$ /Users/minipro/quantdiff/llama.cpp/llama-b11770/llama-server -m /Users/minipro/quantdiff/models/campaign/d5a53342a2f5/LFM2.5-24B-A2B-UD-Q5_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 0.00.042.628 I srv llama_server: initializing ... 0.00.042.636 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.043.795 I srv init_listene: The UI is disabled 0.00.043.796 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.043.918 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) 0.00.046.040 I srv load_model: loading model '/Users/minipro/quantdiff/models/campaign/d5a53342a2f5/LFM2.5-24B-A2B-UD-Q5_K_XL.gguf' 0.01.194.596 I cmn init: llama threadpool init, n_threads = 8 0.01.357.631 I srv load_model: initializing, n_slots = 1, n_ctx_slot = 4096, kv_unified = 'false' 0.01.361.990 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.01.362.048 I srv llama_server: model loaded 0.01.362.055 I srv llama_server: listening on http://127.0.0.1:8089 0.02.020.393 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.02.020.835 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.05.112.830 I slot print_timing: id 0 | task 0 | prompt eval time = 406.78 ms / 172 tokens ( 2.36 ms per token, 422.83 tokens per second) 0.05.112.838 I slot print_timing: id 0 | task 0 | eval time = 2685.18 ms / 165 tokens ( 16.37 ms per token, 61.08 tokens per second) 0.05.112.839 I slot print_timing: id 0 | task 0 | total time = 3091.95 ms / 337 tokens 0.05.112.839 I slot print_timing: id 0 | task 0 | graphs reused = 163 0.05.112.840 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.112.865 I slot release: id 0 | task 0 | stop processing: n_tokens = 336, truncated = 0 0.05.117.210 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.062 0.05.118.032 I slot launch_slot_: id 0 | task 167 | processing task, is_child = 0 0.06.496.908 I slot print_timing: id 0 | task 167 | prompt eval time = 321.73 ms / 123 tokens ( 2.62 ms per token, 382.30 tokens per second) 0.06.496.915 I slot print_timing: id 0 | task 167 | eval time = 1057.13 ms / 65 tokens ( 16.52 ms per token, 60.54 tokens per second) 0.06.496.916 I slot print_timing: id 0 | task 167 | total time = 1378.87 ms / 188 tokens 0.06.496.916 I slot print_timing: id 0 | task 167 | graphs reused = 226 0.06.496.917 I slot print_timing: id 0 | task 167 | graph reallocs = 0 / 0 (same size) / (changed size) 0.06.496.936 I slot release: id 0 | task 167 | stop processing: n_tokens = 187, truncated = 0 0.06.500.268 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.129 (> 0.100 thold), f_keep = 0.112 0.06.500.619 I slot launch_slot_: id 0 | task 234 | processing task, is_child = 0 0.08.014.276 I slot print_timing: id 0 | task 234 | prompt eval time = 362.59 ms / 163 tokens ( 2.22 ms per token, 449.55 tokens per second) 0.08.014.279 I slot print_timing: id 0 | task 234 | eval time = 1151.06 ms / 71 tokens ( 16.44 ms per token, 60.81 tokens per second) 0.08.014.280 I slot print_timing: id 0 | task 234 | total time = 1513.65 ms / 234 tokens 0.08.014.280 I slot print_timing: id 0 | task 234 | graphs reused = 295 0.08.014.281 I slot print_timing: id 0 | task 234 | graph reallocs = 0 / 0 (same size) / (changed size) 0.08.014.308 I slot release: id 0 | task 234 | stop processing: n_tokens = 233, truncated = 0 0.08.017.695 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.103 (> 0.100 thold), f_keep = 0.090 0.08.018.048 I slot launch_slot_: id 0 | task 307 | processing task, is_child = 0 0.10.609.117 I slot print_timing: id 0 | task 307 | prompt eval time = 408.89 ms / 204 tokens ( 2.00 ms per token, 498.91 tokens per second) 0.10.609.123 I slot print_timing: id 0 | task 307 | eval time = 2182.17 ms / 134 tokens ( 16.41 ms per token, 60.95 tokens per second) 0.10.609.123 I slot print_timing: id 0 | task 307 | total time = 2591.06 ms / 338 tokens 0.10.609.124 I slot print_timing: id 0 | task 307 | graphs reused = 426 0.10.609.125 I slot print_timing: id 0 | task 307 | graph reallocs = 0 / 0 (same size) / (changed size) 0.10.609.151 I slot release: id 0 | task 307 | stop processing: n_tokens = 337, truncated = 0 0.10.612.370 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.187 (> 0.100 thold), f_keep = 0.107 0.10.613.188 I slot launch_slot_: id 0 | task 443 | processing task, is_child = 0 0.13.698.483 I slot print_timing: id 0 | task 443 | prompt eval time = 393.08 ms / 193 tokens ( 2.04 ms per token, 491.00 tokens per second) 0.13.698.488 I slot print_timing: id 0 | task 443 | eval time = 2692.20 ms / 165 tokens ( 16.42 ms per token, 60.92 tokens per second) 0.13.698.489 I slot print_timing: id 0 | task 443 | total time = 3085.28 ms / 358 tokens 0.13.698.489 I slot print_timing: id 0 | task 443 | graphs reused = 588 0.13.698.490 I slot print_timing: id 0 | task 443 | graph reallocs = 0 / 0 (same size) / (changed size) 0.13.698.519 I slot release: id 0 | task 443 | stop processing: n_tokens = 357, truncated = 0 0.13.702.088 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.121 (> 0.100 thold), f_keep = 0.059 0.13.703.027 I slot launch_slot_: id 0 | task 610 | processing task, is_child = 0 0.15.692.997 I slot print_timing: id 0 | task 610 | prompt eval time = 382.15 ms / 174 tokens ( 2.20 ms per token, 455.32 tokens per second) 0.15.693.006 I slot print_timing: id 0 | task 610 | eval time = 1607.81 ms / 98 tokens ( 16.58 ms per token, 60.33 tokens per second) 0.15.693.007 I slot print_timing: id 0 | task 610 | total time = 1989.96 ms / 272 tokens 0.15.693.007 I slot print_timing: id 0 | task 610 | graphs reused = 683 0.15.693.008 I slot print_timing: id 0 | task 610 | graph reallocs = 0 / 0 (same size) / (changed size) 0.15.693.031 I slot release: id 0 | task 610 | stop processing: n_tokens = 271, truncated = 0 0.15.696.598 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 271, t_last = 341460772908 0.15.697.375 I slot launch_slot_: id 0 | task 710 | processing task, is_child = 0 0.17.860.635 I slot print_timing: id 0 | task 710 | prompt eval time = 421.11 ms / 224 tokens ( 1.88 ms per token, 531.93 tokens per second) 0.17.860.641 I slot print_timing: id 0 | task 710 | eval time = 1742.14 ms / 107 tokens ( 16.44 ms per token, 60.84 tokens per second) 0.17.860.642 I slot print_timing: id 0 | task 710 | total time = 2163.25 ms / 331 tokens 0.17.860.643 I slot print_timing: id 0 | task 710 | graphs reused = 787 0.17.860.643 I slot print_timing: id 0 | task 710 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.860.670 I slot release: id 0 | task 710 | stop processing: n_tokens = 330, truncated = 0 0.17.864.169 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 330, t_last = 341462940547 0.17.865.057 I slot launch_slot_: id 0 | task 819 | processing task, is_child = 0 0.21.353.172 I slot print_timing: id 0 | task 819 | n_gen = 185, tg = 61.01 t/s, tg_3s = 61.34 t/s 0.23.056.296 I slot print_timing: id 0 | task 819 | prompt eval time = 472.28 ms / 266 tokens ( 1.78 ms per token, 563.22 tokens per second) 0.23.056.302 I slot print_timing: id 0 | task 819 | eval time = 4718.95 ms / 289 tokens ( 16.39 ms per token, 61.03 tokens per second) 0.23.056.302 I slot print_timing: id 0 | task 819 | total time = 5191.23 ms / 555 tokens 0.23.056.303 I slot print_timing: id 0 | task 819 | graphs reused = 1073 0.23.056.304 I slot print_timing: id 0 | task 819 | graph reallocs = 0 / 0 (same size) / (changed size) 0.23.056.333 I slot release: id 0 | task 819 | stop processing: n_tokens = 554, truncated = 0 0.23.059.897 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.143 (> 0.100 thold), f_keep = 0.038 0.23.061.252 I slot launch_slot_: id 0 | task 1110 | processing task, is_child = 0 0.24.710.344 I slot print_timing: id 0 | task 1110 | prompt eval time = 354.76 ms / 147 tokens ( 2.41 ms per token, 414.37 tokens per second) 0.24.710.350 I slot print_timing: id 0 | task 1110 | eval time = 1294.32 ms / 79 tokens ( 16.59 ms per token, 60.26 tokens per second) 0.24.710.350 I slot print_timing: id 0 | task 1110 | total time = 1649.08 ms / 226 tokens 0.24.710.351 I slot print_timing: id 0 | task 1110 | graphs reused = 1150 0.24.710.351 I slot print_timing: id 0 | task 1110 | graph reallocs = 0 / 0 (same size) / (changed size) 0.24.710.371 I slot release: id 0 | task 1110 | stop processing: n_tokens = 225, truncated = 0 0.24.713.551 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.127 (> 0.100 thold), f_keep = 0.093 0.24.714.236 I slot launch_slot_: id 0 | task 1191 | processing task, is_child = 0 0.26.904.574 I slot print_timing: id 0 | task 1191 | prompt eval time = 373.58 ms / 166 tokens ( 2.25 ms per token, 444.35 tokens per second) 0.26.904.577 I slot print_timing: id 0 | task 1191 | eval time = 1816.75 ms / 111 tokens ( 16.52 ms per token, 60.55 tokens per second) 0.26.904.577 I slot print_timing: id 0 | task 1191 | total time = 2190.33 ms / 277 tokens 0.26.904.578 I slot print_timing: id 0 | task 1191 | graphs reused = 1258 0.26.904.578 I slot print_timing: id 0 | task 1191 | graph reallocs = 0 / 0 (same size) / (changed size) 0.26.904.600 I slot release: id 0 | task 1191 | stop processing: n_tokens = 276, truncated = 0 0.26.908.001 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.120 (> 0.100 thold), f_keep = 0.076 0.26.908.767 I slot launch_slot_: id 0 | task 1304 | processing task, is_child = 0 0.29.715.814 I slot print_timing: id 0 | task 1304 | prompt eval time = 382.16 ms / 175 tokens ( 2.18 ms per token, 457.92 tokens per second) 0.29.715.817 I slot print_timing: id 0 | task 1304 | eval time = 2424.88 ms / 149 tokens ( 16.38 ms per token, 61.03 tokens per second) 0.29.715.818 I slot print_timing: id 0 | task 1304 | total time = 2807.04 ms / 324 tokens 0.29.715.819 I slot print_timing: id 0 | task 1304 | graphs reused = 1404 0.29.715.819 I slot print_timing: id 0 | task 1304 | graph reallocs = 0 / 0 (same size) / (changed size) 0.29.715.844 I slot release: id 0 | task 1304 | stop processing: n_tokens = 323, truncated = 0 0.29.719.446 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 323, t_last = 341474795721 0.29.720.330 I slot launch_slot_: id 0 | task 1455 | processing task, is_child = 0 0.32.638.636 I slot print_timing: id 0 | task 1455 | prompt eval time = 418.59 ms / 215 tokens ( 1.95 ms per token, 513.62 tokens per second) 0.32.638.642 I slot print_timing: id 0 | task 1455 | eval time = 2499.70 ms / 153 tokens ( 16.45 ms per token, 60.81 tokens per second) 0.32.638.643 I slot print_timing: id 0 | task 1455 | total time = 2918.30 ms / 368 tokens 0.32.638.644 I slot print_timing: id 0 | task 1455 | graphs reused = 1554 0.32.638.644 I slot print_timing: id 0 | task 1455 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.638.674 I slot release: id 0 | task 1455 | stop processing: n_tokens = 367, truncated = 0 0.32.642.073 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 0.32.643.040 I slot launch_slot_: id 0 | task 1610 | processing task, is_child = 0 0.34.982.092 I slot print_timing: id 0 | task 1610 | prompt eval time = 386.56 ms / 177 tokens ( 2.18 ms per token, 457.89 tokens per second) 0.34.982.099 I slot print_timing: id 0 | task 1610 | eval time = 1952.48 ms / 120 tokens ( 16.41 ms per token, 60.95 tokens per second) 0.34.982.100 I slot print_timing: id 0 | task 1610 | total time = 2339.04 ms / 297 tokens 0.34.982.101 I slot print_timing: id 0 | task 1610 | graphs reused = 1671 0.34.982.101 I slot print_timing: id 0 | task 1610 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.982.127 I slot release: id 0 | task 1610 | stop processing: n_tokens = 296, truncated = 0 0.34.985.649 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.116 (> 0.100 thold), f_keep = 0.071 0.34.986.472 I slot launch_slot_: id 0 | task 1732 | processing task, is_child = 0 0.36.838.720 I slot print_timing: id 0 | task 1732 | prompt eval time = 386.93 ms / 181 tokens ( 2.14 ms per token, 467.79 tokens per second) 0.36.838.726 I slot print_timing: id 0 | task 1732 | eval time = 1465.31 ms / 89 tokens ( 16.65 ms per token, 60.06 tokens per second) 0.36.838.726 I slot print_timing: id 0 | task 1732 | total time = 1852.24 ms / 270 tokens 0.36.838.727 I slot print_timing: id 0 | task 1732 | graphs reused = 1757 0.36.838.727 I slot print_timing: id 0 | task 1732 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.838.749 I slot release: id 0 | task 1732 | stop processing: n_tokens = 269, truncated = 0 0.36.842.276 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.122 (> 0.100 thold), f_keep = 0.078 0.36.843.107 I slot launch_slot_: id 0 | task 1823 | processing task, is_child = 0 0.38.915.151 I slot print_timing: id 0 | task 1823 | prompt eval time = 382.23 ms / 172 tokens ( 2.22 ms per token, 449.99 tokens per second) 0.38.915.157 I slot print_timing: id 0 | task 1823 | eval time = 1689.80 ms / 104 tokens ( 16.41 ms per token, 60.95 tokens per second) 0.38.915.158 I slot print_timing: id 0 | task 1823 | total time = 2072.03 ms / 276 tokens 0.38.915.158 I slot print_timing: id 0 | task 1823 | graphs reused = 1858 0.38.915.159 I slot print_timing: id 0 | task 1823 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.915.181 I slot release: id 0 | task 1823 | stop processing: n_tokens = 275, truncated = 0 0.38.918.542 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.138 (> 0.100 thold), f_keep = 0.076 0.38.919.317 I slot launch_slot_: id 0 | task 1929 | processing task, is_child = 0 0.41.434.297 I slot print_timing: id 0 | task 1929 | prompt eval time = 352.13 ms / 152 tokens ( 2.32 ms per token, 431.65 tokens per second) 0.41.434.304 I slot print_timing: id 0 | task 1929 | eval time = 2162.84 ms / 132 tokens ( 16.51 ms per token, 60.57 tokens per second) 0.41.434.305 I slot print_timing: id 0 | task 1929 | total time = 2514.97 ms / 284 tokens 0.41.434.305 I slot print_timing: id 0 | task 1929 | graphs reused = 1987 0.41.434.306 I slot print_timing: id 0 | task 1929 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.434.325 I slot release: id 0 | task 1929 | stop processing: n_tokens = 283, truncated = 0 0.41.437.717 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.123 (> 0.100 thold), f_keep = 0.074 0.41.438.487 I slot launch_slot_: id 0 | task 2063 | processing task, is_child = 0 0.44.829.201 I slot print_timing: id 0 | task 2063 | n_gen = 185, tg = 61.11 t/s, tg_3s = 61.44 t/s 0.45.713.151 I slot print_timing: id 0 | task 2063 | prompt eval time = 379.62 ms / 171 tokens ( 2.22 ms per token, 450.45 tokens per second) 0.45.713.157 I slot print_timing: id 0 | task 2063 | eval time = 3895.03 ms / 239 tokens ( 16.37 ms per token, 61.10 tokens per second) 0.45.713.158 I slot print_timing: id 0 | task 2063 | total time = 4274.65 ms / 410 tokens 0.45.713.158 I slot print_timing: id 0 | task 2063 | graphs reused = 2223 0.45.713.159 I slot print_timing: id 0 | task 2063 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.713.180 I slot release: id 0 | task 2063 | stop processing: n_tokens = 409, truncated = 0 0.45.716.616 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.136 (> 0.100 thold), f_keep = 0.051 0.45.717.648 I slot launch_slot_: id 0 | task 2304 | processing task, is_child = 0 0.47.790.652 I slot print_timing: id 0 | task 2304 | prompt eval time = 358.08 ms / 154 tokens ( 2.33 ms per token, 430.08 tokens per second) 0.47.790.658 I slot print_timing: id 0 | task 2304 | eval time = 1714.92 ms / 104 tokens ( 16.65 ms per token, 60.06 tokens per second) 0.47.790.659 I slot print_timing: id 0 | task 2304 | total time = 2073.00 ms / 258 tokens 0.47.790.659 I slot print_timing: id 0 | task 2304 | graphs reused = 2324 0.47.790.660 I slot print_timing: id 0 | task 2304 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.790.679 I slot release: id 0 | task 2304 | stop processing: n_tokens = 257, truncated = 0 0.47.793.923 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.140 (> 0.100 thold), f_keep = 0.082 0.47.794.647 I slot launch_slot_: id 0 | task 2410 | processing task, is_child = 0 0.49.557.543 I slot print_timing: id 0 | task 2410 | prompt eval time = 350.23 ms / 150 tokens ( 2.33 ms per token, 428.29 tokens per second) 0.49.557.548 I slot print_timing: id 0 | task 2410 | eval time = 1412.65 ms / 86 tokens ( 16.62 ms per token, 60.17 tokens per second) 0.49.557.550 I slot print_timing: id 0 | task 2410 | total time = 1762.88 ms / 236 tokens 0.49.557.551 I slot print_timing: id 0 | task 2410 | graphs reused = 2408 0.49.557.551 I slot print_timing: id 0 | task 2410 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.557.571 I slot release: id 0 | task 2410 | stop processing: n_tokens = 235, truncated = 0 0.49.561.041 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.111 (> 0.100 thold), f_keep = 0.089 0.49.561.766 I slot launch_slot_: id 0 | task 2498 | processing task, is_child = 0 0.51.913.780 I slot print_timing: id 0 | task 2498 | prompt eval time = 390.34 ms / 190 tokens ( 2.05 ms per token, 486.76 tokens per second) 0.51.913.784 I slot print_timing: id 0 | task 2498 | eval time = 1961.67 ms / 120 tokens ( 16.48 ms per token, 60.66 tokens per second) 0.51.913.784 I slot print_timing: id 0 | task 2498 | total time = 2352.01 ms / 310 tokens 0.51.913.785 I slot print_timing: id 0 | task 2498 | graphs reused = 2525 0.51.913.786 I slot print_timing: id 0 | task 2498 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.913.812 I slot release: id 0 | task 2498 | stop processing: n_tokens = 309, truncated = 0 0.51.917.279 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.131 (> 0.100 thold), f_keep = 0.068 0.51.918.111 I slot launch_slot_: id 0 | task 2620 | processing task, is_child = 0 0.54.103.103 I slot print_timing: id 0 | task 2620 | prompt eval time = 358.74 ms / 160 tokens ( 2.24 ms per token, 446.01 tokens per second) 0.54.103.109 I slot print_timing: id 0 | task 2620 | eval time = 1826.24 ms / 112 tokens ( 16.45 ms per token, 60.78 tokens per second) 0.54.103.110 I slot print_timing: id 0 | task 2620 | total time = 2184.98 ms / 272 tokens 0.54.103.111 I slot print_timing: id 0 | task 2620 | graphs reused = 2634 0.54.103.111 I slot print_timing: id 0 | task 2620 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.103.131 I slot release: id 0 | task 2620 | stop processing: n_tokens = 271, truncated = 0 0.54.106.606 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 271, t_last = 341499183008 0.54.107.365 I slot launch_slot_: id 0 | task 2734 | processing task, is_child = 0 0.56.413.849 I slot print_timing: id 0 | task 2734 | prompt eval time = 420.57 ms / 218 tokens ( 1.93 ms per token, 518.34 tokens per second) 0.56.413.855 I slot print_timing: id 0 | task 2734 | eval time = 1885.90 ms / 116 tokens ( 16.40 ms per token, 60.98 tokens per second) 0.56.413.856 I slot print_timing: id 0 | task 2734 | total time = 2306.48 ms / 334 tokens 0.56.413.857 I slot print_timing: id 0 | task 2734 | graphs reused = 2747 0.56.413.857 I slot print_timing: id 0 | task 2734 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.413.881 I slot release: id 0 | task 2734 | stop processing: n_tokens = 333, truncated = 0 0.56.417.352 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.109 (> 0.100 thold), f_keep = 0.063 0.56.418.222 I slot launch_slot_: id 0 | task 2852 | processing task, is_child = 0 0.59.516.998 I slot print_timing: id 0 | task 2852 | prompt eval time = 389.07 ms / 193 tokens ( 2.02 ms per token, 496.05 tokens per second) 0.59.517.005 I slot print_timing: id 0 | task 2852 | eval time = 2709.70 ms / 166 tokens ( 16.42 ms per token, 60.89 tokens per second) 0.59.517.005 I slot print_timing: id 0 | task 2852 | total time = 3098.77 ms / 359 tokens 0.59.517.006 I slot print_timing: id 0 | task 2852 | graphs reused = 2910 0.59.517.006 I slot print_timing: id 0 | task 2852 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.517.029 I slot release: id 0 | task 2852 | stop processing: n_tokens = 358, truncated = 0 0.59.520.573 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.104 (> 0.100 thold), f_keep = 0.059 0.59.521.543 I slot launch_slot_: id 0 | task 3020 | processing task, is_child = 0 1.02.938.900 I slot print_timing: id 0 | task 3020 | n_gen = 184, tg = 60.82 t/s, tg_3s = 61.15 t/s 1.03.621.872 I slot print_timing: id 0 | task 3020 | prompt eval time = 408.40 ms / 201 tokens ( 2.03 ms per token, 492.17 tokens per second) 1.03.621.880 I slot print_timing: id 0 | task 3020 | eval time = 3691.92 ms / 225 tokens ( 16.48 ms per token, 60.67 tokens per second) 1.03.621.880 I slot print_timing: id 0 | task 3020 | total time = 4100.32 ms / 426 tokens 1.03.621.881 I slot print_timing: id 0 | task 3020 | graphs reused = 3132 1.03.621.881 I slot print_timing: id 0 | task 3020 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.621.907 I slot release: id 0 | task 3020 | stop processing: n_tokens = 425, truncated = 0 1.03.625.402 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 425, t_last = 341508701784 1.03.626.490 I slot launch_slot_: id 0 | task 3247 | processing task, is_child = 0 1.07.078.052 I slot print_timing: id 0 | task 3247 | n_gen = 185, tg = 61.20 t/s, tg_3s = 61.54 t/s 1.09.084.668 I slot print_timing: id 0 | task 3247 | prompt eval time = 445.25 ms / 237 tokens ( 1.88 ms per token, 532.29 tokens per second) 1.09.084.673 I slot print_timing: id 0 | task 3247 | eval time = 5012.92 ms / 307 tokens ( 16.38 ms per token, 61.04 tokens per second) 1.09.084.673 I slot print_timing: id 0 | task 3247 | total time = 5458.17 ms / 544 tokens 1.09.084.674 I slot print_timing: id 0 | task 3247 | graphs reused = 3435 1.09.084.675 I slot print_timing: id 0 | task 3247 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.084.703 I slot release: id 0 | task 3247 | stop processing: n_tokens = 543, truncated = 0 1.09.088.294 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.112 (> 0.100 thold), f_keep = 0.041 1.09.089.566 I slot launch_slot_: id 0 | task 3556 | processing task, is_child = 0 1.11.659.764 I slot print_timing: id 0 | task 3556 | prompt eval time = 395.35 ms / 196 tokens ( 2.02 ms per token, 495.77 tokens per second) 1.11.659.771 I slot print_timing: id 0 | task 3556 | eval time = 2174.84 ms / 133 tokens ( 16.48 ms per token, 60.69 tokens per second) 1.11.659.771 I slot print_timing: id 0 | task 3556 | total time = 2570.19 ms / 329 tokens 1.11.659.772 I slot print_timing: id 0 | task 3556 | graphs reused = 3565 1.11.659.772 I slot print_timing: id 0 | task 3556 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.659.794 I slot release: id 0 | task 3556 | stop processing: n_tokens = 328, truncated = 0 1.11.663.112 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.139 (> 0.100 thold), f_keep = 0.064 1.11.664.026 I slot launch_slot_: id 0 | task 3691 | processing task, is_child = 0 1.13.453.897 I slot print_timing: id 0 | task 3691 | prompt eval time = 361.86 ms / 151 tokens ( 2.40 ms per token, 417.29 tokens per second) 1.13.453.903 I slot print_timing: id 0 | task 3691 | eval time = 1428.01 ms / 88 tokens ( 16.41 ms per token, 60.92 tokens per second) 1.13.453.904 I slot print_timing: id 0 | task 3691 | total time = 1789.86 ms / 239 tokens 1.13.453.904 I slot print_timing: id 0 | task 3691 | graphs reused = 3651 1.13.453.905 I slot print_timing: id 0 | task 3691 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.453.927 I slot release: id 0 | task 3691 | stop processing: n_tokens = 238, truncated = 0 1.13.457.247 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 1.13.457.980 I slot launch_slot_: id 0 | task 3781 | processing task, is_child = 0 1.16.097.368 I slot print_timing: id 0 | task 3781 | prompt eval time = 388.47 ms / 180 tokens ( 2.16 ms per token, 463.36 tokens per second) 1.16.097.371 I slot print_timing: id 0 | task 3781 | eval time = 2250.91 ms / 138 tokens ( 16.43 ms per token, 60.86 tokens per second) 1.16.097.372 I slot print_timing: id 0 | task 3781 | total time = 2639.38 ms / 318 tokens 1.16.097.373 I slot print_timing: id 0 | task 3781 | graphs reused = 3786 1.16.097.374 I slot print_timing: id 0 | task 3781 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.097.402 I slot release: id 0 | task 3781 | stop processing: n_tokens = 317, truncated = 0 1.16.100.949 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 317, t_last = 341521177279 1.16.101.845 I slot launch_slot_: id 0 | task 3921 | processing task, is_child = 0 1.18.884.907 I slot print_timing: id 0 | task 3921 | prompt eval time = 418.70 ms / 211 tokens ( 1.98 ms per token, 503.94 tokens per second) 1.18.884.913 I slot print_timing: id 0 | task 3921 | eval time = 2364.36 ms / 145 tokens ( 16.42 ms per token, 60.90 tokens per second) 1.18.884.915 I slot print_timing: id 0 | task 3921 | total time = 2783.06 ms / 356 tokens 1.18.884.916 I slot print_timing: id 0 | task 3921 | graphs reused = 3928 1.18.884.916 I slot print_timing: id 0 | task 3921 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.884.947 I slot release: id 0 | task 3921 | stop processing: n_tokens = 355, truncated = 0 1.18.888.369 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.113 (> 0.100 thold), f_keep = 0.059 1.18.889.307 I slot launch_slot_: id 0 | task 4068 | processing task, is_child = 0 1.21.290.962 I slot print_timing: id 0 | task 4068 | prompt eval time = 394.70 ms / 186 tokens ( 2.12 ms per token, 471.24 tokens per second) 1.21.290.969 I slot print_timing: id 0 | task 4068 | eval time = 2006.95 ms / 122 tokens ( 16.59 ms per token, 60.29 tokens per second) 1.21.290.969 I slot print_timing: id 0 | task 4068 | total time = 2401.65 ms / 308 tokens 1.21.290.970 I slot print_timing: id 0 | task 4068 | graphs reused = 4047 1.21.290.970 I slot print_timing: id 0 | task 4068 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.290.993 I slot release: id 0 | task 4068 | stop processing: n_tokens = 307, truncated = 0 1.21.294.469 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.128 (> 0.100 thold), f_keep = 0.068 1.21.295.339 I slot launch_slot_: id 0 | task 4192 | processing task, is_child = 0 1.24.289.608 I slot print_timing: id 0 | task 4192 | prompt eval time = 367.10 ms / 164 tokens ( 2.24 ms per token, 446.75 tokens per second) 1.24.289.611 I slot print_timing: id 0 | task 4192 | eval time = 2627.16 ms / 161 tokens ( 16.42 ms per token, 60.90 tokens per second) 1.24.289.612 I slot print_timing: id 0 | task 4192 | total time = 2994.26 ms / 325 tokens 1.24.289.613 I slot print_timing: id 0 | task 4192 | graphs reused = 4205 1.24.289.613 I slot print_timing: id 0 | task 4192 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.289.642 I slot release: id 0 | task 4192 | stop processing: n_tokens = 324, truncated = 0 1.24.292.983 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.130 (> 0.100 thold), f_keep = 0.065 1.24.293.835 I slot launch_slot_: id 0 | task 4355 | processing task, is_child = 0 1.27.497.412 I slot print_timing: id 0 | task 4355 | prompt eval time = 367.79 ms / 162 tokens ( 2.27 ms per token, 440.46 tokens per second) 1.27.497.419 I slot print_timing: id 0 | task 4355 | eval time = 2835.78 ms / 174 tokens ( 16.39 ms per token, 61.01 tokens per second) 1.27.497.419 I slot print_timing: id 0 | task 4355 | total time = 3203.57 ms / 336 tokens 1.27.497.420 I slot print_timing: id 0 | task 4355 | graphs reused = 4376 1.27.497.421 I slot print_timing: id 0 | task 4355 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.497.441 I slot release: id 0 | task 4355 | stop processing: n_tokens = 335, truncated = 0 1.27.500.909 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.111 (> 0.100 thold), f_keep = 0.063 1.27.501.810 I slot launch_slot_: id 0 | task 4531 | processing task, is_child = 0 1.30.389.400 I slot print_timing: id 0 | task 4531 | prompt eval time = 393.06 ms / 190 tokens ( 2.07 ms per token, 483.39 tokens per second) 1.30.389.406 I slot print_timing: id 0 | task 4531 | eval time = 2494.52 ms / 153 tokens ( 16.41 ms per token, 60.93 tokens per second) 1.30.389.407 I slot print_timing: id 0 | task 4531 | total time = 2887.58 ms / 343 tokens 1.30.389.408 I slot print_timing: id 0 | task 4531 | graphs reused = 4526 1.30.389.408 I slot print_timing: id 0 | task 4531 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.389.430 I slot release: id 0 | task 4531 | stop processing: n_tokens = 342, truncated = 0 1.30.392.689 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.102 (> 0.100 thold), f_keep = 0.061 1.30.393.616 I slot launch_slot_: id 0 | task 4686 | processing task, is_child = 0 1.33.054.680 I slot print_timing: id 0 | task 4686 | prompt eval time = 414.98 ms / 206 tokens ( 2.01 ms per token, 496.41 tokens per second) 1.33.054.686 I slot print_timing: id 0 | task 4686 | eval time = 2246.08 ms / 137 tokens ( 16.52 ms per token, 60.55 tokens per second) 1.33.054.687 I slot print_timing: id 0 | task 4686 | total time = 2661.06 ms / 343 tokens 1.33.054.687 I slot print_timing: id 0 | task 4686 | graphs reused = 4660 1.33.054.688 I slot print_timing: id 0 | task 4686 | graph reallocs = 0 / 0 (same size) / (changed size) 1.33.054.712 I slot release: id 0 | task 4686 | stop processing: n_tokens = 342, truncated = 0 1.33.058.219 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.134 (> 0.100 thold), f_keep = 0.061 1.33.059.129 I slot launch_slot_: id 0 | task 4825 | processing task, is_child = 0 1.35.504.475 I slot print_timing: id 0 | task 4825 | prompt eval time = 360.50 ms / 157 tokens ( 2.30 ms per token, 435.50 tokens per second) 1.35.504.478 I slot print_timing: id 0 | task 4825 | eval time = 2084.83 ms / 128 tokens ( 16.42 ms per token, 60.92 tokens per second) 1.35.504.479 I slot print_timing: id 0 | task 4825 | total time = 2445.34 ms / 285 tokens 1.35.504.480 I slot print_timing: id 0 | task 4825 | graphs reused = 4785 1.35.504.480 I slot print_timing: id 0 | task 4825 | graph reallocs = 0 / 0 (same size) / (changed size) 1.35.504.502 I slot release: id 0 | task 4825 | stop processing: n_tokens = 284, truncated = 0 1.35.507.977 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.106 (> 0.100 thold), f_keep = 0.074 1.35.508.756 I slot launch_slot_: id 0 | task 4955 | processing task, is_child = 0 1.38.926.917 I slot print_timing: id 0 | task 4955 | n_gen = 184, tg = 60.80 t/s, tg_3s = 61.14 t/s 1.41.932.303 I slot print_timing: id 0 | task 4955 | n_gen = 367, tg = 60.85 t/s, tg_3s = 60.89 t/s 1.43.988.480 I slot print_timing: id 0 | task 4955 | prompt eval time = 408.47 ms / 198 tokens ( 2.06 ms per token, 484.73 tokens per second) 1.43.988.486 I slot print_timing: id 0 | task 4955 | eval time = 8071.24 ms / 492 tokens ( 16.44 ms per token, 60.83 tokens per second) 1.43.988.487 I slot print_timing: id 0 | task 4955 | total time = 8479.72 ms / 690 tokens 1.43.988.488 I slot print_timing: id 0 | task 4955 | graphs reused = 5273 1.43.988.489 I slot print_timing: id 0 | task 4955 | graph reallocs = 0 / 0 (same size) / (changed size) 1.43.988.513 I slot release: id 0 | task 4955 | stop processing: n_tokens = 689, truncated = 0 1.43.991.935 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.168 (> 0.100 thold), f_keep = 0.030 1.43.993.520 I slot launch_slot_: id 0 | task 5449 | processing task, is_child = 0 1.45.996.595 I slot print_timing: id 0 | task 5449 | prompt eval time = 334.15 ms / 125 tokens ( 2.67 ms per token, 374.08 tokens per second) 1.45.996.599 I slot print_timing: id 0 | task 5449 | eval time = 1668.92 ms / 103 tokens ( 16.36 ms per token, 61.12 tokens per second) 1.45.996.599 I slot print_timing: id 0 | task 5449 | total time = 2003.07 ms / 228 tokens 1.45.996.600 I slot print_timing: id 0 | task 5449 | graphs reused = 5374 1.45.996.600 I slot print_timing: id 0 | task 5449 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.996.619 I slot release: id 0 | task 5449 | stop processing: n_tokens = 227, truncated = 0 1.45.999.995 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.157 (> 0.100 thold), f_keep = 0.093 1.46.000.683 I slot launch_slot_: id 0 | task 5554 | processing task, is_child = 0 1.49.362.732 I slot print_timing: id 0 | task 5554 | n_gen = 184, tg = 60.71 t/s, tg_3s = 61.04 t/s 1.49.659.709 I slot print_timing: id 0 | task 5554 | prompt eval time = 347.66 ms / 134 tokens ( 2.59 ms per token, 385.44 tokens per second) 1.49.659.712 I slot print_timing: id 0 | task 5554 | eval time = 3311.36 ms / 202 tokens ( 16.47 ms per token, 60.70 tokens per second) 1.49.659.713 I slot print_timing: id 0 | task 5554 | total time = 3659.02 ms / 336 tokens 1.49.659.713 I slot print_timing: id 0 | task 5554 | graphs reused = 5573 1.49.659.714 I slot print_timing: id 0 | task 5554 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.659.734 I slot release: id 0 | task 5554 | stop processing: n_tokens = 335, truncated = 0 1.49.663.020 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.142 (> 0.100 thold), f_keep = 0.063 1.49.663.893 I slot launch_slot_: id 0 | task 5758 | processing task, is_child = 0 1.52.919.293 I slot print_timing: id 0 | task 5758 | prompt eval time = 357.36 ms / 148 tokens ( 2.41 ms per token, 414.14 tokens per second) 1.52.919.296 I slot print_timing: id 0 | task 5758 | eval time = 2898.02 ms / 178 tokens ( 16.37 ms per token, 61.08 tokens per second) 1.52.919.296 I slot print_timing: id 0 | task 5758 | total time = 3255.39 ms / 326 tokens 1.52.919.297 I slot print_timing: id 0 | task 5758 | graphs reused = 5748 1.52.919.297 I slot print_timing: id 0 | task 5758 | graph reallocs = 0 / 0 (same size) / (changed size) 1.52.919.317 I slot release: id 0 | task 5758 | stop processing: n_tokens = 325, truncated = 0 1.52.922.883 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.149 (> 0.100 thold), f_keep = 0.065 1.52.923.737 I slot launch_slot_: id 0 | task 5938 | processing task, is_child = 0 1.54.391.778 I slot print_timing: id 0 | task 5938 | prompt eval time = 350.68 ms / 141 tokens ( 2.49 ms per token, 402.08 tokens per second) 1.54.391.783 I slot print_timing: id 0 | task 5938 | eval time = 1117.36 ms / 69 tokens ( 16.43 ms per token, 60.86 tokens per second) 1.54.391.784 I slot print_timing: id 0 | task 5938 | total time = 1468.03 ms / 210 tokens 1.54.391.785 I slot print_timing: id 0 | task 5938 | graphs reused = 5815 1.54.391.785 I slot print_timing: id 0 | task 5938 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.391.804 I slot release: id 0 | task 5938 | stop processing: n_tokens = 209, truncated = 0 1.54.395.077 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 1.54.395.707 I slot launch_slot_: id 0 | task 6009 | processing task, is_child = 0 1.56.776.607 I slot print_timing: id 0 | task 6009 | prompt eval time = 394.77 ms / 196 tokens ( 2.01 ms per token, 496.49 tokens per second) 1.56.776.613 I slot print_timing: id 0 | task 6009 | eval time = 1986.12 ms / 122 tokens ( 16.41 ms per token, 60.92 tokens per second) 1.56.776.614 I slot print_timing: id 0 | task 6009 | total time = 2380.89 ms / 318 tokens 1.56.776.615 I slot print_timing: id 0 | task 6009 | graphs reused = 5934 1.56.776.615 I slot print_timing: id 0 | task 6009 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.776.639 I slot release: id 0 | task 6009 | stop processing: n_tokens = 317, truncated = 0 1.56.780.205 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 317, t_last = 341561856516 1.56.781.026 I slot launch_slot_: id 0 | task 6133 | processing task, is_child = 0 2.00.324.770 I slot print_timing: id 0 | task 6133 | n_gen = 184, tg = 60.83 t/s, tg_3s = 61.16 t/s 2.00.558.097 I slot print_timing: id 0 | task 6133 | prompt eval time = 535.29 ms / 328 tokens ( 1.63 ms per token, 612.75 tokens per second) 2.00.558.103 I slot print_timing: id 0 | task 6133 | eval time = 3241.77 ms / 198 tokens ( 16.46 ms per token, 60.77 tokens per second) 2.00.558.104 I slot print_timing: id 0 | task 6133 | total time = 3777.06 ms / 526 tokens 2.00.558.104 I slot print_timing: id 0 | task 6133 | graphs reused = 6129 2.00.558.105 I slot print_timing: id 0 | task 6133 | graph reallocs = 0 / 0 (same size) / (changed size) 2.00.558.138 I slot release: id 0 | task 6133 | stop processing: n_tokens = 525, truncated = 0 2.00.561.473 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.143 (> 0.100 thold), f_keep = 0.040 2.00.562.735 I slot launch_slot_: id 0 | task 6333 | processing task, is_child = 0 2.02.260.512 I slot print_timing: id 0 | task 6333 | prompt eval time = 354.39 ms / 147 tokens ( 2.41 ms per token, 414.80 tokens per second) 2.02.260.518 I slot print_timing: id 0 | task 6333 | eval time = 1343.38 ms / 83 tokens ( 16.38 ms per token, 61.04 tokens per second) 2.02.260.519 I slot print_timing: id 0 | task 6333 | total time = 1697.77 ms / 230 tokens 2.02.260.519 I slot print_timing: id 0 | task 6333 | graphs reused = 6210 2.02.260.520 I slot print_timing: id 0 | task 6333 | graph reallocs = 0 / 0 (same size) / (changed size) 2.02.260.542 I slot release: id 0 | task 6333 | stop processing: n_tokens = 229, truncated = 0 2.02.263.838 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.115 (> 0.100 thold), f_keep = 0.092 2.02.264.468 I slot launch_slot_: id 0 | task 6418 | processing task, is_child = 0 2.04.345.304 I slot print_timing: id 0 | task 6418 | prompt eval time = 396.71 ms / 182 tokens ( 2.18 ms per token, 458.78 tokens per second) 2.04.345.311 I slot print_timing: id 0 | task 6418 | eval time = 1684.12 ms / 102 tokens ( 16.67 ms per token, 59.97 tokens per second) 2.04.345.311 I slot print_timing: id 0 | task 6418 | total time = 2080.83 ms / 284 tokens 2.04.345.312 I slot print_timing: id 0 | task 6418 | graphs reused = 6309 2.04.345.313 I slot print_timing: id 0 | task 6418 | graph reallocs = 0 / 0 (same size) / (changed size) 2.04.345.334 I slot release: id 0 | task 6418 | stop processing: n_tokens = 283, truncated = 0 2.04.348.877 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 283, t_last = 341569425211 2.04.349.669 I slot launch_slot_: id 0 | task 6522 | processing task, is_child = 0 2.06.839.221 I slot print_timing: id 0 | task 6522 | prompt eval time = 435.52 ms / 230 tokens ( 1.89 ms per token, 528.10 tokens per second) 2.06.839.228 I slot print_timing: id 0 | task 6522 | eval time = 2054.02 ms / 126 tokens ( 16.43 ms per token, 60.86 tokens per second) 2.06.839.228 I slot print_timing: id 0 | task 6522 | total time = 2489.54 ms / 356 tokens 2.06.839.229 I slot print_timing: id 0 | task 6522 | graphs reused = 6432 2.06.839.230 I slot print_timing: id 0 | task 6522 | graph reallocs = 0 / 0 (same size) / (changed size) 2.06.839.255 I slot release: id 0 | task 6522 | stop processing: n_tokens = 355, truncated = 0 2.06.842.929 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 355, t_last = 341571919132 2.06.843.884 I slot launch_slot_: id 0 | task 6650 | processing task, is_child = 0 2.08.833.376 I slot print_timing: id 0 | task 6650 | prompt eval time = 441.56 ms / 239 tokens ( 1.85 ms per token, 541.26 tokens per second) 2.08.833.379 I slot print_timing: id 0 | task 6650 | eval time = 1547.91 ms / 95 tokens ( 16.47 ms per token, 60.73 tokens per second) 2.08.833.380 I slot print_timing: id 0 | task 6650 | total time = 1989.48 ms / 334 tokens 2.08.833.381 I slot print_timing: id 0 | task 6650 | graphs reused = 6524 2.08.833.382 I slot print_timing: id 0 | task 6650 | graph reallocs = 0 / 0 (same size) / (changed size) 2.08.833.411 I slot release: id 0 | task 6650 | stop processing: n_tokens = 333, truncated = 0 2.08.836.785 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.151 (> 0.100 thold), f_keep = 0.072 2.08.837.707 I slot launch_slot_: id 0 | task 6747 | processing task, is_child = 0 2.10.483.305 I slot print_timing: id 0 | task 6747 | prompt eval time = 360.53 ms / 159 tokens ( 2.27 ms per token, 441.02 tokens per second) 2.10.483.309 I slot print_timing: id 0 | task 6747 | eval time = 1285.06 ms / 79 tokens ( 16.48 ms per token, 60.70 tokens per second) 2.10.483.310 I slot print_timing: id 0 | task 6747 | total time = 1645.59 ms / 238 tokens 2.10.483.310 I slot print_timing: id 0 | task 6747 | graphs reused = 6601 2.10.483.311 I slot print_timing: id 0 | task 6747 | graph reallocs = 0 / 0 (same size) / (changed size) 2.10.483.331 I slot release: id 0 | task 6747 | stop processing: n_tokens = 237, truncated = 0 2.10.486.659 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.125 (> 0.100 thold), f_keep = 0.089 2.10.487.457 I slot launch_slot_: id 0 | task 6828 | processing task, is_child = 0 2.12.671.304 I slot print_timing: id 0 | task 6828 | prompt eval time = 383.15 ms / 168 tokens ( 2.28 ms per token, 438.46 tokens per second) 2.12.671.308 I slot print_timing: id 0 | task 6828 | eval time = 1800.68 ms / 110 tokens ( 16.52 ms per token, 60.53 tokens per second) 2.12.671.308 I slot print_timing: id 0 | task 6828 | total time = 2183.84 ms / 278 tokens 2.12.671.309 I slot print_timing: id 0 | task 6828 | graphs reused = 6708 2.12.671.310 I slot print_timing: id 0 | task 6828 | graph reallocs = 0 / 0 (same size) / (changed size) 2.12.671.331 I slot release: id 0 | task 6828 | stop processing: n_tokens = 277, truncated = 0 2.12.674.611 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.119 (> 0.100 thold), f_keep = 0.076 2.12.675.358 I slot launch_slot_: id 0 | task 6940 | processing task, is_child = 0 2.15.236.093 I slot print_timing: id 0 | task 6940 | prompt eval time = 385.06 ms / 177 tokens ( 2.18 ms per token, 459.67 tokens per second) 2.15.236.096 I slot print_timing: id 0 | task 6940 | eval time = 2175.67 ms / 133 tokens ( 16.48 ms per token, 60.67 tokens per second) 2.15.236.097 I slot print_timing: id 0 | task 6940 | total time = 2560.72 ms / 310 tokens 2.15.236.097 I slot print_timing: id 0 | task 6940 | graphs reused = 6838 2.15.236.098 I slot print_timing: id 0 | task 6940 | graph reallocs = 0 / 0 (same size) / (changed size) 2.15.236.120 I slot release: id 0 | task 6940 | stop processing: n_tokens = 309, truncated = 0 2.15.239.707 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.101 (> 0.100 thold), f_keep = 0.068 2.15.240.564 I slot launch_slot_: id 0 | task 7075 | processing task, is_child = 0 2.18.121.689 I slot print_timing: id 0 | task 7075 | prompt eval time = 414.09 ms / 208 tokens ( 1.99 ms per token, 502.31 tokens per second) 2.18.121.695 I slot print_timing: id 0 | task 7075 | eval time = 2467.02 ms / 151 tokens ( 16.45 ms per token, 60.80 tokens per second) 2.18.121.696 I slot print_timing: id 0 | task 7075 | total time = 2881.11 ms / 359 tokens 2.18.121.696 I slot print_timing: id 0 | task 7075 | graphs reused = 6986 2.18.121.697 I slot print_timing: id 0 | task 7075 | graph reallocs = 0 / 0 (same size) / (changed size) 2.18.121.721 I slot release: id 0 | task 7075 | stop processing: n_tokens = 358, truncated = 0 2.18.125.024 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.131 (> 0.100 thold), f_keep = 0.059 2.18.126.016 I slot launch_slot_: id 0 | task 7228 | processing task, is_child = 0 2.20.501.831 I slot print_timing: id 0 | task 7228 | prompt eval time = 361.61 ms / 160 tokens ( 2.26 ms per token, 442.47 tokens per second) 2.20.501.838 I slot print_timing: id 0 | task 7228 | eval time = 2014.20 ms / 123 tokens ( 16.51 ms per token, 60.57 tokens per second) 2.20.501.838 I slot print_timing: id 0 | task 7228 | total time = 2375.81 ms / 283 tokens 2.20.501.839 I slot print_timing: id 0 | task 7228 | graphs reused = 7106 2.20.501.840 I slot print_timing: id 0 | task 7228 | graph reallocs = 0 / 0 (same size) / (changed size) 2.20.501.861 I slot release: id 0 | task 7228 | stop processing: n_tokens = 282, truncated = 0 2.20.505.458 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 282, t_last = 341585581738 2.20.506.287 I slot launch_slot_: id 0 | task 7353 | processing task, is_child = 0 2.23.930.019 I slot print_timing: id 0 | task 7353 | n_gen = 184, tg = 60.92 t/s, tg_3s = 61.25 t/s 2.23.979.797 I slot print_timing: id 0 | task 7353 | prompt eval time = 419.73 ms / 219 tokens ( 1.92 ms per token, 521.76 tokens per second) 2.23.979.803 I slot print_timing: id 0 | task 7353 | eval time = 3053.77 ms / 187 tokens ( 16.42 ms per token, 60.91 tokens per second) 2.23.979.803 I slot print_timing: id 0 | task 7353 | total time = 3473.50 ms / 406 tokens 2.23.979.804 I slot print_timing: id 0 | task 7353 | graphs reused = 7290 2.23.979.805 I slot print_timing: id 0 | task 7353 | graph reallocs = 0 / 0 (same size) / (changed size) 2.23.979.830 I slot release: id 0 | task 7353 | stop processing: n_tokens = 405, truncated = 0 2.23.983.296 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.124 (> 0.100 thold), f_keep = 0.052 2.23.984.380 I slot launch_slot_: id 0 | task 7542 | processing task, is_child = 0 2.26.362.081 I slot print_timing: id 0 | task 7542 | prompt eval time = 380.39 ms / 170 tokens ( 2.24 ms per token, 446.91 tokens per second) 2.26.362.087 I slot print_timing: id 0 | task 7542 | eval time = 1997.30 ms / 122 tokens ( 16.51 ms per token, 60.58 tokens per second) 2.26.362.088 I slot print_timing: id 0 | task 7542 | total time = 2377.69 ms / 292 tokens 2.26.362.089 I slot print_timing: id 0 | task 7542 | graphs reused = 7409 2.26.362.089 I slot print_timing: id 0 | task 7542 | graph reallocs = 0 / 0 (same size) / (changed size) 2.26.362.112 I slot release: id 0 | task 7542 | stop processing: n_tokens = 291, truncated = 0 2.26.365.622 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.124 (> 0.100 thold), f_keep = 0.072 2.26.366.447 I slot launch_slot_: id 0 | task 7666 | processing task, is_child = 0 2.28.833.408 I slot print_timing: id 0 | task 7666 | prompt eval time = 381.86 ms / 169 tokens ( 2.26 ms per token, 442.58 tokens per second) 2.28.833.412 I slot print_timing: id 0 | task 7666 | eval time = 2085.10 ms / 128 tokens ( 16.42 ms per token, 60.91 tokens per second) 2.28.833.413 I slot print_timing: id 0 | task 7666 | total time = 2466.95 ms / 297 tokens 2.28.833.413 I slot print_timing: id 0 | task 7666 | graphs reused = 7534 2.28.833.414 I slot print_timing: id 0 | task 7666 | graph reallocs = 0 / 0 (same size) / (changed size) 2.28.833.446 I slot release: id 0 | task 7666 | stop processing: n_tokens = 296, truncated = 0 2.28.836.967 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 296, t_last = 341593913323 2.28.837.861 I slot launch_slot_: id 0 | task 7796 | processing task, is_child = 0 2.32.332.696 I slot print_timing: id 0 | task 7796 | n_gen = 184, tg = 60.88 t/s, tg_3s = 61.21 t/s 2.32.414.429 I slot print_timing: id 0 | task 7796 | prompt eval time = 488.77 ms / 287 tokens ( 1.70 ms per token, 587.19 tokens per second) 2.32.414.435 I slot print_timing: id 0 | task 7796 | eval time = 3087.79 ms / 189 tokens ( 16.42 ms per token, 60.89 tokens per second) 2.32.414.436 I slot print_timing: id 0 | task 7796 | total time = 3576.56 ms / 476 tokens 2.32.414.436 I slot print_timing: id 0 | task 7796 | graphs reused = 7721 2.32.414.437 I slot print_timing: id 0 | task 7796 | graph reallocs = 0 / 0 (same size) / (changed size) 2.32.414.468 I slot release: id 0 | task 7796 | stop processing: n_tokens = 475, truncated = 0 2.32.417.988 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 475, t_last = 341597494345 2.32.419.218 I slot launch_slot_: id 0 | task 7987 | processing task, is_child = 0 2.35.878.984 I slot print_timing: id 0 | task 7987 | n_gen = 184, tg = 60.90 t/s, tg_3s = 61.23 t/s 2.35.992.896 I slot print_timing: id 0 | task 7987 | prompt eval time = 454.71 ms / 255 tokens ( 1.78 ms per token, 560.80 tokens per second) 2.35.992.902 I slot print_timing: id 0 | task 7987 | eval time = 3118.96 ms / 191 tokens ( 16.42 ms per token, 60.92 tokens per second) 2.35.992.903 I slot print_timing: id 0 | task 7987 | total time = 3573.67 ms / 446 tokens 2.35.992.904 I slot print_timing: id 0 | task 7987 | graphs reused = 7909 2.35.992.904 I slot print_timing: id 0 | task 7987 | graph reallocs = 0 / 0 (same size) / (changed size) 2.35.992.936 I slot release: id 0 | task 7987 | stop processing: n_tokens = 445, truncated = 0 2.35.996.340 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.129 (> 0.100 thold), f_keep = 0.047 2.35.997.436 I slot launch_slot_: id 0 | task 8180 | processing task, is_child = 0 2.38.333.204 I slot print_timing: id 0 | task 8180 | prompt eval time = 365.71 ms / 163 tokens ( 2.24 ms per token, 445.70 tokens per second) 2.38.333.207 I slot print_timing: id 0 | task 8180 | eval time = 1970.04 ms / 119 tokens ( 16.70 ms per token, 59.90 tokens per second) 2.38.333.208 I slot print_timing: id 0 | task 8180 | total time = 2335.75 ms / 282 tokens 2.38.333.209 I slot print_timing: id 0 | task 8180 | graphs reused = 8025 2.38.333.209 I slot print_timing: id 0 | task 8180 | graph reallocs = 0 / 0 (same size) / (changed size) 2.38.333.231 I slot release: id 0 | task 8180 | stop processing: n_tokens = 281, truncated = 0 2.38.336.782 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.104 (> 0.100 thold), f_keep = 0.075 2.38.337.609 I slot launch_slot_: id 0 | task 8301 | processing task, is_child = 0 2.40.487.730 I slot print_timing: id 0 | task 8301 | prompt eval time = 412.38 ms / 201 tokens ( 2.05 ms per token, 487.41 tokens per second) 2.40.487.733 I slot print_timing: id 0 | task 8301 | eval time = 1737.72 ms / 107 tokens ( 16.39 ms per token, 61.00 tokens per second) 2.40.487.734 I slot print_timing: id 0 | task 8301 | total time = 2150.11 ms / 308 tokens 2.40.487.735 I slot print_timing: id 0 | task 8301 | graphs reused = 8129 2.40.487.735 I slot print_timing: id 0 | task 8301 | graph reallocs = 0 / 0 (same size) / (changed size) 2.40.487.760 I slot release: id 0 | task 8301 | stop processing: n_tokens = 307, truncated = 0 2.40.491.093 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.134 (> 0.100 thold), f_keep = 0.068 2.40.491.940 I slot launch_slot_: id 0 | task 8410 | processing task, is_child = 0 2.42.442.051 I slot print_timing: id 0 | task 8410 | prompt eval time = 359.84 ms / 157 tokens ( 2.29 ms per token, 436.31 tokens per second) 2.42.442.057 I slot print_timing: id 0 | task 8410 | eval time = 1590.26 ms / 97 tokens ( 16.57 ms per token, 60.37 tokens per second) 2.42.442.058 I slot print_timing: id 0 | task 8410 | total time = 1950.10 ms / 254 tokens 2.42.442.058 I slot print_timing: id 0 | task 8410 | graphs reused = 8224 2.42.442.059 I slot print_timing: id 0 | task 8410 | graph reallocs = 0 / 0 (same size) / (changed size) 2.42.442.079 I slot release: id 0 | task 8410 | stop processing: n_tokens = 253, truncated = 0 2.42.445.469 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 253, t_last = 341607521956 2.42.446.231 I slot launch_slot_: id 0 | task 8509 | processing task, is_child = 0 2.45.367.406 I slot print_timing: id 0 | task 8509 | prompt eval time = 427.30 ms / 226 tokens ( 1.89 ms per token, 528.91 tokens per second) 2.45.367.409 I slot print_timing: id 0 | task 8509 | eval time = 2493.87 ms / 153 tokens ( 16.41 ms per token, 60.95 tokens per second) 2.45.367.411 I slot print_timing: id 0 | task 8509 | total time = 2921.16 ms / 379 tokens 2.45.367.412 I slot print_timing: id 0 | task 8509 | graphs reused = 8374 2.45.367.412 I slot print_timing: id 0 | task 8509 | graph reallocs = 0 / 0 (same size) / (changed size) 2.45.367.440 I slot release: id 0 | task 8509 | stop processing: n_tokens = 378, truncated = 0 2.45.371.439 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 378, t_last = 341610447317 2.45.372.406 I slot launch_slot_: id 0 | task 8664 | processing task, is_child = 0 2.48.928.859 I slot print_timing: id 0 | task 8664 | n_gen = 183, tg = 60.62 t/s, tg_3s = 60.96 t/s 2.49.489.343 I slot print_timing: id 0 | task 8664 | prompt eval time = 554.29 ms / 356 tokens ( 1.56 ms per token, 642.26 tokens per second) 2.49.489.349 I slot print_timing: id 0 | task 8664 | eval time = 3562.64 ms / 217 tokens ( 16.49 ms per token, 60.63 tokens per second) 2.49.489.350 I slot print_timing: id 0 | task 8664 | total time = 4116.93 ms / 573 tokens 2.49.489.351 I slot print_timing: id 0 | task 8664 | graphs reused = 8588 2.49.489.351 I slot print_timing: id 0 | task 8664 | graph reallocs = 0 / 0 (same size) / (changed size) 2.49.489.383 I slot release: id 0 | task 8664 | stop processing: n_tokens = 572, truncated = 0 2.49.493.349 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 572, t_last = 341614569260 2.49.494.749 I slot launch_slot_: id 0 | task 8883 | processing task, is_child = 0 2.53.143.168 I slot print_timing: id 0 | task 8883 | n_gen = 184, tg = 60.72 t/s, tg_3s = 61.05 t/s 2.53.851.305 I slot print_timing: id 0 | task 8883 | prompt eval time = 634.71 ms / 427 tokens ( 1.49 ms per token, 672.75 tokens per second) 2.53.851.309 I slot print_timing: id 0 | task 8883 | eval time = 3721.84 ms / 227 tokens ( 16.47 ms per token, 60.72 tokens per second) 2.53.851.310 I slot print_timing: id 0 | task 8883 | total time = 4356.55 ms / 654 tokens 2.53.851.310 I slot print_timing: id 0 | task 8883 | graphs reused = 8812 2.53.851.311 I slot print_timing: id 0 | task 8883 | graph reallocs = 0 / 0 (same size) / (changed size) 2.53.851.344 I slot release: id 0 | task 8883 | stop processing: n_tokens = 653, truncated = 0 2.53.855.379 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 653, t_last = 341618931221 2.53.856.934 I slot launch_slot_: id 0 | task 9112 | processing task, is_child = 0 2.57.555.691 I slot print_timing: id 0 | task 9112 | n_gen = 184, tg = 60.82 t/s, tg_3s = 61.15 t/s 2.57.604.956 I slot print_timing: id 0 | task 9112 | prompt eval time = 689.98 ms / 481 tokens ( 1.43 ms per token, 697.12 tokens per second) 2.57.604.959 I slot print_timing: id 0 | task 9112 | eval time = 3058.04 ms / 187 tokens ( 16.44 ms per token, 60.82 tokens per second) 2.57.604.960 I slot print_timing: id 0 | task 9112 | total time = 3748.02 ms / 668 tokens 2.57.604.961 I slot print_timing: id 0 | task 9112 | graphs reused = 8996 2.57.604.961 I slot print_timing: id 0 | task 9112 | graph reallocs = 0 / 0 (same size) / (changed size) 2.57.605.004 I slot release: id 0 | task 9112 | stop processing: n_tokens = 667, truncated = 0 2.57.609.033 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 667, t_last = 341622684881 2.57.610.644 I slot launch_slot_: id 0 | task 9301 | processing task, is_child = 0 3.00.719.594 I slot print_timing: id 0 | task 9301 | prompt eval time = 672.31 ms / 456 tokens ( 1.47 ms per token, 678.26 tokens per second) 3.00.719.597 I slot print_timing: id 0 | task 9301 | eval time = 2436.63 ms / 149 tokens ( 16.46 ms per token, 60.74 tokens per second) 3.00.719.597 I slot print_timing: id 0 | task 9301 | total time = 3108.94 ms / 605 tokens 3.00.719.598 I slot print_timing: id 0 | task 9301 | graphs reused = 9142 3.00.719.599 I slot print_timing: id 0 | task 9301 | graph reallocs = 0 / 0 (same size) / (changed size) 3.00.719.634 I slot release: id 0 | task 9301 | stop processing: n_tokens = 604, truncated = 0 3.00.723.397 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 604, t_last = 341625799511 3.00.724.804 I slot launch_slot_: id 0 | task 9452 | processing task, is_child = 0 3.02.838.979 I slot print_timing: id 0 | task 9452 | prompt eval time = 487.76 ms / 290 tokens ( 1.68 ms per token, 594.56 tokens per second) 3.02.838.985 I slot print_timing: id 0 | task 9452 | eval time = 1626.41 ms / 99 tokens ( 16.60 ms per token, 60.26 tokens per second) 3.02.838.986 I slot print_timing: id 0 | task 9452 | total time = 2114.17 ms / 389 tokens 3.02.838.987 I slot print_timing: id 0 | task 9452 | graphs reused = 9239 3.02.838.987 I slot print_timing: id 0 | task 9452 | graph reallocs = 0 / 0 (same size) / (changed size) 3.02.839.018 I slot release: id 0 | task 9452 | stop processing: n_tokens = 388, truncated = 0 3.02.843.053 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 388, t_last = 341627918895 3.02.844.097 I slot launch_slot_: id 0 | task 9553 | processing task, is_child = 0 3.06.499.379 I slot print_timing: id 0 | task 9553 | n_gen = 184, tg = 60.82 t/s, tg_3s = 61.15 t/s 3.09.505.837 I slot print_timing: id 0 | task 9553 | n_gen = 367, tg = 60.84 t/s, tg_3s = 60.87 t/s 3.09.936.793 I slot print_timing: id 0 | task 9553 | prompt eval time = 646.18 ms / 439 tokens ( 1.47 ms per token, 679.38 tokens per second) 3.09.936.799 I slot print_timing: id 0 | task 9553 | eval time = 6446.51 ms / 393 tokens ( 16.45 ms per token, 60.81 tokens per second) 3.09.936.799 I slot print_timing: id 0 | task 9553 | total time = 7092.69 ms / 832 tokens 3.09.936.800 I slot print_timing: id 0 | task 9553 | graphs reused = 9628 3.09.936.801 I slot print_timing: id 0 | task 9553 | graph reallocs = 0 / 0 (same size) / (changed size) 3.09.936.835 I slot release: id 0 | task 9553 | stop processing: n_tokens = 831, truncated = 0 3.09.940.927 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 831, t_last = 341635016712 3.09.942.776 I slot launch_slot_: id 0 | task 9948 | processing task, is_child = 0 3.13.555.699 I slot print_timing: id 0 | task 9948 | n_gen = 184, tg = 60.83 t/s, tg_3s = 61.16 t/s 3.16.563.967 I slot print_timing: id 0 | task 9948 | n_gen = 367, tg = 60.83 t/s, tg_3s = 60.83 t/s 3.19.575.963 I slot print_timing: id 0 | task 9948 | n_gen = 550, tg = 60.80 t/s, tg_3s = 60.76 t/s 3.22.592.373 I slot print_timing: id 0 | task 9948 | n_gen = 733, tg = 60.77 t/s, tg_3s = 60.67 t/s 3.24.228.421 I slot print_timing: id 0 | task 9948 | prompt eval time = 604.29 ms / 396 tokens ( 1.53 ms per token, 655.31 tokens per second) 3.24.228.427 I slot print_timing: id 0 | task 9948 | eval time = 13681.34 ms / 832 tokens ( 16.46 ms per token, 60.74 tokens per second) 3.24.228.428 I slot print_timing: id 0 | task 9948 | total time = 14285.63 ms / 1228 tokens 3.24.228.429 I slot print_timing: id 0 | task 9948 | graphs reused = 10455 3.24.228.429 I slot print_timing: id 0 | task 9948 | graph reallocs = 0 / 0 (same size) / (changed size) 3.24.228.467 I slot release: id 0 | task 9948 | stop processing: n_tokens = 1227, truncated = 0 3.24.232.558 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1227, t_last = 341649308344 3.24.235.345 I slot launch_slot_: id 0 | task 10782 | processing task, is_child = 0 3.26.322.441 I slot print_timing: id 0 | task 10782 | prompt eval time = 545.63 ms / 342 tokens ( 1.60 ms per token, 626.79 tokens per second) 3.26.322.447 I slot print_timing: id 0 | task 10782 | eval time = 1541.45 ms / 95 tokens ( 16.40 ms per token, 60.98 tokens per second) 3.26.322.448 I slot print_timing: id 0 | task 10782 | total time = 2087.09 ms / 437 tokens 3.26.322.448 I slot print_timing: id 0 | task 10782 | graphs reused = 10548 3.26.322.449 I slot print_timing: id 0 | task 10782 | graph reallocs = 0 / 0 (same size) / (changed size) 3.26.322.480 I slot release: id 0 | task 10782 | stop processing: n_tokens = 436, truncated = 0 3.26.326.317 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 436, t_last = 341651402357 3.26.327.488 I slot launch_slot_: id 0 | task 10879 | processing task, is_child = 0 3.28.656.394 I slot print_timing: id 0 | task 10879 | prompt eval time = 517.57 ms / 314 tokens ( 1.65 ms per token, 606.68 tokens per second) 3.28.656.397 I slot print_timing: id 0 | task 10879 | eval time = 1811.33 ms / 111 tokens ( 16.47 ms per token, 60.73 tokens per second) 3.28.656.398 I slot print_timing: id 0 | task 10879 | total time = 2328.90 ms / 425 tokens 3.28.656.399 I slot print_timing: id 0 | task 10879 | graphs reused = 10657 3.28.656.399 I slot print_timing: id 0 | task 10879 | graph reallocs = 0 / 0 (same size) / (changed size) 3.28.656.428 I slot release: id 0 | task 10879 | stop processing: n_tokens = 424, truncated = 0 3.28.660.488 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 341653736305 3.28.661.630 I slot launch_slot_: id 0 | task 10992 | processing task, is_child = 0 3.30.885.672 I slot print_timing: id 0 | task 10992 | prompt eval time = 607.48 ms / 396 tokens ( 1.53 ms per token, 651.88 tokens per second) 3.30.885.678 I slot print_timing: id 0 | task 10992 | eval time = 1616.56 ms / 98 tokens ( 16.67 ms per token, 60.00 tokens per second) 3.30.885.679 I slot print_timing: id 0 | task 10992 | total time = 2224.03 ms / 494 tokens 3.30.885.680 I slot print_timing: id 0 | task 10992 | graphs reused = 10753 3.30.885.680 I slot print_timing: id 0 | task 10992 | graph reallocs = 0 / 0 (same size) / (changed size) 3.30.885.720 I slot release: id 0 | task 10992 | stop processing: n_tokens = 493, truncated = 0 3.30.892.466 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 493, t_last = 341655965597 3.30.893.708 I slot launch_slot_: id 0 | task 11092 | processing task, is_child = 0 3.34.402.821 I slot print_timing: id 0 | task 11092 | prompt eval time = 544.04 ms / 339 tokens ( 1.60 ms per token, 623.12 tokens per second) 3.34.402.825 I slot print_timing: id 0 | task 11092 | eval time = 2965.06 ms / 181 tokens ( 16.47 ms per token, 60.71 tokens per second) 3.34.402.826 I slot print_timing: id 0 | task 11092 | total time = 3509.10 ms / 520 tokens 3.34.402.826 I slot print_timing: id 0 | task 11092 | graphs reused = 10931 3.34.402.827 I slot print_timing: id 0 | task 11092 | graph reallocs = 0 / 0 (same size) / (changed size) 3.34.402.860 I slot release: id 0 | task 11092 | stop processing: n_tokens = 519, truncated = 0 3.34.406.375 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 519, t_last = 341659482737 3.34.407.703 I slot launch_slot_: id 0 | task 11275 | processing task, is_child = 0 3.36.491.414 I slot print_timing: id 0 | task 11275 | prompt eval time = 474.73 ms / 267 tokens ( 1.78 ms per token, 562.43 tokens per second) 3.36.491.418 I slot print_timing: id 0 | task 11275 | eval time = 1608.97 ms / 98 tokens ( 16.59 ms per token, 60.29 tokens per second) 3.36.491.419 I slot print_timing: id 0 | task 11275 | total time = 2083.70 ms / 365 tokens 3.36.491.419 I slot print_timing: id 0 | task 11275 | graphs reused = 11027 3.36.491.420 I slot print_timing: id 0 | task 11275 | graph reallocs = 0 / 0 (same size) / (changed size) 3.36.491.449 I slot release: id 0 | task 11275 | stop processing: n_tokens = 364, truncated = 0 3.36.495.354 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 364, t_last = 341661571326 3.36.496.377 I slot launch_slot_: id 0 | task 11375 | processing task, is_child = 0 3.40.080.550 I slot print_timing: id 0 | task 11375 | n_gen = 184, tg = 60.70 t/s, tg_3s = 61.03 t/s 3.40.113.457 I slot print_timing: id 0 | task 11375 | prompt eval time = 569.12 ms / 360 tokens ( 1.58 ms per token, 632.56 tokens per second) 3.40.113.463 I slot print_timing: id 0 | task 11375 | eval time = 3047.95 ms / 186 tokens ( 16.48 ms per token, 60.70 tokens per second) 3.40.113.463 I slot print_timing: id 0 | task 11375 | total time = 3617.07 ms / 546 tokens 3.40.113.464 I slot print_timing: id 0 | task 11375 | graphs reused = 11210 3.40.113.465 I slot print_timing: id 0 | task 11375 | graph reallocs = 0 / 0 (same size) / (changed size) 3.40.113.499 I slot release: id 0 | task 11375 | stop processing: n_tokens = 545, truncated = 0 3.40.117.252 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 545, t_last = 341665193376 3.40.118.608 I slot launch_slot_: id 0 | task 11563 | processing task, is_child = 0 3.42.819.154 I slot print_timing: id 0 | task 11563 | prompt eval time = 505.31 ms / 296 tokens ( 1.71 ms per token, 585.77 tokens per second) 3.42.819.162 I slot print_timing: id 0 | task 11563 | eval time = 2195.22 ms / 134 tokens ( 16.51 ms per token, 60.59 tokens per second) 3.42.819.162 I slot print_timing: id 0 | task 11563 | total time = 2700.54 ms / 430 tokens 3.42.819.163 I slot print_timing: id 0 | task 11563 | graphs reused = 11342 3.42.819.163 I slot print_timing: id 0 | task 11563 | graph reallocs = 0 / 0 (same size) / (changed size) 3.42.819.191 I slot release: id 0 | task 11563 | stop processing: n_tokens = 429, truncated = 0 3.42.822.835 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 429, t_last = 341667899068 3.42.823.974 I slot launch_slot_: id 0 | task 11699 | processing task, is_child = 0 3.45.585.923 I slot print_timing: id 0 | task 11699 | prompt eval time = 481.94 ms / 275 tokens ( 1.75 ms per token, 570.61 tokens per second) 3.45.585.927 I slot print_timing: id 0 | task 11699 | eval time = 2280.00 ms / 140 tokens ( 16.40 ms per token, 60.96 tokens per second) 3.45.585.928 I slot print_timing: id 0 | task 11699 | total time = 2761.94 ms / 415 tokens 3.45.585.928 I slot print_timing: id 0 | task 11699 | graphs reused = 11480 3.45.585.929 I slot print_timing: id 0 | task 11699 | graph reallocs = 0 / 0 (same size) / (changed size) 3.45.585.959 I slot release: id 0 | task 11699 | stop processing: n_tokens = 414, truncated = 0 3.45.589.825 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 341670665836 3.45.590.872 I slot launch_slot_: id 0 | task 11841 | processing task, is_child = 0 3.47.494.317 I slot print_timing: id 0 | task 11841 | prompt eval time = 486.37 ms / 287 tokens ( 1.69 ms per token, 590.08 tokens per second) 3.47.494.324 I slot print_timing: id 0 | task 11841 | eval time = 1417.06 ms / 86 tokens ( 16.67 ms per token, 59.98 tokens per second) 3.47.494.325 I slot print_timing: id 0 | task 11841 | total time = 1903.43 ms / 373 tokens 3.47.494.325 I slot print_timing: id 0 | task 11841 | graphs reused = 11564 3.47.494.326 I slot print_timing: id 0 | task 11841 | graph reallocs = 0 / 0 (same size) / (changed size) 3.47.494.355 I slot release: id 0 | task 11841 | stop processing: n_tokens = 372, truncated = 0 3.47.498.062 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 372, t_last = 341672574232 3.47.499.048 I slot launch_slot_: id 0 | task 11929 | processing task, is_child = 0 3.49.451.720 I slot print_timing: id 0 | task 11929 | prompt eval time = 476.12 ms / 266 tokens ( 1.79 ms per token, 558.69 tokens per second) 3.49.451.723 I slot print_timing: id 0 | task 11929 | eval time = 1476.54 ms / 91 tokens ( 16.41 ms per token, 60.95 tokens per second) 3.49.451.724 I slot print_timing: id 0 | task 11929 | total time = 1952.66 ms / 357 tokens 3.49.451.725 I slot print_timing: id 0 | task 11929 | graphs reused = 11653 3.49.451.725 I slot print_timing: id 0 | task 11929 | graph reallocs = 0 / 0 (same size) / (changed size) 3.49.451.753 I slot release: id 0 | task 11929 | stop processing: n_tokens = 356, truncated = 0 3.49.455.821 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 356, t_last = 341674531630 3.49.456.756 I slot launch_slot_: id 0 | task 12022 | processing task, is_child = 0 3.51.829.116 I slot print_timing: id 0 | task 12022 | prompt eval time = 642.16 ms / 435 tokens ( 1.48 ms per token, 677.40 tokens per second) 3.51.829.119 I slot print_timing: id 0 | task 12022 | eval time = 1730.19 ms / 106 tokens ( 16.48 ms per token, 60.69 tokens per second) 3.51.829.120 I slot print_timing: id 0 | task 12022 | total time = 2372.35 ms / 541 tokens 3.51.829.121 I slot print_timing: id 0 | task 12022 | graphs reused = 11756 3.51.829.121 I slot print_timing: id 0 | task 12022 | graph reallocs = 0 / 0 (same size) / (changed size) 3.51.829.159 I slot release: id 0 | task 12022 | stop processing: n_tokens = 540, truncated = 0 3.51.832.890 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 540, t_last = 341676909036 3.51.834.238 I slot launch_slot_: id 0 | task 12130 | processing task, is_child = 0 3.54.602.052 I slot print_timing: id 0 | task 12130 | prompt eval time = 509.26 ms / 307 tokens ( 1.66 ms per token, 602.83 tokens per second) 3.54.602.058 I slot print_timing: id 0 | task 12130 | eval time = 2258.54 ms / 138 tokens ( 16.49 ms per token, 60.66 tokens per second) 3.54.602.059 I slot print_timing: id 0 | task 12130 | total time = 2767.80 ms / 445 tokens 3.54.602.059 I slot print_timing: id 0 | task 12130 | graphs reused = 11892 3.54.602.060 I slot print_timing: id 0 | task 12130 | graph reallocs = 0 / 0 (same size) / (changed size) 3.54.602.089 I slot release: id 0 | task 12130 | stop processing: n_tokens = 444, truncated = 0 3.54.606.609 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 444, t_last = 341679681966 3.54.607.785 I slot launch_slot_: id 0 | task 12270 | processing task, is_child = 0 3.58.658.941 I slot print_timing: id 0 | task 12270 | n_gen = 184, tg = 60.93 t/s, tg_3s = 61.27 t/s 3.59.137.188 I slot print_timing: id 0 | task 12270 | prompt eval time = 1047.82 ms / 675 tokens ( 1.55 ms per token, 644.19 tokens per second) 3.59.137.194 I slot print_timing: id 0 | task 12270 | eval time = 3481.57 ms / 213 tokens ( 16.42 ms per token, 60.89 tokens per second) 3.59.137.195 I slot print_timing: id 0 | task 12270 | total time = 4529.39 ms / 888 tokens 3.59.137.196 I slot print_timing: id 0 | task 12270 | graphs reused = 12102 3.59.137.196 I slot print_timing: id 0 | task 12270 | graph reallocs = 0 / 0 (same size) / (changed size) 3.59.137.248 I slot release: id 0 | task 12270 | stop processing: n_tokens = 887, truncated = 0 3.59.140.825 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 887, t_last = 341684217125 3.59.142.750 I slot launch_slot_: id 0 | task 12486 | processing task, is_child = 0 4.01.715.279 I slot print_timing: id 0 | task 12486 | prompt eval time = 490.50 ms / 287 tokens ( 1.71 ms per token, 585.12 tokens per second) 4.01.715.285 I slot print_timing: id 0 | task 12486 | eval time = 2082.03 ms / 128 tokens ( 16.39 ms per token, 61.00 tokens per second) 4.01.715.286 I slot print_timing: id 0 | task 12486 | total time = 2572.52 ms / 415 tokens 4.01.715.286 I slot print_timing: id 0 | task 12486 | graphs reused = 12228 4.01.715.287 I slot print_timing: id 0 | task 12486 | graph reallocs = 0 / 0 (same size) / (changed size) 4.01.715.319 I slot release: id 0 | task 12486 | stop processing: n_tokens = 414, truncated = 0 4.01.719.528 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 341686795196 4.01.720.617 I slot launch_slot_: id 0 | task 12616 | processing task, is_child = 0 4.03.977.605 I slot print_timing: id 0 | task 12616 | prompt eval time = 708.88 ms / 497 tokens ( 1.43 ms per token, 701.10 tokens per second) 4.03.977.612 I slot print_timing: id 0 | task 12616 | eval time = 1548.10 ms / 95 tokens ( 16.47 ms per token, 60.72 tokens per second) 4.03.977.613 I slot print_timing: id 0 | task 12616 | total time = 2256.98 ms / 592 tokens 4.03.977.613 I slot print_timing: id 0 | task 12616 | graphs reused = 12320 4.03.977.614 I slot print_timing: id 0 | task 12616 | graph reallocs = 0 / 0 (same size) / (changed size) 4.03.977.657 I slot release: id 0 | task 12616 | stop processing: n_tokens = 591, truncated = 0 4.03.982.131 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 591, t_last = 341689057534 4.03.983.845 I slot launch_slot_: id 0 | task 12713 | processing task, is_child = 0 4.07.836.530 I slot print_timing: id 0 | task 12713 | prompt eval time = 980.07 ms / 609 tokens ( 1.61 ms per token, 621.39 tokens per second) 4.07.836.533 I slot print_timing: id 0 | task 12713 | eval time = 2872.61 ms / 175 tokens ( 16.51 ms per token, 60.57 tokens per second) 4.07.836.534 I slot print_timing: id 0 | task 12713 | total time = 3852.67 ms / 784 tokens 4.07.836.534 I slot print_timing: id 0 | task 12713 | graphs reused = 12492 4.07.836.535 I slot print_timing: id 0 | task 12713 | graph reallocs = 0 / 0 (same size) / (changed size) 4.07.836.581 I slot release: id 0 | task 12713 | stop processing: n_tokens = 783, truncated = 0 4.07.840.564 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 783, t_last = 341692916458 4.07.842.446 I slot launch_slot_: id 0 | task 12891 | processing task, is_child = 0 4.10.965.165 I slot print_timing: id 0 | task 12891 | prompt eval time = 619.27 ms / 415 tokens ( 1.49 ms per token, 670.14 tokens per second) 4.10.965.169 I slot print_timing: id 0 | task 12891 | eval time = 2503.44 ms / 153 tokens ( 16.47 ms per token, 60.72 tokens per second) 4.10.965.169 I slot print_timing: id 0 | task 12891 | total time = 3122.71 ms / 568 tokens 4.10.965.170 I slot print_timing: id 0 | task 12891 | graphs reused = 12642 4.10.965.171 I slot print_timing: id 0 | task 12891 | graph reallocs = 0 / 0 (same size) / (changed size) 4.10.965.215 I slot release: id 0 | task 12891 | stop processing: n_tokens = 567, truncated = 0 4.10.969.416 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 567, t_last = 341696045092 4.10.970.856 I slot launch_slot_: id 0 | task 13046 | processing task, is_child = 0 4.13.492.853 I slot print_timing: id 0 | task 13046 | prompt eval time = 502.80 ms / 295 tokens ( 1.70 ms per token, 586.72 tokens per second) 4.13.492.858 I slot print_timing: id 0 | task 13046 | eval time = 2019.19 ms / 124 tokens ( 16.42 ms per token, 60.92 tokens per second) 4.13.492.860 I slot print_timing: id 0 | task 13046 | total time = 2521.99 ms / 419 tokens 4.13.492.860 I slot print_timing: id 0 | task 13046 | graphs reused = 12764 4.13.492.861 I slot print_timing: id 0 | task 13046 | graph reallocs = 0 / 0 (same size) / (changed size) 4.13.492.892 I slot release: id 0 | task 13046 | stop processing: n_tokens = 418, truncated = 0 4.13.496.871 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 418, t_last = 341698572769 4.13.498.003 I slot launch_slot_: id 0 | task 13172 | processing task, is_child = 0 4.17.161.844 I slot print_timing: id 0 | task 13172 | n_gen = 184, tg = 60.74 t/s, tg_3s = 61.07 t/s 4.20.006.662 I slot print_timing: id 0 | task 13172 | prompt eval time = 651.02 ms / 442 tokens ( 1.47 ms per token, 678.93 tokens per second) 4.20.006.668 I slot print_timing: id 0 | task 13172 | eval time = 5857.62 ms / 357 tokens ( 16.45 ms per token, 60.78 tokens per second) 4.20.006.668 I slot print_timing: id 0 | task 13172 | total time = 6508.65 ms / 799 tokens 4.20.006.669 I slot print_timing: id 0 | task 13172 | graphs reused = 13117 4.20.006.669 I slot print_timing: id 0 | task 13172 | graph reallocs = 0 / 0 (same size) / (changed size) 4.20.006.709 I slot release: id 0 | task 13172 | stop processing: n_tokens = 798, truncated = 0 4.20.011.154 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 798, t_last = 341705086586 4.20.013.041 I slot launch_slot_: id 0 | task 13531 | processing task, is_child = 0 4.23.028.480 I slot print_timing: id 0 | task 13531 | prompt eval time = 1005.37 ms / 622 tokens ( 1.62 ms per token, 618.68 tokens per second) 4.23.028.486 I slot print_timing: id 0 | task 13531 | eval time = 2010.06 ms / 123 tokens ( 16.48 ms per token, 60.69 tokens per second) 4.23.028.486 I slot print_timing: id 0 | task 13531 | total time = 3015.43 ms / 745 tokens 4.23.028.487 I slot print_timing: id 0 | task 13531 | graphs reused = 13238 4.23.028.488 I slot print_timing: id 0 | task 13531 | graph reallocs = 0 / 0 (same size) / (changed size) 4.23.028.535 I slot release: id 0 | task 13531 | stop processing: n_tokens = 744, truncated = 0 4.23.032.461 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 744, t_last = 341708108412 4.23.034.745 I slot launch_slot_: id 0 | task 13657 | processing task, is_child = 0 4.25.418.196 I slot print_timing: id 0 | task 13657 | prompt eval time = 638.07 ms / 424 tokens ( 1.50 ms per token, 664.50 tokens per second) 4.25.418.202 I slot print_timing: id 0 | task 13657 | eval time = 1745.37 ms / 107 tokens ( 16.47 ms per token, 60.73 tokens per second) 4.25.418.203 I slot print_timing: id 0 | task 13657 | total time = 2383.44 ms / 531 tokens 4.25.418.204 I slot print_timing: id 0 | task 13657 | graphs reused = 13342 4.25.418.204 I slot print_timing: id 0 | task 13657 | graph reallocs = 0 / 0 (same size) / (changed size) 4.25.418.240 I slot release: id 0 | task 13657 | stop processing: n_tokens = 530, truncated = 0 4.25.422.228 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 530, t_last = 341710498117 4.25.422.796 I slot launch_slot_: id 0 | task 13766 | processing task, is_child = 0 4.29.040.754 I slot print_timing: id 0 | task 13766 | n_gen = 184, tg = 60.81 t/s, tg_3s = 61.14 t/s 4.32.044.542 I slot print_timing: id 0 | task 13766 | n_gen = 367, tg = 60.87 t/s, tg_3s = 60.92 t/s 4.32.308.923 I slot print_timing: id 0 | task 13766 | prompt eval time = 608.67 ms / 395 tokens ( 1.54 ms per token, 648.96 tokens per second) 4.32.308.928 I slot print_timing: id 0 | task 13766 | eval time = 6277.45 ms / 383 tokens ( 16.43 ms per token, 60.85 tokens per second) 4.32.308.929 I slot print_timing: id 0 | task 13766 | total time = 6886.12 ms / 778 tokens 4.32.308.930 I slot print_timing: id 0 | task 13766 | graphs reused = 13721 4.32.308.930 I slot print_timing: id 0 | task 13766 | graph reallocs = 0 / 0 (same size) / (changed size) 4.32.308.965 I slot release: id 0 | task 13766 | stop processing: n_tokens = 777, truncated = 0 4.32.312.719 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 777, t_last = 341717388842 4.32.314.724 I slot launch_slot_: id 0 | task 14151 | processing task, is_child = 0 4.34.553.132 I slot print_timing: id 0 | task 14151 | prompt eval time = 482.65 ms / 279 tokens ( 1.73 ms per token, 578.06 tokens per second) 4.34.553.136 I slot print_timing: id 0 | task 14151 | eval time = 1755.75 ms / 108 tokens ( 16.41 ms per token, 60.94 tokens per second) 4.34.553.137 I slot print_timing: id 0 | task 14151 | total time = 2238.40 ms / 387 tokens 4.34.553.137 I slot print_timing: id 0 | task 14151 | graphs reused = 13827 4.34.553.138 I slot print_timing: id 0 | task 14151 | graph reallocs = 0 / 0 (same size) / (changed size) 4.34.553.165 I slot release: id 0 | task 14151 | stop processing: n_tokens = 386, truncated = 0 4.34.556.903 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 386, t_last = 341719633042 4.34.557.930 I slot launch_slot_: id 0 | task 14261 | processing task, is_child = 0 4.38.091.824 I slot print_timing: id 0 | task 14261 | n_gen = 184, tg = 60.72 t/s, tg_3s = 61.05 t/s 4.38.460.702 I slot print_timing: id 0 | task 14261 | prompt eval time = 520.12 ms / 319 tokens ( 1.63 ms per token, 613.32 tokens per second) 4.38.460.706 I slot print_timing: id 0 | task 14261 | eval time = 3382.64 ms / 206 tokens ( 16.50 ms per token, 60.60 tokens per second) 4.38.460.707 I slot print_timing: id 0 | task 14261 | total time = 3902.76 ms / 525 tokens 4.38.460.707 I slot print_timing: id 0 | task 14261 | graphs reused = 14030 4.38.460.708 I slot print_timing: id 0 | task 14261 | graph reallocs = 0 / 0 (same size) / (changed size) 4.38.460.741 I slot release: id 0 | task 14261 | stop processing: n_tokens = 524, truncated = 0 4.38.464.714 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 524, t_last = 341723540618 4.38.466.072 I slot launch_slot_: id 0 | task 14469 | processing task, is_child = 0 4.40.972.792 I slot print_timing: id 0 | task 14469 | prompt eval time = 547.73 ms / 345 tokens ( 1.59 ms per token, 629.88 tokens per second) 4.40.972.797 I slot print_timing: id 0 | task 14469 | eval time = 1958.98 ms / 120 tokens ( 16.46 ms per token, 60.75 tokens per second) 4.40.972.799 I slot print_timing: id 0 | task 14469 | total time = 2506.70 ms / 465 tokens 4.40.972.799 I slot print_timing: id 0 | task 14469 | graphs reused = 14148 4.40.972.800 I slot print_timing: id 0 | task 14469 | graph reallocs = 0 / 0 (same size) / (changed size) 4.40.972.835 I slot release: id 0 | task 14469 | stop processing: n_tokens = 464, truncated = 0 4.40.977.054 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 464, t_last = 341726052712 4.40.978.287 I slot launch_slot_: id 0 | task 14591 | processing task, is_child = 0 4.44.661.539 I slot print_timing: id 0 | task 14591 | n_gen = 184, tg = 60.85 t/s, tg_3s = 61.18 t/s 4.45.174.358 I slot print_timing: id 0 | task 14591 | prompt eval time = 675.63 ms / 464 tokens ( 1.46 ms per token, 686.77 tokens per second) 4.45.174.361 I slot print_timing: id 0 | task 14591 | eval time = 3520.44 ms / 215 tokens ( 16.45 ms per token, 60.79 tokens per second) 4.45.174.362 I slot print_timing: id 0 | task 14591 | total time = 4196.06 ms / 679 tokens 4.45.174.362 I slot print_timing: id 0 | task 14591 | graphs reused = 14360 4.45.174.363 I slot print_timing: id 0 | task 14591 | graph reallocs = 0 / 0 (same size) / (changed size) 4.45.174.402 I slot release: id 0 | task 14591 | stop processing: n_tokens = 678, truncated = 0 4.45.178.452 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 678, t_last = 341730254279 4.45.180.203 I slot launch_slot_: id 0 | task 14808 | processing task, is_child = 0 4.47.444.937 I slot print_timing: id 0 | task 14808 | prompt eval time = 607.33 ms / 398 tokens ( 1.53 ms per token, 655.32 tokens per second) 4.47.444.940 I slot print_timing: id 0 | task 14808 | eval time = 1657.38 ms / 102 tokens ( 16.41 ms per token, 60.94 tokens per second) 4.47.444.941 I slot print_timing: id 0 | task 14808 | total time = 2264.72 ms / 500 tokens 4.47.444.941 I slot print_timing: id 0 | task 14808 | graphs reused = 14460 4.47.444.942 I slot print_timing: id 0 | task 14808 | graph reallocs = 0 / 0 (same size) / (changed size) 4.47.444.976 I slot release: id 0 | task 14808 | stop processing: n_tokens = 499, truncated = 0 4.47.449.706 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 499, t_last = 341732524853 4.47.451.001 I slot launch_slot_: id 0 | task 14912 | processing task, is_child = 0 4.50.228.043 I slot print_timing: id 0 | task 14912 | prompt eval time = 1008.86 ms / 628 tokens ( 1.61 ms per token, 622.49 tokens per second) 4.50.228.049 I slot print_timing: id 0 | task 14912 | eval time = 1768.18 ms / 108 tokens ( 16.53 ms per token, 60.51 tokens per second) 4.50.228.050 I slot print_timing: id 0 | task 14912 | total time = 2777.03 ms / 736 tokens 4.50.228.050 I slot print_timing: id 0 | task 14912 | graphs reused = 14566 4.50.228.051 I slot print_timing: id 0 | task 14912 | graph reallocs = 0 / 0 (same size) / (changed size) 4.50.228.097 I slot release: id 0 | task 14912 | stop processing: n_tokens = 735, truncated = 0 4.50.232.147 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 735, t_last = 341735307974 4.50.233.806 I slot launch_slot_: id 0 | task 15023 | processing task, is_child = 0 4.53.096.920 I slot print_timing: id 0 | task 15023 | prompt eval time = 612.10 ms / 404 tokens ( 1.52 ms per token, 660.03 tokens per second) 4.53.096.926 I slot print_timing: id 0 | task 15023 | eval time = 2251.01 ms / 138 tokens ( 16.43 ms per token, 60.86 tokens per second) 4.53.096.927 I slot print_timing: id 0 | task 15023 | total time = 2863.10 ms / 542 tokens 4.53.096.928 I slot print_timing: id 0 | task 15023 | graphs reused = 14701 4.53.096.928 I slot print_timing: id 0 | task 15023 | graph reallocs = 0 / 0 (same size) / (changed size) 4.53.096.966 I slot release: id 0 | task 15023 | stop processing: n_tokens = 541, truncated = 0 4.53.100.925 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 541, t_last = 341738176843 4.53.102.217 I slot launch_slot_: id 0 | task 15163 | processing task, is_child = 0 4.56.754.901 I slot print_timing: id 0 | task 15163 | n_gen = 184, tg = 60.94 t/s, tg_3s = 61.27 t/s 4.58.529.396 I slot print_timing: id 0 | task 15163 | prompt eval time = 649.57 ms / 445 tokens ( 1.46 ms per token, 685.07 tokens per second) 4.58.529.399 I slot print_timing: id 0 | task 15163 | eval time = 4777.60 ms / 292 tokens ( 16.42 ms per token, 60.91 tokens per second) 4.58.529.400 I slot print_timing: id 0 | task 15163 | total time = 5427.17 ms / 737 tokens 4.58.529.400 I slot print_timing: id 0 | task 15163 | graphs reused = 14990 4.58.529.401 I slot print_timing: id 0 | task 15163 | graph reallocs = 0 / 0 (same size) / (changed size) 4.58.529.441 I slot release: id 0 | task 15163 | stop processing: n_tokens = 736, truncated = 0 4.58.533.683 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 736, t_last = 341743609318 4.58.535.405 I slot launch_slot_: id 0 | task 15457 | processing task, is_child = 0 5.01.879.933 I slot print_timing: id 0 | task 15457 | prompt eval time = 617.85 ms / 412 tokens ( 1.50 ms per token, 666.83 tokens per second) 5.01.879.939 I slot print_timing: id 0 | task 15457 | eval time = 2726.67 ms / 165 tokens ( 16.63 ms per token, 60.15 tokens per second) 5.01.879.940 I slot print_timing: id 0 | task 15457 | total time = 3344.52 ms / 577 tokens 5.01.879.940 I slot print_timing: id 0 | task 15457 | graphs reused = 15152 5.01.879.941 I slot print_timing: id 0 | task 15457 | graph reallocs = 0 / 0 (same size) / (changed size) 5.01.879.977 I slot release: id 0 | task 15457 | stop processing: n_tokens = 576, truncated = 0 5.01.884.445 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 576, t_last = 341746959854 5.01.885.887 I slot launch_slot_: id 0 | task 15624 | processing task, is_child = 0 5.04.097.270 I slot print_timing: id 0 | task 15624 | prompt eval time = 912.82 ms / 542 tokens ( 1.68 ms per token, 593.77 tokens per second) 5.04.097.276 I slot print_timing: id 0 | task 15624 | eval time = 1298.56 ms / 80 tokens ( 16.44 ms per token, 60.84 tokens per second) 5.04.097.278 I slot print_timing: id 0 | task 15624 | total time = 2211.38 ms / 622 tokens 5.04.097.278 I slot print_timing: id 0 | task 15624 | graphs reused = 15230 5.04.097.279 I slot print_timing: id 0 | task 15624 | graph reallocs = 0 / 0 (same size) / (changed size) 5.04.097.321 I slot release: id 0 | task 15624 | stop processing: n_tokens = 621, truncated = 0 5.04.101.773 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 621, t_last = 341749177198 5.04.103.367 I slot launch_slot_: id 0 | task 15707 | processing task, is_child = 0 5.07.989.517 I slot print_timing: id 0 | task 15707 | prompt eval time = 1001.82 ms / 628 tokens ( 1.60 ms per token, 626.86 tokens per second) 5.07.989.523 I slot print_timing: id 0 | task 15707 | eval time = 2884.33 ms / 176 tokens ( 16.48 ms per token, 60.67 tokens per second) 5.07.989.524 I slot print_timing: id 0 | task 15707 | total time = 3886.14 ms / 804 tokens 5.07.989.524 I slot print_timing: id 0 | task 15707 | graphs reused = 15403 5.07.989.525 I slot print_timing: id 0 | task 15707 | graph reallocs = 0 / 0 (same size) / (changed size) 5.07.989.573 I slot release: id 0 | task 15707 | stop processing: n_tokens = 803, truncated = 0 5.07.993.117 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 5.07.994.941 I slot launch_slot_: id 0 | task 15886 | processing task, is_child = 0 5.10.967.644 I slot print_timing: id 0 | task 15886 | prompt eval time = 403.71 ms / 197 tokens ( 2.05 ms per token, 487.98 tokens per second) 5.10.967.651 I slot print_timing: id 0 | task 15886 | eval time = 2568.99 ms / 157 tokens ( 16.47 ms per token, 60.72 tokens per second) 5.10.967.651 I slot print_timing: id 0 | task 15886 | total time = 2972.69 ms / 354 tokens 5.10.967.652 I slot print_timing: id 0 | task 15886 | graphs reused = 15557 5.10.967.652 I slot print_timing: id 0 | task 15886 | graph reallocs = 0 / 0 (same size) / (changed size) 5.10.967.675 I slot release: id 0 | task 15886 | stop processing: n_tokens = 353, truncated = 0 5.10.971.224 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 353, t_last = 341756047552 5.10.972.084 I slot launch_slot_: id 0 | task 16045 | processing task, is_child = 0 5.13.701.007 I slot print_timing: id 0 | task 16045 | prompt eval time = 417.08 ms / 217 tokens ( 1.92 ms per token, 520.29 tokens per second) 5.13.701.013 I slot print_timing: id 0 | task 16045 | eval time = 2311.83 ms / 142 tokens ( 16.40 ms per token, 60.99 tokens per second) 5.13.701.013 I slot print_timing: id 0 | task 16045 | total time = 2728.91 ms / 359 tokens 5.13.701.014 I slot print_timing: id 0 | task 16045 | graphs reused = 15696 5.13.701.015 I slot print_timing: id 0 | task 16045 | graph reallocs = 0 / 0 (same size) / (changed size) 5.13.701.040 I slot release: id 0 | task 16045 | stop processing: n_tokens = 358, truncated = 0 5.13.704.490 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.105 (> 0.100 thold), f_keep = 0.059 5.13.705.408 I slot launch_slot_: id 0 | task 16189 | processing task, is_child = 0 5.17.121.074 I slot print_timing: id 0 | task 16189 | n_gen = 184, tg = 60.88 t/s, tg_3s = 61.21 t/s 5.18.975.891 I slot print_timing: id 0 | task 16189 | prompt eval time = 409.83 ms / 200 tokens ( 2.05 ms per token, 488.00 tokens per second) 5.18.975.897 I slot print_timing: id 0 | task 16189 | eval time = 4860.64 ms / 297 tokens ( 16.42 ms per token, 60.90 tokens per second) 5.18.975.898 I slot print_timing: id 0 | task 16189 | total time = 5270.47 ms / 497 tokens 5.18.975.899 I slot print_timing: id 0 | task 16189 | graphs reused = 15990 5.18.975.899 I slot print_timing: id 0 | task 16189 | graph reallocs = 0 / 0 (same size) / (changed size) 5.18.975.927 I slot release: id 0 | task 16189 | stop processing: n_tokens = 496, truncated = 0 5.18.979.460 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.124 (> 0.100 thold), f_keep = 0.042 5.18.980.657 I slot launch_slot_: id 0 | task 16488 | processing task, is_child = 0 5.22.362.864 I slot print_timing: id 0 | task 16488 | n_gen = 184, tg = 60.94 t/s, tg_3s = 61.27 t/s 5.22.511.123 I slot print_timing: id 0 | task 16488 | prompt eval time = 379.08 ms / 170 tokens ( 2.23 ms per token, 448.45 tokens per second) 5.22.511.130 I slot print_timing: id 0 | task 16488 | eval time = 3151.37 ms / 193 tokens ( 16.41 ms per token, 60.93 tokens per second) 5.22.511.130 I slot print_timing: id 0 | task 16488 | total time = 3530.46 ms / 363 tokens 5.22.511.131 I slot print_timing: id 0 | task 16488 | graphs reused = 16180 5.22.511.132 I slot print_timing: id 0 | task 16488 | graph reallocs = 0 / 0 (same size) / (changed size) 5.22.511.155 I slot release: id 0 | task 16488 | stop processing: n_tokens = 362, truncated = 0 5.22.514.724 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 362, t_last = 341767591032 5.22.515.740 I slot launch_slot_: id 0 | task 16683 | processing task, is_child = 0 5.25.978.313 I slot print_timing: id 0 | task 16683 | n_gen = 185, tg = 61.01 t/s, tg_3s = 61.34 t/s 5.28.980.997 I slot print_timing: id 0 | task 16683 | n_gen = 368, tg = 60.98 t/s, tg_3s = 60.95 t/s 5.31.987.670 I slot print_timing: id 0 | task 16683 | n_gen = 551, tg = 60.94 t/s, tg_3s = 60.86 t/s 5.35.000.800 I slot print_timing: id 0 | task 16683 | n_gen = 734, tg = 60.89 t/s, tg_3s = 60.73 t/s 5.38.004.506 I slot print_timing: id 0 | task 16683 | n_gen = 916, tg = 60.83 t/s, tg_3s = 60.59 t/s 5.39.784.639 I slot print_timing: id 0 | task 16683 | prompt eval time = 446.61 ms / 241 tokens ( 1.85 ms per token, 539.62 tokens per second) 5.39.784.644 I slot print_timing: id 0 | task 16683 | eval time = 16822.28 ms / 1024 tokens ( 16.44 ms per token, 60.81 tokens per second) 5.39.784.645 I slot print_timing: id 0 | task 16683 | total time = 17268.89 ms / 1265 tokens 5.39.784.645 I slot print_timing: id 0 | task 16683 | graphs reused = 17198 5.39.784.646 I slot print_timing: id 0 | task 16683 | graph reallocs = 0 / 0 (same size) / (changed size) 5.39.784.673 I slot release: id 0 | task 16683 | stop processing: n_tokens = 1264, truncated = 0 5.39.788.280 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1264, t_last = 341784864550 5.39.791.166 I slot launch_slot_: id 0 | task 17709 | processing task, is_child = 0 5.43.242.814 I slot print_timing: id 0 | task 17709 | n_gen = 185, tg = 61.21 t/s, tg_3s = 61.54 t/s 5.44.682.398 I slot print_timing: id 0 | task 17709 | prompt eval time = 445.65 ms / 237 tokens ( 1.88 ms per token, 531.81 tokens per second) 5.44.682.405 I slot print_timing: id 0 | task 17709 | eval time = 4445.57 ms / 273 tokens ( 16.34 ms per token, 61.18 tokens per second) 5.44.682.406 I slot print_timing: id 0 | task 17709 | total time = 4891.22 ms / 510 tokens 5.44.682.406 I slot print_timing: id 0 | task 17709 | graphs reused = 17468 5.44.682.407 I slot print_timing: id 0 | task 17709 | graph reallocs = 0 / 0 (same size) / (changed size) 5.44.682.432 I slot release: id 0 | task 17709 | stop processing: n_tokens = 509, truncated = 0 5.44.686.049 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 509, t_last = 341789762310 5.44.687.311 I slot launch_slot_: id 0 | task 17984 | processing task, is_child = 0 5.48.221.094 I slot print_timing: id 0 | task 17984 | n_gen = 185, tg = 61.04 t/s, tg_3s = 61.37 t/s 5.51.221.553 I slot print_timing: id 0 | task 17984 | n_gen = 368, tg = 61.02 t/s, tg_3s = 60.99 t/s 5.51.417.710 I slot print_timing: id 0 | task 17984 | prompt eval time = 519.48 ms / 322 tokens ( 1.61 ms per token, 619.85 tokens per second) 5.51.417.713 I slot print_timing: id 0 | task 17984 | eval time = 6210.90 ms / 380 tokens ( 16.39 ms per token, 61.02 tokens per second) 5.51.417.715 I slot print_timing: id 0 | task 17984 | total time = 6730.39 ms / 702 tokens 5.51.417.716 I slot print_timing: id 0 | task 17984 | graphs reused = 17845 5.51.417.716 I slot print_timing: id 0 | task 17984 | graph reallocs = 0 / 0 (same size) / (changed size) 5.51.417.749 I slot release: id 0 | task 17984 | stop processing: n_tokens = 701, truncated = 0 5.51.421.248 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.120 (> 0.100 thold), f_keep = 0.030 5.51.422.992 I slot launch_slot_: id 0 | task 18366 | processing task, is_child = 0 5.54.806.062 I slot print_timing: id 0 | task 18366 | n_gen = 181, tg = 59.98 t/s, tg_3s = 60.31 t/s 5.56.392.082 I slot print_timing: id 0 | task 18366 | prompt eval time = 381.91 ms / 175 tokens ( 2.18 ms per token, 458.23 tokens per second) 5.56.392.088 I slot print_timing: id 0 | task 18366 | eval time = 4587.17 ms / 278 tokens ( 16.56 ms per token, 60.39 tokens per second) 5.56.392.089 I slot print_timing: id 0 | task 18366 | total time = 4969.08 ms / 453 tokens 5.56.392.089 I slot print_timing: id 0 | task 18366 | graphs reused = 18120 5.56.392.090 I slot print_timing: id 0 | task 18366 | graph reallocs = 0 / 0 (same size) / (changed size) 5.56.392.116 I slot release: id 0 | task 18366 | stop processing: n_tokens = 452, truncated = 0 5.56.395.713 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.117 (> 0.100 thold), f_keep = 0.046 5.56.396.914 I slot launch_slot_: id 0 | task 18646 | processing task, is_child = 0 5.59.798.728 I slot print_timing: id 0 | task 18646 | n_gen = 184, tg = 60.71 t/s, tg_3s = 61.04 t/s 6.00.648.943 I slot print_timing: id 0 | task 18646 | prompt eval time = 387.60 ms / 179 tokens ( 2.17 ms per token, 461.82 tokens per second) 6.00.648.946 I slot print_timing: id 0 | task 18646 | eval time = 3864.42 ms / 236 tokens ( 16.44 ms per token, 60.81 tokens per second) 6.00.648.946 I slot print_timing: id 0 | task 18646 | total time = 4252.01 ms / 415 tokens 6.00.648.947 I slot print_timing: id 0 | task 18646 | graphs reused = 18353 6.00.648.948 I slot print_timing: id 0 | task 18646 | graph reallocs = 0 / 0 (same size) / (changed size) 6.00.648.969 I slot release: id 0 | task 18646 | stop processing: n_tokens = 414, truncated = 0 6.00.652.410 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 341805728846 6.00.653.783 I slot launch_slot_: id 0 | task 18884 | processing task, is_child = 0 6.04.111.258 I slot print_timing: id 0 | task 18884 | n_gen = 185, tg = 61.01 t/s, tg_3s = 61.35 t/s 6.05.176.304 I slot print_timing: id 0 | task 18884 | prompt eval time = 441.81 ms / 237 tokens ( 1.86 ms per token, 536.42 tokens per second) 6.05.176.309 I slot print_timing: id 0 | task 18884 | eval time = 4080.70 ms / 250 tokens ( 16.39 ms per token, 61.02 tokens per second) 6.05.176.310 I slot print_timing: id 0 | task 18884 | total time = 4522.51 ms / 487 tokens 6.05.176.311 I slot print_timing: id 0 | task 18884 | graphs reused = 18600 6.05.176.311 I slot print_timing: id 0 | task 18884 | graph reallocs = 0 / 0 (same size) / (changed size) 6.05.176.336 I slot release: id 0 | task 18884 | stop processing: n_tokens = 486, truncated = 0 6.05.179.846 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 486, t_last = 341810256213 6.05.181.035 I slot launch_slot_: id 0 | task 19136 | processing task, is_child = 0 6.08.675.889 I slot print_timing: id 0 | task 19136 | n_gen = 184, tg = 60.83 t/s, tg_3s = 61.16 t/s 6.10.864.614 I slot print_timing: id 0 | task 19136 | prompt eval time = 486.50 ms / 287 tokens ( 1.70 ms per token, 589.93 tokens per second) 6.10.864.622 I slot print_timing: id 0 | task 19136 | eval time = 5197.07 ms / 317 tokens ( 16.45 ms per token, 60.80 tokens per second) 6.10.864.622 I slot print_timing: id 0 | task 19136 | total time = 5683.57 ms / 604 tokens 6.10.864.623 I slot print_timing: id 0 | task 19136 | graphs reused = 18914 6.10.864.624 I slot print_timing: id 0 | task 19136 | graph reallocs = 0 / 0 (same size) / (changed size) 6.10.864.655 I slot release: id 0 | task 19136 | stop processing: n_tokens = 603, truncated = 0 6.10.868.270 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.148 (> 0.100 thold), f_keep = 0.060 6.10.869.733 I slot launch_slot_: id 0 | task 19455 | processing task, is_child = 0 6.14.329.698 I slot print_timing: id 0 | task 19455 | n_gen = 184, tg = 60.76 t/s, tg_3s = 61.09 t/s 6.15.302.014 I slot print_timing: id 0 | task 19455 | prompt eval time = 448.00 ms / 243 tokens ( 1.84 ms per token, 542.41 tokens per second) 6.15.302.020 I slot print_timing: id 0 | task 19455 | eval time = 3984.27 ms / 243 tokens ( 16.46 ms per token, 60.74 tokens per second) 6.15.302.020 I slot print_timing: id 0 | task 19455 | total time = 4432.27 ms / 486 tokens 6.15.302.021 I slot print_timing: id 0 | task 19455 | graphs reused = 19154 6.15.302.022 I slot print_timing: id 0 | task 19455 | graph reallocs = 0 / 0 (same size) / (changed size) 6.15.302.051 I slot release: id 0 | task 19455 | stop processing: n_tokens = 485, truncated = 0 6.15.305.642 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 485, t_last = 341820381928 6.15.306.840 I slot launch_slot_: id 0 | task 19700 | processing task, is_child = 0 6.18.768.555 I slot print_timing: id 0 | task 19700 | n_gen = 185, tg = 61.09 t/s, tg_3s = 61.43 t/s 6.20.973.007 I slot print_timing: id 0 | task 19700 | prompt eval time = 449.99 ms / 243 tokens ( 1.85 ms per token, 540.01 tokens per second) 6.20.973.013 I slot print_timing: id 0 | task 19700 | eval time = 5216.17 ms / 319 tokens ( 16.40 ms per token, 60.96 tokens per second) 6.20.973.014 I slot print_timing: id 0 | task 19700 | total time = 5666.16 ms / 562 tokens 6.20.973.015 I slot print_timing: id 0 | task 19700 | graphs reused = 19469 6.20.973.016 I slot print_timing: id 0 | task 19700 | graph reallocs = 0 / 0 (same size) / (changed size) 6.20.973.045 I slot release: id 0 | task 19700 | stop processing: n_tokens = 561, truncated = 0 6.20.976.623 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 561, t_last = 341826052922 6.20.977.964 I slot launch_slot_: id 0 | task 20021 | processing task, is_child = 0 6.24.446.921 I slot print_timing: id 0 | task 20021 | n_gen = 184, tg = 60.99 t/s, tg_3s = 61.32 t/s 6.25.053.554 I slot print_timing: id 0 | task 20021 | prompt eval time = 468.23 ms / 262 tokens ( 1.79 ms per token, 559.56 tokens per second) 6.25.053.561 I slot print_timing: id 0 | task 20021 | eval time = 3607.36 ms / 221 tokens ( 16.40 ms per token, 60.99 tokens per second) 6.25.053.561 I slot print_timing: id 0 | task 20021 | total time = 4075.58 ms / 483 tokens 6.25.053.562 I slot print_timing: id 0 | task 20021 | graphs reused = 19688 6.25.053.563 I slot print_timing: id 0 | task 20021 | graph reallocs = 0 / 0 (same size) / (changed size) 6.25.053.594 I slot release: id 0 | task 20021 | stop processing: n_tokens = 482, truncated = 0 6.25.056.990 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.102 (> 0.100 thold), f_keep = 0.044 6.25.058.166 I slot launch_slot_: id 0 | task 20244 | processing task, is_child = 0 6.27.740.793 I slot print_timing: id 0 | task 20244 | prompt eval time = 411.16 ms / 205 tokens ( 2.01 ms per token, 498.59 tokens per second) 6.27.740.800 I slot print_timing: id 0 | task 20244 | eval time = 2271.46 ms / 139 tokens ( 16.46 ms per token, 60.75 tokens per second) 6.27.740.800 I slot print_timing: id 0 | task 20244 | total time = 2682.62 ms / 344 tokens 6.27.740.801 I slot print_timing: id 0 | task 20244 | graphs reused = 19824 6.27.740.801 I slot print_timing: id 0 | task 20244 | graph reallocs = 0 / 0 (same size) / (changed size) 6.27.740.827 I slot release: id 0 | task 20244 | stop processing: n_tokens = 343, truncated = 0 6.27.745.598 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 343, t_last = 341832820704 6.27.746.469 I slot launch_slot_: id 0 | task 20385 | processing task, is_child = 0 6.31.228.542 I slot print_timing: id 0 | task 20385 | n_gen = 184, tg = 60.97 t/s, tg_3s = 61.30 t/s 6.31.684.739 I slot print_timing: id 0 | task 20385 | prompt eval time = 480.46 ms / 279 tokens ( 1.72 ms per token, 580.69 tokens per second) 6.31.684.744 I slot print_timing: id 0 | task 20385 | eval time = 3457.80 ms / 212 tokens ( 16.39 ms per token, 61.02 tokens per second) 6.31.684.745 I slot print_timing: id 0 | task 20385 | total time = 3938.26 ms / 491 tokens 6.31.684.746 I slot print_timing: id 0 | task 20385 | graphs reused = 20034 6.31.684.746 I slot print_timing: id 0 | task 20385 | graph reallocs = 0 / 0 (same size) / (changed size) 6.31.684.774 I slot release: id 0 | task 20385 | stop processing: n_tokens = 490, truncated = 0 6.31.688.351 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.108 (> 0.100 thold), f_keep = 0.043 6.31.689.627 I slot launch_slot_: id 0 | task 20599 | processing task, is_child = 0 6.35.085.356 I slot print_timing: id 0 | task 20599 | n_gen = 184, tg = 60.94 t/s, tg_3s = 61.28 t/s 6.37.904.471 I slot print_timing: id 0 | task 20599 | prompt eval time = 392.98 ms / 194 tokens ( 2.03 ms per token, 493.66 tokens per second) 6.37.904.477 I slot print_timing: id 0 | task 20599 | eval time = 5821.85 ms / 356 tokens ( 16.40 ms per token, 60.98 tokens per second) 6.37.904.478 I slot print_timing: id 0 | task 20599 | total time = 6214.84 ms / 550 tokens 6.37.904.479 I slot print_timing: id 0 | task 20599 | graphs reused = 20386 6.37.904.480 I slot print_timing: id 0 | task 20599 | graph reallocs = 0 / 0 (same size) / (changed size) 6.37.904.505 I slot release: id 0 | task 20599 | stop processing: n_tokens = 549, truncated = 0 6.37.908.036 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.124 (> 0.100 thold), f_keep = 0.038 6.37.909.368 I slot launch_slot_: id 0 | task 20957 | processing task, is_child = 0 6.40.769.647 I slot print_timing: id 0 | task 20957 | prompt eval time = 379.48 ms / 169 tokens ( 2.25 ms per token, 445.35 tokens per second) 6.40.769.651 I slot print_timing: id 0 | task 20957 | eval time = 2480.79 ms / 151 tokens ( 16.54 ms per token, 60.46 tokens per second) 6.40.769.651 I slot print_timing: id 0 | task 20957 | total time = 2860.27 ms / 320 tokens 6.40.769.652 I slot print_timing: id 0 | task 20957 | graphs reused = 20534 6.40.769.652 I slot print_timing: id 0 | task 20957 | graph reallocs = 0 / 0 (same size) / (changed size) 6.40.769.674 I slot release: id 0 | task 20957 | stop processing: n_tokens = 319, truncated = 0 6.40.773.347 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 319, t_last = 341845849551 6.40.774.126 I slot launch_slot_: id 0 | task 21110 | processing task, is_child = 0 6.44.245.760 I slot print_timing: id 0 | task 21110 | n_gen = 184, tg = 60.96 t/s, tg_3s = 61.30 t/s 6.45.657.486 I slot print_timing: id 0 | task 21110 | prompt eval time = 469.86 ms / 263 tokens ( 1.79 ms per token, 559.74 tokens per second) 6.45.657.493 I slot print_timing: id 0 | task 21110 | eval time = 4413.49 ms / 270 tokens ( 16.41 ms per token, 60.95 tokens per second) 6.45.657.493 I slot print_timing: id 0 | task 21110 | total time = 4883.35 ms / 533 tokens 6.45.657.494 I slot print_timing: id 0 | task 21110 | graphs reused = 20801 6.45.657.495 I slot print_timing: id 0 | task 21110 | graph reallocs = 0 / 0 (same size) / (changed size) 6.45.657.522 I slot release: id 0 | task 21110 | stop processing: n_tokens = 532, truncated = 0 6.45.661.093 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.103 (> 0.100 thold), f_keep = 0.039 6.45.662.378 I slot launch_slot_: id 0 | task 21382 | processing task, is_child = 0 6.49.079.106 I slot print_timing: id 0 | task 21382 | n_gen = 184, tg = 60.88 t/s, tg_3s = 61.22 t/s 6.49.390.263 I slot print_timing: id 0 | task 21382 | prompt eval time = 411.02 ms / 204 tokens ( 2.01 ms per token, 496.33 tokens per second) 6.49.390.266 I slot print_timing: id 0 | task 21382 | eval time = 3316.85 ms / 203 tokens ( 16.42 ms per token, 60.90 tokens per second) 6.49.390.266 I slot print_timing: id 0 | task 21382 | total time = 3727.87 ms / 407 tokens 6.49.390.267 I slot print_timing: id 0 | task 21382 | graphs reused = 21001 6.49.390.268 I slot print_timing: id 0 | task 21382 | graph reallocs = 0 / 0 (same size) / (changed size) 6.49.390.296 I slot release: id 0 | task 21382 | stop processing: n_tokens = 406, truncated = 0 6.49.393.736 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 406, t_last = 341854470173 6.49.394.771 I slot launch_slot_: id 0 | task 21587 | processing task, is_child = 0 6.52.887.085 I slot print_timing: id 0 | task 21587 | n_gen = 185, tg = 61.02 t/s, tg_3s = 61.35 t/s 6.55.887.989 I slot print_timing: id 0 | task 21587 | n_gen = 368, tg = 61.00 t/s, tg_3s = 60.98 t/s 6.58.341.584 I slot print_timing: id 0 | task 21587 | prompt eval time = 476.93 ms / 272 tokens ( 1.75 ms per token, 570.32 tokens per second) 6.58.341.587 I slot print_timing: id 0 | task 21587 | eval time = 8469.87 ms / 517 tokens ( 16.41 ms per token, 60.92 tokens per second) 6.58.341.588 I slot print_timing: id 0 | task 21587 | total time = 8946.80 ms / 789 tokens 6.58.341.589 I slot print_timing: id 0 | task 21587 | graphs reused = 21514 6.58.341.589 I slot print_timing: id 0 | task 21587 | graph reallocs = 0 / 0 (same size) / (changed size) 6.58.341.618 I slot release: id 0 | task 21587 | stop processing: n_tokens = 788, truncated = 0 6.58.345.283 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 788, t_last = 341863421495 6.58.347.024 I slot launch_slot_: id 0 | task 22106 | processing task, is_child = 0 7.01.576.183 I slot print_timing: id 0 | task 22106 | prompt eval time = 440.18 ms / 231 tokens ( 1.91 ms per token, 524.79 tokens per second) 7.01.576.189 I slot print_timing: id 0 | task 22106 | eval time = 2788.97 ms / 171 tokens ( 16.41 ms per token, 60.95 tokens per second) 7.01.576.190 I slot print_timing: id 0 | task 22106 | total time = 3229.15 ms / 402 tokens 7.01.576.190 I slot print_timing: id 0 | task 22106 | graphs reused = 21682 7.01.576.191 I slot print_timing: id 0 | task 22106 | graph reallocs = 0 / 0 (same size) / (changed size) 7.01.576.219 I slot release: id 0 | task 22106 | stop processing: n_tokens = 401, truncated = 0 7.01.579.802 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 401, t_last = 341866656096 7.01.580.799 I slot launch_slot_: id 0 | task 22279 | processing task, is_child = 0 7.05.072.163 I slot print_timing: id 0 | task 22279 | n_gen = 184, tg = 60.97 t/s, tg_3s = 61.30 t/s 7.05.814.490 I slot print_timing: id 0 | task 22279 | prompt eval time = 489.87 ms / 291 tokens ( 1.68 ms per token, 594.04 tokens per second) 7.05.814.496 I slot print_timing: id 0 | task 22279 | eval time = 3743.81 ms / 229 tokens ( 16.42 ms per token, 60.90 tokens per second) 7.05.814.496 I slot print_timing: id 0 | task 22279 | total time = 4233.68 ms / 520 tokens 7.05.814.497 I slot print_timing: id 0 | task 22279 | graphs reused = 21908 7.05.814.498 I slot print_timing: id 0 | task 22279 | graph reallocs = 0 / 0 (same size) / (changed size) 7.05.814.526 I slot release: id 0 | task 22279 | stop processing: n_tokens = 519, truncated = 0 7.05.818.093 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 519, t_last = 341870894403 7.05.819.364 I slot launch_slot_: id 0 | task 22510 | processing task, is_child = 0 7.09.314.923 I slot print_timing: id 0 | task 22510 | n_gen = 185, tg = 61.13 t/s, tg_3s = 61.46 t/s 7.11.515.186 I slot print_timing: id 0 | task 22510 | prompt eval time = 485.57 ms / 285 tokens ( 1.70 ms per token, 586.94 tokens per second) 7.11.515.192 I slot print_timing: id 0 | task 22510 | eval time = 5210.24 ms / 319 tokens ( 16.38 ms per token, 61.03 tokens per second) 7.11.515.194 I slot print_timing: id 0 | task 22510 | total time = 5695.82 ms / 604 tokens 7.11.515.194 I slot print_timing: id 0 | task 22510 | graphs reused = 22224 7.11.515.195 I slot print_timing: id 0 | task 22510 | graph reallocs = 0 / 0 (same size) / (changed size) 7.11.515.223 I slot release: id 0 | task 22510 | stop processing: n_tokens = 603, truncated = 0 7.11.518.852 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 603, t_last = 341876595100 7.11.520.338 I slot launch_slot_: id 0 | task 22831 | processing task, is_child = 0 7.15.009.371 I slot print_timing: id 0 | task 22831 | n_gen = 184, tg = 60.97 t/s, tg_3s = 61.30 t/s 7.17.176.723 I slot print_timing: id 0 | task 22831 | prompt eval time = 487.50 ms / 289 tokens ( 1.69 ms per token, 592.82 tokens per second) 7.17.176.727 I slot print_timing: id 0 | task 22831 | eval time = 5168.88 ms / 316 tokens ( 16.41 ms per token, 60.94 tokens per second) 7.17.176.728 I slot print_timing: id 0 | task 22831 | total time = 5656.37 ms / 605 tokens 7.17.176.729 I slot print_timing: id 0 | task 22831 | graphs reused = 22537 7.17.176.729 I slot print_timing: id 0 | task 22831 | graph reallocs = 0 / 0 (same size) / (changed size) 7.17.176.765 I slot release: id 0 | task 22831 | stop processing: n_tokens = 604, truncated = 0 7.17.180.722 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 604, t_last = 341882256642 7.17.182.192 I slot launch_slot_: id 0 | task 23149 | processing task, is_child = 0 7.20.633.106 I slot print_timing: id 0 | task 23149 | n_gen = 184, tg = 60.88 t/s, tg_3s = 61.21 t/s 7.22.444.480 I slot print_timing: id 0 | task 23149 | prompt eval time = 445.07 ms / 242 tokens ( 1.84 ms per token, 543.74 tokens per second) 7.22.444.486 I slot print_timing: id 0 | task 23149 | eval time = 4817.21 ms / 294 tokens ( 16.44 ms per token, 60.82 tokens per second) 7.22.444.487 I slot print_timing: id 0 | task 23149 | total time = 5262.28 ms / 536 tokens 7.22.444.487 I slot print_timing: id 0 | task 23149 | graphs reused = 22827 7.22.444.488 I slot print_timing: id 0 | task 23149 | graph reallocs = 0 / 0 (same size) / (changed size) 7.22.444.516 I slot release: id 0 | task 23149 | stop processing: n_tokens = 535, truncated = 0 7.22.447.803 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.118 (> 0.100 thold), f_keep = 0.039 7.22.449.026 I slot launch_slot_: id 0 | task 23445 | processing task, is_child = 0 7.25.839.547 I slot print_timing: id 0 | task 23445 | n_gen = 184, tg = 60.91 t/s, tg_3s = 61.24 t/s 7.26.088.593 I slot print_timing: id 0 | task 23445 | prompt eval time = 385.96 ms / 178 tokens ( 2.17 ms per token, 461.19 tokens per second) 7.26.088.599 I slot print_timing: id 0 | task 23445 | eval time = 3253.60 ms / 199 tokens ( 16.43 ms per token, 60.86 tokens per second) 7.26.088.600 I slot print_timing: id 0 | task 23445 | total time = 3639.56 ms / 377 tokens 7.26.088.600 I slot print_timing: id 0 | task 23445 | graphs reused = 23023 7.26.088.601 I slot print_timing: id 0 | task 23445 | graph reallocs = 0 / 0 (same size) / (changed size) 7.26.088.623 I slot release: id 0 | task 23445 | stop processing: n_tokens = 376, truncated = 0 7.26.092.128 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 376, t_last = 341891168500 7.26.093.114 I slot launch_slot_: id 0 | task 23646 | processing task, is_child = 0 7.29.390.173 I slot print_timing: id 0 | task 23646 | prompt eval time = 472.31 ms / 264 tokens ( 1.79 ms per token, 558.96 tokens per second) 7.29.390.179 I slot print_timing: id 0 | task 23646 | eval time = 2824.74 ms / 173 tokens ( 16.42 ms per token, 60.89 tokens per second) 7.29.390.180 I slot print_timing: id 0 | task 23646 | total time = 3297.05 ms / 437 tokens 7.29.390.181 I slot print_timing: id 0 | task 23646 | graphs reused = 23194 7.29.390.181 I slot print_timing: id 0 | task 23646 | graph reallocs = 0 / 0 (same size) / (changed size) 7.29.390.207 I slot release: id 0 | task 23646 | stop processing: n_tokens = 436, truncated = 0 7.29.393.688 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.138 (> 0.100 thold), f_keep = 0.048 7.29.394.818 I slot launch_slot_: id 0 | task 23821 | processing task, is_child = 0 7.31.886.522 I slot print_timing: id 0 | task 23821 | prompt eval time = 359.87 ms / 152 tokens ( 2.37 ms per token, 422.37 tokens per second) 7.31.886.528 I slot print_timing: id 0 | task 23821 | eval time = 2131.82 ms / 130 tokens ( 16.53 ms per token, 60.51 tokens per second) 7.31.886.529 I slot print_timing: id 0 | task 23821 | total time = 2491.70 ms / 282 tokens 7.31.886.529 I slot print_timing: id 0 | task 23821 | graphs reused = 23321 7.31.886.530 I slot print_timing: id 0 | task 23821 | graph reallocs = 0 / 0 (same size) / (changed size) 7.31.886.550 I slot release: id 0 | task 23821 | stop processing: n_tokens = 281, truncated = 0 7.31.889.945 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.108 (> 0.100 thold), f_keep = 0.075 7.31.890.364 I slot launch_slot_: id 0 | task 23953 | processing task, is_child = 0 7.35.304.070 I slot print_timing: id 0 | task 23953 | n_gen = 185, tg = 61.00 t/s, tg_3s = 61.33 t/s 7.35.467.626 I slot print_timing: id 0 | task 23953 | prompt eval time = 397.40 ms / 194 tokens ( 2.05 ms per token, 488.17 tokens per second) 7.35.467.631 I slot print_timing: id 0 | task 23953 | eval time = 3179.85 ms / 195 tokens ( 16.39 ms per token, 61.01 tokens per second) 7.35.467.632 I slot print_timing: id 0 | task 23953 | total time = 3577.26 ms / 389 tokens 7.35.467.633 I slot print_timing: id 0 | task 23953 | graphs reused = 23513 7.35.467.633 I slot print_timing: id 0 | task 23953 | graph reallocs = 0 / 0 (same size) / (changed size) 7.35.467.658 I slot release: id 0 | task 23953 | stop processing: n_tokens = 388, truncated = 0 7.35.471.437 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 388, t_last = 341900547535 7.35.472.461 I slot launch_slot_: id 0 | task 24150 | processing task, is_child = 0 7.38.956.887 I slot print_timing: id 0 | task 24150 | n_gen = 183, tg = 60.46 t/s, tg_3s = 60.79 t/s 7.39.630.512 I slot print_timing: id 0 | task 24150 | prompt eval time = 474.18 ms / 269 tokens ( 1.76 ms per token, 567.30 tokens per second) 7.39.630.518 I slot print_timing: id 0 | task 24150 | eval time = 3683.86 ms / 224 tokens ( 16.52 ms per token, 60.53 tokens per second) 7.39.630.519 I slot print_timing: id 0 | task 24150 | total time = 4158.04 ms / 493 tokens 7.39.630.520 I slot print_timing: id 0 | task 24150 | graphs reused = 23735 7.39.630.520 I slot print_timing: id 0 | task 24150 | graph reallocs = 0 / 0 (same size) / (changed size) 7.39.630.551 I slot release: id 0 | task 24150 | stop processing: n_tokens = 492, truncated = 0 7.39.634.348 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 492, t_last = 341904710428 7.39.635.546 I slot launch_slot_: id 0 | task 24376 | processing task, is_child = 0 7.43.134.238 I slot print_timing: id 0 | task 24376 | n_gen = 184, tg = 60.69 t/s, tg_3s = 61.02 t/s 7.46.141.358 I slot print_timing: id 0 | task 24376 | n_gen = 367, tg = 60.77 t/s, tg_3s = 60.86 t/s 7.49.142.131 I slot print_timing: id 0 | task 24376 | n_gen = 550, tg = 60.84 t/s, tg_3s = 60.98 t/s 7.52.156.970 I slot print_timing: id 0 | task 24376 | n_gen = 733, tg = 60.81 t/s, tg_3s = 60.70 t/s 7.54.911.031 I slot print_timing: id 0 | task 24376 | prompt eval time = 483.34 ms / 283 tokens ( 1.71 ms per token, 585.51 tokens per second) 7.54.911.035 I slot print_timing: id 0 | task 24376 | eval time = 14792.14 ms / 900 tokens ( 16.45 ms per token, 60.78 tokens per second) 7.54.911.036 I slot print_timing: id 0 | task 24376 | total time = 15275.48 ms / 1183 tokens 7.54.911.037 I slot print_timing: id 0 | task 24376 | graphs reused = 24630 7.54.911.037 I slot print_timing: id 0 | task 24376 | graph reallocs = 0 / 0 (same size) / (changed size) 7.54.911.069 I slot release: id 0 | task 24376 | stop processing: n_tokens = 1182, truncated = 0 7.54.914.939 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1182, t_last = 341919990946 7.54.917.505 I slot launch_slot_: id 0 | task 25278 | processing task, is_child = 0 7.58.440.163 I slot print_timing: id 0 | task 25278 | n_gen = 184, tg = 60.69 t/s, tg_3s = 61.03 t/s 7.58.940.799 I slot print_timing: id 0 | task 25278 | prompt eval time = 507.55 ms / 306 tokens ( 1.66 ms per token, 602.90 tokens per second) 7.58.940.805 I slot print_timing: id 0 | task 25278 | eval time = 3515.74 ms / 214 tokens ( 16.51 ms per token, 60.58 tokens per second) 7.58.940.806 I slot print_timing: id 0 | task 25278 | total time = 4023.29 ms / 520 tokens 7.58.940.807 I slot print_timing: id 0 | task 25278 | graphs reused = 24841 7.58.940.807 I slot print_timing: id 0 | task 25278 | graph reallocs = 0 / 0 (same size) / (changed size) 7.58.940.836 I slot release: id 0 | task 25278 | stop processing: n_tokens = 519, truncated = 0 7.58.944.679 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 519, t_last = 341924020713 7.58.945.954 I slot launch_slot_: id 0 | task 25494 | processing task, is_child = 0 8.01.172.712 I slot print_timing: id 0 | task 25494 | prompt eval time = 519.64 ms / 317 tokens ( 1.64 ms per token, 610.04 tokens per second) 8.01.172.717 I slot print_timing: id 0 | task 25494 | eval time = 1707.10 ms / 105 tokens ( 16.41 ms per token, 60.92 tokens per second) 8.01.172.718 I slot print_timing: id 0 | task 25494 | total time = 2226.75 ms / 422 tokens 8.01.172.718 I slot print_timing: id 0 | task 25494 | graphs reused = 24944 8.01.172.719 I slot print_timing: id 0 | task 25494 | graph reallocs = 0 / 0 (same size) / (changed size) 8.01.172.753 I slot release: id 0 | task 25494 | stop processing: n_tokens = 421, truncated = 0 8.01.176.495 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 421, t_last = 341926252630 8.01.177.587 I slot launch_slot_: id 0 | task 25601 | processing task, is_child = 0 8.04.682.594 I slot print_timing: id 0 | task 25601 | n_gen = 184, tg = 60.97 t/s, tg_3s = 61.30 t/s 8.05.180.233 I slot print_timing: id 0 | task 25601 | prompt eval time = 503.42 ms / 296 tokens ( 1.70 ms per token, 587.98 tokens per second) 8.05.180.239 I slot print_timing: id 0 | task 25601 | eval time = 3499.22 ms / 214 tokens ( 16.43 ms per token, 60.87 tokens per second) 8.05.180.240 I slot print_timing: id 0 | task 25601 | total time = 4002.64 ms / 510 tokens 8.05.180.241 I slot print_timing: id 0 | task 25601 | graphs reused = 25156 8.05.180.241 I slot print_timing: id 0 | task 25601 | graph reallocs = 0 / 0 (same size) / (changed size) 8.05.180.274 I slot release: id 0 | task 25601 | stop processing: n_tokens = 509, truncated = 0 8.05.183.977 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 509, t_last = 341930260151 8.05.185.219 I slot launch_slot_: id 0 | task 25817 | processing task, is_child = 0 8.08.645.704 I slot print_timing: id 0 | task 25817 | n_gen = 184, tg = 60.94 t/s, tg_3s = 61.27 t/s 8.10.141.071 I slot print_timing: id 0 | task 25817 | prompt eval time = 457.54 ms / 254 tokens ( 1.80 ms per token, 555.14 tokens per second) 8.10.141.077 I slot print_timing: id 0 | task 25817 | eval time = 4498.30 ms / 275 tokens ( 16.42 ms per token, 60.91 tokens per second) 8.10.141.079 I slot print_timing: id 0 | task 25817 | total time = 4955.85 ms / 529 tokens 8.10.141.079 I slot print_timing: id 0 | task 25817 | graphs reused = 25427 8.10.141.080 I slot print_timing: id 0 | task 25817 | graph reallocs = 0 / 0 (same size) / (changed size) 8.10.141.110 I slot release: id 0 | task 25817 | stop processing: n_tokens = 528, truncated = 0 8.10.144.387 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.112 (> 0.100 thold), f_keep = 0.040 8.10.145.605 I slot launch_slot_: id 0 | task 26094 | processing task, is_child = 0 8.13.032.139 I slot print_timing: id 0 | task 26094 | prompt eval time = 391.07 ms / 188 tokens ( 2.08 ms per token, 480.73 tokens per second) 8.13.032.145 I slot print_timing: id 0 | task 26094 | eval time = 2495.45 ms / 153 tokens ( 16.42 ms per token, 60.91 tokens per second) 8.13.032.146 I slot print_timing: id 0 | task 26094 | total time = 2886.53 ms / 341 tokens 8.13.032.147 I slot print_timing: id 0 | task 26094 | graphs reused = 25577 8.13.032.147 I slot print_timing: id 0 | task 26094 | graph reallocs = 0 / 0 (same size) / (changed size) 8.13.032.177 I slot release: id 0 | task 26094 | stop processing: n_tokens = 340, truncated = 0 8.13.036.115 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 340, t_last = 341938112054 8.13.036.589 I slot launch_slot_: id 0 | task 26249 | processing task, is_child = 0 8.16.654.077 I slot print_timing: id 0 | task 26249 | n_gen = 184, tg = 60.69 t/s, tg_3s = 61.02 t/s 8.16.735.949 I slot print_timing: id 0 | task 26249 | prompt eval time = 601.92 ms / 394 tokens ( 1.53 ms per token, 654.57 tokens per second) 8.16.735.954 I slot print_timing: id 0 | task 26249 | eval time = 3097.43 ms / 189 tokens ( 16.48 ms per token, 60.70 tokens per second) 8.16.735.955 I slot print_timing: id 0 | task 26249 | total time = 3699.35 ms / 583 tokens 8.16.735.956 I slot print_timing: id 0 | task 26249 | graphs reused = 25763 8.16.735.956 I slot print_timing: id 0 | task 26249 | graph reallocs = 0 / 0 (same size) / (changed size) 8.16.735.996 I slot release: id 0 | task 26249 | stop processing: n_tokens = 582, truncated = 0 8.16.740.246 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 582, t_last = 341941815873 8.16.741.624 I slot launch_slot_: id 0 | task 26440 | processing task, is_child = 0 8.20.709.120 I slot print_timing: id 0 | task 26440 | n_gen = 184, tg = 60.78 t/s, tg_3s = 61.11 t/s 8.23.713.004 I slot print_timing: id 0 | task 26440 | n_gen = 366, tg = 60.68 t/s, tg_3s = 60.59 t/s 8.24.716.467 I slot print_timing: id 0 | task 26440 | prompt eval time = 956.50 ms / 584 tokens ( 1.64 ms per token, 610.56 tokens per second) 8.24.716.470 I slot print_timing: id 0 | task 26440 | eval time = 7018.34 ms / 427 tokens ( 16.47 ms per token, 60.70 tokens per second) 8.24.716.471 I slot print_timing: id 0 | task 26440 | total time = 7974.84 ms / 1011 tokens 8.24.716.472 I slot print_timing: id 0 | task 26440 | graphs reused = 26187 8.24.716.472 I slot print_timing: id 0 | task 26440 | graph reallocs = 0 / 0 (same size) / (changed size) 8.24.716.518 I slot release: id 0 | task 26440 | stop processing: n_tokens = 1010, truncated = 0 8.24.720.860 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1010, t_last = 341949796395 8.24.723.228 I slot launch_slot_: id 0 | task 26870 | processing task, is_child = 0 8.28.487.984 I slot print_timing: id 0 | task 26870 | n_gen = 184, tg = 60.72 t/s, tg_3s = 61.05 t/s 8.30.731.380 I slot print_timing: id 0 | task 26870 | prompt eval time = 750.79 ms / 518 tokens ( 1.45 ms per token, 689.94 tokens per second) 8.30.731.386 I slot print_timing: id 0 | task 26870 | eval time = 5257.35 ms / 320 tokens ( 16.48 ms per token, 60.68 tokens per second) 8.30.731.387 I slot print_timing: id 0 | task 26870 | total time = 6008.14 ms / 838 tokens 8.30.731.387 I slot print_timing: id 0 | task 26870 | graphs reused = 26504 8.30.731.388 I slot print_timing: id 0 | task 26870 | graph reallocs = 0 / 0 (same size) / (changed size) 8.30.731.426 I slot release: id 0 | task 26870 | stop processing: n_tokens = 837, truncated = 0 8.30.735.304 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 837, t_last = 341955811303 8.30.737.260 I slot launch_slot_: id 0 | task 27193 | processing task, is_child = 0 8.34.356.370 I slot print_timing: id 0 | task 27193 | n_gen = 185, tg = 61.04 t/s, tg_3s = 61.37 t/s 8.35.605.045 I slot print_timing: id 0 | task 27193 | prompt eval time = 604.79 ms / 399 tokens ( 1.52 ms per token, 659.73 tokens per second) 8.35.605.051 I slot print_timing: id 0 | task 27193 | eval time = 4262.98 ms / 261 tokens ( 16.40 ms per token, 60.99 tokens per second) 8.35.605.053 I slot print_timing: id 0 | task 27193 | total time = 4867.77 ms / 660 tokens 8.35.605.053 I slot print_timing: id 0 | task 27193 | graphs reused = 26762 8.35.605.054 I slot print_timing: id 0 | task 27193 | graph reallocs = 0 / 0 (same size) / (changed size) 8.35.605.089 I slot release: id 0 | task 27193 | stop processing: n_tokens = 661, truncated = 0 8.35.609.032 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 661, t_last = 341960684966 8.35.610.710 I slot launch_slot_: id 0 | task 27456 | processing task, is_child = 0 8.39.165.575 I slot print_timing: id 0 | task 27456 | n_gen = 184, tg = 60.73 t/s, tg_3s = 61.06 t/s 8.39.511.715 I slot print_timing: id 0 | task 27456 | prompt eval time = 541.52 ms / 335 tokens ( 1.62 ms per token, 618.63 tokens per second) 8.39.511.720 I slot print_timing: id 0 | task 27456 | eval time = 3359.48 ms / 205 tokens ( 16.47 ms per token, 60.72 tokens per second) 8.39.511.721 I slot print_timing: id 0 | task 27456 | total time = 3900.99 ms / 540 tokens 8.39.511.722 I slot print_timing: id 0 | task 27456 | graphs reused = 26964 8.39.511.722 I slot print_timing: id 0 | task 27456 | graph reallocs = 0 / 0 (same size) / (changed size) 8.39.511.756 I slot release: id 0 | task 27456 | stop processing: n_tokens = 541, truncated = 0 8.39.516.005 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 541, t_last = 341964591633 8.39.517.384 I slot launch_slot_: id 0 | task 27663 | processing task, is_child = 0 8.43.506.782 I slot print_timing: id 0 | task 27663 | n_gen = 184, tg = 60.71 t/s, tg_3s = 61.04 t/s 8.46.514.269 I slot print_timing: id 0 | task 27663 | n_gen = 367, tg = 60.78 t/s, tg_3s = 60.85 t/s 8.48.474.731 I slot print_timing: id 0 | task 27663 | prompt eval time = 975.20 ms / 603 tokens ( 1.62 ms per token, 618.34 tokens per second) 8.48.474.737 I slot print_timing: id 0 | task 27663 | eval time = 7982.14 ms / 486 tokens ( 16.46 ms per token, 60.76 tokens per second) 8.48.474.738 I slot print_timing: id 0 | task 27663 | total time = 8957.34 ms / 1089 tokens 8.48.474.738 I slot print_timing: id 0 | task 27663 | graphs reused = 27446 8.48.474.739 I slot print_timing: id 0 | task 27663 | graph reallocs = 0 / 0 (same size) / (changed size) 8.48.474.786 I slot release: id 0 | task 27663 | stop processing: n_tokens = 1090, truncated = 0 8.48.478.714 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1090, t_last = 341973554663 8.48.481.306 I slot launch_slot_: id 0 | task 28152 | processing task, is_child = 0 8.52.025.424 I slot print_timing: id 0 | task 28152 | n_gen = 184, tg = 60.89 t/s, tg_3s = 61.22 t/s 8.54.014.570 I slot print_timing: id 0 | task 28152 | prompt eval time = 538.53 ms / 333 tokens ( 1.62 ms per token, 618.35 tokens per second) 8.54.014.577 I slot print_timing: id 0 | task 28152 | eval time = 4994.73 ms / 305 tokens ( 16.43 ms per token, 60.86 tokens per second) 8.54.014.578 I slot print_timing: id 0 | task 28152 | total time = 5533.25 ms / 638 tokens 8.54.014.579 I slot print_timing: id 0 | task 28152 | graphs reused = 27748 8.54.014.579 I slot print_timing: id 0 | task 28152 | graph reallocs = 0 / 0 (same size) / (changed size) 8.54.014.615 I slot release: id 0 | task 28152 | stop processing: n_tokens = 639, truncated = 0 8.54.018.687 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 639, t_last = 341979094492 8.54.020.193 I slot launch_slot_: id 0 | task 28459 | processing task, is_child = 0 8.57.696.019 I slot print_timing: id 0 | task 28459 | n_gen = 184, tg = 60.89 t/s, tg_3s = 61.23 t/s 9.00.708.507 I slot print_timing: id 0 | task 28459 | n_gen = 367, tg = 60.82 t/s, tg_3s = 60.75 t/s 9.02.719.043 I slot print_timing: id 0 | task 28459 | prompt eval time = 670.59 ms / 460 tokens ( 1.46 ms per token, 685.96 tokens per second) 9.02.719.049 I slot print_timing: id 0 | task 28459 | eval time = 8028.25 ms / 489 tokens ( 16.45 ms per token, 60.79 tokens per second) 9.02.719.050 I slot print_timing: id 0 | task 28459 | total time = 8698.84 ms / 949 tokens 9.02.719.050 I slot print_timing: id 0 | task 28459 | graphs reused = 28233 9.02.719.051 I slot print_timing: id 0 | task 28459 | graph reallocs = 0 / 0 (same size) / (changed size) 9.02.719.090 I slot release: id 0 | task 28459 | stop processing: n_tokens = 950, truncated = 0 9.02.722.888 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 950, t_last = 341987798967 9.02.725.040 I slot launch_slot_: id 0 | task 28950 | processing task, is_child = 0 9.05.628.849 I slot print_timing: id 0 | task 28950 | prompt eval time = 424.14 ms / 225 tokens ( 1.89 ms per token, 530.49 tokens per second) 9.05.628.857 I slot print_timing: id 0 | task 28950 | eval time = 2479.66 ms / 152 tokens ( 16.42 ms per token, 60.90 tokens per second) 9.05.628.858 I slot print_timing: id 0 | task 28950 | total time = 2903.80 ms / 377 tokens 9.05.628.858 I slot print_timing: id 0 | task 28950 | graphs reused = 28382 9.05.628.859 I slot print_timing: id 0 | task 28950 | graph reallocs = 0 / 0 (same size) / (changed size) 9.05.628.885 I slot release: id 0 | task 28950 | stop processing: n_tokens = 378, truncated = 0 9.05.632.622 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 378, t_last = 341990708762 9.05.633.708 I slot launch_slot_: id 0 | task 29104 | processing task, is_child = 0 9.09.253.254 I slot print_timing: id 0 | task 29104 | n_gen = 184, tg = 60.96 t/s, tg_3s = 61.29 t/s 9.11.087.815 I slot print_timing: id 0 | task 29104 | prompt eval time = 617.65 ms / 415 tokens ( 1.49 ms per token, 671.90 tokens per second) 9.11.087.822 I slot print_timing: id 0 | task 29104 | eval time = 4836.45 ms / 296 tokens ( 16.39 ms per token, 61.00 tokens per second) 9.11.087.822 I slot print_timing: id 0 | task 29104 | total time = 5454.10 ms / 711 tokens 9.11.087.823 I slot print_timing: id 0 | task 29104 | graphs reused = 28675 9.11.087.824 I slot print_timing: id 0 | task 29104 | graph reallocs = 0 / 0 (same size) / (changed size) 9.11.087.860 I slot release: id 0 | task 29104 | stop processing: n_tokens = 712, truncated = 0 9.11.091.942 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 712, t_last = 341996167737 9.11.093.658 I slot launch_slot_: id 0 | task 29402 | processing task, is_child = 0 9.14.865.782 I slot print_timing: id 0 | task 29402 | n_gen = 184, tg = 60.78 t/s, tg_3s = 61.12 t/s 9.17.872.314 I slot print_timing: id 0 | task 29402 | n_gen = 367, tg = 60.83 t/s, tg_3s = 60.87 t/s 9.20.884.938 I slot print_timing: id 0 | task 29402 | n_gen = 550, tg = 60.80 t/s, tg_3s = 60.74 t/s 9.20.918.052 I slot print_timing: id 0 | task 29402 | prompt eval time = 761.46 ms / 519 tokens ( 1.47 ms per token, 681.58 tokens per second) 9.20.918.056 I slot print_timing: id 0 | task 29402 | eval time = 9062.92 ms / 552 tokens ( 16.45 ms per token, 60.80 tokens per second) 9.20.918.056 I slot print_timing: id 0 | task 29402 | total time = 9824.39 ms / 1071 tokens 9.20.918.057 I slot print_timing: id 0 | task 29402 | graphs reused = 29223 9.20.918.058 I slot print_timing: id 0 | task 29402 | graph reallocs = 0 / 0 (same size) / (changed size) 9.20.918.103 I slot release: id 0 | task 29402 | stop processing: n_tokens = 1072, truncated = 0 9.20.922.497 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1072, t_last = 342005997980 9.20.924.857 I slot launch_slot_: id 0 | task 29957 | processing task, is_child = 0 9.24.910.560 I slot print_timing: id 0 | task 29957 | n_gen = 184, tg = 60.86 t/s, tg_3s = 61.19 t/s 9.27.910.697 I slot print_timing: id 0 | task 29957 | n_gen = 367, tg = 60.93 t/s, tg_3s = 61.00 t/s 9.30.922.143 I slot print_timing: id 0 | task 29957 | n_gen = 550, tg = 60.87 t/s, tg_3s = 60.77 t/s 9.33.937.907 I slot print_timing: id 0 | task 29957 | n_gen = 733, tg = 60.83 t/s, tg_3s = 60.68 t/s 9.36.946.551 I slot print_timing: id 0 | task 29957 | n_gen = 915, tg = 60.76 t/s, tg_3s = 60.49 t/s 9.36.979.556 I slot print_timing: id 0 | task 29957 | prompt eval time = 978.57 ms / 602 tokens ( 1.63 ms per token, 615.19 tokens per second) 9.36.979.558 I slot print_timing: id 0 | task 29957 | eval time = 15076.13 ms / 917 tokens ( 16.46 ms per token, 60.76 tokens per second) 9.36.979.559 I slot print_timing: id 0 | task 29957 | total time = 16054.69 ms / 1519 tokens 9.36.979.559 I slot print_timing: id 0 | task 29957 | graphs reused = 30135 9.36.979.560 I slot print_timing: id 0 | task 29957 | graph reallocs = 0 / 0 (same size) / (changed size) 9.36.979.613 I slot release: id 0 | task 29957 | stop processing: n_tokens = 1523, truncated = 0 9.36.983.733 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1523, t_last = 342022059490 9.36.987.065 I slot launch_slot_: id 0 | task 30877 | processing task, is_child = 0 9.40.612.315 I slot print_timing: id 0 | task 30877 | n_gen = 184, tg = 60.77 t/s, tg_3s = 61.10 t/s 9.43.624.712 I slot print_timing: id 0 | task 30877 | n_gen = 367, tg = 60.76 t/s, tg_3s = 60.75 t/s 9.44.517.868 I slot print_timing: id 0 | task 30877 | prompt eval time = 613.95 ms / 407 tokens ( 1.51 ms per token, 662.92 tokens per second) 9.44.517.874 I slot print_timing: id 0 | task 30877 | eval time = 6916.84 ms / 421 tokens ( 16.47 ms per token, 60.72 tokens per second) 9.44.517.876 I slot print_timing: id 0 | task 30877 | total time = 7530.80 ms / 828 tokens 9.44.517.877 I slot print_timing: id 0 | task 30877 | graphs reused = 30552 9.44.517.877 I slot print_timing: id 0 | task 30877 | graph reallocs = 0 / 0 (same size) / (changed size) 9.44.517.912 I slot release: id 0 | task 30877 | stop processing: n_tokens = 832, truncated = 0 9.44.522.030 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 832, t_last = 342029597789 9.44.524.073 I slot launch_slot_: id 0 | task 31300 | processing task, is_child = 0 9.48.223.511 I slot print_timing: id 0 | task 31300 | n_gen = 184, tg = 60.83 t/s, tg_3s = 61.16 t/s 9.51.231.166 I slot print_timing: id 0 | task 31300 | n_gen = 367, tg = 60.83 t/s, tg_3s = 60.84 t/s 9.53.026.467 I slot print_timing: id 0 | task 31300 | prompt eval time = 690.80 ms / 484 tokens ( 1.43 ms per token, 700.63 tokens per second) 9.53.026.471 I slot print_timing: id 0 | task 31300 | eval time = 7811.58 ms / 476 tokens ( 16.45 ms per token, 60.81 tokens per second) 9.53.026.471 I slot print_timing: id 0 | task 31300 | total time = 8502.38 ms / 960 tokens 9.53.026.472 I slot print_timing: id 0 | task 31300 | graphs reused = 31024 9.53.026.473 I slot print_timing: id 0 | task 31300 | graph reallocs = 0 / 0 (same size) / (changed size) 9.53.026.513 I slot release: id 0 | task 31300 | stop processing: n_tokens = 964, truncated = 0 9.53.030.856 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 964, t_last = 342038106390 9.53.033.082 I slot launch_slot_: id 0 | task 31778 | processing task, is_child = 0 9.56.704.135 I slot print_timing: id 0 | task 31778 | n_gen = 183, tg = 60.59 t/s, tg_3s = 60.92 t/s 9.57.186.726 I slot print_timing: id 0 | task 31778 | prompt eval time = 667.32 ms / 457 tokens ( 1.46 ms per token, 684.83 tokens per second) 9.57.186.731 I slot print_timing: id 0 | task 31778 | eval time = 3486.32 ms / 212 tokens ( 16.52 ms per token, 60.52 tokens per second) 9.57.186.732 I slot print_timing: id 0 | task 31778 | total time = 4153.63 ms / 669 tokens 9.57.186.732 I slot print_timing: id 0 | task 31778 | graphs reused = 31233 9.57.186.733 I slot print_timing: id 0 | task 31778 | graph reallocs = 0 / 0 (same size) / (changed size) 9.57.186.771 I slot release: id 0 | task 31778 | stop processing: n_tokens = 673, truncated = 0 9.57.190.924 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 673, t_last = 342042266648 9.57.193.129 I slot launch_slot_: id 0 | task 31992 | processing task, is_child = 0 10.01.175.803 I slot print_timing: id 0 | task 31992 | n_gen = 183, tg = 60.51 t/s, tg_3s = 60.85 t/s 10.04.180.947 I slot print_timing: id 0 | task 31992 | n_gen = 366, tg = 60.70 t/s, tg_3s = 60.90 t/s 10.07.187.055 I slot print_timing: id 0 | task 31992 | n_gen = 548, tg = 60.65 t/s, tg_3s = 60.54 t/s 10.07.655.194 I slot print_timing: id 0 | task 31992 | prompt eval time = 975.12 ms / 597 tokens ( 1.63 ms per token, 612.23 tokens per second) 10.07.655.198 I slot print_timing: id 0 | task 31992 | eval time = 9486.94 ms / 576 tokens ( 16.50 ms per token, 60.61 tokens per second) 10.07.655.199 I slot print_timing: id 0 | task 31992 | total time = 10462.06 ms / 1173 tokens 10.07.655.199 I slot print_timing: id 0 | task 31992 | graphs reused = 31805 10.07.655.200 I slot print_timing: id 0 | task 31992 | graph reallocs = 0 / 0 (same size) / (changed size) 10.07.655.246 I slot release: id 0 | task 31992 | stop processing: n_tokens = 1172, truncated = 0 10.07.659.830 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1172, t_last = 342052735123 10.07.662.436 I slot launch_slot_: id 0 | task 32571 | processing task, is_child = 0 10.11.009.824 I slot print_timing: id 0 | task 32571 | prompt eval time = 1067.18 ms / 688 tokens ( 1.55 ms per token, 644.69 tokens per second) 10.11.009.827 I slot print_timing: id 0 | task 32571 | eval time = 2280.19 ms / 139 tokens ( 16.52 ms per token, 60.52 tokens per second) 10.11.009.827 I slot print_timing: id 0 | task 32571 | total time = 3347.37 ms / 827 tokens 10.11.009.828 I slot print_timing: id 0 | task 32571 | graphs reused = 31941 10.11.009.829 I slot print_timing: id 0 | task 32571 | graph reallocs = 0 / 0 (same size) / (changed size) 10.11.009.881 I slot release: id 0 | task 32571 | stop processing: n_tokens = 826, truncated = 0 10.11.013.856 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 826, t_last = 342056089758 10.11.016.189 I slot launch_slot_: id 0 | task 32713 | processing task, is_child = 0 10.14.730.977 I slot print_timing: id 0 | task 32713 | n_gen = 184, tg = 60.72 t/s, tg_3s = 61.05 t/s 10.16.204.535 I slot print_timing: id 0 | task 32713 | prompt eval time = 700.74 ms / 489 tokens ( 1.43 ms per token, 697.83 tokens per second) 10.16.204.542 I slot print_timing: id 0 | task 32713 | eval time = 4487.60 ms / 273 tokens ( 16.50 ms per token, 60.61 tokens per second) 10.16.204.543 I slot print_timing: id 0 | task 32713 | total time = 5188.34 ms / 762 tokens 10.16.204.543 I slot print_timing: id 0 | task 32713 | graphs reused = 32211 10.16.204.544 I slot print_timing: id 0 | task 32713 | graph reallocs = 0 / 0 (same size) / (changed size) 10.16.204.585 I slot release: id 0 | task 32713 | stop processing: n_tokens = 761, truncated = 0 10.16.208.918 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 761, t_last = 342061284463 10.16.211.080 I slot launch_slot_: id 0 | task 32988 | processing task, is_child = 0 10.19.590.867 I slot print_timing: id 0 | task 32988 | prompt eval time = 898.60 ms / 550 tokens ( 1.63 ms per token, 612.06 tokens per second) 10.19.590.873 I slot print_timing: id 0 | task 32988 | eval time = 2481.17 ms / 151 tokens ( 16.54 ms per token, 60.46 tokens per second) 10.19.590.874 I slot print_timing: id 0 | task 32988 | total time = 3379.77 ms / 701 tokens 10.19.590.874 I slot print_timing: id 0 | task 32988 | graphs reused = 32360 10.19.590.875 I slot print_timing: id 0 | task 32988 | graph reallocs = 0 / 0 (same size) / (changed size) 10.19.590.919 I slot release: id 0 | task 32988 | stop processing: n_tokens = 700, truncated = 0 10.19.594.654 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 700, t_last = 342064670796 10.19.596.319 I slot launch_slot_: id 0 | task 33142 | processing task, is_child = 0 10.23.135.981 I slot print_timing: id 0 | task 33142 | n_gen = 184, tg = 60.98 t/s, tg_3s = 61.31 t/s 10.25.868.276 I slot print_timing: id 0 | task 33142 | prompt eval time = 538.69 ms / 334 tokens ( 1.61 ms per token, 620.02 tokens per second) 10.25.868.279 I slot print_timing: id 0 | task 33142 | eval time = 5733.26 ms / 350 tokens ( 16.43 ms per token, 60.87 tokens per second) 10.25.868.280 I slot print_timing: id 0 | task 33142 | total time = 6271.95 ms / 684 tokens 10.25.868.281 I slot print_timing: id 0 | task 33142 | graphs reused = 32707 10.25.868.281 I slot print_timing: id 0 | task 33142 | graph reallocs = 0 / 0 (same size) / (changed size) 10.25.868.316 I slot release: id 0 | task 33142 | stop processing: n_tokens = 683, truncated = 0 10.25.872.389 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 683, t_last = 342070948193 10.25.873.996 I slot launch_slot_: id 0 | task 33494 | processing task, is_child = 0 10.29.495.599 I slot print_timing: id 0 | task 33494 | n_gen = 183, tg = 60.66 t/s, tg_3s = 60.99 t/s 10.32.505.268 I slot print_timing: id 0 | task 33494 | n_gen = 366, tg = 60.73 t/s, tg_3s = 60.80 t/s 10.34.165.085 I slot print_timing: id 0 | task 33494 | prompt eval time = 621.20 ms / 416 tokens ( 1.49 ms per token, 669.67 tokens per second) 10.34.165.091 I slot print_timing: id 0 | task 33494 | eval time = 7669.88 ms / 467 tokens ( 16.46 ms per token, 60.76 tokens per second) 10.34.165.092 I slot print_timing: id 0 | task 33494 | total time = 8291.08 ms / 883 tokens 10.34.165.092 I slot print_timing: id 0 | task 33494 | graphs reused = 33170 10.34.165.093 I slot print_timing: id 0 | task 33494 | graph reallocs = 0 / 0 (same size) / (changed size) 10.34.165.129 I slot release: id 0 | task 33494 | stop processing: n_tokens = 882, truncated = 0 10.34.169.895 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 882, t_last = 342079245006 10.34.171.930 I slot launch_slot_: id 0 | task 33963 | processing task, is_child = 0 10.36.460.446 I slot print_timing: id 0 | task 33963 | prompt eval time = 1131.04 ms / 754 tokens ( 1.50 ms per token, 666.64 tokens per second) 10.36.460.452 I slot print_timing: id 0 | task 33963 | eval time = 1157.46 ms / 71 tokens ( 16.54 ms per token, 60.48 tokens per second) 10.36.460.454 I slot print_timing: id 0 | task 33963 | total time = 2288.51 ms / 825 tokens 10.36.460.454 I slot print_timing: id 0 | task 33963 | graphs reused = 33238 10.36.460.455 I slot print_timing: id 0 | task 33963 | graph reallocs = 0 / 0 (same size) / (changed size) 10.36.460.513 I slot release: id 0 | task 33963 | stop processing: n_tokens = 824, truncated = 0 10.36.464.896 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 824, t_last = 342081540390 10.36.466.857 I slot launch_slot_: id 0 | task 34037 | processing task, is_child = 0 10.40.545.272 I slot print_timing: id 0 | task 34037 | n_gen = 183, tg = 60.59 t/s, tg_3s = 60.92 t/s 10.41.555.077 I slot print_timing: id 0 | task 34037 | prompt eval time = 1074.64 ms / 706 tokens ( 1.52 ms per token, 656.96 tokens per second) 10.41.555.084 I slot print_timing: id 0 | task 34037 | eval time = 4013.57 ms / 244 tokens ( 16.52 ms per token, 60.54 tokens per second) 10.41.555.084 I slot print_timing: id 0 | task 34037 | total time = 5088.21 ms / 950 tokens 10.41.555.085 I slot print_timing: id 0 | task 34037 | graphs reused = 33479 10.41.555.086 I slot print_timing: id 0 | task 34037 | graph reallocs = 0 / 0 (same size) / (changed size) 10.41.555.140 I slot release: id 0 | task 34037 | stop processing: n_tokens = 949, truncated = 0 10.41.558.759 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 949, t_last = 342086635017 10.41.560.895 I slot launch_slot_: id 0 | task 34284 | processing task, is_child = 0 10.45.014.872 I slot print_timing: id 0 | task 34284 | n_gen = 185, tg = 61.04 t/s, tg_3s = 61.37 t/s 10.48.022.144 I slot print_timing: id 0 | task 34284 | n_gen = 368, tg = 60.94 t/s, tg_3s = 60.85 t/s 10.49.053.151 I slot print_timing: id 0 | task 34284 | prompt eval time = 439.39 ms / 233 tokens ( 1.89 ms per token, 530.29 tokens per second) 10.49.053.157 I slot print_timing: id 0 | task 34284 | eval time = 7052.86 ms / 431 tokens ( 16.40 ms per token, 60.97 tokens per second) 10.49.053.158 I slot print_timing: id 0 | task 34284 | total time = 7492.25 ms / 664 tokens 10.49.053.159 I slot print_timing: id 0 | task 34284 | graphs reused = 33906 10.49.053.159 I slot print_timing: id 0 | task 34284 | graph reallocs = 0 / 0 (same size) / (changed size) 10.49.053.190 I slot release: id 0 | task 34284 | stop processing: n_tokens = 663, truncated = 0 10.49.056.758 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.133 (> 0.100 thold), f_keep = 0.035 10.49.058.292 I slot launch_slot_: id 0 | task 34717 | processing task, is_child = 0 10.52.391.317 I slot print_timing: id 0 | task 34717 | prompt eval time = 381.75 ms / 173 tokens ( 2.21 ms per token, 453.17 tokens per second) 10.52.391.323 I slot print_timing: id 0 | task 34717 | eval time = 2951.26 ms / 181 tokens ( 16.40 ms per token, 60.99 tokens per second) 10.52.391.324 I slot print_timing: id 0 | task 34717 | total time = 3333.01 ms / 354 tokens 10.52.391.325 I slot print_timing: id 0 | task 34717 | graphs reused = 34084 10.52.391.325 I slot print_timing: id 0 | task 34717 | graph reallocs = 0 / 0 (same size) / (changed size) 10.52.391.346 I slot release: id 0 | task 34717 | stop processing: n_tokens = 353, truncated = 0 10.52.394.753 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.111 (> 0.100 thold), f_keep = 0.062 10.52.395.214 I slot launch_slot_: id 0 | task 34900 | processing task, is_child = 0 10.55.815.377 I slot print_timing: id 0 | task 34900 | n_gen = 185, tg = 61.06 t/s, tg_3s = 61.39 t/s 10.58.822.019 I slot print_timing: id 0 | task 34900 | n_gen = 368, tg = 60.96 t/s, tg_3s = 60.87 t/s 11.01.830.271 I slot print_timing: id 0 | task 34900 | n_gen = 551, tg = 60.92 t/s, tg_3s = 60.83 t/s 11.04.837.438 I slot print_timing: id 0 | task 34900 | n_gen = 734, tg = 60.90 t/s, tg_3s = 60.85 t/s 11.07.848.656 I slot print_timing: id 0 | task 34900 | n_gen = 917, tg = 60.88 t/s, tg_3s = 60.77 t/s 11.09.613.860 I slot print_timing: id 0 | task 34900 | prompt eval time = 406.68 ms / 199 tokens ( 2.04 ms per token, 489.32 tokens per second) 11.09.613.867 I slot print_timing: id 0 | task 34900 | eval time = 16811.96 ms / 1024 tokens ( 16.43 ms per token, 60.85 tokens per second) 11.09.613.868 I slot print_timing: id 0 | task 34900 | total time = 17218.64 ms / 1223 tokens 11.09.613.868 I slot print_timing: id 0 | task 34900 | graphs reused = 35102 11.09.613.869 I slot print_timing: id 0 | task 34900 | graph reallocs = 0 / 0 (same size) / (changed size) 11.09.613.894 I slot release: id 0 | task 34900 | stop processing: n_tokens = 1222, truncated = 0 11.09.617.436 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 11.09.620.120 I slot launch_slot_: id 0 | task 35926 | processing task, is_child = 0 11.12.991.007 I slot print_timing: id 0 | task 35926 | n_gen = 184, tg = 60.71 t/s, tg_3s = 61.04 t/s 11.14.828.618 I slot print_timing: id 0 | task 35926 | prompt eval time = 356.48 ms / 149 tokens ( 2.39 ms per token, 417.98 tokens per second) 11.14.828.624 I slot print_timing: id 0 | task 35926 | eval time = 4852.01 ms / 296 tokens ( 16.45 ms per token, 60.80 tokens per second) 11.14.828.625 I slot print_timing: id 0 | task 35926 | total time = 5208.49 ms / 445 tokens 11.14.828.625 I slot print_timing: id 0 | task 35926 | graphs reused = 35395 11.14.828.626 I slot print_timing: id 0 | task 35926 | graph reallocs = 0 / 0 (same size) / (changed size) 11.14.828.646 I slot release: id 0 | task 35926 | stop processing: n_tokens = 444, truncated = 0 11.14.832.215 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 444, t_last = 342119908523 11.14.832.759 I slot launch_slot_: id 0 | task 36224 | processing task, is_child = 0 11.18.254.419 I slot print_timing: id 0 | task 36224 | n_gen = 184, tg = 60.94 t/s, tg_3s = 61.27 t/s 11.21.259.772 I slot print_timing: id 0 | task 36224 | n_gen = 367, tg = 60.92 t/s, tg_3s = 60.89 t/s 11.24.263.229 I slot print_timing: id 0 | task 36224 | n_gen = 550, tg = 60.92 t/s, tg_3s = 60.93 t/s 11.27.275.685 I slot print_timing: id 0 | task 36224 | n_gen = 734, tg = 60.96 t/s, tg_3s = 61.08 t/s 11.30.284.669 I slot print_timing: id 0 | task 36224 | n_gen = 917, tg = 60.93 t/s, tg_3s = 60.82 t/s 11.32.047.025 I slot print_timing: id 0 | task 36224 | prompt eval time = 418.77 ms / 216 tokens ( 1.94 ms per token, 515.80 tokens per second) 11.32.047.031 I slot print_timing: id 0 | task 36224 | eval time = 16795.49 ms / 1024 tokens ( 16.42 ms per token, 60.91 tokens per second) 11.32.047.032 I slot print_timing: id 0 | task 36224 | total time = 17214.26 ms / 1240 tokens 11.32.047.033 I slot print_timing: id 0 | task 36224 | graphs reused = 36413 11.32.047.033 I slot print_timing: id 0 | task 36224 | graph reallocs = 0 / 0 (same size) / (changed size) 11.32.047.058 I slot release: id 0 | task 36224 | stop processing: n_tokens = 1239, truncated = 0 11.32.050.512 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.160 (> 0.100 thold), f_keep = 0.017 11.32.053.405 I slot launch_slot_: id 0 | task 37250 | processing task, is_child = 0 11.33.731.669 I slot print_timing: id 0 | task 37250 | prompt eval time = 333.58 ms / 131 tokens ( 2.55 ms per token, 392.71 tokens per second) 11.33.731.674 I slot print_timing: id 0 | task 37250 | eval time = 1344.67 ms / 82 tokens ( 16.60 ms per token, 60.24 tokens per second) 11.33.731.674 I slot print_timing: id 0 | task 37250 | total time = 1678.25 ms / 213 tokens 11.33.731.675 I slot print_timing: id 0 | task 37250 | graphs reused = 36493 11.33.731.676 I slot print_timing: id 0 | task 37250 | graph reallocs = 0 / 0 (same size) / (changed size) 11.33.731.700 I slot release: id 0 | task 37250 | stop processing: n_tokens = 212, truncated = 0 11.33.735.416 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.121 (> 0.100 thold), f_keep = 0.099 11.33.735.761 I slot launch_slot_: id 0 | task 37334 | processing task, is_child = 0 11.37.125.974 I slot print_timing: id 0 | task 37334 | n_gen = 184, tg = 60.86 t/s, tg_3s = 61.20 t/s 11.40.131.074 I slot print_timing: id 0 | task 37334 | n_gen = 367, tg = 60.88 t/s, tg_3s = 60.90 t/s 11.42.054.917 I slot print_timing: id 0 | task 37334 | prompt eval time = 383.55 ms / 174 tokens ( 2.20 ms per token, 453.66 tokens per second) 11.42.054.923 I slot print_timing: id 0 | task 37334 | eval time = 7935.60 ms / 484 tokens ( 16.43 ms per token, 60.86 tokens per second) 11.42.054.924 I slot print_timing: id 0 | task 37334 | total time = 8319.15 ms / 658 tokens 11.42.054.925 I slot print_timing: id 0 | task 37334 | graphs reused = 36973 11.42.054.925 I slot print_timing: id 0 | task 37334 | graph reallocs = 0 / 0 (same size) / (changed size) 11.42.054.946 I slot release: id 0 | task 37334 | stop processing: n_tokens = 657, truncated = 0 11.42.058.763 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.129 (> 0.100 thold), f_keep = 0.032 11.42.060.309 I slot launch_slot_: id 0 | task 37820 | processing task, is_child = 0 11.45.429.170 I slot print_timing: id 0 | task 37820 | n_gen = 184, tg = 60.96 t/s, tg_3s = 61.29 t/s 11.46.923.213 I slot print_timing: id 0 | task 37820 | prompt eval time = 366.68 ms / 163 tokens ( 2.25 ms per token, 444.53 tokens per second) 11.46.923.219 I slot print_timing: id 0 | task 37820 | eval time = 4496.21 ms / 275 tokens ( 16.41 ms per token, 60.94 tokens per second) 11.46.923.219 I slot print_timing: id 0 | task 37820 | total time = 4862.89 ms / 438 tokens 11.46.923.220 I slot print_timing: id 0 | task 37820 | graphs reused = 37245 11.46.923.220 I slot print_timing: id 0 | task 37820 | graph reallocs = 0 / 0 (same size) / (changed size) 11.46.923.243 I slot release: id 0 | task 37820 | stop processing: n_tokens = 437, truncated = 0 11.46.926.431 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.208 (> 0.100 thold), f_keep = 0.048 11.46.926.912 I slot launch_slot_: id 0 | task 38097 | processing task, is_child = 0 11.50.256.389 I slot print_timing: id 0 | task 38097 | n_gen = 183, tg = 60.44 t/s, tg_3s = 60.78 t/s 11.53.266.974 I slot print_timing: id 0 | task 38097 | n_gen = 367, tg = 60.78 t/s, tg_3s = 61.12 t/s 11.56.275.797 I slot print_timing: id 0 | task 38097 | n_gen = 550, tg = 60.79 t/s, tg_3s = 60.82 t/s 11.58.186.478 I slot print_timing: id 0 | task 38097 | prompt eval time = 318.38 ms / 101 tokens ( 3.15 ms per token, 317.23 tokens per second) 11.58.186.484 I slot print_timing: id 0 | task 38097 | eval time = 10941.17 ms / 666 tokens ( 16.45 ms per token, 60.78 tokens per second) 11.58.186.485 I slot print_timing: id 0 | task 38097 | total time = 11259.56 ms / 767 tokens 11.58.186.485 I slot print_timing: id 0 | task 38097 | graphs reused = 37907 11.58.186.486 I slot print_timing: id 0 | task 38097 | graph reallocs = 0 / 0 (same size) / (changed size) 11.58.186.503 I slot release: id 0 | task 38097 | stop processing: n_tokens = 766, truncated = 0 11.58.189.975 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.126 (> 0.100 thold), f_keep = 0.027 11.58.191.765 I slot launch_slot_: id 0 | task 38765 | processing task, is_child = 0 12.01.573.587 I slot print_timing: id 0 | task 38765 | n_gen = 184, tg = 60.99 t/s, tg_3s = 61.33 t/s 12.04.585.048 I slot print_timing: id 0 | task 38765 | n_gen = 367, tg = 60.88 t/s, tg_3s = 60.77 t/s 12.05.096.896 I slot print_timing: id 0 | task 38765 | prompt eval time = 381.44 ms / 167 tokens ( 2.28 ms per token, 437.82 tokens per second) 12.05.096.901 I slot print_timing: id 0 | task 38765 | eval time = 6523.68 ms / 398 tokens ( 16.43 ms per token, 60.86 tokens per second) 12.05.096.902 I slot print_timing: id 0 | task 38765 | total time = 6905.12 ms / 565 tokens 12.05.096.903 I slot print_timing: id 0 | task 38765 | graphs reused = 38301 12.05.096.903 I slot print_timing: id 0 | task 38765 | graph reallocs = 0 / 0 (same size) / (changed size) 12.05.096.925 I slot release: id 0 | task 38765 | stop processing: n_tokens = 564, truncated = 0 12.05.100.490 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.123 (> 0.100 thold), f_keep = 0.037 12.05.101.826 I slot launch_slot_: id 0 | task 39165 | processing task, is_child = 0 12.08.501.591 I slot print_timing: id 0 | task 39165 | n_gen = 185, tg = 61.04 t/s, tg_3s = 61.37 t/s 12.09.895.487 I slot print_timing: id 0 | task 39165 | prompt eval time = 385.17 ms / 171 tokens ( 2.25 ms per token, 443.96 tokens per second) 12.09.895.490 I slot print_timing: id 0 | task 39165 | eval time = 4408.48 ms / 270 tokens ( 16.39 ms per token, 61.02 tokens per second) 12.09.895.491 I slot print_timing: id 0 | task 39165 | total time = 4793.65 ms / 441 tokens 12.09.895.491 I slot print_timing: id 0 | task 39165 | graphs reused = 38568 12.09.895.492 I slot print_timing: id 0 | task 39165 | graph reallocs = 0 / 0 (same size) / (changed size) 12.09.895.518 I slot release: id 0 | task 39165 | stop processing: n_tokens = 440, truncated = 0 12.09.899.016 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.117 (> 0.100 thold), f_keep = 0.048 12.09.900.196 I slot launch_slot_: id 0 | task 39437 | processing task, is_child = 0 12.13.286.651 I slot print_timing: id 0 | task 39437 | n_gen = 184, tg = 60.98 t/s, tg_3s = 61.32 t/s 12.16.302.600 I slot print_timing: id 0 | task 39437 | n_gen = 367, tg = 60.83 t/s, tg_3s = 60.68 t/s 12.16.368.955 I slot print_timing: id 0 | task 39437 | prompt eval time = 385.68 ms / 179 tokens ( 2.15 ms per token, 464.12 tokens per second) 12.16.368.961 I slot print_timing: id 0 | task 39437 | eval time = 6083.07 ms / 371 tokens ( 16.44 ms per token, 60.82 tokens per second) 12.16.368.961 I slot print_timing: id 0 | task 39437 | total time = 6468.75 ms / 550 tokens 12.16.368.962 I slot print_timing: id 0 | task 39437 | graphs reused = 38935 12.16.368.963 I slot print_timing: id 0 | task 39437 | graph reallocs = 0 / 0 (same size) / (changed size) 12.16.368.989 I slot release: id 0 | task 39437 | stop processing: n_tokens = 549, truncated = 0 12.16.372.544 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.127 (> 0.100 thold), f_keep = 0.038 12.16.373.973 I slot launch_slot_: id 0 | task 39810 | processing task, is_child = 0 12.19.761.460 I slot print_timing: id 0 | task 39810 | n_gen = 184, tg = 60.82 t/s, tg_3s = 61.16 t/s 12.20.448.513 I slot print_timing: id 0 | task 39810 | prompt eval time = 378.78 ms / 165 tokens ( 2.30 ms per token, 435.60 tokens per second) 12.20.448.523 I slot print_timing: id 0 | task 39810 | eval time = 3695.75 ms / 226 tokens ( 16.43 ms per token, 60.88 tokens per second) 12.20.448.524 I slot print_timing: id 0 | task 39810 | total time = 4074.53 ms / 391 tokens 12.20.448.524 I slot print_timing: id 0 | task 39810 | graphs reused = 39158 12.20.448.525 I slot print_timing: id 0 | task 39810 | graph reallocs = 0 / 0 (same size) / (changed size) 12.20.448.546 I slot release: id 0 | task 39810 | stop processing: n_tokens = 390, truncated = 0 12.20.451.960 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.132 (> 0.100 thold), f_keep = 0.054 12.20.452.997 I slot launch_slot_: id 0 | task 40038 | processing task, is_child = 0 12.23.818.590 I slot print_timing: id 0 | task 40038 | n_gen = 184, tg = 60.98 t/s, tg_3s = 61.32 t/s 12.24.277.805 I slot print_timing: id 0 | task 40038 | prompt eval time = 364.84 ms / 159 tokens ( 2.29 ms per token, 435.81 tokens per second) 12.24.277.811 I slot print_timing: id 0 | task 40038 | eval time = 3459.96 ms / 212 tokens ( 16.40 ms per token, 60.98 tokens per second) 12.24.277.813 I slot print_timing: id 0 | task 40038 | total time = 3824.80 ms / 371 tokens 12.24.277.813 I slot print_timing: id 0 | task 40038 | graphs reused = 39367 12.24.277.814 I slot print_timing: id 0 | task 40038 | graph reallocs = 0 / 0 (same size) / (changed size) 12.24.277.839 I slot release: id 0 | task 40038 | stop processing: n_tokens = 370, truncated = 0 12.24.281.358 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.118 (> 0.100 thold), f_keep = 0.057 12.24.282.401 I slot launch_slot_: id 0 | task 40252 | processing task, is_child = 0 12.27.232.943 I slot print_timing: id 0 | task 40252 | prompt eval time = 388.06 ms / 178 tokens ( 2.18 ms per token, 458.69 tokens per second) 12.27.232.949 I slot print_timing: id 0 | task 40252 | eval time = 2562.47 ms / 157 tokens ( 16.43 ms per token, 60.88 tokens per second) 12.27.232.950 I slot print_timing: id 0 | task 40252 | total time = 2950.53 ms / 335 tokens 12.27.232.950 I slot print_timing: id 0 | task 40252 | graphs reused = 39521 12.27.232.951 I slot print_timing: id 0 | task 40252 | graph reallocs = 0 / 0 (same size) / (changed size) 12.27.232.977 I slot release: id 0 | task 40252 | stop processing: n_tokens = 334, truncated = 0 12.27.236.366 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.112 (> 0.100 thold), f_keep = 0.063 12.27.237.237 I slot launch_slot_: id 0 | task 40411 | processing task, is_child = 0 12.30.643.843 I slot print_timing: id 0 | task 40411 | n_gen = 184, tg = 60.78 t/s, tg_3s = 61.11 t/s 12.33.646.489 I slot print_timing: id 0 | task 40411 | n_gen = 367, tg = 60.86 t/s, tg_3s = 60.95 t/s 12.36.662.307 I slot print_timing: id 0 | task 40411 | n_gen = 551, tg = 60.91 t/s, tg_3s = 61.01 t/s 12.39.667.527 I slot print_timing: id 0 | task 40411 | n_gen = 733, tg = 60.82 t/s, tg_3s = 60.56 t/s 12.42.676.369 I slot print_timing: id 0 | task 40411 | n_gen = 915, tg = 60.76 t/s, tg_3s = 60.49 t/s 12.44.476.193 I slot print_timing: id 0 | task 40411 | prompt eval time = 395.54 ms / 188 tokens ( 2.10 ms per token, 475.30 tokens per second) 12.44.476.199 I slot print_timing: id 0 | task 40411 | eval time = 16843.41 ms / 1024 tokens ( 16.46 ms per token, 60.74 tokens per second) 12.44.476.200 I slot print_timing: id 0 | task 40411 | total time = 17238.94 ms / 1212 tokens 12.44.476.201 I slot print_timing: id 0 | task 40411 | graphs reused = 40539 12.44.476.202 I slot print_timing: id 0 | task 40411 | graph reallocs = 0 / 0 (same size) / (changed size) 12.44.476.225 I slot release: id 0 | task 40411 | stop processing: n_tokens = 1211, truncated = 0 12.44.479.820 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 12.44.482.512 I slot launch_slot_: id 0 | task 41437 | processing task, is_child = 0 12.47.867.220 I slot print_timing: id 0 | task 41437 | n_gen = 185, tg = 61.00 t/s, tg_3s = 61.33 t/s 12.50.871.992 I slot print_timing: id 0 | task 41437 | n_gen = 368, tg = 60.95 t/s, tg_3s = 60.90 t/s 12.53.874.606 I slot print_timing: id 0 | task 41437 | n_gen = 550, tg = 60.84 t/s, tg_3s = 60.61 t/s 12.54.273.551 I slot print_timing: id 0 | task 41437 | prompt eval time = 368.46 ms / 164 tokens ( 2.25 ms per token, 445.09 tokens per second) 12.54.273.557 I slot print_timing: id 0 | task 41437 | eval time = 9422.57 ms / 574 tokens ( 16.44 ms per token, 60.81 tokens per second) 12.54.273.558 I slot print_timing: id 0 | task 41437 | total time = 9791.03 ms / 738 tokens 12.54.273.558 I slot print_timing: id 0 | task 41437 | graphs reused = 41109 12.54.273.559 I slot print_timing: id 0 | task 41437 | graph reallocs = 0 / 0 (same size) / (changed size) 12.54.273.584 I slot release: id 0 | task 41437 | stop processing: n_tokens = 737, truncated = 0 12.54.277.178 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.116 (> 0.100 thold), f_keep = 0.028 12.54.278.919 I slot launch_slot_: id 0 | task 42013 | processing task, is_child = 0 12.57.684.113 I slot print_timing: id 0 | task 42013 | n_gen = 184, tg = 60.67 t/s, tg_3s = 61.01 t/s 13.00.691.837 I slot print_timing: id 0 | task 42013 | n_gen = 367, tg = 60.76 t/s, tg_3s = 60.84 t/s 13.02.538.366 I slot print_timing: id 0 | task 42013 | prompt eval time = 389.09 ms / 181 tokens ( 2.15 ms per token, 465.19 tokens per second) 13.02.538.373 I slot print_timing: id 0 | task 42013 | eval time = 7870.34 ms / 479 tokens ( 16.47 ms per token, 60.73 tokens per second) 13.02.538.373 I slot print_timing: id 0 | task 42013 | total time = 8259.43 ms / 660 tokens 13.02.538.374 I slot print_timing: id 0 | task 42013 | graphs reused = 41584 13.02.538.375 I slot print_timing: id 0 | task 42013 | graph reallocs = 0 / 0 (same size) / (changed size) 13.02.538.406 I slot release: id 0 | task 42013 | stop processing: n_tokens = 659, truncated = 0 13.02.541.880 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.136 (> 0.100 thold), f_keep = 0.032 13.02.543.457 I slot launch_slot_: id 0 | task 42494 | processing task, is_child = 0 13.05.913.339 I slot print_timing: id 0 | task 42494 | n_gen = 184, tg = 60.80 t/s, tg_3s = 61.13 t/s 13.07.115.109 I slot print_timing: id 0 | task 42494 | prompt eval time = 360.08 ms / 154 tokens ( 2.34 ms per token, 427.68 tokens per second) 13.07.115.115 I slot print_timing: id 0 | task 42494 | eval time = 4211.56 ms / 257 tokens ( 16.45 ms per token, 60.79 tokens per second) 13.07.115.116 I slot print_timing: id 0 | task 42494 | total time = 4571.64 ms / 411 tokens 13.07.115.116 I slot print_timing: id 0 | task 42494 | graphs reused = 41838 13.07.115.117 I slot print_timing: id 0 | task 42494 | graph reallocs = 0 / 0 (same size) / (changed size) 13.07.115.139 I slot release: id 0 | task 42494 | stop processing: n_tokens = 410, truncated = 0 13.07.118.544 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.051 13.07.119.657 I slot launch_slot_: id 0 | task 42753 | processing task, is_child = 0 13.09.195.405 I slot print_timing: id 0 | task 42753 | prompt eval time = 348.27 ms / 135 tokens ( 2.58 ms per token, 387.63 tokens per second) 13.09.195.412 I slot print_timing: id 0 | task 42753 | eval time = 1727.47 ms / 106 tokens ( 16.45 ms per token, 60.78 tokens per second) 13.09.195.413 I slot print_timing: id 0 | task 42753 | total time = 2075.74 ms / 241 tokens 13.09.195.413 I slot print_timing: id 0 | task 42753 | graphs reused = 41942 13.09.195.414 I slot print_timing: id 0 | task 42753 | graph reallocs = 0 / 0 (same size) / (changed size) 13.09.195.432 I slot release: id 0 | task 42753 | stop processing: n_tokens = 240, truncated = 0 13.09.198.897 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.117 (> 0.100 thold), f_keep = 0.087 13.09.199.589 I slot launch_slot_: id 0 | task 42861 | processing task, is_child = 0 13.12.588.163 I slot print_timing: id 0 | task 42861 | n_gen = 184, tg = 60.93 t/s, tg_3s = 61.27 t/s 13.15.595.850 I slot print_timing: id 0 | task 42861 | n_gen = 367, tg = 60.89 t/s, tg_3s = 60.84 t/s 13.18.607.431 I slot print_timing: id 0 | task 42861 | n_gen = 550, tg = 60.85 t/s, tg_3s = 60.77 t/s 13.20.321.857 I slot print_timing: id 0 | task 42861 | prompt eval time = 385.34 ms / 179 tokens ( 2.15 ms per token, 464.53 tokens per second) 13.20.321.860 I slot print_timing: id 0 | task 42861 | eval time = 10736.92 ms / 654 tokens ( 16.44 ms per token, 60.82 tokens per second) 13.20.321.861 I slot print_timing: id 0 | task 42861 | total time = 11122.26 ms / 833 tokens 13.20.321.862 I slot print_timing: id 0 | task 42861 | graphs reused = 42591 13.20.321.862 I slot print_timing: id 0 | task 42861 | graph reallocs = 0 / 0 (same size) / (changed size) 13.20.321.888 I slot release: id 0 | task 42861 | stop processing: n_tokens = 832, truncated = 0 13.20.325.628 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.119 (> 0.100 thold), f_keep = 0.030 13.20.327.594 I slot launch_slot_: id 0 | task 43517 | processing task, is_child = 0 13.23.748.575 I slot print_timing: id 0 | task 43517 | n_gen = 184, tg = 60.88 t/s, tg_3s = 61.22 t/s 13.26.763.105 I slot print_timing: id 0 | task 43517 | n_gen = 367, tg = 60.79 t/s, tg_3s = 60.71 t/s 13.28.175.678 I slot print_timing: id 0 | task 43517 | prompt eval time = 415.26 ms / 210 tokens ( 1.98 ms per token, 505.70 tokens per second) 13.28.175.684 I slot print_timing: id 0 | task 43517 | eval time = 7432.81 ms / 453 tokens ( 16.44 ms per token, 60.81 tokens per second) 13.28.175.684 I slot print_timing: id 0 | task 43517 | total time = 7848.08 ms / 663 tokens 13.28.175.685 I slot print_timing: id 0 | task 43517 | graphs reused = 43040 13.28.175.686 I slot print_timing: id 0 | task 43517 | graph reallocs = 0 / 0 (same size) / (changed size) 13.28.175.711 I slot release: id 0 | task 43517 | stop processing: n_tokens = 662, truncated = 0 13.28.179.066 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 13.28.180.623 I slot launch_slot_: id 0 | task 43972 | processing task, is_child = 0 13.31.523.069 I slot print_timing: id 0 | task 43972 | n_gen = 184, tg = 60.87 t/s, tg_3s = 61.20 t/s 13.32.509.274 I slot print_timing: id 0 | task 43972 | prompt eval time = 336.01 ms / 127 tokens ( 2.65 ms per token, 377.97 tokens per second) 13.32.509.281 I slot print_timing: id 0 | task 43972 | eval time = 3992.64 ms / 244 tokens ( 16.43 ms per token, 60.86 tokens per second) 13.32.509.283 I slot print_timing: id 0 | task 43972 | total time = 4328.65 ms / 371 tokens 13.32.509.283 I slot print_timing: id 0 | task 43972 | graphs reused = 43281 13.32.509.284 I slot print_timing: id 0 | task 43972 | graph reallocs = 0 / 0 (same size) / (changed size) 13.32.509.303 I slot release: id 0 | task 43972 | stop processing: n_tokens = 370, truncated = 0 13.32.512.421 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.152 (> 0.100 thold), f_keep = 0.057 13.32.513.405 I slot launch_slot_: id 0 | task 44218 | processing task, is_child = 0 13.35.865.071 I slot print_timing: id 0 | task 44218 | n_gen = 184, tg = 61.00 t/s, tg_3s = 61.33 t/s 13.38.258.920 I slot print_timing: id 0 | task 44218 | prompt eval time = 351.60 ms / 138 tokens ( 2.55 ms per token, 392.49 tokens per second) 13.38.258.923 I slot print_timing: id 0 | task 44218 | eval time = 5393.90 ms / 330 tokens ( 16.39 ms per token, 60.99 tokens per second) 13.38.258.924 I slot print_timing: id 0 | task 44218 | total time = 5745.51 ms / 468 tokens 13.38.258.925 I slot print_timing: id 0 | task 44218 | graphs reused = 43608 13.38.258.925 I slot print_timing: id 0 | task 44218 | graph reallocs = 0 / 0 (same size) / (changed size) 13.38.258.944 I slot release: id 0 | task 44218 | stop processing: n_tokens = 467, truncated = 0 13.38.262.242 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.151 (> 0.100 thold), f_keep = 0.045 13.38.263.458 I slot launch_slot_: id 0 | task 44550 | processing task, is_child = 0 13.41.621.988 I slot print_timing: id 0 | task 44550 | n_gen = 184, tg = 60.81 t/s, tg_3s = 61.15 t/s 13.44.627.127 I slot print_timing: id 0 | task 44550 | n_gen = 367, tg = 60.85 t/s, tg_3s = 60.90 t/s 13.44.892.454 I slot print_timing: id 0 | task 44550 | prompt eval time = 349.36 ms / 139 tokens ( 2.51 ms per token, 397.87 tokens per second) 13.44.892.460 I slot print_timing: id 0 | task 44550 | eval time = 6279.63 ms / 383 tokens ( 16.44 ms per token, 60.83 tokens per second) 13.44.892.460 I slot print_timing: id 0 | task 44550 | total time = 6628.99 ms / 522 tokens 13.44.892.461 I slot print_timing: id 0 | task 44550 | graphs reused = 43987 13.44.892.461 I slot print_timing: id 0 | task 44550 | graph reallocs = 0 / 0 (same size) / (changed size) 13.44.892.481 I slot release: id 0 | task 44550 | stop processing: n_tokens = 521, truncated = 0 13.44.895.915 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.134 (> 0.100 thold), f_keep = 0.040 13.44.897.152 I slot launch_slot_: id 0 | task 44935 | processing task, is_child = 0 13.48.270.058 I slot print_timing: id 0 | task 44935 | n_gen = 183, tg = 60.45 t/s, tg_3s = 60.78 t/s 13.48.713.015 I slot print_timing: id 0 | task 44935 | prompt eval time = 362.23 ms / 157 tokens ( 2.31 ms per token, 433.43 tokens per second) 13.48.713.021 I slot print_timing: id 0 | task 44935 | eval time = 3453.62 ms / 210 tokens ( 16.52 ms per token, 60.52 tokens per second) 13.48.713.022 I slot print_timing: id 0 | task 44935 | total time = 3815.85 ms / 367 tokens 13.48.713.022 I slot print_timing: id 0 | task 44935 | graphs reused = 44194 13.48.713.023 I slot print_timing: id 0 | task 44935 | graph reallocs = 0 / 0 (same size) / (changed size) 13.48.713.044 I slot release: id 0 | task 44935 | stop processing: n_tokens = 366, truncated = 0 13.48.716.506 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.129 (> 0.100 thold), f_keep = 0.057 13.48.717.509 I slot launch_slot_: id 0 | task 45147 | processing task, is_child = 0 13.52.090.392 I slot print_timing: id 0 | task 45147 | n_gen = 184, tg = 60.97 t/s, tg_3s = 61.30 t/s 13.54.578.269 I slot print_timing: id 0 | task 45147 | prompt eval time = 371.18 ms / 163 tokens ( 2.28 ms per token, 439.14 tokens per second) 13.54.578.275 I slot print_timing: id 0 | task 45147 | eval time = 5489.57 ms / 335 tokens ( 16.44 ms per token, 60.84 tokens per second) 13.54.578.276 I slot print_timing: id 0 | task 45147 | total time = 5860.75 ms / 498 tokens 13.54.578.276 I slot print_timing: id 0 | task 45147 | graphs reused = 44526 13.54.578.277 I slot print_timing: id 0 | task 45147 | graph reallocs = 0 / 0 (same size) / (changed size) 13.54.578.299 I slot release: id 0 | task 45147 | stop processing: n_tokens = 497, truncated = 0 13.54.581.767 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 13.54.583.071 I slot launch_slot_: id 0 | task 45484 | processing task, is_child = 0 13.57.960.782 I slot print_timing: id 0 | task 45484 | n_gen = 185, tg = 61.07 t/s, tg_3s = 61.40 t/s 13.59.389.977 I slot print_timing: id 0 | task 45484 | prompt eval time = 364.52 ms / 157 tokens ( 2.32 ms per token, 430.70 tokens per second) 13.59.389.984 I slot print_timing: id 0 | task 45484 | eval time = 4442.38 ms / 272 tokens ( 16.39 ms per token, 61.00 tokens per second) 13.59.389.985 I slot print_timing: id 0 | task 45484 | total time = 4806.90 ms / 429 tokens 13.59.389.985 I slot print_timing: id 0 | task 45484 | graphs reused = 44795 13.59.389.986 I slot print_timing: id 0 | task 45484 | graph reallocs = 0 / 0 (same size) / (changed size) 13.59.390.008 I slot release: id 0 | task 45484 | stop processing: n_tokens = 428, truncated = 0 13.59.393.310 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.134 (> 0.100 thold), f_keep = 0.049 13.59.394.437 I slot launch_slot_: id 0 | task 45758 | processing task, is_child = 0 14.02.757.664 I slot print_timing: id 0 | task 45758 | n_gen = 184, tg = 60.99 t/s, tg_3s = 61.32 t/s 14.05.765.073 I slot print_timing: id 0 | task 45758 | n_gen = 367, tg = 60.92 t/s, tg_3s = 60.85 t/s 14.07.939.698 I slot print_timing: id 0 | task 45758 | prompt eval time = 362.69 ms / 157 tokens ( 2.31 ms per token, 432.88 tokens per second) 14.07.939.702 I slot print_timing: id 0 | task 45758 | eval time = 8182.56 ms / 499 tokens ( 16.43 ms per token, 60.86 tokens per second) 14.07.939.702 I slot print_timing: id 0 | task 45758 | total time = 8545.25 ms / 656 tokens 14.07.939.703 I slot print_timing: id 0 | task 45758 | graphs reused = 45290 14.07.939.703 I slot print_timing: id 0 | task 45758 | graph reallocs = 0 / 0 (same size) / (changed size) 14.07.939.724 I slot release: id 0 | task 45758 | stop processing: n_tokens = 655, truncated = 0 14.07.943.013 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.134 (> 0.100 thold), f_keep = 0.032 14.07.944.528 I slot launch_slot_: id 0 | task 46259 | processing task, is_child = 0 14.11.309.060 I slot print_timing: id 0 | task 46259 | n_gen = 184, tg = 60.96 t/s, tg_3s = 61.29 t/s 14.14.017.015 I slot print_timing: id 0 | task 46259 | prompt eval time = 362.62 ms / 157 tokens ( 2.31 ms per token, 432.96 tokens per second) 14.14.017.018 I slot print_timing: id 0 | task 46259 | eval time = 5709.85 ms / 349 tokens ( 16.41 ms per token, 60.95 tokens per second) 14.14.017.019 I slot print_timing: id 0 | task 46259 | total time = 6072.47 ms / 506 tokens 14.14.017.019 I slot print_timing: id 0 | task 46259 | graphs reused = 45636 14.14.017.020 I slot print_timing: id 0 | task 46259 | graph reallocs = 0 / 0 (same size) / (changed size) 14.14.017.044 I slot release: id 0 | task 46259 | stop processing: n_tokens = 505, truncated = 0 14.14.020.479 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.122 (> 0.100 thold), f_keep = 0.042 14.14.021.676 I slot launch_slot_: id 0 | task 46610 | processing task, is_child = 0 14.15.635.524 I slot print_timing: id 0 | task 46610 | prompt eval time = 382.85 ms / 172 tokens ( 2.23 ms per token, 449.26 tokens per second) 14.15.635.527 I slot print_timing: id 0 | task 46610 | eval time = 1230.99 ms / 76 tokens ( 16.41 ms per token, 60.93 tokens per second) 14.15.635.528 I slot print_timing: id 0 | task 46610 | total time = 1613.84 ms / 248 tokens 14.15.635.528 I slot print_timing: id 0 | task 46610 | graphs reused = 45710 14.15.635.529 I slot print_timing: id 0 | task 46610 | graph reallocs = 0 / 0 (same size) / (changed size) 14.15.635.556 I slot release: id 0 | task 46610 | stop processing: n_tokens = 247, truncated = 0 14.15.638.888 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.135 (> 0.100 thold), f_keep = 0.089 14.15.639.652 I slot launch_slot_: id 0 | task 46688 | processing task, is_child = 0 14.19.010.388 I slot print_timing: id 0 | task 46688 | n_gen = 184, tg = 60.87 t/s, tg_3s = 61.20 t/s 14.19.142.713 I slot print_timing: id 0 | task 46688 | prompt eval time = 364.38 ms / 163 tokens ( 2.24 ms per token, 447.34 tokens per second) 14.19.142.716 I slot print_timing: id 0 | task 46688 | eval time = 3138.67 ms / 192 tokens ( 16.43 ms per token, 60.85 tokens per second) 14.19.142.717 I slot print_timing: id 0 | task 46688 | total time = 3503.05 ms / 355 tokens 14.19.142.718 I slot print_timing: id 0 | task 46688 | graphs reused = 45899 14.19.142.718 I slot print_timing: id 0 | task 46688 | graph reallocs = 0 / 0 (same size) / (changed size) 14.19.142.740 I slot release: id 0 | task 46688 | stop processing: n_tokens = 354, truncated = 0 14.19.145.993 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.127 (> 0.100 thold), f_keep = 0.059 14.19.147.117 I slot launch_slot_: id 0 | task 46882 | processing task, is_child = 0 14.22.528.753 I slot print_timing: id 0 | task 46882 | n_gen = 184, tg = 60.96 t/s, tg_3s = 61.29 t/s 14.24.037.388 I slot print_timing: id 0 | task 46882 | prompt eval time = 379.58 ms / 165 tokens ( 2.30 ms per token, 434.69 tokens per second) 14.24.037.392 I slot print_timing: id 0 | task 46882 | eval time = 4510.67 ms / 276 tokens ( 16.40 ms per token, 60.97 tokens per second) 14.24.037.392 I slot print_timing: id 0 | task 46882 | total time = 4890.25 ms / 441 tokens 14.24.037.393 I slot print_timing: id 0 | task 46882 | graphs reused = 46172 14.24.037.393 I slot print_timing: id 0 | task 46882 | graph reallocs = 0 / 0 (same size) / (changed size) 14.24.037.417 I slot release: id 0 | task 46882 | stop processing: n_tokens = 440, truncated = 0 14.24.040.910 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.121 (> 0.100 thold), f_keep = 0.048 14.24.041.988 I slot launch_slot_: id 0 | task 47160 | processing task, is_child = 0 14.27.430.628 I slot print_timing: id 0 | task 47160 | n_gen = 184, tg = 60.92 t/s, tg_3s = 61.25 t/s 14.29.219.648 I slot print_timing: id 0 | task 47160 | prompt eval time = 384.76 ms / 173 tokens ( 2.22 ms per token, 449.63 tokens per second) 14.29.219.652 I slot print_timing: id 0 | task 47160 | eval time = 4792.89 ms / 293 tokens ( 16.41 ms per token, 60.92 tokens per second) 14.29.219.652 I slot print_timing: id 0 | task 47160 | total time = 5177.65 ms / 466 tokens 14.29.219.653 I slot print_timing: id 0 | task 47160 | graphs reused = 46462 14.29.219.653 I slot print_timing: id 0 | task 47160 | graph reallocs = 0 / 0 (same size) / (changed size) 14.29.219.681 I slot release: id 0 | task 47160 | stop processing: n_tokens = 465, truncated = 0 14.29.223.263 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 14.29.224.536 I slot launch_slot_: id 0 | task 47455 | processing task, is_child = 0 14.32.449.870 I slot print_timing: id 0 | task 47455 | prompt eval time = 397.86 ms / 190 tokens ( 2.09 ms per token, 477.55 tokens per second) 14.32.449.874 I slot print_timing: id 0 | task 47455 | eval time = 2827.45 ms / 173 tokens ( 16.44 ms per token, 60.83 tokens per second) 14.32.449.874 I slot print_timing: id 0 | task 47455 | total time = 3225.32 ms / 363 tokens 14.32.449.875 I slot print_timing: id 0 | task 47455 | graphs reused = 46632 14.32.449.875 I slot print_timing: id 0 | task 47455 | graph reallocs = 0 / 0 (same size) / (changed size) 14.32.449.901 I slot release: id 0 | task 47455 | stop processing: n_tokens = 362, truncated = 0 14.32.453.350 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.121 (> 0.100 thold), f_keep = 0.058 14.32.454.354 I slot launch_slot_: id 0 | task 47630 | processing task, is_child = 0 14.35.845.406 I slot print_timing: id 0 | task 47630 | n_gen = 184, tg = 60.90 t/s, tg_3s = 61.24 t/s 14.38.657.981 I slot print_timing: id 0 | task 47630 | prompt eval time = 386.33 ms / 173 tokens ( 2.23 ms per token, 447.81 tokens per second) 14.38.657.987 I slot print_timing: id 0 | task 47630 | eval time = 5817.29 ms / 355 tokens ( 16.43 ms per token, 60.85 tokens per second) 14.38.657.988 I slot print_timing: id 0 | task 47630 | total time = 6203.62 ms / 528 tokens 14.38.657.989 I slot print_timing: id 0 | task 47630 | graphs reused = 46983 14.38.657.989 I slot print_timing: id 0 | task 47630 | graph reallocs = 0 / 0 (same size) / (changed size) 14.38.658.011 I slot release: id 0 | task 47630 | stop processing: n_tokens = 527, truncated = 0 14.38.661.575 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.111 (> 0.100 thold), f_keep = 0.040 14.38.662.864 I slot launch_slot_: id 0 | task 47987 | processing task, is_child = 0 14.42.054.500 I slot print_timing: id 0 | task 47987 | n_gen = 184, tg = 60.99 t/s, tg_3s = 61.33 t/s 14.44.704.750 I slot print_timing: id 0 | task 47987 | prompt eval time = 391.38 ms / 190 tokens ( 2.06 ms per token, 485.47 tokens per second) 14.44.704.753 I slot print_timing: id 0 | task 47987 | eval time = 5650.50 ms / 345 tokens ( 16.43 ms per token, 60.88 tokens per second) 14.44.704.754 I slot print_timing: id 0 | task 47987 | total time = 6041.87 ms / 535 tokens 14.44.704.754 I slot print_timing: id 0 | task 47987 | graphs reused = 47324 14.44.704.755 I slot print_timing: id 0 | task 47987 | graph reallocs = 0 / 0 (same size) / (changed size) 14.44.704.776 I slot release: id 0 | task 47987 | stop processing: n_tokens = 534, truncated = 0 14.44.708.171 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.126 (> 0.100 thold), f_keep = 0.043 14.44.709.475 I slot launch_slot_: id 0 | task 48334 | processing task, is_child = 0 14.48.107.171 I slot print_timing: id 0 | task 48334 | n_gen = 184, tg = 60.83 t/s, tg_3s = 61.17 t/s 14.51.113.712 I slot print_timing: id 0 | task 48334 | n_gen = 366, tg = 60.68 t/s, tg_3s = 60.53 t/s 14.53.300.635 I slot print_timing: id 0 | task 48334 | prompt eval time = 389.50 ms / 183 tokens ( 2.13 ms per token, 469.84 tokens per second) 14.53.300.638 I slot print_timing: id 0 | task 48334 | eval time = 8201.66 ms / 499 tokens ( 16.47 ms per token, 60.72 tokens per second) 14.53.300.639 I slot print_timing: id 0 | task 48334 | total time = 8591.15 ms / 682 tokens 14.53.300.639 I slot print_timing: id 0 | task 48334 | graphs reused = 47819 14.53.300.640 I slot print_timing: id 0 | task 48334 | graph reallocs = 0 / 0 (same size) / (changed size) 14.53.300.663 I slot release: id 0 | task 48334 | stop processing: n_tokens = 681, truncated = 0 14.53.304.165 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 681, t_last = 342338380540 14.53.305.749 I slot launch_slot_: id 0 | task 48835 | processing task, is_child = 0 14.56.742.078 I slot print_timing: id 0 | task 48835 | n_gen = 184, tg = 60.73 t/s, tg_3s = 61.06 t/s 14.57.005.459 I slot print_timing: id 0 | task 48835 | prompt eval time = 423.11 ms / 222 tokens ( 1.91 ms per token, 524.68 tokens per second) 14.57.005.463 I slot print_timing: id 0 | task 48835 | eval time = 3276.59 ms / 200 tokens ( 16.47 ms per token, 60.73 tokens per second) 14.57.005.463 I slot print_timing: id 0 | task 48835 | total time = 3699.70 ms / 422 tokens 14.57.005.464 I slot print_timing: id 0 | task 48835 | graphs reused = 48016 14.57.005.465 I slot print_timing: id 0 | task 48835 | graph reallocs = 0 / 0 (same size) / (changed size) 14.57.005.493 I slot release: id 0 | task 48835 | stop processing: n_tokens = 421, truncated = 0 14.57.008.827 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.129 (> 0.100 thold), f_keep = 0.050 14.57.009.900 I slot launch_slot_: id 0 | task 49037 | processing task, is_child = 0 15.00.376.780 I slot print_timing: id 0 | task 49037 | n_gen = 183, tg = 60.61 t/s, tg_3s = 60.95 t/s 15.01.050.988 I slot print_timing: id 0 | task 49037 | prompt eval time = 364.29 ms / 163 tokens ( 2.23 ms per token, 447.45 tokens per second) 15.01.050.994 I slot print_timing: id 0 | task 49037 | eval time = 3676.79 ms / 224 tokens ( 16.49 ms per token, 60.65 tokens per second) 15.01.050.995 I slot print_timing: id 0 | task 49037 | total time = 4041.08 ms / 387 tokens 15.01.050.995 I slot print_timing: id 0 | task 49037 | graphs reused = 48237 15.01.050.996 I slot print_timing: id 0 | task 49037 | graph reallocs = 0 / 0 (same size) / (changed size) 15.01.051.017 I slot release: id 0 | task 49037 | stop processing: n_tokens = 386, truncated = 0 15.01.525.224 I srv operator(): operator(): cleaning up before exit...