$ /Users/minipro/quantdiff/llama.cpp/llama-b11770/llama-server -m /Users/minipro/quantdiff/models/campaign/bc1b210bdeec/LFM2.5-24B-A2B-UD-Q2_K_XL.gguf --host 127.0.0.1 --port 8089 -c 4096 -np 1 -ngl 999 -fa on --jinja --seed 1234 --no-webui -a quant 0.00.042.608 I srv llama_server: initializing ... 0.00.042.616 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.042.698 I srv init_listene: The UI is disabled 0.00.042.699 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.042.737 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) 0.00.044.399 I srv load_model: loading model '/Users/minipro/quantdiff/models/campaign/bc1b210bdeec/LFM2.5-24B-A2B-UD-Q2_K_XL.gguf' 0.00.731.660 I cmn init: llama threadpool init, n_threads = 8 0.00.927.891 I srv load_model: initializing, n_slots = 1, n_ctx_slot = 4096, kv_unified = 'false' 0.00.930.256 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.00.930.268 I srv llama_server: model loaded 0.00.930.271 I srv llama_server: listening on http://127.0.0.1:8089 0.02.021.502 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.02.021.735 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.03.669.457 I slot print_timing: id 0 | task 0 | prompt eval time = 431.51 ms / 172 tokens ( 2.51 ms per token, 398.60 tokens per second) 0.03.669.463 I slot print_timing: id 0 | task 0 | eval time = 1216.20 ms / 88 tokens ( 13.98 ms per token, 71.53 tokens per second) 0.03.669.465 I slot print_timing: id 0 | task 0 | total time = 1647.71 ms / 260 tokens 0.03.669.465 I slot print_timing: id 0 | task 0 | graphs reused = 86 0.03.669.466 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.03.669.487 I slot release: id 0 | task 0 | stop processing: n_tokens = 259, truncated = 0 0.03.672.897 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.081 0.03.673.237 I slot launch_slot_: id 0 | task 90 | processing task, is_child = 0 0.04.746.584 I slot print_timing: id 0 | task 90 | prompt eval time = 298.01 ms / 123 tokens ( 2.42 ms per token, 412.74 tokens per second) 0.04.746.590 I slot print_timing: id 0 | task 90 | eval time = 775.33 ms / 56 tokens ( 14.10 ms per token, 70.94 tokens per second) 0.04.746.591 I slot print_timing: id 0 | task 90 | total time = 1073.34 ms / 179 tokens 0.04.746.592 I slot print_timing: id 0 | task 90 | graphs reused = 140 0.04.746.592 I slot print_timing: id 0 | task 90 | graph reallocs = 0 / 0 (same size) / (changed size) 0.04.746.608 I slot release: id 0 | task 90 | stop processing: n_tokens = 178, truncated = 0 0.04.749.699 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.129 (> 0.100 thold), f_keep = 0.118 0.04.750.007 I slot launch_slot_: id 0 | task 148 | processing task, is_child = 0 0.06.342.685 I slot print_timing: id 0 | task 148 | prompt eval time = 334.48 ms / 163 tokens ( 2.05 ms per token, 487.32 tokens per second) 0.06.342.688 I slot print_timing: id 0 | task 148 | eval time = 1258.19 ms / 91 tokens ( 13.98 ms per token, 71.53 tokens per second) 0.06.342.688 I slot print_timing: id 0 | task 148 | total time = 1592.67 ms / 254 tokens 0.06.342.689 I slot print_timing: id 0 | task 148 | graphs reused = 229 0.06.342.690 I slot print_timing: id 0 | task 148 | graph reallocs = 0 / 0 (same size) / (changed size) 0.06.342.710 I slot release: id 0 | task 148 | stop processing: n_tokens = 253, truncated = 0 0.06.346.038 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.103 (> 0.100 thold), f_keep = 0.083 0.06.346.788 I slot launch_slot_: id 0 | task 241 | processing task, is_child = 0 0.09.561.460 I slot print_timing: id 0 | task 241 | prompt eval time = 380.96 ms / 204 tokens ( 1.87 ms per token, 535.49 tokens per second) 0.09.561.463 I slot print_timing: id 0 | task 241 | eval time = 2833.71 ms / 204 tokens ( 13.96 ms per token, 71.64 tokens per second) 0.09.561.464 I slot print_timing: id 0 | task 241 | total time = 3214.66 ms / 408 tokens 0.09.561.465 I slot print_timing: id 0 | task 241 | graphs reused = 430 0.09.561.465 I slot print_timing: id 0 | task 241 | graph reallocs = 0 / 0 (same size) / (changed size) 0.09.561.488 I slot release: id 0 | task 241 | stop processing: n_tokens = 407, truncated = 0 0.09.564.813 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.187 (> 0.100 thold), f_keep = 0.088 0.09.565.795 I slot launch_slot_: id 0 | task 447 | processing task, is_child = 0 0.11.787.581 I slot print_timing: id 0 | task 447 | prompt eval time = 364.61 ms / 193 tokens ( 1.89 ms per token, 529.33 tokens per second) 0.11.787.587 I slot print_timing: id 0 | task 447 | eval time = 1857.16 ms / 134 tokens ( 13.96 ms per token, 71.61 tokens per second) 0.11.787.589 I slot print_timing: id 0 | task 447 | total time = 2221.78 ms / 327 tokens 0.11.787.589 I slot print_timing: id 0 | task 447 | graphs reused = 561 0.11.787.590 I slot print_timing: id 0 | task 447 | graph reallocs = 0 / 0 (same size) / (changed size) 0.11.787.612 I slot release: id 0 | task 447 | stop processing: n_tokens = 326, truncated = 0 0.11.790.974 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.121 (> 0.100 thold), f_keep = 0.064 0.11.791.830 I slot launch_slot_: id 0 | task 583 | processing task, is_child = 0 0.13.872.052 I slot print_timing: id 0 | task 583 | prompt eval time = 353.04 ms / 174 tokens ( 2.03 ms per token, 492.86 tokens per second) 0.13.872.055 I slot print_timing: id 0 | task 583 | eval time = 1727.17 ms / 124 tokens ( 14.04 ms per token, 71.21 tokens per second) 0.13.872.056 I slot print_timing: id 0 | task 583 | total time = 2080.22 ms / 298 tokens 0.13.872.057 I slot print_timing: id 0 | task 583 | graphs reused = 682 0.13.872.057 I slot print_timing: id 0 | task 583 | graph reallocs = 0 / 0 (same size) / (changed size) 0.13.872.077 I slot release: id 0 | task 583 | stop processing: n_tokens = 297, truncated = 0 0.13.875.411 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 297, t_last = 339264990077 0.13.876.192 I slot launch_slot_: id 0 | task 709 | processing task, is_child = 0 0.17.274.135 I slot print_timing: id 0 | task 709 | n_gen = 216, tg = 71.49 t/s, tg_3s = 71.82 t/s 0.17.428.493 I slot print_timing: id 0 | task 709 | prompt eval time = 390.43 ms / 224 tokens ( 1.74 ms per token, 573.72 tokens per second) 0.17.428.496 I slot print_timing: id 0 | task 709 | eval time = 3161.86 ms / 227 tokens ( 13.99 ms per token, 71.48 tokens per second) 0.17.428.497 I slot print_timing: id 0 | task 709 | total time = 3552.29 ms / 451 tokens 0.17.428.497 I slot print_timing: id 0 | task 709 | graphs reused = 906 0.17.428.498 I slot print_timing: id 0 | task 709 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.428.521 I slot release: id 0 | task 709 | stop processing: n_tokens = 450, truncated = 0 0.17.432.348 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 450, t_last = 339268546521 0.17.433.526 I slot launch_slot_: id 0 | task 938 | processing task, is_child = 0 0.20.874.075 I slot print_timing: id 0 | task 938 | n_gen = 216, tg = 71.66 t/s, tg_3s = 71.99 t/s 0.22.285.245 I slot print_timing: id 0 | task 938 | prompt eval time = 440.19 ms / 266 tokens ( 1.65 ms per token, 604.28 tokens per second) 0.22.285.251 I slot print_timing: id 0 | task 938 | eval time = 4411.52 ms / 317 tokens ( 13.96 ms per token, 71.63 tokens per second) 0.22.285.252 I slot print_timing: id 0 | task 938 | total time = 4851.71 ms / 583 tokens 0.22.285.253 I slot print_timing: id 0 | task 938 | graphs reused = 1220 0.22.285.253 I slot print_timing: id 0 | task 938 | graph reallocs = 0 / 0 (same size) / (changed size) 0.22.285.278 I slot release: id 0 | task 938 | stop processing: n_tokens = 582, truncated = 0 0.22.288.711 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.143 (> 0.100 thold), f_keep = 0.036 0.22.290.106 I slot launch_slot_: id 0 | task 1257 | processing task, is_child = 0 0.23.758.962 I slot print_timing: id 0 | task 1257 | prompt eval time = 326.36 ms / 147 tokens ( 2.22 ms per token, 450.42 tokens per second) 0.23.758.968 I slot print_timing: id 0 | task 1257 | eval time = 1142.49 ms / 82 tokens ( 14.10 ms per token, 70.90 tokens per second) 0.23.758.969 I slot print_timing: id 0 | task 1257 | total time = 1468.85 ms / 229 tokens 0.23.758.970 I slot print_timing: id 0 | task 1257 | graphs reused = 1300 0.23.758.970 I slot print_timing: id 0 | task 1257 | graph reallocs = 0 / 0 (same size) / (changed size) 0.23.758.988 I slot release: id 0 | task 1257 | stop processing: n_tokens = 228, truncated = 0 0.23.762.247 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.127 (> 0.100 thold), f_keep = 0.092 0.23.762.961 I slot launch_slot_: id 0 | task 1341 | processing task, is_child = 0 0.26.185.056 I slot print_timing: id 0 | task 1341 | prompt eval time = 347.23 ms / 166 tokens ( 2.09 ms per token, 478.08 tokens per second) 0.26.185.062 I slot print_timing: id 0 | task 1341 | eval time = 2074.86 ms / 149 tokens ( 14.02 ms per token, 71.33 tokens per second) 0.26.185.063 I slot print_timing: id 0 | task 1341 | total time = 2422.09 ms / 315 tokens 0.26.185.064 I slot print_timing: id 0 | task 1341 | graphs reused = 1446 0.26.185.064 I slot print_timing: id 0 | task 1341 | graph reallocs = 0 / 0 (same size) / (changed size) 0.26.185.085 I slot release: id 0 | task 1341 | stop processing: n_tokens = 314, truncated = 0 0.26.188.515 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.120 (> 0.100 thold), f_keep = 0.067 0.26.189.344 I slot launch_slot_: id 0 | task 1492 | processing task, is_child = 0 0.29.046.848 I slot print_timing: id 0 | task 1492 | prompt eval time = 352.92 ms / 175 tokens ( 2.02 ms per token, 495.87 tokens per second) 0.29.046.854 I slot print_timing: id 0 | task 1492 | eval time = 2504.58 ms / 181 tokens ( 13.91 ms per token, 71.87 tokens per second) 0.29.046.855 I slot print_timing: id 0 | task 1492 | total time = 2857.50 ms / 356 tokens 0.29.046.855 I slot print_timing: id 0 | task 1492 | graphs reused = 1624 0.29.046.856 I slot print_timing: id 0 | task 1492 | graph reallocs = 0 / 0 (same size) / (changed size) 0.29.046.877 I slot release: id 0 | task 1492 | stop processing: n_tokens = 355, truncated = 0 0.29.050.315 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 355, t_last = 339280164877 0.29.051.166 I slot launch_slot_: id 0 | task 1675 | processing task, is_child = 0 0.31.423.706 I slot print_timing: id 0 | task 1675 | prompt eval time = 387.16 ms / 215 tokens ( 1.80 ms per token, 555.33 tokens per second) 0.31.423.709 I slot print_timing: id 0 | task 1675 | eval time = 1985.37 ms / 143 tokens ( 13.98 ms per token, 71.52 tokens per second) 0.31.423.710 I slot print_timing: id 0 | task 1675 | total time = 2372.53 ms / 358 tokens 0.31.423.710 I slot print_timing: id 0 | task 1675 | graphs reused = 1764 0.31.423.711 I slot print_timing: id 0 | task 1675 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.423.733 I slot release: id 0 | task 1675 | stop processing: n_tokens = 357, truncated = 0 0.31.427.021 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.119 (> 0.100 thold), f_keep = 0.059 0.31.427.905 I slot launch_slot_: id 0 | task 1820 | processing task, is_child = 0 0.33.673.985 I slot print_timing: id 0 | task 1820 | prompt eval time = 356.73 ms / 177 tokens ( 2.02 ms per token, 496.17 tokens per second) 0.33.673.988 I slot print_timing: id 0 | task 1820 | eval time = 1889.34 ms / 135 tokens ( 14.10 ms per token, 70.92 tokens per second) 0.33.673.989 I slot print_timing: id 0 | task 1820 | total time = 2246.07 ms / 312 tokens 0.33.673.990 I slot print_timing: id 0 | task 1820 | graphs reused = 1896 0.33.673.990 I slot print_timing: id 0 | task 1820 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.674.010 I slot release: id 0 | task 1820 | stop processing: n_tokens = 311, truncated = 0 0.33.677.254 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.116 (> 0.100 thold), f_keep = 0.068 0.33.678.104 I slot launch_slot_: id 0 | task 1957 | processing task, is_child = 0 0.35.515.980 I slot print_timing: id 0 | task 1957 | prompt eval time = 357.96 ms / 181 tokens ( 1.98 ms per token, 505.64 tokens per second) 0.35.515.984 I slot print_timing: id 0 | task 1957 | eval time = 1479.90 ms / 106 tokens ( 14.09 ms per token, 70.95 tokens per second) 0.35.515.984 I slot print_timing: id 0 | task 1957 | total time = 1837.86 ms / 287 tokens 0.35.515.985 I slot print_timing: id 0 | task 1957 | graphs reused = 1999 0.35.515.985 I slot print_timing: id 0 | task 1957 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.516.007 I slot release: id 0 | task 1957 | stop processing: n_tokens = 286, truncated = 0 0.35.519.223 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.122 (> 0.100 thold), f_keep = 0.073 0.35.519.973 I slot launch_slot_: id 0 | task 2065 | processing task, is_child = 0 0.37.365.983 I slot print_timing: id 0 | task 2065 | prompt eval time = 352.97 ms / 172 tokens ( 2.05 ms per token, 487.29 tokens per second) 0.37.365.986 I slot print_timing: id 0 | task 2065 | eval time = 1493.03 ms / 108 tokens ( 13.95 ms per token, 71.67 tokens per second) 0.37.365.987 I slot print_timing: id 0 | task 2065 | total time = 1846.00 ms / 280 tokens 0.37.365.987 I slot print_timing: id 0 | task 2065 | graphs reused = 2104 0.37.365.988 I slot print_timing: id 0 | task 2065 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.366.014 I slot release: id 0 | task 2065 | stop processing: n_tokens = 279, truncated = 0 0.37.369.294 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.138 (> 0.100 thold), f_keep = 0.075 0.37.370.084 I slot launch_slot_: id 0 | task 2175 | processing task, is_child = 0 0.39.244.243 I slot print_timing: id 0 | task 2175 | prompt eval time = 324.85 ms / 152 tokens ( 2.14 ms per token, 467.91 tokens per second) 0.39.244.249 I slot print_timing: id 0 | task 2175 | eval time = 1549.30 ms / 111 tokens ( 14.08 ms per token, 71.00 tokens per second) 0.39.244.250 I slot print_timing: id 0 | task 2175 | total time = 1874.15 ms / 263 tokens 0.39.244.250 I slot print_timing: id 0 | task 2175 | graphs reused = 2212 0.39.244.251 I slot print_timing: id 0 | task 2175 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.244.270 I slot release: id 0 | task 2175 | stop processing: n_tokens = 262, truncated = 0 0.39.247.464 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.123 (> 0.100 thold), f_keep = 0.080 0.39.248.140 I slot launch_slot_: id 0 | task 2288 | processing task, is_child = 0 0.42.607.395 I slot print_timing: id 0 | task 2288 | n_gen = 217, tg = 71.80 t/s, tg_3s = 72.13 t/s 0.44.335.336 I slot print_timing: id 0 | task 2288 | prompt eval time = 350.88 ms / 171 tokens ( 2.05 ms per token, 487.35 tokens per second) 0.44.335.342 I slot print_timing: id 0 | task 2288 | eval time = 4736.31 ms / 341 tokens ( 13.93 ms per token, 71.79 tokens per second) 0.44.335.343 I slot print_timing: id 0 | task 2288 | total time = 5087.19 ms / 512 tokens 0.44.335.343 I slot print_timing: id 0 | task 2288 | graphs reused = 2550 0.44.335.344 I slot print_timing: id 0 | task 2288 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.335.364 I slot release: id 0 | task 2288 | stop processing: n_tokens = 511, truncated = 0 0.44.338.668 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.136 (> 0.100 thold), f_keep = 0.041 0.44.339.859 I slot launch_slot_: id 0 | task 2631 | processing task, is_child = 0 0.46.237.097 I slot print_timing: id 0 | task 2631 | prompt eval time = 331.21 ms / 154 tokens ( 2.15 ms per token, 464.96 tokens per second) 0.46.237.101 I slot print_timing: id 0 | task 2631 | eval time = 1566.02 ms / 112 tokens ( 14.11 ms per token, 70.88 tokens per second) 0.46.237.102 I slot print_timing: id 0 | task 2631 | total time = 1897.23 ms / 266 tokens 0.46.237.102 I slot print_timing: id 0 | task 2631 | graphs reused = 2659 0.46.237.103 I slot print_timing: id 0 | task 2631 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.237.121 I slot release: id 0 | task 2631 | stop processing: n_tokens = 265, truncated = 0 0.46.240.372 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.140 (> 0.100 thold), f_keep = 0.079 0.46.241.045 I slot launch_slot_: id 0 | task 2745 | processing task, is_child = 0 0.47.871.663 I slot print_timing: id 0 | task 2745 | prompt eval time = 323.93 ms / 150 tokens ( 2.16 ms per token, 463.06 tokens per second) 0.47.871.669 I slot print_timing: id 0 | task 2745 | eval time = 1306.68 ms / 94 tokens ( 14.05 ms per token, 71.17 tokens per second) 0.47.871.670 I slot print_timing: id 0 | task 2745 | total time = 1630.61 ms / 244 tokens 0.47.871.670 I slot print_timing: id 0 | task 2745 | graphs reused = 2751 0.47.871.671 I slot print_timing: id 0 | task 2745 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.871.693 I slot release: id 0 | task 2745 | stop processing: n_tokens = 243, truncated = 0 0.47.874.954 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.111 (> 0.100 thold), f_keep = 0.086 0.47.875.653 I slot launch_slot_: id 0 | task 2841 | processing task, is_child = 0 0.49.996.653 I slot print_timing: id 0 | task 2841 | prompt eval time = 362.40 ms / 190 tokens ( 1.91 ms per token, 524.28 tokens per second) 0.49.996.660 I slot print_timing: id 0 | task 2841 | eval time = 1758.59 ms / 127 tokens ( 13.96 ms per token, 71.65 tokens per second) 0.49.996.661 I slot print_timing: id 0 | task 2841 | total time = 2120.99 ms / 317 tokens 0.49.996.662 I slot print_timing: id 0 | task 2841 | graphs reused = 2875 0.49.996.662 I slot print_timing: id 0 | task 2841 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.996.685 I slot release: id 0 | task 2841 | stop processing: n_tokens = 316, truncated = 0 0.49.999.939 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 0.50.000.806 I slot launch_slot_: id 0 | task 2970 | processing task, is_child = 0 0.52.930.273 I slot print_timing: id 0 | task 2970 | prompt eval time = 331.10 ms / 160 tokens ( 2.07 ms per token, 483.24 tokens per second) 0.52.930.276 I slot print_timing: id 0 | task 2970 | eval time = 2598.36 ms / 187 tokens ( 13.97 ms per token, 71.58 tokens per second) 0.52.930.276 I slot print_timing: id 0 | task 2970 | total time = 2929.46 ms / 347 tokens 0.52.930.277 I slot print_timing: id 0 | task 2970 | graphs reused = 3059 0.52.930.278 I slot print_timing: id 0 | task 2970 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.930.299 I slot release: id 0 | task 2970 | stop processing: n_tokens = 346, truncated = 0 0.52.933.746 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 346, t_last = 339304048299 0.52.934.591 I slot launch_slot_: id 0 | task 3159 | processing task, is_child = 0 0.55.002.206 I slot print_timing: id 0 | task 3159 | prompt eval time = 391.19 ms / 218 tokens ( 1.79 ms per token, 557.27 tokens per second) 0.55.002.212 I slot print_timing: id 0 | task 3159 | eval time = 1676.41 ms / 121 tokens ( 13.97 ms per token, 71.58 tokens per second) 0.55.002.212 I slot print_timing: id 0 | task 3159 | total time = 2067.61 ms / 339 tokens 0.55.002.213 I slot print_timing: id 0 | task 3159 | graphs reused = 3177 0.55.002.213 I slot print_timing: id 0 | task 3159 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.002.235 I slot release: id 0 | task 3159 | stop processing: n_tokens = 338, truncated = 0 0.55.005.516 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.109 (> 0.100 thold), f_keep = 0.062 0.55.006.360 I slot launch_slot_: id 0 | task 3282 | processing task, is_child = 0 0.57.756.720 I slot print_timing: id 0 | task 3282 | prompt eval time = 363.17 ms / 193 tokens ( 1.88 ms per token, 531.43 tokens per second) 0.57.756.725 I slot print_timing: id 0 | task 3282 | eval time = 2387.18 ms / 172 tokens ( 13.96 ms per token, 71.63 tokens per second) 0.57.756.725 I slot print_timing: id 0 | task 3282 | total time = 2750.35 ms / 365 tokens 0.57.756.726 I slot print_timing: id 0 | task 3282 | graphs reused = 3346 0.57.756.726 I slot print_timing: id 0 | task 3282 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.756.751 I slot release: id 0 | task 3282 | stop processing: n_tokens = 364, truncated = 0 0.57.760.047 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.104 (> 0.100 thold), f_keep = 0.058 0.57.761.010 I slot launch_slot_: id 0 | task 3456 | processing task, is_child = 0 1.01.143.235 I slot print_timing: id 0 | task 3456 | n_gen = 216, tg = 71.56 t/s, tg_3s = 71.89 t/s 1.01.537.500 I slot print_timing: id 0 | task 3456 | prompt eval time = 377.54 ms / 201 tokens ( 1.88 ms per token, 532.40 tokens per second) 1.01.537.505 I slot print_timing: id 0 | task 3456 | eval time = 3398.95 ms / 244 tokens ( 13.99 ms per token, 71.49 tokens per second) 1.01.537.505 I slot print_timing: id 0 | task 3456 | total time = 3776.48 ms / 445 tokens 1.01.537.506 I slot print_timing: id 0 | task 3456 | graphs reused = 3587 1.01.537.507 I slot print_timing: id 0 | task 3456 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.537.532 I slot release: id 0 | task 3456 | stop processing: n_tokens = 444, truncated = 0 1.01.540.877 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 444, t_last = 339312655532 1.01.541.943 I slot launch_slot_: id 0 | task 3702 | processing task, is_child = 0 1.04.963.345 I slot print_timing: id 0 | task 3702 | n_gen = 216, tg = 71.48 t/s, tg_3s = 71.81 t/s 1.07.970.746 I slot print_timing: id 0 | task 3702 | n_gen = 431, tg = 71.49 t/s, tg_3s = 71.49 t/s 1.08.965.981 I slot print_timing: id 0 | task 3702 | prompt eval time = 413.57 ms / 237 tokens ( 1.75 ms per token, 573.05 tokens per second) 1.08.965.987 I slot print_timing: id 0 | task 3702 | eval time = 7010.46 ms / 502 tokens ( 13.99 ms per token, 71.46 tokens per second) 1.08.965.988 I slot print_timing: id 0 | task 3702 | total time = 7424.03 ms / 739 tokens 1.08.965.989 I slot print_timing: id 0 | task 3702 | graphs reused = 4085 1.08.965.989 I slot print_timing: id 0 | task 3702 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.966.017 I slot release: id 0 | task 3702 | stop processing: n_tokens = 738, truncated = 0 1.08.969.490 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.112 (> 0.100 thold), f_keep = 0.030 1.08.971.053 I slot launch_slot_: id 0 | task 4206 | processing task, is_child = 0 1.11.001.844 I slot print_timing: id 0 | task 4206 | prompt eval time = 364.57 ms / 196 tokens ( 1.86 ms per token, 537.62 tokens per second) 1.11.001.850 I slot print_timing: id 0 | task 4206 | eval time = 1666.21 ms / 120 tokens ( 14.00 ms per token, 71.42 tokens per second) 1.11.001.851 I slot print_timing: id 0 | task 4206 | total time = 2030.78 ms / 316 tokens 1.11.001.851 I slot print_timing: id 0 | task 4206 | graphs reused = 4202 1.11.001.852 I slot print_timing: id 0 | task 4206 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.001.875 I slot release: id 0 | task 4206 | stop processing: n_tokens = 315, truncated = 0 1.11.005.080 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.139 (> 0.100 thold), f_keep = 0.067 1.11.005.887 I slot launch_slot_: id 0 | task 4328 | processing task, is_child = 0 1.12.551.549 I slot print_timing: id 0 | task 4328 | prompt eval time = 332.53 ms / 151 tokens ( 2.20 ms per token, 454.09 tokens per second) 1.12.551.554 I slot print_timing: id 0 | task 4328 | eval time = 1213.12 ms / 88 tokens ( 13.94 ms per token, 71.72 tokens per second) 1.12.551.555 I slot print_timing: id 0 | task 4328 | total time = 1545.65 ms / 239 tokens 1.12.551.555 I slot print_timing: id 0 | task 4328 | graphs reused = 4288 1.12.551.556 I slot print_timing: id 0 | task 4328 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.551.574 I slot release: id 0 | task 4328 | stop processing: n_tokens = 238, truncated = 0 1.12.554.704 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 1.12.555.388 I slot launch_slot_: id 0 | task 4418 | processing task, is_child = 0 1.14.842.220 I slot print_timing: id 0 | task 4418 | prompt eval time = 357.89 ms / 180 tokens ( 1.99 ms per token, 502.94 tokens per second) 1.14.842.226 I slot print_timing: id 0 | task 4418 | eval time = 1928.93 ms / 139 tokens ( 13.98 ms per token, 71.54 tokens per second) 1.14.842.226 I slot print_timing: id 0 | task 4418 | total time = 2286.82 ms / 319 tokens 1.14.842.227 I slot print_timing: id 0 | task 4418 | graphs reused = 4424 1.14.842.228 I slot print_timing: id 0 | task 4418 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.842.265 I slot release: id 0 | task 4418 | stop processing: n_tokens = 318, truncated = 0 1.14.845.509 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 318, t_last = 339325960266 1.14.846.336 I slot launch_slot_: id 0 | task 4559 | processing task, is_child = 0 1.17.038.415 I slot print_timing: id 0 | task 4559 | prompt eval time = 389.22 ms / 211 tokens ( 1.84 ms per token, 542.11 tokens per second) 1.17.038.425 I slot print_timing: id 0 | task 4559 | eval time = 1802.85 ms / 130 tokens ( 13.98 ms per token, 71.55 tokens per second) 1.17.038.425 I slot print_timing: id 0 | task 4559 | total time = 2192.07 ms / 341 tokens 1.17.038.426 I slot print_timing: id 0 | task 4559 | graphs reused = 4551 1.17.038.426 I slot print_timing: id 0 | task 4559 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.038.450 I slot release: id 0 | task 4559 | stop processing: n_tokens = 340, truncated = 0 1.17.041.751 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.113 (> 0.100 thold), f_keep = 0.062 1.17.042.652 I slot launch_slot_: id 0 | task 4691 | processing task, is_child = 0 1.19.069.329 I slot print_timing: id 0 | task 4691 | prompt eval time = 365.97 ms / 186 tokens ( 1.97 ms per token, 508.23 tokens per second) 1.19.069.334 I slot print_timing: id 0 | task 4691 | eval time = 1660.70 ms / 119 tokens ( 14.07 ms per token, 71.05 tokens per second) 1.19.069.335 I slot print_timing: id 0 | task 4691 | total time = 2026.67 ms / 305 tokens 1.19.069.336 I slot print_timing: id 0 | task 4691 | graphs reused = 4667 1.19.069.336 I slot print_timing: id 0 | task 4691 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.069.357 I slot release: id 0 | task 4691 | stop processing: n_tokens = 304, truncated = 0 1.19.072.629 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.128 (> 0.100 thold), f_keep = 0.069 1.19.073.448 I slot launch_slot_: id 0 | task 4812 | processing task, is_child = 0 1.20.977.989 I slot print_timing: id 0 | task 4812 | prompt eval time = 338.47 ms / 164 tokens ( 2.06 ms per token, 484.53 tokens per second) 1.20.977.995 I slot print_timing: id 0 | task 4812 | eval time = 1566.06 ms / 113 tokens ( 13.98 ms per token, 71.52 tokens per second) 1.20.977.996 I slot print_timing: id 0 | task 4812 | total time = 1904.53 ms / 277 tokens 1.20.977.996 I slot print_timing: id 0 | task 4812 | graphs reused = 4777 1.20.977.997 I slot print_timing: id 0 | task 4812 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.978.018 I slot release: id 0 | task 4812 | stop processing: n_tokens = 276, truncated = 0 1.20.981.252 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.130 (> 0.100 thold), f_keep = 0.076 1.20.982.017 I slot launch_slot_: id 0 | task 4927 | processing task, is_child = 0 1.22.647.216 I slot print_timing: id 0 | task 4927 | prompt eval time = 337.17 ms / 162 tokens ( 2.08 ms per token, 480.47 tokens per second) 1.22.647.222 I slot print_timing: id 0 | task 4927 | eval time = 1328.02 ms / 96 tokens ( 13.98 ms per token, 71.53 tokens per second) 1.22.647.223 I slot print_timing: id 0 | task 4927 | total time = 1665.19 ms / 258 tokens 1.22.647.223 I slot print_timing: id 0 | task 4927 | graphs reused = 4870 1.22.647.224 I slot print_timing: id 0 | task 4927 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.647.244 I slot release: id 0 | task 4927 | stop processing: n_tokens = 257, truncated = 0 1.22.650.474 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.111 (> 0.100 thold), f_keep = 0.082 1.22.651.195 I slot launch_slot_: id 0 | task 5025 | processing task, is_child = 0 1.25.472.572 I slot print_timing: id 0 | task 5025 | prompt eval time = 365.19 ms / 190 tokens ( 1.92 ms per token, 520.28 tokens per second) 1.25.472.578 I slot print_timing: id 0 | task 5025 | eval time = 2456.18 ms / 177 tokens ( 13.96 ms per token, 71.66 tokens per second) 1.25.472.578 I slot print_timing: id 0 | task 5025 | total time = 2821.37 ms / 367 tokens 1.25.472.579 I slot print_timing: id 0 | task 5025 | graphs reused = 5044 1.25.472.580 I slot print_timing: id 0 | task 5025 | graph reallocs = 0 / 0 (same size) / (changed size) 1.25.472.604 I slot release: id 0 | task 5025 | stop processing: n_tokens = 366, truncated = 0 1.25.475.850 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.102 (> 0.100 thold), f_keep = 0.057 1.25.476.744 I slot launch_slot_: id 0 | task 5204 | processing task, is_child = 0 1.27.615.762 I slot print_timing: id 0 | task 5204 | prompt eval time = 384.94 ms / 206 tokens ( 1.87 ms per token, 535.15 tokens per second) 1.27.615.765 I slot print_timing: id 0 | task 5204 | eval time = 1754.07 ms / 126 tokens ( 14.03 ms per token, 71.26 tokens per second) 1.27.615.766 I slot print_timing: id 0 | task 5204 | total time = 2139.01 ms / 332 tokens 1.27.615.766 I slot print_timing: id 0 | task 5204 | graphs reused = 5167 1.27.615.767 I slot print_timing: id 0 | task 5204 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.615.796 I slot release: id 0 | task 5204 | stop processing: n_tokens = 331, truncated = 0 1.27.618.937 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.134 (> 0.100 thold), f_keep = 0.063 1.27.619.752 I slot launch_slot_: id 0 | task 5332 | processing task, is_child = 0 1.29.757.078 I slot print_timing: id 0 | task 5332 | prompt eval time = 333.85 ms / 157 tokens ( 2.13 ms per token, 470.27 tokens per second) 1.29.757.084 I slot print_timing: id 0 | task 5332 | eval time = 1803.47 ms / 130 tokens ( 13.98 ms per token, 71.53 tokens per second) 1.29.757.085 I slot print_timing: id 0 | task 5332 | total time = 2137.32 ms / 287 tokens 1.29.757.085 I slot print_timing: id 0 | task 5332 | graphs reused = 5294 1.29.757.086 I slot print_timing: id 0 | task 5332 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.757.105 I slot release: id 0 | task 5332 | stop processing: n_tokens = 286, truncated = 0 1.29.760.524 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.106 (> 0.100 thold), f_keep = 0.073 1.29.761.302 I slot launch_slot_: id 0 | task 5464 | processing task, is_child = 0 1.33.150.575 I slot print_timing: id 0 | task 5464 | n_gen = 216, tg = 71.42 t/s, tg_3s = 71.75 t/s 1.36.159.781 I slot print_timing: id 0 | task 5464 | n_gen = 431, tg = 71.43 t/s, tg_3s = 71.45 t/s 1.36.777.444 I slot print_timing: id 0 | task 5464 | prompt eval time = 378.73 ms / 198 tokens ( 1.91 ms per token, 522.80 tokens per second) 1.36.777.450 I slot print_timing: id 0 | task 5464 | eval time = 6637.40 ms / 475 tokens ( 14.00 ms per token, 71.41 tokens per second) 1.36.777.451 I slot print_timing: id 0 | task 5464 | total time = 7016.13 ms / 673 tokens 1.36.777.451 I slot print_timing: id 0 | task 5464 | graphs reused = 5765 1.36.777.452 I slot print_timing: id 0 | task 5464 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.777.475 I slot release: id 0 | task 5464 | stop processing: n_tokens = 672, truncated = 0 1.36.780.732 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.168 (> 0.100 thold), f_keep = 0.031 1.36.782.177 I slot launch_slot_: id 0 | task 5941 | processing task, is_child = 0 1.38.821.147 I slot print_timing: id 0 | task 5941 | prompt eval time = 309.59 ms / 125 tokens ( 2.48 ms per token, 403.76 tokens per second) 1.38.821.153 I slot print_timing: id 0 | task 5941 | eval time = 1729.37 ms / 125 tokens ( 13.95 ms per token, 71.70 tokens per second) 1.38.821.154 I slot print_timing: id 0 | task 5941 | total time = 2038.96 ms / 250 tokens 1.38.821.155 I slot print_timing: id 0 | task 5941 | graphs reused = 5888 1.38.821.155 I slot print_timing: id 0 | task 5941 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.821.172 I slot release: id 0 | task 5941 | stop processing: n_tokens = 249, truncated = 0 1.38.824.367 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.157 (> 0.100 thold), f_keep = 0.084 1.38.825.063 I slot launch_slot_: id 0 | task 6068 | processing task, is_child = 0 1.42.157.169 I slot print_timing: id 0 | task 6068 | n_gen = 216, tg = 71.34 t/s, tg_3s = 71.67 t/s 1.42.241.237 I slot print_timing: id 0 | task 6068 | prompt eval time = 318.23 ms / 134 tokens ( 2.37 ms per token, 421.08 tokens per second) 1.42.241.243 I slot print_timing: id 0 | task 6068 | eval time = 3097.93 ms / 222 tokens ( 14.02 ms per token, 71.34 tokens per second) 1.42.241.243 I slot print_timing: id 0 | task 6068 | total time = 3416.17 ms / 356 tokens 1.42.241.244 I slot print_timing: id 0 | task 6068 | graphs reused = 6107 1.42.241.245 I slot print_timing: id 0 | task 6068 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.241.267 I slot release: id 0 | task 6068 | stop processing: n_tokens = 355, truncated = 0 1.42.244.534 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.142 (> 0.100 thold), f_keep = 0.059 1.42.245.418 I slot launch_slot_: id 0 | task 6292 | processing task, is_child = 0 1.43.982.710 I slot print_timing: id 0 | task 6292 | prompt eval time = 329.43 ms / 148 tokens ( 2.23 ms per token, 449.26 tokens per second) 1.43.982.717 I slot print_timing: id 0 | task 6292 | eval time = 1407.85 ms / 102 tokens ( 13.94 ms per token, 71.74 tokens per second) 1.43.982.718 I slot print_timing: id 0 | task 6292 | total time = 1737.29 ms / 250 tokens 1.43.982.719 I slot print_timing: id 0 | task 6292 | graphs reused = 6207 1.43.982.719 I slot print_timing: id 0 | task 6292 | graph reallocs = 0 / 0 (same size) / (changed size) 1.43.982.738 I slot release: id 0 | task 6292 | stop processing: n_tokens = 249, truncated = 0 1.43.985.781 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.149 (> 0.100 thold), f_keep = 0.084 1.43.986.463 I slot launch_slot_: id 0 | task 6396 | processing task, is_child = 0 1.45.273.313 I slot print_timing: id 0 | task 6396 | prompt eval time = 323.75 ms / 141 tokens ( 2.30 ms per token, 435.52 tokens per second) 1.45.273.317 I slot print_timing: id 0 | task 6396 | eval time = 963.08 ms / 70 tokens ( 13.96 ms per token, 71.64 tokens per second) 1.45.273.317 I slot print_timing: id 0 | task 6396 | total time = 1286.84 ms / 211 tokens 1.45.273.318 I slot print_timing: id 0 | task 6396 | graphs reused = 6275 1.45.273.318 I slot print_timing: id 0 | task 6396 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.273.337 I slot release: id 0 | task 6396 | stop processing: n_tokens = 210, truncated = 0 1.45.276.498 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 1.45.277.068 I slot launch_slot_: id 0 | task 6468 | processing task, is_child = 0 1.47.900.832 I slot print_timing: id 0 | task 6468 | prompt eval time = 365.03 ms / 196 tokens ( 1.86 ms per token, 536.95 tokens per second) 1.47.900.837 I slot print_timing: id 0 | task 6468 | eval time = 2258.73 ms / 163 tokens ( 13.94 ms per token, 71.72 tokens per second) 1.47.900.838 I slot print_timing: id 0 | task 6468 | total time = 2623.76 ms / 359 tokens 1.47.900.839 I slot print_timing: id 0 | task 6468 | graphs reused = 6435 1.47.900.839 I slot print_timing: id 0 | task 6468 | graph reallocs = 0 / 0 (same size) / (changed size) 1.47.900.870 I slot release: id 0 | task 6468 | stop processing: n_tokens = 358, truncated = 0 1.47.904.317 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 358, t_last = 339359018871 1.47.905.180 I slot launch_slot_: id 0 | task 6633 | processing task, is_child = 0 1.51.413.470 I slot print_timing: id 0 | task 6633 | n_gen = 216, tg = 71.48 t/s, tg_3s = 71.81 t/s 1.52.506.341 I slot print_timing: id 0 | task 6633 | prompt eval time = 500.46 ms / 328 tokens ( 1.53 ms per token, 655.40 tokens per second) 1.52.506.345 I slot print_timing: id 0 | task 6633 | eval time = 4100.70 ms / 294 tokens ( 14.00 ms per token, 71.45 tokens per second) 1.52.506.346 I slot print_timing: id 0 | task 6633 | total time = 4601.15 ms / 622 tokens 1.52.506.346 I slot print_timing: id 0 | task 6633 | graphs reused = 6726 1.52.506.347 I slot print_timing: id 0 | task 6633 | graph reallocs = 0 / 0 (same size) / (changed size) 1.52.506.375 I slot release: id 0 | task 6633 | stop processing: n_tokens = 621, truncated = 0 1.52.509.644 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.143 (> 0.100 thold), f_keep = 0.034 1.52.511.080 I slot launch_slot_: id 0 | task 6929 | processing task, is_child = 0 1.53.842.691 I slot print_timing: id 0 | task 6929 | prompt eval time = 328.34 ms / 147 tokens ( 2.23 ms per token, 447.71 tokens per second) 1.53.842.695 I slot print_timing: id 0 | task 6929 | eval time = 1003.26 ms / 73 tokens ( 13.93 ms per token, 71.77 tokens per second) 1.53.842.695 I slot print_timing: id 0 | task 6929 | total time = 1331.60 ms / 220 tokens 1.53.842.696 I slot print_timing: id 0 | task 6929 | graphs reused = 6797 1.53.842.697 I slot print_timing: id 0 | task 6929 | graph reallocs = 0 / 0 (same size) / (changed size) 1.53.842.715 I slot release: id 0 | task 6929 | stop processing: n_tokens = 219, truncated = 0 1.53.845.862 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 1.53.846.486 I slot launch_slot_: id 0 | task 7004 | processing task, is_child = 0 1.55.560.765 I slot print_timing: id 0 | task 7004 | prompt eval time = 358.72 ms / 182 tokens ( 1.97 ms per token, 507.36 tokens per second) 1.55.560.771 I slot print_timing: id 0 | task 7004 | eval time = 1355.55 ms / 97 tokens ( 14.12 ms per token, 70.82 tokens per second) 1.55.560.772 I slot print_timing: id 0 | task 7004 | total time = 1714.27 ms / 279 tokens 1.55.560.773 I slot print_timing: id 0 | task 7004 | graphs reused = 6891 1.55.560.773 I slot print_timing: id 0 | task 7004 | graph reallocs = 0 / 0 (same size) / (changed size) 1.55.560.793 I slot release: id 0 | task 7004 | stop processing: n_tokens = 278, truncated = 0 1.55.563.984 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 278, t_last = 339366678794 1.55.564.720 I slot launch_slot_: id 0 | task 7103 | processing task, is_child = 0 1.57.387.456 I slot print_timing: id 0 | task 7103 | prompt eval time = 406.31 ms / 230 tokens ( 1.77 ms per token, 566.07 tokens per second) 1.57.387.459 I slot print_timing: id 0 | task 7103 | eval time = 1416.41 ms / 102 tokens ( 14.02 ms per token, 71.31 tokens per second) 1.57.387.460 I slot print_timing: id 0 | task 7103 | total time = 1822.72 ms / 332 tokens 1.57.387.461 I slot print_timing: id 0 | task 7103 | graphs reused = 6990 1.57.387.461 I slot print_timing: id 0 | task 7103 | graph reallocs = 0 / 0 (same size) / (changed size) 1.57.387.487 I slot release: id 0 | task 7103 | stop processing: n_tokens = 331, truncated = 0 1.57.390.928 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 331, t_last = 339368505488 1.57.391.775 I slot launch_slot_: id 0 | task 7207 | processing task, is_child = 0 1.59.787.844 I slot print_timing: id 0 | task 7207 | prompt eval time = 411.06 ms / 239 tokens ( 1.72 ms per token, 581.42 tokens per second) 1.59.787.849 I slot print_timing: id 0 | task 7207 | eval time = 1984.99 ms / 143 tokens ( 13.98 ms per token, 71.54 tokens per second) 1.59.787.850 I slot print_timing: id 0 | task 7207 | total time = 2396.06 ms / 382 tokens 1.59.787.851 I slot print_timing: id 0 | task 7207 | graphs reused = 7130 1.59.787.851 I slot print_timing: id 0 | task 7207 | graph reallocs = 0 / 0 (same size) / (changed size) 1.59.787.878 I slot release: id 0 | task 7207 | stop processing: n_tokens = 381, truncated = 0 1.59.791.031 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.151 (> 0.100 thold), f_keep = 0.063 1.59.791.964 I slot launch_slot_: id 0 | task 7352 | processing task, is_child = 0 2.01.344.087 I slot print_timing: id 0 | task 7352 | prompt eval time = 331.25 ms / 159 tokens ( 2.08 ms per token, 480.01 tokens per second) 2.01.344.095 I slot print_timing: id 0 | task 7352 | eval time = 1220.87 ms / 88 tokens ( 14.03 ms per token, 71.26 tokens per second) 2.01.344.095 I slot print_timing: id 0 | task 7352 | total time = 1552.11 ms / 247 tokens 2.01.344.096 I slot print_timing: id 0 | task 7352 | graphs reused = 7216 2.01.344.096 I slot print_timing: id 0 | task 7352 | graph reallocs = 0 / 0 (same size) / (changed size) 2.01.344.117 I slot release: id 0 | task 7352 | stop processing: n_tokens = 246, truncated = 0 2.01.347.267 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.125 (> 0.100 thold), f_keep = 0.085 2.01.347.981 I slot launch_slot_: id 0 | task 7442 | processing task, is_child = 0 2.04.468.734 I slot print_timing: id 0 | task 7442 | prompt eval time = 354.81 ms / 168 tokens ( 2.11 ms per token, 473.49 tokens per second) 2.04.468.738 I slot print_timing: id 0 | task 7442 | eval time = 2765.93 ms / 199 tokens ( 13.97 ms per token, 71.59 tokens per second) 2.04.468.738 I slot print_timing: id 0 | task 7442 | total time = 3120.74 ms / 367 tokens 2.04.468.739 I slot print_timing: id 0 | task 7442 | graphs reused = 7412 2.04.468.740 I slot print_timing: id 0 | task 7442 | graph reallocs = 0 / 0 (same size) / (changed size) 2.04.468.760 I slot release: id 0 | task 7442 | stop processing: n_tokens = 366, truncated = 0 2.04.471.963 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.119 (> 0.100 thold), f_keep = 0.057 2.04.472.837 I slot launch_slot_: id 0 | task 7643 | processing task, is_child = 0 2.06.313.112 I slot print_timing: id 0 | task 7643 | prompt eval time = 357.83 ms / 177 tokens ( 2.02 ms per token, 494.65 tokens per second) 2.06.313.118 I slot print_timing: id 0 | task 7643 | eval time = 1482.44 ms / 107 tokens ( 13.99 ms per token, 71.50 tokens per second) 2.06.313.119 I slot print_timing: id 0 | task 7643 | total time = 1840.27 ms / 284 tokens 2.06.313.120 I slot print_timing: id 0 | task 7643 | graphs reused = 7516 2.06.313.120 I slot print_timing: id 0 | task 7643 | graph reallocs = 0 / 0 (same size) / (changed size) 2.06.313.141 I slot release: id 0 | task 7643 | stop processing: n_tokens = 283, truncated = 0 2.06.316.530 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.101 (> 0.100 thold), f_keep = 0.074 2.06.317.279 I slot launch_slot_: id 0 | task 7752 | processing task, is_child = 0 2.08.952.273 I slot print_timing: id 0 | task 7752 | prompt eval time = 384.75 ms / 208 tokens ( 1.85 ms per token, 540.61 tokens per second) 2.08.952.277 I slot print_timing: id 0 | task 7752 | eval time = 2250.23 ms / 162 tokens ( 13.98 ms per token, 71.55 tokens per second) 2.08.952.278 I slot print_timing: id 0 | task 7752 | total time = 2634.99 ms / 370 tokens 2.08.952.279 I slot print_timing: id 0 | task 7752 | graphs reused = 7675 2.08.952.279 I slot print_timing: id 0 | task 7752 | graph reallocs = 0 / 0 (same size) / (changed size) 2.08.952.310 I slot release: id 0 | task 7752 | stop processing: n_tokens = 369, truncated = 0 2.08.955.750 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.131 (> 0.100 thold), f_keep = 0.057 2.08.956.740 I slot launch_slot_: id 0 | task 7916 | processing task, is_child = 0 2.11.327.960 I slot print_timing: id 0 | task 7916 | prompt eval time = 334.69 ms / 160 tokens ( 2.09 ms per token, 478.05 tokens per second) 2.11.327.966 I slot print_timing: id 0 | task 7916 | eval time = 2036.52 ms / 146 tokens ( 14.04 ms per token, 71.20 tokens per second) 2.11.327.966 I slot print_timing: id 0 | task 7916 | total time = 2371.21 ms / 306 tokens 2.11.327.967 I slot print_timing: id 0 | task 7916 | graphs reused = 7818 2.11.327.968 I slot print_timing: id 0 | task 7916 | graph reallocs = 0 / 0 (same size) / (changed size) 2.11.327.987 I slot release: id 0 | task 7916 | stop processing: n_tokens = 305, truncated = 0 2.11.331.361 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 305, t_last = 339382445987 2.11.332.206 I slot launch_slot_: id 0 | task 8064 | processing task, is_child = 0 2.14.724.864 I slot print_timing: id 0 | task 8064 | n_gen = 216, tg = 71.60 t/s, tg_3s = 71.93 t/s 2.15.270.005 I slot print_timing: id 0 | task 8064 | prompt eval time = 389.72 ms / 219 tokens ( 1.78 ms per token, 561.94 tokens per second) 2.15.270.011 I slot print_timing: id 0 | task 8064 | eval time = 3548.07 ms / 255 tokens ( 13.97 ms per token, 71.59 tokens per second) 2.15.270.011 I slot print_timing: id 0 | task 8064 | total time = 3937.79 ms / 474 tokens 2.15.270.012 I slot print_timing: id 0 | task 8064 | graphs reused = 8070 2.15.270.012 I slot print_timing: id 0 | task 8064 | graph reallocs = 0 / 0 (same size) / (changed size) 2.15.270.036 I slot release: id 0 | task 8064 | stop processing: n_tokens = 473, truncated = 0 2.15.273.417 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.124 (> 0.100 thold), f_keep = 0.044 2.15.274.589 I slot launch_slot_: id 0 | task 8321 | processing task, is_child = 0 2.17.741.779 I slot print_timing: id 0 | task 8321 | prompt eval time = 350.26 ms / 170 tokens ( 2.06 ms per token, 485.36 tokens per second) 2.17.741.784 I slot print_timing: id 0 | task 8321 | eval time = 2116.92 ms / 152 tokens ( 14.02 ms per token, 71.33 tokens per second) 2.17.741.785 I slot print_timing: id 0 | task 8321 | total time = 2467.18 ms / 322 tokens 2.17.741.786 I slot print_timing: id 0 | task 8321 | graphs reused = 8219 2.17.741.786 I slot print_timing: id 0 | task 8321 | graph reallocs = 0 / 0 (same size) / (changed size) 2.17.741.807 I slot release: id 0 | task 8321 | stop processing: n_tokens = 321, truncated = 0 2.17.745.106 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.124 (> 0.100 thold), f_keep = 0.065 2.17.745.915 I slot launch_slot_: id 0 | task 8475 | processing task, is_child = 0 2.20.475.254 I slot print_timing: id 0 | task 8475 | prompt eval time = 353.29 ms / 169 tokens ( 2.09 ms per token, 478.37 tokens per second) 2.20.475.260 I slot print_timing: id 0 | task 8475 | eval time = 2376.04 ms / 171 tokens ( 13.98 ms per token, 71.55 tokens per second) 2.20.475.260 I slot print_timing: id 0 | task 8475 | total time = 2729.33 ms / 340 tokens 2.20.475.261 I slot print_timing: id 0 | task 8475 | graphs reused = 8387 2.20.475.262 I slot print_timing: id 0 | task 8475 | graph reallocs = 0 / 0 (same size) / (changed size) 2.20.475.283 I slot release: id 0 | task 8475 | stop processing: n_tokens = 339, truncated = 0 2.20.478.785 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 339, t_last = 339391593283 2.20.479.656 I slot launch_slot_: id 0 | task 8648 | processing task, is_child = 0 2.23.449.802 I slot print_timing: id 0 | task 8648 | prompt eval time = 455.63 ms / 287 tokens ( 1.59 ms per token, 629.90 tokens per second) 2.23.449.808 I slot print_timing: id 0 | task 8648 | eval time = 2514.51 ms / 181 tokens ( 13.97 ms per token, 71.58 tokens per second) 2.23.449.809 I slot print_timing: id 0 | task 8648 | total time = 2970.14 ms / 468 tokens 2.23.449.809 I slot print_timing: id 0 | task 8648 | graphs reused = 8566 2.23.449.810 I slot print_timing: id 0 | task 8648 | graph reallocs = 0 / 0 (same size) / (changed size) 2.23.449.842 I slot release: id 0 | task 8648 | stop processing: n_tokens = 467, truncated = 0 2.23.453.280 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 467, t_last = 339394567842 2.23.454.443 I slot launch_slot_: id 0 | task 8831 | processing task, is_child = 0 2.26.460.040 I slot print_timing: id 0 | task 8831 | prompt eval time = 423.96 ms / 255 tokens ( 1.66 ms per token, 601.47 tokens per second) 2.26.460.046 I slot print_timing: id 0 | task 8831 | eval time = 2581.63 ms / 186 tokens ( 13.95 ms per token, 71.66 tokens per second) 2.26.460.046 I slot print_timing: id 0 | task 8831 | total time = 3005.59 ms / 441 tokens 2.26.460.047 I slot print_timing: id 0 | task 8831 | graphs reused = 8749 2.26.460.047 I slot print_timing: id 0 | task 8831 | graph reallocs = 0 / 0 (same size) / (changed size) 2.26.460.073 I slot release: id 0 | task 8831 | stop processing: n_tokens = 440, truncated = 0 2.26.463.413 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.129 (> 0.100 thold), f_keep = 0.048 2.26.464.563 I slot launch_slot_: id 0 | task 9019 | processing task, is_child = 0 2.28.154.169 I slot print_timing: id 0 | task 9019 | prompt eval time = 339.60 ms / 163 tokens ( 2.08 ms per token, 479.98 tokens per second) 2.28.154.175 I slot print_timing: id 0 | task 9019 | eval time = 1350.00 ms / 97 tokens ( 14.06 ms per token, 71.11 tokens per second) 2.28.154.176 I slot print_timing: id 0 | task 9019 | total time = 1689.60 ms / 260 tokens 2.28.154.176 I slot print_timing: id 0 | task 9019 | graphs reused = 8843 2.28.154.177 I slot print_timing: id 0 | task 9019 | graph reallocs = 0 / 0 (same size) / (changed size) 2.28.154.201 I slot release: id 0 | task 9019 | stop processing: n_tokens = 259, truncated = 0 2.28.157.427 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.104 (> 0.100 thold), f_keep = 0.081 2.28.158.175 I slot launch_slot_: id 0 | task 9118 | processing task, is_child = 0 2.30.005.616 I slot print_timing: id 0 | task 9118 | prompt eval time = 380.44 ms / 201 tokens ( 1.89 ms per token, 528.33 tokens per second) 2.30.005.622 I slot print_timing: id 0 | task 9118 | eval time = 1466.99 ms / 106 tokens ( 13.97 ms per token, 71.58 tokens per second) 2.30.005.622 I slot print_timing: id 0 | task 9118 | total time = 1847.43 ms / 307 tokens 2.30.005.623 I slot print_timing: id 0 | task 9118 | graphs reused = 8946 2.30.005.623 I slot print_timing: id 0 | task 9118 | graph reallocs = 0 / 0 (same size) / (changed size) 2.30.005.647 I slot release: id 0 | task 9118 | stop processing: n_tokens = 306, truncated = 0 2.30.008.858 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.134 (> 0.100 thold), f_keep = 0.069 2.30.009.617 I slot launch_slot_: id 0 | task 9226 | processing task, is_child = 0 2.31.408.691 I slot print_timing: id 0 | task 9226 | prompt eval time = 331.62 ms / 157 tokens ( 2.11 ms per token, 473.43 tokens per second) 2.31.408.698 I slot print_timing: id 0 | task 9226 | eval time = 1067.45 ms / 77 tokens ( 14.05 ms per token, 71.20 tokens per second) 2.31.408.698 I slot print_timing: id 0 | task 9226 | total time = 1399.07 ms / 234 tokens 2.31.408.699 I slot print_timing: id 0 | task 9226 | graphs reused = 9021 2.31.408.699 I slot print_timing: id 0 | task 9226 | graph reallocs = 0 / 0 (same size) / (changed size) 2.31.408.719 I slot release: id 0 | task 9226 | stop processing: n_tokens = 233, truncated = 0 2.31.411.965 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 233, t_last = 339402526719 2.31.412.616 I slot launch_slot_: id 0 | task 9305 | processing task, is_child = 0 2.33.751.745 I slot print_timing: id 0 | task 9305 | prompt eval time = 396.24 ms / 226 tokens ( 1.75 ms per token, 570.37 tokens per second) 2.33.751.751 I slot print_timing: id 0 | task 9305 | eval time = 1942.88 ms / 140 tokens ( 13.98 ms per token, 71.54 tokens per second) 2.33.751.752 I slot print_timing: id 0 | task 9305 | total time = 2339.12 ms / 366 tokens 2.33.751.753 I slot print_timing: id 0 | task 9305 | graphs reused = 9158 2.33.751.753 I slot print_timing: id 0 | task 9305 | graph reallocs = 0 / 0 (same size) / (changed size) 2.33.751.777 I slot release: id 0 | task 9305 | stop processing: n_tokens = 365, truncated = 0 2.33.755.506 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 365, t_last = 339404869777 2.33.756.461 I slot launch_slot_: id 0 | task 9447 | processing task, is_child = 0 2.37.275.886 I slot print_timing: id 0 | task 9447 | n_gen = 215, tg = 71.30 t/s, tg_3s = 71.64 t/s 2.37.779.707 I slot print_timing: id 0 | task 9447 | prompt eval time = 518.11 ms / 356 tokens ( 1.46 ms per token, 687.12 tokens per second) 2.37.779.713 I slot print_timing: id 0 | task 9447 | eval time = 3505.13 ms / 251 tokens ( 14.02 ms per token, 71.32 tokens per second) 2.37.779.714 I slot print_timing: id 0 | task 9447 | total time = 4023.24 ms / 607 tokens 2.37.779.715 I slot print_timing: id 0 | task 9447 | graphs reused = 9406 2.37.779.715 I slot print_timing: id 0 | task 9447 | graph reallocs = 0 / 0 (same size) / (changed size) 2.37.779.746 I slot release: id 0 | task 9447 | stop processing: n_tokens = 606, truncated = 0 2.37.783.569 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 606, t_last = 339408897747 2.37.784.915 I slot launch_slot_: id 0 | task 9700 | processing task, is_child = 0 2.41.310.123 I slot print_timing: id 0 | task 9700 | prompt eval time = 598.59 ms / 427 tokens ( 1.40 ms per token, 713.34 tokens per second) 2.41.310.129 I slot print_timing: id 0 | task 9700 | eval time = 2926.61 ms / 210 tokens ( 14.00 ms per token, 71.41 tokens per second) 2.41.310.130 I slot print_timing: id 0 | task 9700 | total time = 3525.20 ms / 637 tokens 2.41.310.131 I slot print_timing: id 0 | task 9700 | graphs reused = 9613 2.41.310.131 I slot print_timing: id 0 | task 9700 | graph reallocs = 0 / 0 (same size) / (changed size) 2.41.310.164 I slot release: id 0 | task 9700 | stop processing: n_tokens = 636, truncated = 0 2.41.314.188 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 636, t_last = 339412428164 2.41.315.649 I slot launch_slot_: id 0 | task 9912 | processing task, is_child = 0 2.43.981.816 I slot print_timing: id 0 | task 9912 | prompt eval time = 648.90 ms / 481 tokens ( 1.35 ms per token, 741.26 tokens per second) 2.43.981.822 I slot print_timing: id 0 | task 9912 | eval time = 2017.26 ms / 145 tokens ( 14.01 ms per token, 71.38 tokens per second) 2.43.981.822 I slot print_timing: id 0 | task 9912 | total time = 2666.16 ms / 626 tokens 2.43.981.823 I slot print_timing: id 0 | task 9912 | graphs reused = 9755 2.43.981.824 I slot print_timing: id 0 | task 9912 | graph reallocs = 0 / 0 (same size) / (changed size) 2.43.981.863 I slot release: id 0 | task 9912 | stop processing: n_tokens = 625, truncated = 0 2.43.985.487 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 625, t_last = 339415099863 2.43.986.885 I slot launch_slot_: id 0 | task 10059 | processing task, is_child = 0 2.47.623.623 I slot print_timing: id 0 | task 10059 | n_gen = 216, tg = 71.58 t/s, tg_3s = 71.91 t/s 2.48.183.157 I slot print_timing: id 0 | task 10059 | prompt eval time = 632.89 ms / 456 tokens ( 1.39 ms per token, 720.50 tokens per second) 2.48.183.163 I slot print_timing: id 0 | task 10059 | eval time = 3563.37 ms / 256 tokens ( 13.97 ms per token, 71.56 tokens per second) 2.48.183.164 I slot print_timing: id 0 | task 10059 | total time = 4196.26 ms / 712 tokens 2.48.183.164 I slot print_timing: id 0 | task 10059 | graphs reused = 10008 2.48.183.165 I slot print_timing: id 0 | task 10059 | graph reallocs = 0 / 0 (same size) / (changed size) 2.48.183.203 I slot release: id 0 | task 10059 | stop processing: n_tokens = 711, truncated = 0 2.48.186.910 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 711, t_last = 339419301203 2.48.188.564 I slot launch_slot_: id 0 | task 10317 | processing task, is_child = 0 2.49.718.745 I slot print_timing: id 0 | task 10317 | prompt eval time = 454.81 ms / 290 tokens ( 1.57 ms per token, 637.63 tokens per second) 2.49.718.752 I slot print_timing: id 0 | task 10317 | eval time = 1075.37 ms / 77 tokens ( 14.15 ms per token, 70.67 tokens per second) 2.49.718.753 I slot print_timing: id 0 | task 10317 | total time = 1530.17 ms / 367 tokens 2.49.718.754 I slot print_timing: id 0 | task 10317 | graphs reused = 10083 2.49.718.754 I slot print_timing: id 0 | task 10317 | graph reallocs = 0 / 0 (same size) / (changed size) 2.49.718.780 I slot release: id 0 | task 10317 | stop processing: n_tokens = 366, truncated = 0 2.49.722.670 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 366, t_last = 339420836780 2.49.723.613 I slot launch_slot_: id 0 | task 10396 | processing task, is_child = 0 2.53.336.096 I slot print_timing: id 0 | task 10396 | n_gen = 216, tg = 71.53 t/s, tg_3s = 71.86 t/s 2.56.349.926 I slot print_timing: id 0 | task 10396 | n_gen = 432, tg = 71.60 t/s, tg_3s = 71.67 t/s 2.59.131.883 I slot print_timing: id 0 | task 10396 | prompt eval time = 606.76 ms / 439 tokens ( 1.38 ms per token, 723.51 tokens per second) 2.59.131.886 I slot print_timing: id 0 | task 10396 | eval time = 8801.50 ms / 631 tokens ( 13.97 ms per token, 71.58 tokens per second) 2.59.131.886 I slot print_timing: id 0 | task 10396 | total time = 9408.26 ms / 1070 tokens 2.59.131.887 I slot print_timing: id 0 | task 10396 | graphs reused = 10709 2.59.131.887 I slot print_timing: id 0 | task 10396 | graph reallocs = 0 / 0 (same size) / (changed size) 2.59.131.924 I slot release: id 0 | task 10396 | stop processing: n_tokens = 1069, truncated = 0 2.59.135.731 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1069, t_last = 339430249924 2.59.137.967 I slot launch_slot_: id 0 | task 11029 | processing task, is_child = 0 3.02.713.911 I slot print_timing: id 0 | task 11029 | n_gen = 216, tg = 71.41 t/s, tg_3s = 71.74 t/s 3.05.722.709 I slot print_timing: id 0 | task 11029 | n_gen = 431, tg = 71.43 t/s, tg_3s = 71.46 t/s 3.08.732.419 I slot print_timing: id 0 | task 11029 | n_gen = 646, tg = 71.43 t/s, tg_3s = 71.44 t/s 3.11.286.890 I slot print_timing: id 0 | task 11029 | prompt eval time = 565.07 ms / 396 tokens ( 1.43 ms per token, 700.79 tokens per second) 3.11.286.895 I slot print_timing: id 0 | task 11029 | eval time = 11583.84 ms / 828 tokens ( 14.01 ms per token, 71.39 tokens per second) 3.11.286.896 I slot print_timing: id 0 | task 11029 | total time = 12148.91 ms / 1224 tokens 3.11.286.897 I slot print_timing: id 0 | task 11029 | graphs reused = 11532 3.11.286.897 I slot print_timing: id 0 | task 11029 | graph reallocs = 0 / 0 (same size) / (changed size) 3.11.286.933 I slot release: id 0 | task 11029 | stop processing: n_tokens = 1223, truncated = 0 3.11.290.776 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1223, t_last = 339442404933 3.11.293.222 I slot launch_slot_: id 0 | task 11859 | processing task, is_child = 0 3.12.738.357 I slot print_timing: id 0 | task 11859 | prompt eval time = 509.96 ms / 342 tokens ( 1.49 ms per token, 670.64 tokens per second) 3.12.738.363 I slot print_timing: id 0 | task 11859 | eval time = 935.17 ms / 68 tokens ( 13.96 ms per token, 71.64 tokens per second) 3.12.738.364 I slot print_timing: id 0 | task 11859 | total time = 1445.13 ms / 410 tokens 3.12.738.364 I slot print_timing: id 0 | task 11859 | graphs reused = 11598 3.12.738.365 I slot print_timing: id 0 | task 11859 | graph reallocs = 0 / 0 (same size) / (changed size) 3.12.738.397 I slot release: id 0 | task 11859 | stop processing: n_tokens = 409, truncated = 0 3.12.742.070 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 339443856397 3.12.743.152 I slot launch_slot_: id 0 | task 11929 | processing task, is_child = 0 3.14.960.212 I slot print_timing: id 0 | task 11929 | prompt eval time = 483.41 ms / 314 tokens ( 1.54 ms per token, 649.55 tokens per second) 3.14.960.218 I slot print_timing: id 0 | task 11929 | eval time = 1733.64 ms / 125 tokens ( 13.98 ms per token, 71.53 tokens per second) 3.14.960.219 I slot print_timing: id 0 | task 11929 | total time = 2217.05 ms / 439 tokens 3.14.960.219 I slot print_timing: id 0 | task 11929 | graphs reused = 11721 3.14.960.220 I slot print_timing: id 0 | task 11929 | graph reallocs = 0 / 0 (same size) / (changed size) 3.14.960.250 I slot release: id 0 | task 11929 | stop processing: n_tokens = 438, truncated = 0 3.14.964.065 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 438, t_last = 339446078250 3.14.965.176 I slot launch_slot_: id 0 | task 12056 | processing task, is_child = 0 3.17.079.159 I slot print_timing: id 0 | task 12056 | prompt eval time = 567.64 ms / 396 tokens ( 1.43 ms per token, 697.63 tokens per second) 3.17.079.165 I slot print_timing: id 0 | task 12056 | eval time = 1546.34 ms / 111 tokens ( 14.06 ms per token, 71.14 tokens per second) 3.17.079.166 I slot print_timing: id 0 | task 12056 | total time = 2113.97 ms / 507 tokens 3.17.079.167 I slot print_timing: id 0 | task 12056 | graphs reused = 11830 3.17.079.168 I slot print_timing: id 0 | task 12056 | graph reallocs = 0 / 0 (same size) / (changed size) 3.17.079.202 I slot release: id 0 | task 12056 | stop processing: n_tokens = 506, truncated = 0 3.17.082.922 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 506, t_last = 339448197202 3.17.084.191 I slot launch_slot_: id 0 | task 12169 | processing task, is_child = 0 3.19.211.984 I slot print_timing: id 0 | task 12169 | prompt eval time = 507.15 ms / 339 tokens ( 1.50 ms per token, 668.44 tokens per second) 3.19.211.990 I slot print_timing: id 0 | task 12169 | eval time = 1620.63 ms / 117 tokens ( 13.97 ms per token, 71.58 tokens per second) 3.19.211.991 I slot print_timing: id 0 | task 12169 | total time = 2127.78 ms / 456 tokens 3.19.211.991 I slot print_timing: id 0 | task 12169 | graphs reused = 11945 3.19.211.992 I slot print_timing: id 0 | task 12169 | graph reallocs = 0 / 0 (same size) / (changed size) 3.19.212.030 I slot release: id 0 | task 12169 | stop processing: n_tokens = 455, truncated = 0 3.19.215.534 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 455, t_last = 339450330030 3.19.216.623 I slot launch_slot_: id 0 | task 12288 | processing task, is_child = 0 3.20.842.520 I slot print_timing: id 0 | task 12288 | prompt eval time = 443.69 ms / 267 tokens ( 1.66 ms per token, 601.76 tokens per second) 3.20.842.526 I slot print_timing: id 0 | task 12288 | eval time = 1182.19 ms / 85 tokens ( 14.07 ms per token, 71.05 tokens per second) 3.20.842.527 I slot print_timing: id 0 | task 12288 | total time = 1625.89 ms / 352 tokens 3.20.842.527 I slot print_timing: id 0 | task 12288 | graphs reused = 12028 3.20.842.528 I slot print_timing: id 0 | task 12288 | graph reallocs = 0 / 0 (same size) / (changed size) 3.20.842.558 I slot release: id 0 | task 12288 | stop processing: n_tokens = 351, truncated = 0 3.20.846.199 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 351, t_last = 339451960559 3.20.847.134 I slot launch_slot_: id 0 | task 12375 | processing task, is_child = 0 3.23.764.749 I slot print_timing: id 0 | task 12375 | prompt eval time = 531.64 ms / 360 tokens ( 1.48 ms per token, 677.15 tokens per second) 3.23.764.753 I slot print_timing: id 0 | task 12375 | eval time = 2385.97 ms / 171 tokens ( 14.04 ms per token, 71.25 tokens per second) 3.23.764.754 I slot print_timing: id 0 | task 12375 | total time = 2917.61 ms / 531 tokens 3.23.764.754 I slot print_timing: id 0 | task 12375 | graphs reused = 12196 3.23.764.755 I slot print_timing: id 0 | task 12375 | graph reallocs = 0 / 0 (same size) / (changed size) 3.23.764.786 I slot release: id 0 | task 12375 | stop processing: n_tokens = 530, truncated = 0 3.23.768.339 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 530, t_last = 339454882786 3.23.769.565 I slot launch_slot_: id 0 | task 12548 | processing task, is_child = 0 3.25.643.627 I slot print_timing: id 0 | task 12548 | prompt eval time = 470.62 ms / 296 tokens ( 1.59 ms per token, 628.96 tokens per second) 3.25.643.632 I slot print_timing: id 0 | task 12548 | eval time = 1403.44 ms / 101 tokens ( 14.03 ms per token, 71.25 tokens per second) 3.25.643.633 I slot print_timing: id 0 | task 12548 | total time = 1874.05 ms / 397 tokens 3.25.643.633 I slot print_timing: id 0 | task 12548 | graphs reused = 12295 3.25.643.634 I slot print_timing: id 0 | task 12548 | graph reallocs = 0 / 0 (same size) / (changed size) 3.25.643.660 I slot release: id 0 | task 12548 | stop processing: n_tokens = 396, truncated = 0 3.25.647.233 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 396, t_last = 339456761660 3.25.648.214 I slot launch_slot_: id 0 | task 12651 | processing task, is_child = 0 3.27.816.968 I slot print_timing: id 0 | task 12651 | prompt eval time = 448.67 ms / 275 tokens ( 1.63 ms per token, 612.92 tokens per second) 3.27.816.974 I slot print_timing: id 0 | task 12651 | eval time = 1720.07 ms / 124 tokens ( 13.98 ms per token, 71.51 tokens per second) 3.27.816.974 I slot print_timing: id 0 | task 12651 | total time = 2168.75 ms / 399 tokens 3.27.816.975 I slot print_timing: id 0 | task 12651 | graphs reused = 12417 3.27.816.976 I slot print_timing: id 0 | task 12651 | graph reallocs = 0 / 0 (same size) / (changed size) 3.27.817.005 I slot release: id 0 | task 12651 | stop processing: n_tokens = 398, truncated = 0 3.27.820.634 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 398, t_last = 339458935005 3.27.821.637 I slot launch_slot_: id 0 | task 12777 | processing task, is_child = 0 3.29.415.504 I slot print_timing: id 0 | task 12777 | prompt eval time = 453.93 ms / 287 tokens ( 1.58 ms per token, 632.25 tokens per second) 3.29.415.510 I slot print_timing: id 0 | task 12777 | eval time = 1139.92 ms / 82 tokens ( 14.07 ms per token, 71.06 tokens per second) 3.29.415.510 I slot print_timing: id 0 | task 12777 | total time = 1593.86 ms / 369 tokens 3.29.415.511 I slot print_timing: id 0 | task 12777 | graphs reused = 12497 3.29.415.512 I slot print_timing: id 0 | task 12777 | graph reallocs = 0 / 0 (same size) / (changed size) 3.29.415.543 I slot release: id 0 | task 12777 | stop processing: n_tokens = 368, truncated = 0 3.29.418.983 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 368, t_last = 339460533543 3.29.419.924 I slot launch_slot_: id 0 | task 12861 | processing task, is_child = 0 3.30.827.491 I slot print_timing: id 0 | task 12861 | prompt eval time = 441.74 ms / 266 tokens ( 1.66 ms per token, 602.17 tokens per second) 3.30.827.497 I slot print_timing: id 0 | task 12861 | eval time = 965.82 ms / 70 tokens ( 14.00 ms per token, 71.44 tokens per second) 3.30.827.498 I slot print_timing: id 0 | task 12861 | total time = 1407.56 ms / 336 tokens 3.30.827.498 I slot print_timing: id 0 | task 12861 | graphs reused = 12565 3.30.827.499 I slot print_timing: id 0 | task 12861 | graph reallocs = 0 / 0 (same size) / (changed size) 3.30.827.524 I slot release: id 0 | task 12861 | stop processing: n_tokens = 335, truncated = 0 3.30.831.284 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 335, t_last = 339461945524 3.30.832.206 I slot launch_slot_: id 0 | task 12933 | processing task, is_child = 0 3.33.119.337 I slot print_timing: id 0 | task 12933 | prompt eval time = 603.53 ms / 435 tokens ( 1.39 ms per token, 720.76 tokens per second) 3.33.119.344 I slot print_timing: id 0 | task 12933 | eval time = 1683.60 ms / 121 tokens ( 14.03 ms per token, 71.28 tokens per second) 3.33.119.345 I slot print_timing: id 0 | task 12933 | total time = 2287.12 ms / 556 tokens 3.33.119.346 I slot print_timing: id 0 | task 12933 | graphs reused = 12683 3.33.119.347 I slot print_timing: id 0 | task 12933 | graph reallocs = 0 / 0 (same size) / (changed size) 3.33.119.380 I slot release: id 0 | task 12933 | stop processing: n_tokens = 555, truncated = 0 3.33.123.134 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 555, t_last = 339464237380 3.33.124.597 I slot launch_slot_: id 0 | task 13056 | processing task, is_child = 0 3.36.068.494 I slot print_timing: id 0 | task 13056 | prompt eval time = 475.50 ms / 307 tokens ( 1.55 ms per token, 645.64 tokens per second) 3.36.068.500 I slot print_timing: id 0 | task 13056 | eval time = 2468.39 ms / 177 tokens ( 14.02 ms per token, 71.30 tokens per second) 3.36.068.501 I slot print_timing: id 0 | task 13056 | total time = 2943.89 ms / 484 tokens 3.36.068.501 I slot print_timing: id 0 | task 13056 | graphs reused = 12858 3.36.068.502 I slot print_timing: id 0 | task 13056 | graph reallocs = 0 / 0 (same size) / (changed size) 3.36.068.533 I slot release: id 0 | task 13056 | stop processing: n_tokens = 483, truncated = 0 3.36.072.632 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 483, t_last = 339467186533 3.36.073.797 I slot launch_slot_: id 0 | task 13235 | processing task, is_child = 0 3.40.060.923 I slot print_timing: id 0 | task 13235 | n_gen = 216, tg = 71.53 t/s, tg_3s = 71.86 t/s 3.40.776.763 I slot print_timing: id 0 | task 13235 | prompt eval time = 981.35 ms / 675 tokens ( 1.45 ms per token, 687.83 tokens per second) 3.40.776.769 I slot print_timing: id 0 | task 13235 | eval time = 3721.61 ms / 267 tokens ( 13.99 ms per token, 71.47 tokens per second) 3.40.776.770 I slot print_timing: id 0 | task 13235 | total time = 4702.96 ms / 942 tokens 3.40.776.770 I slot print_timing: id 0 | task 13235 | graphs reused = 13122 3.40.776.771 I slot print_timing: id 0 | task 13235 | graph reallocs = 0 / 0 (same size) / (changed size) 3.40.776.818 I slot release: id 0 | task 13235 | stop processing: n_tokens = 941, truncated = 0 3.40.780.432 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 941, t_last = 339471894818 3.40.782.484 I slot launch_slot_: id 0 | task 13505 | processing task, is_child = 0 3.42.439.357 I slot print_timing: id 0 | task 13505 | prompt eval time = 455.85 ms / 287 tokens ( 1.59 ms per token, 629.60 tokens per second) 3.42.439.362 I slot print_timing: id 0 | task 13505 | eval time = 1201.02 ms / 87 tokens ( 13.97 ms per token, 71.61 tokens per second) 3.42.439.363 I slot print_timing: id 0 | task 13505 | total time = 1656.87 ms / 374 tokens 3.42.439.364 I slot print_timing: id 0 | task 13505 | graphs reused = 13207 3.42.439.364 I slot print_timing: id 0 | task 13505 | graph reallocs = 0 / 0 (same size) / (changed size) 3.42.439.391 I slot release: id 0 | task 13505 | stop processing: n_tokens = 373, truncated = 0 3.42.443.325 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 373, t_last = 339473557391 3.42.444.267 I slot launch_slot_: id 0 | task 13594 | processing task, is_child = 0 3.44.457.407 I slot print_timing: id 0 | task 13594 | prompt eval time = 668.52 ms / 497 tokens ( 1.35 ms per token, 743.43 tokens per second) 3.44.457.412 I slot print_timing: id 0 | task 13594 | eval time = 1344.61 ms / 97 tokens ( 14.01 ms per token, 71.40 tokens per second) 3.44.457.413 I slot print_timing: id 0 | task 13594 | total time = 2013.13 ms / 594 tokens 3.44.457.413 I slot print_timing: id 0 | task 13594 | graphs reused = 13301 3.44.457.414 I slot print_timing: id 0 | task 13594 | graph reallocs = 0 / 0 (same size) / (changed size) 3.44.457.452 I slot release: id 0 | task 13594 | stop processing: n_tokens = 593, truncated = 0 3.44.461.837 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 593, t_last = 339475575452 3.44.463.622 I slot launch_slot_: id 0 | task 13693 | processing task, is_child = 0 3.48.072.845 I slot print_timing: id 0 | task 13693 | prompt eval time = 920.15 ms / 609 tokens ( 1.51 ms per token, 661.85 tokens per second) 3.48.072.852 I slot print_timing: id 0 | task 13693 | eval time = 2689.07 ms / 193 tokens ( 14.01 ms per token, 71.40 tokens per second) 3.48.072.852 I slot print_timing: id 0 | task 13693 | total time = 3609.21 ms / 802 tokens 3.48.072.853 I slot print_timing: id 0 | task 13693 | graphs reused = 13491 3.48.072.854 I slot print_timing: id 0 | task 13693 | graph reallocs = 0 / 0 (same size) / (changed size) 3.48.072.897 I slot release: id 0 | task 13693 | stop processing: n_tokens = 801, truncated = 0 3.48.076.720 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 801, t_last = 339479190898 3.48.078.557 I slot launch_slot_: id 0 | task 13889 | processing task, is_child = 0 3.50.631.333 I slot print_timing: id 0 | task 13889 | prompt eval time = 580.71 ms / 415 tokens ( 1.40 ms per token, 714.64 tokens per second) 3.50.631.339 I slot print_timing: id 0 | task 13889 | eval time = 1972.06 ms / 142 tokens ( 13.99 ms per token, 71.50 tokens per second) 3.50.631.340 I slot print_timing: id 0 | task 13889 | total time = 2552.77 ms / 557 tokens 3.50.631.340 I slot print_timing: id 0 | task 13889 | graphs reused = 13630 3.50.631.341 I slot print_timing: id 0 | task 13889 | graph reallocs = 0 / 0 (same size) / (changed size) 3.50.631.374 I slot release: id 0 | task 13889 | stop processing: n_tokens = 556, truncated = 0 3.50.634.954 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 556, t_last = 339481749374 3.50.636.258 I slot launch_slot_: id 0 | task 14033 | processing task, is_child = 0 3.53.421.035 I slot print_timing: id 0 | task 14033 | prompt eval time = 470.88 ms / 295 tokens ( 1.60 ms per token, 626.49 tokens per second) 3.53.421.038 I slot print_timing: id 0 | task 14033 | eval time = 2313.89 ms / 167 tokens ( 13.94 ms per token, 71.74 tokens per second) 3.53.421.040 I slot print_timing: id 0 | task 14033 | total time = 2784.76 ms / 462 tokens 3.53.421.040 I slot print_timing: id 0 | task 14033 | graphs reused = 13795 3.53.421.041 I slot print_timing: id 0 | task 14033 | graph reallocs = 0 / 0 (same size) / (changed size) 3.53.421.071 I slot release: id 0 | task 14033 | stop processing: n_tokens = 461, truncated = 0 3.53.425.043 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 461, t_last = 339484539071 3.53.426.179 I slot launch_slot_: id 0 | task 14202 | processing task, is_child = 0 3.57.045.560 I slot print_timing: id 0 | task 14202 | n_gen = 216, tg = 71.44 t/s, tg_3s = 71.77 t/s 4.00.055.244 I slot print_timing: id 0 | task 14202 | n_gen = 431, tg = 71.44 t/s, tg_3s = 71.44 t/s 4.03.062.674 I slot print_timing: id 0 | task 14202 | n_gen = 646, tg = 71.45 t/s, tg_3s = 71.49 t/s 4.04.086.297 I slot print_timing: id 0 | task 14202 | prompt eval time = 609.66 ms / 442 tokens ( 1.38 ms per token, 725.00 tokens per second) 4.04.086.302 I slot print_timing: id 0 | task 14202 | eval time = 10050.45 ms / 719 tokens ( 14.00 ms per token, 71.44 tokens per second) 4.04.086.303 I slot print_timing: id 0 | task 14202 | total time = 10660.11 ms / 1161 tokens 4.04.086.304 I slot print_timing: id 0 | task 14202 | graphs reused = 14509 4.04.086.304 I slot print_timing: id 0 | task 14202 | graph reallocs = 0 / 0 (same size) / (changed size) 4.04.086.347 I slot release: id 0 | task 14202 | stop processing: n_tokens = 1160, truncated = 0 4.04.090.794 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1160, t_last = 339495204347 4.04.093.315 I slot launch_slot_: id 0 | task 14923 | processing task, is_child = 0 4.06.921.660 I slot print_timing: id 0 | task 14923 | prompt eval time = 941.45 ms / 622 tokens ( 1.51 ms per token, 660.68 tokens per second) 4.06.921.663 I slot print_timing: id 0 | task 14923 | eval time = 1886.89 ms / 136 tokens ( 13.98 ms per token, 71.55 tokens per second) 4.06.921.664 I slot print_timing: id 0 | task 14923 | total time = 2828.34 ms / 758 tokens 4.06.921.665 I slot print_timing: id 0 | task 14923 | graphs reused = 14643 4.06.921.665 I slot print_timing: id 0 | task 14923 | graph reallocs = 0 / 0 (same size) / (changed size) 4.06.921.713 I slot release: id 0 | task 14923 | stop processing: n_tokens = 757, truncated = 0 4.06.925.643 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 757, t_last = 339498039713 4.06.927.972 I slot launch_slot_: id 0 | task 15062 | processing task, is_child = 0 4.08.970.046 I slot print_timing: id 0 | task 15062 | prompt eval time = 597.32 ms / 424 tokens ( 1.41 ms per token, 709.84 tokens per second) 4.08.970.049 I slot print_timing: id 0 | task 15062 | eval time = 1444.75 ms / 104 tokens ( 14.03 ms per token, 71.29 tokens per second) 4.08.970.049 I slot print_timing: id 0 | task 15062 | total time = 2042.06 ms / 528 tokens 4.08.970.050 I slot print_timing: id 0 | task 15062 | graphs reused = 14744 4.08.970.050 I slot print_timing: id 0 | task 15062 | graph reallocs = 0 / 0 (same size) / (changed size) 4.08.970.084 I slot release: id 0 | task 15062 | stop processing: n_tokens = 527, truncated = 0 4.08.973.886 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 527, t_last = 339500088084 4.08.974.456 I slot launch_slot_: id 0 | task 15168 | processing task, is_child = 0 4.12.545.304 I slot print_timing: id 0 | task 15168 | n_gen = 216, tg = 71.61 t/s, tg_3s = 71.94 t/s 4.15.548.178 I slot print_timing: id 0 | task 15168 | n_gen = 431, tg = 71.60 t/s, tg_3s = 71.60 t/s 4.16.889.727 I slot print_timing: id 0 | task 15168 | prompt eval time = 568.29 ms / 395 tokens ( 1.44 ms per token, 695.07 tokens per second) 4.16.889.734 I slot print_timing: id 0 | task 15168 | eval time = 7346.97 ms / 527 tokens ( 13.97 ms per token, 71.59 tokens per second) 4.16.889.734 I slot print_timing: id 0 | task 15168 | total time = 7915.26 ms / 922 tokens 4.16.889.735 I slot print_timing: id 0 | task 15168 | graphs reused = 15267 4.16.889.735 I slot print_timing: id 0 | task 15168 | graph reallocs = 0 / 0 (same size) / (changed size) 4.16.889.768 I slot release: id 0 | task 15168 | stop processing: n_tokens = 921, truncated = 0 4.16.893.396 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 921, t_last = 339508007768 4.16.895.724 I slot launch_slot_: id 0 | task 15697 | processing task, is_child = 0 4.19.090.658 I slot print_timing: id 0 | task 15697 | prompt eval time = 449.06 ms / 279 tokens ( 1.61 ms per token, 621.30 tokens per second) 4.19.090.662 I slot print_timing: id 0 | task 15697 | eval time = 1745.86 ms / 126 tokens ( 13.97 ms per token, 71.60 tokens per second) 4.19.090.663 I slot print_timing: id 0 | task 15697 | total time = 2194.92 ms / 405 tokens 4.19.090.663 I slot print_timing: id 0 | task 15697 | graphs reused = 15391 4.19.090.664 I slot print_timing: id 0 | task 15697 | graph reallocs = 0 / 0 (same size) / (changed size) 4.19.090.698 I slot release: id 0 | task 15697 | stop processing: n_tokens = 404, truncated = 0 4.19.094.598 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 404, t_last = 339510208698 4.19.095.740 I slot launch_slot_: id 0 | task 15825 | processing task, is_child = 0 4.22.364.566 I slot print_timing: id 0 | task 15825 | prompt eval time = 484.66 ms / 319 tokens ( 1.52 ms per token, 658.19 tokens per second) 4.22.364.570 I slot print_timing: id 0 | task 15825 | eval time = 2784.15 ms / 200 tokens ( 13.99 ms per token, 71.48 tokens per second) 4.22.364.571 I slot print_timing: id 0 | task 15825 | total time = 3268.81 ms / 519 tokens 4.22.364.572 I slot print_timing: id 0 | task 15825 | graphs reused = 15588 4.22.364.572 I slot print_timing: id 0 | task 15825 | graph reallocs = 0 / 0 (same size) / (changed size) 4.22.364.606 I slot release: id 0 | task 15825 | stop processing: n_tokens = 518, truncated = 0 4.22.368.456 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 518, t_last = 339513482606 4.22.369.737 I slot launch_slot_: id 0 | task 16027 | processing task, is_child = 0 4.24.378.577 I slot print_timing: id 0 | task 16027 | prompt eval time = 513.40 ms / 345 tokens ( 1.49 ms per token, 671.99 tokens per second) 4.24.378.583 I slot print_timing: id 0 | task 16027 | eval time = 1495.43 ms / 108 tokens ( 13.98 ms per token, 71.55 tokens per second) 4.24.378.584 I slot print_timing: id 0 | task 16027 | total time = 2008.83 ms / 453 tokens 4.24.378.585 I slot print_timing: id 0 | task 16027 | graphs reused = 15694 4.24.378.585 I slot print_timing: id 0 | task 16027 | graph reallocs = 0 / 0 (same size) / (changed size) 4.24.378.622 I slot release: id 0 | task 16027 | stop processing: n_tokens = 452, truncated = 0 4.24.382.590 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 452, t_last = 339515496622 4.24.383.734 I slot launch_slot_: id 0 | task 16137 | processing task, is_child = 0 4.27.009.022 I slot print_timing: id 0 | task 16137 | prompt eval time = 635.84 ms / 464 tokens ( 1.37 ms per token, 729.74 tokens per second) 4.27.009.028 I slot print_timing: id 0 | task 16137 | eval time = 1989.44 ms / 143 tokens ( 14.01 ms per token, 71.38 tokens per second) 4.27.009.028 I slot print_timing: id 0 | task 16137 | total time = 2625.28 ms / 607 tokens 4.27.009.029 I slot print_timing: id 0 | task 16137 | graphs reused = 15834 4.27.009.029 I slot print_timing: id 0 | task 16137 | graph reallocs = 0 / 0 (same size) / (changed size) 4.27.009.070 I slot release: id 0 | task 16137 | stop processing: n_tokens = 606, truncated = 0 4.27.012.851 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 606, t_last = 339518127070 4.27.014.277 I slot launch_slot_: id 0 | task 16282 | processing task, is_child = 0 4.28.939.197 I slot print_timing: id 0 | task 16282 | prompt eval time = 569.52 ms / 398 tokens ( 1.43 ms per token, 698.83 tokens per second) 4.28.939.208 I slot print_timing: id 0 | task 16282 | eval time = 1355.39 ms / 98 tokens ( 13.97 ms per token, 71.57 tokens per second) 4.28.939.208 I slot print_timing: id 0 | task 16282 | total time = 1924.91 ms / 496 tokens 4.28.939.209 I slot print_timing: id 0 | task 16282 | graphs reused = 15930 4.28.939.209 I slot print_timing: id 0 | task 16282 | graph reallocs = 0 / 0 (same size) / (changed size) 4.28.939.241 I slot release: id 0 | task 16282 | stop processing: n_tokens = 495, truncated = 0 4.28.943.689 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 495, t_last = 339520057241 4.28.944.911 I slot launch_slot_: id 0 | task 16382 | processing task, is_child = 0 4.31.858.693 I slot print_timing: id 0 | task 16382 | prompt eval time = 944.82 ms / 628 tokens ( 1.50 ms per token, 664.67 tokens per second) 4.31.858.699 I slot print_timing: id 0 | task 16382 | eval time = 1968.95 ms / 141 tokens ( 14.06 ms per token, 71.10 tokens per second) 4.31.858.699 I slot print_timing: id 0 | task 16382 | total time = 2913.77 ms / 769 tokens 4.31.858.700 I slot print_timing: id 0 | task 16382 | graphs reused = 16069 4.31.858.700 I slot print_timing: id 0 | task 16382 | graph reallocs = 0 / 0 (same size) / (changed size) 4.31.858.745 I slot release: id 0 | task 16382 | stop processing: n_tokens = 768, truncated = 0 4.31.862.619 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 768, t_last = 339522976745 4.31.864.376 I slot launch_slot_: id 0 | task 16526 | processing task, is_child = 0 4.34.534.950 I slot print_timing: id 0 | task 16526 | prompt eval time = 573.84 ms / 404 tokens ( 1.42 ms per token, 704.03 tokens per second) 4.34.534.956 I slot print_timing: id 0 | task 16526 | eval time = 2096.72 ms / 151 tokens ( 13.98 ms per token, 71.54 tokens per second) 4.34.534.956 I slot print_timing: id 0 | task 16526 | total time = 2670.56 ms / 555 tokens 4.34.534.957 I slot print_timing: id 0 | task 16526 | graphs reused = 16217 4.34.534.958 I slot print_timing: id 0 | task 16526 | graph reallocs = 0 / 0 (same size) / (changed size) 4.34.534.991 I slot release: id 0 | task 16526 | stop processing: n_tokens = 554, truncated = 0 4.34.538.894 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 554, t_last = 339525652991 4.34.540.212 I slot launch_slot_: id 0 | task 16679 | processing task, is_child = 0 4.37.039.742 I slot print_timing: id 0 | task 16679 | prompt eval time = 612.09 ms / 445 tokens ( 1.38 ms per token, 727.02 tokens per second) 4.37.039.748 I slot print_timing: id 0 | task 16679 | eval time = 1887.43 ms / 136 tokens ( 13.98 ms per token, 71.53 tokens per second) 4.37.039.749 I slot print_timing: id 0 | task 16679 | total time = 2499.52 ms / 581 tokens 4.37.039.749 I slot print_timing: id 0 | task 16679 | graphs reused = 16350 4.37.039.750 I slot print_timing: id 0 | task 16679 | graph reallocs = 0 / 0 (same size) / (changed size) 4.37.039.786 I slot release: id 0 | task 16679 | stop processing: n_tokens = 580, truncated = 0 4.37.043.661 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 580, t_last = 339528157786 4.37.045.067 I slot launch_slot_: id 0 | task 16817 | processing task, is_child = 0 4.40.635.203 I slot print_timing: id 0 | task 16817 | n_gen = 215, tg = 71.11 t/s, tg_3s = 71.45 t/s 4.40.916.391 I slot print_timing: id 0 | task 16817 | prompt eval time = 580.87 ms / 412 tokens ( 1.41 ms per token, 709.28 tokens per second) 4.40.916.398 I slot print_timing: id 0 | task 16817 | eval time = 3290.45 ms / 235 tokens ( 14.06 ms per token, 71.12 tokens per second) 4.40.916.398 I slot print_timing: id 0 | task 16817 | total time = 3871.32 ms / 647 tokens 4.40.916.399 I slot print_timing: id 0 | task 16817 | graphs reused = 16582 4.40.916.399 I slot print_timing: id 0 | task 16817 | graph reallocs = 0 / 0 (same size) / (changed size) 4.40.916.436 I slot release: id 0 | task 16817 | stop processing: n_tokens = 646, truncated = 0 4.40.920.730 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 646, t_last = 339532034436 4.40.922.334 I slot launch_slot_: id 0 | task 17054 | processing task, is_child = 0 4.42.855.928 I slot print_timing: id 0 | task 17054 | prompt eval time = 842.37 ms / 542 tokens ( 1.55 ms per token, 643.42 tokens per second) 4.42.855.931 I slot print_timing: id 0 | task 17054 | eval time = 1091.21 ms / 79 tokens ( 13.99 ms per token, 71.48 tokens per second) 4.42.855.932 I slot print_timing: id 0 | task 17054 | total time = 1933.59 ms / 621 tokens 4.42.855.933 I slot print_timing: id 0 | task 17054 | graphs reused = 16659 4.42.855.933 I slot print_timing: id 0 | task 17054 | graph reallocs = 0 / 0 (same size) / (changed size) 4.42.855.976 I slot release: id 0 | task 17054 | stop processing: n_tokens = 620, truncated = 0 4.42.860.296 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 620, t_last = 339533973976 4.42.861.695 I slot launch_slot_: id 0 | task 17136 | processing task, is_child = 0 4.46.365.874 I slot print_timing: id 0 | task 17136 | prompt eval time = 938.40 ms / 628 tokens ( 1.49 ms per token, 669.22 tokens per second) 4.46.365.881 I slot print_timing: id 0 | task 17136 | eval time = 2565.77 ms / 184 tokens ( 14.02 ms per token, 71.32 tokens per second) 4.46.365.881 I slot print_timing: id 0 | task 17136 | total time = 3504.17 ms / 812 tokens 4.46.365.882 I slot print_timing: id 0 | task 17136 | graphs reused = 16840 4.46.365.882 I slot print_timing: id 0 | task 17136 | graph reallocs = 0 / 0 (same size) / (changed size) 4.46.365.926 I slot release: id 0 | task 17136 | stop processing: n_tokens = 811, truncated = 0 4.46.369.284 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.107 (> 0.100 thold), f_keep = 0.026 4.46.371.076 I slot launch_slot_: id 0 | task 17323 | processing task, is_child = 0 4.49.435.616 I slot print_timing: id 0 | task 17323 | prompt eval time = 373.39 ms / 197 tokens ( 1.90 ms per token, 527.60 tokens per second) 4.49.435.624 I slot print_timing: id 0 | task 17323 | eval time = 2691.14 ms / 194 tokens ( 13.94 ms per token, 71.72 tokens per second) 4.49.435.625 I slot print_timing: id 0 | task 17323 | total time = 3064.53 ms / 391 tokens 4.49.435.626 I slot print_timing: id 0 | task 17323 | graphs reused = 17031 4.49.435.626 I slot print_timing: id 0 | task 17323 | graph reallocs = 0 / 0 (same size) / (changed size) 4.49.435.648 I slot release: id 0 | task 17323 | stop processing: n_tokens = 390, truncated = 0 4.49.439.059 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 390, t_last = 339540553648 4.49.440.013 I slot launch_slot_: id 0 | task 17519 | processing task, is_child = 0 4.51.432.400 I slot print_timing: id 0 | task 17519 | prompt eval time = 387.08 ms / 217 tokens ( 1.78 ms per token, 560.60 tokens per second) 4.51.432.404 I slot print_timing: id 0 | task 17519 | eval time = 1605.29 ms / 116 tokens ( 13.96 ms per token, 71.64 tokens per second) 4.51.432.405 I slot print_timing: id 0 | task 17519 | total time = 1992.38 ms / 333 tokens 4.51.432.406 I slot print_timing: id 0 | task 17519 | graphs reused = 17144 4.51.432.406 I slot print_timing: id 0 | task 17519 | graph reallocs = 0 / 0 (same size) / (changed size) 4.51.432.433 I slot release: id 0 | task 17519 | stop processing: n_tokens = 332, truncated = 0 4.51.435.818 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.105 (> 0.100 thold), f_keep = 0.063 4.51.436.648 I slot launch_slot_: id 0 | task 17637 | processing task, is_child = 0 4.54.823.144 I slot print_timing: id 0 | task 17637 | n_gen = 216, tg = 71.49 t/s, tg_3s = 71.82 t/s 4.55.311.354 I slot print_timing: id 0 | task 17637 | prompt eval time = 379.05 ms / 200 tokens ( 1.90 ms per token, 527.64 tokens per second) 4.55.311.359 I slot print_timing: id 0 | task 17637 | eval time = 3495.65 ms / 251 tokens ( 13.98 ms per token, 71.52 tokens per second) 4.55.311.361 I slot print_timing: id 0 | task 17637 | total time = 3874.69 ms / 451 tokens 4.55.311.361 I slot print_timing: id 0 | task 17637 | graphs reused = 17392 4.55.311.362 I slot print_timing: id 0 | task 17637 | graph reallocs = 0 / 0 (same size) / (changed size) 4.55.311.393 I slot release: id 0 | task 17637 | stop processing: n_tokens = 450, truncated = 0 4.55.314.780 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.124 (> 0.100 thold), f_keep = 0.047 4.55.315.909 I slot launch_slot_: id 0 | task 17890 | processing task, is_child = 0 4.57.931.421 I slot print_timing: id 0 | task 17890 | prompt eval time = 351.27 ms / 170 tokens ( 2.07 ms per token, 483.95 tokens per second) 4.57.931.427 I slot print_timing: id 0 | task 17890 | eval time = 2264.23 ms / 163 tokens ( 13.98 ms per token, 71.55 tokens per second) 4.57.931.427 I slot print_timing: id 0 | task 17890 | total time = 2615.51 ms / 333 tokens 4.57.931.428 I slot print_timing: id 0 | task 17890 | graphs reused = 17552 4.57.931.428 I slot print_timing: id 0 | task 17890 | graph reallocs = 0 / 0 (same size) / (changed size) 4.57.931.449 I slot release: id 0 | task 17890 | stop processing: n_tokens = 332, truncated = 0 4.57.934.951 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 332, t_last = 339549049449 4.57.935.850 I slot launch_slot_: id 0 | task 18055 | processing task, is_child = 0 5.01.352.999 I slot print_timing: id 0 | task 18055 | n_gen = 216, tg = 71.64 t/s, tg_3s = 71.98 t/s 5.04.035.909 I slot print_timing: id 0 | task 18055 | prompt eval time = 416.16 ms / 241 tokens ( 1.73 ms per token, 579.10 tokens per second) 5.04.035.912 I slot print_timing: id 0 | task 18055 | eval time = 5683.89 ms / 408 tokens ( 13.97 ms per token, 71.61 tokens per second) 5.04.035.913 I slot print_timing: id 0 | task 18055 | total time = 6100.05 ms / 649 tokens 5.04.035.913 I slot print_timing: id 0 | task 18055 | graphs reused = 17956 5.04.035.914 I slot print_timing: id 0 | task 18055 | graph reallocs = 0 / 0 (same size) / (changed size) 5.04.035.938 I slot release: id 0 | task 18055 | stop processing: n_tokens = 648, truncated = 0 5.04.039.322 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 648, t_last = 339555153938 5.04.040.774 I slot launch_slot_: id 0 | task 18465 | processing task, is_child = 0 5.07.463.908 I slot print_timing: id 0 | task 18465 | n_gen = 217, tg = 71.79 t/s, tg_3s = 72.12 t/s 5.08.470.024 I slot print_timing: id 0 | task 18465 | prompt eval time = 414.45 ms / 237 tokens ( 1.75 ms per token, 571.84 tokens per second) 5.08.470.030 I slot print_timing: id 0 | task 18465 | eval time = 4014.79 ms / 289 tokens ( 13.94 ms per token, 71.73 tokens per second) 5.08.470.030 I slot print_timing: id 0 | task 18465 | total time = 4429.24 ms / 526 tokens 5.08.470.031 I slot print_timing: id 0 | task 18465 | graphs reused = 18241 5.08.470.032 I slot print_timing: id 0 | task 18465 | graph reallocs = 0 / 0 (same size) / (changed size) 5.08.470.055 I slot release: id 0 | task 18465 | stop processing: n_tokens = 525, truncated = 0 5.08.473.505 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 525, t_last = 339559588055 5.08.474.739 I slot launch_slot_: id 0 | task 18756 | processing task, is_child = 0 5.11.973.782 I slot print_timing: id 0 | task 18756 | n_gen = 217, tg = 71.71 t/s, tg_3s = 72.04 t/s 5.14.580.625 I slot print_timing: id 0 | task 18756 | prompt eval time = 486.92 ms / 322 tokens ( 1.51 ms per token, 661.29 tokens per second) 5.14.580.631 I slot print_timing: id 0 | task 18756 | eval time = 5618.95 ms / 404 tokens ( 13.94 ms per token, 71.72 tokens per second) 5.14.580.632 I slot print_timing: id 0 | task 18756 | total time = 6105.88 ms / 726 tokens 5.14.580.633 I slot print_timing: id 0 | task 18756 | graphs reused = 18642 5.14.580.633 I slot print_timing: id 0 | task 18756 | graph reallocs = 0 / 0 (same size) / (changed size) 5.14.580.662 I slot release: id 0 | task 18756 | stop processing: n_tokens = 725, truncated = 0 5.14.583.962 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.120 (> 0.100 thold), f_keep = 0.029 5.14.585.621 I slot launch_slot_: id 0 | task 19162 | processing task, is_child = 0 5.17.940.594 I slot print_timing: id 0 | task 19162 | n_gen = 215, tg = 71.31 t/s, tg_3s = 71.65 t/s 5.20.535.199 I slot print_timing: id 0 | task 19162 | prompt eval time = 354.07 ms / 175 tokens ( 2.02 ms per token, 494.25 tokens per second) 5.20.535.205 I slot print_timing: id 0 | task 19162 | eval time = 5595.49 ms / 401 tokens ( 13.99 ms per token, 71.49 tokens per second) 5.20.535.206 I slot print_timing: id 0 | task 19162 | total time = 5949.57 ms / 576 tokens 5.20.535.206 I slot print_timing: id 0 | task 19162 | graphs reused = 19039 5.20.535.207 I slot print_timing: id 0 | task 19162 | graph reallocs = 0 / 0 (same size) / (changed size) 5.20.535.238 I slot release: id 0 | task 19162 | stop processing: n_tokens = 575, truncated = 0 5.20.538.581 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.117 (> 0.100 thold), f_keep = 0.037 5.20.539.849 I slot launch_slot_: id 0 | task 19565 | processing task, is_child = 0 5.23.899.876 I slot print_timing: id 0 | task 19565 | n_gen = 214, tg = 70.98 t/s, tg_3s = 71.31 t/s 5.26.901.950 I slot print_timing: id 0 | task 19565 | n_gen = 429, tg = 71.30 t/s, tg_3s = 71.62 t/s 5.27.293.205 I slot print_timing: id 0 | task 19565 | prompt eval time = 359.25 ms / 179 tokens ( 2.01 ms per token, 498.27 tokens per second) 5.27.293.208 I slot print_timing: id 0 | task 19565 | eval time = 6394.10 ms / 457 tokens ( 14.02 ms per token, 71.32 tokens per second) 5.27.293.209 I slot print_timing: id 0 | task 19565 | total time = 6753.35 ms / 636 tokens 5.27.293.210 I slot print_timing: id 0 | task 19565 | graphs reused = 19492 5.27.293.210 I slot print_timing: id 0 | task 19565 | graph reallocs = 0 / 0 (same size) / (changed size) 5.27.293.232 I slot release: id 0 | task 19565 | stop processing: n_tokens = 635, truncated = 0 5.27.296.699 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 635, t_last = 339578411232 5.27.298.401 I slot launch_slot_: id 0 | task 20024 | processing task, is_child = 0 5.30.711.686 I slot print_timing: id 0 | task 20024 | n_gen = 216, tg = 71.61 t/s, tg_3s = 71.94 t/s 5.31.436.928 I slot print_timing: id 0 | task 20024 | prompt eval time = 410.84 ms / 237 tokens ( 1.73 ms per token, 576.87 tokens per second) 5.31.436.933 I slot print_timing: id 0 | task 20024 | eval time = 3727.68 ms / 268 tokens ( 13.96 ms per token, 71.63 tokens per second) 5.31.436.934 I slot print_timing: id 0 | task 20024 | total time = 4138.52 ms / 505 tokens 5.31.436.935 I slot print_timing: id 0 | task 20024 | graphs reused = 19757 5.31.436.935 I slot print_timing: id 0 | task 20024 | graph reallocs = 0 / 0 (same size) / (changed size) 5.31.436.959 I slot release: id 0 | task 20024 | stop processing: n_tokens = 504, truncated = 0 5.31.440.321 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 339582554960 5.31.441.463 I slot launch_slot_: id 0 | task 20294 | processing task, is_child = 0 5.34.896.207 I slot print_timing: id 0 | task 20294 | n_gen = 216, tg = 71.65 t/s, tg_3s = 71.98 t/s 5.35.331.163 I slot print_timing: id 0 | task 20294 | prompt eval time = 453.85 ms / 287 tokens ( 1.58 ms per token, 632.37 tokens per second) 5.35.331.167 I slot print_timing: id 0 | task 20294 | eval time = 3435.84 ms / 247 tokens ( 13.97 ms per token, 71.60 tokens per second) 5.35.331.167 I slot print_timing: id 0 | task 20294 | total time = 3889.69 ms / 534 tokens 5.35.331.168 I slot print_timing: id 0 | task 20294 | graphs reused = 20001 5.35.331.168 I slot print_timing: id 0 | task 20294 | graph reallocs = 0 / 0 (same size) / (changed size) 5.35.331.200 I slot release: id 0 | task 20294 | stop processing: n_tokens = 533, truncated = 0 5.35.334.528 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.148 (> 0.100 thold), f_keep = 0.068 5.35.335.736 I slot launch_slot_: id 0 | task 20543 | processing task, is_child = 0 5.38.637.389 I slot print_timing: id 0 | task 20543 | prompt eval time = 415.32 ms / 243 tokens ( 1.71 ms per token, 585.09 tokens per second) 5.38.637.393 I slot print_timing: id 0 | task 20543 | eval time = 2886.32 ms / 207 tokens ( 14.01 ms per token, 71.37 tokens per second) 5.38.637.395 I slot print_timing: id 0 | task 20543 | total time = 3301.64 ms / 450 tokens 5.38.637.395 I slot print_timing: id 0 | task 20543 | graphs reused = 20205 5.38.637.396 I slot print_timing: id 0 | task 20543 | graph reallocs = 0 / 0 (same size) / (changed size) 5.38.637.420 I slot release: id 0 | task 20543 | stop processing: n_tokens = 449, truncated = 0 5.38.640.870 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 449, t_last = 339589755420 5.38.641.984 I slot launch_slot_: id 0 | task 20752 | processing task, is_child = 0 5.42.069.114 I slot print_timing: id 0 | task 20752 | n_gen = 217, tg = 71.72 t/s, tg_3s = 72.06 t/s 5.43.189.229 I slot print_timing: id 0 | task 20752 | prompt eval time = 415.61 ms / 243 tokens ( 1.71 ms per token, 584.68 tokens per second) 5.43.189.235 I slot print_timing: id 0 | task 20752 | eval time = 4131.63 ms / 297 tokens ( 13.96 ms per token, 71.64 tokens per second) 5.43.189.236 I slot print_timing: id 0 | task 20752 | total time = 4547.24 ms / 540 tokens 5.43.189.237 I slot print_timing: id 0 | task 20752 | graphs reused = 20498 5.43.189.237 I slot print_timing: id 0 | task 20752 | graph reallocs = 0 / 0 (same size) / (changed size) 5.43.189.262 I slot release: id 0 | task 20752 | stop processing: n_tokens = 539, truncated = 0 5.43.192.818 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 539, t_last = 339594307262 5.43.194.044 I slot launch_slot_: id 0 | task 21051 | processing task, is_child = 0 5.46.643.692 I slot print_timing: id 0 | task 21051 | n_gen = 217, tg = 71.68 t/s, tg_3s = 72.01 t/s 5.47.596.044 I slot print_timing: id 0 | task 21051 | prompt eval time = 436.21 ms / 262 tokens ( 1.66 ms per token, 600.62 tokens per second) 5.47.596.048 I slot print_timing: id 0 | task 21051 | eval time = 3965.78 ms / 285 tokens ( 13.96 ms per token, 71.61 tokens per second) 5.47.596.049 I slot print_timing: id 0 | task 21051 | total time = 4401.99 ms / 547 tokens 5.47.596.049 I slot print_timing: id 0 | task 21051 | graphs reused = 20780 5.47.596.050 I slot print_timing: id 0 | task 21051 | graph reallocs = 0 / 0 (same size) / (changed size) 5.47.596.078 I slot release: id 0 | task 21051 | stop processing: n_tokens = 546, truncated = 0 5.47.599.416 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.102 (> 0.100 thold), f_keep = 0.038 5.47.600.697 I slot launch_slot_: id 0 | task 21338 | processing task, is_child = 0 5.50.509.236 I slot print_timing: id 0 | task 21338 | prompt eval time = 381.58 ms / 205 tokens ( 1.86 ms per token, 537.24 tokens per second) 5.50.509.240 I slot print_timing: id 0 | task 21338 | eval time = 2526.95 ms / 182 tokens ( 13.96 ms per token, 71.63 tokens per second) 5.50.509.241 I slot print_timing: id 0 | task 21338 | total time = 2908.53 ms / 387 tokens 5.50.509.242 I slot print_timing: id 0 | task 21338 | graphs reused = 20959 5.50.509.242 I slot print_timing: id 0 | task 21338 | graph reallocs = 0 / 0 (same size) / (changed size) 5.50.509.264 I slot release: id 0 | task 21338 | stop processing: n_tokens = 386, truncated = 0 5.50.512.749 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 386, t_last = 339601627264 5.50.513.706 I slot launch_slot_: id 0 | task 21522 | processing task, is_child = 0 5.53.970.053 I slot print_timing: id 0 | task 21522 | n_gen = 217, tg = 71.75 t/s, tg_3s = 72.08 t/s 5.54.025.684 I slot print_timing: id 0 | task 21522 | prompt eval time = 445.71 ms / 279 tokens ( 1.60 ms per token, 625.97 tokens per second) 5.54.025.690 I slot print_timing: id 0 | task 21522 | eval time = 3066.26 ms / 221 tokens ( 13.94 ms per token, 71.75 tokens per second) 5.54.025.690 I slot print_timing: id 0 | task 21522 | total time = 3511.97 ms / 500 tokens 5.54.025.691 I slot print_timing: id 0 | task 21522 | graphs reused = 21178 5.54.025.692 I slot print_timing: id 0 | task 21522 | graph reallocs = 0 / 0 (same size) / (changed size) 5.54.025.718 I slot release: id 0 | task 21522 | stop processing: n_tokens = 499, truncated = 0 5.54.029.098 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 5.54.030.291 I slot launch_slot_: id 0 | task 21745 | processing task, is_child = 0 5.57.406.209 I slot print_timing: id 0 | task 21745 | n_gen = 217, tg = 71.71 t/s, tg_3s = 72.04 t/s 6.00.407.733 I slot print_timing: id 0 | task 21745 | n_gen = 432, tg = 71.67 t/s, tg_3s = 71.63 t/s 6.01.159.182 I slot print_timing: id 0 | task 21745 | prompt eval time = 363.79 ms / 194 tokens ( 1.88 ms per token, 533.27 tokens per second) 6.01.159.188 I slot print_timing: id 0 | task 21745 | eval time = 6765.09 ms / 486 tokens ( 13.95 ms per token, 71.69 tokens per second) 6.01.159.189 I slot print_timing: id 0 | task 21745 | total time = 7128.88 ms / 680 tokens 6.01.159.189 I slot print_timing: id 0 | task 21745 | graphs reused = 21660 6.01.159.190 I slot print_timing: id 0 | task 21745 | graph reallocs = 0 / 0 (same size) / (changed size) 6.01.159.215 I slot release: id 0 | task 21745 | stop processing: n_tokens = 679, truncated = 0 6.01.162.510 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.124 (> 0.100 thold), f_keep = 0.031 6.01.164.070 I slot launch_slot_: id 0 | task 22233 | processing task, is_child = 0 6.04.522.142 I slot print_timing: id 0 | task 22233 | n_gen = 216, tg = 71.53 t/s, tg_3s = 71.86 t/s 6.05.039.190 I slot print_timing: id 0 | task 22233 | prompt eval time = 352.17 ms / 169 tokens ( 2.08 ms per token, 479.88 tokens per second) 6.05.039.196 I slot print_timing: id 0 | task 22233 | eval time = 3522.94 ms / 253 tokens ( 13.98 ms per token, 71.53 tokens per second) 6.05.039.196 I slot print_timing: id 0 | task 22233 | total time = 3875.11 ms / 422 tokens 6.05.039.197 I slot print_timing: id 0 | task 22233 | graphs reused = 21910 6.05.039.198 I slot print_timing: id 0 | task 22233 | graph reallocs = 0 / 0 (same size) / (changed size) 6.05.039.219 I slot release: id 0 | task 22233 | stop processing: n_tokens = 421, truncated = 0 6.05.042.702 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 421, t_last = 339616157219 6.05.043.981 I slot launch_slot_: id 0 | task 22488 | processing task, is_child = 0 6.08.494.432 I slot print_timing: id 0 | task 22488 | n_gen = 217, tg = 71.70 t/s, tg_3s = 72.03 t/s 6.09.571.095 I slot print_timing: id 0 | task 22488 | prompt eval time = 437.82 ms / 263 tokens ( 1.66 ms per token, 600.70 tokens per second) 6.09.571.099 I slot print_timing: id 0 | task 22488 | eval time = 4089.28 ms / 294 tokens ( 13.96 ms per token, 71.65 tokens per second) 6.09.571.100 I slot print_timing: id 0 | task 22488 | total time = 4527.10 ms / 557 tokens 6.09.571.100 I slot print_timing: id 0 | task 22488 | graphs reused = 22201 6.09.571.101 I slot print_timing: id 0 | task 22488 | graph reallocs = 0 / 0 (same size) / (changed size) 6.09.571.127 I slot release: id 0 | task 22488 | stop processing: n_tokens = 556, truncated = 0 6.09.574.510 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.103 (> 0.100 thold), f_keep = 0.038 6.09.575.778 I slot launch_slot_: id 0 | task 22784 | processing task, is_child = 0 6.12.306.069 I slot print_timing: id 0 | task 22784 | prompt eval time = 380.51 ms / 204 tokens ( 1.87 ms per token, 536.13 tokens per second) 6.12.306.075 I slot print_timing: id 0 | task 22784 | eval time = 2349.77 ms / 169 tokens ( 13.99 ms per token, 71.50 tokens per second) 6.12.306.075 I slot print_timing: id 0 | task 22784 | total time = 2730.28 ms / 373 tokens 6.12.306.076 I slot print_timing: id 0 | task 22784 | graphs reused = 22367 6.12.306.077 I slot print_timing: id 0 | task 22784 | graph reallocs = 0 / 0 (same size) / (changed size) 6.12.306.100 I slot release: id 0 | task 22784 | stop processing: n_tokens = 372, truncated = 0 6.12.309.479 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 372, t_last = 339623424100 6.12.310.405 I slot launch_slot_: id 0 | task 22955 | processing task, is_child = 0 6.15.757.956 I slot print_timing: id 0 | task 22955 | n_gen = 216, tg = 71.61 t/s, tg_3s = 71.94 t/s 6.18.759.018 I slot print_timing: id 0 | task 22955 | n_gen = 431, tg = 71.62 t/s, tg_3s = 71.64 t/s 6.20.342.517 I slot print_timing: id 0 | task 22955 | prompt eval time = 444.97 ms / 272 tokens ( 1.64 ms per token, 611.28 tokens per second) 6.20.342.522 I slot print_timing: id 0 | task 22955 | eval time = 7587.14 ms / 544 tokens ( 13.97 ms per token, 71.57 tokens per second) 6.20.342.523 I slot print_timing: id 0 | task 22955 | total time = 8032.11 ms / 816 tokens 6.20.342.524 I slot print_timing: id 0 | task 22955 | graphs reused = 22907 6.20.342.524 I slot print_timing: id 0 | task 22955 | graph reallocs = 0 / 0 (same size) / (changed size) 6.20.342.553 I slot release: id 0 | task 22955 | stop processing: n_tokens = 815, truncated = 0 6.20.345.930 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 815, t_last = 339631460553 6.20.347.757 I slot launch_slot_: id 0 | task 23501 | processing task, is_child = 0 6.23.339.710 I slot print_timing: id 0 | task 23501 | prompt eval time = 410.50 ms / 231 tokens ( 1.78 ms per token, 562.73 tokens per second) 6.23.339.715 I slot print_timing: id 0 | task 23501 | eval time = 2581.44 ms / 186 tokens ( 13.95 ms per token, 71.67 tokens per second) 6.23.339.715 I slot print_timing: id 0 | task 23501 | total time = 2991.94 ms / 417 tokens 6.23.339.716 I slot print_timing: id 0 | task 23501 | graphs reused = 23090 6.23.339.717 I slot print_timing: id 0 | task 23501 | graph reallocs = 0 / 0 (same size) / (changed size) 6.23.339.743 I slot release: id 0 | task 23501 | stop processing: n_tokens = 416, truncated = 0 6.23.343.163 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 339634457743 6.23.344.169 I slot launch_slot_: id 0 | task 23689 | processing task, is_child = 0 6.26.803.140 I slot print_timing: id 0 | task 23689 | n_gen = 216, tg = 71.63 t/s, tg_3s = 71.96 t/s 6.26.931.018 I slot print_timing: id 0 | task 23689 | prompt eval time = 457.23 ms / 291 tokens ( 1.57 ms per token, 636.44 tokens per second) 6.26.931.024 I slot print_timing: id 0 | task 23689 | eval time = 3129.61 ms / 225 tokens ( 13.97 ms per token, 71.57 tokens per second) 6.26.931.025 I slot print_timing: id 0 | task 23689 | total time = 3586.84 ms / 516 tokens 6.26.931.025 I slot print_timing: id 0 | task 23689 | graphs reused = 23312 6.26.931.026 I slot print_timing: id 0 | task 23689 | graph reallocs = 0 / 0 (same size) / (changed size) 6.26.931.051 I slot release: id 0 | task 23689 | stop processing: n_tokens = 515, truncated = 0 6.26.934.399 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 515, t_last = 339638049051 6.26.935.551 I slot launch_slot_: id 0 | task 23916 | processing task, is_child = 0 6.30.391.651 I slot print_timing: id 0 | task 23916 | n_gen = 216, tg = 71.62 t/s, tg_3s = 71.96 t/s 6.31.492.898 I slot print_timing: id 0 | task 23916 | prompt eval time = 454.27 ms / 285 tokens ( 1.59 ms per token, 627.37 tokens per second) 6.31.492.906 I slot print_timing: id 0 | task 23916 | eval time = 4103.06 ms / 295 tokens ( 13.96 ms per token, 71.65 tokens per second) 6.31.492.906 I slot print_timing: id 0 | task 23916 | total time = 4557.34 ms / 580 tokens 6.31.492.907 I slot print_timing: id 0 | task 23916 | graphs reused = 23604 6.31.492.908 I slot print_timing: id 0 | task 23916 | graph reallocs = 0 / 0 (same size) / (changed size) 6.31.492.940 I slot release: id 0 | task 23916 | stop processing: n_tokens = 579, truncated = 0 6.31.496.476 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 579, t_last = 339642610940 6.31.497.731 I slot launch_slot_: id 0 | task 24213 | processing task, is_child = 0 6.34.953.118 I slot print_timing: id 0 | task 24213 | n_gen = 216, tg = 71.63 t/s, tg_3s = 71.96 t/s 6.37.956.050 I slot print_timing: id 0 | task 24213 | n_gen = 431, tg = 71.61 t/s, tg_3s = 71.60 t/s 6.38.039.638 I slot print_timing: id 0 | task 24213 | prompt eval time = 453.84 ms / 289 tokens ( 1.57 ms per token, 636.79 tokens per second) 6.38.039.644 I slot print_timing: id 0 | task 24213 | eval time = 6088.06 ms / 437 tokens ( 13.96 ms per token, 71.62 tokens per second) 6.38.039.644 I slot print_timing: id 0 | task 24213 | total time = 6541.90 ms / 726 tokens 6.38.039.645 I slot print_timing: id 0 | task 24213 | graphs reused = 24038 6.38.039.646 I slot print_timing: id 0 | task 24213 | graph reallocs = 0 / 0 (same size) / (changed size) 6.38.039.676 I slot release: id 0 | task 24213 | stop processing: n_tokens = 725, truncated = 0 6.38.043.157 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 725, t_last = 339649157676 6.38.044.761 I slot launch_slot_: id 0 | task 24652 | processing task, is_child = 0 6.41.184.282 I slot print_timing: id 0 | task 24652 | prompt eval time = 414.92 ms / 242 tokens ( 1.71 ms per token, 583.24 tokens per second) 6.41.184.288 I slot print_timing: id 0 | task 24652 | eval time = 2724.59 ms / 196 tokens ( 13.97 ms per token, 71.57 tokens per second) 6.41.184.289 I slot print_timing: id 0 | task 24652 | total time = 3139.51 ms / 438 tokens 6.41.184.289 I slot print_timing: id 0 | task 24652 | graphs reused = 24231 6.41.184.290 I slot print_timing: id 0 | task 24652 | graph reallocs = 0 / 0 (same size) / (changed size) 6.41.184.314 I slot release: id 0 | task 24652 | stop processing: n_tokens = 437, truncated = 0 6.41.187.670 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.118 (> 0.100 thold), f_keep = 0.048 6.41.188.786 I slot launch_slot_: id 0 | task 24850 | processing task, is_child = 0 6.44.007.378 I slot print_timing: id 0 | task 24850 | prompt eval time = 357.24 ms / 178 tokens ( 2.01 ms per token, 498.26 tokens per second) 6.44.007.383 I slot print_timing: id 0 | task 24850 | eval time = 2461.34 ms / 177 tokens ( 13.98 ms per token, 71.51 tokens per second) 6.44.007.384 I slot print_timing: id 0 | task 24850 | total time = 2818.58 ms / 355 tokens 6.44.007.385 I slot print_timing: id 0 | task 24850 | graphs reused = 24405 6.44.007.385 I slot print_timing: id 0 | task 24850 | graph reallocs = 0 / 0 (same size) / (changed size) 6.44.007.406 I slot release: id 0 | task 24850 | stop processing: n_tokens = 354, truncated = 0 6.44.010.712 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 354, t_last = 339655125406 6.44.011.160 I slot launch_slot_: id 0 | task 25029 | processing task, is_child = 0 6.47.257.990 I slot print_timing: id 0 | task 25029 | prompt eval time = 440.22 ms / 264 tokens ( 1.67 ms per token, 599.70 tokens per second) 6.47.257.994 I slot print_timing: id 0 | task 25029 | eval time = 2806.60 ms / 202 tokens ( 13.96 ms per token, 71.62 tokens per second) 6.47.257.995 I slot print_timing: id 0 | task 25029 | total time = 3246.82 ms / 466 tokens 6.47.257.996 I slot print_timing: id 0 | task 25029 | graphs reused = 24605 6.47.257.996 I slot print_timing: id 0 | task 25029 | graph reallocs = 0 / 0 (same size) / (changed size) 6.47.258.020 I slot release: id 0 | task 25029 | stop processing: n_tokens = 465, truncated = 0 6.47.261.636 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.138 (> 0.100 thold), f_keep = 0.045 6.47.262.812 I slot launch_slot_: id 0 | task 25233 | processing task, is_child = 0 6.49.475.529 I slot print_timing: id 0 | task 25233 | prompt eval time = 331.37 ms / 152 tokens ( 2.18 ms per token, 458.70 tokens per second) 6.49.475.536 I slot print_timing: id 0 | task 25233 | eval time = 1881.34 ms / 135 tokens ( 14.04 ms per token, 71.23 tokens per second) 6.49.475.537 I slot print_timing: id 0 | task 25233 | total time = 2212.70 ms / 287 tokens 6.49.475.537 I slot print_timing: id 0 | task 25233 | graphs reused = 24737 6.49.475.538 I slot print_timing: id 0 | task 25233 | graph reallocs = 0 / 0 (same size) / (changed size) 6.49.475.557 I slot release: id 0 | task 25233 | stop processing: n_tokens = 286, truncated = 0 6.49.478.835 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.108 (> 0.100 thold), f_keep = 0.073 6.49.479.222 I slot launch_slot_: id 0 | task 25370 | processing task, is_child = 0 6.52.790.723 I slot print_timing: id 0 | task 25370 | prompt eval time = 367.80 ms / 194 tokens ( 1.90 ms per token, 527.46 tokens per second) 6.52.790.727 I slot print_timing: id 0 | task 25370 | eval time = 2943.69 ms / 212 tokens ( 13.95 ms per token, 71.68 tokens per second) 6.52.790.727 I slot print_timing: id 0 | task 25370 | total time = 3311.49 ms / 406 tokens 6.52.790.728 I slot print_timing: id 0 | task 25370 | graphs reused = 24946 6.52.790.729 I slot print_timing: id 0 | task 25370 | graph reallocs = 0 / 0 (same size) / (changed size) 6.52.790.751 I slot release: id 0 | task 25370 | stop processing: n_tokens = 405, truncated = 0 6.52.794.361 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 405, t_last = 339663908751 6.52.795.349 I slot launch_slot_: id 0 | task 25584 | processing task, is_child = 0 6.56.240.558 I slot print_timing: id 0 | task 25584 | n_gen = 213, tg = 70.57 t/s, tg_3s = 70.90 t/s 6.59.250.851 I slot print_timing: id 0 | task 25584 | n_gen = 427, tg = 70.83 t/s, tg_3s = 71.09 t/s 7.01.871.553 I slot print_timing: id 0 | task 25584 | prompt eval time = 441.14 ms / 269 tokens ( 1.64 ms per token, 609.79 tokens per second) 7.01.871.558 I slot print_timing: id 0 | task 25584 | eval time = 8635.06 ms / 614 tokens ( 14.09 ms per token, 70.99 tokens per second) 7.01.871.558 I slot print_timing: id 0 | task 25584 | total time = 9076.20 ms / 883 tokens 7.01.871.559 I slot print_timing: id 0 | task 25584 | graphs reused = 25556 7.01.871.560 I slot print_timing: id 0 | task 25584 | graph reallocs = 0 / 0 (same size) / (changed size) 7.01.871.585 I slot release: id 0 | task 25584 | stop processing: n_tokens = 882, truncated = 0 7.01.875.380 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 882, t_last = 339672989585 7.01.877.416 I slot launch_slot_: id 0 | task 26200 | processing task, is_child = 0 7.05.330.131 I slot print_timing: id 0 | task 26200 | n_gen = 216, tg = 71.66 t/s, tg_3s = 71.99 t/s 7.08.341.880 I slot print_timing: id 0 | task 26200 | n_gen = 432, tg = 71.69 t/s, tg_3s = 71.72 t/s 7.11.351.853 I slot print_timing: id 0 | task 26200 | n_gen = 648, tg = 71.71 t/s, tg_3s = 71.76 t/s 7.14.357.402 I slot print_timing: id 0 | task 26200 | n_gen = 863, tg = 71.67 t/s, tg_3s = 71.53 t/s 7.16.612.808 I slot print_timing: id 0 | task 26200 | prompt eval time = 452.34 ms / 283 tokens ( 1.60 ms per token, 625.63 tokens per second) 7.16.612.815 I slot print_timing: id 0 | task 26200 | eval time = 14283.04 ms / 1024 tokens ( 13.96 ms per token, 71.62 tokens per second) 7.16.612.817 I slot print_timing: id 0 | task 26200 | total time = 14735.38 ms / 1307 tokens 7.16.612.817 I slot print_timing: id 0 | task 26200 | graphs reused = 26574 7.16.612.818 I slot print_timing: id 0 | task 26200 | graph reallocs = 0 / 0 (same size) / (changed size) 7.16.612.847 I slot release: id 0 | task 26200 | stop processing: n_tokens = 1306, truncated = 0 7.16.616.620 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1306, t_last = 339687730847 7.16.619.483 I slot launch_slot_: id 0 | task 27226 | processing task, is_child = 0 7.20.101.584 I slot print_timing: id 0 | task 27226 | n_gen = 216, tg = 71.50 t/s, tg_3s = 71.83 t/s 7.20.143.399 I slot print_timing: id 0 | task 27226 | prompt eval time = 474.95 ms / 306 tokens ( 1.55 ms per token, 644.28 tokens per second) 7.20.143.405 I slot print_timing: id 0 | task 27226 | eval time = 3048.96 ms / 219 tokens ( 13.99 ms per token, 71.50 tokens per second) 7.20.143.405 I slot print_timing: id 0 | task 27226 | total time = 3523.91 ms / 525 tokens 7.20.143.406 I slot print_timing: id 0 | task 27226 | graphs reused = 26790 7.20.143.406 I slot print_timing: id 0 | task 27226 | graph reallocs = 0 / 0 (same size) / (changed size) 7.20.143.436 I slot release: id 0 | task 27226 | stop processing: n_tokens = 524, truncated = 0 7.20.147.097 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 524, t_last = 339691261436 7.20.148.365 I slot launch_slot_: id 0 | task 27447 | processing task, is_child = 0 7.23.636.327 I slot print_timing: id 0 | task 27447 | n_gen = 216, tg = 71.64 t/s, tg_3s = 71.97 t/s 7.24.530.410 I slot print_timing: id 0 | task 27447 | prompt eval time = 486.65 ms / 317 tokens ( 1.54 ms per token, 651.39 tokens per second) 7.24.530.415 I slot print_timing: id 0 | task 27447 | eval time = 3895.39 ms / 280 tokens ( 13.96 ms per token, 71.62 tokens per second) 7.24.530.416 I slot print_timing: id 0 | task 27447 | total time = 4382.04 ms / 597 tokens 7.24.530.416 I slot print_timing: id 0 | task 27447 | graphs reused = 27067 7.24.530.417 I slot print_timing: id 0 | task 27447 | graph reallocs = 0 / 0 (same size) / (changed size) 7.24.530.449 I slot release: id 0 | task 27447 | stop processing: n_tokens = 596, truncated = 0 7.24.534.051 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 596, t_last = 339695648449 7.24.535.471 I slot launch_slot_: id 0 | task 27729 | processing task, is_child = 0 7.28.008.503 I slot print_timing: id 0 | task 27729 | n_gen = 216, tg = 71.63 t/s, tg_3s = 71.97 t/s 7.28.123.617 I slot print_timing: id 0 | task 27729 | prompt eval time = 471.62 ms / 296 tokens ( 1.59 ms per token, 627.63 tokens per second) 7.28.123.623 I slot print_timing: id 0 | task 27729 | eval time = 3116.52 ms / 224 tokens ( 13.98 ms per token, 71.55 tokens per second) 7.28.123.624 I slot print_timing: id 0 | task 27729 | total time = 3588.14 ms / 520 tokens 7.28.123.624 I slot print_timing: id 0 | task 27729 | graphs reused = 27288 7.28.123.625 I slot print_timing: id 0 | task 27729 | graph reallocs = 0 / 0 (same size) / (changed size) 7.28.123.651 I slot release: id 0 | task 27729 | stop processing: n_tokens = 519, truncated = 0 7.28.127.249 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 519, t_last = 339699241652 7.28.128.494 I slot launch_slot_: id 0 | task 27955 | processing task, is_child = 0 7.31.555.157 I slot print_timing: id 0 | task 27955 | n_gen = 216, tg = 71.65 t/s, tg_3s = 71.99 t/s 7.32.480.791 I slot print_timing: id 0 | task 27955 | prompt eval time = 426.15 ms / 254 tokens ( 1.68 ms per token, 596.03 tokens per second) 7.32.480.794 I slot print_timing: id 0 | task 27955 | eval time = 3926.13 ms / 283 tokens ( 13.92 ms per token, 71.83 tokens per second) 7.32.480.795 I slot print_timing: id 0 | task 27955 | total time = 4352.28 ms / 537 tokens 7.32.480.795 I slot print_timing: id 0 | task 27955 | graphs reused = 27567 7.32.480.796 I slot print_timing: id 0 | task 27955 | graph reallocs = 0 / 0 (same size) / (changed size) 7.32.480.824 I slot release: id 0 | task 27955 | stop processing: n_tokens = 536, truncated = 0 7.32.483.683 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.112 (> 0.100 thold), f_keep = 0.039 7.32.484.794 I slot launch_slot_: id 0 | task 28240 | processing task, is_child = 0 7.35.845.546 I slot print_timing: id 0 | task 28240 | n_gen = 216, tg = 71.65 t/s, tg_3s = 71.99 t/s 7.36.978.134 I slot print_timing: id 0 | task 28240 | prompt eval time = 360.14 ms / 188 tokens ( 1.92 ms per token, 522.02 tokens per second) 7.36.978.140 I slot print_timing: id 0 | task 28240 | eval time = 4133.19 ms / 297 tokens ( 13.96 ms per token, 71.62 tokens per second) 7.36.978.141 I slot print_timing: id 0 | task 28240 | total time = 4493.33 ms / 485 tokens 7.36.978.141 I slot print_timing: id 0 | task 28240 | graphs reused = 27861 7.36.978.142 I slot print_timing: id 0 | task 28240 | graph reallocs = 0 / 0 (same size) / (changed size) 7.36.978.164 I slot release: id 0 | task 28240 | stop processing: n_tokens = 484, truncated = 0 7.36.981.934 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 484, t_last = 339708096164 7.36.983.076 I slot launch_slot_: id 0 | task 28539 | processing task, is_child = 0 7.40.556.830 I slot print_timing: id 0 | task 28539 | n_gen = 216, tg = 71.44 t/s, tg_3s = 71.77 t/s 7.41.839.919 I slot print_timing: id 0 | task 28539 | prompt eval time = 564.17 ms / 394 tokens ( 1.43 ms per token, 698.38 tokens per second) 7.41.839.924 I slot print_timing: id 0 | task 28539 | eval time = 4292.67 ms / 308 tokens ( 13.98 ms per token, 71.52 tokens per second) 7.41.839.925 I slot print_timing: id 0 | task 28539 | total time = 4856.84 ms / 702 tokens 7.41.839.926 I slot print_timing: id 0 | task 28539 | graphs reused = 28166 7.41.839.926 I slot print_timing: id 0 | task 28539 | graph reallocs = 0 / 0 (same size) / (changed size) 7.41.839.960 I slot release: id 0 | task 28539 | stop processing: n_tokens = 701, truncated = 0 7.41.844.053 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 701, t_last = 339712957960 7.41.845.646 I slot launch_slot_: id 0 | task 28849 | processing task, is_child = 0 7.45.749.589 I slot print_timing: id 0 | task 28849 | n_gen = 216, tg = 71.49 t/s, tg_3s = 71.82 t/s 7.48.751.912 I slot print_timing: id 0 | task 28849 | n_gen = 431, tg = 71.55 t/s, tg_3s = 71.61 t/s 7.48.807.692 I slot print_timing: id 0 | task 28849 | prompt eval time = 896.46 ms / 584 tokens ( 1.54 ms per token, 651.45 tokens per second) 7.48.807.697 I slot print_timing: id 0 | task 28849 | eval time = 6065.57 ms / 435 tokens ( 13.98 ms per token, 71.55 tokens per second) 7.48.807.698 I slot print_timing: id 0 | task 28849 | total time = 6962.04 ms / 1019 tokens 7.48.807.699 I slot print_timing: id 0 | task 28849 | graphs reused = 28598 7.48.807.699 I slot print_timing: id 0 | task 28849 | graph reallocs = 0 / 0 (same size) / (changed size) 7.48.807.742 I slot release: id 0 | task 28849 | stop processing: n_tokens = 1018, truncated = 0 7.48.811.747 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1018, t_last = 339719925742 7.48.813.971 I slot launch_slot_: id 0 | task 29287 | processing task, is_child = 0 7.52.525.699 I slot print_timing: id 0 | task 29287 | n_gen = 216, tg = 71.48 t/s, tg_3s = 71.81 t/s 7.54.427.353 I slot print_timing: id 0 | task 29287 | prompt eval time = 703.71 ms / 518 tokens ( 1.36 ms per token, 736.10 tokens per second) 7.54.427.360 I slot print_timing: id 0 | task 29287 | eval time = 4909.66 ms / 352 tokens ( 13.99 ms per token, 71.49 tokens per second) 7.54.427.361 I slot print_timing: id 0 | task 29287 | total time = 5613.38 ms / 870 tokens 7.54.427.362 I slot print_timing: id 0 | task 29287 | graphs reused = 28947 7.54.427.362 I slot print_timing: id 0 | task 29287 | graph reallocs = 0 / 0 (same size) / (changed size) 7.54.427.401 I slot release: id 0 | task 29287 | stop processing: n_tokens = 869, truncated = 0 7.54.431.171 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 869, t_last = 339725545401 7.54.433.120 I slot launch_slot_: id 0 | task 29642 | processing task, is_child = 0 7.58.015.477 I slot print_timing: id 0 | task 29642 | n_gen = 217, tg = 71.67 t/s, tg_3s = 72.00 t/s 7.58.433.418 I slot print_timing: id 0 | task 29642 | prompt eval time = 568.61 ms / 399 tokens ( 1.43 ms per token, 701.72 tokens per second) 7.58.433.424 I slot print_timing: id 0 | task 29642 | eval time = 3431.68 ms / 247 tokens ( 13.95 ms per token, 71.68 tokens per second) 7.58.433.424 I slot print_timing: id 0 | task 29642 | total time = 4000.29 ms / 646 tokens 7.58.433.425 I slot print_timing: id 0 | task 29642 | graphs reused = 29191 7.58.433.426 I slot print_timing: id 0 | task 29642 | graph reallocs = 0 / 0 (same size) / (changed size) 7.58.433.462 I slot release: id 0 | task 29642 | stop processing: n_tokens = 647, truncated = 0 7.58.437.122 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 647, t_last = 339729551462 7.58.438.574 I slot launch_slot_: id 0 | task 29891 | processing task, is_child = 0 8.01.561.995 I slot print_timing: id 0 | task 29891 | prompt eval time = 505.57 ms / 335 tokens ( 1.51 ms per token, 662.62 tokens per second) 8.01.562.001 I slot print_timing: id 0 | task 29891 | eval time = 2617.84 ms / 188 tokens ( 14.00 ms per token, 71.43 tokens per second) 8.01.562.002 I slot print_timing: id 0 | task 29891 | total time = 3123.41 ms / 523 tokens 8.01.562.002 I slot print_timing: id 0 | task 29891 | graphs reused = 29376 8.01.562.003 I slot print_timing: id 0 | task 29891 | graph reallocs = 0 / 0 (same size) / (changed size) 8.01.562.033 I slot release: id 0 | task 29891 | stop processing: n_tokens = 524, truncated = 0 8.01.566.054 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 524, t_last = 339732680033 8.01.567.328 I slot launch_slot_: id 0 | task 30081 | processing task, is_child = 0 8.05.492.601 I slot print_timing: id 0 | task 30081 | n_gen = 216, tg = 71.45 t/s, tg_3s = 71.79 t/s 8.08.496.736 I slot print_timing: id 0 | task 30081 | n_gen = 431, tg = 71.51 t/s, tg_3s = 71.57 t/s 8.09.436.777 I slot print_timing: id 0 | task 30081 | prompt eval time = 916.37 ms / 603 tokens ( 1.52 ms per token, 658.03 tokens per second) 8.09.436.780 I slot print_timing: id 0 | task 30081 | eval time = 6953.07 ms / 498 tokens ( 13.99 ms per token, 71.48 tokens per second) 8.09.436.780 I slot print_timing: id 0 | task 30081 | total time = 7869.44 ms / 1101 tokens 8.09.436.781 I slot print_timing: id 0 | task 30081 | graphs reused = 29870 8.09.436.781 I slot print_timing: id 0 | task 30081 | graph reallocs = 0 / 0 (same size) / (changed size) 8.09.436.823 I slot release: id 0 | task 30081 | stop processing: n_tokens = 1102, truncated = 0 8.09.440.448 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1102, t_last = 339740554823 8.09.442.818 I slot launch_slot_: id 0 | task 30582 | processing task, is_child = 0 8.12.954.378 I slot print_timing: id 0 | task 30582 | n_gen = 216, tg = 71.50 t/s, tg_3s = 71.84 t/s 8.13.206.440 I slot print_timing: id 0 | task 30582 | prompt eval time = 504.76 ms / 333 tokens ( 1.52 ms per token, 659.71 tokens per second) 8.13.206.447 I slot print_timing: id 0 | task 30582 | eval time = 3258.85 ms / 234 tokens ( 13.99 ms per token, 71.50 tokens per second) 8.13.206.448 I slot print_timing: id 0 | task 30582 | total time = 3763.62 ms / 567 tokens 8.13.206.449 I slot print_timing: id 0 | task 30582 | graphs reused = 30101 8.13.206.449 I slot print_timing: id 0 | task 30582 | graph reallocs = 0 / 0 (same size) / (changed size) 8.13.206.480 I slot release: id 0 | task 30582 | stop processing: n_tokens = 568, truncated = 0 8.13.210.286 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 568, t_last = 339744324480 8.13.211.704 I slot launch_slot_: id 0 | task 30818 | processing task, is_child = 0 8.16.847.091 I slot print_timing: id 0 | task 30818 | n_gen = 216, tg = 71.56 t/s, tg_3s = 71.90 t/s 8.19.563.581 I slot print_timing: id 0 | task 30818 | prompt eval time = 631.01 ms / 460 tokens ( 1.37 ms per token, 728.99 tokens per second) 8.19.563.588 I slot print_timing: id 0 | task 30818 | eval time = 5720.86 ms / 410 tokens ( 13.99 ms per token, 71.49 tokens per second) 8.19.563.588 I slot print_timing: id 0 | task 30818 | total time = 6351.87 ms / 870 tokens 8.19.563.589 I slot print_timing: id 0 | task 30818 | graphs reused = 30507 8.19.563.589 I slot print_timing: id 0 | task 30818 | graph reallocs = 0 / 0 (same size) / (changed size) 8.19.563.625 I slot release: id 0 | task 30818 | stop processing: n_tokens = 871, truncated = 0 8.19.566.999 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 871, t_last = 339750681625 8.19.568.970 I slot launch_slot_: id 0 | task 31230 | processing task, is_child = 0 8.22.234.827 I slot print_timing: id 0 | task 31230 | prompt eval time = 392.29 ms / 225 tokens ( 1.74 ms per token, 573.55 tokens per second) 8.22.234.831 I slot print_timing: id 0 | task 31230 | eval time = 2273.55 ms / 164 tokens ( 13.95 ms per token, 71.69 tokens per second) 8.22.234.832 I slot print_timing: id 0 | task 31230 | total time = 2665.85 ms / 389 tokens 8.22.234.832 I slot print_timing: id 0 | task 31230 | graphs reused = 30668 8.22.234.833 I slot print_timing: id 0 | task 31230 | graph reallocs = 0 / 0 (same size) / (changed size) 8.22.234.856 I slot release: id 0 | task 31230 | stop processing: n_tokens = 390, truncated = 0 8.22.238.681 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 390, t_last = 339753352856 8.22.239.760 I slot launch_slot_: id 0 | task 31396 | processing task, is_child = 0 8.25.822.699 I slot print_timing: id 0 | task 31396 | n_gen = 216, tg = 71.62 t/s, tg_3s = 71.95 t/s 8.26.464.446 I slot print_timing: id 0 | task 31396 | prompt eval time = 580.84 ms / 415 tokens ( 1.40 ms per token, 714.49 tokens per second) 8.26.464.453 I slot print_timing: id 0 | task 31396 | eval time = 3643.84 ms / 262 tokens ( 13.96 ms per token, 71.63 tokens per second) 8.26.464.453 I slot print_timing: id 0 | task 31396 | total time = 4224.68 ms / 677 tokens 8.26.464.454 I slot print_timing: id 0 | task 31396 | graphs reused = 30927 8.26.464.455 I slot print_timing: id 0 | task 31396 | graph reallocs = 0 / 0 (same size) / (changed size) 8.26.464.491 I slot release: id 0 | task 31396 | stop processing: n_tokens = 678, truncated = 0 8.26.468.365 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 678, t_last = 339757582492 8.26.469.969 I slot launch_slot_: id 0 | task 31660 | processing task, is_child = 0 8.30.185.044 I slot print_timing: id 0 | task 31660 | n_gen = 216, tg = 71.54 t/s, tg_3s = 71.87 t/s 8.31.668.187 I slot print_timing: id 0 | task 31660 | prompt eval time = 709.61 ms / 519 tokens ( 1.37 ms per token, 731.39 tokens per second) 8.31.668.193 I slot print_timing: id 0 | task 31660 | eval time = 4488.60 ms / 322 tokens ( 13.98 ms per token, 71.51 tokens per second) 8.31.668.193 I slot print_timing: id 0 | task 31660 | total time = 5198.21 ms / 841 tokens 8.31.668.194 I slot print_timing: id 0 | task 31660 | graphs reused = 31246 8.31.668.195 I slot print_timing: id 0 | task 31660 | graph reallocs = 0 / 0 (same size) / (changed size) 8.31.668.238 I slot release: id 0 | task 31660 | stop processing: n_tokens = 842, truncated = 0 8.31.672.566 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 842, t_last = 339762786238 8.31.674.504 I slot launch_slot_: id 0 | task 31985 | processing task, is_child = 0 8.35.597.459 I slot print_timing: id 0 | task 31985 | n_gen = 216, tg = 71.55 t/s, tg_3s = 71.88 t/s 8.38.602.613 I slot print_timing: id 0 | task 31985 | n_gen = 431, tg = 71.55 t/s, tg_3s = 71.54 t/s 8.41.611.016 I slot print_timing: id 0 | task 31985 | n_gen = 646, tg = 71.52 t/s, tg_3s = 71.47 t/s 8.44.614.000 I slot print_timing: id 0 | task 31985 | n_gen = 860, tg = 71.46 t/s, tg_3s = 71.26 t/s 8.46.919.415 I slot print_timing: id 0 | task 31985 | prompt eval time = 918.06 ms / 602 tokens ( 1.53 ms per token, 655.73 tokens per second) 8.46.919.421 I slot print_timing: id 0 | task 31985 | eval time = 14326.84 ms / 1024 tokens ( 14.00 ms per token, 71.40 tokens per second) 8.46.919.422 I slot print_timing: id 0 | task 31985 | total time = 15244.90 ms / 1626 tokens 8.46.919.422 I slot print_timing: id 0 | task 31985 | graphs reused = 32264 8.46.919.423 I slot print_timing: id 0 | task 31985 | graph reallocs = 0 / 0 (same size) / (changed size) 8.46.919.469 I slot release: id 0 | task 31985 | stop processing: n_tokens = 1630, truncated = 0 8.46.923.357 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1630, t_last = 339778037469 8.46.926.777 I slot launch_slot_: id 0 | task 33012 | processing task, is_child = 0 8.50.510.746 I slot print_timing: id 0 | task 33012 | n_gen = 216, tg = 71.48 t/s, tg_3s = 71.81 t/s 8.51.253.956 I slot print_timing: id 0 | task 33012 | prompt eval time = 576.02 ms / 407 tokens ( 1.42 ms per token, 706.58 tokens per second) 8.51.253.962 I slot print_timing: id 0 | task 33012 | eval time = 3751.15 ms / 269 tokens ( 14.00 ms per token, 71.44 tokens per second) 8.51.253.963 I slot print_timing: id 0 | task 33012 | total time = 4327.17 ms / 676 tokens 8.51.253.963 I slot print_timing: id 0 | task 33012 | graphs reused = 32530 8.51.253.964 I slot print_timing: id 0 | task 33012 | graph reallocs = 0 / 0 (same size) / (changed size) 8.51.253.998 I slot release: id 0 | task 33012 | stop processing: n_tokens = 680, truncated = 0 8.51.257.731 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 680, t_last = 339782371998 8.51.259.380 I slot launch_slot_: id 0 | task 33283 | processing task, is_child = 0 8.54.918.979 I slot print_timing: id 0 | task 33283 | n_gen = 216, tg = 71.43 t/s, tg_3s = 71.76 t/s 8.56.054.345 I slot print_timing: id 0 | task 33283 | prompt eval time = 649.63 ms / 484 tokens ( 1.34 ms per token, 745.03 tokens per second) 8.56.054.350 I slot print_timing: id 0 | task 33283 | eval time = 4145.32 ms / 297 tokens ( 14.00 ms per token, 71.41 tokens per second) 8.56.054.351 I slot print_timing: id 0 | task 33283 | total time = 4794.96 ms / 781 tokens 8.56.054.352 I slot print_timing: id 0 | task 33283 | graphs reused = 32823 8.56.054.352 I slot print_timing: id 0 | task 33283 | graph reallocs = 0 / 0 (same size) / (changed size) 8.56.054.391 I slot release: id 0 | task 33283 | stop processing: n_tokens = 785, truncated = 0 8.56.058.355 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 785, t_last = 339787172391 8.56.060.189 I slot launch_slot_: id 0 | task 33582 | processing task, is_child = 0 8.58.975.633 I slot print_timing: id 0 | task 33582 | prompt eval time = 627.75 ms / 457 tokens ( 1.37 ms per token, 727.99 tokens per second) 8.58.975.639 I slot print_timing: id 0 | task 33582 | eval time = 2287.68 ms / 164 tokens ( 14.03 ms per token, 71.25 tokens per second) 8.58.975.640 I slot print_timing: id 0 | task 33582 | total time = 2915.43 ms / 621 tokens 8.58.975.640 I slot print_timing: id 0 | task 33582 | graphs reused = 32984 8.58.975.641 I slot print_timing: id 0 | task 33582 | graph reallocs = 0 / 0 (same size) / (changed size) 8.58.975.677 I slot release: id 0 | task 33582 | stop processing: n_tokens = 625, truncated = 0 8.58.979.681 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 625, t_last = 339790093677 8.58.981.552 I slot launch_slot_: id 0 | task 33748 | processing task, is_child = 0 9.02.901.158 I slot print_timing: id 0 | task 33748 | n_gen = 215, tg = 71.24 t/s, tg_3s = 71.57 t/s 9.05.910.132 I slot print_timing: id 0 | task 33748 | prompt eval time = 915.74 ms / 597 tokens ( 1.53 ms per token, 651.93 tokens per second) 9.05.910.139 I slot print_timing: id 0 | task 33748 | eval time = 6012.84 ms / 430 tokens ( 14.02 ms per token, 71.35 tokens per second) 9.05.910.139 I slot print_timing: id 0 | task 33748 | total time = 6928.57 ms / 1027 tokens 9.05.910.140 I slot print_timing: id 0 | task 33748 | graphs reused = 33410 9.05.910.140 I slot print_timing: id 0 | task 33748 | graph reallocs = 0 / 0 (same size) / (changed size) 9.05.910.190 I slot release: id 0 | task 33748 | stop processing: n_tokens = 1026, truncated = 0 9.05.914.569 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1026, t_last = 339797028190 9.05.916.807 I slot launch_slot_: id 0 | task 34181 | processing task, is_child = 0 9.09.928.309 I slot print_timing: id 0 | task 34181 | n_gen = 216, tg = 71.40 t/s, tg_3s = 71.73 t/s 9.12.941.805 I slot print_timing: id 0 | task 34181 | n_gen = 431, tg = 71.37 t/s, tg_3s = 71.35 t/s 9.14.978.279 I slot print_timing: id 0 | task 34181 | prompt eval time = 1000.37 ms / 688 tokens ( 1.45 ms per token, 687.75 tokens per second) 9.14.978.283 I slot print_timing: id 0 | task 34181 | eval time = 8061.10 ms / 576 tokens ( 14.02 ms per token, 71.33 tokens per second) 9.14.978.284 I slot print_timing: id 0 | task 34181 | total time = 9061.46 ms / 1264 tokens 9.14.978.285 I slot print_timing: id 0 | task 34181 | graphs reused = 33982 9.14.978.285 I slot print_timing: id 0 | task 34181 | graph reallocs = 0 / 0 (same size) / (changed size) 9.14.978.338 I slot release: id 0 | task 34181 | stop processing: n_tokens = 1263, truncated = 0 9.14.982.367 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1263, t_last = 339806096338 9.14.985.559 I slot launch_slot_: id 0 | task 34760 | processing task, is_child = 0 9.18.650.726 I slot print_timing: id 0 | task 34760 | n_gen = 215, tg = 71.27 t/s, tg_3s = 71.60 t/s 9.18.889.005 I slot print_timing: id 0 | task 34760 | prompt eval time = 662.57 ms / 489 tokens ( 1.35 ms per token, 738.04 tokens per second) 9.18.889.011 I slot print_timing: id 0 | task 34760 | eval time = 3240.87 ms / 232 tokens ( 14.03 ms per token, 71.28 tokens per second) 9.18.889.012 I slot print_timing: id 0 | task 34760 | total time = 3903.44 ms / 721 tokens 9.18.889.013 I slot print_timing: id 0 | task 34760 | graphs reused = 34211 9.18.889.013 I slot print_timing: id 0 | task 34760 | graph reallocs = 0 / 0 (same size) / (changed size) 9.18.889.052 I slot release: id 0 | task 34760 | stop processing: n_tokens = 720, truncated = 0 9.18.893.094 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 720, t_last = 339810007052 9.18.895.132 I slot launch_slot_: id 0 | task 34994 | processing task, is_child = 0 9.22.753.448 I slot print_timing: id 0 | task 34994 | n_gen = 216, tg = 71.34 t/s, tg_3s = 71.67 t/s 9.25.762.909 I slot print_timing: id 0 | task 34994 | n_gen = 431, tg = 71.39 t/s, tg_3s = 71.44 t/s 9.26.948.650 I slot print_timing: id 0 | task 34994 | prompt eval time = 844.50 ms / 550 tokens ( 1.54 ms per token, 651.27 tokens per second) 9.26.948.656 I slot print_timing: id 0 | task 34994 | eval time = 7209.01 ms / 515 tokens ( 14.03 ms per token, 71.30 tokens per second) 9.26.948.657 I slot print_timing: id 0 | task 34994 | total time = 8053.51 ms / 1065 tokens 9.26.948.658 I slot print_timing: id 0 | task 34994 | graphs reused = 34722 9.26.948.658 I slot print_timing: id 0 | task 34994 | graph reallocs = 0 / 0 (same size) / (changed size) 9.26.948.700 I slot release: id 0 | task 34994 | stop processing: n_tokens = 1064, truncated = 0 9.26.952.543 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1064, t_last = 339818066700 9.26.954.980 I slot launch_slot_: id 0 | task 35512 | processing task, is_child = 0 9.30.462.979 I slot print_timing: id 0 | task 35512 | n_gen = 216, tg = 71.56 t/s, tg_3s = 71.90 t/s 9.33.466.676 I slot print_timing: id 0 | task 35512 | n_gen = 431, tg = 71.57 t/s, tg_3s = 71.58 t/s 9.35.147.011 I slot print_timing: id 0 | task 35512 | prompt eval time = 503.66 ms / 334 tokens ( 1.51 ms per token, 663.14 tokens per second) 9.35.147.018 I slot print_timing: id 0 | task 35512 | eval time = 7688.35 ms / 551 tokens ( 13.98 ms per token, 71.54 tokens per second) 9.35.147.019 I slot print_timing: id 0 | task 35512 | total time = 8192.02 ms / 885 tokens 9.35.147.019 I slot print_timing: id 0 | task 35512 | graphs reused = 35269 9.35.147.020 I slot print_timing: id 0 | task 35512 | graph reallocs = 0 / 0 (same size) / (changed size) 9.35.147.053 I slot release: id 0 | task 35512 | stop processing: n_tokens = 884, truncated = 0 9.35.150.870 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 884, t_last = 339826265053 9.35.153.107 I slot launch_slot_: id 0 | task 36065 | processing task, is_child = 0 9.38.739.289 I slot print_timing: id 0 | task 36065 | n_gen = 216, tg = 71.52 t/s, tg_3s = 71.85 t/s 9.41.748.623 I slot print_timing: id 0 | task 36065 | n_gen = 431, tg = 71.48 t/s, tg_3s = 71.44 t/s 9.42.322.841 I slot print_timing: id 0 | task 36065 | prompt eval time = 579.94 ms / 416 tokens ( 1.39 ms per token, 717.32 tokens per second) 9.42.322.844 I slot print_timing: id 0 | task 36065 | eval time = 6589.79 ms / 472 tokens ( 13.99 ms per token, 71.47 tokens per second) 9.42.322.844 I slot print_timing: id 0 | task 36065 | total time = 7169.73 ms / 888 tokens 9.42.322.845 I slot print_timing: id 0 | task 36065 | graphs reused = 35737 9.42.322.846 I slot print_timing: id 0 | task 36065 | graph reallocs = 0 / 0 (same size) / (changed size) 9.42.322.881 I slot release: id 0 | task 36065 | stop processing: n_tokens = 887, truncated = 0 9.42.327.391 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 887, t_last = 339833440881 9.42.329.313 I slot launch_slot_: id 0 | task 36539 | processing task, is_child = 0 9.46.397.483 I slot print_timing: id 0 | task 36539 | n_gen = 216, tg = 71.52 t/s, tg_3s = 71.85 t/s 9.48.292.087 I slot print_timing: id 0 | task 36539 | prompt eval time = 1062.09 ms / 754 tokens ( 1.41 ms per token, 709.92 tokens per second) 9.48.292.090 I slot print_timing: id 0 | task 36539 | eval time = 4900.68 ms / 351 tokens ( 14.00 ms per token, 71.42 tokens per second) 9.48.292.091 I slot print_timing: id 0 | task 36539 | total time = 5962.77 ms / 1105 tokens 9.48.292.092 I slot print_timing: id 0 | task 36539 | graphs reused = 36084 9.48.292.092 I slot print_timing: id 0 | task 36539 | graph reallocs = 0 / 0 (same size) / (changed size) 9.48.292.147 I slot release: id 0 | task 36539 | stop processing: n_tokens = 1104, truncated = 0 9.48.296.537 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1104, t_last = 339839410147 9.48.298.949 I slot launch_slot_: id 0 | task 36893 | processing task, is_child = 0 9.52.324.553 I slot print_timing: id 0 | task 36893 | n_gen = 216, tg = 71.36 t/s, tg_3s = 71.69 t/s 9.52.702.769 I slot print_timing: id 0 | task 36893 | prompt eval time = 1012.50 ms / 706 tokens ( 1.43 ms per token, 697.28 tokens per second) 9.52.702.771 I slot print_timing: id 0 | task 36893 | eval time = 3391.31 ms / 243 tokens ( 14.01 ms per token, 71.36 tokens per second) 9.52.702.772 I slot print_timing: id 0 | task 36893 | total time = 4403.81 ms / 949 tokens 9.52.702.773 I slot print_timing: id 0 | task 36893 | graphs reused = 36324 9.52.702.773 I slot print_timing: id 0 | task 36893 | graph reallocs = 0 / 0 (same size) / (changed size) 9.52.702.825 I slot release: id 0 | task 36893 | stop processing: n_tokens = 948, truncated = 0 9.52.706.051 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 948, t_last = 339843820825 9.52.708.062 I slot launch_slot_: id 0 | task 37139 | processing task, is_child = 0 9.56.127.443 I slot print_timing: id 0 | task 37139 | n_gen = 217, tg = 71.74 t/s, tg_3s = 72.07 t/s 9.57.772.937 I slot print_timing: id 0 | task 37139 | prompt eval time = 408.43 ms / 233 tokens ( 1.75 ms per token, 570.48 tokens per second) 9.57.772.943 I slot print_timing: id 0 | task 37139 | eval time = 4656.44 ms / 335 tokens ( 13.94 ms per token, 71.73 tokens per second) 9.57.772.944 I slot print_timing: id 0 | task 37139 | total time = 5064.87 ms / 568 tokens 9.57.772.945 I slot print_timing: id 0 | task 37139 | graphs reused = 36655 9.57.772.945 I slot print_timing: id 0 | task 37139 | graph reallocs = 0 / 0 (same size) / (changed size) 9.57.772.970 I slot release: id 0 | task 37139 | stop processing: n_tokens = 567, truncated = 0 9.57.776.333 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.133 (> 0.100 thold), f_keep = 0.041 9.57.776.880 I slot launch_slot_: id 0 | task 37476 | processing task, is_child = 0 10.01.135.759 I slot print_timing: id 0 | task 37476 | n_gen = 216, tg = 71.53 t/s, tg_3s = 71.87 t/s 10.02.222.952 I slot print_timing: id 0 | task 37476 | prompt eval time = 353.25 ms / 173 tokens ( 2.04 ms per token, 489.74 tokens per second) 10.02.222.957 I slot print_timing: id 0 | task 37476 | eval time = 4092.82 ms / 294 tokens ( 13.97 ms per token, 71.59 tokens per second) 10.02.222.959 I slot print_timing: id 0 | task 37476 | total time = 4446.06 ms / 467 tokens 10.02.222.959 I slot print_timing: id 0 | task 37476 | graphs reused = 36946 10.02.222.960 I slot print_timing: id 0 | task 37476 | graph reallocs = 0 / 0 (same size) / (changed size) 10.02.222.981 I slot release: id 0 | task 37476 | stop processing: n_tokens = 466, truncated = 0 10.02.226.347 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.111 (> 0.100 thold), f_keep = 0.047 10.02.226.867 I slot launch_slot_: id 0 | task 37772 | processing task, is_child = 0 10.05.607.262 I slot print_timing: id 0 | task 37772 | n_gen = 216, tg = 71.61 t/s, tg_3s = 71.94 t/s 10.08.614.681 I slot print_timing: id 0 | task 37772 | n_gen = 431, tg = 71.55 t/s, tg_3s = 71.49 t/s 10.11.626.646 I slot print_timing: id 0 | task 37772 | n_gen = 646, tg = 71.49 t/s, tg_3s = 71.38 t/s 10.14.637.221 I slot print_timing: id 0 | task 37772 | n_gen = 861, tg = 71.47 t/s, tg_3s = 71.41 t/s 10.16.923.996 I slot print_timing: id 0 | task 37772 | prompt eval time = 377.85 ms / 199 tokens ( 1.90 ms per token, 526.66 tokens per second) 10.16.924.001 I slot print_timing: id 0 | task 37772 | eval time = 14319.27 ms / 1024 tokens ( 14.00 ms per token, 71.44 tokens per second) 10.16.924.002 I slot print_timing: id 0 | task 37772 | total time = 14697.12 ms / 1223 tokens 10.16.924.002 I slot print_timing: id 0 | task 37772 | graphs reused = 37964 10.16.924.003 I slot print_timing: id 0 | task 37772 | graph reallocs = 0 / 0 (same size) / (changed size) 10.16.924.026 I slot release: id 0 | task 37772 | stop processing: n_tokens = 1222, truncated = 0 10.16.927.437 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 10.16.929.938 I slot launch_slot_: id 0 | task 38798 | processing task, is_child = 0 10.20.261.792 I slot print_timing: id 0 | task 38798 | n_gen = 216, tg = 71.60 t/s, tg_3s = 71.93 t/s 10.20.902.519 I slot print_timing: id 0 | task 38798 | prompt eval time = 329.07 ms / 149 tokens ( 2.21 ms per token, 452.79 tokens per second) 10.20.902.523 I slot print_timing: id 0 | task 38798 | eval time = 3643.50 ms / 262 tokens ( 13.96 ms per token, 71.63 tokens per second) 10.20.902.523 I slot print_timing: id 0 | task 38798 | total time = 3972.57 ms / 411 tokens 10.20.902.524 I slot print_timing: id 0 | task 38798 | graphs reused = 38223 10.20.902.525 I slot print_timing: id 0 | task 38798 | graph reallocs = 0 / 0 (same size) / (changed size) 10.20.902.545 I slot release: id 0 | task 38798 | stop processing: n_tokens = 410, truncated = 0 10.20.905.929 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 410, t_last = 339872020545 10.20.906.407 I slot launch_slot_: id 0 | task 39062 | processing task, is_child = 0 10.24.296.639 I slot print_timing: id 0 | task 39062 | n_gen = 216, tg = 71.64 t/s, tg_3s = 71.98 t/s 10.27.297.807 I slot print_timing: id 0 | task 39062 | n_gen = 431, tg = 71.64 t/s, tg_3s = 71.64 t/s 10.29.552.365 I slot print_timing: id 0 | task 39062 | prompt eval time = 389.21 ms / 216 tokens ( 1.80 ms per token, 554.97 tokens per second) 10.29.552.368 I slot print_timing: id 0 | task 39062 | eval time = 8256.74 ms / 592 tokens ( 13.97 ms per token, 71.58 tokens per second) 10.29.552.369 I slot print_timing: id 0 | task 39062 | total time = 8645.95 ms / 808 tokens 10.29.552.370 I slot print_timing: id 0 | task 39062 | graphs reused = 38810 10.29.552.370 I slot print_timing: id 0 | task 39062 | graph reallocs = 0 / 0 (same size) / (changed size) 10.29.552.402 I slot release: id 0 | task 39062 | stop processing: n_tokens = 807, truncated = 0 10.29.555.986 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.160 (> 0.100 thold), f_keep = 0.026 10.29.557.733 I slot launch_slot_: id 0 | task 39656 | processing task, is_child = 0 10.30.869.537 I slot print_timing: id 0 | task 39656 | prompt eval time = 307.44 ms / 131 tokens ( 2.35 ms per token, 426.10 tokens per second) 10.30.869.543 I slot print_timing: id 0 | task 39656 | eval time = 1004.36 ms / 72 tokens ( 14.15 ms per token, 70.69 tokens per second) 10.30.869.543 I slot print_timing: id 0 | task 39656 | total time = 1311.79 ms / 203 tokens 10.30.869.544 I slot print_timing: id 0 | task 39656 | graphs reused = 38880 10.30.869.545 I slot print_timing: id 0 | task 39656 | graph reallocs = 0 / 0 (same size) / (changed size) 10.30.869.567 I slot release: id 0 | task 39656 | stop processing: n_tokens = 202, truncated = 0 10.30.872.971 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.121 (> 0.100 thold), f_keep = 0.104 10.30.873.295 I slot launch_slot_: id 0 | task 39730 | processing task, is_child = 0 10.34.232.864 I slot print_timing: id 0 | task 39730 | n_gen = 216, tg = 71.54 t/s, tg_3s = 71.87 t/s 10.36.723.266 I slot print_timing: id 0 | task 39730 | prompt eval time = 354.17 ms / 174 tokens ( 2.04 ms per token, 491.30 tokens per second) 10.36.723.273 I slot print_timing: id 0 | task 39730 | eval time = 5495.80 ms / 394 tokens ( 13.98 ms per token, 71.51 tokens per second) 10.36.723.274 I slot print_timing: id 0 | task 39730 | total time = 5849.96 ms / 568 tokens 10.36.723.274 I slot print_timing: id 0 | task 39730 | graphs reused = 39270 10.36.723.275 I slot print_timing: id 0 | task 39730 | graph reallocs = 0 / 0 (same size) / (changed size) 10.36.723.296 I slot release: id 0 | task 39730 | stop processing: n_tokens = 567, truncated = 0 10.36.726.681 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.129 (> 0.100 thold), f_keep = 0.037 10.36.728.050 I slot launch_slot_: id 0 | task 40126 | processing task, is_child = 0 10.40.072.113 I slot print_timing: id 0 | task 40126 | n_gen = 216, tg = 71.52 t/s, tg_3s = 71.85 t/s 10.43.082.064 I slot print_timing: id 0 | task 40126 | n_gen = 431, tg = 71.47 t/s, tg_3s = 71.43 t/s 10.43.124.707 I slot print_timing: id 0 | task 40126 | prompt eval time = 337.75 ms / 163 tokens ( 2.07 ms per token, 482.60 tokens per second) 10.43.124.713 I slot print_timing: id 0 | task 40126 | eval time = 6058.89 ms / 434 tokens ( 13.99 ms per token, 71.47 tokens per second) 10.43.124.713 I slot print_timing: id 0 | task 40126 | total time = 6396.65 ms / 597 tokens 10.43.124.714 I slot print_timing: id 0 | task 40126 | graphs reused = 39700 10.43.124.715 I slot print_timing: id 0 | task 40126 | graph reallocs = 0 / 0 (same size) / (changed size) 10.43.124.738 I slot release: id 0 | task 40126 | stop processing: n_tokens = 596, truncated = 0 10.43.127.902 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.208 (> 0.100 thold), f_keep = 0.035 10.43.129.234 I slot launch_slot_: id 0 | task 40562 | processing task, is_child = 0 10.46.429.358 I slot print_timing: id 0 | task 40562 | n_gen = 216, tg = 71.50 t/s, tg_3s = 71.83 t/s 10.49.435.141 I slot print_timing: id 0 | task 40562 | n_gen = 431, tg = 71.51 t/s, tg_3s = 71.53 t/s 10.51.746.207 I slot print_timing: id 0 | task 40562 | prompt eval time = 293.10 ms / 101 tokens ( 2.90 ms per token, 344.59 tokens per second) 10.51.746.215 I slot print_timing: id 0 | task 40562 | eval time = 8323.86 ms / 596 tokens ( 13.99 ms per token, 71.48 tokens per second) 10.51.746.215 I slot print_timing: id 0 | task 40562 | total time = 8616.96 ms / 697 tokens 10.51.746.216 I slot print_timing: id 0 | task 40562 | graphs reused = 40292 10.51.746.216 I slot print_timing: id 0 | task 40562 | graph reallocs = 0 / 0 (same size) / (changed size) 10.51.746.234 I slot release: id 0 | task 40562 | stop processing: n_tokens = 696, truncated = 0 10.51.749.603 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.126 (> 0.100 thold), f_keep = 0.030 10.51.751.185 I slot launch_slot_: id 0 | task 41160 | processing task, is_child = 0 10.55.105.751 I slot print_timing: id 0 | task 41160 | n_gen = 216, tg = 71.60 t/s, tg_3s = 71.93 t/s 10.58.110.779 I slot print_timing: id 0 | task 41160 | n_gen = 431, tg = 71.57 t/s, tg_3s = 71.55 t/s 10.58.614.731 I slot print_timing: id 0 | task 41160 | prompt eval time = 351.61 ms / 167 tokens ( 2.11 ms per token, 474.96 tokens per second) 10.58.614.737 I slot print_timing: id 0 | task 41160 | eval time = 6511.93 ms / 467 tokens ( 13.97 ms per token, 71.56 tokens per second) 10.58.614.737 I slot print_timing: id 0 | task 41160 | total time = 6863.54 ms / 634 tokens 10.58.614.738 I slot print_timing: id 0 | task 41160 | graphs reused = 40755 10.58.614.738 I slot print_timing: id 0 | task 41160 | graph reallocs = 0 / 0 (same size) / (changed size) 10.58.614.759 I slot release: id 0 | task 41160 | stop processing: n_tokens = 633, truncated = 0 10.58.618.088 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.123 (> 0.100 thold), f_keep = 0.033 10.58.619.629 I slot launch_slot_: id 0 | task 41629 | processing task, is_child = 0 11.01.980.527 I slot print_timing: id 0 | task 41629 | n_gen = 216, tg = 71.50 t/s, tg_3s = 71.83 t/s 11.04.987.377 I slot print_timing: id 0 | task 41629 | n_gen = 431, tg = 71.50 t/s, tg_3s = 71.50 t/s 11.05.225.149 I slot print_timing: id 0 | task 41629 | prompt eval time = 353.80 ms / 171 tokens ( 2.07 ms per token, 483.33 tokens per second) 11.05.225.155 I slot print_timing: id 0 | task 41629 | eval time = 6251.71 ms / 448 tokens ( 13.99 ms per token, 71.50 tokens per second) 11.05.225.156 I slot print_timing: id 0 | task 41629 | total time = 6605.51 ms / 619 tokens 11.05.225.156 I slot print_timing: id 0 | task 41629 | graphs reused = 41199 11.05.225.157 I slot print_timing: id 0 | task 41629 | graph reallocs = 0 / 0 (same size) / (changed size) 11.05.225.178 I slot release: id 0 | task 41629 | stop processing: n_tokens = 618, truncated = 0 11.05.228.554 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.117 (> 0.100 thold), f_keep = 0.034 11.05.229.952 I slot launch_slot_: id 0 | task 42079 | processing task, is_child = 0 11.08.594.156 I slot print_timing: id 0 | task 42079 | n_gen = 217, tg = 71.80 t/s, tg_3s = 72.14 t/s 11.08.849.163 I slot print_timing: id 0 | task 42079 | prompt eval time = 355.96 ms / 179 tokens ( 1.99 ms per token, 502.87 tokens per second) 11.08.849.169 I slot print_timing: id 0 | task 42079 | eval time = 3263.24 ms / 235 tokens ( 13.95 ms per token, 71.71 tokens per second) 11.08.849.169 I slot print_timing: id 0 | task 42079 | total time = 3619.20 ms / 414 tokens 11.08.849.170 I slot print_timing: id 0 | task 42079 | graphs reused = 41431 11.08.849.171 I slot print_timing: id 0 | task 42079 | graph reallocs = 0 / 0 (same size) / (changed size) 11.08.849.191 I slot release: id 0 | task 42079 | stop processing: n_tokens = 413, truncated = 0 11.08.852.411 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.127 (> 0.100 thold), f_keep = 0.051 11.08.852.920 I slot launch_slot_: id 0 | task 42316 | processing task, is_child = 0 11.12.051.988 I slot print_timing: id 0 | task 42316 | prompt eval time = 349.58 ms / 165 tokens ( 2.12 ms per token, 472.00 tokens per second) 11.12.051.998 I slot print_timing: id 0 | task 42316 | eval time = 2849.49 ms / 205 tokens ( 13.97 ms per token, 71.59 tokens per second) 11.12.051.998 I slot print_timing: id 0 | task 42316 | total time = 3199.06 ms / 370 tokens 11.12.051.999 I slot print_timing: id 0 | task 42316 | graphs reused = 41633 11.12.051.999 I slot print_timing: id 0 | task 42316 | graph reallocs = 0 / 0 (same size) / (changed size) 11.12.052.020 I slot release: id 0 | task 42316 | stop processing: n_tokens = 369, truncated = 0 11.12.055.282 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.132 (> 0.100 thold), f_keep = 0.057 11.12.056.233 I slot launch_slot_: id 0 | task 42523 | processing task, is_child = 0 11.15.405.252 I slot print_timing: id 0 | task 42523 | n_gen = 217, tg = 71.70 t/s, tg_3s = 72.04 t/s 11.18.411.627 I slot print_timing: id 0 | task 42523 | n_gen = 432, tg = 71.61 t/s, tg_3s = 71.51 t/s 11.19.477.537 I slot print_timing: id 0 | task 42523 | prompt eval time = 336.60 ms / 159 tokens ( 2.12 ms per token, 472.37 tokens per second) 11.19.477.543 I slot print_timing: id 0 | task 42523 | eval time = 7084.69 ms / 508 tokens ( 13.97 ms per token, 71.56 tokens per second) 11.19.477.543 I slot print_timing: id 0 | task 42523 | total time = 7421.29 ms / 667 tokens 11.19.477.544 I slot print_timing: id 0 | task 42523 | graphs reused = 42137 11.19.477.544 I slot print_timing: id 0 | task 42523 | graph reallocs = 0 / 0 (same size) / (changed size) 11.19.477.569 I slot release: id 0 | task 42523 | stop processing: n_tokens = 666, truncated = 0 11.19.480.852 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.118 (> 0.100 thold), f_keep = 0.032 11.19.482.378 I slot launch_slot_: id 0 | task 43033 | processing task, is_child = 0 11.21.686.937 I slot print_timing: id 0 | task 43033 | prompt eval time = 358.12 ms / 178 tokens ( 2.01 ms per token, 497.03 tokens per second) 11.21.686.940 I slot print_timing: id 0 | task 43033 | eval time = 1846.42 ms / 133 tokens ( 13.99 ms per token, 71.49 tokens per second) 11.21.686.941 I slot print_timing: id 0 | task 43033 | total time = 2204.55 ms / 311 tokens 11.21.686.942 I slot print_timing: id 0 | task 43033 | graphs reused = 42267 11.21.686.942 I slot print_timing: id 0 | task 43033 | graph reallocs = 0 / 0 (same size) / (changed size) 11.21.686.962 I slot release: id 0 | task 43033 | stop processing: n_tokens = 310, truncated = 0 11.21.690.292 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.112 (> 0.100 thold), f_keep = 0.068 11.21.690.710 I slot launch_slot_: id 0 | task 43168 | processing task, is_child = 0 11.25.061.639 I slot print_timing: id 0 | task 43168 | n_gen = 216, tg = 71.51 t/s, tg_3s = 71.85 t/s 11.28.066.270 I slot print_timing: id 0 | task 43168 | n_gen = 431, tg = 71.54 t/s, tg_3s = 71.56 t/s 11.31.071.602 I slot print_timing: id 0 | task 43168 | n_gen = 646, tg = 71.54 t/s, tg_3s = 71.54 t/s 11.34.074.654 I slot print_timing: id 0 | task 43168 | n_gen = 860, tg = 71.47 t/s, tg_3s = 71.26 t/s 11.36.377.036 I slot print_timing: id 0 | task 43168 | prompt eval time = 364.54 ms / 188 tokens ( 1.94 ms per token, 515.72 tokens per second) 11.36.377.042 I slot print_timing: id 0 | task 43168 | eval time = 14321.78 ms / 1024 tokens ( 14.00 ms per token, 71.43 tokens per second) 11.36.377.042 I slot print_timing: id 0 | task 43168 | total time = 14686.32 ms / 1212 tokens 11.36.377.043 I slot print_timing: id 0 | task 43168 | graphs reused = 43285 11.36.377.043 I slot print_timing: id 0 | task 43168 | graph reallocs = 0 / 0 (same size) / (changed size) 11.36.377.069 I slot release: id 0 | task 43168 | stop processing: n_tokens = 1211, truncated = 0 11.36.380.190 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.128 (> 0.100 thold), f_keep = 0.017 11.36.382.780 I slot launch_slot_: id 0 | task 44194 | processing task, is_child = 0 11.39.737.117 I slot print_timing: id 0 | task 44194 | n_gen = 217, tg = 71.67 t/s, tg_3s = 72.00 t/s 11.42.633.702 I slot print_timing: id 0 | task 44194 | prompt eval time = 340.42 ms / 164 tokens ( 2.08 ms per token, 481.76 tokens per second) 11.42.633.708 I slot print_timing: id 0 | task 44194 | eval time = 5910.49 ms / 424 tokens ( 13.97 ms per token, 71.57 tokens per second) 11.42.633.709 I slot print_timing: id 0 | task 44194 | total time = 6250.91 ms / 588 tokens 11.42.633.709 I slot print_timing: id 0 | task 44194 | graphs reused = 43705 11.42.633.710 I slot print_timing: id 0 | task 44194 | graph reallocs = 0 / 0 (same size) / (changed size) 11.42.633.731 I slot release: id 0 | task 44194 | stop processing: n_tokens = 587, truncated = 0 11.42.637.119 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 11.42.638.455 I slot launch_slot_: id 0 | task 44620 | processing task, is_child = 0 11.46.006.060 I slot print_timing: id 0 | task 44620 | n_gen = 216, tg = 71.47 t/s, tg_3s = 71.80 t/s 11.49.014.204 I slot print_timing: id 0 | task 44620 | n_gen = 431, tg = 71.47 t/s, tg_3s = 71.47 t/s 11.52.024.701 I slot print_timing: id 0 | task 44620 | n_gen = 646, tg = 71.45 t/s, tg_3s = 71.42 t/s 11.55.035.035 I slot print_timing: id 0 | task 44620 | n_gen = 861, tg = 71.44 t/s, tg_3s = 71.42 t/s 11.57.322.720 I slot print_timing: id 0 | task 44620 | prompt eval time = 359.16 ms / 181 tokens ( 1.98 ms per token, 503.95 tokens per second) 11.57.322.726 I slot print_timing: id 0 | task 44620 | eval time = 14325.09 ms / 1024 tokens ( 14.00 ms per token, 71.41 tokens per second) 11.57.322.727 I slot print_timing: id 0 | task 44620 | total time = 14684.25 ms / 1205 tokens 11.57.322.727 I slot print_timing: id 0 | task 44620 | graphs reused = 44723 11.57.322.728 I slot print_timing: id 0 | task 44620 | graph reallocs = 0 / 0 (same size) / (changed size) 11.57.322.750 I slot release: id 0 | task 44620 | stop processing: n_tokens = 1204, truncated = 0 11.57.326.149 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.136 (> 0.100 thold), f_keep = 0.017 11.57.328.720 I slot launch_slot_: id 0 | task 45646 | processing task, is_child = 0 12.00.663.611 I slot print_timing: id 0 | task 45646 | n_gen = 216, tg = 71.64 t/s, tg_3s = 71.97 t/s 12.01.668.350 I slot print_timing: id 0 | task 45646 | prompt eval time = 333.71 ms / 154 tokens ( 2.17 ms per token, 461.48 tokens per second) 12.01.668.356 I slot print_timing: id 0 | task 45646 | eval time = 4005.91 ms / 288 tokens ( 13.96 ms per token, 71.64 tokens per second) 12.01.668.357 I slot print_timing: id 0 | task 45646 | total time = 4339.62 ms / 442 tokens 12.01.668.358 I slot print_timing: id 0 | task 45646 | graphs reused = 45008 12.01.668.358 I slot print_timing: id 0 | task 45646 | graph reallocs = 0 / 0 (same size) / (changed size) 12.01.668.378 I slot release: id 0 | task 45646 | stop processing: n_tokens = 441, truncated = 0 12.01.671.709 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.048 12.01.672.782 I slot launch_slot_: id 0 | task 45936 | processing task, is_child = 0 12.03.610.929 I slot print_timing: id 0 | task 45936 | prompt eval time = 321.20 ms / 135 tokens ( 2.38 ms per token, 420.30 tokens per second) 12.03.610.933 I slot print_timing: id 0 | task 45936 | eval time = 1616.94 ms / 117 tokens ( 13.94 ms per token, 71.74 tokens per second) 12.03.610.933 I slot print_timing: id 0 | task 45936 | total time = 1938.14 ms / 252 tokens 12.03.610.934 I slot print_timing: id 0 | task 45936 | graphs reused = 45123 12.03.610.934 I slot print_timing: id 0 | task 45936 | graph reallocs = 0 / 0 (same size) / (changed size) 12.03.610.953 I slot release: id 0 | task 45936 | stop processing: n_tokens = 251, truncated = 0 12.03.614.290 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.117 (> 0.100 thold), f_keep = 0.084 12.03.615.012 I slot launch_slot_: id 0 | task 46055 | processing task, is_child = 0 12.06.975.646 I slot print_timing: id 0 | task 46055 | n_gen = 216, tg = 71.58 t/s, tg_3s = 71.91 t/s 12.09.700.573 I slot print_timing: id 0 | task 46055 | prompt eval time = 356.85 ms / 179 tokens ( 1.99 ms per token, 501.61 tokens per second) 12.09.700.583 I slot print_timing: id 0 | task 46055 | eval time = 5728.70 ms / 411 tokens ( 13.97 ms per token, 71.57 tokens per second) 12.09.700.583 I slot print_timing: id 0 | task 46055 | total time = 6085.55 ms / 590 tokens 12.09.700.584 I slot print_timing: id 0 | task 46055 | graphs reused = 45530 12.09.700.584 I slot print_timing: id 0 | task 46055 | graph reallocs = 0 / 0 (same size) / (changed size) 12.09.700.606 I slot release: id 0 | task 46055 | stop processing: n_tokens = 589, truncated = 0 12.09.704.003 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 12.09.705.370 I slot launch_slot_: id 0 | task 46468 | processing task, is_child = 0 12.13.095.671 I slot print_timing: id 0 | task 46468 | n_gen = 216, tg = 71.55 t/s, tg_3s = 71.88 t/s 12.16.107.634 I slot print_timing: id 0 | task 46468 | n_gen = 431, tg = 71.47 t/s, tg_3s = 71.38 t/s 12.16.205.437 I slot print_timing: id 0 | task 46468 | prompt eval time = 385.48 ms / 210 tokens ( 1.84 ms per token, 544.77 tokens per second) 12.16.205.443 I slot print_timing: id 0 | task 46468 | eval time = 6114.57 ms / 438 tokens ( 13.99 ms per token, 71.47 tokens per second) 12.16.205.443 I slot print_timing: id 0 | task 46468 | total time = 6500.06 ms / 648 tokens 12.16.205.444 I slot print_timing: id 0 | task 46468 | graphs reused = 45964 12.16.205.444 I slot print_timing: id 0 | task 46468 | graph reallocs = 0 / 0 (same size) / (changed size) 12.16.205.471 I slot release: id 0 | task 46468 | stop processing: n_tokens = 647, truncated = 0 12.16.209.119 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.165 (> 0.100 thold), f_keep = 0.032 12.16.210.644 I slot launch_slot_: id 0 | task 46908 | processing task, is_child = 0 12.19.522.922 I slot print_timing: id 0 | task 46908 | n_gen = 216, tg = 71.60 t/s, tg_3s = 71.93 t/s 12.22.531.119 I slot print_timing: id 0 | task 46908 | n_gen = 431, tg = 71.54 t/s, tg_3s = 71.47 t/s 12.22.797.701 I slot print_timing: id 0 | task 46908 | prompt eval time = 309.51 ms / 127 tokens ( 2.44 ms per token, 410.32 tokens per second) 12.22.797.707 I slot print_timing: id 0 | task 46908 | eval time = 6277.54 ms / 450 tokens ( 13.98 ms per token, 71.52 tokens per second) 12.22.797.708 I slot print_timing: id 0 | task 46908 | total time = 6587.05 ms / 577 tokens 12.22.797.708 I slot print_timing: id 0 | task 46908 | graphs reused = 46410 12.22.797.709 I slot print_timing: id 0 | task 46908 | graph reallocs = 0 / 0 (same size) / (changed size) 12.22.797.727 I slot release: id 0 | task 46908 | stop processing: n_tokens = 576, truncated = 0 12.22.800.962 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.152 (> 0.100 thold), f_keep = 0.036 12.22.802.283 I slot launch_slot_: id 0 | task 47360 | processing task, is_child = 0 12.26.131.017 I slot print_timing: id 0 | task 47360 | n_gen = 216, tg = 71.57 t/s, tg_3s = 71.90 t/s 12.27.232.893 I slot print_timing: id 0 | task 47360 | prompt eval time = 324.72 ms / 138 tokens ( 2.35 ms per token, 424.98 tokens per second) 12.27.232.899 I slot print_timing: id 0 | task 47360 | eval time = 4105.88 ms / 295 tokens ( 13.97 ms per token, 71.60 tokens per second) 12.27.232.900 I slot print_timing: id 0 | task 47360 | total time = 4430.60 ms / 433 tokens 12.27.232.900 I slot print_timing: id 0 | task 47360 | graphs reused = 46702 12.27.232.901 I slot print_timing: id 0 | task 47360 | graph reallocs = 0 / 0 (same size) / (changed size) 12.27.232.920 I slot release: id 0 | task 47360 | stop processing: n_tokens = 432, truncated = 0 12.27.236.106 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.151 (> 0.100 thold), f_keep = 0.049 12.27.237.224 I slot launch_slot_: id 0 | task 47657 | processing task, is_child = 0 12.30.562.113 I slot print_timing: id 0 | task 47657 | n_gen = 216, tg = 71.60 t/s, tg_3s = 71.94 t/s 12.33.565.335 I slot print_timing: id 0 | task 47657 | n_gen = 431, tg = 71.60 t/s, tg_3s = 71.59 t/s 12.36.397.570 I slot print_timing: id 0 | task 47657 | prompt eval time = 322.26 ms / 139 tokens ( 2.32 ms per token, 431.33 tokens per second) 12.36.397.576 I slot print_timing: id 0 | task 47657 | eval time = 8838.08 ms / 633 tokens ( 13.98 ms per token, 71.51 tokens per second) 12.36.397.577 I slot print_timing: id 0 | task 47657 | total time = 9160.34 ms / 772 tokens 12.36.397.578 I slot print_timing: id 0 | task 47657 | graphs reused = 47330 12.36.397.578 I slot print_timing: id 0 | task 47657 | graph reallocs = 0 / 0 (same size) / (changed size) 12.36.397.597 I slot release: id 0 | task 47657 | stop processing: n_tokens = 771, truncated = 0 12.36.400.813 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.134 (> 0.100 thold), f_keep = 0.027 12.36.402.544 I slot launch_slot_: id 0 | task 48292 | processing task, is_child = 0 12.39.737.650 I slot print_timing: id 0 | task 48292 | n_gen = 216, tg = 71.64 t/s, tg_3s = 71.97 t/s 12.40.939.614 I slot print_timing: id 0 | task 48292 | prompt eval time = 333.92 ms / 157 tokens ( 2.13 ms per token, 470.17 tokens per second) 12.40.939.618 I slot print_timing: id 0 | task 48292 | eval time = 4203.13 ms / 302 tokens ( 13.96 ms per token, 71.61 tokens per second) 12.40.939.619 I slot print_timing: id 0 | task 48292 | total time = 4537.06 ms / 459 tokens 12.40.939.620 I slot print_timing: id 0 | task 48292 | graphs reused = 47629 12.40.939.620 I slot print_timing: id 0 | task 48292 | graph reallocs = 0 / 0 (same size) / (changed size) 12.40.939.641 I slot release: id 0 | task 48292 | stop processing: n_tokens = 458, truncated = 0 12.40.942.989 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.129 (> 0.100 thold), f_keep = 0.046 12.40.944.115 I slot launch_slot_: id 0 | task 48596 | processing task, is_child = 0 12.44.289.382 I slot print_timing: id 0 | task 48596 | n_gen = 216, tg = 71.57 t/s, tg_3s = 71.90 t/s 12.45.954.260 I slot print_timing: id 0 | task 48596 | prompt eval time = 341.25 ms / 163 tokens ( 2.09 ms per token, 477.66 tokens per second) 12.45.954.266 I slot print_timing: id 0 | task 48596 | eval time = 4668.89 ms / 335 tokens ( 13.98 ms per token, 71.54 tokens per second) 12.45.954.267 I slot print_timing: id 0 | task 48596 | total time = 5010.14 ms / 498 tokens 12.45.954.267 I slot print_timing: id 0 | task 48596 | graphs reused = 47961 12.45.954.268 I slot print_timing: id 0 | task 48596 | graph reallocs = 0 / 0 (same size) / (changed size) 12.45.954.289 I slot release: id 0 | task 48596 | stop processing: n_tokens = 497, truncated = 0 12.45.957.746 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.134 (> 0.100 thold), f_keep = 0.042 12.45.958.906 I slot launch_slot_: id 0 | task 48933 | processing task, is_child = 0 12.49.296.855 I slot print_timing: id 0 | task 48933 | n_gen = 216, tg = 71.58 t/s, tg_3s = 71.92 t/s 12.52.300.395 I slot print_timing: id 0 | task 48933 | n_gen = 431, tg = 71.58 t/s, tg_3s = 71.58 t/s 12.53.432.412 I slot print_timing: id 0 | task 48933 | prompt eval time = 334.51 ms / 157 tokens ( 2.13 ms per token, 469.34 tokens per second) 12.53.432.418 I slot print_timing: id 0 | task 48933 | eval time = 7138.99 ms / 512 tokens ( 13.97 ms per token, 71.58 tokens per second) 12.53.432.419 I slot print_timing: id 0 | task 48933 | total time = 7473.50 ms / 669 tokens 12.53.432.419 I slot print_timing: id 0 | task 48933 | graphs reused = 48469 12.53.432.420 I slot print_timing: id 0 | task 48933 | graph reallocs = 0 / 0 (same size) / (changed size) 12.53.432.442 I slot release: id 0 | task 48933 | stop processing: n_tokens = 668, truncated = 0 12.53.435.725 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.134 (> 0.100 thold), f_keep = 0.031 12.53.437.223 I slot launch_slot_: id 0 | task 49447 | processing task, is_child = 0 12.56.783.335 I slot print_timing: id 0 | task 49447 | n_gen = 217, tg = 71.71 t/s, tg_3s = 72.04 t/s 12.59.790.196 I slot print_timing: id 0 | task 49447 | n_gen = 432, tg = 71.60 t/s, tg_3s = 71.50 t/s 13.01.189.008 I slot print_timing: id 0 | task 49447 | prompt eval time = 333.81 ms / 157 tokens ( 2.13 ms per token, 470.33 tokens per second) 13.01.189.012 I slot print_timing: id 0 | task 49447 | eval time = 7417.97 ms / 532 tokens ( 13.97 ms per token, 71.58 tokens per second) 13.01.189.012 I slot print_timing: id 0 | task 49447 | total time = 7751.78 ms / 689 tokens 13.01.189.013 I slot print_timing: id 0 | task 49447 | graphs reused = 48997 13.01.189.013 I slot print_timing: id 0 | task 49447 | graph reallocs = 0 / 0 (same size) / (changed size) 13.01.189.042 I slot release: id 0 | task 49447 | stop processing: n_tokens = 688, truncated = 0 13.01.192.323 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.134 (> 0.100 thold), f_keep = 0.031 13.01.193.811 I slot launch_slot_: id 0 | task 49981 | processing task, is_child = 0 13.04.540.333 I slot print_timing: id 0 | task 49981 | n_gen = 217, tg = 71.73 t/s, tg_3s = 72.06 t/s 13.05.279.876 I slot print_timing: id 0 | task 49981 | prompt eval time = 335.07 ms / 157 tokens ( 2.13 ms per token, 468.56 tokens per second) 13.05.279.883 I slot print_timing: id 0 | task 49981 | eval time = 3750.98 ms / 270 tokens ( 13.94 ms per token, 71.71 tokens per second) 13.05.279.884 I slot print_timing: id 0 | task 49981 | total time = 4086.05 ms / 427 tokens 13.05.279.885 I slot print_timing: id 0 | task 49981 | graphs reused = 49264 13.05.279.885 I slot print_timing: id 0 | task 49981 | graph reallocs = 0 / 0 (same size) / (changed size) 13.05.279.905 I slot release: id 0 | task 49981 | stop processing: n_tokens = 426, truncated = 0 13.05.283.127 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 13.05.284.156 I slot launch_slot_: id 0 | task 50253 | processing task, is_child = 0 13.06.772.236 I slot print_timing: id 0 | task 50253 | prompt eval time = 354.38 ms / 172 tokens ( 2.06 ms per token, 485.36 tokens per second) 13.06.772.240 I slot print_timing: id 0 | task 50253 | eval time = 1133.69 ms / 82 tokens ( 14.00 ms per token, 71.45 tokens per second) 13.06.772.241 I slot print_timing: id 0 | task 50253 | total time = 1488.07 ms / 254 tokens 13.06.772.242 I slot print_timing: id 0 | task 50253 | graphs reused = 49344 13.06.772.242 I slot print_timing: id 0 | task 50253 | graph reallocs = 0 / 0 (same size) / (changed size) 13.06.772.262 I slot release: id 0 | task 50253 | stop processing: n_tokens = 253, truncated = 0 13.06.775.495 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 13.06.776.227 I slot launch_slot_: id 0 | task 50337 | processing task, is_child = 0 13.10.113.645 I slot print_timing: id 0 | task 50337 | n_gen = 216, tg = 71.60 t/s, tg_3s = 71.93 t/s 13.10.254.286 I slot print_timing: id 0 | task 50337 | prompt eval time = 334.65 ms / 163 tokens ( 2.05 ms per token, 487.08 tokens per second) 13.10.254.289 I slot print_timing: id 0 | task 50337 | eval time = 3143.40 ms / 226 tokens ( 13.97 ms per token, 71.58 tokens per second) 13.10.254.290 I slot print_timing: id 0 | task 50337 | total time = 3478.05 ms / 389 tokens 13.10.254.290 I slot print_timing: id 0 | task 50337 | graphs reused = 49567 13.10.254.291 I slot print_timing: id 0 | task 50337 | graph reallocs = 0 / 0 (same size) / (changed size) 13.10.254.312 I slot release: id 0 | task 50337 | stop processing: n_tokens = 388, truncated = 0 13.10.257.716 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.127 (> 0.100 thold), f_keep = 0.054 13.10.258.737 I slot launch_slot_: id 0 | task 50565 | processing task, is_child = 0 13.13.610.812 I slot print_timing: id 0 | task 50565 | n_gen = 216, tg = 71.62 t/s, tg_3s = 71.96 t/s 13.16.621.156 I slot print_timing: id 0 | task 50565 | n_gen = 431, tg = 71.52 t/s, tg_3s = 71.42 t/s 13.16.914.841 I slot print_timing: id 0 | task 50565 | prompt eval time = 350.20 ms / 165 tokens ( 2.12 ms per token, 471.16 tokens per second) 13.16.914.847 I slot print_timing: id 0 | task 50565 | eval time = 6305.90 ms / 452 tokens ( 13.98 ms per token, 71.52 tokens per second) 13.16.914.848 I slot print_timing: id 0 | task 50565 | total time = 6656.10 ms / 617 tokens 13.16.914.848 I slot print_timing: id 0 | task 50565 | graphs reused = 50015 13.16.914.849 I slot print_timing: id 0 | task 50565 | graph reallocs = 0 / 0 (same size) / (changed size) 13.16.914.870 I slot release: id 0 | task 50565 | stop processing: n_tokens = 616, truncated = 0 13.16.918.279 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.121 (> 0.100 thold), f_keep = 0.034 13.16.919.802 I slot launch_slot_: id 0 | task 51019 | processing task, is_child = 0 13.20.275.192 I slot print_timing: id 0 | task 51019 | n_gen = 216, tg = 71.66 t/s, tg_3s = 72.00 t/s 13.21.311.128 I slot print_timing: id 0 | task 51019 | prompt eval time = 355.25 ms / 173 tokens ( 2.05 ms per token, 486.98 tokens per second) 13.21.311.131 I slot print_timing: id 0 | task 51019 | eval time = 4036.07 ms / 290 tokens ( 13.97 ms per token, 71.60 tokens per second) 13.21.311.132 I slot print_timing: id 0 | task 51019 | total time = 4391.32 ms / 463 tokens 13.21.311.133 I slot print_timing: id 0 | task 51019 | graphs reused = 50302 13.21.311.133 I slot print_timing: id 0 | task 51019 | graph reallocs = 0 / 0 (same size) / (changed size) 13.21.311.155 I slot release: id 0 | task 51019 | stop processing: n_tokens = 462, truncated = 0 13.21.314.493 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.111 (> 0.100 thold), f_keep = 0.045 13.21.315.628 I slot launch_slot_: id 0 | task 51311 | processing task, is_child = 0 13.23.653.483 I slot print_timing: id 0 | task 51311 | prompt eval time = 366.09 ms / 190 tokens ( 1.93 ms per token, 519.00 tokens per second) 13.23.653.485 I slot print_timing: id 0 | task 51311 | eval time = 1971.75 ms / 142 tokens ( 13.98 ms per token, 71.51 tokens per second) 13.23.653.486 I slot print_timing: id 0 | task 51311 | total time = 2337.84 ms / 332 tokens 13.23.653.487 I slot print_timing: id 0 | task 51311 | graphs reused = 50441 13.23.653.487 I slot print_timing: id 0 | task 51311 | graph reallocs = 0 / 0 (same size) / (changed size) 13.23.653.508 I slot release: id 0 | task 51311 | stop processing: n_tokens = 331, truncated = 0 13.23.656.875 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.121 (> 0.100 thold), f_keep = 0.063 13.23.657.765 I slot launch_slot_: id 0 | task 51455 | processing task, is_child = 0 13.27.016.537 I slot print_timing: id 0 | task 51455 | n_gen = 216, tg = 71.58 t/s, tg_3s = 71.92 t/s 13.29.337.306 I slot print_timing: id 0 | task 51455 | prompt eval time = 355.31 ms / 173 tokens ( 2.05 ms per token, 486.90 tokens per second) 13.29.337.309 I slot print_timing: id 0 | task 51455 | eval time = 5324.23 ms / 382 tokens ( 13.97 ms per token, 71.56 tokens per second) 13.29.337.310 I slot print_timing: id 0 | task 51455 | total time = 5679.53 ms / 555 tokens 13.29.337.310 I slot print_timing: id 0 | task 51455 | graphs reused = 50819 13.29.337.311 I slot print_timing: id 0 | task 51455 | graph reallocs = 0 / 0 (same size) / (changed size) 13.29.337.333 I slot release: id 0 | task 51455 | stop processing: n_tokens = 554, truncated = 0 13.29.340.707 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.111 (> 0.100 thold), f_keep = 0.038 13.29.341.989 I slot launch_slot_: id 0 | task 51839 | processing task, is_child = 0 13.32.710.738 I slot print_timing: id 0 | task 51839 | n_gen = 216, tg = 71.54 t/s, tg_3s = 71.87 t/s 13.35.592.494 I slot print_timing: id 0 | task 51839 | prompt eval time = 363.44 ms / 190 tokens ( 1.91 ms per token, 522.79 tokens per second) 13.35.592.498 I slot print_timing: id 0 | task 51839 | eval time = 5887.06 ms / 422 tokens ( 13.98 ms per token, 71.51 tokens per second) 13.35.592.499 I slot print_timing: id 0 | task 51839 | total time = 6250.49 ms / 612 tokens 13.35.592.499 I slot print_timing: id 0 | task 51839 | graphs reused = 51237 13.35.592.500 I slot print_timing: id 0 | task 51839 | graph reallocs = 0 / 0 (same size) / (changed size) 13.35.592.525 I slot release: id 0 | task 51839 | stop processing: n_tokens = 611, truncated = 0 13.35.595.833 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.126 (> 0.100 thold), f_keep = 0.038 13.35.597.192 I slot launch_slot_: id 0 | task 52263 | processing task, is_child = 0 13.38.962.552 I slot print_timing: id 0 | task 52263 | n_gen = 216, tg = 71.51 t/s, tg_3s = 71.84 t/s 13.40.404.064 I slot print_timing: id 0 | task 52263 | prompt eval time = 358.58 ms / 183 tokens ( 1.96 ms per token, 510.35 tokens per second) 13.40.404.070 I slot print_timing: id 0 | task 52263 | eval time = 4448.28 ms / 319 tokens ( 13.99 ms per token, 71.49 tokens per second) 13.40.404.071 I slot print_timing: id 0 | task 52263 | total time = 4806.86 ms / 502 tokens 13.40.404.071 I slot print_timing: id 0 | task 52263 | graphs reused = 51553 13.40.404.072 I slot print_timing: id 0 | task 52263 | graph reallocs = 0 / 0 (same size) / (changed size) 13.40.404.093 I slot release: id 0 | task 52263 | stop processing: n_tokens = 501, truncated = 0 13.40.407.399 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 501, t_last = 340071522093 13.40.408.593 I slot launch_slot_: id 0 | task 52584 | processing task, is_child = 0 13.43.811.904 I slot print_timing: id 0 | task 52584 | n_gen = 216, tg = 71.44 t/s, tg_3s = 71.77 t/s 13.44.077.546 I slot print_timing: id 0 | task 52584 | prompt eval time = 393.61 ms / 222 tokens ( 1.77 ms per token, 564.01 tokens per second) 13.44.077.550 I slot print_timing: id 0 | task 52584 | eval time = 3275.34 ms / 235 tokens ( 14.00 ms per token, 71.44 tokens per second) 13.44.077.551 I slot print_timing: id 0 | task 52584 | total time = 3668.95 ms / 457 tokens 13.44.077.552 I slot print_timing: id 0 | task 52584 | graphs reused = 51785 13.44.077.552 I slot print_timing: id 0 | task 52584 | graph reallocs = 0 / 0 (same size) / (changed size) 13.44.077.578 I slot release: id 0 | task 52584 | stop processing: n_tokens = 456, truncated = 0 13.44.080.756 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.129 (> 0.100 thold), f_keep = 0.046 13.44.081.847 I slot launch_slot_: id 0 | task 52821 | processing task, is_child = 0 13.47.423.284 I slot print_timing: id 0 | task 52821 | n_gen = 216, tg = 71.56 t/s, tg_3s = 71.89 t/s 13.48.583.041 I slot print_timing: id 0 | task 52821 | prompt eval time = 337.00 ms / 163 tokens ( 2.07 ms per token, 483.68 tokens per second) 13.48.583.046 I slot print_timing: id 0 | task 52821 | eval time = 4164.19 ms / 299 tokens ( 13.97 ms per token, 71.56 tokens per second) 13.48.583.047 I slot print_timing: id 0 | task 52821 | total time = 4501.18 ms / 462 tokens 13.48.583.047 I slot print_timing: id 0 | task 52821 | graphs reused = 52081 13.48.583.048 I slot print_timing: id 0 | task 52821 | graph reallocs = 0 / 0 (same size) / (changed size) 13.48.583.073 I slot release: id 0 | task 52821 | stop processing: n_tokens = 461, truncated = 0 13.48.595.685 I srv operator(): operator(): cleaning up before exit...