$ /Users/minipro/quantdiff/llama.cpp/llama-b11770/llama-server -m /Users/minipro/quantdiff/models/campaign/af4779ec3bff/Spark-X2.6-4B-Q8_0.gguf --host 127.0.0.1 --port 8089 -c 4096 -np 1 -ngl 999 -fa on --jinja --seed 1234 --no-webui -a quant 0.00.044.163 I srv llama_server: initializing ... 0.00.044.168 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.045.554 I srv init_listene: The UI is disabled 0.00.045.556 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.045.677 W srv llama_server: security: no API key is set and CORS allows all origins (see https://github.com/ggml-org/llama.cpp/pull/25655) 0.00.047.681 I srv load_model: loading model '/Users/minipro/quantdiff/models/campaign/af4779ec3bff/Spark-X2.6-4B-Q8_0.gguf' 0.00.546.269 I cmn init: llama threadpool init, n_threads = 8 0.00.626.123 I srv load_model: initializing, n_slots = 1, n_ctx_slot = 4096, kv_unified = 'false' 0.00.638.523 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.00.638.718 I srv llama_server: model loaded 0.00.638.721 I srv llama_server: listening on http://127.0.0.1:8089 0.02.025.053 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.02.025.271 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.03.070.010 I slot print_timing: id 0 | task 0 | prompt eval time = 395.23 ms / 172 tokens ( 2.30 ms per token, 435.19 tokens per second) 0.03.070.013 I slot print_timing: id 0 | task 0 | eval time = 649.47 ms / 24 tokens ( 28.24 ms per token, 35.41 tokens per second) 0.03.070.014 I slot print_timing: id 0 | task 0 | total time = 1044.70 ms / 196 tokens 0.03.070.015 I slot print_timing: id 0 | task 0 | graphs reused = 23 0.03.070.015 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.03.070.042 I slot release: id 0 | task 0 | stop processing: n_tokens = 195, truncated = 0 0.03.075.515 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 0.03.082.137 I slot launch_slot_: id 0 | task 27 | processing task, is_child = 0 0.03.986.013 I slot print_timing: id 0 | task 27 | prompt eval time = 311.17 ms / 127 tokens ( 2.45 ms per token, 408.14 tokens per second) 0.03.986.017 I slot print_timing: id 0 | task 27 | eval time = 592.70 ms / 22 tokens ( 28.22 ms per token, 35.43 tokens per second) 0.03.986.018 I slot print_timing: id 0 | task 27 | total time = 903.86 ms / 149 tokens 0.03.986.019 I slot print_timing: id 0 | task 27 | graphs reused = 43 0.03.986.019 I slot print_timing: id 0 | task 27 | graph reallocs = 0 / 0 (same size) / (changed size) 0.03.986.042 I slot release: id 0 | task 27 | stop processing: n_tokens = 148, truncated = 0 0.03.990.568 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 0.03.995.388 I slot launch_slot_: id 0 | task 52 | processing task, is_child = 0 0.04.917.405 I slot print_timing: id 0 | task 52 | prompt eval time = 357.92 ms / 171 tokens ( 2.09 ms per token, 477.76 tokens per second) 0.04.917.409 I slot print_timing: id 0 | task 52 | eval time = 564.09 ms / 21 tokens ( 28.20 ms per token, 35.46 tokens per second) 0.04.917.409 I slot print_timing: id 0 | task 52 | total time = 922.01 ms / 192 tokens 0.04.917.410 I slot print_timing: id 0 | task 52 | graphs reused = 62 0.04.917.411 I slot print_timing: id 0 | task 52 | graph reallocs = 0 / 0 (same size) / (changed size) 0.04.917.439 I slot release: id 0 | task 52 | stop processing: n_tokens = 191, truncated = 0 0.04.922.282 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 0.04.928.374 I slot launch_slot_: id 0 | task 76 | processing task, is_child = 0 0.05.963.062 I slot print_timing: id 0 | task 76 | prompt eval time = 412.15 ms / 204 tokens ( 2.02 ms per token, 494.97 tokens per second) 0.05.963.069 I slot print_timing: id 0 | task 76 | eval time = 622.53 ms / 23 tokens ( 28.30 ms per token, 35.34 tokens per second) 0.05.963.070 I slot print_timing: id 0 | task 76 | total time = 1034.67 ms / 227 tokens 0.05.963.071 I slot print_timing: id 0 | task 76 | graphs reused = 83 0.05.963.071 I slot print_timing: id 0 | task 76 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.963.098 I slot release: id 0 | task 76 | stop processing: n_tokens = 226, truncated = 0 0.05.967.725 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 0.05.975.125 I slot launch_slot_: id 0 | task 102 | processing task, is_child = 0 0.07.192.285 I slot print_timing: id 0 | task 102 | prompt eval time = 400.15 ms / 187 tokens ( 2.14 ms per token, 467.33 tokens per second) 0.07.192.293 I slot print_timing: id 0 | task 102 | eval time = 817.00 ms / 30 tokens ( 28.17 ms per token, 35.50 tokens per second) 0.07.192.293 I slot print_timing: id 0 | task 102 | total time = 1217.15 ms / 217 tokens 0.07.192.294 I slot print_timing: id 0 | task 102 | graphs reused = 111 0.07.192.295 I slot print_timing: id 0 | task 102 | graph reallocs = 0 / 0 (same size) / (changed size) 0.07.192.321 I slot release: id 0 | task 102 | stop processing: n_tokens = 216, truncated = 0 0.07.197.080 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 0.07.203.163 I slot launch_slot_: id 0 | task 135 | processing task, is_child = 0 0.08.413.164 I slot print_timing: id 0 | task 135 | prompt eval time = 348.60 ms / 171 tokens ( 2.04 ms per token, 490.53 tokens per second) 0.08.413.168 I slot print_timing: id 0 | task 135 | eval time = 861.39 ms / 31 tokens ( 28.71 ms per token, 34.83 tokens per second) 0.08.413.169 I slot print_timing: id 0 | task 135 | total time = 1209.99 ms / 202 tokens 0.08.413.170 I slot print_timing: id 0 | task 135 | graphs reused = 140 0.08.413.170 I slot print_timing: id 0 | task 135 | graph reallocs = 0 / 0 (same size) / (changed size) 0.08.413.195 I slot release: id 0 | task 135 | stop processing: n_tokens = 201, truncated = 0 0.08.417.982 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 0.08.424.622 I slot launch_slot_: id 0 | task 169 | processing task, is_child = 0 0.09.616.121 I slot print_timing: id 0 | task 169 | prompt eval time = 455.96 ms / 221 tokens ( 2.06 ms per token, 484.70 tokens per second) 0.09.616.128 I slot print_timing: id 0 | task 169 | eval time = 735.53 ms / 27 tokens ( 28.29 ms per token, 35.35 tokens per second) 0.09.616.129 I slot print_timing: id 0 | task 169 | total time = 1191.49 ms / 248 tokens 0.09.616.129 I slot print_timing: id 0 | task 169 | graphs reused = 165 0.09.616.130 I slot print_timing: id 0 | task 169 | graph reallocs = 0 / 0 (same size) / (changed size) 0.09.616.161 I slot release: id 0 | task 169 | stop processing: n_tokens = 247, truncated = 0 0.09.620.713 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 0.09.628.237 I slot launch_slot_: id 0 | task 199 | processing task, is_child = 0 0.11.307.152 I slot print_timing: id 0 | task 199 | prompt eval time = 545.40 ms / 270 tokens ( 2.02 ms per token, 495.05 tokens per second) 0.11.307.156 I slot print_timing: id 0 | task 199 | eval time = 1133.51 ms / 41 tokens ( 28.34 ms per token, 35.29 tokens per second) 0.11.307.157 I slot print_timing: id 0 | task 199 | total time = 1678.90 ms / 311 tokens 0.11.307.158 I slot print_timing: id 0 | task 199 | graphs reused = 204 0.11.307.158 I slot print_timing: id 0 | task 199 | graph reallocs = 0 / 0 (same size) / (changed size) 0.11.307.184 I slot release: id 0 | task 199 | stop processing: n_tokens = 310, truncated = 0 0.11.311.324 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 0.11.321.037 I slot launch_slot_: id 0 | task 243 | processing task, is_child = 0 0.12.403.747 I slot print_timing: id 0 | task 243 | prompt eval time = 321.69 ms / 150 tokens ( 2.14 ms per token, 466.29 tokens per second) 0.12.403.751 I slot print_timing: id 0 | task 243 | eval time = 761.01 ms / 28 tokens ( 28.19 ms per token, 35.48 tokens per second) 0.12.403.752 I slot print_timing: id 0 | task 243 | total time = 1082.70 ms / 178 tokens 0.12.403.753 I slot print_timing: id 0 | task 243 | graphs reused = 230 0.12.403.753 I slot print_timing: id 0 | task 243 | graph reallocs = 0 / 0 (same size) / (changed size) 0.12.403.774 I slot release: id 0 | task 243 | stop processing: n_tokens = 177, truncated = 0 0.12.409.127 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 0.12.411.401 I slot launch_slot_: id 0 | task 274 | processing task, is_child = 0 0.13.304.928 I slot print_timing: id 0 | task 274 | prompt eval time = 356.49 ms / 167 tokens ( 2.13 ms per token, 468.46 tokens per second) 0.13.304.931 I slot print_timing: id 0 | task 274 | eval time = 537.02 ms / 20 tokens ( 28.26 ms per token, 35.38 tokens per second) 0.13.304.932 I slot print_timing: id 0 | task 274 | total time = 893.51 ms / 187 tokens 0.13.304.933 I slot print_timing: id 0 | task 274 | graphs reused = 248 0.13.304.933 I slot print_timing: id 0 | task 274 | graph reallocs = 0 / 0 (same size) / (changed size) 0.13.304.957 I slot release: id 0 | task 274 | stop processing: n_tokens = 186, truncated = 0 0.13.309.572 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 0.13.314.618 I slot launch_slot_: id 0 | task 297 | processing task, is_child = 0 0.16.661.277 I slot print_timing: id 0 | task 297 | n_gen = 108, tg = 35.52 t/s, tg_3s = 35.86 t/s 0.19.684.241 I slot print_timing: id 0 | task 297 | n_gen = 215, tg = 35.46 t/s, tg_3s = 35.40 t/s 0.20.877.380 I slot print_timing: id 0 | task 297 | prompt eval time = 334.64 ms / 171 tokens ( 1.96 ms per token, 511.00 tokens per second) 0.20.877.388 I slot print_timing: id 0 | task 297 | eval time = 7228.11 ms / 257 tokens ( 28.23 ms per token, 35.42 tokens per second) 0.20.877.389 I slot print_timing: id 0 | task 297 | total time = 7562.75 ms / 428 tokens 0.20.877.390 I slot print_timing: id 0 | task 297 | graphs reused = 502 0.20.877.390 I slot print_timing: id 0 | task 297 | graph reallocs = 0 / 0 (same size) / (changed size) 0.20.877.413 I slot release: id 0 | task 297 | stop processing: n_tokens = 427, truncated = 0 0.20.882.737 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.140 (> 0.100 thold), f_keep = 0.070 0.20.892.879 I slot launch_slot_: id 0 | task 557 | processing task, is_child = 0 0.24.333.040 I slot print_timing: id 0 | task 557 | n_gen = 108, tg = 35.35 t/s, tg_3s = 35.68 t/s 0.26.401.231 I slot print_timing: id 0 | task 557 | prompt eval time = 413.59 ms / 214 tokens ( 1.93 ms per token, 517.42 tokens per second) 0.26.401.239 I slot print_timing: id 0 | task 557 | eval time = 5094.74 ms / 181 tokens ( 28.30 ms per token, 35.33 tokens per second) 0.26.401.240 I slot print_timing: id 0 | task 557 | total time = 5508.33 ms / 395 tokens 0.26.401.241 I slot print_timing: id 0 | task 557 | graphs reused = 680 0.26.401.241 I slot print_timing: id 0 | task 557 | graph reallocs = 0 / 0 (same size) / (changed size) 0.26.401.267 I slot release: id 0 | task 557 | stop processing: n_tokens = 394, truncated = 0 0.26.405.739 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.164 (> 0.100 thold), f_keep = 0.076 0.26.415.874 I slot launch_slot_: id 0 | task 741 | processing task, is_child = 0 0.27.858.706 I slot print_timing: id 0 | task 741 | prompt eval time = 399.86 ms / 183 tokens ( 2.19 ms per token, 457.66 tokens per second) 0.27.858.712 I slot print_timing: id 0 | task 741 | eval time = 1042.96 ms / 38 tokens ( 28.19 ms per token, 35.48 tokens per second) 0.27.858.713 I slot print_timing: id 0 | task 741 | total time = 1442.82 ms / 221 tokens 0.27.858.713 I slot print_timing: id 0 | task 741 | graphs reused = 716 0.27.858.714 I slot print_timing: id 0 | task 741 | graph reallocs = 0 / 0 (same size) / (changed size) 0.27.858.741 I slot release: id 0 | task 741 | stop processing: n_tokens = 220, truncated = 0 0.27.863.472 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 0.27.868.806 I slot launch_slot_: id 0 | task 782 | processing task, is_child = 0 0.29.015.031 I slot print_timing: id 0 | task 782 | prompt eval time = 411.04 ms / 183 tokens ( 2.25 ms per token, 445.21 tokens per second) 0.29.015.036 I slot print_timing: id 0 | task 782 | eval time = 735.16 ms / 27 tokens ( 28.28 ms per token, 35.37 tokens per second) 0.29.015.037 I slot print_timing: id 0 | task 782 | total time = 1146.20 ms / 210 tokens 0.29.015.038 I slot print_timing: id 0 | task 782 | graphs reused = 741 0.29.015.038 I slot print_timing: id 0 | task 782 | graph reallocs = 0 / 0 (same size) / (changed size) 0.29.015.063 I slot release: id 0 | task 782 | stop processing: n_tokens = 209, truncated = 0 0.29.019.645 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 0.29.027.333 I slot launch_slot_: id 0 | task 812 | processing task, is_child = 0 0.30.356.875 I slot print_timing: id 0 | task 812 | prompt eval time = 370.96 ms / 170 tokens ( 2.18 ms per token, 458.27 tokens per second) 0.30.356.879 I slot print_timing: id 0 | task 812 | eval time = 958.56 ms / 35 tokens ( 28.19 ms per token, 35.47 tokens per second) 0.30.356.879 I slot print_timing: id 0 | task 812 | total time = 1329.53 ms / 205 tokens 0.30.356.880 I slot print_timing: id 0 | task 812 | graphs reused = 774 0.30.356.881 I slot print_timing: id 0 | task 812 | graph reallocs = 0 / 0 (same size) / (changed size) 0.30.356.902 I slot release: id 0 | task 812 | stop processing: n_tokens = 204, truncated = 0 0.30.361.429 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 0.30.368.636 I slot launch_slot_: id 0 | task 850 | processing task, is_child = 0 0.31.565.562 I slot print_timing: id 0 | task 850 | prompt eval time = 322.71 ms / 150 tokens ( 2.15 ms per token, 464.82 tokens per second) 0.31.565.569 I slot print_timing: id 0 | task 850 | eval time = 874.21 ms / 32 tokens ( 28.20 ms per token, 35.46 tokens per second) 0.31.565.570 I slot print_timing: id 0 | task 850 | total time = 1196.92 ms / 182 tokens 0.31.565.570 I slot print_timing: id 0 | task 850 | graphs reused = 804 0.31.565.571 I slot print_timing: id 0 | task 850 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.565.592 I slot release: id 0 | task 850 | stop processing: n_tokens = 181, truncated = 0 0.31.570.096 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 0.31.575.303 I slot launch_slot_: id 0 | task 885 | processing task, is_child = 0 0.32.526.776 I slot print_timing: id 0 | task 885 | prompt eval time = 357.53 ms / 174 tokens ( 2.05 ms per token, 486.67 tokens per second) 0.32.526.781 I slot print_timing: id 0 | task 885 | eval time = 593.93 ms / 22 tokens ( 28.28 ms per token, 35.36 tokens per second) 0.32.526.782 I slot print_timing: id 0 | task 885 | total time = 951.46 ms / 196 tokens 0.32.526.783 I slot print_timing: id 0 | task 885 | graphs reused = 824 0.32.526.784 I slot print_timing: id 0 | task 885 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.526.809 I slot release: id 0 | task 885 | stop processing: n_tokens = 195, truncated = 0 0.32.531.204 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 0.32.538.188 I slot launch_slot_: id 0 | task 910 | processing task, is_child = 0 0.33.433.807 I slot print_timing: id 0 | task 910 | prompt eval time = 357.73 ms / 156 tokens ( 2.29 ms per token, 436.08 tokens per second) 0.33.433.814 I slot print_timing: id 0 | task 910 | eval time = 537.88 ms / 20 tokens ( 28.31 ms per token, 35.32 tokens per second) 0.33.433.815 I slot print_timing: id 0 | task 910 | total time = 895.61 ms / 176 tokens 0.33.433.816 I slot print_timing: id 0 | task 910 | graphs reused = 842 0.33.433.816 I slot print_timing: id 0 | task 910 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.433.838 I slot release: id 0 | task 910 | stop processing: n_tokens = 175, truncated = 0 0.33.437.857 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 0.33.443.750 I slot launch_slot_: id 0 | task 933 | processing task, is_child = 0 0.34.257.783 I slot print_timing: id 0 | task 933 | prompt eval time = 333.32 ms / 152 tokens ( 2.19 ms per token, 456.02 tokens per second) 0.34.257.787 I slot print_timing: id 0 | task 933 | eval time = 480.70 ms / 18 tokens ( 28.28 ms per token, 35.36 tokens per second) 0.34.257.788 I slot print_timing: id 0 | task 933 | total time = 814.02 ms / 170 tokens 0.34.257.789 I slot print_timing: id 0 | task 933 | graphs reused = 858 0.34.257.789 I slot print_timing: id 0 | task 933 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.257.809 I slot release: id 0 | task 933 | stop processing: n_tokens = 169, truncated = 0 0.34.262.425 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 0.34.268.314 I slot launch_slot_: id 0 | task 954 | processing task, is_child = 0 0.35.740.092 I slot print_timing: id 0 | task 954 | prompt eval time = 399.31 ms / 187 tokens ( 2.14 ms per token, 468.31 tokens per second) 0.35.740.100 I slot print_timing: id 0 | task 954 | eval time = 1072.46 ms / 39 tokens ( 28.22 ms per token, 35.43 tokens per second) 0.35.740.101 I slot print_timing: id 0 | task 954 | total time = 1471.77 ms / 226 tokens 0.35.740.102 I slot print_timing: id 0 | task 954 | graphs reused = 895 0.35.740.102 I slot print_timing: id 0 | task 954 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.740.128 I slot release: id 0 | task 954 | stop processing: n_tokens = 225, truncated = 0 0.35.744.466 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 0.35.750.952 I slot launch_slot_: id 0 | task 996 | processing task, is_child = 0 0.37.251.786 I slot print_timing: id 0 | task 996 | prompt eval time = 356.97 ms / 160 tokens ( 2.23 ms per token, 448.21 tokens per second) 0.37.251.792 I slot print_timing: id 0 | task 996 | eval time = 1143.85 ms / 41 tokens ( 28.60 ms per token, 34.97 tokens per second) 0.37.251.793 I slot print_timing: id 0 | task 996 | total time = 1500.82 ms / 201 tokens 0.37.251.794 I slot print_timing: id 0 | task 996 | graphs reused = 934 0.37.251.794 I slot print_timing: id 0 | task 996 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.251.815 I slot release: id 0 | task 996 | stop processing: n_tokens = 200, truncated = 0 0.37.256.506 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.144 (> 0.100 thold), f_keep = 0.150 0.37.263.633 I slot launch_slot_: id 0 | task 1040 | processing task, is_child = 0 0.38.732.128 I slot print_timing: id 0 | task 1040 | prompt eval time = 412.20 ms / 208 tokens ( 1.98 ms per token, 504.60 tokens per second) 0.38.732.133 I slot print_timing: id 0 | task 1040 | eval time = 1056.28 ms / 38 tokens ( 28.55 ms per token, 35.03 tokens per second) 0.38.732.134 I slot print_timing: id 0 | task 1040 | total time = 1468.49 ms / 246 tokens 0.38.732.134 I slot print_timing: id 0 | task 1040 | graphs reused = 970 0.38.732.135 I slot print_timing: id 0 | task 1040 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.732.157 I slot release: id 0 | task 1040 | stop processing: n_tokens = 245, truncated = 0 0.38.736.692 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 0.38.745.184 I slot launch_slot_: id 0 | task 1081 | processing task, is_child = 0 0.42.172.962 I slot print_timing: id 0 | task 1081 | n_gen = 108, tg = 35.45 t/s, tg_3s = 35.78 t/s 0.43.190.173 I slot print_timing: id 0 | task 1081 | prompt eval time = 409.44 ms / 192 tokens ( 2.13 ms per token, 468.93 tokens per second) 0.43.190.177 I slot print_timing: id 0 | task 1081 | eval time = 4035.54 ms / 144 tokens ( 28.22 ms per token, 35.44 tokens per second) 0.43.190.178 I slot print_timing: id 0 | task 1081 | total time = 4444.98 ms / 336 tokens 0.43.190.179 I slot print_timing: id 0 | task 1081 | graphs reused = 1111 0.43.190.179 I slot print_timing: id 0 | task 1081 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.190.204 I slot release: id 0 | task 1081 | stop processing: n_tokens = 335, truncated = 0 0.43.195.104 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 0.43.204.344 I slot launch_slot_: id 0 | task 1228 | processing task, is_child = 0 0.44.970.426 I slot print_timing: id 0 | task 1228 | prompt eval time = 400.98 ms / 198 tokens ( 2.03 ms per token, 493.79 tokens per second) 0.44.970.432 I slot print_timing: id 0 | task 1228 | eval time = 1365.08 ms / 49 tokens ( 28.44 ms per token, 35.16 tokens per second) 0.44.970.433 I slot print_timing: id 0 | task 1228 | total time = 1766.06 ms / 247 tokens 0.44.970.433 I slot print_timing: id 0 | task 1228 | graphs reused = 1158 0.44.970.434 I slot print_timing: id 0 | task 1228 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.970.458 I slot release: id 0 | task 1228 | stop processing: n_tokens = 246, truncated = 0 0.44.975.365 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 0.44.983.101 I slot launch_slot_: id 0 | task 1280 | processing task, is_child = 0 0.46.487.310 I slot print_timing: id 0 | task 1280 | prompt eval time = 456.65 ms / 235 tokens ( 1.94 ms per token, 514.62 tokens per second) 0.46.487.317 I slot print_timing: id 0 | task 1280 | eval time = 1047.55 ms / 38 tokens ( 28.31 ms per token, 35.32 tokens per second) 0.46.487.317 I slot print_timing: id 0 | task 1280 | total time = 1504.20 ms / 273 tokens 0.46.487.318 I slot print_timing: id 0 | task 1280 | graphs reused = 1193 0.46.487.319 I slot print_timing: id 0 | task 1280 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.487.350 I slot release: id 0 | task 1280 | stop processing: n_tokens = 272, truncated = 0 0.46.491.906 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 0.46.500.891 I slot launch_slot_: id 0 | task 1321 | processing task, is_child = 0 0.47.861.712 I slot print_timing: id 0 | task 1321 | prompt eval time = 401.44 ms / 199 tokens ( 2.02 ms per token, 495.72 tokens per second) 0.47.861.719 I slot print_timing: id 0 | task 1321 | eval time = 959.37 ms / 35 tokens ( 28.22 ms per token, 35.44 tokens per second) 0.47.861.720 I slot print_timing: id 0 | task 1321 | total time = 1360.81 ms / 234 tokens 0.47.861.720 I slot print_timing: id 0 | task 1321 | graphs reused = 1226 0.47.861.721 I slot print_timing: id 0 | task 1321 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.861.743 I slot release: id 0 | task 1321 | stop processing: n_tokens = 233, truncated = 0 0.47.866.452 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 0.47.873.314 I slot launch_slot_: id 0 | task 1359 | processing task, is_child = 0 0.49.244.771 I slot print_timing: id 0 | task 1359 | prompt eval time = 357.57 ms / 157 tokens ( 2.28 ms per token, 439.07 tokens per second) 0.49.244.778 I slot print_timing: id 0 | task 1359 | eval time = 1013.88 ms / 37 tokens ( 28.16 ms per token, 35.51 tokens per second) 0.49.244.779 I slot print_timing: id 0 | task 1359 | total time = 1371.45 ms / 194 tokens 0.49.244.779 I slot print_timing: id 0 | task 1359 | graphs reused = 1261 0.49.244.780 I slot print_timing: id 0 | task 1359 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.244.806 I slot release: id 0 | task 1359 | stop processing: n_tokens = 193, truncated = 0 0.49.249.234 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 0.49.254.378 I slot launch_slot_: id 0 | task 1399 | processing task, is_child = 0 0.50.629.339 I slot print_timing: id 0 | task 1399 | prompt eval time = 359.31 ms / 184 tokens ( 1.95 ms per token, 512.09 tokens per second) 0.50.629.345 I slot print_timing: id 0 | task 1399 | eval time = 1015.64 ms / 37 tokens ( 28.21 ms per token, 35.45 tokens per second) 0.50.629.346 I slot print_timing: id 0 | task 1399 | total time = 1374.95 ms / 221 tokens 0.50.629.347 I slot print_timing: id 0 | task 1399 | graphs reused = 1296 0.50.629.347 I slot print_timing: id 0 | task 1399 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.629.368 I slot release: id 0 | task 1399 | stop processing: n_tokens = 220, truncated = 0 0.50.634.474 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 0.50.641.828 I slot launch_slot_: id 0 | task 1439 | processing task, is_child = 0 0.52.537.140 I slot print_timing: id 0 | task 1439 | prompt eval time = 454.10 ms / 214 tokens ( 2.12 ms per token, 471.26 tokens per second) 0.52.537.144 I slot print_timing: id 0 | task 1439 | eval time = 1441.20 ms / 52 tokens ( 28.26 ms per token, 35.39 tokens per second) 0.52.537.144 I slot print_timing: id 0 | task 1439 | total time = 1895.30 ms / 266 tokens 0.52.537.145 I slot print_timing: id 0 | task 1439 | graphs reused = 1345 0.52.537.146 I slot print_timing: id 0 | task 1439 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.537.170 I slot release: id 0 | task 1439 | stop processing: n_tokens = 265, truncated = 0 0.52.541.840 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 0.52.549.062 I slot launch_slot_: id 0 | task 1494 | processing task, is_child = 0 0.53.946.831 I slot print_timing: id 0 | task 1494 | prompt eval time = 409.66 ms / 186 tokens ( 2.20 ms per token, 454.04 tokens per second) 0.53.946.835 I slot print_timing: id 0 | task 1494 | eval time = 988.10 ms / 36 tokens ( 28.23 ms per token, 35.42 tokens per second) 0.53.946.835 I slot print_timing: id 0 | task 1494 | total time = 1397.76 ms / 222 tokens 0.53.946.836 I slot print_timing: id 0 | task 1494 | graphs reused = 1379 0.53.946.837 I slot print_timing: id 0 | task 1494 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.946.866 I slot release: id 0 | task 1494 | stop processing: n_tokens = 221, truncated = 0 0.53.951.285 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 0.53.958.743 I slot launch_slot_: id 0 | task 1533 | processing task, is_child = 0 0.55.316.650 I slot print_timing: id 0 | task 1533 | prompt eval time = 372.23 ms / 163 tokens ( 2.28 ms per token, 437.90 tokens per second) 0.55.316.654 I slot print_timing: id 0 | task 1533 | eval time = 985.67 ms / 36 tokens ( 28.16 ms per token, 35.51 tokens per second) 0.55.316.659 I slot print_timing: id 0 | task 1533 | total time = 1357.90 ms / 199 tokens 0.55.316.659 I slot print_timing: id 0 | task 1533 | graphs reused = 1413 0.55.316.660 I slot print_timing: id 0 | task 1533 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.316.686 I slot release: id 0 | task 1533 | stop processing: n_tokens = 198, truncated = 0 0.55.321.497 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 0.55.327.106 I slot launch_slot_: id 0 | task 1572 | processing task, is_child = 0 0.56.085.823 I slot print_timing: id 0 | task 1572 | prompt eval time = 334.48 ms / 163 tokens ( 2.05 ms per token, 487.33 tokens per second) 0.56.085.829 I slot print_timing: id 0 | task 1572 | eval time = 424.23 ms / 16 tokens ( 28.28 ms per token, 35.36 tokens per second) 0.56.085.830 I slot print_timing: id 0 | task 1572 | total time = 758.70 ms / 179 tokens 0.56.085.831 I slot print_timing: id 0 | task 1572 | graphs reused = 1427 0.56.085.831 I slot print_timing: id 0 | task 1572 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.085.861 I slot release: id 0 | task 1572 | stop processing: n_tokens = 178, truncated = 0 0.56.090.767 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.160 (> 0.100 thold), f_keep = 0.169 0.56.096.900 I slot launch_slot_: id 0 | task 1591 | processing task, is_child = 0 0.57.498.677 I slot print_timing: id 0 | task 1591 | prompt eval time = 413.01 ms / 187 tokens ( 2.21 ms per token, 452.77 tokens per second) 0.57.498.684 I slot print_timing: id 0 | task 1591 | eval time = 988.75 ms / 36 tokens ( 28.25 ms per token, 35.40 tokens per second) 0.57.498.684 I slot print_timing: id 0 | task 1591 | total time = 1401.76 ms / 223 tokens 0.57.498.685 I slot print_timing: id 0 | task 1591 | graphs reused = 1461 0.57.498.686 I slot print_timing: id 0 | task 1591 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.498.709 I slot release: id 0 | task 1591 | stop processing: n_tokens = 222, truncated = 0 0.57.503.226 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 0.57.510.412 I slot launch_slot_: id 0 | task 1630 | processing task, is_child = 0 0.58.891.434 I slot print_timing: id 0 | task 1630 | prompt eval time = 421.93 ms / 205 tokens ( 2.06 ms per token, 485.87 tokens per second) 0.58.891.441 I slot print_timing: id 0 | task 1630 | eval time = 959.08 ms / 35 tokens ( 28.21 ms per token, 35.45 tokens per second) 0.58.891.441 I slot print_timing: id 0 | task 1630 | total time = 1381.01 ms / 240 tokens 0.58.891.442 I slot print_timing: id 0 | task 1630 | graphs reused = 1494 0.58.891.443 I slot print_timing: id 0 | task 1630 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.891.473 I slot release: id 0 | task 1630 | stop processing: n_tokens = 239, truncated = 0 0.58.895.818 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 0.58.902.346 I slot launch_slot_: id 0 | task 1668 | processing task, is_child = 0 1.00.117.335 I slot print_timing: id 0 | task 1668 | prompt eval time = 340.99 ms / 158 tokens ( 2.16 ms per token, 463.36 tokens per second) 1.00.117.340 I slot print_timing: id 0 | task 1668 | eval time = 873.98 ms / 32 tokens ( 28.19 ms per token, 35.47 tokens per second) 1.00.117.341 I slot print_timing: id 0 | task 1668 | total time = 1214.97 ms / 190 tokens 1.00.117.342 I slot print_timing: id 0 | task 1668 | graphs reused = 1524 1.00.117.342 I slot print_timing: id 0 | task 1668 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.117.377 I slot release: id 0 | task 1668 | stop processing: n_tokens = 189, truncated = 0 1.00.122.241 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.153 (> 0.100 thold), f_keep = 0.159 1.00.127.513 I slot launch_slot_: id 0 | task 1703 | processing task, is_child = 0 1.01.332.578 I slot print_timing: id 0 | task 1703 | prompt eval time = 387.43 ms / 196 tokens ( 1.98 ms per token, 505.90 tokens per second) 1.01.332.582 I slot print_timing: id 0 | task 1703 | eval time = 817.62 ms / 30 tokens ( 28.19 ms per token, 35.47 tokens per second) 1.01.332.583 I slot print_timing: id 0 | task 1703 | total time = 1205.05 ms / 226 tokens 1.01.332.584 I slot print_timing: id 0 | task 1703 | graphs reused = 1552 1.01.332.584 I slot print_timing: id 0 | task 1703 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.332.608 I slot release: id 0 | task 1703 | stop processing: n_tokens = 225, truncated = 0 1.01.337.023 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 1.01.345.004 I slot launch_slot_: id 0 | task 1736 | processing task, is_child = 0 1.02.223.682 I slot print_timing: id 0 | task 1736 | prompt eval time = 286.90 ms / 127 tokens ( 2.26 ms per token, 442.66 tokens per second) 1.02.223.686 I slot print_timing: id 0 | task 1736 | eval time = 591.76 ms / 22 tokens ( 28.18 ms per token, 35.49 tokens per second) 1.02.223.686 I slot print_timing: id 0 | task 1736 | total time = 878.66 ms / 149 tokens 1.02.223.687 I slot print_timing: id 0 | task 1736 | graphs reused = 1572 1.02.223.687 I slot print_timing: id 0 | task 1736 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.223.715 I slot release: id 0 | task 1736 | stop processing: n_tokens = 148, truncated = 0 1.02.227.877 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 1.02.232.130 I slot launch_slot_: id 0 | task 1761 | processing task, is_child = 0 1.04.097.977 I slot print_timing: id 0 | task 1761 | prompt eval time = 290.39 ms / 134 tokens ( 2.17 ms per token, 461.45 tokens per second) 1.04.097.984 I slot print_timing: id 0 | task 1761 | eval time = 1575.45 ms / 57 tokens ( 28.13 ms per token, 35.55 tokens per second) 1.04.097.984 I slot print_timing: id 0 | task 1761 | total time = 1865.83 ms / 191 tokens 1.04.097.985 I slot print_timing: id 0 | task 1761 | graphs reused = 1627 1.04.097.985 I slot print_timing: id 0 | task 1761 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.098.010 I slot release: id 0 | task 1761 | stop processing: n_tokens = 190, truncated = 0 1.04.102.433 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 1.04.108.283 I slot launch_slot_: id 0 | task 1821 | processing task, is_child = 0 1.04.889.055 I slot print_timing: id 0 | task 1821 | prompt eval time = 329.00 ms / 148 tokens ( 2.22 ms per token, 449.84 tokens per second) 1.04.889.062 I slot print_timing: id 0 | task 1821 | eval time = 451.76 ms / 17 tokens ( 28.23 ms per token, 35.42 tokens per second) 1.04.889.062 I slot print_timing: id 0 | task 1821 | total time = 780.76 ms / 165 tokens 1.04.889.063 I slot print_timing: id 0 | task 1821 | graphs reused = 1642 1.04.889.064 I slot print_timing: id 0 | task 1821 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.889.087 I slot release: id 0 | task 1821 | stop processing: n_tokens = 164, truncated = 0 1.04.893.247 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 1.04.899.050 I slot launch_slot_: id 0 | task 1841 | processing task, is_child = 0 1.05.986.945 I slot print_timing: id 0 | task 1841 | prompt eval time = 326.36 ms / 145 tokens ( 2.25 ms per token, 444.30 tokens per second) 1.05.986.948 I slot print_timing: id 0 | task 1841 | eval time = 761.53 ms / 28 tokens ( 28.20 ms per token, 35.46 tokens per second) 1.05.986.949 I slot print_timing: id 0 | task 1841 | total time = 1087.88 ms / 173 tokens 1.05.986.950 I slot print_timing: id 0 | task 1841 | graphs reused = 1668 1.05.986.950 I slot print_timing: id 0 | task 1841 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.986.976 I slot release: id 0 | task 1841 | stop processing: n_tokens = 172, truncated = 0 1.05.991.751 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 1.05.997.472 I slot launch_slot_: id 0 | task 1872 | processing task, is_child = 0 1.07.285.102 I slot print_timing: id 0 | task 1872 | prompt eval time = 401.71 ms / 200 tokens ( 2.01 ms per token, 497.87 tokens per second) 1.07.285.113 I slot print_timing: id 0 | task 1872 | eval time = 885.91 ms / 32 tokens ( 28.58 ms per token, 34.99 tokens per second) 1.07.285.113 I slot print_timing: id 0 | task 1872 | total time = 1287.62 ms / 232 tokens 1.07.285.115 I slot print_timing: id 0 | task 1872 | graphs reused = 1698 1.07.285.115 I slot print_timing: id 0 | task 1872 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.285.141 I slot release: id 0 | task 1872 | stop processing: n_tokens = 231, truncated = 0 1.07.291.451 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 231, t_last = 318425274689 1.07.298.623 I slot launch_slot_: id 0 | task 1907 | processing task, is_child = 0 1.09.558.965 I slot print_timing: id 0 | task 1907 | prompt eval time = 601.31 ms / 326 tokens ( 1.84 ms per token, 542.15 tokens per second) 1.09.558.969 I slot print_timing: id 0 | task 1907 | eval time = 1659.02 ms / 59 tokens ( 28.60 ms per token, 34.96 tokens per second) 1.09.558.970 I slot print_timing: id 0 | task 1907 | total time = 2260.33 ms / 385 tokens 1.09.558.971 I slot print_timing: id 0 | task 1907 | graphs reused = 1755 1.09.558.971 I slot print_timing: id 0 | task 1907 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.559.005 I slot release: id 0 | task 1907 | stop processing: n_tokens = 384, truncated = 0 1.09.563.561 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 1.09.576.392 I slot launch_slot_: id 0 | task 1969 | processing task, is_child = 0 1.10.541.881 I slot print_timing: id 0 | task 1969 | prompt eval time = 317.60 ms / 148 tokens ( 2.15 ms per token, 465.99 tokens per second) 1.10.541.884 I slot print_timing: id 0 | task 1969 | eval time = 647.88 ms / 24 tokens ( 28.17 ms per token, 35.50 tokens per second) 1.10.541.885 I slot print_timing: id 0 | task 1969 | total time = 965.48 ms / 172 tokens 1.10.541.886 I slot print_timing: id 0 | task 1969 | graphs reused = 1777 1.10.541.886 I slot print_timing: id 0 | task 1969 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.541.917 I slot release: id 0 | task 1969 | stop processing: n_tokens = 171, truncated = 0 1.10.546.608 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 1.10.549.736 I slot launch_slot_: id 0 | task 1996 | processing task, is_child = 0 1.11.653.125 I slot print_timing: id 0 | task 1996 | prompt eval time = 342.63 ms / 175 tokens ( 1.96 ms per token, 510.76 tokens per second) 1.11.653.129 I slot print_timing: id 0 | task 1996 | eval time = 760.75 ms / 28 tokens ( 28.18 ms per token, 35.49 tokens per second) 1.11.653.129 I slot print_timing: id 0 | task 1996 | total time = 1103.38 ms / 203 tokens 1.11.653.130 I slot print_timing: id 0 | task 1996 | graphs reused = 1803 1.11.653.131 I slot print_timing: id 0 | task 1996 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.653.160 I slot release: id 0 | task 1996 | stop processing: n_tokens = 202, truncated = 0 1.11.658.089 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 1.11.664.913 I slot launch_slot_: id 0 | task 2027 | processing task, is_child = 0 1.13.224.857 I slot print_timing: id 0 | task 2027 | prompt eval time = 456.56 ms / 229 tokens ( 1.99 ms per token, 501.57 tokens per second) 1.13.224.862 I slot print_timing: id 0 | task 2027 | eval time = 1103.37 ms / 40 tokens ( 28.29 ms per token, 35.35 tokens per second) 1.13.224.862 I slot print_timing: id 0 | task 2027 | total time = 1559.93 ms / 269 tokens 1.13.224.863 I slot print_timing: id 0 | task 2027 | graphs reused = 1840 1.13.224.864 I slot print_timing: id 0 | task 2027 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.224.889 I slot release: id 0 | task 2027 | stop processing: n_tokens = 268, truncated = 0 1.13.229.875 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 1.13.238.543 I slot launch_slot_: id 0 | task 2070 | processing task, is_child = 0 1.14.475.364 I slot print_timing: id 0 | task 2070 | prompt eval time = 470.22 ms / 238 tokens ( 1.98 ms per token, 506.15 tokens per second) 1.14.475.368 I slot print_timing: id 0 | task 2070 | eval time = 766.59 ms / 28 tokens ( 28.39 ms per token, 35.22 tokens per second) 1.14.475.369 I slot print_timing: id 0 | task 2070 | total time = 1236.81 ms / 266 tokens 1.14.475.369 I slot print_timing: id 0 | task 2070 | graphs reused = 1865 1.14.475.370 I slot print_timing: id 0 | task 2070 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.475.395 I slot release: id 0 | task 2070 | stop processing: n_tokens = 265, truncated = 0 1.14.479.881 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 1.14.489.028 I slot launch_slot_: id 0 | task 2101 | processing task, is_child = 0 1.15.812.897 I slot print_timing: id 0 | task 2101 | prompt eval time = 338.68 ms / 162 tokens ( 2.09 ms per token, 478.33 tokens per second) 1.15.812.904 I slot print_timing: id 0 | task 2101 | eval time = 985.18 ms / 36 tokens ( 28.15 ms per token, 35.53 tokens per second) 1.15.812.904 I slot print_timing: id 0 | task 2101 | total time = 1323.86 ms / 198 tokens 1.15.812.905 I slot print_timing: id 0 | task 2101 | graphs reused = 1899 1.15.812.905 I slot print_timing: id 0 | task 2101 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.812.936 I slot release: id 0 | task 2101 | stop processing: n_tokens = 197, truncated = 0 1.15.817.663 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 1.15.821.285 I slot launch_slot_: id 0 | task 2140 | processing task, is_child = 0 1.16.899.769 I slot print_timing: id 0 | task 2140 | prompt eval time = 371.83 ms / 169 tokens ( 2.20 ms per token, 454.51 tokens per second) 1.16.899.774 I slot print_timing: id 0 | task 2140 | eval time = 706.64 ms / 26 tokens ( 28.27 ms per token, 35.38 tokens per second) 1.16.899.775 I slot print_timing: id 0 | task 2140 | total time = 1078.47 ms / 195 tokens 1.16.899.775 I slot print_timing: id 0 | task 2140 | graphs reused = 1923 1.16.899.776 I slot print_timing: id 0 | task 2140 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.899.799 I slot release: id 0 | task 2140 | stop processing: n_tokens = 194, truncated = 0 1.16.904.438 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 1.16.911.085 I slot launch_slot_: id 0 | task 2169 | processing task, is_child = 0 1.18.069.855 I slot print_timing: id 0 | task 2169 | prompt eval time = 396.15 ms / 180 tokens ( 2.20 ms per token, 454.37 tokens per second) 1.18.069.861 I slot print_timing: id 0 | task 2169 | eval time = 762.60 ms / 28 tokens ( 28.24 ms per token, 35.41 tokens per second) 1.18.069.862 I slot print_timing: id 0 | task 2169 | total time = 1158.76 ms / 208 tokens 1.18.069.863 I slot print_timing: id 0 | task 2169 | graphs reused = 1949 1.18.069.864 I slot print_timing: id 0 | task 2169 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.069.889 I slot release: id 0 | task 2169 | stop processing: n_tokens = 207, truncated = 0 1.18.074.602 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 1.18.081.972 I slot launch_slot_: id 0 | task 2200 | processing task, is_child = 0 1.19.745.734 I slot print_timing: id 0 | task 2200 | prompt eval time = 423.35 ms / 203 tokens ( 2.09 ms per token, 479.51 tokens per second) 1.19.745.741 I slot print_timing: id 0 | task 2200 | eval time = 1240.40 ms / 45 tokens ( 28.19 ms per token, 35.47 tokens per second) 1.19.745.742 I slot print_timing: id 0 | task 2200 | total time = 1663.75 ms / 248 tokens 1.19.745.742 I slot print_timing: id 0 | task 2200 | graphs reused = 1992 1.19.745.743 I slot print_timing: id 0 | task 2200 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.745.775 I slot release: id 0 | task 2200 | stop processing: n_tokens = 247, truncated = 0 1.19.750.241 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 1.19.756.989 I slot launch_slot_: id 0 | task 2248 | processing task, is_child = 0 1.20.939.049 I slot print_timing: id 0 | task 2248 | prompt eval time = 364.06 ms / 157 tokens ( 2.32 ms per token, 431.25 tokens per second) 1.20.939.053 I slot print_timing: id 0 | task 2248 | eval time = 817.98 ms / 30 tokens ( 28.21 ms per token, 35.45 tokens per second) 1.20.939.053 I slot print_timing: id 0 | task 2248 | total time = 1182.04 ms / 187 tokens 1.20.939.054 I slot print_timing: id 0 | task 2248 | graphs reused = 2020 1.20.939.054 I slot print_timing: id 0 | task 2248 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.939.080 I slot release: id 0 | task 2248 | stop processing: n_tokens = 186, truncated = 0 1.20.943.782 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 1.20.948.846 I slot launch_slot_: id 0 | task 2281 | processing task, is_child = 0 1.22.049.503 I slot print_timing: id 0 | task 2281 | prompt eval time = 421.17 ms / 214 tokens ( 1.97 ms per token, 508.11 tokens per second) 1.22.049.512 I slot print_timing: id 0 | task 2281 | eval time = 679.48 ms / 25 tokens ( 28.31 ms per token, 35.32 tokens per second) 1.22.049.513 I slot print_timing: id 0 | task 2281 | total time = 1100.65 ms / 239 tokens 1.22.049.513 I slot print_timing: id 0 | task 2281 | graphs reused = 2043 1.22.049.514 I slot print_timing: id 0 | task 2281 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.049.538 I slot release: id 0 | task 2281 | stop processing: n_tokens = 238, truncated = 0 1.22.054.184 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 1.22.062.662 I slot launch_slot_: id 0 | task 2309 | processing task, is_child = 0 1.23.419.967 I slot print_timing: id 0 | task 2309 | prompt eval time = 330.05 ms / 164 tokens ( 2.01 ms per token, 496.89 tokens per second) 1.23.419.971 I slot print_timing: id 0 | task 2309 | eval time = 1027.24 ms / 37 tokens ( 28.53 ms per token, 35.05 tokens per second) 1.23.419.972 I slot print_timing: id 0 | task 2309 | total time = 1357.29 ms / 201 tokens 1.23.419.972 I slot print_timing: id 0 | task 2309 | graphs reused = 2078 1.23.419.973 I slot print_timing: id 0 | task 2309 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.419.995 I slot release: id 0 | task 2309 | stop processing: n_tokens = 200, truncated = 0 1.23.424.692 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 1.23.429.096 I slot launch_slot_: id 0 | task 2349 | processing task, is_child = 0 1.24.662.264 I slot print_timing: id 0 | task 2349 | prompt eval time = 357.01 ms / 166 tokens ( 2.15 ms per token, 464.97 tokens per second) 1.24.662.268 I slot print_timing: id 0 | task 2349 | eval time = 876.14 ms / 32 tokens ( 28.26 ms per token, 35.38 tokens per second) 1.24.662.269 I slot print_timing: id 0 | task 2349 | total time = 1233.15 ms / 198 tokens 1.24.662.269 I slot print_timing: id 0 | task 2349 | graphs reused = 2108 1.24.662.270 I slot print_timing: id 0 | task 2349 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.662.297 I slot release: id 0 | task 2349 | stop processing: n_tokens = 197, truncated = 0 1.24.667.852 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.108 (> 0.100 thold), f_keep = 0.152 1.24.674.709 I slot launch_slot_: id 0 | task 2384 | processing task, is_child = 0 1.26.807.405 I slot print_timing: id 0 | task 2384 | prompt eval time = 547.59 ms / 277 tokens ( 1.98 ms per token, 505.85 tokens per second) 1.26.807.413 I slot print_timing: id 0 | task 2384 | eval time = 1585.09 ms / 57 tokens ( 28.31 ms per token, 35.33 tokens per second) 1.26.807.413 I slot print_timing: id 0 | task 2384 | total time = 2132.68 ms / 334 tokens 1.26.807.414 I slot print_timing: id 0 | task 2384 | graphs reused = 2163 1.26.807.415 I slot print_timing: id 0 | task 2384 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.807.463 I slot release: id 0 | task 2384 | stop processing: n_tokens = 333, truncated = 0 1.26.812.428 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 1.26.822.989 I slot launch_slot_: id 0 | task 2444 | processing task, is_child = 0 1.28.926.287 I slot print_timing: id 0 | task 2444 | prompt eval time = 459.88 ms / 248 tokens ( 1.85 ms per token, 539.27 tokens per second) 1.28.926.291 I slot print_timing: id 0 | task 2444 | eval time = 1643.40 ms / 59 tokens ( 28.33 ms per token, 35.29 tokens per second) 1.28.926.292 I slot print_timing: id 0 | task 2444 | total time = 2103.28 ms / 307 tokens 1.28.926.292 I slot print_timing: id 0 | task 2444 | graphs reused = 2219 1.28.926.293 I slot print_timing: id 0 | task 2444 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.926.319 I slot release: id 0 | task 2444 | stop processing: n_tokens = 306, truncated = 0 1.28.930.831 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 1.28.940.648 I slot launch_slot_: id 0 | task 2506 | processing task, is_child = 0 1.30.117.520 I slot print_timing: id 0 | task 2506 | prompt eval time = 358.34 ms / 159 tokens ( 2.25 ms per token, 443.72 tokens per second) 1.30.117.526 I slot print_timing: id 0 | task 2506 | eval time = 818.53 ms / 30 tokens ( 28.23 ms per token, 35.43 tokens per second) 1.30.117.527 I slot print_timing: id 0 | task 2506 | total time = 1176.86 ms / 189 tokens 1.30.117.528 I slot print_timing: id 0 | task 2506 | graphs reused = 2247 1.30.117.528 I slot print_timing: id 0 | task 2506 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.117.552 I slot release: id 0 | task 2506 | stop processing: n_tokens = 188, truncated = 0 1.30.122.754 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 1.30.126.260 I slot launch_slot_: id 0 | task 2539 | processing task, is_child = 0 1.31.385.619 I slot print_timing: id 0 | task 2539 | prompt eval time = 410.91 ms / 196 tokens ( 2.10 ms per token, 476.99 tokens per second) 1.31.385.623 I slot print_timing: id 0 | task 2539 | eval time = 848.43 ms / 31 tokens ( 28.28 ms per token, 35.36 tokens per second) 1.31.385.625 I slot print_timing: id 0 | task 2539 | total time = 1259.35 ms / 227 tokens 1.31.385.626 I slot print_timing: id 0 | task 2539 | graphs reused = 2276 1.31.385.626 I slot print_timing: id 0 | task 2539 | graph reallocs = 0 / 0 (same size) / (changed size) 1.31.385.652 I slot release: id 0 | task 2539 | stop processing: n_tokens = 226, truncated = 0 1.31.390.230 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 1.31.397.450 I slot launch_slot_: id 0 | task 2573 | processing task, is_child = 0 1.32.434.340 I slot print_timing: id 0 | task 2573 | prompt eval time = 332.87 ms / 150 tokens ( 2.22 ms per token, 450.63 tokens per second) 1.32.434.344 I slot print_timing: id 0 | task 2573 | eval time = 704.01 ms / 26 tokens ( 28.16 ms per token, 35.51 tokens per second) 1.32.434.346 I slot print_timing: id 0 | task 2573 | total time = 1036.88 ms / 176 tokens 1.32.434.347 I slot print_timing: id 0 | task 2573 | graphs reused = 2300 1.32.434.348 I slot print_timing: id 0 | task 2573 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.434.373 I slot release: id 0 | task 2573 | stop processing: n_tokens = 175, truncated = 0 1.32.439.234 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 1.32.444.163 I slot launch_slot_: id 0 | task 2602 | processing task, is_child = 0 1.34.016.333 I slot print_timing: id 0 | task 2602 | prompt eval time = 414.51 ms / 215 tokens ( 1.93 ms per token, 518.68 tokens per second) 1.34.016.336 I slot print_timing: id 0 | task 2602 | eval time = 1157.64 ms / 42 tokens ( 28.24 ms per token, 35.42 tokens per second) 1.34.016.337 I slot print_timing: id 0 | task 2602 | total time = 1572.16 ms / 257 tokens 1.34.016.338 I slot print_timing: id 0 | task 2602 | graphs reused = 2340 1.34.016.338 I slot print_timing: id 0 | task 2602 | graph reallocs = 0 / 0 (same size) / (changed size) 1.34.016.368 I slot release: id 0 | task 2602 | stop processing: n_tokens = 256, truncated = 0 1.34.021.824 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 256, t_last = 318452005916 1.34.030.186 I slot launch_slot_: id 0 | task 2647 | processing task, is_child = 0 1.35.484.153 I slot print_timing: id 0 | task 2647 | prompt eval time = 602.99 ms / 327 tokens ( 1.84 ms per token, 542.30 tokens per second) 1.35.484.160 I slot print_timing: id 0 | task 2647 | eval time = 850.97 ms / 31 tokens ( 28.37 ms per token, 35.25 tokens per second) 1.35.484.161 I slot print_timing: id 0 | task 2647 | total time = 1453.95 ms / 358 tokens 1.35.484.162 I slot print_timing: id 0 | task 2647 | graphs reused = 2369 1.35.484.162 I slot print_timing: id 0 | task 2647 | graph reallocs = 0 / 0 (same size) / (changed size) 1.35.484.190 I slot release: id 0 | task 2647 | stop processing: n_tokens = 357, truncated = 0 1.35.490.052 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 357, t_last = 318453473738 1.35.502.329 I slot launch_slot_: id 0 | task 2681 | processing task, is_child = 0 1.37.088.596 I slot print_timing: id 0 | task 2681 | prompt eval time = 698.31 ms / 399 tokens ( 1.75 ms per token, 571.38 tokens per second) 1.37.088.604 I slot print_timing: id 0 | task 2681 | eval time = 887.95 ms / 32 tokens ( 28.64 ms per token, 34.91 tokens per second) 1.37.088.605 I slot print_timing: id 0 | task 2681 | total time = 1586.26 ms / 431 tokens 1.37.088.605 I slot print_timing: id 0 | task 2681 | graphs reused = 2399 1.37.088.606 I slot print_timing: id 0 | task 2681 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.088.635 I slot release: id 0 | task 2681 | stop processing: n_tokens = 430, truncated = 0 1.37.095.186 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 430, t_last = 318455078183 1.37.109.529 I slot launch_slot_: id 0 | task 2716 | processing task, is_child = 0 1.40.912.623 I slot print_timing: id 0 | task 2716 | n_gen = 106, tg = 34.85 t/s, tg_3s = 35.18 t/s 1.41.055.334 I slot print_timing: id 0 | task 2716 | prompt eval time = 790.01 ms / 439 tokens ( 1.80 ms per token, 555.69 tokens per second) 1.41.055.337 I slot print_timing: id 0 | task 2716 | eval time = 3155.78 ms / 111 tokens ( 28.69 ms per token, 34.86 tokens per second) 1.41.055.338 I slot print_timing: id 0 | task 2716 | total time = 3945.79 ms / 550 tokens 1.41.055.338 I slot print_timing: id 0 | task 2716 | graphs reused = 2507 1.41.055.339 I slot print_timing: id 0 | task 2716 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.055.377 I slot release: id 0 | task 2716 | stop processing: n_tokens = 549, truncated = 0 1.41.061.673 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 318459044925 1.41.077.982 I slot launch_slot_: id 0 | task 2830 | processing task, is_child = 0 1.42.748.484 I slot print_timing: id 0 | task 2830 | prompt eval time = 696.34 ms / 413 tokens ( 1.69 ms per token, 593.10 tokens per second) 1.42.748.489 I slot print_timing: id 0 | task 2830 | eval time = 974.14 ms / 35 tokens ( 28.65 ms per token, 34.90 tokens per second) 1.42.748.490 I slot print_timing: id 0 | task 2830 | total time = 1670.49 ms / 448 tokens 1.42.748.502 I slot print_timing: id 0 | task 2830 | graphs reused = 2540 1.42.748.503 I slot print_timing: id 0 | task 2830 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.748.536 I slot release: id 0 | task 2830 | stop processing: n_tokens = 447, truncated = 0 1.42.754.045 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 1.42.770.103 I slot launch_slot_: id 0 | task 2868 | processing task, is_child = 0 1.44.038.919 I slot print_timing: id 0 | task 2868 | prompt eval time = 504.04 ms / 268 tokens ( 1.88 ms per token, 531.70 tokens per second) 1.44.038.923 I slot print_timing: id 0 | task 2868 | eval time = 764.76 ms / 28 tokens ( 28.32 ms per token, 35.31 tokens per second) 1.44.038.924 I slot print_timing: id 0 | task 2868 | total time = 1268.80 ms / 296 tokens 1.44.038.925 I slot print_timing: id 0 | task 2868 | graphs reused = 2566 1.44.038.925 I slot print_timing: id 0 | task 2868 | graph reallocs = 0 / 0 (same size) / (changed size) 1.44.038.958 I slot release: id 0 | task 2868 | stop processing: n_tokens = 295, truncated = 0 1.44.044.705 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 295, t_last = 318462028506 1.44.048.500 I slot launch_slot_: id 0 | task 2899 | processing task, is_child = 0 1.46.580.539 I slot print_timing: id 0 | task 2899 | prompt eval time = 699.60 ms / 395 tokens ( 1.77 ms per token, 564.61 tokens per second) 1.46.580.542 I slot print_timing: id 0 | task 2899 | eval time = 1832.42 ms / 65 tokens ( 28.63 ms per token, 34.93 tokens per second) 1.46.580.543 I slot print_timing: id 0 | task 2899 | total time = 2532.03 ms / 460 tokens 1.46.580.544 I slot print_timing: id 0 | task 2899 | graphs reused = 2629 1.46.580.544 I slot print_timing: id 0 | task 2899 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.580.580 I slot release: id 0 | task 2899 | stop processing: n_tokens = 459, truncated = 0 1.46.585.975 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 459, t_last = 318464570128 1.46.600.736 I slot launch_slot_: id 0 | task 2967 | processing task, is_child = 0 1.48.074.562 I slot print_timing: id 0 | task 2967 | prompt eval time = 699.19 ms / 390 tokens ( 1.79 ms per token, 557.79 tokens per second) 1.48.074.565 I slot print_timing: id 0 | task 2967 | eval time = 774.62 ms / 28 tokens ( 28.69 ms per token, 34.86 tokens per second) 1.48.074.566 I slot print_timing: id 0 | task 2967 | total time = 1473.81 ms / 418 tokens 1.48.074.567 I slot print_timing: id 0 | task 2967 | graphs reused = 2655 1.48.074.567 I slot print_timing: id 0 | task 2967 | graph reallocs = 0 / 0 (same size) / (changed size) 1.48.074.601 I slot release: id 0 | task 2967 | stop processing: n_tokens = 417, truncated = 0 1.48.079.986 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 417, t_last = 318466064149 1.48.094.006 I slot launch_slot_: id 0 | task 2998 | processing task, is_child = 0 1.49.329.930 I slot print_timing: id 0 | task 2998 | prompt eval time = 554.55 ms / 304 tokens ( 1.82 ms per token, 548.20 tokens per second) 1.49.329.934 I slot print_timing: id 0 | task 2998 | eval time = 681.37 ms / 25 tokens ( 28.39 ms per token, 35.22 tokens per second) 1.49.329.934 I slot print_timing: id 0 | task 2998 | total time = 1235.91 ms / 329 tokens 1.49.329.935 I slot print_timing: id 0 | task 2998 | graphs reused = 2678 1.49.329.935 I slot print_timing: id 0 | task 2998 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.329.966 I slot release: id 0 | task 2998 | stop processing: n_tokens = 328, truncated = 0 1.49.335.278 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 1.49.342.601 I slot launch_slot_: id 0 | task 3026 | processing task, is_child = 0 1.50.805.212 I slot print_timing: id 0 | task 3026 | prompt eval time = 555.26 ms / 289 tokens ( 1.92 ms per token, 520.48 tokens per second) 1.50.805.219 I slot print_timing: id 0 | task 3026 | eval time = 907.34 ms / 33 tokens ( 28.35 ms per token, 35.27 tokens per second) 1.50.805.220 I slot print_timing: id 0 | task 3026 | total time = 1462.60 ms / 322 tokens 1.50.805.221 I slot print_timing: id 0 | task 3026 | graphs reused = 2709 1.50.805.221 I slot print_timing: id 0 | task 3026 | graph reallocs = 0 / 0 (same size) / (changed size) 1.50.805.250 I slot release: id 0 | task 3026 | stop processing: n_tokens = 321, truncated = 0 1.50.811.111 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 321, t_last = 318468794798 1.50.822.117 I slot launch_slot_: id 0 | task 3062 | processing task, is_child = 0 1.52.048.357 I slot print_timing: id 0 | task 3062 | prompt eval time = 625.46 ms / 360 tokens ( 1.74 ms per token, 575.58 tokens per second) 1.52.048.362 I slot print_timing: id 0 | task 3062 | eval time = 600.77 ms / 22 tokens ( 28.61 ms per token, 34.95 tokens per second) 1.52.048.363 I slot print_timing: id 0 | task 3062 | total time = 1226.23 ms / 382 tokens 1.52.048.363 I slot print_timing: id 0 | task 3062 | graphs reused = 2729 1.52.048.364 I slot print_timing: id 0 | task 3062 | graph reallocs = 0 / 0 (same size) / (changed size) 1.52.048.396 I slot release: id 0 | task 3062 | stop processing: n_tokens = 381, truncated = 0 1.52.054.086 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 381, t_last = 318470037944 1.52.067.139 I slot launch_slot_: id 0 | task 3087 | processing task, is_child = 0 1.53.831.400 I slot print_timing: id 0 | task 3087 | prompt eval time = 601.63 ms / 317 tokens ( 1.90 ms per token, 526.90 tokens per second) 1.53.831.405 I slot print_timing: id 0 | task 3087 | eval time = 1162.62 ms / 42 tokens ( 28.36 ms per token, 35.27 tokens per second) 1.53.831.405 I slot print_timing: id 0 | task 3087 | total time = 1764.25 ms / 359 tokens 1.53.831.406 I slot print_timing: id 0 | task 3087 | graphs reused = 2769 1.53.831.406 I slot print_timing: id 0 | task 3087 | graph reallocs = 0 / 0 (same size) / (changed size) 1.53.831.438 I slot release: id 0 | task 3087 | stop processing: n_tokens = 358, truncated = 0 1.53.836.558 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 1.53.845.213 I slot launch_slot_: id 0 | task 3132 | processing task, is_child = 0 1.54.835.577 I slot print_timing: id 0 | task 3132 | prompt eval time = 479.28 ms / 248 tokens ( 1.93 ms per token, 517.44 tokens per second) 1.54.835.581 I slot print_timing: id 0 | task 3132 | eval time = 511.07 ms / 19 tokens ( 28.39 ms per token, 35.22 tokens per second) 1.54.835.582 I slot print_timing: id 0 | task 3132 | total time = 990.35 ms / 267 tokens 1.54.835.583 I slot print_timing: id 0 | task 3132 | graphs reused = 2785 1.54.835.583 I slot print_timing: id 0 | task 3132 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.835.608 I slot release: id 0 | task 3132 | stop processing: n_tokens = 266, truncated = 0 1.54.841.249 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 266, t_last = 318472825156 1.54.850.633 I slot launch_slot_: id 0 | task 3154 | processing task, is_child = 0 1.56.566.400 I slot print_timing: id 0 | task 3154 | prompt eval time = 605.62 ms / 331 tokens ( 1.83 ms per token, 546.55 tokens per second) 1.56.566.405 I slot print_timing: id 0 | task 3154 | eval time = 1110.13 ms / 40 tokens ( 28.46 ms per token, 35.13 tokens per second) 1.56.566.405 I slot print_timing: id 0 | task 3154 | total time = 1715.76 ms / 371 tokens 1.56.566.406 I slot print_timing: id 0 | task 3154 | graphs reused = 2823 1.56.566.407 I slot print_timing: id 0 | task 3154 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.566.436 I slot release: id 0 | task 3154 | stop processing: n_tokens = 370, truncated = 0 1.56.571.911 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 1.56.584.642 I slot launch_slot_: id 0 | task 3197 | processing task, is_child = 0 1.57.794.357 I slot print_timing: id 0 | task 3197 | prompt eval time = 528.81 ms / 280 tokens ( 1.89 ms per token, 529.49 tokens per second) 1.57.794.364 I slot print_timing: id 0 | task 3197 | eval time = 680.90 ms / 25 tokens ( 28.37 ms per token, 35.25 tokens per second) 1.57.794.366 I slot print_timing: id 0 | task 3197 | total time = 1209.70 ms / 305 tokens 1.57.794.366 I slot print_timing: id 0 | task 3197 | graphs reused = 2846 1.57.794.367 I slot print_timing: id 0 | task 3197 | graph reallocs = 0 / 0 (same size) / (changed size) 1.57.794.394 I slot release: id 0 | task 3197 | stop processing: n_tokens = 304, truncated = 0 1.57.799.456 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 1.57.808.073 I slot launch_slot_: id 0 | task 3225 | processing task, is_child = 0 1.58.938.128 I slot print_timing: id 0 | task 3225 | prompt eval time = 504.67 ms / 252 tokens ( 2.00 ms per token, 499.33 tokens per second) 1.58.938.131 I slot print_timing: id 0 | task 3225 | eval time = 625.37 ms / 23 tokens ( 28.43 ms per token, 35.18 tokens per second) 1.58.938.132 I slot print_timing: id 0 | task 3225 | total time = 1130.04 ms / 275 tokens 1.58.938.133 I slot print_timing: id 0 | task 3225 | graphs reused = 2866 1.58.938.133 I slot print_timing: id 0 | task 3225 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.938.163 I slot release: id 0 | task 3225 | stop processing: n_tokens = 274, truncated = 0 1.58.943.433 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 1.58.952.419 I slot launch_slot_: id 0 | task 3251 | processing task, is_child = 0 2.00.031.764 I slot print_timing: id 0 | task 3251 | prompt eval time = 482.60 ms / 267 tokens ( 1.81 ms per token, 553.25 tokens per second) 2.00.031.767 I slot print_timing: id 0 | task 3251 | eval time = 596.73 ms / 22 tokens ( 28.42 ms per token, 35.19 tokens per second) 2.00.031.768 I slot print_timing: id 0 | task 3251 | total time = 1079.33 ms / 289 tokens 2.00.031.769 I slot print_timing: id 0 | task 3251 | graphs reused = 2886 2.00.031.769 I slot print_timing: id 0 | task 3251 | graph reallocs = 0 / 0 (same size) / (changed size) 2.00.031.800 I slot release: id 0 | task 3251 | stop processing: n_tokens = 288, truncated = 0 2.00.036.753 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 2.00.046.453 I slot launch_slot_: id 0 | task 3276 | processing task, is_child = 0 2.01.145.057 I slot print_timing: id 0 | task 3276 | prompt eval time = 501.75 ms / 255 tokens ( 1.97 ms per token, 508.22 tokens per second) 2.01.145.063 I slot print_timing: id 0 | task 3276 | eval time = 596.84 ms / 22 tokens ( 28.42 ms per token, 35.19 tokens per second) 2.01.145.064 I slot print_timing: id 0 | task 3276 | total time = 1098.59 ms / 277 tokens 2.01.145.065 I slot print_timing: id 0 | task 3276 | graphs reused = 2905 2.01.145.065 I slot print_timing: id 0 | task 3276 | graph reallocs = 0 / 0 (same size) / (changed size) 2.01.145.098 I slot release: id 0 | task 3276 | stop processing: n_tokens = 276, truncated = 0 2.01.151.211 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 276, t_last = 318479134646 2.01.160.417 I slot launch_slot_: id 0 | task 3301 | processing task, is_child = 0 2.02.701.732 I slot print_timing: id 0 | task 3301 | prompt eval time = 711.17 ms / 397 tokens ( 1.79 ms per token, 558.24 tokens per second) 2.02.701.736 I slot print_timing: id 0 | task 3301 | eval time = 830.13 ms / 30 tokens ( 28.63 ms per token, 34.93 tokens per second) 2.02.701.737 I slot print_timing: id 0 | task 3301 | total time = 1541.30 ms / 427 tokens 2.02.701.738 I slot print_timing: id 0 | task 3301 | graphs reused = 2933 2.02.701.738 I slot print_timing: id 0 | task 3301 | graph reallocs = 0 / 0 (same size) / (changed size) 2.02.701.779 I slot release: id 0 | task 3301 | stop processing: n_tokens = 426, truncated = 0 2.02.707.543 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 2.02.722.641 I slot launch_slot_: id 0 | task 3334 | processing task, is_child = 0 2.05.612.912 I slot print_timing: id 0 | task 3334 | prompt eval time = 564.82 ms / 290 tokens ( 1.95 ms per token, 513.44 tokens per second) 2.05.612.916 I slot print_timing: id 0 | task 3334 | eval time = 2325.44 ms / 83 tokens ( 28.36 ms per token, 35.26 tokens per second) 2.05.612.917 I slot print_timing: id 0 | task 3334 | total time = 2890.26 ms / 373 tokens 2.05.612.918 I slot print_timing: id 0 | task 3334 | graphs reused = 3014 2.05.612.918 I slot print_timing: id 0 | task 3334 | graph reallocs = 0 / 0 (same size) / (changed size) 2.05.612.947 I slot release: id 0 | task 3334 | stop processing: n_tokens = 372, truncated = 0 2.05.620.286 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 372, t_last = 318483602495 2.05.628.715 I slot launch_slot_: id 0 | task 3420 | processing task, is_child = 0 2.07.804.867 I slot print_timing: id 0 | task 3420 | prompt eval time = 1085.87 ms / 612 tokens ( 1.77 ms per token, 563.60 tokens per second) 2.07.804.871 I slot print_timing: id 0 | task 3420 | eval time = 1090.26 ms / 39 tokens ( 28.69 ms per token, 34.85 tokens per second) 2.07.804.872 I slot print_timing: id 0 | task 3420 | total time = 2176.13 ms / 651 tokens 2.07.804.873 I slot print_timing: id 0 | task 3420 | graphs reused = 3051 2.07.804.873 I slot print_timing: id 0 | task 3420 | graph reallocs = 0 / 0 (same size) / (changed size) 2.07.804.917 I slot release: id 0 | task 3420 | stop processing: n_tokens = 650, truncated = 0 2.07.810.315 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 2.07.829.374 I slot launch_slot_: id 0 | task 3463 | processing task, is_child = 0 2.08.903.123 I slot print_timing: id 0 | task 3463 | prompt eval time = 505.14 ms / 275 tokens ( 1.84 ms per token, 544.41 tokens per second) 2.08.903.126 I slot print_timing: id 0 | task 3463 | eval time = 568.60 ms / 21 tokens ( 28.43 ms per token, 35.17 tokens per second) 2.08.903.127 I slot print_timing: id 0 | task 3463 | total time = 1073.73 ms / 296 tokens 2.08.903.128 I slot print_timing: id 0 | task 3463 | graphs reused = 3070 2.08.903.129 I slot print_timing: id 0 | task 3463 | graph reallocs = 0 / 0 (same size) / (changed size) 2.08.903.159 I slot release: id 0 | task 3463 | stop processing: n_tokens = 295, truncated = 0 2.08.909.658 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 295, t_last = 318486892707 2.08.915.587 I slot launch_slot_: id 0 | task 3487 | processing task, is_child = 0 2.10.406.965 I slot print_timing: id 0 | task 3487 | prompt eval time = 802.15 ms / 456 tokens ( 1.76 ms per token, 568.47 tokens per second) 2.10.406.969 I slot print_timing: id 0 | task 3487 | eval time = 689.22 ms / 25 tokens ( 28.72 ms per token, 34.82 tokens per second) 2.10.406.970 I slot print_timing: id 0 | task 3487 | total time = 1491.37 ms / 481 tokens 2.10.406.971 I slot print_timing: id 0 | task 3487 | graphs reused = 3093 2.10.406.971 I slot print_timing: id 0 | task 3487 | graph reallocs = 0 / 0 (same size) / (changed size) 2.10.407.014 I slot release: id 0 | task 3487 | stop processing: n_tokens = 480, truncated = 0 2.10.413.947 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 480, t_last = 318488396562 2.10.431.196 I slot launch_slot_: id 0 | task 3515 | processing task, is_child = 0 2.12.494.039 I slot print_timing: id 0 | task 3515 | prompt eval time = 970.65 ms / 542 tokens ( 1.79 ms per token, 558.39 tokens per second) 2.12.494.049 I slot print_timing: id 0 | task 3515 | eval time = 1092.16 ms / 39 tokens ( 28.74 ms per token, 34.79 tokens per second) 2.12.494.050 I slot print_timing: id 0 | task 3515 | total time = 2062.81 ms / 581 tokens 2.12.494.051 I slot print_timing: id 0 | task 3515 | graphs reused = 3130 2.12.494.051 I slot print_timing: id 0 | task 3515 | graph reallocs = 0 / 0 (same size) / (changed size) 2.12.494.103 I slot release: id 0 | task 3515 | stop processing: n_tokens = 580, truncated = 0 2.12.500.162 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 580, t_last = 318490483651 2.12.519.045 I slot launch_slot_: id 0 | task 3558 | processing task, is_child = 0 2.14.444.199 I slot print_timing: id 0 | task 3558 | prompt eval time = 693.46 ms / 361 tokens ( 1.92 ms per token, 520.58 tokens per second) 2.14.444.203 I slot print_timing: id 0 | task 3558 | eval time = 1231.68 ms / 44 tokens ( 28.64 ms per token, 34.91 tokens per second) 2.14.444.203 I slot print_timing: id 0 | task 3558 | total time = 1925.13 ms / 405 tokens 2.14.444.204 I slot print_timing: id 0 | task 3558 | graphs reused = 3172 2.14.444.205 I slot print_timing: id 0 | task 3558 | graph reallocs = 0 / 0 (same size) / (changed size) 2.14.444.237 I slot release: id 0 | task 3558 | stop processing: n_tokens = 429, truncated = 0 2.14.449.501 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 2.14.459.693 I slot launch_slot_: id 0 | task 3605 | processing task, is_child = 0 2.16.043.689 I slot print_timing: id 0 | task 3605 | prompt eval time = 505.43 ms / 258 tokens ( 1.96 ms per token, 510.46 tokens per second) 2.16.043.694 I slot print_timing: id 0 | task 3605 | eval time = 1078.56 ms / 39 tokens ( 28.38 ms per token, 35.23 tokens per second) 2.16.043.695 I slot print_timing: id 0 | task 3605 | total time = 1583.98 ms / 297 tokens 2.16.043.695 I slot print_timing: id 0 | task 3605 | graphs reused = 3209 2.16.043.696 I slot print_timing: id 0 | task 3605 | graph reallocs = 0 / 0 (same size) / (changed size) 2.16.043.728 I slot release: id 0 | task 3605 | stop processing: n_tokens = 320, truncated = 0 2.16.050.123 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 320, t_last = 318494033277 2.16.054.613 I slot launch_slot_: id 0 | task 3647 | processing task, is_child = 0 2.17.358.780 I slot print_timing: id 0 | task 3647 | prompt eval time = 701.24 ms / 379 tokens ( 1.85 ms per token, 540.47 tokens per second) 2.17.358.787 I slot print_timing: id 0 | task 3647 | eval time = 602.91 ms / 22 tokens ( 28.71 ms per token, 34.83 tokens per second) 2.17.358.787 I slot print_timing: id 0 | task 3647 | total time = 1304.15 ms / 401 tokens 2.17.358.788 I slot print_timing: id 0 | task 3647 | graphs reused = 3229 2.17.358.789 I slot print_timing: id 0 | task 3647 | graph reallocs = 0 / 0 (same size) / (changed size) 2.17.358.821 I slot release: id 0 | task 3647 | stop processing: n_tokens = 423, truncated = 0 2.17.365.671 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 423, t_last = 318495348369 2.17.380.470 I slot launch_slot_: id 0 | task 3672 | processing task, is_child = 0 2.19.334.593 I slot print_timing: id 0 | task 3672 | prompt eval time = 977.29 ms / 540 tokens ( 1.81 ms per token, 552.55 tokens per second) 2.19.334.597 I slot print_timing: id 0 | task 3672 | eval time = 976.82 ms / 35 tokens ( 28.73 ms per token, 34.81 tokens per second) 2.19.334.597 I slot print_timing: id 0 | task 3672 | total time = 1954.10 ms / 575 tokens 2.19.334.598 I slot print_timing: id 0 | task 3672 | graphs reused = 3262 2.19.334.599 I slot print_timing: id 0 | task 3672 | graph reallocs = 0 / 0 (same size) / (changed size) 2.19.334.642 I slot release: id 0 | task 3672 | stop processing: n_tokens = 596, truncated = 0 2.19.340.874 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 596, t_last = 318497324190 2.19.361.054 I slot launch_slot_: id 0 | task 3711 | processing task, is_child = 0 2.20.831.852 I slot print_timing: id 0 | task 3711 | prompt eval time = 667.60 ms / 370 tokens ( 1.80 ms per token, 554.22 tokens per second) 2.20.831.856 I slot print_timing: id 0 | task 3711 | eval time = 803.18 ms / 29 tokens ( 28.69 ms per token, 34.86 tokens per second) 2.20.831.856 I slot print_timing: id 0 | task 3711 | total time = 1470.79 ms / 399 tokens 2.20.831.857 I slot print_timing: id 0 | task 3711 | graphs reused = 3289 2.20.831.862 I slot print_timing: id 0 | task 3711 | graph reallocs = 0 / 0 (same size) / (changed size) 2.20.831.894 I slot release: id 0 | task 3711 | stop processing: n_tokens = 422, truncated = 0 2.20.837.834 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 422, t_last = 318498821442 2.20.842.736 I slot launch_slot_: id 0 | task 3743 | processing task, is_child = 0 2.22.147.962 I slot print_timing: id 0 | task 3743 | prompt eval time = 619.22 ms / 336 tokens ( 1.84 ms per token, 542.62 tokens per second) 2.22.147.970 I slot print_timing: id 0 | task 3743 | eval time = 685.99 ms / 25 tokens ( 28.58 ms per token, 34.99 tokens per second) 2.22.147.971 I slot print_timing: id 0 | task 3743 | total time = 1305.21 ms / 361 tokens 2.22.147.972 I slot print_timing: id 0 | task 3743 | graphs reused = 3312 2.22.147.972 I slot print_timing: id 0 | task 3743 | graph reallocs = 0 / 0 (same size) / (changed size) 2.22.148.003 I slot release: id 0 | task 3743 | stop processing: n_tokens = 383, truncated = 0 2.22.153.216 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 2.22.162.163 I slot launch_slot_: id 0 | task 3771 | processing task, is_child = 0 2.23.303.788 I slot print_timing: id 0 | task 3771 | prompt eval time = 489.61 ms / 261 tokens ( 1.88 ms per token, 533.08 tokens per second) 2.23.303.792 I slot print_timing: id 0 | task 3771 | eval time = 652.00 ms / 24 tokens ( 28.35 ms per token, 35.28 tokens per second) 2.23.303.793 I slot print_timing: id 0 | task 3771 | total time = 1141.61 ms / 285 tokens 2.23.303.794 I slot print_timing: id 0 | task 3771 | graphs reused = 3334 2.23.303.795 I slot print_timing: id 0 | task 3771 | graph reallocs = 0 / 0 (same size) / (changed size) 2.23.303.827 I slot release: id 0 | task 3771 | stop processing: n_tokens = 284, truncated = 0 2.23.309.091 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 2.23.312.765 I slot launch_slot_: id 0 | task 3798 | processing task, is_child = 0 2.25.016.012 I slot print_timing: id 0 | task 3798 | prompt eval time = 596.02 ms / 299 tokens ( 1.99 ms per token, 501.66 tokens per second) 2.25.016.019 I slot print_timing: id 0 | task 3798 | eval time = 1107.21 ms / 40 tokens ( 28.39 ms per token, 35.22 tokens per second) 2.25.016.020 I slot print_timing: id 0 | task 3798 | total time = 1703.24 ms / 339 tokens 2.25.016.021 I slot print_timing: id 0 | task 3798 | graphs reused = 3372 2.25.016.021 I slot print_timing: id 0 | task 3798 | graph reallocs = 0 / 0 (same size) / (changed size) 2.25.016.052 I slot release: id 0 | task 3798 | stop processing: n_tokens = 338, truncated = 0 2.25.021.686 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 338, t_last = 318503005600 2.25.031.472 I slot launch_slot_: id 0 | task 3841 | processing task, is_child = 0 2.26.354.249 I slot print_timing: id 0 | task 3841 | prompt eval time = 612.13 ms / 319 tokens ( 1.92 ms per token, 521.13 tokens per second) 2.26.354.253 I slot print_timing: id 0 | task 3841 | eval time = 710.63 ms / 26 tokens ( 28.43 ms per token, 35.18 tokens per second) 2.26.354.254 I slot print_timing: id 0 | task 3841 | total time = 1322.76 ms / 345 tokens 2.26.354.254 I slot print_timing: id 0 | task 3841 | graphs reused = 3396 2.26.354.255 I slot print_timing: id 0 | task 3841 | graph reallocs = 0 / 0 (same size) / (changed size) 2.26.354.296 I slot release: id 0 | task 3841 | stop processing: n_tokens = 344, truncated = 0 2.26.360.645 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 344, t_last = 318504343844 2.26.375.309 I slot launch_slot_: id 0 | task 3870 | processing task, is_child = 0 2.28.106.629 I slot print_timing: id 0 | task 3870 | prompt eval time = 727.57 ms / 423 tokens ( 1.72 ms per token, 581.39 tokens per second) 2.28.106.635 I slot print_timing: id 0 | task 3870 | eval time = 1003.74 ms / 36 tokens ( 28.68 ms per token, 34.87 tokens per second) 2.28.106.636 I slot print_timing: id 0 | task 3870 | total time = 1731.31 ms / 459 tokens 2.28.106.636 I slot print_timing: id 0 | task 3870 | graphs reused = 3430 2.28.106.637 I slot print_timing: id 0 | task 3870 | graph reallocs = 0 / 0 (same size) / (changed size) 2.28.106.673 I slot release: id 0 | task 3870 | stop processing: n_tokens = 458, truncated = 0 2.28.112.500 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 318506096221 2.28.132.528 I slot launch_slot_: id 0 | task 3909 | processing task, is_child = 0 2.29.587.548 I slot print_timing: id 0 | task 3909 | prompt eval time = 653.20 ms / 366 tokens ( 1.78 ms per token, 560.32 tokens per second) 2.29.587.552 I slot print_timing: id 0 | task 3909 | eval time = 801.80 ms / 29 tokens ( 28.64 ms per token, 34.92 tokens per second) 2.29.587.553 I slot print_timing: id 0 | task 3909 | total time = 1455.00 ms / 395 tokens 2.29.587.553 I slot print_timing: id 0 | task 3909 | graphs reused = 3457 2.29.587.554 I slot print_timing: id 0 | task 3909 | graph reallocs = 0 / 0 (same size) / (changed size) 2.29.587.588 I slot release: id 0 | task 3909 | stop processing: n_tokens = 394, truncated = 0 2.29.594.800 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 394, t_last = 318507577136 2.29.611.780 I slot launch_slot_: id 0 | task 3941 | processing task, is_child = 0 2.31.416.233 I slot print_timing: id 0 | task 3941 | prompt eval time = 1000.57 ms / 560 tokens ( 1.79 ms per token, 559.68 tokens per second) 2.31.416.237 I slot print_timing: id 0 | task 3941 | eval time = 803.87 ms / 29 tokens ( 28.71 ms per token, 34.83 tokens per second) 2.31.416.238 I slot print_timing: id 0 | task 3941 | total time = 1804.44 ms / 589 tokens 2.31.416.239 I slot print_timing: id 0 | task 3941 | graphs reused = 3484 2.31.416.239 I slot print_timing: id 0 | task 3941 | graph reallocs = 0 / 0 (same size) / (changed size) 2.31.416.285 I slot release: id 0 | task 3941 | stop processing: n_tokens = 588, truncated = 0 2.31.422.269 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 588, t_last = 318509405834 2.31.422.343 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 60.760 MiB) 2.31.422.351 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 44.657 MiB) 2.31.447.035 I slot launch_slot_: id 0 | task 3974 | processing task, is_child = 0 2.32.728.046 I slot print_timing: id 0 | task 3974 | prompt eval time = 650.78 ms / 366 tokens ( 1.78 ms per token, 562.40 tokens per second) 2.32.728.050 I slot print_timing: id 0 | task 3974 | eval time = 630.21 ms / 23 tokens ( 28.65 ms per token, 34.91 tokens per second) 2.32.728.051 I slot print_timing: id 0 | task 3974 | total time = 1281.00 ms / 389 tokens 2.32.728.051 I slot print_timing: id 0 | task 3974 | graphs reused = 3505 2.32.728.052 I slot print_timing: id 0 | task 3974 | graph reallocs = 0 / 0 (same size) / (changed size) 2.32.728.091 I slot release: id 0 | task 3974 | stop processing: n_tokens = 388, truncated = 0 2.32.734.365 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 388, t_last = 318510717639 2.32.734.427 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 59.776 MiB) 2.32.734.435 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 71.238 MiB) 2.32.746.056 I slot launch_slot_: id 0 | task 4000 | processing task, is_child = 0 2.34.592.829 I slot print_timing: id 0 | task 4000 | prompt eval time = 700.89 ms / 406 tokens ( 1.73 ms per token, 579.26 tokens per second) 2.34.592.832 I slot print_timing: id 0 | task 4000 | eval time = 1145.86 ms / 41 tokens ( 28.65 ms per token, 34.91 tokens per second) 2.34.592.833 I slot print_timing: id 0 | task 4000 | total time = 1846.76 ms / 447 tokens 2.34.592.834 I slot print_timing: id 0 | task 4000 | graphs reused = 3544 2.34.592.834 I slot print_timing: id 0 | task 4000 | graph reallocs = 0 / 0 (same size) / (changed size) 2.34.592.867 I slot release: id 0 | task 4000 | stop processing: n_tokens = 446, truncated = 0 2.34.598.865 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 446, t_last = 318512582415 2.34.598.930 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 64.874 MiB) 2.34.598.936 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 62.132 MiB) 2.34.617.956 I slot launch_slot_: id 0 | task 4044 | processing task, is_child = 0 2.36.433.212 I slot print_timing: id 0 | task 4044 | prompt eval time = 698.54 ms / 379 tokens ( 1.84 ms per token, 542.56 tokens per second) 2.36.433.220 I slot print_timing: id 0 | task 4044 | eval time = 1116.71 ms / 40 tokens ( 28.63 ms per token, 34.92 tokens per second) 2.36.433.221 I slot print_timing: id 0 | task 4044 | total time = 1815.25 ms / 419 tokens 2.36.433.221 I slot print_timing: id 0 | task 4044 | graphs reused = 3582 2.36.433.222 I slot print_timing: id 0 | task 4044 | graph reallocs = 0 / 0 (same size) / (changed size) 2.36.433.255 I slot release: id 0 | task 4044 | stop processing: n_tokens = 418, truncated = 0 2.36.439.712 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 418, t_last = 318514422803 2.36.439.781 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.989 MiB) 2.36.439.785 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 95.710 MiB) 2.36.455.047 I slot launch_slot_: id 0 | task 4087 | processing task, is_child = 0 2.38.134.623 I slot print_timing: id 0 | task 4087 | prompt eval time = 867.75 ms / 487 tokens ( 1.78 ms per token, 561.22 tokens per second) 2.38.134.629 I slot print_timing: id 0 | task 4087 | eval time = 811.82 ms / 29 tokens ( 28.99 ms per token, 34.49 tokens per second) 2.38.134.630 I slot print_timing: id 0 | task 4087 | total time = 1679.56 ms / 516 tokens 2.38.134.630 I slot print_timing: id 0 | task 4087 | graphs reused = 3608 2.38.134.631 I slot print_timing: id 0 | task 4087 | graph reallocs = 0 / 0 (same size) / (changed size) 2.38.134.668 I slot release: id 0 | task 4087 | stop processing: n_tokens = 515, truncated = 0 2.38.185.004 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 515, t_last = 318516124216 2.38.185.088 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 53.271 MiB) 2.38.185.094 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 57.701 MiB) 2.38.185.096 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 93.918 MiB) 2.38.209.843 I slot launch_slot_: id 0 | task 4119 | processing task, is_child = 0 2.40.951.247 I slot print_timing: id 0 | task 4119 | prompt eval time = 1021.67 ms / 565 tokens ( 1.81 ms per token, 553.02 tokens per second) 2.40.951.251 I slot print_timing: id 0 | task 4119 | eval time = 1719.72 ms / 61 tokens ( 28.66 ms per token, 34.89 tokens per second) 2.40.951.252 I slot print_timing: id 0 | task 4119 | total time = 2741.39 ms / 626 tokens 2.40.951.253 I slot print_timing: id 0 | task 4119 | graphs reused = 3667 2.40.951.253 I slot print_timing: id 0 | task 4119 | graph reallocs = 0 / 0 (same size) / (changed size) 2.40.951.296 I slot release: id 0 | task 4119 | stop processing: n_tokens = 625, truncated = 0 2.40.956.203 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 2.40.956.283 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 97.293 MiB) 2.40.956.287 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 64.909 MiB) 2.40.978.858 I slot launch_slot_: id 0 | task 4184 | processing task, is_child = 0 2.43.015.843 I slot print_timing: id 0 | task 4184 | prompt eval time = 400.44 ms / 196 tokens ( 2.04 ms per token, 489.46 tokens per second) 2.43.015.847 I slot print_timing: id 0 | task 4184 | eval time = 1636.53 ms / 59 tokens ( 28.22 ms per token, 35.44 tokens per second) 2.43.015.848 I slot print_timing: id 0 | task 4184 | total time = 2036.97 ms / 255 tokens 2.43.015.848 I slot print_timing: id 0 | task 4184 | graphs reused = 3724 2.43.015.849 I slot print_timing: id 0 | task 4184 | graph reallocs = 0 / 0 (same size) / (changed size) 2.43.015.872 I slot release: id 0 | task 4184 | stop processing: n_tokens = 254, truncated = 0 2.43.020.667 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 2.43.020.715 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.261 MiB) 2.43.023.324 I slot launch_slot_: id 0 | task 4246 | processing task, is_child = 0 2.45.174.107 I slot print_timing: id 0 | task 4246 | prompt eval time = 453.90 ms / 214 tokens ( 2.12 ms per token, 471.47 tokens per second) 2.45.174.114 I slot print_timing: id 0 | task 4246 | eval time = 1696.87 ms / 61 tokens ( 28.28 ms per token, 35.36 tokens per second) 2.45.174.115 I slot print_timing: id 0 | task 4246 | total time = 2150.77 ms / 275 tokens 2.45.174.115 I slot print_timing: id 0 | task 4246 | graphs reused = 3782 2.45.174.116 I slot print_timing: id 0 | task 4246 | graph reallocs = 0 / 0 (same size) / (changed size) 2.45.174.141 I slot release: id 0 | task 4246 | stop processing: n_tokens = 274, truncated = 0 2.45.178.958 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 2.45.179.004 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 61.921 MiB) 2.45.181.816 I slot launch_slot_: id 0 | task 4310 | processing task, is_child = 0 2.48.018.936 I slot print_timing: id 0 | task 4310 | prompt eval time = 452.21 ms / 201 tokens ( 2.25 ms per token, 444.48 tokens per second) 2.48.018.942 I slot print_timing: id 0 | task 4310 | eval time = 2384.90 ms / 85 tokens ( 28.39 ms per token, 35.22 tokens per second) 2.48.018.943 I slot print_timing: id 0 | task 4310 | total time = 2837.11 ms / 286 tokens 2.48.018.943 I slot print_timing: id 0 | task 4310 | graphs reused = 3864 2.48.018.944 I slot print_timing: id 0 | task 4310 | graph reallocs = 0 / 0 (same size) / (changed size) 2.48.018.977 I slot release: id 0 | task 4310 | stop processing: n_tokens = 285, truncated = 0 2.48.023.749 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 2.48.023.803 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 53.728 MiB) 2.48.026.735 I slot launch_slot_: id 0 | task 4398 | processing task, is_child = 0 2.50.370.197 I slot print_timing: id 0 | task 4398 | prompt eval time = 397.41 ms / 168 tokens ( 2.37 ms per token, 422.74 tokens per second) 2.50.370.201 I slot print_timing: id 0 | task 4398 | eval time = 1946.05 ms / 70 tokens ( 28.20 ms per token, 35.46 tokens per second) 2.50.370.202 I slot print_timing: id 0 | task 4398 | total time = 2343.45 ms / 238 tokens 2.50.370.203 I slot print_timing: id 0 | task 4398 | graphs reused = 3932 2.50.370.203 I slot print_timing: id 0 | task 4398 | graph reallocs = 0 / 0 (same size) / (changed size) 2.50.370.225 I slot release: id 0 | task 4398 | stop processing: n_tokens = 237, truncated = 0 2.50.375.456 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 2.50.375.500 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 60.760 MiB) 2.50.377.891 I slot launch_slot_: id 0 | task 4471 | processing task, is_child = 0 2.53.582.291 I slot print_timing: id 0 | task 4471 | prompt eval time = 458.14 ms / 232 tokens ( 1.97 ms per token, 506.40 tokens per second) 2.53.582.298 I slot print_timing: id 0 | task 4471 | eval time = 2746.25 ms / 98 tokens ( 28.31 ms per token, 35.32 tokens per second) 2.53.582.299 I slot print_timing: id 0 | task 4471 | total time = 3204.39 ms / 330 tokens 2.53.582.300 I slot print_timing: id 0 | task 4471 | graphs reused = 4027 2.53.582.301 I slot print_timing: id 0 | task 4471 | graph reallocs = 0 / 0 (same size) / (changed size) 2.53.582.332 I slot release: id 0 | task 4471 | stop processing: n_tokens = 329, truncated = 0 2.53.587.343 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 2.53.587.396 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 54.677 MiB) 2.53.587.402 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 53.306 MiB) 2.53.590.702 I slot launch_slot_: id 0 | task 4572 | processing task, is_child = 0 2.57.092.485 I slot print_timing: id 0 | task 4572 | n_gen = 107, tg = 35.31 t/s, tg_3s = 35.64 t/s 2.57.576.712 I slot print_timing: id 0 | task 4572 | prompt eval time = 499.60 ms / 249 tokens ( 2.01 ms per token, 498.40 tokens per second) 2.57.576.716 I slot print_timing: id 0 | task 4572 | eval time = 3486.40 ms / 124 tokens ( 28.34 ms per token, 35.28 tokens per second) 2.57.576.717 I slot print_timing: id 0 | task 4572 | total time = 3986.00 ms / 373 tokens 2.57.576.718 I slot print_timing: id 0 | task 4572 | graphs reused = 4148 2.57.576.718 I slot print_timing: id 0 | task 4572 | graph reallocs = 0 / 0 (same size) / (changed size) 2.57.576.745 I slot release: id 0 | task 4572 | stop processing: n_tokens = 372, truncated = 0 2.57.582.086 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 2.57.582.140 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 66.562 MiB) 2.57.582.149 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 58.299 MiB) 2.57.585.680 I slot launch_slot_: id 0 | task 4699 | processing task, is_child = 0 3.01.170.311 I slot print_timing: id 0 | task 4699 | n_gen = 107, tg = 35.09 t/s, tg_3s = 35.42 t/s 3.02.142.461 I slot print_timing: id 0 | task 4699 | prompt eval time = 564.00 ms / 320 tokens ( 1.76 ms per token, 567.38 tokens per second) 3.02.142.465 I slot print_timing: id 0 | task 4699 | eval time = 3992.77 ms / 141 tokens ( 28.52 ms per token, 35.06 tokens per second) 3.02.142.466 I slot print_timing: id 0 | task 4699 | total time = 4556.77 ms / 461 tokens 3.02.142.466 I slot print_timing: id 0 | task 4699 | graphs reused = 4287 3.02.142.467 I slot print_timing: id 0 | task 4699 | graph reallocs = 0 / 0 (same size) / (changed size) 3.02.142.494 I slot release: id 0 | task 4699 | stop processing: n_tokens = 460, truncated = 0 3.02.147.281 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 3.02.147.354 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 74.227 MiB) 3.02.161.255 I slot launch_slot_: id 0 | task 4843 | processing task, is_child = 0 3.05.558.008 I slot print_timing: id 0 | task 4843 | n_gen = 108, tg = 35.39 t/s, tg_3s = 35.72 t/s 3.08.574.552 I slot print_timing: id 0 | task 4843 | n_gen = 214, tg = 35.27 t/s, tg_3s = 35.14 t/s 3.11.575.872 I slot print_timing: id 0 | task 4843 | n_gen = 319, tg = 35.17 t/s, tg_3s = 34.98 t/s 3.12.750.908 I slot print_timing: id 0 | task 4843 | prompt eval time = 373.41 ms / 180 tokens ( 2.07 ms per token, 482.05 tokens per second) 3.12.750.914 I slot print_timing: id 0 | task 4843 | eval time = 10216.23 ms / 360 tokens ( 28.46 ms per token, 35.14 tokens per second) 3.12.750.915 I slot print_timing: id 0 | task 4843 | total time = 10589.64 ms / 540 tokens 3.12.750.916 I slot print_timing: id 0 | task 4843 | graphs reused = 4643 3.12.750.916 I slot print_timing: id 0 | task 4843 | graph reallocs = 0 / 0 (same size) / (changed size) 3.12.750.938 I slot release: id 0 | task 4843 | stop processing: n_tokens = 539, truncated = 0 3.12.755.914 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 3.12.755.984 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 84.670 MiB) 3.12.755.992 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 71.414 MiB) 3.12.766.698 I slot launch_slot_: id 0 | task 5206 | processing task, is_child = 0 3.16.186.625 I slot print_timing: id 0 | task 5206 | n_gen = 108, tg = 35.41 t/s, tg_3s = 35.74 t/s 3.19.196.553 I slot print_timing: id 0 | task 5206 | n_gen = 214, tg = 35.31 t/s, tg_3s = 35.22 t/s 3.22.199.465 I slot print_timing: id 0 | task 5206 | n_gen = 319, tg = 35.20 t/s, tg_3s = 34.97 t/s 3.22.687.386 I slot print_timing: id 0 | task 5206 | prompt eval time = 398.30 ms / 184 tokens ( 2.16 ms per token, 461.96 tokens per second) 3.22.687.389 I slot print_timing: id 0 | task 5206 | eval time = 9522.38 ms / 336 tokens ( 28.43 ms per token, 35.18 tokens per second) 3.22.687.390 I slot print_timing: id 0 | task 5206 | total time = 9920.68 ms / 520 tokens 3.22.687.391 I slot print_timing: id 0 | task 5206 | graphs reused = 4975 3.22.687.391 I slot print_timing: id 0 | task 5206 | graph reallocs = 0 / 0 (same size) / (changed size) 3.22.687.413 I slot release: id 0 | task 5206 | stop processing: n_tokens = 519, truncated = 0 3.22.692.460 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.128 (> 0.100 thold), f_keep = 0.058 3.22.692.567 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 82.771 MiB) 3.22.707.104 I slot launch_slot_: id 0 | task 5545 | processing task, is_child = 0 3.25.422.566 I slot print_timing: id 0 | task 5545 | prompt eval time = 447.62 ms / 235 tokens ( 1.90 ms per token, 524.99 tokens per second) 3.25.422.570 I slot print_timing: id 0 | task 5545 | eval time = 2267.82 ms / 81 tokens ( 28.35 ms per token, 35.28 tokens per second) 3.25.422.571 I slot print_timing: id 0 | task 5545 | total time = 2715.45 ms / 316 tokens 3.25.422.571 I slot print_timing: id 0 | task 5545 | graphs reused = 5053 3.25.422.572 I slot print_timing: id 0 | task 5545 | graph reallocs = 0 / 0 (same size) / (changed size) 3.25.422.599 I slot release: id 0 | task 5545 | stop processing: n_tokens = 315, truncated = 0 3.25.427.714 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 3.25.427.764 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 69.480 MiB) 3.25.431.086 I slot launch_slot_: id 0 | task 5629 | processing task, is_child = 0 3.28.993.400 I slot print_timing: id 0 | task 5629 | n_gen = 107, tg = 35.19 t/s, tg_3s = 35.53 t/s 3.32.021.860 I slot print_timing: id 0 | task 5629 | n_gen = 213, tg = 35.10 t/s, tg_3s = 35.00 t/s 3.35.026.862 I slot print_timing: id 0 | task 5629 | n_gen = 318, tg = 35.05 t/s, tg_3s = 34.94 t/s 3.38.034.627 I slot print_timing: id 0 | task 5629 | n_gen = 423, tg = 35.01 t/s, tg_3s = 34.91 t/s 3.40.850.396 I slot print_timing: id 0 | task 5629 | prompt eval time = 550.46 ms / 289 tokens ( 1.90 ms per token, 525.01 tokens per second) 3.40.850.400 I slot print_timing: id 0 | task 5629 | eval time = 14868.83 ms / 521 tokens ( 28.59 ms per token, 34.97 tokens per second) 3.40.850.402 I slot print_timing: id 0 | task 5629 | total time = 15419.30 ms / 810 tokens 3.40.850.402 I slot print_timing: id 0 | task 5629 | graphs reused = 5570 3.40.850.403 I slot print_timing: id 0 | task 5629 | graph reallocs = 0 / 0 (same size) / (changed size) 3.40.850.433 I slot release: id 0 | task 5629 | stop processing: n_tokens = 809, truncated = 0 3.40.855.620 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 3.40.855.708 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 57.526 MiB) 3.40.855.712 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 66.175 MiB) 3.40.867.287 I slot launch_slot_: id 0 | task 6153 | processing task, is_child = 0 3.44.318.089 I slot print_timing: id 0 | task 6153 | n_gen = 107, tg = 35.30 t/s, tg_3s = 35.64 t/s 3.47.343.259 I slot print_timing: id 0 | task 6153 | n_gen = 213, tg = 35.17 t/s, tg_3s = 35.04 t/s 3.50.350.547 I slot print_timing: id 0 | task 6153 | n_gen = 318, tg = 35.09 t/s, tg_3s = 34.92 t/s 3.51.181.355 I slot print_timing: id 0 | task 6153 | prompt eval time = 448.38 ms / 241 tokens ( 1.86 ms per token, 537.49 tokens per second) 3.51.181.359 I slot print_timing: id 0 | task 6153 | eval time = 9865.68 ms / 347 tokens ( 28.51 ms per token, 35.07 tokens per second) 3.51.181.360 I slot print_timing: id 0 | task 6153 | total time = 10314.06 ms / 588 tokens 3.51.181.360 I slot print_timing: id 0 | task 6153 | graphs reused = 5913 3.51.181.361 I slot print_timing: id 0 | task 6153 | graph reallocs = 0 / 0 (same size) / (changed size) 3.51.181.389 I slot release: id 0 | task 6153 | stop processing: n_tokens = 587, truncated = 0 3.51.186.395 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.126 (> 0.100 thold), f_keep = 0.051 3.51.186.466 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 76.723 MiB) 3.51.186.660 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 67.265 MiB) 3.51.196.738 I slot launch_slot_: id 0 | task 6503 | processing task, is_child = 0 3.54.647.565 I slot print_timing: id 0 | task 6503 | n_gen = 107, tg = 35.31 t/s, tg_3s = 35.64 t/s 3.55.557.521 I slot print_timing: id 0 | task 6503 | prompt eval time = 448.87 ms / 239 tokens ( 1.88 ms per token, 532.45 tokens per second) 3.55.557.528 I slot print_timing: id 0 | task 6503 | eval time = 3911.90 ms / 139 tokens ( 28.35 ms per token, 35.28 tokens per second) 3.55.557.528 I slot print_timing: id 0 | task 6503 | total time = 4360.77 ms / 378 tokens 3.55.557.529 I slot print_timing: id 0 | task 6503 | graphs reused = 6049 3.55.557.530 I slot print_timing: id 0 | task 6503 | graph reallocs = 0 / 0 (same size) / (changed size) 3.55.557.562 I slot release: id 0 | task 6503 | stop processing: n_tokens = 377, truncated = 0 3.55.562.592 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 3.55.562.649 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 59.389 MiB) 3.55.566.270 I slot launch_slot_: id 0 | task 6645 | processing task, is_child = 0 3.58.554.940 I slot print_timing: id 0 | task 6645 | prompt eval time = 550.01 ms / 273 tokens ( 2.01 ms per token, 496.35 tokens per second) 3.58.554.945 I slot print_timing: id 0 | task 6645 | eval time = 2438.64 ms / 87 tokens ( 28.36 ms per token, 35.27 tokens per second) 3.58.554.946 I slot print_timing: id 0 | task 6645 | total time = 2988.66 ms / 360 tokens 3.58.554.946 I slot print_timing: id 0 | task 6645 | graphs reused = 6134 3.58.554.947 I slot print_timing: id 0 | task 6645 | graph reallocs = 0 / 0 (same size) / (changed size) 3.58.554.976 I slot release: id 0 | task 6645 | stop processing: n_tokens = 359, truncated = 0 3.58.559.684 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 3.58.559.744 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 57.103 MiB) 3.58.559.750 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 67.828 MiB) 3.58.567.872 I slot launch_slot_: id 0 | task 6735 | processing task, is_child = 0 4.01.995.774 I slot print_timing: id 0 | task 6735 | n_gen = 108, tg = 35.38 t/s, tg_3s = 35.71 t/s 4.03.157.588 I slot print_timing: id 0 | task 6735 | prompt eval time = 403.55 ms / 212 tokens ( 1.90 ms per token, 525.34 tokens per second) 4.03.157.592 I slot print_timing: id 0 | task 6735 | eval time = 4186.15 ms / 149 tokens ( 28.28 ms per token, 35.35 tokens per second) 4.03.157.592 I slot print_timing: id 0 | task 6735 | total time = 4589.70 ms / 361 tokens 4.03.157.593 I slot print_timing: id 0 | task 6735 | graphs reused = 6280 4.03.157.594 I slot print_timing: id 0 | task 6735 | graph reallocs = 0 / 0 (same size) / (changed size) 4.03.157.622 I slot release: id 0 | task 6735 | stop processing: n_tokens = 360, truncated = 0 4.03.162.663 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.105 (> 0.100 thold), f_keep = 0.083 4.03.162.716 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 73.278 MiB) 4.03.170.059 I slot launch_slot_: id 0 | task 6887 | processing task, is_child = 0 4.06.682.006 I slot print_timing: id 0 | task 6887 | n_gen = 107, tg = 35.18 t/s, tg_3s = 35.51 t/s 4.09.696.239 I slot print_timing: id 0 | task 6887 | n_gen = 212, tg = 35.01 t/s, tg_3s = 34.83 t/s 4.10.327.138 I slot print_timing: id 0 | task 6887 | prompt eval time = 498.77 ms / 285 tokens ( 1.75 ms per token, 571.41 tokens per second) 4.10.327.142 I slot print_timing: id 0 | task 6887 | eval time = 6658.30 ms / 234 tokens ( 28.58 ms per token, 34.99 tokens per second) 4.10.327.142 I slot print_timing: id 0 | task 6887 | total time = 7157.07 ms / 519 tokens 4.10.327.143 I slot print_timing: id 0 | task 6887 | graphs reused = 6511 4.10.327.144 I slot print_timing: id 0 | task 6887 | graph reallocs = 0 / 0 (same size) / (changed size) 4.10.327.173 I slot release: id 0 | task 6887 | stop processing: n_tokens = 518, truncated = 0 4.10.332.172 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 4.10.332.239 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 57.490 MiB) 4.10.332.544 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.465 MiB) 4.10.343.438 I slot launch_slot_: id 0 | task 7124 | processing task, is_child = 0 4.13.769.517 I slot print_timing: id 0 | task 7124 | n_gen = 108, tg = 35.37 t/s, tg_3s = 35.70 t/s 4.14.306.987 I slot print_timing: id 0 | task 7124 | prompt eval time = 400.83 ms / 191 tokens ( 2.10 ms per token, 476.51 tokens per second) 4.14.306.993 I slot print_timing: id 0 | task 7124 | eval time = 3562.70 ms / 127 tokens ( 28.28 ms per token, 35.37 tokens per second) 4.14.306.994 I slot print_timing: id 0 | task 7124 | total time = 3963.54 ms / 318 tokens 4.14.306.995 I slot print_timing: id 0 | task 7124 | graphs reused = 6635 4.14.306.995 I slot print_timing: id 0 | task 7124 | graph reallocs = 0 / 0 (same size) / (changed size) 4.14.307.020 I slot release: id 0 | task 7124 | stop processing: n_tokens = 317, truncated = 0 4.14.311.674 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 4.14.311.724 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 45.395 MiB) 4.14.311.959 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 52.462 MiB) 4.14.318.630 I slot launch_slot_: id 0 | task 7254 | processing task, is_child = 0 4.16.852.630 I slot print_timing: id 0 | task 7254 | prompt eval time = 358.01 ms / 171 tokens ( 2.09 ms per token, 477.63 tokens per second) 4.16.852.634 I slot print_timing: id 0 | task 7254 | eval time = 2175.97 ms / 78 tokens ( 28.26 ms per token, 35.39 tokens per second) 4.16.852.635 I slot print_timing: id 0 | task 7254 | total time = 2533.98 ms / 249 tokens 4.16.852.636 I slot print_timing: id 0 | task 7254 | graphs reused = 6711 4.16.852.636 I slot print_timing: id 0 | task 7254 | graph reallocs = 0 / 0 (same size) / (changed size) 4.16.852.665 I slot release: id 0 | task 7254 | stop processing: n_tokens = 248, truncated = 0 4.16.857.887 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 4.16.857.933 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 52.075 MiB) 4.16.860.567 I slot launch_slot_: id 0 | task 7335 | processing task, is_child = 0 4.20.196.230 I slot print_timing: id 0 | task 7335 | prompt eval time = 501.17 ms / 260 tokens ( 1.93 ms per token, 518.79 tokens per second) 4.20.196.233 I slot print_timing: id 0 | task 7335 | eval time = 2834.48 ms / 101 tokens ( 28.34 ms per token, 35.28 tokens per second) 4.20.196.234 I slot print_timing: id 0 | task 7335 | total time = 3335.65 ms / 361 tokens 4.20.196.235 I slot print_timing: id 0 | task 7335 | graphs reused = 6810 4.20.196.236 I slot print_timing: id 0 | task 7335 | graph reallocs = 0 / 0 (same size) / (changed size) 4.20.196.261 I slot release: id 0 | task 7335 | stop processing: n_tokens = 360, truncated = 0 4.20.201.278 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 4.20.201.335 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 52.884 MiB) 4.20.201.339 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 69.726 MiB) 4.20.209.650 I slot launch_slot_: id 0 | task 7439 | processing task, is_child = 0 4.23.633.423 I slot print_timing: id 0 | task 7439 | n_gen = 108, tg = 35.41 t/s, tg_3s = 35.75 t/s 4.26.650.012 I slot print_timing: id 0 | task 7439 | n_gen = 214, tg = 35.28 t/s, tg_3s = 35.14 t/s 4.29.655.451 I slot print_timing: id 0 | task 7439 | n_gen = 319, tg = 35.16 t/s, tg_3s = 34.94 t/s 4.32.656.526 I slot print_timing: id 0 | task 7439 | n_gen = 424, tg = 35.12 t/s, tg_3s = 34.99 t/s 4.35.661.168 I slot print_timing: id 0 | task 7439 | n_gen = 529, tg = 35.09 t/s, tg_3s = 34.95 t/s 4.37.268.735 I slot print_timing: id 0 | task 7439 | prompt eval time = 402.41 ms / 204 tokens ( 1.97 ms per token, 506.95 tokens per second) 4.37.268.738 I slot print_timing: id 0 | task 7439 | eval time = 16656.66 ms / 585 tokens ( 28.52 ms per token, 35.06 tokens per second) 4.37.268.738 I slot print_timing: id 0 | task 7439 | total time = 17059.07 ms / 789 tokens 4.37.268.739 I slot print_timing: id 0 | task 7439 | graphs reused = 7390 4.37.268.739 I slot print_timing: id 0 | task 7439 | graph reallocs = 0 / 0 (same size) / (changed size) 4.37.268.767 I slot release: id 0 | task 7439 | stop processing: n_tokens = 788, truncated = 0 4.37.273.583 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.101 (> 0.100 thold), f_keep = 0.038 4.37.273.668 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 115.928 MiB) 4.37.285.038 I slot launch_slot_: id 0 | task 8027 | processing task, is_child = 0 4.40.854.034 I slot print_timing: id 0 | task 8027 | n_gen = 107, tg = 35.03 t/s, tg_3s = 35.36 t/s 4.43.314.329 I slot print_timing: id 0 | task 8027 | prompt eval time = 543.30 ms / 296 tokens ( 1.84 ms per token, 544.82 tokens per second) 4.43.314.332 I slot print_timing: id 0 | task 8027 | eval time = 5485.98 ms / 193 tokens ( 28.57 ms per token, 35.00 tokens per second) 4.43.314.333 I slot print_timing: id 0 | task 8027 | total time = 6029.28 ms / 489 tokens 4.43.314.334 I slot print_timing: id 0 | task 8027 | graphs reused = 7581 4.43.314.335 I slot print_timing: id 0 | task 8027 | graph reallocs = 0 / 0 (same size) / (changed size) 4.43.314.362 I slot release: id 0 | task 8027 | stop processing: n_tokens = 488, truncated = 0 4.43.319.020 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 4.43.319.092 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 52.638 MiB) 4.43.319.311 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 62.905 MiB) 4.43.329.964 I slot launch_slot_: id 0 | task 8223 | processing task, is_child = 0 4.46.784.008 I slot print_timing: id 0 | task 8223 | n_gen = 107, tg = 35.30 t/s, tg_3s = 35.64 t/s 4.49.805.933 I slot print_timing: id 0 | task 8223 | n_gen = 213, tg = 35.19 t/s, tg_3s = 35.08 t/s 4.52.811.668 I slot print_timing: id 0 | task 8223 | n_gen = 318, tg = 35.10 t/s, tg_3s = 34.93 t/s 4.55.818.234 I slot print_timing: id 0 | task 8223 | n_gen = 423, tg = 35.06 t/s, tg_3s = 34.92 t/s 4.58.582.067 I slot print_timing: id 0 | task 8223 | prompt eval time = 451.37 ms / 236 tokens ( 1.91 ms per token, 522.85 tokens per second) 4.58.582.075 I slot print_timing: id 0 | task 8223 | eval time = 14800.72 ms / 519 tokens ( 28.57 ms per token, 35.00 tokens per second) 4.58.582.075 I slot print_timing: id 0 | task 8223 | total time = 15252.09 ms / 755 tokens 4.58.582.076 I slot print_timing: id 0 | task 8223 | graphs reused = 8096 4.58.582.076 I slot print_timing: id 0 | task 8223 | graph reallocs = 0 / 0 (same size) / (changed size) 4.58.582.102 I slot release: id 0 | task 8223 | stop processing: n_tokens = 754, truncated = 0 4.58.587.265 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.102 (> 0.100 thold), f_keep = 0.040 4.58.587.347 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 81.787 MiB) 4.58.599.042 I slot launch_slot_: id 0 | task 8745 | processing task, is_child = 0 5.01.626.474 I slot print_timing: id 0 | task 8745 | prompt eval time = 551.22 ms / 294 tokens ( 1.87 ms per token, 533.36 tokens per second) 5.01.626.478 I slot print_timing: id 0 | task 8745 | eval time = 2476.19 ms / 88 tokens ( 28.46 ms per token, 35.13 tokens per second) 5.01.626.478 I slot print_timing: id 0 | task 8745 | total time = 3027.41 ms / 382 tokens 5.01.626.479 I slot print_timing: id 0 | task 8745 | graphs reused = 8182 5.01.626.480 I slot print_timing: id 0 | task 8745 | graph reallocs = 0 / 0 (same size) / (changed size) 5.01.626.506 I slot release: id 0 | task 8745 | stop processing: n_tokens = 381, truncated = 0 5.01.631.796 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.103 (> 0.100 thold), f_keep = 0.079 5.01.631.856 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 84.213 MiB) 5.01.632.085 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 59.881 MiB) 5.01.636.536 I slot launch_slot_: id 0 | task 8836 | processing task, is_child = 0 5.05.189.569 I slot print_timing: id 0 | task 8836 | n_gen = 107, tg = 35.20 t/s, tg_3s = 35.53 t/s 5.08.201.555 I slot print_timing: id 0 | task 8836 | n_gen = 212, tg = 35.03 t/s, tg_3s = 34.86 t/s 5.10.523.452 I slot print_timing: id 0 | task 8836 | prompt eval time = 541.86 ms / 291 tokens ( 1.86 ms per token, 537.04 tokens per second) 5.10.523.456 I slot print_timing: id 0 | task 8836 | eval time = 8345.05 ms / 293 tokens ( 28.58 ms per token, 34.99 tokens per second) 5.10.523.457 I slot print_timing: id 0 | task 8836 | total time = 8886.90 ms / 584 tokens 5.10.523.457 I slot print_timing: id 0 | task 8836 | graphs reused = 8472 5.10.523.458 I slot print_timing: id 0 | task 8836 | graph reallocs = 0 / 0 (same size) / (changed size) 5.10.523.484 I slot release: id 0 | task 8836 | stop processing: n_tokens = 583, truncated = 0 5.10.528.536 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.105 (> 0.100 thold), f_keep = 0.051 5.10.528.611 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 60.092 MiB) 5.10.528.615 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 74.086 MiB) 5.10.539.180 I slot launch_slot_: id 0 | task 9132 | processing task, is_child = 0 5.14.105.532 I slot print_timing: id 0 | task 9132 | n_gen = 107, tg = 35.16 t/s, tg_3s = 35.49 t/s 5.14.420.705 I slot print_timing: id 0 | task 9132 | prompt eval time = 551.38 ms / 287 tokens ( 1.92 ms per token, 520.51 tokens per second) 5.14.420.708 I slot print_timing: id 0 | task 9132 | eval time = 3330.13 ms / 118 tokens ( 28.46 ms per token, 35.13 tokens per second) 5.14.420.709 I slot print_timing: id 0 | task 9132 | total time = 3881.51 ms / 405 tokens 5.14.420.709 I slot print_timing: id 0 | task 9132 | graphs reused = 8588 5.14.420.710 I slot print_timing: id 0 | task 9132 | graph reallocs = 0 / 0 (same size) / (changed size) 5.14.420.738 I slot release: id 0 | task 9132 | stop processing: n_tokens = 404, truncated = 0 5.14.425.672 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 5.14.425.735 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 56.541 MiB) 5.14.434.303 I slot launch_slot_: id 0 | task 9253 | processing task, is_child = 0 5.17.897.991 I slot print_timing: id 0 | task 9253 | n_gen = 107, tg = 35.29 t/s, tg_3s = 35.62 t/s 5.19.009.162 I slot print_timing: id 0 | task 9253 | prompt eval time = 459.87 ms / 243 tokens ( 1.89 ms per token, 528.41 tokens per second) 5.19.009.166 I slot print_timing: id 0 | task 9253 | eval time = 4114.97 ms / 146 tokens ( 28.38 ms per token, 35.24 tokens per second) 5.19.009.167 I slot print_timing: id 0 | task 9253 | total time = 4574.85 ms / 389 tokens 5.19.009.168 I slot print_timing: id 0 | task 9253 | graphs reused = 8731 5.19.009.168 I slot print_timing: id 0 | task 9253 | graph reallocs = 0 / 0 (same size) / (changed size) 5.19.009.199 I slot release: id 0 | task 9253 | stop processing: n_tokens = 388, truncated = 0 5.19.013.953 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.166 (> 0.100 thold), f_keep = 0.077 5.19.014.019 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 75.352 MiB) 5.19.022.126 I slot launch_slot_: id 0 | task 9402 | processing task, is_child = 0 5.21.002.869 I slot print_timing: id 0 | task 9402 | prompt eval time = 398.91 ms / 181 tokens ( 2.20 ms per token, 453.74 tokens per second) 5.21.002.873 I slot print_timing: id 0 | task 9402 | eval time = 1581.82 ms / 57 tokens ( 28.25 ms per token, 35.40 tokens per second) 5.21.002.873 I slot print_timing: id 0 | task 9402 | total time = 1980.73 ms / 238 tokens 5.21.002.874 I slot print_timing: id 0 | task 9402 | graphs reused = 8786 5.21.002.874 I slot print_timing: id 0 | task 9402 | graph reallocs = 0 / 0 (same size) / (changed size) 5.21.002.904 I slot release: id 0 | task 9402 | stop processing: n_tokens = 237, truncated = 0 5.21.007.619 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 5.21.007.669 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 59.776 MiB) 5.21.008.015 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 100.844 MiB) 5.21.011.011 I slot launch_slot_: id 0 | task 9462 | processing task, is_child = 0 5.24.510.287 I slot print_timing: id 0 | task 9462 | n_gen = 107, tg = 35.29 t/s, tg_3s = 35.62 t/s 5.27.515.685 I slot print_timing: id 0 | task 9462 | n_gen = 212, tg = 35.11 t/s, tg_3s = 34.94 t/s 5.30.521.748 I slot print_timing: id 0 | task 9462 | n_gen = 317, tg = 35.05 t/s, tg_3s = 34.93 t/s 5.33.527.225 I slot print_timing: id 0 | task 9462 | n_gen = 422, tg = 35.02 t/s, tg_3s = 34.94 t/s 5.36.537.208 I slot print_timing: id 0 | task 9462 | n_gen = 527, tg = 35.00 t/s, tg_3s = 34.88 t/s 5.39.557.687 I slot print_timing: id 0 | task 9462 | n_gen = 632, tg = 34.96 t/s, tg_3s = 34.76 t/s 5.40.160.371 I slot print_timing: id 0 | task 9462 | prompt eval time = 495.73 ms / 265 tokens ( 1.87 ms per token, 534.56 tokens per second) 5.40.160.381 I slot print_timing: id 0 | task 9462 | eval time = 18653.61 ms / 653 tokens ( 28.61 ms per token, 34.95 tokens per second) 5.40.160.381 I slot print_timing: id 0 | task 9462 | total time = 19149.35 ms / 918 tokens 5.40.160.382 I slot print_timing: id 0 | task 9462 | graphs reused = 9435 5.40.160.383 I slot print_timing: id 0 | task 9462 | graph reallocs = 0 / 0 (same size) / (changed size) 5.40.160.410 I slot release: id 0 | task 9462 | stop processing: n_tokens = 917, truncated = 0 5.40.165.093 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.197 (> 0.100 thold), f_keep = 0.033 5.40.165.187 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 91.350 MiB) 5.40.176.809 I slot launch_slot_: id 0 | task 10118 | processing task, is_child = 0 5.41.688.068 I slot print_timing: id 0 | task 10118 | prompt eval time = 353.58 ms / 152 tokens ( 2.33 ms per token, 429.89 tokens per second) 5.41.688.074 I slot print_timing: id 0 | task 10118 | eval time = 1157.66 ms / 42 tokens ( 28.24 ms per token, 35.42 tokens per second) 5.41.688.075 I slot print_timing: id 0 | task 10118 | total time = 1511.24 ms / 194 tokens 5.41.688.076 I slot print_timing: id 0 | task 10118 | graphs reused = 9475 5.41.688.076 I slot print_timing: id 0 | task 10118 | graph reallocs = 0 / 0 (same size) / (changed size) 5.41.688.098 I slot release: id 0 | task 10118 | stop processing: n_tokens = 193, truncated = 0 5.41.692.585 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 5.41.694.853 I slot launch_slot_: id 0 | task 10163 | processing task, is_child = 0 5.43.594.152 I slot print_timing: id 0 | task 10163 | prompt eval time = 400.39 ms / 190 tokens ( 2.11 ms per token, 474.53 tokens per second) 5.43.594.159 I slot print_timing: id 0 | task 10163 | eval time = 1498.89 ms / 54 tokens ( 28.28 ms per token, 35.36 tokens per second) 5.43.594.159 I slot print_timing: id 0 | task 10163 | total time = 1899.28 ms / 244 tokens 5.43.594.160 I slot print_timing: id 0 | task 10163 | graphs reused = 9527 5.43.594.161 I slot print_timing: id 0 | task 10163 | graph reallocs = 0 / 0 (same size) / (changed size) 5.43.594.184 I slot release: id 0 | task 10163 | stop processing: n_tokens = 243, truncated = 0 5.43.599.229 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 5.43.599.274 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 57.244 MiB) 5.43.599.278 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.183 MiB) 5.43.602.178 I slot launch_slot_: id 0 | task 10220 | processing task, is_child = 0 5.47.107.466 I slot print_timing: id 0 | task 10220 | n_gen = 107, tg = 35.30 t/s, tg_3s = 35.63 t/s 5.48.288.209 I slot print_timing: id 0 | task 10220 | prompt eval time = 502.40 ms / 256 tokens ( 1.96 ms per token, 509.56 tokens per second) 5.48.288.213 I slot print_timing: id 0 | task 10220 | eval time = 4183.62 ms / 148 tokens ( 28.46 ms per token, 35.14 tokens per second) 5.48.288.214 I slot print_timing: id 0 | task 10220 | total time = 4686.02 ms / 404 tokens 5.48.288.214 I slot print_timing: id 0 | task 10220 | graphs reused = 9673 5.48.288.215 I slot print_timing: id 0 | task 10220 | graph reallocs = 0 / 0 (same size) / (changed size) 5.48.288.243 I slot release: id 0 | task 10220 | stop processing: n_tokens = 403, truncated = 0 5.48.293.358 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.114 (> 0.100 thold), f_keep = 0.074 5.48.293.413 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 53.728 MiB) 5.48.301.720 I slot launch_slot_: id 0 | task 10371 | processing task, is_child = 0 5.49.855.833 I slot print_timing: id 0 | task 10371 | prompt eval time = 505.02 ms / 264 tokens ( 1.91 ms per token, 522.76 tokens per second) 5.49.855.840 I slot print_timing: id 0 | task 10371 | eval time = 1049.09 ms / 38 tokens ( 28.35 ms per token, 35.27 tokens per second) 5.49.855.841 I slot print_timing: id 0 | task 10371 | total time = 1554.10 ms / 302 tokens 5.49.855.841 I slot print_timing: id 0 | task 10371 | graphs reused = 9709 5.49.855.842 I slot print_timing: id 0 | task 10371 | graph reallocs = 0 / 0 (same size) / (changed size) 5.49.855.872 I slot release: id 0 | task 10371 | stop processing: n_tokens = 301, truncated = 0 5.49.861.011 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 5.49.861.065 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.778 MiB) 5.49.861.267 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 115.400 MiB) 5.49.865.389 I slot launch_slot_: id 0 | task 10412 | processing task, is_child = 0 5.53.431.133 I slot print_timing: id 0 | task 10412 | n_gen = 107, tg = 35.19 t/s, tg_3s = 35.52 t/s 5.56.434.292 I slot print_timing: id 0 | task 10412 | n_gen = 212, tg = 35.08 t/s, tg_3s = 34.96 t/s 5.59.441.000 I slot print_timing: id 0 | task 10412 | n_gen = 317, tg = 35.03 t/s, tg_3s = 34.92 t/s 6.02.450.536 I slot print_timing: id 0 | task 10412 | n_gen = 422, tg = 34.99 t/s, tg_3s = 34.89 t/s 6.05.459.888 I slot print_timing: id 0 | task 10412 | n_gen = 527, tg = 34.97 t/s, tg_3s = 34.89 t/s 6.05.488.522 I slot print_timing: id 0 | task 10412 | prompt eval time = 553.58 ms / 289 tokens ( 1.92 ms per token, 522.06 tokens per second) 6.05.488.525 I slot print_timing: id 0 | task 10412 | eval time = 15069.55 ms / 528 tokens ( 28.59 ms per token, 34.97 tokens per second) 6.05.488.527 I slot print_timing: id 0 | task 10412 | total time = 15623.12 ms / 817 tokens 6.05.488.528 I slot print_timing: id 0 | task 10412 | graphs reused = 10233 6.05.488.529 I slot print_timing: id 0 | task 10412 | graph reallocs = 0 / 0 (same size) / (changed size) 6.05.488.561 I slot release: id 0 | task 10412 | stop processing: n_tokens = 816, truncated = 0 6.05.494.107 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.102 (> 0.100 thold), f_keep = 0.037 6.05.494.191 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 138.958 MiB) 6.05.506.293 I slot launch_slot_: id 0 | task 10943 | processing task, is_child = 0 6.06.441.294 I slot print_timing: id 0 | task 10943 | prompt eval time = 563.31 ms / 294 tokens ( 1.92 ms per token, 521.92 tokens per second) 6.06.441.302 I slot print_timing: id 0 | task 10943 | eval time = 371.68 ms / 14 tokens ( 28.59 ms per token, 34.98 tokens per second) 6.06.441.303 I slot print_timing: id 0 | task 10943 | total time = 934.99 ms / 308 tokens 6.06.441.304 I slot print_timing: id 0 | task 10943 | graphs reused = 10245 6.06.441.304 I slot print_timing: id 0 | task 10943 | graph reallocs = 0 / 0 (same size) / (changed size) 6.06.441.337 I slot release: id 0 | task 10943 | stop processing: n_tokens = 307, truncated = 0 6.06.446.266 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 6.06.449.923 I slot launch_slot_: id 0 | task 10960 | processing task, is_child = 0 6.08.923.863 I slot print_timing: id 0 | task 10960 | prompt eval time = 565.01 ms / 292 tokens ( 1.93 ms per token, 516.81 tokens per second) 6.08.923.870 I slot print_timing: id 0 | task 10960 | eval time = 1908.91 ms / 68 tokens ( 28.49 ms per token, 35.10 tokens per second) 6.08.923.870 I slot print_timing: id 0 | task 10960 | total time = 2473.92 ms / 360 tokens 6.08.923.871 I slot print_timing: id 0 | task 10960 | graphs reused = 10311 6.08.923.871 I slot print_timing: id 0 | task 10960 | graph reallocs = 0 / 0 (same size) / (changed size) 6.08.923.898 I slot release: id 0 | task 10960 | stop processing: n_tokens = 359, truncated = 0 6.08.929.134 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 6.08.929.188 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 160.864 MiB) 6.08.932.923 I slot launch_slot_: id 0 | task 11031 | processing task, is_child = 0 6.10.755.187 I slot print_timing: id 0 | task 11031 | prompt eval time = 459.56 ms / 245 tokens ( 1.88 ms per token, 533.12 tokens per second) 6.10.755.194 I slot print_timing: id 0 | task 11031 | eval time = 1362.69 ms / 49 tokens ( 28.39 ms per token, 35.22 tokens per second) 6.10.755.195 I slot print_timing: id 0 | task 11031 | total time = 1822.25 ms / 294 tokens 6.10.755.195 I slot print_timing: id 0 | task 11031 | graphs reused = 10357 6.10.755.196 I slot print_timing: id 0 | task 11031 | graph reallocs = 0 / 0 (same size) / (changed size) 6.10.755.227 I slot release: id 0 | task 11031 | stop processing: n_tokens = 293, truncated = 0 6.10.759.787 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 6.10.759.835 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 146.518 MiB) 6.10.762.930 I slot launch_slot_: id 0 | task 11083 | processing task, is_child = 0 6.12.195.816 I slot print_timing: id 0 | task 11083 | prompt eval time = 358.54 ms / 178 tokens ( 2.01 ms per token, 496.46 tokens per second) 6.12.195.820 I slot print_timing: id 0 | task 11083 | eval time = 1074.33 ms / 39 tokens ( 28.27 ms per token, 35.37 tokens per second) 6.12.195.820 I slot print_timing: id 0 | task 11083 | total time = 1432.87 ms / 217 tokens 6.12.195.821 I slot print_timing: id 0 | task 11083 | graphs reused = 10394 6.12.195.822 I slot print_timing: id 0 | task 11083 | graph reallocs = 0 / 0 (same size) / (changed size) 6.12.195.843 I slot release: id 0 | task 11083 | stop processing: n_tokens = 216, truncated = 0 6.12.201.479 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 216, t_last = 318730185391 6.12.203.992 I slot launch_slot_: id 0 | task 11125 | processing task, is_child = 0 6.15.239.174 I slot print_timing: id 0 | task 11125 | prompt eval time = 661.22 ms / 355 tokens ( 1.86 ms per token, 536.89 tokens per second) 6.15.239.179 I slot print_timing: id 0 | task 11125 | eval time = 2373.95 ms / 84 tokens ( 28.60 ms per token, 34.96 tokens per second) 6.15.239.179 I slot print_timing: id 0 | task 11125 | total time = 3035.17 ms / 439 tokens 6.15.239.180 I slot print_timing: id 0 | task 11125 | graphs reused = 10476 6.15.239.180 I slot print_timing: id 0 | task 11125 | graph reallocs = 0 / 0 (same size) / (changed size) 6.15.239.211 I slot release: id 0 | task 11125 | stop processing: n_tokens = 438, truncated = 0 6.15.245.867 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 438, t_last = 318733228759 6.15.245.948 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 94.655 MiB) 6.15.250.689 I slot launch_slot_: id 0 | task 11212 | processing task, is_child = 0 6.19.299.250 I slot print_timing: id 0 | task 11212 | n_gen = 106, tg = 34.88 t/s, tg_3s = 35.21 t/s 6.20.502.222 I slot print_timing: id 0 | task 11212 | prompt eval time = 1038.19 ms / 567 tokens ( 1.83 ms per token, 546.14 tokens per second) 6.20.502.225 I slot print_timing: id 0 | task 11212 | eval time = 4213.33 ms / 148 tokens ( 28.66 ms per token, 34.89 tokens per second) 6.20.502.226 I slot print_timing: id 0 | task 11212 | total time = 5251.52 ms / 715 tokens 6.20.502.227 I slot print_timing: id 0 | task 11212 | graphs reused = 10622 6.20.502.227 I slot print_timing: id 0 | task 11212 | graph reallocs = 0 / 0 (same size) / (changed size) 6.20.502.273 I slot release: id 0 | task 11212 | stop processing: n_tokens = 714, truncated = 0 6.20.508.661 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 714, t_last = 318738491821 6.20.508.746 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 144.725 MiB) 6.20.508.750 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 137.446 MiB) 6.20.527.578 I slot launch_slot_: id 0 | task 11364 | processing task, is_child = 0 6.24.378.521 I slot print_timing: id 0 | task 11364 | n_gen = 106, tg = 34.87 t/s, tg_3s = 35.20 t/s 6.24.636.454 I slot print_timing: id 0 | task 11364 | prompt eval time = 839.63 ms / 473 tokens ( 1.78 ms per token, 563.34 tokens per second) 6.24.636.458 I slot print_timing: id 0 | task 11364 | eval time = 3269.23 ms / 115 tokens ( 28.68 ms per token, 34.87 tokens per second) 6.24.636.459 I slot print_timing: id 0 | task 11364 | total time = 4108.86 ms / 588 tokens 6.24.636.459 I slot print_timing: id 0 | task 11364 | graphs reused = 10734 6.24.636.460 I slot print_timing: id 0 | task 11364 | graph reallocs = 0 / 0 (same size) / (changed size) 6.24.636.494 I slot release: id 0 | task 11364 | stop processing: n_tokens = 587, truncated = 0 6.24.642.344 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 587, t_last = 318742626042 6.24.642.428 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 107.313 MiB) 6.24.658.391 I slot launch_slot_: id 0 | task 11482 | processing task, is_child = 0 6.28.375.188 I slot print_timing: id 0 | task 11482 | n_gen = 106, tg = 34.96 t/s, tg_3s = 35.30 t/s 6.31.380.443 I slot print_timing: id 0 | task 11482 | n_gen = 211, tg = 34.95 t/s, tg_3s = 34.94 t/s 6.34.383.380 I slot print_timing: id 0 | task 11482 | n_gen = 316, tg = 34.96 t/s, tg_3s = 34.97 t/s 6.37.404.148 I slot print_timing: id 0 | task 11482 | n_gen = 421, tg = 34.91 t/s, tg_3s = 34.76 t/s 6.40.423.570 I slot print_timing: id 0 | task 11482 | n_gen = 526, tg = 34.88 t/s, tg_3s = 34.77 t/s 6.43.437.204 I slot print_timing: id 0 | task 11482 | n_gen = 631, tg = 34.87 t/s, tg_3s = 34.84 t/s 6.46.452.690 I slot print_timing: id 0 | task 11482 | n_gen = 736, tg = 34.87 t/s, tg_3s = 34.82 t/s 6.49.468.683 I slot print_timing: id 0 | task 11482 | n_gen = 841, tg = 34.86 t/s, tg_3s = 34.81 t/s 6.50.878.216 I slot print_timing: id 0 | task 11482 | prompt eval time = 713.55 ms / 399 tokens ( 1.79 ms per token, 559.18 tokens per second) 6.50.878.223 I slot print_timing: id 0 | task 11482 | eval time = 25506.26 ms / 890 tokens ( 28.69 ms per token, 34.85 tokens per second) 6.50.878.224 I slot print_timing: id 0 | task 11482 | total time = 26219.82 ms / 1289 tokens 6.50.878.225 I slot print_timing: id 0 | task 11482 | graphs reused = 11618 6.50.878.225 I slot print_timing: id 0 | task 11482 | graph reallocs = 0 / 0 (same size) / (changed size) 6.50.878.257 I slot release: id 0 | task 11482 | stop processing: n_tokens = 1288, truncated = 0 6.50.883.771 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1288, t_last = 318768867805 6.50.883.879 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 103.375 MiB) 6.50.898.070 I slot launch_slot_: id 0 | task 12375 | processing task, is_child = 0 6.53.371.330 I slot print_timing: id 0 | task 12375 | prompt eval time = 596.89 ms / 312 tokens ( 1.91 ms per token, 522.71 tokens per second) 6.53.371.334 I slot print_timing: id 0 | task 12375 | eval time = 1876.36 ms / 67 tokens ( 28.43 ms per token, 35.17 tokens per second) 6.53.371.335 I slot print_timing: id 0 | task 12375 | total time = 2473.25 ms / 379 tokens 6.53.371.335 I slot print_timing: id 0 | task 12375 | graphs reused = 11683 6.53.371.336 I slot print_timing: id 0 | task 12375 | graph reallocs = 0 / 0 (same size) / (changed size) 6.53.371.363 I slot release: id 0 | task 12375 | stop processing: n_tokens = 378, truncated = 0 6.53.378.177 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 378, t_last = 318771360911 6.53.378.238 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.109 MiB) 6.53.382.245 I slot launch_slot_: id 0 | task 12445 | processing task, is_child = 0 6.57.398.918 I slot print_timing: id 0 | task 12445 | n_gen = 106, tg = 34.94 t/s, tg_3s = 35.27 t/s 7.00.406.589 I slot print_timing: id 0 | task 12445 | n_gen = 211, tg = 34.92 t/s, tg_3s = 34.91 t/s 7.02.926.437 I slot print_timing: id 0 | task 12445 | prompt eval time = 1011.31 ms / 561 tokens ( 1.80 ms per token, 554.73 tokens per second) 7.02.926.444 I slot print_timing: id 0 | task 12445 | eval time = 8532.87 ms / 299 tokens ( 28.63 ms per token, 34.92 tokens per second) 7.02.926.445 I slot print_timing: id 0 | task 12445 | total time = 9544.18 ms / 860 tokens 7.02.926.446 I slot print_timing: id 0 | task 12445 | graphs reused = 11979 7.02.926.446 I slot print_timing: id 0 | task 12445 | graph reallocs = 0 / 0 (same size) / (changed size) 7.02.926.489 I slot release: id 0 | task 12445 | stop processing: n_tokens = 859, truncated = 0 7.02.932.154 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 859, t_last = 318780916037 7.02.932.245 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 114.275 MiB) 7.02.932.249 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 87.201 MiB) 7.02.948.315 I slot launch_slot_: id 0 | task 12748 | processing task, is_child = 0 7.06.374.831 I slot print_timing: id 0 | task 12748 | prompt eval time = 594.10 ms / 317 tokens ( 1.87 ms per token, 533.58 tokens per second) 7.06.374.838 I slot print_timing: id 0 | task 12748 | eval time = 2832.40 ms / 100 tokens ( 28.61 ms per token, 34.95 tokens per second) 7.06.374.839 I slot print_timing: id 0 | task 12748 | total time = 3426.50 ms / 417 tokens 7.06.374.842 I slot print_timing: id 0 | task 12748 | graphs reused = 12077 7.06.374.843 I slot print_timing: id 0 | task 12748 | graph reallocs = 0 / 0 (same size) / (changed size) 7.06.374.872 I slot release: id 0 | task 12748 | stop processing: n_tokens = 416, truncated = 0 7.06.381.300 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 318784364420 7.06.381.364 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 119.022 MiB) 7.06.390.029 I slot launch_slot_: id 0 | task 12851 | processing task, is_child = 0 7.10.153.552 I slot print_timing: id 0 | task 12851 | n_gen = 106, tg = 34.81 t/s, tg_3s = 35.14 t/s 7.12.501.424 I slot print_timing: id 0 | task 12851 | prompt eval time = 747.08 ms / 428 tokens ( 1.75 ms per token, 572.90 tokens per second) 7.12.501.429 I slot print_timing: id 0 | task 12851 | eval time = 5364.31 ms / 188 tokens ( 28.69 ms per token, 34.86 tokens per second) 7.12.501.430 I slot print_timing: id 0 | task 12851 | total time = 6111.38 ms / 616 tokens 7.12.501.435 I slot print_timing: id 0 | task 12851 | graphs reused = 12262 7.12.501.436 I slot print_timing: id 0 | task 12851 | graph reallocs = 0 / 0 (same size) / (changed size) 7.12.501.472 I slot release: id 0 | task 12851 | stop processing: n_tokens = 615, truncated = 0 7.12.506.447 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.133 (> 0.100 thold), f_keep = 0.049 7.12.506.519 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 99.402 MiB) 7.12.506.527 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 88.854 MiB) 7.12.517.579 I slot launch_slot_: id 0 | task 13042 | processing task, is_child = 0 7.15.178.438 I slot print_timing: id 0 | task 13042 | prompt eval time = 454.69 ms / 226 tokens ( 2.01 ms per token, 497.04 tokens per second) 7.15.178.441 I slot print_timing: id 0 | task 13042 | eval time = 2206.15 ms / 79 tokens ( 28.28 ms per token, 35.36 tokens per second) 7.15.178.442 I slot print_timing: id 0 | task 13042 | total time = 2660.84 ms / 305 tokens 7.15.178.443 I slot print_timing: id 0 | task 13042 | graphs reused = 12338 7.15.178.443 I slot print_timing: id 0 | task 13042 | graph reallocs = 0 / 0 (same size) / (changed size) 7.15.178.472 I slot release: id 0 | task 13042 | stop processing: n_tokens = 304, truncated = 0 7.15.184.490 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 304, t_last = 318793168020 7.15.184.541 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 94.304 MiB) 7.15.187.678 I slot launch_slot_: id 0 | task 13124 | processing task, is_child = 0 7.18.884.669 I slot print_timing: id 0 | task 13124 | n_gen = 106, tg = 34.97 t/s, tg_3s = 35.30 t/s 7.18.913.200 I slot print_timing: id 0 | task 13124 | prompt eval time = 694.51 ms / 386 tokens ( 1.80 ms per token, 555.79 tokens per second) 7.18.913.203 I slot print_timing: id 0 | task 13124 | eval time = 3031.01 ms / 107 tokens ( 28.59 ms per token, 34.97 tokens per second) 7.18.913.203 I slot print_timing: id 0 | task 13124 | total time = 3725.51 ms / 493 tokens 7.18.913.205 I slot print_timing: id 0 | task 13124 | graphs reused = 12443 7.18.913.205 I slot print_timing: id 0 | task 13124 | graph reallocs = 0 / 0 (same size) / (changed size) 7.18.913.236 I slot release: id 0 | task 13124 | stop processing: n_tokens = 492, truncated = 0 7.18.919.962 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 492, t_last = 318796902785 7.18.920.032 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 89.662 MiB) 7.18.930.966 I slot launch_slot_: id 0 | task 13234 | processing task, is_child = 0 7.22.830.187 I slot print_timing: id 0 | task 13234 | n_gen = 106, tg = 34.91 t/s, tg_3s = 35.24 t/s 7.25.835.396 I slot print_timing: id 0 | task 13234 | n_gen = 211, tg = 34.93 t/s, tg_3s = 34.94 t/s 7.25.892.566 I slot print_timing: id 0 | task 13234 | prompt eval time = 891.61 ms / 508 tokens ( 1.76 ms per token, 569.76 tokens per second) 7.25.892.570 I slot print_timing: id 0 | task 13234 | eval time = 6069.98 ms / 213 tokens ( 28.63 ms per token, 34.93 tokens per second) 7.25.892.570 I slot print_timing: id 0 | task 13234 | total time = 6961.59 ms / 721 tokens 7.25.892.571 I slot print_timing: id 0 | task 13234 | graphs reused = 12653 7.25.892.572 I slot print_timing: id 0 | task 13234 | graph reallocs = 0 / 0 (same size) / (changed size) 7.25.892.615 I slot release: id 0 | task 13234 | stop processing: n_tokens = 720, truncated = 0 7.25.899.692 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 720, t_last = 318803882163 7.25.899.776 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 139.450 MiB) 7.25.912.224 I slot launch_slot_: id 0 | task 13450 | processing task, is_child = 0 7.29.942.130 I slot print_timing: id 0 | task 13450 | n_gen = 106, tg = 34.92 t/s, tg_3s = 35.26 t/s 7.30.113.507 I slot print_timing: id 0 | task 13450 | prompt eval time = 1023.38 ms / 567 tokens ( 1.80 ms per token, 554.05 tokens per second) 7.30.113.513 I slot print_timing: id 0 | task 13450 | eval time = 3177.89 ms / 112 tokens ( 28.63 ms per token, 34.93 tokens per second) 7.30.113.513 I slot print_timing: id 0 | task 13450 | total time = 4201.27 ms / 679 tokens 7.30.113.514 I slot print_timing: id 0 | task 13450 | graphs reused = 12763 7.30.113.515 I slot print_timing: id 0 | task 13450 | graph reallocs = 0 / 0 (same size) / (changed size) 7.30.113.551 I slot release: id 0 | task 13450 | stop processing: n_tokens = 678, truncated = 0 7.30.119.519 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 678, t_last = 318808103099 7.30.119.595 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 109.810 MiB) 7.30.119.600 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 195.006 MiB) 7.30.132.290 I slot launch_slot_: id 0 | task 13566 | processing task, is_child = 0 7.32.999.188 I slot print_timing: id 0 | task 13566 | prompt eval time = 694.08 ms / 384 tokens ( 1.81 ms per token, 553.25 tokens per second) 7.32.999.192 I slot print_timing: id 0 | task 13566 | eval time = 2172.80 ms / 77 tokens ( 28.59 ms per token, 34.98 tokens per second) 7.32.999.193 I slot print_timing: id 0 | task 13566 | total time = 2866.88 ms / 461 tokens 7.32.999.194 I slot print_timing: id 0 | task 13566 | graphs reused = 12838 7.32.999.194 I slot print_timing: id 0 | task 13566 | graph reallocs = 0 / 0 (same size) / (changed size) 7.32.999.238 I slot release: id 0 | task 13566 | stop processing: n_tokens = 460, truncated = 0 7.33.005.555 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 460, t_last = 318810988786 7.33.005.633 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 95.288 MiB) 7.33.010.428 I slot launch_slot_: id 0 | task 13646 | processing task, is_child = 0 7.36.420.366 I slot print_timing: id 0 | task 13646 | prompt eval time = 834.30 ms / 457 tokens ( 1.83 ms per token, 547.76 tokens per second) 7.36.420.374 I slot print_timing: id 0 | task 13646 | eval time = 2575.62 ms / 91 tokens ( 28.62 ms per token, 34.94 tokens per second) 7.36.420.375 I slot print_timing: id 0 | task 13646 | total time = 3409.92 ms / 548 tokens 7.36.420.375 I slot print_timing: id 0 | task 13646 | graphs reused = 12926 7.36.420.376 I slot print_timing: id 0 | task 13646 | graph reallocs = 0 / 0 (same size) / (changed size) 7.36.420.410 I slot release: id 0 | task 13646 | stop processing: n_tokens = 547, truncated = 0 7.36.426.376 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 547, t_last = 318814409959 7.36.426.448 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 159.703 MiB) 7.36.437.439 I slot launch_slot_: id 0 | task 13740 | processing task, is_child = 0 7.40.197.182 I slot print_timing: id 0 | task 13740 | n_gen = 106, tg = 34.85 t/s, tg_3s = 35.18 t/s 7.42.771.536 I slot print_timing: id 0 | task 13740 | prompt eval time = 746.51 ms / 428 tokens ( 1.74 ms per token, 573.34 tokens per second) 7.42.771.543 I slot print_timing: id 0 | task 13740 | eval time = 5587.58 ms / 196 tokens ( 28.65 ms per token, 34.90 tokens per second) 7.42.771.543 I slot print_timing: id 0 | task 13740 | total time = 6334.09 ms / 624 tokens 7.42.771.544 I slot print_timing: id 0 | task 13740 | graphs reused = 13119 7.42.771.545 I slot print_timing: id 0 | task 13740 | graph reallocs = 0 / 0 (same size) / (changed size) 7.42.771.581 I slot release: id 0 | task 13740 | stop processing: n_tokens = 623, truncated = 0 7.42.778.429 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 623, t_last = 318820761129 7.42.778.501 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 184.211 MiB) 7.42.790.111 I slot launch_slot_: id 0 | task 13939 | processing task, is_child = 0 7.46.804.584 I slot print_timing: id 0 | task 13939 | n_gen = 106, tg = 34.94 t/s, tg_3s = 35.27 t/s 7.47.804.909 I slot print_timing: id 0 | task 13939 | prompt eval time = 1009.24 ms / 555 tokens ( 1.82 ms per token, 549.92 tokens per second) 7.47.804.914 I slot print_timing: id 0 | task 13939 | eval time = 4005.55 ms / 141 tokens ( 28.61 ms per token, 34.95 tokens per second) 7.47.804.914 I slot print_timing: id 0 | task 13939 | total time = 5014.79 ms / 696 tokens 7.47.804.915 I slot print_timing: id 0 | task 13939 | graphs reused = 13258 7.47.804.916 I slot print_timing: id 0 | task 13939 | graph reallocs = 0 / 0 (same size) / (changed size) 7.47.804.962 I slot release: id 0 | task 13939 | stop processing: n_tokens = 695, truncated = 0 7.47.812.383 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 695, t_last = 318825794511 7.47.812.463 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.345 MiB) 7.47.825.205 I slot launch_slot_: id 0 | task 14084 | processing task, is_child = 0 7.51.947.147 I slot print_timing: id 0 | task 14084 | n_gen = 106, tg = 34.92 t/s, tg_3s = 35.26 t/s 7.52.318.864 I slot print_timing: id 0 | task 14084 | prompt eval time = 1115.27 ms / 643 tokens ( 1.73 ms per token, 576.54 tokens per second) 7.52.318.871 I slot print_timing: id 0 | task 14084 | eval time = 3378.38 ms / 119 tokens ( 28.63 ms per token, 34.93 tokens per second) 7.52.318.872 I slot print_timing: id 0 | task 14084 | total time = 4493.65 ms / 762 tokens 7.52.318.872 I slot print_timing: id 0 | task 14084 | graphs reused = 13375 7.52.318.873 I slot print_timing: id 0 | task 14084 | graph reallocs = 0 / 0 (same size) / (changed size) 7.52.318.917 I slot release: id 0 | task 14084 | stop processing: n_tokens = 761, truncated = 0 7.52.325.195 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 761, t_last = 318830308465 7.52.325.293 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 146.624 MiB) 7.52.325.300 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 190.259 MiB) 7.52.341.071 I slot launch_slot_: id 0 | task 14207 | processing task, is_child = 0 7.55.191.755 I slot print_timing: id 0 | task 14207 | prompt eval time = 790.02 ms / 437 tokens ( 1.81 ms per token, 553.15 tokens per second) 7.55.191.759 I slot print_timing: id 0 | task 14207 | eval time = 2060.65 ms / 73 tokens ( 28.62 ms per token, 34.94 tokens per second) 7.55.191.759 I slot print_timing: id 0 | task 14207 | total time = 2850.67 ms / 510 tokens 7.55.191.760 I slot print_timing: id 0 | task 14207 | graphs reused = 13445 7.55.191.760 I slot print_timing: id 0 | task 14207 | graph reallocs = 0 / 0 (same size) / (changed size) 7.55.191.801 I slot release: id 0 | task 14207 | stop processing: n_tokens = 532, truncated = 0 7.55.198.632 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 532, t_last = 318833181349 7.55.204.051 I slot launch_slot_: id 0 | task 14283 | processing task, is_child = 0 7.59.096.140 I slot print_timing: id 0 | task 14283 | n_gen = 106, tg = 34.95 t/s, tg_3s = 35.28 t/s 8.00.784.386 I slot print_timing: id 0 | task 14283 | prompt eval time = 887.56 ms / 494 tokens ( 1.80 ms per token, 556.58 tokens per second) 8.00.784.393 I slot print_timing: id 0 | task 14283 | eval time = 4692.75 ms / 165 tokens ( 28.61 ms per token, 34.95 tokens per second) 8.00.784.393 I slot print_timing: id 0 | task 14283 | total time = 5580.32 ms / 659 tokens 8.00.784.394 I slot print_timing: id 0 | task 14283 | graphs reused = 13608 8.00.784.395 I slot print_timing: id 0 | task 14283 | graph reallocs = 0 / 0 (same size) / (changed size) 8.00.784.436 I slot release: id 0 | task 14283 | stop processing: n_tokens = 680, truncated = 0 8.00.789.938 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 680, t_last = 318838773984 8.00.790.018 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 130.872 MiB) 8.00.801.947 I slot launch_slot_: id 0 | task 14451 | processing task, is_child = 0 8.04.371.817 I slot print_timing: id 0 | task 14451 | n_gen = 107, tg = 35.13 t/s, tg_3s = 35.46 t/s 8.04.742.933 I slot print_timing: id 0 | task 14451 | prompt eval time = 552.12 ms / 304 tokens ( 1.82 ms per token, 550.60 tokens per second) 8.04.742.937 I slot print_timing: id 0 | task 14451 | eval time = 3388.85 ms / 120 tokens ( 28.48 ms per token, 35.12 tokens per second) 8.04.742.939 I slot print_timing: id 0 | task 14451 | total time = 3940.97 ms / 424 tokens 8.04.742.939 I slot print_timing: id 0 | task 14451 | graphs reused = 13726 8.04.742.940 I slot print_timing: id 0 | task 14451 | graph reallocs = 0 / 0 (same size) / (changed size) 8.04.742.974 I slot release: id 0 | task 14451 | stop processing: n_tokens = 444, truncated = 0 8.04.749.119 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 444, t_last = 318842732522 8.04.749.179 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 92.475 MiB) 8.04.755.443 I slot launch_slot_: id 0 | task 14574 | processing task, is_child = 0 8.08.463.720 I slot print_timing: id 0 | task 14574 | n_gen = 106, tg = 34.83 t/s, tg_3s = 35.16 t/s 8.10.706.947 I slot print_timing: id 0 | task 14574 | prompt eval time = 693.54 ms / 393 tokens ( 1.76 ms per token, 566.66 tokens per second) 8.10.706.953 I slot print_timing: id 0 | task 14574 | eval time = 5257.95 ms / 184 tokens ( 28.73 ms per token, 34.80 tokens per second) 8.10.706.954 I slot print_timing: id 0 | task 14574 | total time = 5951.49 ms / 577 tokens 8.10.706.955 I slot print_timing: id 0 | task 14574 | graphs reused = 13907 8.10.706.955 I slot print_timing: id 0 | task 14574 | graph reallocs = 0 / 0 (same size) / (changed size) 8.10.706.988 I slot release: id 0 | task 14574 | stop processing: n_tokens = 576, truncated = 0 8.10.714.802 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 576, t_last = 318848696536 8.10.722.061 I slot launch_slot_: id 0 | task 14761 | processing task, is_child = 0 8.14.949.365 I slot print_timing: id 0 | task 14761 | n_gen = 106, tg = 34.91 t/s, tg_3s = 35.24 t/s 8.17.953.389 I slot print_timing: id 0 | task 14761 | n_gen = 211, tg = 34.93 t/s, tg_3s = 34.95 t/s 8.19.671.517 I slot print_timing: id 0 | task 14761 | prompt eval time = 1219.55 ms / 695 tokens ( 1.75 ms per token, 569.88 tokens per second) 8.19.671.524 I slot print_timing: id 0 | task 14761 | eval time = 7729.90 ms / 271 tokens ( 28.63 ms per token, 34.93 tokens per second) 8.19.671.524 I slot print_timing: id 0 | task 14761 | total time = 8949.45 ms / 966 tokens 8.19.671.525 I slot print_timing: id 0 | task 14761 | graphs reused = 14175 8.19.671.525 I slot print_timing: id 0 | task 14761 | graph reallocs = 0 / 0 (same size) / (changed size) 8.19.671.585 I slot release: id 0 | task 14761 | stop processing: n_tokens = 965, truncated = 0 8.19.679.006 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 965, t_last = 318857661133 8.19.679.102 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.294 MiB) 8.19.679.106 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 151.124 MiB) 8.19.693.289 I slot launch_slot_: id 0 | task 15036 | processing task, is_child = 0 8.23.855.204 I slot print_timing: id 0 | task 15036 | n_gen = 106, tg = 34.96 t/s, tg_3s = 35.29 t/s 8.24.944.508 I slot print_timing: id 0 | task 15036 | prompt eval time = 1158.21 ms / 657 tokens ( 1.76 ms per token, 567.25 tokens per second) 8.24.944.511 I slot print_timing: id 0 | task 15036 | eval time = 4092.99 ms / 144 tokens ( 28.62 ms per token, 34.94 tokens per second) 8.24.944.512 I slot print_timing: id 0 | task 15036 | total time = 5251.21 ms / 801 tokens 8.24.944.513 I slot print_timing: id 0 | task 15036 | graphs reused = 14316 8.24.944.513 I slot print_timing: id 0 | task 15036 | graph reallocs = 0 / 0 (same size) / (changed size) 8.24.944.562 I slot release: id 0 | task 15036 | stop processing: n_tokens = 800, truncated = 0 8.24.949.646 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 8.24.949.734 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.781 MiB) 8.24.967.042 I slot launch_slot_: id 0 | task 15184 | processing task, is_child = 0 8.28.426.681 I slot print_timing: id 0 | task 15184 | n_gen = 108, tg = 35.35 t/s, tg_3s = 35.68 t/s 8.29.789.183 I slot print_timing: id 0 | task 15184 | prompt eval time = 433.06 ms / 231 tokens ( 1.87 ms per token, 533.42 tokens per second) 8.29.789.187 I slot print_timing: id 0 | task 15184 | eval time = 4389.07 ms / 156 tokens ( 28.32 ms per token, 35.31 tokens per second) 8.29.789.188 I slot print_timing: id 0 | task 15184 | total time = 4822.13 ms / 387 tokens 8.29.789.188 I slot print_timing: id 0 | task 15184 | graphs reused = 14469 8.29.789.189 I slot print_timing: id 0 | task 15184 | graph reallocs = 0 / 0 (same size) / (changed size) 8.29.789.217 I slot release: id 0 | task 15184 | stop processing: n_tokens = 386, truncated = 0 8.29.793.712 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.187 (> 0.100 thold), f_keep = 0.080 8.29.793.770 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 187.340 MiB) 8.29.797.955 I slot launch_slot_: id 0 | task 15343 | processing task, is_child = 0 8.33.129.366 I slot print_timing: id 0 | task 15343 | n_gen = 106, tg = 34.96 t/s, tg_3s = 35.29 t/s 8.34.972.009 I slot print_timing: id 0 | task 15343 | prompt eval time = 327.76 ms / 166 tokens ( 1.97 ms per token, 506.46 tokens per second) 8.34.972.013 I slot print_timing: id 0 | task 15343 | eval time = 4846.27 ms / 171 tokens ( 28.51 ms per token, 35.08 tokens per second) 8.34.972.013 I slot print_timing: id 0 | task 15343 | total time = 5174.04 ms / 337 tokens 8.34.972.014 I slot print_timing: id 0 | task 15343 | graphs reused = 14637 8.34.972.015 I slot print_timing: id 0 | task 15343 | graph reallocs = 0 / 0 (same size) / (changed size) 8.34.972.039 I slot release: id 0 | task 15343 | stop processing: n_tokens = 336, truncated = 0 8.34.976.457 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.160 (> 0.100 thold), f_keep = 0.092 8.34.979.511 I slot launch_slot_: id 0 | task 15517 | processing task, is_child = 0 8.38.399.818 I slot print_timing: id 0 | task 15517 | n_gen = 107, tg = 35.33 t/s, tg_3s = 35.66 t/s 8.41.408.023 I slot print_timing: id 0 | task 15517 | n_gen = 213, tg = 35.28 t/s, tg_3s = 35.24 t/s 8.43.691.886 I slot print_timing: id 0 | task 15517 | prompt eval time = 419.62 ms / 194 tokens ( 2.16 ms per token, 462.32 tokens per second) 8.43.691.890 I slot print_timing: id 0 | task 15517 | eval time = 8292.74 ms / 293 tokens ( 28.40 ms per token, 35.21 tokens per second) 8.43.691.890 I slot print_timing: id 0 | task 15517 | total time = 8712.36 ms / 487 tokens 8.43.691.891 I slot print_timing: id 0 | task 15517 | graphs reused = 14927 8.43.691.892 I slot print_timing: id 0 | task 15517 | graph reallocs = 0 / 0 (same size) / (changed size) 8.43.691.919 I slot release: id 0 | task 15517 | stop processing: n_tokens = 486, truncated = 0 8.43.696.441 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.208 (> 0.100 thold), f_keep = 0.064 8.43.696.507 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.726 MiB) 8.43.702.263 I slot launch_slot_: id 0 | task 15813 | processing task, is_child = 0 8.46.364.042 I slot print_timing: id 0 | task 15813 | prompt eval time = 326.93 ms / 149 tokens ( 2.19 ms per token, 455.75 tokens per second) 8.46.364.049 I slot print_timing: id 0 | task 15813 | eval time = 2334.83 ms / 84 tokens ( 28.13 ms per token, 35.55 tokens per second) 8.46.364.050 I slot print_timing: id 0 | task 15813 | total time = 2661.76 ms / 233 tokens 8.46.364.051 I slot print_timing: id 0 | task 15813 | graphs reused = 15009 8.46.364.051 I slot print_timing: id 0 | task 15813 | graph reallocs = 0 / 0 (same size) / (changed size) 8.46.364.073 I slot release: id 0 | task 15813 | stop processing: n_tokens = 232, truncated = 0 8.46.368.955 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 8.46.369.000 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 145.428 MiB) 8.46.375.031 I slot launch_slot_: id 0 | task 15900 | processing task, is_child = 0 8.49.851.763 I slot print_timing: id 0 | task 15900 | n_gen = 108, tg = 35.41 t/s, tg_3s = 35.74 t/s 8.52.865.965 I slot print_timing: id 0 | task 15900 | n_gen = 214, tg = 35.29 t/s, tg_3s = 35.17 t/s 8.53.921.470 I slot print_timing: id 0 | task 15900 | prompt eval time = 454.76 ms / 219 tokens ( 2.08 ms per token, 481.57 tokens per second) 8.53.921.476 I slot print_timing: id 0 | task 15900 | eval time = 7091.66 ms / 251 tokens ( 28.37 ms per token, 35.25 tokens per second) 8.53.921.477 I slot print_timing: id 0 | task 15900 | total time = 7546.43 ms / 470 tokens 8.53.921.478 I slot print_timing: id 0 | task 15900 | graphs reused = 15257 8.53.921.478 I slot print_timing: id 0 | task 15900 | graph reallocs = 0 / 0 (same size) / (changed size) 8.53.921.502 I slot release: id 0 | task 15900 | stop processing: n_tokens = 469, truncated = 0 8.53.925.842 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.227 (> 0.100 thold), f_keep = 0.064 8.53.936.825 I slot launch_slot_: id 0 | task 16154 | processing task, is_child = 0 8.54.597.981 I slot print_timing: id 0 | task 16154 | prompt eval time = 292.60 ms / 132 tokens ( 2.22 ms per token, 451.12 tokens per second) 8.54.597.985 I slot print_timing: id 0 | task 16154 | eval time = 368.54 ms / 14 tokens ( 28.35 ms per token, 35.27 tokens per second) 8.54.597.986 I slot print_timing: id 0 | task 16154 | total time = 661.14 ms / 146 tokens 8.54.597.987 I slot print_timing: id 0 | task 16154 | graphs reused = 15269 8.54.597.987 I slot print_timing: id 0 | task 16154 | graph reallocs = 0 / 0 (same size) / (changed size) 8.54.598.009 I slot release: id 0 | task 16154 | stop processing: n_tokens = 145, truncated = 0 8.54.602.600 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 8.54.602.634 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 136.004 MiB) 8.54.606.139 I slot launch_slot_: id 0 | task 16171 | processing task, is_child = 0 8.55.626.372 I slot print_timing: id 0 | task 16171 | prompt eval time = 329.14 ms / 169 tokens ( 1.95 ms per token, 513.45 tokens per second) 8.55.626.378 I slot print_timing: id 0 | task 16171 | eval time = 691.08 ms / 25 tokens ( 28.79 ms per token, 34.73 tokens per second) 8.55.626.379 I slot print_timing: id 0 | task 16171 | total time = 1020.22 ms / 194 tokens 8.55.626.380 I slot print_timing: id 0 | task 16171 | graphs reused = 15292 8.55.626.380 I slot print_timing: id 0 | task 16171 | graph reallocs = 0 / 0 (same size) / (changed size) 8.55.626.406 I slot release: id 0 | task 16171 | stop processing: n_tokens = 193, truncated = 0 8.55.630.605 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 8.55.636.703 I slot launch_slot_: id 0 | task 16199 | processing task, is_child = 0 8.58.977.405 I slot print_timing: id 0 | task 16199 | n_gen = 108, tg = 35.54 t/s, tg_3s = 35.87 t/s 9.00.190.346 I slot print_timing: id 0 | task 16199 | prompt eval time = 330.11 ms / 160 tokens ( 2.06 ms per token, 484.69 tokens per second) 9.00.190.349 I slot print_timing: id 0 | task 16199 | eval time = 4223.53 ms / 151 tokens ( 28.16 ms per token, 35.52 tokens per second) 9.00.190.350 I slot print_timing: id 0 | task 16199 | total time = 4553.63 ms / 311 tokens 9.00.190.351 I slot print_timing: id 0 | task 16199 | graphs reused = 15440 9.00.190.351 I slot print_timing: id 0 | task 16199 | graph reallocs = 0 / 0 (same size) / (changed size) 9.00.190.376 I slot release: id 0 | task 16199 | stop processing: n_tokens = 310, truncated = 0 9.00.194.556 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.291 (> 0.100 thold), f_keep = 0.097 9.00.194.606 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 172.220 MiB) 9.00.199.759 I slot launch_slot_: id 0 | task 16353 | processing task, is_child = 0 9.00.805.301 I slot print_timing: id 0 | task 16353 | prompt eval time = 239.47 ms / 103 tokens ( 2.32 ms per token, 430.11 tokens per second) 9.00.805.305 I slot print_timing: id 0 | task 16353 | eval time = 366.06 ms / 14 tokens ( 28.16 ms per token, 35.51 tokens per second) 9.00.805.305 I slot print_timing: id 0 | task 16353 | total time = 605.53 ms / 117 tokens 9.00.805.306 I slot print_timing: id 0 | task 16353 | graphs reused = 15452 9.00.805.307 I slot print_timing: id 0 | task 16353 | graph reallocs = 0 / 0 (same size) / (changed size) 9.00.805.328 I slot release: id 0 | task 16353 | stop processing: n_tokens = 116, truncated = 0 9.00.809.880 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 9.00.813.875 I slot launch_slot_: id 0 | task 16370 | processing task, is_child = 0 9.01.439.028 I slot print_timing: id 0 | task 16370 | prompt eval time = 368.74 ms / 165 tokens ( 2.23 ms per token, 447.47 tokens per second) 9.01.439.033 I slot print_timing: id 0 | task 16370 | eval time = 256.40 ms / 10 tokens ( 28.49 ms per token, 35.10 tokens per second) 9.01.439.033 I slot print_timing: id 0 | task 16370 | total time = 625.14 ms / 175 tokens 9.01.439.034 I slot print_timing: id 0 | task 16370 | graphs reused = 15460 9.01.439.034 I slot print_timing: id 0 | task 16370 | graph reallocs = 0 / 0 (same size) / (changed size) 9.01.439.056 I slot release: id 0 | task 16370 | stop processing: n_tokens = 174, truncated = 0 9.01.443.409 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 9.01.447.720 I slot launch_slot_: id 0 | task 16383 | processing task, is_child = 0 9.04.797.007 I slot print_timing: id 0 | task 16383 | n_gen = 108, tg = 35.50 t/s, tg_3s = 35.83 t/s 9.07.812.702 I slot print_timing: id 0 | task 16383 | n_gen = 214, tg = 35.32 t/s, tg_3s = 35.15 t/s 9.08.819.956 I slot print_timing: id 0 | task 16383 | prompt eval time = 335.18 ms / 165 tokens ( 2.03 ms per token, 492.27 tokens per second) 9.08.819.962 I slot print_timing: id 0 | task 16383 | eval time = 7037.04 ms / 249 tokens ( 28.38 ms per token, 35.24 tokens per second) 9.08.819.963 I slot print_timing: id 0 | task 16383 | total time = 7372.22 ms / 414 tokens 9.08.819.964 I slot print_timing: id 0 | task 16383 | graphs reused = 15706 9.08.819.964 I slot print_timing: id 0 | task 16383 | graph reallocs = 0 / 0 (same size) / (changed size) 9.08.819.991 I slot release: id 0 | task 16383 | stop processing: n_tokens = 413, truncated = 0 9.08.824.374 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.162 (> 0.100 thold), f_keep = 0.073 9.08.824.431 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 189.169 MiB) 9.08.830.141 I slot launch_slot_: id 0 | task 16635 | processing task, is_child = 0 9.12.254.595 I slot print_timing: id 0 | task 16635 | n_gen = 108, tg = 35.47 t/s, tg_3s = 35.80 t/s 9.14.405.569 I slot print_timing: id 0 | task 16635 | prompt eval time = 408.09 ms / 185 tokens ( 2.21 ms per token, 453.33 tokens per second) 9.14.405.573 I slot print_timing: id 0 | task 16635 | eval time = 5167.33 ms / 184 tokens ( 28.24 ms per token, 35.41 tokens per second) 9.14.405.573 I slot print_timing: id 0 | task 16635 | total time = 5575.41 ms / 369 tokens 9.14.405.574 I slot print_timing: id 0 | task 16635 | graphs reused = 15887 9.14.405.575 I slot print_timing: id 0 | task 16635 | graph reallocs = 0 / 0 (same size) / (changed size) 9.14.405.601 I slot release: id 0 | task 16635 | stop processing: n_tokens = 368, truncated = 0 9.14.410.061 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.082 9.14.417.732 I slot launch_slot_: id 0 | task 16822 | processing task, is_child = 0 9.16.039.353 I slot print_timing: id 0 | task 16822 | prompt eval time = 328.13 ms / 160 tokens ( 2.05 ms per token, 487.61 tokens per second) 9.16.039.357 I slot print_timing: id 0 | task 16822 | eval time = 1293.48 ms / 47 tokens ( 28.12 ms per token, 35.56 tokens per second) 9.16.039.358 I slot print_timing: id 0 | task 16822 | total time = 1621.61 ms / 207 tokens 9.16.039.358 I slot print_timing: id 0 | task 16822 | graphs reused = 15932 9.16.039.359 I slot print_timing: id 0 | task 16822 | graph reallocs = 0 / 0 (same size) / (changed size) 9.16.039.380 I slot release: id 0 | task 16822 | stop processing: n_tokens = 206, truncated = 0 9.16.043.931 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.191 (> 0.100 thold), f_keep = 0.146 9.16.048.385 I slot launch_slot_: id 0 | task 16872 | processing task, is_child = 0 9.19.390.195 I slot print_timing: id 0 | task 16872 | n_gen = 108, tg = 35.53 t/s, tg_3s = 35.86 t/s 9.22.411.545 I slot print_timing: id 0 | task 16872 | n_gen = 215, tg = 35.47 t/s, tg_3s = 35.41 t/s 9.25.421.210 I slot print_timing: id 0 | task 16872 | n_gen = 321, tg = 35.39 t/s, tg_3s = 35.22 t/s 9.28.422.946 I slot print_timing: id 0 | task 16872 | n_gen = 426, tg = 35.29 t/s, tg_3s = 34.98 t/s 9.31.432.408 I slot print_timing: id 0 | task 16872 | n_gen = 531, tg = 35.21 t/s, tg_3s = 34.89 t/s 9.34.457.596 I slot print_timing: id 0 | task 16872 | n_gen = 637, tg = 35.18 t/s, tg_3s = 35.04 t/s 9.35.943.116 I slot print_timing: id 0 | task 16872 | prompt eval time = 330.32 ms / 157 tokens ( 2.10 ms per token, 475.29 tokens per second) 9.35.943.122 I slot print_timing: id 0 | task 16872 | eval time = 19564.40 ms / 689 tokens ( 28.44 ms per token, 35.17 tokens per second) 9.35.943.122 I slot print_timing: id 0 | task 16872 | total time = 19894.72 ms / 846 tokens 9.35.943.123 I slot print_timing: id 0 | task 16872 | graphs reused = 16616 9.35.943.123 I slot print_timing: id 0 | task 16872 | graph reallocs = 0 / 0 (same size) / (changed size) 9.35.943.149 I slot release: id 0 | task 16872 | stop processing: n_tokens = 845, truncated = 0 9.35.947.681 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.036 9.35.947.766 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 72.539 MiB) 9.35.947.770 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 78.306 MiB) 9.35.959.358 I slot launch_slot_: id 0 | task 17564 | processing task, is_child = 0 9.39.309.242 I slot print_timing: id 0 | task 17564 | n_gen = 108, tg = 35.44 t/s, tg_3s = 35.78 t/s 9.42.337.288 I slot print_timing: id 0 | task 17564 | n_gen = 215, tg = 35.39 t/s, tg_3s = 35.34 t/s 9.45.350.123 I slot print_timing: id 0 | task 17564 | n_gen = 321, tg = 35.32 t/s, tg_3s = 35.18 t/s 9.48.372.991 I slot print_timing: id 0 | task 17564 | n_gen = 426, tg = 35.17 t/s, tg_3s = 34.74 t/s 9.49.883.156 I slot print_timing: id 0 | task 17564 | prompt eval time = 331.03 ms / 171 tokens ( 1.94 ms per token, 516.57 tokens per second) 9.49.883.161 I slot print_timing: id 0 | task 17564 | eval time = 13592.76 ms / 479 tokens ( 28.44 ms per token, 35.17 tokens per second) 9.49.883.163 I slot print_timing: id 0 | task 17564 | total time = 13923.78 ms / 650 tokens 9.49.883.164 I slot print_timing: id 0 | task 17564 | graphs reused = 17091 9.49.883.164 I slot print_timing: id 0 | task 17564 | graph reallocs = 0 / 0 (same size) / (changed size) 9.49.883.189 I slot release: id 0 | task 17564 | stop processing: n_tokens = 649, truncated = 0 9.49.887.935 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.164 (> 0.100 thold), f_keep = 0.046 9.49.888.011 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.954 MiB) 9.49.898.856 I slot launch_slot_: id 0 | task 18046 | processing task, is_child = 0 9.53.329.161 I slot print_timing: id 0 | task 18046 | n_gen = 108, tg = 35.45 t/s, tg_3s = 35.78 t/s 9.56.341.603 I slot print_timing: id 0 | task 18046 | n_gen = 214, tg = 35.32 t/s, tg_3s = 35.19 t/s 9.59.365.694 I slot print_timing: id 0 | task 18046 | n_gen = 318, tg = 35.01 t/s, tg_3s = 34.39 t/s 10.02.374.536 I slot print_timing: id 0 | task 18046 | n_gen = 422, tg = 34.90 t/s, tg_3s = 34.56 t/s 10.05.402.044 I slot print_timing: id 0 | task 18046 | n_gen = 527, tg = 34.86 t/s, tg_3s = 34.68 t/s 10.08.402.631 I slot print_timing: id 0 | task 18046 | n_gen = 630, tg = 34.77 t/s, tg_3s = 34.33 t/s 10.11.404.722 I slot print_timing: id 0 | task 18046 | n_gen = 735, tg = 34.80 t/s, tg_3s = 34.98 t/s 10.14.410.079 I slot print_timing: id 0 | task 18046 | n_gen = 840, tg = 34.81 t/s, tg_3s = 34.94 t/s 10.17.421.113 I slot print_timing: id 0 | task 18046 | n_gen = 945, tg = 34.82 t/s, tg_3s = 34.87 t/s 10.19.686.389 I slot print_timing: id 0 | task 18046 | prompt eval time = 412.11 ms / 183 tokens ( 2.25 ms per token, 444.06 tokens per second) 10.19.686.396 I slot print_timing: id 0 | task 18046 | eval time = 29375.41 ms / 1024 tokens ( 28.71 ms per token, 34.83 tokens per second) 10.19.686.397 I slot print_timing: id 0 | task 18046 | total time = 29787.52 ms / 1207 tokens 10.19.686.397 I slot print_timing: id 0 | task 18046 | graphs reused = 18109 10.19.686.398 I slot print_timing: id 0 | task 18046 | graph reallocs = 0 / 0 (same size) / (changed size) 10.19.686.421 I slot release: id 0 | task 18046 | stop processing: n_tokens = 1206, truncated = 0 10.19.691.021 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 10.19.691.128 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 64.452 MiB) 10.19.691.135 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 91.526 MiB) 10.19.705.009 I slot launch_slot_: id 0 | task 19073 | processing task, is_child = 0 10.23.058.340 I slot print_timing: id 0 | task 19073 | n_gen = 108, tg = 35.44 t/s, tg_3s = 35.77 t/s 10.26.073.820 I slot print_timing: id 0 | task 19073 | n_gen = 215, tg = 35.46 t/s, tg_3s = 35.48 t/s 10.29.088.702 I slot print_timing: id 0 | task 19073 | n_gen = 321, tg = 35.36 t/s, tg_3s = 35.16 t/s 10.32.105.458 I slot print_timing: id 0 | task 19073 | n_gen = 427, tg = 35.30 t/s, tg_3s = 35.14 t/s 10.35.127.021 I slot print_timing: id 0 | task 19073 | n_gen = 533, tg = 35.26 t/s, tg_3s = 35.08 t/s 10.38.135.866 I slot print_timing: id 0 | task 19073 | n_gen = 638, tg = 35.20 t/s, tg_3s = 34.90 t/s 10.38.310.059 I slot print_timing: id 0 | task 19073 | prompt eval time = 334.03 ms / 163 tokens ( 2.05 ms per token, 487.98 tokens per second) 10.38.310.063 I slot print_timing: id 0 | task 19073 | eval time = 18271.01 ms / 644 tokens ( 28.42 ms per token, 35.19 tokens per second) 10.38.310.063 I slot print_timing: id 0 | task 19073 | total time = 18605.04 ms / 807 tokens 10.38.310.064 I slot print_timing: id 0 | task 19073 | graphs reused = 18748 10.38.310.065 I slot print_timing: id 0 | task 19073 | graph reallocs = 0 / 0 (same size) / (changed size) 10.38.310.087 I slot release: id 0 | task 19073 | stop processing: n_tokens = 806, truncated = 0 10.38.314.764 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.169 (> 0.100 thold), f_keep = 0.037 10.38.314.850 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 96.414 MiB) 10.38.333.928 I slot launch_slot_: id 0 | task 19720 | processing task, is_child = 0 10.41.685.021 I slot print_timing: id 0 | task 19720 | n_gen = 108, tg = 35.48 t/s, tg_3s = 35.81 t/s 10.43.238.909 I slot print_timing: id 0 | task 19720 | prompt eval time = 335.43 ms / 177 tokens ( 1.90 ms per token, 527.68 tokens per second) 10.43.238.916 I slot print_timing: id 0 | task 19720 | eval time = 4569.53 ms / 163 tokens ( 28.21 ms per token, 35.45 tokens per second) 10.43.238.917 I slot print_timing: id 0 | task 19720 | total time = 4904.96 ms / 340 tokens 10.43.238.918 I slot print_timing: id 0 | task 19720 | graphs reused = 18908 10.43.238.918 I slot print_timing: id 0 | task 19720 | graph reallocs = 0 / 0 (same size) / (changed size) 10.43.238.945 I slot release: id 0 | task 19720 | stop processing: n_tokens = 339, truncated = 0 10.43.243.408 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.196 (> 0.100 thold), f_keep = 0.088 10.43.243.469 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 121.238 MiB) 10.43.246.543 I slot launch_slot_: id 0 | task 19886 | processing task, is_child = 0 10.46.588.147 I slot print_timing: id 0 | task 19886 | n_gen = 108, tg = 35.57 t/s, tg_3s = 35.91 t/s 10.46.616.395 I slot print_timing: id 0 | task 19886 | prompt eval time = 333.70 ms / 153 tokens ( 2.18 ms per token, 458.49 tokens per second) 10.46.616.399 I slot print_timing: id 0 | task 19886 | eval time = 3036.13 ms / 109 tokens ( 28.11 ms per token, 35.57 tokens per second) 10.46.616.399 I slot print_timing: id 0 | task 19886 | total time = 3369.84 ms / 262 tokens 10.46.616.400 I slot print_timing: id 0 | task 19886 | graphs reused = 19014 10.46.616.400 I slot print_timing: id 0 | task 19886 | graph reallocs = 0 / 0 (same size) / (changed size) 10.46.616.430 I slot release: id 0 | task 19886 | stop processing: n_tokens = 261, truncated = 0 10.46.620.866 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.217 (> 0.100 thold), f_keep = 0.115 10.46.623.394 I slot launch_slot_: id 0 | task 19998 | processing task, is_child = 0 10.47.753.180 I slot print_timing: id 0 | task 19998 | prompt eval time = 283.43 ms / 138 tokens ( 2.05 ms per token, 486.90 tokens per second) 10.47.753.186 I slot print_timing: id 0 | task 19998 | eval time = 846.35 ms / 31 tokens ( 28.21 ms per token, 35.45 tokens per second) 10.47.753.187 I slot print_timing: id 0 | task 19998 | total time = 1129.78 ms / 169 tokens 10.47.753.187 I slot print_timing: id 0 | task 19998 | graphs reused = 19043 10.47.753.188 I slot print_timing: id 0 | task 19998 | graph reallocs = 0 / 0 (same size) / (changed size) 10.47.753.214 I slot release: id 0 | task 19998 | stop processing: n_tokens = 168, truncated = 0 10.47.757.771 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 10.47.757.808 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 103.764 MiB) 10.47.759.879 I slot launch_slot_: id 0 | task 20032 | processing task, is_child = 0 10.51.108.169 I slot print_timing: id 0 | task 20032 | n_gen = 108, tg = 35.49 t/s, tg_3s = 35.82 t/s 10.52.632.543 I slot print_timing: id 0 | task 20032 | prompt eval time = 333.06 ms / 179 tokens ( 1.86 ms per token, 537.44 tokens per second) 10.52.632.547 I slot print_timing: id 0 | task 20032 | eval time = 4539.59 ms / 162 tokens ( 28.20 ms per token, 35.47 tokens per second) 10.52.632.547 I slot print_timing: id 0 | task 20032 | total time = 4872.65 ms / 341 tokens 10.52.632.548 I slot print_timing: id 0 | task 20032 | graphs reused = 19202 10.52.632.548 I slot print_timing: id 0 | task 20032 | graph reallocs = 0 / 0 (same size) / (changed size) 10.52.632.571 I slot release: id 0 | task 20032 | stop processing: n_tokens = 340, truncated = 0 10.52.637.556 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.169 (> 0.100 thold), f_keep = 0.100 10.52.637.634 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 103.060 MiB) 10.52.640.760 I slot launch_slot_: id 0 | task 20197 | processing task, is_child = 0 10.56.040.275 I slot print_timing: id 0 | task 20197 | n_gen = 108, tg = 35.48 t/s, tg_3s = 35.82 t/s 10.57.085.708 I slot print_timing: id 0 | task 20197 | prompt eval time = 384.06 ms / 201 tokens ( 1.91 ms per token, 523.36 tokens per second) 10.57.085.716 I slot print_timing: id 0 | task 20197 | eval time = 4060.88 ms / 145 tokens ( 28.20 ms per token, 35.46 tokens per second) 10.57.085.716 I slot print_timing: id 0 | task 20197 | total time = 4444.93 ms / 346 tokens 10.57.085.717 I slot print_timing: id 0 | task 20197 | graphs reused = 19344 10.57.085.718 I slot print_timing: id 0 | task 20197 | graph reallocs = 0 / 0 (same size) / (changed size) 10.57.085.743 I slot release: id 0 | task 20197 | stop processing: n_tokens = 345, truncated = 0 10.57.090.098 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.224 (> 0.100 thold), f_keep = 0.087 10.57.098.073 I slot launch_slot_: id 0 | task 20345 | processing task, is_child = 0 11.00.392.569 I slot print_timing: id 0 | task 20345 | n_gen = 108, tg = 35.59 t/s, tg_3s = 35.92 t/s 11.03.086.329 I slot print_timing: id 0 | task 20345 | prompt eval time = 287.77 ms / 134 tokens ( 2.15 ms per token, 465.65 tokens per second) 11.03.086.333 I slot print_timing: id 0 | task 20345 | eval time = 5700.48 ms / 203 tokens ( 28.22 ms per token, 35.44 tokens per second) 11.03.086.334 I slot print_timing: id 0 | task 20345 | total time = 5988.25 ms / 337 tokens 11.03.086.334 I slot print_timing: id 0 | task 20345 | graphs reused = 19544 11.03.086.335 I slot print_timing: id 0 | task 20345 | graph reallocs = 0 / 0 (same size) / (changed size) 11.03.086.359 I slot release: id 0 | task 20345 | stop processing: n_tokens = 336, truncated = 0 11.03.090.924 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.205 (> 0.100 thold), f_keep = 0.089 11.03.090.978 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 84.178 MiB) 11.03.106.010 I slot launch_slot_: id 0 | task 20551 | processing task, is_child = 0 11.03.939.827 I slot print_timing: id 0 | task 20551 | prompt eval time = 326.10 ms / 146 tokens ( 2.23 ms per token, 447.72 tokens per second) 11.03.939.840 I slot print_timing: id 0 | task 20551 | eval time = 507.70 ms / 19 tokens ( 28.21 ms per token, 35.45 tokens per second) 11.03.939.840 I slot print_timing: id 0 | task 20551 | total time = 833.80 ms / 165 tokens 11.03.939.841 I slot print_timing: id 0 | task 20551 | graphs reused = 19561 11.03.939.842 I slot print_timing: id 0 | task 20551 | graph reallocs = 0 / 0 (same size) / (changed size) 11.03.939.866 I slot release: id 0 | task 20551 | stop processing: n_tokens = 164, truncated = 0 11.03.944.087 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 11.03.944.126 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 131.612 MiB) 11.03.946.268 I slot launch_slot_: id 0 | task 20573 | processing task, is_child = 0 11.05.943.369 I slot print_timing: id 0 | task 20573 | prompt eval time = 284.27 ms / 138 tokens ( 2.06 ms per token, 485.45 tokens per second) 11.05.943.373 I slot print_timing: id 0 | task 20573 | eval time = 1712.81 ms / 62 tokens ( 28.08 ms per token, 35.61 tokens per second) 11.05.943.374 I slot print_timing: id 0 | task 20573 | total time = 1997.09 ms / 200 tokens 11.05.943.375 I slot print_timing: id 0 | task 20573 | graphs reused = 19621 11.05.943.375 I slot print_timing: id 0 | task 20573 | graph reallocs = 0 / 0 (same size) / (changed size) 11.05.943.404 I slot release: id 0 | task 20573 | stop processing: n_tokens = 199, truncated = 0 11.05.947.918 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.151 11.05.952.743 I slot launch_slot_: id 0 | task 20638 | processing task, is_child = 0 11.07.040.834 I slot print_timing: id 0 | task 20638 | prompt eval time = 341.72 ms / 155 tokens ( 2.20 ms per token, 453.59 tokens per second) 11.07.040.838 I slot print_timing: id 0 | task 20638 | eval time = 746.36 ms / 27 tokens ( 28.71 ms per token, 34.84 tokens per second) 11.07.040.839 I slot print_timing: id 0 | task 20638 | total time = 1088.08 ms / 182 tokens 11.07.040.840 I slot print_timing: id 0 | task 20638 | graphs reused = 19646 11.07.040.840 I slot print_timing: id 0 | task 20638 | graph reallocs = 0 / 0 (same size) / (changed size) 11.07.040.865 I slot release: id 0 | task 20638 | stop processing: n_tokens = 181, truncated = 0 11.07.045.563 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 11.07.045.633 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 114.945 MiB) 11.07.049.890 I slot launch_slot_: id 0 | task 20668 | processing task, is_child = 0 11.08.903.923 I slot print_timing: id 0 | task 20668 | prompt eval time = 329.66 ms / 160 tokens ( 2.06 ms per token, 485.35 tokens per second) 11.08.903.927 I slot print_timing: id 0 | task 20668 | eval time = 1524.36 ms / 54 tokens ( 28.76 ms per token, 34.77 tokens per second) 11.08.903.928 I slot print_timing: id 0 | task 20668 | total time = 1854.02 ms / 214 tokens 11.08.903.929 I slot print_timing: id 0 | task 20668 | graphs reused = 19698 11.08.903.929 I slot print_timing: id 0 | task 20668 | graph reallocs = 0 / 0 (same size) / (changed size) 11.08.903.958 I slot release: id 0 | task 20668 | stop processing: n_tokens = 213, truncated = 0 11.08.908.527 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.192 (> 0.100 thold), f_keep = 0.141 11.08.912.900 I slot launch_slot_: id 0 | task 20725 | processing task, is_child = 0 11.09.952.983 I slot print_timing: id 0 | task 20725 | prompt eval time = 329.88 ms / 156 tokens ( 2.11 ms per token, 472.89 tokens per second) 11.09.952.987 I slot print_timing: id 0 | task 20725 | eval time = 710.19 ms / 26 tokens ( 28.41 ms per token, 35.20 tokens per second) 11.09.952.988 I slot print_timing: id 0 | task 20725 | total time = 1040.07 ms / 182 tokens 11.09.952.988 I slot print_timing: id 0 | task 20725 | graphs reused = 19722 11.09.952.989 I slot print_timing: id 0 | task 20725 | graph reallocs = 0 / 0 (same size) / (changed size) 11.09.953.010 I slot release: id 0 | task 20725 | stop processing: n_tokens = 181, truncated = 0 11.09.957.377 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 11.09.957.422 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 94.058 MiB) 11.09.961.290 I slot launch_slot_: id 0 | task 20754 | processing task, is_child = 0 11.13.309.239 I slot print_timing: id 0 | task 20754 | n_gen = 108, tg = 35.43 t/s, tg_3s = 35.76 t/s 11.16.321.411 I slot print_timing: id 0 | task 20754 | n_gen = 215, tg = 35.48 t/s, tg_3s = 35.52 t/s 11.19.345.243 I slot print_timing: id 0 | task 20754 | n_gen = 321, tg = 35.34 t/s, tg_3s = 35.06 t/s 11.22.371.168 I slot print_timing: id 0 | task 20754 | n_gen = 426, tg = 35.18 t/s, tg_3s = 34.70 t/s 11.25.391.357 I slot print_timing: id 0 | task 20754 | n_gen = 532, tg = 35.16 t/s, tg_3s = 35.10 t/s 11.28.408.730 I slot print_timing: id 0 | task 20754 | n_gen = 637, tg = 35.10 t/s, tg_3s = 34.80 t/s 11.31.433.625 I slot print_timing: id 0 | task 20754 | n_gen = 743, tg = 35.09 t/s, tg_3s = 35.04 t/s 11.33.262.567 I slot print_timing: id 0 | task 20754 | prompt eval time = 327.79 ms / 158 tokens ( 2.07 ms per token, 482.02 tokens per second) 11.33.262.571 I slot print_timing: id 0 | task 20754 | eval time = 22973.48 ms / 807 tokens ( 28.50 ms per token, 35.08 tokens per second) 11.33.262.572 I slot print_timing: id 0 | task 20754 | total time = 23301.26 ms / 965 tokens 11.33.262.572 I slot print_timing: id 0 | task 20754 | graphs reused = 20524 11.33.262.573 I slot print_timing: id 0 | task 20754 | graph reallocs = 0 / 0 (same size) / (changed size) 11.33.262.596 I slot release: id 0 | task 20754 | stop processing: n_tokens = 964, truncated = 0 11.33.266.988 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.031 11.33.267.084 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 96.062 MiB) 11.33.284.057 I slot launch_slot_: id 0 | task 21564 | processing task, is_child = 0 11.36.606.400 I slot print_timing: id 0 | task 21564 | n_gen = 108, tg = 35.58 t/s, tg_3s = 35.91 t/s 11.37.876.877 I slot print_timing: id 0 | task 21564 | prompt eval time = 315.19 ms / 155 tokens ( 2.03 ms per token, 491.77 tokens per second) 11.37.876.883 I slot print_timing: id 0 | task 21564 | eval time = 4277.62 ms / 153 tokens ( 28.14 ms per token, 35.53 tokens per second) 11.37.876.883 I slot print_timing: id 0 | task 21564 | total time = 4592.81 ms / 308 tokens 11.37.876.884 I slot print_timing: id 0 | task 21564 | graphs reused = 20674 11.37.876.885 I slot print_timing: id 0 | task 21564 | graph reallocs = 0 / 0 (same size) / (changed size) 11.37.876.915 I slot release: id 0 | task 21564 | stop processing: n_tokens = 307, truncated = 0 11.37.881.409 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 11.37.881.457 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 88.081 MiB) 11.37.884.228 I slot launch_slot_: id 0 | task 21720 | processing task, is_child = 0 11.38.588.999 I slot print_timing: id 0 | task 21720 | prompt eval time = 335.51 ms / 170 tokens ( 1.97 ms per token, 506.69 tokens per second) 11.38.589.006 I slot print_timing: id 0 | task 21720 | eval time = 369.25 ms / 14 tokens ( 28.40 ms per token, 35.21 tokens per second) 11.38.589.006 I slot print_timing: id 0 | task 21720 | total time = 704.76 ms / 184 tokens 11.38.589.007 I slot print_timing: id 0 | task 21720 | graphs reused = 20686 11.38.589.008 I slot print_timing: id 0 | task 21720 | graph reallocs = 0 / 0 (same size) / (changed size) 11.38.589.034 I slot release: id 0 | task 21720 | stop processing: n_tokens = 183, truncated = 0 11.38.593.490 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 11.38.599.203 I slot launch_slot_: id 0 | task 21737 | processing task, is_child = 0 11.39.695.589 I slot print_timing: id 0 | task 21737 | prompt eval time = 333.21 ms / 160 tokens ( 2.08 ms per token, 480.18 tokens per second) 11.39.695.596 I slot print_timing: id 0 | task 21737 | eval time = 763.16 ms / 28 tokens ( 28.27 ms per token, 35.38 tokens per second) 11.39.695.597 I slot print_timing: id 0 | task 21737 | total time = 1096.37 ms / 188 tokens 11.39.695.598 I slot print_timing: id 0 | task 21737 | graphs reused = 20712 11.39.695.598 I slot print_timing: id 0 | task 21737 | graph reallocs = 0 / 0 (same size) / (changed size) 11.39.695.624 I slot release: id 0 | task 21737 | stop processing: n_tokens = 187, truncated = 0 11.39.700.137 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 11.39.700.178 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 118.742 MiB) 11.39.702.546 I slot launch_slot_: id 0 | task 21768 | processing task, is_child = 0 11.43.051.950 I slot print_timing: id 0 | task 21768 | n_gen = 108, tg = 35.49 t/s, tg_3s = 35.82 t/s 11.44.969.675 I slot print_timing: id 0 | task 21768 | prompt eval time = 334.14 ms / 161 tokens ( 2.08 ms per token, 481.84 tokens per second) 11.44.969.682 I slot print_timing: id 0 | task 21768 | eval time = 4932.98 ms / 176 tokens ( 28.19 ms per token, 35.48 tokens per second) 11.44.969.682 I slot print_timing: id 0 | task 21768 | total time = 5267.12 ms / 337 tokens 11.44.969.683 I slot print_timing: id 0 | task 21768 | graphs reused = 20885 11.44.969.683 I slot print_timing: id 0 | task 21768 | graph reallocs = 0 / 0 (same size) / (changed size) 11.44.969.709 I slot release: id 0 | task 21768 | stop processing: n_tokens = 336, truncated = 0 11.44.974.385 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.089 11.44.974.437 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 79.291 MiB) 11.44.977.496 I slot launch_slot_: id 0 | task 21947 | processing task, is_child = 0 11.48.311.078 I slot print_timing: id 0 | task 21947 | n_gen = 108, tg = 35.49 t/s, tg_3s = 35.82 t/s 11.50.732.734 I slot print_timing: id 0 | task 21947 | prompt eval time = 318.31 ms / 169 tokens ( 1.88 ms per token, 530.94 tokens per second) 11.50.732.737 I slot print_timing: id 0 | task 21947 | eval time = 5436.92 ms / 194 tokens ( 28.17 ms per token, 35.50 tokens per second) 11.50.732.738 I slot print_timing: id 0 | task 21947 | total time = 5755.23 ms / 363 tokens 11.50.732.739 I slot print_timing: id 0 | task 21947 | graphs reused = 21076 11.50.732.739 I slot print_timing: id 0 | task 21947 | graph reallocs = 0 / 0 (same size) / (changed size) 11.50.732.770 I slot release: id 0 | task 21947 | stop processing: n_tokens = 362, truncated = 0 11.50.737.472 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.164 (> 0.100 thold), f_keep = 0.083 11.50.737.527 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 67.160 MiB) 11.50.742.940 I slot launch_slot_: id 0 | task 22144 | processing task, is_child = 0 11.51.690.567 I slot print_timing: id 0 | task 22144 | prompt eval time = 410.66 ms / 183 tokens ( 2.24 ms per token, 445.62 tokens per second) 11.51.690.577 I slot print_timing: id 0 | task 22144 | eval time = 536.95 ms / 20 tokens ( 28.26 ms per token, 35.38 tokens per second) 11.51.690.578 I slot print_timing: id 0 | task 22144 | total time = 947.62 ms / 203 tokens 11.51.690.578 I slot print_timing: id 0 | task 22144 | graphs reused = 21094 11.51.690.579 I slot print_timing: id 0 | task 22144 | graph reallocs = 0 / 0 (same size) / (changed size) 11.51.690.603 I slot release: id 0 | task 22144 | stop processing: n_tokens = 202, truncated = 0 11.51.695.091 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 11.51.695.131 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 97.047 MiB) 11.51.697.731 I slot launch_slot_: id 0 | task 22167 | processing task, is_child = 0 11.55.053.612 I slot print_timing: id 0 | task 22167 | n_gen = 108, tg = 35.36 t/s, tg_3s = 35.69 t/s 11.56.548.754 I slot print_timing: id 0 | task 22167 | prompt eval time = 330.14 ms / 172 tokens ( 1.92 ms per token, 520.99 tokens per second) 11.56.548.758 I slot print_timing: id 0 | task 22167 | eval time = 4520.86 ms / 161 tokens ( 28.26 ms per token, 35.39 tokens per second) 11.56.548.759 I slot print_timing: id 0 | task 22167 | total time = 4851.01 ms / 333 tokens 11.56.548.760 I slot print_timing: id 0 | task 22167 | graphs reused = 21252 11.56.548.765 I slot print_timing: id 0 | task 22167 | graph reallocs = 0 / 0 (same size) / (changed size) 11.56.548.788 I slot release: id 0 | task 22167 | stop processing: n_tokens = 332, truncated = 0 11.56.553.635 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.165 (> 0.100 thold), f_keep = 0.090 11.56.560.814 I slot launch_slot_: id 0 | task 22331 | processing task, is_child = 0 11.59.955.240 I slot print_timing: id 0 | task 22331 | n_gen = 108, tg = 35.51 t/s, tg_3s = 35.84 t/s 12.02.977.487 I slot print_timing: id 0 | task 22331 | n_gen = 215, tg = 35.46 t/s, tg_3s = 35.40 t/s 12.05.996.646 I slot print_timing: id 0 | task 22331 | n_gen = 321, tg = 35.34 t/s, tg_3s = 35.11 t/s 12.09.001.329 I slot print_timing: id 0 | task 22331 | n_gen = 426, tg = 35.24 t/s, tg_3s = 34.95 t/s 12.12.024.384 I slot print_timing: id 0 | task 22331 | n_gen = 532, tg = 35.21 t/s, tg_3s = 35.06 t/s 12.12.763.793 I slot print_timing: id 0 | task 22331 | prompt eval time = 381.07 ms / 182 tokens ( 2.09 ms per token, 477.61 tokens per second) 12.12.763.800 I slot print_timing: id 0 | task 22331 | eval time = 15821.90 ms / 558 tokens ( 28.41 ms per token, 35.20 tokens per second) 12.12.763.801 I slot print_timing: id 0 | task 22331 | total time = 16202.97 ms / 740 tokens 12.12.763.802 I slot print_timing: id 0 | task 22331 | graphs reused = 21806 12.12.763.802 I slot print_timing: id 0 | task 22331 | graph reallocs = 0 / 0 (same size) / (changed size) 12.12.763.827 I slot release: id 0 | task 22331 | stop processing: n_tokens = 739, truncated = 0 12.12.768.803 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.045 12.12.768.890 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 119.060 MiB) 12.12.775.809 I slot launch_slot_: id 0 | task 22892 | processing task, is_child = 0 12.14.460.403 I slot print_timing: id 0 | task 22892 | prompt eval time = 388.87 ms / 181 tokens ( 2.15 ms per token, 465.45 tokens per second) 12.14.460.407 I slot print_timing: id 0 | task 22892 | eval time = 1295.71 ms / 47 tokens ( 28.17 ms per token, 35.50 tokens per second) 12.14.460.408 I slot print_timing: id 0 | task 22892 | total time = 1684.58 ms / 228 tokens 12.14.460.412 I slot print_timing: id 0 | task 22892 | graphs reused = 21851 12.14.460.412 I slot print_timing: id 0 | task 22892 | graph reallocs = 0 / 0 (same size) / (changed size) 12.14.460.439 I slot release: id 0 | task 22892 | stop processing: n_tokens = 227, truncated = 0 12.14.465.104 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 12.14.465.149 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 115.893 MiB) 12.14.469.522 I slot launch_slot_: id 0 | task 22942 | processing task, is_child = 0 12.17.920.724 I slot print_timing: id 0 | task 22942 | n_gen = 108, tg = 35.44 t/s, tg_3s = 35.77 t/s 12.18.316.480 I slot print_timing: id 0 | task 22942 | prompt eval time = 432.16 ms / 226 tokens ( 1.91 ms per token, 522.96 tokens per second) 12.18.316.484 I slot print_timing: id 0 | task 22942 | eval time = 3414.78 ms / 122 tokens ( 28.22 ms per token, 35.43 tokens per second) 12.18.316.485 I slot print_timing: id 0 | task 22942 | total time = 3846.94 ms / 348 tokens 12.18.316.486 I slot print_timing: id 0 | task 22942 | graphs reused = 21970 12.18.316.486 I slot print_timing: id 0 | task 22942 | graph reallocs = 0 / 0 (same size) / (changed size) 12.18.316.511 I slot release: id 0 | task 22942 | stop processing: n_tokens = 347, truncated = 0 12.18.320.794 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.189 (> 0.100 thold), f_keep = 0.086 12.18.320.847 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 117.864 MiB) 12.18.326.634 I slot launch_slot_: id 0 | task 23067 | processing task, is_child = 0 12.19.475.060 I slot print_timing: id 0 | task 23067 | prompt eval time = 331.63 ms / 159 tokens ( 2.09 ms per token, 479.45 tokens per second) 12.19.475.064 I slot print_timing: id 0 | task 23067 | eval time = 816.78 ms / 30 tokens ( 28.16 ms per token, 35.51 tokens per second) 12.19.475.064 I slot print_timing: id 0 | task 23067 | total time = 1148.42 ms / 189 tokens 12.19.475.065 I slot print_timing: id 0 | task 23067 | graphs reused = 21998 12.19.475.066 I slot print_timing: id 0 | task 23067 | graph reallocs = 0 / 0 (same size) / (changed size) 12.19.475.089 I slot release: id 0 | task 23067 | stop processing: n_tokens = 188, truncated = 0 12.19.826.931 I srv operator(): operator(): cleaning up before exit...