$ /Users/minipro/quantdiff/llama.cpp/llama-b11770/llama-server -m /Users/minipro/quantdiff/models/campaign/d1c03f73ecaf/LFM2.5-24B-A2B-QAD-Q4_0.gguf --host 127.0.0.1 --port 8089 -c 4096 -np 1 -ngl 999 -fa on --jinja --seed 1234 --no-webui -a quant 0.00.042.919 I srv llama_server: initializing ... 0.00.042.930 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.043.012 I srv init_listene: The UI is disabled 0.00.043.013 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.043.051 W srv llama_server: security: no API key is set and CORS allows all origins (see https://github.com/ggml-org/llama.cpp/pull/25655) 0.00.044.718 I srv load_model: loading model '/Users/minipro/quantdiff/models/campaign/d1c03f73ecaf/LFM2.5-24B-A2B-QAD-Q4_0.gguf' 0.00.977.898 I cmn init: llama threadpool init, n_threads = 8 0.01.189.417 I srv load_model: initializing, n_slots = 1, n_ctx_slot = 4096, kv_unified = 'false' 0.01.191.858 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.01.191.869 I srv llama_server: model loaded 0.01.191.872 I srv llama_server: listening on http://127.0.0.1:8089 0.02.021.697 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.02.021.926 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.04.251.559 I slot print_timing: id 0 | task 0 | prompt eval time = 350.65 ms / 172 tokens ( 2.04 ms per token, 490.52 tokens per second) 0.04.251.565 I slot print_timing: id 0 | task 0 | eval time = 1878.97 ms / 163 tokens ( 11.60 ms per token, 86.22 tokens per second) 0.04.251.565 I slot print_timing: id 0 | task 0 | total time = 2229.62 ms / 335 tokens 0.04.251.566 I slot print_timing: id 0 | task 0 | graphs reused = 161 0.04.251.566 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.04.251.626 I slot release: id 0 | task 0 | stop processing: n_tokens = 334, truncated = 0 0.04.254.931 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.063 0.04.255.812 I slot launch_slot_: id 0 | task 165 | processing task, is_child = 0 0.05.184.780 I slot print_timing: id 0 | task 165 | prompt eval time = 240.03 ms / 123 tokens ( 1.95 ms per token, 512.44 tokens per second) 0.05.184.787 I slot print_timing: id 0 | task 165 | eval time = 688.93 ms / 60 tokens ( 11.68 ms per token, 85.64 tokens per second) 0.05.184.788 I slot print_timing: id 0 | task 165 | total time = 928.96 ms / 183 tokens 0.05.184.788 I slot print_timing: id 0 | task 165 | graphs reused = 219 0.05.184.789 I slot print_timing: id 0 | task 165 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.184.819 I slot release: id 0 | task 165 | stop processing: n_tokens = 182, truncated = 0 0.05.188.048 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.129 (> 0.100 thold), f_keep = 0.115 0.05.188.382 I slot launch_slot_: id 0 | task 227 | processing task, is_child = 0 0.06.649.633 I slot print_timing: id 0 | task 227 | prompt eval time = 273.01 ms / 163 tokens ( 1.67 ms per token, 597.04 tokens per second) 0.06.649.639 I slot print_timing: id 0 | task 227 | eval time = 1188.23 ms / 103 tokens ( 11.65 ms per token, 85.84 tokens per second) 0.06.649.640 I slot print_timing: id 0 | task 227 | total time = 1461.24 ms / 266 tokens 0.06.649.640 I slot print_timing: id 0 | task 227 | graphs reused = 319 0.06.649.641 I slot print_timing: id 0 | task 227 | graph reallocs = 0 / 0 (same size) / (changed size) 0.06.649.665 I slot release: id 0 | task 227 | stop processing: n_tokens = 265, truncated = 0 0.06.652.894 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 0.06.653.191 I slot launch_slot_: id 0 | task 332 | processing task, is_child = 0 0.08.814.046 I slot print_timing: id 0 | task 332 | prompt eval time = 313.77 ms / 204 tokens ( 1.54 ms per token, 650.16 tokens per second) 0.08.814.048 I slot print_timing: id 0 | task 332 | eval time = 1847.07 ms / 160 tokens ( 11.62 ms per token, 86.08 tokens per second) 0.08.814.050 I slot print_timing: id 0 | task 332 | total time = 2160.85 ms / 364 tokens 0.08.814.050 I slot print_timing: id 0 | task 332 | graphs reused = 476 0.08.814.051 I slot print_timing: id 0 | task 332 | graph reallocs = 0 / 0 (same size) / (changed size) 0.08.814.086 I slot release: id 0 | task 332 | stop processing: n_tokens = 363, truncated = 0 0.08.817.292 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.187 (> 0.100 thold), f_keep = 0.099 0.08.818.197 I slot launch_slot_: id 0 | task 494 | processing task, is_child = 0 0.11.039.106 I slot print_timing: id 0 | task 494 | prompt eval time = 299.44 ms / 193 tokens ( 1.55 ms per token, 644.53 tokens per second) 0.11.039.109 I slot print_timing: id 0 | task 494 | eval time = 1921.46 ms / 166 tokens ( 11.65 ms per token, 85.87 tokens per second) 0.11.039.110 I slot print_timing: id 0 | task 494 | total time = 2220.90 ms / 359 tokens 0.11.039.110 I slot print_timing: id 0 | task 494 | graphs reused = 639 0.11.039.111 I slot print_timing: id 0 | task 494 | graph reallocs = 0 / 0 (same size) / (changed size) 0.11.039.142 I slot release: id 0 | task 494 | stop processing: n_tokens = 358, truncated = 0 0.11.042.346 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.121 (> 0.100 thold), f_keep = 0.059 0.11.043.251 I slot launch_slot_: id 0 | task 662 | processing task, is_child = 0 0.12.468.720 I slot print_timing: id 0 | task 662 | prompt eval time = 291.20 ms / 174 tokens ( 1.67 ms per token, 597.54 tokens per second) 0.12.468.726 I slot print_timing: id 0 | task 662 | eval time = 1134.26 ms / 98 tokens ( 11.69 ms per token, 85.52 tokens per second) 0.12.468.727 I slot print_timing: id 0 | task 662 | total time = 1425.46 ms / 272 tokens 0.12.468.728 I slot print_timing: id 0 | task 662 | graphs reused = 734 0.12.468.728 I slot print_timing: id 0 | task 662 | graph reallocs = 0 / 0 (same size) / (changed size) 0.12.468.758 I slot release: id 0 | task 662 | stop processing: n_tokens = 271, truncated = 0 0.12.472.180 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 271, t_last = 346267454405 0.12.472.911 I slot launch_slot_: id 0 | task 762 | processing task, is_child = 0 0.15.025.855 I slot print_timing: id 0 | task 762 | prompt eval time = 324.68 ms / 224 tokens ( 1.45 ms per token, 689.91 tokens per second) 0.15.025.861 I slot print_timing: id 0 | task 762 | eval time = 2228.26 ms / 192 tokens ( 11.67 ms per token, 85.72 tokens per second) 0.15.025.861 I slot print_timing: id 0 | task 762 | total time = 2552.94 ms / 416 tokens 0.15.025.862 I slot print_timing: id 0 | task 762 | graphs reused = 923 0.15.025.863 I slot print_timing: id 0 | task 762 | graph reallocs = 0 / 0 (same size) / (changed size) 0.15.025.888 I slot release: id 0 | task 762 | stop processing: n_tokens = 415, truncated = 0 0.15.029.294 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 415, t_last = 346270011535 0.15.030.242 I slot launch_slot_: id 0 | task 956 | processing task, is_child = 0 0.17.826.731 I slot print_timing: id 0 | task 956 | prompt eval time = 369.71 ms / 266 tokens ( 1.39 ms per token, 719.48 tokens per second) 0.17.826.737 I slot print_timing: id 0 | task 956 | eval time = 2426.77 ms / 210 tokens ( 11.61 ms per token, 86.12 tokens per second) 0.17.826.738 I slot print_timing: id 0 | task 956 | total time = 2796.48 ms / 476 tokens 0.17.826.739 I slot print_timing: id 0 | task 956 | graphs reused = 1131 0.17.826.739 I slot print_timing: id 0 | task 956 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.826.776 I slot release: id 0 | task 956 | stop processing: n_tokens = 475, truncated = 0 0.17.829.865 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.143 (> 0.100 thold), f_keep = 0.044 0.17.830.917 I slot launch_slot_: id 0 | task 1168 | processing task, is_child = 0 0.19.032.113 I slot print_timing: id 0 | task 1168 | prompt eval time = 265.40 ms / 147 tokens ( 1.81 ms per token, 553.88 tokens per second) 0.19.032.120 I slot print_timing: id 0 | task 1168 | eval time = 935.79 ms / 81 tokens ( 11.70 ms per token, 85.49 tokens per second) 0.19.032.121 I slot print_timing: id 0 | task 1168 | total time = 1201.18 ms / 228 tokens 0.19.032.122 I slot print_timing: id 0 | task 1168 | graphs reused = 1210 0.19.032.123 I slot print_timing: id 0 | task 1168 | graph reallocs = 0 / 0 (same size) / (changed size) 0.19.032.143 I slot release: id 0 | task 1168 | stop processing: n_tokens = 227, truncated = 0 0.19.035.333 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.127 (> 0.100 thold), f_keep = 0.093 0.19.035.964 I slot launch_slot_: id 0 | task 1251 | processing task, is_child = 0 0.20.848.364 I slot print_timing: id 0 | task 1251 | prompt eval time = 284.31 ms / 166 tokens ( 1.71 ms per token, 583.87 tokens per second) 0.20.848.371 I slot print_timing: id 0 | task 1251 | eval time = 1528.09 ms / 132 tokens ( 11.66 ms per token, 85.73 tokens per second) 0.20.848.372 I slot print_timing: id 0 | task 1251 | total time = 1812.39 ms / 298 tokens 0.20.848.372 I slot print_timing: id 0 | task 1251 | graphs reused = 1339 0.20.848.373 I slot print_timing: id 0 | task 1251 | graph reallocs = 0 / 0 (same size) / (changed size) 0.20.848.393 I slot release: id 0 | task 1251 | stop processing: n_tokens = 297, truncated = 0 0.20.851.653 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.120 (> 0.100 thold), f_keep = 0.071 0.20.852.414 I slot launch_slot_: id 0 | task 1385 | processing task, is_child = 0 0.22.884.372 I slot print_timing: id 0 | task 1385 | prompt eval time = 290.05 ms / 175 tokens ( 1.66 ms per token, 603.35 tokens per second) 0.22.884.378 I slot print_timing: id 0 | task 1385 | eval time = 1741.90 ms / 151 tokens ( 11.61 ms per token, 86.11 tokens per second) 0.22.884.379 I slot print_timing: id 0 | task 1385 | total time = 2031.95 ms / 326 tokens 0.22.884.380 I slot print_timing: id 0 | task 1385 | graphs reused = 1487 0.22.884.380 I slot print_timing: id 0 | task 1385 | graph reallocs = 0 / 0 (same size) / (changed size) 0.22.884.406 I slot release: id 0 | task 1385 | stop processing: n_tokens = 325, truncated = 0 0.22.887.649 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 325, t_last = 346277870053 0.22.888.475 I slot launch_slot_: id 0 | task 1538 | processing task, is_child = 0 0.24.780.070 I slot print_timing: id 0 | task 1538 | prompt eval time = 322.35 ms / 215 tokens ( 1.50 ms per token, 666.98 tokens per second) 0.24.780.075 I slot print_timing: id 0 | task 1538 | eval time = 1569.24 ms / 136 tokens ( 11.62 ms per token, 86.03 tokens per second) 0.24.780.075 I slot print_timing: id 0 | task 1538 | total time = 1891.59 ms / 351 tokens 0.24.780.076 I slot print_timing: id 0 | task 1538 | graphs reused = 1620 0.24.780.077 I slot print_timing: id 0 | task 1538 | graph reallocs = 0 / 0 (same size) / (changed size) 0.24.780.111 I slot release: id 0 | task 1538 | stop processing: n_tokens = 350, truncated = 0 0.24.783.306 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.119 (> 0.100 thold), f_keep = 0.060 0.24.784.172 I slot launch_slot_: id 0 | task 1676 | processing task, is_child = 0 0.26.231.620 I slot print_timing: id 0 | task 1676 | prompt eval time = 294.03 ms / 177 tokens ( 1.66 ms per token, 601.98 tokens per second) 0.26.231.623 I slot print_timing: id 0 | task 1676 | eval time = 1153.41 ms / 100 tokens ( 11.65 ms per token, 85.83 tokens per second) 0.26.231.623 I slot print_timing: id 0 | task 1676 | total time = 1447.44 ms / 277 tokens 0.26.231.624 I slot print_timing: id 0 | task 1676 | graphs reused = 1717 0.26.231.625 I slot print_timing: id 0 | task 1676 | graph reallocs = 0 / 0 (same size) / (changed size) 0.26.231.650 I slot release: id 0 | task 1676 | stop processing: n_tokens = 276, truncated = 0 0.26.234.630 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.116 (> 0.100 thold), f_keep = 0.076 0.26.235.389 I slot launch_slot_: id 0 | task 1778 | processing task, is_child = 0 0.27.372.319 I slot print_timing: id 0 | task 1778 | prompt eval time = 293.74 ms / 181 tokens ( 1.62 ms per token, 616.20 tokens per second) 0.27.372.324 I slot print_timing: id 0 | task 1778 | eval time = 843.18 ms / 73 tokens ( 11.71 ms per token, 85.39 tokens per second) 0.27.372.325 I slot print_timing: id 0 | task 1778 | total time = 1136.92 ms / 254 tokens 0.27.372.326 I slot print_timing: id 0 | task 1778 | graphs reused = 1788 0.27.372.326 I slot print_timing: id 0 | task 1778 | graph reallocs = 0 / 0 (same size) / (changed size) 0.27.372.358 I slot release: id 0 | task 1778 | stop processing: n_tokens = 253, truncated = 0 0.27.375.347 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.122 (> 0.100 thold), f_keep = 0.083 0.27.376.009 I slot launch_slot_: id 0 | task 1853 | processing task, is_child = 0 0.29.002.343 I slot print_timing: id 0 | task 1853 | prompt eval time = 290.17 ms / 172 tokens ( 1.69 ms per token, 592.76 tokens per second) 0.29.002.349 I slot print_timing: id 0 | task 1853 | eval time = 1336.16 ms / 116 tokens ( 11.62 ms per token, 86.07 tokens per second) 0.29.002.350 I slot print_timing: id 0 | task 1853 | total time = 1626.33 ms / 288 tokens 0.29.002.351 I slot print_timing: id 0 | task 1853 | graphs reused = 1901 0.29.002.351 I slot print_timing: id 0 | task 1853 | graph reallocs = 0 / 0 (same size) / (changed size) 0.29.002.374 I slot release: id 0 | task 1853 | stop processing: n_tokens = 287, truncated = 0 0.29.005.545 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.138 (> 0.100 thold), f_keep = 0.073 0.29.006.253 I slot launch_slot_: id 0 | task 1971 | processing task, is_child = 0 0.30.308.682 I slot print_timing: id 0 | task 1971 | prompt eval time = 265.06 ms / 152 tokens ( 1.74 ms per token, 573.47 tokens per second) 0.30.308.685 I slot print_timing: id 0 | task 1971 | eval time = 1037.37 ms / 90 tokens ( 11.66 ms per token, 85.79 tokens per second) 0.30.308.686 I slot print_timing: id 0 | task 1971 | total time = 1302.42 ms / 242 tokens 0.30.308.686 I slot print_timing: id 0 | task 1971 | graphs reused = 1989 0.30.308.687 I slot print_timing: id 0 | task 1971 | graph reallocs = 0 / 0 (same size) / (changed size) 0.30.308.717 I slot release: id 0 | task 1971 | stop processing: n_tokens = 241, truncated = 0 0.30.311.864 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.123 (> 0.100 thold), f_keep = 0.087 0.30.312.507 I slot launch_slot_: id 0 | task 2063 | processing task, is_child = 0 0.32.283.944 I slot print_timing: id 0 | task 2063 | prompt eval time = 288.20 ms / 171 tokens ( 1.69 ms per token, 593.33 tokens per second) 0.32.283.950 I slot print_timing: id 0 | task 2063 | eval time = 1683.22 ms / 146 tokens ( 11.61 ms per token, 86.14 tokens per second) 0.32.283.950 I slot print_timing: id 0 | task 2063 | total time = 1971.43 ms / 317 tokens 0.32.283.951 I slot print_timing: id 0 | task 2063 | graphs reused = 2132 0.32.283.951 I slot print_timing: id 0 | task 2063 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.283.972 I slot release: id 0 | task 2063 | stop processing: n_tokens = 316, truncated = 0 0.32.287.206 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.136 (> 0.100 thold), f_keep = 0.066 0.32.288.026 I slot launch_slot_: id 0 | task 2211 | processing task, is_child = 0 0.34.430.197 I slot print_timing: id 0 | task 2211 | prompt eval time = 270.35 ms / 154 tokens ( 1.76 ms per token, 569.63 tokens per second) 0.34.430.204 I slot print_timing: id 0 | task 2211 | eval time = 1871.81 ms / 161 tokens ( 11.70 ms per token, 85.48 tokens per second) 0.34.430.205 I slot print_timing: id 0 | task 2211 | total time = 2142.16 ms / 315 tokens 0.34.430.205 I slot print_timing: id 0 | task 2211 | graphs reused = 2290 0.34.430.206 I slot print_timing: id 0 | task 2211 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.430.224 I slot release: id 0 | task 2211 | stop processing: n_tokens = 314, truncated = 0 0.34.433.346 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.140 (> 0.100 thold), f_keep = 0.067 0.34.434.123 I slot launch_slot_: id 0 | task 2374 | processing task, is_child = 0 0.35.693.415 I slot print_timing: id 0 | task 2374 | prompt eval time = 265.72 ms / 150 tokens ( 1.77 ms per token, 564.50 tokens per second) 0.35.693.421 I slot print_timing: id 0 | task 2374 | eval time = 993.56 ms / 86 tokens ( 11.69 ms per token, 85.55 tokens per second) 0.35.693.422 I slot print_timing: id 0 | task 2374 | total time = 1259.28 ms / 236 tokens 0.35.693.423 I slot print_timing: id 0 | task 2374 | graphs reused = 2374 0.35.693.423 I slot print_timing: id 0 | task 2374 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.693.443 I slot release: id 0 | task 2374 | stop processing: n_tokens = 235, truncated = 0 0.35.696.685 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.111 (> 0.100 thold), f_keep = 0.089 0.35.697.349 I slot launch_slot_: id 0 | task 2462 | processing task, is_child = 0 0.37.481.363 I slot print_timing: id 0 | task 2462 | prompt eval time = 297.60 ms / 190 tokens ( 1.57 ms per token, 638.44 tokens per second) 0.37.481.369 I slot print_timing: id 0 | task 2462 | eval time = 1486.40 ms / 129 tokens ( 11.61 ms per token, 86.11 tokens per second) 0.37.481.370 I slot print_timing: id 0 | task 2462 | total time = 1784.00 ms / 319 tokens 0.37.481.371 I slot print_timing: id 0 | task 2462 | graphs reused = 2500 0.37.481.371 I slot print_timing: id 0 | task 2462 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.481.396 I slot release: id 0 | task 2462 | stop processing: n_tokens = 318, truncated = 0 0.37.484.540 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.131 (> 0.100 thold), f_keep = 0.066 0.37.485.324 I slot launch_slot_: id 0 | task 2593 | processing task, is_child = 0 0.39.025.065 I slot print_timing: id 0 | task 2593 | prompt eval time = 272.34 ms / 160 tokens ( 1.70 ms per token, 587.50 tokens per second) 0.39.025.068 I slot print_timing: id 0 | task 2593 | eval time = 1267.39 ms / 110 tokens ( 11.63 ms per token, 86.00 tokens per second) 0.39.025.068 I slot print_timing: id 0 | task 2593 | total time = 1539.73 ms / 270 tokens 0.39.025.069 I slot print_timing: id 0 | task 2593 | graphs reused = 2607 0.39.025.069 I slot print_timing: id 0 | task 2593 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.025.089 I slot release: id 0 | task 2593 | stop processing: n_tokens = 269, truncated = 0 0.39.028.258 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 269, t_last = 346294010736 0.39.028.972 I slot launch_slot_: id 0 | task 2705 | processing task, is_child = 0 0.40.552.350 I slot print_timing: id 0 | task 2705 | prompt eval time = 325.90 ms / 218 tokens ( 1.49 ms per token, 668.92 tokens per second) 0.40.552.356 I slot print_timing: id 0 | task 2705 | eval time = 1197.47 ms / 104 tokens ( 11.63 ms per token, 86.01 tokens per second) 0.40.552.356 I slot print_timing: id 0 | task 2705 | total time = 1523.37 ms / 322 tokens 0.40.552.357 I slot print_timing: id 0 | task 2705 | graphs reused = 2708 0.40.552.357 I slot print_timing: id 0 | task 2705 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.552.380 I slot release: id 0 | task 2705 | stop processing: n_tokens = 321, truncated = 0 0.40.555.558 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.109 (> 0.100 thold), f_keep = 0.065 0.40.556.351 I slot launch_slot_: id 0 | task 2811 | processing task, is_child = 0 0.43.470.139 I slot print_timing: id 0 | task 2811 | prompt eval time = 298.19 ms / 193 tokens ( 1.55 ms per token, 647.25 tokens per second) 0.43.470.142 I slot print_timing: id 0 | task 2811 | eval time = 2615.59 ms / 226 tokens ( 11.62 ms per token, 86.02 tokens per second) 0.43.470.143 I slot print_timing: id 0 | task 2811 | total time = 2913.78 ms / 419 tokens 0.43.470.144 I slot print_timing: id 0 | task 2811 | graphs reused = 2931 0.43.470.144 I slot print_timing: id 0 | task 2811 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.470.171 I slot release: id 0 | task 2811 | stop processing: n_tokens = 418, truncated = 0 0.43.473.425 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.104 (> 0.100 thold), f_keep = 0.050 0.43.474.482 I slot launch_slot_: id 0 | task 3039 | processing task, is_child = 0 0.46.786.677 I slot print_timing: id 0 | task 3039 | n_gen = 259, tg = 85.99 t/s, tg_3s = 86.32 t/s 0.47.838.391 I slot print_timing: id 0 | task 3039 | prompt eval time = 311.87 ms / 201 tokens ( 1.55 ms per token, 644.50 tokens per second) 0.47.838.397 I slot print_timing: id 0 | task 3039 | eval time = 4052.03 ms / 349 tokens ( 11.64 ms per token, 85.88 tokens per second) 0.47.838.397 I slot print_timing: id 0 | task 3039 | total time = 4363.90 ms / 550 tokens 0.47.838.398 I slot print_timing: id 0 | task 3039 | graphs reused = 3276 0.47.838.398 I slot print_timing: id 0 | task 3039 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.838.430 I slot release: id 0 | task 3039 | stop processing: n_tokens = 549, truncated = 0 0.47.841.744 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 346302824077 0.47.842.935 I slot launch_slot_: id 0 | task 3390 | processing task, is_child = 0 0.50.573.715 I slot print_timing: id 0 | task 3390 | prompt eval time = 344.56 ms / 237 tokens ( 1.45 ms per token, 687.84 tokens per second) 0.50.573.718 I slot print_timing: id 0 | task 3390 | eval time = 2386.21 ms / 206 tokens ( 11.64 ms per token, 85.91 tokens per second) 0.50.573.719 I slot print_timing: id 0 | task 3390 | total time = 2730.77 ms / 443 tokens 0.50.573.720 I slot print_timing: id 0 | task 3390 | graphs reused = 3479 0.50.573.720 I slot print_timing: id 0 | task 3390 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.573.746 I slot release: id 0 | task 3390 | stop processing: n_tokens = 442, truncated = 0 0.50.576.976 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.112 (> 0.100 thold), f_keep = 0.050 0.50.578.010 I slot launch_slot_: id 0 | task 3598 | processing task, is_child = 0 0.52.183.560 I slot print_timing: id 0 | task 3598 | prompt eval time = 301.56 ms / 196 tokens ( 1.54 ms per token, 649.94 tokens per second) 0.52.183.566 I slot print_timing: id 0 | task 3598 | eval time = 1303.98 ms / 113 tokens ( 11.64 ms per token, 85.89 tokens per second) 0.52.183.566 I slot print_timing: id 0 | task 3598 | total time = 1605.54 ms / 309 tokens 0.52.183.567 I slot print_timing: id 0 | task 3598 | graphs reused = 3589 0.52.183.568 I slot print_timing: id 0 | task 3598 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.183.601 I slot release: id 0 | task 3598 | stop processing: n_tokens = 308, truncated = 0 0.52.186.647 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.139 (> 0.100 thold), f_keep = 0.068 0.52.187.406 I slot launch_slot_: id 0 | task 3713 | processing task, is_child = 0 0.53.469.100 I slot print_timing: id 0 | task 3713 | prompt eval time = 272.06 ms / 151 tokens ( 1.80 ms per token, 555.02 tokens per second) 0.53.469.104 I slot print_timing: id 0 | task 3713 | eval time = 1009.62 ms / 88 tokens ( 11.60 ms per token, 86.17 tokens per second) 0.53.469.104 I slot print_timing: id 0 | task 3713 | total time = 1281.69 ms / 239 tokens 0.53.469.105 I slot print_timing: id 0 | task 3713 | graphs reused = 3675 0.53.469.106 I slot print_timing: id 0 | task 3713 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.469.123 I slot release: id 0 | task 3713 | stop processing: n_tokens = 238, truncated = 0 0.53.472.169 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.122 (> 0.100 thold), f_keep = 0.092 0.53.472.855 I slot launch_slot_: id 0 | task 3803 | processing task, is_child = 0 0.55.406.330 I slot print_timing: id 0 | task 3803 | prompt eval time = 295.09 ms / 180 tokens ( 1.64 ms per token, 609.98 tokens per second) 0.55.406.336 I slot print_timing: id 0 | task 3803 | eval time = 1638.37 ms / 142 tokens ( 11.62 ms per token, 86.06 tokens per second) 0.55.406.336 I slot print_timing: id 0 | task 3803 | total time = 1933.46 ms / 322 tokens 0.55.406.337 I slot print_timing: id 0 | task 3803 | graphs reused = 3814 0.55.406.338 I slot print_timing: id 0 | task 3803 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.406.362 I slot release: id 0 | task 3803 | stop processing: n_tokens = 321, truncated = 0 0.55.409.561 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 321, t_last = 346310392009 0.55.410.426 I slot launch_slot_: id 0 | task 3947 | processing task, is_child = 0 0.57.443.547 I slot print_timing: id 0 | task 3947 | prompt eval time = 322.84 ms / 211 tokens ( 1.53 ms per token, 653.57 tokens per second) 0.57.443.549 I slot print_timing: id 0 | task 3947 | eval time = 1710.27 ms / 148 tokens ( 11.63 ms per token, 85.95 tokens per second) 0.57.443.550 I slot print_timing: id 0 | task 3947 | total time = 2033.11 ms / 359 tokens 0.57.443.550 I slot print_timing: id 0 | task 3947 | graphs reused = 3959 0.57.443.551 I slot print_timing: id 0 | task 3947 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.443.579 I slot release: id 0 | task 3947 | stop processing: n_tokens = 358, truncated = 0 0.57.446.746 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.113 (> 0.100 thold), f_keep = 0.059 0.57.447.600 I slot launch_slot_: id 0 | task 4097 | processing task, is_child = 0 0.59.695.688 I slot print_timing: id 0 | task 4097 | prompt eval time = 300.96 ms / 186 tokens ( 1.62 ms per token, 618.03 tokens per second) 0.59.695.694 I slot print_timing: id 0 | task 4097 | eval time = 1947.12 ms / 168 tokens ( 11.66 ms per token, 85.77 tokens per second) 0.59.695.695 I slot print_timing: id 0 | task 4097 | total time = 2248.08 ms / 354 tokens 0.59.695.696 I slot print_timing: id 0 | task 4097 | graphs reused = 4124 0.59.695.696 I slot print_timing: id 0 | task 4097 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.695.721 I slot release: id 0 | task 4097 | stop processing: n_tokens = 353, truncated = 0 0.59.698.935 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.128 (> 0.100 thold), f_keep = 0.059 0.59.699.824 I slot launch_slot_: id 0 | task 4267 | processing task, is_child = 0 1.01.626.068 I slot print_timing: id 0 | task 4267 | prompt eval time = 276.55 ms / 164 tokens ( 1.69 ms per token, 593.03 tokens per second) 1.01.626.070 I slot print_timing: id 0 | task 4267 | eval time = 1649.68 ms / 143 tokens ( 11.62 ms per token, 86.08 tokens per second) 1.01.626.071 I slot print_timing: id 0 | task 4267 | total time = 1926.23 ms / 307 tokens 1.01.626.071 I slot print_timing: id 0 | task 4267 | graphs reused = 4264 1.01.626.074 I slot print_timing: id 0 | task 4267 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.626.094 I slot release: id 0 | task 4267 | stop processing: n_tokens = 306, truncated = 0 1.01.629.311 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.130 (> 0.100 thold), f_keep = 0.069 1.01.630.123 I slot launch_slot_: id 0 | task 4412 | processing task, is_child = 0 1.03.675.456 I slot print_timing: id 0 | task 4412 | prompt eval time = 276.45 ms / 162 tokens ( 1.71 ms per token, 586.00 tokens per second) 1.03.675.459 I slot print_timing: id 0 | task 4412 | eval time = 1768.87 ms / 153 tokens ( 11.64 ms per token, 85.93 tokens per second) 1.03.675.460 I slot print_timing: id 0 | task 4412 | total time = 2045.33 ms / 315 tokens 1.03.675.461 I slot print_timing: id 0 | task 4412 | graphs reused = 4414 1.03.675.461 I slot print_timing: id 0 | task 4412 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.675.481 I slot release: id 0 | task 4412 | stop processing: n_tokens = 314, truncated = 0 1.03.678.723 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.111 (> 0.100 thold), f_keep = 0.067 1.03.679.515 I slot launch_slot_: id 0 | task 4567 | processing task, is_child = 0 1.05.885.916 I slot print_timing: id 0 | task 4567 | prompt eval time = 300.86 ms / 190 tokens ( 1.58 ms per token, 631.53 tokens per second) 1.05.885.922 I slot print_timing: id 0 | task 4567 | eval time = 1905.54 ms / 165 tokens ( 11.62 ms per token, 86.07 tokens per second) 1.05.885.923 I slot print_timing: id 0 | task 4567 | total time = 2206.39 ms / 355 tokens 1.05.885.924 I slot print_timing: id 0 | task 4567 | graphs reused = 4576 1.05.885.925 I slot print_timing: id 0 | task 4567 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.885.947 I slot release: id 0 | task 4567 | stop processing: n_tokens = 354, truncated = 0 1.05.889.121 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.102 (> 0.100 thold), f_keep = 0.059 1.05.889.923 I slot launch_slot_: id 0 | task 4734 | processing task, is_child = 0 1.07.587.611 I slot print_timing: id 0 | task 4734 | prompt eval time = 318.31 ms / 206 tokens ( 1.55 ms per token, 647.16 tokens per second) 1.07.587.618 I slot print_timing: id 0 | task 4734 | eval time = 1379.37 ms / 119 tokens ( 11.69 ms per token, 85.55 tokens per second) 1.07.587.618 I slot print_timing: id 0 | task 4734 | total time = 1697.68 ms / 325 tokens 1.07.587.619 I slot print_timing: id 0 | task 4734 | graphs reused = 4692 1.07.587.619 I slot print_timing: id 0 | task 4734 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.587.640 I slot release: id 0 | task 4734 | stop processing: n_tokens = 324, truncated = 0 1.07.590.791 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.134 (> 0.100 thold), f_keep = 0.065 1.07.591.594 I slot launch_slot_: id 0 | task 4855 | processing task, is_child = 0 1.09.307.124 I slot print_timing: id 0 | task 4855 | prompt eval time = 272.15 ms / 157 tokens ( 1.73 ms per token, 576.90 tokens per second) 1.09.307.127 I slot print_timing: id 0 | task 4855 | eval time = 1443.37 ms / 125 tokens ( 11.64 ms per token, 85.91 tokens per second) 1.09.307.128 I slot print_timing: id 0 | task 4855 | total time = 1715.52 ms / 282 tokens 1.09.307.128 I slot print_timing: id 0 | task 4855 | graphs reused = 4814 1.09.307.129 I slot print_timing: id 0 | task 4855 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.307.153 I slot release: id 0 | task 4855 | stop processing: n_tokens = 281, truncated = 0 1.09.310.751 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.106 (> 0.100 thold), f_keep = 0.075 1.09.311.527 I slot launch_slot_: id 0 | task 4982 | processing task, is_child = 0 1.12.634.853 I slot print_timing: id 0 | task 4982 | n_gen = 259, tg = 85.75 t/s, tg_3s = 86.08 t/s 1.15.635.675 I slot print_timing: id 0 | task 4982 | n_gen = 516, tg = 85.70 t/s, tg_3s = 85.64 t/s 1.18.089.980 I slot print_timing: id 0 | task 4982 | prompt eval time = 314.62 ms / 198 tokens ( 1.59 ms per token, 629.33 tokens per second) 1.18.089.987 I slot print_timing: id 0 | task 4982 | eval time = 8463.82 ms / 726 tokens ( 11.67 ms per token, 85.66 tokens per second) 1.18.089.987 I slot print_timing: id 0 | task 4982 | total time = 8778.44 ms / 924 tokens 1.18.089.988 I slot print_timing: id 0 | task 4982 | graphs reused = 5535 1.18.089.989 I slot print_timing: id 0 | task 4982 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.090.020 I slot release: id 0 | task 4982 | stop processing: n_tokens = 923, truncated = 0 1.18.093.288 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.168 (> 0.100 thold), f_keep = 0.023 1.18.095.230 I slot launch_slot_: id 0 | task 5710 | processing task, is_child = 0 1.19.575.065 I slot print_timing: id 0 | task 5710 | prompt eval time = 250.68 ms / 125 tokens ( 2.01 ms per token, 498.65 tokens per second) 1.19.575.070 I slot print_timing: id 0 | task 5710 | eval time = 1229.15 ms / 107 tokens ( 11.60 ms per token, 86.24 tokens per second) 1.19.575.071 I slot print_timing: id 0 | task 5710 | total time = 1479.83 ms / 232 tokens 1.19.575.072 I slot print_timing: id 0 | task 5710 | graphs reused = 5640 1.19.575.072 I slot print_timing: id 0 | task 5710 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.575.092 I slot release: id 0 | task 5710 | stop processing: n_tokens = 231, truncated = 0 1.19.578.162 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.157 (> 0.100 thold), f_keep = 0.091 1.19.578.813 I slot launch_slot_: id 0 | task 5819 | processing task, is_child = 0 1.22.840.049 I slot print_timing: id 0 | task 5819 | n_gen = 259, tg = 85.95 t/s, tg_3s = 86.28 t/s 1.24.636.149 I slot print_timing: id 0 | task 5819 | prompt eval time = 259.37 ms / 134 tokens ( 1.94 ms per token, 516.64 tokens per second) 1.24.636.155 I slot print_timing: id 0 | task 5819 | eval time = 4797.96 ms / 413 tokens ( 11.65 ms per token, 85.87 tokens per second) 1.24.636.156 I slot print_timing: id 0 | task 5819 | total time = 5057.33 ms / 547 tokens 1.24.636.156 I slot print_timing: id 0 | task 5819 | graphs reused = 6049 1.24.636.157 I slot print_timing: id 0 | task 5819 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.636.175 I slot release: id 0 | task 5819 | stop processing: n_tokens = 546, truncated = 0 1.24.639.376 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.142 (> 0.100 thold), f_keep = 0.038 1.24.640.654 I slot launch_slot_: id 0 | task 6234 | processing task, is_child = 0 1.26.432.864 I slot print_timing: id 0 | task 6234 | prompt eval time = 269.35 ms / 148 tokens ( 1.82 ms per token, 549.48 tokens per second) 1.26.432.871 I slot print_timing: id 0 | task 6234 | eval time = 1522.85 ms / 132 tokens ( 11.62 ms per token, 86.02 tokens per second) 1.26.432.872 I slot print_timing: id 0 | task 6234 | total time = 1792.20 ms / 280 tokens 1.26.432.873 I slot print_timing: id 0 | task 6234 | graphs reused = 6178 1.26.432.873 I slot print_timing: id 0 | task 6234 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.432.893 I slot release: id 0 | task 6234 | stop processing: n_tokens = 279, truncated = 0 1.26.435.951 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.149 (> 0.100 thold), f_keep = 0.075 1.26.436.677 I slot launch_slot_: id 0 | task 6368 | processing task, is_child = 0 1.27.492.420 I slot print_timing: id 0 | task 6368 | prompt eval time = 262.84 ms / 141 tokens ( 1.86 ms per token, 536.45 tokens per second) 1.27.492.427 I slot print_timing: id 0 | task 6368 | eval time = 792.89 ms / 69 tokens ( 11.66 ms per token, 85.76 tokens per second) 1.27.492.427 I slot print_timing: id 0 | task 6368 | total time = 1055.73 ms / 210 tokens 1.27.492.428 I slot print_timing: id 0 | task 6368 | graphs reused = 6245 1.27.492.428 I slot print_timing: id 0 | task 6368 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.492.449 I slot release: id 0 | task 6368 | stop processing: n_tokens = 209, truncated = 0 1.27.495.493 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.107 (> 0.100 thold), f_keep = 0.100 1.27.496.053 I slot launch_slot_: id 0 | task 6439 | processing task, is_child = 0 1.29.135.928 I slot print_timing: id 0 | task 6439 | prompt eval time = 302.06 ms / 196 tokens ( 1.54 ms per token, 648.89 tokens per second) 1.29.135.934 I slot print_timing: id 0 | task 6439 | eval time = 1337.81 ms / 116 tokens ( 11.63 ms per token, 85.96 tokens per second) 1.29.135.935 I slot print_timing: id 0 | task 6439 | total time = 1639.87 ms / 312 tokens 1.29.135.937 I slot print_timing: id 0 | task 6439 | graphs reused = 6358 1.29.135.937 I slot print_timing: id 0 | task 6439 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.135.959 I slot release: id 0 | task 6439 | stop processing: n_tokens = 311, truncated = 0 1.29.139.359 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 311, t_last = 346344121606 1.29.140.100 I slot launch_slot_: id 0 | task 6557 | processing task, is_child = 0 1.31.911.216 I slot print_timing: id 0 | task 6557 | prompt eval time = 421.53 ms / 328 tokens ( 1.29 ms per token, 778.12 tokens per second) 1.31.911.222 I slot print_timing: id 0 | task 6557 | eval time = 2349.58 ms / 202 tokens ( 11.69 ms per token, 85.55 tokens per second) 1.31.911.223 I slot print_timing: id 0 | task 6557 | total time = 2771.11 ms / 530 tokens 1.31.911.224 I slot print_timing: id 0 | task 6557 | graphs reused = 6557 1.31.911.224 I slot print_timing: id 0 | task 6557 | graph reallocs = 0 / 0 (same size) / (changed size) 1.31.911.250 I slot release: id 0 | task 6557 | stop processing: n_tokens = 529, truncated = 0 1.31.914.265 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.143 (> 0.100 thold), f_keep = 0.040 1.31.915.391 I slot launch_slot_: id 0 | task 6761 | processing task, is_child = 0 1.33.018.313 I slot print_timing: id 0 | task 6761 | prompt eval time = 266.44 ms / 147 tokens ( 1.81 ms per token, 551.73 tokens per second) 1.33.018.319 I slot print_timing: id 0 | task 6761 | eval time = 836.48 ms / 73 tokens ( 11.62 ms per token, 86.08 tokens per second) 1.33.018.320 I slot print_timing: id 0 | task 6761 | total time = 1102.92 ms / 220 tokens 1.33.018.321 I slot print_timing: id 0 | task 6761 | graphs reused = 6628 1.33.018.321 I slot print_timing: id 0 | task 6761 | graph reallocs = 0 / 0 (same size) / (changed size) 1.33.018.342 I slot release: id 0 | task 6761 | stop processing: n_tokens = 219, truncated = 0 1.33.021.396 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.115 (> 0.100 thold), f_keep = 0.096 1.33.022.013 I slot launch_slot_: id 0 | task 6836 | processing task, is_child = 0 1.34.767.894 I slot print_timing: id 0 | task 6836 | prompt eval time = 294.57 ms / 182 tokens ( 1.62 ms per token, 617.84 tokens per second) 1.34.767.901 I slot print_timing: id 0 | task 6836 | eval time = 1451.30 ms / 125 tokens ( 11.70 ms per token, 85.44 tokens per second) 1.34.767.902 I slot print_timing: id 0 | task 6836 | total time = 1745.88 ms / 307 tokens 1.34.767.903 I slot print_timing: id 0 | task 6836 | graphs reused = 6750 1.34.767.904 I slot print_timing: id 0 | task 6836 | graph reallocs = 0 / 0 (same size) / (changed size) 1.34.767.923 I slot release: id 0 | task 6836 | stop processing: n_tokens = 306, truncated = 0 1.34.771.198 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 306, t_last = 346349753570 1.34.771.964 I slot launch_slot_: id 0 | task 6963 | processing task, is_child = 0 1.36.567.427 I slot print_timing: id 0 | task 6963 | prompt eval time = 338.67 ms / 230 tokens ( 1.47 ms per token, 679.13 tokens per second) 1.36.567.434 I slot print_timing: id 0 | task 6963 | eval time = 1456.78 ms / 126 tokens ( 11.65 ms per token, 85.81 tokens per second) 1.36.567.435 I slot print_timing: id 0 | task 6963 | total time = 1795.45 ms / 356 tokens 1.36.567.435 I slot print_timing: id 0 | task 6963 | graphs reused = 6873 1.36.567.436 I slot print_timing: id 0 | task 6963 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.567.458 I slot release: id 0 | task 6963 | stop processing: n_tokens = 355, truncated = 0 1.36.570.722 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 355, t_last = 346351553105 1.36.571.604 I slot launch_slot_: id 0 | task 7091 | processing task, is_child = 0 1.38.420.801 I slot print_timing: id 0 | task 7091 | prompt eval time = 344.48 ms / 239 tokens ( 1.44 ms per token, 693.81 tokens per second) 1.38.420.804 I slot print_timing: id 0 | task 7091 | eval time = 1504.71 ms / 130 tokens ( 11.66 ms per token, 85.73 tokens per second) 1.38.420.805 I slot print_timing: id 0 | task 7091 | total time = 1849.19 ms / 369 tokens 1.38.420.805 I slot print_timing: id 0 | task 7091 | graphs reused = 7000 1.38.420.806 I slot print_timing: id 0 | task 7091 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.420.832 I slot release: id 0 | task 7091 | stop processing: n_tokens = 368, truncated = 0 1.38.423.845 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.151 (> 0.100 thold), f_keep = 0.065 1.38.424.717 I slot launch_slot_: id 0 | task 7223 | processing task, is_child = 0 1.39.675.048 I slot print_timing: id 0 | task 7223 | prompt eval time = 270.50 ms / 159 tokens ( 1.70 ms per token, 587.79 tokens per second) 1.39.675.053 I slot print_timing: id 0 | task 7223 | eval time = 979.81 ms / 85 tokens ( 11.66 ms per token, 85.73 tokens per second) 1.39.675.053 I slot print_timing: id 0 | task 7223 | total time = 1250.32 ms / 244 tokens 1.39.675.054 I slot print_timing: id 0 | task 7223 | graphs reused = 7083 1.39.675.055 I slot print_timing: id 0 | task 7223 | graph reallocs = 0 / 0 (same size) / (changed size) 1.39.675.076 I slot release: id 0 | task 7223 | stop processing: n_tokens = 243, truncated = 0 1.39.678.163 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.125 (> 0.100 thold), f_keep = 0.086 1.39.678.879 I slot launch_slot_: id 0 | task 7310 | processing task, is_child = 0 1.41.730.280 I slot print_timing: id 0 | task 7310 | prompt eval time = 291.47 ms / 168 tokens ( 1.73 ms per token, 576.38 tokens per second) 1.41.730.285 I slot print_timing: id 0 | task 7310 | eval time = 1759.92 ms / 152 tokens ( 11.66 ms per token, 85.80 tokens per second) 1.41.730.287 I slot print_timing: id 0 | task 7310 | total time = 2051.39 ms / 320 tokens 1.41.730.287 I slot print_timing: id 0 | task 7310 | graphs reused = 7232 1.41.730.288 I slot print_timing: id 0 | task 7310 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.730.311 I slot release: id 0 | task 7310 | stop processing: n_tokens = 319, truncated = 0 1.41.733.358 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.119 (> 0.100 thold), f_keep = 0.066 1.41.734.148 I slot launch_slot_: id 0 | task 7464 | processing task, is_child = 0 1.43.356.473 I slot print_timing: id 0 | task 7464 | prompt eval time = 293.39 ms / 177 tokens ( 1.66 ms per token, 603.30 tokens per second) 1.43.356.478 I slot print_timing: id 0 | task 7464 | eval time = 1328.93 ms / 115 tokens ( 11.66 ms per token, 85.78 tokens per second) 1.43.356.479 I slot print_timing: id 0 | task 7464 | total time = 1622.32 ms / 292 tokens 1.43.356.480 I slot print_timing: id 0 | task 7464 | graphs reused = 7344 1.43.356.480 I slot print_timing: id 0 | task 7464 | graph reallocs = 0 / 0 (same size) / (changed size) 1.43.356.500 I slot release: id 0 | task 7464 | stop processing: n_tokens = 291, truncated = 0 1.43.359.761 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.101 (> 0.100 thold), f_keep = 0.072 1.43.360.537 I slot launch_slot_: id 0 | task 7581 | processing task, is_child = 0 1.45.205.682 I slot print_timing: id 0 | task 7581 | prompt eval time = 318.89 ms / 208 tokens ( 1.53 ms per token, 652.25 tokens per second) 1.45.205.689 I slot print_timing: id 0 | task 7581 | eval time = 1526.24 ms / 132 tokens ( 11.65 ms per token, 85.83 tokens per second) 1.45.205.689 I slot print_timing: id 0 | task 7581 | total time = 1845.14 ms / 340 tokens 1.45.205.690 I slot print_timing: id 0 | task 7581 | graphs reused = 7473 1.45.205.690 I slot print_timing: id 0 | task 7581 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.205.712 I slot release: id 0 | task 7581 | stop processing: n_tokens = 339, truncated = 0 1.45.208.772 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.131 (> 0.100 thold), f_keep = 0.062 1.45.209.559 I slot launch_slot_: id 0 | task 7715 | processing task, is_child = 0 1.46.829.510 I slot print_timing: id 0 | task 7715 | prompt eval time = 272.73 ms / 160 tokens ( 1.70 ms per token, 586.66 tokens per second) 1.46.829.515 I slot print_timing: id 0 | task 7715 | eval time = 1347.21 ms / 116 tokens ( 11.71 ms per token, 85.36 tokens per second) 1.46.829.516 I slot print_timing: id 0 | task 7715 | total time = 1619.94 ms / 276 tokens 1.46.829.517 I slot print_timing: id 0 | task 7715 | graphs reused = 7586 1.46.829.517 I slot print_timing: id 0 | task 7715 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.829.535 I slot release: id 0 | task 7715 | stop processing: n_tokens = 275, truncated = 0 1.46.832.834 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 275, t_last = 346361815182 1.46.833.538 I slot launch_slot_: id 0 | task 7833 | processing task, is_child = 0 1.48.777.145 I slot print_timing: id 0 | task 7833 | prompt eval time = 325.32 ms / 219 tokens ( 1.49 ms per token, 673.19 tokens per second) 1.48.777.151 I slot print_timing: id 0 | task 7833 | eval time = 1618.28 ms / 140 tokens ( 11.64 ms per token, 85.89 tokens per second) 1.48.777.152 I slot print_timing: id 0 | task 7833 | total time = 1943.60 ms / 359 tokens 1.48.777.152 I slot print_timing: id 0 | task 7833 | graphs reused = 7723 1.48.777.153 I slot print_timing: id 0 | task 7833 | graph reallocs = 0 / 0 (same size) / (changed size) 1.48.777.175 I slot release: id 0 | task 7833 | stop processing: n_tokens = 358, truncated = 0 1.48.780.511 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.124 (> 0.100 thold), f_keep = 0.059 1.48.781.466 I slot launch_slot_: id 0 | task 7975 | processing task, is_child = 0 1.50.412.503 I slot print_timing: id 0 | task 7975 | prompt eval time = 288.15 ms / 170 tokens ( 1.69 ms per token, 589.98 tokens per second) 1.50.412.509 I slot print_timing: id 0 | task 7975 | eval time = 1342.88 ms / 116 tokens ( 11.68 ms per token, 85.64 tokens per second) 1.50.412.510 I slot print_timing: id 0 | task 7975 | total time = 1631.03 ms / 286 tokens 1.50.412.510 I slot print_timing: id 0 | task 7975 | graphs reused = 7836 1.50.412.511 I slot print_timing: id 0 | task 7975 | graph reallocs = 0 / 0 (same size) / (changed size) 1.50.412.531 I slot release: id 0 | task 7975 | stop processing: n_tokens = 285, truncated = 0 1.50.415.673 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.124 (> 0.100 thold), f_keep = 0.074 1.50.416.466 I slot launch_slot_: id 0 | task 8093 | processing task, is_child = 0 1.51.670.787 I slot print_timing: id 0 | task 8093 | prompt eval time = 289.64 ms / 169 tokens ( 1.71 ms per token, 583.49 tokens per second) 1.51.670.790 I slot print_timing: id 0 | task 8093 | eval time = 964.67 ms / 84 tokens ( 11.62 ms per token, 86.04 tokens per second) 1.51.670.791 I slot print_timing: id 0 | task 8093 | total time = 1254.31 ms / 253 tokens 1.51.670.791 I slot print_timing: id 0 | task 8093 | graphs reused = 7918 1.51.670.792 I slot print_timing: id 0 | task 8093 | graph reallocs = 0 / 0 (same size) / (changed size) 1.51.670.814 I slot release: id 0 | task 8093 | stop processing: n_tokens = 252, truncated = 0 1.51.674.062 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 252, t_last = 346366656461 1.51.674.760 I slot launch_slot_: id 0 | task 8179 | processing task, is_child = 0 1.54.250.305 I slot print_timing: id 0 | task 8179 | prompt eval time = 383.55 ms / 287 tokens ( 1.34 ms per token, 748.27 tokens per second) 1.54.250.311 I slot print_timing: id 0 | task 8179 | eval time = 2191.99 ms / 189 tokens ( 11.66 ms per token, 85.77 tokens per second) 1.54.250.312 I slot print_timing: id 0 | task 8179 | total time = 2575.54 ms / 476 tokens 1.54.250.312 I slot print_timing: id 0 | task 8179 | graphs reused = 8105 1.54.250.313 I slot print_timing: id 0 | task 8179 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.250.338 I slot release: id 0 | task 8179 | stop processing: n_tokens = 475, truncated = 0 1.54.253.647 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 475, t_last = 346369235985 1.54.254.786 I slot launch_slot_: id 0 | task 8370 | processing task, is_child = 0 1.56.880.751 I slot print_timing: id 0 | task 8370 | prompt eval time = 354.23 ms / 255 tokens ( 1.39 ms per token, 719.87 tokens per second) 1.56.880.757 I slot print_timing: id 0 | task 8370 | eval time = 2271.73 ms / 196 tokens ( 11.65 ms per token, 85.84 tokens per second) 1.56.880.758 I slot print_timing: id 0 | task 8370 | total time = 2625.96 ms / 451 tokens 1.56.880.758 I slot print_timing: id 0 | task 8370 | graphs reused = 8298 1.56.880.759 I slot print_timing: id 0 | task 8370 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.880.782 I slot release: id 0 | task 8370 | stop processing: n_tokens = 450, truncated = 0 1.56.883.993 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.129 (> 0.100 thold), f_keep = 0.047 1.56.885.039 I slot launch_slot_: id 0 | task 8568 | processing task, is_child = 0 1.58.319.895 I slot print_timing: id 0 | task 8568 | prompt eval time = 275.82 ms / 163 tokens ( 1.69 ms per token, 590.97 tokens per second) 1.58.319.901 I slot print_timing: id 0 | task 8568 | eval time = 1159.03 ms / 100 tokens ( 11.71 ms per token, 85.42 tokens per second) 1.58.319.901 I slot print_timing: id 0 | task 8568 | total time = 1434.85 ms / 263 tokens 1.58.319.902 I slot print_timing: id 0 | task 8568 | graphs reused = 8395 1.58.319.902 I slot print_timing: id 0 | task 8568 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.319.922 I slot release: id 0 | task 8568 | stop processing: n_tokens = 262, truncated = 0 1.58.323.240 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.104 (> 0.100 thold), f_keep = 0.080 1.58.323.964 I slot launch_slot_: id 0 | task 8670 | processing task, is_child = 0 2.00.071.850 I slot print_timing: id 0 | task 8670 | prompt eval time = 315.34 ms / 201 tokens ( 1.57 ms per token, 637.40 tokens per second) 2.00.071.856 I slot print_timing: id 0 | task 8670 | eval time = 1432.54 ms / 124 tokens ( 11.65 ms per token, 85.86 tokens per second) 2.00.071.856 I slot print_timing: id 0 | task 8670 | total time = 1747.88 ms / 325 tokens 2.00.071.857 I slot print_timing: id 0 | task 8670 | graphs reused = 8516 2.00.071.857 I slot print_timing: id 0 | task 8670 | graph reallocs = 0 / 0 (same size) / (changed size) 2.00.071.879 I slot release: id 0 | task 8670 | stop processing: n_tokens = 324, truncated = 0 2.00.074.969 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.134 (> 0.100 thold), f_keep = 0.065 2.00.075.716 I slot launch_slot_: id 0 | task 8796 | processing task, is_child = 0 2.01.235.483 I slot print_timing: id 0 | task 8796 | prompt eval time = 270.17 ms / 157 tokens ( 1.72 ms per token, 581.11 tokens per second) 2.01.235.488 I slot print_timing: id 0 | task 8796 | eval time = 889.59 ms / 77 tokens ( 11.71 ms per token, 85.43 tokens per second) 2.01.235.489 I slot print_timing: id 0 | task 8796 | total time = 1159.76 ms / 234 tokens 2.01.235.490 I slot print_timing: id 0 | task 8796 | graphs reused = 8591 2.01.235.490 I slot print_timing: id 0 | task 8796 | graph reallocs = 0 / 0 (same size) / (changed size) 2.01.235.513 I slot release: id 0 | task 8796 | stop processing: n_tokens = 233, truncated = 0 2.01.238.550 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 233, t_last = 346376221160 2.01.239.217 I slot launch_slot_: id 0 | task 8875 | processing task, is_child = 0 2.03.244.062 I slot print_timing: id 0 | task 8875 | prompt eval time = 328.91 ms / 226 tokens ( 1.46 ms per token, 687.12 tokens per second) 2.03.244.068 I slot print_timing: id 0 | task 8875 | eval time = 1675.93 ms / 145 tokens ( 11.64 ms per token, 85.92 tokens per second) 2.03.244.068 I slot print_timing: id 0 | task 8875 | total time = 2004.84 ms / 371 tokens 2.03.244.069 I slot print_timing: id 0 | task 8875 | graphs reused = 8733 2.03.244.069 I slot print_timing: id 0 | task 8875 | graph reallocs = 0 / 0 (same size) / (changed size) 2.03.244.091 I slot release: id 0 | task 8875 | stop processing: n_tokens = 370, truncated = 0 2.03.247.660 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 370, t_last = 346378229738 2.03.248.527 I slot launch_slot_: id 0 | task 9022 | processing task, is_child = 0 2.05.037.618 I slot print_timing: id 0 | task 9022 | prompt eval time = 439.31 ms / 356 tokens ( 1.23 ms per token, 810.36 tokens per second) 2.05.037.625 I slot print_timing: id 0 | task 9022 | eval time = 1349.77 ms / 116 tokens ( 11.74 ms per token, 85.20 tokens per second) 2.05.037.626 I slot print_timing: id 0 | task 9022 | total time = 1789.08 ms / 472 tokens 2.05.037.626 I slot print_timing: id 0 | task 9022 | graphs reused = 8847 2.05.037.627 I slot print_timing: id 0 | task 9022 | graph reallocs = 0 / 0 (same size) / (changed size) 2.05.037.658 I slot release: id 0 | task 9022 | stop processing: n_tokens = 471, truncated = 0 2.05.041.200 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 471, t_last = 346380023305 2.05.042.282 I slot launch_slot_: id 0 | task 9140 | processing task, is_child = 0 2.08.519.091 I slot print_timing: id 0 | task 9140 | prompt eval time = 512.52 ms / 427 tokens ( 1.20 ms per token, 833.14 tokens per second) 2.08.519.094 I slot print_timing: id 0 | task 9140 | eval time = 2964.28 ms / 255 tokens ( 11.67 ms per token, 85.69 tokens per second) 2.08.519.095 I slot print_timing: id 0 | task 9140 | total time = 3476.80 ms / 682 tokens 2.08.519.096 I slot print_timing: id 0 | task 9140 | graphs reused = 9099 2.08.519.096 I slot print_timing: id 0 | task 9140 | graph reallocs = 0 / 0 (same size) / (changed size) 2.08.519.129 I slot release: id 0 | task 9140 | stop processing: n_tokens = 681, truncated = 0 2.08.523.044 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 681, t_last = 346383504776 2.08.524.601 I slot launch_slot_: id 0 | task 9397 | processing task, is_child = 0 2.10.752.442 I slot print_timing: id 0 | task 9397 | prompt eval time = 556.40 ms / 481 tokens ( 1.16 ms per token, 864.49 tokens per second) 2.10.752.448 I slot print_timing: id 0 | task 9397 | eval time = 1671.43 ms / 144 tokens ( 11.69 ms per token, 85.56 tokens per second) 2.10.752.449 I slot print_timing: id 0 | task 9397 | total time = 2227.83 ms / 625 tokens 2.10.752.449 I slot print_timing: id 0 | task 9397 | graphs reused = 9240 2.10.752.450 I slot print_timing: id 0 | task 9397 | graph reallocs = 0 / 0 (same size) / (changed size) 2.10.752.488 I slot release: id 0 | task 9397 | stop processing: n_tokens = 624, truncated = 0 2.10.756.281 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 624, t_last = 346385738135 2.10.757.703 I slot launch_slot_: id 0 | task 9543 | processing task, is_child = 0 2.13.109.365 I slot print_timing: id 0 | task 9543 | prompt eval time = 540.58 ms / 456 tokens ( 1.19 ms per token, 843.54 tokens per second) 2.13.109.371 I slot print_timing: id 0 | task 9543 | eval time = 1811.07 ms / 156 tokens ( 11.68 ms per token, 85.58 tokens per second) 2.13.109.372 I slot print_timing: id 0 | task 9543 | total time = 2351.65 ms / 612 tokens 2.13.109.373 I slot print_timing: id 0 | task 9543 | graphs reused = 9393 2.13.109.373 I slot print_timing: id 0 | task 9543 | graph reallocs = 0 / 0 (same size) / (changed size) 2.13.109.409 I slot release: id 0 | task 9543 | stop processing: n_tokens = 611, truncated = 0 2.13.112.835 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 611, t_last = 346388095056 2.13.114.204 I slot launch_slot_: id 0 | task 9701 | processing task, is_child = 0 2.14.508.829 I slot print_timing: id 0 | task 9701 | prompt eval time = 382.51 ms / 290 tokens ( 1.32 ms per token, 758.15 tokens per second) 2.14.508.835 I slot print_timing: id 0 | task 9701 | eval time = 1012.11 ms / 87 tokens ( 11.77 ms per token, 84.97 tokens per second) 2.14.508.835 I slot print_timing: id 0 | task 9701 | total time = 1394.62 ms / 377 tokens 2.14.508.836 I slot print_timing: id 0 | task 9701 | graphs reused = 9478 2.14.508.837 I slot print_timing: id 0 | task 9701 | graph reallocs = 0 / 0 (same size) / (changed size) 2.14.508.860 I slot release: id 0 | task 9701 | stop processing: n_tokens = 376, truncated = 0 2.14.512.448 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 376, t_last = 346389494507 2.14.513.328 I slot launch_slot_: id 0 | task 9790 | processing task, is_child = 0 2.18.032.397 I slot print_timing: id 0 | task 9790 | n_gen = 258, tg = 85.66 t/s, tg_3s = 85.99 t/s 2.18.243.310 I slot print_timing: id 0 | task 9790 | prompt eval time = 518.83 ms / 439 tokens ( 1.18 ms per token, 846.14 tokens per second) 2.18.243.315 I slot print_timing: id 0 | task 9790 | eval time = 3211.14 ms / 276 tokens ( 11.68 ms per token, 85.64 tokens per second) 2.18.243.316 I slot print_timing: id 0 | task 9790 | total time = 3729.97 ms / 715 tokens 2.18.243.317 I slot print_timing: id 0 | task 9790 | graphs reused = 9751 2.18.243.317 I slot print_timing: id 0 | task 9790 | graph reallocs = 0 / 0 (same size) / (changed size) 2.18.243.357 I slot release: id 0 | task 9790 | stop processing: n_tokens = 714, truncated = 0 2.18.246.917 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 714, t_last = 346393229004 2.18.248.556 I slot launch_slot_: id 0 | task 10068 | processing task, is_child = 0 2.21.734.594 I slot print_timing: id 0 | task 10068 | n_gen = 258, tg = 85.59 t/s, tg_3s = 85.93 t/s 2.24.739.119 I slot print_timing: id 0 | task 10068 | n_gen = 515, tg = 85.57 t/s, tg_3s = 85.54 t/s 2.27.153.358 I slot print_timing: id 0 | task 10068 | prompt eval time = 483.51 ms / 396 tokens ( 1.22 ms per token, 819.00 tokens per second) 2.27.153.360 I slot print_timing: id 0 | task 10068 | eval time = 8421.27 ms / 721 tokens ( 11.70 ms per token, 85.50 tokens per second) 2.27.153.361 I slot print_timing: id 0 | task 10068 | total time = 8904.79 ms / 1117 tokens 2.27.153.362 I slot print_timing: id 0 | task 10068 | graphs reused = 10467 2.27.153.362 I slot print_timing: id 0 | task 10068 | graph reallocs = 0 / 0 (same size) / (changed size) 2.27.153.393 I slot release: id 0 | task 10068 | stop processing: n_tokens = 1116, truncated = 0 2.27.157.093 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1116, t_last = 346402139040 2.27.159.563 I slot launch_slot_: id 0 | task 10791 | processing task, is_child = 0 2.28.594.655 I slot print_timing: id 0 | task 10791 | prompt eval time = 432.94 ms / 342 tokens ( 1.27 ms per token, 789.95 tokens per second) 2.28.594.665 I slot print_timing: id 0 | task 10791 | eval time = 1002.14 ms / 87 tokens ( 11.65 ms per token, 85.82 tokens per second) 2.28.594.665 I slot print_timing: id 0 | task 10791 | total time = 1435.08 ms / 429 tokens 2.28.594.666 I slot print_timing: id 0 | task 10791 | graphs reused = 10552 2.28.594.667 I slot print_timing: id 0 | task 10791 | graph reallocs = 0 / 0 (same size) / (changed size) 2.28.594.693 I slot release: id 0 | task 10791 | stop processing: n_tokens = 428, truncated = 0 2.28.598.107 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 428, t_last = 346403580340 2.28.599.108 I slot launch_slot_: id 0 | task 10880 | processing task, is_child = 0 2.30.009.386 I slot print_timing: id 0 | task 10880 | prompt eval time = 408.27 ms / 314 tokens ( 1.30 ms per token, 769.10 tokens per second) 2.30.009.392 I slot print_timing: id 0 | task 10880 | eval time = 1002.00 ms / 87 tokens ( 11.65 ms per token, 85.83 tokens per second) 2.30.009.392 I slot print_timing: id 0 | task 10880 | total time = 1410.27 ms / 401 tokens 2.30.009.393 I slot print_timing: id 0 | task 10880 | graphs reused = 10637 2.30.009.393 I slot print_timing: id 0 | task 10880 | graph reallocs = 0 / 0 (same size) / (changed size) 2.30.009.418 I slot release: id 0 | task 10880 | stop processing: n_tokens = 400, truncated = 0 2.30.012.966 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 346404995065 2.30.014.000 I slot launch_slot_: id 0 | task 10969 | processing task, is_child = 0 2.31.614.342 I slot print_timing: id 0 | task 10969 | prompt eval time = 485.53 ms / 396 tokens ( 1.23 ms per token, 815.61 tokens per second) 2.31.614.345 I slot print_timing: id 0 | task 10969 | eval time = 1114.81 ms / 96 tokens ( 11.73 ms per token, 85.22 tokens per second) 2.31.614.346 I slot print_timing: id 0 | task 10969 | total time = 1600.33 ms / 492 tokens 2.31.614.347 I slot print_timing: id 0 | task 10969 | graphs reused = 10731 2.31.614.347 I slot print_timing: id 0 | task 10969 | graph reallocs = 0 / 0 (same size) / (changed size) 2.31.614.376 I slot release: id 0 | task 10969 | stop processing: n_tokens = 491, truncated = 0 2.31.617.905 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 491, t_last = 346406600023 2.31.619.065 I slot launch_slot_: id 0 | task 11067 | processing task, is_child = 0 2.34.663.287 I slot print_timing: id 0 | task 11067 | prompt eval time = 430.83 ms / 339 tokens ( 1.27 ms per token, 786.85 tokens per second) 2.34.663.293 I slot print_timing: id 0 | task 11067 | eval time = 2613.38 ms / 225 tokens ( 11.67 ms per token, 85.71 tokens per second) 2.34.663.294 I slot print_timing: id 0 | task 11067 | total time = 3044.22 ms / 564 tokens 2.34.663.294 I slot print_timing: id 0 | task 11067 | graphs reused = 10953 2.34.663.295 I slot print_timing: id 0 | task 11067 | graph reallocs = 0 / 0 (same size) / (changed size) 2.34.663.323 I slot release: id 0 | task 11067 | stop processing: n_tokens = 563, truncated = 0 2.34.666.758 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 563, t_last = 346409648970 2.34.668.054 I slot launch_slot_: id 0 | task 11294 | processing task, is_child = 0 2.36.175.548 I slot print_timing: id 0 | task 11294 | prompt eval time = 371.32 ms / 267 tokens ( 1.39 ms per token, 719.05 tokens per second) 2.36.175.553 I slot print_timing: id 0 | task 11294 | eval time = 1136.16 ms / 98 tokens ( 11.71 ms per token, 85.37 tokens per second) 2.36.175.554 I slot print_timing: id 0 | task 11294 | total time = 1507.49 ms / 365 tokens 2.36.175.554 I slot print_timing: id 0 | task 11294 | graphs reused = 11049 2.36.175.555 I slot print_timing: id 0 | task 11294 | graph reallocs = 0 / 0 (same size) / (changed size) 2.36.175.578 I slot release: id 0 | task 11294 | stop processing: n_tokens = 364, truncated = 0 2.36.179.009 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 364, t_last = 346411161225 2.36.179.960 I slot launch_slot_: id 0 | task 11394 | processing task, is_child = 0 2.38.937.843 I slot print_timing: id 0 | task 11394 | prompt eval time = 453.87 ms / 360 tokens ( 1.26 ms per token, 793.18 tokens per second) 2.38.937.846 I slot print_timing: id 0 | task 11394 | eval time = 2304.01 ms / 198 tokens ( 11.70 ms per token, 85.50 tokens per second) 2.38.937.847 I slot print_timing: id 0 | task 11394 | total time = 2757.88 ms / 558 tokens 2.38.937.847 I slot print_timing: id 0 | task 11394 | graphs reused = 11244 2.38.937.848 I slot print_timing: id 0 | task 11394 | graph reallocs = 0 / 0 (same size) / (changed size) 2.38.937.877 I slot release: id 0 | task 11394 | stop processing: n_tokens = 557, truncated = 0 2.38.941.351 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 557, t_last = 346413923524 2.38.942.601 I slot launch_slot_: id 0 | task 11594 | processing task, is_child = 0 2.40.672.209 I slot print_timing: id 0 | task 11594 | prompt eval time = 396.16 ms / 296 tokens ( 1.34 ms per token, 747.18 tokens per second) 2.40.672.216 I slot print_timing: id 0 | task 11594 | eval time = 1333.44 ms / 115 tokens ( 11.70 ms per token, 85.49 tokens per second) 2.40.672.217 I slot print_timing: id 0 | task 11594 | total time = 1729.60 ms / 411 tokens 2.40.672.218 I slot print_timing: id 0 | task 11594 | graphs reused = 11357 2.40.672.218 I slot print_timing: id 0 | task 11594 | graph reallocs = 0 / 0 (same size) / (changed size) 2.40.672.242 I slot release: id 0 | task 11594 | stop processing: n_tokens = 410, truncated = 0 2.40.675.652 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 410, t_last = 346415657889 2.40.676.687 I slot launch_slot_: id 0 | task 11711 | processing task, is_child = 0 2.42.347.507 I slot print_timing: id 0 | task 11711 | prompt eval time = 376.85 ms / 275 tokens ( 1.37 ms per token, 729.74 tokens per second) 2.42.347.513 I slot print_timing: id 0 | task 11711 | eval time = 1293.96 ms / 112 tokens ( 11.66 ms per token, 85.78 tokens per second) 2.42.347.513 I slot print_timing: id 0 | task 11711 | total time = 1670.81 ms / 387 tokens 2.42.347.514 I slot print_timing: id 0 | task 11711 | graphs reused = 11467 2.42.347.515 I slot print_timing: id 0 | task 11711 | graph reallocs = 0 / 0 (same size) / (changed size) 2.42.347.540 I slot release: id 0 | task 11711 | stop processing: n_tokens = 386, truncated = 0 2.42.351.005 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 386, t_last = 346417333187 2.42.351.965 I slot launch_slot_: id 0 | task 11825 | processing task, is_child = 0 2.43.838.419 I slot print_timing: id 0 | task 11825 | prompt eval time = 382.03 ms / 287 tokens ( 1.33 ms per token, 751.25 tokens per second) 2.43.838.425 I slot print_timing: id 0 | task 11825 | eval time = 1104.41 ms / 95 tokens ( 11.75 ms per token, 85.11 tokens per second) 2.43.838.426 I slot print_timing: id 0 | task 11825 | total time = 1486.44 ms / 382 tokens 2.43.838.427 I slot print_timing: id 0 | task 11825 | graphs reused = 11560 2.43.838.427 I slot print_timing: id 0 | task 11825 | graph reallocs = 0 / 0 (same size) / (changed size) 2.43.838.460 I slot release: id 0 | task 11825 | stop processing: n_tokens = 381, truncated = 0 2.43.842.064 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 381, t_last = 346418824107 2.43.843.033 I slot launch_slot_: id 0 | task 11922 | processing task, is_child = 0 2.44.972.975 I slot print_timing: id 0 | task 11922 | prompt eval time = 372.43 ms / 266 tokens ( 1.40 ms per token, 714.23 tokens per second) 2.44.972.981 I slot print_timing: id 0 | task 11922 | eval time = 757.50 ms / 66 tokens ( 11.65 ms per token, 85.81 tokens per second) 2.44.972.982 I slot print_timing: id 0 | task 11922 | total time = 1129.93 ms / 332 tokens 2.44.972.983 I slot print_timing: id 0 | task 11922 | graphs reused = 11624 2.44.972.983 I slot print_timing: id 0 | task 11922 | graph reallocs = 0 / 0 (same size) / (changed size) 2.44.973.010 I slot release: id 0 | task 11922 | stop processing: n_tokens = 331, truncated = 0 2.44.976.734 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 331, t_last = 346419958658 2.44.977.633 I slot launch_slot_: id 0 | task 11990 | processing task, is_child = 0 2.46.673.407 I slot print_timing: id 0 | task 11990 | prompt eval time = 516.82 ms / 435 tokens ( 1.19 ms per token, 841.69 tokens per second) 2.46.673.413 I slot print_timing: id 0 | task 11990 | eval time = 1178.95 ms / 102 tokens ( 11.67 ms per token, 85.67 tokens per second) 2.46.673.414 I slot print_timing: id 0 | task 11990 | total time = 1695.77 ms / 537 tokens 2.46.673.414 I slot print_timing: id 0 | task 11990 | graphs reused = 11723 2.46.673.415 I slot print_timing: id 0 | task 11990 | graph reallocs = 0 / 0 (same size) / (changed size) 2.46.673.456 I slot release: id 0 | task 11990 | stop processing: n_tokens = 536, truncated = 0 2.46.676.902 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 536, t_last = 346421659103 2.46.678.108 I slot launch_slot_: id 0 | task 12094 | processing task, is_child = 0 2.48.476.174 I slot print_timing: id 0 | task 12094 | prompt eval time = 402.02 ms / 307 tokens ( 1.31 ms per token, 763.64 tokens per second) 2.48.476.177 I slot print_timing: id 0 | task 12094 | eval time = 1396.04 ms / 120 tokens ( 11.73 ms per token, 85.24 tokens per second) 2.48.476.178 I slot print_timing: id 0 | task 12094 | total time = 1798.06 ms / 427 tokens 2.48.476.178 I slot print_timing: id 0 | task 12094 | graphs reused = 11841 2.48.476.179 I slot print_timing: id 0 | task 12094 | graph reallocs = 0 / 0 (same size) / (changed size) 2.48.476.205 I slot release: id 0 | task 12094 | stop processing: n_tokens = 426, truncated = 0 2.48.480.461 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 346423461852 2.48.481.489 I slot launch_slot_: id 0 | task 12216 | processing task, is_child = 0 2.51.770.262 I slot print_timing: id 0 | task 12216 | prompt eval time = 836.58 ms / 675 tokens ( 1.24 ms per token, 806.86 tokens per second) 2.51.770.265 I slot print_timing: id 0 | task 12216 | eval time = 2452.18 ms / 211 tokens ( 11.68 ms per token, 85.64 tokens per second) 2.51.770.267 I slot print_timing: id 0 | task 12216 | total time = 3288.77 ms / 886 tokens 2.51.770.267 I slot print_timing: id 0 | task 12216 | graphs reused = 12049 2.51.770.268 I slot print_timing: id 0 | task 12216 | graph reallocs = 0 / 0 (same size) / (changed size) 2.51.770.316 I slot release: id 0 | task 12216 | stop processing: n_tokens = 885, truncated = 0 2.51.773.899 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 885, t_last = 346426755963 2.51.775.807 I slot launch_slot_: id 0 | task 12430 | processing task, is_child = 0 2.53.437.598 I slot print_timing: id 0 | task 12430 | prompt eval time = 383.85 ms / 287 tokens ( 1.34 ms per token, 747.70 tokens per second) 2.53.437.605 I slot print_timing: id 0 | task 12430 | eval time = 1277.93 ms / 111 tokens ( 11.62 ms per token, 86.08 tokens per second) 2.53.437.606 I slot print_timing: id 0 | task 12430 | total time = 1661.78 ms / 398 tokens 2.53.437.606 I slot print_timing: id 0 | task 12430 | graphs reused = 12158 2.53.437.607 I slot print_timing: id 0 | task 12430 | graph reallocs = 0 / 0 (same size) / (changed size) 2.53.437.641 I slot release: id 0 | task 12430 | stop processing: n_tokens = 397, truncated = 0 2.53.441.260 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 397, t_last = 346428423288 2.53.442.274 I slot launch_slot_: id 0 | task 12543 | processing task, is_child = 0 2.55.161.810 I slot print_timing: id 0 | task 12543 | prompt eval time = 573.24 ms / 497 tokens ( 1.15 ms per token, 867.00 tokens per second) 2.55.161.817 I slot print_timing: id 0 | task 12543 | eval time = 1146.29 ms / 99 tokens ( 11.70 ms per token, 85.49 tokens per second) 2.55.161.817 I slot print_timing: id 0 | task 12543 | total time = 1719.53 ms / 596 tokens 2.55.161.818 I slot print_timing: id 0 | task 12543 | graphs reused = 12254 2.55.161.819 I slot print_timing: id 0 | task 12543 | graph reallocs = 0 / 0 (same size) / (changed size) 2.55.161.855 I slot release: id 0 | task 12543 | stop processing: n_tokens = 595, truncated = 0 2.55.165.971 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 595, t_last = 346430147502 2.55.167.838 I slot launch_slot_: id 0 | task 12644 | processing task, is_child = 0 2.57.817.384 I slot print_timing: id 0 | task 12644 | prompt eval time = 779.88 ms / 609 tokens ( 1.28 ms per token, 780.89 tokens per second) 2.57.817.390 I slot print_timing: id 0 | task 12644 | eval time = 1869.66 ms / 161 tokens ( 11.69 ms per token, 85.58 tokens per second) 2.57.817.390 I slot print_timing: id 0 | task 12644 | total time = 2649.54 ms / 770 tokens 2.57.817.391 I slot print_timing: id 0 | task 12644 | graphs reused = 12412 2.57.817.391 I slot print_timing: id 0 | task 12644 | graph reallocs = 0 / 0 (same size) / (changed size) 2.57.817.435 I slot release: id 0 | task 12644 | stop processing: n_tokens = 769, truncated = 0 2.57.821.125 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 769, t_last = 346432803082 2.57.822.872 I slot launch_slot_: id 0 | task 12808 | processing task, is_child = 0 3.00.080.073 I slot print_timing: id 0 | task 12808 | prompt eval time = 495.56 ms / 415 tokens ( 1.19 ms per token, 837.44 tokens per second) 3.00.080.076 I slot print_timing: id 0 | task 12808 | eval time = 1761.63 ms / 152 tokens ( 11.67 ms per token, 85.72 tokens per second) 3.00.080.077 I slot print_timing: id 0 | task 12808 | total time = 2257.19 ms / 567 tokens 3.00.080.077 I slot print_timing: id 0 | task 12808 | graphs reused = 12561 3.00.080.078 I slot print_timing: id 0 | task 12808 | graph reallocs = 0 / 0 (same size) / (changed size) 3.00.080.111 I slot release: id 0 | task 12808 | stop processing: n_tokens = 566, truncated = 0 3.00.083.493 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 566, t_last = 346435065758 3.00.084.697 I slot launch_slot_: id 0 | task 12962 | processing task, is_child = 0 3.01.913.085 I slot print_timing: id 0 | task 12962 | prompt eval time = 395.94 ms / 295 tokens ( 1.34 ms per token, 745.07 tokens per second) 3.01.913.089 I slot print_timing: id 0 | task 12962 | eval time = 1432.44 ms / 124 tokens ( 11.65 ms per token, 85.87 tokens per second) 3.01.913.089 I slot print_timing: id 0 | task 12962 | total time = 1828.38 ms / 419 tokens 3.01.913.090 I slot print_timing: id 0 | task 12962 | graphs reused = 12683 3.01.913.090 I slot print_timing: id 0 | task 12962 | graph reallocs = 0 / 0 (same size) / (changed size) 3.01.913.118 I slot release: id 0 | task 12962 | stop processing: n_tokens = 418, truncated = 0 3.01.916.980 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 418, t_last = 346436898765 3.01.917.997 I slot launch_slot_: id 0 | task 13088 | processing task, is_child = 0 3.05.450.966 I slot print_timing: id 0 | task 13088 | n_gen = 259, tg = 85.67 t/s, tg_3s = 86.00 t/s 3.08.452.809 I slot print_timing: id 0 | task 13088 | n_gen = 516, tg = 85.64 t/s, tg_3s = 85.61 t/s 3.10.172.159 I slot print_timing: id 0 | task 13088 | prompt eval time = 521.31 ms / 442 tokens ( 1.18 ms per token, 847.87 tokens per second) 3.10.172.162 I slot print_timing: id 0 | task 13088 | eval time = 7732.85 ms / 663 tokens ( 11.68 ms per token, 85.61 tokens per second) 3.10.172.163 I slot print_timing: id 0 | task 13088 | total time = 8254.15 ms / 1105 tokens 3.10.172.164 I slot print_timing: id 0 | task 13088 | graphs reused = 13341 3.10.172.164 I slot print_timing: id 0 | task 13088 | graph reallocs = 0 / 0 (same size) / (changed size) 3.10.172.199 I slot release: id 0 | task 13088 | stop processing: n_tokens = 1104, truncated = 0 3.10.176.470 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1104, t_last = 346445157846 3.10.178.806 I slot launch_slot_: id 0 | task 13753 | processing task, is_child = 0 3.12.402.772 I slot print_timing: id 0 | task 13753 | prompt eval time = 798.35 ms / 622 tokens ( 1.28 ms per token, 779.10 tokens per second) 3.12.402.779 I slot print_timing: id 0 | task 13753 | eval time = 1425.61 ms / 123 tokens ( 11.69 ms per token, 85.58 tokens per second) 3.12.402.780 I slot print_timing: id 0 | task 13753 | total time = 2223.96 ms / 745 tokens 3.12.402.780 I slot print_timing: id 0 | task 13753 | graphs reused = 13462 3.12.402.781 I slot print_timing: id 0 | task 13753 | graph reallocs = 0 / 0 (same size) / (changed size) 3.12.402.828 I slot release: id 0 | task 13753 | stop processing: n_tokens = 744, truncated = 0 3.12.406.463 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 744, t_last = 346447388475 3.12.408.989 I slot launch_slot_: id 0 | task 13879 | processing task, is_child = 0 3.14.218.353 I slot print_timing: id 0 | task 13879 | prompt eval time = 510.82 ms / 424 tokens ( 1.20 ms per token, 830.04 tokens per second) 3.14.218.360 I slot print_timing: id 0 | task 13879 | eval time = 1298.53 ms / 112 tokens ( 11.70 ms per token, 85.48 tokens per second) 3.14.218.360 I slot print_timing: id 0 | task 13879 | total time = 1809.35 ms / 536 tokens 3.14.218.361 I slot print_timing: id 0 | task 13879 | graphs reused = 13571 3.14.218.362 I slot print_timing: id 0 | task 13879 | graph reallocs = 0 / 0 (same size) / (changed size) 3.14.218.395 I slot release: id 0 | task 13879 | stop processing: n_tokens = 535, truncated = 0 3.14.222.049 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 535, t_last = 346449204043 3.14.222.590 I slot launch_slot_: id 0 | task 13993 | processing task, is_child = 0 3.17.714.288 I slot print_timing: id 0 | task 13993 | n_gen = 259, tg = 85.79 t/s, tg_3s = 86.13 t/s 3.18.952.161 I slot print_timing: id 0 | task 13993 | prompt eval time = 484.52 ms / 395 tokens ( 1.23 ms per token, 815.24 tokens per second) 3.18.952.165 I slot print_timing: id 0 | task 13993 | eval time = 4245.05 ms / 365 tokens ( 11.66 ms per token, 85.75 tokens per second) 3.18.952.166 I slot print_timing: id 0 | task 13993 | total time = 4729.56 ms / 760 tokens 3.18.952.166 I slot print_timing: id 0 | task 13993 | graphs reused = 13933 3.18.952.167 I slot print_timing: id 0 | task 13993 | graph reallocs = 0 / 0 (same size) / (changed size) 3.18.952.202 I slot release: id 0 | task 13993 | stop processing: n_tokens = 759, truncated = 0 3.18.955.731 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 759, t_last = 346453937849 3.18.957.843 I slot launch_slot_: id 0 | task 14360 | processing task, is_child = 0 3.20.605.141 I slot print_timing: id 0 | task 14360 | prompt eval time = 379.91 ms / 279 tokens ( 1.36 ms per token, 734.38 tokens per second) 3.20.605.143 I slot print_timing: id 0 | task 14360 | eval time = 1267.38 ms / 110 tokens ( 11.63 ms per token, 86.00 tokens per second) 3.20.605.144 I slot print_timing: id 0 | task 14360 | total time = 1647.29 ms / 389 tokens 3.20.605.145 I slot print_timing: id 0 | task 14360 | graphs reused = 14041 3.20.605.145 I slot print_timing: id 0 | task 14360 | graph reallocs = 0 / 0 (same size) / (changed size) 3.20.605.170 I slot release: id 0 | task 14360 | stop processing: n_tokens = 388, truncated = 0 3.20.608.581 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 388, t_last = 346455590817 3.20.609.566 I slot launch_slot_: id 0 | task 14472 | processing task, is_child = 0 3.22.688.029 I slot print_timing: id 0 | task 14472 | prompt eval time = 412.27 ms / 319 tokens ( 1.29 ms per token, 773.77 tokens per second) 3.22.688.035 I slot print_timing: id 0 | task 14472 | eval time = 1666.18 ms / 144 tokens ( 11.65 ms per token, 85.82 tokens per second) 3.22.688.036 I slot print_timing: id 0 | task 14472 | total time = 2078.45 ms / 463 tokens 3.22.688.036 I slot print_timing: id 0 | task 14472 | graphs reused = 14183 3.22.688.037 I slot print_timing: id 0 | task 14472 | graph reallocs = 0 / 0 (same size) / (changed size) 3.22.688.064 I slot release: id 0 | task 14472 | stop processing: n_tokens = 462, truncated = 0 3.22.691.617 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 462, t_last = 346457673711 3.22.692.848 I slot launch_slot_: id 0 | task 14618 | processing task, is_child = 0 3.24.291.930 I slot print_timing: id 0 | task 14618 | prompt eval time = 435.07 ms / 345 tokens ( 1.26 ms per token, 792.98 tokens per second) 3.24.291.933 I slot print_timing: id 0 | task 14618 | eval time = 1164.00 ms / 101 tokens ( 11.64 ms per token, 85.91 tokens per second) 3.24.291.934 I slot print_timing: id 0 | task 14618 | total time = 1599.07 ms / 446 tokens 3.24.291.934 I slot print_timing: id 0 | task 14618 | graphs reused = 14282 3.24.291.935 I slot print_timing: id 0 | task 14618 | graph reallocs = 0 / 0 (same size) / (changed size) 3.24.291.980 I slot release: id 0 | task 14618 | stop processing: n_tokens = 445, truncated = 0 3.24.295.723 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 445, t_last = 346459277627 3.24.296.885 I slot launch_slot_: id 0 | task 14721 | processing task, is_child = 0 3.26.676.999 I slot print_timing: id 0 | task 14721 | prompt eval time = 546.91 ms / 464 tokens ( 1.18 ms per token, 848.41 tokens per second) 3.26.677.002 I slot print_timing: id 0 | task 14721 | eval time = 1833.20 ms / 158 tokens ( 11.68 ms per token, 85.64 tokens per second) 3.26.677.003 I slot print_timing: id 0 | task 14721 | total time = 2380.10 ms / 622 tokens 3.26.677.003 I slot print_timing: id 0 | task 14721 | graphs reused = 14437 3.26.677.004 I slot print_timing: id 0 | task 14721 | graph reallocs = 0 / 0 (same size) / (changed size) 3.26.677.044 I slot release: id 0 | task 14721 | stop processing: n_tokens = 621, truncated = 0 3.26.680.812 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 621, t_last = 346461662691 3.26.682.187 I slot launch_slot_: id 0 | task 14881 | processing task, is_child = 0 3.28.263.025 I slot print_timing: id 0 | task 14881 | prompt eval time = 486.62 ms / 398 tokens ( 1.22 ms per token, 817.88 tokens per second) 3.28.263.030 I slot print_timing: id 0 | task 14881 | eval time = 1094.20 ms / 95 tokens ( 11.64 ms per token, 85.91 tokens per second) 3.28.263.031 I slot print_timing: id 0 | task 14881 | total time = 1580.83 ms / 493 tokens 3.28.263.031 I slot print_timing: id 0 | task 14881 | graphs reused = 14530 3.28.263.032 I slot print_timing: id 0 | task 14881 | graph reallocs = 0 / 0 (same size) / (changed size) 3.28.263.067 I slot release: id 0 | task 14881 | stop processing: n_tokens = 492, truncated = 0 3.28.267.158 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 492, t_last = 346463248714 3.28.268.360 I slot launch_slot_: id 0 | task 14978 | processing task, is_child = 0 3.30.805.529 I slot print_timing: id 0 | task 14978 | prompt eval time = 802.32 ms / 628 tokens ( 1.28 ms per token, 782.73 tokens per second) 3.30.805.535 I slot print_timing: id 0 | task 14978 | eval time = 1734.84 ms / 149 tokens ( 11.72 ms per token, 85.31 tokens per second) 3.30.805.536 I slot print_timing: id 0 | task 14978 | total time = 2537.16 ms / 777 tokens 3.30.805.536 I slot print_timing: id 0 | task 14978 | graphs reused = 14676 3.30.805.537 I slot print_timing: id 0 | task 14978 | graph reallocs = 0 / 0 (same size) / (changed size) 3.30.805.579 I slot release: id 0 | task 14978 | stop processing: n_tokens = 776, truncated = 0 3.30.809.224 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 776, t_last = 346465791226 3.30.810.968 I slot launch_slot_: id 0 | task 15130 | processing task, is_child = 0 3.32.910.061 I slot print_timing: id 0 | task 15130 | prompt eval time = 489.76 ms / 404 tokens ( 1.21 ms per token, 824.89 tokens per second) 3.32.910.067 I slot print_timing: id 0 | task 15130 | eval time = 1609.32 ms / 139 tokens ( 11.66 ms per token, 85.75 tokens per second) 3.32.910.067 I slot print_timing: id 0 | task 15130 | total time = 2099.08 ms / 543 tokens 3.32.910.068 I slot print_timing: id 0 | task 15130 | graphs reused = 14812 3.32.910.068 I slot print_timing: id 0 | task 15130 | graph reallocs = 0 / 0 (same size) / (changed size) 3.32.910.107 I slot release: id 0 | task 15130 | stop processing: n_tokens = 542, truncated = 0 3.32.913.919 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 542, t_last = 346467895754 3.32.915.158 I slot launch_slot_: id 0 | task 15271 | processing task, is_child = 0 3.35.352.258 I slot print_timing: id 0 | task 15271 | prompt eval time = 524.12 ms / 445 tokens ( 1.18 ms per token, 849.05 tokens per second) 3.35.352.264 I slot print_timing: id 0 | task 15271 | eval time = 1912.97 ms / 165 tokens ( 11.66 ms per token, 85.73 tokens per second) 3.35.352.264 I slot print_timing: id 0 | task 15271 | total time = 2437.09 ms / 610 tokens 3.35.352.265 I slot print_timing: id 0 | task 15271 | graphs reused = 14974 3.35.352.265 I slot print_timing: id 0 | task 15271 | graph reallocs = 0 / 0 (same size) / (changed size) 3.35.352.299 I slot release: id 0 | task 15271 | stop processing: n_tokens = 609, truncated = 0 3.35.356.049 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 609, t_last = 346470337946 3.35.357.366 I slot launch_slot_: id 0 | task 15438 | processing task, is_child = 0 3.38.510.700 I slot print_timing: id 0 | task 15438 | prompt eval time = 494.26 ms / 412 tokens ( 1.20 ms per token, 833.56 tokens per second) 3.38.510.703 I slot print_timing: id 0 | task 15438 | eval time = 2659.06 ms / 228 tokens ( 11.71 ms per token, 85.37 tokens per second) 3.38.510.703 I slot print_timing: id 0 | task 15438 | total time = 3153.32 ms / 640 tokens 3.38.510.704 I slot print_timing: id 0 | task 15438 | graphs reused = 15199 3.38.510.704 I slot print_timing: id 0 | task 15438 | graph reallocs = 0 / 0 (same size) / (changed size) 3.38.510.739 I slot release: id 0 | task 15438 | stop processing: n_tokens = 639, truncated = 0 3.38.514.772 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 639, t_last = 346473496386 3.38.516.197 I slot launch_slot_: id 0 | task 15668 | processing task, is_child = 0 3.40.124.647 I slot print_timing: id 0 | task 15668 | prompt eval time = 685.09 ms / 542 tokens ( 1.26 ms per token, 791.14 tokens per second) 3.40.124.650 I slot print_timing: id 0 | task 15668 | eval time = 923.35 ms / 80 tokens ( 11.69 ms per token, 85.56 tokens per second) 3.40.124.651 I slot print_timing: id 0 | task 15668 | total time = 1608.44 ms / 622 tokens 3.40.124.651 I slot print_timing: id 0 | task 15668 | graphs reused = 15277 3.40.124.652 I slot print_timing: id 0 | task 15668 | graph reallocs = 0 / 0 (same size) / (changed size) 3.40.124.690 I slot release: id 0 | task 15668 | stop processing: n_tokens = 621, truncated = 0 3.40.128.916 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 621, t_last = 346475110337 3.40.130.284 I slot launch_slot_: id 0 | task 15751 | processing task, is_child = 0 3.42.780.967 I slot print_timing: id 0 | task 15751 | prompt eval time = 798.45 ms / 628 tokens ( 1.27 ms per token, 786.52 tokens per second) 3.42.780.973 I slot print_timing: id 0 | task 15751 | eval time = 1852.22 ms / 159 tokens ( 11.72 ms per token, 85.30 tokens per second) 3.42.780.973 I slot print_timing: id 0 | task 15751 | total time = 2650.67 ms / 787 tokens 3.42.780.974 I slot print_timing: id 0 | task 15751 | graphs reused = 15433 3.42.780.975 I slot print_timing: id 0 | task 15751 | graph reallocs = 0 / 0 (same size) / (changed size) 3.42.781.028 I slot release: id 0 | task 15751 | stop processing: n_tokens = 786, truncated = 0 3.42.784.255 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.107 (> 0.100 thold), f_keep = 0.027 3.42.786.008 I slot launch_slot_: id 0 | task 15913 | processing task, is_child = 0 3.45.424.397 I slot print_timing: id 0 | task 15913 | prompt eval time = 309.89 ms / 197 tokens ( 1.57 ms per token, 635.71 tokens per second) 3.45.424.400 I slot print_timing: id 0 | task 15913 | eval time = 2328.49 ms / 201 tokens ( 11.64 ms per token, 85.89 tokens per second) 3.45.424.401 I slot print_timing: id 0 | task 15913 | total time = 2638.38 ms / 398 tokens 3.45.424.401 I slot print_timing: id 0 | task 15913 | graphs reused = 15631 3.45.424.402 I slot print_timing: id 0 | task 15913 | graph reallocs = 0 / 0 (same size) / (changed size) 3.45.424.423 I slot release: id 0 | task 15913 | stop processing: n_tokens = 397, truncated = 0 3.45.427.645 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 397, t_last = 346480410070 3.45.428.602 I slot launch_slot_: id 0 | task 16116 | processing task, is_child = 0 3.47.369.314 I slot print_timing: id 0 | task 16116 | prompt eval time = 323.71 ms / 217 tokens ( 1.49 ms per token, 670.36 tokens per second) 3.47.369.320 I slot print_timing: id 0 | task 16116 | eval time = 1616.99 ms / 140 tokens ( 11.63 ms per token, 85.96 tokens per second) 3.47.369.320 I slot print_timing: id 0 | task 16116 | total time = 1940.70 ms / 357 tokens 3.47.369.321 I slot print_timing: id 0 | task 16116 | graphs reused = 15768 3.47.369.321 I slot print_timing: id 0 | task 16116 | graph reallocs = 0 / 0 (same size) / (changed size) 3.47.369.347 I slot release: id 0 | task 16116 | stop processing: n_tokens = 356, truncated = 0 3.47.372.537 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.105 (> 0.100 thold), f_keep = 0.059 3.47.373.378 I slot launch_slot_: id 0 | task 16258 | processing task, is_child = 0 3.50.293.328 I slot print_timing: id 0 | task 16258 | prompt eval time = 314.13 ms / 200 tokens ( 1.57 ms per token, 636.68 tokens per second) 3.50.293.331 I slot print_timing: id 0 | task 16258 | eval time = 2605.81 ms / 225 tokens ( 11.63 ms per token, 85.96 tokens per second) 3.50.293.332 I slot print_timing: id 0 | task 16258 | total time = 2919.94 ms / 425 tokens 3.50.293.332 I slot print_timing: id 0 | task 16258 | graphs reused = 15990 3.50.293.333 I slot print_timing: id 0 | task 16258 | graph reallocs = 0 / 0 (same size) / (changed size) 3.50.293.362 I slot release: id 0 | task 16258 | stop processing: n_tokens = 424, truncated = 0 3.50.296.659 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.124 (> 0.100 thold), f_keep = 0.050 3.50.297.728 I slot launch_slot_: id 0 | task 16485 | processing task, is_child = 0 3.53.497.489 I slot print_timing: id 0 | task 16485 | prompt eval time = 289.28 ms / 170 tokens ( 1.70 ms per token, 587.67 tokens per second) 3.53.497.492 I slot print_timing: id 0 | task 16485 | eval time = 2910.47 ms / 251 tokens ( 11.64 ms per token, 85.90 tokens per second) 3.53.497.493 I slot print_timing: id 0 | task 16485 | total time = 3199.75 ms / 421 tokens 3.53.497.493 I slot print_timing: id 0 | task 16485 | graphs reused = 16238 3.53.497.494 I slot print_timing: id 0 | task 16485 | graph reallocs = 0 / 0 (same size) / (changed size) 3.53.497.514 I slot release: id 0 | task 16485 | stop processing: n_tokens = 420, truncated = 0 3.53.500.807 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 420, t_last = 346488483161 3.53.501.869 I slot launch_slot_: id 0 | task 16738 | processing task, is_child = 0 3.56.857.820 I slot print_timing: id 0 | task 16738 | n_gen = 261, tg = 86.41 t/s, tg_3s = 86.74 t/s 3.59.859.145 I slot print_timing: id 0 | task 16738 | n_gen = 518, tg = 86.02 t/s, tg_3s = 85.63 t/s 4.00.641.392 I slot print_timing: id 0 | task 16738 | prompt eval time = 347.03 ms / 241 tokens ( 1.44 ms per token, 694.47 tokens per second) 4.00.641.395 I slot print_timing: id 0 | task 16738 | eval time = 6792.49 ms / 585 tokens ( 11.63 ms per token, 85.98 tokens per second) 4.00.641.396 I slot print_timing: id 0 | task 16738 | total time = 7139.52 ms / 826 tokens 4.00.641.396 I slot print_timing: id 0 | task 16738 | graphs reused = 16818 4.00.641.397 I slot print_timing: id 0 | task 16738 | graph reallocs = 0 / 0 (same size) / (changed size) 4.00.641.420 I slot release: id 0 | task 16738 | stop processing: n_tokens = 825, truncated = 0 4.00.644.759 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 825, t_last = 346495627067 4.00.646.522 I slot launch_slot_: id 0 | task 17325 | processing task, is_child = 0 4.03.997.687 I slot print_timing: id 0 | task 17325 | n_gen = 260, tg = 86.16 t/s, tg_3s = 86.49 t/s 4.04.197.017 I slot print_timing: id 0 | task 17325 | prompt eval time = 344.95 ms / 237 tokens ( 1.46 ms per token, 687.05 tokens per second) 4.04.197.023 I slot print_timing: id 0 | task 17325 | eval time = 3205.54 ms / 277 tokens ( 11.61 ms per token, 86.10 tokens per second) 4.04.197.024 I slot print_timing: id 0 | task 17325 | total time = 3550.49 ms / 514 tokens 4.04.197.024 I slot print_timing: id 0 | task 17325 | graphs reused = 17091 4.04.197.025 I slot print_timing: id 0 | task 17325 | graph reallocs = 0 / 0 (same size) / (changed size) 4.04.197.047 I slot release: id 0 | task 17325 | stop processing: n_tokens = 513, truncated = 0 4.04.200.444 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 513, t_last = 346499182694 4.04.201.632 I slot launch_slot_: id 0 | task 17604 | processing task, is_child = 0 4.07.617.963 I slot print_timing: id 0 | task 17604 | n_gen = 259, tg = 85.84 t/s, tg_3s = 86.18 t/s 4.08.444.516 I slot print_timing: id 0 | task 17604 | prompt eval time = 410.90 ms / 322 tokens ( 1.28 ms per token, 783.65 tokens per second) 4.08.444.519 I slot print_timing: id 0 | task 17604 | eval time = 3831.97 ms / 330 tokens ( 11.65 ms per token, 85.86 tokens per second) 4.08.444.519 I slot print_timing: id 0 | task 17604 | total time = 4242.87 ms / 652 tokens 4.08.444.520 I slot print_timing: id 0 | task 17604 | graphs reused = 17418 4.08.444.520 I slot print_timing: id 0 | task 17604 | graph reallocs = 0 / 0 (same size) / (changed size) 4.08.444.551 I slot release: id 0 | task 17604 | stop processing: n_tokens = 651, truncated = 0 4.08.447.832 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.120 (> 0.100 thold), f_keep = 0.032 4.08.449.235 I slot launch_slot_: id 0 | task 17936 | processing task, is_child = 0 4.11.741.318 I slot print_timing: id 0 | task 17936 | n_gen = 258, tg = 85.62 t/s, tg_3s = 85.95 t/s 4.12.416.977 I slot print_timing: id 0 | task 17936 | prompt eval time = 290.43 ms / 175 tokens ( 1.66 ms per token, 602.56 tokens per second) 4.12.416.983 I slot print_timing: id 0 | task 17936 | eval time = 3677.30 ms / 316 tokens ( 11.67 ms per token, 85.66 tokens per second) 4.12.416.984 I slot print_timing: id 0 | task 17936 | total time = 3967.73 ms / 491 tokens 4.12.416.984 I slot print_timing: id 0 | task 17936 | graphs reused = 17731 4.12.416.985 I slot print_timing: id 0 | task 17936 | graph reallocs = 0 / 0 (same size) / (changed size) 4.12.417.005 I slot release: id 0 | task 17936 | stop processing: n_tokens = 490, truncated = 0 4.12.420.251 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.117 (> 0.100 thold), f_keep = 0.043 4.12.421.361 I slot launch_slot_: id 0 | task 18254 | processing task, is_child = 0 4.14.885.477 I slot print_timing: id 0 | task 18254 | prompt eval time = 295.72 ms / 179 tokens ( 1.65 ms per token, 605.30 tokens per second) 4.14.885.480 I slot print_timing: id 0 | task 18254 | eval time = 2168.38 ms / 187 tokens ( 11.66 ms per token, 85.78 tokens per second) 4.14.885.481 I slot print_timing: id 0 | task 18254 | total time = 2464.10 ms / 366 tokens 4.14.885.481 I slot print_timing: id 0 | task 18254 | graphs reused = 17915 4.14.885.482 I slot print_timing: id 0 | task 18254 | graph reallocs = 0 / 0 (same size) / (changed size) 4.14.885.508 I slot release: id 0 | task 18254 | stop processing: n_tokens = 365, truncated = 0 4.14.888.671 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 365, t_last = 346509871155 4.14.890.203 I slot launch_slot_: id 0 | task 18443 | processing task, is_child = 0 4.17.892.639 I slot print_timing: id 0 | task 18443 | prompt eval time = 343.12 ms / 237 tokens ( 1.45 ms per token, 690.72 tokens per second) 4.17.892.643 I slot print_timing: id 0 | task 18443 | eval time = 2659.30 ms / 230 tokens ( 11.61 ms per token, 86.11 tokens per second) 4.17.892.643 I slot print_timing: id 0 | task 18443 | total time = 3002.42 ms / 467 tokens 4.17.892.644 I slot print_timing: id 0 | task 18443 | graphs reused = 18142 4.17.892.645 I slot print_timing: id 0 | task 18443 | graph reallocs = 0 / 0 (same size) / (changed size) 4.17.892.667 I slot release: id 0 | task 18443 | stop processing: n_tokens = 466, truncated = 0 4.17.895.908 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 466, t_last = 346512878314 4.17.897.003 I slot launch_slot_: id 0 | task 18675 | processing task, is_child = 0 4.20.769.896 I slot print_timing: id 0 | task 18675 | prompt eval time = 382.80 ms / 287 tokens ( 1.33 ms per token, 749.73 tokens per second) 4.20.769.902 I slot print_timing: id 0 | task 18675 | eval time = 2490.08 ms / 215 tokens ( 11.64 ms per token, 85.94 tokens per second) 4.20.769.903 I slot print_timing: id 0 | task 18675 | total time = 2872.88 ms / 502 tokens 4.20.769.903 I slot print_timing: id 0 | task 18675 | graphs reused = 18355 4.20.769.904 I slot print_timing: id 0 | task 18675 | graph reallocs = 0 / 0 (same size) / (changed size) 4.20.769.934 I slot release: id 0 | task 18675 | stop processing: n_tokens = 501, truncated = 0 4.20.773.063 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.148 (> 0.100 thold), f_keep = 0.072 4.20.774.260 I slot launch_slot_: id 0 | task 18892 | processing task, is_child = 0 4.23.923.796 I slot print_timing: id 0 | task 18892 | prompt eval time = 348.50 ms / 243 tokens ( 1.43 ms per token, 697.27 tokens per second) 4.23.923.799 I slot print_timing: id 0 | task 18892 | eval time = 2801.02 ms / 241 tokens ( 11.67 ms per token, 85.68 tokens per second) 4.23.923.800 I slot print_timing: id 0 | task 18892 | total time = 3149.53 ms / 484 tokens 4.23.923.800 I slot print_timing: id 0 | task 18892 | graphs reused = 18593 4.23.923.801 I slot print_timing: id 0 | task 18892 | graph reallocs = 0 / 0 (same size) / (changed size) 4.23.923.825 I slot release: id 0 | task 18892 | stop processing: n_tokens = 483, truncated = 0 4.23.927.067 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 483, t_last = 346518909472 4.23.928.183 I slot launch_slot_: id 0 | task 19135 | processing task, is_child = 0 4.27.286.577 I slot print_timing: id 0 | task 19135 | n_gen = 260, tg = 86.06 t/s, tg_3s = 86.39 t/s 4.27.463.198 I slot print_timing: id 0 | task 19135 | prompt eval time = 348.83 ms / 243 tokens ( 1.44 ms per token, 696.62 tokens per second) 4.27.463.204 I slot print_timing: id 0 | task 19135 | eval time = 3186.18 ms / 275 tokens ( 11.63 ms per token, 86.00 tokens per second) 4.27.463.205 I slot print_timing: id 0 | task 19135 | total time = 3535.01 ms / 518 tokens 4.27.463.205 I slot print_timing: id 0 | task 19135 | graphs reused = 18864 4.27.463.206 I slot print_timing: id 0 | task 19135 | graph reallocs = 0 / 0 (same size) / (changed size) 4.27.463.232 I slot release: id 0 | task 19135 | stop processing: n_tokens = 517, truncated = 0 4.27.466.617 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 517, t_last = 346522448879 4.27.467.762 I slot launch_slot_: id 0 | task 19412 | processing task, is_child = 0 4.30.602.704 I slot print_timing: id 0 | task 19412 | prompt eval time = 365.97 ms / 262 tokens ( 1.40 ms per token, 715.90 tokens per second) 4.30.602.710 I slot print_timing: id 0 | task 19412 | eval time = 2768.95 ms / 239 tokens ( 11.63 ms per token, 85.95 tokens per second) 4.30.602.711 I slot print_timing: id 0 | task 19412 | total time = 3134.93 ms / 501 tokens 4.30.602.711 I slot print_timing: id 0 | task 19412 | graphs reused = 19101 4.30.602.712 I slot print_timing: id 0 | task 19412 | graph reallocs = 0 / 0 (same size) / (changed size) 4.30.602.738 I slot release: id 0 | task 19412 | stop processing: n_tokens = 500, truncated = 0 4.30.605.881 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.102 (> 0.100 thold), f_keep = 0.042 4.30.606.980 I slot launch_slot_: id 0 | task 19653 | processing task, is_child = 0 4.32.715.483 I slot print_timing: id 0 | task 19653 | prompt eval time = 315.59 ms / 205 tokens ( 1.54 ms per token, 649.59 tokens per second) 4.32.715.489 I slot print_timing: id 0 | task 19653 | eval time = 1792.91 ms / 155 tokens ( 11.64 ms per token, 85.89 tokens per second) 4.32.715.490 I slot print_timing: id 0 | task 19653 | total time = 2108.49 ms / 360 tokens 4.32.715.491 I slot print_timing: id 0 | task 19653 | graphs reused = 19253 4.32.715.491 I slot print_timing: id 0 | task 19653 | graph reallocs = 0 / 0 (same size) / (changed size) 4.32.715.528 I slot release: id 0 | task 19653 | stop processing: n_tokens = 359, truncated = 0 4.32.718.886 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 359, t_last = 346527701175 4.32.719.797 I slot launch_slot_: id 0 | task 19810 | processing task, is_child = 0 4.35.733.898 I slot print_timing: id 0 | task 19810 | prompt eval time = 376.69 ms / 279 tokens ( 1.35 ms per token, 740.66 tokens per second) 4.35.733.906 I slot print_timing: id 0 | task 19810 | eval time = 2637.40 ms / 228 tokens ( 11.62 ms per token, 86.07 tokens per second) 4.35.733.907 I slot print_timing: id 0 | task 19810 | total time = 3014.09 ms / 507 tokens 4.35.733.907 I slot print_timing: id 0 | task 19810 | graphs reused = 19479 4.35.733.908 I slot print_timing: id 0 | task 19810 | graph reallocs = 0 / 0 (same size) / (changed size) 4.35.733.936 I slot release: id 0 | task 19810 | stop processing: n_tokens = 506, truncated = 0 4.35.737.158 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.108 (> 0.100 thold), f_keep = 0.042 4.35.738.317 I slot launch_slot_: id 0 | task 20040 | processing task, is_child = 0 4.39.041.578 I slot print_timing: id 0 | task 20040 | n_gen = 259, tg = 85.91 t/s, tg_3s = 86.24 t/s 4.39.785.344 I slot print_timing: id 0 | task 20040 | prompt eval time = 300.12 ms / 194 tokens ( 1.55 ms per token, 646.40 tokens per second) 4.39.785.349 I slot print_timing: id 0 | task 20040 | eval time = 3746.89 ms / 323 tokens ( 11.64 ms per token, 85.94 tokens per second) 4.39.785.350 I slot print_timing: id 0 | task 20040 | total time = 4047.02 ms / 517 tokens 4.39.785.351 I slot print_timing: id 0 | task 20040 | graphs reused = 19798 4.39.785.351 I slot print_timing: id 0 | task 20040 | graph reallocs = 0 / 0 (same size) / (changed size) 4.39.785.376 I slot release: id 0 | task 20040 | stop processing: n_tokens = 516, truncated = 0 4.39.788.383 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.124 (> 0.100 thold), f_keep = 0.041 4.39.789.570 I slot launch_slot_: id 0 | task 20365 | processing task, is_child = 0 4.42.273.435 I slot print_timing: id 0 | task 20365 | prompt eval time = 287.81 ms / 169 tokens ( 1.70 ms per token, 587.18 tokens per second) 4.42.273.441 I slot print_timing: id 0 | task 20365 | eval time = 2196.04 ms / 189 tokens ( 11.68 ms per token, 85.61 tokens per second) 4.42.273.442 I slot print_timing: id 0 | task 20365 | total time = 2483.86 ms / 358 tokens 4.42.273.442 I slot print_timing: id 0 | task 20365 | graphs reused = 19984 4.42.273.443 I slot print_timing: id 0 | task 20365 | graph reallocs = 0 / 0 (same size) / (changed size) 4.42.273.463 I slot release: id 0 | task 20365 | stop processing: n_tokens = 357, truncated = 0 4.42.276.511 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 357, t_last = 346537259110 4.42.278.045 I slot launch_slot_: id 0 | task 20556 | processing task, is_child = 0 4.45.652.280 I slot print_timing: id 0 | task 20556 | n_gen = 259, tg = 85.80 t/s, tg_3s = 86.13 t/s 4.45.768.026 I slot print_timing: id 0 | task 20556 | prompt eval time = 367.28 ms / 263 tokens ( 1.40 ms per token, 716.08 tokens per second) 4.45.768.032 I slot print_timing: id 0 | task 20556 | eval time = 3122.70 ms / 269 tokens ( 11.65 ms per token, 85.82 tokens per second) 4.45.768.032 I slot print_timing: id 0 | task 20556 | total time = 3489.97 ms / 532 tokens 4.45.768.033 I slot print_timing: id 0 | task 20556 | graphs reused = 20250 4.45.768.033 I slot print_timing: id 0 | task 20556 | graph reallocs = 0 / 0 (same size) / (changed size) 4.45.768.061 I slot release: id 0 | task 20556 | stop processing: n_tokens = 531, truncated = 0 4.45.771.449 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.103 (> 0.100 thold), f_keep = 0.040 4.45.772.741 I slot launch_slot_: id 0 | task 20827 | processing task, is_child = 0 4.47.833.769 I slot print_timing: id 0 | task 20827 | prompt eval time = 315.39 ms / 204 tokens ( 1.55 ms per token, 646.81 tokens per second) 4.47.833.772 I slot print_timing: id 0 | task 20827 | eval time = 1745.63 ms / 151 tokens ( 11.64 ms per token, 85.93 tokens per second) 4.47.833.773 I slot print_timing: id 0 | task 20827 | total time = 2061.02 ms / 355 tokens 4.47.833.773 I slot print_timing: id 0 | task 20827 | graphs reused = 20398 4.47.833.774 I slot print_timing: id 0 | task 20827 | graph reallocs = 0 / 0 (same size) / (changed size) 4.47.833.795 I slot release: id 0 | task 20827 | stop processing: n_tokens = 354, truncated = 0 4.47.837.012 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 354, t_last = 346542819442 4.47.837.902 I slot launch_slot_: id 0 | task 20980 | processing task, is_child = 0 4.51.215.287 I slot print_timing: id 0 | task 20980 | n_gen = 259, tg = 85.88 t/s, tg_3s = 86.21 t/s 4.53.813.435 I slot print_timing: id 0 | task 20980 | prompt eval time = 373.04 ms / 272 tokens ( 1.37 ms per token, 729.14 tokens per second) 4.53.813.438 I slot print_timing: id 0 | task 20980 | eval time = 5602.48 ms / 482 tokens ( 11.65 ms per token, 85.85 tokens per second) 4.53.813.438 I slot print_timing: id 0 | task 20980 | total time = 5975.52 ms / 754 tokens 4.53.813.439 I slot print_timing: id 0 | task 20980 | graphs reused = 20877 4.53.813.440 I slot print_timing: id 0 | task 20980 | graph reallocs = 0 / 0 (same size) / (changed size) 4.53.813.466 I slot release: id 0 | task 20980 | stop processing: n_tokens = 753, truncated = 0 4.53.816.840 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 753, t_last = 346548799113 4.53.818.409 I slot launch_slot_: id 0 | task 21464 | processing task, is_child = 0 4.56.579.331 I slot print_timing: id 0 | task 21464 | prompt eval time = 340.97 ms / 231 tokens ( 1.48 ms per token, 677.49 tokens per second) 4.56.579.337 I slot print_timing: id 0 | task 21464 | eval time = 2419.95 ms / 209 tokens ( 11.63 ms per token, 85.95 tokens per second) 4.56.579.338 I slot print_timing: id 0 | task 21464 | total time = 2760.91 ms / 440 tokens 4.56.579.339 I slot print_timing: id 0 | task 21464 | graphs reused = 21083 4.56.579.339 I slot print_timing: id 0 | task 21464 | graph reallocs = 0 / 0 (same size) / (changed size) 4.56.579.362 I slot release: id 0 | task 21464 | stop processing: n_tokens = 439, truncated = 0 4.56.582.680 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 439, t_last = 346551565009 4.56.583.740 I slot launch_slot_: id 0 | task 21675 | processing task, is_child = 0 4.59.169.453 I slot print_timing: id 0 | task 21675 | prompt eval time = 385.66 ms / 291 tokens ( 1.33 ms per token, 754.56 tokens per second) 4.59.169.456 I slot print_timing: id 0 | task 21675 | eval time = 2200.05 ms / 190 tokens ( 11.64 ms per token, 85.91 tokens per second) 4.59.169.457 I slot print_timing: id 0 | task 21675 | total time = 2585.70 ms / 481 tokens 4.59.169.458 I slot print_timing: id 0 | task 21675 | graphs reused = 21271 4.59.169.458 I slot print_timing: id 0 | task 21675 | graph reallocs = 0 / 0 (same size) / (changed size) 4.59.169.483 I slot release: id 0 | task 21675 | stop processing: n_tokens = 480, truncated = 0 4.59.172.742 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 480, t_last = 346554155130 4.59.173.873 I slot launch_slot_: id 0 | task 21867 | processing task, is_child = 0 5.02.156.708 I slot print_timing: id 0 | task 21867 | prompt eval time = 381.83 ms / 285 tokens ( 1.34 ms per token, 746.41 tokens per second) 5.02.156.711 I slot print_timing: id 0 | task 21867 | eval time = 2601.00 ms / 225 tokens ( 11.61 ms per token, 86.12 tokens per second) 5.02.156.713 I slot print_timing: id 0 | task 21867 | total time = 2982.82 ms / 510 tokens 5.02.156.713 I slot print_timing: id 0 | task 21867 | graphs reused = 21494 5.02.156.714 I slot print_timing: id 0 | task 21867 | graph reallocs = 0 / 0 (same size) / (changed size) 5.02.156.743 I slot release: id 0 | task 21867 | stop processing: n_tokens = 509, truncated = 0 5.02.159.933 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 509, t_last = 346557142390 5.02.161.103 I slot launch_slot_: id 0 | task 22094 | processing task, is_child = 0 5.05.551.221 I slot print_timing: id 0 | task 22094 | n_gen = 259, tg = 85.81 t/s, tg_3s = 86.15 t/s 5.06.389.957 I slot print_timing: id 0 | task 22094 | prompt eval time = 383.58 ms / 289 tokens ( 1.33 ms per token, 753.42 tokens per second) 5.06.389.961 I slot print_timing: id 0 | task 22094 | eval time = 3845.26 ms / 331 tokens ( 11.65 ms per token, 85.82 tokens per second) 5.06.389.962 I slot print_timing: id 0 | task 22094 | total time = 4228.85 ms / 620 tokens 5.06.389.963 I slot print_timing: id 0 | task 22094 | graphs reused = 21822 5.06.389.963 I slot print_timing: id 0 | task 22094 | graph reallocs = 0 / 0 (same size) / (changed size) 5.06.389.988 I slot release: id 0 | task 22094 | stop processing: n_tokens = 619, truncated = 0 5.06.393.377 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 619, t_last = 346561375635 5.06.394.807 I slot launch_slot_: id 0 | task 22427 | processing task, is_child = 0 5.09.747.167 I slot print_timing: id 0 | task 22427 | n_gen = 259, tg = 85.82 t/s, tg_3s = 86.15 t/s 5.12.094.967 I slot print_timing: id 0 | task 22427 | prompt eval time = 346.07 ms / 242 tokens ( 1.43 ms per token, 699.28 tokens per second) 5.12.094.970 I slot print_timing: id 0 | task 22427 | eval time = 5354.08 ms / 460 tokens ( 11.66 ms per token, 85.73 tokens per second) 5.12.094.970 I slot print_timing: id 0 | task 22427 | total time = 5700.15 ms / 702 tokens 5.12.094.971 I slot print_timing: id 0 | task 22427 | graphs reused = 22278 5.12.094.971 I slot print_timing: id 0 | task 22427 | graph reallocs = 0 / 0 (same size) / (changed size) 5.12.094.995 I slot release: id 0 | task 22427 | stop processing: n_tokens = 701, truncated = 0 5.12.098.258 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.118 (> 0.100 thold), f_keep = 0.030 5.12.099.791 I slot launch_slot_: id 0 | task 22889 | processing task, is_child = 0 5.14.871.227 I slot print_timing: id 0 | task 22889 | prompt eval time = 294.29 ms / 178 tokens ( 1.65 ms per token, 604.85 tokens per second) 5.14.871.230 I slot print_timing: id 0 | task 22889 | eval time = 2477.14 ms / 214 tokens ( 11.63 ms per token, 85.99 tokens per second) 5.14.871.230 I slot print_timing: id 0 | task 22889 | total time = 2771.42 ms / 392 tokens 5.14.871.231 I slot print_timing: id 0 | task 22889 | graphs reused = 22489 5.14.871.232 I slot print_timing: id 0 | task 22889 | graph reallocs = 0 / 0 (same size) / (changed size) 5.14.871.252 I slot release: id 0 | task 22889 | stop processing: n_tokens = 391, truncated = 0 5.14.874.482 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 391, t_last = 346569856899 5.14.875.441 I slot launch_slot_: id 0 | task 23105 | processing task, is_child = 0 5.17.352.710 I slot print_timing: id 0 | task 23105 | prompt eval time = 369.78 ms / 264 tokens ( 1.40 ms per token, 713.93 tokens per second) 5.17.352.714 I slot print_timing: id 0 | task 23105 | eval time = 2107.47 ms / 182 tokens ( 11.64 ms per token, 85.88 tokens per second) 5.17.352.715 I slot print_timing: id 0 | task 23105 | total time = 2477.26 ms / 446 tokens 5.17.352.716 I slot print_timing: id 0 | task 23105 | graphs reused = 22669 5.17.352.716 I slot print_timing: id 0 | task 23105 | graph reallocs = 0 / 0 (same size) / (changed size) 5.17.352.739 I slot release: id 0 | task 23105 | stop processing: n_tokens = 445, truncated = 0 5.17.355.923 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.138 (> 0.100 thold), f_keep = 0.047 5.17.356.897 I slot launch_slot_: id 0 | task 23289 | processing task, is_child = 0 5.19.764.579 I slot print_timing: id 0 | task 23289 | prompt eval time = 270.58 ms / 152 tokens ( 1.78 ms per token, 561.75 tokens per second) 5.19.764.588 I slot print_timing: id 0 | task 23289 | eval time = 2137.09 ms / 184 tokens ( 11.68 ms per token, 85.63 tokens per second) 5.19.764.589 I slot print_timing: id 0 | task 23289 | total time = 2407.68 ms / 336 tokens 5.19.764.589 I slot print_timing: id 0 | task 23289 | graphs reused = 22850 5.19.764.590 I slot print_timing: id 0 | task 23289 | graph reallocs = 0 / 0 (same size) / (changed size) 5.19.764.608 I slot release: id 0 | task 23289 | stop processing: n_tokens = 335, truncated = 0 5.19.767.781 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.108 (> 0.100 thold), f_keep = 0.063 5.19.768.169 I slot launch_slot_: id 0 | task 23475 | processing task, is_child = 0 5.21.596.885 I slot print_timing: id 0 | task 23475 | prompt eval time = 303.63 ms / 194 tokens ( 1.57 ms per token, 638.94 tokens per second) 5.21.596.891 I slot print_timing: id 0 | task 23475 | eval time = 1525.08 ms / 132 tokens ( 11.64 ms per token, 85.90 tokens per second) 5.21.596.892 I slot print_timing: id 0 | task 23475 | total time = 1828.71 ms / 326 tokens 5.21.596.892 I slot print_timing: id 0 | task 23475 | graphs reused = 22979 5.21.596.893 I slot print_timing: id 0 | task 23475 | graph reallocs = 0 / 0 (same size) / (changed size) 5.21.596.913 I slot release: id 0 | task 23475 | stop processing: n_tokens = 325, truncated = 0 5.21.600.335 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 325, t_last = 346576582560 5.21.600.747 I slot launch_slot_: id 0 | task 23609 | processing task, is_child = 0 5.24.768.028 I slot print_timing: id 0 | task 23609 | prompt eval time = 371.09 ms / 269 tokens ( 1.38 ms per token, 724.89 tokens per second) 5.24.768.034 I slot print_timing: id 0 | task 23609 | eval time = 2796.18 ms / 240 tokens ( 11.70 ms per token, 85.47 tokens per second) 5.24.768.035 I slot print_timing: id 0 | task 23609 | total time = 3167.28 ms / 509 tokens 5.24.768.036 I slot print_timing: id 0 | task 23609 | graphs reused = 23217 5.24.768.036 I slot print_timing: id 0 | task 23609 | graph reallocs = 0 / 0 (same size) / (changed size) 5.24.768.059 I slot release: id 0 | task 23609 | stop processing: n_tokens = 508, truncated = 0 5.24.771.564 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 508, t_last = 346579753706 5.24.772.710 I slot launch_slot_: id 0 | task 23851 | processing task, is_child = 0 5.28.154.909 I slot print_timing: id 0 | task 23851 | n_gen = 258, tg = 85.60 t/s, tg_3s = 85.93 t/s 5.31.165.581 I slot print_timing: id 0 | task 23851 | n_gen = 517, tg = 85.81 t/s, tg_3s = 86.03 t/s 5.31.726.081 I slot print_timing: id 0 | task 23851 | prompt eval time = 379.86 ms / 283 tokens ( 1.34 ms per token, 745.01 tokens per second) 5.31.726.087 I slot print_timing: id 0 | task 23851 | eval time = 6573.50 ms / 565 tokens ( 11.66 ms per token, 85.80 tokens per second) 5.31.726.088 I slot print_timing: id 0 | task 23851 | total time = 6953.36 ms / 848 tokens 5.31.726.088 I slot print_timing: id 0 | task 23851 | graphs reused = 23778 5.31.726.089 I slot print_timing: id 0 | task 23851 | graph reallocs = 0 / 0 (same size) / (changed size) 5.31.726.115 I slot release: id 0 | task 23851 | stop processing: n_tokens = 847, truncated = 0 5.31.729.722 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 847, t_last = 346586711762 5.31.731.464 I slot launch_slot_: id 0 | task 24418 | processing task, is_child = 0 5.35.133.221 I slot print_timing: id 0 | task 24418 | n_gen = 258, tg = 85.61 t/s, tg_3s = 85.94 t/s 5.35.892.618 I slot print_timing: id 0 | task 24418 | prompt eval time = 399.64 ms / 306 tokens ( 1.31 ms per token, 765.70 tokens per second) 5.35.892.620 I slot print_timing: id 0 | task 24418 | eval time = 3761.51 ms / 323 tokens ( 11.68 ms per token, 85.60 tokens per second) 5.35.892.621 I slot print_timing: id 0 | task 24418 | total time = 4161.14 ms / 629 tokens 5.35.892.621 I slot print_timing: id 0 | task 24418 | graphs reused = 24098 5.35.892.622 I slot print_timing: id 0 | task 24418 | graph reallocs = 0 / 0 (same size) / (changed size) 5.35.892.652 I slot release: id 0 | task 24418 | stop processing: n_tokens = 628, truncated = 0 5.35.896.246 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 628, t_last = 346590878299 5.35.897.658 I slot launch_slot_: id 0 | task 24743 | processing task, is_child = 0 5.37.786.255 I slot print_timing: id 0 | task 24743 | prompt eval time = 408.17 ms / 317 tokens ( 1.29 ms per token, 776.64 tokens per second) 5.37.786.262 I slot print_timing: id 0 | task 24743 | eval time = 1480.42 ms / 128 tokens ( 11.66 ms per token, 85.79 tokens per second) 5.37.786.263 I slot print_timing: id 0 | task 24743 | total time = 1888.59 ms / 445 tokens 5.37.786.263 I slot print_timing: id 0 | task 24743 | graphs reused = 24224 5.37.786.264 I slot print_timing: id 0 | task 24743 | graph reallocs = 0 / 0 (same size) / (changed size) 5.37.786.294 I slot release: id 0 | task 24743 | stop processing: n_tokens = 444, truncated = 0 5.37.789.696 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 444, t_last = 346592771941 5.37.790.744 I slot launch_slot_: id 0 | task 24873 | processing task, is_child = 0 5.40.679.887 I slot print_timing: id 0 | task 24873 | prompt eval time = 396.48 ms / 296 tokens ( 1.34 ms per token, 746.58 tokens per second) 5.40.679.894 I slot print_timing: id 0 | task 24873 | eval time = 2492.66 ms / 215 tokens ( 11.65 ms per token, 85.85 tokens per second) 5.40.679.895 I slot print_timing: id 0 | task 24873 | total time = 2889.13 ms / 511 tokens 5.40.679.895 I slot print_timing: id 0 | task 24873 | graphs reused = 24437 5.40.679.896 I slot print_timing: id 0 | task 24873 | graph reallocs = 0 / 0 (same size) / (changed size) 5.40.679.927 I slot release: id 0 | task 24873 | stop processing: n_tokens = 510, truncated = 0 5.40.683.344 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 510, t_last = 346595665574 5.40.684.640 I slot launch_slot_: id 0 | task 25090 | processing task, is_child = 0 5.43.798.131 I slot print_timing: id 0 | task 25090 | prompt eval time = 354.65 ms / 254 tokens ( 1.40 ms per token, 716.19 tokens per second) 5.43.798.134 I slot print_timing: id 0 | task 25090 | eval time = 2758.83 ms / 238 tokens ( 11.64 ms per token, 85.91 tokens per second) 5.43.798.134 I slot print_timing: id 0 | task 25090 | total time = 3113.48 ms / 492 tokens 5.43.798.135 I slot print_timing: id 0 | task 25090 | graphs reused = 24672 5.43.798.136 I slot print_timing: id 0 | task 25090 | graph reallocs = 0 / 0 (same size) / (changed size) 5.43.798.160 I slot release: id 0 | task 25090 | stop processing: n_tokens = 491, truncated = 0 5.43.801.596 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.112 (> 0.100 thold), f_keep = 0.043 5.43.802.781 I slot launch_slot_: id 0 | task 25330 | processing task, is_child = 0 5.45.617.675 I slot print_timing: id 0 | task 25330 | prompt eval time = 299.87 ms / 188 tokens ( 1.60 ms per token, 626.94 tokens per second) 5.45.617.682 I slot print_timing: id 0 | task 25330 | eval time = 1515.02 ms / 131 tokens ( 11.65 ms per token, 85.81 tokens per second) 5.45.617.682 I slot print_timing: id 0 | task 25330 | total time = 1814.89 ms / 319 tokens 5.45.617.683 I slot print_timing: id 0 | task 25330 | graphs reused = 24800 5.45.617.684 I slot print_timing: id 0 | task 25330 | graph reallocs = 0 / 0 (same size) / (changed size) 5.45.617.703 I slot release: id 0 | task 25330 | stop processing: n_tokens = 318, truncated = 0 5.45.621.263 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 318, t_last = 346600603350 5.45.622.101 I slot launch_slot_: id 0 | task 25463 | processing task, is_child = 0 5.48.714.407 I slot print_timing: id 0 | task 25463 | prompt eval time = 483.32 ms / 394 tokens ( 1.23 ms per token, 815.20 tokens per second) 5.48.714.413 I slot print_timing: id 0 | task 25463 | eval time = 2608.97 ms / 224 tokens ( 11.70 ms per token, 85.47 tokens per second) 5.48.714.414 I slot print_timing: id 0 | task 25463 | total time = 3092.29 ms / 618 tokens 5.48.714.415 I slot print_timing: id 0 | task 25463 | graphs reused = 25021 5.48.714.415 I slot print_timing: id 0 | task 25463 | graph reallocs = 0 / 0 (same size) / (changed size) 5.48.714.455 I slot release: id 0 | task 25463 | stop processing: n_tokens = 617, truncated = 0 5.48.718.397 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 617, t_last = 346603700102 5.48.719.820 I slot launch_slot_: id 0 | task 25689 | processing task, is_child = 0 5.52.492.585 I slot print_timing: id 0 | task 25689 | n_gen = 259, tg = 85.67 t/s, tg_3s = 86.01 t/s 5.55.287.149 I slot print_timing: id 0 | task 25689 | prompt eval time = 761.33 ms / 584 tokens ( 1.30 ms per token, 767.08 tokens per second) 5.55.287.155 I slot print_timing: id 0 | task 25689 | eval time = 5805.99 ms / 498 tokens ( 11.68 ms per token, 85.60 tokens per second) 5.55.287.156 I slot print_timing: id 0 | task 25689 | total time = 6567.32 ms / 1082 tokens 5.55.287.156 I slot print_timing: id 0 | task 25689 | graphs reused = 25515 5.55.287.157 I slot print_timing: id 0 | task 25689 | graph reallocs = 0 / 0 (same size) / (changed size) 5.55.287.196 I slot release: id 0 | task 25689 | stop processing: n_tokens = 1081, truncated = 0 5.55.291.164 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1081, t_last = 346610272843 5.55.293.642 I slot launch_slot_: id 0 | task 26190 | processing task, is_child = 0 5.58.900.940 I slot print_timing: id 0 | task 26190 | n_gen = 258, tg = 85.48 t/s, tg_3s = 85.81 t/s 6.01.443.390 I slot print_timing: id 0 | task 26190 | prompt eval time = 600.69 ms / 518 tokens ( 1.16 ms per token, 862.34 tokens per second) 6.01.443.393 I slot print_timing: id 0 | task 26190 | eval time = 5549.05 ms / 476 tokens ( 11.68 ms per token, 85.60 tokens per second) 6.01.443.394 I slot print_timing: id 0 | task 26190 | total time = 6149.73 ms / 994 tokens 6.01.443.394 I slot print_timing: id 0 | task 26190 | graphs reused = 25988 6.01.443.395 I slot print_timing: id 0 | task 26190 | graph reallocs = 0 / 0 (same size) / (changed size) 6.01.443.431 I slot release: id 0 | task 26190 | stop processing: n_tokens = 993, truncated = 0 6.01.447.484 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 993, t_last = 346616429078 6.01.449.951 I slot launch_slot_: id 0 | task 26669 | processing task, is_child = 0 6.04.937.608 I slot print_timing: id 0 | task 26669 | n_gen = 259, tg = 85.91 t/s, tg_3s = 86.25 t/s 6.04.960.729 I slot print_timing: id 0 | task 26669 | prompt eval time = 484.64 ms / 399 tokens ( 1.21 ms per token, 823.28 tokens per second) 6.04.960.734 I slot print_timing: id 0 | task 26669 | eval time = 3026.13 ms / 261 tokens ( 11.64 ms per token, 85.92 tokens per second) 6.04.960.734 I slot print_timing: id 0 | task 26669 | total time = 3510.77 ms / 660 tokens 6.04.960.735 I slot print_timing: id 0 | task 26669 | graphs reused = 26246 6.04.960.736 I slot print_timing: id 0 | task 26669 | graph reallocs = 0 / 0 (same size) / (changed size) 6.04.960.767 I slot release: id 0 | task 26669 | stop processing: n_tokens = 661, truncated = 0 6.04.964.401 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 661, t_last = 346619946414 6.04.965.860 I slot launch_slot_: id 0 | task 26932 | processing task, is_child = 0 6.07.775.064 I slot print_timing: id 0 | task 26932 | prompt eval time = 428.31 ms / 335 tokens ( 1.28 ms per token, 782.13 tokens per second) 6.07.775.070 I slot print_timing: id 0 | task 26932 | eval time = 2380.88 ms / 205 tokens ( 11.67 ms per token, 85.68 tokens per second) 6.07.775.071 I slot print_timing: id 0 | task 26932 | total time = 2809.19 ms / 540 tokens 6.07.775.071 I slot print_timing: id 0 | task 26932 | graphs reused = 26448 6.07.775.072 I slot print_timing: id 0 | task 26932 | graph reallocs = 0 / 0 (same size) / (changed size) 6.07.775.100 I slot release: id 0 | task 26932 | stop processing: n_tokens = 541, truncated = 0 6.07.779.004 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 541, t_last = 346622760747 6.07.780.272 I slot launch_slot_: id 0 | task 27139 | processing task, is_child = 0 6.11.559.148 I slot print_timing: id 0 | task 27139 | n_gen = 258, tg = 85.57 t/s, tg_3s = 85.90 t/s 6.14.038.923 I slot print_timing: id 0 | task 27139 | prompt eval time = 775.45 ms / 603 tokens ( 1.29 ms per token, 777.61 tokens per second) 6.14.038.926 I slot print_timing: id 0 | task 27139 | eval time = 5483.19 ms / 470 tokens ( 11.69 ms per token, 85.53 tokens per second) 6.14.038.927 I slot print_timing: id 0 | task 27139 | total time = 6258.64 ms / 1073 tokens 6.14.038.927 I slot print_timing: id 0 | task 27139 | graphs reused = 26914 6.14.038.928 I slot print_timing: id 0 | task 27139 | graph reallocs = 0 / 0 (same size) / (changed size) 6.14.038.970 I slot release: id 0 | task 27139 | stop processing: n_tokens = 1074, truncated = 0 6.14.042.584 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1074, t_last = 346629024617 6.14.045.185 I slot launch_slot_: id 0 | task 27612 | processing task, is_child = 0 6.17.480.539 I slot print_timing: id 0 | task 27612 | n_gen = 259, tg = 85.73 t/s, tg_3s = 86.07 t/s 6.18.216.208 I slot print_timing: id 0 | task 27612 | prompt eval time = 426.07 ms / 333 tokens ( 1.28 ms per token, 781.57 tokens per second) 6.18.216.215 I slot print_timing: id 0 | task 27612 | eval time = 3744.95 ms / 322 tokens ( 11.67 ms per token, 85.72 tokens per second) 6.18.216.215 I slot print_timing: id 0 | task 27612 | total time = 4171.01 ms / 655 tokens 6.18.216.216 I slot print_timing: id 0 | task 27612 | graphs reused = 27233 6.18.216.216 I slot print_timing: id 0 | task 27612 | graph reallocs = 0 / 0 (same size) / (changed size) 6.18.216.249 I slot release: id 0 | task 27612 | stop processing: n_tokens = 656, truncated = 0 6.18.220.037 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 656, t_last = 346633201896 6.18.221.631 I slot launch_slot_: id 0 | task 27936 | processing task, is_child = 0 6.21.774.999 I slot print_timing: id 0 | task 27936 | n_gen = 259, tg = 85.67 t/s, tg_3s = 86.00 t/s 6.23.284.557 I slot print_timing: id 0 | task 27936 | prompt eval time = 541.71 ms / 460 tokens ( 1.18 ms per token, 849.16 tokens per second) 6.23.284.559 I slot print_timing: id 0 | task 27936 | eval time = 4521.20 ms / 388 tokens ( 11.68 ms per token, 85.60 tokens per second) 6.23.284.560 I slot print_timing: id 0 | task 27936 | total time = 5062.91 ms / 848 tokens 6.23.284.560 I slot print_timing: id 0 | task 27936 | graphs reused = 27617 6.23.284.561 I slot print_timing: id 0 | task 27936 | graph reallocs = 0 / 0 (same size) / (changed size) 6.23.284.595 I slot release: id 0 | task 27936 | stop processing: n_tokens = 849, truncated = 0 6.23.288.079 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 849, t_last = 346638270242 6.23.289.981 I slot launch_slot_: id 0 | task 28326 | processing task, is_child = 0 6.25.537.564 I slot print_timing: id 0 | task 28326 | prompt eval time = 337.49 ms / 225 tokens ( 1.50 ms per token, 666.69 tokens per second) 6.25.537.568 I slot print_timing: id 0 | task 28326 | eval time = 1910.09 ms / 165 tokens ( 11.65 ms per token, 85.86 tokens per second) 6.25.537.569 I slot print_timing: id 0 | task 28326 | total time = 2247.57 ms / 390 tokens 6.25.537.569 I slot print_timing: id 0 | task 28326 | graphs reused = 27779 6.25.537.570 I slot print_timing: id 0 | task 28326 | graph reallocs = 0 / 0 (same size) / (changed size) 6.25.537.594 I slot release: id 0 | task 28326 | stop processing: n_tokens = 391, truncated = 0 6.25.541.182 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 391, t_last = 346640523241 6.25.542.271 I slot launch_slot_: id 0 | task 28493 | processing task, is_child = 0 6.29.043.000 I slot print_timing: id 0 | task 28493 | n_gen = 259, tg = 85.81 t/s, tg_3s = 86.15 t/s 6.29.101.102 I slot print_timing: id 0 | task 28493 | prompt eval time = 494.17 ms / 415 tokens ( 1.19 ms per token, 839.80 tokens per second) 6.29.101.105 I slot print_timing: id 0 | task 28493 | eval time = 3064.66 ms / 264 tokens ( 11.65 ms per token, 85.82 tokens per second) 6.29.101.106 I slot print_timing: id 0 | task 28493 | total time = 3558.82 ms / 679 tokens 6.29.101.106 I slot print_timing: id 0 | task 28493 | graphs reused = 28040 6.29.101.107 I slot print_timing: id 0 | task 28493 | graph reallocs = 0 / 0 (same size) / (changed size) 6.29.101.139 I slot release: id 0 | task 28493 | stop processing: n_tokens = 680, truncated = 0 6.29.104.945 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 680, t_last = 346644086786 6.29.106.548 I slot launch_slot_: id 0 | task 28759 | processing task, is_child = 0 6.32.714.725 I slot print_timing: id 0 | task 28759 | n_gen = 258, tg = 85.58 t/s, tg_3s = 85.92 t/s 6.35.231.329 I slot print_timing: id 0 | task 28759 | prompt eval time = 605.25 ms / 519 tokens ( 1.17 ms per token, 857.49 tokens per second) 6.35.231.335 I slot print_timing: id 0 | task 28759 | eval time = 5519.52 ms / 474 tokens ( 11.67 ms per token, 85.70 tokens per second) 6.35.231.336 I slot print_timing: id 0 | task 28759 | total time = 6124.77 ms / 993 tokens 6.35.231.336 I slot print_timing: id 0 | task 28759 | graphs reused = 28511 6.35.231.337 I slot print_timing: id 0 | task 28759 | graph reallocs = 0 / 0 (same size) / (changed size) 6.35.231.375 I slot release: id 0 | task 28759 | stop processing: n_tokens = 994, truncated = 0 6.35.235.161 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 994, t_last = 346650217022 6.35.237.353 I slot launch_slot_: id 0 | task 29236 | processing task, is_child = 0 6.39.015.756 I slot print_timing: id 0 | task 29236 | n_gen = 258, tg = 85.66 t/s, tg_3s = 85.99 t/s 6.42.019.454 I slot print_timing: id 0 | task 29236 | n_gen = 515, tg = 85.61 t/s, tg_3s = 85.56 t/s 6.45.020.815 I slot print_timing: id 0 | task 29236 | n_gen = 771, tg = 85.51 t/s, tg_3s = 85.29 t/s 6.47.929.939 I slot print_timing: id 0 | task 29236 | prompt eval time = 778.17 ms / 602 tokens ( 1.29 ms per token, 773.60 tokens per second) 6.47.929.944 I slot print_timing: id 0 | task 29236 | eval time = 11914.39 ms / 1018 tokens ( 11.72 ms per token, 85.36 tokens per second) 6.47.929.945 I slot print_timing: id 0 | task 29236 | total time = 12692.57 ms / 1620 tokens 6.47.929.945 I slot print_timing: id 0 | task 29236 | graphs reused = 29523 6.47.929.946 I slot print_timing: id 0 | task 29236 | graph reallocs = 0 / 0 (same size) / (changed size) 6.47.929.986 I slot release: id 0 | task 29236 | stop processing: n_tokens = 1624, truncated = 0 6.47.933.797 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1624, t_last = 346662915633 6.47.937.406 I slot launch_slot_: id 0 | task 30257 | processing task, is_child = 0 6.51.440.972 I slot print_timing: id 0 | task 30257 | n_gen = 259, tg = 85.67 t/s, tg_3s = 86.00 t/s 6.52.528.795 I slot print_timing: id 0 | task 30257 | prompt eval time = 491.99 ms / 407 tokens ( 1.21 ms per token, 827.25 tokens per second) 6.52.528.801 I slot print_timing: id 0 | task 30257 | eval time = 4099.39 ms / 352 tokens ( 11.68 ms per token, 85.62 tokens per second) 6.52.528.802 I slot print_timing: id 0 | task 30257 | total time = 4591.38 ms / 759 tokens 6.52.528.802 I slot print_timing: id 0 | task 30257 | graphs reused = 29872 6.52.528.803 I slot print_timing: id 0 | task 30257 | graph reallocs = 0 / 0 (same size) / (changed size) 6.52.528.837 I slot release: id 0 | task 30257 | stop processing: n_tokens = 763, truncated = 0 6.52.532.577 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 763, t_last = 346667514484 6.52.534.376 I slot launch_slot_: id 0 | task 30611 | processing task, is_child = 0 6.56.101.874 I slot print_timing: id 0 | task 30611 | n_gen = 259, tg = 85.69 t/s, tg_3s = 86.03 t/s 6.59.105.069 I slot print_timing: id 0 | task 30611 | n_gen = 516, tg = 85.63 t/s, tg_3s = 85.58 t/s 6.59.831.624 I slot print_timing: id 0 | task 30611 | prompt eval time = 556.79 ms / 484 tokens ( 1.15 ms per token, 869.27 tokens per second) 6.59.831.630 I slot print_timing: id 0 | task 30611 | eval time = 6740.45 ms / 578 tokens ( 11.68 ms per token, 85.60 tokens per second) 6.59.831.630 I slot print_timing: id 0 | task 30611 | total time = 7297.24 ms / 1062 tokens 6.59.831.631 I slot print_timing: id 0 | task 30611 | graphs reused = 30445 6.59.831.632 I slot print_timing: id 0 | task 30611 | graph reallocs = 0 / 0 (same size) / (changed size) 6.59.831.668 I slot release: id 0 | task 30611 | stop processing: n_tokens = 1066, truncated = 0 6.59.835.473 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1066, t_last = 346674817315 6.59.838.001 I slot launch_slot_: id 0 | task 31191 | processing task, is_child = 0 7.02.599.310 I slot print_timing: id 0 | task 31191 | prompt eval time = 538.41 ms / 457 tokens ( 1.18 ms per token, 848.79 tokens per second) 7.02.599.314 I slot print_timing: id 0 | task 31191 | eval time = 2222.88 ms / 191 tokens ( 11.70 ms per token, 85.47 tokens per second) 7.02.599.315 I slot print_timing: id 0 | task 31191 | total time = 2761.30 ms / 648 tokens 7.02.599.315 I slot print_timing: id 0 | task 31191 | graphs reused = 30633 7.02.599.316 I slot print_timing: id 0 | task 31191 | graph reallocs = 0 / 0 (same size) / (changed size) 7.02.599.358 I slot release: id 0 | task 31191 | stop processing: n_tokens = 652, truncated = 0 7.02.603.391 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 652, t_last = 346677585005 7.02.605.669 I slot launch_slot_: id 0 | task 31384 | processing task, is_child = 0 7.06.387.345 I slot print_timing: id 0 | task 31384 | n_gen = 258, tg = 85.50 t/s, tg_3s = 85.83 t/s 7.09.390.149 I slot print_timing: id 0 | task 31384 | n_gen = 515, tg = 85.54 t/s, tg_3s = 85.59 t/s 7.10.353.729 I slot print_timing: id 0 | task 31384 | prompt eval time = 775.79 ms / 597 tokens ( 1.30 ms per token, 769.53 tokens per second) 7.10.353.732 I slot print_timing: id 0 | task 31384 | eval time = 6972.25 ms / 597 tokens ( 11.70 ms per token, 85.48 tokens per second) 7.10.353.732 I slot print_timing: id 0 | task 31384 | total time = 7748.04 ms / 1194 tokens 7.10.353.733 I slot print_timing: id 0 | task 31384 | graphs reused = 31226 7.10.353.734 I slot print_timing: id 0 | task 31384 | graph reallocs = 0 / 0 (same size) / (changed size) 7.10.353.779 I slot release: id 0 | task 31384 | stop processing: n_tokens = 1193, truncated = 0 7.10.358.061 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1193, t_last = 346685339426 7.10.360.737 I slot launch_slot_: id 0 | task 31984 | processing task, is_child = 0 7.14.219.962 I slot print_timing: id 0 | task 31984 | n_gen = 258, tg = 85.50 t/s, tg_3s = 85.83 t/s 7.14.770.828 I slot print_timing: id 0 | task 31984 | prompt eval time = 853.42 ms / 688 tokens ( 1.24 ms per token, 806.17 tokens per second) 7.14.770.832 I slot print_timing: id 0 | task 31984 | eval time = 3556.66 ms / 305 tokens ( 11.70 ms per token, 85.47 tokens per second) 7.14.770.833 I slot print_timing: id 0 | task 31984 | total time = 4410.08 ms / 993 tokens 7.14.770.833 I slot print_timing: id 0 | task 31984 | graphs reused = 31528 7.14.770.834 I slot print_timing: id 0 | task 31984 | graph reallocs = 0 / 0 (same size) / (changed size) 7.14.770.882 I slot release: id 0 | task 31984 | stop processing: n_tokens = 992, truncated = 0 7.14.774.675 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 992, t_last = 346689756529 7.14.777.364 I slot launch_slot_: id 0 | task 32292 | processing task, is_child = 0 7.18.341.571 I slot print_timing: id 0 | task 32292 | prompt eval time = 569.35 ms / 489 tokens ( 1.16 ms per token, 858.87 tokens per second) 7.18.341.577 I slot print_timing: id 0 | task 32292 | eval time = 2994.85 ms / 257 tokens ( 11.70 ms per token, 85.48 tokens per second) 7.18.341.578 I slot print_timing: id 0 | task 32292 | total time = 3564.20 ms / 746 tokens 7.18.341.578 I slot print_timing: id 0 | task 32292 | graphs reused = 31782 7.18.341.579 I slot print_timing: id 0 | task 32292 | graph reallocs = 0 / 0 (same size) / (changed size) 7.18.341.616 I slot release: id 0 | task 32292 | stop processing: n_tokens = 745, truncated = 0 7.18.345.470 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 745, t_last = 346693327263 7.18.347.708 I slot launch_slot_: id 0 | task 32551 | processing task, is_child = 0 7.22.071.804 I slot print_timing: id 0 | task 32551 | n_gen = 258, tg = 85.45 t/s, tg_3s = 85.78 t/s 7.25.075.349 I slot print_timing: id 0 | task 32551 | n_gen = 515, tg = 85.51 t/s, tg_3s = 85.57 t/s 7.28.080.959 I slot print_timing: id 0 | task 32551 | n_gen = 771, tg = 85.40 t/s, tg_3s = 85.17 t/s 7.31.058.713 I slot print_timing: id 0 | task 32551 | prompt eval time = 716.54 ms / 550 tokens ( 1.30 ms per token, 767.57 tokens per second) 7.31.058.717 I slot print_timing: id 0 | task 32551 | eval time = 11994.45 ms / 1024 tokens ( 11.72 ms per token, 85.29 tokens per second) 7.31.058.717 I slot print_timing: id 0 | task 32551 | total time = 12710.99 ms / 1574 tokens 7.31.058.718 I slot print_timing: id 0 | task 32551 | graphs reused = 32800 7.31.058.719 I slot print_timing: id 0 | task 32551 | graph reallocs = 0 / 0 (same size) / (changed size) 7.31.058.764 I slot release: id 0 | task 32551 | stop processing: n_tokens = 1573, truncated = 0 7.31.062.339 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1573, t_last = 346706044411 7.31.065.689 I slot launch_slot_: id 0 | task 33578 | processing task, is_child = 0 7.34.496.608 I slot print_timing: id 0 | task 33578 | n_gen = 259, tg = 85.87 t/s, tg_3s = 86.20 t/s 7.36.457.563 I slot print_timing: id 0 | task 33578 | prompt eval time = 426.31 ms / 334 tokens ( 1.28 ms per token, 783.46 tokens per second) 7.36.457.568 I slot print_timing: id 0 | task 33578 | eval time = 4965.55 ms / 427 tokens ( 11.66 ms per token, 85.79 tokens per second) 7.36.457.569 I slot print_timing: id 0 | task 33578 | total time = 5391.87 ms / 761 tokens 7.36.457.569 I slot print_timing: id 0 | task 33578 | graphs reused = 33224 7.36.457.570 I slot print_timing: id 0 | task 33578 | graph reallocs = 0 / 0 (same size) / (changed size) 7.36.457.600 I slot release: id 0 | task 33578 | stop processing: n_tokens = 760, truncated = 0 7.36.461.388 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 760, t_last = 346711443247 7.36.463.647 I slot launch_slot_: id 0 | task 34007 | processing task, is_child = 0 7.39.972.917 I slot print_timing: id 0 | task 34007 | n_gen = 259, tg = 85.69 t/s, tg_3s = 86.03 t/s 7.41.518.511 I slot print_timing: id 0 | task 34007 | prompt eval time = 498.53 ms / 416 tokens ( 1.20 ms per token, 834.46 tokens per second) 7.41.518.517 I slot print_timing: id 0 | task 34007 | eval time = 4556.33 ms / 391 tokens ( 11.68 ms per token, 85.60 tokens per second) 7.41.518.518 I slot print_timing: id 0 | task 34007 | total time = 5054.85 ms / 807 tokens 7.41.518.519 I slot print_timing: id 0 | task 34007 | graphs reused = 33611 7.41.518.520 I slot print_timing: id 0 | task 34007 | graph reallocs = 0 / 0 (same size) / (changed size) 7.41.518.556 I slot release: id 0 | task 34007 | stop processing: n_tokens = 806, truncated = 0 7.41.522.698 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 806, t_last = 346716504203 7.41.524.458 I slot launch_slot_: id 0 | task 34400 | processing task, is_child = 0 7.44.034.527 I slot print_timing: id 0 | task 34400 | prompt eval time = 907.85 ms / 754 tokens ( 1.20 ms per token, 830.53 tokens per second) 7.44.034.531 I slot print_timing: id 0 | task 34400 | eval time = 1602.20 ms / 138 tokens ( 11.69 ms per token, 85.51 tokens per second) 7.44.034.532 I slot print_timing: id 0 | task 34400 | total time = 2510.06 ms / 892 tokens 7.44.034.533 I slot print_timing: id 0 | task 34400 | graphs reused = 33746 7.44.034.533 I slot print_timing: id 0 | task 34400 | graph reallocs = 0 / 0 (same size) / (changed size) 7.44.034.587 I slot release: id 0 | task 34400 | stop processing: n_tokens = 891, truncated = 0 7.44.038.648 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 891, t_last = 346719020234 7.44.040.670 I slot launch_slot_: id 0 | task 34541 | processing task, is_child = 0 7.47.907.465 I slot print_timing: id 0 | task 34541 | n_gen = 258, tg = 85.51 t/s, tg_3s = 85.84 t/s 7.50.709.849 I slot print_timing: id 0 | task 34541 | prompt eval time = 861.25 ms / 706 tokens ( 1.22 ms per token, 819.73 tokens per second) 7.50.709.852 I slot print_timing: id 0 | task 34541 | eval time = 5807.91 ms / 497 tokens ( 11.71 ms per token, 85.40 tokens per second) 7.50.709.853 I slot print_timing: id 0 | task 34541 | total time = 6669.16 ms / 1203 tokens 7.50.709.853 I slot print_timing: id 0 | task 34541 | graphs reused = 34239 7.50.709.854 I slot print_timing: id 0 | task 34541 | graph reallocs = 0 / 0 (same size) / (changed size) 7.50.709.902 I slot release: id 0 | task 34541 | stop processing: n_tokens = 1202, truncated = 0 7.50.713.372 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1202, t_last = 346725695549 7.50.715.948 I slot launch_slot_: id 0 | task 35041 | processing task, is_child = 0 7.54.059.756 I slot print_timing: id 0 | task 35041 | n_gen = 259, tg = 85.88 t/s, tg_3s = 86.21 t/s 7.55.050.748 I slot print_timing: id 0 | task 35041 | prompt eval time = 339.44 ms / 233 tokens ( 1.46 ms per token, 686.42 tokens per second) 7.55.050.754 I slot print_timing: id 0 | task 35041 | eval time = 3995.35 ms / 344 tokens ( 11.65 ms per token, 85.85 tokens per second) 7.55.050.754 I slot print_timing: id 0 | task 35041 | total time = 4334.79 ms / 577 tokens 7.55.050.755 I slot print_timing: id 0 | task 35041 | graphs reused = 34579 7.55.050.755 I slot print_timing: id 0 | task 35041 | graph reallocs = 0 / 0 (same size) / (changed size) 7.55.050.778 I slot release: id 0 | task 35041 | stop processing: n_tokens = 576, truncated = 0 7.55.054.062 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.133 (> 0.100 thold), f_keep = 0.040 7.55.055.403 I slot launch_slot_: id 0 | task 35387 | processing task, is_child = 0 7.58.352.436 I slot print_timing: id 0 | task 35387 | n_gen = 259, tg = 85.81 t/s, tg_3s = 86.14 t/s 7.58.445.815 I slot print_timing: id 0 | task 35387 | prompt eval time = 290.34 ms / 173 tokens ( 1.68 ms per token, 595.86 tokens per second) 7.58.445.824 I slot print_timing: id 0 | task 35387 | eval time = 3100.07 ms / 267 tokens ( 11.65 ms per token, 85.80 tokens per second) 7.58.445.824 I slot print_timing: id 0 | task 35387 | total time = 3390.41 ms / 440 tokens 7.58.445.825 I slot print_timing: id 0 | task 35387 | graphs reused = 34843 7.58.445.826 I slot print_timing: id 0 | task 35387 | graph reallocs = 0 / 0 (same size) / (changed size) 7.58.445.846 I slot release: id 0 | task 35387 | stop processing: n_tokens = 439, truncated = 0 7.58.449.016 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.111 (> 0.100 thold), f_keep = 0.050 7.58.449.507 I slot launch_slot_: id 0 | task 35656 | processing task, is_child = 0 8.01.764.095 I slot print_timing: id 0 | task 35656 | n_gen = 259, tg = 85.91 t/s, tg_3s = 86.24 t/s 8.04.766.395 I slot print_timing: id 0 | task 35656 | n_gen = 516, tg = 85.76 t/s, tg_3s = 85.60 t/s 8.07.771.208 I slot print_timing: id 0 | task 35656 | n_gen = 773, tg = 85.68 t/s, tg_3s = 85.53 t/s 8.10.715.261 I slot print_timing: id 0 | task 35656 | prompt eval time = 311.43 ms / 199 tokens ( 1.56 ms per token, 638.98 tokens per second) 8.10.715.267 I slot print_timing: id 0 | task 35656 | eval time = 11954.32 ms / 1024 tokens ( 11.69 ms per token, 85.58 tokens per second) 8.10.715.268 I slot print_timing: id 0 | task 35656 | total time = 12265.75 ms / 1223 tokens 8.10.715.269 I slot print_timing: id 0 | task 35656 | graphs reused = 35861 8.10.715.269 I slot print_timing: id 0 | task 35656 | graph reallocs = 0 / 0 (same size) / (changed size) 8.10.715.293 I slot release: id 0 | task 35656 | stop processing: n_tokens = 1222, truncated = 0 8.10.718.494 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.148 (> 0.100 thold), f_keep = 0.018 8.10.721.075 I slot launch_slot_: id 0 | task 36682 | processing task, is_child = 0 8.13.636.498 I slot print_timing: id 0 | task 36682 | prompt eval time = 268.19 ms / 149 tokens ( 1.80 ms per token, 555.57 tokens per second) 8.13.636.502 I slot print_timing: id 0 | task 36682 | eval time = 2647.22 ms / 228 tokens ( 11.66 ms per token, 85.75 tokens per second) 8.13.636.502 I slot print_timing: id 0 | task 36682 | total time = 2915.41 ms / 377 tokens 8.13.636.503 I slot print_timing: id 0 | task 36682 | graphs reused = 36086 8.13.636.503 I slot print_timing: id 0 | task 36682 | graph reallocs = 0 / 0 (same size) / (changed size) 8.13.636.521 I slot release: id 0 | task 36682 | stop processing: n_tokens = 376, truncated = 0 8.13.639.709 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 376, t_last = 346748622168 8.13.640.161 I slot launch_slot_: id 0 | task 36912 | processing task, is_child = 0 8.16.969.275 I slot print_timing: id 0 | task 36912 | n_gen = 259, tg = 85.86 t/s, tg_3s = 86.20 t/s 8.19.969.346 I slot print_timing: id 0 | task 36912 | n_gen = 516, tg = 85.76 t/s, tg_3s = 85.66 t/s 8.22.969.984 I slot print_timing: id 0 | task 36912 | n_gen = 773, tg = 85.73 t/s, tg_3s = 85.65 t/s 8.25.911.531 I slot print_timing: id 0 | task 36912 | prompt eval time = 324.33 ms / 216 tokens ( 1.50 ms per token, 665.99 tokens per second) 8.25.911.538 I slot print_timing: id 0 | task 36912 | eval time = 11947.03 ms / 1024 tokens ( 11.68 ms per token, 85.63 tokens per second) 8.25.911.538 I slot print_timing: id 0 | task 36912 | total time = 12271.36 ms / 1240 tokens 8.25.911.539 I slot print_timing: id 0 | task 36912 | graphs reused = 37104 8.25.911.539 I slot print_timing: id 0 | task 36912 | graph reallocs = 0 / 0 (same size) / (changed size) 8.25.911.562 I slot release: id 0 | task 36912 | stop processing: n_tokens = 1239, truncated = 0 8.25.914.720 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.160 (> 0.100 thold), f_keep = 0.017 8.25.917.373 I slot launch_slot_: id 0 | task 37938 | processing task, is_child = 0 8.27.094.050 I slot print_timing: id 0 | task 37938 | prompt eval time = 250.42 ms / 131 tokens ( 1.91 ms per token, 523.13 tokens per second) 8.27.094.056 I slot print_timing: id 0 | task 37938 | eval time = 926.25 ms / 80 tokens ( 11.72 ms per token, 85.29 tokens per second) 8.27.094.057 I slot print_timing: id 0 | task 37938 | total time = 1176.67 ms / 211 tokens 8.27.094.058 I slot print_timing: id 0 | task 37938 | graphs reused = 37182 8.27.094.058 I slot print_timing: id 0 | task 37938 | graph reallocs = 0 / 0 (same size) / (changed size) 8.27.094.078 I slot release: id 0 | task 37938 | stop processing: n_tokens = 210, truncated = 0 8.27.097.213 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.121 (> 0.100 thold), f_keep = 0.100 8.27.097.552 I slot launch_slot_: id 0 | task 38020 | processing task, is_child = 0 8.30.395.061 I slot print_timing: id 0 | task 38020 | n_gen = 259, tg = 85.83 t/s, tg_3s = 86.16 t/s 8.32.496.431 I slot print_timing: id 0 | task 38020 | prompt eval time = 291.48 ms / 174 tokens ( 1.68 ms per token, 596.96 tokens per second) 8.32.496.437 I slot print_timing: id 0 | task 38020 | eval time = 5107.40 ms / 439 tokens ( 11.66 ms per token, 85.76 tokens per second) 8.32.496.438 I slot print_timing: id 0 | task 38020 | total time = 5398.87 ms / 613 tokens 8.32.496.438 I slot print_timing: id 0 | task 38020 | graphs reused = 37617 8.32.496.439 I slot print_timing: id 0 | task 38020 | graph reallocs = 0 / 0 (same size) / (changed size) 8.32.496.459 I slot release: id 0 | task 38020 | stop processing: n_tokens = 612, truncated = 0 8.32.499.667 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.129 (> 0.100 thold), f_keep = 0.034 8.32.501.027 I slot launch_slot_: id 0 | task 38461 | processing task, is_child = 0 8.35.782.980 I slot print_timing: id 0 | task 38461 | n_gen = 259, tg = 85.86 t/s, tg_3s = 86.19 t/s 8.36.504.325 I slot print_timing: id 0 | task 38461 | prompt eval time = 277.00 ms / 163 tokens ( 1.70 ms per token, 588.45 tokens per second) 8.36.504.332 I slot print_timing: id 0 | task 38461 | eval time = 3726.29 ms / 321 tokens ( 11.64 ms per token, 85.88 tokens per second) 8.36.504.332 I slot print_timing: id 0 | task 38461 | total time = 4003.29 ms / 484 tokens 8.36.504.333 I slot print_timing: id 0 | task 38461 | graphs reused = 37935 8.36.504.333 I slot print_timing: id 0 | task 38461 | graph reallocs = 0 / 0 (same size) / (changed size) 8.36.504.353 I slot release: id 0 | task 38461 | stop processing: n_tokens = 483, truncated = 0 8.36.507.355 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.208 (> 0.100 thold), f_keep = 0.043 8.36.507.837 I slot launch_slot_: id 0 | task 38784 | processing task, is_child = 0 8.39.750.075 I slot print_timing: id 0 | task 38784 | n_gen = 259, tg = 85.81 t/s, tg_3s = 86.14 t/s 8.42.759.698 I slot print_timing: id 0 | task 38784 | n_gen = 517, tg = 85.77 t/s, tg_3s = 85.73 t/s 8.45.760.121 I slot print_timing: id 0 | task 38784 | n_gen = 774, tg = 85.73 t/s, tg_3s = 85.65 t/s 8.48.687.684 I slot print_timing: id 0 | task 38784 | prompt eval time = 235.49 ms / 101 tokens ( 2.33 ms per token, 428.89 tokens per second) 8.48.687.690 I slot print_timing: id 0 | task 38784 | eval time = 11944.35 ms / 1024 tokens ( 11.68 ms per token, 85.65 tokens per second) 8.48.687.691 I slot print_timing: id 0 | task 38784 | total time = 12179.84 ms / 1125 tokens 8.48.687.691 I slot print_timing: id 0 | task 38784 | graphs reused = 38953 8.48.687.692 I slot print_timing: id 0 | task 38784 | graph reallocs = 0 / 0 (same size) / (changed size) 8.48.687.708 I slot release: id 0 | task 38784 | stop processing: n_tokens = 1124, truncated = 0 8.48.691.044 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.126 (> 0.100 thold), f_keep = 0.019 8.48.693.449 I slot launch_slot_: id 0 | task 39810 | processing task, is_child = 0 8.51.983.866 I slot print_timing: id 0 | task 39810 | n_gen = 259, tg = 85.93 t/s, tg_3s = 86.26 t/s 8.54.987.132 I slot print_timing: id 0 | task 39810 | n_gen = 516, tg = 85.75 t/s, tg_3s = 85.57 t/s 8.55.407.404 I slot print_timing: id 0 | task 39810 | prompt eval time = 287.82 ms / 167 tokens ( 1.72 ms per token, 580.23 tokens per second) 8.55.407.410 I slot print_timing: id 0 | task 39810 | eval time = 6426.13 ms / 552 tokens ( 11.66 ms per token, 85.74 tokens per second) 8.55.407.411 I slot print_timing: id 0 | task 39810 | total time = 6713.95 ms / 719 tokens 8.55.407.412 I slot print_timing: id 0 | task 39810 | graphs reused = 39501 8.55.407.413 I slot print_timing: id 0 | task 39810 | graph reallocs = 0 / 0 (same size) / (changed size) 8.55.407.433 I slot release: id 0 | task 39810 | stop processing: n_tokens = 718, truncated = 0 8.55.410.684 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.123 (> 0.100 thold), f_keep = 0.029 8.55.412.242 I slot launch_slot_: id 0 | task 40364 | processing task, is_child = 0 8.58.709.272 I slot print_timing: id 0 | task 40364 | n_gen = 259, tg = 85.87 t/s, tg_3s = 86.20 t/s 9.00.530.481 I slot print_timing: id 0 | task 40364 | prompt eval time = 292.49 ms / 171 tokens ( 1.71 ms per token, 584.64 tokens per second) 9.00.530.488 I slot print_timing: id 0 | task 40364 | eval time = 4825.75 ms / 415 tokens ( 11.66 ms per token, 85.79 tokens per second) 9.00.530.488 I slot print_timing: id 0 | task 40364 | total time = 5118.23 ms / 586 tokens 9.00.530.489 I slot print_timing: id 0 | task 40364 | graphs reused = 39912 9.00.530.489 I slot print_timing: id 0 | task 40364 | graph reallocs = 0 / 0 (same size) / (changed size) 9.00.530.510 I slot release: id 0 | task 40364 | stop processing: n_tokens = 585, truncated = 0 9.00.533.495 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.117 (> 0.100 thold), f_keep = 0.036 9.00.534.737 I slot launch_slot_: id 0 | task 40781 | processing task, is_child = 0 9.03.829.459 I slot print_timing: id 0 | task 40781 | n_gen = 259, tg = 85.94 t/s, tg_3s = 86.27 t/s 9.06.838.899 I slot print_timing: id 0 | task 40781 | n_gen = 517, tg = 85.83 t/s, tg_3s = 85.73 t/s 9.09.219.228 I slot print_timing: id 0 | task 40781 | prompt eval time = 292.54 ms / 179 tokens ( 1.63 ms per token, 611.89 tokens per second) 9.09.219.231 I slot print_timing: id 0 | task 40781 | eval time = 8391.95 ms / 721 tokens ( 11.66 ms per token, 85.80 tokens per second) 9.09.219.232 I slot print_timing: id 0 | task 40781 | total time = 8684.48 ms / 900 tokens 9.09.219.232 I slot print_timing: id 0 | task 40781 | graphs reused = 40628 9.09.219.233 I slot print_timing: id 0 | task 40781 | graph reallocs = 0 / 0 (same size) / (changed size) 9.09.219.254 I slot release: id 0 | task 40781 | stop processing: n_tokens = 899, truncated = 0 9.09.222.574 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.127 (> 0.100 thold), f_keep = 0.023 9.09.224.539 I slot launch_slot_: id 0 | task 41504 | processing task, is_child = 0 9.11.841.751 I slot print_timing: id 0 | task 41504 | prompt eval time = 287.21 ms / 165 tokens ( 1.74 ms per token, 574.48 tokens per second) 9.11.841.757 I slot print_timing: id 0 | task 41504 | eval time = 2329.99 ms / 201 tokens ( 11.65 ms per token, 85.84 tokens per second) 9.11.841.757 I slot print_timing: id 0 | task 41504 | total time = 2617.20 ms / 366 tokens 9.11.841.758 I slot print_timing: id 0 | task 41504 | graphs reused = 40826 9.11.841.758 I slot print_timing: id 0 | task 41504 | graph reallocs = 0 / 0 (same size) / (changed size) 9.11.841.777 I slot release: id 0 | task 41504 | stop processing: n_tokens = 365, truncated = 0 9.11.844.968 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.132 (> 0.100 thold), f_keep = 0.058 9.11.845.414 I slot launch_slot_: id 0 | task 41707 | processing task, is_child = 0 9.15.131.301 I slot print_timing: id 0 | task 41707 | n_gen = 260, tg = 86.02 t/s, tg_3s = 86.35 t/s 9.15.807.815 I slot print_timing: id 0 | task 41707 | prompt eval time = 274.96 ms / 159 tokens ( 1.73 ms per token, 578.27 tokens per second) 9.15.807.822 I slot print_timing: id 0 | task 41707 | eval time = 3687.44 ms / 318 tokens ( 11.63 ms per token, 85.97 tokens per second) 9.15.807.823 I slot print_timing: id 0 | task 41707 | total time = 3962.39 ms / 477 tokens 9.15.807.823 I slot print_timing: id 0 | task 41707 | graphs reused = 41141 9.15.807.824 I slot print_timing: id 0 | task 41707 | graph reallocs = 0 / 0 (same size) / (changed size) 9.15.807.844 I slot release: id 0 | task 41707 | stop processing: n_tokens = 476, truncated = 0 9.15.810.978 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.118 (> 0.100 thold), f_keep = 0.044 9.15.812.124 I slot launch_slot_: id 0 | task 42027 | processing task, is_child = 0 9.18.222.708 I slot print_timing: id 0 | task 42027 | prompt eval time = 295.69 ms / 178 tokens ( 1.66 ms per token, 601.98 tokens per second) 9.18.222.714 I slot print_timing: id 0 | task 42027 | eval time = 2114.89 ms / 183 tokens ( 11.62 ms per token, 86.06 tokens per second) 9.18.222.715 I slot print_timing: id 0 | task 42027 | total time = 2410.58 ms / 361 tokens 9.18.222.716 I slot print_timing: id 0 | task 42027 | graphs reused = 41321 9.18.222.716 I slot print_timing: id 0 | task 42027 | graph reallocs = 0 / 0 (same size) / (changed size) 9.18.222.736 I slot release: id 0 | task 42027 | stop processing: n_tokens = 360, truncated = 0 9.18.225.865 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.112 (> 0.100 thold), f_keep = 0.058 9.18.226.812 I slot launch_slot_: id 0 | task 42212 | processing task, is_child = 0 9.21.528.951 I slot print_timing: id 0 | task 42212 | n_gen = 259, tg = 85.99 t/s, tg_3s = 86.32 t/s 9.24.529.126 I slot print_timing: id 0 | task 42212 | n_gen = 516, tg = 85.82 t/s, tg_3s = 85.66 t/s 9.26.095.791 I slot print_timing: id 0 | task 42212 | prompt eval time = 301.63 ms / 188 tokens ( 1.60 ms per token, 623.27 tokens per second) 9.26.095.794 I slot print_timing: id 0 | task 42212 | eval time = 7567.34 ms / 650 tokens ( 11.66 ms per token, 85.76 tokens per second) 9.26.095.795 I slot print_timing: id 0 | task 42212 | total time = 7868.97 ms / 838 tokens 9.26.095.795 I slot print_timing: id 0 | task 42212 | graphs reused = 41966 9.26.095.796 I slot print_timing: id 0 | task 42212 | graph reallocs = 0 / 0 (same size) / (changed size) 9.26.095.823 I slot release: id 0 | task 42212 | stop processing: n_tokens = 837, truncated = 0 9.26.098.855 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.128 (> 0.100 thold), f_keep = 0.025 9.26.100.675 I slot launch_slot_: id 0 | task 42864 | processing task, is_child = 0 9.29.380.157 I slot print_timing: id 0 | task 42864 | n_gen = 259, tg = 85.97 t/s, tg_3s = 86.30 t/s 9.31.214.273 I slot print_timing: id 0 | task 42864 | prompt eval time = 278.39 ms / 164 tokens ( 1.70 ms per token, 589.10 tokens per second) 9.31.214.276 I slot print_timing: id 0 | task 42864 | eval time = 4835.20 ms / 416 tokens ( 11.65 ms per token, 85.83 tokens per second) 9.31.214.277 I slot print_timing: id 0 | task 42864 | total time = 5113.59 ms / 580 tokens 9.31.214.277 I slot print_timing: id 0 | task 42864 | graphs reused = 42378 9.31.214.278 I slot print_timing: id 0 | task 42864 | graph reallocs = 0 / 0 (same size) / (changed size) 9.31.214.305 I slot release: id 0 | task 42864 | stop processing: n_tokens = 579, truncated = 0 9.31.217.565 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.116 (> 0.100 thold), f_keep = 0.036 9.31.218.860 I slot launch_slot_: id 0 | task 43282 | processing task, is_child = 0 9.34.522.705 I slot print_timing: id 0 | task 43282 | n_gen = 259, tg = 85.77 t/s, tg_3s = 86.11 t/s 9.37.524.062 I slot print_timing: id 0 | task 43282 | n_gen = 516, tg = 85.70 t/s, tg_3s = 85.63 t/s 9.39.242.639 I slot print_timing: id 0 | task 43282 | prompt eval time = 295.92 ms / 181 tokens ( 1.63 ms per token, 611.66 tokens per second) 9.39.242.641 I slot print_timing: id 0 | task 43282 | eval time = 7727.85 ms / 663 tokens ( 11.67 ms per token, 85.66 tokens per second) 9.39.242.642 I slot print_timing: id 0 | task 43282 | total time = 8023.77 ms / 844 tokens 9.39.242.643 I slot print_timing: id 0 | task 43282 | graphs reused = 43036 9.39.242.643 I slot print_timing: id 0 | task 43282 | graph reallocs = 0 / 0 (same size) / (changed size) 9.39.242.664 I slot release: id 0 | task 43282 | stop processing: n_tokens = 843, truncated = 0 9.39.245.968 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.136 (> 0.100 thold), f_keep = 0.025 9.39.247.868 I slot launch_slot_: id 0 | task 43947 | processing task, is_child = 0 9.42.363.058 I slot print_timing: id 0 | task 43947 | prompt eval time = 273.02 ms / 154 tokens ( 1.77 ms per token, 564.06 tokens per second) 9.42.363.062 I slot print_timing: id 0 | task 43947 | eval time = 2842.16 ms / 245 tokens ( 11.65 ms per token, 85.85 tokens per second) 9.42.363.062 I slot print_timing: id 0 | task 43947 | total time = 3115.18 ms / 399 tokens 9.42.363.063 I slot print_timing: id 0 | task 43947 | graphs reused = 43278 9.42.363.064 I slot print_timing: id 0 | task 43947 | graph reallocs = 0 / 0 (same size) / (changed size) 9.42.363.082 I slot release: id 0 | task 43947 | stop processing: n_tokens = 398, truncated = 0 9.42.366.560 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.053 9.42.367.555 I slot launch_slot_: id 0 | task 44194 | processing task, is_child = 0 9.44.256.068 I slot print_timing: id 0 | task 44194 | prompt eval time = 259.81 ms / 135 tokens ( 1.92 ms per token, 519.60 tokens per second) 9.44.256.071 I slot print_timing: id 0 | task 44194 | eval time = 1628.69 ms / 141 tokens ( 11.63 ms per token, 85.96 tokens per second) 9.44.256.071 I slot print_timing: id 0 | task 44194 | total time = 1888.50 ms / 276 tokens 9.44.256.072 I slot print_timing: id 0 | task 44194 | graphs reused = 43416 9.44.256.072 I slot print_timing: id 0 | task 44194 | graph reallocs = 0 / 0 (same size) / (changed size) 9.44.256.091 I slot release: id 0 | task 44194 | stop processing: n_tokens = 275, truncated = 0 9.44.259.277 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.117 (> 0.100 thold), f_keep = 0.076 9.44.259.611 I slot launch_slot_: id 0 | task 44337 | processing task, is_child = 0 9.47.561.602 I slot print_timing: id 0 | task 44337 | n_gen = 259, tg = 85.77 t/s, tg_3s = 86.10 t/s 9.49.451.898 I slot print_timing: id 0 | task 44337 | prompt eval time = 293.90 ms / 179 tokens ( 1.64 ms per token, 609.05 tokens per second) 9.49.451.902 I slot print_timing: id 0 | task 44337 | eval time = 4898.38 ms / 421 tokens ( 11.66 ms per token, 85.74 tokens per second) 9.49.451.902 I slot print_timing: id 0 | task 44337 | total time = 5192.28 ms / 600 tokens 9.49.451.903 I slot print_timing: id 0 | task 44337 | graphs reused = 43833 9.49.451.903 I slot print_timing: id 0 | task 44337 | graph reallocs = 0 / 0 (same size) / (changed size) 9.49.451.924 I slot release: id 0 | task 44337 | stop processing: n_tokens = 599, truncated = 0 9.49.455.276 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.119 (> 0.100 thold), f_keep = 0.042 9.49.456.638 I slot launch_slot_: id 0 | task 44760 | processing task, is_child = 0 9.52.784.574 I slot print_timing: id 0 | task 44760 | n_gen = 259, tg = 85.78 t/s, tg_3s = 86.12 t/s 9.54.573.183 I slot print_timing: id 0 | task 44760 | prompt eval time = 320.33 ms / 210 tokens ( 1.53 ms per token, 655.57 tokens per second) 9.54.573.189 I slot print_timing: id 0 | task 44760 | eval time = 4796.21 ms / 412 tokens ( 11.67 ms per token, 85.69 tokens per second) 9.54.573.190 I slot print_timing: id 0 | task 44760 | total time = 5116.54 ms / 622 tokens 9.54.573.190 I slot print_timing: id 0 | task 44760 | graphs reused = 44241 9.54.573.191 I slot print_timing: id 0 | task 44760 | graph reallocs = 0 / 0 (same size) / (changed size) 9.54.573.213 I slot release: id 0 | task 44760 | stop processing: n_tokens = 621, truncated = 0 9.54.576.285 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.165 (> 0.100 thold), f_keep = 0.034 9.54.577.732 I slot launch_slot_: id 0 | task 45174 | processing task, is_child = 0 9.57.835.151 I slot print_timing: id 0 | task 45174 | n_gen = 259, tg = 85.81 t/s, tg_3s = 86.14 t/s 9.58.417.284 I slot print_timing: id 0 | task 45174 | prompt eval time = 250.80 ms / 127 tokens ( 1.97 ms per token, 506.39 tokens per second) 9.58.417.288 I slot print_timing: id 0 | task 45174 | eval time = 3588.74 ms / 309 tokens ( 11.65 ms per token, 85.82 tokens per second) 9.58.417.289 I slot print_timing: id 0 | task 45174 | total time = 3839.54 ms / 436 tokens 9.58.417.289 I slot print_timing: id 0 | task 45174 | graphs reused = 44547 9.58.417.290 I slot print_timing: id 0 | task 45174 | graph reallocs = 0 / 0 (same size) / (changed size) 9.58.417.307 I slot release: id 0 | task 45174 | stop processing: n_tokens = 435, truncated = 0 9.58.420.427 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.152 (> 0.100 thold), f_keep = 0.048 9.58.421.538 I slot launch_slot_: id 0 | task 45485 | processing task, is_child = 0 10.00.794.629 I slot print_timing: id 0 | task 45485 | prompt eval time = 262.96 ms / 138 tokens ( 1.91 ms per token, 524.79 tokens per second) 10.00.794.636 I slot print_timing: id 0 | task 45485 | eval time = 2110.12 ms / 182 tokens ( 11.66 ms per token, 85.78 tokens per second) 10.00.794.636 I slot print_timing: id 0 | task 45485 | total time = 2373.08 ms / 320 tokens 10.00.794.637 I slot print_timing: id 0 | task 45485 | graphs reused = 44726 10.00.794.637 I slot print_timing: id 0 | task 45485 | graph reallocs = 0 / 0 (same size) / (changed size) 10.00.794.657 I slot release: id 0 | task 45485 | stop processing: n_tokens = 319, truncated = 0 10.00.797.661 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.151 (> 0.100 thold), f_keep = 0.066 10.00.798.496 I slot launch_slot_: id 0 | task 45669 | processing task, is_child = 0 10.04.066.845 I slot print_timing: id 0 | task 45669 | n_gen = 259, tg = 85.81 t/s, tg_3s = 86.14 t/s 10.07.070.001 I slot print_timing: id 0 | task 45669 | n_gen = 516, tg = 85.69 t/s, tg_3s = 85.58 t/s 10.07.607.764 I slot print_timing: id 0 | task 45669 | prompt eval time = 261.67 ms / 139 tokens ( 1.88 ms per token, 531.21 tokens per second) 10.07.607.766 I slot print_timing: id 0 | task 45669 | eval time = 6547.59 ms / 562 tokens ( 11.67 ms per token, 85.68 tokens per second) 10.07.607.767 I slot print_timing: id 0 | task 45669 | total time = 6809.26 ms / 701 tokens 10.07.607.768 I slot print_timing: id 0 | task 45669 | graphs reused = 45284 10.07.607.768 I slot print_timing: id 0 | task 45669 | graph reallocs = 0 / 0 (same size) / (changed size) 10.07.607.788 I slot release: id 0 | task 45669 | stop processing: n_tokens = 700, truncated = 0 10.07.610.986 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.134 (> 0.100 thold), f_keep = 0.030 10.07.612.584 I slot launch_slot_: id 0 | task 46233 | processing task, is_child = 0 10.10.773.455 I slot print_timing: id 0 | task 46233 | prompt eval time = 272.55 ms / 157 tokens ( 1.74 ms per token, 576.05 tokens per second) 10.10.773.458 I slot print_timing: id 0 | task 46233 | eval time = 2888.31 ms / 249 tokens ( 11.65 ms per token, 85.86 tokens per second) 10.10.773.458 I slot print_timing: id 0 | task 46233 | total time = 3160.86 ms / 406 tokens 10.10.773.459 I slot print_timing: id 0 | task 46233 | graphs reused = 45530 10.10.773.459 I slot print_timing: id 0 | task 46233 | graph reallocs = 0 / 0 (same size) / (changed size) 10.10.773.482 I slot release: id 0 | task 46233 | stop processing: n_tokens = 405, truncated = 0 10.10.776.650 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.129 (> 0.100 thold), f_keep = 0.052 10.10.777.635 I slot launch_slot_: id 0 | task 46484 | processing task, is_child = 0 10.14.064.280 I slot print_timing: id 0 | task 46484 | n_gen = 259, tg = 85.81 t/s, tg_3s = 86.15 t/s 10.14.192.711 I slot print_timing: id 0 | task 46484 | prompt eval time = 280.11 ms / 163 tokens ( 1.72 ms per token, 581.92 tokens per second) 10.14.192.717 I slot print_timing: id 0 | task 46484 | eval time = 3134.96 ms / 270 tokens ( 11.65 ms per token, 85.81 tokens per second) 10.14.192.717 I slot print_timing: id 0 | task 46484 | total time = 3415.07 ms / 433 tokens 10.14.192.718 I slot print_timing: id 0 | task 46484 | graphs reused = 45797 10.14.192.718 I slot print_timing: id 0 | task 46484 | graph reallocs = 0 / 0 (same size) / (changed size) 10.14.192.738 I slot release: id 0 | task 46484 | stop processing: n_tokens = 432, truncated = 0 10.14.195.984 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.134 (> 0.100 thold), f_keep = 0.049 10.14.197.015 I slot launch_slot_: id 0 | task 46756 | processing task, is_child = 0 10.17.473.056 I slot print_timing: id 0 | task 46756 | n_gen = 259, tg = 85.91 t/s, tg_3s = 86.25 t/s 10.19.797.943 I slot print_timing: id 0 | task 46756 | prompt eval time = 272.98 ms / 157 tokens ( 1.74 ms per token, 575.13 tokens per second) 10.19.797.949 I slot print_timing: id 0 | task 46756 | eval time = 5327.94 ms / 458 tokens ( 11.66 ms per token, 85.77 tokens per second) 10.19.797.949 I slot print_timing: id 0 | task 46756 | total time = 5600.92 ms / 615 tokens 10.19.797.950 I slot print_timing: id 0 | task 46756 | graphs reused = 46251 10.19.797.951 I slot print_timing: id 0 | task 46756 | graph reallocs = 0 / 0 (same size) / (changed size) 10.19.797.969 I slot release: id 0 | task 46756 | stop processing: n_tokens = 614, truncated = 0 10.19.801.131 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.134 (> 0.100 thold), f_keep = 0.034 10.19.802.479 I slot launch_slot_: id 0 | task 47216 | processing task, is_child = 0 10.23.076.409 I slot print_timing: id 0 | task 47216 | n_gen = 259, tg = 85.98 t/s, tg_3s = 86.31 t/s 10.26.080.881 I slot print_timing: id 0 | task 47216 | n_gen = 516, tg = 85.76 t/s, tg_3s = 85.54 t/s 10.26.395.817 I slot print_timing: id 0 | task 47216 | prompt eval time = 273.25 ms / 157 tokens ( 1.74 ms per token, 574.57 tokens per second) 10.26.395.823 I slot print_timing: id 0 | task 47216 | eval time = 6320.07 ms / 543 tokens ( 11.66 ms per token, 85.76 tokens per second) 10.26.395.824 I slot print_timing: id 0 | task 47216 | total time = 6593.32 ms / 700 tokens 10.26.395.824 I slot print_timing: id 0 | task 47216 | graphs reused = 46790 10.26.395.825 I slot print_timing: id 0 | task 47216 | graph reallocs = 0 / 0 (same size) / (changed size) 10.26.395.845 I slot release: id 0 | task 47216 | stop processing: n_tokens = 699, truncated = 0 10.26.399.018 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.134 (> 0.100 thold), f_keep = 0.030 10.26.400.575 I slot launch_slot_: id 0 | task 47761 | processing task, is_child = 0 10.29.675.351 I slot print_timing: id 0 | task 47761 | n_gen = 259, tg = 85.97 t/s, tg_3s = 86.31 t/s 10.29.838.304 I slot print_timing: id 0 | task 47761 | prompt eval time = 273.89 ms / 157 tokens ( 1.74 ms per token, 573.22 tokens per second) 10.29.838.310 I slot print_timing: id 0 | task 47761 | eval time = 3163.83 ms / 273 tokens ( 11.63 ms per token, 85.97 tokens per second) 10.29.838.310 I slot print_timing: id 0 | task 47761 | total time = 3437.72 ms / 430 tokens 10.29.838.311 I slot print_timing: id 0 | task 47761 | graphs reused = 47060 10.29.838.312 I slot print_timing: id 0 | task 47761 | graph reallocs = 0 / 0 (same size) / (changed size) 10.29.838.330 I slot release: id 0 | task 47761 | stop processing: n_tokens = 429, truncated = 0 10.29.841.394 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.122 (> 0.100 thold), f_keep = 0.049 10.29.842.394 I slot launch_slot_: id 0 | task 48036 | processing task, is_child = 0 10.31.086.475 I slot print_timing: id 0 | task 48036 | prompt eval time = 291.07 ms / 172 tokens ( 1.69 ms per token, 590.93 tokens per second) 10.31.086.480 I slot print_timing: id 0 | task 48036 | eval time = 953.01 ms / 83 tokens ( 11.62 ms per token, 86.04 tokens per second) 10.31.086.481 I slot print_timing: id 0 | task 48036 | total time = 1244.07 ms / 255 tokens 10.31.086.482 I slot print_timing: id 0 | task 48036 | graphs reused = 47141 10.31.086.482 I slot print_timing: id 0 | task 48036 | graph reallocs = 0 / 0 (same size) / (changed size) 10.31.086.504 I slot release: id 0 | task 48036 | stop processing: n_tokens = 254, truncated = 0 10.31.089.531 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.135 (> 0.100 thold), f_keep = 0.087 10.31.090.299 I slot launch_slot_: id 0 | task 48121 | processing task, is_child = 0 10.34.365.292 I slot print_timing: id 0 | task 48121 | n_gen = 259, tg = 85.99 t/s, tg_3s = 86.32 t/s 10.34.634.410 I slot print_timing: id 0 | task 48121 | prompt eval time = 274.58 ms / 163 tokens ( 1.68 ms per token, 593.63 tokens per second) 10.34.634.416 I slot print_timing: id 0 | task 48121 | eval time = 3269.52 ms / 282 tokens ( 11.64 ms per token, 85.95 tokens per second) 10.34.634.417 I slot print_timing: id 0 | task 48121 | total time = 3544.10 ms / 445 tokens 10.34.634.417 I slot print_timing: id 0 | task 48121 | graphs reused = 47420 10.34.634.418 I slot print_timing: id 0 | task 48121 | graph reallocs = 0 / 0 (same size) / (changed size) 10.34.634.438 I slot release: id 0 | task 48121 | stop processing: n_tokens = 444, truncated = 0 10.34.637.605 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.127 (> 0.100 thold), f_keep = 0.047 10.34.638.693 I slot launch_slot_: id 0 | task 48405 | processing task, is_child = 0 10.37.929.818 I slot print_timing: id 0 | task 48405 | n_gen = 259, tg = 85.91 t/s, tg_3s = 86.24 t/s 10.40.374.388 I slot print_timing: id 0 | task 48405 | prompt eval time = 287.96 ms / 165 tokens ( 1.75 ms per token, 573.00 tokens per second) 10.40.374.394 I slot print_timing: id 0 | task 48405 | eval time = 5447.73 ms / 468 tokens ( 11.67 ms per token, 85.72 tokens per second) 10.40.374.395 I slot print_timing: id 0 | task 48405 | total time = 5735.69 ms / 633 tokens 10.40.374.395 I slot print_timing: id 0 | task 48405 | graphs reused = 47884 10.40.374.396 I slot print_timing: id 0 | task 48405 | graph reallocs = 0 / 0 (same size) / (changed size) 10.40.374.417 I slot release: id 0 | task 48405 | stop processing: n_tokens = 632, truncated = 0 10.40.377.822 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.121 (> 0.100 thold), f_keep = 0.033 10.40.379.327 I slot launch_slot_: id 0 | task 48875 | processing task, is_child = 0 10.43.292.985 I slot print_timing: id 0 | task 48875 | prompt eval time = 292.27 ms / 173 tokens ( 1.69 ms per token, 591.92 tokens per second) 10.43.292.992 I slot print_timing: id 0 | task 48875 | eval time = 2621.38 ms / 226 tokens ( 11.65 ms per token, 85.83 tokens per second) 10.43.292.993 I slot print_timing: id 0 | task 48875 | total time = 2913.65 ms / 399 tokens 10.43.292.993 I slot print_timing: id 0 | task 48875 | graphs reused = 48107 10.43.292.994 I slot print_timing: id 0 | task 48875 | graph reallocs = 0 / 0 (same size) / (changed size) 10.43.293.014 I slot release: id 0 | task 48875 | stop processing: n_tokens = 398, truncated = 0 10.43.296.479 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.111 (> 0.100 thold), f_keep = 0.053 10.43.297.523 I slot launch_slot_: id 0 | task 49103 | processing task, is_child = 0 10.45.497.828 I slot print_timing: id 0 | task 49103 | prompt eval time = 302.53 ms / 190 tokens ( 1.59 ms per token, 628.03 tokens per second) 10.45.497.834 I slot print_timing: id 0 | task 49103 | eval time = 1897.76 ms / 164 tokens ( 11.64 ms per token, 85.89 tokens per second) 10.45.497.835 I slot print_timing: id 0 | task 49103 | total time = 2200.30 ms / 354 tokens 10.45.497.836 I slot print_timing: id 0 | task 49103 | graphs reused = 48268 10.45.497.836 I slot print_timing: id 0 | task 49103 | graph reallocs = 0 / 0 (same size) / (changed size) 10.45.497.858 I slot release: id 0 | task 49103 | stop processing: n_tokens = 353, truncated = 0 10.45.501.111 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.121 (> 0.100 thold), f_keep = 0.059 10.45.502.065 I slot launch_slot_: id 0 | task 49269 | processing task, is_child = 0 10.48.795.766 I slot print_timing: id 0 | task 49269 | n_gen = 259, tg = 85.97 t/s, tg_3s = 86.30 t/s 10.50.326.133 I slot print_timing: id 0 | task 49269 | prompt eval time = 292.66 ms / 173 tokens ( 1.69 ms per token, 591.13 tokens per second) 10.50.326.137 I slot print_timing: id 0 | task 49269 | eval time = 4531.40 ms / 390 tokens ( 11.65 ms per token, 85.85 tokens per second) 10.50.326.138 I slot print_timing: id 0 | task 49269 | total time = 4824.06 ms / 563 tokens 10.50.326.138 I slot print_timing: id 0 | task 49269 | graphs reused = 48654 10.50.326.139 I slot print_timing: id 0 | task 49269 | graph reallocs = 0 / 0 (same size) / (changed size) 10.50.326.161 I slot release: id 0 | task 49269 | stop processing: n_tokens = 562, truncated = 0 10.50.329.599 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.111 (> 0.100 thold), f_keep = 0.037 10.50.331.061 I slot launch_slot_: id 0 | task 49661 | processing task, is_child = 0 10.53.635.968 I slot print_timing: id 0 | task 49661 | n_gen = 259, tg = 85.81 t/s, tg_3s = 86.14 t/s 10.54.079.335 I slot print_timing: id 0 | task 49661 | prompt eval time = 298.25 ms / 190 tokens ( 1.57 ms per token, 637.05 tokens per second) 10.54.079.340 I slot print_timing: id 0 | task 49661 | eval time = 3450.02 ms / 297 tokens ( 11.66 ms per token, 85.80 tokens per second) 10.54.079.341 I slot print_timing: id 0 | task 49661 | total time = 3748.27 ms / 487 tokens 10.54.079.342 I slot print_timing: id 0 | task 49661 | graphs reused = 48948 10.54.079.342 I slot print_timing: id 0 | task 49661 | graph reallocs = 0 / 0 (same size) / (changed size) 10.54.079.363 I slot release: id 0 | task 49661 | stop processing: n_tokens = 486, truncated = 0 10.54.082.458 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.126 (> 0.100 thold), f_keep = 0.047 10.54.083.584 I slot launch_slot_: id 0 | task 49960 | processing task, is_child = 0 10.57.383.430 I slot print_timing: id 0 | task 49960 | n_gen = 259, tg = 85.87 t/s, tg_3s = 86.20 t/s 11.00.386.931 I slot print_timing: id 0 | task 49960 | n_gen = 516, tg = 85.72 t/s, tg_3s = 85.57 t/s 11.02.235.234 I slot print_timing: id 0 | task 49960 | prompt eval time = 295.34 ms / 183 tokens ( 1.61 ms per token, 619.63 tokens per second) 11.02.235.240 I slot print_timing: id 0 | task 49960 | eval time = 7856.31 ms / 674 tokens ( 11.67 ms per token, 85.66 tokens per second) 11.02.235.241 I slot print_timing: id 0 | task 49960 | total time = 8151.64 ms / 857 tokens 11.02.235.242 I slot print_timing: id 0 | task 49960 | graphs reused = 49617 11.02.235.242 I slot print_timing: id 0 | task 49960 | graph reallocs = 0 / 0 (same size) / (changed size) 11.02.235.262 I slot release: id 0 | task 49960 | stop processing: n_tokens = 856, truncated = 0 11.02.238.365 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 856, t_last = 346917220909 11.02.240.178 I slot launch_slot_: id 0 | task 50636 | processing task, is_child = 0 11.04.949.961 I slot print_timing: id 0 | task 50636 | prompt eval time = 327.96 ms / 222 tokens ( 1.48 ms per token, 676.90 tokens per second) 11.04.949.966 I slot print_timing: id 0 | task 50636 | eval time = 2381.81 ms / 205 tokens ( 11.68 ms per token, 85.65 tokens per second) 11.04.949.966 I slot print_timing: id 0 | task 50636 | total time = 2709.77 ms / 427 tokens 11.04.949.967 I slot print_timing: id 0 | task 50636 | graphs reused = 49819 11.04.949.967 I slot print_timing: id 0 | task 50636 | graph reallocs = 0 / 0 (same size) / (changed size) 11.04.949.989 I slot release: id 0 | task 50636 | stop processing: n_tokens = 426, truncated = 0 11.04.953.098 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.129 (> 0.100 thold), f_keep = 0.049 11.04.954.162 I slot launch_slot_: id 0 | task 50843 | processing task, is_child = 0 11.08.235.038 I slot print_timing: id 0 | task 50843 | n_gen = 259, tg = 85.80 t/s, tg_3s = 86.14 t/s 11.08.420.834 I slot print_timing: id 0 | task 50843 | prompt eval time = 274.03 ms / 163 tokens ( 1.68 ms per token, 594.83 tokens per second) 11.08.420.841 I slot print_timing: id 0 | task 50843 | eval time = 3192.64 ms / 275 tokens ( 11.65 ms per token, 85.82 tokens per second) 11.08.420.841 I slot print_timing: id 0 | task 50843 | total time = 3466.66 ms / 438 tokens 11.08.420.842 I slot print_timing: id 0 | task 50843 | graphs reused = 50091 11.08.420.842 I slot print_timing: id 0 | task 50843 | graph reallocs = 0 / 0 (same size) / (changed size) 11.08.420.862 I slot release: id 0 | task 50843 | stop processing: n_tokens = 437, truncated = 0 11.08.466.704 I srv operator(): operator(): cleaning up before exit...