$ /Users/minipro/quantdiff/llama.cpp/llama-b11770/llama-server -m /Users/minipro/quantdiff/models/campaign/d54834c785c7/LFM2.5-24B-A2B-UD-Q3_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 0.00.042.227 I srv llama_server: initializing ... 0.00.042.233 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.042.319 I srv init_listene: The UI is disabled 0.00.042.320 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.042.354 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) 0.00.044.019 I srv load_model: loading model '/Users/minipro/quantdiff/models/campaign/d54834c785c7/LFM2.5-24B-A2B-UD-Q3_K_XL.gguf' 0.00.865.545 I cmn init: llama threadpool init, n_threads = 8 0.00.939.517 I srv load_model: initializing, n_slots = 1, n_ctx_slot = 4096, kv_unified = 'false' 0.00.942.672 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.00.942.689 I srv llama_server: model loaded 0.00.942.691 I srv llama_server: listening on http://127.0.0.1:8089 0.02.020.373 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.02.020.585 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.03.894.647 I slot print_timing: id 0 | task 0 | prompt eval time = 363.68 ms / 172 tokens ( 2.11 ms per token, 472.94 tokens per second) 0.03.894.654 I slot print_timing: id 0 | task 0 | eval time = 1510.37 ms / 103 tokens ( 14.81 ms per token, 67.53 tokens per second) 0.03.894.654 I slot print_timing: id 0 | task 0 | total time = 1874.05 ms / 275 tokens 0.03.894.655 I slot print_timing: id 0 | task 0 | graphs reused = 101 0.03.894.656 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.03.894.677 I slot release: id 0 | task 0 | stop processing: n_tokens = 274, truncated = 0 0.03.897.965 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 0.03.898.330 I slot launch_slot_: id 0 | task 105 | processing task, is_child = 0 0.05.149.236 I slot print_timing: id 0 | task 105 | prompt eval time = 295.01 ms / 123 tokens ( 2.40 ms per token, 416.94 tokens per second) 0.05.149.242 I slot print_timing: id 0 | task 105 | eval time = 955.89 ms / 65 tokens ( 14.94 ms per token, 66.95 tokens per second) 0.05.149.242 I slot print_timing: id 0 | task 105 | total time = 1250.90 ms / 188 tokens 0.05.149.243 I slot print_timing: id 0 | task 105 | graphs reused = 164 0.05.149.243 I slot print_timing: id 0 | task 105 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.149.260 I slot release: id 0 | task 105 | stop processing: n_tokens = 187, truncated = 0 0.05.152.625 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 0.05.152.935 I slot launch_slot_: id 0 | task 172 | processing task, is_child = 0 0.06.542.052 I slot print_timing: id 0 | task 172 | prompt eval time = 332.67 ms / 163 tokens ( 2.04 ms per token, 489.98 tokens per second) 0.06.542.058 I slot print_timing: id 0 | task 172 | eval time = 1056.44 ms / 72 tokens ( 14.88 ms per token, 67.21 tokens per second) 0.06.542.059 I slot print_timing: id 0 | task 172 | total time = 1389.11 ms / 235 tokens 0.06.542.059 I slot print_timing: id 0 | task 172 | graphs reused = 234 0.06.542.060 I slot print_timing: id 0 | task 172 | graph reallocs = 0 / 0 (same size) / (changed size) 0.06.542.081 I slot release: id 0 | task 172 | stop processing: n_tokens = 234, truncated = 0 0.06.545.342 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.103 (> 0.100 thold), f_keep = 0.090 0.06.545.960 I slot launch_slot_: id 0 | task 246 | processing task, is_child = 0 0.09.330.379 I slot print_timing: id 0 | task 246 | prompt eval time = 377.68 ms / 204 tokens ( 1.85 ms per token, 540.15 tokens per second) 0.09.330.385 I slot print_timing: id 0 | task 246 | eval time = 2406.73 ms / 163 tokens ( 14.86 ms per token, 67.31 tokens per second) 0.09.330.385 I slot print_timing: id 0 | task 246 | total time = 2784.41 ms / 367 tokens 0.09.330.386 I slot print_timing: id 0 | task 246 | graphs reused = 394 0.09.330.387 I slot print_timing: id 0 | task 246 | graph reallocs = 0 / 0 (same size) / (changed size) 0.09.330.409 I slot release: id 0 | task 246 | stop processing: n_tokens = 366, truncated = 0 0.09.333.725 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.187 (> 0.100 thold), f_keep = 0.098 0.09.334.581 I slot launch_slot_: id 0 | task 411 | processing task, is_child = 0 0.11.609.629 I slot print_timing: id 0 | task 411 | prompt eval time = 360.82 ms / 193 tokens ( 1.87 ms per token, 534.90 tokens per second) 0.11.609.633 I slot print_timing: id 0 | task 411 | eval time = 1914.22 ms / 130 tokens ( 14.84 ms per token, 67.39 tokens per second) 0.11.609.633 I slot print_timing: id 0 | task 411 | total time = 2275.04 ms / 323 tokens 0.11.609.634 I slot print_timing: id 0 | task 411 | graphs reused = 521 0.11.609.635 I slot print_timing: id 0 | task 411 | graph reallocs = 0 / 0 (same size) / (changed size) 0.11.609.656 I slot release: id 0 | task 411 | stop processing: n_tokens = 322, truncated = 0 0.11.612.893 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.121 (> 0.100 thold), f_keep = 0.065 0.11.613.787 I slot launch_slot_: id 0 | task 543 | processing task, is_child = 0 0.13.416.667 I slot print_timing: id 0 | task 543 | prompt eval time = 352.92 ms / 174 tokens ( 2.03 ms per token, 493.04 tokens per second) 0.13.416.673 I slot print_timing: id 0 | task 543 | eval time = 1449.95 ms / 98 tokens ( 14.95 ms per token, 66.90 tokens per second) 0.13.416.674 I slot print_timing: id 0 | task 543 | total time = 1802.86 ms / 272 tokens 0.13.416.675 I slot print_timing: id 0 | task 543 | graphs reused = 616 0.13.416.675 I slot print_timing: id 0 | task 543 | graph reallocs = 0 / 0 (same size) / (changed size) 0.13.416.695 I slot release: id 0 | task 543 | stop processing: n_tokens = 271, truncated = 0 0.13.420.225 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 271, t_last = 336941802409 0.13.420.999 I slot launch_slot_: id 0 | task 643 | processing task, is_child = 0 0.16.201.503 I slot print_timing: id 0 | task 643 | prompt eval time = 389.63 ms / 224 tokens ( 1.74 ms per token, 574.90 tokens per second) 0.16.201.509 I slot print_timing: id 0 | task 643 | eval time = 2390.86 ms / 162 tokens ( 14.85 ms per token, 67.34 tokens per second) 0.16.201.510 I slot print_timing: id 0 | task 643 | total time = 2780.50 ms / 386 tokens 0.16.201.510 I slot print_timing: id 0 | task 643 | graphs reused = 775 0.16.201.511 I slot print_timing: id 0 | task 643 | graph reallocs = 0 / 0 (same size) / (changed size) 0.16.201.534 I slot release: id 0 | task 643 | stop processing: n_tokens = 385, truncated = 0 0.16.204.940 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 385, t_last = 336944587248 0.16.205.858 I slot launch_slot_: id 0 | task 807 | processing task, is_child = 0 0.18.794.456 I slot print_timing: id 0 | task 807 | prompt eval time = 438.88 ms / 266 tokens ( 1.65 ms per token, 606.08 tokens per second) 0.18.794.462 I slot print_timing: id 0 | task 807 | eval time = 2149.71 ms / 146 tokens ( 14.83 ms per token, 67.45 tokens per second) 0.18.794.462 I slot print_timing: id 0 | task 807 | total time = 2588.59 ms / 412 tokens 0.18.794.463 I slot print_timing: id 0 | task 807 | graphs reused = 919 0.18.794.463 I slot print_timing: id 0 | task 807 | graph reallocs = 0 / 0 (same size) / (changed size) 0.18.794.488 I slot release: id 0 | task 807 | stop processing: n_tokens = 411, truncated = 0 0.18.797.750 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.143 (> 0.100 thold), f_keep = 0.051 0.18.798.775 I slot launch_slot_: id 0 | task 955 | processing task, is_child = 0 0.20.290.094 I slot print_timing: id 0 | task 955 | prompt eval time = 324.78 ms / 147 tokens ( 2.21 ms per token, 452.62 tokens per second) 0.20.290.100 I slot print_timing: id 0 | task 955 | eval time = 1166.54 ms / 79 tokens ( 14.96 ms per token, 66.86 tokens per second) 0.20.290.101 I slot print_timing: id 0 | task 955 | total time = 1491.31 ms / 226 tokens 0.20.290.102 I slot print_timing: id 0 | task 955 | graphs reused = 996 0.20.290.102 I slot print_timing: id 0 | task 955 | graph reallocs = 0 / 0 (same size) / (changed size) 0.20.290.121 I slot release: id 0 | task 955 | stop processing: n_tokens = 225, truncated = 0 0.20.293.238 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 0.20.293.878 I slot launch_slot_: id 0 | task 1036 | processing task, is_child = 0 0.22.203.405 I slot print_timing: id 0 | task 1036 | prompt eval time = 343.02 ms / 166 tokens ( 2.07 ms per token, 483.94 tokens per second) 0.22.203.411 I slot print_timing: id 0 | task 1036 | eval time = 1566.50 ms / 106 tokens ( 14.92 ms per token, 67.03 tokens per second) 0.22.203.412 I slot print_timing: id 0 | task 1036 | total time = 1909.52 ms / 272 tokens 0.22.203.412 I slot print_timing: id 0 | task 1036 | graphs reused = 1099 0.22.203.413 I slot print_timing: id 0 | task 1036 | graph reallocs = 0 / 0 (same size) / (changed size) 0.22.203.434 I slot release: id 0 | task 1036 | stop processing: n_tokens = 271, truncated = 0 0.22.206.702 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.120 (> 0.100 thold), f_keep = 0.077 0.22.207.467 I slot launch_slot_: id 0 | task 1144 | processing task, is_child = 0 0.23.983.870 I slot print_timing: id 0 | task 1144 | prompt eval time = 352.59 ms / 175 tokens ( 2.01 ms per token, 496.33 tokens per second) 0.23.983.876 I slot print_timing: id 0 | task 1144 | eval time = 1423.81 ms / 97 tokens ( 14.83 ms per token, 67.42 tokens per second) 0.23.983.876 I slot print_timing: id 0 | task 1144 | total time = 1776.40 ms / 272 tokens 0.23.983.877 I slot print_timing: id 0 | task 1144 | graphs reused = 1193 0.23.983.878 I slot print_timing: id 0 | task 1144 | graph reallocs = 0 / 0 (same size) / (changed size) 0.23.983.898 I slot release: id 0 | task 1144 | stop processing: n_tokens = 271, truncated = 0 0.23.987.190 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 271, t_last = 336952369612 0.23.987.880 I slot launch_slot_: id 0 | task 1243 | processing task, is_child = 0 0.26.526.230 I slot print_timing: id 0 | task 1243 | prompt eval time = 385.79 ms / 215 tokens ( 1.79 ms per token, 557.30 tokens per second) 0.26.526.236 I slot print_timing: id 0 | task 1243 | eval time = 2152.55 ms / 146 tokens ( 14.85 ms per token, 67.36 tokens per second) 0.26.526.237 I slot print_timing: id 0 | task 1243 | total time = 2538.34 ms / 361 tokens 0.26.526.238 I slot print_timing: id 0 | task 1243 | graphs reused = 1336 0.26.526.238 I slot print_timing: id 0 | task 1243 | graph reallocs = 0 / 0 (same size) / (changed size) 0.26.526.262 I slot release: id 0 | task 1243 | stop processing: n_tokens = 360, truncated = 0 0.26.529.521 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 0.26.530.412 I slot launch_slot_: id 0 | task 1391 | processing task, is_child = 0 0.28.956.773 I slot print_timing: id 0 | task 1391 | prompt eval time = 353.72 ms / 177 tokens ( 2.00 ms per token, 500.40 tokens per second) 0.28.956.779 I slot print_timing: id 0 | task 1391 | eval time = 2072.63 ms / 141 tokens ( 14.80 ms per token, 67.55 tokens per second) 0.28.956.780 I slot print_timing: id 0 | task 1391 | total time = 2426.35 ms / 318 tokens 0.28.956.781 I slot print_timing: id 0 | task 1391 | graphs reused = 1474 0.28.956.781 I slot print_timing: id 0 | task 1391 | graph reallocs = 0 / 0 (same size) / (changed size) 0.28.956.802 I slot release: id 0 | task 1391 | stop processing: n_tokens = 317, truncated = 0 0.28.960.117 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.116 (> 0.100 thold), f_keep = 0.066 0.28.960.972 I slot launch_slot_: id 0 | task 1534 | processing task, is_child = 0 0.30.563.157 I slot print_timing: id 0 | task 1534 | prompt eval time = 356.18 ms / 181 tokens ( 1.97 ms per token, 508.17 tokens per second) 0.30.563.163 I slot print_timing: id 0 | task 1534 | eval time = 1246.00 ms / 85 tokens ( 14.83 ms per token, 67.42 tokens per second) 0.30.563.163 I slot print_timing: id 0 | task 1534 | total time = 1602.18 ms / 266 tokens 0.30.563.164 I slot print_timing: id 0 | task 1534 | graphs reused = 1556 0.30.563.165 I slot print_timing: id 0 | task 1534 | graph reallocs = 0 / 0 (same size) / (changed size) 0.30.563.186 I slot release: id 0 | task 1534 | stop processing: n_tokens = 265, truncated = 0 0.30.566.450 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 0.30.567.206 I slot launch_slot_: id 0 | task 1621 | processing task, is_child = 0 0.32.502.533 I slot print_timing: id 0 | task 1621 | prompt eval time = 350.83 ms / 172 tokens ( 2.04 ms per token, 490.26 tokens per second) 0.32.502.539 I slot print_timing: id 0 | task 1621 | eval time = 1584.49 ms / 108 tokens ( 14.81 ms per token, 67.53 tokens per second) 0.32.502.540 I slot print_timing: id 0 | task 1621 | total time = 1935.32 ms / 280 tokens 0.32.502.540 I slot print_timing: id 0 | task 1621 | graphs reused = 1661 0.32.502.541 I slot print_timing: id 0 | task 1621 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.502.565 I slot release: id 0 | task 1621 | stop processing: n_tokens = 279, truncated = 0 0.32.505.776 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.138 (> 0.100 thold), f_keep = 0.075 0.32.506.555 I slot launch_slot_: id 0 | task 1731 | processing task, is_child = 0 0.34.734.986 I slot print_timing: id 0 | task 1731 | prompt eval time = 322.18 ms / 152 tokens ( 2.12 ms per token, 471.78 tokens per second) 0.34.734.992 I slot print_timing: id 0 | task 1731 | eval time = 1906.24 ms / 129 tokens ( 14.89 ms per token, 67.15 tokens per second) 0.34.734.993 I slot print_timing: id 0 | task 1731 | total time = 2228.42 ms / 281 tokens 0.34.734.993 I slot print_timing: id 0 | task 1731 | graphs reused = 1787 0.34.734.994 I slot print_timing: id 0 | task 1731 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.735.013 I slot release: id 0 | task 1731 | stop processing: n_tokens = 280, truncated = 0 0.34.738.263 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.123 (> 0.100 thold), f_keep = 0.075 0.34.739.028 I slot launch_slot_: id 0 | task 1862 | processing task, is_child = 0 0.38.094.893 I slot print_timing: id 0 | task 1862 | n_gen = 204, tg = 67.51 t/s, tg_3s = 67.84 t/s 0.38.347.451 I slot print_timing: id 0 | task 1862 | prompt eval time = 348.73 ms / 171 tokens ( 2.04 ms per token, 490.35 tokens per second) 0.38.347.457 I slot print_timing: id 0 | task 1862 | eval time = 3259.68 ms / 221 tokens ( 14.82 ms per token, 67.49 tokens per second) 0.38.347.457 I slot print_timing: id 0 | task 1862 | total time = 3608.41 ms / 392 tokens 0.38.347.458 I slot print_timing: id 0 | task 1862 | graphs reused = 2005 0.38.347.459 I slot print_timing: id 0 | task 1862 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.347.479 I slot release: id 0 | task 1862 | stop processing: n_tokens = 391, truncated = 0 0.38.350.720 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.136 (> 0.100 thold), f_keep = 0.054 0.38.351.701 I slot launch_slot_: id 0 | task 2085 | processing task, is_child = 0 0.40.559.934 I slot print_timing: id 0 | task 2085 | prompt eval time = 329.31 ms / 154 tokens ( 2.14 ms per token, 467.64 tokens per second) 0.40.559.940 I slot print_timing: id 0 | task 2085 | eval time = 1878.91 ms / 126 tokens ( 15.03 ms per token, 66.53 tokens per second) 0.40.559.941 I slot print_timing: id 0 | task 2085 | total time = 2208.22 ms / 280 tokens 0.40.559.942 I slot print_timing: id 0 | task 2085 | graphs reused = 2128 0.40.559.942 I slot print_timing: id 0 | task 2085 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.559.961 I slot release: id 0 | task 2085 | stop processing: n_tokens = 279, truncated = 0 0.40.563.262 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.140 (> 0.100 thold), f_keep = 0.075 0.40.564.067 I slot launch_slot_: id 0 | task 2213 | processing task, is_child = 0 0.42.165.406 I slot print_timing: id 0 | task 2213 | prompt eval time = 321.68 ms / 150 tokens ( 2.14 ms per token, 466.31 tokens per second) 0.42.165.412 I slot print_timing: id 0 | task 2213 | eval time = 1279.65 ms / 86 tokens ( 15.05 ms per token, 66.42 tokens per second) 0.42.165.413 I slot print_timing: id 0 | task 2213 | total time = 1601.33 ms / 236 tokens 0.42.165.413 I slot print_timing: id 0 | task 2213 | graphs reused = 2212 0.42.165.414 I slot print_timing: id 0 | task 2213 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.165.433 I slot release: id 0 | task 2213 | stop processing: n_tokens = 235, truncated = 0 0.42.169.215 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 0.42.170.064 I slot launch_slot_: id 0 | task 2301 | processing task, is_child = 0 0.45.036.849 I slot print_timing: id 0 | task 2301 | prompt eval time = 359.67 ms / 190 tokens ( 1.89 ms per token, 528.26 tokens per second) 0.45.036.854 I slot print_timing: id 0 | task 2301 | eval time = 2507.11 ms / 170 tokens ( 14.83 ms per token, 67.41 tokens per second) 0.45.036.855 I slot print_timing: id 0 | task 2301 | total time = 2866.78 ms / 360 tokens 0.45.036.855 I slot print_timing: id 0 | task 2301 | graphs reused = 2379 0.45.036.856 I slot print_timing: id 0 | task 2301 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.036.878 I slot release: id 0 | task 2301 | stop processing: n_tokens = 359, truncated = 0 0.45.040.222 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.131 (> 0.100 thold), f_keep = 0.058 0.45.041.137 I slot launch_slot_: id 0 | task 2473 | processing task, is_child = 0 0.46.990.301 I slot print_timing: id 0 | task 2473 | prompt eval time = 329.66 ms / 160 tokens ( 2.06 ms per token, 485.35 tokens per second) 0.46.990.306 I slot print_timing: id 0 | task 2473 | eval time = 1619.50 ms / 110 tokens ( 14.86 ms per token, 67.30 tokens per second) 0.46.990.307 I slot print_timing: id 0 | task 2473 | total time = 1949.16 ms / 270 tokens 0.46.990.308 I slot print_timing: id 0 | task 2473 | graphs reused = 2486 0.46.990.308 I slot print_timing: id 0 | task 2473 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.990.330 I slot release: id 0 | task 2473 | stop processing: n_tokens = 269, truncated = 0 0.46.993.641 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 269, t_last = 336975376044 0.46.994.375 I slot launch_slot_: id 0 | task 2585 | processing task, is_child = 0 0.48.807.411 I slot print_timing: id 0 | task 2585 | prompt eval time = 388.82 ms / 218 tokens ( 1.78 ms per token, 560.68 tokens per second) 0.48.807.414 I slot print_timing: id 0 | task 2585 | eval time = 1424.21 ms / 97 tokens ( 14.84 ms per token, 67.41 tokens per second) 0.48.807.415 I slot print_timing: id 0 | task 2585 | total time = 1813.03 ms / 315 tokens 0.48.807.416 I slot print_timing: id 0 | task 2585 | graphs reused = 2580 0.48.807.416 I slot print_timing: id 0 | task 2585 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.807.438 I slot release: id 0 | task 2585 | stop processing: n_tokens = 314, truncated = 0 0.48.810.699 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.109 (> 0.100 thold), f_keep = 0.067 0.48.811.534 I slot launch_slot_: id 0 | task 2684 | processing task, is_child = 0 0.51.187.260 I slot print_timing: id 0 | task 2684 | prompt eval time = 359.31 ms / 193 tokens ( 1.86 ms per token, 537.13 tokens per second) 0.51.187.266 I slot print_timing: id 0 | task 2684 | eval time = 2016.40 ms / 137 tokens ( 14.83 ms per token, 67.45 tokens per second) 0.51.187.266 I slot print_timing: id 0 | task 2684 | total time = 2375.72 ms / 330 tokens 0.51.187.267 I slot print_timing: id 0 | task 2684 | graphs reused = 2714 0.51.187.268 I slot print_timing: id 0 | task 2684 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.187.289 I slot release: id 0 | task 2684 | stop processing: n_tokens = 329, truncated = 0 0.51.190.574 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.104 (> 0.100 thold), f_keep = 0.064 0.51.191.389 I slot launch_slot_: id 0 | task 2823 | processing task, is_child = 0 0.54.581.086 I slot print_timing: id 0 | task 2823 | n_gen = 204, tg = 67.37 t/s, tg_3s = 67.71 t/s 0.56.588.023 I slot print_timing: id 0 | task 2823 | prompt eval time = 376.66 ms / 201 tokens ( 1.87 ms per token, 533.64 tokens per second) 0.56.588.026 I slot print_timing: id 0 | task 2823 | eval time = 5019.97 ms / 339 tokens ( 14.85 ms per token, 67.33 tokens per second) 0.56.588.026 I slot print_timing: id 0 | task 2823 | total time = 5396.63 ms / 540 tokens 0.56.588.027 I slot print_timing: id 0 | task 2823 | graphs reused = 3049 0.56.588.028 I slot print_timing: id 0 | task 2823 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.588.053 I slot release: id 0 | task 2823 | stop processing: n_tokens = 539, truncated = 0 0.56.591.506 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 539, t_last = 336984973768 0.56.592.721 I slot launch_slot_: id 0 | task 3164 | processing task, is_child = 0 0.59.053.898 I slot print_timing: id 0 | task 3164 | prompt eval time = 412.38 ms / 237 tokens ( 1.74 ms per token, 574.72 tokens per second) 0.59.053.903 I slot print_timing: id 0 | task 3164 | eval time = 2048.79 ms / 139 tokens ( 14.85 ms per token, 67.36 tokens per second) 0.59.053.904 I slot print_timing: id 0 | task 3164 | total time = 2461.17 ms / 376 tokens 0.59.053.905 I slot print_timing: id 0 | task 3164 | graphs reused = 3185 0.59.053.905 I slot print_timing: id 0 | task 3164 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.053.929 I slot release: id 0 | task 3164 | stop processing: n_tokens = 375, truncated = 0 0.59.057.238 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 0.59.058.154 I slot launch_slot_: id 0 | task 3305 | processing task, is_child = 0 1.00.894.677 I slot print_timing: id 0 | task 3305 | prompt eval time = 362.42 ms / 196 tokens ( 1.85 ms per token, 540.81 tokens per second) 1.00.894.684 I slot print_timing: id 0 | task 3305 | eval time = 1474.10 ms / 100 tokens ( 14.89 ms per token, 67.16 tokens per second) 1.00.894.685 I slot print_timing: id 0 | task 3305 | total time = 1836.51 ms / 296 tokens 1.00.894.685 I slot print_timing: id 0 | task 3305 | graphs reused = 3282 1.00.894.686 I slot print_timing: id 0 | task 3305 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.894.707 I slot release: id 0 | task 3305 | stop processing: n_tokens = 295, truncated = 0 1.00.897.763 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 1.00.898.574 I slot launch_slot_: id 0 | task 3407 | processing task, is_child = 0 1.02.518.935 I slot print_timing: id 0 | task 3407 | prompt eval time = 332.14 ms / 151 tokens ( 2.20 ms per token, 454.63 tokens per second) 1.02.518.938 I slot print_timing: id 0 | task 3407 | eval time = 1288.22 ms / 88 tokens ( 14.81 ms per token, 67.54 tokens per second) 1.02.518.939 I slot print_timing: id 0 | task 3407 | total time = 1620.35 ms / 239 tokens 1.02.518.939 I slot print_timing: id 0 | task 3407 | graphs reused = 3368 1.02.518.940 I slot print_timing: id 0 | task 3407 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.518.958 I slot release: id 0 | task 3407 | stop processing: n_tokens = 238, truncated = 0 1.02.522.279 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 1.02.522.914 I slot launch_slot_: id 0 | task 3497 | processing task, is_child = 0 1.04.675.202 I slot print_timing: id 0 | task 3497 | prompt eval time = 356.09 ms / 180 tokens ( 1.98 ms per token, 505.49 tokens per second) 1.04.675.207 I slot print_timing: id 0 | task 3497 | eval time = 1796.19 ms / 122 tokens ( 14.84 ms per token, 67.36 tokens per second) 1.04.675.207 I slot print_timing: id 0 | task 3497 | total time = 2152.28 ms / 302 tokens 1.04.675.208 I slot print_timing: id 0 | task 3497 | graphs reused = 3487 1.04.675.208 I slot print_timing: id 0 | task 3497 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.675.229 I slot release: id 0 | task 3497 | stop processing: n_tokens = 301, truncated = 0 1.04.678.514 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 301, t_last = 336993060943 1.04.679.292 I slot launch_slot_: id 0 | task 3621 | processing task, is_child = 0 1.07.201.288 I slot print_timing: id 0 | task 3621 | prompt eval time = 385.99 ms / 211 tokens ( 1.83 ms per token, 546.65 tokens per second) 1.07.201.294 I slot print_timing: id 0 | task 3621 | eval time = 2136.00 ms / 145 tokens ( 14.83 ms per token, 67.42 tokens per second) 1.07.201.295 I slot print_timing: id 0 | task 3621 | total time = 2521.99 ms / 356 tokens 1.07.201.295 I slot print_timing: id 0 | task 3621 | graphs reused = 3629 1.07.201.296 I slot print_timing: id 0 | task 3621 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.201.320 I slot release: id 0 | task 3621 | stop processing: n_tokens = 355, truncated = 0 1.07.204.581 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.113 (> 0.100 thold), f_keep = 0.059 1.07.205.504 I slot launch_slot_: id 0 | task 3768 | processing task, is_child = 0 1.09.390.843 I slot print_timing: id 0 | task 3768 | prompt eval time = 362.61 ms / 186 tokens ( 1.95 ms per token, 512.95 tokens per second) 1.09.390.850 I slot print_timing: id 0 | task 3768 | eval time = 1822.72 ms / 123 tokens ( 14.94 ms per token, 66.93 tokens per second) 1.09.390.850 I slot print_timing: id 0 | task 3768 | total time = 2185.33 ms / 309 tokens 1.09.390.851 I slot print_timing: id 0 | task 3768 | graphs reused = 3749 1.09.390.852 I slot print_timing: id 0 | task 3768 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.390.874 I slot release: id 0 | task 3768 | stop processing: n_tokens = 308, truncated = 0 1.09.394.186 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 1.09.395.000 I slot launch_slot_: id 0 | task 3893 | processing task, is_child = 0 1.11.600.523 I slot print_timing: id 0 | task 3893 | prompt eval time = 336.23 ms / 164 tokens ( 2.05 ms per token, 487.76 tokens per second) 1.11.600.526 I slot print_timing: id 0 | task 3893 | eval time = 1869.28 ms / 127 tokens ( 14.84 ms per token, 67.41 tokens per second) 1.11.600.526 I slot print_timing: id 0 | task 3893 | total time = 2205.51 ms / 291 tokens 1.11.600.527 I slot print_timing: id 0 | task 3893 | graphs reused = 3873 1.11.600.528 I slot print_timing: id 0 | task 3893 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.600.552 I slot release: id 0 | task 3893 | stop processing: n_tokens = 290, truncated = 0 1.11.603.776 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.130 (> 0.100 thold), f_keep = 0.072 1.11.604.519 I slot launch_slot_: id 0 | task 4022 | processing task, is_child = 0 1.13.734.952 I slot print_timing: id 0 | task 4022 | prompt eval time = 335.70 ms / 162 tokens ( 2.07 ms per token, 482.57 tokens per second) 1.13.734.957 I slot print_timing: id 0 | task 4022 | eval time = 1794.72 ms / 122 tokens ( 14.83 ms per token, 67.42 tokens per second) 1.13.734.958 I slot print_timing: id 0 | task 4022 | total time = 2130.43 ms / 284 tokens 1.13.734.958 I slot print_timing: id 0 | task 4022 | graphs reused = 3992 1.13.734.959 I slot print_timing: id 0 | task 4022 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.734.979 I slot release: id 0 | task 4022 | stop processing: n_tokens = 283, truncated = 0 1.13.738.328 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.111 (> 0.100 thold), f_keep = 0.074 1.13.739.073 I slot launch_slot_: id 0 | task 4146 | processing task, is_child = 0 1.15.932.442 I slot print_timing: id 0 | task 4146 | prompt eval time = 361.94 ms / 190 tokens ( 1.90 ms per token, 524.95 tokens per second) 1.15.932.451 I slot print_timing: id 0 | task 4146 | eval time = 1831.42 ms / 125 tokens ( 14.77 ms per token, 67.71 tokens per second) 1.15.932.451 I slot print_timing: id 0 | task 4146 | total time = 2193.36 ms / 315 tokens 1.15.932.452 I slot print_timing: id 0 | task 4146 | graphs reused = 4114 1.15.932.452 I slot print_timing: id 0 | task 4146 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.932.475 I slot release: id 0 | task 4146 | stop processing: n_tokens = 314, truncated = 0 1.15.935.768 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.102 (> 0.100 thold), f_keep = 0.067 1.15.936.565 I slot launch_slot_: id 0 | task 4273 | processing task, is_child = 0 1.18.123.050 I slot print_timing: id 0 | task 4273 | prompt eval time = 382.18 ms / 206 tokens ( 1.86 ms per token, 539.01 tokens per second) 1.18.123.057 I slot print_timing: id 0 | task 4273 | eval time = 1804.30 ms / 122 tokens ( 14.91 ms per token, 67.06 tokens per second) 1.18.123.058 I slot print_timing: id 0 | task 4273 | total time = 2186.47 ms / 328 tokens 1.18.123.058 I slot print_timing: id 0 | task 4273 | graphs reused = 4233 1.18.123.059 I slot print_timing: id 0 | task 4273 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.123.081 I slot release: id 0 | task 4273 | stop processing: n_tokens = 327, truncated = 0 1.18.126.306 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.134 (> 0.100 thold), f_keep = 0.064 1.18.127.089 I slot launch_slot_: id 0 | task 4397 | processing task, is_child = 0 1.20.921.500 I slot print_timing: id 0 | task 4397 | prompt eval time = 331.07 ms / 157 tokens ( 2.11 ms per token, 474.22 tokens per second) 1.20.921.506 I slot print_timing: id 0 | task 4397 | eval time = 2463.33 ms / 167 tokens ( 14.84 ms per token, 67.39 tokens per second) 1.20.921.507 I slot print_timing: id 0 | task 4397 | total time = 2794.40 ms / 324 tokens 1.20.921.508 I slot print_timing: id 0 | task 4397 | graphs reused = 4397 1.20.921.508 I slot print_timing: id 0 | task 4397 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.921.528 I slot release: id 0 | task 4397 | stop processing: n_tokens = 323, truncated = 0 1.20.924.868 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.106 (> 0.100 thold), f_keep = 0.065 1.20.925.744 I slot launch_slot_: id 0 | task 4566 | processing task, is_child = 0 1.24.302.482 I slot print_timing: id 0 | task 4566 | n_gen = 203, tg = 67.33 t/s, tg_3s = 67.66 t/s 1.27.315.089 I slot print_timing: id 0 | task 4566 | n_gen = 406, tg = 67.36 t/s, tg_3s = 67.38 t/s 1.30.320.641 I slot print_timing: id 0 | task 4566 | n_gen = 608, tg = 67.31 t/s, tg_3s = 67.21 t/s 1.30.469.603 I slot print_timing: id 0 | task 4566 | prompt eval time = 376.65 ms / 198 tokens ( 1.90 ms per token, 525.69 tokens per second) 1.30.469.608 I slot print_timing: id 0 | task 4566 | eval time = 9167.20 ms / 618 tokens ( 14.86 ms per token, 67.31 tokens per second) 1.30.469.608 I slot print_timing: id 0 | task 4566 | total time = 9543.85 ms / 816 tokens 1.30.469.609 I slot print_timing: id 0 | task 4566 | graphs reused = 5010 1.30.469.610 I slot print_timing: id 0 | task 4566 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.469.633 I slot release: id 0 | task 4566 | stop processing: n_tokens = 815, truncated = 0 1.30.472.926 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.168 (> 0.100 thold), f_keep = 0.026 1.30.474.691 I slot launch_slot_: id 0 | task 5186 | processing task, is_child = 0 1.33.251.302 I slot print_timing: id 0 | task 5186 | prompt eval time = 306.96 ms / 125 tokens ( 2.46 ms per token, 407.22 tokens per second) 1.33.251.308 I slot print_timing: id 0 | task 5186 | eval time = 2469.64 ms / 168 tokens ( 14.79 ms per token, 67.62 tokens per second) 1.33.251.309 I slot print_timing: id 0 | task 5186 | total time = 2776.60 ms / 293 tokens 1.33.251.309 I slot print_timing: id 0 | task 5186 | graphs reused = 5175 1.33.251.310 I slot print_timing: id 0 | task 5186 | graph reallocs = 0 / 0 (same size) / (changed size) 1.33.251.329 I slot release: id 0 | task 5186 | stop processing: n_tokens = 292, truncated = 0 1.33.254.634 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.157 (> 0.100 thold), f_keep = 0.072 1.33.255.394 I slot launch_slot_: id 0 | task 5356 | processing task, is_child = 0 1.36.266.239 I slot print_timing: id 0 | task 5356 | prompt eval time = 317.53 ms / 134 tokens ( 2.37 ms per token, 422.01 tokens per second) 1.36.266.245 I slot print_timing: id 0 | task 5356 | eval time = 2693.31 ms / 182 tokens ( 14.88 ms per token, 67.20 tokens per second) 1.36.266.245 I slot print_timing: id 0 | task 5356 | total time = 3010.83 ms / 316 tokens 1.36.266.246 I slot print_timing: id 0 | task 5356 | graphs reused = 5354 1.36.266.247 I slot print_timing: id 0 | task 5356 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.266.266 I slot release: id 0 | task 5356 | stop processing: n_tokens = 315, truncated = 0 1.36.269.516 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.142 (> 0.100 thold), f_keep = 0.067 1.36.270.274 I slot launch_slot_: id 0 | task 5540 | processing task, is_child = 0 1.38.186.079 I slot print_timing: id 0 | task 5540 | prompt eval time = 328.54 ms / 148 tokens ( 2.22 ms per token, 450.48 tokens per second) 1.38.186.087 I slot print_timing: id 0 | task 5540 | eval time = 1587.26 ms / 108 tokens ( 14.83 ms per token, 67.41 tokens per second) 1.38.186.090 I slot print_timing: id 0 | task 5540 | total time = 1915.80 ms / 256 tokens 1.38.186.091 I slot print_timing: id 0 | task 5540 | graphs reused = 5460 1.38.186.092 I slot print_timing: id 0 | task 5540 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.186.116 I slot release: id 0 | task 5540 | stop processing: n_tokens = 255, truncated = 0 1.38.189.592 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.149 (> 0.100 thold), f_keep = 0.082 1.38.190.304 I slot launch_slot_: id 0 | task 5650 | processing task, is_child = 0 1.39.523.293 I slot print_timing: id 0 | task 5650 | prompt eval time = 321.24 ms / 141 tokens ( 2.28 ms per token, 438.92 tokens per second) 1.39.523.298 I slot print_timing: id 0 | task 5650 | eval time = 1011.74 ms / 69 tokens ( 14.88 ms per token, 67.21 tokens per second) 1.39.523.298 I slot print_timing: id 0 | task 5650 | total time = 1332.98 ms / 210 tokens 1.39.523.299 I slot print_timing: id 0 | task 5650 | graphs reused = 5527 1.39.523.299 I slot print_timing: id 0 | task 5650 | graph reallocs = 0 / 0 (same size) / (changed size) 1.39.523.318 I slot release: id 0 | task 5650 | stop processing: n_tokens = 209, truncated = 0 1.39.526.488 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 1.39.527.122 I slot launch_slot_: id 0 | task 5721 | processing task, is_child = 0 1.41.818.123 I slot print_timing: id 0 | task 5721 | prompt eval time = 362.86 ms / 196 tokens ( 1.85 ms per token, 540.16 tokens per second) 1.41.818.129 I slot print_timing: id 0 | task 5721 | eval time = 1928.14 ms / 131 tokens ( 14.83 ms per token, 67.42 tokens per second) 1.41.818.130 I slot print_timing: id 0 | task 5721 | total time = 2290.99 ms / 327 tokens 1.41.818.130 I slot print_timing: id 0 | task 5721 | graphs reused = 5655 1.41.818.131 I slot print_timing: id 0 | task 5721 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.818.153 I slot release: id 0 | task 5721 | stop processing: n_tokens = 326, truncated = 0 1.41.821.619 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 326, t_last = 337030203867 1.41.822.449 I slot launch_slot_: id 0 | task 5854 | processing task, is_child = 0 1.45.321.089 I slot print_timing: id 0 | task 5854 | n_gen = 203, tg = 67.31 t/s, tg_3s = 67.64 t/s 1.46.660.190 I slot print_timing: id 0 | task 5854 | prompt eval time = 497.63 ms / 328 tokens ( 1.52 ms per token, 659.12 tokens per second) 1.46.660.196 I slot print_timing: id 0 | task 5854 | eval time = 4340.10 ms / 293 tokens ( 14.86 ms per token, 67.28 tokens per second) 1.46.660.196 I slot print_timing: id 0 | task 5854 | total time = 4837.73 ms / 621 tokens 1.46.660.197 I slot print_timing: id 0 | task 5854 | graphs reused = 5945 1.46.660.198 I slot print_timing: id 0 | task 5854 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.660.229 I slot release: id 0 | task 5854 | stop processing: n_tokens = 620, truncated = 0 1.46.663.501 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.143 (> 0.100 thold), f_keep = 0.034 1.46.664.841 I slot launch_slot_: id 0 | task 6149 | processing task, is_child = 0 1.48.206.556 I slot print_timing: id 0 | task 6149 | prompt eval time = 326.60 ms / 147 tokens ( 2.22 ms per token, 450.10 tokens per second) 1.48.206.567 I slot print_timing: id 0 | task 6149 | eval time = 1215.11 ms / 83 tokens ( 14.82 ms per token, 67.48 tokens per second) 1.48.206.571 I slot print_timing: id 0 | task 6149 | total time = 1541.70 ms / 230 tokens 1.48.206.573 I slot print_timing: id 0 | task 6149 | graphs reused = 6026 1.48.206.574 I slot print_timing: id 0 | task 6149 | graph reallocs = 0 / 0 (same size) / (changed size) 1.48.206.597 I slot release: id 0 | task 6149 | stop processing: n_tokens = 229, truncated = 0 1.48.209.616 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.115 (> 0.100 thold), f_keep = 0.092 1.48.210.238 I slot launch_slot_: id 0 | task 6234 | processing task, is_child = 0 1.50.728.419 I slot print_timing: id 0 | task 6234 | prompt eval time = 358.02 ms / 182 tokens ( 1.97 ms per token, 508.35 tokens per second) 1.50.728.426 I slot print_timing: id 0 | task 6234 | eval time = 2160.16 ms / 146 tokens ( 14.90 ms per token, 67.12 tokens per second) 1.50.728.427 I slot print_timing: id 0 | task 6234 | total time = 2518.17 ms / 328 tokens 1.50.728.428 I slot print_timing: id 0 | task 6234 | graphs reused = 6169 1.50.728.428 I slot print_timing: id 0 | task 6234 | graph reallocs = 0 / 0 (same size) / (changed size) 1.50.728.448 I slot release: id 0 | task 6234 | stop processing: n_tokens = 327, truncated = 0 1.50.732.033 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 327, t_last = 337039114162 1.50.732.935 I slot launch_slot_: id 0 | task 6382 | processing task, is_child = 0 1.52.858.896 I slot print_timing: id 0 | task 6382 | prompt eval time = 404.26 ms / 230 tokens ( 1.76 ms per token, 568.94 tokens per second) 1.52.858.902 I slot print_timing: id 0 | task 6382 | eval time = 1721.69 ms / 117 tokens ( 14.84 ms per token, 67.38 tokens per second) 1.52.858.904 I slot print_timing: id 0 | task 6382 | total time = 2125.95 ms / 347 tokens 1.52.858.905 I slot print_timing: id 0 | task 6382 | graphs reused = 6283 1.52.858.905 I slot print_timing: id 0 | task 6382 | graph reallocs = 0 / 0 (same size) / (changed size) 1.52.858.930 I slot release: id 0 | task 6382 | stop processing: n_tokens = 346, truncated = 0 1.52.862.306 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 346, t_last = 337041244644 1.52.863.156 I slot launch_slot_: id 0 | task 6501 | processing task, is_child = 0 1.55.544.182 I slot print_timing: id 0 | task 6501 | prompt eval time = 409.17 ms / 239 tokens ( 1.71 ms per token, 584.12 tokens per second) 1.55.544.188 I slot print_timing: id 0 | task 6501 | eval time = 2271.85 ms / 154 tokens ( 14.85 ms per token, 67.35 tokens per second) 1.55.544.188 I slot print_timing: id 0 | task 6501 | total time = 2681.02 ms / 393 tokens 1.55.544.189 I slot print_timing: id 0 | task 6501 | graphs reused = 6434 1.55.544.190 I slot print_timing: id 0 | task 6501 | graph reallocs = 0 / 0 (same size) / (changed size) 1.55.544.218 I slot release: id 0 | task 6501 | stop processing: n_tokens = 392, truncated = 0 1.55.547.282 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.151 (> 0.100 thold), f_keep = 0.061 1.55.548.260 I slot launch_slot_: id 0 | task 6657 | processing task, is_child = 0 1.56.937.127 I slot print_timing: id 0 | task 6657 | prompt eval time = 330.82 ms / 159 tokens ( 2.08 ms per token, 480.63 tokens per second) 1.56.937.133 I slot print_timing: id 0 | task 6657 | eval time = 1058.04 ms / 72 tokens ( 14.90 ms per token, 67.11 tokens per second) 1.56.937.133 I slot print_timing: id 0 | task 6657 | total time = 1388.86 ms / 231 tokens 1.56.937.134 I slot print_timing: id 0 | task 6657 | graphs reused = 6504 1.56.937.134 I slot print_timing: id 0 | task 6657 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.937.157 I slot release: id 0 | task 6657 | stop processing: n_tokens = 230, truncated = 0 1.56.940.353 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.125 (> 0.100 thold), f_keep = 0.091 1.56.941.022 I slot launch_slot_: id 0 | task 6731 | processing task, is_child = 0 1.58.735.425 I slot print_timing: id 0 | task 6731 | prompt eval time = 351.80 ms / 168 tokens ( 2.09 ms per token, 477.55 tokens per second) 1.58.735.431 I slot print_timing: id 0 | task 6731 | eval time = 1442.59 ms / 98 tokens ( 14.87 ms per token, 67.24 tokens per second) 1.58.735.431 I slot print_timing: id 0 | task 6731 | total time = 1794.39 ms / 266 tokens 1.58.735.432 I slot print_timing: id 0 | task 6731 | graphs reused = 6599 1.58.735.432 I slot print_timing: id 0 | task 6731 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.735.455 I slot release: id 0 | task 6731 | stop processing: n_tokens = 265, truncated = 0 1.58.738.688 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.119 (> 0.100 thold), f_keep = 0.079 1.58.739.498 I slot launch_slot_: id 0 | task 6831 | processing task, is_child = 0 2.01.471.159 I slot print_timing: id 0 | task 6831 | prompt eval time = 354.94 ms / 177 tokens ( 2.01 ms per token, 498.68 tokens per second) 2.01.471.165 I slot print_timing: id 0 | task 6831 | eval time = 2376.72 ms / 161 tokens ( 14.85 ms per token, 67.32 tokens per second) 2.01.471.166 I slot print_timing: id 0 | task 6831 | total time = 2731.65 ms / 338 tokens 2.01.471.166 I slot print_timing: id 0 | task 6831 | graphs reused = 6757 2.01.471.167 I slot print_timing: id 0 | task 6831 | graph reallocs = 0 / 0 (same size) / (changed size) 2.01.471.189 I slot release: id 0 | task 6831 | stop processing: n_tokens = 337, truncated = 0 2.01.474.600 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.101 (> 0.100 thold), f_keep = 0.062 2.01.475.535 I slot launch_slot_: id 0 | task 6994 | processing task, is_child = 0 2.03.791.852 I slot print_timing: id 0 | task 6994 | prompt eval time = 382.14 ms / 208 tokens ( 1.84 ms per token, 544.30 tokens per second) 2.03.791.857 I slot print_timing: id 0 | task 6994 | eval time = 1934.16 ms / 131 tokens ( 14.88 ms per token, 67.21 tokens per second) 2.03.791.858 I slot print_timing: id 0 | task 6994 | total time = 2316.31 ms / 339 tokens 2.03.791.859 I slot print_timing: id 0 | task 6994 | graphs reused = 6885 2.03.791.859 I slot print_timing: id 0 | task 6994 | graph reallocs = 0 / 0 (same size) / (changed size) 2.03.791.882 I slot release: id 0 | task 6994 | stop processing: n_tokens = 338, truncated = 0 2.03.795.102 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.131 (> 0.100 thold), f_keep = 0.062 2.03.795.929 I slot launch_slot_: id 0 | task 7127 | processing task, is_child = 0 2.06.081.476 I slot print_timing: id 0 | task 7127 | prompt eval time = 333.90 ms / 160 tokens ( 2.09 ms per token, 479.19 tokens per second) 2.06.081.481 I slot print_timing: id 0 | task 7127 | eval time = 1951.64 ms / 132 tokens ( 14.90 ms per token, 67.12 tokens per second) 2.06.081.481 I slot print_timing: id 0 | task 7127 | total time = 2285.54 ms / 292 tokens 2.06.081.482 I slot print_timing: id 0 | task 7127 | graphs reused = 7014 2.06.081.482 I slot print_timing: id 0 | task 7127 | graph reallocs = 0 / 0 (same size) / (changed size) 2.06.081.502 I slot release: id 0 | task 7127 | stop processing: n_tokens = 291, truncated = 0 2.06.084.811 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 291, t_last = 337054467217 2.06.085.567 I slot launch_slot_: id 0 | task 7261 | processing task, is_child = 0 2.08.537.480 I slot print_timing: id 0 | task 7261 | prompt eval time = 388.70 ms / 219 tokens ( 1.77 ms per token, 563.41 tokens per second) 2.08.537.486 I slot print_timing: id 0 | task 7261 | eval time = 2063.20 ms / 140 tokens ( 14.84 ms per token, 67.37 tokens per second) 2.08.537.487 I slot print_timing: id 0 | task 7261 | total time = 2451.91 ms / 359 tokens 2.08.537.488 I slot print_timing: id 0 | task 7261 | graphs reused = 7151 2.08.537.489 I slot print_timing: id 0 | task 7261 | graph reallocs = 0 / 0 (same size) / (changed size) 2.08.537.512 I slot release: id 0 | task 7261 | stop processing: n_tokens = 358, truncated = 0 2.08.540.948 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.124 (> 0.100 thold), f_keep = 0.059 2.08.541.957 I slot launch_slot_: id 0 | task 7403 | processing task, is_child = 0 2.11.039.076 I slot print_timing: id 0 | task 7403 | prompt eval time = 349.73 ms / 170 tokens ( 2.06 ms per token, 486.08 tokens per second) 2.11.039.078 I slot print_timing: id 0 | task 7403 | eval time = 2147.38 ms / 144 tokens ( 15.02 ms per token, 66.59 tokens per second) 2.11.039.079 I slot print_timing: id 0 | task 7403 | total time = 2497.11 ms / 314 tokens 2.11.039.080 I slot print_timing: id 0 | task 7403 | graphs reused = 7292 2.11.039.080 I slot print_timing: id 0 | task 7403 | graph reallocs = 0 / 0 (same size) / (changed size) 2.11.039.104 I slot release: id 0 | task 7403 | stop processing: n_tokens = 313, truncated = 0 2.11.042.277 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.124 (> 0.100 thold), f_keep = 0.067 2.11.043.113 I slot launch_slot_: id 0 | task 7549 | processing task, is_child = 0 2.14.348.549 I slot print_timing: id 0 | task 7549 | prompt eval time = 350.88 ms / 169 tokens ( 2.08 ms per token, 481.65 tokens per second) 2.14.348.555 I slot print_timing: id 0 | task 7549 | eval time = 2954.55 ms / 200 tokens ( 14.85 ms per token, 67.35 tokens per second) 2.14.348.555 I slot print_timing: id 0 | task 7549 | total time = 3305.43 ms / 369 tokens 2.14.348.556 I slot print_timing: id 0 | task 7549 | graphs reused = 7489 2.14.348.557 I slot print_timing: id 0 | task 7549 | graph reallocs = 0 / 0 (same size) / (changed size) 2.14.348.581 I slot release: id 0 | task 7549 | stop processing: n_tokens = 368, truncated = 0 2.14.352.204 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 368, t_last = 337062734295 2.14.353.220 I slot launch_slot_: id 0 | task 7751 | processing task, is_child = 0 2.17.331.853 I slot print_timing: id 0 | task 7751 | prompt eval time = 453.45 ms / 287 tokens ( 1.58 ms per token, 632.92 tokens per second) 2.17.331.859 I slot print_timing: id 0 | task 7751 | eval time = 2525.17 ms / 171 tokens ( 14.85 ms per token, 67.32 tokens per second) 2.17.331.860 I slot print_timing: id 0 | task 7751 | total time = 2978.62 ms / 458 tokens 2.17.331.860 I slot print_timing: id 0 | task 7751 | graphs reused = 7658 2.17.331.861 I slot print_timing: id 0 | task 7751 | graph reallocs = 0 / 0 (same size) / (changed size) 2.17.331.888 I slot release: id 0 | task 7751 | stop processing: n_tokens = 457, truncated = 0 2.17.335.282 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 457, t_last = 337065717602 2.17.336.386 I slot launch_slot_: id 0 | task 7924 | processing task, is_child = 0 2.20.674.348 I slot print_timing: id 0 | task 7924 | prompt eval time = 422.80 ms / 255 tokens ( 1.66 ms per token, 603.12 tokens per second) 2.20.674.365 I slot print_timing: id 0 | task 7924 | eval time = 2915.15 ms / 197 tokens ( 14.87 ms per token, 67.23 tokens per second) 2.20.674.365 I slot print_timing: id 0 | task 7924 | total time = 3337.95 ms / 452 tokens 2.20.674.366 I slot print_timing: id 0 | task 7924 | graphs reused = 7852 2.20.674.367 I slot print_timing: id 0 | task 7924 | graph reallocs = 0 / 0 (same size) / (changed size) 2.20.674.393 I slot release: id 0 | task 7924 | stop processing: n_tokens = 451, truncated = 0 2.20.678.344 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 2.20.679.770 I slot launch_slot_: id 0 | task 8123 | processing task, is_child = 0 2.22.408.093 I slot print_timing: id 0 | task 8123 | prompt eval time = 335.28 ms / 163 tokens ( 2.06 ms per token, 486.16 tokens per second) 2.22.408.099 I slot print_timing: id 0 | task 8123 | eval time = 1393.03 ms / 94 tokens ( 14.98 ms per token, 66.76 tokens per second) 2.22.408.099 I slot print_timing: id 0 | task 8123 | total time = 1728.31 ms / 257 tokens 2.22.408.100 I slot print_timing: id 0 | task 8123 | graphs reused = 7944 2.22.408.100 I slot print_timing: id 0 | task 8123 | graph reallocs = 0 / 0 (same size) / (changed size) 2.22.408.120 I slot release: id 0 | task 8123 | stop processing: n_tokens = 256, truncated = 0 2.22.411.561 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.104 (> 0.100 thold), f_keep = 0.082 2.22.412.316 I slot launch_slot_: id 0 | task 8219 | processing task, is_child = 0 2.24.261.894 I slot print_timing: id 0 | task 8219 | prompt eval time = 379.01 ms / 201 tokens ( 1.89 ms per token, 530.33 tokens per second) 2.24.261.900 I slot print_timing: id 0 | task 8219 | eval time = 1470.56 ms / 100 tokens ( 14.85 ms per token, 67.32 tokens per second) 2.24.261.901 I slot print_timing: id 0 | task 8219 | total time = 1849.57 ms / 301 tokens 2.24.261.901 I slot print_timing: id 0 | task 8219 | graphs reused = 8041 2.24.261.902 I slot print_timing: id 0 | task 8219 | graph reallocs = 0 / 0 (same size) / (changed size) 2.24.261.924 I slot release: id 0 | task 8219 | stop processing: n_tokens = 300, truncated = 0 2.24.265.102 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 2.24.265.860 I slot launch_slot_: id 0 | task 8321 | processing task, is_child = 0 2.26.024.518 I slot print_timing: id 0 | task 8321 | prompt eval time = 328.76 ms / 157 tokens ( 2.09 ms per token, 477.55 tokens per second) 2.26.024.524 I slot print_timing: id 0 | task 8321 | eval time = 1429.89 ms / 97 tokens ( 14.89 ms per token, 67.14 tokens per second) 2.26.024.525 I slot print_timing: id 0 | task 8321 | total time = 1758.65 ms / 254 tokens 2.26.024.526 I slot print_timing: id 0 | task 8321 | graphs reused = 8136 2.26.024.526 I slot print_timing: id 0 | task 8321 | graph reallocs = 0 / 0 (same size) / (changed size) 2.26.024.545 I slot release: id 0 | task 8321 | stop processing: n_tokens = 253, truncated = 0 2.26.028.166 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 253, t_last = 337074410259 2.26.029.045 I slot launch_slot_: id 0 | task 8420 | processing task, is_child = 0 2.29.437.100 I slot print_timing: id 0 | task 8420 | n_gen = 204, tg = 67.34 t/s, tg_3s = 67.68 t/s 2.30.624.457 I slot print_timing: id 0 | task 8420 | prompt eval time = 393.71 ms / 226 tokens ( 1.74 ms per token, 574.03 tokens per second) 2.30.624.464 I slot print_timing: id 0 | task 8420 | eval time = 4201.69 ms / 284 tokens ( 14.85 ms per token, 67.35 tokens per second) 2.30.624.465 I slot print_timing: id 0 | task 8420 | total time = 4595.41 ms / 510 tokens 2.30.624.465 I slot print_timing: id 0 | task 8420 | graphs reused = 8417 2.30.624.466 I slot print_timing: id 0 | task 8420 | graph reallocs = 0 / 0 (same size) / (changed size) 2.30.624.491 I slot release: id 0 | task 8420 | stop processing: n_tokens = 509, truncated = 0 2.30.628.395 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 509, t_last = 337079010205 2.30.629.699 I slot launch_slot_: id 0 | task 8706 | processing task, is_child = 0 2.32.733.186 I slot print_timing: id 0 | task 8706 | prompt eval time = 517.82 ms / 356 tokens ( 1.45 ms per token, 687.50 tokens per second) 2.32.733.191 I slot print_timing: id 0 | task 8706 | eval time = 1585.66 ms / 107 tokens ( 14.96 ms per token, 66.85 tokens per second) 2.32.733.192 I slot print_timing: id 0 | task 8706 | total time = 2103.48 ms / 463 tokens 2.32.733.193 I slot print_timing: id 0 | task 8706 | graphs reused = 8522 2.32.733.193 I slot print_timing: id 0 | task 8706 | graph reallocs = 0 / 0 (same size) / (changed size) 2.32.733.225 I slot release: id 0 | task 8706 | stop processing: n_tokens = 462, truncated = 0 2.32.736.896 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 462, t_last = 337081118939 2.32.737.969 I slot launch_slot_: id 0 | task 8815 | processing task, is_child = 0 2.36.338.444 I slot print_timing: id 0 | task 8815 | n_gen = 203, tg = 67.20 t/s, tg_3s = 67.53 t/s 2.37.346.392 I slot print_timing: id 0 | task 8815 | prompt eval time = 594.47 ms / 427 tokens ( 1.39 ms per token, 718.29 tokens per second) 2.37.346.398 I slot print_timing: id 0 | task 8815 | eval time = 4013.95 ms / 271 tokens ( 14.87 ms per token, 67.27 tokens per second) 2.37.346.399 I slot print_timing: id 0 | task 8815 | total time = 4608.42 ms / 698 tokens 2.37.346.400 I slot print_timing: id 0 | task 8815 | graphs reused = 8790 2.37.346.400 I slot print_timing: id 0 | task 8815 | graph reallocs = 0 / 0 (same size) / (changed size) 2.37.346.437 I slot release: id 0 | task 8815 | stop processing: n_tokens = 697, truncated = 0 2.37.350.608 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 697, t_last = 337085732151 2.37.352.284 I slot launch_slot_: id 0 | task 9088 | processing task, is_child = 0 2.40.957.683 I slot print_timing: id 0 | task 9088 | prompt eval time = 646.99 ms / 481 tokens ( 1.35 ms per token, 743.44 tokens per second) 2.40.957.689 I slot print_timing: id 0 | task 9088 | eval time = 2958.40 ms / 200 tokens ( 14.87 ms per token, 67.27 tokens per second) 2.40.957.690 I slot print_timing: id 0 | task 9088 | total time = 3605.39 ms / 681 tokens 2.40.957.690 I slot print_timing: id 0 | task 9088 | graphs reused = 8987 2.40.957.691 I slot print_timing: id 0 | task 9088 | graph reallocs = 0 / 0 (same size) / (changed size) 2.40.957.729 I slot release: id 0 | task 9088 | stop processing: n_tokens = 680, truncated = 0 2.40.961.745 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 680, t_last = 337089343443 2.40.963.410 I slot launch_slot_: id 0 | task 9290 | processing task, is_child = 0 2.44.593.483 I slot print_timing: id 0 | task 9290 | n_gen = 203, tg = 67.29 t/s, tg_3s = 67.62 t/s 2.44.832.945 I slot print_timing: id 0 | task 9290 | prompt eval time = 628.16 ms / 456 tokens ( 1.38 ms per token, 725.93 tokens per second) 2.44.832.951 I slot print_timing: id 0 | task 9290 | eval time = 3241.36 ms / 219 tokens ( 14.87 ms per token, 67.26 tokens per second) 2.44.832.952 I slot print_timing: id 0 | task 9290 | total time = 3869.53 ms / 675 tokens 2.44.832.952 I slot print_timing: id 0 | task 9290 | graphs reused = 9203 2.44.832.953 I slot print_timing: id 0 | task 9290 | graph reallocs = 0 / 0 (same size) / (changed size) 2.44.832.991 I slot release: id 0 | task 9290 | stop processing: n_tokens = 674, truncated = 0 2.44.836.703 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 674, t_last = 337093218705 2.44.838.198 I slot launch_slot_: id 0 | task 9511 | processing task, is_child = 0 2.46.571.729 I slot print_timing: id 0 | task 9511 | prompt eval time = 451.19 ms / 290 tokens ( 1.56 ms per token, 642.74 tokens per second) 2.46.571.734 I slot print_timing: id 0 | task 9511 | eval time = 1282.33 ms / 86 tokens ( 15.09 ms per token, 66.29 tokens per second) 2.46.571.735 I slot print_timing: id 0 | task 9511 | total time = 1733.52 ms / 376 tokens 2.46.571.736 I slot print_timing: id 0 | task 9511 | graphs reused = 9287 2.46.571.736 I slot print_timing: id 0 | task 9511 | graph reallocs = 0 / 0 (same size) / (changed size) 2.46.571.763 I slot release: id 0 | task 9511 | stop processing: n_tokens = 375, truncated = 0 2.46.575.537 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 375, t_last = 337094957477 2.46.576.461 I slot launch_slot_: id 0 | task 9599 | processing task, is_child = 0 2.50.183.451 I slot print_timing: id 0 | task 9599 | n_gen = 203, tg = 67.24 t/s, tg_3s = 67.57 t/s 2.51.388.035 I slot print_timing: id 0 | task 9599 | prompt eval time = 602.87 ms / 439 tokens ( 1.37 ms per token, 728.18 tokens per second) 2.51.388.041 I slot print_timing: id 0 | task 9599 | eval time = 4208.69 ms / 284 tokens ( 14.87 ms per token, 67.24 tokens per second) 2.51.388.041 I slot print_timing: id 0 | task 9599 | total time = 4811.57 ms / 723 tokens 2.51.388.042 I slot print_timing: id 0 | task 9599 | graphs reused = 9568 2.51.388.042 I slot print_timing: id 0 | task 9599 | graph reallocs = 0 / 0 (same size) / (changed size) 2.51.388.079 I slot release: id 0 | task 9599 | stop processing: n_tokens = 722, truncated = 0 2.51.391.860 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 722, t_last = 337099773793 2.51.393.417 I slot launch_slot_: id 0 | task 9885 | processing task, is_child = 0 2.54.962.977 I slot print_timing: id 0 | task 9885 | n_gen = 203, tg = 67.18 t/s, tg_3s = 67.51 t/s 2.57.972.980 I slot print_timing: id 0 | task 9885 | n_gen = 405, tg = 67.14 t/s, tg_3s = 67.11 t/s 3.00.324.251 I slot print_timing: id 0 | task 9885 | prompt eval time = 562.66 ms / 396 tokens ( 1.42 ms per token, 703.80 tokens per second) 3.00.324.257 I slot print_timing: id 0 | task 9885 | eval time = 8368.16 ms / 563 tokens ( 14.89 ms per token, 67.16 tokens per second) 3.00.324.257 I slot print_timing: id 0 | task 9885 | total time = 8930.82 ms / 959 tokens 3.00.324.258 I slot print_timing: id 0 | task 9885 | graphs reused = 10127 3.00.324.259 I slot print_timing: id 0 | task 9885 | graph reallocs = 0 / 0 (same size) / (changed size) 3.00.324.295 I slot release: id 0 | task 9885 | stop processing: n_tokens = 958, truncated = 0 3.00.328.081 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 958, t_last = 337108710009 3.00.330.115 I slot launch_slot_: id 0 | task 10450 | processing task, is_child = 0 3.01.938.540 I slot print_timing: id 0 | task 10450 | prompt eval time = 509.58 ms / 342 tokens ( 1.49 ms per token, 671.14 tokens per second) 3.01.938.546 I slot print_timing: id 0 | task 10450 | eval time = 1098.84 ms / 75 tokens ( 14.85 ms per token, 67.34 tokens per second) 3.01.938.546 I slot print_timing: id 0 | task 10450 | total time = 1608.42 ms / 417 tokens 3.01.938.547 I slot print_timing: id 0 | task 10450 | graphs reused = 10200 3.01.938.548 I slot print_timing: id 0 | task 10450 | graph reallocs = 0 / 0 (same size) / (changed size) 3.01.938.577 I slot release: id 0 | task 10450 | stop processing: n_tokens = 416, truncated = 0 3.01.942.233 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 337110324291 3.01.943.273 I slot launch_slot_: id 0 | task 10527 | processing task, is_child = 0 3.04.061.346 I slot print_timing: id 0 | task 10527 | prompt eval time = 481.66 ms / 314 tokens ( 1.53 ms per token, 651.91 tokens per second) 3.04.061.351 I slot print_timing: id 0 | task 10527 | eval time = 1636.41 ms / 111 tokens ( 14.88 ms per token, 67.22 tokens per second) 3.04.061.352 I slot print_timing: id 0 | task 10527 | total time = 2118.07 ms / 425 tokens 3.04.061.353 I slot print_timing: id 0 | task 10527 | graphs reused = 10309 3.04.061.353 I slot print_timing: id 0 | task 10527 | graph reallocs = 0 / 0 (same size) / (changed size) 3.04.061.381 I slot release: id 0 | task 10527 | stop processing: n_tokens = 424, truncated = 0 3.04.065.199 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 337112447095 3.04.066.328 I slot launch_slot_: id 0 | task 10640 | processing task, is_child = 0 3.06.082.932 I slot print_timing: id 0 | task 10640 | prompt eval time = 566.87 ms / 396 tokens ( 1.43 ms per token, 698.57 tokens per second) 3.06.082.941 I slot print_timing: id 0 | task 10640 | eval time = 1449.73 ms / 98 tokens ( 14.95 ms per token, 66.91 tokens per second) 3.06.082.942 I slot print_timing: id 0 | task 10640 | total time = 2016.60 ms / 494 tokens 3.06.082.942 I slot print_timing: id 0 | task 10640 | graphs reused = 10405 3.06.082.943 I slot print_timing: id 0 | task 10640 | graph reallocs = 0 / 0 (same size) / (changed size) 3.06.082.974 I slot release: id 0 | task 10640 | stop processing: n_tokens = 493, truncated = 0 3.06.086.682 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 493, t_last = 337114468688 3.06.087.956 I slot launch_slot_: id 0 | task 10740 | processing task, is_child = 0 3.08.287.548 I slot print_timing: id 0 | task 10740 | prompt eval time = 505.61 ms / 339 tokens ( 1.49 ms per token, 670.48 tokens per second) 3.08.287.553 I slot print_timing: id 0 | task 10740 | eval time = 1693.97 ms / 115 tokens ( 14.86 ms per token, 67.30 tokens per second) 3.08.287.554 I slot print_timing: id 0 | task 10740 | total time = 2199.58 ms / 454 tokens 3.08.287.555 I slot print_timing: id 0 | task 10740 | graphs reused = 10518 3.08.287.555 I slot print_timing: id 0 | task 10740 | graph reallocs = 0 / 0 (same size) / (changed size) 3.08.287.587 I slot release: id 0 | task 10740 | stop processing: n_tokens = 453, truncated = 0 3.08.291.029 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 453, t_last = 337116673301 3.08.292.110 I slot launch_slot_: id 0 | task 10857 | processing task, is_child = 0 3.10.020.127 I slot print_timing: id 0 | task 10857 | prompt eval time = 441.06 ms / 267 tokens ( 1.65 ms per token, 605.37 tokens per second) 3.10.020.132 I slot print_timing: id 0 | task 10857 | eval time = 1286.95 ms / 87 tokens ( 14.96 ms per token, 66.82 tokens per second) 3.10.020.133 I slot print_timing: id 0 | task 10857 | total time = 1728.01 ms / 354 tokens 3.10.020.134 I slot print_timing: id 0 | task 10857 | graphs reused = 10603 3.10.020.134 I slot print_timing: id 0 | task 10857 | graph reallocs = 0 / 0 (same size) / (changed size) 3.10.020.160 I slot release: id 0 | task 10857 | stop processing: n_tokens = 353, truncated = 0 3.10.023.771 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 353, t_last = 337118405874 3.10.024.711 I slot launch_slot_: id 0 | task 10946 | processing task, is_child = 0 3.13.002.898 I slot print_timing: id 0 | task 10946 | prompt eval time = 530.68 ms / 360 tokens ( 1.47 ms per token, 678.37 tokens per second) 3.13.002.904 I slot print_timing: id 0 | task 10946 | eval time = 2447.50 ms / 165 tokens ( 14.92 ms per token, 67.01 tokens per second) 3.13.002.905 I slot print_timing: id 0 | task 10946 | total time = 2978.18 ms / 525 tokens 3.13.002.905 I slot print_timing: id 0 | task 10946 | graphs reused = 10765 3.13.002.906 I slot print_timing: id 0 | task 10946 | graph reallocs = 0 / 0 (same size) / (changed size) 3.13.002.940 I slot release: id 0 | task 10946 | stop processing: n_tokens = 524, truncated = 0 3.13.006.554 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 524, t_last = 337121388654 3.13.007.837 I slot launch_slot_: id 0 | task 11113 | processing task, is_child = 0 3.15.057.033 I slot print_timing: id 0 | task 11113 | prompt eval time = 468.46 ms / 296 tokens ( 1.58 ms per token, 631.86 tokens per second) 3.15.057.038 I slot print_timing: id 0 | task 11113 | eval time = 1580.73 ms / 107 tokens ( 14.91 ms per token, 67.06 tokens per second) 3.15.057.039 I slot print_timing: id 0 | task 11113 | total time = 2049.19 ms / 403 tokens 3.15.057.040 I slot print_timing: id 0 | task 11113 | graphs reused = 10870 3.15.057.040 I slot print_timing: id 0 | task 11113 | graph reallocs = 0 / 0 (same size) / (changed size) 3.15.057.066 I slot release: id 0 | task 11113 | stop processing: n_tokens = 402, truncated = 0 3.15.060.648 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 402, t_last = 337123442780 3.15.061.634 I slot launch_slot_: id 0 | task 11222 | processing task, is_child = 0 3.17.644.094 I slot print_timing: id 0 | task 11222 | prompt eval time = 446.41 ms / 275 tokens ( 1.62 ms per token, 616.02 tokens per second) 3.17.644.097 I slot print_timing: id 0 | task 11222 | eval time = 2136.04 ms / 145 tokens ( 14.83 ms per token, 67.41 tokens per second) 3.17.644.097 I slot print_timing: id 0 | task 11222 | total time = 2582.45 ms / 420 tokens 3.17.644.098 I slot print_timing: id 0 | task 11222 | graphs reused = 11013 3.17.644.098 I slot print_timing: id 0 | task 11222 | graph reallocs = 0 / 0 (same size) / (changed size) 3.17.644.125 I slot release: id 0 | task 11222 | stop processing: n_tokens = 419, truncated = 0 3.17.647.602 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 337126029839 3.17.648.624 I slot launch_slot_: id 0 | task 11369 | processing task, is_child = 0 3.19.387.128 I slot print_timing: id 0 | task 11369 | prompt eval time = 450.51 ms / 287 tokens ( 1.57 ms per token, 637.05 tokens per second) 3.19.387.135 I slot print_timing: id 0 | task 11369 | eval time = 1287.98 ms / 87 tokens ( 14.98 ms per token, 66.77 tokens per second) 3.19.387.136 I slot print_timing: id 0 | task 11369 | total time = 1738.50 ms / 374 tokens 3.19.387.137 I slot print_timing: id 0 | task 11369 | graphs reused = 11098 3.19.387.137 I slot print_timing: id 0 | task 11369 | graph reallocs = 0 / 0 (same size) / (changed size) 3.19.387.163 I slot release: id 0 | task 11369 | stop processing: n_tokens = 373, truncated = 0 3.19.390.534 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 373, t_last = 337127772877 3.19.391.439 I slot launch_slot_: id 0 | task 11458 | processing task, is_child = 0 3.20.784.155 I slot print_timing: id 0 | task 11458 | prompt eval time = 440.86 ms / 266 tokens ( 1.66 ms per token, 603.36 tokens per second) 3.20.784.159 I slot print_timing: id 0 | task 11458 | eval time = 951.85 ms / 65 tokens ( 14.87 ms per token, 67.24 tokens per second) 3.20.784.160 I slot print_timing: id 0 | task 11458 | total time = 1392.71 ms / 331 tokens 3.20.784.160 I slot print_timing: id 0 | task 11458 | graphs reused = 11161 3.20.784.161 I slot print_timing: id 0 | task 11458 | graph reallocs = 0 / 0 (same size) / (changed size) 3.20.784.189 I slot release: id 0 | task 11458 | stop processing: n_tokens = 330, truncated = 0 3.20.787.980 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 330, t_last = 337129169903 3.20.788.894 I slot launch_slot_: id 0 | task 11525 | processing task, is_child = 0 3.24.184.319 I slot print_timing: id 0 | task 11525 | prompt eval time = 601.74 ms / 435 tokens ( 1.38 ms per token, 722.90 tokens per second) 3.24.184.326 I slot print_timing: id 0 | task 11525 | eval time = 2793.68 ms / 189 tokens ( 14.86 ms per token, 67.29 tokens per second) 3.24.184.327 I slot print_timing: id 0 | task 11525 | total time = 3395.42 ms / 624 tokens 3.24.184.328 I slot print_timing: id 0 | task 11525 | graphs reused = 11347 3.24.184.328 I slot print_timing: id 0 | task 11525 | graph reallocs = 0 / 0 (same size) / (changed size) 3.24.184.363 I slot release: id 0 | task 11525 | stop processing: n_tokens = 623, truncated = 0 3.24.188.010 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 623, t_last = 337132570077 3.24.189.500 I slot launch_slot_: id 0 | task 11716 | processing task, is_child = 0 3.26.613.655 I slot print_timing: id 0 | task 11716 | prompt eval time = 473.92 ms / 307 tokens ( 1.54 ms per token, 647.79 tokens per second) 3.26.613.661 I slot print_timing: id 0 | task 11716 | eval time = 1950.23 ms / 132 tokens ( 14.89 ms per token, 67.17 tokens per second) 3.26.613.662 I slot print_timing: id 0 | task 11716 | total time = 2424.15 ms / 439 tokens 3.26.613.662 I slot print_timing: id 0 | task 11716 | graphs reused = 11477 3.26.613.663 I slot print_timing: id 0 | task 11716 | graph reallocs = 0 / 0 (same size) / (changed size) 3.26.613.693 I slot release: id 0 | task 11716 | stop processing: n_tokens = 438, truncated = 0 3.26.618.114 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 438, t_last = 337134999407 3.26.619.202 I slot launch_slot_: id 0 | task 11850 | processing task, is_child = 0 3.30.603.084 I slot print_timing: id 0 | task 11850 | n_gen = 203, tg = 67.24 t/s, tg_3s = 67.57 t/s 3.30.766.362 I slot print_timing: id 0 | task 11850 | prompt eval time = 979.62 ms / 675 tokens ( 1.45 ms per token, 689.04 tokens per second) 3.30.766.368 I slot print_timing: id 0 | task 11850 | eval time = 3167.53 ms / 214 tokens ( 14.87 ms per token, 67.24 tokens per second) 3.30.766.368 I slot print_timing: id 0 | task 11850 | total time = 4147.15 ms / 889 tokens 3.30.766.369 I slot print_timing: id 0 | task 11850 | graphs reused = 11688 3.30.766.370 I slot print_timing: id 0 | task 11850 | graph reallocs = 0 / 0 (same size) / (changed size) 3.30.766.421 I slot release: id 0 | task 11850 | stop processing: n_tokens = 888, truncated = 0 3.30.770.484 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 888, t_last = 337139152135 3.30.772.488 I slot launch_slot_: id 0 | task 12067 | processing task, is_child = 0 3.33.009.211 I slot print_timing: id 0 | task 12067 | prompt eval time = 455.01 ms / 287 tokens ( 1.59 ms per token, 630.76 tokens per second) 3.33.009.216 I slot print_timing: id 0 | task 12067 | eval time = 1781.70 ms / 121 tokens ( 14.85 ms per token, 67.35 tokens per second) 3.33.009.217 I slot print_timing: id 0 | task 12067 | total time = 2236.71 ms / 408 tokens 3.33.009.218 I slot print_timing: id 0 | task 12067 | graphs reused = 11807 3.33.009.218 I slot print_timing: id 0 | task 12067 | graph reallocs = 0 / 0 (same size) / (changed size) 3.33.009.250 I slot release: id 0 | task 12067 | stop processing: n_tokens = 407, truncated = 0 3.33.013.290 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 407, t_last = 337141394964 3.33.014.348 I slot launch_slot_: id 0 | task 12190 | processing task, is_child = 0 3.35.019.929 I slot print_timing: id 0 | task 12190 | prompt eval time = 664.77 ms / 497 tokens ( 1.34 ms per token, 747.62 tokens per second) 3.35.019.935 I slot print_timing: id 0 | task 12190 | eval time = 1340.80 ms / 91 tokens ( 14.90 ms per token, 67.12 tokens per second) 3.35.019.936 I slot print_timing: id 0 | task 12190 | total time = 2005.57 ms / 588 tokens 3.35.019.937 I slot print_timing: id 0 | task 12190 | graphs reused = 11895 3.35.019.937 I slot print_timing: id 0 | task 12190 | graph reallocs = 0 / 0 (same size) / (changed size) 3.35.019.976 I slot release: id 0 | task 12190 | stop processing: n_tokens = 587, truncated = 0 3.35.024.409 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 587, t_last = 337143405690 3.35.026.108 I slot launch_slot_: id 0 | task 12283 | processing task, is_child = 0 3.37.976.754 I slot print_timing: id 0 | task 12283 | prompt eval time = 914.20 ms / 609 tokens ( 1.50 ms per token, 666.16 tokens per second) 3.37.976.757 I slot print_timing: id 0 | task 12283 | eval time = 2036.44 ms / 138 tokens ( 14.86 ms per token, 67.27 tokens per second) 3.37.976.758 I slot print_timing: id 0 | task 12283 | total time = 2950.64 ms / 747 tokens 3.37.976.759 I slot print_timing: id 0 | task 12283 | graphs reused = 12031 3.37.976.759 I slot print_timing: id 0 | task 12283 | graph reallocs = 0 / 0 (same size) / (changed size) 3.37.976.808 I slot release: id 0 | task 12283 | stop processing: n_tokens = 746, truncated = 0 3.37.980.667 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 746, t_last = 337146362522 3.37.982.373 I slot launch_slot_: id 0 | task 12424 | processing task, is_child = 0 3.40.685.544 I slot print_timing: id 0 | task 12424 | prompt eval time = 577.84 ms / 415 tokens ( 1.39 ms per token, 718.20 tokens per second) 3.40.685.550 I slot print_timing: id 0 | task 12424 | eval time = 2125.32 ms / 144 tokens ( 14.86 ms per token, 67.28 tokens per second) 3.40.685.551 I slot print_timing: id 0 | task 12424 | total time = 2703.16 ms / 559 tokens 3.40.685.552 I slot print_timing: id 0 | task 12424 | graphs reused = 12172 3.40.685.552 I slot print_timing: id 0 | task 12424 | graph reallocs = 0 / 0 (same size) / (changed size) 3.40.685.588 I slot release: id 0 | task 12424 | stop processing: n_tokens = 558, truncated = 0 3.40.689.223 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 337149071302 3.40.690.487 I slot launch_slot_: id 0 | task 12570 | processing task, is_child = 0 3.42.893.643 I slot print_timing: id 0 | task 12570 | prompt eval time = 468.22 ms / 295 tokens ( 1.59 ms per token, 630.04 tokens per second) 3.42.893.649 I slot print_timing: id 0 | task 12570 | eval time = 1734.93 ms / 118 tokens ( 14.83 ms per token, 67.44 tokens per second) 3.42.893.650 I slot print_timing: id 0 | task 12570 | total time = 2203.15 ms / 413 tokens 3.42.893.650 I slot print_timing: id 0 | task 12570 | graphs reused = 12288 3.42.893.651 I slot print_timing: id 0 | task 12570 | graph reallocs = 0 / 0 (same size) / (changed size) 3.42.893.682 I slot release: id 0 | task 12570 | stop processing: n_tokens = 412, truncated = 0 3.42.897.685 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 412, t_last = 337151279396 3.42.898.754 I slot launch_slot_: id 0 | task 12690 | processing task, is_child = 0 3.46.508.451 I slot print_timing: id 0 | task 12690 | n_gen = 203, tg = 67.29 t/s, tg_3s = 67.62 t/s 3.49.511.867 I slot print_timing: id 0 | task 12690 | n_gen = 405, tg = 67.27 t/s, tg_3s = 67.26 t/s 3.50.135.518 I slot print_timing: id 0 | task 12690 | prompt eval time = 607.57 ms / 442 tokens ( 1.37 ms per token, 727.49 tokens per second) 3.50.135.523 I slot print_timing: id 0 | task 12690 | eval time = 6629.18 ms / 447 tokens ( 14.86 ms per token, 67.28 tokens per second) 3.50.135.523 I slot print_timing: id 0 | task 12690 | total time = 7236.75 ms / 889 tokens 3.50.135.524 I slot print_timing: id 0 | task 12690 | graphs reused = 12731 3.50.135.525 I slot print_timing: id 0 | task 12690 | graph reallocs = 0 / 0 (same size) / (changed size) 3.50.135.563 I slot release: id 0 | task 12690 | stop processing: n_tokens = 888, truncated = 0 3.50.139.910 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 888, t_last = 337158521277 3.50.141.908 I slot launch_slot_: id 0 | task 13139 | processing task, is_child = 0 3.52.864.439 I slot print_timing: id 0 | task 13139 | prompt eval time = 937.16 ms / 622 tokens ( 1.51 ms per token, 663.71 tokens per second) 3.52.864.445 I slot print_timing: id 0 | task 13139 | eval time = 1785.36 ms / 121 tokens ( 14.88 ms per token, 67.21 tokens per second) 3.52.864.445 I slot print_timing: id 0 | task 13139 | total time = 2722.52 ms / 743 tokens 3.52.864.446 I slot print_timing: id 0 | task 13139 | graphs reused = 12850 3.52.864.447 I slot print_timing: id 0 | task 13139 | graph reallocs = 0 / 0 (same size) / (changed size) 3.52.864.492 I slot release: id 0 | task 13139 | stop processing: n_tokens = 742, truncated = 0 3.52.868.317 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 742, t_last = 337161250206 3.52.870.655 I slot launch_slot_: id 0 | task 13263 | processing task, is_child = 0 3.55.122.365 I slot print_timing: id 0 | task 13263 | prompt eval time = 596.95 ms / 424 tokens ( 1.41 ms per token, 710.28 tokens per second) 3.55.122.368 I slot print_timing: id 0 | task 13263 | eval time = 1654.75 ms / 112 tokens ( 14.91 ms per token, 67.08 tokens per second) 3.55.122.369 I slot print_timing: id 0 | task 13263 | total time = 2251.70 ms / 536 tokens 3.55.122.370 I slot print_timing: id 0 | task 13263 | graphs reused = 12959 3.55.122.371 I slot print_timing: id 0 | task 13263 | graph reallocs = 0 / 0 (same size) / (changed size) 3.55.122.406 I slot release: id 0 | task 13263 | stop processing: n_tokens = 535, truncated = 0 3.55.126.503 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 535, t_last = 337163508120 3.55.127.085 I slot launch_slot_: id 0 | task 13377 | processing task, is_child = 0 3.58.693.920 I slot print_timing: id 0 | task 13377 | n_gen = 203, tg = 67.33 t/s, tg_3s = 67.66 t/s 3.59.794.150 I slot print_timing: id 0 | task 13377 | prompt eval time = 566.71 ms / 395 tokens ( 1.43 ms per token, 697.01 tokens per second) 3.59.794.156 I slot print_timing: id 0 | task 13377 | eval time = 4100.35 ms / 277 tokens ( 14.86 ms per token, 67.31 tokens per second) 3.59.794.157 I slot print_timing: id 0 | task 13377 | total time = 4667.05 ms / 672 tokens 3.59.794.158 I slot print_timing: id 0 | task 13377 | graphs reused = 13233 3.59.794.158 I slot print_timing: id 0 | task 13377 | graph reallocs = 0 / 0 (same size) / (changed size) 3.59.794.194 I slot release: id 0 | task 13377 | stop processing: n_tokens = 671, truncated = 0 3.59.797.820 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 671, t_last = 337168179908 3.59.799.658 I slot launch_slot_: id 0 | task 13656 | processing task, is_child = 0 4.01.845.917 I slot print_timing: id 0 | task 13656 | prompt eval time = 446.18 ms / 279 tokens ( 1.60 ms per token, 625.30 tokens per second) 4.01.845.931 I slot print_timing: id 0 | task 13656 | eval time = 1600.07 ms / 109 tokens ( 14.82 ms per token, 67.50 tokens per second) 4.01.845.934 I slot print_timing: id 0 | task 13656 | total time = 2046.25 ms / 388 tokens 4.01.845.934 I slot print_timing: id 0 | task 13656 | graphs reused = 13340 4.01.845.935 I slot print_timing: id 0 | task 13656 | graph reallocs = 0 / 0 (same size) / (changed size) 4.01.845.964 I slot release: id 0 | task 13656 | stop processing: n_tokens = 387, truncated = 0 4.01.849.619 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 387, t_last = 337170231678 4.01.850.677 I slot launch_slot_: id 0 | task 13767 | processing task, is_child = 0 4.04.133.315 I slot print_timing: id 0 | task 13767 | prompt eval time = 481.90 ms / 319 tokens ( 1.51 ms per token, 661.96 tokens per second) 4.04.133.318 I slot print_timing: id 0 | task 13767 | eval time = 1800.73 ms / 122 tokens ( 14.88 ms per token, 67.20 tokens per second) 4.04.133.319 I slot print_timing: id 0 | task 13767 | total time = 2282.63 ms / 441 tokens 4.04.133.319 I slot print_timing: id 0 | task 13767 | graphs reused = 13460 4.04.133.320 I slot print_timing: id 0 | task 13767 | graph reallocs = 0 / 0 (same size) / (changed size) 4.04.133.351 I slot release: id 0 | task 13767 | stop processing: n_tokens = 440, truncated = 0 4.04.137.170 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 440, t_last = 337172519065 4.04.138.289 I slot launch_slot_: id 0 | task 13891 | processing task, is_child = 0 4.06.100.791 I slot print_timing: id 0 | task 13891 | prompt eval time = 509.94 ms / 345 tokens ( 1.48 ms per token, 676.55 tokens per second) 4.06.100.795 I slot print_timing: id 0 | task 13891 | eval time = 1452.56 ms / 99 tokens ( 14.82 ms per token, 67.47 tokens per second) 4.06.100.795 I slot print_timing: id 0 | task 13891 | total time = 1962.49 ms / 444 tokens 4.06.100.796 I slot print_timing: id 0 | task 13891 | graphs reused = 13557 4.06.100.797 I slot print_timing: id 0 | task 13891 | graph reallocs = 0 / 0 (same size) / (changed size) 4.06.100.829 I slot release: id 0 | task 13891 | stop processing: n_tokens = 443, truncated = 0 4.06.104.863 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 443, t_last = 337174486543 4.06.106.081 I slot launch_slot_: id 0 | task 13992 | processing task, is_child = 0 4.08.588.709 I slot print_timing: id 0 | task 13992 | prompt eval time = 633.26 ms / 464 tokens ( 1.36 ms per token, 732.71 tokens per second) 4.08.588.712 I slot print_timing: id 0 | task 13992 | eval time = 1849.36 ms / 125 tokens ( 14.91 ms per token, 67.05 tokens per second) 4.08.588.713 I slot print_timing: id 0 | task 13992 | total time = 2482.62 ms / 589 tokens 4.08.588.713 I slot print_timing: id 0 | task 13992 | graphs reused = 13679 4.08.588.714 I slot print_timing: id 0 | task 13992 | graph reallocs = 0 / 0 (same size) / (changed size) 4.08.588.754 I slot release: id 0 | task 13992 | stop processing: n_tokens = 588, truncated = 0 4.08.592.649 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 588, t_last = 337176974468 4.08.594.124 I slot launch_slot_: id 0 | task 14119 | processing task, is_child = 0 4.10.644.279 I slot print_timing: id 0 | task 14119 | prompt eval time = 566.57 ms / 398 tokens ( 1.42 ms per token, 702.48 tokens per second) 4.10.644.282 I slot print_timing: id 0 | task 14119 | eval time = 1483.58 ms / 101 tokens ( 14.84 ms per token, 67.40 tokens per second) 4.10.644.283 I slot print_timing: id 0 | task 14119 | total time = 2050.14 ms / 499 tokens 4.10.644.283 I slot print_timing: id 0 | task 14119 | graphs reused = 13778 4.10.644.284 I slot print_timing: id 0 | task 14119 | graph reallocs = 0 / 0 (same size) / (changed size) 4.10.644.319 I slot release: id 0 | task 14119 | stop processing: n_tokens = 498, truncated = 0 4.10.648.723 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 498, t_last = 337179030033 4.10.649.986 I slot launch_slot_: id 0 | task 14222 | processing task, is_child = 0 4.14.602.051 I slot print_timing: id 0 | task 14222 | n_gen = 203, tg = 67.12 t/s, tg_3s = 67.45 t/s 4.15.357.796 I slot print_timing: id 0 | task 14222 | prompt eval time = 942.58 ms / 628 tokens ( 1.50 ms per token, 666.25 tokens per second) 4.15.357.800 I slot print_timing: id 0 | task 14222 | eval time = 3765.22 ms / 254 tokens ( 14.88 ms per token, 67.19 tokens per second) 4.15.357.800 I slot print_timing: id 0 | task 14222 | total time = 4707.80 ms / 882 tokens 4.15.357.801 I slot print_timing: id 0 | task 14222 | graphs reused = 14029 4.15.357.802 I slot print_timing: id 0 | task 14222 | graph reallocs = 0 / 0 (same size) / (changed size) 4.15.357.847 I slot release: id 0 | task 14222 | stop processing: n_tokens = 881, truncated = 0 4.15.361.824 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 881, t_last = 337183743561 4.15.363.687 I slot launch_slot_: id 0 | task 14479 | processing task, is_child = 0 4.17.330.782 I slot print_timing: id 0 | task 14479 | prompt eval time = 571.14 ms / 404 tokens ( 1.41 ms per token, 707.36 tokens per second) 4.17.330.786 I slot print_timing: id 0 | task 14479 | eval time = 1395.94 ms / 95 tokens ( 14.85 ms per token, 67.34 tokens per second) 4.17.330.787 I slot print_timing: id 0 | task 14479 | total time = 1967.08 ms / 499 tokens 4.17.330.787 I slot print_timing: id 0 | task 14479 | graphs reused = 14122 4.17.330.788 I slot print_timing: id 0 | task 14479 | graph reallocs = 0 / 0 (same size) / (changed size) 4.17.330.823 I slot release: id 0 | task 14479 | stop processing: n_tokens = 498, truncated = 0 4.17.334.776 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 498, t_last = 337185716537 4.17.336.071 I slot launch_slot_: id 0 | task 14576 | processing task, is_child = 0 4.20.956.651 I slot print_timing: id 0 | task 14576 | n_gen = 204, tg = 67.40 t/s, tg_3s = 67.73 t/s 4.22.933.102 I slot print_timing: id 0 | task 14576 | prompt eval time = 608.72 ms / 445 tokens ( 1.37 ms per token, 731.04 tokens per second) 4.22.933.108 I slot print_timing: id 0 | task 14576 | eval time = 4988.31 ms / 337 tokens ( 14.85 ms per token, 67.36 tokens per second) 4.22.933.108 I slot print_timing: id 0 | task 14576 | total time = 5597.02 ms / 782 tokens 4.22.933.109 I slot print_timing: id 0 | task 14576 | graphs reused = 14455 4.22.933.109 I slot print_timing: id 0 | task 14576 | graph reallocs = 0 / 0 (same size) / (changed size) 4.22.933.149 I slot release: id 0 | task 14576 | stop processing: n_tokens = 781, truncated = 0 4.22.937.282 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 781, t_last = 337191318863 4.22.939.218 I slot launch_slot_: id 0 | task 14915 | processing task, is_child = 0 4.26.523.374 I slot print_timing: id 0 | task 14915 | n_gen = 202, tg = 66.81 t/s, tg_3s = 67.14 t/s 4.27.597.968 I slot print_timing: id 0 | task 14915 | prompt eval time = 575.65 ms / 412 tokens ( 1.40 ms per token, 715.71 tokens per second) 4.27.597.971 I slot print_timing: id 0 | task 14915 | eval time = 4083.09 ms / 274 tokens ( 14.96 ms per token, 66.86 tokens per second) 4.27.597.972 I slot print_timing: id 0 | task 14915 | total time = 4658.74 ms / 686 tokens 4.27.597.973 I slot print_timing: id 0 | task 14915 | graphs reused = 14726 4.27.597.973 I slot print_timing: id 0 | task 14915 | graph reallocs = 0 / 0 (same size) / (changed size) 4.27.598.012 I slot release: id 0 | task 14915 | stop processing: n_tokens = 685, truncated = 0 4.27.602.915 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 685, t_last = 337195983726 4.27.604.611 I slot launch_slot_: id 0 | task 15191 | processing task, is_child = 0 4.29.603.044 I slot print_timing: id 0 | task 15191 | prompt eval time = 824.66 ms / 542 tokens ( 1.52 ms per token, 657.24 tokens per second) 4.29.603.050 I slot print_timing: id 0 | task 15191 | eval time = 1173.76 ms / 80 tokens ( 14.86 ms per token, 67.30 tokens per second) 4.29.603.051 I slot print_timing: id 0 | task 15191 | total time = 1998.43 ms / 622 tokens 4.29.603.051 I slot print_timing: id 0 | task 15191 | graphs reused = 14804 4.29.603.052 I slot print_timing: id 0 | task 15191 | graph reallocs = 0 / 0 (same size) / (changed size) 4.29.603.091 I slot release: id 0 | task 15191 | stop processing: n_tokens = 621, truncated = 0 4.29.607.375 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 621, t_last = 337197988805 4.29.608.831 I slot launch_slot_: id 0 | task 15274 | processing task, is_child = 0 4.33.163.925 I slot print_timing: id 0 | task 15274 | prompt eval time = 935.05 ms / 628 tokens ( 1.49 ms per token, 671.62 tokens per second) 4.33.163.930 I slot print_timing: id 0 | task 15274 | eval time = 2620.03 ms / 177 tokens ( 14.89 ms per token, 67.17 tokens per second) 4.33.163.931 I slot print_timing: id 0 | task 15274 | total time = 3555.09 ms / 805 tokens 4.33.163.932 I slot print_timing: id 0 | task 15274 | graphs reused = 14978 4.33.163.932 I slot print_timing: id 0 | task 15274 | graph reallocs = 0 / 0 (same size) / (changed size) 4.33.163.977 I slot release: id 0 | task 15274 | stop processing: n_tokens = 804, truncated = 0 4.33.167.339 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 4.33.169.111 I slot launch_slot_: id 0 | task 15454 | processing task, is_child = 0 4.36.554.211 I slot print_timing: id 0 | task 15454 | n_gen = 204, tg = 67.41 t/s, tg_3s = 67.75 t/s 4.36.568.949 I slot print_timing: id 0 | task 15454 | prompt eval time = 373.81 ms / 197 tokens ( 1.90 ms per token, 527.01 tokens per second) 4.36.568.955 I slot print_timing: id 0 | task 15454 | eval time = 3026.02 ms / 205 tokens ( 14.83 ms per token, 67.42 tokens per second) 4.36.568.956 I slot print_timing: id 0 | task 15454 | total time = 3399.82 ms / 402 tokens 4.36.568.956 I slot print_timing: id 0 | task 15454 | graphs reused = 15180 4.36.568.957 I slot print_timing: id 0 | task 15454 | graph reallocs = 0 / 0 (same size) / (changed size) 4.36.568.978 I slot release: id 0 | task 15454 | stop processing: n_tokens = 401, truncated = 0 4.36.572.443 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 401, t_last = 337204954692 4.36.573.428 I slot launch_slot_: id 0 | task 15661 | processing task, is_child = 0 4.38.651.244 I slot print_timing: id 0 | task 15661 | prompt eval time = 386.38 ms / 217 tokens ( 1.78 ms per token, 561.62 tokens per second) 4.38.651.246 I slot print_timing: id 0 | task 15661 | eval time = 1691.43 ms / 115 tokens ( 14.84 ms per token, 67.40 tokens per second) 4.38.651.247 I slot print_timing: id 0 | task 15661 | total time = 2077.81 ms / 332 tokens 4.38.651.248 I slot print_timing: id 0 | task 15661 | graphs reused = 15292 4.38.651.248 I slot print_timing: id 0 | task 15661 | graph reallocs = 0 / 0 (same size) / (changed size) 4.38.651.273 I slot release: id 0 | task 15661 | stop processing: n_tokens = 331, truncated = 0 4.38.654.673 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.105 (> 0.100 thold), f_keep = 0.063 4.38.655.112 I slot launch_slot_: id 0 | task 15778 | processing task, is_child = 0 4.42.045.567 I slot print_timing: id 0 | task 15778 | n_gen = 204, tg = 67.38 t/s, tg_3s = 67.71 t/s 4.42.565.998 I slot print_timing: id 0 | task 15778 | prompt eval time = 377.75 ms / 200 tokens ( 1.89 ms per token, 529.45 tokens per second) 4.42.566.004 I slot print_timing: id 0 | task 15778 | eval time = 3533.13 ms / 239 tokens ( 14.85 ms per token, 67.36 tokens per second) 4.42.566.005 I slot print_timing: id 0 | task 15778 | total time = 3910.88 ms / 439 tokens 4.42.566.006 I slot print_timing: id 0 | task 15778 | graphs reused = 15528 4.42.566.006 I slot print_timing: id 0 | task 15778 | graph reallocs = 0 / 0 (same size) / (changed size) 4.42.566.033 I slot release: id 0 | task 15778 | stop processing: n_tokens = 438, truncated = 0 4.42.569.510 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.124 (> 0.100 thold), f_keep = 0.048 4.42.570.573 I slot launch_slot_: id 0 | task 16019 | processing task, is_child = 0 4.45.930.577 I slot print_timing: id 0 | task 16019 | n_gen = 204, tg = 67.42 t/s, tg_3s = 67.75 t/s 4.47.133.562 I slot print_timing: id 0 | task 16019 | prompt eval time = 348.82 ms / 170 tokens ( 2.05 ms per token, 487.36 tokens per second) 4.47.133.568 I slot print_timing: id 0 | task 16019 | eval time = 4214.16 ms / 285 tokens ( 14.84 ms per token, 67.39 tokens per second) 4.47.133.569 I slot print_timing: id 0 | task 16019 | total time = 4562.98 ms / 455 tokens 4.47.133.570 I slot print_timing: id 0 | task 16019 | graphs reused = 15810 4.47.133.570 I slot print_timing: id 0 | task 16019 | graph reallocs = 0 / 0 (same size) / (changed size) 4.47.133.593 I slot release: id 0 | task 16019 | stop processing: n_tokens = 454, truncated = 0 4.47.137.267 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 454, t_last = 337215519307 4.47.138.438 I slot launch_slot_: id 0 | task 16306 | processing task, is_child = 0 4.50.564.327 I slot print_timing: id 0 | task 16306 | n_gen = 204, tg = 67.39 t/s, tg_3s = 67.72 t/s 4.53.564.818 I slot print_timing: id 0 | task 16306 | n_gen = 406, tg = 67.35 t/s, tg_3s = 67.32 t/s 4.56.565.276 I slot print_timing: id 0 | task 16306 | n_gen = 608, tg = 67.34 t/s, tg_3s = 67.32 t/s 4.56.669.096 I slot print_timing: id 0 | task 16306 | prompt eval time = 413.44 ms / 241 tokens ( 1.72 ms per token, 582.92 tokens per second) 4.56.669.100 I slot print_timing: id 0 | task 16306 | eval time = 9117.21 ms / 615 tokens ( 14.85 ms per token, 67.35 tokens per second) 4.56.669.101 I slot print_timing: id 0 | task 16306 | total time = 9530.65 ms / 856 tokens 4.56.669.102 I slot print_timing: id 0 | task 16306 | graphs reused = 16420 4.56.669.102 I slot print_timing: id 0 | task 16306 | graph reallocs = 0 / 0 (same size) / (changed size) 4.56.669.126 I slot release: id 0 | task 16306 | stop processing: n_tokens = 855, truncated = 0 4.56.672.616 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 855, t_last = 337225054840 4.56.674.552 I slot launch_slot_: id 0 | task 16923 | processing task, is_child = 0 5.00.088.079 I slot print_timing: id 0 | task 16923 | n_gen = 204, tg = 67.63 t/s, tg_3s = 67.96 t/s 5.01.093.171 I slot print_timing: id 0 | task 16923 | prompt eval time = 411.88 ms / 237 tokens ( 1.74 ms per token, 575.41 tokens per second) 5.01.093.177 I slot print_timing: id 0 | task 16923 | eval time = 4006.73 ms / 272 tokens ( 14.78 ms per token, 67.64 tokens per second) 5.01.093.178 I slot print_timing: id 0 | task 16923 | total time = 4418.61 ms / 509 tokens 5.01.093.178 I slot print_timing: id 0 | task 16923 | graphs reused = 16689 5.01.093.179 I slot print_timing: id 0 | task 16923 | graph reallocs = 0 / 0 (same size) / (changed size) 5.01.093.203 I slot release: id 0 | task 16923 | stop processing: n_tokens = 508, truncated = 0 5.01.096.762 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 508, t_last = 337229478917 5.01.097.972 I slot launch_slot_: id 0 | task 17197 | processing task, is_child = 0 5.04.591.735 I slot print_timing: id 0 | task 17197 | n_gen = 204, tg = 67.47 t/s, tg_3s = 67.80 t/s 5.06.428.017 I slot print_timing: id 0 | task 17197 | prompt eval time = 485.02 ms / 322 tokens ( 1.51 ms per token, 663.88 tokens per second) 5.06.428.020 I slot print_timing: id 0 | task 17197 | eval time = 4845.01 ms / 328 tokens ( 14.82 ms per token, 67.49 tokens per second) 5.06.428.021 I slot print_timing: id 0 | task 17197 | total time = 5330.03 ms / 650 tokens 5.06.428.022 I slot print_timing: id 0 | task 17197 | graphs reused = 17014 5.06.428.022 I slot print_timing: id 0 | task 17197 | graph reallocs = 0 / 0 (same size) / (changed size) 5.06.428.055 I slot release: id 0 | task 17197 | stop processing: n_tokens = 649, truncated = 0 5.06.431.442 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 5.06.432.935 I slot launch_slot_: id 0 | task 17527 | processing task, is_child = 0 5.09.787.250 I slot print_timing: id 0 | task 17527 | n_gen = 203, tg = 67.26 t/s, tg_3s = 67.60 t/s 5.10.751.998 I slot print_timing: id 0 | task 17527 | prompt eval time = 351.22 ms / 175 tokens ( 2.01 ms per token, 498.26 tokens per second) 5.10.752.001 I slot print_timing: id 0 | task 17527 | eval time = 3967.83 ms / 268 tokens ( 14.86 ms per token, 67.29 tokens per second) 5.10.752.002 I slot print_timing: id 0 | task 17527 | total time = 4319.05 ms / 443 tokens 5.10.752.002 I slot print_timing: id 0 | task 17527 | graphs reused = 17279 5.10.752.003 I slot print_timing: id 0 | task 17527 | graph reallocs = 0 / 0 (same size) / (changed size) 5.10.752.026 I slot release: id 0 | task 17527 | stop processing: n_tokens = 442, truncated = 0 5.10.755.449 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.117 (> 0.100 thold), f_keep = 0.048 5.10.756.579 I slot launch_slot_: id 0 | task 17797 | processing task, is_child = 0 5.14.125.876 I slot print_timing: id 0 | task 17797 | n_gen = 204, tg = 67.38 t/s, tg_3s = 67.71 t/s 5.14.881.677 I slot print_timing: id 0 | task 17797 | prompt eval time = 356.43 ms / 179 tokens ( 1.99 ms per token, 502.20 tokens per second) 5.14.881.684 I slot print_timing: id 0 | task 17797 | eval time = 3768.66 ms / 255 tokens ( 14.84 ms per token, 67.40 tokens per second) 5.14.881.684 I slot print_timing: id 0 | task 17797 | total time = 4125.09 ms / 434 tokens 5.14.881.685 I slot print_timing: id 0 | task 17797 | graphs reused = 17531 5.14.881.685 I slot print_timing: id 0 | task 17797 | graph reallocs = 0 / 0 (same size) / (changed size) 5.14.881.706 I slot release: id 0 | task 17797 | stop processing: n_tokens = 433, truncated = 0 5.14.884.862 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 433, t_last = 337243267420 5.14.886.113 I slot launch_slot_: id 0 | task 18054 | processing task, is_child = 0 5.18.298.897 I slot print_timing: id 0 | task 18054 | n_gen = 204, tg = 67.54 t/s, tg_3s = 67.87 t/s 5.18.818.447 I slot print_timing: id 0 | task 18054 | prompt eval time = 407.23 ms / 237 tokens ( 1.72 ms per token, 581.98 tokens per second) 5.18.818.453 I slot print_timing: id 0 | task 18054 | eval time = 3525.10 ms / 239 tokens ( 14.81 ms per token, 67.52 tokens per second) 5.18.818.454 I slot print_timing: id 0 | task 18054 | total time = 3932.33 ms / 476 tokens 5.18.818.455 I slot print_timing: id 0 | task 18054 | graphs reused = 17767 5.18.818.455 I slot print_timing: id 0 | task 18054 | graph reallocs = 0 / 0 (same size) / (changed size) 5.18.818.479 I slot release: id 0 | task 18054 | stop processing: n_tokens = 475, truncated = 0 5.18.821.929 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 475, t_last = 337247204193 5.18.823.099 I slot launch_slot_: id 0 | task 18295 | processing task, is_child = 0 5.22.282.134 I slot print_timing: id 0 | task 18295 | n_gen = 204, tg = 67.49 t/s, tg_3s = 67.82 t/s 5.22.326.571 I slot print_timing: id 0 | task 18295 | prompt eval time = 450.97 ms / 287 tokens ( 1.57 ms per token, 636.41 tokens per second) 5.22.326.573 I slot print_timing: id 0 | task 18295 | eval time = 3052.50 ms / 207 tokens ( 14.82 ms per token, 67.49 tokens per second) 5.22.326.574 I slot print_timing: id 0 | task 18295 | total time = 3503.47 ms / 494 tokens 5.22.326.574 I slot print_timing: id 0 | task 18295 | graphs reused = 17972 5.22.326.575 I slot print_timing: id 0 | task 18295 | graph reallocs = 0 / 0 (same size) / (changed size) 5.22.326.602 I slot release: id 0 | task 18295 | stop processing: n_tokens = 493, truncated = 0 5.22.329.992 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.148 (> 0.100 thold), f_keep = 0.073 5.22.331.220 I slot launch_slot_: id 0 | task 18504 | processing task, is_child = 0 5.25.749.622 I slot print_timing: id 0 | task 18504 | n_gen = 203, tg = 67.25 t/s, tg_3s = 67.59 t/s 5.26.123.326 I slot print_timing: id 0 | task 18504 | prompt eval time = 414.89 ms / 243 tokens ( 1.71 ms per token, 585.69 tokens per second) 5.26.123.329 I slot print_timing: id 0 | task 18504 | eval time = 3377.21 ms / 228 tokens ( 14.88 ms per token, 67.22 tokens per second) 5.26.123.330 I slot print_timing: id 0 | task 18504 | total time = 3792.10 ms / 471 tokens 5.26.123.330 I slot print_timing: id 0 | task 18504 | graphs reused = 18197 5.26.123.331 I slot print_timing: id 0 | task 18504 | graph reallocs = 0 / 0 (same size) / (changed size) 5.26.123.357 I slot release: id 0 | task 18504 | stop processing: n_tokens = 470, truncated = 0 5.26.126.808 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 337254509071 5.26.128.041 I slot launch_slot_: id 0 | task 18734 | processing task, is_child = 0 5.29.549.201 I slot print_timing: id 0 | task 18734 | n_gen = 204, tg = 67.52 t/s, tg_3s = 67.86 t/s 5.30.696.250 I slot print_timing: id 0 | task 18734 | prompt eval time = 414.74 ms / 243 tokens ( 1.71 ms per token, 585.91 tokens per second) 5.30.696.254 I slot print_timing: id 0 | task 18734 | eval time = 4153.46 ms / 281 tokens ( 14.83 ms per token, 67.41 tokens per second) 5.30.696.254 I slot print_timing: id 0 | task 18734 | total time = 4568.20 ms / 524 tokens 5.30.696.255 I slot print_timing: id 0 | task 18734 | graphs reused = 18474 5.30.696.256 I slot print_timing: id 0 | task 18734 | graph reallocs = 0 / 0 (same size) / (changed size) 5.30.696.280 I slot release: id 0 | task 18734 | stop processing: n_tokens = 523, truncated = 0 5.30.699.903 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 523, t_last = 337259081994 5.30.701.192 I slot launch_slot_: id 0 | task 19017 | processing task, is_child = 0 5.34.141.447 I slot print_timing: id 0 | task 19017 | n_gen = 204, tg = 67.54 t/s, tg_3s = 67.87 t/s 5.34.764.854 I slot print_timing: id 0 | task 19017 | prompt eval time = 434.57 ms / 262 tokens ( 1.66 ms per token, 602.89 tokens per second) 5.34.764.861 I slot print_timing: id 0 | task 19017 | eval time = 3629.09 ms / 246 tokens ( 14.81 ms per token, 67.51 tokens per second) 5.34.764.862 I slot print_timing: id 0 | task 19017 | total time = 4063.66 ms / 508 tokens 5.34.764.863 I slot print_timing: id 0 | task 19017 | graphs reused = 18718 5.34.764.863 I slot print_timing: id 0 | task 19017 | graph reallocs = 0 / 0 (same size) / (changed size) 5.34.764.888 I slot release: id 0 | task 19017 | stop processing: n_tokens = 507, truncated = 0 5.34.768.158 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.102 (> 0.100 thold), f_keep = 0.041 5.34.769.317 I slot launch_slot_: id 0 | task 19265 | processing task, is_child = 0 5.37.753.163 I slot print_timing: id 0 | task 19265 | prompt eval time = 379.99 ms / 205 tokens ( 1.85 ms per token, 539.49 tokens per second) 5.37.753.169 I slot print_timing: id 0 | task 19265 | eval time = 2603.85 ms / 176 tokens ( 14.88 ms per token, 67.21 tokens per second) 5.37.753.169 I slot print_timing: id 0 | task 19265 | total time = 2983.84 ms / 381 tokens 5.37.753.170 I slot print_timing: id 0 | task 19265 | graphs reused = 18891 5.37.753.171 I slot print_timing: id 0 | task 19265 | graph reallocs = 0 / 0 (same size) / (changed size) 5.37.753.192 I slot release: id 0 | task 19265 | stop processing: n_tokens = 380, truncated = 0 5.37.756.780 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 380, t_last = 337266138906 5.37.757.781 I slot launch_slot_: id 0 | task 19443 | processing task, is_child = 0 5.41.153.539 I slot print_timing: id 0 | task 19443 | prompt eval time = 447.34 ms / 279 tokens ( 1.60 ms per token, 623.69 tokens per second) 5.41.153.544 I slot print_timing: id 0 | task 19443 | eval time = 2948.41 ms / 200 tokens ( 14.82 ms per token, 67.49 tokens per second) 5.41.153.546 I slot print_timing: id 0 | task 19443 | total time = 3395.74 ms / 479 tokens 5.41.153.546 I slot print_timing: id 0 | task 19443 | graphs reused = 19089 5.41.153.547 I slot print_timing: id 0 | task 19443 | graph reallocs = 0 / 0 (same size) / (changed size) 5.41.153.573 I slot release: id 0 | task 19443 | stop processing: n_tokens = 478, truncated = 0 5.41.156.984 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 5.41.158.238 I slot launch_slot_: id 0 | task 19645 | processing task, is_child = 0 5.44.530.563 I slot print_timing: id 0 | task 19645 | n_gen = 204, tg = 67.43 t/s, tg_3s = 67.76 t/s 5.46.442.653 I slot print_timing: id 0 | task 19645 | prompt eval time = 361.70 ms / 194 tokens ( 1.86 ms per token, 536.35 tokens per second) 5.46.442.659 I slot print_timing: id 0 | task 19645 | eval time = 4922.71 ms / 333 tokens ( 14.83 ms per token, 67.44 tokens per second) 5.46.442.659 I slot print_timing: id 0 | task 19645 | total time = 5284.41 ms / 527 tokens 5.46.442.660 I slot print_timing: id 0 | task 19645 | graphs reused = 19418 5.46.442.661 I slot print_timing: id 0 | task 19645 | graph reallocs = 0 / 0 (same size) / (changed size) 5.46.442.686 I slot release: id 0 | task 19645 | stop processing: n_tokens = 526, truncated = 0 5.46.445.972 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.124 (> 0.100 thold), f_keep = 0.040 5.46.447.269 I slot launch_slot_: id 0 | task 19980 | processing task, is_child = 0 5.49.391.465 I slot print_timing: id 0 | task 19980 | prompt eval time = 349.10 ms / 169 tokens ( 2.07 ms per token, 484.11 tokens per second) 5.49.391.468 I slot print_timing: id 0 | task 19980 | eval time = 2595.09 ms / 175 tokens ( 14.91 ms per token, 67.05 tokens per second) 5.49.391.469 I slot print_timing: id 0 | task 19980 | total time = 2944.19 ms / 344 tokens 5.49.391.469 I slot print_timing: id 0 | task 19980 | graphs reused = 19590 5.49.391.470 I slot print_timing: id 0 | task 19980 | graph reallocs = 0 / 0 (same size) / (changed size) 5.49.391.491 I slot release: id 0 | task 19980 | stop processing: n_tokens = 343, truncated = 0 5.49.394.940 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 343, t_last = 337277777205 5.49.396.117 I slot launch_slot_: id 0 | task 20157 | processing task, is_child = 0 5.52.845.878 I slot print_timing: id 0 | task 20157 | n_gen = 204, tg = 67.38 t/s, tg_3s = 67.71 t/s 5.53.781.443 I slot print_timing: id 0 | task 20157 | prompt eval time = 436.91 ms / 263 tokens ( 1.66 ms per token, 601.95 tokens per second) 5.53.781.450 I slot print_timing: id 0 | task 20157 | eval time = 3948.40 ms / 267 tokens ( 14.84 ms per token, 67.37 tokens per second) 5.53.781.450 I slot print_timing: id 0 | task 20157 | total time = 4385.31 ms / 530 tokens 5.53.781.451 I slot print_timing: id 0 | task 20157 | graphs reused = 19854 5.53.781.452 I slot print_timing: id 0 | task 20157 | graph reallocs = 0 / 0 (same size) / (changed size) 5.53.781.478 I slot release: id 0 | task 20157 | stop processing: n_tokens = 529, truncated = 0 5.53.784.903 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.103 (> 0.100 thold), f_keep = 0.040 5.53.786.115 I slot launch_slot_: id 0 | task 20426 | processing task, is_child = 0 5.56.674.803 I slot print_timing: id 0 | task 20426 | prompt eval time = 380.06 ms / 204 tokens ( 1.86 ms per token, 536.76 tokens per second) 5.56.674.809 I slot print_timing: id 0 | task 20426 | eval time = 2508.62 ms / 170 tokens ( 14.84 ms per token, 67.37 tokens per second) 5.56.674.810 I slot print_timing: id 0 | task 20426 | total time = 2888.68 ms / 374 tokens 5.56.674.811 I slot print_timing: id 0 | task 20426 | graphs reused = 20021 5.56.674.811 I slot print_timing: id 0 | task 20426 | graph reallocs = 0 / 0 (same size) / (changed size) 5.56.674.835 I slot release: id 0 | task 20426 | stop processing: n_tokens = 373, truncated = 0 5.56.678.194 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 373, t_last = 337285060549 5.56.679.116 I slot launch_slot_: id 0 | task 20598 | processing task, is_child = 0 6.00.127.572 I slot print_timing: id 0 | task 20598 | n_gen = 204, tg = 67.52 t/s, tg_3s = 67.85 t/s 6.02.878.397 I slot print_timing: id 0 | task 20598 | prompt eval time = 441.90 ms / 272 tokens ( 1.62 ms per token, 615.52 tokens per second) 6.02.878.400 I slot print_timing: id 0 | task 20598 | eval time = 5757.37 ms / 389 tokens ( 14.84 ms per token, 67.39 tokens per second) 6.02.878.400 I slot print_timing: id 0 | task 20598 | total time = 6199.27 ms / 661 tokens 6.02.878.401 I slot print_timing: id 0 | task 20598 | graphs reused = 20407 6.02.878.402 I slot print_timing: id 0 | task 20598 | graph reallocs = 0 / 0 (same size) / (changed size) 6.02.878.429 I slot release: id 0 | task 20598 | stop processing: n_tokens = 660, truncated = 0 6.02.881.962 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 660, t_last = 337291264143 6.02.883.559 I slot launch_slot_: id 0 | task 20989 | processing task, is_child = 0 6.05.535.950 I slot print_timing: id 0 | task 20989 | prompt eval time = 407.67 ms / 231 tokens ( 1.76 ms per token, 566.64 tokens per second) 6.05.535.953 I slot print_timing: id 0 | task 20989 | eval time = 2244.72 ms / 152 tokens ( 14.87 ms per token, 67.27 tokens per second) 6.05.535.954 I slot print_timing: id 0 | task 20989 | total time = 2652.38 ms / 383 tokens 6.05.535.954 I slot print_timing: id 0 | task 20989 | graphs reused = 20556 6.05.535.955 I slot print_timing: id 0 | task 20989 | graph reallocs = 0 / 0 (same size) / (changed size) 6.05.535.987 I slot release: id 0 | task 20989 | stop processing: n_tokens = 382, truncated = 0 6.05.539.896 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 382, t_last = 337293921701 6.05.540.857 I slot launch_slot_: id 0 | task 21143 | processing task, is_child = 0 6.08.996.267 I slot print_timing: id 0 | task 21143 | n_gen = 203, tg = 67.33 t/s, tg_3s = 67.66 t/s 6.09.218.168 I slot print_timing: id 0 | task 21143 | prompt eval time = 455.22 ms / 291 tokens ( 1.56 ms per token, 639.25 tokens per second) 6.09.218.174 I slot print_timing: id 0 | task 21143 | eval time = 3222.08 ms / 218 tokens ( 14.85 ms per token, 67.35 tokens per second) 6.09.218.175 I slot print_timing: id 0 | task 21143 | total time = 3677.30 ms / 509 tokens 6.09.218.175 I slot print_timing: id 0 | task 21143 | graphs reused = 20772 6.09.218.176 I slot print_timing: id 0 | task 21143 | graph reallocs = 0 / 0 (same size) / (changed size) 6.09.218.206 I slot release: id 0 | task 21143 | stop processing: n_tokens = 508, truncated = 0 6.09.221.645 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 508, t_last = 337297603920 6.09.222.800 I slot launch_slot_: id 0 | task 21363 | processing task, is_child = 0 6.12.679.892 I slot print_timing: id 0 | task 21363 | n_gen = 204, tg = 67.51 t/s, tg_3s = 67.84 t/s 6.12.975.414 I slot print_timing: id 0 | task 21363 | prompt eval time = 450.00 ms / 285 tokens ( 1.58 ms per token, 633.33 tokens per second) 6.12.975.420 I slot print_timing: id 0 | task 21363 | eval time = 3302.61 ms / 224 tokens ( 14.81 ms per token, 67.52 tokens per second) 6.12.975.420 I slot print_timing: id 0 | task 21363 | total time = 3752.61 ms / 509 tokens 6.12.975.421 I slot print_timing: id 0 | task 21363 | graphs reused = 20994 6.12.975.422 I slot print_timing: id 0 | task 21363 | graph reallocs = 0 / 0 (same size) / (changed size) 6.12.975.452 I slot release: id 0 | task 21363 | stop processing: n_tokens = 508, truncated = 0 6.12.978.940 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 508, t_last = 337301361166 6.12.980.134 I slot launch_slot_: id 0 | task 21589 | processing task, is_child = 0 6.16.446.637 I slot print_timing: id 0 | task 21589 | n_gen = 204, tg = 67.36 t/s, tg_3s = 67.69 t/s 6.19.456.581 I slot print_timing: id 0 | task 21589 | n_gen = 407, tg = 67.40 t/s, tg_3s = 67.44 t/s 6.20.481.462 I slot print_timing: id 0 | task 21589 | prompt eval time = 452.95 ms / 289 tokens ( 1.57 ms per token, 638.04 tokens per second) 6.20.481.468 I slot print_timing: id 0 | task 21589 | eval time = 7048.37 ms / 476 tokens ( 14.84 ms per token, 67.39 tokens per second) 6.20.481.468 I slot print_timing: id 0 | task 21589 | total time = 7501.32 ms / 765 tokens 6.20.481.469 I slot print_timing: id 0 | task 21589 | graphs reused = 21467 6.20.481.470 I slot print_timing: id 0 | task 21589 | graph reallocs = 0 / 0 (same size) / (changed size) 6.20.481.496 I slot release: id 0 | task 21589 | stop processing: n_tokens = 764, truncated = 0 6.20.485.416 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 764, t_last = 337308867210 6.20.487.613 I slot launch_slot_: id 0 | task 22067 | processing task, is_child = 0 6.23.900.388 I slot print_timing: id 0 | task 22067 | n_gen = 203, tg = 67.32 t/s, tg_3s = 67.65 t/s 6.24.063.464 I slot print_timing: id 0 | task 22067 | prompt eval time = 412.09 ms / 242 tokens ( 1.70 ms per token, 587.25 tokens per second) 6.24.063.470 I slot print_timing: id 0 | task 22067 | eval time = 3163.75 ms / 214 tokens ( 14.85 ms per token, 67.33 tokens per second) 6.24.063.470 I slot print_timing: id 0 | task 22067 | total time = 3575.84 ms / 456 tokens 6.24.063.471 I slot print_timing: id 0 | task 22067 | graphs reused = 21678 6.24.063.472 I slot print_timing: id 0 | task 22067 | graph reallocs = 0 / 0 (same size) / (changed size) 6.24.063.496 I slot release: id 0 | task 22067 | stop processing: n_tokens = 455, truncated = 0 6.24.066.878 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.118 (> 0.100 thold), f_keep = 0.046 6.24.068.069 I slot launch_slot_: id 0 | task 22283 | processing task, is_child = 0 6.27.432.205 I slot print_timing: id 0 | task 22283 | n_gen = 204, tg = 67.45 t/s, tg_3s = 67.78 t/s 6.27.491.453 I slot print_timing: id 0 | task 22283 | prompt eval time = 354.35 ms / 178 tokens ( 1.99 ms per token, 502.32 tokens per second) 6.27.491.459 I slot print_timing: id 0 | task 22283 | eval time = 3069.02 ms / 208 tokens ( 14.83 ms per token, 67.45 tokens per second) 6.27.491.460 I slot print_timing: id 0 | task 22283 | total time = 3423.38 ms / 386 tokens 6.27.491.461 I slot print_timing: id 0 | task 22283 | graphs reused = 21883 6.27.491.461 I slot print_timing: id 0 | task 22283 | graph reallocs = 0 / 0 (same size) / (changed size) 6.27.491.482 I slot release: id 0 | task 22283 | stop processing: n_tokens = 385, truncated = 0 6.27.494.823 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 385, t_last = 337315877196 6.27.495.761 I slot launch_slot_: id 0 | task 22493 | processing task, is_child = 0 6.29.955.888 I slot print_timing: id 0 | task 22493 | prompt eval time = 438.94 ms / 264 tokens ( 1.66 ms per token, 601.45 tokens per second) 6.29.955.894 I slot print_timing: id 0 | task 22493 | eval time = 2021.18 ms / 137 tokens ( 14.86 ms per token, 67.29 tokens per second) 6.29.955.895 I slot print_timing: id 0 | task 22493 | total time = 2460.12 ms / 401 tokens 6.29.955.896 I slot print_timing: id 0 | task 22493 | graphs reused = 22018 6.29.955.896 I slot print_timing: id 0 | task 22493 | graph reallocs = 0 / 0 (same size) / (changed size) 6.29.955.923 I slot release: id 0 | task 22493 | stop processing: n_tokens = 400, truncated = 0 6.29.959.208 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.138 (> 0.100 thold), f_keep = 0.052 6.29.960.244 I slot launch_slot_: id 0 | task 22632 | processing task, is_child = 0 6.32.069.890 I slot print_timing: id 0 | task 22632 | prompt eval time = 331.32 ms / 152 tokens ( 2.18 ms per token, 458.78 tokens per second) 6.32.069.893 I slot print_timing: id 0 | task 22632 | eval time = 1778.32 ms / 120 tokens ( 14.94 ms per token, 66.92 tokens per second) 6.32.069.893 I slot print_timing: id 0 | task 22632 | total time = 2109.64 ms / 272 tokens 6.32.069.894 I slot print_timing: id 0 | task 22632 | graphs reused = 22135 6.32.069.895 I slot print_timing: id 0 | task 22632 | graph reallocs = 0 / 0 (same size) / (changed size) 6.32.069.914 I slot release: id 0 | task 22632 | stop processing: n_tokens = 271, truncated = 0 6.32.073.156 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.108 (> 0.100 thold), f_keep = 0.077 6.32.073.571 I slot launch_slot_: id 0 | task 22754 | processing task, is_child = 0 6.33.926.595 I slot print_timing: id 0 | task 22754 | prompt eval time = 366.94 ms / 194 tokens ( 1.89 ms per token, 528.70 tokens per second) 6.33.926.602 I slot print_timing: id 0 | task 22754 | eval time = 1486.08 ms / 101 tokens ( 14.86 ms per token, 67.29 tokens per second) 6.33.926.602 I slot print_timing: id 0 | task 22754 | total time = 1853.02 ms / 295 tokens 6.33.926.603 I slot print_timing: id 0 | task 22754 | graphs reused = 22233 6.33.926.604 I slot print_timing: id 0 | task 22754 | graph reallocs = 0 / 0 (same size) / (changed size) 6.33.926.628 I slot release: id 0 | task 22754 | stop processing: n_tokens = 294, truncated = 0 6.33.930.228 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 294, t_last = 337322312342 6.33.930.645 I slot launch_slot_: id 0 | task 22857 | processing task, is_child = 0 6.37.382.787 I slot print_timing: id 0 | task 22857 | n_gen = 203, tg = 67.09 t/s, tg_3s = 67.42 t/s 6.38.321.537 I slot print_timing: id 0 | task 22857 | prompt eval time = 441.23 ms / 269 tokens ( 1.64 ms per token, 609.67 tokens per second) 6.38.321.543 I slot print_timing: id 0 | task 22857 | eval time = 3949.65 ms / 266 tokens ( 14.90 ms per token, 67.09 tokens per second) 6.38.321.543 I slot print_timing: id 0 | task 22857 | total time = 4390.88 ms / 535 tokens 6.38.321.544 I slot print_timing: id 0 | task 22857 | graphs reused = 22496 6.38.321.545 I slot print_timing: id 0 | task 22857 | graph reallocs = 0 / 0 (same size) / (changed size) 6.38.321.571 I slot release: id 0 | task 22857 | stop processing: n_tokens = 534, truncated = 0 6.38.325.234 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 534, t_last = 337326707285 6.38.326.456 I slot launch_slot_: id 0 | task 23125 | processing task, is_child = 0 6.41.786.103 I slot print_timing: id 0 | task 23125 | n_gen = 204, tg = 67.44 t/s, tg_3s = 67.78 t/s 6.44.800.132 I slot print_timing: id 0 | task 23125 | n_gen = 407, tg = 67.40 t/s, tg_3s = 67.35 t/s 6.47.813.600 I slot print_timing: id 0 | task 23125 | n_gen = 610, tg = 67.39 t/s, tg_3s = 67.36 t/s 6.50.825.874 I slot print_timing: id 0 | task 23125 | n_gen = 813, tg = 67.39 t/s, tg_3s = 67.39 t/s 6.53.828.455 I slot print_timing: id 0 | task 23125 | n_gen = 1014, tg = 67.30 t/s, tg_3s = 66.94 t/s 6.53.977.541 I slot print_timing: id 0 | task 23125 | prompt eval time = 449.77 ms / 283 tokens ( 1.59 ms per token, 629.21 tokens per second) 6.53.977.544 I slot print_timing: id 0 | task 23125 | eval time = 15201.31 ms / 1024 tokens ( 14.86 ms per token, 67.30 tokens per second) 6.53.977.545 I slot print_timing: id 0 | task 23125 | total time = 15651.08 ms / 1307 tokens 6.53.977.546 I slot print_timing: id 0 | task 23125 | graphs reused = 23514 6.53.977.546 I slot print_timing: id 0 | task 23125 | graph reallocs = 0 / 0 (same size) / (changed size) 6.53.977.576 I slot release: id 0 | task 23125 | stop processing: n_tokens = 1306, truncated = 0 6.53.981.392 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1306, t_last = 337342363290 6.53.984.065 I slot launch_slot_: id 0 | task 24151 | processing task, is_child = 0 6.57.028.494 I slot print_timing: id 0 | task 24151 | prompt eval time = 470.88 ms / 306 tokens ( 1.54 ms per token, 649.84 tokens per second) 6.57.028.497 I slot print_timing: id 0 | task 24151 | eval time = 2573.53 ms / 174 tokens ( 14.88 ms per token, 67.22 tokens per second) 6.57.028.497 I slot print_timing: id 0 | task 24151 | total time = 3044.42 ms / 480 tokens 6.57.028.498 I slot print_timing: id 0 | task 24151 | graphs reused = 23686 6.57.028.499 I slot print_timing: id 0 | task 24151 | graph reallocs = 0 / 0 (same size) / (changed size) 6.57.028.529 I slot release: id 0 | task 24151 | stop processing: n_tokens = 479, truncated = 0 6.57.032.227 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 479, t_last = 337345414243 6.57.033.547 I slot launch_slot_: id 0 | task 24327 | processing task, is_child = 0 6.59.077.263 I slot print_timing: id 0 | task 24327 | prompt eval time = 482.88 ms / 317 tokens ( 1.52 ms per token, 656.48 tokens per second) 6.59.077.269 I slot print_timing: id 0 | task 24327 | eval time = 1560.83 ms / 106 tokens ( 14.87 ms per token, 67.27 tokens per second) 6.59.077.269 I slot print_timing: id 0 | task 24327 | total time = 2043.71 ms / 423 tokens 6.59.077.270 I slot print_timing: id 0 | task 24327 | graphs reused = 23790 6.59.077.271 I slot print_timing: id 0 | task 24327 | graph reallocs = 0 / 0 (same size) / (changed size) 6.59.077.302 I slot release: id 0 | task 24327 | stop processing: n_tokens = 422, truncated = 0 6.59.080.595 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 422, t_last = 337347463016 6.59.081.570 I slot launch_slot_: id 0 | task 24435 | processing task, is_child = 0 7.02.550.235 I slot print_timing: id 0 | task 24435 | n_gen = 203, tg = 67.32 t/s, tg_3s = 67.66 t/s 7.02.792.352 I slot print_timing: id 0 | task 24435 | prompt eval time = 468.21 ms / 296 tokens ( 1.58 ms per token, 632.20 tokens per second) 7.02.792.357 I slot print_timing: id 0 | task 24435 | eval time = 3242.57 ms / 219 tokens ( 14.87 ms per token, 67.23 tokens per second) 7.02.792.359 I slot print_timing: id 0 | task 24435 | total time = 3710.77 ms / 515 tokens 7.02.792.359 I slot print_timing: id 0 | task 24435 | graphs reused = 24006 7.02.792.360 I slot print_timing: id 0 | task 24435 | graph reallocs = 0 / 0 (same size) / (changed size) 7.02.792.387 I slot release: id 0 | task 24435 | stop processing: n_tokens = 514, truncated = 0 7.02.796.215 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 514, t_last = 337351178101 7.02.797.779 I slot launch_slot_: id 0 | task 24656 | processing task, is_child = 0 7.05.892.724 I slot print_timing: id 0 | task 24656 | prompt eval time = 422.53 ms / 254 tokens ( 1.66 ms per token, 601.14 tokens per second) 7.05.892.727 I slot print_timing: id 0 | task 24656 | eval time = 2672.40 ms / 181 tokens ( 14.85 ms per token, 67.36 tokens per second) 7.05.892.727 I slot print_timing: id 0 | task 24656 | total time = 3094.93 ms / 435 tokens 7.05.892.728 I slot print_timing: id 0 | task 24656 | graphs reused = 24184 7.05.892.729 I slot print_timing: id 0 | task 24656 | graph reallocs = 0 / 0 (same size) / (changed size) 7.05.892.754 I slot release: id 0 | task 24656 | stop processing: n_tokens = 434, truncated = 0 7.05.896.090 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.112 (> 0.100 thold), f_keep = 0.048 7.05.897.130 I slot launch_slot_: id 0 | task 24839 | processing task, is_child = 0 7.07.608.405 I slot print_timing: id 0 | task 24839 | prompt eval time = 358.25 ms / 188 tokens ( 1.91 ms per token, 524.78 tokens per second) 7.07.608.408 I slot print_timing: id 0 | task 24839 | eval time = 1353.02 ms / 92 tokens ( 14.87 ms per token, 67.26 tokens per second) 7.07.608.409 I slot print_timing: id 0 | task 24839 | total time = 1711.27 ms / 280 tokens 7.07.608.410 I slot print_timing: id 0 | task 24839 | graphs reused = 24273 7.07.608.410 I slot print_timing: id 0 | task 24839 | graph reallocs = 0 / 0 (same size) / (changed size) 7.07.608.436 I slot release: id 0 | task 24839 | stop processing: n_tokens = 279, truncated = 0 7.07.612.119 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 279, t_last = 337355994150 7.07.612.568 I slot launch_slot_: id 0 | task 24933 | processing task, is_child = 0 7.11.178.274 I slot print_timing: id 0 | task 24933 | n_gen = 203, tg = 67.30 t/s, tg_3s = 67.63 t/s 7.11.624.149 I slot print_timing: id 0 | task 24933 | prompt eval time = 564.03 ms / 394 tokens ( 1.43 ms per token, 698.54 tokens per second) 7.11.624.156 I slot print_timing: id 0 | task 24933 | eval time = 3447.55 ms / 233 tokens ( 14.86 ms per token, 67.29 tokens per second) 7.11.624.157 I slot print_timing: id 0 | task 24933 | total time = 4011.57 ms / 627 tokens 7.11.624.157 I slot print_timing: id 0 | task 24933 | graphs reused = 24503 7.11.624.158 I slot print_timing: id 0 | task 24933 | graph reallocs = 0 / 0 (same size) / (changed size) 7.11.624.192 I slot release: id 0 | task 24933 | stop processing: n_tokens = 626, truncated = 0 7.11.628.676 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 626, t_last = 337360009906 7.11.630.194 I slot launch_slot_: id 0 | task 25168 | processing task, is_child = 0 7.15.527.031 I slot print_timing: id 0 | task 25168 | n_gen = 203, tg = 67.25 t/s, tg_3s = 67.58 t/s 7.18.541.103 I slot print_timing: id 0 | task 25168 | n_gen = 406, tg = 67.30 t/s, tg_3s = 67.35 t/s 7.19.542.256 I slot print_timing: id 0 | task 25168 | prompt eval time = 892.97 ms / 584 tokens ( 1.53 ms per token, 654.00 tokens per second) 7.19.542.259 I slot print_timing: id 0 | task 25168 | eval time = 7019.09 ms / 473 tokens ( 14.87 ms per token, 67.25 tokens per second) 7.19.542.260 I slot print_timing: id 0 | task 25168 | total time = 7912.06 ms / 1057 tokens 7.19.542.261 I slot print_timing: id 0 | task 25168 | graphs reused = 24972 7.19.542.261 I slot print_timing: id 0 | task 25168 | graph reallocs = 0 / 0 (same size) / (changed size) 7.19.542.301 I slot release: id 0 | task 25168 | stop processing: n_tokens = 1056, truncated = 0 7.19.546.438 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1056, t_last = 337367928015 7.19.548.814 I slot launch_slot_: id 0 | task 25644 | processing task, is_child = 0 7.23.255.819 I slot print_timing: id 0 | task 25644 | n_gen = 203, tg = 67.24 t/s, tg_3s = 67.57 t/s 7.24.687.266 I slot print_timing: id 0 | task 25644 | prompt eval time = 702.77 ms / 518 tokens ( 1.36 ms per token, 737.09 tokens per second) 7.24.687.271 I slot print_timing: id 0 | task 25644 | eval time = 4435.67 ms / 299 tokens ( 14.88 ms per token, 67.18 tokens per second) 7.24.687.272 I slot print_timing: id 0 | task 25644 | total time = 5138.44 ms / 817 tokens 7.24.687.273 I slot print_timing: id 0 | task 25644 | graphs reused = 25268 7.24.687.273 I slot print_timing: id 0 | task 25644 | graph reallocs = 0 / 0 (same size) / (changed size) 7.24.687.314 I slot release: id 0 | task 25644 | stop processing: n_tokens = 816, truncated = 0 7.24.691.097 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 816, t_last = 337373073028 7.24.692.953 I slot launch_slot_: id 0 | task 25946 | processing task, is_child = 0 7.28.269.673 I slot print_timing: id 0 | task 25946 | n_gen = 204, tg = 67.38 t/s, tg_3s = 67.71 t/s 7.28.847.925 I slot print_timing: id 0 | task 25946 | prompt eval time = 564.06 ms / 399 tokens ( 1.41 ms per token, 707.37 tokens per second) 7.28.847.927 I slot print_timing: id 0 | task 25946 | eval time = 3590.90 ms / 243 tokens ( 14.84 ms per token, 67.39 tokens per second) 7.28.847.928 I slot print_timing: id 0 | task 25946 | total time = 4154.96 ms / 642 tokens 7.28.847.929 I slot print_timing: id 0 | task 25946 | graphs reused = 25508 7.28.847.929 I slot print_timing: id 0 | task 25946 | graph reallocs = 0 / 0 (same size) / (changed size) 7.28.847.963 I slot release: id 0 | task 25946 | stop processing: n_tokens = 643, truncated = 0 7.28.851.617 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 643, t_last = 337377233677 7.28.853.153 I slot launch_slot_: id 0 | task 26191 | processing task, is_child = 0 7.32.358.958 I slot print_timing: id 0 | task 26191 | n_gen = 203, tg = 67.28 t/s, tg_3s = 67.61 t/s 7.34.333.897 I slot print_timing: id 0 | task 26191 | prompt eval time = 503.32 ms / 335 tokens ( 1.50 ms per token, 665.58 tokens per second) 7.34.333.903 I slot print_timing: id 0 | task 26191 | eval time = 4977.42 ms / 336 tokens ( 14.86 ms per token, 67.30 tokens per second) 7.34.333.903 I slot print_timing: id 0 | task 26191 | total time = 5480.74 ms / 671 tokens 7.34.333.904 I slot print_timing: id 0 | task 26191 | graphs reused = 25841 7.34.333.905 I slot print_timing: id 0 | task 26191 | graph reallocs = 0 / 0 (same size) / (changed size) 7.34.333.935 I slot release: id 0 | task 26191 | stop processing: n_tokens = 672, truncated = 0 7.34.338.272 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 672, t_last = 337382719649 7.34.339.788 I slot launch_slot_: id 0 | task 26529 | processing task, is_child = 0 7.38.257.590 I slot print_timing: id 0 | task 26529 | n_gen = 203, tg = 67.16 t/s, tg_3s = 67.49 t/s 7.41.257.842 I slot print_timing: id 0 | task 26529 | n_gen = 405, tg = 67.24 t/s, tg_3s = 67.33 t/s 7.41.287.663 I slot print_timing: id 0 | task 26529 | prompt eval time = 910.14 ms / 603 tokens ( 1.51 ms per token, 662.54 tokens per second) 7.41.287.669 I slot print_timing: id 0 | task 26529 | eval time = 6037.73 ms / 407 tokens ( 14.87 ms per token, 67.24 tokens per second) 7.41.287.669 I slot print_timing: id 0 | task 26529 | total time = 6947.87 ms / 1010 tokens 7.41.287.670 I slot print_timing: id 0 | task 26529 | graphs reused = 26245 7.41.287.671 I slot print_timing: id 0 | task 26529 | graph reallocs = 0 / 0 (same size) / (changed size) 7.41.287.716 I slot release: id 0 | task 26529 | stop processing: n_tokens = 1011, truncated = 0 7.41.291.827 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1011, t_last = 337389673430 7.41.294.426 I slot launch_slot_: id 0 | task 26939 | processing task, is_child = 0 7.44.796.487 I slot print_timing: id 0 | task 26939 | n_gen = 203, tg = 67.31 t/s, tg_3s = 67.64 t/s 7.46.060.722 I slot print_timing: id 0 | task 26939 | prompt eval time = 500.85 ms / 333 tokens ( 1.50 ms per token, 664.87 tokens per second) 7.46.060.728 I slot print_timing: id 0 | task 26939 | eval time = 4265.43 ms / 288 tokens ( 14.86 ms per token, 67.29 tokens per second) 7.46.060.729 I slot print_timing: id 0 | task 26939 | total time = 4766.29 ms / 621 tokens 7.46.060.730 I slot print_timing: id 0 | task 26939 | graphs reused = 26530 7.46.060.730 I slot print_timing: id 0 | task 26939 | graph reallocs = 0 / 0 (same size) / (changed size) 7.46.060.763 I slot release: id 0 | task 26939 | stop processing: n_tokens = 622, truncated = 0 7.46.064.688 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 622, t_last = 337394446477 7.46.066.281 I slot launch_slot_: id 0 | task 27229 | processing task, is_child = 0 7.49.701.253 I slot print_timing: id 0 | task 27229 | n_gen = 203, tg = 67.22 t/s, tg_3s = 67.56 t/s 7.52.704.513 I slot print_timing: id 0 | task 27229 | n_gen = 405, tg = 67.24 t/s, tg_3s = 67.26 t/s 7.53.552.079 I slot print_timing: id 0 | task 27229 | prompt eval time = 630.07 ms / 460 tokens ( 1.37 ms per token, 730.08 tokens per second) 7.53.552.082 I slot print_timing: id 0 | task 27229 | eval time = 6855.73 ms / 462 tokens ( 14.87 ms per token, 67.24 tokens per second) 7.53.552.083 I slot print_timing: id 0 | task 27229 | total time = 7485.79 ms / 922 tokens 7.53.552.084 I slot print_timing: id 0 | task 27229 | graphs reused = 26988 7.53.552.084 I slot print_timing: id 0 | task 27229 | graph reallocs = 0 / 0 (same size) / (changed size) 7.53.552.120 I slot release: id 0 | task 27229 | stop processing: n_tokens = 923, truncated = 0 7.53.555.659 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 923, t_last = 337401937834 7.53.557.803 I slot launch_slot_: id 0 | task 27693 | processing task, is_child = 0 7.56.192.108 I slot print_timing: id 0 | task 27693 | prompt eval time = 391.23 ms / 225 tokens ( 1.74 ms per token, 575.11 tokens per second) 7.56.192.115 I slot print_timing: id 0 | task 27693 | eval time = 2243.07 ms / 152 tokens ( 14.85 ms per token, 67.32 tokens per second) 7.56.192.115 I slot print_timing: id 0 | task 27693 | total time = 2634.29 ms / 377 tokens 7.56.192.116 I slot print_timing: id 0 | task 27693 | graphs reused = 27137 7.56.192.117 I slot print_timing: id 0 | task 27693 | graph reallocs = 0 / 0 (same size) / (changed size) 7.56.192.140 I slot release: id 0 | task 27693 | stop processing: n_tokens = 378, truncated = 0 7.56.195.739 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 378, t_last = 337404577854 7.56.196.791 I slot launch_slot_: id 0 | task 27847 | processing task, is_child = 0 7.59.786.643 I slot print_timing: id 0 | task 27847 | n_gen = 204, tg = 67.38 t/s, tg_3s = 67.71 t/s 8.01.329.726 I slot print_timing: id 0 | task 27847 | prompt eval time = 576.91 ms / 415 tokens ( 1.39 ms per token, 719.34 tokens per second) 8.01.329.732 I slot print_timing: id 0 | task 27847 | eval time = 4556.01 ms / 308 tokens ( 14.84 ms per token, 67.38 tokens per second) 8.01.329.732 I slot print_timing: id 0 | task 27847 | total time = 5132.92 ms / 723 tokens 8.01.329.733 I slot print_timing: id 0 | task 27847 | graphs reused = 27442 8.01.329.734 I slot print_timing: id 0 | task 27847 | graph reallocs = 0 / 0 (same size) / (changed size) 8.01.329.768 I slot release: id 0 | task 27847 | stop processing: n_tokens = 724, truncated = 0 8.01.333.676 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 724, t_last = 337409715482 8.01.335.509 I slot launch_slot_: id 0 | task 28157 | processing task, is_child = 0 8.05.045.906 I slot print_timing: id 0 | task 28157 | n_gen = 203, tg = 67.23 t/s, tg_3s = 67.56 t/s 8.07.247.863 I slot print_timing: id 0 | task 28157 | prompt eval time = 705.56 ms / 519 tokens ( 1.36 ms per token, 735.58 tokens per second) 8.07.247.868 I slot print_timing: id 0 | task 28157 | eval time = 5206.78 ms / 351 tokens ( 14.88 ms per token, 67.22 tokens per second) 8.07.247.869 I slot print_timing: id 0 | task 28157 | total time = 5912.34 ms / 870 tokens 8.07.247.870 I slot print_timing: id 0 | task 28157 | graphs reused = 27790 8.07.247.870 I slot print_timing: id 0 | task 28157 | graph reallocs = 0 / 0 (same size) / (changed size) 8.07.247.910 I slot release: id 0 | task 28157 | stop processing: n_tokens = 871, truncated = 0 8.07.252.082 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 871, t_last = 337415633624 8.07.254.008 I slot launch_slot_: id 0 | task 28511 | processing task, is_child = 0 8.11.173.880 I slot print_timing: id 0 | task 28511 | n_gen = 203, tg = 67.23 t/s, tg_3s = 67.56 t/s 8.12.970.416 I slot print_timing: id 0 | task 28511 | prompt eval time = 915.31 ms / 602 tokens ( 1.52 ms per token, 657.70 tokens per second) 8.12.970.422 I slot print_timing: id 0 | task 28511 | eval time = 4801.09 ms / 324 tokens ( 14.86 ms per token, 67.28 tokens per second) 8.12.970.423 I slot print_timing: id 0 | task 28511 | total time = 5716.40 ms / 926 tokens 8.12.970.423 I slot print_timing: id 0 | task 28511 | graphs reused = 28111 8.12.970.424 I slot print_timing: id 0 | task 28511 | graph reallocs = 0 / 0 (same size) / (changed size) 8.12.970.470 I slot release: id 0 | task 28511 | stop processing: n_tokens = 930, truncated = 0 8.12.974.299 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 930, t_last = 337421356184 8.12.976.399 I slot launch_slot_: id 0 | task 28838 | processing task, is_child = 0 8.16.555.739 I slot print_timing: id 0 | task 28838 | n_gen = 203, tg = 67.21 t/s, tg_3s = 67.54 t/s 8.17.617.713 I slot print_timing: id 0 | task 28838 | prompt eval time = 573.90 ms / 407 tokens ( 1.41 ms per token, 709.18 tokens per second) 8.17.617.720 I slot print_timing: id 0 | task 28838 | eval time = 4067.41 ms / 274 tokens ( 14.90 ms per token, 67.12 tokens per second) 8.17.617.721 I slot print_timing: id 0 | task 28838 | total time = 4641.31 ms / 681 tokens 8.17.617.721 I slot print_timing: id 0 | task 28838 | graphs reused = 28382 8.17.617.722 I slot print_timing: id 0 | task 28838 | graph reallocs = 0 / 0 (same size) / (changed size) 8.17.617.756 I slot release: id 0 | task 28838 | stop processing: n_tokens = 685, truncated = 0 8.17.621.625 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 685, t_last = 337426003470 8.17.623.373 I slot launch_slot_: id 0 | task 29114 | processing task, is_child = 0 8.21.275.208 I slot print_timing: id 0 | task 29114 | n_gen = 203, tg = 67.23 t/s, tg_3s = 67.56 t/s 8.24.279.148 I slot print_timing: id 0 | task 29114 | n_gen = 405, tg = 67.24 t/s, tg_3s = 67.24 t/s 8.26.558.176 I slot print_timing: id 0 | task 29114 | prompt eval time = 647.09 ms / 484 tokens ( 1.34 ms per token, 747.96 tokens per second) 8.26.558.181 I slot print_timing: id 0 | task 29114 | eval time = 8287.70 ms / 558 tokens ( 14.88 ms per token, 67.21 tokens per second) 8.26.558.182 I slot print_timing: id 0 | task 29114 | total time = 8934.79 ms / 1042 tokens 8.26.558.183 I slot print_timing: id 0 | task 29114 | graphs reused = 28935 8.26.558.183 I slot print_timing: id 0 | task 29114 | graph reallocs = 0 / 0 (same size) / (changed size) 8.26.558.221 I slot release: id 0 | task 29114 | stop processing: n_tokens = 1046, truncated = 0 8.26.562.385 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1046, t_last = 337434943935 8.26.564.745 I slot launch_slot_: id 0 | task 29674 | processing task, is_child = 0 8.29.396.801 I slot print_timing: id 0 | task 29674 | prompt eval time = 626.06 ms / 457 tokens ( 1.37 ms per token, 729.96 tokens per second) 8.29.396.804 I slot print_timing: id 0 | task 29674 | eval time = 2205.99 ms / 149 tokens ( 14.91 ms per token, 67.09 tokens per second) 8.29.396.805 I slot print_timing: id 0 | task 29674 | total time = 2832.05 ms / 606 tokens 8.29.396.805 I slot print_timing: id 0 | task 29674 | graphs reused = 29081 8.29.396.806 I slot print_timing: id 0 | task 29674 | graph reallocs = 0 / 0 (same size) / (changed size) 8.29.396.843 I slot release: id 0 | task 29674 | stop processing: n_tokens = 610, truncated = 0 8.29.400.919 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 610, t_last = 337437782557 8.29.402.859 I slot launch_slot_: id 0 | task 29825 | processing task, is_child = 0 8.33.326.571 I slot print_timing: id 0 | task 29825 | n_gen = 203, tg = 67.01 t/s, tg_3s = 67.34 t/s 8.36.331.371 I slot print_timing: id 0 | task 29825 | n_gen = 405, tg = 67.12 t/s, tg_3s = 67.23 t/s 8.39.345.260 I slot print_timing: id 0 | task 29825 | n_gen = 607, tg = 67.09 t/s, tg_3s = 67.02 t/s 8.42.213.190 I slot print_timing: id 0 | task 29825 | prompt eval time = 909.15 ms / 597 tokens ( 1.52 ms per token, 656.66 tokens per second) 8.42.213.195 I slot print_timing: id 0 | task 29825 | eval time = 11901.18 ms / 798 tokens ( 14.93 ms per token, 66.97 tokens per second) 8.42.213.196 I slot print_timing: id 0 | task 29825 | total time = 12810.32 ms / 1395 tokens 8.42.213.197 I slot print_timing: id 0 | task 29825 | graphs reused = 29874 8.42.213.197 I slot print_timing: id 0 | task 29825 | graph reallocs = 0 / 0 (same size) / (changed size) 8.42.213.241 I slot release: id 0 | task 29825 | stop processing: n_tokens = 1394, truncated = 0 8.42.217.849 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1394, t_last = 337450598955 8.42.220.694 I slot launch_slot_: id 0 | task 30626 | processing task, is_child = 0 8.46.226.246 I slot print_timing: id 0 | task 30626 | n_gen = 203, tg = 67.12 t/s, tg_3s = 67.45 t/s 8.47.511.236 I slot print_timing: id 0 | task 30626 | prompt eval time = 995.96 ms / 688 tokens ( 1.45 ms per token, 690.79 tokens per second) 8.47.511.242 I slot print_timing: id 0 | task 30626 | eval time = 4294.57 ms / 289 tokens ( 14.91 ms per token, 67.06 tokens per second) 8.47.511.242 I slot print_timing: id 0 | task 30626 | total time = 5290.53 ms / 977 tokens 8.47.511.243 I slot print_timing: id 0 | task 30626 | graphs reused = 30160 8.47.511.244 I slot print_timing: id 0 | task 30626 | graph reallocs = 0 / 0 (same size) / (changed size) 8.47.511.295 I slot release: id 0 | task 30626 | stop processing: n_tokens = 976, truncated = 0 8.47.515.314 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 976, t_last = 337455897009 8.47.517.877 I slot launch_slot_: id 0 | task 30918 | processing task, is_child = 0 8.51.177.793 I slot print_timing: id 0 | task 30918 | n_gen = 202, tg = 66.99 t/s, tg_3s = 67.32 t/s 8.51.536.029 I slot print_timing: id 0 | task 30918 | prompt eval time = 659.27 ms / 489 tokens ( 1.35 ms per token, 741.72 tokens per second) 8.51.536.035 I slot print_timing: id 0 | task 30918 | eval time = 3358.87 ms / 226 tokens ( 14.93 ms per token, 66.99 tokens per second) 8.51.536.036 I slot print_timing: id 0 | task 30918 | total time = 4018.14 ms / 715 tokens 8.51.536.036 I slot print_timing: id 0 | task 30918 | graphs reused = 30383 8.51.536.037 I slot print_timing: id 0 | task 30918 | graph reallocs = 0 / 0 (same size) / (changed size) 8.51.536.075 I slot release: id 0 | task 30918 | stop processing: n_tokens = 714, truncated = 0 8.51.540.140 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 714, t_last = 337459921790 8.51.541.959 I slot launch_slot_: id 0 | task 31146 | processing task, is_child = 0 8.55.394.068 I slot print_timing: id 0 | task 31146 | n_gen = 203, tg = 67.06 t/s, tg_3s = 67.40 t/s 8.58.402.521 I slot print_timing: id 0 | task 31146 | n_gen = 405, tg = 67.10 t/s, tg_3s = 67.14 t/s 8.59.193.939 I slot print_timing: id 0 | task 31146 | prompt eval time = 840.08 ms / 550 tokens ( 1.53 ms per token, 654.70 tokens per second) 8.59.193.941 I slot print_timing: id 0 | task 31146 | eval time = 6811.89 ms / 458 tokens ( 14.91 ms per token, 67.09 tokens per second) 8.59.193.942 I slot print_timing: id 0 | task 31146 | total time = 7651.97 ms / 1008 tokens 8.59.193.943 I slot print_timing: id 0 | task 31146 | graphs reused = 30838 8.59.193.943 I slot print_timing: id 0 | task 31146 | graph reallocs = 0 / 0 (same size) / (changed size) 8.59.193.986 I slot release: id 0 | task 31146 | stop processing: n_tokens = 1007, truncated = 0 8.59.197.830 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1007, t_last = 337467579700 8.59.200.118 I slot launch_slot_: id 0 | task 31607 | processing task, is_child = 0 9.02.715.251 I slot print_timing: id 0 | task 31607 | n_gen = 204, tg = 67.35 t/s, tg_3s = 67.68 t/s 9.05.122.141 I slot print_timing: id 0 | task 31607 | prompt eval time = 501.04 ms / 334 tokens ( 1.50 ms per token, 666.62 tokens per second) 9.05.122.143 I slot print_timing: id 0 | task 31607 | eval time = 5420.97 ms / 366 tokens ( 14.85 ms per token, 67.33 tokens per second) 9.05.122.144 I slot print_timing: id 0 | task 31607 | total time = 5922.01 ms / 700 tokens 9.05.122.144 I slot print_timing: id 0 | task 31607 | graphs reused = 31201 9.05.122.145 I slot print_timing: id 0 | task 31607 | graph reallocs = 0 / 0 (same size) / (changed size) 9.05.122.177 I slot release: id 0 | task 31607 | stop processing: n_tokens = 699, truncated = 0 9.05.126.109 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 699, t_last = 337473507892 9.05.128.075 I slot launch_slot_: id 0 | task 31975 | processing task, is_child = 0 9.08.715.828 I slot print_timing: id 0 | task 31975 | n_gen = 203, tg = 67.15 t/s, tg_3s = 67.48 t/s 9.11.717.449 I slot print_timing: id 0 | task 31975 | n_gen = 405, tg = 67.22 t/s, tg_3s = 67.30 t/s 9.13.024.544 I slot print_timing: id 0 | task 31975 | prompt eval time = 579.57 ms / 416 tokens ( 1.39 ms per token, 717.78 tokens per second) 9.13.024.548 I slot print_timing: id 0 | task 31975 | eval time = 7316.89 ms / 493 tokens ( 14.87 ms per token, 67.24 tokens per second) 9.13.024.549 I slot print_timing: id 0 | task 31975 | total time = 7896.46 ms / 909 tokens 9.13.024.549 I slot print_timing: id 0 | task 31975 | graphs reused = 31690 9.13.024.550 I slot print_timing: id 0 | task 31975 | graph reallocs = 0 / 0 (same size) / (changed size) 9.13.024.586 I slot release: id 0 | task 31975 | stop processing: n_tokens = 908, truncated = 0 9.13.029.222 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 908, t_last = 337481410300 9.13.031.259 I slot launch_slot_: id 0 | task 32470 | processing task, is_child = 0 9.16.520.311 I slot print_timing: id 0 | task 32470 | prompt eval time = 1060.22 ms / 754 tokens ( 1.41 ms per token, 711.17 tokens per second) 9.16.520.316 I slot print_timing: id 0 | task 32470 | eval time = 2428.82 ms / 164 tokens ( 14.90 ms per token, 67.11 tokens per second) 9.16.520.317 I slot print_timing: id 0 | task 32470 | total time = 3489.04 ms / 918 tokens 9.16.520.317 I slot print_timing: id 0 | task 32470 | graphs reused = 31851 9.16.520.318 I slot print_timing: id 0 | task 32470 | graph reallocs = 0 / 0 (same size) / (changed size) 9.16.520.374 I slot release: id 0 | task 32470 | stop processing: n_tokens = 917, truncated = 0 9.16.524.712 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 917, t_last = 337484906088 9.16.526.830 I slot launch_slot_: id 0 | task 32637 | processing task, is_child = 0 9.20.546.206 I slot print_timing: id 0 | task 32637 | n_gen = 203, tg = 67.09 t/s, tg_3s = 67.42 t/s 9.22.534.020 I slot print_timing: id 0 | task 32637 | prompt eval time = 1008.33 ms / 706 tokens ( 1.43 ms per token, 700.17 tokens per second) 9.22.534.027 I slot print_timing: id 0 | task 32637 | eval time = 4998.85 ms / 336 tokens ( 14.92 ms per token, 67.02 tokens per second) 9.22.534.028 I slot print_timing: id 0 | task 32637 | total time = 6007.18 ms / 1042 tokens 9.22.534.028 I slot print_timing: id 0 | task 32637 | graphs reused = 32183 9.22.534.029 I slot print_timing: id 0 | task 32637 | graph reallocs = 0 / 0 (same size) / (changed size) 9.22.534.081 I slot release: id 0 | task 32637 | stop processing: n_tokens = 1041, truncated = 0 9.22.537.735 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1041, t_last = 337490919795 9.22.540.187 I slot launch_slot_: id 0 | task 32976 | processing task, is_child = 0 9.25.959.044 I slot print_timing: id 0 | task 32976 | n_gen = 204, tg = 67.35 t/s, tg_3s = 67.68 t/s 9.27.947.635 I slot print_timing: id 0 | task 32976 | prompt eval time = 404.78 ms / 233 tokens ( 1.74 ms per token, 575.63 tokens per second) 9.27.947.641 I slot print_timing: id 0 | task 32976 | eval time = 5002.67 ms / 338 tokens ( 14.84 ms per token, 67.36 tokens per second) 9.27.947.642 I slot print_timing: id 0 | task 32976 | total time = 5407.44 ms / 571 tokens 9.27.947.643 I slot print_timing: id 0 | task 32976 | graphs reused = 32517 9.27.947.643 I slot print_timing: id 0 | task 32976 | graph reallocs = 0 / 0 (same size) / (changed size) 9.27.947.668 I slot release: id 0 | task 32976 | stop processing: n_tokens = 570, truncated = 0 9.27.951.069 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.133 (> 0.100 thold), f_keep = 0.040 9.27.952.334 I slot launch_slot_: id 0 | task 33316 | processing task, is_child = 0 9.31.308.303 I slot print_timing: id 0 | task 33316 | n_gen = 203, tg = 67.24 t/s, tg_3s = 67.57 t/s 9.31.456.236 I slot print_timing: id 0 | task 33316 | prompt eval time = 351.82 ms / 173 tokens ( 2.03 ms per token, 491.73 tokens per second) 9.31.456.242 I slot print_timing: id 0 | task 33316 | eval time = 3152.08 ms / 213 tokens ( 14.87 ms per token, 67.26 tokens per second) 9.31.456.243 I slot print_timing: id 0 | task 33316 | total time = 3503.89 ms / 386 tokens 9.31.456.244 I slot print_timing: id 0 | task 33316 | graphs reused = 32727 9.31.456.244 I slot print_timing: id 0 | task 33316 | graph reallocs = 0 / 0 (same size) / (changed size) 9.31.456.264 I slot release: id 0 | task 33316 | stop processing: n_tokens = 385, truncated = 0 9.31.459.707 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.111 (> 0.100 thold), f_keep = 0.057 9.31.460.187 I slot launch_slot_: id 0 | task 33531 | processing task, is_child = 0 9.34.845.079 I slot print_timing: id 0 | task 33531 | n_gen = 204, tg = 67.43 t/s, tg_3s = 67.77 t/s 9.37.851.156 I slot print_timing: id 0 | task 33531 | n_gen = 406, tg = 67.32 t/s, tg_3s = 67.20 t/s 9.40.857.908 I slot print_timing: id 0 | task 33531 | n_gen = 608, tg = 67.27 t/s, tg_3s = 67.18 t/s 9.43.861.726 I slot print_timing: id 0 | task 33531 | n_gen = 810, tg = 67.27 t/s, tg_3s = 67.25 t/s 9.45.195.682 I slot print_timing: id 0 | task 33531 | prompt eval time = 374.56 ms / 199 tokens ( 1.88 ms per token, 531.29 tokens per second) 9.45.195.684 I slot print_timing: id 0 | task 33531 | eval time = 13360.92 ms / 899 tokens ( 14.88 ms per token, 67.21 tokens per second) 9.45.195.686 I slot print_timing: id 0 | task 33531 | total time = 13735.49 ms / 1098 tokens 9.45.195.687 I slot print_timing: id 0 | task 33531 | graphs reused = 33620 9.45.195.687 I slot print_timing: id 0 | task 33531 | graph reallocs = 0 / 0 (same size) / (changed size) 9.45.195.710 I slot release: id 0 | task 33531 | stop processing: n_tokens = 1097, truncated = 0 9.45.199.461 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.148 (> 0.100 thold), f_keep = 0.020 9.45.201.790 I slot launch_slot_: id 0 | task 34432 | processing task, is_child = 0 9.48.543.690 I slot print_timing: id 0 | task 34432 | n_gen = 204, tg = 67.35 t/s, tg_3s = 67.68 t/s 9.48.959.906 I slot print_timing: id 0 | task 34432 | prompt eval time = 327.77 ms / 149 tokens ( 2.20 ms per token, 454.59 tokens per second) 9.48.959.912 I slot print_timing: id 0 | task 34432 | eval time = 3430.34 ms / 232 tokens ( 14.85 ms per token, 67.34 tokens per second) 9.48.959.912 I slot print_timing: id 0 | task 34432 | total time = 3758.11 ms / 381 tokens 9.48.959.913 I slot print_timing: id 0 | task 34432 | graphs reused = 33849 9.48.959.914 I slot print_timing: id 0 | task 34432 | graph reallocs = 0 / 0 (same size) / (changed size) 9.48.959.934 I slot release: id 0 | task 34432 | stop processing: n_tokens = 380, truncated = 0 9.48.963.424 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 380, t_last = 337517345648 9.48.963.849 I slot launch_slot_: id 0 | task 34666 | processing task, is_child = 0 9.52.360.122 I slot print_timing: id 0 | task 34666 | n_gen = 204, tg = 67.45 t/s, tg_3s = 67.79 t/s 9.55.362.957 I slot print_timing: id 0 | task 34666 | n_gen = 406, tg = 67.36 t/s, tg_3s = 67.27 t/s 9.58.371.982 I slot print_timing: id 0 | task 34666 | n_gen = 609, tg = 67.40 t/s, tg_3s = 67.46 t/s 9.59.830.311 I slot print_timing: id 0 | task 34666 | prompt eval time = 386.81 ms / 216 tokens ( 1.79 ms per token, 558.41 tokens per second) 9.59.830.317 I slot print_timing: id 0 | task 34666 | eval time = 10479.64 ms / 707 tokens ( 14.84 ms per token, 67.37 tokens per second) 9.59.830.318 I slot print_timing: id 0 | task 34666 | total time = 10866.46 ms / 923 tokens 9.59.830.318 I slot print_timing: id 0 | task 34666 | graphs reused = 34551 9.59.830.319 I slot print_timing: id 0 | task 34666 | graph reallocs = 0 / 0 (same size) / (changed size) 9.59.830.343 I slot release: id 0 | task 34666 | stop processing: n_tokens = 922, truncated = 0 9.59.833.650 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.160 (> 0.100 thold), f_keep = 0.023 9.59.835.573 I slot launch_slot_: id 0 | task 35375 | processing task, is_child = 0 10.01.656.207 I slot print_timing: id 0 | task 35375 | prompt eval time = 305.20 ms / 131 tokens ( 2.33 ms per token, 429.23 tokens per second) 10.01.656.210 I slot print_timing: id 0 | task 35375 | eval time = 1515.43 ms / 103 tokens ( 14.86 ms per token, 67.31 tokens per second) 10.01.656.210 I slot print_timing: id 0 | task 35375 | total time = 1820.63 ms / 234 tokens 10.01.656.211 I slot print_timing: id 0 | task 35375 | graphs reused = 34652 10.01.656.211 I slot print_timing: id 0 | task 35375 | graph reallocs = 0 / 0 (same size) / (changed size) 10.01.656.230 I slot release: id 0 | task 35375 | stop processing: n_tokens = 233, truncated = 0 10.01.659.498 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.121 (> 0.100 thold), f_keep = 0.090 10.01.659.861 I slot launch_slot_: id 0 | task 35480 | processing task, is_child = 0 10.05.026.348 I slot print_timing: id 0 | task 35480 | n_gen = 204, tg = 67.35 t/s, tg_3s = 67.68 t/s 10.08.027.601 I slot print_timing: id 0 | task 35480 | n_gen = 406, tg = 67.33 t/s, tg_3s = 67.31 t/s 10.08.711.232 I slot print_timing: id 0 | task 35480 | prompt eval time = 352.20 ms / 174 tokens ( 2.02 ms per token, 494.04 tokens per second) 10.08.711.236 I slot print_timing: id 0 | task 35480 | eval time = 6699.16 ms / 452 tokens ( 14.85 ms per token, 67.32 tokens per second) 10.08.711.236 I slot print_timing: id 0 | task 35480 | total time = 7051.36 ms / 626 tokens 10.08.711.237 I slot print_timing: id 0 | task 35480 | graphs reused = 35100 10.08.711.238 I slot print_timing: id 0 | task 35480 | graph reallocs = 0 / 0 (same size) / (changed size) 10.08.711.263 I slot release: id 0 | task 35480 | stop processing: n_tokens = 625, truncated = 0 10.08.714.585 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.129 (> 0.100 thold), f_keep = 0.034 10.08.715.985 I slot launch_slot_: id 0 | task 35934 | processing task, is_child = 0 10.12.054.951 I slot print_timing: id 0 | task 35934 | n_gen = 203, tg = 67.30 t/s, tg_3s = 67.63 t/s 10.12.737.951 I slot print_timing: id 0 | task 35934 | prompt eval time = 337.48 ms / 163 tokens ( 2.07 ms per token, 482.99 tokens per second) 10.12.737.956 I slot print_timing: id 0 | task 35934 | eval time = 3684.48 ms / 249 tokens ( 14.86 ms per token, 67.31 tokens per second) 10.12.737.956 I slot print_timing: id 0 | task 35934 | total time = 4021.96 ms / 412 tokens 10.12.737.957 I slot print_timing: id 0 | task 35934 | graphs reused = 35346 10.12.737.958 I slot print_timing: id 0 | task 35934 | graph reallocs = 0 / 0 (same size) / (changed size) 10.12.737.979 I slot release: id 0 | task 35934 | stop processing: n_tokens = 411, truncated = 0 10.12.741.146 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.208 (> 0.100 thold), f_keep = 0.051 10.12.741.613 I slot launch_slot_: id 0 | task 36185 | processing task, is_child = 0 10.14.591.375 I slot print_timing: id 0 | task 36185 | prompt eval time = 290.09 ms / 101 tokens ( 2.87 ms per token, 348.17 tokens per second) 10.14.591.381 I slot print_timing: id 0 | task 36185 | eval time = 1559.67 ms / 106 tokens ( 14.85 ms per token, 67.32 tokens per second) 10.14.591.382 I slot print_timing: id 0 | task 36185 | total time = 1849.75 ms / 207 tokens 10.14.591.383 I slot print_timing: id 0 | task 36185 | graphs reused = 35450 10.14.591.383 I slot print_timing: id 0 | task 36185 | graph reallocs = 0 / 0 (same size) / (changed size) 10.14.591.400 I slot release: id 0 | task 36185 | stop processing: n_tokens = 206, truncated = 0 10.14.594.697 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.126 (> 0.100 thold), f_keep = 0.102 10.14.595.388 I slot launch_slot_: id 0 | task 36293 | processing task, is_child = 0 10.17.954.764 I slot print_timing: id 0 | task 36293 | n_gen = 204, tg = 67.48 t/s, tg_3s = 67.81 t/s 10.19.750.599 I slot print_timing: id 0 | task 36293 | prompt eval time = 350.89 ms / 167 tokens ( 2.10 ms per token, 475.94 tokens per second) 10.19.750.602 I slot print_timing: id 0 | task 36293 | eval time = 4804.32 ms / 325 tokens ( 14.83 ms per token, 67.44 tokens per second) 10.19.750.603 I slot print_timing: id 0 | task 36293 | total time = 5155.20 ms / 492 tokens 10.19.750.604 I slot print_timing: id 0 | task 36293 | graphs reused = 35772 10.19.750.604 I slot print_timing: id 0 | task 36293 | graph reallocs = 0 / 0 (same size) / (changed size) 10.19.750.625 I slot release: id 0 | task 36293 | stop processing: n_tokens = 491, truncated = 0 10.19.753.904 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.123 (> 0.100 thold), f_keep = 0.043 10.19.755.092 I slot launch_slot_: id 0 | task 36620 | processing task, is_child = 0 10.23.118.143 I slot print_timing: id 0 | task 36620 | n_gen = 204, tg = 67.46 t/s, tg_3s = 67.79 t/s 10.24.097.453 I slot print_timing: id 0 | task 36620 | prompt eval time = 353.72 ms / 171 tokens ( 2.07 ms per token, 483.43 tokens per second) 10.24.097.458 I slot print_timing: id 0 | task 36620 | eval time = 3988.63 ms / 270 tokens ( 14.83 ms per token, 67.44 tokens per second) 10.24.097.459 I slot print_timing: id 0 | task 36620 | total time = 4342.35 ms / 441 tokens 10.24.097.459 I slot print_timing: id 0 | task 36620 | graphs reused = 36039 10.24.097.460 I slot print_timing: id 0 | task 36620 | graph reallocs = 0 / 0 (same size) / (changed size) 10.24.097.483 I slot release: id 0 | task 36620 | stop processing: n_tokens = 440, truncated = 0 10.24.100.863 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.117 (> 0.100 thold), f_keep = 0.048 10.24.101.921 I slot launch_slot_: id 0 | task 36892 | processing task, is_child = 0 10.27.464.186 I slot print_timing: id 0 | task 36892 | n_gen = 204, tg = 67.53 t/s, tg_3s = 67.87 t/s 10.28.931.267 I slot print_timing: id 0 | task 36892 | prompt eval time = 356.36 ms / 179 tokens ( 1.99 ms per token, 502.31 tokens per second) 10.28.931.270 I slot print_timing: id 0 | task 36892 | eval time = 4472.98 ms / 303 tokens ( 14.81 ms per token, 67.52 tokens per second) 10.28.931.270 I slot print_timing: id 0 | task 36892 | total time = 4829.34 ms / 482 tokens 10.28.931.271 I slot print_timing: id 0 | task 36892 | graphs reused = 36339 10.28.931.272 I slot print_timing: id 0 | task 36892 | graph reallocs = 0 / 0 (same size) / (changed size) 10.28.931.294 I slot release: id 0 | task 36892 | stop processing: n_tokens = 481, truncated = 0 10.28.934.657 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.127 (> 0.100 thold), f_keep = 0.044 10.28.935.821 I slot launch_slot_: id 0 | task 37197 | processing task, is_child = 0 10.31.658.520 I slot print_timing: id 0 | task 37197 | prompt eval time = 347.53 ms / 165 tokens ( 2.11 ms per token, 474.78 tokens per second) 10.31.658.526 I slot print_timing: id 0 | task 37197 | eval time = 2375.16 ms / 161 tokens ( 14.84 ms per token, 67.36 tokens per second) 10.31.658.527 I slot print_timing: id 0 | task 37197 | total time = 2722.69 ms / 326 tokens 10.31.658.527 I slot print_timing: id 0 | task 37197 | graphs reused = 36497 10.31.658.528 I slot print_timing: id 0 | task 37197 | graph reallocs = 0 / 0 (same size) / (changed size) 10.31.658.549 I slot release: id 0 | task 37197 | stop processing: n_tokens = 325, truncated = 0 10.31.661.779 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.132 (> 0.100 thold), f_keep = 0.065 10.31.662.688 I slot launch_slot_: id 0 | task 37360 | processing task, is_child = 0 10.35.005.217 I slot print_timing: id 0 | task 37360 | n_gen = 204, tg = 67.48 t/s, tg_3s = 67.82 t/s 10.35.405.356 I slot print_timing: id 0 | task 37360 | prompt eval time = 334.40 ms / 159 tokens ( 2.10 ms per token, 475.48 tokens per second) 10.35.405.360 I slot print_timing: id 0 | task 37360 | eval time = 3408.26 ms / 231 tokens ( 14.82 ms per token, 67.48 tokens per second) 10.35.405.361 I slot print_timing: id 0 | task 37360 | total time = 3742.66 ms / 390 tokens 10.35.405.361 I slot print_timing: id 0 | task 37360 | graphs reused = 36725 10.35.405.362 I slot print_timing: id 0 | task 37360 | graph reallocs = 0 / 0 (same size) / (changed size) 10.35.405.382 I slot release: id 0 | task 37360 | stop processing: n_tokens = 389, truncated = 0 10.35.408.588 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.118 (> 0.100 thold), f_keep = 0.054 10.35.409.570 I slot launch_slot_: id 0 | task 37593 | processing task, is_child = 0 10.38.052.681 I slot print_timing: id 0 | task 37593 | prompt eval time = 356.66 ms / 178 tokens ( 2.00 ms per token, 499.08 tokens per second) 10.38.052.684 I slot print_timing: id 0 | task 37593 | eval time = 2286.44 ms / 155 tokens ( 14.85 ms per token, 67.35 tokens per second) 10.38.052.684 I slot print_timing: id 0 | task 37593 | total time = 2643.10 ms / 333 tokens 10.38.052.691 I slot print_timing: id 0 | task 37593 | graphs reused = 36877 10.38.052.691 I slot print_timing: id 0 | task 37593 | graph reallocs = 0 / 0 (same size) / (changed size) 10.38.052.715 I slot release: id 0 | task 37593 | stop processing: n_tokens = 332, truncated = 0 10.38.056.022 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.112 (> 0.100 thold), f_keep = 0.063 10.38.056.905 I slot launch_slot_: id 0 | task 37750 | processing task, is_child = 0 10.41.433.132 I slot print_timing: id 0 | task 37750 | n_gen = 204, tg = 67.39 t/s, tg_3s = 67.72 t/s 10.44.446.983 I slot print_timing: id 0 | task 37750 | n_gen = 407, tg = 67.37 t/s, tg_3s = 67.36 t/s 10.47.453.850 I slot print_timing: id 0 | task 37750 | n_gen = 609, tg = 67.31 t/s, tg_3s = 67.18 t/s 10.50.467.215 I slot print_timing: id 0 | task 37750 | n_gen = 811, tg = 67.24 t/s, tg_3s = 67.03 t/s 10.53.470.750 I slot print_timing: id 0 | task 37750 | n_gen = 1012, tg = 67.18 t/s, tg_3s = 66.92 t/s 10.53.648.922 I slot print_timing: id 0 | task 37750 | prompt eval time = 363.84 ms / 188 tokens ( 1.94 ms per token, 516.72 tokens per second) 10.53.648.928 I slot print_timing: id 0 | task 37750 | eval time = 15228.17 ms / 1024 tokens ( 14.89 ms per token, 67.18 tokens per second) 10.53.648.929 I slot print_timing: id 0 | task 37750 | total time = 15592.01 ms / 1212 tokens 10.53.648.929 I slot print_timing: id 0 | task 37750 | graphs reused = 37895 10.53.648.930 I slot print_timing: id 0 | task 37750 | graph reallocs = 0 / 0 (same size) / (changed size) 10.53.648.953 I slot release: id 0 | task 37750 | stop processing: n_tokens = 1211, truncated = 0 10.53.652.266 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 10.53.655.114 I slot launch_slot_: id 0 | task 38776 | processing task, is_child = 0 10.57.002.379 I slot print_timing: id 0 | task 38776 | n_gen = 204, tg = 67.45 t/s, tg_3s = 67.78 t/s 10.59.439.919 I slot print_timing: id 0 | task 38776 | prompt eval time = 337.58 ms / 164 tokens ( 2.06 ms per token, 485.81 tokens per second) 10.59.439.922 I slot print_timing: id 0 | task 38776 | eval time = 5447.22 ms / 368 tokens ( 14.84 ms per token, 67.37 tokens per second) 10.59.439.923 I slot print_timing: id 0 | task 38776 | total time = 5784.80 ms / 532 tokens 10.59.439.923 I slot print_timing: id 0 | task 38776 | graphs reused = 38259 10.59.439.924 I slot print_timing: id 0 | task 38776 | graph reallocs = 0 / 0 (same size) / (changed size) 10.59.439.948 I slot release: id 0 | task 38776 | stop processing: n_tokens = 531, truncated = 0 10.59.443.401 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.116 (> 0.100 thold), f_keep = 0.040 10.59.444.781 I slot launch_slot_: id 0 | task 39146 | processing task, is_child = 0 11.02.811.189 I slot print_timing: id 0 | task 39146 | n_gen = 203, tg = 67.17 t/s, tg_3s = 67.50 t/s 11.05.811.818 I slot print_timing: id 0 | task 39146 | n_gen = 405, tg = 67.24 t/s, tg_3s = 67.32 t/s 11.07.594.858 I slot print_timing: id 0 | task 39146 | prompt eval time = 358.92 ms / 181 tokens ( 1.98 ms per token, 504.29 tokens per second) 11.07.594.865 I slot print_timing: id 0 | task 39146 | eval time = 7791.15 ms / 525 tokens ( 14.87 ms per token, 67.26 tokens per second) 11.07.594.865 I slot print_timing: id 0 | task 39146 | total time = 8150.07 ms / 706 tokens 11.07.594.866 I slot print_timing: id 0 | task 39146 | graphs reused = 38780 11.07.594.867 I slot print_timing: id 0 | task 39146 | graph reallocs = 0 / 0 (same size) / (changed size) 11.07.594.889 I slot release: id 0 | task 39146 | stop processing: n_tokens = 705, truncated = 0 11.07.598.375 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.136 (> 0.100 thold), f_keep = 0.030 11.07.600.033 I slot launch_slot_: id 0 | task 39673 | processing task, is_child = 0 11.10.938.645 I slot print_timing: id 0 | task 39673 | n_gen = 204, tg = 67.48 t/s, tg_3s = 67.82 t/s 11.11.768.674 I slot print_timing: id 0 | task 39673 | prompt eval time = 330.44 ms / 154 tokens ( 2.15 ms per token, 466.04 tokens per second) 11.11.768.680 I slot print_timing: id 0 | task 39673 | eval time = 3838.19 ms / 260 tokens ( 14.82 ms per token, 67.48 tokens per second) 11.11.768.680 I slot print_timing: id 0 | task 39673 | total time = 4168.63 ms / 414 tokens 11.11.768.681 I slot print_timing: id 0 | task 39673 | graphs reused = 39037 11.11.768.681 I slot print_timing: id 0 | task 39673 | graph reallocs = 0 / 0 (same size) / (changed size) 11.11.768.701 I slot release: id 0 | task 39673 | stop processing: n_tokens = 413, truncated = 0 11.11.771.951 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.051 11.11.772.966 I slot launch_slot_: id 0 | task 39935 | processing task, is_child = 0 11.13.602.619 I slot print_timing: id 0 | task 39935 | prompt eval time = 318.48 ms / 135 tokens ( 2.36 ms per token, 423.89 tokens per second) 11.13.602.621 I slot print_timing: id 0 | task 39935 | eval time = 1511.16 ms / 103 tokens ( 14.82 ms per token, 67.50 tokens per second) 11.13.602.622 I slot print_timing: id 0 | task 39935 | total time = 1829.64 ms / 238 tokens 11.13.602.623 I slot print_timing: id 0 | task 39935 | graphs reused = 39138 11.13.602.623 I slot print_timing: id 0 | task 39935 | graph reallocs = 0 / 0 (same size) / (changed size) 11.13.602.642 I slot release: id 0 | task 39935 | stop processing: n_tokens = 237, truncated = 0 11.13.606.164 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.117 (> 0.100 thold), f_keep = 0.089 11.13.606.922 I slot launch_slot_: id 0 | task 40040 | processing task, is_child = 0 11.16.971.745 I slot print_timing: id 0 | task 40040 | n_gen = 204, tg = 67.42 t/s, tg_3s = 67.75 t/s 11.19.975.330 I slot print_timing: id 0 | task 40040 | n_gen = 406, tg = 67.33 t/s, tg_3s = 67.25 t/s 11.21.243.676 I slot print_timing: id 0 | task 40040 | prompt eval time = 353.67 ms / 179 tokens ( 1.98 ms per token, 506.13 tokens per second) 11.21.243.679 I slot print_timing: id 0 | task 40040 | eval time = 7283.08 ms / 491 tokens ( 14.86 ms per token, 67.28 tokens per second) 11.21.243.680 I slot print_timing: id 0 | task 40040 | total time = 7636.75 ms / 670 tokens 11.21.243.680 I slot print_timing: id 0 | task 40040 | graphs reused = 39625 11.21.243.681 I slot print_timing: id 0 | task 40040 | graph reallocs = 0 / 0 (same size) / (changed size) 11.21.243.703 I slot release: id 0 | task 40040 | stop processing: n_tokens = 669, truncated = 0 11.21.247.294 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.119 (> 0.100 thold), f_keep = 0.037 11.21.248.966 I slot launch_slot_: id 0 | task 40533 | processing task, is_child = 0 11.24.642.438 I slot print_timing: id 0 | task 40533 | n_gen = 204, tg = 67.43 t/s, tg_3s = 67.76 t/s 11.27.643.521 I slot print_timing: id 0 | task 40533 | n_gen = 406, tg = 67.37 t/s, tg_3s = 67.31 t/s 11.29.109.028 I slot print_timing: id 0 | task 40533 | prompt eval time = 382.91 ms / 210 tokens ( 1.82 ms per token, 548.43 tokens per second) 11.29.109.034 I slot print_timing: id 0 | task 40533 | eval time = 7477.14 ms / 505 tokens ( 14.84 ms per token, 67.41 tokens per second) 11.29.109.034 I slot print_timing: id 0 | task 40533 | total time = 7860.05 ms / 715 tokens 11.29.109.035 I slot print_timing: id 0 | task 40533 | graphs reused = 40126 11.29.109.035 I slot print_timing: id 0 | task 40533 | graph reallocs = 0 / 0 (same size) / (changed size) 11.29.109.059 I slot release: id 0 | task 40533 | stop processing: n_tokens = 714, truncated = 0 11.29.112.315 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.165 (> 0.100 thold), f_keep = 0.029 11.29.113.925 I slot launch_slot_: id 0 | task 41040 | processing task, is_child = 0 11.32.005.056 I slot print_timing: id 0 | task 41040 | prompt eval time = 307.87 ms / 127 tokens ( 2.42 ms per token, 412.51 tokens per second) 11.32.005.061 I slot print_timing: id 0 | task 41040 | eval time = 2583.25 ms / 175 tokens ( 14.85 ms per token, 67.36 tokens per second) 11.32.005.062 I slot print_timing: id 0 | task 41040 | total time = 2891.12 ms / 302 tokens 11.32.005.062 I slot print_timing: id 0 | task 41040 | graphs reused = 40298 11.32.005.063 I slot print_timing: id 0 | task 41040 | graph reallocs = 0 / 0 (same size) / (changed size) 11.32.005.081 I slot release: id 0 | task 41040 | stop processing: n_tokens = 301, truncated = 0 11.32.008.249 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.152 (> 0.100 thold), f_keep = 0.070 11.32.009.128 I slot launch_slot_: id 0 | task 41217 | processing task, is_child = 0 11.35.344.338 I slot print_timing: id 0 | task 41217 | n_gen = 204, tg = 67.39 t/s, tg_3s = 67.72 t/s 11.36.127.813 I slot print_timing: id 0 | task 41217 | prompt eval time = 322.78 ms / 138 tokens ( 2.34 ms per token, 427.54 tokens per second) 11.36.127.819 I slot print_timing: id 0 | task 41217 | eval time = 3795.90 ms / 257 tokens ( 14.83 ms per token, 67.44 tokens per second) 11.36.127.820 I slot print_timing: id 0 | task 41217 | total time = 4118.67 ms / 395 tokens 11.36.127.821 I slot print_timing: id 0 | task 41217 | graphs reused = 40552 11.36.127.821 I slot print_timing: id 0 | task 41217 | graph reallocs = 0 / 0 (same size) / (changed size) 11.36.127.840 I slot release: id 0 | task 41217 | stop processing: n_tokens = 394, truncated = 0 11.36.131.008 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.151 (> 0.100 thold), f_keep = 0.053 11.36.131.975 I slot launch_slot_: id 0 | task 41476 | processing task, is_child = 0 11.39.454.253 I slot print_timing: id 0 | task 41476 | n_gen = 203, tg = 67.32 t/s, tg_3s = 67.65 t/s 11.41.085.049 I slot print_timing: id 0 | task 41476 | prompt eval time = 321.57 ms / 139 tokens ( 2.31 ms per token, 432.25 tokens per second) 11.41.085.054 I slot print_timing: id 0 | task 41476 | eval time = 4631.49 ms / 313 tokens ( 14.84 ms per token, 67.36 tokens per second) 11.41.085.055 I slot print_timing: id 0 | task 41476 | total time = 4953.07 ms / 452 tokens 11.41.085.056 I slot print_timing: id 0 | task 41476 | graphs reused = 40862 11.41.085.056 I slot print_timing: id 0 | task 41476 | graph reallocs = 0 / 0 (same size) / (changed size) 11.41.085.074 I slot release: id 0 | task 41476 | stop processing: n_tokens = 451, truncated = 0 11.41.087.780 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.134 (> 0.100 thold), f_keep = 0.047 11.41.088.749 I slot launch_slot_: id 0 | task 41791 | processing task, is_child = 0 11.44.428.001 I slot print_timing: id 0 | task 41791 | n_gen = 203, tg = 67.13 t/s, tg_3s = 67.47 t/s 11.44.916.580 I slot print_timing: id 0 | task 41791 | prompt eval time = 330.36 ms / 157 tokens ( 2.10 ms per token, 475.24 tokens per second) 11.44.916.583 I slot print_timing: id 0 | task 41791 | eval time = 3497.46 ms / 236 tokens ( 14.88 ms per token, 67.19 tokens per second) 11.44.916.584 I slot print_timing: id 0 | task 41791 | total time = 3827.82 ms / 393 tokens 11.44.916.584 I slot print_timing: id 0 | task 41791 | graphs reused = 41095 11.44.916.585 I slot print_timing: id 0 | task 41791 | graph reallocs = 0 / 0 (same size) / (changed size) 11.44.916.605 I slot release: id 0 | task 41791 | stop processing: n_tokens = 392, truncated = 0 11.44.919.908 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.129 (> 0.100 thold), f_keep = 0.054 11.44.920.869 I slot launch_slot_: id 0 | task 42029 | processing task, is_child = 0 11.48.264.425 I slot print_timing: id 0 | task 42029 | n_gen = 206, tg = 68.24 t/s, tg_3s = 68.58 t/s 11.50.045.931 I slot print_timing: id 0 | task 42029 | prompt eval time = 339.55 ms / 163 tokens ( 2.08 ms per token, 480.04 tokens per second) 11.50.045.936 I slot print_timing: id 0 | task 42029 | eval time = 4785.50 ms / 326 tokens ( 14.72 ms per token, 67.91 tokens per second) 11.50.045.936 I slot print_timing: id 0 | task 42029 | total time = 5125.05 ms / 489 tokens 11.50.045.937 I slot print_timing: id 0 | task 42029 | graphs reused = 41418 11.50.045.938 I slot print_timing: id 0 | task 42029 | graph reallocs = 0 / 0 (same size) / (changed size) 11.50.045.958 I slot release: id 0 | task 42029 | stop processing: n_tokens = 488, truncated = 0 11.50.049.242 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.134 (> 0.100 thold), f_keep = 0.043 11.50.050.350 I slot launch_slot_: id 0 | task 42357 | processing task, is_child = 0 11.53.396.132 I slot print_timing: id 0 | task 42357 | n_gen = 204, tg = 67.41 t/s, tg_3s = 67.74 t/s 11.54.047.565 I slot print_timing: id 0 | task 42357 | prompt eval time = 334.20 ms / 157 tokens ( 2.13 ms per token, 469.78 tokens per second) 11.54.047.571 I slot print_timing: id 0 | task 42357 | eval time = 3663.00 ms / 248 tokens ( 14.83 ms per token, 67.43 tokens per second) 11.54.047.571 I slot print_timing: id 0 | task 42357 | total time = 3997.20 ms / 405 tokens 11.54.047.572 I slot print_timing: id 0 | task 42357 | graphs reused = 41663 11.54.047.572 I slot print_timing: id 0 | task 42357 | graph reallocs = 0 / 0 (same size) / (changed size) 11.54.047.592 I slot release: id 0 | task 42357 | stop processing: n_tokens = 404, truncated = 0 11.54.050.737 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.134 (> 0.100 thold), f_keep = 0.052 11.54.051.745 I slot launch_slot_: id 0 | task 42607 | processing task, is_child = 0 11.57.397.051 I slot print_timing: id 0 | task 42607 | n_gen = 204, tg = 67.37 t/s, tg_3s = 67.70 t/s 12.00.403.016 I slot print_timing: id 0 | task 42607 | n_gen = 406, tg = 67.29 t/s, tg_3s = 67.20 t/s 12.03.405.747 I slot print_timing: id 0 | task 42607 | n_gen = 608, tg = 67.28 t/s, tg_3s = 67.27 t/s 12.03.868.078 I slot print_timing: id 0 | task 42607 | prompt eval time = 332.15 ms / 157 tokens ( 2.12 ms per token, 472.68 tokens per second) 12.03.868.081 I slot print_timing: id 0 | task 42607 | eval time = 9484.17 ms / 639 tokens ( 14.87 ms per token, 67.27 tokens per second) 12.03.868.082 I slot print_timing: id 0 | task 42607 | total time = 9816.32 ms / 796 tokens 12.03.868.082 I slot print_timing: id 0 | task 42607 | graphs reused = 42297 12.03.868.083 I slot print_timing: id 0 | task 42607 | graph reallocs = 0 / 0 (same size) / (changed size) 12.03.868.104 I slot release: id 0 | task 42607 | stop processing: n_tokens = 795, truncated = 0 12.03.871.636 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.134 (> 0.100 thold), f_keep = 0.026 12.03.873.390 I slot launch_slot_: id 0 | task 43248 | processing task, is_child = 0 12.07.217.312 I slot print_timing: id 0 | task 43248 | n_gen = 204, tg = 67.42 t/s, tg_3s = 67.76 t/s 12.07.929.671 I slot print_timing: id 0 | task 43248 | prompt eval time = 333.10 ms / 157 tokens ( 2.12 ms per token, 471.33 tokens per second) 12.07.929.677 I slot print_timing: id 0 | task 43248 | eval time = 3723.17 ms / 252 tokens ( 14.83 ms per token, 67.42 tokens per second) 12.07.929.677 I slot print_timing: id 0 | task 43248 | total time = 4056.27 ms / 409 tokens 12.07.929.678 I slot print_timing: id 0 | task 43248 | graphs reused = 42546 12.07.929.679 I slot print_timing: id 0 | task 43248 | graph reallocs = 0 / 0 (same size) / (changed size) 12.07.929.698 I slot release: id 0 | task 43248 | stop processing: n_tokens = 408, truncated = 0 12.07.933.000 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.122 (> 0.100 thold), f_keep = 0.051 12.07.934.077 I slot launch_slot_: id 0 | task 43502 | processing task, is_child = 0 12.09.340.838 I slot print_timing: id 0 | task 43502 | prompt eval time = 352.35 ms / 172 tokens ( 2.05 ms per token, 488.16 tokens per second) 12.09.340.845 I slot print_timing: id 0 | task 43502 | eval time = 1054.41 ms / 72 tokens ( 14.85 ms per token, 67.34 tokens per second) 12.09.340.846 I slot print_timing: id 0 | task 43502 | total time = 1406.75 ms / 244 tokens 12.09.340.847 I slot print_timing: id 0 | task 43502 | graphs reused = 42616 12.09.340.847 I slot print_timing: id 0 | task 43502 | graph reallocs = 0 / 0 (same size) / (changed size) 12.09.340.870 I slot release: id 0 | task 43502 | stop processing: n_tokens = 243, truncated = 0 12.09.344.124 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.135 (> 0.100 thold), f_keep = 0.091 12.09.345.061 I slot launch_slot_: id 0 | task 43576 | processing task, is_child = 0 12.12.689.083 I slot print_timing: id 0 | task 43576 | n_gen = 204, tg = 67.43 t/s, tg_3s = 67.77 t/s 12.13.478.676 I slot print_timing: id 0 | task 43576 | prompt eval time = 333.63 ms / 163 tokens ( 2.05 ms per token, 488.57 tokens per second) 12.13.478.681 I slot print_timing: id 0 | task 43576 | eval time = 3799.98 ms / 257 tokens ( 14.84 ms per token, 67.37 tokens per second) 12.13.478.682 I slot print_timing: id 0 | task 43576 | total time = 4133.61 ms / 420 tokens 12.13.478.682 I slot print_timing: id 0 | task 43576 | graphs reused = 42870 12.13.478.683 I slot print_timing: id 0 | task 43576 | graph reallocs = 0 / 0 (same size) / (changed size) 12.13.478.705 I slot release: id 0 | task 43576 | stop processing: n_tokens = 419, truncated = 0 12.13.482.536 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.127 (> 0.100 thold), f_keep = 0.050 12.13.483.921 I slot launch_slot_: id 0 | task 43835 | processing task, is_child = 0 12.16.842.015 I slot print_timing: id 0 | task 43835 | n_gen = 204, tg = 67.46 t/s, tg_3s = 67.79 t/s 12.18.712.006 I slot print_timing: id 0 | task 43835 | prompt eval time = 348.89 ms / 165 tokens ( 2.11 ms per token, 472.93 tokens per second) 12.18.712.011 I slot print_timing: id 0 | task 43835 | eval time = 4879.19 ms / 330 tokens ( 14.83 ms per token, 67.43 tokens per second) 12.18.712.012 I slot print_timing: id 0 | task 43835 | total time = 5228.08 ms / 495 tokens 12.18.712.013 I slot print_timing: id 0 | task 43835 | graphs reused = 43197 12.18.712.013 I slot print_timing: id 0 | task 43835 | graph reallocs = 0 / 0 (same size) / (changed size) 12.18.712.038 I slot release: id 0 | task 43835 | stop processing: n_tokens = 494, truncated = 0 12.18.715.557 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.121 (> 0.100 thold), f_keep = 0.043 12.18.716.835 I slot launch_slot_: id 0 | task 44167 | processing task, is_child = 0 12.21.237.846 I slot print_timing: id 0 | task 44167 | prompt eval time = 354.08 ms / 173 tokens ( 2.05 ms per token, 488.58 tokens per second) 12.21.237.852 I slot print_timing: id 0 | task 44167 | eval time = 2166.92 ms / 147 tokens ( 14.84 ms per token, 67.38 tokens per second) 12.21.237.853 I slot print_timing: id 0 | task 44167 | total time = 2521.00 ms / 320 tokens 12.21.237.854 I slot print_timing: id 0 | task 44167 | graphs reused = 43341 12.21.237.854 I slot print_timing: id 0 | task 44167 | graph reallocs = 0 / 0 (same size) / (changed size) 12.21.237.875 I slot release: id 0 | task 44167 | stop processing: n_tokens = 319, truncated = 0 12.21.241.262 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 12.21.242.197 I slot launch_slot_: id 0 | task 44316 | processing task, is_child = 0 12.24.024.857 I slot print_timing: id 0 | task 44316 | prompt eval time = 364.63 ms / 190 tokens ( 1.92 ms per token, 521.08 tokens per second) 12.24.024.863 I slot print_timing: id 0 | task 44316 | eval time = 2418.02 ms / 164 tokens ( 14.83 ms per token, 67.41 tokens per second) 12.24.024.863 I slot print_timing: id 0 | task 44316 | total time = 2782.65 ms / 354 tokens 12.24.024.864 I slot print_timing: id 0 | task 44316 | graphs reused = 43502 12.24.024.865 I slot print_timing: id 0 | task 44316 | graph reallocs = 0 / 0 (same size) / (changed size) 12.24.024.886 I slot release: id 0 | task 44316 | stop processing: n_tokens = 353, truncated = 0 12.24.028.176 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 12.24.029.107 I slot launch_slot_: id 0 | task 44482 | processing task, is_child = 0 12.27.392.609 I slot print_timing: id 0 | task 44482 | n_gen = 204, tg = 67.46 t/s, tg_3s = 67.79 t/s 12.30.130.162 I slot print_timing: id 0 | task 44482 | prompt eval time = 354.12 ms / 173 tokens ( 2.05 ms per token, 488.53 tokens per second) 12.30.130.168 I slot print_timing: id 0 | task 44482 | eval time = 5746.92 ms / 388 tokens ( 14.85 ms per token, 67.34 tokens per second) 12.30.130.168 I slot print_timing: id 0 | task 44482 | total time = 6101.04 ms / 561 tokens 12.30.130.169 I slot print_timing: id 0 | task 44482 | graphs reused = 43886 12.30.130.169 I slot print_timing: id 0 | task 44482 | graph reallocs = 0 / 0 (same size) / (changed size) 12.30.130.190 I slot release: id 0 | task 44482 | stop processing: n_tokens = 560, truncated = 0 12.30.133.443 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.111 (> 0.100 thold), f_keep = 0.038 12.30.134.710 I slot launch_slot_: id 0 | task 44872 | processing task, is_child = 0 12.33.496.044 I slot print_timing: id 0 | task 44872 | n_gen = 203, tg = 67.33 t/s, tg_3s = 67.66 t/s 12.34.700.900 I slot print_timing: id 0 | task 44872 | prompt eval time = 361.21 ms / 190 tokens ( 1.90 ms per token, 526.01 tokens per second) 12.34.700.906 I slot print_timing: id 0 | task 44872 | eval time = 4204.97 ms / 284 tokens ( 14.86 ms per token, 67.30 tokens per second) 12.34.700.907 I slot print_timing: id 0 | task 44872 | total time = 4566.18 ms / 474 tokens 12.34.700.907 I slot print_timing: id 0 | task 44872 | graphs reused = 44167 12.34.700.908 I slot print_timing: id 0 | task 44872 | graph reallocs = 0 / 0 (same size) / (changed size) 12.34.700.930 I slot release: id 0 | task 44872 | stop processing: n_tokens = 473, truncated = 0 12.34.704.186 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.126 (> 0.100 thold), f_keep = 0.049 12.34.705.309 I slot launch_slot_: id 0 | task 45158 | processing task, is_child = 0 12.38.076.013 I slot print_timing: id 0 | task 45158 | n_gen = 204, tg = 67.39 t/s, tg_3s = 67.72 t/s 12.40.976.808 I slot print_timing: id 0 | task 45158 | prompt eval time = 358.24 ms / 183 tokens ( 1.96 ms per token, 510.83 tokens per second) 12.40.976.814 I slot print_timing: id 0 | task 45158 | eval time = 5913.25 ms / 399 tokens ( 14.86 ms per token, 67.31 tokens per second) 12.40.976.815 I slot print_timing: id 0 | task 45158 | total time = 6271.49 ms / 582 tokens 12.40.976.816 I slot print_timing: id 0 | task 45158 | graphs reused = 44562 12.40.976.816 I slot print_timing: id 0 | task 45158 | graph reallocs = 0 / 0 (same size) / (changed size) 12.40.976.838 I slot release: id 0 | task 45158 | stop processing: n_tokens = 581, truncated = 0 12.40.980.250 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 581, t_last = 337689362552 12.40.981.671 I slot launch_slot_: id 0 | task 45559 | processing task, is_child = 0 12.44.080.823 I slot print_timing: id 0 | task 45559 | prompt eval time = 392.87 ms / 222 tokens ( 1.77 ms per token, 565.07 tokens per second) 12.44.080.826 I slot print_timing: id 0 | task 45559 | eval time = 2706.27 ms / 183 tokens ( 14.87 ms per token, 67.25 tokens per second) 12.44.080.826 I slot print_timing: id 0 | task 45559 | total time = 3099.14 ms / 405 tokens 12.44.080.827 I slot print_timing: id 0 | task 45559 | graphs reused = 44742 12.44.080.827 I slot print_timing: id 0 | task 45559 | graph reallocs = 0 / 0 (same size) / (changed size) 12.44.080.855 I slot release: id 0 | task 45559 | stop processing: n_tokens = 404, truncated = 0 12.44.084.038 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.129 (> 0.100 thold), f_keep = 0.052 12.44.085.082 I slot launch_slot_: id 0 | task 45744 | processing task, is_child = 0 12.47.426.953 I slot print_timing: id 0 | task 45744 | n_gen = 203, tg = 67.17 t/s, tg_3s = 67.50 t/s 12.47.694.536 I slot print_timing: id 0 | task 45744 | prompt eval time = 334.45 ms / 163 tokens ( 2.05 ms per token, 487.37 tokens per second) 12.47.694.540 I slot print_timing: id 0 | task 45744 | eval time = 3275.00 ms / 221 tokens ( 14.89 ms per token, 67.18 tokens per second) 12.47.694.541 I slot print_timing: id 0 | task 45744 | total time = 3609.45 ms / 384 tokens 12.47.694.542 I slot print_timing: id 0 | task 45744 | graphs reused = 44960 12.47.694.542 I slot print_timing: id 0 | task 45744 | graph reallocs = 0 / 0 (same size) / (changed size) 12.47.694.571 I slot release: id 0 | task 45744 | stop processing: n_tokens = 383, truncated = 0 12.48.101.117 I srv operator(): operator(): cleaning up before exit...