 | prompt eval time = 409.00 ms / 160 tokens ( 2.56 ms per token, 391.19 tokens per second) 0.51.070.697 I slot print_timing: id 0 | task 1913 | eval time = 2443.41 ms / 120 tokens ( 20.53 ms per token, 48.70 tokens per second) 0.51.070.698 I slot print_timing: id 0 | task 1913 | total time = 2852.42 ms / 280 tokens 0.51.070.699 I slot print_timing: id 0 | task 1913 | graphs reused = 1923 0.51.070.699 I slot print_timing: id 0 | task 1913 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.070.717 I slot release: id 0 | task 1913 | stop processing: n_tokens = 279, truncated = 0 0.51.074.868 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.144 (> 0.100 thold), f_keep = 0.108 0.51.081.344 I slot launch_slot_: id 0 | task 2036 | processing task, is_child = 0 0.52.305.860 I slot print_timing: id 0 | task 2036 | prompt eval time = 474.16 ms / 208 tokens ( 2.28 ms per token, 438.67 tokens per second) 0.52.305.866 I slot print_timing: id 0 | task 2036 | eval time = 750.35 ms / 38 tokens ( 20.28 ms per token, 49.31 tokens per second) 0.52.305.867 I slot print_timing: id 0 | task 2036 | total time = 1224.51 ms / 246 tokens 0.52.305.867 I slot print_timing: id 0 | task 2036 | graphs reused = 1959 0.52.305.868 I slot print_timing: id 0 | task 2036 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.305.887 I slot release: id 0 | task 2036 | stop processing: n_tokens = 245, truncated = 0 0.52.309.876 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.122 0.52.316.553 I slot launch_slot_: id 0 | task 2077 | processing task, is_child = 0 0.55.789.336 I slot print_timing: id 0 | task 2077 | n_gen = 149, tg = 49.31 t/s, tg_3s = 49.65 t/s 0.56.381.493 I slot print_timing: id 0 | task 2077 | prompt eval time = 471.55 ms / 192 tokens ( 2.46 ms per token, 407.17 tokens per second) 0.56.381.499 I slot print_timing: id 0 | task 2077 | eval time = 3593.39 ms / 178 tokens ( 20.30 ms per token, 49.26 tokens per second) 0.56.381.500 I slot print_timing: id 0 | task 2077 | total time = 4064.93 ms / 370 tokens 0.56.381.501 I slot print_timing: id 0 | task 2077 | graphs reused = 2134 0.56.381.502 I slot print_timing: id 0 | task 2077 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.381.521 I slot release: id 0 | task 2077 | stop processing: n_tokens = 369, truncated = 0 0.56.385.772 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.152 (> 0.100 thold), f_keep = 0.081 0.56.393.938 I slot launch_slot_: id 0 | task 2258 | processing task, is_child = 0 0.59.309.063 I slot print_timing: id 0 | task 2258 | prompt eval time = 461.68 ms / 198 tokens ( 2.33 ms per token, 428.86 tokens per second) 0.59.309.067 I slot print_timing: id 0 | task 2258 | eval time = 2453.43 ms / 122 tokens ( 20.28 ms per token, 49.32 tokens per second) 0.59.309.067 I slot print_timing: id 0 | task 2258 | total time = 2915.12 ms / 320 tokens 0.59.309.068 I slot print_timing: id 0 | task 2258 | graphs reused = 2253 0.59.309.069 I slot print_timing: id 0 | task 2258 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.309.088 I slot release: id 0 | task 2258 | stop processing: n_tokens = 319, truncated = 0 0.59.313.489 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.128 (> 0.100 thold), f_keep = 0.094 0.59.320.970 I slot launch_slot_: id 0 | task 2383 | processing task, is_child = 0 1.00.540.706 I slot print_timing: id 0 | task 2383 | prompt eval time = 526.29 ms / 235 tokens ( 2.24 ms per token, 446.52 tokens per second) 1.00.540.713 I slot print_timing: id 0 | task 2383 | eval time = 693.44 ms / 35 tokens ( 20.40 ms per token, 49.03 tokens per second) 1.00.540.713 I slot print_timing: id 0 | task 2383 | total time = 1219.73 ms / 270 tokens 1.00.540.714 I slot print_timing: id 0 | task 2383 | graphs reused = 2285 1.00.540.714 I slot print_timing: id 0 | task 2383 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.540.737 I slot release: id 0 | task 2383 | stop processing: n_tokens = 269, truncated = 0 1.00.544.599 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.115 1.00.551.918 I slot launch_slot_: id 0 | task 2421 | processing task, is_child = 0 1.01.704.242 I slot print_timing: id 0 | task 2421 | prompt eval time = 461.94 ms / 199 tokens ( 2.32 ms per token, 430.79 tokens per second) 1.01.704.246 I slot print_timing: id 0 | task 2421 | eval time = 690.37 ms / 35 tokens ( 20.30 ms per token, 49.25 tokens per second) 1.01.704.246 I slot print_timing: id 0 | task 2421 | total time = 1152.31 ms / 234 tokens 1.01.704.247 I slot print_timing: id 0 | task 2421 | graphs reused = 2318 1.01.704.248 I slot print_timing: id 0 | task 2421 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.704.268 I slot release: id 0 | task 2421 | stop processing: n_tokens = 233, truncated = 0 1.01.708.096 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.191 (> 0.100 thold), f_keep = 0.129 1.01.713.835 I slot launch_slot_: id 0 | task 2459 | processing task, is_child = 0 1.05.129.398 I slot print_timing: id 0 | task 2459 | n_gen = 150, tg = 49.57 t/s, tg_3s = 49.90 t/s 1.08.146.709 I slot print_timing: id 0 | task 2459 | n_gen = 298, tg = 49.31 t/s, tg_3s = 49.05 t/s 1.09.940.598 I slot print_timing: id 0 | task 2459 | prompt eval time = 409.81 ms / 157 tokens ( 2.61 ms per token, 383.10 tokens per second) 1.09.940.604 I slot print_timing: id 0 | task 2459 | eval time = 7816.94 ms / 385 tokens ( 20.36 ms per token, 49.12 tokens per second) 1.09.940.605 I slot print_timing: id 0 | task 2459 | total time = 8226.75 ms / 542 tokens 1.09.940.606 I slot print_timing: id 0 | task 2459 | graphs reused = 2699 1.09.940.606 I slot print_timing: id 0 | task 2459 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.940.626 I slot release: id 0 | task 2459 | stop processing: n_tokens = 541, truncated = 0 1.09.944.775 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.168 (> 0.100 thold), f_keep = 0.057 1.09.953.558 I slot launch_slot_: id 0 | task 2847 | processing task, is_child = 0 1.11.318.894 I slot print_timing: id 0 | task 2847 | prompt eval time = 412.47 ms / 184 tokens ( 2.24 ms per token, 446.09 tokens per second) 1.11.318.899 I slot print_timing: id 0 | task 2847 | eval time = 952.85 ms / 48 tokens ( 20.27 ms per token, 49.33 tokens per second) 1.11.318.900 I slot print_timing: id 0 | task 2847 | total time = 1365.32 ms / 232 tokens 1.11.318.901 I slot print_timing: id 0 | task 2847 | graphs reused = 2745 1.11.318.901 I slot print_timing: id 0 | task 2847 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.318.920 I slot release: id 0 | task 2847 | stop processing: n_tokens = 231, truncated = 0 1.11.323.257 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.140 (> 0.100 thold), f_keep = 0.130 1.11.329.735 I slot launch_slot_: id 0 | task 2898 | processing task, is_child = 0 1.14.859.310 I slot print_timing: id 0 | task 2898 | n_gen = 149, tg = 49.23 t/s, tg_3s = 49.56 t/s 1.16.193.567 I slot print_timing: id 0 | task 2898 | prompt eval time = 523.18 ms / 214 tokens ( 2.44 ms per token, 409.04 tokens per second) 1.16.193.570 I slot print_timing: id 0 | task 2898 | eval time = 4340.64 ms / 214 tokens ( 20.38 ms per token, 49.07 tokens per second) 1.16.193.571 I slot print_timing: id 0 | task 2898 | total time = 4863.82 ms / 428 tokens 1.16.193.571 I slot print_timing: id 0 | task 2898 | graphs reused = 2956 1.16.193.572 I slot print_timing: id 0 | task 2898 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.193.595 I slot release: id 0 | task 2898 | stop processing: n_tokens = 427, truncated = 0 1.16.197.736 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.161 (> 0.100 thold), f_keep = 0.070 1.16.205.785 I slot launch_slot_: id 0 | task 3115 | processing task, is_child = 0 1.17.407.539 I slot print_timing: id 0 | task 3115 | prompt eval time = 471.82 ms / 186 tokens ( 2.54 ms per token, 394.22 tokens per second) 1.17.407.544 I slot print_timing: id 0 | task 3115 | eval time = 729.93 ms / 37 tokens ( 20.28 ms per token, 49.32 tokens per second) 1.17.407.545 I slot print_timing: id 0 | task 3115 | total time = 1201.75 ms / 223 tokens 1.17.407.550 I slot print_timing: id 0 | task 3115 | graphs reused = 2991 1.17.407.551 I slot print_timing: id 0 | task 3115 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.407.569 I slot release: id 0 | task 3115 | stop processing: n_tokens = 222, truncated = 0 1.17.411.519 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.184 (> 0.100 thold), f_keep = 0.135 1.17.417.586 I slot launch_slot_: id 0 | task 3155 | processing task, is_child = 0 1.18.538.667 I slot print_timing: id 0 | task 3155 | prompt eval time = 411.90 ms / 163 tokens ( 2.53 ms per token, 395.73 tokens per second) 1.18.538.673 I slot print_timing: id 0 | task 3155 | eval time = 709.17 ms / 36 tokens ( 20.26 ms per token, 49.35 tokens per second) 1.18.538.674 I slot print_timing: id 0 | task 3155 | total time = 1121.07 ms / 199 tokens 1.18.538.674 I slot print_timing: id 0 | task 3155 | graphs reused = 3025 1.18.538.675 I slot print_timing: id 0 | task 3155 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.538.694 I slot release: id 0 | task 3155 | stop processing: n_tokens = 198, truncated = 0 1.18.542.528 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.184 (> 0.100 thold), f_keep = 0.152 1.18.547.231 I slot launch_slot_: id 0 | task 3194 | processing task, is_child = 0 1.19.231.710 I slot print_timing: id 0 | task 3194 | prompt eval time = 378.13 ms / 163 tokens ( 2.32 ms per token, 431.07 tokens per second) 1.19.231.720 I slot print_timing: id 0 | task 3194 | eval time = 306.34 ms / 16 tokens ( 20.42 ms per token, 48.97 tokens per second) 1.19.231.720 I slot print_timing: id 0 | task 3194 | total time = 684.47 ms / 179 tokens 1.19.231.721 I slot print_timing: id 0 | task 3194 | graphs reused = 3039 1.19.231.721 I slot print_timing: id 0 | task 3194 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.231.742 I slot release: id 0 | task 3194 | stop processing: n_tokens = 178, truncated = 0 1.19.235.808 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.160 (> 0.100 thold), f_keep = 0.169 1.19.240.986 I slot launch_slot_: id 0 | task 3213 | processing task, is_child = 0 1.20.437.429 I slot print_timing: id 0 | task 3213 | prompt eval time = 473.55 ms / 187 tokens ( 2.53 ms per token, 394.89 tokens per second) 1.20.437.435 I slot print_timing: id 0 | task 3213 | eval time = 722.88 ms / 36 tokens ( 20.65 ms per token, 48.42 tokens per second) 1.20.437.436 I slot print_timing: id 0 | task 3213 | total time = 1196.43 ms / 223 tokens 1.20.437.436 I slot print_timing: id 0 | task 3213 | graphs reused = 3073 1.20.437.437 I slot print_timing: id 0 | task 3213 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.437.455 I slot release: id 0 | task 3213 | stop processing: n_tokens = 222, truncated = 0 1.20.441.552 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.146 (> 0.100 thold), f_keep = 0.135 1.20.447.618 I slot launch_slot_: id 0 | task 3252 | processing task, is_child = 0 1.21.449.575 I slot print_timing: id 0 | task 3252 | prompt eval time = 473.88 ms / 205 tokens ( 2.31 ms per token, 432.60 tokens per second) 1.21.449.580 I slot print_timing: id 0 | task 3252 | eval time = 528.06 ms / 27 tokens ( 20.31 ms per token, 49.24 tokens per second) 1.21.449.581 I slot print_timing: id 0 | task 3252 | total time = 1001.94 ms / 232 tokens 1.21.449.582 I slot print_timing: id 0 | task 3252 | graphs reused = 3098 1.21.449.582 I slot print_timing: id 0 | task 3252 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.449.603 I slot release: id 0 | task 3252 | stop processing: n_tokens = 231, truncated = 0 1.21.453.456 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.190 (> 0.100 thold), f_keep = 0.130 1.21.458.848 I slot launch_slot_: id 0 | task 3282 | processing task, is_child = 0 1.22.474.329 I slot print_timing: id 0 | task 3282 | prompt eval time = 386.94 ms / 158 tokens ( 2.45 ms per token, 408.33 tokens per second) 1.22.474.336 I slot print_timing: id 0 | task 3282 | eval time = 628.54 ms / 32 tokens ( 20.28 ms per token, 49.32 tokens per second) 1.22.474.336 I slot print_timing: id 0 | task 3282 | total time = 1015.47 ms / 190 tokens 1.22.474.337 I slot print_timing: id 0 | task 3282 | graphs reused = 3128 1.22.474.337 I slot print_timing: id 0 | task 3282 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.474.355 I slot release: id 0 | task 3282 | stop processing: n_tokens = 189, truncated = 0 1.22.478.449 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.153 (> 0.100 thold), f_keep = 0.159 1.22.482.892 I slot launch_slot_: id 0 | task 3317 | processing task, is_child = 0 1.25.927.051 I slot print_timing: id 0 | task 3317 | n_gen = 145, tg = 47.96 t/s, tg_3s = 48.29 t/s 1.27.866.658 I slot print_timing: id 0 | task 3317 | prompt eval time = 441.71 ms / 196 tokens ( 2.25 ms per token, 443.73 tokens per second) 1.27.866.664 I slot print_timing: id 0 | task 3317 | eval time = 4942.04 ms / 239 tokens ( 20.76 ms per token, 48.16 tokens per second) 1.27.866.664 I slot print_timing: id 0 | task 3317 | total time = 5383.76 ms / 435 tokens 1.27.866.665 I slot print_timing: id 0 | task 3317 | graphs reused = 3364 1.27.866.666 I slot print_timing: id 0 | task 3317 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.866.685 I slot release: id 0 | task 3317 | stop processing: n_tokens = 434, truncated = 0 1.27.870.518 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.236 (> 0.100 thold), f_keep = 0.069 1.27.879.646 I slot launch_slot_: id 0 | task 3559 | processing task, is_child = 0 1.28.570.274 I slot print_timing: id 0 | task 3559 | prompt eval time = 323.63 ms / 127 tokens ( 2.55 ms per token, 392.42 tokens per second) 1.28.570.280 I slot print_timing: id 0 | task 3559 | eval time = 366.98 ms / 19 tokens ( 20.39 ms per token, 49.05 tokens per second) 1.28.570.281 I slot print_timing: id 0 | task 3559 | total time = 690.62 ms / 146 tokens 1.28.570.281 I slot print_timing: id 0 | task 3559 | graphs reused = 3381 1.28.570.282 I slot print_timing: id 0 | task 3559 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.570.298 I slot release: id 0 | task 3559 | stop processing: n_tokens = 145, truncated = 0 1.28.573.871 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.224 (> 0.100 thold), f_keep = 0.207 1.28.577.300 I slot launch_slot_: id 0 | task 3581 | processing task, is_child = 0 1.29.893.254 I slot print_timing: id 0 | task 3581 | prompt eval time = 326.12 ms / 134 tokens ( 2.43 ms per token, 410.90 tokens per second) 1.29.893.257 I slot print_timing: id 0 | task 3581 | eval time = 989.83 ms / 50 tokens ( 20.20 ms per token, 49.50 tokens per second) 1.29.893.262 I slot print_timing: id 0 | task 3581 | total time = 1315.94 ms / 184 tokens 1.29.893.262 I slot print_timing: id 0 | task 3581 | graphs reused = 3429 1.29.893.263 I slot print_timing: id 0 | task 3581 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.893.282 I slot release: id 0 | task 3581 | stop processing: n_tokens = 183, truncated = 0 1.29.897.598 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.164 1.29.902.921 I slot launch_slot_: id 0 | task 3634 | processing task, is_child = 0 1.30.604.458 I slot print_timing: id 0 | task 3634 | prompt eval time = 375.20 ms / 148 tokens ( 2.54 ms per token, 394.45 tokens per second) 1.30.604.463 I slot print_timing: id 0 | task 3634 | eval time = 326.32 ms / 17 tokens ( 20.40 ms per token, 49.03 tokens per second) 1.30.604.464 I slot print_timing: id 0 | task 3634 | total time = 701.53 ms / 165 tokens 1.30.604.465 I slot print_timing: id 0 | task 3634 | graphs reused = 3444 1.30.604.465 I slot print_timing: id 0 | task 3634 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.604.482 I slot release: id 0 | task 3634 | stop processing: n_tokens = 164, truncated = 0 1.30.608.135 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.183 1.30.612.853 I slot launch_slot_: id 0 | task 3654 | processing task, is_child = 0 1.31.533.087 I slot print_timing: id 0 | task 3654 | prompt eval time = 373.11 ms / 145 tokens ( 2.57 ms per token, 388.63 tokens per second) 1.31.533.091 I slot print_timing: id 0 | task 3654 | eval time = 547.12 ms / 28 tokens ( 20.26 ms per token, 49.35 tokens per second) 1.31.533.092 I slot print_timing: id 0 | task 3654 | total time = 920.23 ms / 173 tokens 1.31.533.092 I slot print_timing: id 0 | task 3654 | graphs reused = 3470 1.31.533.093 I slot print_timing: id 0 | task 3654 | graph reallocs = 0 / 0 (same size) / (changed size) 1.31.533.113 I slot release: id 0 | task 3654 | stop processing: n_tokens = 172, truncated = 0 1.31.537.139 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.150 (> 0.100 thold), f_keep = 0.174 1.31.541.974 I slot launch_slot_: id 0 | task 3685 | processing task, is_child = 0 1.32.643.552 I slot print_timing: id 0 | task 3685 | prompt eval time = 461.80 ms / 200 tokens ( 2.31 ms per token, 433.09 tokens per second) 1.32.643.556 I slot print_timing: id 0 | task 3685 | eval time = 639.77 ms / 32 tokens ( 20.64 ms per token, 48.45 tokens per second) 1.32.643.556 I slot print_timing: id 0 | task 3685 | total time = 1101.57 ms / 232 tokens 1.32.643.557 I slot print_timing: id 0 | task 3685 | graphs reused = 3500 1.32.643.558 I slot print_timing: id 0 | task 3685 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.643.576 I slot release: id 0 | task 3685 | stop processing: n_tokens = 231, truncated = 0 1.32.648.155 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 231, t_last = 327874632839 1.32.654.384 I slot launch_slot_: id 0 | task 3720 | processing task, is_child = 0 1.34.532.936 I slot print_timing: id 0 | task 3720 | prompt eval time = 690.94 ms / 326 tokens ( 2.12 ms per token, 471.82 tokens per second) 1.34.532.942 I slot print_timing: id 0 | task 3720 | eval time = 1187.61 ms / 59 tokens ( 20.48 ms per token, 48.84 tokens per second) 1.34.532.943 I slot print_timing: id 0 | task 3720 | total time = 1878.54 ms / 385 tokens 1.34.532.944 I slot print_timing: id 0 | task 3720 | graphs reused = 3557 1.34.532.944 I slot print_timing: id 0 | task 3720 | graph reallocs = 0 / 0 (same size) / (changed size) 1.34.532.968 I slot release: id 0 | task 3720 | stop processing: n_tokens = 384, truncated = 0 1.34.536.764 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.078 1.34.547.129 I slot launch_slot_: id 0 | task 3782 | processing task, is_child = 0 1.35.374.740 I slot print_timing: id 0 | task 3782 | prompt eval time = 360.10 ms / 148 tokens ( 2.43 ms per token, 410.99 tokens per second) 1.35.374.746 I slot print_timing: id 0 | task 3782 | eval time = 467.50 ms / 24 tokens ( 20.33 ms per token, 49.20 tokens per second) 1.35.374.746 I slot print_timing: id 0 | task 3782 | total time = 827.60 ms / 172 tokens 1.35.374.752 I slot print_timing: id 0 | task 3782 | graphs reused = 3579 1.35.374.753 I slot print_timing: id 0 | task 3782 | graph reallocs = 0 / 0 (same size) / (changed size) 1.35.374.772 I slot release: id 0 | task 3782 | stop processing: n_tokens = 171, truncated = 0 1.35.378.719 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.175 1.35.381.436 I slot launch_slot_: id 0 | task 3809 | processing task, is_child = 0 1.36.322.355 I slot print_timing: id 0 | task 3809 | prompt eval time = 380.29 ms / 175 tokens ( 2.17 ms per token, 460.18 tokens per second) 1.36.322.358 I slot print_timing: id 0 | task 3809 | eval time = 560.62 ms / 28 tokens ( 20.76 ms per token, 48.16 tokens per second) 1.36.322.358 I slot print_timing: id 0 | task 3809 | total time = 940.90 ms / 203 tokens 1.36.322.359 I slot print_timing: id 0 | task 3809 | graphs reused = 3605 1.36.322.359 I slot print_timing: id 0 | task 3809 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.322.386 I slot release: id 0 | task 3809 | stop processing: n_tokens = 202, truncated = 0 1.36.326.838 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.131 (> 0.100 thold), f_keep = 0.149 1.36.332.452 I slot launch_slot_: id 0 | task 3840 | processing task, is_child = 0 1.37.650.162 I slot print_timing: id 0 | task 3840 | prompt eval time = 524.89 ms / 229 tokens ( 2.29 ms per token, 436.28 tokens per second) 1.37.650.165 I slot print_timing: id 0 | task 3840 | eval time = 792.81 ms / 40 tokens ( 20.33 ms per token, 49.19 tokens per second) 1.37.650.166 I slot print_timing: id 0 | task 3840 | total time = 1317.70 ms / 269 tokens 1.37.650.166 I slot print_timing: id 0 | task 3840 | graphs reused = 3642 1.37.650.167 I slot print_timing: id 0 | task 3840 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.650.186 I slot release: id 0 | task 3840 | stop processing: n_tokens = 268, truncated = 0 1.37.654.394 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.130 (> 0.100 thold), f_keep = 0.116 1.37.662.189 I slot launch_slot_: id 0 | task 3883 | processing task, is_child = 0 1.38.708.826 I slot print_timing: id 0 | task 3883 | prompt eval time = 526.15 ms / 238 tokens ( 2.21 ms per token, 452.34 tokens per second) 1.38.708.831 I slot print_timing: id 0 | task 3883 | eval time = 520.47 ms / 26 tokens ( 20.82 ms per token, 48.03 tokens per second) 1.38.708.832 I slot print_timing: id 0 | task 3883 | total time = 1046.63 ms / 264 tokens 1.38.708.833 I slot print_timing: id 0 | task 3883 | graphs reused = 3665 1.38.708.833 I slot print_timing: id 0 | task 3883 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.708.855 I slot release: id 0 | task 3883 | stop processing: n_tokens = 263, truncated = 0 1.38.712.384 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.204 (> 0.100 thold), f_keep = 0.125 1.38.719.656 I slot launch_slot_: id 0 | task 3912 | processing task, is_child = 0 1.39.359.574 I slot print_timing: id 0 | task 3912 | prompt eval time = 376.10 ms / 162 tokens ( 2.32 ms per token, 430.74 tokens per second) 1.39.359.581 I slot print_timing: id 0 | task 3912 | eval time = 263.81 ms / 14 tokens ( 20.29 ms per token, 49.28 tokens per second) 1.39.359.581 I slot print_timing: id 0 | task 3912 | total time = 639.91 ms / 176 tokens 1.39.359.582 I slot print_timing: id 0 | task 3912 | graphs reused = 3677 1.39.359.582 I slot print_timing: id 0 | task 3912 | graph reallocs = 0 / 0 (same size) / (changed size) 1.39.359.613 I slot release: id 0 | task 3912 | stop processing: n_tokens = 175, truncated = 0 1.39.363.467 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.171 1.39.366.263 I slot launch_slot_: id 0 | task 3929 | processing task, is_child = 0 1.40.286.713 I slot print_timing: id 0 | task 3929 | prompt eval time = 412.35 ms / 169 tokens ( 2.44 ms per token, 409.85 tokens per second) 1.40.286.717 I slot print_timing: id 0 | task 3929 | eval time = 508.10 ms / 26 tokens ( 20.32 ms per token, 49.20 tokens per second) 1.40.286.718 I slot print_timing: id 0 | task 3929 | total time = 920.44 ms / 195 tokens 1.40.286.719 I slot print_timing: id 0 | task 3929 | graphs reused = 3701 1.40.286.719 I slot print_timing: id 0 | task 3929 | graph reallocs = 0 / 0 (same size) / (changed size) 1.40.286.737 I slot release: id 0 | task 3929 | stop processing: n_tokens = 194, truncated = 0 1.40.290.778 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.167 (> 0.100 thold), f_keep = 0.155 1.40.296.132 I slot launch_slot_: id 0 | task 3958 | processing task, is_child = 0 1.41.284.868 I slot print_timing: id 0 | task 3958 | prompt eval time = 439.97 ms / 180 tokens ( 2.44 ms per token, 409.12 tokens per second) 1.41.284.874 I slot print_timing: id 0 | task 3958 | eval time = 548.76 ms / 28 tokens ( 20.32 ms per token, 49.20 tokens per second) 1.41.284.875 I slot print_timing: id 0 | task 3958 | total time = 988.73 ms / 208 tokens 1.41.284.875 I slot print_timing: id 0 | task 3958 | graphs reused = 3727 1.41.284.876 I slot print_timing: id 0 | task 3958 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.284.894 I slot release: id 0 | task 3958 | stop processing: n_tokens = 207, truncated = 0 1.41.289.102 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.148 (> 0.100 thold), f_keep = 0.145 1.41.295.107 I slot launch_slot_: id 0 | task 3989 | processing task, is_child = 0 1.42.661.970 I slot print_timing: id 0 | task 3989 | prompt eval time = 474.01 ms / 203 tokens ( 2.34 ms per token, 428.26 tokens per second) 1.42.661.976 I slot print_timing: id 0 | task 3989 | eval time = 892.84 ms / 45 tokens ( 20.29 ms per token, 49.28 tokens per second) 1.42.661.977 I slot print_timing: id 0 | task 3989 | total time = 1366.85 ms / 248 tokens 1.42.661.977 I slot print_timing: id 0 | task 3989 | graphs reused = 3770 1.42.661.978 I slot print_timing: id 0 | task 3989 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.661.996 I slot release: id 0 | task 3989 | stop processing: n_tokens = 247, truncated = 0 1.42.665.768 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.191 (> 0.100 thold), f_keep = 0.121 1.42.671.539 I slot launch_slot_: id 0 | task 4037 | processing task, is_child = 0 1.43.680.471 I slot print_timing: id 0 | task 4037 | prompt eval time = 409.86 ms / 157 tokens ( 2.61 ms per token, 383.06 tokens per second) 1.43.680.476 I slot print_timing: id 0 | task 4037 | eval time = 599.07 ms / 30 tokens ( 20.66 ms per token, 48.41 tokens per second) 1.43.680.476 I slot print_timing: id 0 | task 4037 | total time = 1008.92 ms / 187 tokens 1.43.680.477 I slot print_timing: id 0 | task 4037 | graphs reused = 3798 1.43.680.478 I slot print_timing: id 0 | task 4037 | graph reallocs = 0 / 0 (same size) / (changed size) 1.43.680.498 I slot release: id 0 | task 4037 | stop processing: n_tokens = 186, truncated = 0 1.43.684.794 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.140 (> 0.100 thold), f_keep = 0.161 1.43.689.203 I slot launch_slot_: id 0 | task 4070 | processing task, is_child = 0 1.44.794.460 I slot print_timing: id 0 | task 4070 | prompt eval time = 474.89 ms / 214 tokens ( 2.22 ms per token, 450.63 tokens per second) 1.44.794.466 I slot print_timing: id 0 | task 4070 | eval time = 630.35 ms / 32 tokens ( 20.33 ms per token, 49.18 tokens per second) 1.44.794.467 I slot print_timing: id 0 | task 4070 | total time = 1105.24 ms / 246 tokens 1.44.794.468 I slot print_timing: id 0 | task 4070 | graphs reused = 3828 1.44.794.468 I slot print_timing: id 0 | task 4070 | graph reallocs = 0 / 0 (same size) / (changed size) 1.44.794.486 I slot release: id 0 | task 4070 | stop processing: n_tokens = 245, truncated = 0 1.44.798.366 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.183 (> 0.100 thold), f_keep = 0.122 1.44.805.369 I slot launch_slot_: id 0 | task 4105 | processing task, is_child = 0 1.45.406.501 I slot print_timing: id 0 | task 4105 | prompt eval time = 376.52 ms / 164 tokens ( 2.30 ms per token, 435.56 tokens per second) 1.45.406.508 I slot print_timing: id 0 | task 4105 | eval time = 224.60 ms / 12 tokens ( 20.42 ms per token, 48.98 tokens per second) 1.45.406.508 I slot print_timing: id 0 | task 4105 | total time = 601.12 ms / 176 tokens 1.45.406.509 I slot print_timing: id 0 | task 4105 | graphs reused = 3838 1.45.406.509 I slot print_timing: id 0 | task 4105 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.406.528 I slot release: id 0 | task 4105 | stop processing: n_tokens = 175, truncated = 0 1.45.410.522 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.181 (> 0.100 thold), f_keep = 0.171 1.45.414.151 I slot launch_slot_: id 0 | task 4120 | processing task, is_child = 0 1.46.432.895 I slot print_timing: id 0 | task 4120 | prompt eval time = 410.23 ms / 166 tokens ( 2.47 ms per token, 404.65 tokens per second) 1.46.432.899 I slot print_timing: id 0 | task 4120 | eval time = 608.50 ms / 31 tokens ( 20.28 ms per token, 49.30 tokens per second) 1.46.432.900 I slot print_timing: id 0 | task 4120 | total time = 1018.74 ms / 197 tokens 1.46.432.901 I slot print_timing: id 0 | task 4120 | graphs reused = 3867 1.46.432.901 I slot print_timing: id 0 | task 4120 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.432.919 I slot release: id 0 | task 4120 | stop processing: n_tokens = 196, truncated = 0 1.46.437.346 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.108 (> 0.100 thold), f_keep = 0.153 1.46.442.716 I slot launch_slot_: id 0 | task 4154 | processing task, is_child = 0 1.49.769.121 I slot print_timing: id 0 | task 4154 | prompt eval time = 629.71 ms / 277 tokens ( 2.27 ms per token, 439.89 tokens per second) 1.49.769.124 I slot print_timing: id 0 | task 4154 | eval time = 2696.69 ms / 133 tokens ( 20.43 ms per token, 48.95 tokens per second) 1.49.769.125 I slot print_timing: id 0 | task 4154 | total time = 3326.39 ms / 410 tokens 1.49.769.125 I slot print_timing: id 0 | task 4154 | graphs reused = 3998 1.49.769.126 I slot print_timing: id 0 | task 4154 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.769.159 I slot release: id 0 | task 4154 | stop processing: n_tokens = 409, truncated = 0 1.49.773.563 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.121 (> 0.100 thold), f_keep = 0.073 1.49.783.683 I slot launch_slot_: id 0 | task 4290 | processing task, is_child = 0 1.51.492.872 I slot print_timing: id 0 | task 4290 | prompt eval time = 528.61 ms / 248 tokens ( 2.13 ms per token, 469.15 tokens per second) 1.51.492.879 I slot print_timing: id 0 | task 4290 | eval time = 1180.57 ms / 59 tokens ( 20.35 ms per token, 49.13 tokens per second) 1.51.492.879 I slot print_timing: id 0 | task 4290 | total time = 1709.18 ms / 307 tokens 1.51.492.880 I slot print_timing: id 0 | task 4290 | graphs reused = 4054 1.51.492.880 I slot print_timing: id 0 | task 4290 | graph reallocs = 0 / 0 (same size) / (changed size) 1.51.492.906 I slot release: id 0 | task 4290 | stop processing: n_tokens = 306, truncated = 0 1.51.496.857 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.189 (> 0.100 thold), f_keep = 0.098 1.51.504.844 I slot launch_slot_: id 0 | task 4352 | processing task, is_child = 0 1.53.472.980 I slot print_timing: id 0 | task 4352 | prompt eval time = 411.19 ms / 159 tokens ( 2.59 ms per token, 386.68 tokens per second) 1.53.472.986 I slot print_timing: id 0 | task 4352 | eval time = 1556.93 ms / 78 tokens ( 20.22 ms per token, 49.46 tokens per second) 1.53.472.987 I slot print_timing: id 0 | task 4352 | total time = 1968.12 ms / 237 tokens 1.53.472.988 I slot print_timing: id 0 | task 4352 | graphs reused = 4130 1.53.472.989 I slot print_timing: id 0 | task 4352 | graph reallocs = 0 / 0 (same size) / (changed size) 1.53.473.010 I slot release: id 0 | task 4352 | stop processing: n_tokens = 236, truncated = 0 1.53.477.560 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.153 (> 0.100 thold), f_keep = 0.127 1.53.481.981 I slot launch_slot_: id 0 | task 4433 | processing task, is_child = 0 1.54.564.432 I slot print_timing: id 0 | task 4433 | prompt eval time = 473.06 ms / 196 tokens ( 2.41 ms per token, 414.33 tokens per second) 1.54.564.438 I slot print_timing: id 0 | task 4433 | eval time = 609.39 ms / 31 tokens ( 20.31 ms per token, 49.23 tokens per second) 1.54.564.439 I slot print_timing: id 0 | task 4433 | total time = 1082.44 ms / 227 tokens 1.54.564.439 I slot print_timing: id 0 | task 4433 | graphs reused = 4159 1.54.564.440 I slot print_timing: id 0 | task 4433 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.564.458 I slot release: id 0 | task 4433 | stop processing: n_tokens = 226, truncated = 0 1.54.568.141 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.133 1.54.574.455 I slot launch_slot_: id 0 | task 4467 | processing task, is_child = 0 1.57.947.601 I slot print_timing: id 0 | task 4467 | prompt eval time = 377.28 ms / 150 tokens ( 2.52 ms per token, 397.58 tokens per second) 1.57.947.607 I slot print_timing: id 0 | task 4467 | eval time = 2995.85 ms / 149 tokens ( 20.24 ms per token, 49.40 tokens per second) 1.57.947.607 I slot print_timing: id 0 | task 4467 | total time = 3373.14 ms / 299 tokens 1.57.947.608 I slot print_timing: id 0 | task 4467 | graphs reused = 4305 1.57.947.609 I slot print_timing: id 0 | task 4467 | graph reallocs = 0 / 0 (same size) / (changed size) 1.57.947.626 I slot release: id 0 | task 4467 | stop processing: n_tokens = 298, truncated = 0 1.57.951.937 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.140 (> 0.100 thold), f_keep = 0.101 1.57.957.556 I slot launch_slot_: id 0 | task 4619 | processing task, is_child = 0 1.59.549.725 I slot print_timing: id 0 | task 4619 | prompt eval time = 474.71 ms / 215 tokens ( 2.21 ms per token, 452.91 tokens per second) 1.59.549.728 I slot print_timing: id 0 | task 4619 | eval time = 1117.45 ms / 56 tokens ( 20.32 ms per token, 49.22 tokens per second) 1.59.549.729 I slot print_timing: id 0 | task 4619 | total time = 1592.16 ms / 271 tokens 1.59.549.729 I slot print_timing: id 0 | task 4619 | graphs reused = 4358 1.59.549.730 I slot print_timing: id 0 | task 4619 | graph reallocs = 0 / 0 (same size) / (changed size) 1.59.549.753 I slot release: id 0 | task 4619 | stop processing: n_tokens = 270, truncated = 0 1.59.554.453 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 270, t_last = 327901539015 1.59.561.840 I slot launch_slot_: id 0 | task 4678 | processing task, is_child = 0 2.00.867.872 I slot print_timing: id 0 | task 4678 | prompt eval time = 692.36 ms / 327 tokens ( 2.12 ms per token, 472.30 tokens per second) 2.00.867.878 I slot print_timing: id 0 | task 4678 | eval time = 613.66 ms / 31 tokens ( 20.46 ms per token, 48.89 tokens per second) 2.00.867.880 I slot print_timing: id 0 | task 4678 | total time = 1306.03 ms / 358 tokens 2.00.867.881 I slot print_timing: id 0 | task 4678 | graphs reused = 4387 2.00.867.881 I slot print_timing: id 0 | task 4678 | graph reallocs = 0 / 0 (same size) / (changed size) 2.00.867.902 I slot release: id 0 | task 4678 | stop processing: n_tokens = 357, truncated = 0 2.00.872.945 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 357, t_last = 327902857164 2.00.883.514 I slot launch_slot_: id 0 | task 4712 | processing task, is_child = 0 2.04.700.390 I slot print_timing: id 0 | task 4712 | n_gen = 147, tg = 48.42 t/s, tg_3s = 48.75 t/s 2.06.125.626 I slot print_timing: id 0 | task 4712 | prompt eval time = 801.58 ms / 399 tokens ( 2.01 ms per token, 497.77 tokens per second) 2.06.125.629 I slot print_timing: id 0 | task 4712 | eval time = 4440.52 ms / 216 tokens ( 20.65 ms per token, 48.42 tokens per second) 2.06.125.629 I slot print_timing: id 0 | task 4712 | total time = 5242.10 ms / 615 tokens 2.06.125.630 I slot print_timing: id 0 | task 4712 | graphs reused = 4600 2.06.125.631 I slot print_timing: id 0 | task 4712 | graph reallocs = 0 / 0 (same size) / (changed size) 2.06.125.663 I slot release: id 0 | task 4712 | stop processing: n_tokens = 614, truncated = 0 2.06.131.401 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 614, t_last = 327908114925 2.06.145.297 I slot launch_slot_: id 0 | task 4931 | processing task, is_child = 0 2.08.833.140 I slot print_timing: id 0 | task 4931 | prompt eval time = 908.66 ms / 439 tokens ( 2.07 ms per token, 483.13 tokens per second) 2.08.833.146 I slot print_timing: id 0 | task 4931 | eval time = 1779.17 ms / 86 tokens ( 20.93 ms per token, 47.78 tokens per second) 2.08.833.148 I slot print_timing: id 0 | task 4931 | total time = 2687.84 ms / 525 tokens 2.08.833.148 I slot print_timing: id 0 | task 4931 | graphs reused = 4683 2.08.833.149 I slot print_timing: id 0 | task 4931 | graph reallocs = 0 / 0 (same size) / (changed size) 2.08.833.178 I slot release: id 0 | task 4931 | stop processing: n_tokens = 524, truncated = 0 2.08.838.645 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 524, t_last = 327910822440 2.08.854.510 I slot launch_slot_: id 0 | task 5020 | processing task, is_child = 0 2.10.357.052 I slot print_timing: id 0 | task 5020 | prompt eval time = 797.87 ms / 413 tokens ( 1.93 ms per token, 517.63 tokens per second) 2.10.357.058 I slot print_timing: id 0 | task 5020 | eval time = 704.66 ms / 35 tokens ( 20.73 ms per token, 48.25 tokens per second) 2.10.357.059 I slot print_timing: id 0 | task 5020 | total time = 1502.53 ms / 448 tokens 2.10.357.060 I slot print_timing: id 0 | task 5020 | graphs reused = 4716 2.10.357.060 I slot print_timing: id 0 | task 5020 | graph reallocs = 0 / 0 (same size) / (changed size) 2.10.357.091 I slot release: id 0 | task 5020 | stop processing: n_tokens = 447, truncated = 0 2.10.361.689 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.112 (> 0.100 thold), f_keep = 0.067 2.10.375.663 I slot launch_slot_: id 0 | task 5058 | processing task, is_child = 0 2.12.297.601 I slot print_timing: id 0 | task 5058 | prompt eval time = 579.42 ms / 268 tokens ( 2.16 ms per token, 462.53 tokens per second) 2.12.297.608 I slot print_timing: id 0 | task 5058 | eval time = 1342.51 ms / 67 tokens ( 20.34 ms per token, 49.16 tokens per second) 2.12.297.610 I slot print_timing: id 0 | task 5058 | total time = 1921.93 ms / 335 tokens 2.12.297.611 I slot print_timing: id 0 | task 5058 | graphs reused = 4781 2.12.297.611 I slot print_timing: id 0 | task 5058 | graph reallocs = 0 / 0 (same size) / (changed size) 2.12.297.632 I slot release: id 0 | task 5058 | stop processing: n_tokens = 334, truncated = 0 2.12.302.679 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 334, t_last = 327914286894 2.12.308.660 I slot launch_slot_: id 0 | task 5128 | processing task, is_child = 0 2.16.125.831 I slot print_timing: id 0 | task 5128 | n_gen = 147, tg = 48.45 t/s, tg_3s = 48.78 t/s 2.16.497.743 I slot print_timing: id 0 | task 5128 | prompt eval time = 803.54 ms / 395 tokens ( 2.03 ms per token, 491.58 tokens per second) 2.16.497.747 I slot print_timing: id 0 | task 5128 | eval time = 3385.53 ms / 165 tokens ( 20.64 ms per token, 48.44 tokens per second) 2.16.497.747 I slot print_timing: id 0 | task 5128 | total time = 4189.07 ms / 560 tokens 2.16.497.748 I slot print_timing: id 0 | task 5128 | graphs reused = 4943 2.16.497.748 I slot print_timing: id 0 | task 5128 | graph reallocs = 0 / 0 (same size) / (changed size) 2.16.497.774 I slot release: id 0 | task 5128 | stop processing: n_tokens = 559, truncated = 0 2.16.502.774 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 559, t_last = 327918487036 2.16.517.416 I slot launch_slot_: id 0 | task 5296 | processing task, is_child = 0 2.17.889.787 I slot print_timing: id 0 | task 5296 | prompt eval time = 802.76 ms / 390 tokens ( 2.06 ms per token, 485.82 tokens per second) 2.17.889.795 I slot print_timing: id 0 | task 5296 | eval time = 569.60 ms / 28 tokens ( 21.10 ms per token, 47.40 tokens per second) 2.17.889.795 I slot print_timing: id 0 | task 5296 | total time = 1372.36 ms / 418 tokens 2.17.889.796 I slot print_timing: id 0 | task 5296 | graphs reused = 4969 2.17.889.797 I slot print_timing: id 0 | task 5296 | graph reallocs = 0 / 0 (same size) / (changed size) 2.17.889.836 I slot release: id 0 | task 5296 | stop processing: n_tokens = 417, truncated = 0 2.17.895.741 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 417, t_last = 327919879098 2.17.910.334 I slot launch_slot_: id 0 | task 5327 | processing task, is_child = 0 2.18.917.838 I slot print_timing: id 0 | task 5327 | prompt eval time = 637.67 ms / 304 tokens ( 2.10 ms per token, 476.73 tokens per second) 2.18.917.844 I slot print_timing: id 0 | task 5327 | eval time = 369.82 ms / 19 tokens ( 20.55 ms per token, 48.67 tokens per second) 2.18.917.844 I slot print_timing: id 0 | task 5327 | total time = 1007.49 ms / 323 tokens 2.18.917.845 I slot print_timing: id 0 | task 5327 | graphs reused = 4986 2.18.917.845 I slot print_timing: id 0 | task 5327 | graph reallocs = 0 / 0 (same size) / (changed size) 2.18.917.866 I slot release: id 0 | task 5327 | stop processing: n_tokens = 322, truncated = 0 2.18.922.525 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.104 (> 0.100 thold), f_keep = 0.093 2.18.927.787 I slot launch_slot_: id 0 | task 5349 | processing task, is_child = 0 2.20.546.496 I slot print_timing: id 0 | task 5349 | prompt eval time = 637.86 ms / 289 tokens ( 2.21 ms per token, 453.08 tokens per second) 2.20.546.502 I slot print_timing: id 0 | task 5349 | eval time = 980.84 ms / 49 tokens ( 20.43 ms per token, 48.94 tokens per second) 2.20.546.503 I slot print_timing: id 0 | task 5349 | total time = 1618.70 ms / 338 tokens 2.20.546.504 I slot print_timing: id 0 | task 5349 | graphs reused = 5033 2.20.546.504 I slot print_timing: id 0 | task 5349 | graph reallocs = 0 / 0 (same size) / (changed size) 2.20.546.525 I slot release: id 0 | task 5349 | stop processing: n_tokens = 337, truncated = 0 2.20.551.527 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 337, t_last = 327922535787 2.20.561.534 I slot launch_slot_: id 0 | task 5401 | processing task, is_child = 0 2.21.722.176 I slot print_timing: id 0 | task 5401 | prompt eval time = 715.07 ms / 360 tokens ( 1.99 ms per token, 503.44 tokens per second) 2.21.722.182 I slot print_timing: id 0 | task 5401 | eval time = 445.56 ms / 22 tokens ( 21.22 ms per token, 47.13 tokens per second) 2.21.722.184 I slot print_timing: id 0 | task 5401 | total time = 1160.63 ms / 382 tokens 2.21.722.184 I slot print_timing: id 0 | task 5401 | graphs reused = 5053 2.21.722.185 I slot print_timing: id 0 | task 5401 | graph reallocs = 0 / 0 (same size) / (changed size) 2.21.722.207 I slot release: id 0 | task 5401 | stop processing: n_tokens = 381, truncated = 0 2.21.726.692 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 381, t_last = 327923711469 2.21.738.036 I slot launch_slot_: id 0 | task 5426 | processing task, is_child = 0 2.25.442.503 I slot print_timing: id 0 | task 5426 | n_gen = 148, tg = 48.77 t/s, tg_3s = 49.10 t/s 2.28.456.311 I slot print_timing: id 0 | task 5426 | n_gen = 294, tg = 48.61 t/s, tg_3s = 48.44 t/s 2.31.470.774 I slot print_timing: id 0 | task 5426 | n_gen = 440, tg = 48.55 t/s, tg_3s = 48.43 t/s 2.34.471.153 I slot print_timing: id 0 | task 5426 | n_gen = 585, tg = 48.49 t/s, tg_3s = 48.33 t/s 2.37.476.546 I slot print_timing: id 0 | task 5426 | n_gen = 730, tg = 48.44 t/s, tg_3s = 48.25 t/s 2.40.487.853 I slot print_timing: id 0 | task 5426 | n_gen = 875, tg = 48.40 t/s, tg_3s = 48.15 t/s 2.43.086.242 I slot print_timing: id 0 | task 5426 | prompt eval time = 690.40 ms / 317 tokens ( 2.18 ms per token, 459.16 tokens per second) 2.43.086.245 I slot print_timing: id 0 | task 5426 | eval time = 20657.80 ms / 1000 tokens ( 20.68 ms per token, 48.36 tokens per second) 2.43.086.246 I slot print_timing: id 0 | task 5426 | total time = 21348.20 ms / 1317 tokens 2.43.086.247 I slot print_timing: id 0 | task 5426 | graphs reused = 6047 2.43.086.247 I slot print_timing: id 0 | task 5426 | graph reallocs = 0 / 0 (same size) / (changed size) 2.43.086.277 I slot release: id 0 | task 5426 | stop processing: n_tokens = 1316, truncated = 0 2.43.091.172 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.121 (> 0.100 thold), f_keep = 0.023 2.43.103.459 I slot launch_slot_: id 0 | task 6429 | processing task, is_child = 0 2.44.018.022 I slot print_timing: id 0 | task 6429 | prompt eval time = 545.80 ms / 248 tokens ( 2.20 ms per token, 454.38 tokens per second) 2.44.018.028 I slot print_timing: id 0 | task 6429 | eval time = 368.76 ms / 19 tokens ( 20.49 ms per token, 48.81 tokens per second) 2.44.018.029 I slot print_timing: id 0 | task 6429 | total time = 914.56 ms / 267 tokens 2.44.018.029 I slot print_timing: id 0 | task 6429 | graphs reused = 6063 2.44.018.030 I slot print_timing: id 0 | task 6429 | graph reallocs = 0 / 0 (same size) / (changed size) 2.44.018.049 I slot release: id 0 | task 6429 | stop processing: n_tokens = 266, truncated = 0 2.44.023.062 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 266, t_last = 327946007312 2.44.031.486 I slot launch_slot_: id 0 | task 6451 | processing task, is_child = 0 2.45.874.799 I slot print_timing: id 0 | task 6451 | prompt eval time = 695.40 ms / 331 tokens ( 2.10 ms per token, 475.98 tokens per second) 2.45.874.805 I slot print_timing: id 0 | task 6451 | eval time = 1147.90 ms / 57 tokens ( 20.50 ms per token, 48.78 tokens per second) 2.45.874.806 I slot print_timing: id 0 | task 6451 | total time = 1843.31 ms / 388 tokens 2.45.874.806 I slot print_timing: id 0 | task 6451 | graphs reused = 6118 2.45.874.807 I slot print_timing: id 0 | task 6451 | graph reallocs = 0 / 0 (same size) / (changed size) 2.45.874.830 I slot release: id 0 | task 6451 | stop processing: n_tokens = 387, truncated = 0 2.45.879.460 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.107 (> 0.100 thold), f_keep = 0.078 2.45.891.531 I slot launch_slot_: id 0 | task 6511 | processing task, is_child = 0 2.46.967.192 I slot print_timing: id 0 | task 6511 | prompt eval time = 603.11 ms / 280 tokens ( 2.15 ms per token, 464.26 tokens per second) 2.46.967.195 I slot print_timing: id 0 | task 6511 | eval time = 472.54 ms / 24 tokens ( 20.55 ms per token, 48.67 tokens per second) 2.46.967.196 I slot print_timing: id 0 | task 6511 | total time = 1075.65 ms / 304 tokens 2.46.967.197 I slot print_timing: id 0 | task 6511 | graphs reused = 6140 2.46.967.197 I slot print_timing: id 0 | task 6511 | graph reallocs = 0 / 0 (same size) / (changed size) 2.46.967.225 I slot release: id 0 | task 6511 | stop processing: n_tokens = 303, truncated = 0 2.46.971.585 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.119 (> 0.100 thold), f_keep = 0.099 2.46.979.458 I slot launch_slot_: id 0 | task 6538 | processing task, is_child = 0 2.48.009.751 I slot print_timing: id 0 | task 6538 | prompt eval time = 579.12 ms / 252 tokens ( 2.30 ms per token, 435.15 tokens per second) 2.48.009.758 I slot print_timing: id 0 | task 6538 | eval time = 451.17 ms / 23 tokens ( 20.51 ms per token, 48.76 tokens per second) 2.48.009.758 I slot print_timing: id 0 | task 6538 | total time = 1030.28 ms / 275 tokens 2.48.009.759 I slot print_timing: id 0 | task 6538 | graphs reused = 6160 2.48.009.759 I slot print_timing: id 0 | task 6538 | graph reallocs = 0 / 0 (same size) / (changed size) 2.48.009.779 I slot release: id 0 | task 6538 | stop processing: n_tokens = 274, truncated = 0 2.48.014.411 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.112 (> 0.100 thold), f_keep = 0.109 2.48.023.204 I slot launch_slot_: id 0 | task 6564 | processing task, is_child = 0 2.51.572.311 I slot print_timing: id 0 | task 6564 | n_gen = 148, tg = 48.98 t/s, tg_3s = 49.31 t/s 2.54.584.380 I slot print_timing: id 0 | task 6564 | n_gen = 294, tg = 48.72 t/s, tg_3s = 48.47 t/s 2.54.956.157 I slot print_timing: id 0 | task 6564 | prompt eval time = 547.57 ms / 267 tokens ( 2.05 ms per token, 487.61 tokens per second) 2.54.956.166 I slot print_timing: id 0 | task 6564 | eval time = 6385.37 ms / 312 tokens ( 20.53 ms per token, 48.71 tokens per second) 2.54.956.167 I slot print_timing: id 0 | task 6564 | total time = 6932.94 ms / 579 tokens 2.54.956.167 I slot print_timing: id 0 | task 6564 | graphs reused = 6469 2.54.956.169 I slot print_timing: id 0 | task 6564 | graph reallocs = 0 / 0 (same size) / (changed size) 2.54.956.195 I slot release: id 0 | task 6564 | stop processing: n_tokens = 578, truncated = 0 2.54.960.777 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.118 (> 0.100 thold), f_keep = 0.052 2.54.973.036 I slot launch_slot_: id 0 | task 6879 | processing task, is_child = 0 2.55.980.744 I slot print_timing: id 0 | task 6879 | prompt eval time = 576.57 ms / 255 tokens ( 2.26 ms per token, 442.27 tokens per second) 2.55.980.750 I slot print_timing: id 0 | task 6879 | eval time = 431.13 ms / 22 tokens ( 20.53 ms per token, 48.71 tokens per second) 2.55.980.751 I slot print_timing: id 0 | task 6879 | total time = 1007.70 ms / 277 tokens 2.55.980.752 I slot print_timing: id 0 | task 6879 | graphs reused = 6488 2.55.980.752 I slot print_timing: id 0 | task 6879 | graph reallocs = 0 / 0 (same size) / (changed size) 2.55.980.772 I slot release: id 0 | task 6879 | stop processing: n_tokens = 276, truncated = 0 2.55.986.031 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 276, t_last = 327957970034 2.55.994.900 I slot launch_slot_: id 0 | task 6904 | processing task, is_child = 0 2.57.408.974 I slot print_timing: id 0 | task 6904 | prompt eval time = 803.08 ms / 397 tokens ( 2.02 ms per token, 494.35 tokens per second) 2.57.408.978 I slot print_timing: id 0 | task 6904 | eval time = 610.99 ms / 30 tokens ( 21.07 ms per token, 47.46 tokens per second) 2.57.408.979 I slot print_timing: id 0 | task 6904 | total time = 1414.06 ms / 427 tokens 2.57.408.979 I slot print_timing: id 0 | task 6904 | graphs reused = 6516 2.57.408.980 I slot print_timing: id 0 | task 6904 | graph reallocs = 0 / 0 (same size) / (changed size) 2.57.409.011 I slot release: id 0 | task 6904 | stop processing: n_tokens = 426, truncated = 0 2.57.413.858 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.103 (> 0.100 thold), f_keep = 0.070 2.57.428.922 I slot launch_slot_: id 0 | task 6937 | processing task, is_child = 0 2.59.328.232 I slot print_timing: id 0 | task 6937 | prompt eval time = 636.32 ms / 290 tokens ( 2.19 ms per token, 455.75 tokens per second) 2.59.328.238 I slot print_timing: id 0 | task 6937 | eval time = 1262.98 ms / 63 tokens ( 20.37 ms per token, 49.09 tokens per second) 2.59.328.239 I slot print_timing: id 0 | task 6937 | total time = 1899.30 ms / 353 tokens 2.59.328.239 I slot print_timing: id 0 | task 6937 | graphs reused = 6577 2.59.328.240 I slot print_timing: id 0 | task 6937 | graph reallocs = 0 / 0 (same size) / (changed size) 2.59.328.266 I slot release: id 0 | task 6937 | stop processing: n_tokens = 352, truncated = 0 2.59.334.862 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 352, t_last = 327961317528 2.59.341.338 I slot launch_slot_: id 0 | task 7003 | processing task, is_child = 0 3.03.581.080 I slot print_timing: id 0 | task 7003 | n_gen = 147, tg = 48.39 t/s, tg_3s = 48.72 t/s 3.04.263.547 I slot print_timing: id 0 | task 7003 | prompt eval time = 1222.36 ms / 612 tokens ( 2.00 ms per token, 500.67 tokens per second) 3.04.263.550 I slot print_timing: id 0 | task 7003 | eval time = 3699.83 ms / 180 tokens ( 20.67 ms per token, 48.38 tokens per second) 3.04.263.551 I slot print_timing: id 0 | task 7003 | total time = 4922.19 ms / 792 tokens 3.04.263.552 I slot print_timing: id 0 | task 7003 | graphs reused = 6754 3.04.263.557 I slot print_timing: id 0 | task 7003 | graph reallocs = 0 / 0 (same size) / (changed size) 3.04.263.601 I slot release: id 0 | task 7003 | stop processing: n_tokens = 791, truncated = 0 3.04.268.444 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.109 (> 0.100 thold), f_keep = 0.038 3.04.287.535 I slot launch_slot_: id 0 | task 7187 | processing task, is_child = 0 3.07.502.226 I slot print_timing: id 0 | task 7187 | prompt eval time = 580.27 ms / 275 tokens ( 2.11 ms per token, 473.92 tokens per second) 3.07.502.229 I slot print_timing: id 0 | task 7187 | eval time = 2634.41 ms / 130 tokens ( 20.42 ms per token, 48.97 tokens per second) 3.07.502.230 I slot print_timing: id 0 | task 7187 | total time = 3214.68 ms / 405 tokens 3.07.502.231 I slot print_timing: id 0 | task 7187 | graphs reused = 6882 3.07.502.232 I slot print_timing: id 0 | task 7187 | graph reallocs = 0 / 0 (same size) / (changed size) 3.07.502.258 I slot release: id 0 | task 7187 | stop processing: n_tokens = 404, truncated = 0 3.07.507.945 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 404, t_last = 327969491520 3.07.516.849 I slot launch_slot_: id 0 | task 7320 | processing task, is_child = 0 3.08.937.258 I slot print_timing: id 0 | task 7320 | prompt eval time = 921.62 ms / 456 tokens ( 2.02 ms per token, 494.78 tokens per second) 3.08.937.264 I slot print_timing: id 0 | task 7320 | eval time = 498.78 ms / 25 tokens ( 20.78 ms per token, 48.12 tokens per second) 3.08.937.265 I slot print_timing: id 0 | task 7320 | total time = 1420.40 ms / 481 tokens 3.08.937.266 I slot print_timing: id 0 | task 7320 | graphs reused = 6905 3.08.937.266 I slot print_timing: id 0 | task 7320 | graph reallocs = 0 / 0 (same size) / (changed size) 3.08.937.299 I slot release: id 0 | task 7320 | stop processing: n_tokens = 480, truncated = 0 3.08.943.672 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 480, t_last = 327970926561 3.08.960.127 I slot launch_slot_: id 0 | task 7348 | processing task, is_child = 0 3.10.865.121 I slot print_timing: id 0 | task 7348 | prompt eval time = 1114.38 ms / 542 tokens ( 2.06 ms per token, 486.37 tokens per second) 3.10.865.127 I slot print_timing: id 0 | task 7348 | eval time = 790.61 ms / 39 tokens ( 20.81 ms per token, 48.06 tokens per second) 3.10.865.127 I slot print_timing: id 0 | task 7348 | total time = 1904.99 ms / 581 tokens 3.10.865.128 I slot print_timing: id 0 | task 7348 | graphs reused = 6942 3.10.865.132 I slot print_timing: id 0 | task 7348 | graph reallocs = 0 / 0 (same size) / (changed size) 3.10.865.173 I slot release: id 0 | task 7348 | stop processing: n_tokens = 580, truncated = 0 3.10.870.381 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 580, t_last = 327972854435 3.10.887.057 I slot launch_slot_: id 0 | task 7391 | processing task, is_child = 0 3.12.572.943 I slot print_timing: id 0 | task 7391 | prompt eval time = 795.60 ms / 361 tokens ( 2.20 ms per token, 453.75 tokens per second) 3.12.572.949 I slot print_timing: id 0 | task 7391 | eval time = 890.27 ms / 44 tokens ( 20.70 ms per token, 48.30 tokens per second) 3.12.572.950 I slot print_timing: id 0 | task 7391 | total time = 1685.87 ms / 405 tokens 3.12.572.951 I slot print_timing: id 0 | task 7391 | graphs reused = 6984 3.12.572.951 I slot print_timing: id 0 | task 7391 | graph reallocs = 0 / 0 (same size) / (changed size) 3.12.572.980 I slot release: id 0 | task 7391 | stop processing: n_tokens = 429, truncated = 0 3.12.577.553 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.106 (> 0.100 thold), f_keep = 0.070 3.12.588.029 I slot launch_slot_: id 0 | task 7438 | processing task, is_child = 0 3.16.174.553 I slot print_timing: id 0 | task 7438 | n_gen = 148, tg = 48.89 t/s, tg_3s = 49.22 t/s 3.16.566.708 I slot print_timing: id 0 | task 7438 | prompt eval time = 579.72 ms / 258 tokens ( 2.25 ms per token, 445.04 tokens per second) 3.16.566.711 I slot print_timing: id 0 | task 7438 | eval time = 3398.95 ms / 167 tokens ( 20.48 ms per token, 48.84 tokens per second) 3.16.566.712 I slot print_timing: id 0 | task 7438 | total time = 3978.67 ms / 425 tokens 3.16.566.713 I slot print_timing: id 0 | task 7438 | graphs reused = 7149 3.16.566.713 I slot print_timing: id 0 | task 7438 | graph reallocs = 0 / 0 (same size) / (changed size) 3.16.566.742 I slot release: id 0 | task 7438 | stop processing: n_tokens = 448, truncated = 0 3.16.572.336 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 327978556004 3.16.580.819 I slot launch_slot_: id 0 | task 7608 | processing task, is_child = 0 3.20.400.412 I slot print_timing: id 0 | task 7608 | n_gen = 147, tg = 48.42 t/s, tg_3s = 48.75 t/s 3.23.184.702 I slot print_timing: id 0 | task 7608 | prompt eval time = 804.29 ms / 379 tokens ( 2.12 ms per token, 471.22 tokens per second) 3.23.184.707 I slot print_timing: id 0 | task 7608 | eval time = 5799.58 ms / 282 tokens ( 20.64 ms per token, 48.45 tokens per second) 3.23.184.707 I slot print_timing: id 0 | task 7608 | total time = 6603.87 ms / 661 tokens 3.23.184.708 I slot print_timing: id 0 | task 7608 | graphs reused = 7428 3.23.184.709 I slot print_timing: id 0 | task 7608 | graph reallocs = 0 / 0 (same size) / (changed size) 3.23.184.737 I slot release: id 0 | task 7608 | stop processing: n_tokens = 683, truncated = 0 3.23.191.178 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 683, t_last = 327985173999 3.23.207.843 I slot launch_slot_: id 0 | task 7893 | processing task, is_child = 0 3.27.339.925 I slot print_timing: id 0 | task 7893 | n_gen = 147, tg = 48.48 t/s, tg_3s = 48.81 t/s 3.29.666.856 I slot print_timing: id 0 | task 7893 | prompt eval time = 1120.68 ms / 540 tokens ( 2.08 ms per token, 481.85 tokens per second) 3.29.666.862 I slot print_timing: id 0 | task 7893 | eval time = 5338.33 ms / 260 tokens ( 20.61 ms per token, 48.52 tokens per second) 3.29.666.863 I slot print_timing: id 0 | task 7893 | total time = 6459.00 ms / 800 tokens 3.29.666.864 I slot print_timing: id 0 | task 7893 | graphs reused = 7685 3.29.666.864 I slot print_timing: id 0 | task 7893 | graph reallocs = 0 / 0 (same size) / (changed size) 3.29.666.908 I slot release: id 0 | task 7893 | stop processing: n_tokens = 821, truncated = 0 3.29.674.762 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 821, t_last = 327991656170 3.29.696.187 I slot launch_slot_: id 0 | task 8157 | processing task, is_child = 0 3.31.025.924 I slot print_timing: id 0 | task 8157 | prompt eval time = 749.69 ms / 370 tokens ( 2.03 ms per token, 493.54 tokens per second) 3.31.025.930 I slot print_timing: id 0 | task 8157 | eval time = 580.03 ms / 29 tokens ( 20.72 ms per token, 48.27 tokens per second) 3.31.025.932 I slot print_timing: id 0 | task 8157 | total time = 1329.72 ms / 399 tokens 3.31.025.933 I slot print_timing: id 0 | task 8157 | graphs reused = 7712 3.31.025.933 I slot print_timing: id 0 | task 8157 | graph reallocs = 0 / 0 (same size) / (changed size) 3.31.025.965 I slot release: id 0 | task 8157 | stop processing: n_tokens = 422, truncated = 0 3.31.031.186 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 422, t_last = 327993015227 3.31.035.167 I slot launch_slot_: id 0 | task 8189 | processing task, is_child = 0 3.34.742.715 I slot print_timing: id 0 | task 8189 | n_gen = 147, tg = 48.48 t/s, tg_3s = 48.81 t/s 3.35.859.088 I slot print_timing: id 0 | task 8189 | prompt eval time = 695.69 ms / 336 tokens ( 2.07 ms per token, 482.97 tokens per second) 3.35.859.092 I slot print_timing: id 0 | task 8189 | eval time = 4128.23 ms / 201 tokens ( 20.64 ms per token, 48.45 tokens per second) 3.35.859.092 I slot print_timing: id 0 | task 8189 | total time = 4823.91 ms / 537 tokens 3.35.859.093 I slot print_timing: id 0 | task 8189 | graphs reused = 7910 3.35.859.094 I slot print_timing: id 0 | task 8189 | graph reallocs = 0 / 0 (same size) / (changed size) 3.35.859.118 I slot release: id 0 | task 8189 | stop processing: n_tokens = 559, truncated = 0 3.35.863.935 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.115 (> 0.100 thold), f_keep = 0.054 3.35.874.816 I slot launch_slot_: id 0 | task 8393 | processing task, is_child = 0 3.36.892.391 I slot print_timing: id 0 | task 8393 | prompt eval time = 548.21 ms / 261 tokens ( 2.10 ms per token, 476.09 tokens per second) 3.36.892.394 I slot print_timing: id 0 | task 8393 | eval time = 469.35 ms / 24 tokens ( 20.41 ms per token, 49.00 tokens per second) 3.36.892.395 I slot print_timing: id 0 | task 8393 | total time = 1017.56 ms / 285 tokens 3.36.892.396 I slot print_timing: id 0 | task 8393 | graphs reused = 7932 3.36.892.396 I slot print_timing: id 0 | task 8393 | graph reallocs = 0 / 0 (same size) / (changed size) 3.36.892.417 I slot release: id 0 | task 8393 | stop processing: n_tokens = 284, truncated = 0 3.36.897.240 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.100 (> 0.100 thold), f_keep = 0.106 3.36.899.920 I slot launch_slot_: id 0 | task 8420 | processing task, is_child = 0 3.40.596.069 I slot print_timing: id 0 | task 8420 | n_gen = 147, tg = 48.50 t/s, tg_3s = 48.83 t/s 3.43.601.889 I slot print_timing: id 0 | task 8420 | n_gen = 293, tg = 48.54 t/s, tg_3s = 48.57 t/s 3.46.612.743 I slot print_timing: id 0 | task 8420 | n_gen = 439, tg = 48.52 t/s, tg_3s = 48.49 t/s 3.47.231.932 I slot print_timing: id 0 | task 8420 | prompt eval time = 685.81 ms / 299 tokens ( 2.29 ms per token, 435.98 tokens per second) 3.47.231.935 I slot print_timing: id 0 | task 8420 | eval time = 9646.19 ms / 469 tokens ( 20.61 ms per token, 48.52 tokens per second) 3.47.231.936 I slot print_timing: id 0 | task 8420 | total time = 10332.00 ms / 768 tokens 3.47.231.937 I slot print_timing: id 0 | task 8420 | graphs reused = 8398 3.47.231.937 I slot print_timing: id 0 | task 8420 | graph reallocs = 0 / 0 (same size) / (changed size) 3.47.231.961 I slot release: id 0 | task 8420 | stop processing: n_tokens = 767, truncated = 0 3.47.237.006 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 767, t_last = 328009221223 3.47.237.089 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 95.219 MiB) 3.47.249.751 I slot launch_slot_: id 0 | task 8892 | processing task, is_child = 0 3.48.451.396 I slot print_timing: id 0 | task 8892 | prompt eval time = 690.13 ms / 319 tokens ( 2.16 ms per token, 462.23 tokens per second) 3.48.451.402 I slot print_timing: id 0 | task 8892 | eval time = 511.51 ms / 26 tokens ( 20.46 ms per token, 48.87 tokens per second) 3.48.451.403 I slot print_timing: id 0 | task 8892 | total time = 1201.64 ms / 345 tokens 3.48.451.403 I slot print_timing: id 0 | task 8892 | graphs reused = 8422 3.48.451.404 I slot print_timing: id 0 | task 8892 | graph reallocs = 0 / 0 (same size) / (changed size) 3.48.451.434 I slot release: id 0 | task 8892 | stop processing: n_tokens = 344, truncated = 0 3.48.457.015 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 344, t_last = 328010440696 3.48.457.060 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 44.657 MiB) 3.48.468.024 I slot launch_slot_: id 0 | task 8921 | processing task, is_child = 0 3.50.020.702 I slot print_timing: id 0 | task 8921 | prompt eval time = 827.16 ms / 423 tokens ( 1.96 ms per token, 511.39 tokens per second) 3.50.020.707 I slot print_timing: id 0 | task 8921 | eval time = 725.51 ms / 36 tokens ( 20.73 ms per token, 48.24 tokens per second) 3.50.020.708 I slot print_timing: id 0 | task 8921 | total time = 1552.67 ms / 459 tokens 3.50.020.709 I slot print_timing: id 0 | task 8921 | graphs reused = 8456 3.50.020.709 I slot print_timing: id 0 | task 8921 | graph reallocs = 0 / 0 (same size) / (changed size) 3.50.020.741 I slot release: id 0 | task 8921 | stop processing: n_tokens = 458, truncated = 0 3.50.025.931 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 328012010003 3.50.025.999 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 71.731 MiB) 3.50.026.003 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 90.788 MiB) 3.50.038.250 I slot launch_slot_: id 0 | task 8960 | processing task, is_child = 0 3.51.358.840 I slot print_timing: id 0 | task 8960 | prompt eval time = 749.61 ms / 366 tokens ( 2.05 ms per token, 488.25 tokens per second) 3.51.358.843 I slot print_timing: id 0 | task 8960 | eval time = 570.97 ms / 29 tokens ( 20.39 ms per token, 49.04 tokens per second) 3.51.358.843 I slot print_timing: id 0 | task 8960 | total time = 1320.58 ms / 395 tokens 3.51.358.844 I slot print_timing: id 0 | task 8960 | graphs reused = 8483 3.51.358.844 I slot print_timing: id 0 | task 8960 | graph reallocs = 0 / 0 (same size) / (changed size) 3.51.358.866 I slot release: id 0 | task 8960 | stop processing: n_tokens = 394, truncated = 0 3.51.364.069 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 394, t_last = 328013348128 3.51.364.120 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 90.753 MiB) 3.51.364.123 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 62.132 MiB) 3.51.369.835 I slot launch_slot_: id 0 | task 8992 | processing task, is_child = 0 3.53.089.035 I slot print_timing: id 0 | task 8992 | prompt eval time = 1137.21 ms / 560 tokens ( 2.03 ms per token, 492.43 tokens per second) 3.53.089.040 I slot print_timing: id 0 | task 8992 | eval time = 581.98 ms / 29 tokens ( 20.79 ms per token, 48.11 tokens per second) 3.53.089.041 I slot print_timing: id 0 | task 8992 | total time = 1719.19 ms / 589 tokens 3.53.089.041 I slot print_timing: id 0 | task 8992 | graphs reused = 8510 3.53.089.042 I slot print_timing: id 0 | task 8992 | graph reallocs = 0 / 0 (same size) / (changed size) 3.53.089.078 I slot release: id 0 | task 8992 | stop processing: n_tokens = 588, truncated = 0 3.53.094.251 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 588, t_last = 328015078340 3.53.094.319 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.989 MiB) 3.53.094.322 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 125.246 MiB) 3.53.108.641 I slot launch_slot_: id 0 | task 9025 | processing task, is_child = 0 3.54.435.167 I slot print_timing: id 0 | task 9025 | prompt eval time = 747.12 ms / 366 tokens ( 2.04 ms per token, 489.88 tokens per second) 3.54.435.173 I slot print_timing: id 0 | task 9025 | eval time = 579.40 ms / 29 tokens ( 20.69 ms per token, 48.33 tokens per second) 3.54.435.174 I slot print_timing: id 0 | task 9025 | total time = 1326.51 ms / 395 tokens 3.54.435.179 I slot print_timing: id 0 | task 9025 | graphs reused = 8537 3.54.435.179 I slot print_timing: id 0 | task 9025 | graph reallocs = 0 / 0 (same size) / (changed size) 3.54.435.206 I slot release: id 0 | task 9025 | stop processing: n_tokens = 394, truncated = 0 3.54.440.567 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 394, t_last = 328016424468 3.54.440.619 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 53.271 MiB) 3.54.440.622 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.078 MiB) 3.54.447.934 I slot launch_slot_: id 0 | task 9057 | processing task, is_child = 0 3.55.874.508 I slot print_timing: id 0 | task 9057 | prompt eval time = 805.37 ms / 406 tokens ( 1.98 ms per token, 504.12 tokens per second) 3.55.874.515 I slot print_timing: id 0 | task 9057 | eval time = 621.20 ms / 31 tokens ( 20.71 ms per token, 48.29 tokens per second) 3.55.874.515 I slot print_timing: id 0 | task 9057 | total time = 1426.57 ms / 437 tokens 3.55.874.516 I slot print_timing: id 0 | task 9057 | graphs reused = 8566 3.55.874.517 I slot print_timing: id 0 | task 9057 | graph reallocs = 0 / 0 (same size) / (changed size) 3.55.874.543 I slot release: id 0 | task 9057 | stop processing: n_tokens = 436, truncated = 0 3.55.879.784 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 436, t_last = 328017863805 3.55.879.840 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 97.715 MiB) 3.55.889.648 I slot launch_slot_: id 0 | task 9091 | processing task, is_child = 0 3.57.497.312 I slot print_timing: id 0 | task 9091 | prompt eval time = 802.55 ms / 379 tokens ( 2.12 ms per token, 472.24 tokens per second) 3.57.497.321 I slot print_timing: id 0 | task 9091 | eval time = 805.10 ms / 40 tokens ( 20.64 ms per token, 48.44 tokens per second) 3.57.497.322 I slot print_timing: id 0 | task 9091 | total time = 1607.65 ms / 419 tokens 3.57.497.322 I slot print_timing: id 0 | task 9091 | graphs reused = 8604 3.57.497.323 I slot print_timing: id 0 | task 9091 | graph reallocs = 0 / 0 (same size) / (changed size) 3.57.497.352 I slot release: id 0 | task 9091 | stop processing: n_tokens = 418, truncated = 0 3.57.503.220 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 418, t_last = 328019486614 3.57.503.274 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 82.666 MiB) 3.57.503.277 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 64.909 MiB) 3.57.511.179 I slot launch_slot_: id 0 | task 9134 | processing task, is_child = 0 3.59.069.538 I slot print_timing: id 0 | task 9134 | prompt eval time = 976.40 ms / 487 tokens ( 2.00 ms per token, 498.77 tokens per second) 3.59.069.545 I slot print_timing: id 0 | task 9134 | eval time = 581.95 ms / 29 tokens ( 20.78 ms per token, 48.11 tokens per second) 3.59.069.545 I slot print_timing: id 0 | task 9134 | total time = 1558.35 ms / 516 tokens 3.59.069.546 I slot print_timing: id 0 | task 9134 | graphs reused = 8630 3.59.069.547 I slot print_timing: id 0 | task 9134 | graph reallocs = 0 / 0 (same size) / (changed size) 3.59.069.579 I slot release: id 0 | task 9134 | stop processing: n_tokens = 515, truncated = 0 3.59.075.927 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 515, t_last = 328021058841 3.59.075.985 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 64.839 MiB) 3.59.075.991 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 61.921 MiB) 3.59.075.993 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 52.884 MiB) 3.59.099.183 I slot launch_slot_: id 0 | task 9166 | processing task, is_child = 0 4.02.658.455 I slot print_timing: id 0 | task 9166 | prompt eval time = 1183.24 ms / 565 tokens ( 2.09 ms per token, 477.50 tokens per second) 4.02.658.461 I slot print_timing: id 0 | task 9166 | eval time = 2376.02 ms / 116 tokens ( 20.66 ms per token, 48.40 tokens per second) 4.02.658.461 I slot print_timing: id 0 | task 9166 | total time = 3559.26 ms / 681 tokens 4.02.658.462 I slot print_timing: id 0 | task 9166 | graphs reused = 8744 4.02.658.463 I slot print_timing: id 0 | task 9166 | graph reallocs = 0 / 0 (same size) / (changed size) 4.02.658.513 I slot release: id 0 | task 9166 | stop processing: n_tokens = 680, truncated = 0 4.02.663.295 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.153 (> 0.100 thold), f_keep = 0.044 4.02.663.374 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 64.698 MiB) 4.02.663.379 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 54.677 MiB) 4.02.663.381 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 53.306 MiB) 4.02.688.746 I slot launch_slot_: id 0 | task 9286 | processing task, is_child = 0 4.03.739.266 I slot print_timing: id 0 | task 9286 | prompt eval time = 461.69 ms / 196 tokens ( 2.36 ms per token, 424.53 tokens per second) 4.03.739.272 I slot print_timing: id 0 | task 9286 | eval time = 588.82 ms / 30 tokens ( 20.30 ms per token, 49.25 tokens per second) 4.03.739.273 I slot print_timing: id 0 | task 9286 | total time = 1050.51 ms / 226 tokens 4.03.739.273 I slot print_timing: id 0 | task 9286 | graphs reused = 8772 4.03.739.274 I slot print_timing: id 0 | task 9286 | graph reallocs = 0 / 0 (same size) / (changed size) 4.03.739.300 I slot release: id 0 | task 9286 | stop processing: n_tokens = 225, truncated = 0 4.03.743.431 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.140 (> 0.100 thold), f_keep = 0.133 4.03.743.467 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 66.562 MiB) 4.03.745.484 I slot launch_slot_: id 0 | task 9319 | processing task, is_child = 0 4.07.278.639 I slot print_timing: id 0 | task 9319 | n_gen = 149, tg = 49.16 t/s, tg_3s = 49.49 t/s 4.09.999.758 I slot print_timing: id 0 | task 9319 | prompt eval time = 522.63 ms / 214 tokens ( 2.44 ms per token, 409.47 tokens per second) 4.09.999.761 I slot print_timing: id 0 | task 9319 | eval time = 5731.64 ms / 281 tokens ( 20.47 ms per token, 48.85 tokens per second) 4.09.999.762 I slot print_timing: id 0 | task 9319 | total time = 6254.26 ms / 495 tokens 4.09.999.762 I slot print_timing: id 0 | task 9319 | graphs reused = 9050 4.09.999.763 I slot print_timing: id 0 | task 9319 | graph reallocs = 0 / 0 (same size) / (changed size) 4.09.999.783 I slot release: id 0 | task 9319 | stop processing: n_tokens = 494, truncated = 0 4.10.004.085 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.149 (> 0.100 thold), f_keep = 0.061 4.10.004.150 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 69.410 MiB) 4.10.004.155 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 74.227 MiB) 4.10.012.188 I slot launch_slot_: id 0 | task 9603 | processing task, is_child = 0 4.12.442.835 I slot print_timing: id 0 | task 9603 | prompt eval time = 521.84 ms / 201 tokens ( 2.60 ms per token, 385.17 tokens per second) 4.12.442.838 I slot print_timing: id 0 | task 9603 | eval time = 1908.79 ms / 95 tokens ( 20.31 ms per token, 49.25 tokens per second) 4.12.442.839 I slot print_timing: id 0 | task 9603 | total time = 2430.63 ms / 296 tokens 4.12.442.840 I slot print_timing: id 0 | task 9603 | graphs reused = 9142 4.12.442.841 I slot print_timing: id 0 | task 9603 | graph reallocs = 0 / 0 (same size) / (changed size) 4.12.442.860 I slot release: id 0 | task 9603 | stop processing: n_tokens = 295, truncated = 0 4.12.446.948 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.179 (> 0.100 thold), f_keep = 0.102 4.12.446.991 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 89.452 MiB) 4.12.449.465 I slot launch_slot_: id 0 | task 9701 | processing task, is_child = 0 4.14.671.627 I slot print_timing: id 0 | task 9701 | prompt eval time = 458.35 ms / 168 tokens ( 2.73 ms per token, 366.54 tokens per second) 4.14.671.633 I slot print_timing: id 0 | task 9701 | eval time = 1763.81 ms / 88 tokens ( 20.27 ms per token, 49.33 tokens per second) 4.14.671.634 I slot print_timing: id 0 | task 9701 | total time = 2222.15 ms / 256 tokens 4.14.671.635 I slot print_timing: id 0 | task 9701 | graphs reused = 9228 4.14.671.636 I slot print_timing: id 0 | task 9701 | graph reallocs = 0 / 0 (same size) / (changed size) 4.14.671.657 I slot release: id 0 | task 9701 | stop processing: n_tokens = 255, truncated = 0 4.14.676.136 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.129 (> 0.100 thold), f_keep = 0.118 4.14.676.177 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 81.681 MiB) 4.14.678.202 I slot launch_slot_: id 0 | task 9792 | processing task, is_child = 0 4.18.214.747 I slot print_timing: id 0 | task 9792 | n_gen = 149, tg = 49.17 t/s, tg_3s = 49.50 t/s 4.18.358.504 I slot print_timing: id 0 | task 9792 | prompt eval time = 526.46 ms / 232 tokens ( 2.27 ms per token, 440.68 tokens per second) 4.18.358.508 I slot print_timing: id 0 | task 9792 | eval time = 3153.83 ms / 156 tokens ( 20.35 ms per token, 49.15 tokens per second) 4.18.358.509 I slot print_timing: id 0 | task 9792 | total time = 3680.30 ms / 388 tokens 4.18.358.509 I slot print_timing: id 0 | task 9792 | graphs reused = 9381 4.18.358.510 I slot print_timing: id 0 | task 9792 | graph reallocs = 0 / 0 (same size) / (changed size) 4.18.358.534 I slot release: id 0 | task 9792 | stop processing: n_tokens = 387, truncated = 0 4.18.362.884 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.120 (> 0.100 thold), f_keep = 0.078 4.18.362.930 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 82.349 MiB) 4.18.369.416 I slot launch_slot_: id 0 | task 9951 | processing task, is_child = 0 4.21.612.471 I slot print_timing: id 0 | task 9951 | prompt eval time = 576.43 ms / 249 tokens ( 2.31 ms per token, 431.97 tokens per second) 4.21.612.477 I slot print_timing: id 0 | task 9951 | eval time = 2666.61 ms / 132 tokens ( 20.36 ms per token, 49.13 tokens per second) 4.21.612.477 I slot print_timing: id 0 | task 9951 | total time = 3243.04 ms / 381 tokens 4.21.612.478 I slot print_timing: id 0 | task 9951 | graphs reused = 9510 4.21.612.479 I slot print_timing: id 0 | task 9951 | graph reallocs = 0 / 0 (same size) / (changed size) 4.21.612.498 I slot release: id 0 | task 9951 | stop processing: n_tokens = 380, truncated = 0 4.21.617.123 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.106 (> 0.100 thold), f_keep = 0.089 4.21.617.177 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 69.480 MiB) 4.21.620.283 I slot launch_slot_: id 0 | task 10086 | processing task, is_child = 0 4.24.885.063 I slot print_timing: id 0 | task 10086 | prompt eval time = 634.67 ms / 320 tokens ( 1.98 ms per token, 504.20 tokens per second) 4.24.885.068 I slot print_timing: id 0 | task 10086 | eval time = 2630.10 ms / 129 tokens ( 20.55 ms per token, 48.67 tokens per second) 4.24.885.069 I slot print_timing: id 0 | task 10086 | total time = 3264.77 ms / 449 tokens 4.24.885.070 I slot print_timing: id 0 | task 10086 | graphs reused = 9637 4.24.885.075 I slot print_timing: id 0 | task 10086 | graph reallocs = 0 / 0 (same size) / (changed size) 4.24.885.104 I slot release: id 0 | task 10086 | stop processing: n_tokens = 448, truncated = 0 4.24.889.162 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.167 (> 0.100 thold), f_keep = 0.067 4.24.889.220 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 103.412 MiB) 4.24.892.885 I slot launch_slot_: id 0 | task 10218 | processing task, is_child = 0 4.28.323.024 I slot print_timing: id 0 | task 10218 | n_gen = 150, tg = 49.33 t/s, tg_3s = 49.66 t/s 4.31.261.470 I slot print_timing: id 0 | task 10218 | prompt eval time = 409.87 ms / 180 tokens ( 2.28 ms per token, 439.17 tokens per second) 4.31.261.475 I slot print_timing: id 0 | task 10218 | eval time = 5958.71 ms / 293 tokens ( 20.41 ms per token, 49.00 tokens per second) 4.31.261.476 I slot print_timing: id 0 | task 10218 | total time = 6368.57 ms / 473 tokens 4.31.261.477 I slot print_timing: id 0 | task 10218 | graphs reused = 9927 4.31.261.478 I slot print_timing: id 0 | task 10218 | graph reallocs = 0 / 0 (same size) / (changed size) 4.31.261.496 I slot release: id 0 | task 10218 | stop processing: n_tokens = 472, truncated = 0 4.31.265.675 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.163 (> 0.100 thold), f_keep = 0.064 4.31.265.735 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 67.722 MiB) 4.31.265.738 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 99.508 MiB) 4.31.273.553 I slot launch_slot_: id 0 | task 10514 | processing task, is_child = 0 4.34.736.830 I slot print_timing: id 0 | task 10514 | n_gen = 149, tg = 49.26 t/s, tg_3s = 49.60 t/s 4.37.756.742 I slot print_timing: id 0 | task 10514 | n_gen = 296, tg = 48.97 t/s, tg_3s = 48.68 t/s 4.40.757.207 I slot print_timing: id 0 | task 10514 | prompt eval time = 458.99 ms / 184 tokens ( 2.49 ms per token, 400.88 tokens per second) 4.40.757.210 I slot print_timing: id 0 | task 10514 | eval time = 9024.66 ms / 441 tokens ( 20.51 ms per token, 48.76 tokens per second) 4.40.757.211 I slot print_timing: id 0 | task 10514 | total time = 9483.64 ms / 625 tokens 4.40.757.212 I slot print_timing: id 0 | task 10514 | graphs reused = 10364 4.40.757.212 I slot print_timing: id 0 | task 10514 | graph reallocs = 0 / 0 (same size) / (changed size) 4.40.757.230 I slot release: id 0 | task 10514 | stop processing: n_tokens = 624, truncated = 0 4.40.761.766 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.128 (> 0.100 thold), f_keep = 0.048 4.40.761.835 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 67.406 MiB) 4.40.771.438 I slot launch_slot_: id 0 | task 10958 | processing task, is_child = 0 4.41.899.342 I slot print_timing: id 0 | task 10958 | prompt eval time = 516.31 ms / 235 tokens ( 2.20 ms per token, 455.15 tokens per second) 4.41.899.345 I slot print_timing: id 0 | task 10958 | eval time = 611.58 ms / 31 tokens ( 20.39 ms per token, 49.05 tokens per second) 4.41.899.347 I slot print_timing: id 0 | task 10958 | total time = 1127.89 ms / 266 tokens 4.41.899.347 I slot print_timing: id 0 | task 10958 | graphs reused = 10392 4.41.899.348 I slot print_timing: id 0 | task 10958 | graph reallocs = 0 / 0 (same size) / (changed size) 4.41.899.369 I slot release: id 0 | task 10958 | stop processing: n_tokens = 265, truncated = 0 4.41.903.713 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.104 (> 0.100 thold), f_keep = 0.113 4.41.903.753 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 59.389 MiB) 4.41.906.149 I slot launch_slot_: id 0 | task 10992 | processing task, is_child = 0 4.43.854.123 I slot print_timing: id 0 | task 10992 | prompt eval time = 632.72 ms / 289 tokens ( 2.19 ms per token, 456.76 tokens per second) 4.43.854.127 I slot print_timing: id 0 | task 10992 | eval time = 1315.24 ms / 65 tokens ( 20.55 ms per token, 48.66 tokens per second) 4.43.854.127 I slot print_timing: id 0 | task 10992 | total time = 1947.96 ms / 354 tokens 4.43.854.128 I slot print_timing: id 0 | task 10992 | graphs reused = 10455 4.43.854.129 I slot print_timing: id 0 | task 10992 | graph reallocs = 0 / 0 (same size) / (changed size) 4.43.854.156 I slot release: id 0 | task 10992 | stop processing: n_tokens = 353, truncated = 0 4.43.858.444 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.183 (> 0.100 thold), f_keep = 0.125 4.43.858.499 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 57.103 MiB) 4.43.858.807 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 67.828 MiB) 4.43.862.084 I slot launch_slot_: id 0 | task 11060 | processing task, is_child = 0 4.45.640.455 I slot print_timing: id 0 | task 11060 | prompt eval time = 516.93 ms / 241 tokens ( 2.14 ms per token, 466.21 tokens per second) 4.45.640.460 I slot print_timing: id 0 | task 11060 | eval time = 1261.43 ms / 63 tokens ( 20.35 ms per token, 49.15 tokens per second) 4.45.640.461 I slot print_timing: id 0 | task 11060 | total time = 1778.36 ms / 304 tokens 4.45.640.462 I slot print_timing: id 0 | task 11060 | graphs reused = 10515 4.45.640.462 I slot print_timing: id 0 | task 11060 | graph reallocs = 0 / 0 (same size) / (changed size) 4.45.640.482 I slot release: id 0 | task 11060 | stop processing: n_tokens = 303, truncated = 0 4.45.644.894 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.126 (> 0.100 thold), f_keep = 0.099 4.45.644.940 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 72.152 MiB) 4.45.647.384 I slot launch_slot_: id 0 | task 11126 | processing task, is_child = 0 4.49.173.297 I slot print_timing: id 0 | task 11126 | n_gen = 149, tg = 49.18 t/s, tg_3s = 49.51 t/s 4.52.182.963 I slot print_timing: id 0 | task 11126 | n_gen = 295, tg = 48.85 t/s, tg_3s = 48.51 t/s 4.52.430.326 I slot print_timing: id 0 | task 11126 | prompt eval time = 516.68 ms / 239 tokens ( 2.16 ms per token, 462.57 tokens per second) 4.52.430.329 I slot print_timing: id 0 | task 11126 | eval time = 6266.24 ms / 307 tokens ( 20.48 ms per token, 48.83 tokens per second) 4.52.430.329 I slot print_timing: id 0 | task 11126 | total time = 6782.93 ms / 546 tokens 4.52.430.330 I slot print_timing: id 0 | task 11126 | graphs reused = 10818 4.52.430.331 I slot print_timing: id 0 | task 11126 | graph reallocs = 0 / 0 (same size) / (changed size) 4.52.430.352 I slot release: id 0 | task 11126 | stop processing: n_tokens = 545, truncated = 0 4.52.434.587 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.110 (> 0.100 thold), f_keep = 0.055 4.52.434.649 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 57.490 MiB) 4.52.434.653 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 99.860 MiB) 4.52.442.975 I slot launch_slot_: id 0 | task 11436 | processing task, is_child = 0 4.56.078.899 I slot print_timing: id 0 | task 11436 | n_gen = 148, tg = 48.94 t/s, tg_3s = 49.28 t/s 4.59.091.031 I slot print_timing: id 0 | task 11436 | n_gen = 294, tg = 48.71 t/s, tg_3s = 48.47 t/s 5.02.102.561 I slot print_timing: id 0 | task 11436 | n_gen = 440, tg = 48.63 t/s, tg_3s = 48.48 t/s 5.05.120.332 I slot print_timing: id 0 | task 11436 | n_gen = 586, tg = 48.57 t/s, tg_3s = 48.38 t/s 5.07.891.874 I slot print_timing: id 0 | task 11436 | prompt eval time = 632.46 ms / 273 tokens ( 2.32 ms per token, 431.65 tokens per second) 5.07.891.877 I slot print_timing: id 0 | task 11436 | eval time = 14816.42 ms / 720 tokens ( 20.61 ms per token, 48.53 tokens per second) 5.07.891.878 I slot print_timing: id 0 | task 11436 | total time = 15448.88 ms / 993 tokens 5.07.891.878 I slot print_timing: id 0 | task 11436 | graphs reused = 11534 5.07.891.879 I slot print_timing: id 0 | task 11436 | graph reallocs = 0 / 0 (same size) / (changed size) 5.07.891.908 I slot release: id 0 | task 11436 | stop processing: n_tokens = 992, truncated = 0 5.07.896.037 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.142 (> 0.100 thold), f_keep = 0.030 5.07.896.132 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 44.973 MiB) 5.07.896.313 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 51.478 MiB) 5.07.906.027 I slot launch_slot_: id 0 | task 12159 | processing task, is_child = 0 5.09.027.425 I slot print_timing: id 0 | task 12159 | prompt eval time = 473.19 ms / 212 tokens ( 2.23 ms per token, 448.02 tokens per second) 5.09.027.430 I slot print_timing: id 0 | task 12159 | eval time = 648.18 ms / 33 tokens ( 20.26 ms per token, 49.37 tokens per second) 5.09.027.431 I slot print_timing: id 0 | task 12159 | total time = 1121.37 ms / 245 tokens 5.09.027.432 I slot print_timing: id 0 | task 12159 | graphs reused = 11565 5.09.027.432 I slot print_timing: id 0 | task 12159 | graph reallocs = 0 / 0 (same size) / (changed size) 5.09.027.451 I slot release: id 0 | task 12159 | stop processing: n_tokens = 244, truncated = 0 5.09.031.817 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.105 (> 0.100 thold), f_keep = 0.123 5.09.031.856 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 52.075 MiB) 5.09.034.093 I slot launch_slot_: id 0 | task 12195 | processing task, is_child = 0 5.12.612.672 I slot print_timing: id 0 | task 12195 | n_gen = 148, tg = 48.90 t/s, tg_3s = 49.23 t/s 5.15.416.716 I slot print_timing: id 0 | task 12195 | prompt eval time = 572.14 ms / 285 tokens ( 2.01 ms per token, 498.13 tokens per second) 5.15.416.719 I slot print_timing: id 0 | task 12195 | eval time = 5810.47 ms / 284 tokens ( 20.53 ms per token, 48.71 tokens per second) 5.15.416.720 I slot print_timing: id 0 | task 12195 | total time = 6382.61 ms / 569 tokens 5.15.416.721 I slot print_timing: id 0 | task 12195 | graphs reused = 11846 5.15.416.722 I slot print_timing: id 0 | task 12195 | graph reallocs = 0 / 0 (same size) / (changed size) 5.15.416.746 I slot release: id 0 | task 12195 | stop processing: n_tokens = 568, truncated = 0 5.15.421.282 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.157 (> 0.100 thold), f_keep = 0.053 5.15.421.349 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 52.884 MiB) 5.15.421.353 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 69.726 MiB) 5.15.430.714 I slot launch_slot_: id 0 | task 12482 | processing task, is_child = 0 5.16.572.688 I slot print_timing: id 0 | task 12482 | prompt eval time = 461.18 ms / 191 tokens ( 2.41 ms per token, 414.15 tokens per second) 5.16.572.694 I slot print_timing: id 0 | task 12482 | eval time = 680.78 ms / 34 tokens ( 20.63 ms per token, 48.47 tokens per second) 5.16.572.695 I slot print_timing: id 0 | task 12482 | total time = 1141.96 ms / 225 tokens 5.16.572.696 I slot print_timing: id 0 | task 12482 | graphs reused = 11878 5.16.572.696 I slot print_timing: id 0 | task 12482 | graph reallocs = 0 / 0 (same size) / (changed size) 5.16.572.715 I slot release: id 0 | task 12482 | stop processing: n_tokens = 224, truncated = 0 5.16.576.591 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.134 5.16.576.630 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 115.928 MiB) 5.16.578.711 I slot launch_slot_: id 0 | task 12519 | processing task, is_child = 0 5.20.003.188 I slot print_timing: id 0 | task 12519 | n_gen = 149, tg = 49.11 t/s, tg_3s = 49.44 t/s 5.21.246.728 I slot print_timing: id 0 | task 12519 | prompt eval time = 410.67 ms / 171 tokens ( 2.40 ms per token, 416.39 tokens per second) 5.21.246.733 I slot print_timing: id 0 | task 12519 | eval time = 4257.34 ms / 210 tokens ( 20.37 ms per token, 49.09 tokens per second) 5.21.246.733 I slot print_timing: id 0 | task 12519 | total time = 4668.01 ms / 381 tokens 5.21.246.734 I slot print_timing: id 0 | task 12519 | graphs reused = 12085 5.21.246.735 I slot print_timing: id 0 | task 12519 | graph reallocs = 0 / 0 (same size) / (changed size) 5.21.246.753 I slot release: id 0 | task 12519 | stop processing: n_tokens = 380, truncated = 0 5.21.251.110 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.115 (> 0.100 thold), f_keep = 0.079 5.21.251.158 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 52.638 MiB) 5.21.253.741 I slot launch_slot_: id 0 | task 12732 | processing task, is_child = 0 5.24.073.782 I slot print_timing: id 0 | task 12732 | prompt eval time = 577.73 ms / 260 tokens ( 2.22 ms per token, 450.04 tokens per second) 5.24.073.785 I slot print_timing: id 0 | task 12732 | eval time = 2242.30 ms / 111 tokens ( 20.38 ms per token, 49.06 tokens per second) 5.24.073.786 I slot print_timing: id 0 | task 12732 | total time = 2820.03 ms / 371 tokens 5.24.073.787 I slot print_timing: id 0 | task 12732 | graphs reused = 12194 5.24.073.787 I slot print_timing: id 0 | task 12732 | graph reallocs = 0 / 0 (same size) / (changed size) 5.24.073.813 I slot release: id 0 | task 12732 | stop processing: n_tokens = 370, truncated = 0 5.24.078.080 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.147 (> 0.100 thold), f_keep = 0.081 5.24.078.132 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 62.905 MiB) 5.24.080.996 I slot launch_slot_: id 0 | task 12846 | processing task, is_child = 0 5.27.563.504 I slot print_timing: id 0 | task 12846 | n_gen = 150, tg = 49.33 t/s, tg_3s = 49.66 t/s 5.30.280.242 I slot print_timing: id 0 | task 12846 | prompt eval time = 462.10 ms / 204 tokens ( 2.27 ms per token, 441.46 tokens per second) 5.30.280.245 I slot print_timing: id 0 | task 12846 | eval time = 5737.14 ms / 282 tokens ( 20.42 ms per token, 48.98 tokens per second) 5.30.280.246 I slot print_timing: id 0 | task 12846 | total time = 6199.24 ms / 486 tokens 5.30.280.246 I slot print_timing: id 0 | task 12846 | graphs reused = 12473 5.30.280.247 I slot print_timing: id 0 | task 12846 | graph reallocs = 0 / 0 (same size) / (changed size) 5.30.280.274 I slot release: id 0 | task 12846 | stop processing: n_tokens = 485, truncated = 0 5.30.284.698 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.101 (> 0.100 thold), f_keep = 0.062 5.30.284.755 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 81.787 MiB) 5.30.284.759 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 83.931 MiB) 5.30.292.649 I slot launch_slot_: id 0 | task 13131 | processing task, is_child = 0 5.33.929.987 I slot print_timing: id 0 | task 13131 | n_gen = 147, tg = 48.45 t/s, tg_3s = 48.78 t/s 5.35.169.761 I slot print_timing: id 0 | task 13131 | prompt eval time = 623.84 ms / 296 tokens ( 2.11 ms per token, 474.48 tokens per second) 5.35.169.768 I slot print_timing: id 0 | task 13131 | eval time = 4253.26 ms / 207 tokens ( 20.65 ms per token, 48.43 tokens per second) 5.35.169.769 I slot print_timing: id 0 | task 13131 | total time = 4877.10 ms / 503 tokens 5.35.169.770 I slot print_timing: id 0 | task 13131 | graphs reused = 12678 5.35.169.770 I slot print_timing: id 0 | task 13131 | graph reallocs = 0 / 0 (same size) / (changed size) 5.35.169.794 I slot release: id 0 | task 13131 | stop processing: n_tokens = 502, truncated = 0 5.35.174.056 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.131 (> 0.100 thold), f_keep = 0.062 5.35.174.117 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 56.787 MiB) 5.35.182.138 I slot launch_slot_: id 0 | task 13341 | processing task, is_child = 0 5.38.713.641 I slot print_timing: id 0 | task 13341 | n_gen = 149, tg = 49.10 t/s, tg_3s = 49.44 t/s 5.41.723.912 I slot print_timing: id 0 | task 13341 | n_gen = 295, tg = 48.80 t/s, tg_3s = 48.50 t/s 5.44.464.288 I slot print_timing: id 0 | task 13341 | prompt eval time = 517.53 ms / 236 tokens ( 2.19 ms per token, 456.01 tokens per second) 5.44.464.294 I slot print_timing: id 0 | task 13341 | eval time = 8764.61 ms / 428 tokens ( 20.53 ms per token, 48.72 tokens per second) 5.44.464.295 I slot print_timing: id 0 | task 13341 | total time = 9282.14 ms / 664 tokens 5.44.464.295 I slot print_timing: id 0 | task 13341 | graphs reused = 13102 5.44.464.296 I slot print_timing: id 0 | task 13341 | graph reallocs = 0 / 0 (same size) / (changed size) 5.44.464.316 I slot release: id 0 | task 13341 | stop processing: n_tokens = 663, truncated = 0 5.44.468.774 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.102 (> 0.100 thold), f_keep = 0.045 5.44.468.845 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 60.092 MiB) 5.44.468.849 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 74.086 MiB) 5.44.476.970 I slot launch_slot_: id 0 | task 13772 | processing task, is_child = 0 5.46.889.086 I slot print_timing: id 0 | task 13772 | prompt eval time = 634.97 ms / 294 tokens ( 2.16 ms per token, 463.01 tokens per second) 5.46.889.092 I slot print_timing: id 0 | task 13772 | eval time = 1777.13 ms / 88 tokens ( 20.43 ms per token, 48.96 tokens per second) 5.46.889.093 I slot print_timing: id 0 | task 13772 | total time = 2412.11 ms / 382 tokens 5.46.889.094 I slot print_timing: id 0 | task 13772 | graphs reused = 13188 5.46.889.094 I slot print_timing: id 0 | task 13772 | graph reallocs = 0 / 0 (same size) / (changed size) 5.46.889.120 I slot release: id 0 | task 13772 | stop processing: n_tokens = 381, truncated = 0 5.46.893.684 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.103 (> 0.100 thold), f_keep = 0.079 5.46.893.736 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 56.541 MiB) 5.46.893.740 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 76.337 MiB) 5.46.899.881 I slot launch_slot_: id 0 | task 13863 | processing task, is_child = 0 5.50.536.487 I slot print_timing: id 0 | task 13863 | n_gen = 148, tg = 48.78 t/s, tg_3s = 49.11 t/s 5.53.117.591 I slot print_timing: id 0 | task 13863 | prompt eval time = 623.13 ms / 291 tokens ( 2.14 ms per token, 467.00 tokens per second) 5.53.117.594 I slot print_timing: id 0 | task 13863 | eval time = 5594.57 ms / 273 tokens ( 20.57 ms per token, 48.62 tokens per second) 5.53.117.595 I slot print_timing: id 0 | task 13863 | total time = 6217.70 ms / 564 tokens 5.53.117.596 I slot print_timing: id 0 | task 13863 | graphs reused = 13458 5.53.117.597 I slot print_timing: id 0 | task 13863 | graph reallocs = 0 / 0 (same size) / (changed size) 5.53.117.626 I slot release: id 0 | task 13863 | stop processing: n_tokens = 563, truncated = 0 5.53.122.338 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.105 (> 0.100 thold), f_keep = 0.053 5.53.122.408 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 59.635 MiB) 5.53.122.412 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 111.533 MiB) 5.53.130.480 I slot launch_slot_: id 0 | task 14139 | processing task, is_child = 0 5.56.775.158 I slot print_timing: id 0 | task 14139 | n_gen = 148, tg = 48.83 t/s, tg_3s = 49.16 t/s 5.59.788.715 I slot print_timing: id 0 | task 14139 | n_gen = 294, tg = 48.64 t/s, tg_3s = 48.45 t/s 6.02.803.140 I slot print_timing: id 0 | task 14139 | n_gen = 440, tg = 48.57 t/s, tg_3s = 48.43 t/s 6.05.811.525 I slot print_timing: id 0 | task 14139 | n_gen = 585, tg = 48.48 t/s, tg_3s = 48.20 t/s 6.06.286.889 I slot print_timing: id 0 | task 14139 | prompt eval time = 634.11 ms / 287 tokens ( 2.21 ms per token, 452.61 tokens per second) 6.06.286.892 I slot print_timing: id 0 | task 14139 | eval time = 12522.29 ms / 608 tokens ( 20.63 ms per token, 48.47 tokens per second) 6.06.286.893 I slot print_timing: id 0 | task 14139 | total time = 13156.40 ms / 895 tokens 6.06.286.894 I slot print_timing: id 0 | task 14139 | graphs reused = 14062 6.06.286.894 I slot print_timing: id 0 | task 14139 | graph reallocs = 0 / 0 (same size) / (changed size) 6.06.286.919 I slot release: id 0 | task 14139 | stop processing: n_tokens = 894, truncated = 0 6.06.291.242 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.123 (> 0.100 thold), f_keep = 0.034 6.06.291.322 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 91.350 MiB) 6.06.300.410 I slot launch_slot_: id 0 | task 14750 | processing task, is_child = 0 6.09.712.595 I slot print_timing: id 0 | task 14750 | prompt eval time = 517.03 ms / 243 tokens ( 2.13 ms per token, 469.99 tokens per second) 6.09.712.598 I slot print_timing: id 0 | task 14750 | eval time = 2895.15 ms / 143 tokens ( 20.39 ms per token, 49.05 tokens per second) 6.09.712.599 I slot print_timing: id 0 | task 14750 | total time = 3412.18 ms / 386 tokens 6.09.712.599 I slot print_timing: id 0 | task 14750 | graphs reused = 14202 6.09.712.600 I slot print_timing: id 0 | task 14750 | graph reallocs = 0 / 0 (same size) / (changed size) 6.09.712.624 I slot release: id 0 | task 14750 | stop processing: n_tokens = 385, truncated = 0 6.09.716.867 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.166 (> 0.100 thold), f_keep = 0.078 6.09.716.923 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 63.995 MiB) 6.09.719.693 I slot launch_slot_: id 0 | task 14896 | processing task, is_child = 0 6.13.199.484 I slot print_timing: id 0 | task 14896 | n_gen = 150, tg = 49.33 t/s, tg_3s = 49.66 t/s 6.16.218.148 I slot print_timing: id 0 | task 14896 | n_gen = 297, tg = 49.01 t/s, tg_3s = 48.70 t/s 6.19.232.261 I slot print_timing: id 0 | task 14896 | n_gen = 443, tg = 48.82 t/s, tg_3s = 48.44 t/s 6.22.248.820 I slot print_timing: id 0 | task 14896 | n_gen = 589, tg = 48.72 t/s, tg_3s = 48.40 t/s 6.25.267.003 I slot print_timing: id 0 | task 14896 | n_gen = 735, tg = 48.65 t/s, tg_3s = 48.37 t/s 6.28.278.243 I slot print_timing: id 0 | task 14896 | n_gen = 880, tg = 48.57 t/s, tg_3s = 48.15 t/s 6.28.507.597 I slot print_timing: id 0 | task 14896 | prompt eval time = 459.41 ms / 181 tokens ( 2.54 ms per token, 393.98 tokens per second) 6.28.507.600 I slot print_timing: id 0 | task 14896 | eval time = 18328.49 ms / 891 tokens ( 20.59 ms per token, 48.56 tokens per second) 6.28.507.601 I slot print_timing: id 0 | task 14896 | total time = 18787.90 ms / 1072 tokens 6.28.507.602 I slot print_timing: id 0 | task 14896 | graphs reused = 15087 6.28.507.602 I slot print_timing: id 0 | task 14896 | graph reallocs = 0 / 0 (same size) / (changed size) 6.28.507.626 I slot release: id 0 | task 14896 | stop processing: n_tokens = 1071, truncated = 0 6.28.511.743 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.113 (> 0.100 thold), f_keep = 0.028 6.28.511.847 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.183 MiB) 6.28.511.851 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 71.028 MiB) 6.28.521.216 I slot launch_slot_: id 0 | task 15790 | processing task, is_child = 0 6.30.210.855 I slot print_timing: id 0 | task 15790 | prompt eval time = 569.86 ms / 265 tokens ( 2.15 ms per token, 465.03 tokens per second) 6.30.210.861 I slot print_timing: id 0 | task 15790 | eval time = 1119.77 ms / 56 tokens ( 20.36 ms per token, 49.12 tokens per second) 6.30.210.862 I slot print_timing: id 0 | task 15790 | total time = 1689.63 ms / 321 tokens 6.30.210.862 I slot print_timing: id 0 | task 15790 | graphs reused = 15141 6.30.210.863 I slot print_timing: id 0 | task 15790 | graph reallocs = 0 / 0 (same size) / (changed size) 6.30.210.886 I slot release: id 0 | task 15790 | stop processing: n_tokens = 320, truncated = 0 6.30.215.148 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.197 (> 0.100 thold), f_keep = 0.094 6.30.215.196 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 79.747 MiB) 6.30.221.034 I slot launch_slot_: id 0 | task 15849 | processing task, is_child = 0 6.33.630.818 I slot print_timing: id 0 | task 15849 | n_gen = 144, tg = 47.61 t/s, tg_3s = 47.95 t/s 6.36.642.030 I slot print_timing: id 0 | task 15849 | n_gen = 291, tg = 48.22 t/s, tg_3s = 48.82 t/s 6.39.647.037 I slot print_timing: id 0 | task 15849 | n_gen = 436, tg = 48.23 t/s, tg_3s = 48.25 t/s 6.42.665.779 I slot print_timing: id 0 | task 15849 | n_gen = 582, tg = 48.26 t/s, tg_3s = 48.36 t/s 6.45.667.557 I slot print_timing: id 0 | task 15849 | n_gen = 727, tg = 48.27 t/s, tg_3s = 48.30 t/s 6.48.670.727 I slot print_timing: id 0 | task 15849 | n_gen = 872, tg = 48.27 t/s, tg_3s = 48.28 t/s 6.51.681.117 I slot print_timing: id 0 | task 15849 | n_gen = 1017, tg = 48.26 t/s, tg_3s = 48.17 t/s 6.51.826.536 I slot print_timing: id 0 | task 15849 | prompt eval time = 406.37 ms / 152 tokens ( 2.67 ms per token, 374.04 tokens per second) 6.51.826.546 I slot print_timing: id 0 | task 15849 | eval time = 21199.12 ms / 1024 tokens ( 20.72 ms per token, 48.26 tokens per second) 6.51.826.546 I slot print_timing: id 0 | task 15849 | total time = 21605.49 ms / 1176 tokens 6.51.826.547 I slot print_timing: id 0 | task 15849 | graphs reused = 16159 6.51.826.548 I slot print_timing: id 0 | task 15849 | graph reallocs = 0 / 0 (same size) / (changed size) 6.51.826.570 I slot release: id 0 | task 15849 | stop processing: n_tokens = 1175, truncated = 0 6.51.830.909 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.158 (> 0.100 thold), f_keep = 0.026 6.51.831.011 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 115.400 MiB) 6.51.840.447 I slot launch_slot_: id 0 | task 16876 | processing task, is_child = 0 6.53.376.466 I slot print_timing: id 0 | task 16876 | prompt eval time = 461.00 ms / 190 tokens ( 2.43 ms per token, 412.15 tokens per second) 6.53.376.472 I slot print_timing: id 0 | task 16876 | eval time = 1075.01 ms / 54 tokens ( 20.28 ms per token, 49.30 tokens per second) 6.53.376.473 I slot print_timing: id 0 | task 16876 | total time = 1536.01 ms / 244 tokens 6.53.376.473 I slot print_timing: id 0 | task 16876 | graphs reused = 16211 6.53.376.474 I slot print_timing: id 0 | task 16876 | graph reallocs = 0 / 0 (same size) / (changed size) 6.53.376.492 I slot release: id 0 | task 16876 | stop processing: n_tokens = 243, truncated = 0 6.53.380.849 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.117 (> 0.100 thold), f_keep = 0.123 6.53.380.891 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 154.078 MiB) 6.53.382.957 I slot launch_slot_: id 0 | task 16933 | processing task, is_child = 0 6.55.048.516 I slot print_timing: id 0 | task 16933 | prompt eval time = 576.62 ms / 256 tokens ( 2.25 ms per token, 443.97 tokens per second) 6.55.048.522 I slot print_timing: id 0 | task 16933 | eval time = 1088.93 ms / 54 tokens ( 20.55 ms per token, 48.67 tokens per second) 6.55.048.523 I slot print_timing: id 0 | task 16933 | total time = 1665.55 ms / 310 tokens 6.55.048.524 I slot print_timing: id 0 | task 16933 | graphs reused = 16263 6.55.048.524 I slot print_timing: id 0 | task 16933 | graph reallocs = 0 / 0 (same size) / (changed size) 6.55.048.543 I slot release: id 0 | task 16933 | stop processing: n_tokens = 309, truncated = 0 6.55.052.970 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.114 (> 0.100 thold), f_keep = 0.097 6.55.055.631 I slot launch_slot_: id 0 | task 16990 | processing task, is_child = 0 6.56.389.733 I slot print_timing: id 0 | task 16990 | prompt eval time = 579.79 ms / 264 tokens ( 2.20 ms per token, 455.33 tokens per second) 6.56.389.739 I slot print_timing: id 0 | task 16990 | eval time = 754.30 ms / 38 tokens ( 20.39 ms per token, 49.05 tokens per second) 6.56.389.741 I slot print_timing: id 0 | task 16990 | total time = 1334.10 ms / 302 tokens 6.56.389.741 I slot print_timing: id 0 | task 16990 | graphs reused = 16299 6.56.389.742 I slot print_timing: id 0 | task 16990 | graph reallocs = 0 / 0 (same size) / (changed size) 6.56.389.761 I slot release: id 0 | task 16990 | stop processing: n_tokens = 301, truncated = 0 6.56.394.277 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.104 (> 0.100 thold), f_keep = 0.100 6.56.394.319 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 159.984 MiB) 6.56.396.944 I slot launch_slot_: id 0 | task 17031 | processing task, is_child = 0 7.00.039.912 I slot print_timing: id 0 | task 17031 | n_gen = 148, tg = 48.81 t/s, tg_3s = 49.15 t/s 7.03.055.650 I slot print_timing: id 0 | task 17031 | n_gen = 294, tg = 48.61 t/s, tg_3s = 48.41 t/s 7.06.073.582 I slot print_timing: id 0 | task 17031 | n_gen = 440, tg = 48.53 t/s, tg_3s = 48.38 t/s 7.08.865.470 I slot print_timing: id 0 | task 17031 | prompt eval time = 631.55 ms / 289 tokens ( 2.19 ms per token, 457.60 tokens per second) 7.08.865.476 I slot print_timing: id 0 | task 17031 | eval time = 11836.97 ms / 575 tokens ( 20.62 ms per token, 48.49 tokens per second) 7.08.865.477 I slot print_timing: id 0 | task 17031 | total time = 12468.52 ms / 864 tokens 7.08.865.477 I slot print_timing: id 0 | task 17031 | graphs reused = 16870 7.08.865.478 I slot print_timing: id 0 | task 17031 | graph reallocs = 0 / 0 (same size) / (changed size) 7.08.865.500 I slot release: id 0 | task 17031 | stop processing: n_tokens = 863, truncated = 0 7.08.870.432 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.102 (> 0.100 thold), f_keep = 0.035 7.08.870.517 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 146.518 MiB) 7.08.879.736 I slot launch_slot_: id 0 | task 17609 | processing task, is_child = 0 7.10.229.494 I slot print_timing: id 0 | task 17609 | prompt eval time = 632.88 ms / 294 tokens ( 2.15 ms per token, 464.54 tokens per second) 7.10.229.500 I slot print_timing: id 0 | task 17609 | eval time = 716.87 ms / 36 tokens ( 20.48 ms per token, 48.82 tokens per second) 7.10.229.500 I slot print_timing: id 0 | task 17609 | total time = 1349.75 ms / 330 tokens 7.10.229.501 I slot print_timing: id 0 | task 17609 | graphs reused = 16904 7.10.229.502 I slot print_timing: id 0 | task 17609 | graph reallocs = 0 / 0 (same size) / (changed size) 7.10.229.522 I slot release: id 0 | task 17609 | stop processing: n_tokens = 329, truncated = 0 7.10.233.951 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.103 (> 0.100 thold), f_keep = 0.091 7.10.233.995 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 100.141 MiB) 7.10.236.840 I slot launch_slot_: id 0 | task 17648 | processing task, is_child = 0 7.12.236.924 I slot print_timing: id 0 | task 17648 | prompt eval time = 632.45 ms / 292 tokens ( 2.17 ms per token, 461.70 tokens per second) 7.12.236.929 I slot print_timing: id 0 | task 17648 | eval time = 1367.62 ms / 68 tokens ( 20.41 ms per token, 48.99 tokens per second) 7.12.236.930 I slot print_timing: id 0 | task 17648 | total time = 2000.07 ms / 360 tokens 7.12.236.931 I slot print_timing: id 0 | task 17648 | graphs reused = 16970 7.12.236.931 I slot print_timing: id 0 | task 17648 | graph reallocs = 0 / 0 (same size) / (changed size) 7.12.236.952 I slot release: id 0 | task 17648 | stop processing: n_tokens = 359, truncated = 0 7.12.241.439 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.122 (> 0.100 thold), f_keep = 0.084 7.12.241.498 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 153.832 MiB) 7.12.244.456 I slot launch_slot_: id 0 | task 17719 | processing task, is_child = 0 7.15.040.630 I slot print_timing: id 0 | task 17719 | prompt eval time = 527.82 ms / 245 tokens ( 2.15 ms per token, 464.18 tokens per second) 7.15.040.633 I slot print_timing: id 0 | task 17719 | eval time = 2268.35 ms / 112 tokens ( 20.44 ms per token, 48.93 tokens per second) 7.15.040.634 I slot print_timing: id 0 | task 17719 | total time = 2796.16 ms / 357 tokens 7.15.040.635 I slot print_timing: id 0 | task 17719 | graphs reused = 17079 7.15.040.635 I slot print_timing: id 0 | task 17719 | graph reallocs = 0 / 0 (same size) / (changed size) 7.15.040.662 I slot release: id 0 | task 17719 | stop processing: n_tokens = 356, truncated = 0 7.15.044.826 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.169 (> 0.100 thold), f_keep = 0.084 7.15.047.660 I slot launch_slot_: id 0 | task 17834 | processing task, is_child = 0 7.18.351.265 I slot print_timing: id 0 | task 17834 | prompt eval time = 411.44 ms / 178 tokens ( 2.31 ms per token, 432.63 tokens per second) 7.18.351.268 I slot print_timing: id 0 | task 17834 | eval time = 2892.15 ms / 144 tokens ( 20.22 ms per token, 49.44 tokens per second) 7.18.351.269 I slot print_timing: id 0 | task 17834 | total time = 3303.59 ms / 322 tokens 7.18.351.269 I slot print_timing: id 0 | task 17834 | graphs reused = 17220 7.18.351.270 I slot print_timing: id 0 | task 17834 | graph reallocs = 0 / 0 (same size) / (changed size) 7.18.351.288 I slot release: id 0 | task 17834 | stop processing: n_tokens = 321, truncated = 0 7.18.356.415 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 321, t_last = 328220340550 7.18.356.462 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 137.446 MiB) 7.18.358.912 I slot launch_slot_: id 0 | task 17981 | processing task, is_child = 0 7.22.117.593 I slot print_timing: id 0 | task 17981 | n_gen = 142, tg = 46.79 t/s, tg_3s = 47.12 t/s 7.24.687.334 I slot print_timing: id 0 | task 17981 | prompt eval time = 745.28 ms / 355 tokens ( 2.10 ms per token, 476.33 tokens per second) 7.24.687.339 I slot print_timing: id 0 | task 17981 | eval time = 5583.12 ms / 264 tokens ( 21.23 ms per token, 47.11 tokens per second) 7.24.687.339 I slot print_timing: id 0 | task 17981 | total time = 6328.41 ms / 619 tokens 7.24.687.340 I slot print_timing: id 0 | task 17981 | graphs reused = 17481 7.24.687.341 I slot print_timing: id 0 | task 17981 | graph reallocs = 0 / 0 (same size) / (changed size) 7.24.687.377 I slot release: id 0 | task 17981 | stop processing: n_tokens = 618, truncated = 0 7.24.694.183 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 618, t_last = 328226676639 7.24.694.257 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.469 MiB) 7.24.703.728 I slot launch_slot_: id 0 | task 18248 | processing task, is_child = 0 7.28.896.103 I slot print_timing: id 0 | task 18248 | n_gen = 147, tg = 48.35 t/s, tg_3s = 48.68 t/s 7.31.914.574 I slot print_timing: id 0 | task 18248 | n_gen = 293, tg = 48.36 t/s, tg_3s = 48.37 t/s 7.34.918.715 I slot print_timing: id 0 | task 18248 | n_gen = 438, tg = 48.33 t/s, tg_3s = 48.27 t/s 7.37.930.255 I slot print_timing: id 0 | task 18248 | n_gen = 583, tg = 48.28 t/s, tg_3s = 48.15 t/s 7.40.944.543 I slot print_timing: id 0 | task 18248 | n_gen = 728, tg = 48.25 t/s, tg_3s = 48.10 t/s 7.41.796.203 I slot print_timing: id 0 | task 18248 | prompt eval time = 1172.82 ms / 567 tokens ( 2.07 ms per token, 483.45 tokens per second) 7.41.796.209 I slot print_timing: id 0 | task 18248 | eval time = 15919.64 ms / 769 tokens ( 20.73 ms per token, 48.24 tokens per second) 7.41.796.210 I slot print_timing: id 0 | task 18248 | total time = 17092.46 ms / 1336 tokens 7.41.796.210 I slot print_timing: id 0 | task 18248 | graphs reused = 18245 7.41.796.211 I slot print_timing: id 0 | task 18248 | graph reallocs = 0 / 0 (same size) / (changed size) 7.41.796.246 I slot release: id 0 | task 18248 | stop processing: n_tokens = 1335, truncated = 0 7.41.802.137 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1335, t_last = 328243785509 7.41.802.243 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.626 MiB) 7.41.802.246 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.109 MiB) 7.41.814.763 I slot launch_slot_: id 0 | task 19021 | processing task, is_child = 0 7.45.799.330 I slot print_timing: id 0 | task 19021 | n_gen = 147, tg = 48.34 t/s, tg_3s = 48.67 t/s 7.48.812.857 I slot print_timing: id 0 | task 19021 | n_gen = 293, tg = 48.39 t/s, tg_3s = 48.45 t/s 7.49.619.521 I slot print_timing: id 0 | task 19021 | prompt eval time = 964.14 ms / 473 tokens ( 2.04 ms per token, 490.59 tokens per second) 7.49.619.526 I slot print_timing: id 0 | task 19021 | eval time = 6840.61 ms / 332 tokens ( 20.67 ms per token, 48.39 tokens per second) 7.49.619.527 I slot print_timing: id 0 | task 19021 | total time = 7804.75 ms / 805 tokens 7.49.619.528 I slot print_timing: id 0 | task 19021 | graphs reused = 18573 7.49.619.529 I slot print_timing: id 0 | task 19021 | graph reallocs = 0 / 0 (same size) / (changed size) 7.49.619.564 I slot release: id 0 | task 19021 | stop processing: n_tokens = 804, truncated = 0 7.49.624.995 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 804, t_last = 328251608826 7.49.625.074 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.210 MiB) 7.49.630.101 I slot launch_slot_: id 0 | task 19356 | processing task, is_child = 0 7.53.447.012 I slot print_timing: id 0 | task 19356 | n_gen = 147, tg = 48.43 t/s, tg_3s = 48.76 t/s 7.56.462.301 I slot print_timing: id 0 | task 19356 | n_gen = 293, tg = 48.42 t/s, tg_3s = 48.42 t/s 7.59.478.295 I slot print_timing: id 0 | task 19356 | n_gen = 439, tg = 48.42 t/s, tg_3s = 48.41 t/s 8.02.480.492 I slot print_timing: id 0 | task 19356 | n_gen = 584, tg = 48.39 t/s, tg_3s = 48.30 t/s 8.05.483.618 I slot print_timing: id 0 | task 19356 | n_gen = 728, tg = 48.30 t/s, tg_3s = 47.95 t/s 8.08.491.558 I slot print_timing: id 0 | task 19356 | n_gen = 873, tg = 48.28 t/s, tg_3s = 48.21 t/s 8.10.072.224 I slot print_timing: id 0 | task 19356 | prompt eval time = 801.99 ms / 399 tokens ( 2.01 ms per token, 497.51 tokens per second) 8.10.072.227 I slot print_timing: id 0 | task 19356 | eval time = 19640.12 ms / 949 tokens ( 20.72 ms per token, 48.27 tokens per second) 8.10.072.228 I slot print_timing: id 0 | task 19356 | total time = 20442.11 ms / 1348 tokens 8.10.072.229 I slot print_timing: id 0 | task 19356 | graphs reused = 19516 8.10.072.229 I slot print_timing: id 0 | task 19356 | graph reallocs = 0 / 0 (same size) / (changed size) 8.10.072.259 I slot release: id 0 | task 19356 | stop processing: n_tokens = 1347, truncated = 0 8.10.077.238 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1347, t_last = 328272061521 8.10.077.351 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 87.201 MiB) 8.10.088.521 I slot launch_slot_: id 0 | task 20308 | processing task, is_child = 0 8.13.795.814 I slot print_timing: id 0 | task 20308 | n_gen = 148, tg = 48.69 t/s, tg_3s = 49.02 t/s 8.15.364.389 I slot print_timing: id 0 | task 20308 | prompt eval time = 688.41 ms / 312 tokens ( 2.21 ms per token, 453.22 tokens per second) 8.15.364.392 I slot print_timing: id 0 | task 20308 | eval time = 4587.44 ms / 224 tokens ( 20.57 ms per token, 48.61 tokens per second) 8.15.364.393 I slot print_timing: id 0 | task 20308 | total time = 5275.85 ms / 536 tokens 8.15.364.394 I slot print_timing: id 0 | task 20308 | graphs reused = 19737 8.15.364.394 I slot print_timing: id 0 | task 20308 | graph reallocs = 0 / 0 (same size) / (changed size) 8.15.364.427 I slot release: id 0 | task 20308 | stop processing: n_tokens = 535, truncated = 0 8.15.370.493 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 535, t_last = 328277353689 8.15.370.564 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 121.413 MiB) 8.15.370.568 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 99.261 MiB) 8.15.374.379 I slot launch_slot_: id 0 | task 20535 | processing task, is_child = 0 8.19.558.056 I slot print_timing: id 0 | task 20535 | n_gen = 147, tg = 48.35 t/s, tg_3s = 48.68 t/s 8.21.234.008 I slot print_timing: id 0 | task 20535 | prompt eval time = 1164.03 ms / 561 tokens ( 2.07 ms per token, 481.95 tokens per second) 8.21.234.010 I slot print_timing: id 0 | task 20535 | eval time = 4695.58 ms / 228 tokens ( 20.69 ms per token, 48.34 tokens per second) 8.21.234.011 I slot print_timing: id 0 | task 20535 | total time = 5859.62 ms / 789 tokens 8.21.234.012 I slot print_timing: id 0 | task 20535 | graphs reused = 19962 8.21.234.012 I slot print_timing: id 0 | task 20535 | graph reallocs = 0 / 0 (same size) / (changed size) 8.21.234.044 I slot release: id 0 | task 20535 | stop processing: n_tokens = 788, truncated = 0 8.21.239.034 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 788, t_last = 328283223306 8.21.239.114 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 88.854 MiB) 8.21.252.774 I slot launch_slot_: id 0 | task 20767 | processing task, is_child = 0 8.23.987.648 I slot print_timing: id 0 | task 20767 | prompt eval time = 693.08 ms / 317 tokens ( 2.19 ms per token, 457.38 tokens per second) 8.23.987.654 I slot print_timing: id 0 | task 20767 | eval time = 2041.79 ms / 100 tokens ( 20.62 ms per token, 48.49 tokens per second) 8.23.987.656 I slot print_timing: id 0 | task 20767 | total time = 2734.86 ms / 417 tokens 8.23.987.656 I slot print_timing: id 0 | task 20767 | graphs reused = 20060 8.23.987.657 I slot print_timing: id 0 | task 20767 | graph reallocs = 0 / 0 (same size) / (changed size) 8.23.987.680 I slot release: id 0 | task 20767 | stop processing: n_tokens = 416, truncated = 0 8.23.993.183 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 328285976943 8.23.993.239 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.130 MiB) 8.23.996.585 I slot launch_slot_: id 0 | task 20870 | processing task, is_child = 0 8.27.878.082 I slot print_timing: id 0 | task 20870 | n_gen = 147, tg = 48.43 t/s, tg_3s = 48.76 t/s 8.30.896.644 I slot print_timing: id 0 | task 20870 | n_gen = 293, tg = 48.40 t/s, tg_3s = 48.37 t/s 8.33.914.059 I slot print_timing: id 0 | task 20870 | n_gen = 439, tg = 48.39 t/s, tg_3s = 48.39 t/s 8.36.932.245 I slot print_timing: id 0 | task 20870 | n_gen = 584, tg = 48.31 t/s, tg_3s = 48.04 t/s 8.39.935.426 I slot print_timing: id 0 | task 20870 | n_gen = 728, tg = 48.24 t/s, tg_3s = 47.95 t/s 8.42.945.798 I slot print_timing: id 0 | task 20870 | n_gen = 873, tg = 48.22 t/s, tg_3s = 48.17 t/s 8.45.963.482 I slot print_timing: id 0 | task 20870 | n_gen = 1018, tg = 48.20 t/s, tg_3s = 48.05 t/s 8.46.088.688 I slot print_timing: id 0 | task 20870 | prompt eval time = 866.81 ms / 428 tokens ( 2.03 ms per token, 493.77 tokens per second) 8.46.088.692 I slot print_timing: id 0 | task 20870 | eval time = 21225.28 ms / 1024 tokens ( 20.75 ms per token, 48.20 tokens per second) 8.46.088.692 I slot print_timing: id 0 | task 20870 | total time = 22092.09 ms / 1452 tokens 8.46.088.693 I slot print_timing: id 0 | task 20870 | graphs reused = 21078 8.46.088.694 I slot print_timing: id 0 | task 20870 | graph reallocs = 0 / 0 (same size) / (changed size) 8.46.088.733 I slot release: id 0 | task 20870 | stop processing: n_tokens = 1451, truncated = 0 8.46.093.166 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.133 (> 0.100 thold), f_keep = 0.021 8.46.093.285 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 89.662 MiB) 8.46.093.293 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 139.450 MiB) 8.46.104.911 I slot launch_slot_: id 0 | task 21897 | processing task, is_child = 0 8.49.639.291 I slot print_timing: id 0 | task 21897 | n_gen = 145, tg = 47.83 t/s, tg_3s = 48.16 t/s 8.52.654.271 I slot print_timing: id 0 | task 21897 | n_gen = 285, tg = 47.13 t/s, tg_3s = 46.43 t/s 8.55.657.370 I slot print_timing: id 0 | task 21897 | n_gen = 427, tg = 47.18 t/s, tg_3s = 47.28 t/s 8.58.664.646 I slot print_timing: id 0 | task 21897 | n_gen = 569, tg = 47.19 t/s, tg_3s = 47.22 t/s 8.58.932.321 I slot print_timing: id 0 | task 21897 | prompt eval time = 523.50 ms / 226 tokens ( 2.32 ms per token, 431.71 tokens per second) 8.58.932.327 I slot print_timing: id 0 | task 21897 | eval time = 12303.90 ms / 582 tokens ( 21.18 ms per token, 47.22 tokens per second) 8.58.932.327 I slot print_timing: id 0 | task 21897 | total time = 12827.40 ms / 808 tokens 8.58.932.328 I slot print_timing: id 0 | task 21897 | graphs reused = 21655 8.58.932.329 I slot print_timing: id 0 | task 21897 | graph reallocs = 0 / 0 (same size) / (changed size) 8.58.932.350 I slot release: id 0 | task 21897 | stop processing: n_tokens = 807, truncated = 0 8.58.937.628 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 807, t_last = 328320921612 8.58.937.703 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.997 MiB) 8.58.946.692 I slot launch_slot_: id 0 | task 22482 | processing task, is_child = 0 9.02.759.693 I slot print_timing: id 0 | task 22482 | n_gen = 147, tg = 48.42 t/s, tg_3s = 48.75 t/s 9.03.564.992 I slot print_timing: id 0 | task 22482 | prompt eval time = 797.78 ms / 386 tokens ( 2.07 ms per token, 483.84 tokens per second) 9.03.564.998 I slot print_timing: id 0 | task 22482 | eval time = 3820.51 ms / 186 tokens ( 20.65 ms per token, 48.42 tokens per second) 9.03.564.999 I slot print_timing: id 0 | task 22482 | total time = 4618.29 ms / 572 tokens 9.03.564.999 I slot print_timing: id 0 | task 22482 | graphs reused = 21838 9.03.565.000 I slot print_timing: id 0 | task 22482 | graph reallocs = 0 / 0 (same size) / (changed size) 9.03.565.039 I slot release: id 0 | task 22482 | stop processing: n_tokens = 571, truncated = 0 9.03.570.857 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 571, t_last = 328325554301 9.03.570.931 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 199.964 MiB) 9.03.575.045 I slot launch_slot_: id 0 | task 22671 | processing task, is_child = 0 9.07.608.577 I slot print_timing: id 0 | task 22671 | n_gen = 144, tg = 47.56 t/s, tg_3s = 47.89 t/s 9.10.623.636 I slot print_timing: id 0 | task 22671 | n_gen = 287, tg = 47.49 t/s, tg_3s = 47.43 t/s 9.13.639.975 I slot print_timing: id 0 | task 22671 | n_gen = 433, tg = 47.80 t/s, tg_3s = 48.40 t/s 9.15.360.619 I slot print_timing: id 0 | task 22671 | prompt eval time = 1026.79 ms / 508 tokens ( 2.02 ms per token, 494.74 tokens per second) 9.15.360.624 I slot print_timing: id 0 | task 22671 | eval time = 10758.77 ms / 516 tokens ( 20.89 ms per token, 47.87 tokens per second) 9.15.360.625 I slot print_timing: id 0 | task 22671 | total time = 11785.57 ms / 1024 tokens 9.15.360.626 I slot print_timing: id 0 | task 22671 | graphs reused = 22350 9.15.360.627 I slot print_timing: id 0 | task 22671 | graph reallocs = 0 / 0 (same size) / (changed size) 9.15.360.660 I slot release: id 0 | task 22671 | stop processing: n_tokens = 1023, truncated = 0 9.15.366.831 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1023, t_last = 328337349922 9.15.366.933 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 110.619 MiB) 9.15.377.802 I slot launch_slot_: id 0 | task 23190 | processing task, is_child = 0 9.19.558.477 I slot print_timing: id 0 | task 23190 | n_gen = 147, tg = 48.38 t/s, tg_3s = 48.72 t/s 9.21.981.171 I slot print_timing: id 0 | task 23190 | prompt eval time = 1163.12 ms / 567 tokens ( 2.05 ms per token, 487.48 tokens per second) 9.21.981.174 I slot print_timing: id 0 | task 23190 | eval time = 5440.24 ms / 264 tokens ( 20.69 ms per token, 48.34 tokens per second) 9.21.981.175 I slot print_timing: id 0 | task 23190 | total time = 6603.36 ms / 831 tokens 9.21.981.175 I slot print_timing: id 0 | task 23190 | graphs reused = 22611 9.21.981.176 I slot print_timing: id 0 | task 23190 | graph reallocs = 0 / 0 (same size) / (changed size) 9.21.981.210 I slot release: id 0 | task 23190 | stop processing: n_tokens = 830, truncated = 0 9.21.986.550 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 830, t_last = 328343970473 9.21.986.632 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 159.703 MiB) 9.21.997.209 I slot launch_slot_: id 0 | task 23458 | processing task, is_child = 0 9.25.796.472 I slot print_timing: id 0 | task 23458 | n_gen = 147, tg = 48.65 t/s, tg_3s = 48.99 t/s 9.28.805.745 I slot print_timing: id 0 | task 23458 | n_gen = 293, tg = 48.58 t/s, tg_3s = 48.52 t/s 9.30.557.184 I slot print_timing: id 0 | task 23458 | prompt eval time = 798.37 ms / 384 tokens ( 2.08 ms per token, 480.98 tokens per second) 9.30.557.187 I slot print_timing: id 0 | task 23458 | eval time = 7761.59 ms / 377 tokens ( 20.64 ms per token, 48.44 tokens per second) 9.30.557.187 I slot print_timing: id 0 | task 23458 | total time = 8559.96 ms / 761 tokens 9.30.557.188 I slot print_timing: id 0 | task 23458 | graphs reused = 22985 9.30.557.189 I slot print_timing: id 0 | task 23458 | graph reallocs = 0 / 0 (same size) / (changed size) 9.30.557.213 I slot release: id 0 | task 23458 | stop processing: n_tokens = 760, truncated = 0 9.30.562.350 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 760, t_last = 328352546475 9.30.562.423 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 184.211 MiB) 9.30.571.806 I slot launch_slot_: id 0 | task 23838 | processing task, is_child = 0 9.34.550.314 I slot print_timing: id 0 | task 23838 | n_gen = 147, tg = 48.37 t/s, tg_3s = 48.70 t/s 9.37.562.549 I slot print_timing: id 0 | task 23838 | n_gen = 293, tg = 48.42 t/s, tg_3s = 48.47 t/s 9.38.129.487 I slot print_timing: id 0 | task 23838 | prompt eval time = 960.05 ms / 457 tokens ( 2.10 ms per token, 476.01 tokens per second) 9.38.129.492 I slot print_timing: id 0 | task 23838 | eval time = 6597.62 ms / 320 tokens ( 20.68 ms per token, 48.35 tokens per second) 9.38.129.493 I slot print_timing: id 0 | task 23838 | total time = 7557.67 ms / 777 tokens 9.38.129.494 I slot print_timing: id 0 | task 23838 | graphs reused = 23301 9.38.129.494 I slot print_timing: id 0 | task 23838 | graph reallocs = 0 / 0 (same size) / (changed size) 9.38.129.527 I slot release: id 0 | task 23838 | stop processing: n_tokens = 776, truncated = 0 9.38.134.696 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 776, t_last = 328360118789 9.38.134.765 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 123.348 MiB) 9.38.134.769 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.156 MiB) 9.38.143.945 I slot launch_slot_: id 0 | task 24161 | processing task, is_child = 0 9.42.011.444 I slot print_timing: id 0 | task 24161 | n_gen = 147, tg = 48.50 t/s, tg_3s = 48.83 t/s 9.44.421.718 I slot print_timing: id 0 | task 24161 | prompt eval time = 856.93 ms / 428 tokens ( 2.00 ms per token, 499.46 tokens per second) 9.44.421.723 I slot print_timing: id 0 | task 24161 | eval time = 5420.84 ms / 264 tokens ( 20.61 ms per token, 48.52 tokens per second) 9.44.421.724 I slot print_timing: id 0 | task 24161 | total time = 6277.77 ms / 692 tokens 9.44.421.724 I slot print_timing: id 0 | task 24161 | graphs reused = 23562 9.44.421.725 I slot print_timing: id 0 | task 24161 | graph reallocs = 0 / 0 (same size) / (changed size) 9.44.421.753 I slot release: id 0 | task 24161 | stop processing: n_tokens = 691, truncated = 0 9.44.427.681 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 691, t_last = 328366411015 9.44.436.750 I slot launch_slot_: id 0 | task 24428 | processing task, is_child = 0 9.48.618.420 I slot print_timing: id 0 | task 24428 | n_gen = 148, tg = 48.67 t/s, tg_3s = 49.00 t/s 9.51.636.617 I slot print_timing: id 0 | task 24428 | n_gen = 295, tg = 48.69 t/s, tg_3s = 48.70 t/s 9.52.751.877 I slot print_timing: id 0 | task 24428 | prompt eval time = 1161.34 ms / 555 tokens ( 2.09 ms per token, 477.90 tokens per second) 9.52.751.881 I slot print_timing: id 0 | task 24428 | eval time = 7153.78 ms / 349 tokens ( 20.56 ms per token, 48.65 tokens per second) 9.52.751.881 I slot print_timing: id 0 | task 24428 | total time = 8315.12 ms / 904 tokens 9.52.751.882 I slot print_timing: id 0 | task 24428 | graphs reused = 23908 9.52.751.883 I slot print_timing: id 0 | task 24428 | graph reallocs = 0 / 0 (same size) / (changed size) 9.52.751.918 I slot release: id 0 | task 24428 | stop processing: n_tokens = 903, truncated = 0 9.52.758.498 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 903, t_last = 328374741180 9.52.758.577 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 198.172 MiB) 9.52.768.942 I slot launch_slot_: id 0 | task 24781 | processing task, is_child = 0 9.57.053.643 I slot print_timing: id 0 | task 24781 | n_gen = 146, tg = 48.29 t/s, tg_3s = 48.62 t/s 9.57.074.149 I slot print_timing: id 0 | task 24781 | prompt eval time = 1281.89 ms / 643 tokens ( 1.99 ms per token, 501.60 tokens per second) 9.57.074.152 I slot print_timing: id 0 | task 24781 | eval time = 3023.31 ms / 147 tokens ( 20.71 ms per token, 48.29 tokens per second) 9.57.074.153 I slot print_timing: id 0 | task 24781 | total time = 4305.20 ms / 790 tokens 9.57.074.153 I slot print_timing: id 0 | task 24781 | graphs reused = 24052 9.57.074.154 I slot print_timing: id 0 | task 24781 | graph reallocs = 0 / 0 (same size) / (changed size) 9.57.074.195 I slot release: id 0 | task 24781 | stop processing: n_tokens = 789, truncated = 0 9.57.079.879 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 789, t_last = 328379063457 9.57.079.960 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 144.585 MiB) 9.57.079.964 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 150.669 MiB) 9.57.085.856 I slot launch_slot_: id 0 | task 24932 | processing task, is_child = 0 10.01.016.647 I slot print_timing: id 0 | task 24932 | n_gen = 148, tg = 48.68 t/s, tg_3s = 49.01 t/s 10.04.033.312 I slot print_timing: id 0 | task 24932 | n_gen = 295, tg = 48.70 t/s, tg_3s = 48.73 t/s 10.04.712.689 I slot print_timing: id 0 | task 24932 | prompt eval time = 910.97 ms / 460 tokens ( 1.98 ms per token, 504.96 tokens per second) 10.04.712.695 I slot print_timing: id 0 | task 24932 | eval time = 6715.86 ms / 328 tokens ( 20.54 ms per token, 48.69 tokens per second) 10.04.712.695 I slot print_timing: id 0 | task 24932 | total time = 7626.83 ms / 788 tokens 10.04.712.696 I slot print_timing: id 0 | task 24932 | graphs reused = 24376 10.04.712.697 I slot print_timing: id 0 | task 24932 | graph reallocs = 0 / 0 (same size) / (changed size) 10.04.712.730 I slot release: id 0 | task 24932 | stop processing: n_tokens = 787, truncated = 0 10.04.718.592 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 787, t_last = 328386701992 10.04.718.662 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 92.475 MiB) 10.04.728.091 I slot launch_slot_: id 0 | task 25263 | processing task, is_child = 0 10.08.742.779 I slot print_timing: id 0 | task 25263 | prompt eval time = 1021.78 ms / 516 tokens ( 1.98 ms per token, 505.00 tokens per second) 10.08.742.782 I slot print_timing: id 0 | task 25263 | eval time = 2992.90 ms / 146 tokens ( 20.64 ms per token, 48.45 tokens per second) 10.08.742.782 I slot print_timing: id 0 | task 25263 | total time = 4014.68 ms / 662 tokens 10.08.742.783 I slot print_timing: id 0 | task 25263 | graphs reused = 24520 10.08.742.784 I slot print_timing: id 0 | task 25263 | graph reallocs = 0 / 0 (same size) / (changed size) 10.08.742.815 I slot release: id 0 | task 25263 | stop processing: n_tokens = 661, truncated = 0 10.08.747.777 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 661, t_last = 328390732077 10.08.747.843 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 139.734 MiB) 10.08.752.449 I slot launch_slot_: id 0 | task 25412 | processing task, is_child = 0 10.12.438.631 I slot print_timing: id 0 | task 25412 | n_gen = 148, tg = 48.98 t/s, tg_3s = 49.32 t/s 10.15.457.972 I slot print_timing: id 0 | task 25412 | n_gen = 295, tg = 48.83 t/s, tg_3s = 48.69 t/s 10.15.478.532 I slot print_timing: id 0 | task 25412 | prompt eval time = 685.12 ms / 325 tokens ( 2.11 ms per token, 474.37 tokens per second) 10.15.478.535 I slot print_timing: id 0 | task 25412 | eval time = 6040.96 ms / 296 tokens ( 20.48 ms per token, 48.83 tokens per second) 10.15.478.535 I slot print_timing: id 0 | task 25412 | total time = 6726.08 ms / 621 tokens 10.15.478.536 I slot print_timing: id 0 | task 25412 | graphs reused = 24813 10.15.478.537 I slot print_timing: id 0 | task 25412 | graph reallocs = 0 / 0 (same size) / (changed size) 10.15.478.562 I slot release: id 0 | task 25412 | stop processing: n_tokens = 620, truncated = 0 10.15.483.859 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 620, t_last = 328397467824 10.15.483.926 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 112.306 MiB) 10.15.483.930 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 151.124 MiB) 10.15.487.770 I slot launch_slot_: id 0 | task 25711 | processing task, is_child = 0 10.19.302.726 I slot print_timing: id 0 | task 25711 | n_gen = 148, tg = 48.72 t/s, tg_3s = 49.05 t/s 10.22.319.657 I slot print_timing: id 0 | task 25711 | n_gen = 295, tg = 48.72 t/s, tg_3s = 48.73 t/s 10.25.339.873 I slot print_timing: id 0 | task 25711 | n_gen = 441, tg = 48.59 t/s, tg_3s = 48.34 t/s 10.26.496.566 I slot print_timing: id 0 | task 25711 | prompt eval time = 797.54 ms / 393 tokens ( 2.03 ms per token, 492.76 tokens per second) 10.26.496.570 I slot print_timing: id 0 | task 25711 | eval time = 10211.25 ms / 497 tokens ( 20.59 ms per token, 48.57 tokens per second) 10.26.496.571 I slot print_timing: id 0 | task 25711 | total time = 11008.79 ms / 890 tokens 10.26.496.572 I slot print_timing: id 0 | task 25711 | graphs reused = 25306 10.26.496.572 I slot print_timing: id 0 | task 25711 | graph reallocs = 0 / 0 (same size) / (changed size) 10.26.496.599 I slot release: id 0 | task 25711 | stop processing: n_tokens = 889, truncated = 0 10.26.503.713 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 889, t_last = 328408485861 10.26.503.795 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.781 MiB) 10.26.513.907 I slot launch_slot_: id 0 | task 26211 | processing task, is_child = 0 10.29.964.531 I slot print_timing: id 0 | task 26211 | prompt eval time = 1401.59 ms / 695 tokens ( 2.02 ms per token, 495.87 tokens per second) 10.29.964.538 I slot print_timing: id 0 | task 26211 | eval time = 2049.03 ms / 100 tokens ( 20.70 ms per token, 48.32 tokens per second) 10.29.964.538 I slot print_timing: id 0 | task 26211 | total time = 3450.62 ms / 795 tokens 10.29.964.539 I slot print_timing: id 0 | task 26211 | graphs reused = 25403 10.29.964.540 I slot print_timing: id 0 | task 26211 | graph reallocs = 0 / 0 (same size) / (changed size) 10.29.964.583 I slot release: id 0 | task 26211 | stop processing: n_tokens = 794, truncated = 0 10.29.971.514 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 794, t_last = 328411953845 10.29.971.584 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 187.340 MiB) 10.29.986.296 I slot launch_slot_: id 0 | task 26315 | processing task, is_child = 0 10.34.343.979 I slot print_timing: id 0 | task 26315 | n_gen = 145, tg = 47.72 t/s, tg_3s = 48.05 t/s 10.37.358.748 I slot print_timing: id 0 | task 26315 | n_gen = 291, tg = 48.07 t/s, tg_3s = 48.43 t/s 10.40.361.460 I slot print_timing: id 0 | task 26315 | n_gen = 436, tg = 48.15 t/s, tg_3s = 48.29 t/s 10.42.622.896 I slot print_timing: id 0 | task 26315 | prompt eval time = 1340.18 ms / 657 tokens ( 2.04 ms per token, 490.23 tokens per second) 10.42.622.902 I slot print_timing: id 0 | task 26315 | eval time = 11296.41 ms / 545 tokens ( 20.77 ms per token, 48.16 tokens per second) 10.42.622.903 I slot print_timing: id 0 | task 26315 | total time = 12636.59 ms / 1202 tokens 10.42.622.903 I slot print_timing: id 0 | task 26315 | graphs reused = 25944 10.42.622.904 I slot print_timing: id 0 | task 26315 | graph reallocs = 0 / 0 (same size) / (changed size) 10.42.622.944 I slot release: id 0 | task 26315 | stop processing: n_tokens = 1201, truncated = 0 10.42.627.202 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.130 (> 0.100 thold), f_keep = 0.025 10.42.627.305 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.570 MiB) 10.42.627.309 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 144.021 MiB) 10.42.640.153 I slot launch_slot_: id 0 | task 26864 | processing task, is_child = 0 10.46.142.883 I slot print_timing: id 0 | task 26864 | n_gen = 149, tg = 49.19 t/s, tg_3s = 49.53 t/s 10.48.384.612 I slot print_timing: id 0 | task 26864 | prompt eval time = 494.17 ms / 231 tokens ( 2.14 ms per token, 467.45 tokens per second) 10.48.384.614 I slot print_timing: id 0 | task 26864 | eval time = 5250.27 ms / 258 tokens ( 20.43 ms per token, 48.95 tokens per second) 10.48.384.615 I slot print_timing: id 0 | task 26864 | total time = 5744.44 ms / 489 tokens 10.48.384.616 I slot print_timing: id 0 | task 26864 | graphs reused = 26199 10.48.384.616 I slot print_timing: id 0 | task 26864 | graph reallocs = 0 / 0 (same size) / (changed size) 10.48.384.637 I slot release: id 0 | task 26864 | stop processing: n_tokens = 488, truncated = 0 10.48.388.695 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.187 (> 0.100 thold), f_keep = 0.064 10.48.392.088 I slot launch_slot_: id 0 | task 27125 | processing task, is_child = 0 10.51.773.526 I slot print_timing: id 0 | task 27125 | n_gen = 148, tg = 48.91 t/s, tg_3s = 49.24 t/s 10.52.098.429 I slot print_timing: id 0 | task 27125 | prompt eval time = 375.86 ms / 166 tokens ( 2.26 ms per token, 441.66 tokens per second) 10.52.098.435 I slot print_timing: id 0 | task 27125 | eval time = 3330.47 ms / 164 tokens ( 20.43 ms per token, 48.94 tokens per second) 10.52.098.436 I slot print_timing: id 0 | task 27125 | total time = 3706.33 ms / 330 tokens 10.52.098.436 I slot print_timing: id 0 | task 27125 | graphs reused = 26360 10.52.098.437 I slot print_timing: id 0 | task 27125 | graph reallocs = 0 / 0 (same size) / (changed size) 10.52.098.458 I slot release: id 0 | task 27125 | stop processing: n_tokens = 329, truncated = 0 10.52.102.490 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.160 (> 0.100 thold), f_keep = 0.094 10.52.102.535 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 136.004 MiB) 10.52.106.343 I slot launch_slot_: id 0 | task 27292 | processing task, is_child = 0 10.55.582.142 I slot print_timing: id 0 | task 27292 | n_gen = 149, tg = 49.28 t/s, tg_3s = 49.62 t/s 10.56.397.776 I slot print_timing: id 0 | task 27292 | prompt eval time = 472.71 ms / 194 tokens ( 2.44 ms per token, 410.40 tokens per second) 10.56.397.779 I slot print_timing: id 0 | task 27292 | eval time = 3818.71 ms / 189 tokens ( 20.31 ms per token, 49.23 tokens per second) 10.56.397.780 I slot print_timing: id 0 | task 27292 | total time = 4291.42 ms / 383 tokens 10.56.397.781 I slot print_timing: id 0 | task 27292 | graphs reused = 26546 10.56.397.782 I slot print_timing: id 0 | task 27292 | graph reallocs = 0 / 0 (same size) / (changed size) 10.56.397.804 I slot release: id 0 | task 27292 | stop processing: n_tokens = 382, truncated = 0 10.56.402.140 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.208 (> 0.100 thold), f_keep = 0.081 10.56.402.202 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 172.220 MiB) 10.56.406.948 I slot launch_slot_: id 0 | task 27484 | processing task, is_child = 0 10.58.841.295 I slot print_timing: id 0 | task 27484 | prompt eval time = 374.35 ms / 149 tokens ( 2.51 ms per token, 398.03 tokens per second) 10.58.841.298 I slot print_timing: id 0 | task 27484 | eval time = 2059.99 ms / 103 tokens ( 20.20 ms per token, 49.51 tokens per second) 10.58.841.302 I slot print_timing: id 0 | task 27484 | total time = 2434.34 ms / 252 tokens 10.58.841.303 I slot print_timing: id 0 | task 27484 | graphs reused = 26647 10.58.841.304 I slot print_timing: id 0 | task 27484 | graph reallocs = 0 / 0 (same size) / (changed size) 10.58.841.327 I slot release: id 0 | task 27484 | stop processing: n_tokens = 251, truncated = 0 10.58.845.586 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.137 (> 0.100 thold), f_keep = 0.120 10.58.850.236 I slot launch_slot_: id 0 | task 27590 | processing task, is_child = 0 11.02.377.438 I slot print_timing: id 0 | task 27590 | n_gen = 149, tg = 49.27 t/s, tg_3s = 49.61 t/s 11.02.705.152 I slot print_timing: id 0 | task 27590 | prompt eval time = 523.53 ms / 219 tokens ( 2.39 ms per token, 418.32 tokens per second) 11.02.705.158 I slot print_timing: id 0 | task 27590 | eval time = 3331.38 ms / 165 tokens ( 20.31 ms per token, 49.23 tokens per second) 11.02.705.158 I slot print_timing: id 0 | task 27590 | total time = 3854.91 ms / 384 tokens 11.02.705.159 I slot print_timing: id 0 | task 27590 | graphs reused = 26809 11.02.705.160 I slot print_timing: id 0 | task 27590 | graph reallocs = 0 / 0 (same size) / (changed size) 11.02.705.180 I slot release: id 0 | task 27590 | stop processing: n_tokens = 383, truncated = 0 11.02.709.035 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.227 (> 0.100 thold), f_keep = 0.078 11.02.709.088 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 191.103 MiB) 11.02.716.236 I slot launch_slot_: id 0 | task 27758 | processing task, is_child = 0 11.06.057.843 I slot print_timing: id 0 | task 27758 | n_gen = 150, tg = 49.39 t/s, tg_3s = 49.72 t/s 11.06.622.880 I slot print_timing: id 0 | task 27758 | prompt eval time = 324.50 ms / 132 tokens ( 2.46 ms per token, 406.78 tokens per second) 11.06.622.886 I slot print_timing: id 0 | task 27758 | eval time = 3582.14 ms / 178 tokens ( 20.24 ms per token, 49.41 tokens per second) 11.06.622.887 I slot print_timing: id 0 | task 27758 | total time = 3906.64 ms / 310 tokens 11.06.622.888 I slot print_timing: id 0 | task 27758 | graphs reused = 26984 11.06.622.888 I slot print_timing: id 0 | task 27758 | graph reallocs = 0 / 0 (same size) / (changed size) 11.06.622.909 I slot release: id 0 | task 27758 | stop processing: n_tokens = 309, truncated = 0 11.06.626.936 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.097 11.06.631.598 I slot launch_slot_: id 0 | task 27939 | processing task, is_child = 0 11.08.070.747 I slot print_timing: id 0 | task 27939 | prompt eval time = 376.62 ms / 169 tokens ( 2.23 ms per token, 448.73 tokens per second) 11.08.070.753 I slot print_timing: id 0 | task 27939 | eval time = 1062.52 ms / 53 tokens ( 20.43 ms per token, 48.94 tokens per second) 11.08.070.754 I slot print_timing: id 0 | task 27939 | total time = 1439.14 ms / 222 tokens 11.08.070.754 I slot print_timing: id 0 | task 27939 | graphs reused = 27035 11.08.070.755 I slot print_timing: id 0 | task 27939 | graph reallocs = 0 / 0 (same size) / (changed size) 11.08.070.778 I slot release: id 0 | task 27939 | stop processing: n_tokens = 221, truncated = 0 11.08.074.822 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.136 11.08.079.875 I slot launch_slot_: id 0 | task 27995 | processing task, is_child = 0 11.11.474.608 I slot print_timing: id 0 | task 27995 | n_gen = 147, tg = 48.37 t/s, tg_3s = 48.70 t/s 11.12.165.460 I slot print_timing: id 0 | task 27995 | prompt eval time = 376.20 ms / 160 tokens ( 2.35 ms per token, 425.31 tokens per second) 11.12.165.466 I slot print_timing: id 0 | task 27995 | eval time = 3709.38 ms / 181 tokens ( 20.61 ms per token, 48.53 tokens per second) 11.12.165.470 I slot print_timing: id 0 | task 27995 | total time = 4085.58 ms / 341 tokens 11.12.165.471 I slot print_timing: id 0 | task 27995 | graphs reused = 27213 11.12.165.472 I slot print_timing: id 0 | task 27995 | graph reallocs = 0 / 0 (same size) / (changed size) 11.12.165.489 I slot release: id 0 | task 27995 | stop processing: n_tokens = 340, truncated = 0 11.12.169.174 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.291 (> 0.100 thold), f_keep = 0.088 11.12.169.223 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 68.461 MiB) 11.12.171.565 I slot launch_slot_: id 0 | task 28179 | processing task, is_child = 0 11.14.420.759 I slot print_timing: id 0 | task 28179 | prompt eval time = 270.80 ms / 103 tokens ( 2.63 ms per token, 380.35 tokens per second) 11.14.420.765 I slot print_timing: id 0 | task 28179 | eval time = 1978.38 ms / 99 tokens ( 20.19 ms per token, 49.54 tokens per second) 11.14.420.766 I slot print_timing: id 0 | task 28179 | total time = 2249.18 ms / 202 tokens 11.14.420.767 I slot print_timing: id 0 | task 28179 | graphs reused = 27310 11.14.420.767 I slot print_timing: id 0 | task 28179 | graph reallocs = 0 / 0 (same size) / (changed size) 11.14.420.783 I slot release: id 0 | task 28179 | stop processing: n_tokens = 201, truncated = 0 11.14.424.767 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.149 11.14.424.808 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 109.248 MiB) 11.14.427.238 I slot launch_slot_: id 0 | task 28281 | processing task, is_child = 0 11.15.726.871 I slot print_timing: id 0 | task 28281 | prompt eval time = 410.92 ms / 165 tokens ( 2.49 ms per token, 401.54 tokens per second) 11.15.726.875 I slot print_timing: id 0 | task 28281 | eval time = 888.70 ms / 45 tokens ( 20.20 ms per token, 49.51 tokens per second) 11.15.726.875 I slot print_timing: id 0 | task 28281 | total time = 1299.62 ms / 210 tokens 11.15.726.876 I slot print_timing: id 0 | task 28281 | graphs reused = 27353 11.15.726.881 I slot print_timing: id 0 | task 28281 | graph reallocs = 0 / 0 (same size) / (changed size) 11.15.726.902 I slot release: id 0 | task 28281 | stop processing: n_tokens = 209, truncated = 0 11.15.730.950 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.144 11.15.734.596 I slot launch_slot_: id 0 | task 28329 | processing task, is_child = 0 11.19.124.387 I slot print_timing: id 0 | task 28329 | n_gen = 149, tg = 49.14 t/s, tg_3s = 49.48 t/s 11.21.361.818 I slot print_timing: id 0 | task 28329 | prompt eval time = 378.22 ms / 165 tokens ( 2.29 ms per token, 436.26 tokens per second) 11.21.361.825 I slot print_timing: id 0 | task 28329 | eval time = 5248.99 ms / 256 tokens ( 20.58 ms per token, 48.58 tokens per second) 11.21.361.825 I slot print_timing: id 0 | task 28329 | total time = 5627.21 ms / 421 tokens 11.21.361.826 I slot print_timing: id 0 | task 28329 | graphs reused = 27606 11.21.361.827 I slot print_timing: id 0 | task 28329 | graph reallocs = 0 / 0 (same size) / (changed size) 11.21.361.849 I slot release: id 0 | task 28329 | stop processing: n_tokens = 420, truncated = 0 11.21.365.927 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.162 (> 0.100 thold), f_keep = 0.071 11.21.365.987 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 79.361 MiB) 11.21.368.774 I slot launch_slot_: id 0 | task 28588 | processing task, is_child = 0 11.24.838.984 I slot print_timing: id 0 | task 28588 | n_gen = 149, tg = 49.17 t/s, tg_3s = 49.50 t/s 11.25.718.070 I slot print_timing: id 0 | task 28588 | prompt eval time = 460.09 ms / 185 tokens ( 2.49 ms per token, 402.09 tokens per second) 11.25.718.077 I slot print_timing: id 0 | task 28588 | eval time = 3889.20 ms / 192 tokens ( 20.36 ms per token, 49.11 tokens per second) 11.25.718.078 I slot print_timing: id 0 | task 28588 | total time = 4349.29 ms / 377 tokens 11.25.718.078 I slot print_timing: id 0 | task 28588 | graphs reused = 27795 11.25.718.079 I slot print_timing: id 0 | task 28588 | graph reallocs = 0 / 0 (same size) / (changed size) 11.25.718.097 I slot release: id 0 | task 28588 | stop processing: n_tokens = 376, truncated = 0 11.25.722.055 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.080 11.25.722.109 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 66.984 MiB) 11.25.729.173 I slot launch_slot_: id 0 | task 28783 | processing task, is_child = 0 11.27.035.491 I slot print_timing: id 0 | task 28783 | prompt eval time = 375.46 ms / 160 tokens ( 2.35 ms per token, 426.15 tokens per second) 11.27.035.497 I slot print_timing: id 0 | task 28783 | eval time = 930.85 ms / 47 tokens ( 20.24 ms per token, 49.42 tokens per second) 11.27.035.498 I slot print_timing: id 0 | task 28783 | total time = 1306.31 ms / 207 tokens 11.27.035.499 I slot print_timing: id 0 | task 28783 | graphs reused = 27840 11.27.035.499 I slot print_timing: id 0 | task 28783 | graph reallocs = 0 / 0 (same size) / (changed size) 11.27.035.519 I slot release: id 0 | task 28783 | stop processing: n_tokens = 206, truncated = 0 11.27.039.521 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.191 (> 0.100 thold), f_keep = 0.146 11.27.039.561 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 99.684 MiB) 11.27.041.352 I slot launch_slot_: id 0 | task 28833 | processing task, is_child = 0 11.30.429.436 I slot print_timing: id 0 | task 28833 | n_gen = 149, tg = 49.13 t/s, tg_3s = 49.46 t/s 11.33.431.123 I slot print_timing: id 0 | task 28833 | n_gen = 296, tg = 49.05 t/s, tg_3s = 48.97 t/s 11.36.440.206 I slot print_timing: id 0 | task 28833 | n_gen = 439, tg = 48.54 t/s, tg_3s = 47.52 t/s 11.36.996.037 I slot print_timing: id 0 | task 28833 | prompt eval time = 375.78 ms / 157 tokens ( 2.39 ms per token, 417.79 tokens per second) 11.36.996.044 I slot print_timing: id 0 | task 28833 | eval time = 9578.89 ms / 466 tokens ( 20.60 ms per token, 48.54 tokens per second) 11.36.996.044 I slot print_timing: id 0 | task 28833 | total time = 9954.67 ms / 623 tokens 11.36.996.045 I slot print_timing: id 0 | task 28833 | graphs reused = 28302 11.36.996.046 I slot print_timing: id 0 | task 28833 | graph reallocs = 0 / 0 (same size) / (changed size) 11.36.996.072 I slot release: id 0 | task 28833 | stop processing: n_tokens = 622, truncated = 0 11.36.999.987 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.048 11.37.000.056 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 97.539 MiB) 11.37.003.375 I slot launch_slot_: id 0 | task 29302 | processing task, is_child = 0 11.38.954.404 I slot print_timing: id 0 | task 29302 | prompt eval time = 378.00 ms / 171 tokens ( 2.21 ms per token, 452.38 tokens per second) 11.38.954.407 I slot print_timing: id 0 | task 29302 | eval time = 1573.02 ms / 79 tokens ( 20.17 ms per token, 49.59 tokens per second) 11.38.954.408 I slot print_timing: id 0 | task 29302 | total time = 1951.02 ms / 250 tokens 11.38.954.413 I slot print_timing: id 0 | task 29302 | graphs reused = 28379 11.38.954.414 I slot print_timing: id 0 | task 29302 | graph reallocs = 0 / 0 (same size) / (changed size) 11.38.954.431 I slot release: id 0 | task 29302 | stop processing: n_tokens = 249, truncated = 0 11.38.958.489 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.164 (> 0.100 thold), f_keep = 0.120 11.38.958.531 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 119.550 MiB) 11.38.960.604 I slot launch_slot_: id 0 | task 29384 | processing task, is_child = 0 11.42.434.687 I slot print_timing: id 0 | task 29384 | n_gen = 143, tg = 47.30 t/s, tg_3s = 47.64 t/s 11.45.443.065 I slot print_timing: id 0 | task 29384 | n_gen = 282, tg = 46.75 t/s, tg_3s = 46.20 t/s 11.48.449.625 I slot print_timing: id 0 | task 29384 | n_gen = 421, tg = 46.58 t/s, tg_3s = 46.23 t/s 11.51.460.206 I slot print_timing: id 0 | task 29384 | n_gen = 563, tg = 46.73 t/s, tg_3s = 47.17 t/s 11.54.476.733 I slot print_timing: id 0 | task 29384 | n_gen = 709, tg = 47.06 t/s, tg_3s = 48.40 t/s 11.57.481.457 I slot print_timing: id 0 | task 29384 | n_gen = 854, tg = 47.26 t/s, tg_3s = 48.26 t/s 12.00.496.188 I slot print_timing: id 0 | task 29384 | n_gen = 999, tg = 47.38 t/s, tg_3s = 48.10 t/s 12.01.015.486 I slot print_timing: id 0 | task 29384 | prompt eval time = 472.23 ms / 183 tokens ( 2.58 ms per token, 387.52 tokens per second) 12.01.015.493 I slot print_timing: id 0 | task 29384 | eval time = 21582.64 ms / 1024 tokens ( 21.10 ms per token, 47.40 tokens per second) 12.01.015.494 I slot print_timing: id 0 | task 29384 | total time = 22054.87 ms / 1207 tokens 12.01.015.504 I slot print_timing: id 0 | task 29384 | graphs reused = 29397 12.01.015.505 I slot print_timing: id 0 | task 29384 | graph reallocs = 0 / 0 (same size) / (changed size) 12.01.015.539 I slot release: id 0 | task 29384 | stop processing: n_tokens = 1206, truncated = 0 12.01.020.642 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.184 (> 0.100 thold), f_keep = 0.025 12.01.020.750 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 97.188 MiB) 12.01.043.929 I slot launch_slot_: id 0 | task 30411 | processing task, is_child = 0 12.04.429.126 I slot print_timing: id 0 | task 30411 | n_gen = 150, tg = 49.56 t/s, tg_3s = 49.90 t/s 12.07.439.577 I slot print_timing: id 0 | task 30411 | n_gen = 297, tg = 49.20 t/s, tg_3s = 48.83 t/s 12.10.450.098 I slot print_timing: id 0 | task 30411 | n_gen = 443, tg = 48.96 t/s, tg_3s = 48.50 t/s 12.13.452.263 I slot print_timing: id 0 | task 30411 | n_gen = 589, tg = 48.88 t/s, tg_3s = 48.63 t/s 12.16.313.469 I slot print_timing: id 0 | task 30411 | prompt eval time = 379.03 ms / 163 tokens ( 2.33 ms per token, 430.05 tokens per second) 12.16.313.475 I slot print_timing: id 0 | task 30411 | eval time = 14890.50 ms / 728 tokens ( 20.48 ms per token, 48.82 tokens per second) 12.16.313.476 I slot print_timing: id 0 | task 30411 | total time = 15269.53 ms / 891 tokens 12.16.313.477 I slot print_timing: id 0 | task 30411 | graphs reused = 30120 12.16.313.477 I slot print_timing: id 0 | task 30411 | graph reallocs = 0 / 0 (same size) / (changed size) 12.16.313.500 I slot release: id 0 | task 30411 | stop processing: n_tokens = 890, truncated = 0 12.16.317.882 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.169 (> 0.100 thold), f_keep = 0.034 12.16.317.965 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.753 MiB) 12.16.336.163 I slot launch_slot_: id 0 | task 31142 | processing task, is_child = 0 12.19.730.399 I slot print_timing: id 0 | task 31142 | n_gen = 149, tg = 49.11 t/s, tg_3s = 49.44 t/s 12.20.279.044 I slot print_timing: id 0 | task 31142 | prompt eval time = 380.48 ms / 177 tokens ( 2.15 ms per token, 465.20 tokens per second) 12.20.279.046 I slot print_timing: id 0 | task 31142 | eval time = 3562.39 ms / 176 tokens ( 20.36 ms per token, 49.12 tokens per second) 12.20.279.047 I slot print_timing: id 0 | task 31142 | total time = 3942.87 ms / 353 tokens 12.20.279.048 I slot print_timing: id 0 | task 31142 | graphs reused = 30293 12.20.279.048 I slot print_timing: id 0 | task 31142 | graph reallocs = 0 / 0 (same size) / (changed size) 12.20.279.072 I slot release: id 0 | task 31142 | stop processing: n_tokens = 352, truncated = 0 12.20.283.059 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.196 (> 0.100 thold), f_keep = 0.085 12.20.283.107 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.145 MiB) 12.20.289.685 I slot launch_slot_: id 0 | task 31321 | processing task, is_child = 0 12.23.146.306 I slot print_timing: id 0 | task 31321 | prompt eval time = 374.77 ms / 153 tokens ( 2.45 ms per token, 408.25 tokens per second) 12.23.146.309 I slot print_timing: id 0 | task 31321 | eval time = 2481.84 ms / 124 tokens ( 20.18 ms per token, 49.56 tokens per second) 12.23.146.310 I slot print_timing: id 0 | task 31321 | total time = 2856.61 ms / 277 tokens 12.23.146.310 I slot print_timing: id 0 | task 31321 | graphs reused = 30414 12.23.146.311 I slot print_timing: id 0 | task 31321 | graph reallocs = 0 / 0 (same size) / (changed size) 12.23.146.335 I slot release: id 0 | task 31321 | stop processing: n_tokens = 276, truncated = 0 12.23.150.754 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.217 (> 0.100 thold), f_keep = 0.109 12.23.150.801 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 98.805 MiB) 12.23.153.038 I slot launch_slot_: id 0 | task 31448 | processing task, is_child = 0 12.26.482.655 I slot print_timing: id 0 | task 31448 | n_gen = 150, tg = 49.58 t/s, tg_3s = 49.92 t/s 12.29.490.074 I slot print_timing: id 0 | task 31448 | n_gen = 296, tg = 49.07 t/s, tg_3s = 48.55 t/s 12.32.496.118 I slot print_timing: id 0 | task 31448 | n_gen = 440, tg = 48.68 t/s, tg_3s = 47.90 t/s 12.35.498.890 I slot print_timing: id 0 | task 31448 | n_gen = 585, tg = 48.58 t/s, tg_3s = 48.29 t/s 12.38.511.209 I slot print_timing: id 0 | task 31448 | n_gen = 729, tg = 48.42 t/s, tg_3s = 47.80 t/s 12.39.276.195 I slot print_timing: id 0 | task 31448 | prompt eval time = 324.60 ms / 138 tokens ( 2.35 ms per token, 425.13 tokens per second) 12.39.276.201 I slot print_timing: id 0 | task 31448 | eval time = 15798.55 ms / 766 tokens ( 20.65 ms per token, 48.42 tokens per second) 12.39.276.202 I slot print_timing: id 0 | task 31448 | total time = 16123.15 ms / 904 tokens 12.39.276.202 I slot print_timing: id 0 | task 31448 | graphs reused = 31175 12.39.276.203 I slot print_timing: id 0 | task 31448 | graph reallocs = 0 / 0 (same size) / (changed size) 12.39.276.221 I slot release: id 0 | task 31448 | stop processing: n_tokens = 903, truncated = 0 12.39.280.380 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.168 (> 0.100 thold), f_keep = 0.033 12.39.280.462 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 82.912 MiB) 12.39.295.217 I slot launch_slot_: id 0 | task 32217 | processing task, is_child = 0 12.41.646.400 I slot print_timing: id 0 | task 32217 | prompt eval time = 378.00 ms / 179 tokens ( 2.11 ms per token, 473.54 tokens per second) 12.41.646.405 I slot print_timing: id 0 | task 32217 | eval time = 1973.17 ms / 98 tokens ( 20.34 ms per token, 49.16 tokens per second) 12.41.646.406 I slot print_timing: id 0 | task 32217 | total time = 2351.17 ms / 277 tokens 12.41.646.406 I slot print_timing: id 0 | task 32217 | graphs reused = 31270 12.41.646.407 I slot print_timing: id 0 | task 32217 | graph reallocs = 0 / 0 (same size) / (changed size) 12.41.646.425 I slot release: id 0 | task 32217 | stop processing: n_tokens = 276, truncated = 0 12.41.650.642 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.169 (> 0.100 thold), f_keep = 0.123 12.41.650.691 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 114.206 MiB) 12.41.652.941 I slot launch_slot_: id 0 | task 32318 | processing task, is_child = 0 12.44.013.037 I slot print_timing: id 0 | task 32318 | prompt eval time = 440.24 ms / 201 tokens ( 2.19 ms per token, 456.57 tokens per second) 12.44.013.041 I slot print_timing: id 0 | task 32318 | eval time = 1919.85 ms / 96 tokens ( 20.21 ms per token, 49.48 tokens per second) 12.44.013.041 I slot print_timing: id 0 | task 32318 | total time = 2360.09 ms / 297 tokens 12.44.013.042 I slot print_timing: id 0 | task 32318 | graphs reused = 31363 12.44.013.043 I slot print_timing: id 0 | task 32318 | graph reallocs = 0 / 0 (same size) / (changed size) 12.44.013.064 I slot release: id 0 | task 32318 | stop processing: n_tokens = 296, truncated = 0 12.44.017.192 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.224 (> 0.100 thold), f_keep = 0.101 12.44.017.239 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 134.462 MiB) 12.44.022.243 I slot launch_slot_: id 0 | task 32417 | processing task, is_child = 0 12.47.360.148 I slot print_timing: id 0 | task 32417 | prompt eval time = 325.21 ms / 134 tokens ( 2.43 ms per token, 412.04 tokens per second) 12.47.360.159 I slot print_timing: id 0 | task 32417 | eval time = 3012.69 ms / 149 tokens ( 20.36 ms per token, 49.13 tokens per second) 12.47.360.160 I slot print_timing: id 0 | task 32417 | total time = 3337.90 ms / 283 tokens 12.47.360.161 I slot print_timing: id 0 | task 32417 | graphs reused = 31509 12.47.360.161 I slot print_timing: id 0 | task 32417 | graph reallocs = 0 / 0 (same size) / (changed size) 12.47.360.186 I slot release: id 0 | task 32417 | stop processing: n_tokens = 282, truncated = 0 12.47.364.115 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.205 (> 0.100 thold), f_keep = 0.106 12.47.366.355 I slot launch_slot_: id 0 | task 32569 | processing task, is_child = 0 12.48.086.616 I slot print_timing: id 0 | task 32569 | prompt eval time = 374.19 ms / 146 tokens ( 2.56 ms per token, 390.17 tokens per second) 12.48.086.622 I slot print_timing: id 0 | task 32569 | eval time = 346.06 ms / 18 tokens ( 20.36 ms per token, 49.13 tokens per second) 12.48.086.623 I slot print_timing: id 0 | task 32569 | total time = 720.25 ms / 164 tokens 12.48.086.624 I slot print_timing: id 0 | task 32569 | graphs reused = 31525 12.48.086.624 I slot print_timing: id 0 | task 32569 | graph reallocs = 0 / 0 (same size) / (changed size) 12.48.086.638 I slot release: id 0 | task 32569 | stop processing: n_tokens = 163, truncated = 0 12.48.090.039 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.217 (> 0.100 thold), f_keep = 0.184 12.48.091.573 I slot launch_slot_: id 0 | task 32590 | processing task, is_child = 0 12.50.013.764 I slot print_timing: id 0 | task 32590 | prompt eval time = 324.53 ms / 138 tokens ( 2.35 ms per token, 425.23 tokens per second) 12.50.013.774 I slot print_timing: id 0 | task 32590 | eval time = 1597.65 ms / 79 tokens ( 20.48 ms per token, 48.82 tokens per second) 12.50.013.775 I slot print_timing: id 0 | task 32590 | total time = 1922.18 ms / 217 tokens 12.50.013.776 I slot print_timing: id 0 | task 32590 | graphs reused = 31602 12.50.013.776 I slot print_timing: id 0 | task 32590 | graph reallocs = 0 / 0 (same size) / (changed size) 12.50.013.792 I slot release: id 0 | task 32590 | stop processing: n_tokens = 216, truncated = 0 12.50.017.680 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.139 12.50.017.718 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 71.766 MiB) 12.50.019.452 I slot launch_slot_: id 0 | task 32672 | processing task, is_child = 0 12.53.413.451 I slot print_timing: id 0 | task 32672 | n_gen = 150, tg = 49.36 t/s, tg_3s = 49.69 t/s 12.56.423.307 I slot print_timing: id 0 | task 32672 | n_gen = 297, tg = 49.10 t/s, tg_3s = 48.84 t/s 12.59.434.485 I slot print_timing: id 0 | task 32672 | n_gen = 443, tg = 48.90 t/s, tg_3s = 48.49 t/s 13.02.446.468 I slot print_timing: id 0 | task 32672 | n_gen = 589, tg = 48.79 t/s, tg_3s = 48.47 t/s 13.05.464.751 I slot print_timing: id 0 | task 32672 | n_gen = 735, tg = 48.71 t/s, tg_3s = 48.37 t/s 13.08.481.826 I slot print_timing: id 0 | task 32672 | n_gen = 880, tg = 48.60 t/s, tg_3s = 48.06 t/s 13.11.470.988 I slot print_timing: id 0 | task 32672 | prompt eval time = 375.37 ms / 155 tokens ( 2.42 ms per token, 412.93 tokens per second) 13.11.470.992 I slot print_timing: id 0 | task 32672 | eval time = 21076.15 ms / 1024 tokens ( 20.60 ms per token, 48.54 tokens per second) 13.11.470.992 I slot print_timing: id 0 | task 32672 | total time = 21451.52 ms / 1179 tokens 13.11.470.993 I slot print_timing: id 0 | task 32672 | graphs reused = 32620 13.11.470.994 I slot print_timing: id 0 | task 32672 | graph reallocs = 0 / 0 (same size) / (changed size) 13.11.471.015 I slot release: id 0 | task 32672 | stop processing: n_tokens = 1178, truncated = 0 13.11.475.307 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.025 13.11.475.403 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 120.500 MiB) 13.11.494.245 I slot launch_slot_: id 0 | task 33699 | processing task, is_child = 0 13.14.887.343 I slot print_timing: id 0 | task 33699 | n_gen = 143, tg = 47.07 t/s, tg_3s = 47.41 t/s 13.14.989.380 I slot print_timing: id 0 | task 33699 | prompt eval time = 376.56 ms / 160 tokens ( 2.35 ms per token, 424.90 tokens per second) 13.14.989.386 I slot print_timing: id 0 | task 33699 | eval time = 3118.57 ms / 148 tokens ( 21.21 ms per token, 47.14 tokens per second) 13.14.989.387 I slot print_timing: id 0 | task 33699 | total time = 3495.13 ms / 308 tokens 13.14.989.388 I slot print_timing: id 0 | task 33699 | graphs reused = 32765 13.14.989.388 I slot print_timing: id 0 | task 33699 | graph reallocs = 0 / 0 (same size) / (changed size) 13.14.989.407 I slot release: id 0 | task 33699 | stop processing: n_tokens = 307, truncated = 0 13.14.993.333 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.192 (> 0.100 thold), f_keep = 0.098 13.14.993.385 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 66.210 MiB) 13.14.998.046 I slot launch_slot_: id 0 | task 33850 | processing task, is_child = 0 13.17.814.489 I slot print_timing: id 0 | task 33850 | prompt eval time = 375.66 ms / 156 tokens ( 2.41 ms per token, 415.26 tokens per second) 13.17.814.494 I slot print_timing: id 0 | task 33850 | eval time = 2440.76 ms / 121 tokens ( 20.34 ms per token, 49.16 tokens per second) 13.17.814.494 I slot print_timing: id 0 | task 33850 | total time = 2816.43 ms / 277 tokens 13.17.814.495 I slot print_timing: id 0 | task 33850 | graphs reused = 32883 13.17.814.496 I slot print_timing: id 0 | task 33850 | graph reallocs = 0 / 0 (same size) / (changed size) 13.17.814.513 I slot release: id 0 | task 33850 | stop processing: n_tokens = 276, truncated = 0 13.17.818.450 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.190 (> 0.100 thold), f_keep = 0.109 13.17.818.498 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 85.725 MiB) 13.17.820.633 I slot launch_slot_: id 0 | task 33974 | processing task, is_child = 0 13.21.212.062 I slot print_timing: id 0 | task 33974 | n_gen = 149, tg = 49.07 t/s, tg_3s = 49.40 t/s 13.24.243.477 I slot print_timing: id 0 | task 33974 | n_gen = 290, tg = 47.79 t/s, tg_3s = 46.51 t/s 13.27.255.300 I slot print_timing: id 0 | task 33974 | n_gen = 432, tg = 47.58 t/s, tg_3s = 47.15 t/s 13.30.268.094 I slot print_timing: id 0 | task 33974 | n_gen = 576, tg = 47.63 t/s, tg_3s = 47.80 t/s 13.33.279.586 I slot print_timing: id 0 | task 33974 | n_gen = 718, tg = 47.54 t/s, tg_3s = 47.15 t/s 13.36.287.043 I slot print_timing: id 0 | task 33974 | n_gen = 864, tg = 47.70 t/s, tg_3s = 48.55 t/s 13.39.289.421 I slot print_timing: id 0 | task 33974 | n_gen = 1009, tg = 47.79 t/s, tg_3s = 48.30 t/s 13.39.600.023 I slot print_timing: id 0 | task 33974 | prompt eval time = 375.32 ms / 158 tokens ( 2.38 ms per token, 420.97 tokens per second) 13.39.600.029 I slot print_timing: id 0 | task 33974 | eval time = 21404.05 ms / 1024 tokens ( 20.92 ms per token, 47.79 tokens per second) 13.39.600.030 I slot print_timing: id 0 | task 33974 | total time = 21779.38 ms / 1182 tokens 13.39.600.030 I slot print_timing: id 0 | task 33974 | graphs reused = 33901 13.39.600.031 I slot print_timing: id 0 | task 33974 | graph reallocs = 0 / 0 (same size) / (changed size) 13.39.600.053 I slot release: id 0 | task 33974 | stop processing: n_tokens = 1181, truncated = 0 13.39.604.194 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.025 13.39.604.299 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 98.453 MiB) 13.39.622.947 I slot launch_slot_: id 0 | task 35001 | processing task, is_child = 0 13.42.986.618 I slot print_timing: id 0 | task 35001 | n_gen = 146, tg = 48.26 t/s, tg_3s = 48.60 t/s 13.45.996.666 I slot print_timing: id 0 | task 35001 | n_gen = 287, tg = 47.55 t/s, tg_3s = 46.84 t/s 13.49.007.392 I slot print_timing: id 0 | task 35001 | n_gen = 429, tg = 47.42 t/s, tg_3s = 47.16 t/s 13.52.022.062 I slot print_timing: id 0 | task 35001 | n_gen = 575, tg = 47.68 t/s, tg_3s = 48.43 t/s 13.55.040.701 I slot print_timing: id 0 | task 35001 | n_gen = 721, tg = 47.81 t/s, tg_3s = 48.37 t/s 13.58.040.958 I slot print_timing: id 0 | task 35001 | n_gen = 866, tg = 47.90 t/s, tg_3s = 48.33 t/s 14.01.042.352 I slot print_timing: id 0 | task 35001 | n_gen = 1010, tg = 47.91 t/s, tg_3s = 47.98 t/s 14.01.332.882 I slot print_timing: id 0 | task 35001 | prompt eval time = 359.39 ms / 155 tokens ( 2.32 ms per token, 431.29 tokens per second) 14.01.332.888 I slot print_timing: id 0 | task 35001 | eval time = 21350.54 ms / 1024 tokens ( 20.87 ms per token, 47.91 tokens per second) 14.01.332.889 I slot print_timing: id 0 | task 35001 | total time = 21709.93 ms / 1179 tokens 14.01.332.890 I slot print_timing: id 0 | task 35001 | graphs reused = 34919 14.01.332.890 I slot print_timing: id 0 | task 35001 | graph reallocs = 0 / 0 (same size) / (changed size) 14.01.332.914 I slot release: id 0 | task 35001 | stop processing: n_tokens = 1178, truncated = 0 14.01.337.390 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.176 (> 0.100 thold), f_keep = 0.025 14.01.337.498 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.556 MiB) 14.01.337.502 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 117.863 MiB) 14.01.355.125 I slot launch_slot_: id 0 | task 36028 | processing task, is_child = 0 14.01.917.333 I slot print_timing: id 0 | task 36028 | prompt eval time = 378.15 ms / 170 tokens ( 2.22 ms per token, 449.55 tokens per second) 14.01.917.343 I slot print_timing: id 0 | task 36028 | eval time = 184.05 ms / 10 tokens ( 20.45 ms per token, 48.90 tokens per second) 14.01.917.344 I slot print_timing: id 0 | task 36028 | total time = 562.20 ms / 180 tokens 14.01.917.345 I slot print_timing: id 0 | task 36028 | graphs reused = 34927 14.01.917.345 I slot print_timing: id 0 | task 36028 | graph reallocs = 0 / 0 (same size) / (changed size) 14.01.917.364 I slot release: id 0 | task 36028 | stop processing: n_tokens = 179, truncated = 0 14.01.921.462 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.173 14.01.923.262 I slot launch_slot_: id 0 | task 36041 | processing task, is_child = 0 14.04.813.484 I slot print_timing: id 0 | task 36041 | prompt eval time = 377.04 ms / 160 tokens ( 2.36 ms per token, 424.35 tokens per second) 14.04.813.486 I slot print_timing: id 0 | task 36041 | eval time = 2513.17 ms / 126 tokens ( 20.11 ms per token, 49.74 tokens per second) 14.04.813.491 I slot print_timing: id 0 | task 36041 | total time = 2890.21 ms / 286 tokens 14.04.813.492 I slot print_timing: id 0 | task 36041 | graphs reused = 35050 14.04.813.492 I slot print_timing: id 0 | task 36041 | graph reallocs = 0 / 0 (same size) / (changed size) 14.04.813.517 I slot release: id 0 | task 36041 | stop processing: n_tokens = 285, truncated = 0 14.04.817.582 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.186 (> 0.100 thold), f_keep = 0.105 14.04.817.628 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 114.664 MiB) 14.04.819.867 I slot launch_slot_: id 0 | task 36170 | processing task, is_child = 0 14.07.366.480 I slot print_timing: id 0 | task 36170 | prompt eval time = 378.31 ms / 161 tokens ( 2.35 ms per token, 425.58 tokens per second) 14.07.366.485 I slot print_timing: id 0 | task 36170 | eval time = 2168.30 ms / 108 tokens ( 20.26 ms per token, 49.35 tokens per second) 14.07.366.486 I slot print_timing: id 0 | task 36170 | total time = 2546.61 ms / 269 tokens 14.07.366.487 I slot print_timing: id 0 | task 36170 | graphs reused = 35155 14.07.366.487 I slot print_timing: id 0 | task 36170 | graph reallocs = 0 / 0 (same size) / (changed size) 14.07.366.509 I slot release: id 0 | task 36170 | stop processing: n_tokens = 268, truncated = 0 14.07.370.661 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.112 14.07.374.134 I slot launch_slot_: id 0 | task 36281 | processing task, is_child = 0 14.09.506.562 I slot print_timing: id 0 | task 36281 | prompt eval time = 361.18 ms / 169 tokens ( 2.14 ms per token, 467.91 tokens per second) 14.09.506.566 I slot print_timing: id 0 | task 36281 | eval time = 1771.24 ms / 88 tokens ( 20.36 ms per token, 49.12 tokens per second) 14.09.506.566 I slot print_timing: id 0 | task 36281 | total time = 2132.42 ms / 257 tokens 14.09.506.567 I slot print_timing: id 0 | task 36281 | graphs reused = 35241 14.09.506.568 I slot print_timing: id 0 | task 36281 | graph reallocs = 0 / 0 (same size) / (changed size) 14.09.506.586 I slot release: id 0 | task 36281 | stop processing: n_tokens = 256, truncated = 0 14.09.510.497 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.164 (> 0.100 thold), f_keep = 0.117 14.09.510.543 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.325 MiB) 14.09.512.625 I slot launch_slot_: id 0 | task 36372 | processing task, is_child = 0 14.10.834.303 I slot print_timing: id 0 | task 36372 | prompt eval time = 472.44 ms / 183 tokens ( 2.58 ms per token, 387.35 tokens per second) 14.10.834.308 I slot print_timing: id 0 | task 36372 | eval time = 849.23 ms / 43 tokens ( 20.22 ms per token, 49.46 tokens per second) 14.10.834.309 I slot print_timing: id 0 | task 36372 | total time = 1321.66 ms / 226 tokens 14.10.834.310 I slot print_timing: id 0 | task 36372 | graphs reused = 35282 14.10.834.310 I slot print_timing: id 0 | task 36372 | graph reallocs = 0 / 0 (same size) / (changed size) 14.10.834.332 I slot release: id 0 | task 36372 | stop processing: n_tokens = 225, truncated = 0 14.10.838.292 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.174 (> 0.100 thold), f_keep = 0.133 14.10.838.329 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 119.164 MiB) 14.10.843.648 I slot launch_slot_: id 0 | task 36418 | processing task, is_child = 0 14.14.018.806 I slot print_timing: id 0 | task 36418 | prompt eval time = 376.85 ms / 172 tokens ( 2.19 ms per token, 456.42 tokens per second) 14.14.018.809 I slot print_timing: id 0 | task 36418 | eval time = 2798.30 ms / 139 tokens ( 20.28 ms per token, 49.32 tokens per second) 14.14.018.810 I slot print_timing: id 0 | task 36418 | total time = 3175.15 ms / 311 tokens 14.14.018.810 I slot print_timing: id 0 | task 36418 | graphs reused = 35418 14.14.018.811 I slot print_timing: id 0 | task 36418 | graph reallocs = 0 / 0 (same size) / (changed size) 14.14.018.828 I slot release: id 0 | task 36418 | stop processing: n_tokens = 310, truncated = 0 14.14.022.951 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.165 (> 0.100 thold), f_keep = 0.097 14.14.028.630 I slot launch_slot_: id 0 | task 36560 | processing task, is_child = 0 14.17.480.673 I slot print_timing: id 0 | task 36560 | n_gen = 148, tg = 48.77 t/s, tg_3s = 49.11 t/s 14.20.485.684 I slot print_timing: id 0 | task 36560 | n_gen = 294, tg = 48.68 t/s, tg_3s = 48.59 t/s 14.22.892.275 I slot print_timing: id 0 | task 36560 | prompt eval time = 438.11 ms / 182 tokens ( 2.41 ms per token, 415.42 tokens per second) 14.22.892.281 I slot print_timing: id 0 | task 36560 | eval time = 8425.53 ms / 410 tokens ( 20.60 ms per token, 48.54 tokens per second) 14.22.892.282 I slot print_timing: id 0 | task 36560 | total time = 8863.64 ms / 592 tokens 14.22.892.282 I slot print_timing: id 0 | task 36560 | graphs reused = 35824 14.22.892.283 I slot print_timing: id 0 | task 36560 | graph reallocs = 0 / 0 (same size) / (changed size) 14.22.892.310 I slot release: id 0 | task 36560 | stop processing: n_tokens = 591, truncated = 0 14.22.896.584 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.056 14.22.896.651 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 134.285 MiB) 14.22.899.971 I slot launch_slot_: id 0 | task 36973 | processing task, is_child = 0 14.26.190.434 I slot print_timing: id 0 | task 36973 | prompt eval time = 437.27 ms / 181 tokens ( 2.42 ms per token, 413.93 tokens per second) 14.26.190.437 I slot print_timing: id 0 | task 36973 | eval time = 2853.18 ms / 142 tokens ( 20.24 ms per token, 49.42 tokens per second) 14.26.190.438 I slot print_timing: id 0 | task 36973 | total time = 3290.45 ms / 323 tokens 14.26.190.438 I slot print_timing: id 0 | task 36973 | graphs reused = 35963 14.26.190.439 I slot print_timing: id 0 | task 36973 | graph reallocs = 0 / 0 (same size) / (changed size) 14.26.190.458 I slot release: id 0 | task 36973 | stop processing: n_tokens = 322, truncated = 0 14.26.194.960 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.133 (> 0.100 thold), f_keep = 0.093 14.26.195.014 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 94.656 MiB) 14.26.199.227 I slot launch_slot_: id 0 | task 37118 | processing task, is_child = 0 14.28.065.591 I slot print_timing: id 0 | task 37118 | prompt eval time = 494.47 ms / 226 tokens ( 2.19 ms per token, 457.05 tokens per second) 14.28.065.596 I slot print_timing: id 0 | task 37118 | eval time = 1371.88 ms / 68 tokens ( 20.48 ms per token, 48.84 tokens per second) 14.28.065.597 I slot print_timing: id 0 | task 37118 | total time = 1866.35 ms / 294 tokens 14.28.065.598 I slot print_timing: id 0 | task 37118 | graphs reused = 36028 14.28.065.598 I slot print_timing: id 0 | task 37118 | graph reallocs = 0 / 0 (same size) / (changed size) 14.28.065.617 I slot release: id 0 | task 37118 | stop processing: n_tokens = 293, truncated = 0 14.28.069.468 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.189 (> 0.100 thold), f_keep = 0.102 14.28.069.507 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 125.215 MiB) 14.28.076.256 I slot launch_slot_: id 0 | task 37189 | processing task, is_child = 0 14.29.042.907 I slot print_timing: id 0 | task 37189 | prompt eval time = 377.33 ms / 159 tokens ( 2.37 ms per token, 421.38 tokens per second) 14.29.042.910 I slot print_timing: id 0 | task 37189 | eval time = 589.31 ms / 30 tokens ( 20.32 ms per token, 49.21 tokens per second) 14.29.042.911 I slot print_timing: id 0 | task 37189 | total time = 966.64 ms / 189 tokens 14.29.042.911 I slot print_timing: id 0 | task 37189 | graphs reused = 36056 14.29.042.912 I slot print_timing: id 0 | task 37189 | graph reallocs = 0 / 0 (same size) / (changed size) 14.29.042.928 I slot release: id 0 | task 37189 | stop processing: n_tokens = 188, truncated = 0 14.29.071.755 I srv operator(): operator(): cleaning up before exit...