$ /Users/minipro/quantdiff/llama.cpp/llama-b11770/llama-server -m /Users/minipro/quantdiff/models/campaign/a235d23638cc/LFM2.5-24B-A2B-UD-Q4_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 0.00.042.790 I srv llama_server: initializing ... 0.00.042.798 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.042.881 I srv init_listene: The UI is disabled 0.00.042.882 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.042.917 W srv llama_server: security: no API key is set and CORS allows all origins (see https://github.com/ggml-org/llama.cpp/pull/25655) 0.00.044.590 I srv load_model: loading model '/Users/minipro/quantdiff/models/campaign/a235d23638cc/LFM2.5-24B-A2B-UD-Q4_K_XL.gguf' 0.01.026.233 I cmn init: llama threadpool init, n_threads = 8 0.01.205.960 I srv load_model: initializing, n_slots = 1, n_ctx_slot = 4096, kv_unified = 'false' 0.01.208.883 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.01.208.897 I srv llama_server: model loaded 0.01.208.899 I srv llama_server: listening on http://127.0.0.1:8089 0.02.022.369 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.02.022.590 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.03.911.780 I slot print_timing: id 0 | task 0 | prompt eval time = 376.01 ms / 172 tokens ( 2.19 ms per token, 457.43 tokens per second) 0.03.911.783 I slot print_timing: id 0 | task 0 | eval time = 1513.16 ms / 103 tokens ( 14.83 ms per token, 67.41 tokens per second) 0.03.911.783 I slot print_timing: id 0 | task 0 | total time = 1889.17 ms / 275 tokens 0.03.911.784 I slot print_timing: id 0 | task 0 | graphs reused = 101 0.03.911.784 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.03.911.805 I slot release: id 0 | task 0 | stop processing: n_tokens = 274, truncated = 0 0.03.915.223 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.077 0.03.915.605 I slot launch_slot_: id 0 | task 105 | processing task, is_child = 0 0.05.234.147 I slot print_timing: id 0 | task 105 | prompt eval time = 361.52 ms / 123 tokens ( 2.94 ms per token, 340.23 tokens per second) 0.05.234.153 I slot print_timing: id 0 | task 105 | eval time = 957.01 ms / 65 tokens ( 14.95 ms per token, 66.87 tokens per second) 0.05.234.154 I slot print_timing: id 0 | task 105 | total time = 1318.53 ms / 188 tokens 0.05.234.155 I slot print_timing: id 0 | task 105 | graphs reused = 164 0.05.234.155 I slot print_timing: id 0 | task 105 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.234.176 I slot release: id 0 | task 105 | stop processing: n_tokens = 187, truncated = 0 0.05.237.456 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.129 (> 0.100 thold), f_keep = 0.112 0.05.237.785 I slot launch_slot_: id 0 | task 172 | processing task, is_child = 0 0.06.901.200 I slot print_timing: id 0 | task 172 | prompt eval time = 336.81 ms / 163 tokens ( 2.07 ms per token, 483.96 tokens per second) 0.06.901.203 I slot print_timing: id 0 | task 172 | eval time = 1326.59 ms / 90 tokens ( 14.91 ms per token, 67.09 tokens per second) 0.06.901.203 I slot print_timing: id 0 | task 172 | total time = 1663.40 ms / 253 tokens 0.06.901.204 I slot print_timing: id 0 | task 172 | graphs reused = 252 0.06.901.204 I slot print_timing: id 0 | task 172 | graph reallocs = 0 / 0 (same size) / (changed size) 0.06.901.225 I slot release: id 0 | task 172 | stop processing: n_tokens = 252, truncated = 0 0.06.904.566 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.103 (> 0.100 thold), f_keep = 0.083 0.06.905.326 I slot launch_slot_: id 0 | task 264 | processing task, is_child = 0 0.09.780.941 I slot print_timing: id 0 | task 264 | prompt eval time = 381.67 ms / 204 tokens ( 1.87 ms per token, 534.50 tokens per second) 0.09.780.944 I slot print_timing: id 0 | task 264 | eval time = 2493.94 ms / 169 tokens ( 14.84 ms per token, 67.36 tokens per second) 0.09.780.946 I slot print_timing: id 0 | task 264 | total time = 2875.61 ms / 373 tokens 0.09.780.946 I slot print_timing: id 0 | task 264 | graphs reused = 418 0.09.780.947 I slot print_timing: id 0 | task 264 | graph reallocs = 0 / 0 (same size) / (changed size) 0.09.780.970 I slot release: id 0 | task 264 | stop processing: n_tokens = 372, truncated = 0 0.09.784.374 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.187 (> 0.100 thold), f_keep = 0.097 0.09.785.268 I slot launch_slot_: id 0 | task 435 | processing task, is_child = 0 0.12.527.743 I slot print_timing: id 0 | task 435 | prompt eval time = 365.54 ms / 193 tokens ( 1.89 ms per token, 527.98 tokens per second) 0.12.527.748 I slot print_timing: id 0 | task 435 | eval time = 2376.92 ms / 161 tokens ( 14.86 ms per token, 67.31 tokens per second) 0.12.527.749 I slot print_timing: id 0 | task 435 | total time = 2742.46 ms / 354 tokens 0.12.527.750 I slot print_timing: id 0 | task 435 | graphs reused = 576 0.12.527.750 I slot print_timing: id 0 | task 435 | graph reallocs = 0 / 0 (same size) / (changed size) 0.12.527.771 I slot release: id 0 | task 435 | stop processing: n_tokens = 353, truncated = 0 0.12.530.987 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 0.12.531.890 I slot launch_slot_: id 0 | task 598 | processing task, is_child = 0 0.14.337.252 I slot print_timing: id 0 | task 598 | prompt eval time = 355.96 ms / 174 tokens ( 2.05 ms per token, 488.81 tokens per second) 0.14.337.257 I slot print_timing: id 0 | task 598 | eval time = 1449.39 ms / 98 tokens ( 14.94 ms per token, 66.92 tokens per second) 0.14.337.258 I slot print_timing: id 0 | task 598 | total time = 1805.35 ms / 272 tokens 0.14.337.258 I slot print_timing: id 0 | task 598 | graphs reused = 671 0.14.337.259 I slot print_timing: id 0 | task 598 | graph reallocs = 0 / 0 (same size) / (changed size) 0.14.337.279 I slot release: id 0 | task 598 | stop processing: n_tokens = 271, truncated = 0 0.14.340.622 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 271, t_last = 334558868294 0.14.341.354 I slot launch_slot_: id 0 | task 698 | processing task, is_child = 0 0.17.364.296 I slot print_timing: id 0 | task 698 | prompt eval time = 393.54 ms / 224 tokens ( 1.76 ms per token, 569.19 tokens per second) 0.17.364.302 I slot print_timing: id 0 | task 698 | eval time = 2629.39 ms / 178 tokens ( 14.86 ms per token, 67.32 tokens per second) 0.17.364.302 I slot print_timing: id 0 | task 698 | total time = 3022.93 ms / 402 tokens 0.17.364.303 I slot print_timing: id 0 | task 698 | graphs reused = 846 0.17.364.303 I slot print_timing: id 0 | task 698 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.364.326 I slot release: id 0 | task 698 | stop processing: n_tokens = 401, truncated = 0 0.17.367.772 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 401, t_last = 334561895341 0.17.368.810 I slot launch_slot_: id 0 | task 878 | processing task, is_child = 0 0.20.816.669 I slot print_timing: id 0 | task 878 | n_gen = 204, tg = 67.52 t/s, tg_3s = 67.86 t/s 0.22.228.364 I slot print_timing: id 0 | task 878 | prompt eval time = 441.54 ms / 266 tokens ( 1.66 ms per token, 602.44 tokens per second) 0.22.228.370 I slot print_timing: id 0 | task 878 | eval time = 4418.01 ms / 299 tokens ( 14.83 ms per token, 67.45 tokens per second) 0.22.228.370 I slot print_timing: id 0 | task 878 | total time = 4859.54 ms / 565 tokens 0.22.228.371 I slot print_timing: id 0 | task 878 | graphs reused = 1142 0.22.228.371 I slot print_timing: id 0 | task 878 | graph reallocs = 0 / 0 (same size) / (changed size) 0.22.228.397 I slot release: id 0 | task 878 | stop processing: n_tokens = 564, truncated = 0 0.22.231.565 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.143 (> 0.100 thold), f_keep = 0.037 0.22.232.827 I slot launch_slot_: id 0 | task 1179 | processing task, is_child = 0 0.23.729.401 I slot print_timing: id 0 | task 1179 | prompt eval time = 329.00 ms / 147 tokens ( 2.24 ms per token, 446.82 tokens per second) 0.23.729.407 I slot print_timing: id 0 | task 1179 | eval time = 1167.57 ms / 79 tokens ( 14.97 ms per token, 66.81 tokens per second) 0.23.729.408 I slot print_timing: id 0 | task 1179 | total time = 1496.57 ms / 226 tokens 0.23.729.408 I slot print_timing: id 0 | task 1179 | graphs reused = 1219 0.23.729.409 I slot print_timing: id 0 | task 1179 | graph reallocs = 0 / 0 (same size) / (changed size) 0.23.729.428 I slot release: id 0 | task 1179 | stop processing: n_tokens = 225, truncated = 0 0.23.732.725 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 0.23.733.441 I slot launch_slot_: id 0 | task 1260 | processing task, is_child = 0 0.25.758.165 I slot print_timing: id 0 | task 1260 | prompt eval time = 350.12 ms / 166 tokens ( 2.11 ms per token, 474.12 tokens per second) 0.25.758.171 I slot print_timing: id 0 | task 1260 | eval time = 1674.59 ms / 113 tokens ( 14.95 ms per token, 66.88 tokens per second) 0.25.758.171 I slot print_timing: id 0 | task 1260 | total time = 2024.71 ms / 279 tokens 0.25.758.172 I slot print_timing: id 0 | task 1260 | graphs reused = 1329 0.25.758.173 I slot print_timing: id 0 | task 1260 | graph reallocs = 0 / 0 (same size) / (changed size) 0.25.758.192 I slot release: id 0 | task 1260 | stop processing: n_tokens = 278, truncated = 0 0.25.761.582 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 0.25.762.311 I slot launch_slot_: id 0 | task 1375 | processing task, is_child = 0 0.28.457.760 I slot print_timing: id 0 | task 1375 | prompt eval time = 355.21 ms / 175 tokens ( 2.03 ms per token, 492.67 tokens per second) 0.28.457.763 I slot print_timing: id 0 | task 1375 | eval time = 2340.24 ms / 159 tokens ( 14.81 ms per token, 67.51 tokens per second) 0.28.457.763 I slot print_timing: id 0 | task 1375 | total time = 2695.44 ms / 334 tokens 0.28.457.764 I slot print_timing: id 0 | task 1375 | graphs reused = 1485 0.28.457.764 I slot print_timing: id 0 | task 1375 | graph reallocs = 0 / 0 (same size) / (changed size) 0.28.457.789 I slot release: id 0 | task 1375 | stop processing: n_tokens = 333, truncated = 0 0.28.461.160 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 333, t_last = 334572988804 0.28.462.022 I slot launch_slot_: id 0 | task 1536 | processing task, is_child = 0 0.31.007.515 I slot print_timing: id 0 | task 1536 | prompt eval time = 390.19 ms / 215 tokens ( 1.81 ms per token, 551.01 tokens per second) 0.31.007.520 I slot print_timing: id 0 | task 1536 | eval time = 2155.29 ms / 146 tokens ( 14.86 ms per token, 67.28 tokens per second) 0.31.007.521 I slot print_timing: id 0 | task 1536 | total time = 2545.49 ms / 361 tokens 0.31.007.521 I slot print_timing: id 0 | task 1536 | graphs reused = 1628 0.31.007.522 I slot print_timing: id 0 | task 1536 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.007.547 I slot release: id 0 | task 1536 | stop processing: n_tokens = 360, truncated = 0 0.31.010.953 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.119 (> 0.100 thold), f_keep = 0.058 0.31.011.941 I slot launch_slot_: id 0 | task 1684 | processing task, is_child = 0 0.33.166.553 I slot print_timing: id 0 | task 1684 | prompt eval time = 359.63 ms / 177 tokens ( 2.03 ms per token, 492.18 tokens per second) 0.33.166.559 I slot print_timing: id 0 | task 1684 | eval time = 1794.98 ms / 121 tokens ( 14.96 ms per token, 66.85 tokens per second) 0.33.166.559 I slot print_timing: id 0 | task 1684 | total time = 2154.60 ms / 298 tokens 0.33.166.560 I slot print_timing: id 0 | task 1684 | graphs reused = 1746 0.33.166.561 I slot print_timing: id 0 | task 1684 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.166.581 I slot release: id 0 | task 1684 | stop processing: n_tokens = 297, truncated = 0 0.33.169.896 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 0.33.170.752 I slot launch_slot_: id 0 | task 1807 | processing task, is_child = 0 0.34.778.185 I slot print_timing: id 0 | task 1807 | prompt eval time = 359.17 ms / 181 tokens ( 1.98 ms per token, 503.93 tokens per second) 0.34.778.190 I slot print_timing: id 0 | task 1807 | eval time = 1248.25 ms / 85 tokens ( 14.86 ms per token, 67.29 tokens per second) 0.34.778.191 I slot print_timing: id 0 | task 1807 | total time = 1607.42 ms / 266 tokens 0.34.778.192 I slot print_timing: id 0 | task 1807 | graphs reused = 1828 0.34.778.192 I slot print_timing: id 0 | task 1807 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.778.220 I slot release: id 0 | task 1807 | stop processing: n_tokens = 265, truncated = 0 0.34.781.467 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.122 (> 0.100 thold), f_keep = 0.079 0.34.782.244 I slot launch_slot_: id 0 | task 1894 | processing task, is_child = 0 0.36.844.211 I slot print_timing: id 0 | task 1894 | prompt eval time = 355.39 ms / 172 tokens ( 2.07 ms per token, 483.98 tokens per second) 0.36.844.216 I slot print_timing: id 0 | task 1894 | eval time = 1706.57 ms / 116 tokens ( 14.84 ms per token, 67.39 tokens per second) 0.36.844.217 I slot print_timing: id 0 | task 1894 | total time = 2061.96 ms / 288 tokens 0.36.844.217 I slot print_timing: id 0 | task 1894 | graphs reused = 1941 0.36.844.218 I slot print_timing: id 0 | task 1894 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.844.240 I slot release: id 0 | task 1894 | stop processing: n_tokens = 287, truncated = 0 0.36.847.561 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.138 (> 0.100 thold), f_keep = 0.073 0.36.848.365 I slot launch_slot_: id 0 | task 2012 | processing task, is_child = 0 0.39.126.151 I slot print_timing: id 0 | task 2012 | prompt eval time = 327.77 ms / 152 tokens ( 2.16 ms per token, 463.74 tokens per second) 0.39.126.157 I slot print_timing: id 0 | task 2012 | eval time = 1950.01 ms / 132 tokens ( 14.89 ms per token, 67.18 tokens per second) 0.39.126.158 I slot print_timing: id 0 | task 2012 | total time = 2277.78 ms / 284 tokens 0.39.126.158 I slot print_timing: id 0 | task 2012 | graphs reused = 2070 0.39.126.159 I slot print_timing: id 0 | task 2012 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.126.178 I slot release: id 0 | task 2012 | stop processing: n_tokens = 283, truncated = 0 0.39.129.443 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 0.39.130.261 I slot launch_slot_: id 0 | task 2146 | processing task, is_child = 0 0.42.486.573 I slot print_timing: id 0 | task 2146 | n_gen = 204, tg = 67.58 t/s, tg_3s = 67.91 t/s 0.42.961.962 I slot print_timing: id 0 | task 2146 | prompt eval time = 352.55 ms / 171 tokens ( 2.06 ms per token, 485.04 tokens per second) 0.42.961.967 I slot print_timing: id 0 | task 2146 | eval time = 3479.15 ms / 236 tokens ( 14.80 ms per token, 67.55 tokens per second) 0.42.961.968 I slot print_timing: id 0 | task 2146 | total time = 3831.69 ms / 407 tokens 0.42.961.969 I slot print_timing: id 0 | task 2146 | graphs reused = 2303 0.42.961.969 I slot print_timing: id 0 | task 2146 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.961.990 I slot release: id 0 | task 2146 | stop processing: n_tokens = 406, truncated = 0 0.42.965.200 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.136 (> 0.100 thold), f_keep = 0.052 0.42.966.201 I slot launch_slot_: id 0 | task 2384 | processing task, is_child = 0 0.44.796.334 I slot print_timing: id 0 | task 2384 | prompt eval time = 332.30 ms / 154 tokens ( 2.16 ms per token, 463.44 tokens per second) 0.44.796.340 I slot print_timing: id 0 | task 2384 | eval time = 1497.83 ms / 101 tokens ( 14.98 ms per token, 66.76 tokens per second) 0.44.796.341 I slot print_timing: id 0 | task 2384 | total time = 1830.12 ms / 255 tokens 0.44.796.341 I slot print_timing: id 0 | task 2384 | graphs reused = 2402 0.44.796.342 I slot print_timing: id 0 | task 2384 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.796.361 I slot release: id 0 | task 2384 | stop processing: n_tokens = 254, truncated = 0 0.44.799.555 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.140 (> 0.100 thold), f_keep = 0.083 0.44.800.306 I slot launch_slot_: id 0 | task 2487 | processing task, is_child = 0 0.46.397.228 I slot print_timing: id 0 | task 2487 | prompt eval time = 326.88 ms / 150 tokens ( 2.18 ms per token, 458.88 tokens per second) 0.46.397.234 I slot print_timing: id 0 | task 2487 | eval time = 1270.04 ms / 86 tokens ( 14.94 ms per token, 66.93 tokens per second) 0.46.397.235 I slot print_timing: id 0 | task 2487 | total time = 1596.92 ms / 236 tokens 0.46.397.235 I slot print_timing: id 0 | task 2487 | graphs reused = 2486 0.46.397.236 I slot print_timing: id 0 | task 2487 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.397.254 I slot release: id 0 | task 2487 | stop processing: n_tokens = 235, truncated = 0 0.46.400.511 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 0.46.401.215 I slot launch_slot_: id 0 | task 2575 | processing task, is_child = 0 0.48.622.208 I slot print_timing: id 0 | task 2575 | prompt eval time = 364.08 ms / 190 tokens ( 1.92 ms per token, 521.86 tokens per second) 0.48.622.211 I slot print_timing: id 0 | task 2575 | eval time = 1856.90 ms / 126 tokens ( 14.86 ms per token, 67.32 tokens per second) 0.48.622.212 I slot print_timing: id 0 | task 2575 | total time = 2220.99 ms / 316 tokens 0.48.622.213 I slot print_timing: id 0 | task 2575 | graphs reused = 2609 0.48.622.213 I slot print_timing: id 0 | task 2575 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.622.235 I slot release: id 0 | task 2575 | stop processing: n_tokens = 315, truncated = 0 0.48.625.504 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.131 (> 0.100 thold), f_keep = 0.067 0.48.626.359 I slot launch_slot_: id 0 | task 2703 | processing task, is_child = 0 0.50.578.000 I slot print_timing: id 0 | task 2703 | prompt eval time = 333.42 ms / 160 tokens ( 2.08 ms per token, 479.88 tokens per second) 0.50.578.006 I slot print_timing: id 0 | task 2703 | eval time = 1618.22 ms / 110 tokens ( 14.85 ms per token, 67.36 tokens per second) 0.50.578.007 I slot print_timing: id 0 | task 2703 | total time = 1951.63 ms / 270 tokens 0.50.578.007 I slot print_timing: id 0 | task 2703 | graphs reused = 2716 0.50.578.008 I slot print_timing: id 0 | task 2703 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.578.028 I slot release: id 0 | task 2703 | stop processing: n_tokens = 269, truncated = 0 0.50.581.135 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 269, t_last = 334595109043 0.50.581.905 I slot launch_slot_: id 0 | task 2815 | processing task, is_child = 0 0.52.682.631 I slot print_timing: id 0 | task 2815 | prompt eval time = 393.40 ms / 218 tokens ( 1.80 ms per token, 554.14 tokens per second) 0.52.682.633 I slot print_timing: id 0 | task 2815 | eval time = 1707.31 ms / 116 tokens ( 14.85 ms per token, 67.36 tokens per second) 0.52.682.634 I slot print_timing: id 0 | task 2815 | total time = 2100.71 ms / 334 tokens 0.52.682.634 I slot print_timing: id 0 | task 2815 | graphs reused = 2829 0.52.682.635 I slot print_timing: id 0 | task 2815 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.682.659 I slot release: id 0 | task 2815 | stop processing: n_tokens = 333, truncated = 0 0.52.686.347 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 0.52.687.262 I slot launch_slot_: id 0 | task 2933 | processing task, is_child = 0 0.55.503.789 I slot print_timing: id 0 | task 2933 | prompt eval time = 365.05 ms / 193 tokens ( 1.89 ms per token, 528.69 tokens per second) 0.55.503.796 I slot print_timing: id 0 | task 2933 | eval time = 2451.47 ms / 166 tokens ( 14.86 ms per token, 67.31 tokens per second) 0.55.503.797 I slot print_timing: id 0 | task 2933 | total time = 2816.52 ms / 359 tokens 0.55.503.797 I slot print_timing: id 0 | task 2933 | graphs reused = 2992 0.55.503.798 I slot print_timing: id 0 | task 2933 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.503.823 I slot release: id 0 | task 2933 | stop processing: n_tokens = 358, truncated = 0 0.55.507.324 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 0.55.508.363 I slot launch_slot_: id 0 | task 3101 | processing task, is_child = 0 0.58.864.008 I slot print_timing: id 0 | task 3101 | prompt eval time = 380.85 ms / 201 tokens ( 1.89 ms per token, 527.77 tokens per second) 0.58.864.012 I slot print_timing: id 0 | task 3101 | eval time = 2974.79 ms / 201 tokens ( 14.87 ms per token, 67.23 tokens per second) 0.58.864.013 I slot print_timing: id 0 | task 3101 | total time = 3355.64 ms / 402 tokens 0.58.864.014 I slot print_timing: id 0 | task 3101 | graphs reused = 3190 0.58.864.014 I slot print_timing: id 0 | task 3101 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.864.038 I slot release: id 0 | task 3101 | stop processing: n_tokens = 401, truncated = 0 0.58.867.477 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 401, t_last = 334603395053 0.58.868.504 I slot launch_slot_: id 0 | task 3304 | processing task, is_child = 0 1.01.485.712 I slot print_timing: id 0 | task 3304 | prompt eval time = 414.64 ms / 237 tokens ( 1.75 ms per token, 571.57 tokens per second) 1.01.485.723 I slot print_timing: id 0 | task 3304 | eval time = 2202.55 ms / 149 tokens ( 14.88 ms per token, 67.19 tokens per second) 1.01.485.724 I slot print_timing: id 0 | task 3304 | total time = 2617.19 ms / 386 tokens 1.01.485.724 I slot print_timing: id 0 | task 3304 | graphs reused = 3336 1.01.485.725 I slot print_timing: id 0 | task 3304 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.485.752 I slot release: id 0 | task 3304 | stop processing: n_tokens = 385, truncated = 0 1.01.489.024 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.112 (> 0.100 thold), f_keep = 0.057 1.01.490.051 I slot launch_slot_: id 0 | task 3455 | processing task, is_child = 0 1.03.363.033 I slot print_timing: id 0 | task 3455 | prompt eval time = 368.01 ms / 196 tokens ( 1.88 ms per token, 532.60 tokens per second) 1.03.363.039 I slot print_timing: id 0 | task 3455 | eval time = 1504.97 ms / 102 tokens ( 14.90 ms per token, 67.11 tokens per second) 1.03.363.040 I slot print_timing: id 0 | task 3455 | total time = 1872.98 ms / 298 tokens 1.03.363.041 I slot print_timing: id 0 | task 3455 | graphs reused = 3435 1.03.363.041 I slot print_timing: id 0 | task 3455 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.363.066 I slot release: id 0 | task 3455 | stop processing: n_tokens = 297, truncated = 0 1.03.366.277 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.139 (> 0.100 thold), f_keep = 0.071 1.03.367.181 I slot launch_slot_: id 0 | task 3559 | processing task, is_child = 0 1.04.994.106 I slot print_timing: id 0 | task 3559 | prompt eval time = 336.59 ms / 151 tokens ( 2.23 ms per token, 448.62 tokens per second) 1.04.994.111 I slot print_timing: id 0 | task 3559 | eval time = 1290.32 ms / 88 tokens ( 14.83 ms per token, 67.43 tokens per second) 1.04.994.112 I slot print_timing: id 0 | task 3559 | total time = 1626.91 ms / 239 tokens 1.04.994.112 I slot print_timing: id 0 | task 3559 | graphs reused = 3521 1.04.994.113 I slot print_timing: id 0 | task 3559 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.994.132 I slot release: id 0 | task 3559 | stop processing: n_tokens = 238, truncated = 0 1.04.997.289 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 1.04.998.010 I slot launch_slot_: id 0 | task 3649 | processing task, is_child = 0 1.07.276.309 I slot print_timing: id 0 | task 3649 | prompt eval time = 360.46 ms / 180 tokens ( 2.00 ms per token, 499.35 tokens per second) 1.07.276.315 I slot print_timing: id 0 | task 3649 | eval time = 1917.83 ms / 130 tokens ( 14.87 ms per token, 67.26 tokens per second) 1.07.276.316 I slot print_timing: id 0 | task 3649 | total time = 2278.29 ms / 310 tokens 1.07.276.317 I slot print_timing: id 0 | task 3649 | graphs reused = 3648 1.07.276.317 I slot print_timing: id 0 | task 3649 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.276.337 I slot release: id 0 | task 3649 | stop processing: n_tokens = 309, truncated = 0 1.07.279.972 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 309, t_last = 334611807352 1.07.281.070 I slot launch_slot_: id 0 | task 3781 | processing task, is_child = 0 1.10.048.424 I slot print_timing: id 0 | task 3781 | prompt eval time = 391.56 ms / 211 tokens ( 1.86 ms per token, 538.88 tokens per second) 1.10.048.430 I slot print_timing: id 0 | task 3781 | eval time = 2375.79 ms / 161 tokens ( 14.85 ms per token, 67.35 tokens per second) 1.10.048.431 I slot print_timing: id 0 | task 3781 | total time = 2767.34 ms / 372 tokens 1.10.048.431 I slot print_timing: id 0 | task 3781 | graphs reused = 3806 1.10.048.432 I slot print_timing: id 0 | task 3781 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.048.455 I slot release: id 0 | task 3781 | stop processing: n_tokens = 371, truncated = 0 1.10.051.834 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.113 (> 0.100 thold), f_keep = 0.057 1.10.052.904 I slot launch_slot_: id 0 | task 3944 | processing task, is_child = 0 1.12.229.659 I slot print_timing: id 0 | task 3944 | prompt eval time = 368.14 ms / 186 tokens ( 1.98 ms per token, 505.25 tokens per second) 1.12.229.664 I slot print_timing: id 0 | task 3944 | eval time = 1808.61 ms / 122 tokens ( 14.95 ms per token, 66.90 tokens per second) 1.12.229.665 I slot print_timing: id 0 | task 3944 | total time = 2176.75 ms / 308 tokens 1.12.229.666 I slot print_timing: id 0 | task 3944 | graphs reused = 3925 1.12.229.666 I slot print_timing: id 0 | task 3944 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.229.687 I slot release: id 0 | task 3944 | stop processing: n_tokens = 307, truncated = 0 1.12.232.903 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 1.12.233.801 I slot launch_slot_: id 0 | task 4068 | processing task, is_child = 0 1.14.993.642 I slot print_timing: id 0 | task 4068 | prompt eval time = 339.67 ms / 164 tokens ( 2.07 ms per token, 482.83 tokens per second) 1.14.993.648 I slot print_timing: id 0 | task 4068 | eval time = 2420.17 ms / 164 tokens ( 14.85 ms per token, 67.35 tokens per second) 1.14.993.648 I slot print_timing: id 0 | task 4068 | total time = 2759.83 ms / 328 tokens 1.14.993.649 I slot print_timing: id 0 | task 4068 | graphs reused = 4086 1.14.993.650 I slot print_timing: id 0 | task 4068 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.993.671 I slot release: id 0 | task 4068 | stop processing: n_tokens = 327, truncated = 0 1.14.997.200 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.130 (> 0.100 thold), f_keep = 0.064 1.14.998.305 I slot launch_slot_: id 0 | task 4234 | processing task, is_child = 0 1.17.402.862 I slot print_timing: id 0 | task 4234 | prompt eval time = 340.58 ms / 162 tokens ( 2.10 ms per token, 475.65 tokens per second) 1.17.402.868 I slot print_timing: id 0 | task 4234 | eval time = 2063.96 ms / 140 tokens ( 14.85 ms per token, 67.35 tokens per second) 1.17.402.869 I slot print_timing: id 0 | task 4234 | total time = 2404.55 ms / 302 tokens 1.17.402.869 I slot print_timing: id 0 | task 4234 | graphs reused = 4223 1.17.402.870 I slot print_timing: id 0 | task 4234 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.402.891 I slot release: id 0 | task 4234 | stop processing: n_tokens = 301, truncated = 0 1.17.406.290 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.111 (> 0.100 thold), f_keep = 0.070 1.17.407.169 I slot launch_slot_: id 0 | task 4376 | processing task, is_child = 0 1.20.016.524 I slot print_timing: id 0 | task 4376 | prompt eval time = 366.61 ms / 190 tokens ( 1.93 ms per token, 518.26 tokens per second) 1.20.016.529 I slot print_timing: id 0 | task 4376 | eval time = 2242.74 ms / 152 tokens ( 14.85 ms per token, 67.33 tokens per second) 1.20.016.530 I slot print_timing: id 0 | task 4376 | total time = 2609.35 ms / 342 tokens 1.20.016.531 I slot print_timing: id 0 | task 4376 | graphs reused = 4372 1.20.016.531 I slot print_timing: id 0 | task 4376 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.016.552 I slot release: id 0 | task 4376 | stop processing: n_tokens = 341, truncated = 0 1.20.020.196 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.102 (> 0.100 thold), f_keep = 0.062 1.20.021.435 I slot launch_slot_: id 0 | task 4530 | processing task, is_child = 0 1.22.366.082 I slot print_timing: id 0 | task 4530 | prompt eval time = 386.65 ms / 206 tokens ( 1.88 ms per token, 532.78 tokens per second) 1.22.366.088 I slot print_timing: id 0 | task 4530 | eval time = 1957.99 ms / 132 tokens ( 14.95 ms per token, 66.91 tokens per second) 1.22.366.088 I slot print_timing: id 0 | task 4530 | total time = 2344.64 ms / 338 tokens 1.22.366.089 I slot print_timing: id 0 | task 4530 | graphs reused = 4501 1.22.366.090 I slot print_timing: id 0 | task 4530 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.366.116 I slot release: id 0 | task 4530 | stop processing: n_tokens = 337, truncated = 0 1.22.369.430 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.134 (> 0.100 thold), f_keep = 0.062 1.22.370.391 I slot launch_slot_: id 0 | task 4664 | processing task, is_child = 0 1.24.577.017 I slot print_timing: id 0 | task 4664 | prompt eval time = 335.22 ms / 157 tokens ( 2.14 ms per token, 468.35 tokens per second) 1.24.577.023 I slot print_timing: id 0 | task 4664 | eval time = 1871.40 ms / 127 tokens ( 14.85 ms per token, 67.33 tokens per second) 1.24.577.023 I slot print_timing: id 0 | task 4664 | total time = 2206.62 ms / 284 tokens 1.24.577.024 I slot print_timing: id 0 | task 4664 | graphs reused = 4625 1.24.577.025 I slot print_timing: id 0 | task 4664 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.577.044 I slot release: id 0 | task 4664 | stop processing: n_tokens = 283, truncated = 0 1.24.580.506 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 1.24.581.336 I slot launch_slot_: id 0 | task 4793 | processing task, is_child = 0 1.27.963.470 I slot print_timing: id 0 | task 4793 | n_gen = 203, tg = 67.28 t/s, tg_3s = 67.61 t/s 1.30.972.588 I slot print_timing: id 0 | task 4793 | n_gen = 405, tg = 67.20 t/s, tg_3s = 67.13 t/s 1.31.210.873 I slot print_timing: id 0 | task 4793 | prompt eval time = 379.73 ms / 198 tokens ( 1.92 ms per token, 521.43 tokens per second) 1.31.210.879 I slot print_timing: id 0 | task 4793 | eval time = 6249.80 ms / 421 tokens ( 14.88 ms per token, 67.20 tokens per second) 1.31.210.879 I slot print_timing: id 0 | task 4793 | total time = 6629.53 ms / 619 tokens 1.31.210.880 I slot print_timing: id 0 | task 4793 | graphs reused = 5042 1.31.210.881 I slot print_timing: id 0 | task 4793 | graph reallocs = 0 / 0 (same size) / (changed size) 1.31.210.903 I slot release: id 0 | task 4793 | stop processing: n_tokens = 618, truncated = 0 1.31.214.149 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.168 (> 0.100 thold), f_keep = 0.034 1.31.215.579 I slot launch_slot_: id 0 | task 5216 | processing task, is_child = 0 1.33.039.011 I slot print_timing: id 0 | task 5216 | prompt eval time = 312.41 ms / 125 tokens ( 2.50 ms per token, 400.12 tokens per second) 1.33.039.017 I slot print_timing: id 0 | task 5216 | eval time = 1511.02 ms / 103 tokens ( 14.81 ms per token, 67.50 tokens per second) 1.33.039.019 I slot print_timing: id 0 | task 5216 | total time = 1823.42 ms / 228 tokens 1.33.039.019 I slot print_timing: id 0 | task 5216 | graphs reused = 5143 1.33.039.020 I slot print_timing: id 0 | task 5216 | graph reallocs = 0 / 0 (same size) / (changed size) 1.33.039.037 I slot release: id 0 | task 5216 | stop processing: n_tokens = 227, truncated = 0 1.33.042.158 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 1.33.042.835 I slot launch_slot_: id 0 | task 5321 | processing task, is_child = 0 1.36.372.943 I slot print_timing: id 0 | task 5321 | n_gen = 203, tg = 67.13 t/s, tg_3s = 67.47 t/s 1.38.259.928 I slot print_timing: id 0 | task 5321 | prompt eval time = 321.15 ms / 134 tokens ( 2.40 ms per token, 417.26 tokens per second) 1.38.259.934 I slot print_timing: id 0 | task 5321 | eval time = 4895.94 ms / 330 tokens ( 14.88 ms per token, 67.20 tokens per second) 1.38.259.935 I slot print_timing: id 0 | task 5321 | total time = 5217.08 ms / 464 tokens 1.38.259.936 I slot print_timing: id 0 | task 5321 | graphs reused = 5470 1.38.259.936 I slot print_timing: id 0 | task 5321 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.259.958 I slot release: id 0 | task 5321 | stop processing: n_tokens = 463, truncated = 0 1.38.263.440 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.142 (> 0.100 thold), f_keep = 0.045 1.38.264.649 I slot launch_slot_: id 0 | task 5653 | processing task, is_child = 0 1.40.345.578 I slot print_timing: id 0 | task 5653 | prompt eval time = 332.59 ms / 148 tokens ( 2.25 ms per token, 444.99 tokens per second) 1.40.345.584 I slot print_timing: id 0 | task 5653 | eval time = 1748.33 ms / 119 tokens ( 14.82 ms per token, 67.49 tokens per second) 1.40.345.585 I slot print_timing: id 0 | task 5653 | total time = 2080.92 ms / 267 tokens 1.40.345.585 I slot print_timing: id 0 | task 5653 | graphs reused = 5586 1.40.345.586 I slot print_timing: id 0 | task 5653 | graph reallocs = 0 / 0 (same size) / (changed size) 1.40.345.605 I slot release: id 0 | task 5653 | stop processing: n_tokens = 266, truncated = 0 1.40.348.718 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.149 (> 0.100 thold), f_keep = 0.079 1.40.349.423 I slot launch_slot_: id 0 | task 5774 | processing task, is_child = 0 1.41.688.698 I slot print_timing: id 0 | task 5774 | prompt eval time = 326.44 ms / 141 tokens ( 2.32 ms per token, 431.93 tokens per second) 1.41.688.704 I slot print_timing: id 0 | task 5774 | eval time = 1012.82 ms / 69 tokens ( 14.89 ms per token, 67.14 tokens per second) 1.41.688.704 I slot print_timing: id 0 | task 5774 | total time = 1339.26 ms / 210 tokens 1.41.688.705 I slot print_timing: id 0 | task 5774 | graphs reused = 5653 1.41.688.706 I slot print_timing: id 0 | task 5774 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.688.724 I slot release: id 0 | task 5774 | stop processing: n_tokens = 209, truncated = 0 1.41.691.921 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 1.41.692.532 I slot launch_slot_: id 0 | task 5845 | processing task, is_child = 0 1.43.766.049 I slot print_timing: id 0 | task 5845 | prompt eval time = 367.10 ms / 196 tokens ( 1.87 ms per token, 533.92 tokens per second) 1.43.766.055 I slot print_timing: id 0 | task 5845 | eval time = 1706.41 ms / 116 tokens ( 14.84 ms per token, 67.39 tokens per second) 1.43.766.056 I slot print_timing: id 0 | task 5845 | total time = 2073.51 ms / 312 tokens 1.43.766.056 I slot print_timing: id 0 | task 5845 | graphs reused = 5766 1.43.766.057 I slot print_timing: id 0 | task 5845 | graph reallocs = 0 / 0 (same size) / (changed size) 1.43.766.079 I slot release: id 0 | task 5845 | stop processing: n_tokens = 311, truncated = 0 1.43.769.492 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 311, t_last = 334648297094 1.43.770.307 I slot launch_slot_: id 0 | task 5963 | processing task, is_child = 0 1.47.273.872 I slot print_timing: id 0 | task 5963 | n_gen = 203, tg = 67.25 t/s, tg_3s = 67.58 t/s 1.47.705.947 I slot print_timing: id 0 | task 5963 | prompt eval time = 499.91 ms / 328 tokens ( 1.52 ms per token, 656.11 tokens per second) 1.47.705.953 I slot print_timing: id 0 | task 5963 | eval time = 3435.72 ms / 232 tokens ( 14.87 ms per token, 67.23 tokens per second) 1.47.705.953 I slot print_timing: id 0 | task 5963 | total time = 3935.63 ms / 560 tokens 1.47.705.954 I slot print_timing: id 0 | task 5963 | graphs reused = 5995 1.47.705.954 I slot print_timing: id 0 | task 5963 | graph reallocs = 0 / 0 (same size) / (changed size) 1.47.705.988 I slot release: id 0 | task 5963 | stop processing: n_tokens = 559, truncated = 0 1.47.709.229 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 1.47.710.745 I slot launch_slot_: id 0 | task 6197 | processing task, is_child = 0 1.49.316.090 I slot print_timing: id 0 | task 6197 | prompt eval time = 330.00 ms / 147 tokens ( 2.24 ms per token, 445.45 tokens per second) 1.49.316.095 I slot print_timing: id 0 | task 6197 | eval time = 1275.33 ms / 87 tokens ( 14.83 ms per token, 67.43 tokens per second) 1.49.316.096 I slot print_timing: id 0 | task 6197 | total time = 1605.34 ms / 234 tokens 1.49.316.096 I slot print_timing: id 0 | task 6197 | graphs reused = 6080 1.49.316.097 I slot print_timing: id 0 | task 6197 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.316.118 I slot release: id 0 | task 6197 | stop processing: n_tokens = 233, truncated = 0 1.49.319.524 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.115 (> 0.100 thold), f_keep = 0.090 1.49.320.217 I slot launch_slot_: id 0 | task 6286 | processing task, is_child = 0 1.51.533.684 I slot print_timing: id 0 | task 6286 | prompt eval time = 359.68 ms / 182 tokens ( 1.98 ms per token, 506.01 tokens per second) 1.51.533.690 I slot print_timing: id 0 | task 6286 | eval time = 1853.78 ms / 125 tokens ( 14.95 ms per token, 66.89 tokens per second) 1.51.533.690 I slot print_timing: id 0 | task 6286 | total time = 2213.46 ms / 307 tokens 1.51.533.691 I slot print_timing: id 0 | task 6286 | graphs reused = 6202 1.51.533.691 I slot print_timing: id 0 | task 6286 | graph reallocs = 0 / 0 (same size) / (changed size) 1.51.533.711 I slot release: id 0 | task 6286 | stop processing: n_tokens = 306, truncated = 0 1.51.537.140 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 306, t_last = 334656064727 1.51.538.045 I slot launch_slot_: id 0 | task 6413 | processing task, is_child = 0 1.53.830.674 I slot print_timing: id 0 | task 6413 | prompt eval time = 405.63 ms / 230 tokens ( 1.76 ms per token, 567.02 tokens per second) 1.53.830.681 I slot print_timing: id 0 | task 6413 | eval time = 1886.98 ms / 128 tokens ( 14.86 ms per token, 67.30 tokens per second) 1.53.830.682 I slot print_timing: id 0 | task 6413 | total time = 2292.61 ms / 358 tokens 1.53.830.682 I slot print_timing: id 0 | task 6413 | graphs reused = 6327 1.53.830.683 I slot print_timing: id 0 | task 6413 | graph reallocs = 0 / 0 (same size) / (changed size) 1.53.830.707 I slot release: id 0 | task 6413 | stop processing: n_tokens = 357, truncated = 0 1.53.834.079 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 357, t_last = 334658361722 1.53.835.020 I slot launch_slot_: id 0 | task 6543 | processing task, is_child = 0 1.56.138.481 I slot print_timing: id 0 | task 6543 | prompt eval time = 413.44 ms / 239 tokens ( 1.73 ms per token, 578.08 tokens per second) 1.56.138.486 I slot print_timing: id 0 | task 6543 | eval time = 1890.02 ms / 128 tokens ( 14.88 ms per token, 67.20 tokens per second) 1.56.138.487 I slot print_timing: id 0 | task 6543 | total time = 2303.45 ms / 367 tokens 1.56.138.488 I slot print_timing: id 0 | task 6543 | graphs reused = 6452 1.56.138.488 I slot print_timing: id 0 | task 6543 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.138.513 I slot release: id 0 | task 6543 | stop processing: n_tokens = 366, truncated = 0 1.56.141.644 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.151 (> 0.100 thold), f_keep = 0.066 1.56.142.538 I slot launch_slot_: id 0 | task 6673 | processing task, is_child = 0 1.57.730.644 I slot print_timing: id 0 | task 6673 | prompt eval time = 335.02 ms / 159 tokens ( 2.11 ms per token, 474.59 tokens per second) 1.57.730.650 I slot print_timing: id 0 | task 6673 | eval time = 1253.07 ms / 85 tokens ( 14.92 ms per token, 67.04 tokens per second) 1.57.730.651 I slot print_timing: id 0 | task 6673 | total time = 1588.10 ms / 244 tokens 1.57.730.652 I slot print_timing: id 0 | task 6673 | graphs reused = 6535 1.57.730.652 I slot print_timing: id 0 | task 6673 | graph reallocs = 0 / 0 (same size) / (changed size) 1.57.730.672 I slot release: id 0 | task 6673 | stop processing: n_tokens = 243, truncated = 0 1.57.733.799 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.125 (> 0.100 thold), f_keep = 0.086 1.57.734.519 I slot launch_slot_: id 0 | task 6760 | processing task, is_child = 0 1.59.835.315 I slot print_timing: id 0 | task 6760 | prompt eval time = 356.83 ms / 168 tokens ( 2.12 ms per token, 470.81 tokens per second) 1.59.835.320 I slot print_timing: id 0 | task 6760 | eval time = 1743.96 ms / 118 tokens ( 14.91 ms per token, 67.09 tokens per second) 1.59.835.321 I slot print_timing: id 0 | task 6760 | total time = 2100.79 ms / 286 tokens 1.59.835.321 I slot print_timing: id 0 | task 6760 | graphs reused = 6650 1.59.835.322 I slot print_timing: id 0 | task 6760 | graph reallocs = 0 / 0 (same size) / (changed size) 1.59.835.343 I slot release: id 0 | task 6760 | stop processing: n_tokens = 285, truncated = 0 1.59.838.529 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.119 (> 0.100 thold), f_keep = 0.074 1.59.839.315 I slot launch_slot_: id 0 | task 6880 | processing task, is_child = 0 2.02.313.796 I slot print_timing: id 0 | task 6880 | prompt eval time = 358.26 ms / 177 tokens ( 2.02 ms per token, 494.05 tokens per second) 2.02.313.802 I slot print_timing: id 0 | task 6880 | eval time = 2116.21 ms / 143 tokens ( 14.90 ms per token, 67.10 tokens per second) 2.02.313.803 I slot print_timing: id 0 | task 6880 | total time = 2474.47 ms / 320 tokens 2.02.313.803 I slot print_timing: id 0 | task 6880 | graphs reused = 6790 2.02.313.804 I slot print_timing: id 0 | task 6880 | graph reallocs = 0 / 0 (same size) / (changed size) 2.02.313.825 I slot release: id 0 | task 6880 | stop processing: n_tokens = 319, truncated = 0 2.02.317.328 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.101 (> 0.100 thold), f_keep = 0.066 2.02.318.216 I slot launch_slot_: id 0 | task 7025 | processing task, is_child = 0 2.04.712.920 I slot print_timing: id 0 | task 7025 | prompt eval time = 386.16 ms / 208 tokens ( 1.86 ms per token, 538.63 tokens per second) 2.04.712.930 I slot print_timing: id 0 | task 7025 | eval time = 2008.53 ms / 136 tokens ( 14.88 ms per token, 67.21 tokens per second) 2.04.712.930 I slot print_timing: id 0 | task 7025 | total time = 2394.69 ms / 344 tokens 2.04.712.931 I slot print_timing: id 0 | task 7025 | graphs reused = 6923 2.04.712.932 I slot print_timing: id 0 | task 7025 | graph reallocs = 0 / 0 (same size) / (changed size) 2.04.712.954 I slot release: id 0 | task 7025 | stop processing: n_tokens = 343, truncated = 0 2.04.716.126 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.131 (> 0.100 thold), f_keep = 0.061 2.04.717.063 I slot launch_slot_: id 0 | task 7163 | processing task, is_child = 0 2.07.012.178 I slot print_timing: id 0 | task 7163 | prompt eval time = 337.21 ms / 160 tokens ( 2.11 ms per token, 474.48 tokens per second) 2.07.012.183 I slot print_timing: id 0 | task 7163 | eval time = 1957.89 ms / 132 tokens ( 14.95 ms per token, 66.91 tokens per second) 2.07.012.184 I slot print_timing: id 0 | task 7163 | total time = 2295.11 ms / 292 tokens 2.07.012.185 I slot print_timing: id 0 | task 7163 | graphs reused = 7052 2.07.012.185 I slot print_timing: id 0 | task 7163 | graph reallocs = 0 / 0 (same size) / (changed size) 2.07.012.204 I slot release: id 0 | task 7163 | stop processing: n_tokens = 291, truncated = 0 2.07.015.763 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 291, t_last = 334671543219 2.07.016.684 I slot launch_slot_: id 0 | task 7297 | processing task, is_child = 0 2.09.948.681 I slot print_timing: id 0 | task 7297 | prompt eval time = 393.29 ms / 219 tokens ( 1.80 ms per token, 556.84 tokens per second) 2.09.948.685 I slot print_timing: id 0 | task 7297 | eval time = 2538.70 ms / 172 tokens ( 14.85 ms per token, 67.36 tokens per second) 2.09.948.686 I slot print_timing: id 0 | task 7297 | total time = 2931.99 ms / 391 tokens 2.09.948.686 I slot print_timing: id 0 | task 7297 | graphs reused = 7221 2.09.948.687 I slot print_timing: id 0 | task 7297 | graph reallocs = 0 / 0 (same size) / (changed size) 2.09.948.710 I slot release: id 0 | task 7297 | stop processing: n_tokens = 390, truncated = 0 2.09.951.954 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.124 (> 0.100 thold), f_keep = 0.054 2.09.952.923 I slot launch_slot_: id 0 | task 7471 | processing task, is_child = 0 2.13.178.699 I slot print_timing: id 0 | task 7471 | prompt eval time = 353.28 ms / 170 tokens ( 2.08 ms per token, 481.20 tokens per second) 2.13.178.701 I slot print_timing: id 0 | task 7471 | eval time = 2872.48 ms / 194 tokens ( 14.88 ms per token, 67.19 tokens per second) 2.13.178.702 I slot print_timing: id 0 | task 7471 | total time = 3225.77 ms / 364 tokens 2.13.178.703 I slot print_timing: id 0 | task 7471 | graphs reused = 7412 2.13.178.703 I slot print_timing: id 0 | task 7471 | graph reallocs = 0 / 0 (same size) / (changed size) 2.13.178.723 I slot release: id 0 | task 7471 | stop processing: n_tokens = 363, truncated = 0 2.13.181.956 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.124 (> 0.100 thold), f_keep = 0.058 2.13.182.868 I slot launch_slot_: id 0 | task 7667 | processing task, is_child = 0 2.15.395.468 I slot print_timing: id 0 | task 7667 | prompt eval time = 354.81 ms / 169 tokens ( 2.10 ms per token, 476.31 tokens per second) 2.15.395.471 I slot print_timing: id 0 | task 7667 | eval time = 1857.78 ms / 126 tokens ( 14.86 ms per token, 67.28 tokens per second) 2.15.395.471 I slot print_timing: id 0 | task 7667 | total time = 2212.59 ms / 295 tokens 2.15.395.472 I slot print_timing: id 0 | task 7667 | graphs reused = 7535 2.15.395.472 I slot print_timing: id 0 | task 7667 | graph reallocs = 0 / 0 (same size) / (changed size) 2.15.395.493 I slot release: id 0 | task 7667 | stop processing: n_tokens = 294, truncated = 0 2.15.398.949 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 294, t_last = 334679926509 2.15.399.770 I slot launch_slot_: id 0 | task 7795 | processing task, is_child = 0 2.18.650.990 I slot print_timing: id 0 | task 7795 | prompt eval time = 457.14 ms / 287 tokens ( 1.59 ms per token, 627.82 tokens per second) 2.18.650.996 I slot print_timing: id 0 | task 7795 | eval time = 2794.08 ms / 189 tokens ( 14.86 ms per token, 67.29 tokens per second) 2.18.650.997 I slot print_timing: id 0 | task 7795 | total time = 3251.21 ms / 476 tokens 2.18.650.997 I slot print_timing: id 0 | task 7795 | graphs reused = 7722 2.18.650.998 I slot print_timing: id 0 | task 7795 | graph reallocs = 0 / 0 (same size) / (changed size) 2.18.651.025 I slot release: id 0 | task 7795 | stop processing: n_tokens = 475, truncated = 0 2.18.654.331 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 475, t_last = 334683182040 2.18.655.622 I slot launch_slot_: id 0 | task 7986 | processing task, is_child = 0 2.21.977.719 I slot print_timing: id 0 | task 7986 | prompt eval time = 424.62 ms / 255 tokens ( 1.67 ms per token, 600.54 tokens per second) 2.21.977.725 I slot print_timing: id 0 | task 7986 | eval time = 2897.47 ms / 196 tokens ( 14.86 ms per token, 67.30 tokens per second) 2.21.977.725 I slot print_timing: id 0 | task 7986 | total time = 3322.09 ms / 451 tokens 2.21.977.726 I slot print_timing: id 0 | task 7986 | graphs reused = 7915 2.21.977.726 I slot print_timing: id 0 | task 7986 | graph reallocs = 0 / 0 (same size) / (changed size) 2.21.977.751 I slot release: id 0 | task 7986 | stop processing: n_tokens = 450, truncated = 0 2.21.981.017 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 2.21.982.184 I slot launch_slot_: id 0 | task 8184 | processing task, is_child = 0 2.24.062.419 I slot print_timing: id 0 | task 8184 | prompt eval time = 339.64 ms / 163 tokens ( 2.08 ms per token, 479.92 tokens per second) 2.24.062.424 I slot print_timing: id 0 | task 8184 | eval time = 1740.58 ms / 117 tokens ( 15.01 ms per token, 66.64 tokens per second) 2.24.062.426 I slot print_timing: id 0 | task 8184 | total time = 2080.22 ms / 280 tokens 2.24.062.426 I slot print_timing: id 0 | task 8184 | graphs reused = 8029 2.24.062.427 I slot print_timing: id 0 | task 8184 | graph reallocs = 0 / 0 (same size) / (changed size) 2.24.062.446 I slot release: id 0 | task 8184 | stop processing: n_tokens = 279, truncated = 0 2.24.065.739 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 2.24.066.539 I slot launch_slot_: id 0 | task 8303 | processing task, is_child = 0 2.25.937.815 I slot print_timing: id 0 | task 8303 | prompt eval time = 383.60 ms / 201 tokens ( 1.91 ms per token, 523.99 tokens per second) 2.25.937.820 I slot print_timing: id 0 | task 8303 | eval time = 1487.67 ms / 101 tokens ( 14.88 ms per token, 67.22 tokens per second) 2.25.937.821 I slot print_timing: id 0 | task 8303 | total time = 1871.27 ms / 302 tokens 2.25.937.821 I slot print_timing: id 0 | task 8303 | graphs reused = 8127 2.25.937.822 I slot print_timing: id 0 | task 8303 | graph reallocs = 0 / 0 (same size) / (changed size) 2.25.937.845 I slot release: id 0 | task 8303 | stop processing: n_tokens = 301, truncated = 0 2.25.940.955 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.134 (> 0.100 thold), f_keep = 0.070 2.25.941.766 I slot launch_slot_: id 0 | task 8406 | processing task, is_child = 0 2.27.408.092 I slot print_timing: id 0 | task 8406 | prompt eval time = 332.71 ms / 157 tokens ( 2.12 ms per token, 471.89 tokens per second) 2.27.408.098 I slot print_timing: id 0 | task 8406 | eval time = 1133.61 ms / 77 tokens ( 14.92 ms per token, 67.04 tokens per second) 2.27.408.099 I slot print_timing: id 0 | task 8406 | total time = 1466.32 ms / 234 tokens 2.27.408.099 I slot print_timing: id 0 | task 8406 | graphs reused = 8202 2.27.408.100 I slot print_timing: id 0 | task 8406 | graph reallocs = 0 / 0 (same size) / (changed size) 2.27.408.119 I slot release: id 0 | task 8406 | stop processing: n_tokens = 233, truncated = 0 2.27.411.496 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 233, t_last = 334691939134 2.27.412.302 I slot launch_slot_: id 0 | task 8485 | processing task, is_child = 0 2.29.803.079 I slot print_timing: id 0 | task 8485 | prompt eval time = 399.46 ms / 226 tokens ( 1.77 ms per token, 565.76 tokens per second) 2.29.803.085 I slot print_timing: id 0 | task 8485 | eval time = 1991.30 ms / 135 tokens ( 14.86 ms per token, 67.29 tokens per second) 2.29.803.086 I slot print_timing: id 0 | task 8485 | total time = 2390.77 ms / 361 tokens 2.29.803.087 I slot print_timing: id 0 | task 8485 | graphs reused = 8334 2.29.803.087 I slot print_timing: id 0 | task 8485 | graph reallocs = 0 / 0 (same size) / (changed size) 2.29.803.112 I slot release: id 0 | task 8485 | stop processing: n_tokens = 360, truncated = 0 2.29.806.877 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 360, t_last = 334694334127 2.29.807.798 I slot launch_slot_: id 0 | task 8622 | processing task, is_child = 0 2.33.015.036 I slot print_timing: id 0 | task 8622 | prompt eval time = 520.50 ms / 356 tokens ( 1.46 ms per token, 683.96 tokens per second) 2.33.015.042 I slot print_timing: id 0 | task 8622 | eval time = 2686.73 ms / 181 tokens ( 14.93 ms per token, 67.00 tokens per second) 2.33.015.042 I slot print_timing: id 0 | task 8622 | total time = 3207.23 ms / 537 tokens 2.33.015.043 I slot print_timing: id 0 | task 8622 | graphs reused = 8512 2.33.015.043 I slot print_timing: id 0 | task 8622 | graph reallocs = 0 / 0 (same size) / (changed size) 2.33.015.079 I slot release: id 0 | task 8622 | stop processing: n_tokens = 536, truncated = 0 2.33.018.817 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 536, t_last = 334697546094 2.33.020.071 I slot launch_slot_: id 0 | task 8805 | processing task, is_child = 0 2.36.624.743 I slot print_timing: id 0 | task 8805 | n_gen = 203, tg = 67.18 t/s, tg_3s = 67.51 t/s 2.37.517.456 I slot print_timing: id 0 | task 8805 | prompt eval time = 597.79 ms / 427 tokens ( 1.40 ms per token, 714.30 tokens per second) 2.37.517.460 I slot print_timing: id 0 | task 8805 | eval time = 3899.59 ms / 263 tokens ( 14.88 ms per token, 67.19 tokens per second) 2.37.517.460 I slot print_timing: id 0 | task 8805 | total time = 4497.38 ms / 690 tokens 2.37.517.461 I slot print_timing: id 0 | task 8805 | graphs reused = 8772 2.37.517.462 I slot print_timing: id 0 | task 8805 | graph reallocs = 0 / 0 (same size) / (changed size) 2.37.517.495 I slot release: id 0 | task 8805 | stop processing: n_tokens = 689, truncated = 0 2.37.521.600 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 689, t_last = 334702048510 2.37.523.251 I slot launch_slot_: id 0 | task 9070 | processing task, is_child = 0 2.40.542.200 I slot print_timing: id 0 | task 9070 | prompt eval time = 650.41 ms / 481 tokens ( 1.35 ms per token, 739.53 tokens per second) 2.40.542.204 I slot print_timing: id 0 | task 9070 | eval time = 2368.53 ms / 160 tokens ( 14.90 ms per token, 67.13 tokens per second) 2.40.542.205 I slot print_timing: id 0 | task 9070 | total time = 3018.94 ms / 641 tokens 2.40.542.205 I slot print_timing: id 0 | task 9070 | graphs reused = 8929 2.40.542.206 I slot print_timing: id 0 | task 9070 | graph reallocs = 0 / 0 (same size) / (changed size) 2.40.542.243 I slot release: id 0 | task 9070 | stop processing: n_tokens = 640, truncated = 0 2.40.546.239 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 640, t_last = 334705073258 2.40.547.860 I slot launch_slot_: id 0 | task 9232 | processing task, is_child = 0 2.43.279.328 I slot print_timing: id 0 | task 9232 | prompt eval time = 632.63 ms / 456 tokens ( 1.39 ms per token, 720.80 tokens per second) 2.43.279.337 I slot print_timing: id 0 | task 9232 | eval time = 2098.83 ms / 142 tokens ( 14.89 ms per token, 67.18 tokens per second) 2.43.279.337 I slot print_timing: id 0 | task 9232 | total time = 2731.46 ms / 598 tokens 2.43.279.338 I slot print_timing: id 0 | task 9232 | graphs reused = 9068 2.43.279.339 I slot print_timing: id 0 | task 9232 | graph reallocs = 0 / 0 (same size) / (changed size) 2.43.279.373 I slot release: id 0 | task 9232 | stop processing: n_tokens = 597, truncated = 0 2.43.282.847 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 597, t_last = 334707810388 2.43.284.269 I slot launch_slot_: id 0 | task 9376 | processing task, is_child = 0 2.45.161.878 I slot print_timing: id 0 | task 9376 | prompt eval time = 454.69 ms / 290 tokens ( 1.57 ms per token, 637.80 tokens per second) 2.45.161.883 I slot print_timing: id 0 | task 9376 | eval time = 1422.91 ms / 96 tokens ( 14.98 ms per token, 66.76 tokens per second) 2.45.161.884 I slot print_timing: id 0 | task 9376 | total time = 1877.60 ms / 386 tokens 2.45.161.884 I slot print_timing: id 0 | task 9376 | graphs reused = 9162 2.45.161.885 I slot print_timing: id 0 | task 9376 | graph reallocs = 0 / 0 (same size) / (changed size) 2.45.161.910 I slot release: id 0 | task 9376 | stop processing: n_tokens = 385, truncated = 0 2.45.165.811 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 385, t_last = 334709692925 2.45.166.828 I slot launch_slot_: id 0 | task 9474 | processing task, is_child = 0 2.48.780.159 I slot print_timing: id 0 | task 9474 | n_gen = 203, tg = 67.21 t/s, tg_3s = 67.54 t/s 2.51.790.749 I slot print_timing: id 0 | task 9474 | n_gen = 403, tg = 66.82 t/s, tg_3s = 66.43 t/s 2.54.768.157 I slot print_timing: id 0 | task 9474 | prompt eval time = 607.73 ms / 439 tokens ( 1.38 ms per token, 722.36 tokens per second) 2.54.768.160 I slot print_timing: id 0 | task 9474 | eval time = 8993.59 ms / 603 tokens ( 14.94 ms per token, 66.94 tokens per second) 2.54.768.160 I slot print_timing: id 0 | task 9474 | total time = 9601.32 ms / 1042 tokens 2.54.768.161 I slot print_timing: id 0 | task 9474 | graphs reused = 9760 2.54.768.162 I slot print_timing: id 0 | task 9474 | graph reallocs = 0 / 0 (same size) / (changed size) 2.54.768.204 I slot release: id 0 | task 9474 | stop processing: n_tokens = 1041, truncated = 0 2.54.772.527 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1041, t_last = 334719299220 2.54.774.941 I slot launch_slot_: id 0 | task 10079 | processing task, is_child = 0 2.58.346.643 I slot print_timing: id 0 | task 10079 | n_gen = 203, tg = 67.22 t/s, tg_3s = 67.56 t/s 3.01.354.672 I slot print_timing: id 0 | task 10079 | n_gen = 405, tg = 67.19 t/s, tg_3s = 67.15 t/s 3.04.358.797 I slot print_timing: id 0 | task 10079 | n_gen = 607, tg = 67.21 t/s, tg_3s = 67.24 t/s 3.07.371.074 I slot print_timing: id 0 | task 10079 | n_gen = 809, tg = 67.17 t/s, tg_3s = 67.06 t/s 3.10.378.234 I slot print_timing: id 0 | task 10079 | n_gen = 1010, tg = 67.10 t/s, tg_3s = 66.84 t/s 3.10.587.445 I slot print_timing: id 0 | task 10079 | prompt eval time = 566.80 ms / 396 tokens ( 1.43 ms per token, 698.66 tokens per second) 3.10.587.448 I slot print_timing: id 0 | task 10079 | eval time = 15245.70 ms / 1024 tokens ( 14.90 ms per token, 67.10 tokens per second) 3.10.587.449 I slot print_timing: id 0 | task 10079 | total time = 15812.50 ms / 1420 tokens 3.10.587.449 I slot print_timing: id 0 | task 10079 | graphs reused = 10778 3.10.587.450 I slot print_timing: id 0 | task 10079 | graph reallocs = 0 / 0 (same size) / (changed size) 3.10.587.485 I slot release: id 0 | task 10079 | stop processing: n_tokens = 1419, truncated = 0 3.10.591.538 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1419, t_last = 334735118500 3.10.594.746 I slot launch_slot_: id 0 | task 11105 | processing task, is_child = 0 3.12.384.417 I slot print_timing: id 0 | task 11105 | prompt eval time = 512.95 ms / 342 tokens ( 1.50 ms per token, 666.73 tokens per second) 3.12.384.422 I slot print_timing: id 0 | task 11105 | eval time = 1276.71 ms / 87 tokens ( 14.85 ms per token, 67.36 tokens per second) 3.12.384.423 I slot print_timing: id 0 | task 11105 | total time = 1789.66 ms / 429 tokens 3.12.384.423 I slot print_timing: id 0 | task 11105 | graphs reused = 10863 3.12.384.424 I slot print_timing: id 0 | task 11105 | graph reallocs = 0 / 0 (same size) / (changed size) 3.12.384.454 I slot release: id 0 | task 11105 | stop processing: n_tokens = 428, truncated = 0 3.12.388.100 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 428, t_last = 334736915469 3.12.389.158 I slot launch_slot_: id 0 | task 11194 | processing task, is_child = 0 3.14.151.879 I slot print_timing: id 0 | task 11194 | prompt eval time = 484.07 ms / 314 tokens ( 1.54 ms per token, 648.67 tokens per second) 3.14.151.886 I slot print_timing: id 0 | task 11194 | eval time = 1278.64 ms / 87 tokens ( 14.87 ms per token, 67.26 tokens per second) 3.14.151.887 I slot print_timing: id 0 | task 11194 | total time = 1762.71 ms / 401 tokens 3.14.151.887 I slot print_timing: id 0 | task 11194 | graphs reused = 10948 3.14.151.888 I slot print_timing: id 0 | task 11194 | graph reallocs = 0 / 0 (same size) / (changed size) 3.14.151.915 I slot release: id 0 | task 11194 | stop processing: n_tokens = 400, truncated = 0 3.14.155.627 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 334738682930 3.14.156.682 I slot launch_slot_: id 0 | task 11283 | processing task, is_child = 0 3.16.180.086 I slot print_timing: id 0 | task 11283 | prompt eval time = 569.27 ms / 396 tokens ( 1.44 ms per token, 695.63 tokens per second) 3.16.180.089 I slot print_timing: id 0 | task 11283 | eval time = 1454.13 ms / 98 tokens ( 14.99 ms per token, 66.71 tokens per second) 3.16.180.089 I slot print_timing: id 0 | task 11283 | total time = 2023.40 ms / 494 tokens 3.16.180.090 I slot print_timing: id 0 | task 11283 | graphs reused = 11044 3.16.180.091 I slot print_timing: id 0 | task 11283 | graph reallocs = 0 / 0 (same size) / (changed size) 3.16.180.124 I slot release: id 0 | task 11283 | stop processing: n_tokens = 493, truncated = 0 3.16.183.887 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 493, t_last = 334740711139 3.16.185.161 I slot launch_slot_: id 0 | task 11383 | processing task, is_child = 0 3.19.699.487 I slot print_timing: id 0 | task 11383 | n_gen = 203, tg = 67.19 t/s, tg_3s = 67.52 t/s 3.22.704.221 I slot print_timing: id 0 | task 11383 | n_gen = 405, tg = 67.21 t/s, tg_3s = 67.23 t/s 3.23.229.232 I slot print_timing: id 0 | task 11383 | prompt eval time = 507.93 ms / 339 tokens ( 1.50 ms per token, 667.42 tokens per second) 3.23.229.238 I slot print_timing: id 0 | task 11383 | eval time = 6536.14 ms / 440 tokens ( 14.89 ms per token, 67.17 tokens per second) 3.23.229.239 I slot print_timing: id 0 | task 11383 | total time = 7044.06 ms / 779 tokens 3.23.229.239 I slot print_timing: id 0 | task 11383 | graphs reused = 11480 3.23.229.240 I slot print_timing: id 0 | task 11383 | graph reallocs = 0 / 0 (same size) / (changed size) 3.23.229.268 I slot release: id 0 | task 11383 | stop processing: n_tokens = 778, truncated = 0 3.23.232.915 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 778, t_last = 334747760283 3.23.234.679 I slot launch_slot_: id 0 | task 11825 | processing task, is_child = 0 3.24.976.371 I slot print_timing: id 0 | task 11825 | prompt eval time = 443.82 ms / 267 tokens ( 1.66 ms per token, 601.59 tokens per second) 3.24.976.373 I slot print_timing: id 0 | task 11825 | eval time = 1297.86 ms / 88 tokens ( 14.92 ms per token, 67.03 tokens per second) 3.24.976.374 I slot print_timing: id 0 | task 11825 | total time = 1741.68 ms / 355 tokens 3.24.976.374 I slot print_timing: id 0 | task 11825 | graphs reused = 11566 3.24.976.375 I slot print_timing: id 0 | task 11825 | graph reallocs = 0 / 0 (same size) / (changed size) 3.24.976.402 I slot release: id 0 | task 11825 | stop processing: n_tokens = 354, truncated = 0 3.24.980.118 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 354, t_last = 334749507417 3.24.981.113 I slot launch_slot_: id 0 | task 11915 | processing task, is_child = 0 3.28.152.626 I slot print_timing: id 0 | task 11915 | prompt eval time = 534.93 ms / 360 tokens ( 1.49 ms per token, 672.99 tokens per second) 3.28.152.632 I slot print_timing: id 0 | task 11915 | eval time = 2636.58 ms / 178 tokens ( 14.90 ms per token, 67.13 tokens per second) 3.28.152.633 I slot print_timing: id 0 | task 11915 | total time = 3171.51 ms / 538 tokens 3.28.152.633 I slot print_timing: id 0 | task 11915 | graphs reused = 11741 3.28.152.634 I slot print_timing: id 0 | task 11915 | graph reallocs = 0 / 0 (same size) / (changed size) 3.28.152.667 I slot release: id 0 | task 11915 | stop processing: n_tokens = 537, truncated = 0 3.28.156.187 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 537, t_last = 334752683682 3.28.157.477 I slot launch_slot_: id 0 | task 12095 | processing task, is_child = 0 3.30.642.016 I slot print_timing: id 0 | task 12095 | prompt eval time = 471.56 ms / 296 tokens ( 1.59 ms per token, 627.70 tokens per second) 3.30.642.022 I slot print_timing: id 0 | task 12095 | eval time = 2012.97 ms / 136 tokens ( 14.91 ms per token, 67.07 tokens per second) 3.30.642.023 I slot print_timing: id 0 | task 12095 | total time = 2484.53 ms / 432 tokens 3.30.642.023 I slot print_timing: id 0 | task 12095 | graphs reused = 11875 3.30.642.024 I slot print_timing: id 0 | task 12095 | graph reallocs = 0 / 0 (same size) / (changed size) 3.30.642.050 I slot release: id 0 | task 12095 | stop processing: n_tokens = 431, truncated = 0 3.30.645.715 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 431, t_last = 334755173065 3.30.646.874 I slot launch_slot_: id 0 | task 12233 | processing task, is_child = 0 3.34.079.799 I slot print_timing: id 0 | task 12233 | prompt eval time = 451.67 ms / 275 tokens ( 1.64 ms per token, 608.86 tokens per second) 3.34.079.806 I slot print_timing: id 0 | task 12233 | eval time = 2981.25 ms / 202 tokens ( 14.83 ms per token, 67.42 tokens per second) 3.34.079.806 I slot print_timing: id 0 | task 12233 | total time = 3432.92 ms / 477 tokens 3.34.079.807 I slot print_timing: id 0 | task 12233 | graphs reused = 12075 3.34.079.808 I slot print_timing: id 0 | task 12233 | graph reallocs = 0 / 0 (same size) / (changed size) 3.34.079.839 I slot release: id 0 | task 12233 | stop processing: n_tokens = 476, truncated = 0 3.34.083.805 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 476, t_last = 334758610854 3.34.085.081 I slot launch_slot_: id 0 | task 12437 | processing task, is_child = 0 3.35.817.545 I slot print_timing: id 0 | task 12437 | prompt eval time = 454.90 ms / 287 tokens ( 1.59 ms per token, 630.90 tokens per second) 3.35.817.551 I slot print_timing: id 0 | task 12437 | eval time = 1277.55 ms / 86 tokens ( 15.03 ms per token, 66.53 tokens per second) 3.35.817.551 I slot print_timing: id 0 | task 12437 | total time = 1732.46 ms / 373 tokens 3.35.817.552 I slot print_timing: id 0 | task 12437 | graphs reused = 12159 3.35.817.552 I slot print_timing: id 0 | task 12437 | graph reallocs = 0 / 0 (same size) / (changed size) 3.35.817.579 I slot release: id 0 | task 12437 | stop processing: n_tokens = 372, truncated = 0 3.35.820.993 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 372, t_last = 334760348594 3.35.821.944 I slot launch_slot_: id 0 | task 12525 | processing task, is_child = 0 3.37.232.552 I slot print_timing: id 0 | task 12525 | prompt eval time = 443.81 ms / 266 tokens ( 1.67 ms per token, 599.36 tokens per second) 3.37.232.558 I slot print_timing: id 0 | task 12525 | eval time = 966.79 ms / 66 tokens ( 14.87 ms per token, 67.23 tokens per second) 3.37.232.559 I slot print_timing: id 0 | task 12525 | total time = 1410.60 ms / 332 tokens 3.37.232.559 I slot print_timing: id 0 | task 12525 | graphs reused = 12223 3.37.232.560 I slot print_timing: id 0 | task 12525 | graph reallocs = 0 / 0 (same size) / (changed size) 3.37.232.585 I slot release: id 0 | task 12525 | stop processing: n_tokens = 331, truncated = 0 3.37.236.370 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 331, t_last = 334761763600 3.37.237.384 I slot launch_slot_: id 0 | task 12593 | processing task, is_child = 0 3.40.394.559 I slot print_timing: id 0 | task 12593 | prompt eval time = 604.73 ms / 435 tokens ( 1.39 ms per token, 719.32 tokens per second) 3.40.394.563 I slot print_timing: id 0 | task 12593 | eval time = 2552.43 ms / 172 tokens ( 14.93 ms per token, 66.99 tokens per second) 3.40.394.563 I slot print_timing: id 0 | task 12593 | total time = 3157.17 ms / 607 tokens 3.40.394.564 I slot print_timing: id 0 | task 12593 | graphs reused = 12392 3.40.394.564 I slot print_timing: id 0 | task 12593 | graph reallocs = 0 / 0 (same size) / (changed size) 3.40.394.599 I slot release: id 0 | task 12593 | stop processing: n_tokens = 606, truncated = 0 3.40.398.025 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 606, t_last = 334764925614 3.40.399.435 I slot launch_slot_: id 0 | task 12767 | processing task, is_child = 0 3.43.188.780 I slot print_timing: id 0 | task 12767 | prompt eval time = 478.14 ms / 307 tokens ( 1.56 ms per token, 642.07 tokens per second) 3.43.188.786 I slot print_timing: id 0 | task 12767 | eval time = 2311.19 ms / 155 tokens ( 15.01 ms per token, 66.63 tokens per second) 3.43.188.786 I slot print_timing: id 0 | task 12767 | total time = 2789.33 ms / 462 tokens 3.43.188.787 I slot print_timing: id 0 | task 12767 | graphs reused = 12545 3.43.188.788 I slot print_timing: id 0 | task 12767 | graph reallocs = 0 / 0 (same size) / (changed size) 3.43.188.815 I slot release: id 0 | task 12767 | stop processing: n_tokens = 461, truncated = 0 3.43.193.459 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 461, t_last = 334767719830 3.43.195.230 I slot launch_slot_: id 0 | task 12924 | processing task, is_child = 0 3.47.183.196 I slot print_timing: id 0 | task 12924 | n_gen = 203, tg = 67.22 t/s, tg_3s = 67.56 t/s 3.47.257.498 I slot print_timing: id 0 | task 12924 | prompt eval time = 983.03 ms / 675 tokens ( 1.46 ms per token, 686.65 tokens per second) 3.47.257.504 I slot print_timing: id 0 | task 12924 | eval time = 3079.23 ms / 208 tokens ( 14.88 ms per token, 67.22 tokens per second) 3.47.257.505 I slot print_timing: id 0 | task 12924 | total time = 4062.26 ms / 883 tokens 3.47.257.505 I slot print_timing: id 0 | task 12924 | graphs reused = 12750 3.47.257.506 I slot print_timing: id 0 | task 12924 | graph reallocs = 0 / 0 (same size) / (changed size) 3.47.257.561 I slot release: id 0 | task 12924 | stop processing: n_tokens = 882, truncated = 0 3.47.261.232 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 882, t_last = 334771788576 3.47.263.490 I slot launch_slot_: id 0 | task 13135 | processing task, is_child = 0 3.49.207.805 I slot print_timing: id 0 | task 13135 | prompt eval time = 458.59 ms / 287 tokens ( 1.60 ms per token, 625.83 tokens per second) 3.49.207.811 I slot print_timing: id 0 | task 13135 | eval time = 1485.71 ms / 101 tokens ( 14.86 ms per token, 67.31 tokens per second) 3.49.207.812 I slot print_timing: id 0 | task 13135 | total time = 1944.31 ms / 388 tokens 3.49.207.813 I slot print_timing: id 0 | task 13135 | graphs reused = 12849 3.49.207.814 I slot print_timing: id 0 | task 13135 | graph reallocs = 0 / 0 (same size) / (changed size) 3.49.207.845 I slot release: id 0 | task 13135 | stop processing: n_tokens = 387, truncated = 0 3.49.211.907 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 387, t_last = 334773738860 3.49.212.920 I slot launch_slot_: id 0 | task 13238 | processing task, is_child = 0 3.51.281.581 I slot print_timing: id 0 | task 13238 | prompt eval time = 667.86 ms / 497 tokens ( 1.34 ms per token, 744.17 tokens per second) 3.51.281.587 I slot print_timing: id 0 | task 13238 | eval time = 1400.80 ms / 95 tokens ( 14.90 ms per token, 67.10 tokens per second) 3.51.281.588 I slot print_timing: id 0 | task 13238 | total time = 2068.65 ms / 592 tokens 3.51.281.589 I slot print_timing: id 0 | task 13238 | graphs reused = 12941 3.51.281.589 I slot print_timing: id 0 | task 13238 | graph reallocs = 0 / 0 (same size) / (changed size) 3.51.281.626 I slot release: id 0 | task 13238 | stop processing: n_tokens = 591, truncated = 0 3.51.286.025 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 591, t_last = 334775812641 3.51.287.798 I slot launch_slot_: id 0 | task 13335 | processing task, is_child = 0 3.54.590.600 I slot print_timing: id 0 | task 13335 | prompt eval time = 917.15 ms / 609 tokens ( 1.51 ms per token, 664.01 tokens per second) 3.54.590.606 I slot print_timing: id 0 | task 13335 | eval time = 2385.64 ms / 161 tokens ( 14.91 ms per token, 67.07 tokens per second) 3.54.590.608 I slot print_timing: id 0 | task 13335 | total time = 3302.80 ms / 770 tokens 3.54.590.608 I slot print_timing: id 0 | task 13335 | graphs reused = 13099 3.54.590.609 I slot print_timing: id 0 | task 13335 | graph reallocs = 0 / 0 (same size) / (changed size) 3.54.590.657 I slot release: id 0 | task 13335 | stop processing: n_tokens = 769, truncated = 0 3.54.594.547 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 769, t_last = 334779121672 3.54.596.356 I slot launch_slot_: id 0 | task 13499 | processing task, is_child = 0 3.57.260.588 I slot print_timing: id 0 | task 13499 | prompt eval time = 581.60 ms / 415 tokens ( 1.40 ms per token, 713.55 tokens per second) 3.57.260.593 I slot print_timing: id 0 | task 13499 | eval time = 2082.63 ms / 141 tokens ( 14.88 ms per token, 67.22 tokens per second) 3.57.260.594 I slot print_timing: id 0 | task 13499 | total time = 2664.22 ms / 556 tokens 3.57.260.595 I slot print_timing: id 0 | task 13499 | graphs reused = 13237 3.57.260.595 I slot print_timing: id 0 | task 13499 | graph reallocs = 0 / 0 (same size) / (changed size) 3.57.260.630 I slot release: id 0 | task 13499 | stop processing: n_tokens = 555, truncated = 0 3.57.264.211 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 555, t_last = 334781791645 3.57.265.532 I slot launch_slot_: id 0 | task 13642 | processing task, is_child = 0 3.59.460.176 I slot print_timing: id 0 | task 13642 | prompt eval time = 471.13 ms / 295 tokens ( 1.60 ms per token, 626.15 tokens per second) 3.59.460.182 I slot print_timing: id 0 | task 13642 | eval time = 1723.50 ms / 117 tokens ( 14.86 ms per token, 67.30 tokens per second) 3.59.460.183 I slot print_timing: id 0 | task 13642 | total time = 2194.63 ms / 412 tokens 3.59.460.184 I slot print_timing: id 0 | task 13642 | graphs reused = 13352 3.59.460.184 I slot print_timing: id 0 | task 13642 | graph reallocs = 0 / 0 (same size) / (changed size) 3.59.460.211 I slot release: id 0 | task 13642 | stop processing: n_tokens = 411, truncated = 0 3.59.464.097 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 334783991226 3.59.465.145 I slot launch_slot_: id 0 | task 13761 | processing task, is_child = 0 4.03.082.193 I slot print_timing: id 0 | task 13761 | n_gen = 203, tg = 67.21 t/s, tg_3s = 67.54 t/s 4.06.086.373 I slot print_timing: id 0 | task 13761 | n_gen = 405, tg = 67.22 t/s, tg_3s = 67.24 t/s 4.08.512.176 I slot print_timing: id 0 | task 13761 | prompt eval time = 611.37 ms / 442 tokens ( 1.38 ms per token, 722.97 tokens per second) 4.08.512.182 I slot print_timing: id 0 | task 13761 | eval time = 8435.65 ms / 568 tokens ( 14.88 ms per token, 67.21 tokens per second) 4.08.512.183 I slot print_timing: id 0 | task 13761 | total time = 9047.02 ms / 1010 tokens 4.08.512.183 I slot print_timing: id 0 | task 13761 | graphs reused = 13916 4.08.512.184 I slot print_timing: id 0 | task 13761 | graph reallocs = 0 / 0 (same size) / (changed size) 4.08.512.218 I slot release: id 0 | task 13761 | stop processing: n_tokens = 1009, truncated = 0 4.08.516.640 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1009, t_last = 334793043233 4.08.518.966 I slot launch_slot_: id 0 | task 14331 | processing task, is_child = 0 4.11.247.613 I slot print_timing: id 0 | task 14331 | prompt eval time = 942.17 ms / 622 tokens ( 1.51 ms per token, 660.18 tokens per second) 4.11.247.618 I slot print_timing: id 0 | task 14331 | eval time = 1786.47 ms / 121 tokens ( 14.89 ms per token, 67.17 tokens per second) 4.11.247.619 I slot print_timing: id 0 | task 14331 | total time = 2728.64 ms / 743 tokens 4.11.247.620 I slot print_timing: id 0 | task 14331 | graphs reused = 14035 4.11.247.620 I slot print_timing: id 0 | task 14331 | graph reallocs = 0 / 0 (same size) / (changed size) 4.11.247.664 I slot release: id 0 | task 14331 | stop processing: n_tokens = 742, truncated = 0 4.11.251.423 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 742, t_last = 334795778679 4.11.253.577 I slot launch_slot_: id 0 | task 14455 | processing task, is_child = 0 4.13.510.101 I slot print_timing: id 0 | task 14455 | prompt eval time = 597.66 ms / 424 tokens ( 1.41 ms per token, 709.43 tokens per second) 4.13.510.107 I slot print_timing: id 0 | task 14455 | eval time = 1658.85 ms / 112 tokens ( 14.94 ms per token, 66.91 tokens per second) 4.13.510.108 I slot print_timing: id 0 | task 14455 | total time = 2256.51 ms / 536 tokens 4.13.510.108 I slot print_timing: id 0 | task 14455 | graphs reused = 14144 4.13.510.109 I slot print_timing: id 0 | task 14455 | graph reallocs = 0 / 0 (same size) / (changed size) 4.13.510.146 I slot release: id 0 | task 14455 | stop processing: n_tokens = 535, truncated = 0 4.13.514.158 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 535, t_last = 334798041161 4.13.514.856 I slot launch_slot_: id 0 | task 14569 | processing task, is_child = 0 4.17.088.933 I slot print_timing: id 0 | task 14569 | n_gen = 203, tg = 67.23 t/s, tg_3s = 67.56 t/s 4.20.094.380 I slot print_timing: id 0 | task 14569 | n_gen = 405, tg = 67.22 t/s, tg_3s = 67.21 t/s 4.20.540.203 I slot print_timing: id 0 | task 14569 | prompt eval time = 569.30 ms / 395 tokens ( 1.44 ms per token, 693.83 tokens per second) 4.20.540.208 I slot print_timing: id 0 | task 14569 | eval time = 6456.03 ms / 435 tokens ( 14.88 ms per token, 67.22 tokens per second) 4.20.540.209 I slot print_timing: id 0 | task 14569 | total time = 7025.34 ms / 830 tokens 4.20.540.210 I slot print_timing: id 0 | task 14569 | graphs reused = 14575 4.20.540.210 I slot print_timing: id 0 | task 14569 | graph reallocs = 0 / 0 (same size) / (changed size) 4.20.540.251 I slot release: id 0 | task 14569 | stop processing: n_tokens = 829, truncated = 0 4.20.543.789 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 829, t_last = 334805071266 4.20.546.037 I slot launch_slot_: id 0 | task 15006 | processing task, is_child = 0 4.22.573.945 I slot print_timing: id 0 | task 15006 | prompt eval time = 451.69 ms / 279 tokens ( 1.62 ms per token, 617.68 tokens per second) 4.22.573.948 I slot print_timing: id 0 | task 15006 | eval time = 1576.21 ms / 107 tokens ( 14.87 ms per token, 67.25 tokens per second) 4.22.573.949 I slot print_timing: id 0 | task 15006 | total time = 2027.90 ms / 386 tokens 4.22.573.949 I slot print_timing: id 0 | task 15006 | graphs reused = 14680 4.22.573.950 I slot print_timing: id 0 | task 15006 | graph reallocs = 0 / 0 (same size) / (changed size) 4.22.573.976 I slot release: id 0 | task 15006 | stop processing: n_tokens = 385, truncated = 0 4.22.577.688 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 385, t_last = 334807104991 4.22.578.801 I slot launch_slot_: id 0 | task 15115 | processing task, is_child = 0 4.25.227.775 I slot print_timing: id 0 | task 15115 | prompt eval time = 487.07 ms / 319 tokens ( 1.53 ms per token, 654.94 tokens per second) 4.25.227.781 I slot print_timing: id 0 | task 15115 | eval time = 2161.90 ms / 146 tokens ( 14.91 ms per token, 67.07 tokens per second) 4.25.227.782 I slot print_timing: id 0 | task 15115 | total time = 2648.96 ms / 465 tokens 4.25.227.782 I slot print_timing: id 0 | task 15115 | graphs reused = 14824 4.25.227.783 I slot print_timing: id 0 | task 15115 | graph reallocs = 0 / 0 (same size) / (changed size) 4.25.227.810 I slot release: id 0 | task 15115 | stop processing: n_tokens = 464, truncated = 0 4.25.231.587 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 464, t_last = 334809758825 4.25.232.747 I slot launch_slot_: id 0 | task 15263 | processing task, is_child = 0 4.27.530.887 I slot print_timing: id 0 | task 15263 | prompt eval time = 513.39 ms / 345 tokens ( 1.49 ms per token, 672.00 tokens per second) 4.27.530.891 I slot print_timing: id 0 | task 15263 | eval time = 1784.74 ms / 121 tokens ( 14.87 ms per token, 67.24 tokens per second) 4.27.530.892 I slot print_timing: id 0 | task 15263 | total time = 2298.13 ms / 466 tokens 4.27.530.893 I slot print_timing: id 0 | task 15263 | graphs reused = 14943 4.27.530.893 I slot print_timing: id 0 | task 15263 | graph reallocs = 0 / 0 (same size) / (changed size) 4.27.530.929 I slot release: id 0 | task 15263 | stop processing: n_tokens = 465, truncated = 0 4.27.535.110 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 465, t_last = 334812061944 4.27.536.416 I slot launch_slot_: id 0 | task 15386 | processing task, is_child = 0 4.30.718.215 I slot print_timing: id 0 | task 15386 | prompt eval time = 635.21 ms / 464 tokens ( 1.37 ms per token, 730.47 tokens per second) 4.30.718.221 I slot print_timing: id 0 | task 15386 | eval time = 2546.58 ms / 172 tokens ( 14.89 ms per token, 67.15 tokens per second) 4.30.718.222 I slot print_timing: id 0 | task 15386 | total time = 3181.79 ms / 636 tokens 4.30.718.223 I slot print_timing: id 0 | task 15386 | graphs reused = 15112 4.30.718.223 I slot print_timing: id 0 | task 15386 | graph reallocs = 0 / 0 (same size) / (changed size) 4.30.718.260 I slot release: id 0 | task 15386 | stop processing: n_tokens = 635, truncated = 0 4.30.722.072 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 635, t_last = 334815249275 4.30.723.601 I slot launch_slot_: id 0 | task 15560 | processing task, is_child = 0 4.32.703.079 I slot print_timing: id 0 | task 15560 | prompt eval time = 570.64 ms / 398 tokens ( 1.43 ms per token, 697.46 tokens per second) 4.32.703.085 I slot print_timing: id 0 | task 15560 | eval time = 1408.83 ms / 96 tokens ( 14.83 ms per token, 67.43 tokens per second) 4.32.703.085 I slot print_timing: id 0 | task 15560 | total time = 1979.47 ms / 494 tokens 4.32.703.086 I slot print_timing: id 0 | task 15560 | graphs reused = 15206 4.32.703.086 I slot print_timing: id 0 | task 15560 | graph reallocs = 0 / 0 (same size) / (changed size) 4.32.703.121 I slot release: id 0 | task 15560 | stop processing: n_tokens = 493, truncated = 0 4.32.707.262 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 493, t_last = 334817234136 4.32.708.721 I slot launch_slot_: id 0 | task 15658 | processing task, is_child = 0 4.35.322.127 I slot print_timing: id 0 | task 15658 | prompt eval time = 947.24 ms / 628 tokens ( 1.51 ms per token, 662.98 tokens per second) 4.35.322.130 I slot print_timing: id 0 | task 15658 | eval time = 1666.15 ms / 112 tokens ( 15.01 ms per token, 66.62 tokens per second) 4.35.322.130 I slot print_timing: id 0 | task 15658 | total time = 2613.39 ms / 740 tokens 4.35.322.131 I slot print_timing: id 0 | task 15658 | graphs reused = 15316 4.35.322.131 I slot print_timing: id 0 | task 15658 | graph reallocs = 0 / 0 (same size) / (changed size) 4.35.322.176 I slot release: id 0 | task 15658 | stop processing: n_tokens = 739, truncated = 0 4.35.326.212 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 739, t_last = 334819853191 4.35.328.210 I slot launch_slot_: id 0 | task 15773 | processing task, is_child = 0 4.37.798.336 I slot print_timing: id 0 | task 15773 | prompt eval time = 575.10 ms / 404 tokens ( 1.42 ms per token, 702.48 tokens per second) 4.37.798.340 I slot print_timing: id 0 | task 15773 | eval time = 1895.01 ms / 128 tokens ( 14.92 ms per token, 67.02 tokens per second) 4.37.798.340 I slot print_timing: id 0 | task 15773 | total time = 2470.12 ms / 532 tokens 4.37.798.341 I slot print_timing: id 0 | task 15773 | graphs reused = 15441 4.37.798.342 I slot print_timing: id 0 | task 15773 | graph reallocs = 0 / 0 (same size) / (changed size) 4.37.798.381 I slot release: id 0 | task 15773 | stop processing: n_tokens = 531, truncated = 0 4.37.802.394 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 531, t_last = 334822329396 4.37.803.710 I slot launch_slot_: id 0 | task 15903 | processing task, is_child = 0 4.40.707.971 I slot print_timing: id 0 | task 15903 | prompt eval time = 612.74 ms / 445 tokens ( 1.38 ms per token, 726.25 tokens per second) 4.40.707.978 I slot print_timing: id 0 | task 15903 | eval time = 2291.51 ms / 155 tokens ( 14.88 ms per token, 67.20 tokens per second) 4.40.707.978 I slot print_timing: id 0 | task 15903 | total time = 2904.25 ms / 600 tokens 4.40.707.979 I slot print_timing: id 0 | task 15903 | graphs reused = 15593 4.40.707.979 I slot print_timing: id 0 | task 15903 | graph reallocs = 0 / 0 (same size) / (changed size) 4.40.708.015 I slot release: id 0 | task 15903 | stop processing: n_tokens = 599, truncated = 0 4.40.712.195 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 599, t_last = 334825239030 4.40.714.083 I slot launch_slot_: id 0 | task 16060 | processing task, is_child = 0 4.43.762.945 I slot print_timing: id 0 | task 16060 | prompt eval time = 580.11 ms / 412 tokens ( 1.41 ms per token, 710.21 tokens per second) 4.43.762.948 I slot print_timing: id 0 | task 16060 | eval time = 2468.74 ms / 166 tokens ( 14.96 ms per token, 66.84 tokens per second) 4.43.762.948 I slot print_timing: id 0 | task 16060 | total time = 3048.85 ms / 578 tokens 4.43.762.949 I slot print_timing: id 0 | task 16060 | graphs reused = 15756 4.43.762.949 I slot print_timing: id 0 | task 16060 | graph reallocs = 0 / 0 (same size) / (changed size) 4.43.762.987 I slot release: id 0 | task 16060 | stop processing: n_tokens = 577, truncated = 0 4.43.767.250 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 577, t_last = 334828294002 4.43.768.708 I slot launch_slot_: id 0 | task 16228 | processing task, is_child = 0 4.45.801.856 I slot print_timing: id 0 | task 16228 | prompt eval time = 855.57 ms / 542 tokens ( 1.58 ms per token, 633.49 tokens per second) 4.45.801.861 I slot print_timing: id 0 | task 16228 | eval time = 1177.56 ms / 80 tokens ( 14.91 ms per token, 67.09 tokens per second) 4.45.801.861 I slot print_timing: id 0 | task 16228 | total time = 2033.13 ms / 622 tokens 4.45.801.862 I slot print_timing: id 0 | task 16228 | graphs reused = 15834 4.45.801.862 I slot print_timing: id 0 | task 16228 | graph reallocs = 0 / 0 (same size) / (changed size) 4.45.801.906 I slot release: id 0 | task 16228 | stop processing: n_tokens = 621, truncated = 0 4.45.806.320 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 621, t_last = 334830332921 4.45.807.830 I slot launch_slot_: id 0 | task 16311 | processing task, is_child = 0 4.49.473.837 I slot print_timing: id 0 | task 16311 | prompt eval time = 938.25 ms / 628 tokens ( 1.49 ms per token, 669.33 tokens per second) 4.49.473.839 I slot print_timing: id 0 | task 16311 | eval time = 2727.74 ms / 184 tokens ( 14.91 ms per token, 67.09 tokens per second) 4.49.473.840 I slot print_timing: id 0 | task 16311 | total time = 3665.99 ms / 812 tokens 4.49.473.841 I slot print_timing: id 0 | task 16311 | graphs reused = 16015 4.49.473.841 I slot print_timing: id 0 | task 16311 | graph reallocs = 0 / 0 (same size) / (changed size) 4.49.473.885 I slot release: id 0 | task 16311 | stop processing: n_tokens = 811, truncated = 0 4.49.477.541 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.107 (> 0.100 thold), f_keep = 0.026 4.49.479.567 I slot launch_slot_: id 0 | task 16498 | processing task, is_child = 0 4.52.487.204 I slot print_timing: id 0 | task 16498 | prompt eval time = 377.05 ms / 197 tokens ( 1.91 ms per token, 522.48 tokens per second) 4.52.487.207 I slot print_timing: id 0 | task 16498 | eval time = 2630.58 ms / 178 tokens ( 14.86 ms per token, 67.29 tokens per second) 4.52.487.208 I slot print_timing: id 0 | task 16498 | total time = 3007.63 ms / 375 tokens 4.52.487.208 I slot print_timing: id 0 | task 16498 | graphs reused = 16190 4.52.487.209 I slot print_timing: id 0 | task 16498 | graph reallocs = 0 / 0 (same size) / (changed size) 4.52.487.233 I slot release: id 0 | task 16498 | stop processing: n_tokens = 374, truncated = 0 4.52.490.499 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 374, t_last = 334837018248 4.52.491.421 I slot launch_slot_: id 0 | task 16678 | processing task, is_child = 0 4.54.972.342 I slot print_timing: id 0 | task 16678 | prompt eval time = 389.53 ms / 217 tokens ( 1.80 ms per token, 557.08 tokens per second) 4.54.972.348 I slot print_timing: id 0 | task 16678 | eval time = 2091.38 ms / 142 tokens ( 14.83 ms per token, 67.42 tokens per second) 4.54.972.349 I slot print_timing: id 0 | task 16678 | total time = 2480.91 ms / 359 tokens 4.54.972.349 I slot print_timing: id 0 | task 16678 | graphs reused = 16329 4.54.972.350 I slot print_timing: id 0 | task 16678 | graph reallocs = 0 / 0 (same size) / (changed size) 4.54.972.374 I slot release: id 0 | task 16678 | stop processing: n_tokens = 358, truncated = 0 4.54.975.714 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 4.54.976.145 I slot launch_slot_: id 0 | task 16822 | processing task, is_child = 0 4.58.368.498 I slot print_timing: id 0 | task 16822 | n_gen = 204, tg = 67.42 t/s, tg_3s = 67.75 t/s 4.59.526.741 I slot print_timing: id 0 | task 16822 | prompt eval time = 381.41 ms / 200 tokens ( 1.91 ms per token, 524.37 tokens per second) 4.59.526.747 I slot print_timing: id 0 | task 16822 | eval time = 4169.17 ms / 282 tokens ( 14.84 ms per token, 67.40 tokens per second) 4.59.526.748 I slot print_timing: id 0 | task 16822 | total time = 4550.59 ms / 482 tokens 4.59.526.748 I slot print_timing: id 0 | task 16822 | graphs reused = 16608 4.59.526.749 I slot print_timing: id 0 | task 16822 | graph reallocs = 0 / 0 (same size) / (changed size) 4.59.526.776 I slot release: id 0 | task 16822 | stop processing: n_tokens = 481, truncated = 0 4.59.530.150 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.124 (> 0.100 thold), f_keep = 0.044 4.59.531.343 I slot launch_slot_: id 0 | task 17106 | processing task, is_child = 0 5.02.895.618 I slot print_timing: id 0 | task 17106 | n_gen = 204, tg = 67.41 t/s, tg_3s = 67.74 t/s 5.03.430.742 I slot print_timing: id 0 | task 17106 | prompt eval time = 352.72 ms / 170 tokens ( 2.07 ms per token, 481.97 tokens per second) 5.03.430.747 I slot print_timing: id 0 | task 17106 | eval time = 3546.67 ms / 240 tokens ( 14.84 ms per token, 67.39 tokens per second) 5.03.430.748 I slot print_timing: id 0 | task 17106 | total time = 3899.39 ms / 410 tokens 5.03.430.749 I slot print_timing: id 0 | task 17106 | graphs reused = 16845 5.03.430.749 I slot print_timing: id 0 | task 17106 | graph reallocs = 0 / 0 (same size) / (changed size) 5.03.430.770 I slot release: id 0 | task 17106 | stop processing: n_tokens = 409, truncated = 0 5.03.434.213 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 334847961785 5.03.435.251 I slot launch_slot_: id 0 | task 17348 | processing task, is_child = 0 5.06.865.788 I slot print_timing: id 0 | task 17348 | n_gen = 204, tg = 67.37 t/s, tg_3s = 67.70 t/s 5.09.868.412 I slot print_timing: id 0 | task 17348 | n_gen = 406, tg = 67.32 t/s, tg_3s = 67.27 t/s 5.12.875.242 I slot print_timing: id 0 | task 17348 | n_gen = 608, tg = 67.27 t/s, tg_3s = 67.18 t/s 5.15.888.153 I slot print_timing: id 0 | task 17348 | n_gen = 810, tg = 67.22 t/s, tg_3s = 67.04 t/s 5.18.892.063 I slot print_timing: id 0 | task 17348 | n_gen = 1011, tg = 67.16 t/s, tg_3s = 66.91 t/s 5.18.981.852 I slot print_timing: id 0 | task 17348 | prompt eval time = 417.18 ms / 241 tokens ( 1.73 ms per token, 577.69 tokens per second) 5.18.981.854 I slot print_timing: id 0 | task 17348 | eval time = 15129.41 ms / 1017 tokens ( 14.89 ms per token, 67.15 tokens per second) 5.18.981.855 I slot print_timing: id 0 | task 17348 | total time = 15546.59 ms / 1258 tokens 5.18.981.856 I slot print_timing: id 0 | task 17348 | graphs reused = 17856 5.18.981.856 I slot print_timing: id 0 | task 17348 | graph reallocs = 0 / 0 (same size) / (changed size) 5.18.981.889 I slot release: id 0 | task 17348 | stop processing: n_tokens = 1257, truncated = 0 5.18.985.673 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1257, t_last = 334863512904 5.18.988.608 I slot launch_slot_: id 0 | task 18367 | processing task, is_child = 0 5.22.412.004 I slot print_timing: id 0 | task 18367 | n_gen = 204, tg = 67.54 t/s, tg_3s = 67.87 t/s 5.23.433.546 I slot print_timing: id 0 | task 18367 | prompt eval time = 417.63 ms / 237 tokens ( 1.76 ms per token, 567.49 tokens per second) 5.23.433.551 I slot print_timing: id 0 | task 18367 | eval time = 4027.30 ms / 273 tokens ( 14.81 ms per token, 67.54 tokens per second) 5.23.433.552 I slot print_timing: id 0 | task 18367 | total time = 4444.93 ms / 510 tokens 5.23.433.553 I slot print_timing: id 0 | task 18367 | graphs reused = 18126 5.23.433.553 I slot print_timing: id 0 | task 18367 | graph reallocs = 0 / 0 (same size) / (changed size) 5.23.433.576 I slot release: id 0 | task 18367 | stop processing: n_tokens = 509, truncated = 0 5.23.437.058 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 509, t_last = 334867964591 5.23.438.274 I slot launch_slot_: id 0 | task 18642 | processing task, is_child = 0 5.26.935.944 I slot print_timing: id 0 | task 18642 | n_gen = 204, tg = 67.41 t/s, tg_3s = 67.74 t/s 5.28.790.896 I slot print_timing: id 0 | task 18642 | prompt eval time = 486.23 ms / 322 tokens ( 1.51 ms per token, 662.24 tokens per second) 5.28.790.901 I slot print_timing: id 0 | task 18642 | eval time = 4866.38 ms / 329 tokens ( 14.84 ms per token, 67.40 tokens per second) 5.28.790.902 I slot print_timing: id 0 | task 18642 | total time = 5352.61 ms / 651 tokens 5.28.790.905 I slot print_timing: id 0 | task 18642 | graphs reused = 18452 5.28.790.906 I slot print_timing: id 0 | task 18642 | graph reallocs = 0 / 0 (same size) / (changed size) 5.28.790.938 I slot release: id 0 | task 18642 | stop processing: n_tokens = 650, truncated = 0 5.28.794.310 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.120 (> 0.100 thold), f_keep = 0.032 5.28.795.850 I slot launch_slot_: id 0 | task 18973 | processing task, is_child = 0 5.32.154.046 I slot print_timing: id 0 | task 18973 | n_gen = 203, tg = 67.26 t/s, tg_3s = 67.60 t/s 5.35.017.905 I slot print_timing: id 0 | task 18973 | prompt eval time = 355.08 ms / 175 tokens ( 2.03 ms per token, 492.84 tokens per second) 5.35.017.908 I slot print_timing: id 0 | task 18973 | eval time = 5866.96 ms / 396 tokens ( 14.85 ms per token, 67.33 tokens per second) 5.35.017.909 I slot print_timing: id 0 | task 18973 | total time = 6222.04 ms / 571 tokens 5.35.017.909 I slot print_timing: id 0 | task 18973 | graphs reused = 18844 5.35.017.910 I slot print_timing: id 0 | task 18973 | graph reallocs = 0 / 0 (same size) / (changed size) 5.35.017.933 I slot release: id 0 | task 18973 | stop processing: n_tokens = 570, truncated = 0 5.35.021.423 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.117 (> 0.100 thold), f_keep = 0.037 5.35.022.751 I slot launch_slot_: id 0 | task 19371 | processing task, is_child = 0 5.38.393.872 I slot print_timing: id 0 | task 19371 | n_gen = 203, tg = 67.09 t/s, tg_3s = 67.42 t/s 5.40.824.434 I slot print_timing: id 0 | task 19371 | prompt eval time = 360.06 ms / 179 tokens ( 2.01 ms per token, 497.14 tokens per second) 5.40.824.437 I slot print_timing: id 0 | task 19371 | eval time = 5441.61 ms / 367 tokens ( 14.87 ms per token, 67.26 tokens per second) 5.40.824.437 I slot print_timing: id 0 | task 19371 | total time = 5801.67 ms / 546 tokens 5.40.824.438 I slot print_timing: id 0 | task 19371 | graphs reused = 19207 5.40.824.438 I slot print_timing: id 0 | task 19371 | graph reallocs = 0 / 0 (same size) / (changed size) 5.40.824.464 I slot release: id 0 | task 19371 | stop processing: n_tokens = 545, truncated = 0 5.40.828.182 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 545, t_last = 334885355479 5.40.830.253 I slot launch_slot_: id 0 | task 19740 | processing task, is_child = 0 5.44.257.978 I slot print_timing: id 0 | task 19740 | n_gen = 204, tg = 67.34 t/s, tg_3s = 67.67 t/s 5.45.759.734 I slot print_timing: id 0 | task 19740 | prompt eval time = 413.19 ms / 237 tokens ( 1.74 ms per token, 573.59 tokens per second) 5.45.759.738 I slot print_timing: id 0 | task 19740 | eval time = 4516.29 ms / 305 tokens ( 14.86 ms per token, 67.31 tokens per second) 5.45.759.738 I slot print_timing: id 0 | task 19740 | total time = 4929.47 ms / 542 tokens 5.45.759.739 I slot print_timing: id 0 | task 19740 | graphs reused = 19508 5.45.759.740 I slot print_timing: id 0 | task 19740 | graph reallocs = 0 / 0 (same size) / (changed size) 5.45.759.768 I slot release: id 0 | task 19740 | stop processing: n_tokens = 541, truncated = 0 5.45.763.323 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 541, t_last = 334890290783 5.45.764.717 I slot launch_slot_: id 0 | task 20047 | processing task, is_child = 0 5.49.222.684 I slot print_timing: id 0 | task 20047 | n_gen = 203, tg = 67.30 t/s, tg_3s = 67.64 t/s 5.49.564.466 I slot print_timing: id 0 | task 20047 | prompt eval time = 456.59 ms / 287 tokens ( 1.59 ms per token, 628.57 tokens per second) 5.49.564.472 I slot print_timing: id 0 | task 20047 | eval time = 3343.15 ms / 226 tokens ( 14.86 ms per token, 67.30 tokens per second) 5.49.564.473 I slot print_timing: id 0 | task 20047 | total time = 3799.74 ms / 513 tokens 5.49.564.474 I slot print_timing: id 0 | task 20047 | graphs reused = 19732 5.49.564.474 I slot print_timing: id 0 | task 20047 | graph reallocs = 0 / 0 (same size) / (changed size) 5.49.564.505 I slot release: id 0 | task 20047 | stop processing: n_tokens = 512, truncated = 0 5.49.567.894 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.148 (> 0.100 thold), f_keep = 0.070 5.49.569.100 I slot launch_slot_: id 0 | task 20275 | processing task, is_child = 0 5.52.989.910 I slot print_timing: id 0 | task 20275 | n_gen = 203, tg = 67.28 t/s, tg_3s = 67.61 t/s 5.53.525.973 I slot print_timing: id 0 | task 20275 | prompt eval time = 418.31 ms / 243 tokens ( 1.72 ms per token, 580.90 tokens per second) 5.53.525.976 I slot print_timing: id 0 | task 20275 | eval time = 3538.55 ms / 239 tokens ( 14.87 ms per token, 67.26 tokens per second) 5.53.525.977 I slot print_timing: id 0 | task 20275 | total time = 3956.87 ms / 482 tokens 5.53.525.977 I slot print_timing: id 0 | task 20275 | graphs reused = 19968 5.53.525.978 I slot print_timing: id 0 | task 20275 | graph reallocs = 0 / 0 (same size) / (changed size) 5.53.526.002 I slot release: id 0 | task 20275 | stop processing: n_tokens = 481, truncated = 0 5.53.529.452 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 481, t_last = 334898057017 5.53.530.678 I slot launch_slot_: id 0 | task 20516 | processing task, is_child = 0 5.56.957.776 I slot print_timing: id 0 | task 20516 | n_gen = 204, tg = 67.47 t/s, tg_3s = 67.80 t/s 5.59.958.899 I slot print_timing: id 0 | task 20516 | n_gen = 406, tg = 67.39 t/s, tg_3s = 67.31 t/s 6.00.418.345 I slot print_timing: id 0 | task 20516 | prompt eval time = 418.13 ms / 243 tokens ( 1.72 ms per token, 581.16 tokens per second) 6.00.418.351 I slot print_timing: id 0 | task 20516 | eval time = 6469.53 ms / 437 tokens ( 14.84 ms per token, 67.39 tokens per second) 6.00.418.351 I slot print_timing: id 0 | task 20516 | total time = 6887.66 ms / 680 tokens 6.00.418.352 I slot print_timing: id 0 | task 20516 | graphs reused = 20401 6.00.418.352 I slot print_timing: id 0 | task 20516 | graph reallocs = 0 / 0 (same size) / (changed size) 6.00.418.377 I slot release: id 0 | task 20516 | stop processing: n_tokens = 679, truncated = 0 6.00.421.901 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 679, t_last = 334904949393 6.00.423.396 I slot launch_slot_: id 0 | task 20955 | processing task, is_child = 0 6.03.870.681 I slot print_timing: id 0 | task 20955 | n_gen = 204, tg = 67.43 t/s, tg_3s = 67.77 t/s 6.05.123.847 I slot print_timing: id 0 | task 20955 | prompt eval time = 436.93 ms / 262 tokens ( 1.67 ms per token, 599.64 tokens per second) 6.05.123.853 I slot print_timing: id 0 | task 20955 | eval time = 4263.51 ms / 288 tokens ( 14.86 ms per token, 67.32 tokens per second) 6.05.123.854 I slot print_timing: id 0 | task 20955 | total time = 4700.44 ms / 550 tokens 6.05.123.854 I slot print_timing: id 0 | task 20955 | graphs reused = 20686 6.05.123.855 I slot print_timing: id 0 | task 20955 | graph reallocs = 0 / 0 (same size) / (changed size) 6.05.123.884 I slot release: id 0 | task 20955 | stop processing: n_tokens = 549, truncated = 0 6.05.127.422 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.102 (> 0.100 thold), f_keep = 0.038 6.05.128.826 I slot launch_slot_: id 0 | task 21245 | processing task, is_child = 0 6.07.814.120 I slot print_timing: id 0 | task 21245 | prompt eval time = 382.61 ms / 205 tokens ( 1.87 ms per token, 535.79 tokens per second) 6.07.814.123 I slot print_timing: id 0 | task 21245 | eval time = 2302.67 ms / 156 tokens ( 14.86 ms per token, 67.31 tokens per second) 6.07.814.124 I slot print_timing: id 0 | task 21245 | total time = 2685.28 ms / 361 tokens 6.07.814.124 I slot print_timing: id 0 | task 21245 | graphs reused = 20839 6.07.814.125 I slot print_timing: id 0 | task 21245 | graph reallocs = 0 / 0 (same size) / (changed size) 6.07.814.152 I slot release: id 0 | task 21245 | stop processing: n_tokens = 360, truncated = 0 6.07.817.623 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 360, t_last = 334912345167 6.07.818.602 I slot launch_slot_: id 0 | task 21403 | processing task, is_child = 0 6.11.217.886 I slot print_timing: id 0 | task 21403 | prompt eval time = 449.28 ms / 279 tokens ( 1.61 ms per token, 620.99 tokens per second) 6.11.217.889 I slot print_timing: id 0 | task 21403 | eval time = 2949.99 ms / 200 tokens ( 14.82 ms per token, 67.46 tokens per second) 6.11.217.890 I slot print_timing: id 0 | task 21403 | total time = 3399.27 ms / 479 tokens 6.11.217.891 I slot print_timing: id 0 | task 21403 | graphs reused = 21037 6.11.217.891 I slot print_timing: id 0 | task 21403 | graph reallocs = 0 / 0 (same size) / (changed size) 6.11.217.922 I slot release: id 0 | task 21403 | stop processing: n_tokens = 478, truncated = 0 6.11.221.514 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.108 (> 0.100 thold), f_keep = 0.044 6.11.222.822 I slot launch_slot_: id 0 | task 21605 | processing task, is_child = 0 6.14.604.705 I slot print_timing: id 0 | task 21605 | n_gen = 204, tg = 67.34 t/s, tg_3s = 67.67 t/s 6.16.606.868 I slot print_timing: id 0 | task 21605 | prompt eval time = 367.36 ms / 194 tokens ( 1.89 ms per token, 528.10 tokens per second) 6.16.606.874 I slot print_timing: id 0 | task 21605 | eval time = 5016.68 ms / 339 tokens ( 14.84 ms per token, 67.38 tokens per second) 6.16.606.875 I slot print_timing: id 0 | task 21605 | total time = 5384.04 ms / 533 tokens 6.16.606.875 I slot print_timing: id 0 | task 21605 | graphs reused = 21372 6.16.606.876 I slot print_timing: id 0 | task 21605 | graph reallocs = 0 / 0 (same size) / (changed size) 6.16.606.902 I slot release: id 0 | task 21605 | stop processing: n_tokens = 532, truncated = 0 6.16.610.421 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.124 (> 0.100 thold), f_keep = 0.039 6.16.611.692 I slot launch_slot_: id 0 | task 21946 | processing task, is_child = 0 6.19.556.044 I slot print_timing: id 0 | task 21946 | prompt eval time = 351.87 ms / 169 tokens ( 2.08 ms per token, 480.29 tokens per second) 6.19.556.047 I slot print_timing: id 0 | task 21946 | eval time = 2592.47 ms / 175 tokens ( 14.90 ms per token, 67.12 tokens per second) 6.19.556.048 I slot print_timing: id 0 | task 21946 | total time = 2944.34 ms / 344 tokens 6.19.556.048 I slot print_timing: id 0 | task 21946 | graphs reused = 21544 6.19.556.049 I slot print_timing: id 0 | task 21946 | graph reallocs = 0 / 0 (same size) / (changed size) 6.19.556.075 I slot release: id 0 | task 21946 | stop processing: n_tokens = 343, truncated = 0 6.19.559.520 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 343, t_last = 334924087090 6.19.560.695 I slot launch_slot_: id 0 | task 22123 | processing task, is_child = 0 6.23.001.648 I slot print_timing: id 0 | task 22123 | n_gen = 203, tg = 67.30 t/s, tg_3s = 67.63 t/s 6.23.997.351 I slot print_timing: id 0 | task 22123 | prompt eval time = 439.25 ms / 263 tokens ( 1.67 ms per token, 598.75 tokens per second) 6.23.997.354 I slot print_timing: id 0 | task 22123 | eval time = 3997.40 ms / 270 tokens ( 14.86 ms per token, 67.29 tokens per second) 6.23.997.355 I slot print_timing: id 0 | task 22123 | total time = 4436.65 ms / 533 tokens 6.23.997.355 I slot print_timing: id 0 | task 22123 | graphs reused = 21811 6.23.997.356 I slot print_timing: id 0 | task 22123 | graph reallocs = 0 / 0 (same size) / (changed size) 6.23.997.384 I slot release: id 0 | task 22123 | stop processing: n_tokens = 532, truncated = 0 6.24.000.841 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 6.24.002.205 I slot launch_slot_: id 0 | task 22395 | processing task, is_child = 0 6.26.970.935 I slot print_timing: id 0 | task 22395 | prompt eval time = 383.99 ms / 204 tokens ( 1.88 ms per token, 531.27 tokens per second) 6.26.970.938 I slot print_timing: id 0 | task 22395 | eval time = 2584.73 ms / 175 tokens ( 14.85 ms per token, 67.32 tokens per second) 6.26.970.938 I slot print_timing: id 0 | task 22395 | total time = 2968.72 ms / 379 tokens 6.26.970.939 I slot print_timing: id 0 | task 22395 | graphs reused = 21983 6.26.970.939 I slot print_timing: id 0 | task 22395 | graph reallocs = 0 / 0 (same size) / (changed size) 6.26.970.966 I slot release: id 0 | task 22395 | stop processing: n_tokens = 378, truncated = 0 6.26.974.378 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 378, t_last = 334931501981 6.26.975.398 I slot launch_slot_: id 0 | task 22572 | processing task, is_child = 0 6.30.431.797 I slot print_timing: id 0 | task 22572 | n_gen = 204, tg = 67.42 t/s, tg_3s = 67.76 t/s 6.33.433.125 I slot print_timing: id 0 | task 22572 | n_gen = 406, tg = 67.36 t/s, tg_3s = 67.30 t/s 6.34.804.827 I slot print_timing: id 0 | task 22572 | prompt eval time = 445.56 ms / 272 tokens ( 1.64 ms per token, 610.47 tokens per second) 6.34.804.831 I slot print_timing: id 0 | task 22572 | eval time = 7383.86 ms / 498 tokens ( 14.86 ms per token, 67.31 tokens per second) 6.34.804.832 I slot print_timing: id 0 | task 22572 | total time = 7829.42 ms / 770 tokens 6.34.804.832 I slot print_timing: id 0 | task 22572 | graphs reused = 22477 6.34.804.833 I slot print_timing: id 0 | task 22572 | graph reallocs = 0 / 0 (same size) / (changed size) 6.34.804.863 I slot release: id 0 | task 22572 | stop processing: n_tokens = 769, truncated = 0 6.34.808.265 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 769, t_last = 334939335879 6.34.810.053 I slot launch_slot_: id 0 | task 23072 | processing task, is_child = 0 6.37.747.866 I slot print_timing: id 0 | task 23072 | prompt eval time = 411.77 ms / 231 tokens ( 1.78 ms per token, 561.00 tokens per second) 6.37.747.869 I slot print_timing: id 0 | task 23072 | eval time = 2526.04 ms / 171 tokens ( 14.86 ms per token, 67.30 tokens per second) 6.37.747.869 I slot print_timing: id 0 | task 23072 | total time = 2937.80 ms / 402 tokens 6.37.747.870 I slot print_timing: id 0 | task 23072 | graphs reused = 22645 6.37.747.871 I slot print_timing: id 0 | task 23072 | graph reallocs = 0 / 0 (same size) / (changed size) 6.37.747.902 I slot release: id 0 | task 23072 | stop processing: n_tokens = 401, truncated = 0 6.37.751.482 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 401, t_last = 334942278917 6.37.752.662 I slot launch_slot_: id 0 | task 23245 | processing task, is_child = 0 6.41.224.677 I slot print_timing: id 0 | task 23245 | n_gen = 204, tg = 67.36 t/s, tg_3s = 67.70 t/s 6.41.328.393 I slot print_timing: id 0 | task 23245 | prompt eval time = 458.56 ms / 291 tokens ( 1.58 ms per token, 634.60 tokens per second) 6.41.328.400 I slot print_timing: id 0 | task 23245 | eval time = 3117.16 ms / 211 tokens ( 14.84 ms per token, 67.37 tokens per second) 6.41.328.401 I slot print_timing: id 0 | task 23245 | total time = 3575.72 ms / 502 tokens 6.41.328.401 I slot print_timing: id 0 | task 23245 | graphs reused = 22854 6.41.328.402 I slot print_timing: id 0 | task 23245 | graph reallocs = 0 / 0 (same size) / (changed size) 6.41.328.431 I slot release: id 0 | task 23245 | stop processing: n_tokens = 501, truncated = 0 6.41.331.870 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 501, t_last = 334945859447 6.41.333.045 I slot launch_slot_: id 0 | task 23458 | processing task, is_child = 0 6.44.792.238 I slot print_timing: id 0 | task 23458 | n_gen = 204, tg = 67.54 t/s, tg_3s = 67.87 t/s 6.46.502.881 I slot print_timing: id 0 | task 23458 | prompt eval time = 453.61 ms / 285 tokens ( 1.59 ms per token, 628.30 tokens per second) 6.46.502.884 I slot print_timing: id 0 | task 23458 | eval time = 4716.22 ms / 319 tokens ( 14.83 ms per token, 67.43 tokens per second) 6.46.502.885 I slot print_timing: id 0 | task 23458 | total time = 5169.82 ms / 604 tokens 6.46.502.885 I slot print_timing: id 0 | task 23458 | graphs reused = 23170 6.46.502.886 I slot print_timing: id 0 | task 23458 | graph reallocs = 0 / 0 (same size) / (changed size) 6.46.502.915 I slot release: id 0 | task 23458 | stop processing: n_tokens = 603, truncated = 0 6.46.506.476 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 603, t_last = 334951033930 6.46.507.850 I slot launch_slot_: id 0 | task 23779 | processing task, is_child = 0 6.49.975.942 I slot print_timing: id 0 | task 23779 | n_gen = 204, tg = 67.40 t/s, tg_3s = 67.73 t/s 6.51.718.722 I slot print_timing: id 0 | task 23779 | prompt eval time = 456.26 ms / 289 tokens ( 1.58 ms per token, 633.41 tokens per second) 6.51.718.728 I slot print_timing: id 0 | task 23779 | eval time = 4754.60 ms / 321 tokens ( 14.86 ms per token, 67.30 tokens per second) 6.51.718.728 I slot print_timing: id 0 | task 23779 | total time = 5210.86 ms / 610 tokens 6.51.718.729 I slot print_timing: id 0 | task 23779 | graphs reused = 23488 6.51.718.730 I slot print_timing: id 0 | task 23779 | graph reallocs = 0 / 0 (same size) / (changed size) 6.51.718.762 I slot release: id 0 | task 23779 | stop processing: n_tokens = 609, truncated = 0 6.51.722.113 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 609, t_last = 334956249777 6.51.723.519 I slot launch_slot_: id 0 | task 24102 | processing task, is_child = 0 6.55.141.229 I slot print_timing: id 0 | task 24102 | n_gen = 203, tg = 67.28 t/s, tg_3s = 67.61 t/s 6.56.646.518 I slot print_timing: id 0 | task 24102 | prompt eval time = 415.29 ms / 242 tokens ( 1.72 ms per token, 582.72 tokens per second) 6.56.646.523 I slot print_timing: id 0 | task 24102 | eval time = 4507.70 ms / 304 tokens ( 14.88 ms per token, 67.22 tokens per second) 6.56.646.524 I slot print_timing: id 0 | task 24102 | total time = 4922.99 ms / 546 tokens 6.56.646.524 I slot print_timing: id 0 | task 24102 | graphs reused = 23788 6.56.646.525 I slot print_timing: id 0 | task 24102 | graph reallocs = 0 / 0 (same size) / (changed size) 6.56.646.550 I slot release: id 0 | task 24102 | stop processing: n_tokens = 545, truncated = 0 6.56.649.876 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 6.56.651.189 I slot launch_slot_: id 0 | task 24408 | processing task, is_child = 0 7.00.023.145 I slot print_timing: id 0 | task 24408 | n_gen = 204, tg = 67.34 t/s, tg_3s = 67.67 t/s 7.00.052.828 I slot print_timing: id 0 | task 24408 | prompt eval time = 357.49 ms / 178 tokens ( 2.01 ms per token, 497.91 tokens per second) 7.00.052.833 I slot print_timing: id 0 | task 24408 | eval time = 3044.14 ms / 206 tokens ( 14.85 ms per token, 67.34 tokens per second) 7.00.052.834 I slot print_timing: id 0 | task 24408 | total time = 3401.63 ms / 384 tokens 7.00.052.835 I slot print_timing: id 0 | task 24408 | graphs reused = 23991 7.00.052.835 I slot print_timing: id 0 | task 24408 | graph reallocs = 0 / 0 (same size) / (changed size) 7.00.052.857 I slot release: id 0 | task 24408 | stop processing: n_tokens = 383, truncated = 0 7.00.056.149 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 383, t_last = 334964583872 7.00.057.099 I slot launch_slot_: id 0 | task 24616 | processing task, is_child = 0 7.03.055.088 I slot print_timing: id 0 | task 24616 | prompt eval time = 441.68 ms / 264 tokens ( 1.67 ms per token, 597.72 tokens per second) 7.03.055.091 I slot print_timing: id 0 | task 24616 | eval time = 2556.30 ms / 173 tokens ( 14.86 ms per token, 67.28 tokens per second) 7.03.055.092 I slot print_timing: id 0 | task 24616 | total time = 2997.98 ms / 437 tokens 7.03.055.093 I slot print_timing: id 0 | task 24616 | graphs reused = 24162 7.03.055.093 I slot print_timing: id 0 | task 24616 | graph reallocs = 0 / 0 (same size) / (changed size) 7.03.055.125 I slot release: id 0 | task 24616 | stop processing: n_tokens = 436, truncated = 0 7.03.058.492 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 7.03.059.688 I slot launch_slot_: id 0 | task 24791 | processing task, is_child = 0 7.05.321.634 I slot print_timing: id 0 | task 24791 | prompt eval time = 334.71 ms / 152 tokens ( 2.20 ms per token, 454.13 tokens per second) 7.05.321.637 I slot print_timing: id 0 | task 24791 | eval time = 1927.23 ms / 130 tokens ( 14.94 ms per token, 66.94 tokens per second) 7.05.321.638 I slot print_timing: id 0 | task 24791 | total time = 2261.93 ms / 282 tokens 7.05.321.638 I slot print_timing: id 0 | task 24791 | graphs reused = 24289 7.05.321.639 I slot print_timing: id 0 | task 24791 | graph reallocs = 0 / 0 (same size) / (changed size) 7.05.321.663 I slot release: id 0 | task 24791 | stop processing: n_tokens = 281, truncated = 0 7.05.324.988 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 7.05.325.415 I slot launch_slot_: id 0 | task 24923 | processing task, is_child = 0 7.08.708.189 I slot print_timing: id 0 | task 24923 | n_gen = 204, tg = 67.37 t/s, tg_3s = 67.70 t/s 7.08.811.700 I slot print_timing: id 0 | task 24923 | prompt eval time = 369.61 ms / 194 tokens ( 1.91 ms per token, 524.88 tokens per second) 7.08.811.706 I slot print_timing: id 0 | task 24923 | eval time = 3116.67 ms / 211 tokens ( 14.84 ms per token, 67.38 tokens per second) 7.08.811.707 I slot print_timing: id 0 | task 24923 | total time = 3486.28 ms / 405 tokens 7.08.811.708 I slot print_timing: id 0 | task 24923 | graphs reused = 24497 7.08.811.708 I slot print_timing: id 0 | task 24923 | graph reallocs = 0 / 0 (same size) / (changed size) 7.08.811.731 I slot release: id 0 | task 24923 | stop processing: n_tokens = 404, truncated = 0 7.08.815.632 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 404, t_last = 334973342746 7.08.816.756 I slot launch_slot_: id 0 | task 25136 | processing task, is_child = 0 7.12.270.262 I slot print_timing: id 0 | task 25136 | n_gen = 203, tg = 67.10 t/s, tg_3s = 67.43 t/s 7.12.434.008 I slot print_timing: id 0 | task 25136 | prompt eval time = 442.87 ms / 269 tokens ( 1.65 ms per token, 607.40 tokens per second) 7.12.434.014 I slot print_timing: id 0 | task 25136 | eval time = 3174.37 ms / 214 tokens ( 14.90 ms per token, 67.10 tokens per second) 7.12.434.014 I slot print_timing: id 0 | task 25136 | total time = 3617.25 ms / 483 tokens 7.12.434.015 I slot print_timing: id 0 | task 25136 | graphs reused = 24709 7.12.434.016 I slot print_timing: id 0 | task 25136 | graph reallocs = 0 / 0 (same size) / (changed size) 7.12.434.043 I slot release: id 0 | task 25136 | stop processing: n_tokens = 482, truncated = 0 7.12.437.777 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 482, t_last = 334976965058 7.12.439.022 I slot launch_slot_: id 0 | task 25352 | processing task, is_child = 0 7.15.906.501 I slot print_timing: id 0 | task 25352 | n_gen = 203, tg = 67.02 t/s, tg_3s = 67.35 t/s 7.18.911.632 I slot print_timing: id 0 | task 25352 | n_gen = 405, tg = 67.12 t/s, tg_3s = 67.22 t/s 7.21.926.118 I slot print_timing: id 0 | task 25352 | n_gen = 608, tg = 67.19 t/s, tg_3s = 67.34 t/s 7.24.932.869 I slot print_timing: id 0 | task 25352 | n_gen = 810, tg = 67.19 t/s, tg_3s = 67.18 t/s 7.27.941.532 I slot print_timing: id 0 | task 25352 | n_gen = 1012, tg = 67.18 t/s, tg_3s = 67.14 t/s 7.28.120.322 I slot print_timing: id 0 | task 25352 | prompt eval time = 453.52 ms / 283 tokens ( 1.60 ms per token, 624.01 tokens per second) 7.28.120.328 I slot print_timing: id 0 | task 25352 | eval time = 15227.77 ms / 1024 tokens ( 14.89 ms per token, 67.18 tokens per second) 7.28.120.329 I slot print_timing: id 0 | task 25352 | total time = 15681.29 ms / 1307 tokens 7.28.120.329 I slot print_timing: id 0 | task 25352 | graphs reused = 25727 7.28.120.330 I slot print_timing: id 0 | task 25352 | graph reallocs = 0 / 0 (same size) / (changed size) 7.28.120.357 I slot release: id 0 | task 25352 | stop processing: n_tokens = 1306, truncated = 0 7.28.124.055 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1306, t_last = 334992651372 7.28.126.854 I slot launch_slot_: id 0 | task 26378 | processing task, is_child = 0 7.31.575.002 I slot print_timing: id 0 | task 26378 | prompt eval time = 474.79 ms / 306 tokens ( 1.55 ms per token, 644.50 tokens per second) 7.31.575.005 I slot print_timing: id 0 | task 26378 | eval time = 2973.35 ms / 201 tokens ( 14.87 ms per token, 67.26 tokens per second) 7.31.575.006 I slot print_timing: id 0 | task 26378 | total time = 3448.13 ms / 507 tokens 7.31.575.007 I slot print_timing: id 0 | task 26378 | graphs reused = 25926 7.31.575.008 I slot print_timing: id 0 | task 26378 | graph reallocs = 0 / 0 (same size) / (changed size) 7.31.575.041 I slot release: id 0 | task 26378 | stop processing: n_tokens = 506, truncated = 0 7.31.578.680 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 506, t_last = 334996106056 7.31.579.910 I slot launch_slot_: id 0 | task 26581 | processing task, is_child = 0 7.33.614.987 I slot print_timing: id 0 | task 26581 | prompt eval time = 487.34 ms / 317 tokens ( 1.54 ms per token, 650.47 tokens per second) 7.33.614.990 I slot print_timing: id 0 | task 26581 | eval time = 1547.72 ms / 105 tokens ( 14.88 ms per token, 67.20 tokens per second) 7.33.614.992 I slot print_timing: id 0 | task 26581 | total time = 2035.07 ms / 422 tokens 7.33.614.993 I slot print_timing: id 0 | task 26581 | graphs reused = 26029 7.33.614.993 I slot print_timing: id 0 | task 26581 | graph reallocs = 0 / 0 (same size) / (changed size) 7.33.615.021 I slot release: id 0 | task 26581 | stop processing: n_tokens = 421, truncated = 0 7.33.618.501 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 421, t_last = 334998146036 7.33.619.576 I slot launch_slot_: id 0 | task 26688 | processing task, is_child = 0 7.37.091.445 I slot print_timing: id 0 | task 26688 | n_gen = 203, tg = 67.31 t/s, tg_3s = 67.65 t/s 7.37.255.853 I slot print_timing: id 0 | task 26688 | prompt eval time = 470.93 ms / 296 tokens ( 1.59 ms per token, 628.55 tokens per second) 7.37.255.859 I slot print_timing: id 0 | task 26688 | eval time = 3165.34 ms / 214 tokens ( 14.86 ms per token, 67.29 tokens per second) 7.37.255.860 I slot print_timing: id 0 | task 26688 | total time = 3636.27 ms / 510 tokens 7.37.255.860 I slot print_timing: id 0 | task 26688 | graphs reused = 26241 7.37.255.861 I slot print_timing: id 0 | task 26688 | graph reallocs = 0 / 0 (same size) / (changed size) 7.37.255.886 I slot release: id 0 | task 26688 | stop processing: n_tokens = 509, truncated = 0 7.37.259.373 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 509, t_last = 335001786901 7.37.260.646 I slot launch_slot_: id 0 | task 26904 | processing task, is_child = 0 7.40.644.697 I slot print_timing: id 0 | task 26904 | prompt eval time = 426.81 ms / 254 tokens ( 1.68 ms per token, 595.11 tokens per second) 7.40.644.703 I slot print_timing: id 0 | task 26904 | eval time = 2957.23 ms / 200 tokens ( 14.86 ms per token, 67.29 tokens per second) 7.40.644.704 I slot print_timing: id 0 | task 26904 | total time = 3384.04 ms / 454 tokens 7.40.644.704 I slot print_timing: id 0 | task 26904 | graphs reused = 26438 7.40.644.705 I slot print_timing: id 0 | task 26904 | graph reallocs = 0 / 0 (same size) / (changed size) 7.40.644.730 I slot release: id 0 | task 26904 | stop processing: n_tokens = 453, truncated = 0 7.40.648.151 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.112 (> 0.100 thold), f_keep = 0.046 7.40.649.307 I slot launch_slot_: id 0 | task 27106 | processing task, is_child = 0 7.43.079.224 I slot print_timing: id 0 | task 27106 | prompt eval time = 364.99 ms / 188 tokens ( 1.94 ms per token, 515.08 tokens per second) 7.43.079.230 I slot print_timing: id 0 | task 27106 | eval time = 2064.91 ms / 140 tokens ( 14.86 ms per token, 67.32 tokens per second) 7.43.079.231 I slot print_timing: id 0 | task 27106 | total time = 2429.91 ms / 328 tokens 7.43.079.231 I slot print_timing: id 0 | task 27106 | graphs reused = 26575 7.43.079.232 I slot print_timing: id 0 | task 27106 | graph reallocs = 0 / 0 (same size) / (changed size) 7.43.079.253 I slot release: id 0 | task 27106 | stop processing: n_tokens = 327, truncated = 0 7.43.083.230 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 327, t_last = 335007610268 7.43.083.753 I slot launch_slot_: id 0 | task 27248 | processing task, is_child = 0 7.46.482.777 I slot print_timing: id 0 | task 27248 | prompt eval time = 567.46 ms / 394 tokens ( 1.44 ms per token, 694.32 tokens per second) 7.46.482.783 I slot print_timing: id 0 | task 27248 | eval time = 2831.55 ms / 191 tokens ( 14.90 ms per token, 67.10 tokens per second) 7.46.482.783 I slot print_timing: id 0 | task 27248 | total time = 3399.01 ms / 585 tokens 7.46.482.784 I slot print_timing: id 0 | task 27248 | graphs reused = 26763 7.46.482.784 I slot print_timing: id 0 | task 27248 | graph reallocs = 0 / 0 (same size) / (changed size) 7.46.482.821 I slot release: id 0 | task 27248 | stop processing: n_tokens = 584, truncated = 0 7.46.486.897 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 584, t_last = 335011013836 7.46.488.289 I slot launch_slot_: id 0 | task 27441 | processing task, is_child = 0 7.50.393.379 I slot print_timing: id 0 | task 27441 | n_gen = 203, tg = 67.15 t/s, tg_3s = 67.48 t/s 7.53.399.972 I slot print_timing: id 0 | task 27441 | n_gen = 405, tg = 67.17 t/s, tg_3s = 67.19 t/s 7.54.402.183 I slot print_timing: id 0 | task 27441 | prompt eval time = 896.92 ms / 584 tokens ( 1.54 ms per token, 651.11 tokens per second) 7.54.402.189 I slot print_timing: id 0 | task 27441 | eval time = 7016.96 ms / 472 tokens ( 14.90 ms per token, 67.12 tokens per second) 7.54.402.189 I slot print_timing: id 0 | task 27441 | total time = 7913.88 ms / 1056 tokens 7.54.402.190 I slot print_timing: id 0 | task 27441 | graphs reused = 27231 7.54.402.190 I slot print_timing: id 0 | task 27441 | graph reallocs = 0 / 0 (same size) / (changed size) 7.54.402.234 I slot release: id 0 | task 27441 | stop processing: n_tokens = 1055, truncated = 0 7.54.406.320 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1055, t_last = 335018933249 7.54.408.707 I slot launch_slot_: id 0 | task 27916 | processing task, is_child = 0 7.58.119.440 I slot print_timing: id 0 | task 27916 | n_gen = 203, tg = 67.19 t/s, tg_3s = 67.52 t/s 8.01.124.613 I slot print_timing: id 0 | task 27916 | n_gen = 405, tg = 67.20 t/s, tg_3s = 67.22 t/s 8.01.556.640 I slot print_timing: id 0 | task 27916 | prompt eval time = 704.36 ms / 518 tokens ( 1.36 ms per token, 735.42 tokens per second) 8.01.556.646 I slot print_timing: id 0 | task 27916 | eval time = 6443.56 ms / 434 tokens ( 14.88 ms per token, 67.20 tokens per second) 8.01.556.647 I slot print_timing: id 0 | task 27916 | total time = 7147.92 ms / 952 tokens 8.01.556.647 I slot print_timing: id 0 | task 27916 | graphs reused = 27662 8.01.556.648 I slot print_timing: id 0 | task 27916 | graph reallocs = 0 / 0 (same size) / (changed size) 8.01.556.689 I slot release: id 0 | task 27916 | stop processing: n_tokens = 951, truncated = 0 8.01.560.444 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 951, t_last = 335026087704 8.01.562.622 I slot launch_slot_: id 0 | task 28353 | processing task, is_child = 0 8.05.144.748 I slot print_timing: id 0 | task 28353 | n_gen = 204, tg = 67.35 t/s, tg_3s = 67.68 t/s 8.05.991.628 I slot print_timing: id 0 | task 28353 | prompt eval time = 568.14 ms / 399 tokens ( 1.42 ms per token, 702.29 tokens per second) 8.05.991.634 I slot print_timing: id 0 | task 28353 | eval time = 3860.85 ms / 261 tokens ( 14.85 ms per token, 67.34 tokens per second) 8.05.991.634 I slot print_timing: id 0 | task 28353 | total time = 4429.00 ms / 660 tokens 8.05.991.635 I slot print_timing: id 0 | task 28353 | graphs reused = 27920 8.05.991.635 I slot print_timing: id 0 | task 28353 | graph reallocs = 0 / 0 (same size) / (changed size) 8.05.991.674 I slot release: id 0 | task 28353 | stop processing: n_tokens = 661, truncated = 0 8.05.995.444 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 661, t_last = 335030522690 8.05.997.123 I slot launch_slot_: id 0 | task 28616 | processing task, is_child = 0 8.09.513.126 I slot print_timing: id 0 | task 28616 | n_gen = 203, tg = 67.15 t/s, tg_3s = 67.48 t/s 8.09.542.736 I slot print_timing: id 0 | task 28616 | prompt eval time = 507.60 ms / 335 tokens ( 1.52 ms per token, 659.96 tokens per second) 8.09.542.742 I slot print_timing: id 0 | task 28616 | eval time = 3038.00 ms / 205 tokens ( 14.89 ms per token, 67.15 tokens per second) 8.09.542.742 I slot print_timing: id 0 | task 28616 | total time = 3545.61 ms / 540 tokens 8.09.542.743 I slot print_timing: id 0 | task 28616 | graphs reused = 28122 8.09.542.743 I slot print_timing: id 0 | task 28616 | graph reallocs = 0 / 0 (same size) / (changed size) 8.09.542.771 I slot release: id 0 | task 28616 | stop processing: n_tokens = 541, truncated = 0 8.09.546.888 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 541, t_last = 335034073786 8.09.548.188 I slot launch_slot_: id 0 | task 28823 | processing task, is_child = 0 8.13.469.827 I slot print_timing: id 0 | task 28823 | n_gen = 203, tg = 67.17 t/s, tg_3s = 67.50 t/s 8.16.470.581 I slot print_timing: id 0 | task 28823 | n_gen = 405, tg = 67.24 t/s, tg_3s = 67.32 t/s 8.18.159.122 I slot print_timing: id 0 | task 28823 | prompt eval time = 914.28 ms / 603 tokens ( 1.52 ms per token, 659.53 tokens per second) 8.18.159.128 I slot print_timing: id 0 | task 28823 | eval time = 7696.64 ms / 518 tokens ( 14.89 ms per token, 67.17 tokens per second) 8.18.159.129 I slot print_timing: id 0 | task 28823 | total time = 8610.92 ms / 1121 tokens 8.18.159.129 I slot print_timing: id 0 | task 28823 | graphs reused = 28636 8.18.159.130 I slot print_timing: id 0 | task 28823 | graph reallocs = 0 / 0 (same size) / (changed size) 8.18.159.173 I slot release: id 0 | task 28823 | stop processing: n_tokens = 1122, truncated = 0 8.18.162.870 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1122, t_last = 335042690189 8.18.165.362 I slot launch_slot_: id 0 | task 29344 | processing task, is_child = 0 8.21.677.801 I slot print_timing: id 0 | task 29344 | n_gen = 203, tg = 67.20 t/s, tg_3s = 67.53 t/s 8.23.166.578 I slot print_timing: id 0 | task 29344 | prompt eval time = 506.50 ms / 333 tokens ( 1.52 ms per token, 657.46 tokens per second) 8.23.166.581 I slot print_timing: id 0 | task 29344 | eval time = 4494.71 ms / 303 tokens ( 14.88 ms per token, 67.19 tokens per second) 8.23.166.582 I slot print_timing: id 0 | task 29344 | total time = 5001.20 ms / 636 tokens 8.23.166.583 I slot print_timing: id 0 | task 29344 | graphs reused = 28936 8.23.166.583 I slot print_timing: id 0 | task 29344 | graph reallocs = 0 / 0 (same size) / (changed size) 8.23.166.613 I slot release: id 0 | task 29344 | stop processing: n_tokens = 637, truncated = 0 8.23.170.465 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 335047697628 8.23.172.025 I slot launch_slot_: id 0 | task 29649 | processing task, is_child = 0 8.26.811.053 I slot print_timing: id 0 | task 29649 | n_gen = 203, tg = 67.17 t/s, tg_3s = 67.50 t/s 8.29.818.799 I slot print_timing: id 0 | task 29649 | n_gen = 405, tg = 67.17 t/s, tg_3s = 67.16 t/s 8.30.952.755 I slot print_timing: id 0 | task 29649 | prompt eval time = 631.76 ms / 460 tokens ( 1.37 ms per token, 728.12 tokens per second) 8.30.952.761 I slot print_timing: id 0 | task 29649 | eval time = 7148.96 ms / 481 tokens ( 14.89 ms per token, 67.14 tokens per second) 8.30.952.762 I slot print_timing: id 0 | task 29649 | total time = 7780.72 ms / 941 tokens 8.30.952.763 I slot print_timing: id 0 | task 29649 | graphs reused = 29413 8.30.952.763 I slot print_timing: id 0 | task 29649 | graph reallocs = 0 / 0 (same size) / (changed size) 8.30.952.802 I slot release: id 0 | task 29649 | stop processing: n_tokens = 942, truncated = 0 8.30.956.453 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 942, t_last = 335055483817 8.30.958.706 I slot launch_slot_: id 0 | task 30132 | processing task, is_child = 0 8.34.055.935 I slot print_timing: id 0 | task 30132 | prompt eval time = 393.95 ms / 225 tokens ( 1.75 ms per token, 571.14 tokens per second) 8.34.055.938 I slot print_timing: id 0 | task 30132 | eval time = 2703.27 ms / 183 tokens ( 14.85 ms per token, 67.33 tokens per second) 8.34.055.939 I slot print_timing: id 0 | task 30132 | total time = 3097.22 ms / 408 tokens 8.34.055.939 I slot print_timing: id 0 | task 30132 | graphs reused = 29593 8.34.055.940 I slot print_timing: id 0 | task 30132 | graph reallocs = 0 / 0 (same size) / (changed size) 8.34.055.963 I slot release: id 0 | task 30132 | stop processing: n_tokens = 409, truncated = 0 8.34.059.814 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 335058586978 8.34.061.037 I slot launch_slot_: id 0 | task 30317 | processing task, is_child = 0 8.37.643.837 I slot print_timing: id 0 | task 30317 | n_gen = 203, tg = 67.27 t/s, tg_3s = 67.60 t/s 8.38.401.189 I slot print_timing: id 0 | task 30317 | prompt eval time = 580.05 ms / 415 tokens ( 1.40 ms per token, 715.45 tokens per second) 8.38.401.195 I slot print_timing: id 0 | task 30317 | eval time = 3760.09 ms / 254 tokens ( 14.86 ms per token, 67.29 tokens per second) 8.38.401.196 I slot print_timing: id 0 | task 30317 | total time = 4340.14 ms / 669 tokens 8.38.401.196 I slot print_timing: id 0 | task 30317 | graphs reused = 29844 8.38.401.197 I slot print_timing: id 0 | task 30317 | graph reallocs = 0 / 0 (same size) / (changed size) 8.38.401.230 I slot release: id 0 | task 30317 | stop processing: n_tokens = 670, truncated = 0 8.38.405.103 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 670, t_last = 335062932246 8.38.406.710 I slot launch_slot_: id 0 | task 30573 | processing task, is_child = 0 8.42.124.429 I slot print_timing: id 0 | task 30573 | n_gen = 203, tg = 67.17 t/s, tg_3s = 67.50 t/s 8.45.130.414 I slot print_timing: id 0 | task 30573 | n_gen = 405, tg = 67.19 t/s, tg_3s = 67.20 t/s 8.45.931.160 I slot print_timing: id 0 | task 30573 | prompt eval time = 710.45 ms / 519 tokens ( 1.37 ms per token, 730.52 tokens per second) 8.45.931.166 I slot print_timing: id 0 | task 30573 | eval time = 6813.99 ms / 459 tokens ( 14.88 ms per token, 67.21 tokens per second) 8.45.931.167 I slot print_timing: id 0 | task 30573 | total time = 7524.44 ms / 978 tokens 8.45.931.167 I slot print_timing: id 0 | task 30573 | graphs reused = 30300 8.45.931.168 I slot print_timing: id 0 | task 30573 | graph reallocs = 0 / 0 (same size) / (changed size) 8.45.931.212 I slot release: id 0 | task 30573 | stop processing: n_tokens = 979, truncated = 0 8.45.935.365 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 979, t_last = 335070462227 8.45.937.636 I slot launch_slot_: id 0 | task 31035 | processing task, is_child = 0 8.49.857.289 I slot print_timing: id 0 | task 31035 | n_gen = 203, tg = 67.27 t/s, tg_3s = 67.60 t/s 8.52.871.044 I slot print_timing: id 0 | task 31035 | n_gen = 406, tg = 67.31 t/s, tg_3s = 67.36 t/s 8.55.882.600 I slot print_timing: id 0 | task 31035 | n_gen = 608, tg = 67.23 t/s, tg_3s = 67.07 t/s 8.58.888.253 I slot print_timing: id 0 | task 31035 | n_gen = 809, tg = 67.14 t/s, tg_3s = 66.87 t/s 9.01.209.562 I slot print_timing: id 0 | task 31035 | prompt eval time = 916.89 ms / 602 tokens ( 1.52 ms per token, 656.57 tokens per second) 9.01.209.568 I slot print_timing: id 0 | task 31035 | eval time = 14355.02 ms / 964 tokens ( 14.91 ms per token, 67.08 tokens per second) 9.01.209.569 I slot print_timing: id 0 | task 31035 | total time = 15271.91 ms / 1566 tokens 9.01.209.570 I slot print_timing: id 0 | task 31035 | graphs reused = 31258 9.01.209.570 I slot print_timing: id 0 | task 31035 | graph reallocs = 0 / 0 (same size) / (changed size) 9.01.209.617 I slot release: id 0 | task 31035 | stop processing: n_tokens = 1570, truncated = 0 9.01.213.903 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1570, t_last = 335085740632 9.01.217.322 I slot launch_slot_: id 0 | task 32002 | processing task, is_child = 0 9.04.804.317 I slot print_timing: id 0 | task 32002 | n_gen = 203, tg = 67.09 t/s, tg_3s = 67.43 t/s 9.06.200.824 I slot print_timing: id 0 | task 32002 | prompt eval time = 576.32 ms / 407 tokens ( 1.42 ms per token, 706.20 tokens per second) 9.06.200.830 I slot print_timing: id 0 | task 32002 | eval time = 4407.16 ms / 297 tokens ( 14.89 ms per token, 67.16 tokens per second) 9.06.200.831 I slot print_timing: id 0 | task 32002 | total time = 4983.49 ms / 704 tokens 9.06.200.831 I slot print_timing: id 0 | task 32002 | graphs reused = 31552 9.06.200.832 I slot print_timing: id 0 | task 32002 | graph reallocs = 0 / 0 (same size) / (changed size) 9.06.200.867 I slot release: id 0 | task 32002 | stop processing: n_tokens = 708, truncated = 0 9.06.204.782 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 708, t_last = 335090731882 9.06.206.556 I slot launch_slot_: id 0 | task 32301 | processing task, is_child = 0 9.09.861.091 I slot print_timing: id 0 | task 32301 | n_gen = 203, tg = 67.22 t/s, tg_3s = 67.55 t/s 9.12.863.774 I slot print_timing: id 0 | task 32301 | n_gen = 405, tg = 67.25 t/s, tg_3s = 67.27 t/s 9.13.862.023 I slot print_timing: id 0 | task 32301 | prompt eval time = 649.34 ms / 484 tokens ( 1.34 ms per token, 745.38 tokens per second) 9.13.862.026 I slot print_timing: id 0 | task 32301 | eval time = 7006.12 ms / 472 tokens ( 14.87 ms per token, 67.23 tokens per second) 9.13.862.026 I slot print_timing: id 0 | task 32301 | total time = 7655.45 ms / 956 tokens 9.13.862.027 I slot print_timing: id 0 | task 32301 | graphs reused = 32020 9.13.862.028 I slot print_timing: id 0 | task 32301 | graph reallocs = 0 / 0 (same size) / (changed size) 9.13.862.065 I slot release: id 0 | task 32301 | stop processing: n_tokens = 960, truncated = 0 9.13.866.010 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 960, t_last = 335098393080 9.13.868.198 I slot launch_slot_: id 0 | task 32775 | processing task, is_child = 0 9.17.436.353 I slot print_timing: id 0 | task 32775 | prompt eval time = 628.04 ms / 457 tokens ( 1.37 ms per token, 727.66 tokens per second) 9.17.436.360 I slot print_timing: id 0 | task 32775 | eval time = 2940.11 ms / 198 tokens ( 14.92 ms per token, 67.00 tokens per second) 9.17.436.361 I slot print_timing: id 0 | task 32775 | total time = 3568.15 ms / 655 tokens 9.17.436.361 I slot print_timing: id 0 | task 32775 | graphs reused = 32215 9.17.436.362 I slot print_timing: id 0 | task 32775 | graph reallocs = 0 / 0 (same size) / (changed size) 9.17.436.400 I slot release: id 0 | task 32775 | stop processing: n_tokens = 659, truncated = 0 9.17.440.494 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 659, t_last = 335101967415 9.17.442.575 I slot launch_slot_: id 0 | task 32975 | processing task, is_child = 0 9.21.357.110 I slot print_timing: id 0 | task 32975 | n_gen = 202, tg = 66.98 t/s, tg_3s = 67.31 t/s 9.24.369.116 I slot print_timing: id 0 | task 32975 | n_gen = 404, tg = 67.02 t/s, tg_3s = 67.06 t/s 9.24.594.248 I slot print_timing: id 0 | task 32975 | prompt eval time = 913.58 ms / 597 tokens ( 1.53 ms per token, 653.47 tokens per second) 9.24.594.251 I slot print_timing: id 0 | task 32975 | eval time = 6238.08 ms / 419 tokens ( 14.92 ms per token, 67.01 tokens per second) 9.24.594.253 I slot print_timing: id 0 | task 32975 | total time = 7151.66 ms / 1016 tokens 9.24.594.254 I slot print_timing: id 0 | task 32975 | graphs reused = 32631 9.24.594.254 I slot print_timing: id 0 | task 32975 | graph reallocs = 0 / 0 (same size) / (changed size) 9.24.594.300 I slot release: id 0 | task 32975 | stop processing: n_tokens = 1015, truncated = 0 9.24.599.491 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1015, t_last = 335109125315 9.24.602.016 I slot launch_slot_: id 0 | task 33397 | processing task, is_child = 0 9.27.623.070 I slot print_timing: id 0 | task 33397 | prompt eval time = 1003.11 ms / 688 tokens ( 1.46 ms per token, 685.87 tokens per second) 9.27.623.073 I slot print_timing: id 0 | task 33397 | eval time = 2017.94 ms / 136 tokens ( 14.95 ms per token, 66.90 tokens per second) 9.27.623.073 I slot print_timing: id 0 | task 33397 | total time = 3021.05 ms / 824 tokens 9.27.623.074 I slot print_timing: id 0 | task 33397 | graphs reused = 32764 9.27.623.075 I slot print_timing: id 0 | task 33397 | graph reallocs = 0 / 0 (same size) / (changed size) 9.27.623.125 I slot release: id 0 | task 33397 | stop processing: n_tokens = 823, truncated = 0 9.27.627.081 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 823, t_last = 335112154140 9.27.629.426 I slot launch_slot_: id 0 | task 33536 | processing task, is_child = 0 9.31.298.369 I slot print_timing: id 0 | task 33536 | n_gen = 203, tg = 67.16 t/s, tg_3s = 67.49 t/s 9.32.499.333 I slot print_timing: id 0 | task 33536 | prompt eval time = 661.22 ms / 489 tokens ( 1.35 ms per token, 739.54 tokens per second) 9.32.499.340 I slot print_timing: id 0 | task 33536 | eval time = 4208.67 ms / 283 tokens ( 14.92 ms per token, 67.00 tokens per second) 9.32.499.340 I slot print_timing: id 0 | task 33536 | total time = 4869.89 ms / 772 tokens 9.32.499.341 I slot print_timing: id 0 | task 33536 | graphs reused = 33043 9.32.499.342 I slot print_timing: id 0 | task 33536 | graph reallocs = 0 / 0 (same size) / (changed size) 9.32.499.383 I slot release: id 0 | task 33536 | stop processing: n_tokens = 771, truncated = 0 9.32.503.386 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 771, t_last = 335117030398 9.32.505.569 I slot launch_slot_: id 0 | task 33821 | processing task, is_child = 0 9.36.368.242 I slot print_timing: id 0 | task 33821 | n_gen = 203, tg = 67.03 t/s, tg_3s = 67.36 t/s 9.38.309.372 I slot print_timing: id 0 | task 33821 | prompt eval time = 848.87 ms / 550 tokens ( 1.54 ms per token, 647.92 tokens per second) 9.38.309.376 I slot print_timing: id 0 | task 33821 | eval time = 4954.92 ms / 333 tokens ( 14.92 ms per token, 67.00 tokens per second) 9.38.309.376 I slot print_timing: id 0 | task 33821 | total time = 5803.79 ms / 883 tokens 9.38.309.377 I slot print_timing: id 0 | task 33821 | graphs reused = 33373 9.38.309.377 I slot print_timing: id 0 | task 33821 | graph reallocs = 0 / 0 (same size) / (changed size) 9.38.309.419 I slot release: id 0 | task 33821 | stop processing: n_tokens = 882, truncated = 0 9.38.313.234 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 882, t_last = 335122840434 9.38.315.334 I slot launch_slot_: id 0 | task 34157 | processing task, is_child = 0 9.41.826.222 I slot print_timing: id 0 | task 34157 | n_gen = 203, tg = 67.18 t/s, tg_3s = 67.52 t/s 9.44.833.152 I slot print_timing: id 0 | task 34157 | n_gen = 405, tg = 67.18 t/s, tg_3s = 67.18 t/s 9.45.310.593 I slot print_timing: id 0 | task 34157 | prompt eval time = 504.14 ms / 334 tokens ( 1.51 ms per token, 662.51 tokens per second) 9.45.310.599 I slot print_timing: id 0 | task 34157 | eval time = 6491.11 ms / 437 tokens ( 14.89 ms per token, 67.17 tokens per second) 9.45.310.599 I slot print_timing: id 0 | task 34157 | total time = 6995.25 ms / 771 tokens 9.45.310.600 I slot print_timing: id 0 | task 34157 | graphs reused = 33806 9.45.310.601 I slot print_timing: id 0 | task 34157 | graph reallocs = 0 / 0 (same size) / (changed size) 9.45.310.632 I slot release: id 0 | task 34157 | stop processing: n_tokens = 770, truncated = 0 9.45.314.538 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 770, t_last = 335129841647 9.45.316.366 I slot launch_slot_: id 0 | task 34596 | processing task, is_child = 0 9.48.906.252 I slot print_timing: id 0 | task 34596 | n_gen = 203, tg = 67.17 t/s, tg_3s = 67.50 t/s 9.51.497.526 I slot print_timing: id 0 | task 34596 | prompt eval time = 582.59 ms / 416 tokens ( 1.40 ms per token, 714.05 tokens per second) 9.51.497.532 I slot print_timing: id 0 | task 34596 | eval time = 5598.56 ms / 377 tokens ( 14.89 ms per token, 67.16 tokens per second) 9.51.497.533 I slot print_timing: id 0 | task 34596 | total time = 6181.15 ms / 793 tokens 9.51.497.533 I slot print_timing: id 0 | task 34596 | graphs reused = 34179 9.51.497.534 I slot print_timing: id 0 | task 34596 | graph reallocs = 0 / 0 (same size) / (changed size) 9.51.497.571 I slot release: id 0 | task 34596 | stop processing: n_tokens = 792, truncated = 0 9.51.502.271 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 792, t_last = 335136028586 9.51.504.249 I slot launch_slot_: id 0 | task 34975 | processing task, is_child = 0 9.54.581.086 I slot print_timing: id 0 | task 34975 | prompt eval time = 1062.05 ms / 754 tokens ( 1.41 ms per token, 709.95 tokens per second) 9.54.581.093 I slot print_timing: id 0 | task 34975 | eval time = 2014.78 ms / 136 tokens ( 14.92 ms per token, 67.00 tokens per second) 9.54.581.093 I slot print_timing: id 0 | task 34975 | total time = 3076.83 ms / 890 tokens 9.54.581.094 I slot print_timing: id 0 | task 34975 | graphs reused = 34312 9.54.581.095 I slot print_timing: id 0 | task 34975 | graph reallocs = 0 / 0 (same size) / (changed size) 9.54.581.146 I slot release: id 0 | task 34975 | stop processing: n_tokens = 889, truncated = 0 9.54.586.026 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 889, t_last = 335139112162 9.54.588.390 I slot launch_slot_: id 0 | task 35114 | processing task, is_child = 0 9.58.611.694 I slot print_timing: id 0 | task 35114 | n_gen = 203, tg = 67.07 t/s, tg_3s = 67.40 t/s 10.00.689.909 I slot print_timing: id 0 | task 35114 | prompt eval time = 1011.35 ms / 706 tokens ( 1.43 ms per token, 698.08 tokens per second) 10.00.689.915 I slot print_timing: id 0 | task 35114 | eval time = 5090.16 ms / 342 tokens ( 14.93 ms per token, 66.99 tokens per second) 10.00.689.916 I slot print_timing: id 0 | task 35114 | total time = 6101.51 ms / 1048 tokens 10.00.689.916 I slot print_timing: id 0 | task 35114 | graphs reused = 34650 10.00.689.917 I slot print_timing: id 0 | task 35114 | graph reallocs = 0 / 0 (same size) / (changed size) 10.00.689.968 I slot release: id 0 | task 35114 | stop processing: n_tokens = 1047, truncated = 0 10.00.693.552 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1047, t_last = 335145220983 10.00.695.899 I slot launch_slot_: id 0 | task 35459 | processing task, is_child = 0 10.04.115.215 I slot print_timing: id 0 | task 35459 | n_gen = 204, tg = 67.41 t/s, tg_3s = 67.75 t/s 10.04.572.961 I slot print_timing: id 0 | task 35459 | prompt eval time = 408.06 ms / 233 tokens ( 1.75 ms per token, 571.00 tokens per second) 10.04.572.968 I slot print_timing: id 0 | task 35459 | eval time = 3469.00 ms / 235 tokens ( 14.82 ms per token, 67.45 tokens per second) 10.04.572.968 I slot print_timing: id 0 | task 35459 | total time = 3877.05 ms / 468 tokens 10.04.572.969 I slot print_timing: id 0 | task 35459 | graphs reused = 34882 10.04.572.969 I slot print_timing: id 0 | task 35459 | graph reallocs = 0 / 0 (same size) / (changed size) 10.04.572.995 I slot release: id 0 | task 35459 | stop processing: n_tokens = 467, truncated = 0 10.04.576.379 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.133 (> 0.100 thold), f_keep = 0.049 10.04.576.897 I slot launch_slot_: id 0 | task 35696 | processing task, is_child = 0 10.07.943.733 I slot print_timing: id 0 | task 35696 | n_gen = 204, tg = 67.39 t/s, tg_3s = 67.72 t/s 10.08.850.735 I slot print_timing: id 0 | task 35696 | prompt eval time = 354.42 ms / 173 tokens ( 2.05 ms per token, 488.13 tokens per second) 10.08.850.741 I slot print_timing: id 0 | task 35696 | eval time = 3919.41 ms / 265 tokens ( 14.85 ms per token, 67.36 tokens per second) 10.08.850.742 I slot print_timing: id 0 | task 35696 | total time = 4273.83 ms / 438 tokens 10.08.850.742 I slot print_timing: id 0 | task 35696 | graphs reused = 35144 10.08.850.743 I slot print_timing: id 0 | task 35696 | graph reallocs = 0 / 0 (same size) / (changed size) 10.08.850.763 I slot release: id 0 | task 35696 | stop processing: n_tokens = 437, truncated = 0 10.08.854.068 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.111 (> 0.100 thold), f_keep = 0.050 10.08.854.553 I slot launch_slot_: id 0 | task 35963 | processing task, is_child = 0 10.12.243.684 I slot print_timing: id 0 | task 35963 | n_gen = 204, tg = 67.44 t/s, tg_3s = 67.78 t/s 10.15.245.706 I slot print_timing: id 0 | task 35963 | n_gen = 406, tg = 67.37 t/s, tg_3s = 67.29 t/s 10.18.253.560 I slot print_timing: id 0 | task 35963 | n_gen = 608, tg = 67.30 t/s, tg_3s = 67.16 t/s 10.21.262.352 I slot print_timing: id 0 | task 35963 | n_gen = 810, tg = 67.26 t/s, tg_3s = 67.14 t/s 10.24.266.025 I slot print_timing: id 0 | task 35963 | n_gen = 1011, tg = 67.19 t/s, tg_3s = 66.92 t/s 10.24.460.520 I slot print_timing: id 0 | task 35963 | prompt eval time = 379.21 ms / 199 tokens ( 1.91 ms per token, 524.78 tokens per second) 10.24.460.529 I slot print_timing: id 0 | task 35963 | eval time = 15226.76 ms / 1024 tokens ( 14.88 ms per token, 67.18 tokens per second) 10.24.460.530 I slot print_timing: id 0 | task 35963 | total time = 15605.96 ms / 1223 tokens 10.24.460.530 I slot print_timing: id 0 | task 35963 | graphs reused = 36162 10.24.460.531 I slot print_timing: id 0 | task 35963 | graph reallocs = 0 / 0 (same size) / (changed size) 10.24.460.554 I slot release: id 0 | task 35963 | stop processing: n_tokens = 1222, truncated = 0 10.24.464.025 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.148 (> 0.100 thold), f_keep = 0.018 10.24.466.883 I slot launch_slot_: id 0 | task 36989 | processing task, is_child = 0 10.27.806.318 I slot print_timing: id 0 | task 36989 | n_gen = 203, tg = 67.18 t/s, tg_3s = 67.51 t/s 10.28.829.336 I slot print_timing: id 0 | task 36989 | prompt eval time = 332.44 ms / 149 tokens ( 2.23 ms per token, 448.21 tokens per second) 10.28.829.339 I slot print_timing: id 0 | task 36989 | eval time = 4030.00 ms / 272 tokens ( 14.87 ms per token, 67.25 tokens per second) 10.28.829.340 I slot print_timing: id 0 | task 36989 | total time = 4362.44 ms / 421 tokens 10.28.829.340 I slot print_timing: id 0 | task 36989 | graphs reused = 36431 10.28.829.341 I slot print_timing: id 0 | task 36989 | graph reallocs = 0 / 0 (same size) / (changed size) 10.28.829.364 I slot release: id 0 | task 36989 | stop processing: n_tokens = 420, truncated = 0 10.28.832.807 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 420, t_last = 335173360379 10.28.833.855 I slot launch_slot_: id 0 | task 37263 | processing task, is_child = 0 10.32.239.888 I slot print_timing: id 0 | task 37263 | n_gen = 204, tg = 67.35 t/s, tg_3s = 67.68 t/s 10.35.245.447 I slot print_timing: id 0 | task 37263 | n_gen = 406, tg = 67.28 t/s, tg_3s = 67.21 t/s 10.38.250.435 I slot print_timing: id 0 | task 37263 | n_gen = 608, tg = 67.26 t/s, tg_3s = 67.22 t/s 10.41.258.970 I slot print_timing: id 0 | task 37263 | n_gen = 810, tg = 67.23 t/s, tg_3s = 67.14 t/s 10.44.265.595 I slot print_timing: id 0 | task 37263 | n_gen = 1012, tg = 67.22 t/s, tg_3s = 67.19 t/s 10.44.443.658 I slot print_timing: id 0 | task 37263 | prompt eval time = 391.90 ms / 216 tokens ( 1.81 ms per token, 551.17 tokens per second) 10.44.443.665 I slot print_timing: id 0 | task 37263 | eval time = 15217.90 ms / 1024 tokens ( 14.88 ms per token, 67.22 tokens per second) 10.44.443.665 I slot print_timing: id 0 | task 37263 | total time = 15609.79 ms / 1240 tokens 10.44.443.666 I slot print_timing: id 0 | task 37263 | graphs reused = 37449 10.44.443.667 I slot print_timing: id 0 | task 37263 | graph reallocs = 0 / 0 (same size) / (changed size) 10.44.443.690 I slot release: id 0 | task 37263 | stop processing: n_tokens = 1239, truncated = 0 10.44.446.921 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 10.44.449.559 I slot launch_slot_: id 0 | task 38289 | processing task, is_child = 0 10.45.958.353 I slot print_timing: id 0 | task 38289 | prompt eval time = 310.84 ms / 131 tokens ( 2.37 ms per token, 421.43 tokens per second) 10.45.958.359 I slot print_timing: id 0 | task 38289 | eval time = 1197.94 ms / 81 tokens ( 14.97 ms per token, 66.78 tokens per second) 10.45.958.359 I slot print_timing: id 0 | task 38289 | total time = 1508.79 ms / 212 tokens 10.45.958.360 I slot print_timing: id 0 | task 38289 | graphs reused = 37528 10.45.958.360 I slot print_timing: id 0 | task 38289 | graph reallocs = 0 / 0 (same size) / (changed size) 10.45.958.379 I slot release: id 0 | task 38289 | stop processing: n_tokens = 211, truncated = 0 10.45.961.480 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.121 (> 0.100 thold), f_keep = 0.100 10.45.961.825 I slot launch_slot_: id 0 | task 38372 | processing task, is_child = 0 10.49.321.760 I slot print_timing: id 0 | task 38372 | n_gen = 203, tg = 67.28 t/s, tg_3s = 67.61 t/s 10.52.323.841 I slot print_timing: id 0 | task 38372 | n_gen = 405, tg = 67.28 t/s, tg_3s = 67.29 t/s 10.54.825.686 I slot print_timing: id 0 | task 38372 | prompt eval time = 357.33 ms / 174 tokens ( 2.05 ms per token, 486.94 tokens per second) 10.54.825.689 I slot print_timing: id 0 | task 38372 | eval time = 8506.52 ms / 573 tokens ( 14.87 ms per token, 67.24 tokens per second) 10.54.825.689 I slot print_timing: id 0 | task 38372 | total time = 8863.85 ms / 747 tokens 10.54.825.690 I slot print_timing: id 0 | task 38372 | graphs reused = 38097 10.54.825.691 I slot print_timing: id 0 | task 38372 | graph reallocs = 0 / 0 (same size) / (changed size) 10.54.825.711 I slot release: id 0 | task 38372 | stop processing: n_tokens = 746, truncated = 0 10.54.829.180 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.129 (> 0.100 thold), f_keep = 0.028 10.54.830.965 I slot launch_slot_: id 0 | task 38947 | processing task, is_child = 0 10.58.184.895 I slot print_timing: id 0 | task 38947 | n_gen = 204, tg = 67.36 t/s, tg_3s = 67.70 t/s 10.59.120.332 I slot print_timing: id 0 | task 38947 | prompt eval time = 340.45 ms / 163 tokens ( 2.09 ms per token, 478.77 tokens per second) 10.59.120.338 I slot print_timing: id 0 | task 38947 | eval time = 3948.91 ms / 267 tokens ( 14.85 ms per token, 67.36 tokens per second) 10.59.120.339 I slot print_timing: id 0 | task 38947 | total time = 4289.36 ms / 430 tokens 10.59.120.339 I slot print_timing: id 0 | task 38947 | graphs reused = 38361 10.59.120.340 I slot print_timing: id 0 | task 38947 | graph reallocs = 0 / 0 (same size) / (changed size) 10.59.120.360 I slot release: id 0 | task 38947 | stop processing: n_tokens = 429, truncated = 0 10.59.123.890 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.208 (> 0.100 thold), f_keep = 0.049 10.59.125.260 I slot launch_slot_: id 0 | task 39216 | processing task, is_child = 0 11.02.422.842 I slot print_timing: id 0 | task 39216 | n_gen = 203, tg = 67.26 t/s, tg_3s = 67.60 t/s 11.05.424.218 I slot print_timing: id 0 | task 39216 | n_gen = 405, tg = 67.28 t/s, tg_3s = 67.30 t/s 11.08.433.752 I slot print_timing: id 0 | task 39216 | n_gen = 608, tg = 67.34 t/s, tg_3s = 67.45 t/s 11.09.015.764 I slot print_timing: id 0 | task 39216 | prompt eval time = 294.41 ms / 101 tokens ( 2.91 ms per token, 343.06 tokens per second) 11.09.015.770 I slot print_timing: id 0 | task 39216 | eval time = 9596.09 ms / 647 tokens ( 14.85 ms per token, 67.32 tokens per second) 11.09.015.771 I slot print_timing: id 0 | task 39216 | total time = 9890.50 ms / 748 tokens 11.09.015.771 I slot print_timing: id 0 | task 39216 | graphs reused = 39004 11.09.015.772 I slot print_timing: id 0 | task 39216 | graph reallocs = 0 / 0 (same size) / (changed size) 11.09.015.791 I slot release: id 0 | task 39216 | stop processing: n_tokens = 747, truncated = 0 11.09.019.280 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.126 (> 0.100 thold), f_keep = 0.028 11.09.021.046 I slot launch_slot_: id 0 | task 39865 | processing task, is_child = 0 11.12.387.094 I slot print_timing: id 0 | task 39865 | n_gen = 204, tg = 67.40 t/s, tg_3s = 67.73 t/s 11.13.679.950 I slot print_timing: id 0 | task 39865 | prompt eval time = 354.13 ms / 167 tokens ( 2.12 ms per token, 471.58 tokens per second) 11.13.679.956 I slot print_timing: id 0 | task 39865 | eval time = 4304.77 ms / 291 tokens ( 14.84 ms per token, 67.37 tokens per second) 11.13.679.958 I slot print_timing: id 0 | task 39865 | total time = 4658.90 ms / 458 tokens 11.13.679.958 I slot print_timing: id 0 | task 39865 | graphs reused = 39292 11.13.679.959 I slot print_timing: id 0 | task 39865 | graph reallocs = 0 / 0 (same size) / (changed size) 11.13.679.980 I slot release: id 0 | task 39865 | stop processing: n_tokens = 457, truncated = 0 11.13.683.334 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.123 (> 0.100 thold), f_keep = 0.046 11.13.684.550 I slot launch_slot_: id 0 | task 40158 | processing task, is_child = 0 11.17.052.858 I slot print_timing: id 0 | task 40158 | n_gen = 204, tg = 67.43 t/s, tg_3s = 67.76 t/s 11.19.371.344 I slot print_timing: id 0 | task 40158 | prompt eval time = 357.60 ms / 171 tokens ( 2.09 ms per token, 478.19 tokens per second) 11.19.371.350 I slot print_timing: id 0 | task 40158 | eval time = 5329.18 ms / 360 tokens ( 14.84 ms per token, 67.36 tokens per second) 11.19.371.351 I slot print_timing: id 0 | task 40158 | total time = 5686.78 ms / 531 tokens 11.19.371.351 I slot print_timing: id 0 | task 40158 | graphs reused = 39648 11.19.371.352 I slot print_timing: id 0 | task 40158 | graph reallocs = 0 / 0 (same size) / (changed size) 11.19.371.372 I slot release: id 0 | task 40158 | stop processing: n_tokens = 530, truncated = 0 11.19.374.697 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.117 (> 0.100 thold), f_keep = 0.040 11.19.375.989 I slot launch_slot_: id 0 | task 40520 | processing task, is_child = 0 11.22.747.214 I slot print_timing: id 0 | task 40520 | n_gen = 204, tg = 67.37 t/s, tg_3s = 67.71 t/s 11.25.560.775 I slot print_timing: id 0 | task 40520 | prompt eval time = 358.23 ms / 179 tokens ( 2.00 ms per token, 499.69 tokens per second) 11.25.560.781 I slot print_timing: id 0 | task 40520 | eval time = 5826.55 ms / 393 tokens ( 14.86 ms per token, 67.28 tokens per second) 11.25.560.782 I slot print_timing: id 0 | task 40520 | total time = 6184.78 ms / 572 tokens 11.25.560.783 I slot print_timing: id 0 | task 40520 | graphs reused = 40037 11.25.560.783 I slot print_timing: id 0 | task 40520 | graph reallocs = 0 / 0 (same size) / (changed size) 11.25.560.804 I slot release: id 0 | task 40520 | stop processing: n_tokens = 571, truncated = 0 11.25.564.139 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.127 (> 0.100 thold), f_keep = 0.037 11.25.565.504 I slot launch_slot_: id 0 | task 40915 | processing task, is_child = 0 11.28.160.233 I slot print_timing: id 0 | task 40915 | prompt eval time = 350.86 ms / 165 tokens ( 2.13 ms per token, 470.28 tokens per second) 11.28.160.235 I slot print_timing: id 0 | task 40915 | eval time = 2243.86 ms / 152 tokens ( 14.86 ms per token, 67.29 tokens per second) 11.28.160.237 I slot print_timing: id 0 | task 40915 | total time = 2594.72 ms / 317 tokens 11.28.160.237 I slot print_timing: id 0 | task 40915 | graphs reused = 40186 11.28.160.238 I slot print_timing: id 0 | task 40915 | graph reallocs = 0 / 0 (same size) / (changed size) 11.28.160.258 I slot release: id 0 | task 40915 | stop processing: n_tokens = 316, truncated = 0 11.28.163.533 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.132 (> 0.100 thold), f_keep = 0.066 11.28.164.018 I slot launch_slot_: id 0 | task 41069 | processing task, is_child = 0 11.31.516.719 I slot print_timing: id 0 | task 41069 | n_gen = 204, tg = 67.38 t/s, tg_3s = 67.71 t/s 11.32.065.729 I slot print_timing: id 0 | task 41069 | prompt eval time = 339.86 ms / 159 tokens ( 2.14 ms per token, 467.84 tokens per second) 11.32.065.735 I slot print_timing: id 0 | task 41069 | eval time = 3561.85 ms / 241 tokens ( 14.84 ms per token, 67.38 tokens per second) 11.32.065.737 I slot print_timing: id 0 | task 41069 | total time = 3901.71 ms / 400 tokens 11.32.065.737 I slot print_timing: id 0 | task 41069 | graphs reused = 40424 11.32.065.738 I slot print_timing: id 0 | task 41069 | graph reallocs = 0 / 0 (same size) / (changed size) 11.32.065.759 I slot release: id 0 | task 41069 | stop processing: n_tokens = 399, truncated = 0 11.32.068.973 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.118 (> 0.100 thold), f_keep = 0.053 11.32.070.006 I slot launch_slot_: id 0 | task 41312 | processing task, is_child = 0 11.35.031.154 I slot print_timing: id 0 | task 41312 | prompt eval time = 361.97 ms / 178 tokens ( 2.03 ms per token, 491.75 tokens per second) 11.35.031.157 I slot print_timing: id 0 | task 41312 | eval time = 2599.17 ms / 176 tokens ( 14.85 ms per token, 67.33 tokens per second) 11.35.031.158 I slot print_timing: id 0 | task 41312 | total time = 2961.14 ms / 354 tokens 11.35.031.158 I slot print_timing: id 0 | task 41312 | graphs reused = 40597 11.35.031.159 I slot print_timing: id 0 | task 41312 | graph reallocs = 0 / 0 (same size) / (changed size) 11.35.031.181 I slot release: id 0 | task 41312 | stop processing: n_tokens = 353, truncated = 0 11.35.034.505 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.112 (> 0.100 thold), f_keep = 0.059 11.35.035.434 I slot launch_slot_: id 0 | task 41490 | processing task, is_child = 0 11.38.407.978 I slot print_timing: id 0 | task 41490 | n_gen = 203, tg = 67.24 t/s, tg_3s = 67.57 t/s 11.41.420.111 I slot print_timing: id 0 | task 41490 | n_gen = 406, tg = 67.32 t/s, tg_3s = 67.39 t/s 11.44.432.912 I slot print_timing: id 0 | task 41490 | n_gen = 609, tg = 67.34 t/s, tg_3s = 67.38 t/s 11.47.436.813 I slot print_timing: id 0 | task 41490 | n_gen = 811, tg = 67.31 t/s, tg_3s = 67.25 t/s 11.50.446.003 I slot print_timing: id 0 | task 41490 | n_gen = 1012, tg = 67.21 t/s, tg_3s = 66.80 t/s 11.50.625.984 I slot print_timing: id 0 | task 41490 | prompt eval time = 368.21 ms / 188 tokens ( 1.96 ms per token, 510.58 tokens per second) 11.50.625.990 I slot print_timing: id 0 | task 41490 | eval time = 15222.33 ms / 1024 tokens ( 14.88 ms per token, 67.20 tokens per second) 11.50.625.991 I slot print_timing: id 0 | task 41490 | total time = 15590.54 ms / 1212 tokens 11.50.625.991 I slot print_timing: id 0 | task 41490 | graphs reused = 41615 11.50.625.992 I slot print_timing: id 0 | task 41490 | graph reallocs = 0 / 0 (same size) / (changed size) 11.50.626.014 I slot release: id 0 | task 41490 | stop processing: n_tokens = 1211, truncated = 0 11.50.629.319 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.128 (> 0.100 thold), f_keep = 0.017 11.50.631.914 I slot launch_slot_: id 0 | task 42516 | processing task, is_child = 0 11.53.987.266 I slot print_timing: id 0 | task 42516 | n_gen = 204, tg = 67.38 t/s, tg_3s = 67.71 t/s 11.56.991.571 I slot print_timing: id 0 | task 42516 | n_gen = 406, tg = 67.31 t/s, tg_3s = 67.24 t/s 11.57.869.464 I slot print_timing: id 0 | task 42516 | prompt eval time = 342.44 ms / 164 tokens ( 2.09 ms per token, 478.91 tokens per second) 11.57.869.467 I slot print_timing: id 0 | task 42516 | eval time = 6895.10 ms / 465 tokens ( 14.86 ms per token, 67.29 tokens per second) 11.57.869.467 I slot print_timing: id 0 | task 42516 | total time = 7237.54 ms / 629 tokens 11.57.869.468 I slot print_timing: id 0 | task 42516 | graphs reused = 42076 11.57.869.469 I slot print_timing: id 0 | task 42516 | graph reallocs = 0 / 0 (same size) / (changed size) 11.57.869.490 I slot release: id 0 | task 42516 | stop processing: n_tokens = 628, truncated = 0 11.57.873.548 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.116 (> 0.100 thold), f_keep = 0.033 11.57.875.570 I slot launch_slot_: id 0 | task 42983 | processing task, is_child = 0 12.01.243.849 I slot print_timing: id 0 | task 42983 | n_gen = 203, tg = 67.21 t/s, tg_3s = 67.54 t/s 12.04.249.571 I slot print_timing: id 0 | task 42983 | n_gen = 405, tg = 67.21 t/s, tg_3s = 67.21 t/s 12.07.082.213 I slot print_timing: id 0 | task 42983 | prompt eval time = 362.69 ms / 181 tokens ( 2.00 ms per token, 499.04 tokens per second) 12.07.082.219 I slot print_timing: id 0 | task 42983 | eval time = 8843.94 ms / 595 tokens ( 14.89 ms per token, 67.16 tokens per second) 12.07.082.220 I slot print_timing: id 0 | task 42983 | total time = 9206.63 ms / 776 tokens 12.07.082.220 I slot print_timing: id 0 | task 42983 | graphs reused = 42666 12.07.082.221 I slot print_timing: id 0 | task 42983 | graph reallocs = 0 / 0 (same size) / (changed size) 12.07.082.243 I slot release: id 0 | task 42983 | stop processing: n_tokens = 775, truncated = 0 12.07.085.676 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.136 (> 0.100 thold), f_keep = 0.027 12.07.087.434 I slot launch_slot_: id 0 | task 43580 | processing task, is_child = 0 12.10.434.588 I slot print_timing: id 0 | task 43580 | n_gen = 204, tg = 67.39 t/s, tg_3s = 67.72 t/s 12.10.820.130 I slot print_timing: id 0 | task 43580 | prompt eval time = 334.94 ms / 154 tokens ( 2.17 ms per token, 459.79 tokens per second) 12.10.820.136 I slot print_timing: id 0 | task 43580 | eval time = 3397.75 ms / 230 tokens ( 14.84 ms per token, 67.40 tokens per second) 12.10.820.137 I slot print_timing: id 0 | task 43580 | total time = 3732.68 ms / 384 tokens 12.10.820.138 I slot print_timing: id 0 | task 43580 | graphs reused = 42893 12.10.820.139 I slot print_timing: id 0 | task 43580 | graph reallocs = 0 / 0 (same size) / (changed size) 12.10.820.158 I slot release: id 0 | task 43580 | stop processing: n_tokens = 383, truncated = 0 12.10.823.469 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.055 12.10.824.463 I slot launch_slot_: id 0 | task 43812 | processing task, is_child = 0 12.12.478.851 I slot print_timing: id 0 | task 43812 | prompt eval time = 321.04 ms / 135 tokens ( 2.38 ms per token, 420.50 tokens per second) 12.12.478.854 I slot print_timing: id 0 | task 43812 | eval time = 1333.34 ms / 91 tokens ( 14.81 ms per token, 67.50 tokens per second) 12.12.478.855 I slot print_timing: id 0 | task 43812 | total time = 1654.38 ms / 226 tokens 12.12.478.855 I slot print_timing: id 0 | task 43812 | graphs reused = 42982 12.12.478.856 I slot print_timing: id 0 | task 43812 | graph reallocs = 0 / 0 (same size) / (changed size) 12.12.478.874 I slot release: id 0 | task 43812 | stop processing: n_tokens = 225, truncated = 0 12.12.482.204 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.117 (> 0.100 thold), f_keep = 0.093 12.12.482.873 I slot launch_slot_: id 0 | task 43905 | processing task, is_child = 0 12.15.843.039 I slot print_timing: id 0 | task 43905 | n_gen = 203, tg = 67.31 t/s, tg_3s = 67.64 t/s 12.18.295.481 I slot print_timing: id 0 | task 43905 | prompt eval time = 359.15 ms / 179 tokens ( 2.01 ms per token, 498.40 tokens per second) 12.18.295.487 I slot print_timing: id 0 | task 43905 | eval time = 5453.45 ms / 368 tokens ( 14.86 ms per token, 67.30 tokens per second) 12.18.295.488 I slot print_timing: id 0 | task 43905 | total time = 5812.60 ms / 547 tokens 12.18.295.489 I slot print_timing: id 0 | task 43905 | graphs reused = 43346 12.18.295.489 I slot print_timing: id 0 | task 43905 | graph reallocs = 0 / 0 (same size) / (changed size) 12.18.295.512 I slot release: id 0 | task 43905 | stop processing: n_tokens = 546, truncated = 0 12.18.298.826 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.119 (> 0.100 thold), f_keep = 0.046 12.18.300.156 I slot launch_slot_: id 0 | task 44275 | processing task, is_child = 0 12.21.689.566 I slot print_timing: id 0 | task 44275 | n_gen = 203, tg = 67.31 t/s, tg_3s = 67.64 t/s 12.24.098.185 I slot print_timing: id 0 | task 44275 | prompt eval time = 388.16 ms / 210 tokens ( 1.85 ms per token, 541.01 tokens per second) 12.24.098.189 I slot print_timing: id 0 | task 44275 | eval time = 5409.86 ms / 365 tokens ( 14.86 ms per token, 67.28 tokens per second) 12.24.098.189 I slot print_timing: id 0 | task 44275 | total time = 5798.02 ms / 575 tokens 12.24.098.190 I slot print_timing: id 0 | task 44275 | graphs reused = 43707 12.24.098.191 I slot print_timing: id 0 | task 44275 | graph reallocs = 0 / 0 (same size) / (changed size) 12.24.098.214 I slot release: id 0 | task 44275 | stop processing: n_tokens = 574, truncated = 0 12.24.101.364 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.165 (> 0.100 thold), f_keep = 0.037 12.24.102.736 I slot launch_slot_: id 0 | task 44642 | processing task, is_child = 0 12.27.074.091 I slot print_timing: id 0 | task 44642 | prompt eval time = 310.79 ms / 127 tokens ( 2.45 ms per token, 408.64 tokens per second) 12.27.074.094 I slot print_timing: id 0 | task 44642 | eval time = 2660.56 ms / 180 tokens ( 14.86 ms per token, 67.28 tokens per second) 12.27.074.095 I slot print_timing: id 0 | task 44642 | total time = 2971.34 ms / 307 tokens 12.27.074.096 I slot print_timing: id 0 | task 44642 | graphs reused = 43884 12.27.074.096 I slot print_timing: id 0 | task 44642 | graph reallocs = 0 / 0 (same size) / (changed size) 12.27.074.114 I slot release: id 0 | task 44642 | stop processing: n_tokens = 306, truncated = 0 12.27.077.372 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.152 (> 0.100 thold), f_keep = 0.069 12.27.078.213 I slot launch_slot_: id 0 | task 44824 | processing task, is_child = 0 12.30.346.997 I slot print_timing: id 0 | task 44824 | prompt eval time = 327.22 ms / 138 tokens ( 2.37 ms per token, 421.73 tokens per second) 12.30.347.003 I slot print_timing: id 0 | task 44824 | eval time = 2941.55 ms / 199 tokens ( 14.86 ms per token, 67.31 tokens per second) 12.30.347.003 I slot print_timing: id 0 | task 44824 | total time = 3268.78 ms / 337 tokens 12.30.347.004 I slot print_timing: id 0 | task 44824 | graphs reused = 44080 12.30.347.004 I slot print_timing: id 0 | task 44824 | graph reallocs = 0 / 0 (same size) / (changed size) 12.30.347.023 I slot release: id 0 | task 44824 | stop processing: n_tokens = 336, truncated = 0 12.30.350.166 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.151 (> 0.100 thold), f_keep = 0.062 12.30.351.102 I slot launch_slot_: id 0 | task 45025 | processing task, is_child = 0 12.33.690.669 I slot print_timing: id 0 | task 45025 | n_gen = 204, tg = 67.34 t/s, tg_3s = 67.67 t/s 12.36.697.409 I slot print_timing: id 0 | task 45025 | n_gen = 406, tg = 67.26 t/s, tg_3s = 67.18 t/s 12.38.097.103 I slot print_timing: id 0 | task 45025 | prompt eval time = 324.98 ms / 139 tokens ( 2.34 ms per token, 427.72 tokens per second) 12.38.097.109 I slot print_timing: id 0 | task 45025 | eval time = 7421.01 ms / 500 tokens ( 14.87 ms per token, 67.24 tokens per second) 12.38.097.110 I slot print_timing: id 0 | task 45025 | total time = 7745.99 ms / 639 tokens 12.38.097.110 I slot print_timing: id 0 | task 45025 | graphs reused = 44576 12.38.097.111 I slot print_timing: id 0 | task 45025 | graph reallocs = 0 / 0 (same size) / (changed size) 12.38.097.133 I slot release: id 0 | task 45025 | stop processing: n_tokens = 638, truncated = 0 12.38.100.553 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.134 (> 0.100 thold), f_keep = 0.033 12.38.102.129 I slot launch_slot_: id 0 | task 45527 | processing task, is_child = 0 12.41.442.181 I slot print_timing: id 0 | task 45527 | n_gen = 203, tg = 67.25 t/s, tg_3s = 67.59 t/s 12.42.392.605 I slot print_timing: id 0 | task 45527 | prompt eval time = 336.51 ms / 157 tokens ( 2.14 ms per token, 466.55 tokens per second) 12.42.392.608 I slot print_timing: id 0 | task 45527 | eval time = 3953.95 ms / 267 tokens ( 14.86 ms per token, 67.27 tokens per second) 12.42.392.609 I slot print_timing: id 0 | task 45527 | total time = 4290.46 ms / 424 tokens 12.42.392.610 I slot print_timing: id 0 | task 45527 | graphs reused = 44840 12.42.392.610 I slot print_timing: id 0 | task 45527 | graph reallocs = 0 / 0 (same size) / (changed size) 12.42.392.631 I slot release: id 0 | task 45527 | stop processing: n_tokens = 423, truncated = 0 12.42.396.075 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 12.42.397.155 I slot launch_slot_: id 0 | task 45796 | processing task, is_child = 0 12.45.745.713 I slot print_timing: id 0 | task 45796 | n_gen = 203, tg = 67.25 t/s, tg_3s = 67.58 t/s 12.47.054.211 I slot print_timing: id 0 | task 45796 | prompt eval time = 344.84 ms / 163 tokens ( 2.12 ms per token, 472.68 tokens per second) 12.47.054.214 I slot print_timing: id 0 | task 45796 | eval time = 4312.20 ms / 291 tokens ( 14.87 ms per token, 67.25 tokens per second) 12.47.054.215 I slot print_timing: id 0 | task 45796 | total time = 4657.05 ms / 454 tokens 12.47.054.215 I slot print_timing: id 0 | task 45796 | graphs reused = 45128 12.47.054.216 I slot print_timing: id 0 | task 45796 | graph reallocs = 0 / 0 (same size) / (changed size) 12.47.054.237 I slot release: id 0 | task 45796 | stop processing: n_tokens = 453, truncated = 0 12.47.057.956 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.134 (> 0.100 thold), f_keep = 0.046 12.47.059.211 I slot launch_slot_: id 0 | task 46089 | processing task, is_child = 0 12.50.412.327 I slot print_timing: id 0 | task 46089 | n_gen = 204, tg = 67.36 t/s, tg_3s = 67.69 t/s 12.50.753.959 I slot print_timing: id 0 | task 46089 | prompt eval time = 339.33 ms / 157 tokens ( 2.16 ms per token, 462.67 tokens per second) 12.50.753.965 I slot print_timing: id 0 | task 46089 | eval time = 3355.40 ms / 227 tokens ( 14.85 ms per token, 67.35 tokens per second) 12.50.753.966 I slot print_timing: id 0 | task 46089 | total time = 3694.73 ms / 384 tokens 12.50.753.966 I slot print_timing: id 0 | task 46089 | graphs reused = 45352 12.50.753.967 I slot print_timing: id 0 | task 46089 | graph reallocs = 0 / 0 (same size) / (changed size) 12.50.753.987 I slot release: id 0 | task 46089 | stop processing: n_tokens = 383, truncated = 0 12.50.757.195 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.134 (> 0.100 thold), f_keep = 0.055 12.50.758.146 I slot launch_slot_: id 0 | task 46318 | processing task, is_child = 0 12.54.095.690 I slot print_timing: id 0 | task 46318 | n_gen = 203, tg = 67.31 t/s, tg_3s = 67.64 t/s 12.57.102.462 I slot print_timing: id 0 | task 46318 | n_gen = 405, tg = 67.25 t/s, tg_3s = 67.18 t/s 13.00.110.643 I slot print_timing: id 0 | task 46318 | n_gen = 607, tg = 67.21 t/s, tg_3s = 67.15 t/s 13.03.117.272 I slot print_timing: id 0 | task 46318 | n_gen = 809, tg = 67.21 t/s, tg_3s = 67.18 t/s 13.03.445.373 I slot print_timing: id 0 | task 46318 | prompt eval time = 336.47 ms / 157 tokens ( 2.14 ms per token, 466.61 tokens per second) 13.03.445.376 I slot print_timing: id 0 | task 46318 | eval time = 12350.75 ms / 831 tokens ( 14.88 ms per token, 67.20 tokens per second) 13.03.445.377 I slot print_timing: id 0 | task 46318 | total time = 12687.22 ms / 988 tokens 13.03.445.378 I slot print_timing: id 0 | task 46318 | graphs reused = 46178 13.03.445.378 I slot print_timing: id 0 | task 46318 | graph reallocs = 0 / 0 (same size) / (changed size) 13.03.445.403 I slot release: id 0 | task 46318 | stop processing: n_tokens = 987, truncated = 0 13.03.449.197 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.134 (> 0.100 thold), f_keep = 0.021 13.03.451.610 I slot launch_slot_: id 0 | task 47151 | processing task, is_child = 0 13.06.803.717 I slot print_timing: id 0 | task 47151 | n_gen = 204, tg = 67.36 t/s, tg_3s = 67.69 t/s 13.07.872.671 I slot print_timing: id 0 | task 47151 | prompt eval time = 338.29 ms / 157 tokens ( 2.15 ms per token, 464.10 tokens per second) 13.07.872.684 I slot print_timing: id 0 | task 47151 | eval time = 4082.76 ms / 276 tokens ( 14.85 ms per token, 67.36 tokens per second) 13.07.872.684 I slot print_timing: id 0 | task 47151 | total time = 4421.05 ms / 433 tokens 13.07.872.685 I slot print_timing: id 0 | task 47151 | graphs reused = 46451 13.07.872.685 I slot print_timing: id 0 | task 47151 | graph reallocs = 0 / 0 (same size) / (changed size) 13.07.872.710 I slot release: id 0 | task 47151 | stop processing: n_tokens = 432, truncated = 0 13.07.875.954 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.122 (> 0.100 thold), f_keep = 0.049 13.07.876.970 I slot launch_slot_: id 0 | task 47429 | processing task, is_child = 0 13.09.346.749 I slot print_timing: id 0 | task 47429 | prompt eval time = 357.22 ms / 172 tokens ( 2.08 ms per token, 481.49 tokens per second) 13.09.346.755 I slot print_timing: id 0 | task 47429 | eval time = 1112.55 ms / 76 tokens ( 14.83 ms per token, 67.41 tokens per second) 13.09.346.756 I slot print_timing: id 0 | task 47429 | total time = 1469.77 ms / 248 tokens 13.09.346.756 I slot print_timing: id 0 | task 47429 | graphs reused = 46525 13.09.346.757 I slot print_timing: id 0 | task 47429 | graph reallocs = 0 / 0 (same size) / (changed size) 13.09.346.777 I slot release: id 0 | task 47429 | stop processing: n_tokens = 247, truncated = 0 13.09.349.868 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 13.09.350.576 I slot launch_slot_: id 0 | task 47507 | processing task, is_child = 0 13.12.572.264 I slot print_timing: id 0 | task 47507 | prompt eval time = 338.45 ms / 163 tokens ( 2.08 ms per token, 481.60 tokens per second) 13.12.572.267 I slot print_timing: id 0 | task 47507 | eval time = 2883.23 ms / 195 tokens ( 14.86 ms per token, 67.29 tokens per second) 13.12.572.267 I slot print_timing: id 0 | task 47507 | total time = 3221.68 ms / 358 tokens 13.12.572.268 I slot print_timing: id 0 | task 47507 | graphs reused = 46717 13.12.572.269 I slot print_timing: id 0 | task 47507 | graph reallocs = 0 / 0 (same size) / (changed size) 13.12.572.290 I slot release: id 0 | task 47507 | stop processing: n_tokens = 357, truncated = 0 13.12.575.585 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 13.12.576.530 I slot launch_slot_: id 0 | task 47704 | processing task, is_child = 0 13.15.942.623 I slot print_timing: id 0 | task 47704 | n_gen = 204, tg = 67.38 t/s, tg_3s = 67.71 t/s 13.16.774.794 I slot print_timing: id 0 | task 47704 | prompt eval time = 353.18 ms / 165 tokens ( 2.14 ms per token, 467.18 tokens per second) 13.16.774.796 I slot print_timing: id 0 | task 47704 | eval time = 3845.08 ms / 260 tokens ( 14.85 ms per token, 67.36 tokens per second) 13.16.774.797 I slot print_timing: id 0 | task 47704 | total time = 4198.26 ms / 425 tokens 13.16.774.797 I slot print_timing: id 0 | task 47704 | graphs reused = 46974 13.16.774.798 I slot print_timing: id 0 | task 47704 | graph reallocs = 0 / 0 (same size) / (changed size) 13.16.774.821 I slot release: id 0 | task 47704 | stop processing: n_tokens = 424, truncated = 0 13.16.778.180 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.121 (> 0.100 thold), f_keep = 0.050 13.16.779.288 I slot launch_slot_: id 0 | task 47966 | processing task, is_child = 0 13.19.306.184 I slot print_timing: id 0 | task 47966 | prompt eval time = 358.80 ms / 173 tokens ( 2.07 ms per token, 482.16 tokens per second) 13.19.306.190 I slot print_timing: id 0 | task 47966 | eval time = 2168.09 ms / 147 tokens ( 14.85 ms per token, 67.34 tokens per second) 13.19.306.192 I slot print_timing: id 0 | task 47966 | total time = 2526.88 ms / 320 tokens 13.19.306.192 I slot print_timing: id 0 | task 47966 | graphs reused = 47118 13.19.306.193 I slot print_timing: id 0 | task 47966 | graph reallocs = 0 / 0 (same size) / (changed size) 13.19.306.213 I slot release: id 0 | task 47966 | stop processing: n_tokens = 319, truncated = 0 13.19.309.442 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.111 (> 0.100 thold), f_keep = 0.066 13.19.310.308 I slot launch_slot_: id 0 | task 48115 | processing task, is_child = 0 13.22.133.695 I slot print_timing: id 0 | task 48115 | prompt eval time = 370.31 ms / 190 tokens ( 1.95 ms per token, 513.09 tokens per second) 13.22.133.698 I slot print_timing: id 0 | task 48115 | eval time = 2453.07 ms / 166 tokens ( 14.87 ms per token, 67.26 tokens per second) 13.22.133.699 I slot print_timing: id 0 | task 48115 | total time = 2823.38 ms / 356 tokens 13.22.133.699 I slot print_timing: id 0 | task 48115 | graphs reused = 47281 13.22.133.700 I slot print_timing: id 0 | task 48115 | graph reallocs = 0 / 0 (same size) / (changed size) 13.22.133.723 I slot release: id 0 | task 48115 | stop processing: n_tokens = 355, truncated = 0 13.22.137.130 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 13.22.138.101 I slot launch_slot_: id 0 | task 48283 | processing task, is_child = 0 13.25.509.795 I slot print_timing: id 0 | task 48283 | n_gen = 204, tg = 67.36 t/s, tg_3s = 67.69 t/s 13.27.860.075 I slot print_timing: id 0 | task 48283 | prompt eval time = 357.85 ms / 173 tokens ( 2.07 ms per token, 483.44 tokens per second) 13.27.860.080 I slot print_timing: id 0 | task 48283 | eval time = 5364.11 ms / 362 tokens ( 14.86 ms per token, 67.30 tokens per second) 13.27.860.081 I slot print_timing: id 0 | task 48283 | total time = 5721.96 ms / 535 tokens 13.27.860.081 I slot print_timing: id 0 | task 48283 | graphs reused = 47639 13.27.860.082 I slot print_timing: id 0 | task 48283 | graph reallocs = 0 / 0 (same size) / (changed size) 13.27.860.104 I slot release: id 0 | task 48283 | stop processing: n_tokens = 534, truncated = 0 13.27.863.544 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.111 (> 0.100 thold), f_keep = 0.039 13.27.864.788 I slot launch_slot_: id 0 | task 48647 | processing task, is_child = 0 13.31.231.169 I slot print_timing: id 0 | task 48647 | n_gen = 203, tg = 67.29 t/s, tg_3s = 67.62 t/s 13.34.119.123 I slot print_timing: id 0 | task 48647 | prompt eval time = 364.48 ms / 190 tokens ( 1.92 ms per token, 521.29 tokens per second) 13.34.119.125 I slot print_timing: id 0 | task 48647 | eval time = 5889.84 ms / 397 tokens ( 14.87 ms per token, 67.23 tokens per second) 13.34.119.126 I slot print_timing: id 0 | task 48647 | total time = 6254.32 ms / 587 tokens 13.34.119.127 I slot print_timing: id 0 | task 48647 | graphs reused = 48032 13.34.119.127 I slot print_timing: id 0 | task 48647 | graph reallocs = 0 / 0 (same size) / (changed size) 13.34.119.152 I slot release: id 0 | task 48647 | stop processing: n_tokens = 586, truncated = 0 13.34.122.453 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.126 (> 0.100 thold), f_keep = 0.039 13.34.123.829 I slot launch_slot_: id 0 | task 49046 | processing task, is_child = 0 13.37.487.376 I slot print_timing: id 0 | task 49046 | n_gen = 203, tg = 67.33 t/s, tg_3s = 67.66 t/s 13.40.494.633 I slot print_timing: id 0 | task 49046 | n_gen = 405, tg = 67.25 t/s, tg_3s = 67.17 t/s 13.41.000.033 I slot print_timing: id 0 | task 49046 | prompt eval time = 363.24 ms / 183 tokens ( 1.98 ms per token, 503.81 tokens per second) 13.41.000.035 I slot print_timing: id 0 | task 49046 | eval time = 6512.96 ms / 439 tokens ( 14.87 ms per token, 67.25 tokens per second) 13.41.000.036 I slot print_timing: id 0 | task 49046 | total time = 6876.19 ms / 622 tokens 13.41.000.037 I slot print_timing: id 0 | task 49046 | graphs reused = 48467 13.41.000.037 I slot print_timing: id 0 | task 49046 | graph reallocs = 0 / 0 (same size) / (changed size) 13.41.000.060 I slot release: id 0 | task 49046 | stop processing: n_tokens = 621, truncated = 0 13.41.003.588 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 621, t_last = 335365531075 13.41.005.028 I slot launch_slot_: id 0 | task 49487 | processing task, is_child = 0 13.44.409.859 I slot print_timing: id 0 | task 49487 | n_gen = 203, tg = 67.13 t/s, tg_3s = 67.46 t/s 13.44.915.163 I slot print_timing: id 0 | task 49487 | prompt eval time = 395.71 ms / 222 tokens ( 1.78 ms per token, 561.02 tokens per second) 13.44.915.168 I slot print_timing: id 0 | task 49487 | eval time = 3514.42 ms / 237 tokens ( 14.89 ms per token, 67.15 tokens per second) 13.44.915.168 I slot print_timing: id 0 | task 49487 | total time = 3910.12 ms / 459 tokens 13.44.915.169 I slot print_timing: id 0 | task 49487 | graphs reused = 48701 13.44.915.170 I slot print_timing: id 0 | task 49487 | graph reallocs = 0 / 0 (same size) / (changed size) 13.44.915.194 I slot release: id 0 | task 49487 | stop processing: n_tokens = 458, truncated = 0 13.44.918.497 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.129 (> 0.100 thold), f_keep = 0.046 13.44.919.698 I slot launch_slot_: id 0 | task 49726 | processing task, is_child = 0 13.48.268.406 I slot print_timing: id 0 | task 49726 | n_gen = 203, tg = 67.13 t/s, tg_3s = 67.46 t/s 13.50.315.544 I slot print_timing: id 0 | task 49726 | prompt eval time = 339.70 ms / 163 tokens ( 2.08 ms per token, 479.84 tokens per second) 13.50.315.549 I slot print_timing: id 0 | task 49726 | eval time = 5056.14 ms / 341 tokens ( 14.87 ms per token, 67.25 tokens per second) 13.50.315.550 I slot print_timing: id 0 | task 49726 | total time = 5395.84 ms / 504 tokens 13.50.315.551 I slot print_timing: id 0 | task 49726 | graphs reused = 49039 13.50.315.552 I slot print_timing: id 0 | task 49726 | graph reallocs = 0 / 0 (same size) / (changed size) 13.50.315.573 I slot release: id 0 | task 49726 | stop processing: n_tokens = 503, truncated = 0 13.50.439.732 I srv operator(): operator(): cleaning up before exit...