$ /Users/minipro/quantdiff/llama.cpp/llama-b11770/llama-server -m /Users/minipro/quantdiff/models/campaign/8f4aabaf93cd/Spark-X2.6-4B-Q5_K_M.gguf --host 127.0.0.1 --port 8089 -c 4096 -np 1 -ngl 999 -fa on --jinja --seed 1234 --no-webui -a quant 0.00.042.605 I srv llama_server: initializing ... 0.00.042.610 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.042.695 I srv init_listene: The UI is disabled 0.00.042.696 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.042.729 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) 0.00.044.396 I srv load_model: loading model '/Users/minipro/quantdiff/models/campaign/8f4aabaf93cd/Spark-X2.6-4B-Q5_K_M.gguf' 0.00.453.754 I cmn init: llama threadpool init, n_threads = 8 0.00.541.268 I srv load_model: initializing, n_slots = 1, n_ctx_slot = 4096, kv_unified = 'false' 0.00.548.776 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.00.548.786 I srv llama_server: model loaded 0.00.548.788 I srv llama_server: listening on http://127.0.0.1:8089 0.02.022.126 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.02.022.368 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.03.065.181 I slot print_timing: id 0 | task 0 | prompt eval time = 472.13 ms / 172 tokens ( 2.74 ms per token, 364.31 tokens per second) 0.03.065.185 I slot print_timing: id 0 | task 0 | eval time = 570.67 ms / 24 tokens ( 24.81 ms per token, 40.30 tokens per second) 0.03.065.185 I slot print_timing: id 0 | task 0 | total time = 1042.80 ms / 196 tokens 0.03.065.186 I slot print_timing: id 0 | task 0 | graphs reused = 23 0.03.065.187 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.03.065.209 I slot release: id 0 | task 0 | stop processing: n_tokens = 195, truncated = 0 0.03.068.726 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.236 (> 0.100 thold), f_keep = 0.154 0.03.074.320 I slot launch_slot_: id 0 | task 27 | processing task, is_child = 0 0.03.969.570 I slot print_timing: id 0 | task 27 | prompt eval time = 374.34 ms / 127 tokens ( 2.95 ms per token, 339.27 tokens per second) 0.03.969.577 I slot print_timing: id 0 | task 27 | eval time = 520.90 ms / 22 tokens ( 24.80 ms per token, 40.31 tokens per second) 0.03.969.577 I slot print_timing: id 0 | task 27 | total time = 895.24 ms / 149 tokens 0.03.969.578 I slot print_timing: id 0 | task 27 | graphs reused = 43 0.03.969.578 I slot print_timing: id 0 | task 27 | graph reallocs = 0 / 0 (same size) / (changed size) 0.03.969.597 I slot release: id 0 | task 27 | stop processing: n_tokens = 148, truncated = 0 0.03.973.817 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 0.03.978.018 I slot launch_slot_: id 0 | task 52 | processing task, is_child = 0 0.04.905.910 I slot print_timing: id 0 | task 52 | prompt eval time = 432.41 ms / 171 tokens ( 2.53 ms per token, 395.46 tokens per second) 0.04.905.913 I slot print_timing: id 0 | task 52 | eval time = 495.47 ms / 21 tokens ( 24.77 ms per token, 40.37 tokens per second) 0.04.905.914 I slot print_timing: id 0 | task 52 | total time = 927.88 ms / 192 tokens 0.04.905.918 I slot print_timing: id 0 | task 52 | graphs reused = 62 0.04.905.919 I slot print_timing: id 0 | task 52 | graph reallocs = 0 / 0 (same size) / (changed size) 0.04.905.946 I slot release: id 0 | task 52 | stop processing: n_tokens = 191, truncated = 0 0.04.910.032 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.147 (> 0.100 thold), f_keep = 0.157 0.04.915.520 I slot launch_slot_: id 0 | task 76 | processing task, is_child = 0 0.05.962.132 I slot print_timing: id 0 | task 76 | prompt eval time = 500.11 ms / 204 tokens ( 2.45 ms per token, 407.91 tokens per second) 0.05.962.138 I slot print_timing: id 0 | task 76 | eval time = 546.49 ms / 23 tokens ( 24.84 ms per token, 40.26 tokens per second) 0.05.962.139 I slot print_timing: id 0 | task 76 | total time = 1046.60 ms / 227 tokens 0.05.962.139 I slot print_timing: id 0 | task 76 | graphs reused = 83 0.05.962.140 I slot print_timing: id 0 | task 76 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.962.159 I slot release: id 0 | task 76 | stop processing: n_tokens = 226, truncated = 0 0.05.966.078 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.190 0.05.972.702 I slot launch_slot_: id 0 | task 102 | processing task, is_child = 0 0.07.176.513 I slot print_timing: id 0 | task 102 | prompt eval time = 483.87 ms / 187 tokens ( 2.59 ms per token, 386.47 tokens per second) 0.07.176.518 I slot print_timing: id 0 | task 102 | eval time = 719.93 ms / 30 tokens ( 24.83 ms per token, 40.28 tokens per second) 0.07.176.519 I slot print_timing: id 0 | task 102 | total time = 1203.80 ms / 217 tokens 0.07.176.519 I slot print_timing: id 0 | task 102 | graphs reused = 111 0.07.176.520 I slot print_timing: id 0 | task 102 | graph reallocs = 0 / 0 (same size) / (changed size) 0.07.176.541 I slot release: id 0 | task 102 | stop processing: n_tokens = 216, truncated = 0 0.07.180.349 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.139 0.07.185.247 I slot launch_slot_: id 0 | task 135 | processing task, is_child = 0 0.08.487.137 I slot print_timing: id 0 | task 135 | prompt eval time = 560.92 ms / 171 tokens ( 3.28 ms per token, 304.85 tokens per second) 0.08.487.140 I slot print_timing: id 0 | task 135 | eval time = 740.96 ms / 31 tokens ( 24.70 ms per token, 40.49 tokens per second) 0.08.487.141 I slot print_timing: id 0 | task 135 | total time = 1301.88 ms / 202 tokens 0.08.487.142 I slot print_timing: id 0 | task 135 | graphs reused = 140 0.08.487.142 I slot print_timing: id 0 | task 135 | graph reallocs = 0 / 0 (same size) / (changed size) 0.08.487.162 I slot release: id 0 | task 135 | stop processing: n_tokens = 201, truncated = 0 0.08.491.426 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 0.08.497.147 I slot launch_slot_: id 0 | task 169 | processing task, is_child = 0 0.09.695.145 I slot print_timing: id 0 | task 169 | prompt eval time = 551.55 ms / 221 tokens ( 2.50 ms per token, 400.69 tokens per second) 0.09.695.148 I slot print_timing: id 0 | task 169 | eval time = 646.43 ms / 27 tokens ( 24.86 ms per token, 40.22 tokens per second) 0.09.695.149 I slot print_timing: id 0 | task 169 | total time = 1197.98 ms / 248 tokens 0.09.695.150 I slot print_timing: id 0 | task 169 | graphs reused = 165 0.09.695.151 I slot print_timing: id 0 | task 169 | graph reallocs = 0 / 0 (same size) / (changed size) 0.09.695.170 I slot release: id 0 | task 169 | stop processing: n_tokens = 247, truncated = 0 0.09.699.626 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 0.09.706.643 I slot launch_slot_: id 0 | task 199 | processing task, is_child = 0 0.11.359.922 I slot print_timing: id 0 | task 199 | prompt eval time = 658.25 ms / 270 tokens ( 2.44 ms per token, 410.18 tokens per second) 0.11.359.925 I slot print_timing: id 0 | task 199 | eval time = 995.02 ms / 41 tokens ( 24.88 ms per token, 40.20 tokens per second) 0.11.359.926 I slot print_timing: id 0 | task 199 | total time = 1653.27 ms / 311 tokens 0.11.359.927 I slot print_timing: id 0 | task 199 | graphs reused = 204 0.11.359.927 I slot print_timing: id 0 | task 199 | graph reallocs = 0 / 0 (same size) / (changed size) 0.11.359.952 I slot release: id 0 | task 199 | stop processing: n_tokens = 310, truncated = 0 0.11.363.910 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.097 0.11.372.764 I slot launch_slot_: id 0 | task 243 | processing task, is_child = 0 0.12.418.891 I slot print_timing: id 0 | task 243 | prompt eval time = 378.00 ms / 150 tokens ( 2.52 ms per token, 396.83 tokens per second) 0.12.418.894 I slot print_timing: id 0 | task 243 | eval time = 668.12 ms / 28 tokens ( 24.75 ms per token, 40.41 tokens per second) 0.12.418.895 I slot print_timing: id 0 | task 243 | total time = 1046.11 ms / 178 tokens 0.12.418.895 I slot print_timing: id 0 | task 243 | graphs reused = 230 0.12.418.896 I slot print_timing: id 0 | task 243 | graph reallocs = 0 / 0 (same size) / (changed size) 0.12.418.924 I slot release: id 0 | task 243 | stop processing: n_tokens = 177, truncated = 0 0.12.423.568 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 0.12.425.200 I slot launch_slot_: id 0 | task 274 | processing task, is_child = 0 0.13.327.920 I slot print_timing: id 0 | task 274 | prompt eval time = 431.39 ms / 167 tokens ( 2.58 ms per token, 387.12 tokens per second) 0.13.327.923 I slot print_timing: id 0 | task 274 | eval time = 471.32 ms / 20 tokens ( 24.81 ms per token, 40.31 tokens per second) 0.13.327.924 I slot print_timing: id 0 | task 274 | total time = 902.71 ms / 187 tokens 0.13.327.925 I slot print_timing: id 0 | task 274 | graphs reused = 248 0.13.327.925 I slot print_timing: id 0 | task 274 | graph reallocs = 0 / 0 (same size) / (changed size) 0.13.327.953 I slot release: id 0 | task 274 | stop processing: n_tokens = 186, truncated = 0 0.13.332.081 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.161 0.13.336.500 I slot launch_slot_: id 0 | task 297 | processing task, is_child = 0 0.16.780.221 I slot print_timing: id 0 | task 297 | n_gen = 123, tg = 40.38 t/s, tg_3s = 40.71 t/s 0.19.791.574 I slot print_timing: id 0 | task 297 | n_gen = 244, tg = 40.28 t/s, tg_3s = 40.18 t/s 0.20.794.919 I slot print_timing: id 0 | task 297 | prompt eval time = 422.71 ms / 171 tokens ( 2.47 ms per token, 404.53 tokens per second) 0.20.794.922 I slot print_timing: id 0 | task 297 | eval time = 7035.70 ms / 284 tokens ( 24.86 ms per token, 40.22 tokens per second) 0.20.794.923 I slot print_timing: id 0 | task 297 | total time = 7458.41 ms / 455 tokens 0.20.794.924 I slot print_timing: id 0 | task 297 | graphs reused = 529 0.20.794.924 I slot print_timing: id 0 | task 297 | graph reallocs = 0 / 0 (same size) / (changed size) 0.20.794.949 I slot release: id 0 | task 297 | stop processing: n_tokens = 454, truncated = 0 0.20.799.398 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 0.20.808.596 I slot launch_slot_: id 0 | task 584 | processing task, is_child = 0 0.24.311.027 I slot print_timing: id 0 | task 584 | n_gen = 122, tg = 40.32 t/s, tg_3s = 40.65 t/s 0.24.658.236 I slot print_timing: id 0 | task 584 | prompt eval time = 501.26 ms / 214 tokens ( 2.34 ms per token, 426.93 tokens per second) 0.24.658.240 I slot print_timing: id 0 | task 584 | eval time = 3348.37 ms / 136 tokens ( 24.80 ms per token, 40.32 tokens per second) 0.24.658.240 I slot print_timing: id 0 | task 584 | total time = 3849.63 ms / 350 tokens 0.24.658.241 I slot print_timing: id 0 | task 584 | graphs reused = 662 0.24.658.241 I slot print_timing: id 0 | task 584 | graph reallocs = 0 / 0 (same size) / (changed size) 0.24.658.270 I slot release: id 0 | task 584 | stop processing: n_tokens = 349, truncated = 0 0.24.662.498 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.164 (> 0.100 thold), f_keep = 0.086 0.24.670.991 I slot launch_slot_: id 0 | task 723 | processing task, is_child = 0 0.26.070.724 I slot print_timing: id 0 | task 723 | prompt eval time = 482.75 ms / 183 tokens ( 2.64 ms per token, 379.08 tokens per second) 0.26.070.728 I slot print_timing: id 0 | task 723 | eval time = 916.97 ms / 38 tokens ( 24.78 ms per token, 40.35 tokens per second) 0.26.070.728 I slot print_timing: id 0 | task 723 | total time = 1399.72 ms / 221 tokens 0.26.070.729 I slot print_timing: id 0 | task 723 | graphs reused = 698 0.26.070.729 I slot print_timing: id 0 | task 723 | graph reallocs = 0 / 0 (same size) / (changed size) 0.26.070.753 I slot release: id 0 | task 723 | stop processing: n_tokens = 220, truncated = 0 0.26.074.925 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 0.26.078.781 I slot launch_slot_: id 0 | task 764 | processing task, is_child = 0 0.27.222.143 I slot print_timing: id 0 | task 764 | prompt eval time = 498.84 ms / 183 tokens ( 2.73 ms per token, 366.85 tokens per second) 0.27.222.147 I slot print_timing: id 0 | task 764 | eval time = 644.51 ms / 27 tokens ( 24.79 ms per token, 40.34 tokens per second) 0.27.222.148 I slot print_timing: id 0 | task 764 | total time = 1143.35 ms / 210 tokens 0.27.222.148 I slot print_timing: id 0 | task 764 | graphs reused = 723 0.27.222.149 I slot print_timing: id 0 | task 764 | graph reallocs = 0 / 0 (same size) / (changed size) 0.27.222.172 I slot release: id 0 | task 764 | stop processing: n_tokens = 209, truncated = 0 0.27.226.386 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.176 (> 0.100 thold), f_keep = 0.144 0.27.232.460 I slot launch_slot_: id 0 | task 794 | processing task, is_child = 0 0.28.521.210 I slot print_timing: id 0 | task 794 | prompt eval time = 446.11 ms / 170 tokens ( 2.62 ms per token, 381.07 tokens per second) 0.28.521.214 I slot print_timing: id 0 | task 794 | eval time = 842.63 ms / 35 tokens ( 24.78 ms per token, 40.35 tokens per second) 0.28.521.214 I slot print_timing: id 0 | task 794 | total time = 1288.74 ms / 205 tokens 0.28.521.215 I slot print_timing: id 0 | task 794 | graphs reused = 756 0.28.521.216 I slot print_timing: id 0 | task 794 | graph reallocs = 0 / 0 (same size) / (changed size) 0.28.521.233 I slot release: id 0 | task 794 | stop processing: n_tokens = 204, truncated = 0 0.28.525.170 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 0.28.531.004 I slot launch_slot_: id 0 | task 832 | processing task, is_child = 0 0.29.691.251 I slot print_timing: id 0 | task 832 | prompt eval time = 390.64 ms / 150 tokens ( 2.60 ms per token, 383.98 tokens per second) 0.29.691.254 I slot print_timing: id 0 | task 832 | eval time = 769.59 ms / 32 tokens ( 24.83 ms per token, 40.28 tokens per second) 0.29.691.255 I slot print_timing: id 0 | task 832 | total time = 1160.23 ms / 182 tokens 0.29.691.256 I slot print_timing: id 0 | task 832 | graphs reused = 786 0.29.691.256 I slot print_timing: id 0 | task 832 | graph reallocs = 0 / 0 (same size) / (changed size) 0.29.691.277 I slot release: id 0 | task 832 | stop processing: n_tokens = 181, truncated = 0 0.29.695.408 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.172 (> 0.100 thold), f_keep = 0.166 0.29.699.578 I slot launch_slot_: id 0 | task 867 | processing task, is_child = 0 0.30.654.771 I slot print_timing: id 0 | task 867 | prompt eval time = 433.15 ms / 174 tokens ( 2.49 ms per token, 401.71 tokens per second) 0.30.654.778 I slot print_timing: id 0 | task 867 | eval time = 522.03 ms / 22 tokens ( 24.86 ms per token, 40.23 tokens per second) 0.30.654.778 I slot print_timing: id 0 | task 867 | total time = 955.18 ms / 196 tokens 0.30.654.779 I slot print_timing: id 0 | task 867 | graphs reused = 806 0.30.654.779 I slot print_timing: id 0 | task 867 | graph reallocs = 0 / 0 (same size) / (changed size) 0.30.654.802 I slot release: id 0 | task 867 | stop processing: n_tokens = 195, truncated = 0 0.30.658.715 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.192 (> 0.100 thold), f_keep = 0.154 0.30.664.582 I slot launch_slot_: id 0 | task 892 | processing task, is_child = 0 0.31.569.004 I slot print_timing: id 0 | task 892 | prompt eval time = 432.29 ms / 156 tokens ( 2.77 ms per token, 360.87 tokens per second) 0.31.569.011 I slot print_timing: id 0 | task 892 | eval time = 472.12 ms / 20 tokens ( 24.85 ms per token, 40.24 tokens per second) 0.31.569.011 I slot print_timing: id 0 | task 892 | total time = 904.41 ms / 176 tokens 0.31.569.012 I slot print_timing: id 0 | task 892 | graphs reused = 824 0.31.569.013 I slot print_timing: id 0 | task 892 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.569.034 I slot release: id 0 | task 892 | stop processing: n_tokens = 175, truncated = 0 0.31.572.703 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 0.31.577.651 I slot launch_slot_: id 0 | task 915 | processing task, is_child = 0 0.32.434.582 I slot print_timing: id 0 | task 915 | prompt eval time = 433.71 ms / 152 tokens ( 2.85 ms per token, 350.46 tokens per second) 0.32.434.585 I slot print_timing: id 0 | task 915 | eval time = 423.21 ms / 18 tokens ( 24.89 ms per token, 40.17 tokens per second) 0.32.434.586 I slot print_timing: id 0 | task 915 | total time = 856.92 ms / 170 tokens 0.32.434.587 I slot print_timing: id 0 | task 915 | graphs reused = 840 0.32.434.587 I slot print_timing: id 0 | task 915 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.434.605 I slot release: id 0 | task 915 | stop processing: n_tokens = 169, truncated = 0 0.32.438.727 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 0.32.443.591 I slot launch_slot_: id 0 | task 936 | processing task, is_child = 0 0.33.869.772 I slot print_timing: id 0 | task 936 | prompt eval time = 483.08 ms / 187 tokens ( 2.58 ms per token, 387.10 tokens per second) 0.33.869.779 I slot print_timing: id 0 | task 936 | eval time = 943.09 ms / 39 tokens ( 24.82 ms per token, 40.29 tokens per second) 0.33.869.779 I slot print_timing: id 0 | task 936 | total time = 1426.17 ms / 226 tokens 0.33.869.780 I slot print_timing: id 0 | task 936 | graphs reused = 877 0.33.869.780 I slot print_timing: id 0 | task 936 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.869.800 I slot release: id 0 | task 936 | stop processing: n_tokens = 225, truncated = 0 0.33.873.664 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 0.33.878.916 I slot launch_slot_: id 0 | task 978 | processing task, is_child = 0 0.35.142.386 I slot print_timing: id 0 | task 978 | prompt eval time = 431.19 ms / 160 tokens ( 2.69 ms per token, 371.06 tokens per second) 0.35.142.389 I slot print_timing: id 0 | task 978 | eval time = 832.26 ms / 34 tokens ( 25.22 ms per token, 39.65 tokens per second) 0.35.142.390 I slot print_timing: id 0 | task 978 | total time = 1263.45 ms / 194 tokens 0.35.142.391 I slot print_timing: id 0 | task 978 | graphs reused = 909 0.35.142.392 I slot print_timing: id 0 | task 978 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.142.424 I slot release: id 0 | task 978 | stop processing: n_tokens = 193, truncated = 0 0.35.146.569 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.144 (> 0.100 thold), f_keep = 0.155 0.35.152.150 I slot launch_slot_: id 0 | task 1015 | processing task, is_child = 0 0.36.569.965 I slot print_timing: id 0 | task 1015 | prompt eval time = 499.89 ms / 208 tokens ( 2.40 ms per token, 416.09 tokens per second) 0.36.569.975 I slot print_timing: id 0 | task 1015 | eval time = 917.92 ms / 38 tokens ( 24.81 ms per token, 40.31 tokens per second) 0.36.569.976 I slot print_timing: id 0 | task 1015 | total time = 1417.81 ms / 246 tokens 0.36.569.977 I slot print_timing: id 0 | task 1015 | graphs reused = 945 0.36.569.977 I slot print_timing: id 0 | task 1015 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.569.996 I slot release: id 0 | task 1015 | stop processing: n_tokens = 245, truncated = 0 0.36.573.957 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 0.36.580.471 I slot launch_slot_: id 0 | task 1056 | processing task, is_child = 0 0.40.078.795 I slot print_timing: id 0 | task 1056 | n_gen = 122, tg = 40.32 t/s, tg_3s = 40.66 t/s 0.40.600.564 I slot print_timing: id 0 | task 1056 | prompt eval time = 497.46 ms / 192 tokens ( 2.59 ms per token, 385.96 tokens per second) 0.40.600.571 I slot print_timing: id 0 | task 1056 | eval time = 3522.62 ms / 143 tokens ( 24.81 ms per token, 40.31 tokens per second) 0.40.600.571 I slot print_timing: id 0 | task 1056 | total time = 4020.08 ms / 335 tokens 0.40.600.572 I slot print_timing: id 0 | task 1056 | graphs reused = 1085 0.40.600.572 I slot print_timing: id 0 | task 1056 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.600.595 I slot release: id 0 | task 1056 | stop processing: n_tokens = 334, truncated = 0 0.40.604.817 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.152 (> 0.100 thold), f_keep = 0.090 0.40.612.299 I slot launch_slot_: id 0 | task 1202 | processing task, is_child = 0 0.42.297.968 I slot print_timing: id 0 | task 1202 | prompt eval time = 485.60 ms / 198 tokens ( 2.45 ms per token, 407.74 tokens per second) 0.42.297.972 I slot print_timing: id 0 | task 1202 | eval time = 1200.06 ms / 49 tokens ( 25.00 ms per token, 40.00 tokens per second) 0.42.297.972 I slot print_timing: id 0 | task 1202 | total time = 1685.66 ms / 247 tokens 0.42.297.973 I slot print_timing: id 0 | task 1202 | graphs reused = 1132 0.42.297.973 I slot print_timing: id 0 | task 1202 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.297.993 I slot release: id 0 | task 1202 | stop processing: n_tokens = 246, truncated = 0 0.42.302.375 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.128 (> 0.100 thold), f_keep = 0.122 0.42.308.748 I slot launch_slot_: id 0 | task 1254 | processing task, is_child = 0 0.43.781.792 I slot print_timing: id 0 | task 1254 | prompt eval time = 552.98 ms / 235 tokens ( 2.35 ms per token, 424.97 tokens per second) 0.43.781.796 I slot print_timing: id 0 | task 1254 | eval time = 920.05 ms / 38 tokens ( 24.87 ms per token, 40.22 tokens per second) 0.43.781.796 I slot print_timing: id 0 | task 1254 | total time = 1473.04 ms / 273 tokens 0.43.781.797 I slot print_timing: id 0 | task 1254 | graphs reused = 1167 0.43.781.798 I slot print_timing: id 0 | task 1254 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.781.826 I slot release: id 0 | task 1254 | stop processing: n_tokens = 272, truncated = 0 0.43.785.802 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.114 0.43.793.079 I slot launch_slot_: id 0 | task 1295 | processing task, is_child = 0 0.45.135.687 I slot print_timing: id 0 | task 1295 | prompt eval time = 498.77 ms / 199 tokens ( 2.51 ms per token, 398.98 tokens per second) 0.45.135.694 I slot print_timing: id 0 | task 1295 | eval time = 843.82 ms / 35 tokens ( 24.82 ms per token, 40.29 tokens per second) 0.45.135.695 I slot print_timing: id 0 | task 1295 | total time = 1342.60 ms / 234 tokens 0.45.135.695 I slot print_timing: id 0 | task 1295 | graphs reused = 1200 0.45.135.696 I slot print_timing: id 0 | task 1295 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.135.715 I slot release: id 0 | task 1295 | stop processing: n_tokens = 233, truncated = 0 0.45.139.656 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 0.45.145.125 I slot launch_slot_: id 0 | task 1333 | processing task, is_child = 0 0.46.465.259 I slot print_timing: id 0 | task 1333 | prompt eval time = 431.83 ms / 157 tokens ( 2.75 ms per token, 363.57 tokens per second) 0.46.465.265 I slot print_timing: id 0 | task 1333 | eval time = 888.29 ms / 37 tokens ( 24.67 ms per token, 40.53 tokens per second) 0.46.465.265 I slot print_timing: id 0 | task 1333 | total time = 1320.12 ms / 194 tokens 0.46.465.266 I slot print_timing: id 0 | task 1333 | graphs reused = 1235 0.46.465.267 I slot print_timing: id 0 | task 1333 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.465.286 I slot release: id 0 | task 1333 | stop processing: n_tokens = 193, truncated = 0 0.46.469.293 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.168 (> 0.100 thold), f_keep = 0.161 0.46.473.956 I slot launch_slot_: id 0 | task 1373 | processing task, is_child = 0 0.47.801.643 I slot print_timing: id 0 | task 1373 | prompt eval time = 435.13 ms / 184 tokens ( 2.36 ms per token, 422.86 tokens per second) 0.47.801.647 I slot print_timing: id 0 | task 1373 | eval time = 892.54 ms / 37 tokens ( 24.79 ms per token, 40.33 tokens per second) 0.47.801.647 I slot print_timing: id 0 | task 1373 | total time = 1327.67 ms / 221 tokens 0.47.801.648 I slot print_timing: id 0 | task 1373 | graphs reused = 1270 0.47.801.649 I slot print_timing: id 0 | task 1373 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.801.667 I slot release: id 0 | task 1373 | stop processing: n_tokens = 220, truncated = 0 0.47.805.899 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.140 (> 0.100 thold), f_keep = 0.136 0.47.811.974 I slot launch_slot_: id 0 | task 1413 | processing task, is_child = 0 0.49.641.544 I slot print_timing: id 0 | task 1413 | prompt eval time = 563.42 ms / 214 tokens ( 2.63 ms per token, 379.82 tokens per second) 0.49.641.551 I slot print_timing: id 0 | task 1413 | eval time = 1266.14 ms / 52 tokens ( 24.83 ms per token, 40.28 tokens per second) 0.49.641.552 I slot print_timing: id 0 | task 1413 | total time = 1829.56 ms / 266 tokens 0.49.641.552 I slot print_timing: id 0 | task 1413 | graphs reused = 1319 0.49.641.553 I slot print_timing: id 0 | task 1413 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.641.574 I slot release: id 0 | task 1413 | stop processing: n_tokens = 265, truncated = 0 0.49.645.823 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.161 (> 0.100 thold), f_keep = 0.113 0.49.651.873 I slot launch_slot_: id 0 | task 1468 | processing task, is_child = 0 0.51.016.799 I slot print_timing: id 0 | task 1468 | prompt eval time = 497.15 ms / 186 tokens ( 2.67 ms per token, 374.13 tokens per second) 0.51.016.805 I slot print_timing: id 0 | task 1468 | eval time = 867.76 ms / 36 tokens ( 24.79 ms per token, 40.33 tokens per second) 0.51.016.806 I slot print_timing: id 0 | task 1468 | total time = 1364.91 ms / 222 tokens 0.51.016.806 I slot print_timing: id 0 | task 1468 | graphs reused = 1353 0.51.016.807 I slot print_timing: id 0 | task 1468 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.016.829 I slot release: id 0 | task 1468 | stop processing: n_tokens = 221, truncated = 0 0.51.020.893 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.184 (> 0.100 thold), f_keep = 0.136 0.51.027.052 I slot launch_slot_: id 0 | task 1507 | processing task, is_child = 0 0.52.328.343 I slot print_timing: id 0 | task 1507 | prompt eval time = 433.48 ms / 163 tokens ( 2.66 ms per token, 376.03 tokens per second) 0.52.328.347 I slot print_timing: id 0 | task 1507 | eval time = 867.80 ms / 36 tokens ( 24.79 ms per token, 40.33 tokens per second) 0.52.328.347 I slot print_timing: id 0 | task 1507 | total time = 1301.28 ms / 199 tokens 0.52.328.348 I slot print_timing: id 0 | task 1507 | graphs reused = 1387 0.52.328.348 I slot print_timing: id 0 | task 1507 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.328.366 I slot release: id 0 | task 1507 | stop processing: n_tokens = 198, truncated = 0 0.52.332.399 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 0.52.337.013 I slot launch_slot_: id 0 | task 1546 | processing task, is_child = 0 0.54.119.174 I slot print_timing: id 0 | task 1546 | prompt eval time = 421.18 ms / 163 tokens ( 2.58 ms per token, 387.01 tokens per second) 0.54.119.179 I slot print_timing: id 0 | task 1546 | eval time = 1360.97 ms / 56 tokens ( 24.74 ms per token, 40.41 tokens per second) 0.54.119.180 I slot print_timing: id 0 | task 1546 | total time = 1782.15 ms / 219 tokens 0.54.119.181 I slot print_timing: id 0 | task 1546 | graphs reused = 1441 0.54.119.181 I slot print_timing: id 0 | task 1546 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.119.199 I slot release: id 0 | task 1546 | stop processing: n_tokens = 218, truncated = 0 0.54.123.198 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.160 (> 0.100 thold), f_keep = 0.138 0.54.129.268 I slot launch_slot_: id 0 | task 1605 | processing task, is_child = 0 0.55.497.468 I slot print_timing: id 0 | task 1605 | prompt eval time = 499.21 ms / 187 tokens ( 2.67 ms per token, 374.59 tokens per second) 0.55.497.473 I slot print_timing: id 0 | task 1605 | eval time = 868.98 ms / 36 tokens ( 24.83 ms per token, 40.28 tokens per second) 0.55.497.474 I slot print_timing: id 0 | task 1605 | total time = 1368.19 ms / 223 tokens 0.55.497.475 I slot print_timing: id 0 | task 1605 | graphs reused = 1475 0.55.497.475 I slot print_timing: id 0 | task 1605 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.497.495 I slot release: id 0 | task 1605 | stop processing: n_tokens = 222, truncated = 0 0.55.501.665 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 0.55.507.959 I slot launch_slot_: id 0 | task 1644 | processing task, is_child = 0 0.56.850.165 I slot print_timing: id 0 | task 1644 | prompt eval time = 499.85 ms / 205 tokens ( 2.44 ms per token, 410.13 tokens per second) 0.56.850.171 I slot print_timing: id 0 | task 1644 | eval time = 842.35 ms / 35 tokens ( 24.77 ms per token, 40.36 tokens per second) 0.56.850.172 I slot print_timing: id 0 | task 1644 | total time = 1342.19 ms / 240 tokens 0.56.850.173 I slot print_timing: id 0 | task 1644 | graphs reused = 1508 0.56.850.173 I slot print_timing: id 0 | task 1644 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.850.193 I slot release: id 0 | task 1644 | stop processing: n_tokens = 239, truncated = 0 0.56.853.913 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.190 (> 0.100 thold), f_keep = 0.126 0.56.859.227 I slot launch_slot_: id 0 | task 1682 | processing task, is_child = 0 0.58.059.892 I slot print_timing: id 0 | task 1682 | prompt eval time = 434.73 ms / 158 tokens ( 2.75 ms per token, 363.44 tokens per second) 0.58.059.899 I slot print_timing: id 0 | task 1682 | eval time = 765.92 ms / 32 tokens ( 24.71 ms per token, 40.47 tokens per second) 0.58.059.899 I slot print_timing: id 0 | task 1682 | total time = 1200.66 ms / 190 tokens 0.58.059.900 I slot print_timing: id 0 | task 1682 | graphs reused = 1538 0.58.059.901 I slot print_timing: id 0 | task 1682 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.059.918 I slot release: id 0 | task 1682 | stop processing: n_tokens = 189, truncated = 0 0.58.064.012 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 0.58.068.497 I slot launch_slot_: id 0 | task 1717 | processing task, is_child = 0 0.59.279.274 I slot print_timing: id 0 | task 1717 | prompt eval time = 490.28 ms / 196 tokens ( 2.50 ms per token, 399.77 tokens per second) 0.59.279.280 I slot print_timing: id 0 | task 1717 | eval time = 720.49 ms / 30 tokens ( 24.84 ms per token, 40.25 tokens per second) 0.59.279.280 I slot print_timing: id 0 | task 1717 | total time = 1210.77 ms / 226 tokens 0.59.279.281 I slot print_timing: id 0 | task 1717 | graphs reused = 1566 0.59.279.281 I slot print_timing: id 0 | task 1717 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.279.301 I slot release: id 0 | task 1717 | stop processing: n_tokens = 225, truncated = 0 0.59.283.210 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.236 (> 0.100 thold), f_keep = 0.133 0.59.289.890 I slot launch_slot_: id 0 | task 1750 | processing task, is_child = 0 1.00.175.759 I slot print_timing: id 0 | task 1750 | prompt eval time = 363.50 ms / 127 tokens ( 2.86 ms per token, 349.39 tokens per second) 1.00.175.765 I slot print_timing: id 0 | task 1750 | eval time = 522.36 ms / 22 tokens ( 24.87 ms per token, 40.20 tokens per second) 1.00.175.765 I slot print_timing: id 0 | task 1750 | total time = 885.86 ms / 149 tokens 1.00.175.766 I slot print_timing: id 0 | task 1750 | graphs reused = 1586 1.00.175.767 I slot print_timing: id 0 | task 1750 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.175.789 I slot release: id 0 | task 1750 | stop processing: n_tokens = 148, truncated = 0 1.00.179.633 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.224 (> 0.100 thold), f_keep = 0.203 1.00.183.243 I slot launch_slot_: id 0 | task 1775 | processing task, is_child = 0 1.01.934.480 I slot print_timing: id 0 | task 1775 | prompt eval time = 367.39 ms / 134 tokens ( 2.74 ms per token, 364.73 tokens per second) 1.01.934.484 I slot print_timing: id 0 | task 1775 | eval time = 1383.84 ms / 57 tokens ( 24.71 ms per token, 40.47 tokens per second) 1.01.934.485 I slot print_timing: id 0 | task 1775 | total time = 1751.23 ms / 191 tokens 1.01.934.485 I slot print_timing: id 0 | task 1775 | graphs reused = 1641 1.01.934.486 I slot print_timing: id 0 | task 1775 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.934.503 I slot release: id 0 | task 1775 | stop processing: n_tokens = 190, truncated = 0 1.01.938.226 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.158 1.01.943.118 I slot launch_slot_: id 0 | task 1835 | processing task, is_child = 0 1.02.774.615 I slot print_timing: id 0 | task 1835 | prompt eval time = 432.55 ms / 148 tokens ( 2.92 ms per token, 342.16 tokens per second) 1.02.774.623 I slot print_timing: id 0 | task 1835 | eval time = 398.94 ms / 17 tokens ( 24.93 ms per token, 40.11 tokens per second) 1.02.774.623 I slot print_timing: id 0 | task 1835 | total time = 831.49 ms / 165 tokens 1.02.774.624 I slot print_timing: id 0 | task 1835 | graphs reused = 1656 1.02.774.624 I slot print_timing: id 0 | task 1835 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.774.648 I slot release: id 0 | task 1835 | stop processing: n_tokens = 164, truncated = 0 1.02.778.503 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 1.02.783.454 I slot launch_slot_: id 0 | task 1855 | processing task, is_child = 0 1.03.869.643 I slot print_timing: id 0 | task 1855 | prompt eval time = 416.24 ms / 145 tokens ( 2.87 ms per token, 348.36 tokens per second) 1.03.869.648 I slot print_timing: id 0 | task 1855 | eval time = 669.93 ms / 28 tokens ( 24.81 ms per token, 40.30 tokens per second) 1.03.869.649 I slot print_timing: id 0 | task 1855 | total time = 1086.17 ms / 173 tokens 1.03.869.649 I slot print_timing: id 0 | task 1855 | graphs reused = 1682 1.03.869.650 I slot print_timing: id 0 | task 1855 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.869.678 I slot release: id 0 | task 1855 | stop processing: n_tokens = 172, truncated = 0 1.03.873.887 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 1.03.878.838 I slot launch_slot_: id 0 | task 1886 | processing task, is_child = 0 1.05.144.194 I slot print_timing: id 0 | task 1886 | prompt eval time = 485.53 ms / 200 tokens ( 2.43 ms per token, 411.92 tokens per second) 1.05.144.198 I slot print_timing: id 0 | task 1886 | eval time = 779.82 ms / 32 tokens ( 25.16 ms per token, 39.75 tokens per second) 1.05.144.199 I slot print_timing: id 0 | task 1886 | total time = 1265.35 ms / 232 tokens 1.05.144.199 I slot print_timing: id 0 | task 1886 | graphs reused = 1712 1.05.144.200 I slot print_timing: id 0 | task 1886 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.144.224 I slot release: id 0 | task 1886 | stop processing: n_tokens = 231, truncated = 0 1.05.149.209 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 231, t_last = 323037069794 1.05.155.913 I slot launch_slot_: id 0 | task 1921 | processing task, is_child = 0 1.07.332.450 I slot print_timing: id 0 | task 1921 | prompt eval time = 727.23 ms / 326 tokens ( 2.23 ms per token, 448.28 tokens per second) 1.07.332.457 I slot print_timing: id 0 | task 1921 | eval time = 1449.30 ms / 59 tokens ( 24.99 ms per token, 40.02 tokens per second) 1.07.332.458 I slot print_timing: id 0 | task 1921 | total time = 2176.52 ms / 385 tokens 1.07.332.458 I slot print_timing: id 0 | task 1921 | graphs reused = 1769 1.07.332.459 I slot print_timing: id 0 | task 1921 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.332.492 I slot release: id 0 | task 1921 | stop processing: n_tokens = 384, truncated = 0 1.07.336.604 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 1.07.347.081 I slot launch_slot_: id 0 | task 1983 | processing task, is_child = 0 1.08.304.477 I slot print_timing: id 0 | task 1983 | prompt eval time = 386.58 ms / 148 tokens ( 2.61 ms per token, 382.84 tokens per second) 1.08.304.484 I slot print_timing: id 0 | task 1983 | eval time = 570.81 ms / 24 tokens ( 24.82 ms per token, 40.29 tokens per second) 1.08.304.485 I slot print_timing: id 0 | task 1983 | total time = 957.39 ms / 172 tokens 1.08.304.485 I slot print_timing: id 0 | task 1983 | graphs reused = 1791 1.08.304.486 I slot print_timing: id 0 | task 1983 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.304.508 I slot release: id 0 | task 1983 | stop processing: n_tokens = 171, truncated = 0 1.08.308.581 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 1.08.311.279 I slot launch_slot_: id 0 | task 2010 | processing task, is_child = 0 1.09.404.638 I slot print_timing: id 0 | task 2010 | prompt eval time = 424.21 ms / 175 tokens ( 2.42 ms per token, 412.53 tokens per second) 1.09.404.644 I slot print_timing: id 0 | task 2010 | eval time = 669.13 ms / 28 tokens ( 24.78 ms per token, 40.35 tokens per second) 1.09.404.645 I slot print_timing: id 0 | task 2010 | total time = 1093.35 ms / 203 tokens 1.09.404.646 I slot print_timing: id 0 | task 2010 | graphs reused = 1817 1.09.404.646 I slot print_timing: id 0 | task 2010 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.404.665 I slot release: id 0 | task 2010 | stop processing: n_tokens = 202, truncated = 0 1.09.409.032 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 1.09.414.962 I slot launch_slot_: id 0 | task 2041 | processing task, is_child = 0 1.10.938.567 I slot print_timing: id 0 | task 2041 | prompt eval time = 552.96 ms / 229 tokens ( 2.41 ms per token, 414.13 tokens per second) 1.10.938.570 I slot print_timing: id 0 | task 2041 | eval time = 970.64 ms / 40 tokens ( 24.89 ms per token, 40.18 tokens per second) 1.10.938.571 I slot print_timing: id 0 | task 2041 | total time = 1523.60 ms / 269 tokens 1.10.938.571 I slot print_timing: id 0 | task 2041 | graphs reused = 1854 1.10.938.572 I slot print_timing: id 0 | task 2041 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.938.597 I slot release: id 0 | task 2041 | stop processing: n_tokens = 268, truncated = 0 1.10.943.053 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 1.10.950.334 I slot launch_slot_: id 0 | task 2084 | processing task, is_child = 0 1.12.176.966 I slot print_timing: id 0 | task 2084 | prompt eval time = 554.27 ms / 238 tokens ( 2.33 ms per token, 429.39 tokens per second) 1.12.176.975 I slot print_timing: id 0 | task 2084 | eval time = 672.35 ms / 28 tokens ( 24.90 ms per token, 40.16 tokens per second) 1.12.176.976 I slot print_timing: id 0 | task 2084 | total time = 1226.62 ms / 266 tokens 1.12.176.976 I slot print_timing: id 0 | task 2084 | graphs reused = 1879 1.12.176.977 I slot print_timing: id 0 | task 2084 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.177.002 I slot release: id 0 | task 2084 | stop processing: n_tokens = 265, truncated = 0 1.12.180.870 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 1.12.188.613 I slot launch_slot_: id 0 | task 2115 | processing task, is_child = 0 1.13.471.638 I slot print_timing: id 0 | task 2115 | prompt eval time = 418.10 ms / 162 tokens ( 2.58 ms per token, 387.47 tokens per second) 1.13.471.644 I slot print_timing: id 0 | task 2115 | eval time = 864.92 ms / 36 tokens ( 24.71 ms per token, 40.47 tokens per second) 1.13.471.646 I slot print_timing: id 0 | task 2115 | total time = 1283.01 ms / 198 tokens 1.13.471.647 I slot print_timing: id 0 | task 2115 | graphs reused = 1913 1.13.471.647 I slot print_timing: id 0 | task 2115 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.471.673 I slot release: id 0 | task 2115 | stop processing: n_tokens = 197, truncated = 0 1.13.475.592 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.152 1.13.478.459 I slot launch_slot_: id 0 | task 2154 | processing task, is_child = 0 1.14.536.754 I slot print_timing: id 0 | task 2154 | prompt eval time = 434.88 ms / 169 tokens ( 2.57 ms per token, 388.62 tokens per second) 1.14.536.761 I slot print_timing: id 0 | task 2154 | eval time = 623.41 ms / 26 tokens ( 24.94 ms per token, 40.10 tokens per second) 1.14.536.762 I slot print_timing: id 0 | task 2154 | total time = 1058.28 ms / 195 tokens 1.14.536.762 I slot print_timing: id 0 | task 2154 | graphs reused = 1937 1.14.536.763 I slot print_timing: id 0 | task 2154 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.536.781 I slot release: id 0 | task 2154 | stop processing: n_tokens = 194, truncated = 0 1.14.540.753 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 1.14.546.226 I slot launch_slot_: id 0 | task 2183 | processing task, is_child = 0 1.15.704.516 I slot print_timing: id 0 | task 2183 | prompt eval time = 487.39 ms / 180 tokens ( 2.71 ms per token, 369.31 tokens per second) 1.15.704.523 I slot print_timing: id 0 | task 2183 | eval time = 670.89 ms / 28 tokens ( 24.85 ms per token, 40.25 tokens per second) 1.15.704.524 I slot print_timing: id 0 | task 2183 | total time = 1158.28 ms / 208 tokens 1.15.704.525 I slot print_timing: id 0 | task 2183 | graphs reused = 1963 1.15.704.525 I slot print_timing: id 0 | task 2183 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.704.550 I slot release: id 0 | task 2183 | stop processing: n_tokens = 207, truncated = 0 1.15.708.833 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 1.15.714.937 I slot launch_slot_: id 0 | task 2214 | processing task, is_child = 0 1.17.304.003 I slot print_timing: id 0 | task 2214 | prompt eval time = 498.99 ms / 203 tokens ( 2.46 ms per token, 406.82 tokens per second) 1.17.304.008 I slot print_timing: id 0 | task 2214 | eval time = 1090.07 ms / 45 tokens ( 24.77 ms per token, 40.36 tokens per second) 1.17.304.008 I slot print_timing: id 0 | task 2214 | total time = 1589.06 ms / 248 tokens 1.17.304.009 I slot print_timing: id 0 | task 2214 | graphs reused = 2006 1.17.304.009 I slot print_timing: id 0 | task 2214 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.304.035 I slot release: id 0 | task 2214 | stop processing: n_tokens = 247, truncated = 0 1.17.308.031 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 1.17.313.774 I slot launch_slot_: id 0 | task 2262 | processing task, is_child = 0 1.18.462.962 I slot print_timing: id 0 | task 2262 | prompt eval time = 431.44 ms / 157 tokens ( 2.75 ms per token, 363.90 tokens per second) 1.18.462.966 I slot print_timing: id 0 | task 2262 | eval time = 717.74 ms / 30 tokens ( 24.75 ms per token, 40.40 tokens per second) 1.18.462.967 I slot print_timing: id 0 | task 2262 | total time = 1149.18 ms / 187 tokens 1.18.462.967 I slot print_timing: id 0 | task 2262 | graphs reused = 2034 1.18.462.968 I slot print_timing: id 0 | task 2262 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.462.990 I slot release: id 0 | task 2262 | stop processing: n_tokens = 186, truncated = 0 1.18.467.356 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 1.18.472.018 I slot launch_slot_: id 0 | task 2295 | processing task, is_child = 0 1.19.571.650 I slot print_timing: id 0 | task 2295 | prompt eval time = 501.79 ms / 214 tokens ( 2.34 ms per token, 426.48 tokens per second) 1.19.571.654 I slot print_timing: id 0 | task 2295 | eval time = 597.84 ms / 25 tokens ( 24.91 ms per token, 40.14 tokens per second) 1.19.571.655 I slot print_timing: id 0 | task 2295 | total time = 1099.62 ms / 239 tokens 1.19.571.655 I slot print_timing: id 0 | task 2295 | graphs reused = 2057 1.19.571.656 I slot print_timing: id 0 | task 2295 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.571.680 I slot release: id 0 | task 2295 | stop processing: n_tokens = 238, truncated = 0 1.19.575.785 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.183 (> 0.100 thold), f_keep = 0.126 1.19.582.726 I slot launch_slot_: id 0 | task 2323 | processing task, is_child = 0 1.20.903.499 I slot print_timing: id 0 | task 2323 | prompt eval time = 419.93 ms / 164 tokens ( 2.56 ms per token, 390.55 tokens per second) 1.20.903.502 I slot print_timing: id 0 | task 2323 | eval time = 900.83 ms / 37 tokens ( 25.02 ms per token, 39.96 tokens per second) 1.20.903.503 I slot print_timing: id 0 | task 2323 | total time = 1320.76 ms / 201 tokens 1.20.903.504 I slot print_timing: id 0 | task 2323 | graphs reused = 2092 1.20.903.505 I slot print_timing: id 0 | task 2323 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.903.529 I slot release: id 0 | task 2323 | stop processing: n_tokens = 200, truncated = 0 1.20.907.568 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.181 (> 0.100 thold), f_keep = 0.150 1.20.911.118 I slot launch_slot_: id 0 | task 2363 | processing task, is_child = 0 1.22.111.801 I slot print_timing: id 0 | task 2363 | prompt eval time = 445.32 ms / 166 tokens ( 2.68 ms per token, 372.76 tokens per second) 1.22.111.805 I slot print_timing: id 0 | task 2363 | eval time = 755.35 ms / 31 tokens ( 25.18 ms per token, 39.72 tokens per second) 1.22.111.806 I slot print_timing: id 0 | task 2363 | total time = 1200.67 ms / 197 tokens 1.22.111.806 I slot print_timing: id 0 | task 2363 | graphs reused = 2121 1.22.111.807 I slot print_timing: id 0 | task 2363 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.111.825 I slot release: id 0 | task 2363 | stop processing: n_tokens = 196, truncated = 0 1.22.116.527 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 1.22.122.162 I slot launch_slot_: id 0 | task 2397 | processing task, is_child = 0 1.24.175.174 I slot print_timing: id 0 | task 2397 | prompt eval time = 659.22 ms / 277 tokens ( 2.38 ms per token, 420.19 tokens per second) 1.24.175.180 I slot print_timing: id 0 | task 2397 | eval time = 1393.78 ms / 57 tokens ( 24.89 ms per token, 40.18 tokens per second) 1.24.175.180 I slot print_timing: id 0 | task 2397 | total time = 2053.00 ms / 334 tokens 1.24.175.181 I slot print_timing: id 0 | task 2397 | graphs reused = 2176 1.24.175.182 I slot print_timing: id 0 | task 2397 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.175.220 I slot release: id 0 | task 2397 | stop processing: n_tokens = 333, truncated = 0 1.24.179.736 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.121 (> 0.100 thold), f_keep = 0.090 1.24.189.050 I slot launch_slot_: id 0 | task 2457 | processing task, is_child = 0 1.26.184.311 I slot print_timing: id 0 | task 2457 | prompt eval time = 555.94 ms / 248 tokens ( 2.24 ms per token, 446.09 tokens per second) 1.26.184.318 I slot print_timing: id 0 | task 2457 | eval time = 1439.31 ms / 59 tokens ( 24.82 ms per token, 40.30 tokens per second) 1.26.184.318 I slot print_timing: id 0 | task 2457 | total time = 1995.25 ms / 307 tokens 1.26.184.319 I slot print_timing: id 0 | task 2457 | graphs reused = 2232 1.26.184.320 I slot print_timing: id 0 | task 2457 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.184.342 I slot release: id 0 | task 2457 | stop processing: n_tokens = 306, truncated = 0 1.26.188.437 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 1.26.197.132 I slot launch_slot_: id 0 | task 2519 | processing task, is_child = 0 1.27.348.372 I slot print_timing: id 0 | task 2519 | prompt eval time = 433.49 ms / 159 tokens ( 2.73 ms per token, 366.79 tokens per second) 1.27.348.376 I slot print_timing: id 0 | task 2519 | eval time = 717.74 ms / 30 tokens ( 24.75 ms per token, 40.40 tokens per second) 1.27.348.376 I slot print_timing: id 0 | task 2519 | total time = 1151.23 ms / 189 tokens 1.27.348.377 I slot print_timing: id 0 | task 2519 | graphs reused = 2260 1.27.348.378 I slot print_timing: id 0 | task 2519 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.348.395 I slot release: id 0 | task 2519 | stop processing: n_tokens = 188, truncated = 0 1.27.352.682 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.153 (> 0.100 thold), f_keep = 0.160 1.27.355.636 I slot launch_slot_: id 0 | task 2552 | processing task, is_child = 0 1.28.599.488 I slot print_timing: id 0 | task 2552 | prompt eval time = 498.54 ms / 196 tokens ( 2.54 ms per token, 393.14 tokens per second) 1.28.599.495 I slot print_timing: id 0 | task 2552 | eval time = 745.29 ms / 31 tokens ( 24.84 ms per token, 40.25 tokens per second) 1.28.599.496 I slot print_timing: id 0 | task 2552 | total time = 1243.84 ms / 227 tokens 1.28.599.497 I slot print_timing: id 0 | task 2552 | graphs reused = 2289 1.28.599.497 I slot print_timing: id 0 | task 2552 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.599.517 I slot release: id 0 | task 2552 | stop processing: n_tokens = 226, truncated = 0 1.28.603.569 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 1.28.610.120 I slot launch_slot_: id 0 | task 2586 | processing task, is_child = 0 1.29.653.110 I slot print_timing: id 0 | task 2586 | prompt eval time = 421.86 ms / 150 tokens ( 2.81 ms per token, 355.57 tokens per second) 1.29.653.117 I slot print_timing: id 0 | task 2586 | eval time = 621.12 ms / 26 tokens ( 24.84 ms per token, 40.25 tokens per second) 1.29.653.118 I slot print_timing: id 0 | task 2586 | total time = 1042.98 ms / 176 tokens 1.29.653.118 I slot print_timing: id 0 | task 2586 | graphs reused = 2313 1.29.653.119 I slot print_timing: id 0 | task 2586 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.653.140 I slot release: id 0 | task 2586 | stop processing: n_tokens = 175, truncated = 0 1.29.657.671 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.140 (> 0.100 thold), f_keep = 0.171 1.29.662.092 I slot launch_slot_: id 0 | task 2615 | processing task, is_child = 0 1.31.183.001 I slot print_timing: id 0 | task 2615 | prompt eval time = 502.09 ms / 215 tokens ( 2.34 ms per token, 428.21 tokens per second) 1.31.183.007 I slot print_timing: id 0 | task 2615 | eval time = 1018.81 ms / 42 tokens ( 24.85 ms per token, 40.24 tokens per second) 1.31.183.007 I slot print_timing: id 0 | task 2615 | total time = 1520.90 ms / 257 tokens 1.31.183.008 I slot print_timing: id 0 | task 2615 | graphs reused = 2353 1.31.183.008 I slot print_timing: id 0 | task 2615 | graph reallocs = 0 / 0 (same size) / (changed size) 1.31.183.030 I slot release: id 0 | task 2615 | stop processing: n_tokens = 256, truncated = 0 1.31.187.843 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 256, t_last = 323063108600 1.31.194.979 I slot launch_slot_: id 0 | task 2660 | processing task, is_child = 0 1.32.685.960 I slot print_timing: id 0 | task 2660 | prompt eval time = 741.38 ms / 327 tokens ( 2.27 ms per token, 441.07 tokens per second) 1.32.685.964 I slot print_timing: id 0 | task 2660 | eval time = 749.59 ms / 31 tokens ( 24.99 ms per token, 40.02 tokens per second) 1.32.685.965 I slot print_timing: id 0 | task 2660 | total time = 1490.97 ms / 358 tokens 1.32.685.965 I slot print_timing: id 0 | task 2660 | graphs reused = 2382 1.32.685.966 I slot print_timing: id 0 | task 2660 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.685.995 I slot release: id 0 | task 2660 | stop processing: n_tokens = 357, truncated = 0 1.32.691.139 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 357, t_last = 323064611565 1.32.701.939 I slot launch_slot_: id 0 | task 2694 | processing task, is_child = 0 1.34.326.811 I slot print_timing: id 0 | task 2694 | prompt eval time = 844.09 ms / 399 tokens ( 2.12 ms per token, 472.70 tokens per second) 1.34.326.814 I slot print_timing: id 0 | task 2694 | eval time = 780.78 ms / 32 tokens ( 25.19 ms per token, 39.70 tokens per second) 1.34.326.815 I slot print_timing: id 0 | task 2694 | total time = 1624.86 ms / 431 tokens 1.34.326.816 I slot print_timing: id 0 | task 2694 | graphs reused = 2412 1.34.326.816 I slot print_timing: id 0 | task 2694 | graph reallocs = 0 / 0 (same size) / (changed size) 1.34.326.844 I slot release: id 0 | task 2694 | stop processing: n_tokens = 430, truncated = 0 1.34.333.013 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 430, t_last = 323066252414 1.34.346.461 I slot launch_slot_: id 0 | task 2729 | processing task, is_child = 0 1.38.047.817 I slot print_timing: id 0 | task 2729 | prompt eval time = 957.17 ms / 439 tokens ( 2.18 ms per token, 458.64 tokens per second) 1.38.047.821 I slot print_timing: id 0 | task 2729 | eval time = 2744.17 ms / 110 tokens ( 25.18 ms per token, 39.72 tokens per second) 1.38.047.821 I slot print_timing: id 0 | task 2729 | total time = 3701.34 ms / 549 tokens 1.38.047.822 I slot print_timing: id 0 | task 2729 | graphs reused = 2519 1.38.047.823 I slot print_timing: id 0 | task 2729 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.047.851 I slot release: id 0 | task 2729 | stop processing: n_tokens = 548, truncated = 0 1.38.053.609 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 548, t_last = 323069973421 1.38.069.396 I slot launch_slot_: id 0 | task 2842 | processing task, is_child = 0 1.39.773.920 I slot print_timing: id 0 | task 2842 | prompt eval time = 848.08 ms / 413 tokens ( 2.05 ms per token, 486.98 tokens per second) 1.39.773.924 I slot print_timing: id 0 | task 2842 | eval time = 856.43 ms / 35 tokens ( 25.19 ms per token, 39.70 tokens per second) 1.39.773.924 I slot print_timing: id 0 | task 2842 | total time = 1704.51 ms / 448 tokens 1.39.773.925 I slot print_timing: id 0 | task 2842 | graphs reused = 2552 1.39.773.925 I slot print_timing: id 0 | task 2842 | graph reallocs = 0 / 0 (same size) / (changed size) 1.39.773.952 I slot release: id 0 | task 2842 | stop processing: n_tokens = 447, truncated = 0 1.39.778.751 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 1.39.793.430 I slot launch_slot_: id 0 | task 2880 | processing task, is_child = 0 1.41.070.711 I slot print_timing: id 0 | task 2880 | prompt eval time = 605.52 ms / 268 tokens ( 2.26 ms per token, 442.59 tokens per second) 1.41.070.718 I slot print_timing: id 0 | task 2880 | eval time = 671.75 ms / 28 tokens ( 24.88 ms per token, 40.19 tokens per second) 1.41.070.718 I slot print_timing: id 0 | task 2880 | total time = 1277.27 ms / 296 tokens 1.41.070.719 I slot print_timing: id 0 | task 2880 | graphs reused = 2578 1.41.070.720 I slot print_timing: id 0 | task 2880 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.070.746 I slot release: id 0 | task 2880 | stop processing: n_tokens = 295, truncated = 0 1.41.075.777 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 295, t_last = 323072996316 1.41.078.475 I slot launch_slot_: id 0 | task 2911 | processing task, is_child = 0 1.43.551.393 I slot print_timing: id 0 | task 2911 | prompt eval time = 862.35 ms / 395 tokens ( 2.18 ms per token, 458.05 tokens per second) 1.43.551.398 I slot print_timing: id 0 | task 2911 | eval time = 1610.56 ms / 65 tokens ( 25.16 ms per token, 39.74 tokens per second) 1.43.551.399 I slot print_timing: id 0 | task 2911 | total time = 2472.91 ms / 460 tokens 1.43.551.399 I slot print_timing: id 0 | task 2911 | graphs reused = 2641 1.43.551.400 I slot print_timing: id 0 | task 2911 | graph reallocs = 0 / 0 (same size) / (changed size) 1.43.551.432 I slot release: id 0 | task 2911 | stop processing: n_tokens = 459, truncated = 0 1.43.556.700 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 459, t_last = 323075477002 1.43.570.516 I slot launch_slot_: id 0 | task 2979 | processing task, is_child = 0 1.45.096.914 I slot print_timing: id 0 | task 2979 | prompt eval time = 845.46 ms / 390 tokens ( 2.17 ms per token, 461.29 tokens per second) 1.45.096.917 I slot print_timing: id 0 | task 2979 | eval time = 680.93 ms / 28 tokens ( 25.22 ms per token, 39.65 tokens per second) 1.45.096.918 I slot print_timing: id 0 | task 2979 | total time = 1526.39 ms / 418 tokens 1.45.096.919 I slot print_timing: id 0 | task 2979 | graphs reused = 2667 1.45.096.919 I slot print_timing: id 0 | task 2979 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.096.951 I slot release: id 0 | task 2979 | stop processing: n_tokens = 417, truncated = 0 1.45.101.802 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 417, t_last = 323077022521 1.45.115.070 I slot launch_slot_: id 0 | task 3010 | processing task, is_child = 0 1.46.387.165 I slot print_timing: id 0 | task 3010 | prompt eval time = 672.65 ms / 304 tokens ( 2.21 ms per token, 451.95 tokens per second) 1.46.387.171 I slot print_timing: id 0 | task 3010 | eval time = 599.44 ms / 25 tokens ( 24.98 ms per token, 40.04 tokens per second) 1.46.387.171 I slot print_timing: id 0 | task 3010 | total time = 1272.08 ms / 329 tokens 1.46.387.172 I slot print_timing: id 0 | task 3010 | graphs reused = 2690 1.46.387.173 I slot print_timing: id 0 | task 3010 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.387.200 I slot release: id 0 | task 3010 | stop processing: n_tokens = 328, truncated = 0 1.46.392.024 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.104 (> 0.100 thold), f_keep = 0.091 1.46.398.288 I slot launch_slot_: id 0 | task 3038 | processing task, is_child = 0 1.47.817.884 I slot print_timing: id 0 | task 3038 | prompt eval time = 672.34 ms / 289 tokens ( 2.33 ms per token, 429.84 tokens per second) 1.47.817.888 I slot print_timing: id 0 | task 3038 | eval time = 747.24 ms / 31 tokens ( 24.91 ms per token, 40.15 tokens per second) 1.47.817.888 I slot print_timing: id 0 | task 3038 | total time = 1419.58 ms / 320 tokens 1.47.817.889 I slot print_timing: id 0 | task 3038 | graphs reused = 2719 1.47.817.890 I slot print_timing: id 0 | task 3038 | graph reallocs = 0 / 0 (same size) / (changed size) 1.47.817.913 I slot release: id 0 | task 3038 | stop processing: n_tokens = 319, truncated = 0 1.47.823.172 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 319, t_last = 323079743483 1.47.833.293 I slot launch_slot_: id 0 | task 3072 | processing task, is_child = 0 1.49.138.828 I slot print_timing: id 0 | task 3072 | prompt eval time = 778.26 ms / 360 tokens ( 2.16 ms per token, 462.57 tokens per second) 1.49.138.835 I slot print_timing: id 0 | task 3072 | eval time = 527.26 ms / 22 tokens ( 25.11 ms per token, 39.83 tokens per second) 1.49.138.835 I slot print_timing: id 0 | task 3072 | total time = 1305.52 ms / 382 tokens 1.49.138.836 I slot print_timing: id 0 | task 3072 | graphs reused = 2739 1.49.138.837 I slot print_timing: id 0 | task 3072 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.138.862 I slot release: id 0 | task 3072 | stop processing: n_tokens = 381, truncated = 0 1.49.143.775 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 381, t_last = 323081064432 1.49.156.007 I slot launch_slot_: id 0 | task 3097 | processing task, is_child = 0 1.50.918.785 I slot print_timing: id 0 | task 3097 | prompt eval time = 740.17 ms / 317 tokens ( 2.33 ms per token, 428.28 tokens per second) 1.50.918.788 I slot print_timing: id 0 | task 3097 | eval time = 1022.59 ms / 42 tokens ( 24.94 ms per token, 40.09 tokens per second) 1.50.918.789 I slot print_timing: id 0 | task 3097 | total time = 1762.77 ms / 359 tokens 1.50.918.790 I slot print_timing: id 0 | task 3097 | graphs reused = 2779 1.50.918.790 I slot print_timing: id 0 | task 3097 | graph reallocs = 0 / 0 (same size) / (changed size) 1.50.918.814 I slot release: id 0 | task 3097 | stop processing: n_tokens = 358, truncated = 0 1.50.923.486 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.121 (> 0.100 thold), f_keep = 0.084 1.50.930.399 I slot launch_slot_: id 0 | task 3142 | processing task, is_child = 0 1.51.979.452 I slot print_timing: id 0 | task 3142 | prompt eval time = 597.46 ms / 248 tokens ( 2.41 ms per token, 415.09 tokens per second) 1.51.979.459 I slot print_timing: id 0 | task 3142 | eval time = 451.59 ms / 19 tokens ( 25.09 ms per token, 39.86 tokens per second) 1.51.979.460 I slot print_timing: id 0 | task 3142 | total time = 1049.04 ms / 267 tokens 1.51.979.460 I slot print_timing: id 0 | task 3142 | graphs reused = 2795 1.51.979.461 I slot print_timing: id 0 | task 3142 | graph reallocs = 0 / 0 (same size) / (changed size) 1.51.979.482 I slot release: id 0 | task 3142 | stop processing: n_tokens = 266, truncated = 0 1.51.984.561 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 266, t_last = 323083905052 1.51.993.224 I slot launch_slot_: id 0 | task 3164 | processing task, is_child = 0 1.53.701.421 I slot print_timing: id 0 | task 3164 | prompt eval time = 733.41 ms / 331 tokens ( 2.22 ms per token, 451.32 tokens per second) 1.53.701.428 I slot print_timing: id 0 | task 3164 | eval time = 974.77 ms / 40 tokens ( 24.99 ms per token, 40.01 tokens per second) 1.53.701.428 I slot print_timing: id 0 | task 3164 | total time = 1708.18 ms / 371 tokens 1.53.701.429 I slot print_timing: id 0 | task 3164 | graphs reused = 2833 1.53.701.429 I slot print_timing: id 0 | task 3164 | graph reallocs = 0 / 0 (same size) / (changed size) 1.53.701.454 I slot release: id 0 | task 3164 | stop processing: n_tokens = 370, truncated = 0 1.53.706.294 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.107 (> 0.100 thold), f_keep = 0.081 1.53.717.383 I slot launch_slot_: id 0 | task 3207 | processing task, is_child = 0 1.54.975.324 I slot print_timing: id 0 | task 3207 | prompt eval time = 659.80 ms / 280 tokens ( 2.36 ms per token, 424.37 tokens per second) 1.54.975.330 I slot print_timing: id 0 | task 3207 | eval time = 598.12 ms / 25 tokens ( 24.92 ms per token, 40.13 tokens per second) 1.54.975.331 I slot print_timing: id 0 | task 3207 | total time = 1257.92 ms / 305 tokens 1.54.975.331 I slot print_timing: id 0 | task 3207 | graphs reused = 2856 1.54.975.332 I slot print_timing: id 0 | task 3207 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.975.353 I slot release: id 0 | task 3207 | stop processing: n_tokens = 304, truncated = 0 1.54.979.909 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 1.54.987.494 I slot launch_slot_: id 0 | task 3235 | processing task, is_child = 0 1.56.144.462 I slot print_timing: id 0 | task 3235 | prompt eval time = 607.09 ms / 252 tokens ( 2.41 ms per token, 415.09 tokens per second) 1.56.144.468 I slot print_timing: id 0 | task 3235 | eval time = 549.86 ms / 23 tokens ( 24.99 ms per token, 40.01 tokens per second) 1.56.144.469 I slot print_timing: id 0 | task 3235 | total time = 1156.95 ms / 275 tokens 1.56.144.470 I slot print_timing: id 0 | task 3235 | graphs reused = 2876 1.56.144.471 I slot print_timing: id 0 | task 3235 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.144.491 I slot release: id 0 | task 3235 | stop processing: n_tokens = 274, truncated = 0 1.56.149.333 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 1.56.158.078 I slot launch_slot_: id 0 | task 3261 | processing task, is_child = 0 1.57.281.627 I slot print_timing: id 0 | task 3261 | prompt eval time = 599.69 ms / 267 tokens ( 2.25 ms per token, 445.23 tokens per second) 1.57.281.631 I slot print_timing: id 0 | task 3261 | eval time = 523.85 ms / 22 tokens ( 24.95 ms per token, 40.09 tokens per second) 1.57.281.632 I slot print_timing: id 0 | task 3261 | total time = 1123.54 ms / 289 tokens 1.57.281.633 I slot print_timing: id 0 | task 3261 | graphs reused = 2896 1.57.281.633 I slot print_timing: id 0 | task 3261 | graph reallocs = 0 / 0 (same size) / (changed size) 1.57.281.656 I slot release: id 0 | task 3261 | stop processing: n_tokens = 288, truncated = 0 1.57.285.987 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.118 (> 0.100 thold), f_keep = 0.104 1.57.294.278 I slot launch_slot_: id 0 | task 3286 | processing task, is_child = 0 1.58.423.301 I slot print_timing: id 0 | task 3286 | prompt eval time = 604.31 ms / 255 tokens ( 2.37 ms per token, 421.97 tokens per second) 1.58.423.308 I slot print_timing: id 0 | task 3286 | eval time = 524.70 ms / 22 tokens ( 24.99 ms per token, 40.02 tokens per second) 1.58.423.308 I slot print_timing: id 0 | task 3286 | total time = 1129.01 ms / 277 tokens 1.58.423.309 I slot print_timing: id 0 | task 3286 | graphs reused = 2915 1.58.423.309 I slot print_timing: id 0 | task 3286 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.423.331 I slot release: id 0 | task 3286 | stop processing: n_tokens = 276, truncated = 0 1.58.428.830 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 276, t_last = 323090348902 1.58.437.941 I slot launch_slot_: id 0 | task 3311 | processing task, is_child = 0 2.00.016.435 I slot print_timing: id 0 | task 3311 | prompt eval time = 846.83 ms / 397 tokens ( 2.13 ms per token, 468.81 tokens per second) 2.00.016.438 I slot print_timing: id 0 | task 3311 | eval time = 731.66 ms / 30 tokens ( 25.23 ms per token, 39.64 tokens per second) 2.00.016.439 I slot print_timing: id 0 | task 3311 | total time = 1578.49 ms / 427 tokens 2.00.016.444 I slot print_timing: id 0 | task 3311 | graphs reused = 2943 2.00.016.444 I slot print_timing: id 0 | task 3311 | graph reallocs = 0 / 0 (same size) / (changed size) 2.00.016.472 I slot release: id 0 | task 3311 | stop processing: n_tokens = 426, truncated = 0 2.00.021.148 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 2.00.034.641 I slot launch_slot_: id 0 | task 3344 | processing task, is_child = 0 2.02.849.979 I slot print_timing: id 0 | task 3344 | prompt eval time = 671.96 ms / 290 tokens ( 2.32 ms per token, 431.57 tokens per second) 2.02.849.983 I slot print_timing: id 0 | task 3344 | eval time = 2143.37 ms / 87 tokens ( 24.92 ms per token, 40.12 tokens per second) 2.02.849.984 I slot print_timing: id 0 | task 3344 | total time = 2815.33 ms / 377 tokens 2.02.849.984 I slot print_timing: id 0 | task 3344 | graphs reused = 3028 2.02.849.985 I slot print_timing: id 0 | task 3344 | graph reallocs = 0 / 0 (same size) / (changed size) 2.02.850.016 I slot release: id 0 | task 3344 | stop processing: n_tokens = 376, truncated = 0 2.02.856.637 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 376, t_last = 323094775586 2.02.863.415 I slot launch_slot_: id 0 | task 3434 | processing task, is_child = 0 2.05.113.658 I slot print_timing: id 0 | task 3434 | prompt eval time = 1291.76 ms / 612 tokens ( 2.11 ms per token, 473.77 tokens per second) 2.05.113.667 I slot print_timing: id 0 | task 3434 | eval time = 958.47 ms / 39 tokens ( 25.22 ms per token, 39.65 tokens per second) 2.05.113.668 I slot print_timing: id 0 | task 3434 | total time = 2250.23 ms / 651 tokens 2.05.113.669 I slot print_timing: id 0 | task 3434 | graphs reused = 3065 2.05.113.669 I slot print_timing: id 0 | task 3434 | graph reallocs = 0 / 0 (same size) / (changed size) 2.05.113.709 I slot release: id 0 | task 3434 | stop processing: n_tokens = 650, truncated = 0 2.05.118.345 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.109 (> 0.100 thold), f_keep = 0.046 2.05.135.703 I slot launch_slot_: id 0 | task 3477 | processing task, is_child = 0 2.06.394.812 I slot print_timing: id 0 | task 3477 | prompt eval time = 610.59 ms / 275 tokens ( 2.22 ms per token, 450.38 tokens per second) 2.06.394.816 I slot print_timing: id 0 | task 3477 | eval time = 648.51 ms / 27 tokens ( 24.94 ms per token, 40.09 tokens per second) 2.06.394.816 I slot print_timing: id 0 | task 3477 | total time = 1259.10 ms / 302 tokens 2.06.394.817 I slot print_timing: id 0 | task 3477 | graphs reused = 3090 2.06.394.817 I slot print_timing: id 0 | task 3477 | graph reallocs = 0 / 0 (same size) / (changed size) 2.06.394.845 I slot release: id 0 | task 3477 | stop processing: n_tokens = 301, truncated = 0 2.06.400.704 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 301, t_last = 323098320415 2.06.405.163 I slot launch_slot_: id 0 | task 3507 | processing task, is_child = 0 2.07.983.109 I slot print_timing: id 0 | task 3507 | prompt eval time = 972.19 ms / 456 tokens ( 2.13 ms per token, 469.04 tokens per second) 2.07.983.116 I slot print_timing: id 0 | task 3507 | eval time = 605.74 ms / 25 tokens ( 25.24 ms per token, 39.62 tokens per second) 2.07.983.117 I slot print_timing: id 0 | task 3507 | total time = 1577.94 ms / 481 tokens 2.07.983.117 I slot print_timing: id 0 | task 3507 | graphs reused = 3113 2.07.983.118 I slot print_timing: id 0 | task 3507 | graph reallocs = 0 / 0 (same size) / (changed size) 2.07.983.151 I slot release: id 0 | task 3507 | stop processing: n_tokens = 480, truncated = 0 2.07.989.718 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 480, t_last = 323099908721 2.08.005.781 I slot launch_slot_: id 0 | task 3535 | processing task, is_child = 0 2.10.137.729 I slot print_timing: id 0 | task 3535 | prompt eval time = 1173.17 ms / 542 tokens ( 2.16 ms per token, 462.00 tokens per second) 2.10.137.733 I slot print_timing: id 0 | task 3535 | eval time = 958.77 ms / 39 tokens ( 25.23 ms per token, 39.63 tokens per second) 2.10.137.733 I slot print_timing: id 0 | task 3535 | total time = 2131.94 ms / 581 tokens 2.10.137.734 I slot print_timing: id 0 | task 3535 | graphs reused = 3150 2.10.137.734 I slot print_timing: id 0 | task 3535 | graph reallocs = 0 / 0 (same size) / (changed size) 2.10.137.786 I slot release: id 0 | task 3535 | stop processing: n_tokens = 580, truncated = 0 2.10.143.338 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 580, t_last = 323102063356 2.10.160.628 I slot launch_slot_: id 0 | task 3578 | processing task, is_child = 0 2.12.082.135 I slot print_timing: id 0 | task 3578 | prompt eval time = 838.36 ms / 361 tokens ( 2.32 ms per token, 430.60 tokens per second) 2.12.082.141 I slot print_timing: id 0 | task 3578 | eval time = 1083.14 ms / 44 tokens ( 25.19 ms per token, 39.70 tokens per second) 2.12.082.142 I slot print_timing: id 0 | task 3578 | total time = 1921.49 ms / 405 tokens 2.12.082.143 I slot print_timing: id 0 | task 3578 | graphs reused = 3192 2.12.082.144 I slot print_timing: id 0 | task 3578 | graph reallocs = 0 / 0 (same size) / (changed size) 2.12.082.177 I slot release: id 0 | task 3578 | stop processing: n_tokens = 429, truncated = 0 2.12.086.848 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 2.12.094.982 I slot launch_slot_: id 0 | task 3625 | processing task, is_child = 0 2.13.577.538 I slot print_timing: id 0 | task 3625 | prompt eval time = 610.10 ms / 258 tokens ( 2.36 ms per token, 422.88 tokens per second) 2.13.577.545 I slot print_timing: id 0 | task 3625 | eval time = 872.45 ms / 36 tokens ( 24.93 ms per token, 40.12 tokens per second) 2.13.577.545 I slot print_timing: id 0 | task 3625 | total time = 1482.55 ms / 294 tokens 2.13.577.546 I slot print_timing: id 0 | task 3625 | graphs reused = 3226 2.13.577.547 I slot print_timing: id 0 | task 3625 | graph reallocs = 0 / 0 (same size) / (changed size) 2.13.577.580 I slot release: id 0 | task 3625 | stop processing: n_tokens = 317, truncated = 0 2.13.583.146 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 317, t_last = 323105503150 2.13.586.597 I slot launch_slot_: id 0 | task 3664 | processing task, is_child = 0 2.14.965.132 I slot print_timing: id 0 | task 3664 | prompt eval time = 847.64 ms / 379 tokens ( 2.24 ms per token, 447.12 tokens per second) 2.14.965.142 I slot print_timing: id 0 | task 3664 | eval time = 530.89 ms / 22 tokens ( 25.28 ms per token, 39.56 tokens per second) 2.14.965.143 I slot print_timing: id 0 | task 3664 | total time = 1378.53 ms / 401 tokens 2.14.965.144 I slot print_timing: id 0 | task 3664 | graphs reused = 3246 2.14.965.145 I slot print_timing: id 0 | task 3664 | graph reallocs = 0 / 0 (same size) / (changed size) 2.14.965.176 I slot release: id 0 | task 3664 | stop processing: n_tokens = 423, truncated = 0 2.14.971.780 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 423, t_last = 323106890746 2.14.985.182 I slot launch_slot_: id 0 | task 3689 | processing task, is_child = 0 2.17.025.922 I slot print_timing: id 0 | task 3689 | prompt eval time = 1180.96 ms / 540 tokens ( 2.19 ms per token, 457.26 tokens per second) 2.17.025.928 I slot print_timing: id 0 | task 3689 | eval time = 859.77 ms / 35 tokens ( 25.29 ms per token, 39.55 tokens per second) 2.17.025.928 I slot print_timing: id 0 | task 3689 | total time = 2040.73 ms / 575 tokens 2.17.025.929 I slot print_timing: id 0 | task 3689 | graphs reused = 3279 2.17.025.929 I slot print_timing: id 0 | task 3689 | graph reallocs = 0 / 0 (same size) / (changed size) 2.17.025.967 I slot release: id 0 | task 3689 | stop processing: n_tokens = 596, truncated = 0 2.17.031.546 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 596, t_last = 323108951537 2.17.050.932 I slot launch_slot_: id 0 | task 3728 | processing task, is_child = 0 2.18.549.150 I slot print_timing: id 0 | task 3728 | prompt eval time = 791.65 ms / 370 tokens ( 2.14 ms per token, 467.38 tokens per second) 2.18.549.153 I slot print_timing: id 0 | task 3728 | eval time = 706.56 ms / 29 tokens ( 25.23 ms per token, 39.63 tokens per second) 2.18.549.154 I slot print_timing: id 0 | task 3728 | total time = 1498.21 ms / 399 tokens 2.18.549.155 I slot print_timing: id 0 | task 3728 | graphs reused = 3306 2.18.549.155 I slot print_timing: id 0 | task 3728 | graph reallocs = 0 / 0 (same size) / (changed size) 2.18.549.183 I slot release: id 0 | task 3728 | stop processing: n_tokens = 422, truncated = 0 2.18.554.289 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 422, t_last = 323110474753 2.18.558.410 I slot launch_slot_: id 0 | task 3760 | processing task, is_child = 0 2.19.894.939 I slot print_timing: id 0 | task 3760 | prompt eval time = 733.36 ms / 336 tokens ( 2.18 ms per token, 458.17 tokens per second) 2.19.894.942 I slot print_timing: id 0 | task 3760 | eval time = 603.16 ms / 25 tokens ( 25.13 ms per token, 39.79 tokens per second) 2.19.894.943 I slot print_timing: id 0 | task 3760 | total time = 1336.52 ms / 361 tokens 2.19.894.944 I slot print_timing: id 0 | task 3760 | graphs reused = 3329 2.19.894.944 I slot print_timing: id 0 | task 3760 | graph reallocs = 0 / 0 (same size) / (changed size) 2.19.894.971 I slot release: id 0 | task 3760 | stop processing: n_tokens = 383, truncated = 0 2.19.899.798 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.115 (> 0.100 thold), f_keep = 0.078 2.19.907.323 I slot launch_slot_: id 0 | task 3788 | processing task, is_child = 0 2.21.079.953 I slot print_timing: id 0 | task 3788 | prompt eval time = 599.80 ms / 261 tokens ( 2.30 ms per token, 435.14 tokens per second) 2.21.079.959 I slot print_timing: id 0 | task 3788 | eval time = 572.82 ms / 24 tokens ( 24.91 ms per token, 40.15 tokens per second) 2.21.079.960 I slot print_timing: id 0 | task 3788 | total time = 1172.62 ms / 285 tokens 2.21.079.960 I slot print_timing: id 0 | task 3788 | graphs reused = 3351 2.21.079.961 I slot print_timing: id 0 | task 3788 | graph reallocs = 0 / 0 (same size) / (changed size) 2.21.079.984 I slot release: id 0 | task 3788 | stop processing: n_tokens = 284, truncated = 0 2.21.084.745 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 2.21.087.464 I slot launch_slot_: id 0 | task 3815 | processing task, is_child = 0 2.22.796.707 I slot print_timing: id 0 | task 3815 | prompt eval time = 733.98 ms / 299 tokens ( 2.45 ms per token, 407.37 tokens per second) 2.22.796.711 I slot print_timing: id 0 | task 3815 | eval time = 975.25 ms / 40 tokens ( 25.01 ms per token, 39.99 tokens per second) 2.22.796.712 I slot print_timing: id 0 | task 3815 | total time = 1709.23 ms / 339 tokens 2.22.796.713 I slot print_timing: id 0 | task 3815 | graphs reused = 3389 2.22.796.713 I slot print_timing: id 0 | task 3815 | graph reallocs = 0 / 0 (same size) / (changed size) 2.22.796.738 I slot release: id 0 | task 3815 | stop processing: n_tokens = 338, truncated = 0 2.22.801.801 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 338, t_last = 323114722308 2.22.810.302 I slot launch_slot_: id 0 | task 3858 | processing task, is_child = 0 2.24.161.622 I slot print_timing: id 0 | task 3858 | prompt eval time = 726.03 ms / 319 tokens ( 2.28 ms per token, 439.37 tokens per second) 2.24.161.626 I slot print_timing: id 0 | task 3858 | eval time = 625.27 ms / 26 tokens ( 25.01 ms per token, 39.98 tokens per second) 2.24.161.626 I slot print_timing: id 0 | task 3858 | total time = 1351.31 ms / 345 tokens 2.24.161.627 I slot print_timing: id 0 | task 3858 | graphs reused = 3413 2.24.161.627 I slot print_timing: id 0 | task 3858 | graph reallocs = 0 / 0 (same size) / (changed size) 2.24.161.658 I slot release: id 0 | task 3858 | stop processing: n_tokens = 344, truncated = 0 2.24.167.639 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 344, t_last = 323116087228 2.24.178.861 I slot launch_slot_: id 0 | task 3887 | processing task, is_child = 0 2.25.960.350 I slot print_timing: id 0 | task 3887 | prompt eval time = 897.98 ms / 423 tokens ( 2.12 ms per token, 471.06 tokens per second) 2.25.960.356 I slot print_timing: id 0 | task 3887 | eval time = 883.50 ms / 36 tokens ( 25.24 ms per token, 39.62 tokens per second) 2.25.960.357 I slot print_timing: id 0 | task 3887 | total time = 1781.48 ms / 459 tokens 2.25.960.357 I slot print_timing: id 0 | task 3887 | graphs reused = 3447 2.25.960.358 I slot print_timing: id 0 | task 3887 | graph reallocs = 0 / 0 (same size) / (changed size) 2.25.960.392 I slot release: id 0 | task 3887 | stop processing: n_tokens = 458, truncated = 0 2.25.965.826 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 323117885963 2.25.980.283 I slot launch_slot_: id 0 | task 3926 | processing task, is_child = 0 2.27.475.014 I slot print_timing: id 0 | task 3926 | prompt eval time = 790.62 ms / 366 tokens ( 2.16 ms per token, 462.93 tokens per second) 2.27.475.018 I slot print_timing: id 0 | task 3926 | eval time = 704.10 ms / 29 tokens ( 25.15 ms per token, 39.77 tokens per second) 2.27.475.019 I slot print_timing: id 0 | task 3926 | total time = 1494.72 ms / 395 tokens 2.27.475.019 I slot print_timing: id 0 | task 3926 | graphs reused = 3474 2.27.475.020 I slot print_timing: id 0 | task 3926 | graph reallocs = 0 / 0 (same size) / (changed size) 2.27.475.048 I slot release: id 0 | task 3926 | stop processing: n_tokens = 394, truncated = 0 2.27.481.700 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 394, t_last = 323119400618 2.27.494.471 I slot launch_slot_: id 0 | task 3958 | processing task, is_child = 0 2.29.443.557 I slot print_timing: id 0 | task 3958 | prompt eval time = 1241.63 ms / 560 tokens ( 2.22 ms per token, 451.02 tokens per second) 2.29.443.561 I slot print_timing: id 0 | task 3958 | eval time = 707.45 ms / 29 tokens ( 25.27 ms per token, 39.58 tokens per second) 2.29.443.566 I slot print_timing: id 0 | task 3958 | total time = 1949.07 ms / 589 tokens 2.29.443.567 I slot print_timing: id 0 | task 3958 | graphs reused = 3501 2.29.443.568 I slot print_timing: id 0 | task 3958 | graph reallocs = 0 / 0 (same size) / (changed size) 2.29.443.604 I slot release: id 0 | task 3958 | stop processing: n_tokens = 588, truncated = 0 2.29.448.919 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 588, t_last = 323121369174 2.29.448.989 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 60.760 MiB) 2.29.448.995 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 44.657 MiB) 2.29.465.947 I slot launch_slot_: id 0 | task 3991 | processing task, is_child = 0 2.30.819.761 I slot print_timing: id 0 | task 3991 | prompt eval time = 800.25 ms / 366 tokens ( 2.19 ms per token, 457.35 tokens per second) 2.30.819.764 I slot print_timing: id 0 | task 3991 | eval time = 553.55 ms / 23 tokens ( 25.16 ms per token, 39.74 tokens per second) 2.30.819.765 I slot print_timing: id 0 | task 3991 | total time = 1353.80 ms / 389 tokens 2.30.819.770 I slot print_timing: id 0 | task 3991 | graphs reused = 3522 2.30.819.775 I slot print_timing: id 0 | task 3991 | graph reallocs = 0 / 0 (same size) / (changed size) 2.30.819.804 I slot release: id 0 | task 3991 | stop processing: n_tokens = 388, truncated = 0 2.30.825.372 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 388, t_last = 323122745374 2.30.825.430 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 59.776 MiB) 2.30.825.439 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 71.238 MiB) 2.30.832.583 I slot launch_slot_: id 0 | task 4017 | processing task, is_child = 0 2.32.689.763 I slot print_timing: id 0 | task 4017 | prompt eval time = 849.85 ms / 406 tokens ( 2.09 ms per token, 477.73 tokens per second) 2.32.689.771 I slot print_timing: id 0 | task 4017 | eval time = 1007.32 ms / 41 tokens ( 25.18 ms per token, 39.71 tokens per second) 2.32.689.771 I slot print_timing: id 0 | task 4017 | total time = 1857.17 ms / 447 tokens 2.32.689.772 I slot print_timing: id 0 | task 4017 | graphs reused = 3561 2.32.689.772 I slot print_timing: id 0 | task 4017 | graph reallocs = 0 / 0 (same size) / (changed size) 2.32.689.805 I slot release: id 0 | task 4017 | stop processing: n_tokens = 446, truncated = 0 2.32.695.277 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 446, t_last = 323124615375 2.32.695.336 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 64.874 MiB) 2.32.695.341 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 62.132 MiB) 2.32.708.822 I slot launch_slot_: id 0 | task 4061 | processing task, is_child = 0 2.34.536.988 I slot print_timing: id 0 | task 4061 | prompt eval time = 845.65 ms / 379 tokens ( 2.23 ms per token, 448.18 tokens per second) 2.34.536.991 I slot print_timing: id 0 | task 4061 | eval time = 982.50 ms / 40 tokens ( 25.19 ms per token, 39.69 tokens per second) 2.34.536.992 I slot print_timing: id 0 | task 4061 | total time = 1828.15 ms / 419 tokens 2.34.536.992 I slot print_timing: id 0 | task 4061 | graphs reused = 3599 2.34.536.993 I slot print_timing: id 0 | task 4061 | graph reallocs = 0 / 0 (same size) / (changed size) 2.34.537.020 I slot release: id 0 | task 4061 | stop processing: n_tokens = 418, truncated = 0 2.34.543.200 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 418, t_last = 323126462590 2.34.543.258 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.989 MiB) 2.34.543.266 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 95.710 MiB) 2.34.553.695 I slot launch_slot_: id 0 | task 4104 | processing task, is_child = 0 2.36.289.236 I slot print_timing: id 0 | task 4104 | prompt eval time = 1028.09 ms / 487 tokens ( 2.11 ms per token, 473.69 tokens per second) 2.36.289.242 I slot print_timing: id 0 | task 4104 | eval time = 707.44 ms / 29 tokens ( 25.27 ms per token, 39.58 tokens per second) 2.36.289.243 I slot print_timing: id 0 | task 4104 | total time = 1735.53 ms / 516 tokens 2.36.289.243 I slot print_timing: id 0 | task 4104 | graphs reused = 3625 2.36.289.244 I slot print_timing: id 0 | task 4104 | graph reallocs = 0 / 0 (same size) / (changed size) 2.36.289.278 I slot release: id 0 | task 4104 | stop processing: n_tokens = 515, truncated = 0 2.36.295.547 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 515, t_last = 323128214849 2.36.295.609 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 53.271 MiB) 2.36.295.612 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 57.701 MiB) 2.36.295.614 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 97.715 MiB) 2.36.307.487 I slot launch_slot_: id 0 | task 4136 | processing task, is_child = 0 2.39.055.528 I slot print_timing: id 0 | task 4136 | prompt eval time = 1234.07 ms / 565 tokens ( 2.18 ms per token, 457.83 tokens per second) 2.39.055.532 I slot print_timing: id 0 | task 4136 | eval time = 1513.96 ms / 61 tokens ( 25.23 ms per token, 39.63 tokens per second) 2.39.055.532 I slot print_timing: id 0 | task 4136 | total time = 2748.03 ms / 626 tokens 2.39.055.533 I slot print_timing: id 0 | task 4136 | graphs reused = 3684 2.39.055.533 I slot print_timing: id 0 | task 4136 | graph reallocs = 0 / 0 (same size) / (changed size) 2.39.055.567 I slot release: id 0 | task 4136 | stop processing: n_tokens = 625, truncated = 0 2.39.059.786 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.153 (> 0.100 thold), f_keep = 0.048 2.39.059.863 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 90.964 MiB) 2.39.059.867 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 64.909 MiB) 2.39.081.492 I slot launch_slot_: id 0 | task 4201 | processing task, is_child = 0 2.41.002.865 I slot print_timing: id 0 | task 4201 | prompt eval time = 484.35 ms / 196 tokens ( 2.47 ms per token, 404.67 tokens per second) 2.41.002.868 I slot print_timing: id 0 | task 4201 | eval time = 1437.01 ms / 59 tokens ( 24.78 ms per token, 40.36 tokens per second) 2.41.002.869 I slot print_timing: id 0 | task 4201 | total time = 1921.36 ms / 255 tokens 2.41.002.869 I slot print_timing: id 0 | task 4201 | graphs reused = 3741 2.41.002.870 I slot print_timing: id 0 | task 4201 | graph reallocs = 0 / 0 (same size) / (changed size) 2.41.002.895 I slot release: id 0 | task 4201 | stop processing: n_tokens = 254, truncated = 0 2.41.007.427 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.140 (> 0.100 thold), f_keep = 0.118 2.41.007.473 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.261 MiB) 2.41.009.616 I slot launch_slot_: id 0 | task 4263 | processing task, is_child = 0 2.43.045.750 I slot print_timing: id 0 | task 4263 | prompt eval time = 549.30 ms / 214 tokens ( 2.57 ms per token, 389.59 tokens per second) 2.43.045.754 I slot print_timing: id 0 | task 4263 | eval time = 1486.82 ms / 61 tokens ( 24.78 ms per token, 40.35 tokens per second) 2.43.045.755 I slot print_timing: id 0 | task 4263 | total time = 2036.12 ms / 275 tokens 2.43.045.755 I slot print_timing: id 0 | task 4263 | graphs reused = 3799 2.43.045.756 I slot print_timing: id 0 | task 4263 | graph reallocs = 0 / 0 (same size) / (changed size) 2.43.045.781 I slot release: id 0 | task 4263 | stop processing: n_tokens = 274, truncated = 0 2.43.050.028 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.149 (> 0.100 thold), f_keep = 0.109 2.43.050.076 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 61.921 MiB) 2.43.052.407 I slot launch_slot_: id 0 | task 4327 | processing task, is_child = 0 2.45.695.725 I slot print_timing: id 0 | task 4327 | prompt eval time = 547.18 ms / 201 tokens ( 2.72 ms per token, 367.34 tokens per second) 2.45.695.730 I slot print_timing: id 0 | task 4327 | eval time = 2096.13 ms / 85 tokens ( 24.95 ms per token, 40.07 tokens per second) 2.45.695.731 I slot print_timing: id 0 | task 4327 | total time = 2643.31 ms / 286 tokens 2.45.695.731 I slot print_timing: id 0 | task 4327 | graphs reused = 3881 2.45.695.732 I slot print_timing: id 0 | task 4327 | graph reallocs = 0 / 0 (same size) / (changed size) 2.45.695.752 I slot release: id 0 | task 4327 | stop processing: n_tokens = 285, truncated = 0 2.45.700.131 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.179 (> 0.100 thold), f_keep = 0.105 2.45.700.181 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 53.728 MiB) 2.45.702.551 I slot launch_slot_: id 0 | task 4415 | processing task, is_child = 0 2.47.904.337 I slot print_timing: id 0 | task 4415 | prompt eval time = 493.53 ms / 168 tokens ( 2.94 ms per token, 340.40 tokens per second) 2.47.904.341 I slot print_timing: id 0 | task 4415 | eval time = 1708.24 ms / 70 tokens ( 24.76 ms per token, 40.39 tokens per second) 2.47.904.341 I slot print_timing: id 0 | task 4415 | total time = 2201.78 ms / 238 tokens 2.47.904.342 I slot print_timing: id 0 | task 4415 | graphs reused = 3949 2.47.904.343 I slot print_timing: id 0 | task 4415 | graph reallocs = 0 / 0 (same size) / (changed size) 2.47.904.367 I slot release: id 0 | task 4415 | stop processing: n_tokens = 237, truncated = 0 2.47.909.019 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.129 (> 0.100 thold), f_keep = 0.127 2.47.909.060 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 60.760 MiB) 2.47.909.067 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 54.677 MiB) 2.47.911.024 I slot launch_slot_: id 0 | task 4488 | processing task, is_child = 0 2.50.871.254 I slot print_timing: id 0 | task 4488 | prompt eval time = 553.48 ms / 232 tokens ( 2.39 ms per token, 419.17 tokens per second) 2.50.871.260 I slot print_timing: id 0 | task 4488 | eval time = 2406.74 ms / 98 tokens ( 24.81 ms per token, 40.30 tokens per second) 2.50.871.261 I slot print_timing: id 0 | task 4488 | total time = 2960.22 ms / 330 tokens 2.50.871.261 I slot print_timing: id 0 | task 4488 | graphs reused = 4044 2.50.871.262 I slot print_timing: id 0 | task 4488 | graph reallocs = 0 / 0 (same size) / (changed size) 2.50.871.287 I slot release: id 0 | task 4488 | stop processing: n_tokens = 329, truncated = 0 2.50.875.682 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.120 (> 0.100 thold), f_keep = 0.091 2.50.875.733 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 53.306 MiB) 2.50.878.452 I slot launch_slot_: id 0 | task 4589 | processing task, is_child = 0 2.54.500.470 I slot print_timing: id 0 | task 4589 | n_gen = 122, tg = 40.18 t/s, tg_3s = 40.51 t/s 2.54.550.417 I slot print_timing: id 0 | task 4589 | prompt eval time = 610.67 ms / 249 tokens ( 2.45 ms per token, 407.75 tokens per second) 2.54.550.420 I slot print_timing: id 0 | task 4589 | eval time = 3061.28 ms / 124 tokens ( 24.89 ms per token, 40.18 tokens per second) 2.54.550.420 I slot print_timing: id 0 | task 4589 | total time = 3671.95 ms / 373 tokens 2.54.550.421 I slot print_timing: id 0 | task 4589 | graphs reused = 4165 2.54.550.422 I slot print_timing: id 0 | task 4589 | graph reallocs = 0 / 0 (same size) / (changed size) 2.54.550.447 I slot release: id 0 | task 4589 | stop processing: n_tokens = 372, truncated = 0 2.54.555.115 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.106 (> 0.100 thold), f_keep = 0.091 2.54.555.168 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 66.562 MiB) 2.54.555.172 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 57.315 MiB) 2.54.558.122 I slot launch_slot_: id 0 | task 4716 | processing task, is_child = 0 2.58.235.788 I slot print_timing: id 0 | task 4716 | n_gen = 121, tg = 39.93 t/s, tg_3s = 40.26 t/s 2.58.738.118 I slot print_timing: id 0 | task 4716 | prompt eval time = 672.15 ms / 320 tokens ( 2.10 ms per token, 476.08 tokens per second) 2.58.738.124 I slot print_timing: id 0 | task 4716 | eval time = 3507.83 ms / 141 tokens ( 25.06 ms per token, 39.91 tokens per second) 2.58.738.125 I slot print_timing: id 0 | task 4716 | total time = 4179.99 ms / 461 tokens 2.58.738.125 I slot print_timing: id 0 | task 4716 | graphs reused = 4304 2.58.738.126 I slot print_timing: id 0 | task 4716 | graph reallocs = 0 / 0 (same size) / (changed size) 2.58.738.149 I slot release: id 0 | task 4716 | stop processing: n_tokens = 460, truncated = 0 2.58.742.268 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.167 (> 0.100 thold), f_keep = 0.065 2.58.742.332 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 74.227 MiB) 2.58.742.337 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 84.530 MiB) 2.58.750.464 I slot launch_slot_: id 0 | task 4860 | processing task, is_child = 0 3.02.201.646 I slot print_timing: id 0 | task 4860 | n_gen = 123, tg = 40.40 t/s, tg_3s = 40.73 t/s 3.05.219.917 I slot print_timing: id 0 | task 4860 | n_gen = 244, tg = 40.24 t/s, tg_3s = 40.09 t/s 3.07.959.404 I slot print_timing: id 0 | task 4860 | prompt eval time = 431.02 ms / 180 tokens ( 2.39 ms per token, 417.62 tokens per second) 3.07.959.410 I slot print_timing: id 0 | task 4860 | eval time = 8777.91 ms / 353 tokens ( 24.94 ms per token, 40.10 tokens per second) 3.07.959.411 I slot print_timing: id 0 | task 4860 | total time = 9208.93 ms / 533 tokens 3.07.959.412 I slot print_timing: id 0 | task 4860 | graphs reused = 4653 3.07.959.412 I slot print_timing: id 0 | task 4860 | graph reallocs = 0 / 0 (same size) / (changed size) 3.07.959.430 I slot release: id 0 | task 4860 | stop processing: n_tokens = 532, truncated = 0 3.07.963.788 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.163 (> 0.100 thold), f_keep = 0.056 3.07.963.852 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 71.414 MiB) 3.07.975.316 I slot launch_slot_: id 0 | task 5216 | processing task, is_child = 0 3.11.110.801 I slot print_timing: id 0 | task 5216 | prompt eval time = 485.88 ms / 184 tokens ( 2.64 ms per token, 378.70 tokens per second) 3.11.110.805 I slot print_timing: id 0 | task 5216 | eval time = 2649.60 ms / 108 tokens ( 24.76 ms per token, 40.38 tokens per second) 3.11.110.805 I slot print_timing: id 0 | task 5216 | total time = 3135.48 ms / 292 tokens 3.11.110.806 I slot print_timing: id 0 | task 5216 | graphs reused = 4758 3.11.110.807 I slot print_timing: id 0 | task 5216 | graph reallocs = 0 / 0 (same size) / (changed size) 3.11.110.830 I slot release: id 0 | task 5216 | stop processing: n_tokens = 291, truncated = 0 3.11.115.371 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.128 (> 0.100 thold), f_keep = 0.103 3.11.115.421 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 82.771 MiB) 3.11.117.941 I slot launch_slot_: id 0 | task 5327 | processing task, is_child = 0 3.13.649.139 I slot print_timing: id 0 | task 5327 | prompt eval time = 546.05 ms / 235 tokens ( 2.32 ms per token, 430.36 tokens per second) 3.13.649.143 I slot print_timing: id 0 | task 5327 | eval time = 1985.13 ms / 81 tokens ( 24.81 ms per token, 40.30 tokens per second) 3.13.649.144 I slot print_timing: id 0 | task 5327 | total time = 2531.19 ms / 316 tokens 3.13.649.144 I slot print_timing: id 0 | task 5327 | graphs reused = 4836 3.13.649.145 I slot print_timing: id 0 | task 5327 | graph reallocs = 0 / 0 (same size) / (changed size) 3.13.649.166 I slot release: id 0 | task 5327 | stop processing: n_tokens = 315, truncated = 0 3.13.653.707 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.104 (> 0.100 thold), f_keep = 0.095 3.13.653.752 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 69.480 MiB) 3.13.656.231 I slot launch_slot_: id 0 | task 5411 | processing task, is_child = 0 3.17.338.806 I slot print_timing: id 0 | task 5411 | n_gen = 122, tg = 40.13 t/s, tg_3s = 40.46 t/s 3.20.353.700 I slot print_timing: id 0 | task 5411 | n_gen = 242, tg = 39.97 t/s, tg_3s = 39.80 t/s 3.23.373.177 I slot print_timing: id 0 | task 5411 | n_gen = 362, tg = 39.89 t/s, tg_3s = 39.74 t/s 3.26.391.956 I slot print_timing: id 0 | task 5411 | n_gen = 482, tg = 39.86 t/s, tg_3s = 39.75 t/s 3.27.348.412 I slot print_timing: id 0 | task 5411 | prompt eval time = 667.50 ms / 289 tokens ( 2.31 ms per token, 432.96 tokens per second) 3.27.348.416 I slot print_timing: id 0 | task 5411 | eval time = 13024.67 ms / 520 tokens ( 25.10 ms per token, 39.85 tokens per second) 3.27.348.417 I slot print_timing: id 0 | task 5411 | total time = 13692.17 ms / 809 tokens 3.27.348.417 I slot print_timing: id 0 | task 5411 | graphs reused = 5352 3.27.348.418 I slot print_timing: id 0 | task 5411 | graph reallocs = 0 / 0 (same size) / (changed size) 3.27.348.440 I slot release: id 0 | task 5411 | stop processing: n_tokens = 808, truncated = 0 3.27.352.918 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.183 (> 0.100 thold), f_keep = 0.054 3.27.352.998 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 57.526 MiB) 3.27.353.007 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 66.175 MiB) 3.27.362.567 I slot launch_slot_: id 0 | task 5934 | processing task, is_child = 0 3.29.311.507 I slot print_timing: id 0 | task 5934 | prompt eval time = 558.75 ms / 241 tokens ( 2.32 ms per token, 431.32 tokens per second) 3.29.311.511 I slot print_timing: id 0 | task 5934 | eval time = 1390.18 ms / 57 tokens ( 24.82 ms per token, 40.28 tokens per second) 3.29.311.511 I slot print_timing: id 0 | task 5934 | total time = 1948.93 ms / 298 tokens 3.29.311.512 I slot print_timing: id 0 | task 5934 | graphs reused = 5406 3.29.311.513 I slot print_timing: id 0 | task 5934 | graph reallocs = 0 / 0 (same size) / (changed size) 3.29.311.533 I slot release: id 0 | task 5934 | stop processing: n_tokens = 297, truncated = 0 3.29.315.880 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.126 (> 0.100 thold), f_keep = 0.101 3.29.315.983 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 76.723 MiB) 3.29.318.685 I slot launch_slot_: id 0 | task 5994 | processing task, is_child = 0 3.32.888.884 I slot print_timing: id 0 | task 5994 | n_gen = 122, tg = 40.26 t/s, tg_3s = 40.60 t/s 3.33.214.779 I slot print_timing: id 0 | task 5994 | prompt eval time = 565.01 ms / 239 tokens ( 2.36 ms per token, 423.00 tokens per second) 3.33.214.782 I slot print_timing: id 0 | task 5994 | eval time = 3331.07 ms / 135 tokens ( 24.86 ms per token, 40.23 tokens per second) 3.33.214.783 I slot print_timing: id 0 | task 5994 | total time = 3896.08 ms / 374 tokens 3.33.214.784 I slot print_timing: id 0 | task 5994 | graphs reused = 5538 3.33.214.784 I slot print_timing: id 0 | task 5994 | graph reallocs = 0 / 0 (same size) / (changed size) 3.33.214.808 I slot release: id 0 | task 5994 | stop processing: n_tokens = 373, truncated = 0 3.33.219.452 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.110 (> 0.100 thold), f_keep = 0.080 3.33.219.505 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 67.265 MiB) 3.33.226.173 I slot launch_slot_: id 0 | task 6132 | processing task, is_child = 0 3.36.044.877 I slot print_timing: id 0 | task 6132 | prompt eval time = 679.23 ms / 273 tokens ( 2.49 ms per token, 401.93 tokens per second) 3.36.044.881 I slot print_timing: id 0 | task 6132 | eval time = 2139.46 ms / 87 tokens ( 24.88 ms per token, 40.20 tokens per second) 3.36.044.882 I slot print_timing: id 0 | task 6132 | total time = 2818.68 ms / 360 tokens 3.36.044.883 I slot print_timing: id 0 | task 6132 | graphs reused = 5623 3.36.044.883 I slot print_timing: id 0 | task 6132 | graph reallocs = 0 / 0 (same size) / (changed size) 3.36.044.911 I slot release: id 0 | task 6132 | stop processing: n_tokens = 359, truncated = 0 3.36.049.467 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.142 (> 0.100 thold), f_keep = 0.084 3.36.049.523 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 59.389 MiB) 3.36.049.642 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 62.729 MiB) 3.36.056.012 I slot launch_slot_: id 0 | task 6222 | processing task, is_child = 0 3.39.565.565 I slot print_timing: id 0 | task 6222 | n_gen = 123, tg = 40.36 t/s, tg_3s = 40.69 t/s 3.40.985.626 I slot print_timing: id 0 | task 6222 | prompt eval time = 486.99 ms / 212 tokens ( 2.30 ms per token, 435.33 tokens per second) 3.40.985.630 I slot print_timing: id 0 | task 6222 | eval time = 4442.61 ms / 180 tokens ( 24.82 ms per token, 40.29 tokens per second) 3.40.985.631 I slot print_timing: id 0 | task 6222 | total time = 4929.61 ms / 392 tokens 3.40.985.632 I slot print_timing: id 0 | task 6222 | graphs reused = 5800 3.40.985.632 I slot print_timing: id 0 | task 6222 | graph reallocs = 0 / 0 (same size) / (changed size) 3.40.985.657 I slot release: id 0 | task 6222 | stop processing: n_tokens = 391, truncated = 0 3.40.990.323 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.105 (> 0.100 thold), f_keep = 0.077 3.40.990.382 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 67.828 MiB) 3.40.996.853 I slot launch_slot_: id 0 | task 6405 | processing task, is_child = 0 3.44.624.048 I slot print_timing: id 0 | task 6405 | n_gen = 122, tg = 40.02 t/s, tg_3s = 40.35 t/s 3.47.390.796 I slot print_timing: id 0 | task 6405 | prompt eval time = 603.94 ms / 285 tokens ( 2.12 ms per token, 471.90 tokens per second) 3.47.390.803 I slot print_timing: id 0 | task 6405 | eval time = 5789.99 ms / 232 tokens ( 25.06 ms per token, 39.90 tokens per second) 3.47.390.804 I slot print_timing: id 0 | task 6405 | total time = 6393.93 ms / 517 tokens 3.47.390.804 I slot print_timing: id 0 | task 6405 | graphs reused = 6029 3.47.390.805 I slot print_timing: id 0 | task 6405 | graph reallocs = 0 / 0 (same size) / (changed size) 3.47.390.830 I slot release: id 0 | task 6405 | stop processing: n_tokens = 516, truncated = 0 3.47.395.346 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.157 (> 0.100 thold), f_keep = 0.058 3.47.395.410 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 73.278 MiB) 3.47.395.570 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 57.490 MiB) 3.47.403.986 I slot launch_slot_: id 0 | task 6640 | processing task, is_child = 0 3.50.922.511 I slot print_timing: id 0 | task 6640 | n_gen = 123, tg = 40.35 t/s, tg_3s = 40.68 t/s 3.51.021.940 I slot print_timing: id 0 | task 6640 | prompt eval time = 494.80 ms / 191 tokens ( 2.59 ms per token, 386.02 tokens per second) 3.51.021.943 I slot print_timing: id 0 | task 6640 | eval time = 3123.15 ms / 127 tokens ( 24.79 ms per token, 40.34 tokens per second) 3.51.021.944 I slot print_timing: id 0 | task 6640 | total time = 3617.94 ms / 318 tokens 3.51.021.945 I slot print_timing: id 0 | task 6640 | graphs reused = 6153 3.51.021.945 I slot print_timing: id 0 | task 6640 | graph reallocs = 0 / 0 (same size) / (changed size) 3.51.021.972 I slot release: id 0 | task 6640 | stop processing: n_tokens = 317, truncated = 0 3.51.026.120 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.095 3.51.026.175 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.465 MiB) 3.51.031.851 I slot launch_slot_: id 0 | task 6770 | processing task, is_child = 0 3.53.383.453 I slot print_timing: id 0 | task 6770 | prompt eval time = 445.77 ms / 171 tokens ( 2.61 ms per token, 383.60 tokens per second) 3.53.383.457 I slot print_timing: id 0 | task 6770 | eval time = 1905.81 ms / 78 tokens ( 24.75 ms per token, 40.40 tokens per second) 3.53.383.457 I slot print_timing: id 0 | task 6770 | total time = 2351.58 ms / 249 tokens 3.53.383.458 I slot print_timing: id 0 | task 6770 | graphs reused = 6229 3.53.383.458 I slot print_timing: id 0 | task 6770 | graph reallocs = 0 / 0 (same size) / (changed size) 3.53.383.485 I slot release: id 0 | task 6770 | stop processing: n_tokens = 248, truncated = 0 3.53.387.937 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.115 (> 0.100 thold), f_keep = 0.121 3.53.387.983 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 45.395 MiB) 3.53.388.238 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 52.462 MiB) 3.53.390.607 I slot launch_slot_: id 0 | task 6851 | processing task, is_child = 0 3.56.492.605 I slot print_timing: id 0 | task 6851 | prompt eval time = 612.64 ms / 260 tokens ( 2.36 ms per token, 424.39 tokens per second) 3.56.492.610 I slot print_timing: id 0 | task 6851 | eval time = 2489.34 ms / 101 tokens ( 24.89 ms per token, 40.17 tokens per second) 3.56.492.611 I slot print_timing: id 0 | task 6851 | total time = 3101.99 ms / 361 tokens 3.56.492.612 I slot print_timing: id 0 | task 6851 | graphs reused = 6328 3.56.492.612 I slot print_timing: id 0 | task 6851 | graph reallocs = 0 / 0 (same size) / (changed size) 3.56.492.634 I slot release: id 0 | task 6851 | stop processing: n_tokens = 360, truncated = 0 3.56.497.257 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.147 (> 0.100 thold), f_keep = 0.083 3.56.497.312 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 52.075 MiB) 3.56.497.319 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 52.884 MiB) 3.56.503.806 I slot launch_slot_: id 0 | task 6955 | processing task, is_child = 0 4.00.011.858 I slot print_timing: id 0 | task 6955 | n_gen = 123, tg = 40.37 t/s, tg_3s = 40.70 t/s 4.03.033.959 I slot print_timing: id 0 | task 6955 | n_gen = 244, tg = 40.20 t/s, tg_3s = 40.04 t/s 4.06.045.777 I slot print_timing: id 0 | task 6955 | n_gen = 364, tg = 40.08 t/s, tg_3s = 39.84 t/s 4.09.017.887 I slot print_timing: id 0 | task 6955 | prompt eval time = 485.73 ms / 204 tokens ( 2.38 ms per token, 419.99 tokens per second) 4.09.017.893 I slot print_timing: id 0 | task 6955 | eval time = 12028.35 ms / 482 tokens ( 25.01 ms per token, 39.99 tokens per second) 4.09.017.894 I slot print_timing: id 0 | task 6955 | total time = 12514.07 ms / 686 tokens 4.09.017.894 I slot print_timing: id 0 | task 6955 | graphs reused = 6806 4.09.017.895 I slot print_timing: id 0 | task 6955 | graph reallocs = 0 / 0 (same size) / (changed size) 4.09.017.919 I slot release: id 0 | task 6955 | stop processing: n_tokens = 685, truncated = 0 4.09.022.401 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.101 (> 0.100 thold), f_keep = 0.044 4.09.022.482 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 69.726 MiB) 4.09.030.695 I slot launch_slot_: id 0 | task 7440 | processing task, is_child = 0 4.12.728.669 I slot print_timing: id 0 | task 7440 | n_gen = 122, tg = 40.02 t/s, tg_3s = 40.35 t/s 4.14.518.506 I slot print_timing: id 0 | task 7440 | prompt eval time = 674.59 ms / 296 tokens ( 2.28 ms per token, 438.79 tokens per second) 4.14.518.510 I slot print_timing: id 0 | task 7440 | eval time = 4813.21 ms / 193 tokens ( 25.07 ms per token, 39.89 tokens per second) 4.14.518.511 I slot print_timing: id 0 | task 7440 | total time = 5487.80 ms / 489 tokens 4.14.518.511 I slot print_timing: id 0 | task 7440 | graphs reused = 6997 4.14.518.512 I slot print_timing: id 0 | task 7440 | graph reallocs = 0 / 0 (same size) / (changed size) 4.14.518.535 I slot release: id 0 | task 7440 | stop processing: n_tokens = 488, truncated = 0 4.14.523.087 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.131 (> 0.100 thold), f_keep = 0.064 4.14.523.151 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 115.928 MiB) 4.14.531.060 I slot launch_slot_: id 0 | task 7636 | processing task, is_child = 0 4.18.094.602 I slot print_timing: id 0 | task 7636 | n_gen = 122, tg = 40.28 t/s, tg_3s = 40.61 t/s 4.19.925.088 I slot print_timing: id 0 | task 7636 | prompt eval time = 559.34 ms / 236 tokens ( 2.37 ms per token, 421.93 tokens per second) 4.19.925.095 I slot print_timing: id 0 | task 7636 | eval time = 4834.68 ms / 195 tokens ( 24.92 ms per token, 40.13 tokens per second) 4.19.925.096 I slot print_timing: id 0 | task 7636 | total time = 5394.02 ms / 431 tokens 4.19.925.097 I slot print_timing: id 0 | task 7636 | graphs reused = 7189 4.19.925.097 I slot print_timing: id 0 | task 7636 | graph reallocs = 0 / 0 (same size) / (changed size) 4.19.925.123 I slot release: id 0 | task 7636 | stop processing: n_tokens = 430, truncated = 0 4.19.929.622 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.102 (> 0.100 thold), f_keep = 0.070 4.19.929.685 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 52.638 MiB) 4.19.929.688 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 62.905 MiB) 4.19.936.422 I slot launch_slot_: id 0 | task 7834 | processing task, is_child = 0 4.22.789.100 I slot print_timing: id 0 | task 7834 | prompt eval time = 684.01 ms / 294 tokens ( 2.33 ms per token, 429.82 tokens per second) 4.22.789.104 I slot print_timing: id 0 | task 7834 | eval time = 2168.65 ms / 88 tokens ( 24.93 ms per token, 40.12 tokens per second) 4.22.789.104 I slot print_timing: id 0 | task 7834 | total time = 2852.66 ms / 382 tokens 4.22.789.105 I slot print_timing: id 0 | task 7834 | graphs reused = 7275 4.22.789.105 I slot print_timing: id 0 | task 7834 | graph reallocs = 0 / 0 (same size) / (changed size) 4.22.789.129 I slot release: id 0 | task 7834 | stop processing: n_tokens = 381, truncated = 0 4.22.793.788 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 4.22.793.844 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 81.787 MiB) 4.22.793.851 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 84.213 MiB) 4.22.796.869 I slot launch_slot_: id 0 | task 7925 | processing task, is_child = 0 4.26.472.134 I slot print_timing: id 0 | task 7925 | n_gen = 122, tg = 40.08 t/s, tg_3s = 40.41 t/s 4.29.486.454 I slot print_timing: id 0 | task 7925 | n_gen = 242, tg = 39.95 t/s, tg_3s = 39.81 t/s 4.30.743.956 I slot print_timing: id 0 | task 7925 | prompt eval time = 656.41 ms / 291 tokens ( 2.26 ms per token, 443.32 tokens per second) 4.30.743.960 I slot print_timing: id 0 | task 7925 | eval time = 7290.66 ms / 292 tokens ( 25.05 ms per token, 39.91 tokens per second) 4.30.743.961 I slot print_timing: id 0 | task 7925 | total time = 7947.08 ms / 583 tokens 4.30.743.961 I slot print_timing: id 0 | task 7925 | graphs reused = 7564 4.30.743.962 I slot print_timing: id 0 | task 7925 | graph reallocs = 0 / 0 (same size) / (changed size) 4.30.743.988 I slot release: id 0 | task 7925 | stop processing: n_tokens = 582, truncated = 0 4.30.748.529 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.105 (> 0.100 thold), f_keep = 0.052 4.30.748.601 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 59.881 MiB) 4.30.756.675 I slot launch_slot_: id 0 | task 8220 | processing task, is_child = 0 4.34.343.387 I slot print_timing: id 0 | task 8220 | prompt eval time = 667.89 ms / 287 tokens ( 2.33 ms per token, 429.71 tokens per second) 4.34.343.391 I slot print_timing: id 0 | task 8220 | eval time = 2918.81 ms / 118 tokens ( 24.95 ms per token, 40.08 tokens per second) 4.34.343.392 I slot print_timing: id 0 | task 8220 | total time = 3586.70 ms / 405 tokens 4.34.343.392 I slot print_timing: id 0 | task 8220 | graphs reused = 7680 4.34.343.393 I slot print_timing: id 0 | task 8220 | graph reallocs = 0 / 0 (same size) / (changed size) 4.34.343.421 I slot release: id 0 | task 8220 | stop processing: n_tokens = 404, truncated = 0 4.34.347.597 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.123 (> 0.100 thold), f_keep = 0.074 4.34.347.650 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 60.092 MiB) 4.34.347.654 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 74.086 MiB) 4.34.354.240 I slot launch_slot_: id 0 | task 8341 | processing task, is_child = 0 4.37.906.127 I slot print_timing: id 0 | task 8341 | n_gen = 122, tg = 40.29 t/s, tg_3s = 40.62 t/s 4.38.756.879 I slot print_timing: id 0 | task 8341 | prompt eval time = 548.39 ms / 243 tokens ( 2.26 ms per token, 443.11 tokens per second) 4.38.756.882 I slot print_timing: id 0 | task 8341 | eval time = 3854.23 ms / 156 tokens ( 24.87 ms per token, 40.22 tokens per second) 4.38.756.883 I slot print_timing: id 0 | task 8341 | total time = 4402.63 ms / 399 tokens 4.38.756.883 I slot print_timing: id 0 | task 8341 | graphs reused = 7833 4.38.756.884 I slot print_timing: id 0 | task 8341 | graph reallocs = 0 / 0 (same size) / (changed size) 4.38.756.907 I slot release: id 0 | task 8341 | stop processing: n_tokens = 398, truncated = 0 4.38.761.229 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.166 (> 0.100 thold), f_keep = 0.075 4.38.761.291 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 56.541 MiB) 4.38.767.679 I slot launch_slot_: id 0 | task 8500 | processing task, is_child = 0 4.40.636.893 I slot print_timing: id 0 | task 8500 | prompt eval time = 483.19 ms / 181 tokens ( 2.67 ms per token, 374.60 tokens per second) 4.40.636.904 I slot print_timing: id 0 | task 8500 | eval time = 1386.02 ms / 57 tokens ( 24.75 ms per token, 40.40 tokens per second) 4.40.636.905 I slot print_timing: id 0 | task 8500 | total time = 1869.20 ms / 238 tokens 4.40.636.906 I slot print_timing: id 0 | task 8500 | graphs reused = 7888 4.40.636.909 I slot print_timing: id 0 | task 8500 | graph reallocs = 0 / 0 (same size) / (changed size) 4.40.636.927 I slot release: id 0 | task 8500 | stop processing: n_tokens = 237, truncated = 0 4.40.641.164 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.113 (> 0.100 thold), f_keep = 0.127 4.40.641.207 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 75.352 MiB) 4.40.643.203 I slot launch_slot_: id 0 | task 8560 | processing task, is_child = 0 4.44.194.806 I slot print_timing: id 0 | task 8560 | prompt eval time = 613.65 ms / 265 tokens ( 2.32 ms per token, 431.84 tokens per second) 4.44.194.812 I slot print_timing: id 0 | task 8560 | eval time = 2937.95 ms / 119 tokens ( 24.90 ms per token, 40.16 tokens per second) 4.44.194.813 I slot print_timing: id 0 | task 8560 | total time = 3551.60 ms / 384 tokens 4.44.194.813 I slot print_timing: id 0 | task 8560 | graphs reused = 8005 4.44.194.814 I slot print_timing: id 0 | task 8560 | graph reallocs = 0 / 0 (same size) / (changed size) 4.44.194.841 I slot release: id 0 | task 8560 | stop processing: n_tokens = 383, truncated = 0 4.44.199.016 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.197 (> 0.100 thold), f_keep = 0.078 4.44.199.078 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 59.635 MiB) 4.44.199.086 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 100.844 MiB) 4.44.205.342 I slot launch_slot_: id 0 | task 8682 | processing task, is_child = 0 4.45.647.812 I slot print_timing: id 0 | task 8682 | prompt eval time = 427.06 ms / 152 tokens ( 2.81 ms per token, 355.92 tokens per second) 4.45.647.819 I slot print_timing: id 0 | task 8682 | eval time = 1015.41 ms / 42 tokens ( 24.77 ms per token, 40.38 tokens per second) 4.45.647.820 I slot print_timing: id 0 | task 8682 | total time = 1442.46 ms / 194 tokens 4.45.647.820 I slot print_timing: id 0 | task 8682 | graphs reused = 8045 4.45.647.821 I slot print_timing: id 0 | task 8682 | graph reallocs = 0 / 0 (same size) / (changed size) 4.45.647.839 I slot release: id 0 | task 8682 | stop processing: n_tokens = 193, truncated = 0 4.45.651.997 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.158 (> 0.100 thold), f_keep = 0.155 4.45.653.666 I slot launch_slot_: id 0 | task 8727 | processing task, is_child = 0 4.47.450.302 I slot print_timing: id 0 | task 8727 | prompt eval time = 483.57 ms / 190 tokens ( 2.55 ms per token, 392.91 tokens per second) 4.47.450.308 I slot print_timing: id 0 | task 8727 | eval time = 1313.06 ms / 54 tokens ( 24.77 ms per token, 40.36 tokens per second) 4.47.450.309 I slot print_timing: id 0 | task 8727 | total time = 1796.63 ms / 244 tokens 4.47.450.310 I slot print_timing: id 0 | task 8727 | graphs reused = 8097 4.47.450.310 I slot print_timing: id 0 | task 8727 | graph reallocs = 0 / 0 (same size) / (changed size) 4.47.450.333 I slot release: id 0 | task 8727 | stop processing: n_tokens = 243, truncated = 0 4.47.454.807 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 4.47.454.849 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 91.350 MiB) 4.47.456.893 I slot launch_slot_: id 0 | task 8784 | processing task, is_child = 0 4.51.073.665 I slot print_timing: id 0 | task 8784 | n_gen = 122, tg = 40.20 t/s, tg_3s = 40.53 t/s 4.52.312.472 I slot print_timing: id 0 | task 8784 | prompt eval time = 606.83 ms / 256 tokens ( 2.37 ms per token, 421.86 tokens per second) 4.52.312.478 I slot print_timing: id 0 | task 8784 | eval time = 4248.74 ms / 171 tokens ( 24.99 ms per token, 40.01 tokens per second) 4.52.312.479 I slot print_timing: id 0 | task 8784 | total time = 4855.57 ms / 427 tokens 4.52.312.480 I slot print_timing: id 0 | task 8784 | graphs reused = 8266 4.52.312.480 I slot print_timing: id 0 | task 8784 | graph reallocs = 0 / 0 (same size) / (changed size) 4.52.312.502 I slot release: id 0 | task 8784 | stop processing: n_tokens = 426, truncated = 0 4.52.316.905 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.114 (> 0.100 thold), f_keep = 0.070 4.52.316.961 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 57.244 MiB) 4.52.316.965 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.183 MiB) 4.52.324.146 I slot launch_slot_: id 0 | task 8958 | processing task, is_child = 0 4.53.852.136 I slot print_timing: id 0 | task 8958 | prompt eval time = 606.98 ms / 264 tokens ( 2.30 ms per token, 434.94 tokens per second) 4.53.852.147 I slot print_timing: id 0 | task 8958 | eval time = 920.99 ms / 38 tokens ( 24.89 ms per token, 40.17 tokens per second) 4.53.852.147 I slot print_timing: id 0 | task 8958 | total time = 1527.98 ms / 302 tokens 4.53.852.148 I slot print_timing: id 0 | task 8958 | graphs reused = 8302 4.53.852.149 I slot print_timing: id 0 | task 8958 | graph reallocs = 0 / 0 (same size) / (changed size) 4.53.852.170 I slot release: id 0 | task 8958 | stop processing: n_tokens = 301, truncated = 0 4.53.856.858 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 4.53.856.909 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 53.728 MiB) 4.53.859.620 I slot launch_slot_: id 0 | task 8999 | processing task, is_child = 0 4.57.539.845 I slot print_timing: id 0 | task 8999 | n_gen = 122, tg = 40.07 t/s, tg_3s = 40.40 t/s 5.00.556.146 I slot print_timing: id 0 | task 8999 | n_gen = 242, tg = 39.93 t/s, tg_3s = 39.78 t/s 5.03.574.146 I slot print_timing: id 0 | task 8999 | n_gen = 362, tg = 39.87 t/s, tg_3s = 39.76 t/s 5.06.594.431 I slot print_timing: id 0 | task 8999 | n_gen = 482, tg = 39.84 t/s, tg_3s = 39.73 t/s 5.09.613.722 I slot print_timing: id 0 | task 8999 | n_gen = 602, tg = 39.82 t/s, tg_3s = 39.74 t/s 5.10.118.657 I slot print_timing: id 0 | task 8999 | prompt eval time = 660.69 ms / 289 tokens ( 2.29 ms per token, 437.42 tokens per second) 5.10.118.661 I slot print_timing: id 0 | task 8999 | eval time = 15598.33 ms / 622 tokens ( 25.12 ms per token, 39.81 tokens per second) 5.10.118.662 I slot print_timing: id 0 | task 8999 | total time = 16259.03 ms / 911 tokens 5.10.118.663 I slot print_timing: id 0 | task 8999 | graphs reused = 8920 5.10.118.663 I slot print_timing: id 0 | task 8999 | graph reallocs = 0 / 0 (same size) / (changed size) 5.10.118.690 I slot release: id 0 | task 8999 | stop processing: n_tokens = 910, truncated = 0 5.10.123.535 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.102 (> 0.100 thold), f_keep = 0.033 5.10.123.623 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.778 MiB) 5.10.123.627 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 115.400 MiB) 5.10.133.553 I slot launch_slot_: id 0 | task 9624 | processing task, is_child = 0 5.11.122.234 I slot print_timing: id 0 | task 9624 | prompt eval time = 662.66 ms / 294 tokens ( 2.25 ms per token, 443.67 tokens per second) 5.11.122.241 I slot print_timing: id 0 | task 9624 | eval time = 326.01 ms / 14 tokens ( 25.08 ms per token, 39.88 tokens per second) 5.11.122.241 I slot print_timing: id 0 | task 9624 | total time = 988.67 ms / 308 tokens 5.11.122.242 I slot print_timing: id 0 | task 9624 | graphs reused = 8932 5.11.122.243 I slot print_timing: id 0 | task 9624 | graph reallocs = 0 / 0 (same size) / (changed size) 5.11.122.270 I slot release: id 0 | task 9624 | stop processing: n_tokens = 307, truncated = 0 5.11.126.784 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.103 (> 0.100 thold), f_keep = 0.098 5.11.126.833 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 138.958 MiB) 5.11.129.668 I slot launch_slot_: id 0 | task 9641 | processing task, is_child = 0 5.13.466.809 I slot print_timing: id 0 | task 9641 | prompt eval time = 668.99 ms / 292 tokens ( 2.29 ms per token, 436.48 tokens per second) 5.13.466.815 I slot print_timing: id 0 | task 9641 | eval time = 1668.14 ms / 68 tokens ( 24.90 ms per token, 40.16 tokens per second) 5.13.466.815 I slot print_timing: id 0 | task 9641 | total time = 2337.13 ms / 360 tokens 5.13.466.816 I slot print_timing: id 0 | task 9641 | graphs reused = 8998 5.13.466.817 I slot print_timing: id 0 | task 9641 | graph reallocs = 0 / 0 (same size) / (changed size) 5.13.466.849 I slot release: id 0 | task 9641 | stop processing: n_tokens = 359, truncated = 0 5.13.471.420 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 5.13.474.478 I slot launch_slot_: id 0 | task 9712 | processing task, is_child = 0 5.15.223.820 I slot print_timing: id 0 | task 9712 | prompt eval time = 556.05 ms / 245 tokens ( 2.27 ms per token, 440.61 tokens per second) 5.15.223.827 I slot print_timing: id 0 | task 9712 | eval time = 1193.28 ms / 49 tokens ( 24.86 ms per token, 40.23 tokens per second) 5.15.223.834 I slot print_timing: id 0 | task 9712 | total time = 1749.33 ms / 294 tokens 5.15.223.834 I slot print_timing: id 0 | task 9712 | graphs reused = 9044 5.15.223.835 I slot print_timing: id 0 | task 9712 | graph reallocs = 0 / 0 (same size) / (changed size) 5.15.223.856 I slot release: id 0 | task 9712 | stop processing: n_tokens = 293, truncated = 0 5.15.228.144 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.169 (> 0.100 thold), f_keep = 0.102 5.15.228.190 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 160.828 MiB) 5.15.230.709 I slot launch_slot_: id 0 | task 9764 | processing task, is_child = 0 5.16.605.494 I slot print_timing: id 0 | task 9764 | prompt eval time = 433.27 ms / 178 tokens ( 2.43 ms per token, 410.83 tokens per second) 5.16.605.498 I slot print_timing: id 0 | task 9764 | eval time = 941.50 ms / 39 tokens ( 24.78 ms per token, 40.36 tokens per second) 5.16.605.498 I slot print_timing: id 0 | task 9764 | total time = 1374.77 ms / 217 tokens 5.16.605.499 I slot print_timing: id 0 | task 9764 | graphs reused = 9081 5.16.605.500 I slot print_timing: id 0 | task 9764 | graph reallocs = 0 / 0 (same size) / (changed size) 5.16.605.519 I slot release: id 0 | task 9764 | stop processing: n_tokens = 216, truncated = 0 5.16.610.816 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 216, t_last = 323288531089 5.16.612.849 I slot launch_slot_: id 0 | task 9806 | processing task, is_child = 0 5.19.482.085 I slot print_timing: id 0 | task 9806 | prompt eval time = 784.32 ms / 355 tokens ( 2.21 ms per token, 452.62 tokens per second) 5.19.482.088 I slot print_timing: id 0 | task 9806 | eval time = 2084.91 ms / 84 tokens ( 25.12 ms per token, 39.81 tokens per second) 5.19.482.089 I slot print_timing: id 0 | task 9806 | total time = 2869.22 ms / 439 tokens 5.19.482.090 I slot print_timing: id 0 | task 9806 | graphs reused = 9163 5.19.482.090 I slot print_timing: id 0 | task 9806 | graph reallocs = 0 / 0 (same size) / (changed size) 5.19.482.117 I slot release: id 0 | task 9806 | stop processing: n_tokens = 438, truncated = 0 5.19.488.270 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 438, t_last = 323291407687 5.19.488.350 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 146.518 MiB) 5.19.492.220 I slot launch_slot_: id 0 | task 9893 | processing task, is_child = 0 5.23.723.801 I slot print_timing: id 0 | task 9893 | n_gen = 120, tg = 39.67 t/s, tg_3s = 40.00 t/s 5.26.745.477 I slot print_timing: id 0 | task 9893 | n_gen = 240, tg = 39.69 t/s, tg_3s = 39.71 t/s 5.29.267.845 I slot print_timing: id 0 | task 9893 | prompt eval time = 1231.47 ms / 567 tokens ( 2.17 ms per token, 460.43 tokens per second) 5.29.267.849 I slot print_timing: id 0 | task 9893 | eval time = 8544.15 ms / 340 tokens ( 25.20 ms per token, 39.68 tokens per second) 5.29.267.850 I slot print_timing: id 0 | task 9893 | total time = 9775.62 ms / 907 tokens 5.29.267.850 I slot print_timing: id 0 | task 9893 | graphs reused = 9500 5.29.267.851 I slot print_timing: id 0 | task 9893 | graph reallocs = 0 / 0 (same size) / (changed size) 5.29.267.890 I slot release: id 0 | task 9893 | stop processing: n_tokens = 906, truncated = 0 5.29.273.958 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 906, t_last = 323301193460 5.29.274.046 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 94.655 MiB) 5.29.274.050 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 144.725 MiB) 5.29.286.928 I slot launch_slot_: id 0 | task 10237 | processing task, is_child = 0 5.33.174.100 I slot print_timing: id 0 | task 10237 | prompt eval time = 1015.44 ms / 473 tokens ( 2.15 ms per token, 465.81 tokens per second) 5.33.174.104 I slot print_timing: id 0 | task 10237 | eval time = 2871.72 ms / 115 tokens ( 25.19 ms per token, 39.70 tokens per second) 5.33.174.105 I slot print_timing: id 0 | task 10237 | total time = 3887.16 ms / 588 tokens 5.33.174.105 I slot print_timing: id 0 | task 10237 | graphs reused = 9612 5.33.174.106 I slot print_timing: id 0 | task 10237 | graph reallocs = 0 / 0 (same size) / (changed size) 5.33.174.140 I slot release: id 0 | task 10237 | stop processing: n_tokens = 587, truncated = 0 5.33.179.496 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 587, t_last = 323305099710 5.33.179.573 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 137.446 MiB) 5.33.189.432 I slot launch_slot_: id 0 | task 10355 | processing task, is_child = 0 5.37.054.291 I slot print_timing: id 0 | task 10355 | n_gen = 121, tg = 39.74 t/s, tg_3s = 40.07 t/s 5.40.071.669 I slot print_timing: id 0 | task 10355 | n_gen = 241, tg = 39.75 t/s, tg_3s = 39.77 t/s 5.43.089.289 I slot print_timing: id 0 | task 10355 | n_gen = 361, tg = 39.76 t/s, tg_3s = 39.77 t/s 5.46.091.093 I slot print_timing: id 0 | task 10355 | n_gen = 480, tg = 39.73 t/s, tg_3s = 39.64 t/s 5.49.094.224 I slot print_timing: id 0 | task 10355 | n_gen = 599, tg = 39.71 t/s, tg_3s = 39.63 t/s 5.52.099.562 I slot print_timing: id 0 | task 10355 | n_gen = 718, tg = 39.69 t/s, tg_3s = 39.60 t/s 5.52.881.203 I slot print_timing: id 0 | task 10355 | prompt eval time = 845.16 ms / 399 tokens ( 2.12 ms per token, 472.10 tokens per second) 5.52.881.207 I slot print_timing: id 0 | task 10355 | eval time = 18846.60 ms / 749 tokens ( 25.20 ms per token, 39.69 tokens per second) 5.52.881.208 I slot print_timing: id 0 | task 10355 | total time = 19691.76 ms / 1148 tokens 5.52.881.208 I slot print_timing: id 0 | task 10355 | graphs reused = 10356 5.52.881.209 I slot print_timing: id 0 | task 10355 | graph reallocs = 0 / 0 (same size) / (changed size) 5.52.881.240 I slot release: id 0 | task 10355 | stop processing: n_tokens = 1147, truncated = 0 5.52.885.918 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1147, t_last = 323324806811 5.52.886.010 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 107.313 MiB) 5.52.898.096 I slot launch_slot_: id 0 | task 11107 | processing task, is_child = 0 5.55.268.077 I slot print_timing: id 0 | task 11107 | prompt eval time = 724.13 ms / 312 tokens ( 2.32 ms per token, 430.86 tokens per second) 5.55.268.081 I slot print_timing: id 0 | task 11107 | eval time = 1645.84 ms / 67 tokens ( 24.94 ms per token, 40.10 tokens per second) 5.55.268.082 I slot print_timing: id 0 | task 11107 | total time = 2369.97 ms / 379 tokens 5.55.268.083 I slot print_timing: id 0 | task 11107 | graphs reused = 10421 5.55.268.083 I slot print_timing: id 0 | task 11107 | graph reallocs = 0 / 0 (same size) / (changed size) 5.55.268.115 I slot release: id 0 | task 11107 | stop processing: n_tokens = 378, truncated = 0 5.55.274.072 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 378, t_last = 323327193685 5.55.274.130 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 103.094 MiB) 5.55.277.363 I slot launch_slot_: id 0 | task 11177 | processing task, is_child = 0 5.59.518.582 I slot print_timing: id 0 | task 11177 | n_gen = 120, tg = 39.66 t/s, tg_3s = 39.99 t/s 6.02.541.640 I slot print_timing: id 0 | task 11177 | n_gen = 240, tg = 39.68 t/s, tg_3s = 39.69 t/s 6.04.054.071 I slot print_timing: id 0 | task 11177 | prompt eval time = 1240.62 ms / 561 tokens ( 2.21 ms per token, 452.19 tokens per second) 6.04.054.077 I slot print_timing: id 0 | task 11177 | eval time = 7536.08 ms / 300 tokens ( 25.20 ms per token, 39.68 tokens per second) 6.04.054.078 I slot print_timing: id 0 | task 11177 | total time = 8776.70 ms / 861 tokens 6.04.054.078 I slot print_timing: id 0 | task 11177 | graphs reused = 10718 6.04.054.079 I slot print_timing: id 0 | task 11177 | graph reallocs = 0 / 0 (same size) / (changed size) 6.04.054.123 I slot release: id 0 | task 11177 | stop processing: n_tokens = 860, truncated = 0 6.04.059.174 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 860, t_last = 323335979694 6.04.059.266 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.109 MiB) 6.04.059.273 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 114.275 MiB) 6.04.074.416 I slot launch_slot_: id 0 | task 11481 | processing task, is_child = 0 6.07.283.708 I slot print_timing: id 0 | task 11481 | prompt eval time = 722.44 ms / 317 tokens ( 2.28 ms per token, 438.79 tokens per second) 6.07.283.715 I slot print_timing: id 0 | task 11481 | eval time = 2486.84 ms / 100 tokens ( 25.12 ms per token, 39.81 tokens per second) 6.07.283.716 I slot print_timing: id 0 | task 11481 | total time = 3209.28 ms / 417 tokens 6.07.283.716 I slot print_timing: id 0 | task 11481 | graphs reused = 10816 6.07.283.717 I slot print_timing: id 0 | task 11481 | graph reallocs = 0 / 0 (same size) / (changed size) 6.07.283.741 I slot release: id 0 | task 11481 | stop processing: n_tokens = 416, truncated = 0 6.07.289.321 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 323339209311 6.07.289.378 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 87.201 MiB) 6.07.298.804 I slot launch_slot_: id 0 | task 11584 | processing task, is_child = 0 6.11.220.528 I slot print_timing: id 0 | task 11584 | n_gen = 121, tg = 39.75 t/s, tg_3s = 40.09 t/s 6.12.226.632 I slot print_timing: id 0 | task 11584 | prompt eval time = 903.18 ms / 428 tokens ( 2.11 ms per token, 473.88 tokens per second) 6.12.226.639 I slot print_timing: id 0 | task 11584 | eval time = 4024.64 ms / 161 tokens ( 25.15 ms per token, 39.76 tokens per second) 6.12.226.640 I slot print_timing: id 0 | task 11584 | total time = 4927.82 ms / 589 tokens 6.12.226.640 I slot print_timing: id 0 | task 11584 | graphs reused = 10974 6.12.226.641 I slot print_timing: id 0 | task 11584 | graph reallocs = 0 / 0 (same size) / (changed size) 6.12.226.673 I slot release: id 0 | task 11584 | stop processing: n_tokens = 588, truncated = 0 6.12.231.211 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.133 (> 0.100 thold), f_keep = 0.051 6.12.231.280 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 119.022 MiB) 6.12.231.284 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 99.402 MiB) 6.12.245.929 I slot launch_slot_: id 0 | task 11748 | processing task, is_child = 0 6.14.736.179 I slot print_timing: id 0 | task 11748 | prompt eval time = 559.84 ms / 226 tokens ( 2.48 ms per token, 403.69 tokens per second) 6.14.736.182 I slot print_timing: id 0 | task 11748 | eval time = 1930.40 ms / 79 tokens ( 24.75 ms per token, 40.41 tokens per second) 6.14.736.183 I slot print_timing: id 0 | task 11748 | total time = 2490.24 ms / 305 tokens 6.14.736.183 I slot print_timing: id 0 | task 11748 | graphs reused = 11050 6.14.736.183 I slot print_timing: id 0 | task 11748 | graph reallocs = 0 / 0 (same size) / (changed size) 6.14.736.206 I slot release: id 0 | task 11748 | stop processing: n_tokens = 304, truncated = 0 6.14.740.295 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 304, t_last = 323346661776 6.14.742.753 I slot launch_slot_: id 0 | task 11830 | processing task, is_child = 0 6.18.253.745 I slot print_timing: id 0 | task 11830 | prompt eval time = 846.40 ms / 386 tokens ( 2.19 ms per token, 456.05 tokens per second) 6.18.253.748 I slot print_timing: id 0 | task 11830 | eval time = 2664.58 ms / 107 tokens ( 25.14 ms per token, 39.78 tokens per second) 6.18.253.749 I slot print_timing: id 0 | task 11830 | total time = 3510.98 ms / 493 tokens 6.18.253.750 I slot print_timing: id 0 | task 11830 | graphs reused = 11155 6.18.253.750 I slot print_timing: id 0 | task 11830 | graph reallocs = 0 / 0 (same size) / (changed size) 6.18.253.783 I slot release: id 0 | task 11830 | stop processing: n_tokens = 492, truncated = 0 6.18.259.665 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 492, t_last = 323350179353 6.18.259.728 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 88.854 MiB) 6.18.259.731 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 94.304 MiB) 6.18.273.466 I slot launch_slot_: id 0 | task 11940 | processing task, is_child = 0 6.22.373.954 I slot print_timing: id 0 | task 11940 | n_gen = 120, tg = 39.66 t/s, tg_3s = 39.99 t/s 6.23.304.839 I slot print_timing: id 0 | task 11940 | prompt eval time = 1099.90 ms / 508 tokens ( 2.17 ms per token, 461.86 tokens per second) 6.23.304.844 I slot print_timing: id 0 | task 11940 | eval time = 3931.46 ms / 157 tokens ( 25.20 ms per token, 39.68 tokens per second) 6.23.304.845 I slot print_timing: id 0 | task 11940 | total time = 5031.36 ms / 665 tokens 6.23.304.845 I slot print_timing: id 0 | task 11940 | graphs reused = 11309 6.23.304.846 I slot print_timing: id 0 | task 11940 | graph reallocs = 0 / 0 (same size) / (changed size) 6.23.304.878 I slot release: id 0 | task 11940 | stop processing: n_tokens = 664, truncated = 0 6.23.311.100 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 664, t_last = 323355230448 6.23.311.189 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 89.662 MiB) 6.23.311.192 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 139.450 MiB) 6.23.326.522 I slot launch_slot_: id 0 | task 12100 | processing task, is_child = 0 6.26.963.241 I slot print_timing: id 0 | task 12100 | prompt eval time = 1242.05 ms / 567 tokens ( 2.19 ms per token, 456.50 tokens per second) 6.26.963.245 I slot print_timing: id 0 | task 12100 | eval time = 2394.66 ms / 96 tokens ( 25.21 ms per token, 39.67 tokens per second) 6.26.963.246 I slot print_timing: id 0 | task 12100 | total time = 3636.70 ms / 663 tokens 6.26.963.251 I slot print_timing: id 0 | task 12100 | graphs reused = 11403 6.26.963.251 I slot print_timing: id 0 | task 12100 | graph reallocs = 0 / 0 (same size) / (changed size) 6.26.963.288 I slot release: id 0 | task 12100 | stop processing: n_tokens = 662, truncated = 0 6.26.968.506 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 662, t_last = 323358888858 6.26.968.588 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 110.372 MiB) 6.26.988.438 I slot launch_slot_: id 0 | task 12200 | processing task, is_child = 0 6.29.746.727 I slot print_timing: id 0 | task 12200 | prompt eval time = 845.40 ms / 384 tokens ( 2.20 ms per token, 454.22 tokens per second) 6.29.746.734 I slot print_timing: id 0 | task 12200 | eval time = 1912.88 ms / 77 tokens ( 25.17 ms per token, 39.73 tokens per second) 6.29.746.735 I slot print_timing: id 0 | task 12200 | total time = 2758.28 ms / 461 tokens 6.29.746.735 I slot print_timing: id 0 | task 12200 | graphs reused = 11478 6.29.746.735 I slot print_timing: id 0 | task 12200 | graph reallocs = 0 / 0 (same size) / (changed size) 6.29.746.762 I slot release: id 0 | task 12200 | stop processing: n_tokens = 460, truncated = 0 6.29.752.445 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 460, t_last = 323361672332 6.29.752.505 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 195.006 MiB) 6.29.756.657 I slot launch_slot_: id 0 | task 12280 | processing task, is_child = 0 6.33.787.089 I slot print_timing: id 0 | task 12280 | n_gen = 121, tg = 39.73 t/s, tg_3s = 40.07 t/s 6.33.887.319 I slot print_timing: id 0 | task 12280 | prompt eval time = 1010.36 ms / 457 tokens ( 2.21 ms per token, 452.31 tokens per second) 6.33.887.322 I slot print_timing: id 0 | task 12280 | eval time = 3120.29 ms / 125 tokens ( 25.16 ms per token, 39.74 tokens per second) 6.33.887.323 I slot print_timing: id 0 | task 12280 | total time = 4130.65 ms / 582 tokens 6.33.887.324 I slot print_timing: id 0 | task 12280 | graphs reused = 11600 6.33.887.324 I slot print_timing: id 0 | task 12280 | graph reallocs = 0 / 0 (same size) / (changed size) 6.33.887.357 I slot release: id 0 | task 12280 | stop processing: n_tokens = 581, truncated = 0 6.33.892.782 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 581, t_last = 323365812927 6.33.892.852 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 96.132 MiB) 6.33.906.708 I slot launch_slot_: id 0 | task 12408 | processing task, is_child = 0 6.36.168.248 I slot print_timing: id 0 | task 12408 | prompt eval time = 902.65 ms / 428 tokens ( 2.11 ms per token, 474.16 tokens per second) 6.36.168.254 I slot print_timing: id 0 | task 12408 | eval time = 1358.88 ms / 55 tokens ( 25.16 ms per token, 39.74 tokens per second) 6.36.168.255 I slot print_timing: id 0 | task 12408 | total time = 2261.53 ms / 483 tokens 6.36.168.256 I slot print_timing: id 0 | task 12408 | graphs reused = 11653 6.36.168.256 I slot print_timing: id 0 | task 12408 | graph reallocs = 0 / 0 (same size) / (changed size) 6.36.168.286 I slot release: id 0 | task 12408 | stop processing: n_tokens = 482, truncated = 0 6.36.174.392 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 482, t_last = 323368093856 6.36.174.454 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 159.703 MiB) 6.36.186.181 I slot launch_slot_: id 0 | task 12466 | processing task, is_child = 0 6.40.450.377 I slot print_timing: id 0 | task 12466 | n_gen = 121, tg = 39.69 t/s, tg_3s = 40.02 t/s 6.40.852.415 I slot print_timing: id 0 | task 12466 | prompt eval time = 1240.90 ms / 555 tokens ( 2.24 ms per token, 447.26 tokens per second) 6.40.852.419 I slot print_timing: id 0 | task 12466 | eval time = 3425.32 ms / 137 tokens ( 25.19 ms per token, 39.70 tokens per second) 6.40.852.420 I slot print_timing: id 0 | task 12466 | total time = 4666.23 ms / 692 tokens 6.40.852.426 I slot print_timing: id 0 | task 12466 | graphs reused = 11788 6.40.852.429 I slot print_timing: id 0 | task 12466 | graph reallocs = 0 / 0 (same size) / (changed size) 6.40.852.472 I slot release: id 0 | task 12466 | stop processing: n_tokens = 691, truncated = 0 6.40.859.320 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 691, t_last = 323372778042 6.40.859.401 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 184.211 MiB) 6.40.874.655 I slot launch_slot_: id 0 | task 12607 | processing task, is_child = 0 6.45.260.859 I slot print_timing: id 0 | task 12607 | n_gen = 120, tg = 39.54 t/s, tg_3s = 39.88 t/s 6.45.893.091 I slot print_timing: id 0 | task 12607 | prompt eval time = 1376.92 ms / 643 tokens ( 2.14 ms per token, 466.98 tokens per second) 6.45.893.095 I slot print_timing: id 0 | task 12607 | eval time = 3641.50 ms / 145 tokens ( 25.29 ms per token, 39.54 tokens per second) 6.45.893.095 I slot print_timing: id 0 | task 12607 | total time = 5018.42 ms / 788 tokens 6.45.893.096 I slot print_timing: id 0 | task 12607 | graphs reused = 11930 6.45.893.097 I slot print_timing: id 0 | task 12607 | graph reallocs = 0 / 0 (same size) / (changed size) 6.45.893.142 I slot release: id 0 | task 12607 | stop processing: n_tokens = 787, truncated = 0 6.45.898.970 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 787, t_last = 323377818712 6.45.899.055 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.924 MiB) 6.45.899.391 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 146.624 MiB) 6.45.912.381 I slot launch_slot_: id 0 | task 12756 | processing task, is_child = 0 6.49.408.699 I slot print_timing: id 0 | task 12756 | prompt eval time = 958.14 ms / 437 tokens ( 2.19 ms per token, 456.09 tokens per second) 6.49.408.701 I slot print_timing: id 0 | task 12756 | eval time = 2538.17 ms / 102 tokens ( 25.13 ms per token, 39.79 tokens per second) 6.49.408.702 I slot print_timing: id 0 | task 12756 | total time = 3496.31 ms / 539 tokens 6.49.408.703 I slot print_timing: id 0 | task 12756 | graphs reused = 12029 6.49.408.703 I slot print_timing: id 0 | task 12756 | graph reallocs = 0 / 0 (same size) / (changed size) 6.49.408.735 I slot release: id 0 | task 12756 | stop processing: n_tokens = 561, truncated = 0 6.49.414.271 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 561, t_last = 323381334305 6.49.418.658 I slot launch_slot_: id 0 | task 12861 | processing task, is_child = 0 6.53.534.609 I slot print_timing: id 0 | task 12861 | n_gen = 121, tg = 39.71 t/s, tg_3s = 40.04 t/s 6.54.212.831 I slot print_timing: id 0 | task 12861 | prompt eval time = 1093.66 ms / 494 tokens ( 2.21 ms per token, 451.69 tokens per second) 6.54.212.834 I slot print_timing: id 0 | task 12861 | eval time = 3700.49 ms / 148 tokens ( 25.17 ms per token, 39.72 tokens per second) 6.54.212.835 I slot print_timing: id 0 | task 12861 | total time = 4794.16 ms / 642 tokens 6.54.212.836 I slot print_timing: id 0 | task 12861 | graphs reused = 12175 6.54.212.836 I slot print_timing: id 0 | task 12861 | graph reallocs = 0 / 0 (same size) / (changed size) 6.54.212.880 I slot release: id 0 | task 12861 | stop processing: n_tokens = 663, truncated = 0 6.54.218.150 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 663, t_last = 323386138450 6.54.218.229 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 190.259 MiB) 6.54.227.993 I slot launch_slot_: id 0 | task 13012 | processing task, is_child = 0 6.57.877.714 I slot print_timing: id 0 | task 13012 | prompt eval time = 672.74 ms / 304 tokens ( 2.21 ms per token, 451.88 tokens per second) 6.57.877.717 I slot print_timing: id 0 | task 13012 | eval time = 2976.96 ms / 120 tokens ( 25.02 ms per token, 39.97 tokens per second) 6.57.877.718 I slot print_timing: id 0 | task 13012 | total time = 3649.71 ms / 424 tokens 6.57.877.719 I slot print_timing: id 0 | task 13012 | graphs reused = 12293 6.57.877.719 I slot print_timing: id 0 | task 13012 | graph reallocs = 0 / 0 (same size) / (changed size) 6.57.877.747 I slot release: id 0 | task 13012 | stop processing: n_tokens = 444, truncated = 0 6.57.883.243 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 444, t_last = 323389803317 6.57.883.303 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 130.872 MiB) 6.57.888.173 I slot launch_slot_: id 0 | task 13135 | processing task, is_child = 0 7.01.734.413 I slot print_timing: id 0 | task 13135 | n_gen = 120, tg = 39.64 t/s, tg_3s = 39.98 t/s 7.02.112.220 I slot print_timing: id 0 | task 13135 | prompt eval time = 844.42 ms / 393 tokens ( 2.15 ms per token, 465.41 tokens per second) 7.02.112.226 I slot print_timing: id 0 | task 13135 | eval time = 3379.62 ms / 135 tokens ( 25.22 ms per token, 39.65 tokens per second) 7.02.112.227 I slot print_timing: id 0 | task 13135 | total time = 4224.04 ms / 528 tokens 7.02.112.228 I slot print_timing: id 0 | task 13135 | graphs reused = 12425 7.02.112.228 I slot print_timing: id 0 | task 13135 | graph reallocs = 0 / 0 (same size) / (changed size) 7.02.112.259 I slot release: id 0 | task 13135 | stop processing: n_tokens = 527, truncated = 0 7.02.119.306 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 527, t_last = 323394037829 7.02.123.458 I slot launch_slot_: id 0 | task 13273 | processing task, is_child = 0 7.06.017.969 I slot print_timing: id 0 | task 13273 | prompt eval time = 1475.02 ms / 695 tokens ( 2.12 ms per token, 471.18 tokens per second) 7.06.017.972 I slot print_timing: id 0 | task 13273 | eval time = 2419.48 ms / 97 tokens ( 25.20 ms per token, 39.68 tokens per second) 7.06.017.973 I slot print_timing: id 0 | task 13273 | total time = 3894.50 ms / 792 tokens 7.06.017.973 I slot print_timing: id 0 | task 13273 | graphs reused = 12519 7.06.017.974 I slot print_timing: id 0 | task 13273 | graph reallocs = 0 / 0 (same size) / (changed size) 7.06.018.013 I slot release: id 0 | task 13273 | stop processing: n_tokens = 791, truncated = 0 7.06.024.774 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 791, t_last = 323397943583 7.06.024.860 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 92.475 MiB) 7.06.024.864 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.294 MiB) 7.06.037.783 I slot launch_slot_: id 0 | task 13374 | processing task, is_child = 0 7.10.447.243 I slot print_timing: id 0 | task 13374 | n_gen = 120, tg = 39.65 t/s, tg_3s = 39.98 t/s 7.11.050.390 I slot print_timing: id 0 | task 13374 | prompt eval time = 1407.90 ms / 657 tokens ( 2.14 ms per token, 466.65 tokens per second) 7.11.050.397 I slot print_timing: id 0 | task 13374 | eval time = 3604.69 ms / 144 tokens ( 25.21 ms per token, 39.67 tokens per second) 7.11.050.397 I slot print_timing: id 0 | task 13374 | total time = 5012.60 ms / 801 tokens 7.11.050.402 I slot print_timing: id 0 | task 13374 | graphs reused = 12660 7.11.050.403 I slot print_timing: id 0 | task 13374 | graph reallocs = 0 / 0 (same size) / (changed size) 7.11.050.440 I slot release: id 0 | task 13374 | stop processing: n_tokens = 800, truncated = 0 7.11.054.896 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.130 (> 0.100 thold), f_keep = 0.038 7.11.054.995 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 151.124 MiB) 7.11.065.670 I slot launch_slot_: id 0 | task 13522 | processing task, is_child = 0 7.14.600.625 I slot print_timing: id 0 | task 13522 | prompt eval time = 557.10 ms / 231 tokens ( 2.41 ms per token, 414.65 tokens per second) 7.14.600.628 I slot print_timing: id 0 | task 13522 | eval time = 2977.84 ms / 121 tokens ( 24.82 ms per token, 40.30 tokens per second) 7.14.600.628 I slot print_timing: id 0 | task 13522 | total time = 3534.94 ms / 352 tokens 7.14.600.629 I slot print_timing: id 0 | task 13522 | graphs reused = 12778 7.14.600.629 I slot print_timing: id 0 | task 13522 | graph reallocs = 0 / 0 (same size) / (changed size) 7.14.600.653 I slot release: id 0 | task 13522 | stop processing: n_tokens = 351, truncated = 0 7.14.604.578 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.187 (> 0.100 thold), f_keep = 0.088 7.14.604.630 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.781 MiB) 7.14.607.467 I slot launch_slot_: id 0 | task 13646 | processing task, is_child = 0 7.18.055.125 I slot print_timing: id 0 | task 13646 | n_gen = 123, tg = 40.41 t/s, tg_3s = 40.74 t/s 7.19.143.930 I slot print_timing: id 0 | task 13646 | prompt eval time = 428.71 ms / 166 tokens ( 2.58 ms per token, 387.21 tokens per second) 7.19.143.939 I slot print_timing: id 0 | task 13646 | eval time = 4107.73 ms / 167 tokens ( 24.75 ms per token, 40.41 tokens per second) 7.19.143.939 I slot print_timing: id 0 | task 13646 | total time = 4536.45 ms / 333 tokens 7.19.143.940 I slot print_timing: id 0 | task 13646 | graphs reused = 12942 7.19.143.941 I slot print_timing: id 0 | task 13646 | graph reallocs = 0 / 0 (same size) / (changed size) 7.19.143.959 I slot release: id 0 | task 13646 | stop processing: n_tokens = 332, truncated = 0 7.19.147.959 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.160 (> 0.100 thold), f_keep = 0.093 7.19.148.013 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 187.340 MiB) 7.19.150.465 I slot launch_slot_: id 0 | task 13816 | processing task, is_child = 0 7.22.686.003 I slot print_timing: id 0 | task 13816 | n_gen = 123, tg = 40.36 t/s, tg_3s = 40.69 t/s 7.25.710.581 I slot print_timing: id 0 | task 13816 | n_gen = 244, tg = 40.18 t/s, tg_3s = 40.01 t/s 7.28.727.497 I slot print_timing: id 0 | task 13816 | n_gen = 364, tg = 40.05 t/s, tg_3s = 39.78 t/s 7.30.385.480 I slot print_timing: id 0 | task 13816 | prompt eval time = 512.57 ms / 194 tokens ( 2.64 ms per token, 378.49 tokens per second) 7.30.385.484 I slot print_timing: id 0 | task 13816 | eval time = 10722.44 ms / 430 tokens ( 24.99 ms per token, 40.01 tokens per second) 7.30.385.484 I slot print_timing: id 0 | task 13816 | total time = 11235.01 ms / 624 tokens 7.30.385.485 I slot print_timing: id 0 | task 13816 | graphs reused = 13368 7.30.385.485 I slot print_timing: id 0 | task 13816 | graph reallocs = 0 / 0 (same size) / (changed size) 7.30.385.508 I slot release: id 0 | task 13816 | stop processing: n_tokens = 623, truncated = 0 7.30.389.636 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.208 (> 0.100 thold), f_keep = 0.050 7.30.397.894 I slot launch_slot_: id 0 | task 14249 | processing task, is_child = 0 7.32.859.876 I slot print_timing: id 0 | task 14249 | prompt eval time = 416.00 ms / 149 tokens ( 2.79 ms per token, 358.17 tokens per second) 7.32.859.879 I slot print_timing: id 0 | task 14249 | eval time = 2045.97 ms / 84 tokens ( 24.65 ms per token, 40.57 tokens per second) 7.32.859.880 I slot print_timing: id 0 | task 14249 | total time = 2461.97 ms / 233 tokens 7.32.859.880 I slot print_timing: id 0 | task 14249 | graphs reused = 13450 7.32.859.881 I slot print_timing: id 0 | task 14249 | graph reallocs = 0 / 0 (same size) / (changed size) 7.32.859.900 I slot release: id 0 | task 14249 | stop processing: n_tokens = 232, truncated = 0 7.32.864.171 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.137 (> 0.100 thold), f_keep = 0.129 7.32.864.213 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.726 MiB) 7.32.867.264 I slot launch_slot_: id 0 | task 14336 | processing task, is_child = 0 7.36.441.398 I slot print_timing: id 0 | task 14336 | n_gen = 123, tg = 40.36 t/s, tg_3s = 40.69 t/s 7.37.188.839 I slot print_timing: id 0 | task 14336 | prompt eval time = 551.24 ms / 219 tokens ( 2.52 ms per token, 397.29 tokens per second) 7.37.188.847 I slot print_timing: id 0 | task 14336 | eval time = 3770.33 ms / 153 tokens ( 24.80 ms per token, 40.31 tokens per second) 7.37.188.847 I slot print_timing: id 0 | task 14336 | total time = 4321.57 ms / 372 tokens 7.37.188.848 I slot print_timing: id 0 | task 14336 | graphs reused = 13600 7.37.188.849 I slot print_timing: id 0 | task 14336 | graph reallocs = 0 / 0 (same size) / (changed size) 7.37.188.874 I slot release: id 0 | task 14336 | stop processing: n_tokens = 371, truncated = 0 7.37.192.803 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.227 (> 0.100 thold), f_keep = 0.081 7.37.196.922 I slot launch_slot_: id 0 | task 14492 | processing task, is_child = 0 7.37.884.956 I slot print_timing: id 0 | task 14492 | prompt eval time = 363.85 ms / 132 tokens ( 2.76 ms per token, 362.79 tokens per second) 7.37.884.960 I slot print_timing: id 0 | task 14492 | eval time = 324.18 ms / 14 tokens ( 24.94 ms per token, 40.10 tokens per second) 7.37.884.961 I slot print_timing: id 0 | task 14492 | total time = 688.02 ms / 146 tokens 7.37.884.962 I slot print_timing: id 0 | task 14492 | graphs reused = 13612 7.37.884.962 I slot print_timing: id 0 | task 14492 | graph reallocs = 0 / 0 (same size) / (changed size) 7.37.884.979 I slot release: id 0 | task 14492 | stop processing: n_tokens = 145, truncated = 0 7.37.889.034 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.207 7.37.889.069 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 145.428 MiB) 7.37.892.215 I slot launch_slot_: id 0 | task 14509 | processing task, is_child = 0 7.38.920.301 I slot print_timing: id 0 | task 14509 | prompt eval time = 419.39 ms / 169 tokens ( 2.48 ms per token, 402.97 tokens per second) 7.38.920.305 I slot print_timing: id 0 | task 14509 | eval time = 608.69 ms / 25 tokens ( 25.36 ms per token, 39.43 tokens per second) 7.38.920.305 I slot print_timing: id 0 | task 14509 | total time = 1028.08 ms / 194 tokens 7.38.920.306 I slot print_timing: id 0 | task 14509 | graphs reused = 13635 7.38.920.307 I slot print_timing: id 0 | task 14509 | graph reallocs = 0 / 0 (same size) / (changed size) 7.38.920.328 I slot release: id 0 | task 14509 | stop processing: n_tokens = 193, truncated = 0 7.38.924.263 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.155 7.38.928.360 I slot launch_slot_: id 0 | task 14537 | processing task, is_child = 0 7.42.364.082 I slot print_timing: id 0 | task 14537 | n_gen = 123, tg = 40.47 t/s, tg_3s = 40.80 t/s 7.42.562.211 I slot print_timing: id 0 | task 14537 | prompt eval time = 420.85 ms / 160 tokens ( 2.63 ms per token, 380.18 tokens per second) 7.42.562.219 I slot print_timing: id 0 | task 14537 | eval time = 3212.99 ms / 131 tokens ( 24.72 ms per token, 40.46 tokens per second) 7.42.562.220 I slot print_timing: id 0 | task 14537 | total time = 3633.84 ms / 291 tokens 7.42.562.220 I slot print_timing: id 0 | task 14537 | graphs reused = 13763 7.42.562.221 I slot print_timing: id 0 | task 14537 | graph reallocs = 0 / 0 (same size) / (changed size) 7.42.562.249 I slot release: id 0 | task 14537 | stop processing: n_tokens = 290, truncated = 0 7.42.565.907 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.291 (> 0.100 thold), f_keep = 0.103 7.42.565.959 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 136.004 MiB) 7.42.569.476 I slot launch_slot_: id 0 | task 14671 | processing task, is_child = 0 7.43.208.388 I slot print_timing: id 0 | task 14671 | prompt eval time = 313.62 ms / 103 tokens ( 3.04 ms per token, 328.42 tokens per second) 7.43.208.394 I slot print_timing: id 0 | task 14671 | eval time = 325.28 ms / 14 tokens ( 25.02 ms per token, 39.97 tokens per second) 7.43.208.395 I slot print_timing: id 0 | task 14671 | total time = 638.90 ms / 117 tokens 7.43.208.396 I slot print_timing: id 0 | task 14671 | graphs reused = 13775 7.43.208.396 I slot print_timing: id 0 | task 14671 | graph reallocs = 0 / 0 (same size) / (changed size) 7.43.208.417 I slot release: id 0 | task 14671 | stop processing: n_tokens = 116, truncated = 0 7.43.212.464 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.259 7.43.215.946 I slot launch_slot_: id 0 | task 14688 | processing task, is_child = 0 7.43.873.297 I slot print_timing: id 0 | task 14688 | prompt eval time = 432.19 ms / 165 tokens ( 2.62 ms per token, 381.78 tokens per second) 7.43.873.300 I slot print_timing: id 0 | task 14688 | eval time = 225.16 ms / 10 tokens ( 25.02 ms per token, 39.97 tokens per second) 7.43.873.301 I slot print_timing: id 0 | task 14688 | total time = 657.34 ms / 175 tokens 7.43.873.302 I slot print_timing: id 0 | task 14688 | graphs reused = 13783 7.43.873.302 I slot print_timing: id 0 | task 14688 | graph reallocs = 0 / 0 (same size) / (changed size) 7.43.873.322 I slot release: id 0 | task 14688 | stop processing: n_tokens = 174, truncated = 0 7.43.877.225 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.172 7.43.881.325 I slot launch_slot_: id 0 | task 14701 | processing task, is_child = 0 7.47.306.682 I slot print_timing: id 0 | task 14701 | n_gen = 122, tg = 40.31 t/s, tg_3s = 40.64 t/s 7.49.116.439 I slot print_timing: id 0 | task 14701 | prompt eval time = 423.40 ms / 165 tokens ( 2.57 ms per token, 389.70 tokens per second) 7.49.116.446 I slot print_timing: id 0 | task 14701 | eval time = 4811.70 ms / 195 tokens ( 24.80 ms per token, 40.32 tokens per second) 7.49.116.447 I slot print_timing: id 0 | task 14701 | total time = 5235.10 ms / 360 tokens 7.49.116.447 I slot print_timing: id 0 | task 14701 | graphs reused = 13975 7.49.116.448 I slot print_timing: id 0 | task 14701 | graph reallocs = 0 / 0 (same size) / (changed size) 7.49.116.469 I slot release: id 0 | task 14701 | stop processing: n_tokens = 359, truncated = 0 7.49.120.469 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.162 (> 0.100 thold), f_keep = 0.084 7.49.120.525 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 172.220 MiB) 7.49.126.113 I slot launch_slot_: id 0 | task 14899 | processing task, is_child = 0 7.52.642.511 I slot print_timing: id 0 | task 14899 | n_gen = 123, tg = 40.46 t/s, tg_3s = 40.79 t/s 7.55.660.348 I slot print_timing: id 0 | task 14899 | n_gen = 244, tg = 40.28 t/s, tg_3s = 40.09 t/s 7.58.071.407 I slot print_timing: id 0 | task 14899 | prompt eval time = 500.80 ms / 185 tokens ( 2.71 ms per token, 369.41 tokens per second) 7.58.071.411 I slot print_timing: id 0 | task 14899 | eval time = 8444.48 ms / 340 tokens ( 24.91 ms per token, 40.14 tokens per second) 7.58.071.412 I slot print_timing: id 0 | task 14899 | total time = 8945.28 ms / 525 tokens 7.58.071.412 I slot print_timing: id 0 | task 14899 | graphs reused = 14311 7.58.071.413 I slot print_timing: id 0 | task 14899 | graph reallocs = 0 / 0 (same size) / (changed size) 7.58.071.443 I slot release: id 0 | task 14899 | stop processing: n_tokens = 524, truncated = 0 7.58.075.578 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.057 7.58.080.397 I slot launch_slot_: id 0 | task 15242 | processing task, is_child = 0 7.58.945.869 I slot print_timing: id 0 | task 15242 | prompt eval time = 418.47 ms / 160 tokens ( 2.62 ms per token, 382.34 tokens per second) 7.58.945.875 I slot print_timing: id 0 | task 15242 | eval time = 446.99 ms / 19 tokens ( 24.83 ms per token, 40.27 tokens per second) 7.58.945.876 I slot print_timing: id 0 | task 15242 | total time = 865.46 ms / 179 tokens 7.58.945.877 I slot print_timing: id 0 | task 15242 | graphs reused = 14328 7.58.945.877 I slot print_timing: id 0 | task 15242 | graph reallocs = 0 / 0 (same size) / (changed size) 7.58.945.895 I slot release: id 0 | task 15242 | stop processing: n_tokens = 178, truncated = 0 7.58.950.045 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.191 (> 0.100 thold), f_keep = 0.169 7.58.950.086 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 189.169 MiB) 7.58.953.981 I slot launch_slot_: id 0 | task 15264 | processing task, is_child = 0 8.02.382.478 I slot print_timing: id 0 | task 15264 | n_gen = 123, tg = 40.53 t/s, tg_3s = 40.86 t/s 8.05.402.881 I slot print_timing: id 0 | task 15264 | n_gen = 244, tg = 40.29 t/s, tg_3s = 40.06 t/s 8.08.413.311 I slot print_timing: id 0 | task 15264 | n_gen = 364, tg = 40.15 t/s, tg_3s = 39.86 t/s 8.11.416.439 I slot print_timing: id 0 | task 15264 | n_gen = 483, tg = 40.02 t/s, tg_3s = 39.63 t/s 8.14.431.789 I slot print_timing: id 0 | task 15264 | n_gen = 602, tg = 39.91 t/s, tg_3s = 39.46 t/s 8.17.435.208 I slot print_timing: id 0 | task 15264 | n_gen = 720, tg = 39.81 t/s, tg_3s = 39.29 t/s 8.20.440.115 I slot print_timing: id 0 | task 15264 | n_gen = 839, tg = 39.78 t/s, tg_3s = 39.60 t/s 8.21.222.588 I slot print_timing: id 0 | task 15264 | prompt eval time = 418.22 ms / 157 tokens ( 2.66 ms per token, 375.40 tokens per second) 8.21.222.596 I slot print_timing: id 0 | task 15264 | eval time = 21850.38 ms / 870 tokens ( 25.14 ms per token, 39.77 tokens per second) 8.21.222.597 I slot print_timing: id 0 | task 15264 | total time = 22268.60 ms / 1027 tokens 8.21.222.603 I slot print_timing: id 0 | task 15264 | graphs reused = 15192 8.21.222.604 I slot print_timing: id 0 | task 15264 | graph reallocs = 0 / 0 (same size) / (changed size) 8.21.222.623 I slot release: id 0 | task 15264 | stop processing: n_tokens = 1026, truncated = 0 8.21.226.982 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.029 8.21.239.877 I slot launch_slot_: id 0 | task 16137 | processing task, is_child = 0 8.24.208.869 I slot print_timing: id 0 | task 16137 | prompt eval time = 421.79 ms / 171 tokens ( 2.47 ms per token, 405.42 tokens per second) 8.24.208.873 I slot print_timing: id 0 | task 16137 | eval time = 2547.20 ms / 104 tokens ( 24.73 ms per token, 40.44 tokens per second) 8.24.208.874 I slot print_timing: id 0 | task 16137 | total time = 2968.98 ms / 275 tokens 8.24.208.874 I slot print_timing: id 0 | task 16137 | graphs reused = 15293 8.24.208.875 I slot print_timing: id 0 | task 16137 | graph reallocs = 0 / 0 (same size) / (changed size) 8.24.208.903 I slot release: id 0 | task 16137 | stop processing: n_tokens = 274, truncated = 0 8.24.213.171 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.164 (> 0.100 thold), f_keep = 0.109 8.24.213.217 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 72.539 MiB) 8.24.215.400 I slot launch_slot_: id 0 | task 16244 | processing task, is_child = 0 8.27.742.852 I slot print_timing: id 0 | task 16244 | n_gen = 122, tg = 40.15 t/s, tg_3s = 40.49 t/s 8.30.756.255 I slot print_timing: id 0 | task 16244 | n_gen = 241, tg = 39.82 t/s, tg_3s = 39.49 t/s 8.33.767.456 I slot print_timing: id 0 | task 16244 | n_gen = 357, tg = 39.39 t/s, tg_3s = 38.52 t/s 8.36.786.391 I slot print_timing: id 0 | task 16244 | n_gen = 475, tg = 39.31 t/s, tg_3s = 39.09 t/s 8.39.809.874 I slot print_timing: id 0 | task 16244 | n_gen = 595, tg = 39.39 t/s, tg_3s = 39.69 t/s 8.42.833.550 I slot print_timing: id 0 | task 16244 | n_gen = 715, tg = 39.44 t/s, tg_3s = 39.69 t/s 8.45.834.561 I slot print_timing: id 0 | task 16244 | n_gen = 834, tg = 39.47 t/s, tg_3s = 39.65 t/s 8.48.839.460 I slot print_timing: id 0 | task 16244 | n_gen = 953, tg = 39.49 t/s, tg_3s = 39.60 t/s 8.50.620.635 I slot print_timing: id 0 | task 16244 | prompt eval time = 514.01 ms / 183 tokens ( 2.81 ms per token, 356.03 tokens per second) 8.50.620.639 I slot print_timing: id 0 | task 16244 | eval time = 25891.22 ms / 1024 tokens ( 25.31 ms per token, 39.51 tokens per second) 8.50.620.640 I slot print_timing: id 0 | task 16244 | total time = 26405.22 ms / 1207 tokens 8.50.620.641 I slot print_timing: id 0 | task 16244 | graphs reused = 16311 8.50.620.641 I slot print_timing: id 0 | task 16244 | graph reallocs = 0 / 0 (same size) / (changed size) 8.50.620.668 I slot release: id 0 | task 16244 | stop processing: n_tokens = 1206, truncated = 0 8.50.625.858 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 8.50.625.951 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 78.306 MiB) 8.50.625.955 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.954 MiB) 8.50.636.523 I slot launch_slot_: id 0 | task 17271 | processing task, is_child = 0 8.54.074.703 I slot print_timing: id 0 | task 17271 | n_gen = 123, tg = 40.51 t/s, tg_3s = 40.84 t/s 8.57.081.855 I slot print_timing: id 0 | task 17271 | n_gen = 244, tg = 40.37 t/s, tg_3s = 40.24 t/s 9.00.090.739 I slot print_timing: id 0 | task 17271 | n_gen = 364, tg = 40.21 t/s, tg_3s = 39.88 t/s 9.01.699.234 I slot print_timing: id 0 | task 17271 | prompt eval time = 426.47 ms / 163 tokens ( 2.62 ms per token, 382.20 tokens per second) 9.01.699.244 I slot print_timing: id 0 | task 17271 | eval time = 10636.22 ms / 428 tokens ( 24.91 ms per token, 40.15 tokens per second) 9.01.699.244 I slot print_timing: id 0 | task 17271 | total time = 11062.69 ms / 591 tokens 9.01.699.245 I slot print_timing: id 0 | task 17271 | graphs reused = 16735 9.01.699.245 I slot print_timing: id 0 | task 17271 | graph reallocs = 0 / 0 (same size) / (changed size) 9.01.699.265 I slot release: id 0 | task 17271 | stop processing: n_tokens = 590, truncated = 0 9.01.703.516 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.169 (> 0.100 thold), f_keep = 0.051 9.01.703.586 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 64.452 MiB) 9.01.707.014 I slot launch_slot_: id 0 | task 17702 | processing task, is_child = 0 9.05.162.890 I slot print_timing: id 0 | task 17702 | n_gen = 123, tg = 40.41 t/s, tg_3s = 40.74 t/s 9.06.952.176 I slot print_timing: id 0 | task 17702 | prompt eval time = 436.57 ms / 177 tokens ( 2.47 ms per token, 405.43 tokens per second) 9.06.952.179 I slot print_timing: id 0 | task 17702 | eval time = 4808.58 ms / 195 tokens ( 24.79 ms per token, 40.34 tokens per second) 9.06.952.180 I slot print_timing: id 0 | task 17702 | total time = 5245.15 ms / 372 tokens 9.06.952.181 I slot print_timing: id 0 | task 17702 | graphs reused = 16927 9.06.952.181 I slot print_timing: id 0 | task 17702 | graph reallocs = 0 / 0 (same size) / (changed size) 9.06.952.203 I slot release: id 0 | task 17702 | stop processing: n_tokens = 371, truncated = 0 9.06.956.209 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.196 (> 0.100 thold), f_keep = 0.081 9.06.956.263 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 91.526 MiB) 9.06.968.247 I slot launch_slot_: id 0 | task 17900 | processing task, is_child = 0 9.10.415.549 I slot print_timing: id 0 | task 17900 | n_gen = 123, tg = 40.44 t/s, tg_3s = 40.77 t/s 9.10.762.152 I slot print_timing: id 0 | task 17900 | prompt eval time = 430.45 ms / 153 tokens ( 2.81 ms per token, 355.45 tokens per second) 9.10.762.156 I slot print_timing: id 0 | task 17900 | eval time = 3363.45 ms / 137 tokens ( 24.73 ms per token, 40.43 tokens per second) 9.10.762.157 I slot print_timing: id 0 | task 17900 | total time = 3793.89 ms / 290 tokens 9.10.762.157 I slot print_timing: id 0 | task 17900 | graphs reused = 17061 9.10.762.158 I slot print_timing: id 0 | task 17900 | graph reallocs = 0 / 0 (same size) / (changed size) 9.10.762.177 I slot release: id 0 | task 17900 | stop processing: n_tokens = 289, truncated = 0 9.10.766.089 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.217 (> 0.100 thold), f_keep = 0.104 9.10.766.138 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 96.414 MiB) 9.10.768.661 I slot launch_slot_: id 0 | task 18040 | processing task, is_child = 0 9.11.886.342 I slot print_timing: id 0 | task 18040 | prompt eval time = 372.36 ms / 138 tokens ( 2.70 ms per token, 370.61 tokens per second) 9.11.886.345 I slot print_timing: id 0 | task 18040 | eval time = 745.30 ms / 31 tokens ( 24.84 ms per token, 40.25 tokens per second) 9.11.886.346 I slot print_timing: id 0 | task 18040 | total time = 1117.67 ms / 169 tokens 9.11.886.347 I slot print_timing: id 0 | task 18040 | graphs reused = 17090 9.11.886.347 I slot print_timing: id 0 | task 18040 | graph reallocs = 0 / 0 (same size) / (changed size) 9.11.886.368 I slot release: id 0 | task 18040 | stop processing: n_tokens = 168, truncated = 0 9.11.890.468 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.168 (> 0.100 thold), f_keep = 0.179 9.11.892.061 I slot launch_slot_: id 0 | task 18074 | processing task, is_child = 0 9.15.330.752 I slot print_timing: id 0 | task 18074 | n_gen = 123, tg = 40.46 t/s, tg_3s = 40.80 t/s 9.18.334.414 I slot print_timing: id 0 | task 18074 | n_gen = 244, tg = 40.37 t/s, tg_3s = 40.28 t/s 9.18.935.186 I slot print_timing: id 0 | task 18074 | prompt eval time = 423.69 ms / 179 tokens ( 2.37 ms per token, 422.48 tokens per second) 9.18.935.192 I slot print_timing: id 0 | task 18074 | eval time = 6619.43 ms / 268 tokens ( 24.79 ms per token, 40.34 tokens per second) 9.18.935.193 I slot print_timing: id 0 | task 18074 | total time = 7043.12 ms / 447 tokens 9.18.935.194 I slot print_timing: id 0 | task 18074 | graphs reused = 17355 9.18.935.194 I slot print_timing: id 0 | task 18074 | graph reallocs = 0 / 0 (same size) / (changed size) 9.18.935.214 I slot release: id 0 | task 18074 | stop processing: n_tokens = 446, truncated = 0 9.18.939.679 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.169 (> 0.100 thold), f_keep = 0.076 9.18.939.752 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 121.238 MiB) 9.18.942.842 I slot launch_slot_: id 0 | task 18345 | processing task, is_child = 0 9.22.457.478 I slot print_timing: id 0 | task 18345 | n_gen = 123, tg = 40.43 t/s, tg_3s = 40.76 t/s 9.24.702.100 I slot print_timing: id 0 | task 18345 | prompt eval time = 496.80 ms / 201 tokens ( 2.47 ms per token, 404.59 tokens per second) 9.24.702.104 I slot print_timing: id 0 | task 18345 | eval time = 5262.45 ms / 213 tokens ( 24.82 ms per token, 40.29 tokens per second) 9.24.702.104 I slot print_timing: id 0 | task 18345 | total time = 5759.25 ms / 414 tokens 9.24.702.105 I slot print_timing: id 0 | task 18345 | graphs reused = 17565 9.24.702.105 I slot print_timing: id 0 | task 18345 | graph reallocs = 0 / 0 (same size) / (changed size) 9.24.702.125 I slot release: id 0 | task 18345 | stop processing: n_tokens = 413, truncated = 0 9.24.706.064 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.224 (> 0.100 thold), f_keep = 0.073 9.24.706.123 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 103.517 MiB) 9.24.710.336 I slot launch_slot_: id 0 | task 18561 | processing task, is_child = 0 9.28.097.544 I slot print_timing: id 0 | task 18561 | n_gen = 123, tg = 40.56 t/s, tg_3s = 40.89 t/s 9.31.098.137 I slot print_timing: id 0 | task 18561 | n_gen = 243, tg = 40.28 t/s, tg_3s = 39.99 t/s 9.31.272.965 I slot print_timing: id 0 | task 18561 | prompt eval time = 379.45 ms / 134 tokens ( 2.83 ms per token, 353.14 tokens per second) 9.31.272.971 I slot print_timing: id 0 | task 18561 | eval time = 6183.17 ms / 250 tokens ( 24.83 ms per token, 40.27 tokens per second) 9.31.272.972 I slot print_timing: id 0 | task 18561 | total time = 6562.62 ms / 384 tokens 9.31.272.972 I slot print_timing: id 0 | task 18561 | graphs reused = 17812 9.31.272.973 I slot print_timing: id 0 | task 18561 | graph reallocs = 0 / 0 (same size) / (changed size) 9.31.272.991 I slot release: id 0 | task 18561 | stop processing: n_tokens = 383, truncated = 0 9.31.276.839 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.205 (> 0.100 thold), f_keep = 0.078 9.31.276.893 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 71.731 MiB) 9.31.279.391 I slot launch_slot_: id 0 | task 18814 | processing task, is_child = 0 9.32.154.183 I slot print_timing: id 0 | task 18814 | prompt eval time = 427.38 ms / 146 tokens ( 2.93 ms per token, 341.62 tokens per second) 9.32.154.187 I slot print_timing: id 0 | task 18814 | eval time = 447.40 ms / 19 tokens ( 24.86 ms per token, 40.23 tokens per second) 9.32.154.187 I slot print_timing: id 0 | task 18814 | total time = 874.78 ms / 165 tokens 9.32.154.188 I slot print_timing: id 0 | task 18814 | graphs reused = 17829 9.32.154.188 I slot print_timing: id 0 | task 18814 | graph reallocs = 0 / 0 (same size) / (changed size) 9.32.154.207 I slot release: id 0 | task 18814 | stop processing: n_tokens = 164, truncated = 0 9.32.158.058 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.217 (> 0.100 thold), f_keep = 0.183 9.32.158.094 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 84.178 MiB) 9.32.159.692 I slot launch_slot_: id 0 | task 18836 | processing task, is_child = 0 9.34.174.186 I slot print_timing: id 0 | task 18836 | prompt eval time = 375.71 ms / 138 tokens ( 2.72 ms per token, 367.30 tokens per second) 9.34.174.190 I slot print_timing: id 0 | task 18836 | eval time = 1638.77 ms / 67 tokens ( 24.83 ms per token, 40.27 tokens per second) 9.34.174.191 I slot print_timing: id 0 | task 18836 | total time = 2014.48 ms / 205 tokens 9.34.174.192 I slot print_timing: id 0 | task 18836 | graphs reused = 17894 9.34.174.192 I slot print_timing: id 0 | task 18836 | graph reallocs = 0 / 0 (same size) / (changed size) 9.34.174.209 I slot release: id 0 | task 18836 | stop processing: n_tokens = 204, truncated = 0 9.34.178.634 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.147 9.34.180.384 I slot launch_slot_: id 0 | task 18906 | processing task, is_child = 0 9.35.269.645 I slot print_timing: id 0 | task 18906 | prompt eval time = 431.02 ms / 155 tokens ( 2.78 ms per token, 359.61 tokens per second) 9.35.269.648 I slot print_timing: id 0 | task 18906 | eval time = 658.23 ms / 27 tokens ( 25.32 ms per token, 39.50 tokens per second) 9.35.269.649 I slot print_timing: id 0 | task 18906 | total time = 1089.25 ms / 182 tokens 9.35.269.650 I slot print_timing: id 0 | task 18906 | graphs reused = 17919 9.35.269.650 I slot print_timing: id 0 | task 18906 | graph reallocs = 0 / 0 (same size) / (changed size) 9.35.269.671 I slot release: id 0 | task 18906 | stop processing: n_tokens = 181, truncated = 0 9.35.273.598 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.166 9.35.273.639 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 131.577 MiB) 9.35.276.546 I slot launch_slot_: id 0 | task 18936 | processing task, is_child = 0 9.37.222.167 I slot print_timing: id 0 | task 18936 | prompt eval time = 427.34 ms / 160 tokens ( 2.67 ms per token, 374.41 tokens per second) 9.37.222.170 I slot print_timing: id 0 | task 18936 | eval time = 1518.27 ms / 62 tokens ( 24.89 ms per token, 40.18 tokens per second) 9.37.222.171 I slot print_timing: id 0 | task 18936 | total time = 1945.61 ms / 222 tokens 9.37.222.172 I slot print_timing: id 0 | task 18936 | graphs reused = 17979 9.37.222.172 I slot print_timing: id 0 | task 18936 | graph reallocs = 0 / 0 (same size) / (changed size) 9.37.222.194 I slot release: id 0 | task 18936 | stop processing: n_tokens = 221, truncated = 0 9.37.226.239 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.192 (> 0.100 thold), f_keep = 0.136 9.37.230.440 I slot launch_slot_: id 0 | task 19001 | processing task, is_child = 0 9.38.281.433 I slot print_timing: id 0 | task 19001 | prompt eval time = 431.12 ms / 156 tokens ( 2.76 ms per token, 361.85 tokens per second) 9.38.281.436 I slot print_timing: id 0 | task 19001 | eval time = 619.86 ms / 26 tokens ( 24.79 ms per token, 40.33 tokens per second) 9.38.281.437 I slot print_timing: id 0 | task 19001 | total time = 1050.98 ms / 182 tokens 9.38.281.437 I slot print_timing: id 0 | task 19001 | graphs reused = 18003 9.38.281.438 I slot print_timing: id 0 | task 19001 | graph reallocs = 0 / 0 (same size) / (changed size) 9.38.281.466 I slot release: id 0 | task 19001 | stop processing: n_tokens = 181, truncated = 0 9.38.285.290 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.190 (> 0.100 thold), f_keep = 0.166 9.38.285.328 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 82.068 MiB) 9.38.288.291 I slot launch_slot_: id 0 | task 19030 | processing task, is_child = 0 9.41.724.345 I slot print_timing: id 0 | task 19030 | n_gen = 123, tg = 40.55 t/s, tg_3s = 40.89 t/s 9.44.747.637 I slot print_timing: id 0 | task 19030 | n_gen = 242, tg = 39.96 t/s, tg_3s = 39.36 t/s 9.47.750.620 I slot print_timing: id 0 | task 19030 | n_gen = 362, tg = 39.96 t/s, tg_3s = 39.96 t/s 9.50.758.228 I slot print_timing: id 0 | task 19030 | n_gen = 480, tg = 39.78 t/s, tg_3s = 39.23 t/s 9.53.760.716 I slot print_timing: id 0 | task 19030 | n_gen = 600, tg = 39.81 t/s, tg_3s = 39.97 t/s 9.56.766.301 I slot print_timing: id 0 | task 19030 | n_gen = 719, tg = 39.78 t/s, tg_3s = 39.59 t/s 9.59.781.944 I slot print_timing: id 0 | task 19030 | n_gen = 839, tg = 39.78 t/s, tg_3s = 39.79 t/s 10.02.803.143 I slot print_timing: id 0 | task 19030 | n_gen = 959, tg = 39.77 t/s, tg_3s = 39.72 t/s 10.04.245.606 I slot print_timing: id 0 | task 19030 | prompt eval time = 427.68 ms / 158 tokens ( 2.71 ms per token, 369.43 tokens per second) 10.04.245.614 I slot print_timing: id 0 | task 19030 | eval time = 25529.62 ms / 1016 tokens ( 25.15 ms per token, 39.76 tokens per second) 10.04.245.615 I slot print_timing: id 0 | task 19030 | total time = 25957.31 ms / 1174 tokens 10.04.245.616 I slot print_timing: id 0 | task 19030 | graphs reused = 19013 10.04.245.616 I slot print_timing: id 0 | task 19030 | graph reallocs = 0 / 0 (same size) / (changed size) 10.04.245.647 I slot release: id 0 | task 19030 | stop processing: n_tokens = 1173, truncated = 0 10.04.249.775 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.026 10.04.249.874 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 93.496 MiB) 10.04.266.343 I slot launch_slot_: id 0 | task 20049 | processing task, is_child = 0 10.07.659.660 I slot print_timing: id 0 | task 20049 | n_gen = 123, tg = 40.51 t/s, tg_3s = 40.84 t/s 10.08.377.247 I slot print_timing: id 0 | task 20049 | prompt eval time = 381.68 ms / 155 tokens ( 2.46 ms per token, 406.10 tokens per second) 10.08.377.254 I slot print_timing: id 0 | task 20049 | eval time = 3729.22 ms / 152 tokens ( 24.70 ms per token, 40.49 tokens per second) 10.08.377.255 I slot print_timing: id 0 | task 20049 | total time = 4110.90 ms / 307 tokens 10.08.377.255 I slot print_timing: id 0 | task 20049 | graphs reused = 19162 10.08.377.256 I slot print_timing: id 0 | task 20049 | graph reallocs = 0 / 0 (same size) / (changed size) 10.08.377.274 I slot release: id 0 | task 20049 | stop processing: n_tokens = 306, truncated = 0 10.08.381.461 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.176 (> 0.100 thold), f_keep = 0.098 10.08.381.509 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 96.062 MiB) 10.08.383.754 I slot launch_slot_: id 0 | task 20204 | processing task, is_child = 0 10.09.130.373 I slot print_timing: id 0 | task 20204 | prompt eval time = 423.40 ms / 170 tokens ( 2.49 ms per token, 401.51 tokens per second) 10.09.130.377 I slot print_timing: id 0 | task 20204 | eval time = 323.20 ms / 14 tokens ( 24.86 ms per token, 40.22 tokens per second) 10.09.130.378 I slot print_timing: id 0 | task 20204 | total time = 746.61 ms / 184 tokens 10.09.130.378 I slot print_timing: id 0 | task 20204 | graphs reused = 19174 10.09.130.379 I slot print_timing: id 0 | task 20204 | graph reallocs = 0 / 0 (same size) / (changed size) 10.09.130.404 I slot release: id 0 | task 20204 | stop processing: n_tokens = 183, truncated = 0 10.09.134.423 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.169 10.09.134.461 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 92.441 MiB) 10.09.137.488 I slot launch_slot_: id 0 | task 20221 | processing task, is_child = 0 10.10.226.951 I slot print_timing: id 0 | task 20221 | prompt eval time = 421.02 ms / 160 tokens ( 2.63 ms per token, 380.03 tokens per second) 10.10.226.955 I slot print_timing: id 0 | task 20221 | eval time = 668.43 ms / 28 tokens ( 24.76 ms per token, 40.39 tokens per second) 10.10.226.955 I slot print_timing: id 0 | task 20221 | total time = 1089.45 ms / 188 tokens 10.10.226.956 I slot print_timing: id 0 | task 20221 | graphs reused = 19200 10.10.226.957 I slot print_timing: id 0 | task 20221 | graph reallocs = 0 / 0 (same size) / (changed size) 10.10.226.980 I slot release: id 0 | task 20221 | stop processing: n_tokens = 187, truncated = 0 10.10.230.807 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.186 (> 0.100 thold), f_keep = 0.160 10.10.233.925 I slot launch_slot_: id 0 | task 20252 | processing task, is_child = 0 10.13.670.071 I slot print_timing: id 0 | task 20252 | n_gen = 122, tg = 40.15 t/s, tg_3s = 40.48 t/s 10.16.681.938 I slot print_timing: id 0 | task 20252 | n_gen = 243, tg = 40.16 t/s, tg_3s = 40.17 t/s 10.17.568.890 I slot print_timing: id 0 | task 20252 | prompt eval time = 422.19 ms / 161 tokens ( 2.62 ms per token, 381.35 tokens per second) 10.17.568.896 I slot print_timing: id 0 | task 20252 | eval time = 6912.77 ms / 278 tokens ( 24.96 ms per token, 40.07 tokens per second) 10.17.568.897 I slot print_timing: id 0 | task 20252 | total time = 7334.96 ms / 439 tokens 10.17.568.897 I slot print_timing: id 0 | task 20252 | graphs reused = 19475 10.17.568.898 I slot print_timing: id 0 | task 20252 | graph reallocs = 0 / 0 (same size) / (changed size) 10.17.568.917 I slot release: id 0 | task 20252 | stop processing: n_tokens = 438, truncated = 0 10.17.573.023 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.068 10.17.573.087 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 118.671 MiB) 10.17.575.991 I slot launch_slot_: id 0 | task 20533 | processing task, is_child = 0 10.20.966.885 I slot print_timing: id 0 | task 20533 | n_gen = 122, tg = 40.24 t/s, tg_3s = 40.58 t/s 10.21.785.438 I slot print_timing: id 0 | task 20533 | prompt eval time = 384.12 ms / 169 tokens ( 2.27 ms per token, 439.97 tokens per second) 10.21.785.444 I slot print_timing: id 0 | task 20533 | eval time = 3825.32 ms / 155 tokens ( 24.84 ms per token, 40.26 tokens per second) 10.21.785.445 I slot print_timing: id 0 | task 20533 | total time = 4209.44 ms / 324 tokens 10.21.785.445 I slot print_timing: id 0 | task 20533 | graphs reused = 19627 10.21.785.446 I slot print_timing: id 0 | task 20533 | graph reallocs = 0 / 0 (same size) / (changed size) 10.21.785.465 I slot release: id 0 | task 20533 | stop processing: n_tokens = 323, truncated = 0 10.21.789.364 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.164 (> 0.100 thold), f_keep = 0.093 10.21.789.414 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 79.291 MiB) 10.21.793.387 I slot launch_slot_: id 0 | task 20691 | processing task, is_child = 0 10.22.763.401 I slot print_timing: id 0 | task 20691 | prompt eval time = 497.76 ms / 183 tokens ( 2.72 ms per token, 367.65 tokens per second) 10.22.763.404 I slot print_timing: id 0 | task 20691 | eval time = 472.25 ms / 20 tokens ( 24.86 ms per token, 40.23 tokens per second) 10.22.763.406 I slot print_timing: id 0 | task 20691 | total time = 970.00 ms / 203 tokens 10.22.763.406 I slot print_timing: id 0 | task 20691 | graphs reused = 19645 10.22.763.407 I slot print_timing: id 0 | task 20691 | graph reallocs = 0 / 0 (same size) / (changed size) 10.22.763.425 I slot release: id 0 | task 20691 | stop processing: n_tokens = 202, truncated = 0 10.22.767.533 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.174 (> 0.100 thold), f_keep = 0.149 10.22.767.574 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 67.160 MiB) 10.22.771.314 I slot launch_slot_: id 0 | task 20714 | processing task, is_child = 0 10.26.209.605 I slot print_timing: id 0 | task 20714 | n_gen = 123, tg = 40.40 t/s, tg_3s = 40.73 t/s 10.27.556.960 I slot print_timing: id 0 | task 20714 | prompt eval time = 418.63 ms / 172 tokens ( 2.43 ms per token, 410.87 tokens per second) 10.27.556.964 I slot print_timing: id 0 | task 20714 | eval time = 4367.01 ms / 177 tokens ( 24.81 ms per token, 40.30 tokens per second) 10.27.556.965 I slot print_timing: id 0 | task 20714 | total time = 4785.64 ms / 349 tokens 10.27.556.965 I slot print_timing: id 0 | task 20714 | graphs reused = 19819 10.27.556.966 I slot print_timing: id 0 | task 20714 | graph reallocs = 0 / 0 (same size) / (changed size) 10.27.556.991 I slot release: id 0 | task 20714 | stop processing: n_tokens = 348, truncated = 0 10.27.561.227 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.165 (> 0.100 thold), f_keep = 0.086 10.27.561.279 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 97.047 MiB) 10.27.564.028 I slot launch_slot_: id 0 | task 20894 | processing task, is_child = 0 10.31.057.514 I slot print_timing: id 0 | task 20894 | n_gen = 123, tg = 40.52 t/s, tg_3s = 40.85 t/s 10.34.062.397 I slot print_timing: id 0 | task 20894 | n_gen = 244, tg = 40.39 t/s, tg_3s = 40.27 t/s 10.37.063.198 I slot print_timing: id 0 | task 20894 | n_gen = 364, tg = 40.26 t/s, tg_3s = 39.99 t/s 10.40.074.142 I slot print_timing: id 0 | task 20894 | n_gen = 484, tg = 40.16 t/s, tg_3s = 39.85 t/s 10.40.249.236 I slot print_timing: id 0 | task 20894 | prompt eval time = 482.30 ms / 182 tokens ( 2.65 ms per token, 377.36 tokens per second) 10.40.249.243 I slot print_timing: id 0 | task 20894 | eval time = 12202.90 ms / 491 tokens ( 24.90 ms per token, 40.15 tokens per second) 10.40.249.243 I slot print_timing: id 0 | task 20894 | total time = 12685.20 ms / 673 tokens 10.40.249.244 I slot print_timing: id 0 | task 20894 | graphs reused = 20306 10.40.249.245 I slot print_timing: id 0 | task 20894 | graph reallocs = 0 / 0 (same size) / (changed size) 10.40.249.267 I slot release: id 0 | task 20894 | stop processing: n_tokens = 672, truncated = 0 10.40.253.515 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.049 10.40.253.590 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 115.438 MiB) 10.40.258.356 I slot launch_slot_: id 0 | task 21388 | processing task, is_child = 0 10.41.880.198 I slot print_timing: id 0 | task 21388 | prompt eval time = 483.02 ms / 181 tokens ( 2.67 ms per token, 374.73 tokens per second) 10.41.880.202 I slot print_timing: id 0 | task 21388 | eval time = 1138.81 ms / 47 tokens ( 24.76 ms per token, 40.39 tokens per second) 10.41.880.202 I slot print_timing: id 0 | task 21388 | total time = 1621.83 ms / 228 tokens 10.41.880.203 I slot print_timing: id 0 | task 21388 | graphs reused = 20351 10.41.880.204 I slot print_timing: id 0 | task 21388 | graph reallocs = 0 / 0 (same size) / (changed size) 10.41.880.222 I slot release: id 0 | task 21388 | stop processing: n_tokens = 227, truncated = 0 10.41.884.437 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.133 (> 0.100 thold), f_keep = 0.132 10.41.884.479 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 115.893 MiB) 10.41.886.479 I slot launch_slot_: id 0 | task 21438 | processing task, is_child = 0 10.45.433.569 I slot print_timing: id 0 | task 21438 | n_gen = 122, tg = 40.27 t/s, tg_3s = 40.60 t/s 10.45.683.139 I slot print_timing: id 0 | task 21438 | prompt eval time = 542.22 ms / 226 tokens ( 2.40 ms per token, 416.81 tokens per second) 10.45.683.143 I slot print_timing: id 0 | task 21438 | eval time = 3254.43 ms / 132 tokens ( 24.84 ms per token, 40.25 tokens per second) 10.45.683.144 I slot print_timing: id 0 | task 21438 | total time = 3796.65 ms / 358 tokens 10.45.683.145 I slot print_timing: id 0 | task 21438 | graphs reused = 20480 10.45.683.145 I slot print_timing: id 0 | task 21438 | graph reallocs = 0 / 0 (same size) / (changed size) 10.45.683.170 I slot release: id 0 | task 21438 | stop processing: n_tokens = 357, truncated = 0 10.45.687.145 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.189 (> 0.100 thold), f_keep = 0.084 10.45.692.850 I slot launch_slot_: id 0 | task 21573 | processing task, is_child = 0 10.46.834.048 I slot print_timing: id 0 | task 21573 | prompt eval time = 421.61 ms / 159 tokens ( 2.65 ms per token, 377.12 tokens per second) 10.46.834.054 I slot print_timing: id 0 | task 21573 | eval time = 719.58 ms / 30 tokens ( 24.81 ms per token, 40.30 tokens per second) 10.46.834.055 I slot print_timing: id 0 | task 21573 | total time = 1141.19 ms / 189 tokens 10.46.834.056 I slot print_timing: id 0 | task 21573 | graphs reused = 20508 10.46.834.056 I slot print_timing: id 0 | task 21573 | graph reallocs = 0 / 0 (same size) / (changed size) 10.46.834.075 I slot release: id 0 | task 21573 | stop processing: n_tokens = 188, truncated = 0 10.47.195.081 I srv operator(): operator(): cleaning up before exit...