$ /Users/minipro/quantdiff/llama.cpp/llama-b11770/llama-server -m /Users/minipro/quantdiff/models/campaign/d3334405b962/LFM2.5-24B-A2B-Q4_K_M.gguf --host 127.0.0.1 --port 8089 -c 4096 -np 1 -ngl 999 -fa on --jinja --seed 1234 --no-webui -a quant 0.00.042.885 I srv llama_server: initializing ... 0.00.042.891 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.044.091 I srv init_listene: The UI is disabled 0.00.044.092 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.044.204 W srv llama_server: security: no API key is set and CORS allows all origins (see https://github.com/ggml-org/llama.cpp/pull/25655) 0.00.046.287 I srv load_model: loading model '/Users/minipro/quantdiff/models/campaign/d3334405b962/LFM2.5-24B-A2B-Q4_K_M.gguf' 0.01.031.859 I cmn init: llama threadpool init, n_threads = 8 0.01.099.380 I srv load_model: initializing, n_slots = 1, n_ctx_slot = 4096, kv_unified = 'false' 0.01.104.612 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.01.104.665 I srv llama_server: model loaded 0.01.104.669 I srv llama_server: listening on http://127.0.0.1:8089 0.02.021.233 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.02.021.682 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.03.746.251 I slot print_timing: id 0 | task 0 | prompt eval time = 370.01 ms / 172 tokens ( 2.15 ms per token, 464.85 tokens per second) 0.03.746.256 I slot print_timing: id 0 | task 0 | eval time = 1354.48 ms / 104 tokens ( 13.15 ms per token, 76.04 tokens per second) 0.03.746.257 I slot print_timing: id 0 | task 0 | total time = 1724.49 ms / 276 tokens 0.03.746.257 I slot print_timing: id 0 | task 0 | graphs reused = 102 0.03.746.258 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.03.746.279 I slot release: id 0 | task 0 | stop processing: n_tokens = 275, truncated = 0 0.03.749.991 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.076 0.03.750.341 I slot launch_slot_: id 0 | task 106 | processing task, is_child = 0 0.04.886.260 I slot print_timing: id 0 | task 106 | prompt eval time = 290.48 ms / 123 tokens ( 2.36 ms per token, 423.44 tokens per second) 0.04.886.266 I slot print_timing: id 0 | task 106 | eval time = 845.43 ms / 65 tokens ( 13.21 ms per token, 75.70 tokens per second) 0.04.886.267 I slot print_timing: id 0 | task 106 | total time = 1135.91 ms / 188 tokens 0.04.886.268 I slot print_timing: id 0 | task 106 | graphs reused = 165 0.04.886.268 I slot print_timing: id 0 | task 106 | graph reallocs = 0 / 0 (same size) / (changed size) 0.04.886.286 I slot release: id 0 | task 106 | stop processing: n_tokens = 187, truncated = 0 0.04.889.460 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 0.04.889.778 I slot launch_slot_: id 0 | task 173 | processing task, is_child = 0 0.06.246.199 I slot print_timing: id 0 | task 173 | prompt eval time = 325.66 ms / 163 tokens ( 2.00 ms per token, 500.52 tokens per second) 0.06.246.205 I slot print_timing: id 0 | task 173 | eval time = 1030.75 ms / 79 tokens ( 13.21 ms per token, 75.67 tokens per second) 0.06.246.206 I slot print_timing: id 0 | task 173 | total time = 1356.41 ms / 242 tokens 0.06.246.206 I slot print_timing: id 0 | task 173 | graphs reused = 242 0.06.246.207 I slot print_timing: id 0 | task 173 | graph reallocs = 0 / 0 (same size) / (changed size) 0.06.246.229 I slot release: id 0 | task 173 | stop processing: n_tokens = 241, truncated = 0 0.06.249.516 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.103 (> 0.100 thold), f_keep = 0.087 0.06.250.188 I slot launch_slot_: id 0 | task 254 | processing task, is_child = 0 0.08.473.904 I slot print_timing: id 0 | task 254 | prompt eval time = 369.83 ms / 204 tokens ( 1.81 ms per token, 551.61 tokens per second) 0.08.473.910 I slot print_timing: id 0 | task 254 | eval time = 1853.88 ms / 142 tokens ( 13.15 ms per token, 76.06 tokens per second) 0.08.473.911 I slot print_timing: id 0 | task 254 | total time = 2223.71 ms / 346 tokens 0.08.473.911 I slot print_timing: id 0 | task 254 | graphs reused = 381 0.08.473.912 I slot print_timing: id 0 | task 254 | graph reallocs = 0 / 0 (same size) / (changed size) 0.08.473.935 I slot release: id 0 | task 254 | stop processing: n_tokens = 345, truncated = 0 0.08.477.260 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.187 (> 0.100 thold), f_keep = 0.104 0.08.478.201 I slot launch_slot_: id 0 | task 398 | processing task, is_child = 0 0.10.923.846 I slot print_timing: id 0 | task 398 | prompt eval time = 353.37 ms / 193 tokens ( 1.83 ms per token, 546.18 tokens per second) 0.10.923.852 I slot print_timing: id 0 | task 398 | eval time = 2092.27 ms / 160 tokens ( 13.16 ms per token, 75.99 tokens per second) 0.10.923.853 I slot print_timing: id 0 | task 398 | total time = 2445.63 ms / 353 tokens 0.10.923.854 I slot print_timing: id 0 | task 398 | graphs reused = 538 0.10.923.854 I slot print_timing: id 0 | task 398 | graph reallocs = 0 / 0 (same size) / (changed size) 0.10.923.877 I slot release: id 0 | task 398 | stop processing: n_tokens = 352, truncated = 0 0.10.927.066 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.121 (> 0.100 thold), f_keep = 0.060 0.10.927.910 I slot launch_slot_: id 0 | task 560 | processing task, is_child = 0 0.12.597.762 I slot print_timing: id 0 | task 560 | prompt eval time = 345.55 ms / 174 tokens ( 1.99 ms per token, 503.55 tokens per second) 0.12.597.768 I slot print_timing: id 0 | task 560 | eval time = 1324.30 ms / 101 tokens ( 13.24 ms per token, 75.51 tokens per second) 0.12.597.769 I slot print_timing: id 0 | task 560 | total time = 1669.85 ms / 275 tokens 0.12.597.769 I slot print_timing: id 0 | task 560 | graphs reused = 636 0.12.597.770 I slot print_timing: id 0 | task 560 | graph reallocs = 0 / 0 (same size) / (changed size) 0.12.597.789 I slot release: id 0 | task 560 | stop processing: n_tokens = 274, truncated = 0 0.12.601.035 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 274, t_last = 344069293209 0.12.601.778 I slot launch_slot_: id 0 | task 663 | processing task, is_child = 0 0.14.380.427 I slot print_timing: id 0 | task 663 | prompt eval time = 381.75 ms / 224 tokens ( 1.70 ms per token, 586.78 tokens per second) 0.14.380.433 I slot print_timing: id 0 | task 663 | eval time = 1396.89 ms / 107 tokens ( 13.18 ms per token, 75.88 tokens per second) 0.14.380.433 I slot print_timing: id 0 | task 663 | total time = 1778.64 ms / 331 tokens 0.14.380.434 I slot print_timing: id 0 | task 663 | graphs reused = 740 0.14.380.435 I slot print_timing: id 0 | task 663 | graph reallocs = 0 / 0 (same size) / (changed size) 0.14.380.458 I slot release: id 0 | task 663 | stop processing: n_tokens = 330, truncated = 0 0.14.383.830 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 330, t_last = 344071075878 0.14.384.679 I slot launch_slot_: id 0 | task 772 | processing task, is_child = 0 0.17.498.787 I slot print_timing: id 0 | task 772 | prompt eval time = 430.93 ms / 266 tokens ( 1.62 ms per token, 617.28 tokens per second) 0.17.498.790 I slot print_timing: id 0 | task 772 | eval time = 2683.17 ms / 205 tokens ( 13.15 ms per token, 76.03 tokens per second) 0.17.498.790 I slot print_timing: id 0 | task 772 | total time = 3114.10 ms / 471 tokens 0.17.498.791 I slot print_timing: id 0 | task 772 | graphs reused = 943 0.17.498.792 I slot print_timing: id 0 | task 772 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.498.817 I slot release: id 0 | task 772 | stop processing: n_tokens = 470, truncated = 0 0.17.502.410 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.143 (> 0.100 thold), f_keep = 0.045 0.17.503.691 I slot launch_slot_: id 0 | task 979 | processing task, is_child = 0 0.18.854.548 I slot print_timing: id 0 | task 979 | prompt eval time = 318.91 ms / 147 tokens ( 2.17 ms per token, 460.95 tokens per second) 0.18.854.554 I slot print_timing: id 0 | task 979 | eval time = 1031.94 ms / 79 tokens ( 13.23 ms per token, 75.59 tokens per second) 0.18.854.555 I slot print_timing: id 0 | task 979 | total time = 1350.85 ms / 226 tokens 0.18.854.556 I slot print_timing: id 0 | task 979 | graphs reused = 1020 0.18.854.556 I slot print_timing: id 0 | task 979 | graph reallocs = 0 / 0 (same size) / (changed size) 0.18.854.575 I slot release: id 0 | task 979 | stop processing: n_tokens = 225, truncated = 0 0.18.857.729 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 0.18.858.327 I slot launch_slot_: id 0 | task 1060 | processing task, is_child = 0 0.20.465.464 I slot print_timing: id 0 | task 1060 | prompt eval time = 338.28 ms / 166 tokens ( 2.04 ms per token, 490.72 tokens per second) 0.20.465.470 I slot print_timing: id 0 | task 1060 | eval time = 1268.85 ms / 96 tokens ( 13.36 ms per token, 74.87 tokens per second) 0.20.465.471 I slot print_timing: id 0 | task 1060 | total time = 1607.13 ms / 262 tokens 0.20.465.471 I slot print_timing: id 0 | task 1060 | graphs reused = 1113 0.20.465.472 I slot print_timing: id 0 | task 1060 | graph reallocs = 0 / 0 (same size) / (changed size) 0.20.465.490 I slot release: id 0 | task 1060 | stop processing: n_tokens = 261, truncated = 0 0.20.468.619 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.120 (> 0.100 thold), f_keep = 0.080 0.20.469.353 I slot launch_slot_: id 0 | task 1158 | processing task, is_child = 0 0.22.771.232 I slot print_timing: id 0 | task 1158 | prompt eval time = 344.66 ms / 175 tokens ( 1.97 ms per token, 507.74 tokens per second) 0.22.771.236 I slot print_timing: id 0 | task 1158 | eval time = 1957.20 ms / 150 tokens ( 13.14 ms per token, 76.13 tokens per second) 0.22.771.237 I slot print_timing: id 0 | task 1158 | total time = 2301.87 ms / 325 tokens 0.22.771.237 I slot print_timing: id 0 | task 1158 | graphs reused = 1260 0.22.771.238 I slot print_timing: id 0 | task 1158 | graph reallocs = 0 / 0 (same size) / (changed size) 0.22.771.259 I slot release: id 0 | task 1158 | stop processing: n_tokens = 324, truncated = 0 0.22.774.569 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 324, t_last = 344079466679 0.22.775.360 I slot launch_slot_: id 0 | task 1310 | processing task, is_child = 0 0.25.196.530 I slot print_timing: id 0 | task 1310 | prompt eval time = 380.53 ms / 215 tokens ( 1.77 ms per token, 565.01 tokens per second) 0.25.196.535 I slot print_timing: id 0 | task 1310 | eval time = 2040.64 ms / 156 tokens ( 13.17 ms per token, 75.96 tokens per second) 0.25.196.536 I slot print_timing: id 0 | task 1310 | total time = 2421.16 ms / 371 tokens 0.25.196.537 I slot print_timing: id 0 | task 1310 | graphs reused = 1413 0.25.196.537 I slot print_timing: id 0 | task 1310 | graph reallocs = 0 / 0 (same size) / (changed size) 0.25.196.560 I slot release: id 0 | task 1310 | stop processing: n_tokens = 370, truncated = 0 0.25.199.826 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.119 (> 0.100 thold), f_keep = 0.057 0.25.200.744 I slot launch_slot_: id 0 | task 1468 | processing task, is_child = 0 0.27.230.786 I slot print_timing: id 0 | task 1468 | prompt eval time = 348.45 ms / 177 tokens ( 1.97 ms per token, 507.96 tokens per second) 0.27.230.792 I slot print_timing: id 0 | task 1468 | eval time = 1681.58 ms / 128 tokens ( 13.24 ms per token, 75.52 tokens per second) 0.27.230.793 I slot print_timing: id 0 | task 1468 | total time = 2030.03 ms / 305 tokens 0.27.230.793 I slot print_timing: id 0 | task 1468 | graphs reused = 1538 0.27.230.794 I slot print_timing: id 0 | task 1468 | graph reallocs = 0 / 0 (same size) / (changed size) 0.27.230.814 I slot release: id 0 | task 1468 | stop processing: n_tokens = 304, truncated = 0 0.27.234.087 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.116 (> 0.100 thold), f_keep = 0.069 0.27.234.849 I slot launch_slot_: id 0 | task 1598 | processing task, is_child = 0 0.28.809.266 I slot print_timing: id 0 | task 1598 | prompt eval time = 349.87 ms / 181 tokens ( 1.93 ms per token, 517.33 tokens per second) 0.28.809.272 I slot print_timing: id 0 | task 1598 | eval time = 1224.54 ms / 94 tokens ( 13.17 ms per token, 75.95 tokens per second) 0.28.809.272 I slot print_timing: id 0 | task 1598 | total time = 1574.41 ms / 275 tokens 0.28.809.273 I slot print_timing: id 0 | task 1598 | graphs reused = 1629 0.28.809.274 I slot print_timing: id 0 | task 1598 | graph reallocs = 0 / 0 (same size) / (changed size) 0.28.809.295 I slot release: id 0 | task 1598 | stop processing: n_tokens = 274, truncated = 0 0.28.812.516 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.122 (> 0.100 thold), f_keep = 0.077 0.28.813.297 I slot launch_slot_: id 0 | task 1694 | processing task, is_child = 0 0.30.566.087 I slot print_timing: id 0 | task 1694 | prompt eval time = 345.60 ms / 172 tokens ( 2.01 ms per token, 497.68 tokens per second) 0.30.566.090 I slot print_timing: id 0 | task 1694 | eval time = 1407.18 ms / 108 tokens ( 13.15 ms per token, 76.04 tokens per second) 0.30.566.090 I slot print_timing: id 0 | task 1694 | total time = 1752.78 ms / 280 tokens 0.30.566.091 I slot print_timing: id 0 | task 1694 | graphs reused = 1734 0.30.566.092 I slot print_timing: id 0 | task 1694 | graph reallocs = 0 / 0 (same size) / (changed size) 0.30.566.113 I slot release: id 0 | task 1694 | stop processing: n_tokens = 279, truncated = 0 0.30.569.072 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 0.30.569.763 I slot launch_slot_: id 0 | task 1804 | processing task, is_child = 0 0.32.392.115 I slot print_timing: id 0 | task 1804 | prompt eval time = 316.14 ms / 152 tokens ( 2.08 ms per token, 480.79 tokens per second) 0.32.392.118 I slot print_timing: id 0 | task 1804 | eval time = 1506.20 ms / 115 tokens ( 13.21 ms per token, 75.69 tokens per second) 0.32.392.119 I slot print_timing: id 0 | task 1804 | total time = 1822.34 ms / 267 tokens 0.32.392.119 I slot print_timing: id 0 | task 1804 | graphs reused = 1846 0.32.392.120 I slot print_timing: id 0 | task 1804 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.392.139 I slot release: id 0 | task 1804 | stop processing: n_tokens = 266, truncated = 0 0.32.395.572 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.123 (> 0.100 thold), f_keep = 0.079 0.32.396.337 I slot launch_slot_: id 0 | task 1921 | processing task, is_child = 0 0.35.618.878 I slot print_timing: id 0 | task 1921 | prompt eval time = 342.32 ms / 171 tokens ( 2.00 ms per token, 499.54 tokens per second) 0.35.618.884 I slot print_timing: id 0 | task 1921 | eval time = 2880.21 ms / 220 tokens ( 13.15 ms per token, 76.04 tokens per second) 0.35.618.884 I slot print_timing: id 0 | task 1921 | total time = 3222.53 ms / 391 tokens 0.35.618.885 I slot print_timing: id 0 | task 1921 | graphs reused = 2063 0.35.618.886 I slot print_timing: id 0 | task 1921 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.618.907 I slot release: id 0 | task 1921 | stop processing: n_tokens = 390, truncated = 0 0.35.622.131 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 0.35.623.090 I slot launch_slot_: id 0 | task 2143 | processing task, is_child = 0 0.37.483.622 I slot print_timing: id 0 | task 2143 | prompt eval time = 321.96 ms / 154 tokens ( 2.09 ms per token, 478.32 tokens per second) 0.37.483.628 I slot print_timing: id 0 | task 2143 | eval time = 1538.56 ms / 117 tokens ( 13.26 ms per token, 75.40 tokens per second) 0.37.483.630 I slot print_timing: id 0 | task 2143 | total time = 1860.52 ms / 271 tokens 0.37.483.630 I slot print_timing: id 0 | task 2143 | graphs reused = 2177 0.37.483.631 I slot print_timing: id 0 | task 2143 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.483.651 I slot release: id 0 | task 2143 | stop processing: n_tokens = 270, truncated = 0 0.37.486.894 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.140 (> 0.100 thold), f_keep = 0.078 0.37.487.627 I slot launch_slot_: id 0 | task 2262 | processing task, is_child = 0 0.38.912.778 I slot print_timing: id 0 | task 2262 | prompt eval time = 314.93 ms / 150 tokens ( 2.10 ms per token, 476.30 tokens per second) 0.38.912.784 I slot print_timing: id 0 | task 2262 | eval time = 1110.22 ms / 85 tokens ( 13.22 ms per token, 75.66 tokens per second) 0.38.912.785 I slot print_timing: id 0 | task 2262 | total time = 1425.15 ms / 235 tokens 0.38.912.786 I slot print_timing: id 0 | task 2262 | graphs reused = 2260 0.38.912.786 I slot print_timing: id 0 | task 2262 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.912.805 I slot release: id 0 | task 2262 | stop processing: n_tokens = 234, truncated = 0 0.38.916.079 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.111 (> 0.100 thold), f_keep = 0.090 0.38.916.746 I slot launch_slot_: id 0 | task 2349 | processing task, is_child = 0 0.41.058.986 I slot print_timing: id 0 | task 2349 | prompt eval time = 351.83 ms / 190 tokens ( 1.85 ms per token, 540.03 tokens per second) 0.41.058.992 I slot print_timing: id 0 | task 2349 | eval time = 1790.40 ms / 137 tokens ( 13.16 ms per token, 75.96 tokens per second) 0.41.058.993 I slot print_timing: id 0 | task 2349 | total time = 2142.23 ms / 327 tokens 0.41.058.993 I slot print_timing: id 0 | task 2349 | graphs reused = 2394 0.41.058.994 I slot print_timing: id 0 | task 2349 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.059.015 I slot release: id 0 | task 2349 | stop processing: n_tokens = 326, truncated = 0 0.41.062.251 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.131 (> 0.100 thold), f_keep = 0.064 0.41.063.074 I slot launch_slot_: id 0 | task 2488 | processing task, is_child = 0 0.42.798.318 I slot print_timing: id 0 | task 2488 | prompt eval time = 323.64 ms / 160 tokens ( 2.02 ms per token, 494.37 tokens per second) 0.42.798.324 I slot print_timing: id 0 | task 2488 | eval time = 1411.59 ms / 108 tokens ( 13.19 ms per token, 75.80 tokens per second) 0.42.798.324 I slot print_timing: id 0 | task 2488 | total time = 1735.23 ms / 268 tokens 0.42.798.325 I slot print_timing: id 0 | task 2488 | graphs reused = 2499 0.42.798.325 I slot print_timing: id 0 | task 2488 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.798.344 I slot release: id 0 | task 2488 | stop processing: n_tokens = 267, truncated = 0 0.42.801.524 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 267, t_last = 344099493764 0.42.802.260 I slot launch_slot_: id 0 | task 2598 | processing task, is_child = 0 0.44.369.485 I slot print_timing: id 0 | task 2598 | prompt eval time = 382.95 ms / 218 tokens ( 1.76 ms per token, 569.27 tokens per second) 0.44.369.491 I slot print_timing: id 0 | task 2598 | eval time = 1184.27 ms / 91 tokens ( 13.16 ms per token, 76.00 tokens per second) 0.44.369.492 I slot print_timing: id 0 | task 2598 | total time = 1567.22 ms / 309 tokens 0.44.369.493 I slot print_timing: id 0 | task 2598 | graphs reused = 2587 0.44.369.493 I slot print_timing: id 0 | task 2598 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.369.515 I slot release: id 0 | task 2598 | stop processing: n_tokens = 308, truncated = 0 0.44.373.439 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.109 (> 0.100 thold), f_keep = 0.068 0.44.374.731 I slot launch_slot_: id 0 | task 2691 | processing task, is_child = 0 0.47.250.362 I slot print_timing: id 0 | task 2691 | prompt eval time = 353.64 ms / 193 tokens ( 1.83 ms per token, 545.76 tokens per second) 0.47.250.368 I slot print_timing: id 0 | task 2691 | eval time = 2521.98 ms / 193 tokens ( 13.14 ms per token, 76.13 tokens per second) 0.47.250.368 I slot print_timing: id 0 | task 2691 | total time = 2875.62 ms / 386 tokens 0.47.250.369 I slot print_timing: id 0 | task 2691 | graphs reused = 2777 0.47.250.369 I slot print_timing: id 0 | task 2691 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.250.390 I slot release: id 0 | task 2691 | stop processing: n_tokens = 385, truncated = 0 0.47.253.620 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.104 (> 0.100 thold), f_keep = 0.055 0.47.254.529 I slot launch_slot_: id 0 | task 2886 | processing task, is_child = 0 0.49.734.499 I slot print_timing: id 0 | task 2886 | prompt eval time = 369.18 ms / 201 tokens ( 1.84 ms per token, 544.45 tokens per second) 0.49.734.502 I slot print_timing: id 0 | task 2886 | eval time = 2110.78 ms / 161 tokens ( 13.19 ms per token, 75.80 tokens per second) 0.49.734.503 I slot print_timing: id 0 | task 2886 | total time = 2479.96 ms / 362 tokens 0.49.734.503 I slot print_timing: id 0 | task 2886 | graphs reused = 2935 0.49.734.504 I slot print_timing: id 0 | task 2886 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.734.526 I slot release: id 0 | task 2886 | stop processing: n_tokens = 361, truncated = 0 0.49.738.200 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 361, t_last = 344106429946 0.49.739.268 I slot launch_slot_: id 0 | task 3049 | processing task, is_child = 0 0.51.946.692 I slot print_timing: id 0 | task 3049 | prompt eval time = 403.93 ms / 237 tokens ( 1.70 ms per token, 586.74 tokens per second) 0.51.946.698 I slot print_timing: id 0 | task 3049 | eval time = 1803.49 ms / 138 tokens ( 13.16 ms per token, 75.96 tokens per second) 0.51.946.699 I slot print_timing: id 0 | task 3049 | total time = 2207.42 ms / 375 tokens 0.51.946.699 I slot print_timing: id 0 | task 3049 | graphs reused = 3070 0.51.946.700 I slot print_timing: id 0 | task 3049 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.946.725 I slot release: id 0 | task 3049 | stop processing: n_tokens = 374, truncated = 0 0.51.950.053 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 0.51.950.960 I slot launch_slot_: id 0 | task 3189 | processing task, is_child = 0 0.54.416.913 I slot print_timing: id 0 | task 3189 | prompt eval time = 355.59 ms / 196 tokens ( 1.81 ms per token, 551.19 tokens per second) 0.54.416.919 I slot print_timing: id 0 | task 3189 | eval time = 2110.35 ms / 161 tokens ( 13.19 ms per token, 75.82 tokens per second) 0.54.416.920 I slot print_timing: id 0 | task 3189 | total time = 2465.95 ms / 357 tokens 0.54.416.920 I slot print_timing: id 0 | task 3189 | graphs reused = 3228 0.54.416.921 I slot print_timing: id 0 | task 3189 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.416.945 I slot release: id 0 | task 3189 | stop processing: n_tokens = 356, truncated = 0 0.54.420.189 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.139 (> 0.100 thold), f_keep = 0.059 0.54.421.116 I slot launch_slot_: id 0 | task 3352 | processing task, is_child = 0 0.55.895.668 I slot print_timing: id 0 | task 3352 | prompt eval time = 329.90 ms / 151 tokens ( 2.18 ms per token, 457.71 tokens per second) 0.55.895.675 I slot print_timing: id 0 | task 3352 | eval time = 1144.64 ms / 88 tokens ( 13.16 ms per token, 76.01 tokens per second) 0.55.895.676 I slot print_timing: id 0 | task 3352 | total time = 1474.55 ms / 239 tokens 0.55.895.676 I slot print_timing: id 0 | task 3352 | graphs reused = 3314 0.55.895.677 I slot print_timing: id 0 | task 3352 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.895.695 I slot release: id 0 | task 3352 | stop processing: n_tokens = 238, truncated = 0 0.55.898.893 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.122 (> 0.100 thold), f_keep = 0.092 0.55.899.525 I slot launch_slot_: id 0 | task 3442 | processing task, is_child = 0 0.58.181.588 I slot print_timing: id 0 | task 3442 | prompt eval time = 349.89 ms / 180 tokens ( 1.94 ms per token, 514.44 tokens per second) 0.58.181.594 I slot print_timing: id 0 | task 3442 | eval time = 1932.16 ms / 148 tokens ( 13.14 ms per token, 76.08 tokens per second) 0.58.181.595 I slot print_timing: id 0 | task 3442 | total time = 2282.05 ms / 328 tokens 0.58.181.595 I slot print_timing: id 0 | task 3442 | graphs reused = 3459 0.58.181.596 I slot print_timing: id 0 | task 3442 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.181.617 I slot release: id 0 | task 3442 | stop processing: n_tokens = 327, truncated = 0 0.58.185.493 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 327, t_last = 344114877037 0.58.186.940 I slot launch_slot_: id 0 | task 3592 | processing task, is_child = 0 1.00.740.315 I slot print_timing: id 0 | task 3592 | prompt eval time = 380.28 ms / 211 tokens ( 1.80 ms per token, 554.85 tokens per second) 1.00.740.318 I slot print_timing: id 0 | task 3592 | eval time = 2173.08 ms / 166 tokens ( 13.17 ms per token, 75.93 tokens per second) 1.00.740.318 I slot print_timing: id 0 | task 3592 | total time = 2553.36 ms / 377 tokens 1.00.740.319 I slot print_timing: id 0 | task 3592 | graphs reused = 3622 1.00.740.319 I slot print_timing: id 0 | task 3592 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.740.346 I slot release: id 0 | task 3592 | stop processing: n_tokens = 376, truncated = 0 1.00.743.593 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.113 (> 0.100 thold), f_keep = 0.056 1.00.744.583 I slot launch_slot_: id 0 | task 3760 | processing task, is_child = 0 1.02.663.457 I slot print_timing: id 0 | task 3760 | prompt eval time = 356.30 ms / 186 tokens ( 1.92 ms per token, 522.03 tokens per second) 1.02.663.463 I slot print_timing: id 0 | task 3760 | eval time = 1562.56 ms / 119 tokens ( 13.24 ms per token, 75.52 tokens per second) 1.02.663.464 I slot print_timing: id 0 | task 3760 | total time = 1918.87 ms / 305 tokens 1.02.663.464 I slot print_timing: id 0 | task 3760 | graphs reused = 3738 1.02.663.465 I slot print_timing: id 0 | task 3760 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.663.485 I slot release: id 0 | task 3760 | stop processing: n_tokens = 304, truncated = 0 1.02.666.588 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.128 (> 0.100 thold), f_keep = 0.069 1.02.667.370 I slot launch_slot_: id 0 | task 3881 | processing task, is_child = 0 1.06.004.279 I slot print_timing: id 0 | task 3881 | n_gen = 230, tg = 76.12 t/s, tg_3s = 76.45 t/s 1.07.518.405 I slot print_timing: id 0 | task 3881 | prompt eval time = 328.31 ms / 164 tokens ( 2.00 ms per token, 499.52 tokens per second) 1.07.518.412 I slot print_timing: id 0 | task 3881 | eval time = 4522.72 ms / 345 tokens ( 13.15 ms per token, 76.06 tokens per second) 1.07.518.412 I slot print_timing: id 0 | task 3881 | total time = 4851.03 ms / 509 tokens 1.07.518.413 I slot print_timing: id 0 | task 3881 | graphs reused = 4080 1.07.518.414 I slot print_timing: id 0 | task 3881 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.518.434 I slot release: id 0 | task 3881 | stop processing: n_tokens = 508, truncated = 0 1.07.521.616 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.130 (> 0.100 thold), f_keep = 0.041 1.07.522.827 I slot launch_slot_: id 0 | task 4228 | processing task, is_child = 0 1.09.774.973 I slot print_timing: id 0 | task 4228 | prompt eval time = 330.93 ms / 162 tokens ( 2.04 ms per token, 489.54 tokens per second) 1.09.774.977 I slot print_timing: id 0 | task 4228 | eval time = 1921.21 ms / 147 tokens ( 13.16 ms per token, 75.99 tokens per second) 1.09.774.978 I slot print_timing: id 0 | task 4228 | total time = 2252.14 ms / 309 tokens 1.09.774.978 I slot print_timing: id 0 | task 4228 | graphs reused = 4224 1.09.774.979 I slot print_timing: id 0 | task 4228 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.775.000 I slot release: id 0 | task 4228 | stop processing: n_tokens = 308, truncated = 0 1.09.778.505 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.111 (> 0.100 thold), f_keep = 0.068 1.09.779.417 I slot launch_slot_: id 0 | task 4377 | processing task, is_child = 0 1.11.923.373 I slot print_timing: id 0 | task 4377 | prompt eval time = 354.72 ms / 190 tokens ( 1.87 ms per token, 535.63 tokens per second) 1.11.923.379 I slot print_timing: id 0 | task 4377 | eval time = 1789.23 ms / 137 tokens ( 13.16 ms per token, 76.01 tokens per second) 1.11.923.380 I slot print_timing: id 0 | task 4377 | total time = 2143.95 ms / 327 tokens 1.11.923.381 I slot print_timing: id 0 | task 4377 | graphs reused = 4358 1.11.923.381 I slot print_timing: id 0 | task 4377 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.923.404 I slot release: id 0 | task 4377 | stop processing: n_tokens = 326, truncated = 0 1.11.926.633 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.102 (> 0.100 thold), f_keep = 0.064 1.11.927.490 I slot launch_slot_: id 0 | task 4516 | processing task, is_child = 0 1.14.536.980 I slot print_timing: id 0 | task 4516 | prompt eval time = 375.72 ms / 206 tokens ( 1.82 ms per token, 548.29 tokens per second) 1.14.536.985 I slot print_timing: id 0 | task 4516 | eval time = 2233.77 ms / 170 tokens ( 13.22 ms per token, 75.66 tokens per second) 1.14.536.986 I slot print_timing: id 0 | task 4516 | total time = 2609.48 ms / 376 tokens 1.14.536.987 I slot print_timing: id 0 | task 4516 | graphs reused = 4525 1.14.536.987 I slot print_timing: id 0 | task 4516 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.537.012 I slot release: id 0 | task 4516 | stop processing: n_tokens = 375, truncated = 0 1.14.540.256 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.134 (> 0.100 thold), f_keep = 0.056 1.14.541.172 I slot launch_slot_: id 0 | task 4688 | processing task, is_child = 0 1.16.523.959 I slot print_timing: id 0 | task 4688 | prompt eval time = 324.52 ms / 157 tokens ( 2.07 ms per token, 483.79 tokens per second) 1.16.523.962 I slot print_timing: id 0 | task 4688 | eval time = 1658.26 ms / 127 tokens ( 13.16 ms per token, 75.98 tokens per second) 1.16.523.962 I slot print_timing: id 0 | task 4688 | total time = 1982.78 ms / 284 tokens 1.16.523.963 I slot print_timing: id 0 | task 4688 | graphs reused = 4649 1.16.523.963 I slot print_timing: id 0 | task 4688 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.523.983 I slot release: id 0 | task 4688 | stop processing: n_tokens = 283, truncated = 0 1.16.527.286 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.106 (> 0.100 thold), f_keep = 0.074 1.16.528.239 I slot launch_slot_: id 0 | task 4817 | processing task, is_child = 0 1.19.903.194 I slot print_timing: id 0 | task 4817 | n_gen = 229, tg = 75.88 t/s, tg_3s = 76.21 t/s 1.22.912.549 I slot print_timing: id 0 | task 4817 | n_gen = 457, tg = 75.82 t/s, tg_3s = 75.76 t/s 1.25.925.172 I slot print_timing: id 0 | task 4817 | n_gen = 685, tg = 75.77 t/s, tg_3s = 75.68 t/s 1.28.928.921 I slot print_timing: id 0 | task 4817 | n_gen = 912, tg = 75.72 t/s, tg_3s = 75.57 t/s 1.29.181.008 I slot print_timing: id 0 | task 4817 | prompt eval time = 370.18 ms / 198 tokens ( 1.87 ms per token, 534.88 tokens per second) 1.29.181.014 I slot print_timing: id 0 | task 4817 | eval time = 12282.58 ms / 931 tokens ( 13.21 ms per token, 75.72 tokens per second) 1.29.181.015 I slot print_timing: id 0 | task 4817 | total time = 12652.76 ms / 1129 tokens 1.29.181.015 I slot print_timing: id 0 | task 4817 | graphs reused = 5574 1.29.181.016 I slot print_timing: id 0 | task 4817 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.181.038 I slot release: id 0 | task 4817 | stop processing: n_tokens = 1128, truncated = 0 1.29.184.290 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.168 (> 0.100 thold), f_keep = 0.019 1.29.186.568 I slot launch_slot_: id 0 | task 5750 | processing task, is_child = 0 1.31.998.182 I slot print_timing: id 0 | task 5750 | prompt eval time = 301.31 ms / 125 tokens ( 2.41 ms per token, 414.86 tokens per second) 1.31.998.188 I slot print_timing: id 0 | task 5750 | eval time = 2510.30 ms / 192 tokens ( 13.14 ms per token, 76.09 tokens per second) 1.31.998.188 I slot print_timing: id 0 | task 5750 | total time = 2811.61 ms / 317 tokens 1.31.998.189 I slot print_timing: id 0 | task 5750 | graphs reused = 5763 1.31.998.189 I slot print_timing: id 0 | task 5750 | graph reallocs = 0 / 0 (same size) / (changed size) 1.31.998.207 I slot release: id 0 | task 5750 | stop processing: n_tokens = 316, truncated = 0 1.32.001.435 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.157 (> 0.100 thold), f_keep = 0.066 1.32.002.304 I slot launch_slot_: id 0 | task 5944 | processing task, is_child = 0 1.35.317.848 I slot print_timing: id 0 | task 5944 | n_gen = 229, tg = 75.89 t/s, tg_3s = 76.22 t/s 1.37.229.053 I slot print_timing: id 0 | task 5944 | prompt eval time = 311.24 ms / 134 tokens ( 2.32 ms per token, 430.54 tokens per second) 1.37.229.059 I slot print_timing: id 0 | task 5944 | eval time = 4915.50 ms / 374 tokens ( 13.18 ms per token, 75.88 tokens per second) 1.37.229.060 I slot print_timing: id 0 | task 5944 | total time = 5226.74 ms / 508 tokens 1.37.229.060 I slot print_timing: id 0 | task 5944 | graphs reused = 6134 1.37.229.061 I slot print_timing: id 0 | task 5944 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.229.079 I slot release: id 0 | task 5944 | stop processing: n_tokens = 507, truncated = 0 1.37.232.365 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.142 (> 0.100 thold), f_keep = 0.041 1.37.233.615 I slot launch_slot_: id 0 | task 6320 | processing task, is_child = 0 1.40.064.147 I slot print_timing: id 0 | task 6320 | prompt eval time = 321.87 ms / 148 tokens ( 2.17 ms per token, 459.82 tokens per second) 1.40.064.153 I slot print_timing: id 0 | task 6320 | eval time = 2508.66 ms / 192 tokens ( 13.13 ms per token, 76.14 tokens per second) 1.40.064.155 I slot print_timing: id 0 | task 6320 | total time = 2830.53 ms / 340 tokens 1.40.064.155 I slot print_timing: id 0 | task 6320 | graphs reused = 6323 1.40.064.156 I slot print_timing: id 0 | task 6320 | graph reallocs = 0 / 0 (same size) / (changed size) 1.40.064.176 I slot release: id 0 | task 6320 | stop processing: n_tokens = 339, truncated = 0 1.40.067.354 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.149 (> 0.100 thold), f_keep = 0.062 1.40.068.163 I slot launch_slot_: id 0 | task 6514 | processing task, is_child = 0 1.41.292.106 I slot print_timing: id 0 | task 6514 | prompt eval time = 315.11 ms / 141 tokens ( 2.23 ms per token, 447.47 tokens per second) 1.41.292.112 I slot print_timing: id 0 | task 6514 | eval time = 908.83 ms / 70 tokens ( 13.17 ms per token, 75.92 tokens per second) 1.41.292.112 I slot print_timing: id 0 | task 6514 | total time = 1223.94 ms / 211 tokens 1.41.292.113 I slot print_timing: id 0 | task 6514 | graphs reused = 6391 1.41.292.113 I slot print_timing: id 0 | task 6514 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.292.131 I slot release: id 0 | task 6514 | stop processing: n_tokens = 210, truncated = 0 1.41.295.190 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.107 (> 0.100 thold), f_keep = 0.100 1.41.295.847 I slot launch_slot_: id 0 | task 6586 | processing task, is_child = 0 1.43.886.991 I slot print_timing: id 0 | task 6586 | prompt eval time = 356.31 ms / 196 tokens ( 1.82 ms per token, 550.08 tokens per second) 1.43.886.994 I slot print_timing: id 0 | task 6586 | eval time = 2234.82 ms / 171 tokens ( 13.15 ms per token, 76.07 tokens per second) 1.43.886.995 I slot print_timing: id 0 | task 6586 | total time = 2591.13 ms / 367 tokens 1.43.886.995 I slot print_timing: id 0 | task 6586 | graphs reused = 6559 1.43.886.996 I slot print_timing: id 0 | task 6586 | graph reallocs = 0 / 0 (same size) / (changed size) 1.43.887.026 I slot release: id 0 | task 6586 | stop processing: n_tokens = 366, truncated = 0 1.43.890.583 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 366, t_last = 344160582446 1.43.891.588 I slot launch_slot_: id 0 | task 6759 | processing task, is_child = 0 1.47.384.910 I slot print_timing: id 0 | task 6759 | n_gen = 229, tg = 75.90 t/s, tg_3s = 76.23 t/s 1.47.861.192 I slot print_timing: id 0 | task 6759 | prompt eval time = 489.42 ms / 328 tokens ( 1.49 ms per token, 670.18 tokens per second) 1.47.861.198 I slot print_timing: id 0 | task 6759 | eval time = 3480.17 ms / 265 tokens ( 13.18 ms per token, 75.86 tokens per second) 1.47.861.198 I slot print_timing: id 0 | task 6759 | total time = 3969.59 ms / 593 tokens 1.47.861.199 I slot print_timing: id 0 | task 6759 | graphs reused = 6821 1.47.861.200 I slot print_timing: id 0 | task 6759 | graph reallocs = 0 / 0 (same size) / (changed size) 1.47.861.230 I slot release: id 0 | task 6759 | stop processing: n_tokens = 592, truncated = 0 1.47.864.584 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.143 (> 0.100 thold), f_keep = 0.035 1.47.866.036 I slot launch_slot_: id 0 | task 7026 | processing task, is_child = 0 1.49.312.792 I slot print_timing: id 0 | task 7026 | prompt eval time = 318.38 ms / 147 tokens ( 2.17 ms per token, 461.72 tokens per second) 1.49.312.798 I slot print_timing: id 0 | task 7026 | eval time = 1128.37 ms / 87 tokens ( 13.12 ms per token, 76.22 tokens per second) 1.49.312.799 I slot print_timing: id 0 | task 7026 | total time = 1446.75 ms / 234 tokens 1.49.312.799 I slot print_timing: id 0 | task 7026 | graphs reused = 6906 1.49.312.800 I slot print_timing: id 0 | task 7026 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.312.821 I slot release: id 0 | task 7026 | stop processing: n_tokens = 233, truncated = 0 1.49.316.135 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.115 (> 0.100 thold), f_keep = 0.090 1.49.316.806 I slot launch_slot_: id 0 | task 7115 | processing task, is_child = 0 1.51.347.531 I slot print_timing: id 0 | task 7115 | prompt eval time = 351.36 ms / 182 tokens ( 1.93 ms per token, 517.99 tokens per second) 1.51.347.537 I slot print_timing: id 0 | task 7115 | eval time = 1679.35 ms / 128 tokens ( 13.22 ms per token, 75.62 tokens per second) 1.51.347.538 I slot print_timing: id 0 | task 7115 | total time = 2030.71 ms / 310 tokens 1.51.347.538 I slot print_timing: id 0 | task 7115 | graphs reused = 7031 1.51.347.539 I slot print_timing: id 0 | task 7115 | graph reallocs = 0 / 0 (same size) / (changed size) 1.51.347.558 I slot release: id 0 | task 7115 | stop processing: n_tokens = 309, truncated = 0 1.51.350.856 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 309, t_last = 344168042978 1.51.351.644 I slot launch_slot_: id 0 | task 7245 | processing task, is_child = 0 1.53.211.607 I slot print_timing: id 0 | task 7245 | prompt eval time = 397.27 ms / 230 tokens ( 1.73 ms per token, 578.95 tokens per second) 1.53.211.612 I slot print_timing: id 0 | task 7245 | eval time = 1462.68 ms / 112 tokens ( 13.18 ms per token, 75.89 tokens per second) 1.53.211.613 I slot print_timing: id 0 | task 7245 | total time = 1859.95 ms / 342 tokens 1.53.211.614 I slot print_timing: id 0 | task 7245 | graphs reused = 7140 1.53.211.614 I slot print_timing: id 0 | task 7245 | graph reallocs = 0 / 0 (same size) / (changed size) 1.53.211.639 I slot release: id 0 | task 7245 | stop processing: n_tokens = 341, truncated = 0 1.53.214.880 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 341, t_last = 344169907059 1.53.215.701 I slot launch_slot_: id 0 | task 7359 | processing task, is_child = 0 1.55.343.029 I slot print_timing: id 0 | task 7359 | prompt eval time = 401.99 ms / 239 tokens ( 1.68 ms per token, 594.54 tokens per second) 1.55.343.035 I slot print_timing: id 0 | task 7359 | eval time = 1725.33 ms / 132 tokens ( 13.17 ms per token, 75.93 tokens per second) 1.55.343.036 I slot print_timing: id 0 | task 7359 | total time = 2127.32 ms / 371 tokens 1.55.343.036 I slot print_timing: id 0 | task 7359 | graphs reused = 7269 1.55.343.037 I slot print_timing: id 0 | task 7359 | graph reallocs = 0 / 0 (same size) / (changed size) 1.55.343.062 I slot release: id 0 | task 7359 | stop processing: n_tokens = 370, truncated = 0 1.55.346.248 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.151 (> 0.100 thold), f_keep = 0.065 1.55.347.144 I slot launch_slot_: id 0 | task 7493 | processing task, is_child = 0 1.56.858.617 I slot print_timing: id 0 | task 7493 | prompt eval time = 324.55 ms / 159 tokens ( 2.04 ms per token, 489.91 tokens per second) 1.56.858.623 I slot print_timing: id 0 | task 7493 | eval time = 1186.90 ms / 91 tokens ( 13.19 ms per token, 75.83 tokens per second) 1.56.858.623 I slot print_timing: id 0 | task 7493 | total time = 1511.45 ms / 250 tokens 1.56.858.624 I slot print_timing: id 0 | task 7493 | graphs reused = 7358 1.56.858.625 I slot print_timing: id 0 | task 7493 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.858.648 I slot release: id 0 | task 7493 | stop processing: n_tokens = 249, truncated = 0 1.56.861.802 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.125 (> 0.100 thold), f_keep = 0.084 1.56.862.509 I slot launch_slot_: id 0 | task 7586 | processing task, is_child = 0 1.58.644.947 I slot print_timing: id 0 | task 7586 | prompt eval time = 345.23 ms / 168 tokens ( 2.05 ms per token, 486.63 tokens per second) 1.58.644.953 I slot print_timing: id 0 | task 7586 | eval time = 1437.18 ms / 110 tokens ( 13.19 ms per token, 75.84 tokens per second) 1.58.644.954 I slot print_timing: id 0 | task 7586 | total time = 1782.41 ms / 278 tokens 1.58.644.954 I slot print_timing: id 0 | task 7586 | graphs reused = 7465 1.58.644.955 I slot print_timing: id 0 | task 7586 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.644.973 I slot release: id 0 | task 7586 | stop processing: n_tokens = 277, truncated = 0 1.58.648.020 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.119 (> 0.100 thold), f_keep = 0.076 1.58.648.781 I slot launch_slot_: id 0 | task 7698 | processing task, is_child = 0 2.00.723.133 I slot print_timing: id 0 | task 7698 | prompt eval time = 348.08 ms / 177 tokens ( 1.97 ms per token, 508.50 tokens per second) 2.00.723.139 I slot print_timing: id 0 | task 7698 | eval time = 1726.26 ms / 132 tokens ( 13.18 ms per token, 75.89 tokens per second) 2.00.723.139 I slot print_timing: id 0 | task 7698 | total time = 2074.34 ms / 309 tokens 2.00.723.140 I slot print_timing: id 0 | task 7698 | graphs reused = 7594 2.00.723.140 I slot print_timing: id 0 | task 7698 | graph reallocs = 0 / 0 (same size) / (changed size) 2.00.723.159 I slot release: id 0 | task 7698 | stop processing: n_tokens = 308, truncated = 0 2.00.726.362 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.101 (> 0.100 thold), f_keep = 0.068 2.00.727.231 I slot launch_slot_: id 0 | task 7832 | processing task, is_child = 0 2.02.854.409 I slot print_timing: id 0 | task 7832 | prompt eval time = 375.18 ms / 208 tokens ( 1.80 ms per token, 554.40 tokens per second) 2.02.854.414 I slot print_timing: id 0 | task 7832 | eval time = 1751.99 ms / 134 tokens ( 13.17 ms per token, 75.91 tokens per second) 2.02.854.415 I slot print_timing: id 0 | task 7832 | total time = 2127.17 ms / 342 tokens 2.02.854.416 I slot print_timing: id 0 | task 7832 | graphs reused = 7725 2.02.854.416 I slot print_timing: id 0 | task 7832 | graph reallocs = 0 / 0 (same size) / (changed size) 2.02.854.441 I slot release: id 0 | task 7832 | stop processing: n_tokens = 341, truncated = 0 2.02.857.691 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 2.02.858.636 I slot launch_slot_: id 0 | task 7968 | processing task, is_child = 0 2.05.978.087 I slot print_timing: id 0 | task 7968 | prompt eval time = 327.03 ms / 160 tokens ( 2.04 ms per token, 489.25 tokens per second) 2.05.978.093 I slot print_timing: id 0 | task 7968 | eval time = 2792.41 ms / 213 tokens ( 13.17 ms per token, 75.92 tokens per second) 2.05.978.094 I slot print_timing: id 0 | task 7968 | total time = 3119.44 ms / 373 tokens 2.05.978.094 I slot print_timing: id 0 | task 7968 | graphs reused = 7935 2.05.978.095 I slot print_timing: id 0 | task 7968 | graph reallocs = 0 / 0 (same size) / (changed size) 2.05.978.114 I slot release: id 0 | task 7968 | stop processing: n_tokens = 372, truncated = 0 2.05.981.435 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 372, t_last = 344182673534 2.05.982.314 I slot launch_slot_: id 0 | task 8183 | processing task, is_child = 0 2.09.375.200 I slot print_timing: id 0 | task 8183 | n_gen = 230, tg = 76.05 t/s, tg_3s = 76.38 t/s 2.09.454.441 I slot print_timing: id 0 | task 8183 | prompt eval time = 381.59 ms / 219 tokens ( 1.74 ms per token, 573.91 tokens per second) 2.09.454.446 I slot print_timing: id 0 | task 8183 | eval time = 3090.53 ms / 236 tokens ( 13.15 ms per token, 76.04 tokens per second) 2.09.454.447 I slot print_timing: id 0 | task 8183 | total time = 3472.12 ms / 455 tokens 2.09.454.448 I slot print_timing: id 0 | task 8183 | graphs reused = 8168 2.09.454.448 I slot print_timing: id 0 | task 8183 | graph reallocs = 0 / 0 (same size) / (changed size) 2.09.454.474 I slot release: id 0 | task 8183 | stop processing: n_tokens = 454, truncated = 0 2.09.457.672 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.124 (> 0.100 thold), f_keep = 0.046 2.09.458.713 I slot launch_slot_: id 0 | task 8421 | processing task, is_child = 0 2.11.349.916 I slot print_timing: id 0 | task 8421 | prompt eval time = 343.40 ms / 170 tokens ( 2.02 ms per token, 495.05 tokens per second) 2.11.349.925 I slot print_timing: id 0 | task 8421 | eval time = 1547.79 ms / 118 tokens ( 13.23 ms per token, 75.59 tokens per second) 2.11.349.926 I slot print_timing: id 0 | task 8421 | total time = 1891.19 ms / 288 tokens 2.11.349.927 I slot print_timing: id 0 | task 8421 | graphs reused = 8283 2.11.349.927 I slot print_timing: id 0 | task 8421 | graph reallocs = 0 / 0 (same size) / (changed size) 2.11.349.946 I slot release: id 0 | task 8421 | stop processing: n_tokens = 287, truncated = 0 2.11.353.074 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.124 (> 0.100 thold), f_keep = 0.073 2.11.353.854 I slot launch_slot_: id 0 | task 8541 | processing task, is_child = 0 2.14.383.522 I slot print_timing: id 0 | task 8541 | prompt eval time = 344.33 ms / 169 tokens ( 2.04 ms per token, 490.81 tokens per second) 2.14.383.528 I slot print_timing: id 0 | task 8541 | eval time = 2685.33 ms / 205 tokens ( 13.16 ms per token, 75.97 tokens per second) 2.14.383.529 I slot print_timing: id 0 | task 8541 | total time = 3029.66 ms / 374 tokens 2.14.383.529 I slot print_timing: id 0 | task 8541 | graphs reused = 8485 2.14.383.530 I slot print_timing: id 0 | task 8541 | graph reallocs = 0 / 0 (same size) / (changed size) 2.14.383.549 I slot release: id 0 | task 8541 | stop processing: n_tokens = 373, truncated = 0 2.14.386.983 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 373, t_last = 344191078969 2.14.387.937 I slot launch_slot_: id 0 | task 8748 | processing task, is_child = 0 2.17.311.722 I slot print_timing: id 0 | task 8748 | prompt eval time = 445.51 ms / 287 tokens ( 1.55 ms per token, 644.20 tokens per second) 2.17.311.725 I slot print_timing: id 0 | task 8748 | eval time = 2478.26 ms / 189 tokens ( 13.18 ms per token, 75.86 tokens per second) 2.17.311.726 I slot print_timing: id 0 | task 8748 | total time = 2923.78 ms / 476 tokens 2.17.311.726 I slot print_timing: id 0 | task 8748 | graphs reused = 8672 2.17.311.727 I slot print_timing: id 0 | task 8748 | graph reallocs = 0 / 0 (same size) / (changed size) 2.17.311.756 I slot release: id 0 | task 8748 | stop processing: n_tokens = 475, truncated = 0 2.17.315.126 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 475, t_last = 344194007176 2.17.316.339 I slot launch_slot_: id 0 | task 8939 | processing task, is_child = 0 2.20.314.329 I slot print_timing: id 0 | task 8939 | prompt eval time = 415.71 ms / 255 tokens ( 1.63 ms per token, 613.41 tokens per second) 2.20.314.335 I slot print_timing: id 0 | task 8939 | eval time = 2582.27 ms / 197 tokens ( 13.17 ms per token, 75.90 tokens per second) 2.20.314.336 I slot print_timing: id 0 | task 8939 | total time = 2997.98 ms / 452 tokens 2.20.314.336 I slot print_timing: id 0 | task 8939 | graphs reused = 8866 2.20.314.337 I slot print_timing: id 0 | task 8939 | graph reallocs = 0 / 0 (same size) / (changed size) 2.20.314.364 I slot release: id 0 | task 8939 | stop processing: n_tokens = 451, truncated = 0 2.20.317.675 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 2.20.318.813 I slot launch_slot_: id 0 | task 9138 | processing task, is_child = 0 2.21.957.624 I slot print_timing: id 0 | task 9138 | prompt eval time = 327.51 ms / 163 tokens ( 2.01 ms per token, 497.70 tokens per second) 2.21.957.631 I slot print_timing: id 0 | task 9138 | eval time = 1311.30 ms / 100 tokens ( 13.25 ms per token, 75.50 tokens per second) 2.21.957.632 I slot print_timing: id 0 | task 9138 | total time = 1638.80 ms / 263 tokens 2.21.957.632 I slot print_timing: id 0 | task 9138 | graphs reused = 8963 2.21.957.633 I slot print_timing: id 0 | task 9138 | graph reallocs = 0 / 0 (same size) / (changed size) 2.21.957.652 I slot release: id 0 | task 9138 | stop processing: n_tokens = 262, truncated = 0 2.21.960.706 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.104 (> 0.100 thold), f_keep = 0.080 2.21.961.426 I slot launch_slot_: id 0 | task 9240 | processing task, is_child = 0 2.23.849.714 I slot print_timing: id 0 | task 9240 | prompt eval time = 372.56 ms / 201 tokens ( 1.85 ms per token, 539.51 tokens per second) 2.23.849.720 I slot print_timing: id 0 | task 9240 | eval time = 1515.72 ms / 116 tokens ( 13.18 ms per token, 75.87 tokens per second) 2.23.849.720 I slot print_timing: id 0 | task 9240 | total time = 1888.28 ms / 317 tokens 2.23.849.721 I slot print_timing: id 0 | task 9240 | graphs reused = 9076 2.23.849.722 I slot print_timing: id 0 | task 9240 | graph reallocs = 0 / 0 (same size) / (changed size) 2.23.849.743 I slot release: id 0 | task 9240 | stop processing: n_tokens = 316, truncated = 0 2.23.852.706 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.134 (> 0.100 thold), f_keep = 0.066 2.23.853.573 I slot launch_slot_: id 0 | task 9358 | processing task, is_child = 0 2.25.182.142 I slot print_timing: id 0 | task 9358 | prompt eval time = 323.34 ms / 157 tokens ( 2.06 ms per token, 485.56 tokens per second) 2.25.182.148 I slot print_timing: id 0 | task 9358 | eval time = 1005.22 ms / 77 tokens ( 13.23 ms per token, 75.61 tokens per second) 2.25.182.149 I slot print_timing: id 0 | task 9358 | total time = 1328.56 ms / 234 tokens 2.25.182.149 I slot print_timing: id 0 | task 9358 | graphs reused = 9151 2.25.182.150 I slot print_timing: id 0 | task 9358 | graph reallocs = 0 / 0 (same size) / (changed size) 2.25.182.169 I slot release: id 0 | task 9358 | stop processing: n_tokens = 233, truncated = 0 2.25.186.123 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 233, t_last = 344201877590 2.25.187.199 I slot launch_slot_: id 0 | task 9437 | processing task, is_child = 0 2.27.628.501 I slot print_timing: id 0 | task 9437 | prompt eval time = 387.32 ms / 226 tokens ( 1.71 ms per token, 583.50 tokens per second) 2.27.628.507 I slot print_timing: id 0 | task 9437 | eval time = 2053.97 ms / 157 tokens ( 13.17 ms per token, 75.95 tokens per second) 2.27.628.508 I slot print_timing: id 0 | task 9437 | total time = 2441.29 ms / 383 tokens 2.27.628.509 I slot print_timing: id 0 | task 9437 | graphs reused = 9305 2.27.628.509 I slot print_timing: id 0 | task 9437 | graph reallocs = 0 / 0 (same size) / (changed size) 2.27.628.534 I slot release: id 0 | task 9437 | stop processing: n_tokens = 382, truncated = 0 2.27.632.283 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 382, t_last = 344204323954 2.27.633.211 I slot launch_slot_: id 0 | task 9596 | processing task, is_child = 0 2.30.047.501 I slot print_timing: id 0 | task 9596 | prompt eval time = 507.95 ms / 356 tokens ( 1.43 ms per token, 700.86 tokens per second) 2.30.047.508 I slot print_timing: id 0 | task 9596 | eval time = 1906.34 ms / 146 tokens ( 13.15 ms per token, 76.06 tokens per second) 2.30.047.508 I slot print_timing: id 0 | task 9596 | total time = 2414.28 ms / 502 tokens 2.30.047.509 I slot print_timing: id 0 | task 9596 | graphs reused = 9449 2.30.047.509 I slot print_timing: id 0 | task 9596 | graph reallocs = 0 / 0 (same size) / (changed size) 2.30.047.539 I slot release: id 0 | task 9596 | stop processing: n_tokens = 501, truncated = 0 2.30.051.359 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 501, t_last = 344206742959 2.30.052.584 I slot launch_slot_: id 0 | task 9744 | processing task, is_child = 0 2.33.647.236 I slot print_timing: id 0 | task 9744 | n_gen = 229, tg = 75.77 t/s, tg_3s = 76.10 t/s 2.33.991.912 I slot print_timing: id 0 | task 9744 | prompt eval time = 585.42 ms / 427 tokens ( 1.37 ms per token, 729.39 tokens per second) 2.33.991.918 I slot print_timing: id 0 | task 9744 | eval time = 3353.90 ms / 255 tokens ( 13.20 ms per token, 75.73 tokens per second) 2.33.991.919 I slot print_timing: id 0 | task 9744 | total time = 3939.32 ms / 682 tokens 2.33.991.919 I slot print_timing: id 0 | task 9744 | graphs reused = 9701 2.33.991.920 I slot print_timing: id 0 | task 9744 | graph reallocs = 0 / 0 (same size) / (changed size) 2.33.991.954 I slot release: id 0 | task 9744 | stop processing: n_tokens = 681, truncated = 0 2.33.996.100 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 681, t_last = 344210687374 2.33.997.661 I slot launch_slot_: id 0 | task 10001 | processing task, is_child = 0 2.37.259.922 I slot print_timing: id 0 | task 10001 | prompt eval time = 636.03 ms / 481 tokens ( 1.32 ms per token, 756.25 tokens per second) 2.37.259.928 I slot print_timing: id 0 | task 10001 | eval time = 2626.22 ms / 200 tokens ( 13.20 ms per token, 75.77 tokens per second) 2.37.259.929 I slot print_timing: id 0 | task 10001 | total time = 3262.25 ms / 681 tokens 2.37.259.929 I slot print_timing: id 0 | task 10001 | graphs reused = 9898 2.37.259.930 I slot print_timing: id 0 | task 10001 | graph reallocs = 0 / 0 (same size) / (changed size) 2.37.259.966 I slot release: id 0 | task 10001 | stop processing: n_tokens = 680, truncated = 0 2.37.263.879 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 680, t_last = 344213955387 2.37.265.435 I slot launch_slot_: id 0 | task 10203 | processing task, is_child = 0 2.40.205.086 I slot print_timing: id 0 | task 10203 | prompt eval time = 619.30 ms / 456 tokens ( 1.36 ms per token, 736.31 tokens per second) 2.40.205.092 I slot print_timing: id 0 | task 10203 | eval time = 2320.34 ms / 177 tokens ( 13.18 ms per token, 75.85 tokens per second) 2.40.205.093 I slot print_timing: id 0 | task 10203 | total time = 2939.64 ms / 633 tokens 2.40.205.094 I slot print_timing: id 0 | task 10203 | graphs reused = 10072 2.40.205.094 I slot print_timing: id 0 | task 10203 | graph reallocs = 0 / 0 (same size) / (changed size) 2.40.205.132 I slot release: id 0 | task 10203 | stop processing: n_tokens = 632, truncated = 0 2.40.208.798 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 632, t_last = 344216900552 2.40.210.261 I slot launch_slot_: id 0 | task 10382 | processing task, is_child = 0 2.41.962.574 I slot print_timing: id 0 | task 10382 | prompt eval time = 444.11 ms / 290 tokens ( 1.53 ms per token, 652.99 tokens per second) 2.41.962.583 I slot print_timing: id 0 | task 10382 | eval time = 1308.20 ms / 100 tokens ( 13.21 ms per token, 75.68 tokens per second) 2.41.962.584 I slot print_timing: id 0 | task 10382 | total time = 1752.31 ms / 390 tokens 2.41.962.584 I slot print_timing: id 0 | task 10382 | graphs reused = 10170 2.41.962.585 I slot print_timing: id 0 | task 10382 | graph reallocs = 0 / 0 (same size) / (changed size) 2.41.962.611 I slot release: id 0 | task 10382 | stop processing: n_tokens = 389, truncated = 0 2.41.966.681 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 389, t_last = 344218658031 2.41.967.669 I slot launch_slot_: id 0 | task 10484 | processing task, is_child = 0 2.45.566.431 I slot print_timing: id 0 | task 10484 | n_gen = 229, tg = 75.87 t/s, tg_3s = 76.20 t/s 2.46.079.130 I slot print_timing: id 0 | task 10484 | prompt eval time = 593.59 ms / 439 tokens ( 1.35 ms per token, 739.56 tokens per second) 2.46.079.136 I slot print_timing: id 0 | task 10484 | eval time = 3517.85 ms / 268 tokens ( 13.18 ms per token, 75.90 tokens per second) 2.46.079.137 I slot print_timing: id 0 | task 10484 | total time = 4111.45 ms / 707 tokens 2.46.079.137 I slot print_timing: id 0 | task 10484 | graphs reused = 10435 2.46.079.138 I slot print_timing: id 0 | task 10484 | graph reallocs = 0 / 0 (same size) / (changed size) 2.46.079.174 I slot release: id 0 | task 10484 | stop processing: n_tokens = 706, truncated = 0 2.46.082.824 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 706, t_last = 344222774594 2.46.084.321 I slot launch_slot_: id 0 | task 10754 | processing task, is_child = 0 2.49.647.060 I slot print_timing: id 0 | task 10754 | n_gen = 229, tg = 75.77 t/s, tg_3s = 76.10 t/s 2.52.658.644 I slot print_timing: id 0 | task 10754 | n_gen = 457, tg = 75.74 t/s, tg_3s = 75.71 t/s 2.55.660.158 I slot print_timing: id 0 | task 10754 | n_gen = 684, tg = 75.70 t/s, tg_3s = 75.63 t/s 2.58.672.132 I slot print_timing: id 0 | task 10754 | n_gen = 911, tg = 75.62 t/s, tg_3s = 75.37 t/s 2.59.866.544 I slot print_timing: id 0 | task 10754 | prompt eval time = 553.47 ms / 396 tokens ( 1.40 ms per token, 715.49 tokens per second) 2.59.866.551 I slot print_timing: id 0 | task 10754 | eval time = 13228.75 ms / 1001 tokens ( 13.23 ms per token, 75.59 tokens per second) 2.59.866.552 I slot print_timing: id 0 | task 10754 | total time = 13782.22 ms / 1397 tokens 2.59.866.552 I slot print_timing: id 0 | task 10754 | graphs reused = 11430 2.59.866.553 I slot print_timing: id 0 | task 10754 | graph reallocs = 0 / 0 (same size) / (changed size) 2.59.866.588 I slot release: id 0 | task 10754 | stop processing: n_tokens = 1396, truncated = 0 2.59.870.468 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1396, t_last = 344236562008 2.59.873.340 I slot launch_slot_: id 0 | task 11757 | processing task, is_child = 0 3.01.464.630 I slot print_timing: id 0 | task 11757 | prompt eval time = 499.97 ms / 342 tokens ( 1.46 ms per token, 684.04 tokens per second) 3.01.464.637 I slot print_timing: id 0 | task 11757 | eval time = 1091.31 ms / 84 tokens ( 13.15 ms per token, 76.06 tokens per second) 3.01.464.638 I slot print_timing: id 0 | task 11757 | total time = 1591.28 ms / 426 tokens 3.01.464.638 I slot print_timing: id 0 | task 11757 | graphs reused = 11512 3.01.464.639 I slot print_timing: id 0 | task 11757 | graph reallocs = 0 / 0 (same size) / (changed size) 3.01.464.671 I slot release: id 0 | task 11757 | stop processing: n_tokens = 425, truncated = 0 3.01.468.053 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 425, t_last = 344238160091 3.01.469.070 I slot launch_slot_: id 0 | task 11843 | processing task, is_child = 0 3.03.390.570 I slot print_timing: id 0 | task 11843 | prompt eval time = 471.95 ms / 314 tokens ( 1.50 ms per token, 665.32 tokens per second) 3.03.390.576 I slot print_timing: id 0 | task 11843 | eval time = 1449.54 ms / 111 tokens ( 13.18 ms per token, 75.89 tokens per second) 3.03.390.576 I slot print_timing: id 0 | task 11843 | total time = 1921.49 ms / 425 tokens 3.03.390.577 I slot print_timing: id 0 | task 11843 | graphs reused = 11621 3.03.390.578 I slot print_timing: id 0 | task 11843 | graph reallocs = 0 / 0 (same size) / (changed size) 3.03.390.610 I slot release: id 0 | task 11843 | stop processing: n_tokens = 424, truncated = 0 3.03.394.392 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 344240086030 3.03.395.484 I slot launch_slot_: id 0 | task 11956 | processing task, is_child = 0 3.05.239.834 I slot print_timing: id 0 | task 11956 | prompt eval time = 555.84 ms / 396 tokens ( 1.40 ms per token, 712.44 tokens per second) 3.05.239.841 I slot print_timing: id 0 | task 11956 | eval time = 1288.50 ms / 98 tokens ( 13.28 ms per token, 75.28 tokens per second) 3.05.239.842 I slot print_timing: id 0 | task 11956 | total time = 1844.34 ms / 494 tokens 3.05.239.843 I slot print_timing: id 0 | task 11956 | graphs reused = 11717 3.05.239.843 I slot print_timing: id 0 | task 11956 | graph reallocs = 0 / 0 (same size) / (changed size) 3.05.239.875 I slot release: id 0 | task 11956 | stop processing: n_tokens = 493, truncated = 0 3.05.244.487 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 493, t_last = 344241935295 3.05.246.431 I slot launch_slot_: id 0 | task 12056 | processing task, is_child = 0 3.08.751.862 I slot print_timing: id 0 | task 12056 | n_gen = 229, tg = 75.82 t/s, tg_3s = 76.15 t/s 3.11.747.269 I slot print_timing: id 0 | task 12056 | prompt eval time = 498.28 ms / 339 tokens ( 1.47 ms per token, 680.34 tokens per second) 3.11.747.275 I slot print_timing: id 0 | task 12056 | eval time = 6002.55 ms / 456 tokens ( 13.19 ms per token, 75.80 tokens per second) 3.11.747.276 I slot print_timing: id 0 | task 12056 | total time = 6500.83 ms / 795 tokens 3.11.747.276 I slot print_timing: id 0 | task 12056 | graphs reused = 12169 3.11.747.277 I slot print_timing: id 0 | task 12056 | graph reallocs = 0 / 0 (same size) / (changed size) 3.11.747.306 I slot release: id 0 | task 12056 | stop processing: n_tokens = 794, truncated = 0 3.11.750.891 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 794, t_last = 344248442726 3.11.752.672 I slot launch_slot_: id 0 | task 12514 | processing task, is_child = 0 3.13.681.586 I slot print_timing: id 0 | task 12514 | prompt eval time = 432.05 ms / 267 tokens ( 1.62 ms per token, 617.98 tokens per second) 3.13.681.591 I slot print_timing: id 0 | task 12514 | eval time = 1496.85 ms / 114 tokens ( 13.25 ms per token, 75.49 tokens per second) 3.13.681.592 I slot print_timing: id 0 | task 12514 | total time = 1928.90 ms / 381 tokens 3.13.681.593 I slot print_timing: id 0 | task 12514 | graphs reused = 12281 3.13.681.593 I slot print_timing: id 0 | task 12514 | graph reallocs = 0 / 0 (same size) / (changed size) 3.13.681.617 I slot release: id 0 | task 12514 | stop processing: n_tokens = 380, truncated = 0 3.13.685.181 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 380, t_last = 344250377037 3.13.686.165 I slot launch_slot_: id 0 | task 12630 | processing task, is_child = 0 3.16.863.378 I slot print_timing: id 0 | task 12630 | prompt eval time = 522.43 ms / 360 tokens ( 1.45 ms per token, 689.09 tokens per second) 3.16.863.384 I slot print_timing: id 0 | task 12630 | eval time = 2654.77 ms / 202 tokens ( 13.21 ms per token, 75.71 tokens per second) 3.16.863.385 I slot print_timing: id 0 | task 12630 | total time = 3177.20 ms / 562 tokens 3.16.863.385 I slot print_timing: id 0 | task 12630 | graphs reused = 12480 3.16.863.386 I slot print_timing: id 0 | task 12630 | graph reallocs = 0 / 0 (same size) / (changed size) 3.16.863.421 I slot release: id 0 | task 12630 | stop processing: n_tokens = 561, truncated = 0 3.16.867.078 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 561, t_last = 344253558841 3.16.868.482 I slot launch_slot_: id 0 | task 12834 | processing task, is_child = 0 3.18.651.921 I slot print_timing: id 0 | task 12834 | prompt eval time = 461.08 ms / 296 tokens ( 1.56 ms per token, 641.97 tokens per second) 3.18.651.927 I slot print_timing: id 0 | task 12834 | eval time = 1322.35 ms / 101 tokens ( 13.22 ms per token, 75.62 tokens per second) 3.18.651.927 I slot print_timing: id 0 | task 12834 | total time = 1783.43 ms / 397 tokens 3.18.651.928 I slot print_timing: id 0 | task 12834 | graphs reused = 12579 3.18.651.928 I slot print_timing: id 0 | task 12834 | graph reallocs = 0 / 0 (same size) / (changed size) 3.18.651.953 I slot release: id 0 | task 12834 | stop processing: n_tokens = 396, truncated = 0 3.18.655.342 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 396, t_last = 344255347373 3.18.656.310 I slot launch_slot_: id 0 | task 12937 | processing task, is_child = 0 3.21.739.799 I slot print_timing: id 0 | task 12937 | prompt eval time = 438.11 ms / 275 tokens ( 1.59 ms per token, 627.69 tokens per second) 3.21.739.802 I slot print_timing: id 0 | task 12937 | eval time = 2645.37 ms / 202 tokens ( 13.16 ms per token, 75.98 tokens per second) 3.21.739.802 I slot print_timing: id 0 | task 12937 | total time = 3083.48 ms / 477 tokens 3.21.739.803 I slot print_timing: id 0 | task 12937 | graphs reused = 12779 3.21.739.803 I slot print_timing: id 0 | task 12937 | graph reallocs = 0 / 0 (same size) / (changed size) 3.21.739.830 I slot release: id 0 | task 12937 | stop processing: n_tokens = 476, truncated = 0 3.21.743.273 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 476, t_last = 344258435250 3.21.744.388 I slot launch_slot_: id 0 | task 13141 | processing task, is_child = 0 3.23.331.482 I slot print_timing: id 0 | task 13141 | prompt eval time = 444.12 ms / 287 tokens ( 1.55 ms per token, 646.22 tokens per second) 3.23.331.488 I slot print_timing: id 0 | task 13141 | eval time = 1142.97 ms / 87 tokens ( 13.29 ms per token, 75.24 tokens per second) 3.23.331.488 I slot print_timing: id 0 | task 13141 | total time = 1587.09 ms / 374 tokens 3.23.331.489 I slot print_timing: id 0 | task 13141 | graphs reused = 12864 3.23.331.489 I slot print_timing: id 0 | task 13141 | graph reallocs = 0 / 0 (same size) / (changed size) 3.23.331.523 I slot release: id 0 | task 13141 | stop processing: n_tokens = 373, truncated = 0 3.23.334.967 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 373, t_last = 344260026943 3.23.335.915 I slot launch_slot_: id 0 | task 13230 | processing task, is_child = 0 3.25.220.180 I slot print_timing: id 0 | task 13230 | prompt eval time = 434.05 ms / 266 tokens ( 1.63 ms per token, 612.83 tokens per second) 3.25.220.187 I slot print_timing: id 0 | task 13230 | eval time = 1450.20 ms / 111 tokens ( 13.18 ms per token, 75.85 tokens per second) 3.25.220.187 I slot print_timing: id 0 | task 13230 | total time = 1884.26 ms / 377 tokens 3.25.220.188 I slot print_timing: id 0 | task 13230 | graphs reused = 12973 3.25.220.189 I slot print_timing: id 0 | task 13230 | graph reallocs = 0 / 0 (same size) / (changed size) 3.25.220.219 I slot release: id 0 | task 13230 | stop processing: n_tokens = 376, truncated = 0 3.25.223.953 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 376, t_last = 344261915639 3.25.224.885 I slot launch_slot_: id 0 | task 13343 | processing task, is_child = 0 3.28.113.689 I slot print_timing: id 0 | task 13343 | prompt eval time = 591.16 ms / 435 tokens ( 1.36 ms per token, 735.84 tokens per second) 3.28.113.700 I slot print_timing: id 0 | task 13343 | eval time = 2297.63 ms / 175 tokens ( 13.20 ms per token, 75.73 tokens per second) 3.28.113.701 I slot print_timing: id 0 | task 13343 | total time = 2888.79 ms / 610 tokens 3.28.113.701 I slot print_timing: id 0 | task 13343 | graphs reused = 13145 3.28.113.702 I slot print_timing: id 0 | task 13343 | graph reallocs = 0 / 0 (same size) / (changed size) 3.28.113.742 I slot release: id 0 | task 13343 | stop processing: n_tokens = 609, truncated = 0 3.28.118.225 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 609, t_last = 344264809162 3.28.120.539 I slot launch_slot_: id 0 | task 13520 | processing task, is_child = 0 3.29.926.401 I slot print_timing: id 0 | task 13520 | prompt eval time = 467.78 ms / 307 tokens ( 1.52 ms per token, 656.29 tokens per second) 3.29.926.404 I slot print_timing: id 0 | task 13520 | eval time = 1338.07 ms / 102 tokens ( 13.25 ms per token, 75.48 tokens per second) 3.29.926.405 I slot print_timing: id 0 | task 13520 | total time = 1805.85 ms / 409 tokens 3.29.926.405 I slot print_timing: id 0 | task 13520 | graphs reused = 13245 3.29.926.406 I slot print_timing: id 0 | task 13520 | graph reallocs = 0 / 0 (same size) / (changed size) 3.29.926.433 I slot release: id 0 | task 13520 | stop processing: n_tokens = 408, truncated = 0 3.29.931.546 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 408, t_last = 344266621853 3.29.932.769 I slot launch_slot_: id 0 | task 13624 | processing task, is_child = 0 3.33.692.252 I slot print_timing: id 0 | task 13624 | prompt eval time = 963.56 ms / 675 tokens ( 1.43 ms per token, 700.53 tokens per second) 3.33.692.259 I slot print_timing: id 0 | task 13624 | eval time = 2795.91 ms / 213 tokens ( 13.19 ms per token, 75.82 tokens per second) 3.33.692.260 I slot print_timing: id 0 | task 13624 | total time = 3759.48 ms / 888 tokens 3.33.692.260 I slot print_timing: id 0 | task 13624 | graphs reused = 13455 3.33.692.261 I slot print_timing: id 0 | task 13624 | graph reallocs = 0 / 0 (same size) / (changed size) 3.33.692.313 I slot release: id 0 | task 13624 | stop processing: n_tokens = 887, truncated = 0 3.33.695.860 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 887, t_last = 344270387733 3.33.697.762 I slot launch_slot_: id 0 | task 13840 | processing task, is_child = 0 3.35.777.610 I slot print_timing: id 0 | task 13840 | prompt eval time = 445.78 ms / 287 tokens ( 1.55 ms per token, 643.81 tokens per second) 3.35.777.616 I slot print_timing: id 0 | task 13840 | eval time = 1634.06 ms / 125 tokens ( 13.18 ms per token, 75.88 tokens per second) 3.35.777.617 I slot print_timing: id 0 | task 13840 | total time = 2079.84 ms / 412 tokens 3.35.777.617 I slot print_timing: id 0 | task 13840 | graphs reused = 13578 3.35.777.618 I slot print_timing: id 0 | task 13840 | graph reallocs = 0 / 0 (same size) / (changed size) 3.35.777.646 I slot release: id 0 | task 13840 | stop processing: n_tokens = 411, truncated = 0 3.35.781.496 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 344272473066 3.35.782.617 I slot launch_slot_: id 0 | task 13967 | processing task, is_child = 0 3.37.722.221 I slot print_timing: id 0 | task 13967 | prompt eval time = 656.04 ms / 497 tokens ( 1.32 ms per token, 757.57 tokens per second) 3.37.722.224 I slot print_timing: id 0 | task 13967 | eval time = 1283.55 ms / 98 tokens ( 13.23 ms per token, 75.57 tokens per second) 3.37.722.225 I slot print_timing: id 0 | task 13967 | total time = 1939.59 ms / 595 tokens 3.37.722.226 I slot print_timing: id 0 | task 13967 | graphs reused = 13673 3.37.722.226 I slot print_timing: id 0 | task 13967 | graph reallocs = 0 / 0 (same size) / (changed size) 3.37.722.265 I slot release: id 0 | task 13967 | stop processing: n_tokens = 594, truncated = 0 3.37.727.722 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 594, t_last = 344274417685 3.37.729.749 I slot launch_slot_: id 0 | task 14067 | processing task, is_child = 0 3.40.821.573 I slot print_timing: id 0 | task 14067 | prompt eval time = 899.65 ms / 609 tokens ( 1.48 ms per token, 676.93 tokens per second) 3.40.821.579 I slot print_timing: id 0 | task 14067 | eval time = 2192.17 ms / 167 tokens ( 13.21 ms per token, 75.72 tokens per second) 3.40.821.580 I slot print_timing: id 0 | task 14067 | total time = 3091.81 ms / 776 tokens 3.40.821.581 I slot print_timing: id 0 | task 14067 | graphs reused = 13837 3.40.821.581 I slot print_timing: id 0 | task 14067 | graph reallocs = 0 / 0 (same size) / (changed size) 3.40.821.625 I slot release: id 0 | task 14067 | stop processing: n_tokens = 775, truncated = 0 3.40.825.487 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 775, t_last = 344277517045 3.40.827.277 I slot launch_slot_: id 0 | task 14237 | processing task, is_child = 0 3.43.258.507 I slot print_timing: id 0 | task 14237 | prompt eval time = 570.06 ms / 415 tokens ( 1.37 ms per token, 727.99 tokens per second) 3.43.258.513 I slot print_timing: id 0 | task 14237 | eval time = 1861.16 ms / 142 tokens ( 13.20 ms per token, 75.76 tokens per second) 3.43.258.513 I slot print_timing: id 0 | task 14237 | total time = 2431.22 ms / 557 tokens 3.43.258.514 I slot print_timing: id 0 | task 14237 | graphs reused = 13976 3.43.258.514 I slot print_timing: id 0 | task 14237 | graph reallocs = 0 / 0 (same size) / (changed size) 3.43.258.549 I slot release: id 0 | task 14237 | stop processing: n_tokens = 556, truncated = 0 3.43.262.023 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 556, t_last = 344279953969 3.43.263.297 I slot launch_slot_: id 0 | task 14381 | processing task, is_child = 0 3.45.751.746 I slot print_timing: id 0 | task 14381 | prompt eval time = 460.67 ms / 295 tokens ( 1.56 ms per token, 640.37 tokens per second) 3.45.751.751 I slot print_timing: id 0 | task 14381 | eval time = 2027.77 ms / 155 tokens ( 13.17 ms per token, 75.95 tokens per second) 3.45.751.752 I slot print_timing: id 0 | task 14381 | total time = 2488.44 ms / 450 tokens 3.45.751.753 I slot print_timing: id 0 | task 14381 | graphs reused = 14129 3.45.751.753 I slot print_timing: id 0 | task 14381 | graph reallocs = 0 / 0 (same size) / (changed size) 3.45.751.780 I slot release: id 0 | task 14381 | stop processing: n_tokens = 449, truncated = 0 3.45.755.742 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 449, t_last = 344282447200 3.45.756.895 I slot launch_slot_: id 0 | task 14538 | processing task, is_child = 0 3.49.366.111 I slot print_timing: id 0 | task 14538 | n_gen = 229, tg = 75.72 t/s, tg_3s = 76.05 t/s 3.52.124.575 I slot print_timing: id 0 | task 14538 | prompt eval time = 598.03 ms / 442 tokens ( 1.35 ms per token, 739.09 tokens per second) 3.52.124.578 I slot print_timing: id 0 | task 14538 | eval time = 5769.64 ms / 438 tokens ( 13.20 ms per token, 75.74 tokens per second) 3.52.124.579 I slot print_timing: id 0 | task 14538 | total time = 6367.67 ms / 880 tokens 3.52.124.580 I slot print_timing: id 0 | task 14538 | graphs reused = 14563 3.52.124.580 I slot print_timing: id 0 | task 14538 | graph reallocs = 0 / 0 (same size) / (changed size) 3.52.124.621 I slot release: id 0 | task 14538 | stop processing: n_tokens = 879, truncated = 0 3.52.129.106 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 879, t_last = 344288820041 3.52.131.061 I slot launch_slot_: id 0 | task 14978 | processing task, is_child = 0 3.55.379.201 I slot print_timing: id 0 | task 14978 | prompt eval time = 923.50 ms / 622 tokens ( 1.48 ms per token, 673.52 tokens per second) 3.55.379.204 I slot print_timing: id 0 | task 14978 | eval time = 2324.62 ms / 177 tokens ( 13.21 ms per token, 75.71 tokens per second) 3.55.379.205 I slot print_timing: id 0 | task 14978 | total time = 3248.13 ms / 799 tokens 3.55.379.205 I slot print_timing: id 0 | task 14978 | graphs reused = 14737 3.55.379.206 I slot print_timing: id 0 | task 14978 | graph reallocs = 0 / 0 (same size) / (changed size) 3.55.379.256 I slot release: id 0 | task 14978 | stop processing: n_tokens = 798, truncated = 0 3.55.383.061 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 798, t_last = 344292074676 3.55.385.380 I slot launch_slot_: id 0 | task 15158 | processing task, is_child = 0 3.57.439.822 I slot print_timing: id 0 | task 15158 | prompt eval time = 586.69 ms / 424 tokens ( 1.38 ms per token, 722.70 tokens per second) 3.57.439.828 I slot print_timing: id 0 | task 15158 | eval time = 1467.74 ms / 112 tokens ( 13.22 ms per token, 75.63 tokens per second) 3.57.439.828 I slot print_timing: id 0 | task 15158 | total time = 2054.43 ms / 536 tokens 3.57.439.829 I slot print_timing: id 0 | task 15158 | graphs reused = 14846 3.57.439.829 I slot print_timing: id 0 | task 15158 | graph reallocs = 0 / 0 (same size) / (changed size) 3.57.439.862 I slot release: id 0 | task 15158 | stop processing: n_tokens = 535, truncated = 0 3.57.443.545 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 535, t_last = 344294135282 3.57.444.173 I slot launch_slot_: id 0 | task 15272 | processing task, is_child = 0 4.01.006.011 I slot print_timing: id 0 | task 15272 | n_gen = 229, tg = 75.92 t/s, tg_3s = 76.25 t/s 4.04.012.706 I slot print_timing: id 0 | task 15272 | n_gen = 457, tg = 75.87 t/s, tg_3s = 75.83 t/s 4.04.328.574 I slot print_timing: id 0 | task 15272 | prompt eval time = 558.48 ms / 395 tokens ( 1.41 ms per token, 707.27 tokens per second) 4.04.328.580 I slot print_timing: id 0 | task 15272 | eval time = 6325.91 ms / 481 tokens ( 13.18 ms per token, 75.88 tokens per second) 4.04.328.581 I slot print_timing: id 0 | task 15272 | total time = 6884.39 ms / 876 tokens 4.04.328.581 I slot print_timing: id 0 | task 15272 | graphs reused = 15323 4.04.328.582 I slot print_timing: id 0 | task 15272 | graph reallocs = 0 / 0 (same size) / (changed size) 4.04.328.622 I slot release: id 0 | task 15272 | stop processing: n_tokens = 875, truncated = 0 4.04.334.374 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 875, t_last = 344301024042 4.04.336.826 I slot launch_slot_: id 0 | task 15755 | processing task, is_child = 0 4.05.682.588 I slot print_timing: id 0 | task 15755 | prompt eval time = 438.33 ms / 279 tokens ( 1.57 ms per token, 636.51 tokens per second) 4.05.682.595 I slot print_timing: id 0 | task 15755 | eval time = 907.43 ms / 70 tokens ( 13.15 ms per token, 76.04 tokens per second) 4.05.682.595 I slot print_timing: id 0 | task 15755 | total time = 1345.76 ms / 349 tokens 4.05.682.596 I slot print_timing: id 0 | task 15755 | graphs reused = 15391 4.05.682.597 I slot print_timing: id 0 | task 15755 | graph reallocs = 0 / 0 (same size) / (changed size) 4.05.682.627 I slot release: id 0 | task 15755 | stop processing: n_tokens = 348, truncated = 0 4.05.686.103 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 348, t_last = 344302378048 4.05.687.003 I slot launch_slot_: id 0 | task 15827 | processing task, is_child = 0 4.09.171.513 I slot print_timing: id 0 | task 15827 | n_gen = 229, tg = 75.78 t/s, tg_3s = 76.11 t/s 4.09.237.208 I slot print_timing: id 0 | task 15827 | prompt eval time = 475.87 ms / 319 tokens ( 1.49 ms per token, 670.35 tokens per second) 4.09.237.215 I slot print_timing: id 0 | task 15827 | eval time = 3074.32 ms / 234 tokens ( 13.19 ms per token, 75.79 tokens per second) 4.09.237.215 I slot print_timing: id 0 | task 15827 | total time = 3550.19 ms / 553 tokens 4.09.237.216 I slot print_timing: id 0 | task 15827 | graphs reused = 15622 4.09.237.217 I slot print_timing: id 0 | task 15827 | graph reallocs = 0 / 0 (same size) / (changed size) 4.09.237.244 I slot release: id 0 | task 15827 | stop processing: n_tokens = 552, truncated = 0 4.09.240.873 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 552, t_last = 344305932664 4.09.242.214 I slot launch_slot_: id 0 | task 16063 | processing task, is_child = 0 4.11.326.944 I slot print_timing: id 0 | task 16063 | prompt eval time = 503.93 ms / 345 tokens ( 1.46 ms per token, 684.61 tokens per second) 4.11.326.950 I slot print_timing: id 0 | task 16063 | eval time = 1580.79 ms / 121 tokens ( 13.17 ms per token, 75.91 tokens per second) 4.11.326.951 I slot print_timing: id 0 | task 16063 | total time = 2084.72 ms / 466 tokens 4.11.326.951 I slot print_timing: id 0 | task 16063 | graphs reused = 15741 4.11.326.952 I slot print_timing: id 0 | task 16063 | graph reallocs = 0 / 0 (same size) / (changed size) 4.11.326.987 I slot release: id 0 | task 16063 | stop processing: n_tokens = 465, truncated = 0 4.11.330.961 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 465, t_last = 344308022407 4.11.332.227 I slot launch_slot_: id 0 | task 16186 | processing task, is_child = 0 4.14.230.433 I slot print_timing: id 0 | task 16186 | prompt eval time = 623.85 ms / 464 tokens ( 1.34 ms per token, 743.77 tokens per second) 4.14.230.437 I slot print_timing: id 0 | task 16186 | eval time = 2274.35 ms / 173 tokens ( 13.22 ms per token, 75.63 tokens per second) 4.14.230.438 I slot print_timing: id 0 | task 16186 | total time = 2898.19 ms / 637 tokens 4.14.230.439 I slot print_timing: id 0 | task 16186 | graphs reused = 15911 4.14.230.439 I slot print_timing: id 0 | task 16186 | graph reallocs = 0 / 0 (same size) / (changed size) 4.14.230.477 I slot release: id 0 | task 16186 | stop processing: n_tokens = 636, truncated = 0 4.14.234.695 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 636, t_last = 344310925897 4.14.236.441 I slot launch_slot_: id 0 | task 16361 | processing task, is_child = 0 4.16.010.609 I slot print_timing: id 0 | task 16361 | prompt eval time = 559.05 ms / 398 tokens ( 1.40 ms per token, 711.93 tokens per second) 4.16.010.615 I slot print_timing: id 0 | task 16361 | eval time = 1215.11 ms / 93 tokens ( 13.21 ms per token, 75.71 tokens per second) 4.16.010.615 I slot print_timing: id 0 | task 16361 | total time = 1774.16 ms / 491 tokens 4.16.010.616 I slot print_timing: id 0 | task 16361 | graphs reused = 16002 4.16.010.616 I slot print_timing: id 0 | task 16361 | graph reallocs = 0 / 0 (same size) / (changed size) 4.16.010.647 I slot release: id 0 | task 16361 | stop processing: n_tokens = 490, truncated = 0 4.16.015.787 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 490, t_last = 344312706067 4.16.017.469 I slot launch_slot_: id 0 | task 16456 | processing task, is_child = 0 4.19.528.423 I slot print_timing: id 0 | task 16456 | prompt eval time = 924.01 ms / 628 tokens ( 1.47 ms per token, 679.64 tokens per second) 4.19.528.430 I slot print_timing: id 0 | task 16456 | eval time = 2586.93 ms / 196 tokens ( 13.27 ms per token, 75.38 tokens per second) 4.19.528.431 I slot print_timing: id 0 | task 16456 | total time = 3510.95 ms / 824 tokens 4.19.528.432 I slot print_timing: id 0 | task 16456 | graphs reused = 16195 4.19.528.432 I slot print_timing: id 0 | task 16456 | graph reallocs = 0 / 0 (same size) / (changed size) 4.19.528.482 I slot release: id 0 | task 16456 | stop processing: n_tokens = 823, truncated = 0 4.19.532.753 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 823, t_last = 344316223902 4.19.535.066 I slot launch_slot_: id 0 | task 16655 | processing task, is_child = 0 4.21.685.594 I slot print_timing: id 0 | task 16655 | prompt eval time = 563.43 ms / 404 tokens ( 1.39 ms per token, 717.03 tokens per second) 4.21.685.597 I slot print_timing: id 0 | task 16655 | eval time = 1587.08 ms / 121 tokens ( 13.23 ms per token, 75.61 tokens per second) 4.21.685.597 I slot print_timing: id 0 | task 16655 | total time = 2150.51 ms / 525 tokens 4.21.685.598 I slot print_timing: id 0 | task 16655 | graphs reused = 16313 4.21.685.598 I slot print_timing: id 0 | task 16655 | graph reallocs = 0 / 0 (same size) / (changed size) 4.21.685.634 I slot release: id 0 | task 16655 | stop processing: n_tokens = 524, truncated = 0 4.21.689.472 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 524, t_last = 344318381054 4.21.690.692 I slot launch_slot_: id 0 | task 16778 | processing task, is_child = 0 4.23.917.198 I slot print_timing: id 0 | task 16778 | prompt eval time = 600.44 ms / 445 tokens ( 1.35 ms per token, 741.12 tokens per second) 4.23.917.202 I slot print_timing: id 0 | task 16778 | eval time = 1626.06 ms / 124 tokens ( 13.22 ms per token, 75.64 tokens per second) 4.23.917.203 I slot print_timing: id 0 | task 16778 | total time = 2226.50 ms / 569 tokens 4.23.917.204 I slot print_timing: id 0 | task 16778 | graphs reused = 16434 4.23.917.204 I slot print_timing: id 0 | task 16778 | graph reallocs = 0 / 0 (same size) / (changed size) 4.23.917.240 I slot release: id 0 | task 16778 | stop processing: n_tokens = 568, truncated = 0 4.23.921.196 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 568, t_last = 344320612660 4.23.922.540 I slot launch_slot_: id 0 | task 16904 | processing task, is_child = 0 4.27.481.088 I slot print_timing: id 0 | task 16904 | prompt eval time = 567.25 ms / 412 tokens ( 1.38 ms per token, 726.30 tokens per second) 4.27.481.092 I slot print_timing: id 0 | task 16904 | eval time = 2991.28 ms / 227 tokens ( 13.24 ms per token, 75.55 tokens per second) 4.27.481.093 I slot print_timing: id 0 | task 16904 | total time = 3558.54 ms / 639 tokens 4.27.481.093 I slot print_timing: id 0 | task 16904 | graphs reused = 16658 4.27.481.094 I slot print_timing: id 0 | task 16904 | graph reallocs = 0 / 0 (same size) / (changed size) 4.27.481.131 I slot release: id 0 | task 16904 | stop processing: n_tokens = 638, truncated = 0 4.27.485.434 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 638, t_last = 344324176551 4.27.487.052 I slot launch_slot_: id 0 | task 17133 | processing task, is_child = 0 4.29.086.292 I slot print_timing: id 0 | task 17133 | prompt eval time = 817.54 ms / 542 tokens ( 1.51 ms per token, 662.97 tokens per second) 4.29.086.297 I slot print_timing: id 0 | task 17133 | eval time = 781.69 ms / 60 tokens ( 13.25 ms per token, 75.48 tokens per second) 4.29.086.298 I slot print_timing: id 0 | task 17133 | total time = 1599.23 ms / 602 tokens 4.29.086.298 I slot print_timing: id 0 | task 17133 | graphs reused = 16716 4.29.086.299 I slot print_timing: id 0 | task 17133 | graph reallocs = 0 / 0 (same size) / (changed size) 4.29.086.338 I slot release: id 0 | task 17133 | stop processing: n_tokens = 601, truncated = 0 4.29.090.577 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 601, t_last = 344325781758 4.29.092.048 I slot launch_slot_: id 0 | task 17196 | processing task, is_child = 0 4.32.654.068 I slot print_timing: id 0 | task 17196 | prompt eval time = 917.07 ms / 628 tokens ( 1.46 ms per token, 684.79 tokens per second) 4.32.654.075 I slot print_timing: id 0 | task 17196 | eval time = 2644.94 ms / 201 tokens ( 13.22 ms per token, 75.62 tokens per second) 4.32.654.075 I slot print_timing: id 0 | task 17196 | total time = 3562.01 ms / 829 tokens 4.32.654.076 I slot print_timing: id 0 | task 17196 | graphs reused = 16914 4.32.654.077 I slot print_timing: id 0 | task 17196 | graph reallocs = 0 / 0 (same size) / (changed size) 4.32.654.122 I slot release: id 0 | task 17196 | stop processing: n_tokens = 828, truncated = 0 4.32.657.573 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.107 (> 0.100 thold), f_keep = 0.025 4.32.659.451 I slot launch_slot_: id 0 | task 17400 | processing task, is_child = 0 4.36.025.832 I slot print_timing: id 0 | task 17400 | n_gen = 229, tg = 75.98 t/s, tg_3s = 76.32 t/s 4.36.051.952 I slot print_timing: id 0 | task 17400 | prompt eval time = 365.77 ms / 197 tokens ( 1.86 ms per token, 538.59 tokens per second) 4.36.051.957 I slot print_timing: id 0 | task 17400 | eval time = 3026.73 ms / 231 tokens ( 13.16 ms per token, 75.99 tokens per second) 4.36.051.959 I slot print_timing: id 0 | task 17400 | total time = 3392.49 ms / 428 tokens 4.36.051.960 I slot print_timing: id 0 | task 17400 | graphs reused = 17142 4.36.051.960 I slot print_timing: id 0 | task 17400 | graph reallocs = 0 / 0 (same size) / (changed size) 4.36.051.986 I slot release: id 0 | task 17400 | stop processing: n_tokens = 427, truncated = 0 4.36.055.332 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 427, t_last = 344332747406 4.36.056.384 I slot launch_slot_: id 0 | task 17633 | processing task, is_child = 0 4.37.949.710 I slot print_timing: id 0 | task 17633 | prompt eval time = 379.33 ms / 217 tokens ( 1.75 ms per token, 572.06 tokens per second) 4.37.949.716 I slot print_timing: id 0 | task 17633 | eval time = 1513.99 ms / 116 tokens ( 13.17 ms per token, 75.96 tokens per second) 4.37.949.716 I slot print_timing: id 0 | task 17633 | total time = 1893.32 ms / 333 tokens 4.37.949.717 I slot print_timing: id 0 | task 17633 | graphs reused = 17255 4.37.949.718 I slot print_timing: id 0 | task 17633 | graph reallocs = 0 / 0 (same size) / (changed size) 4.37.949.741 I slot release: id 0 | task 17633 | stop processing: n_tokens = 332, truncated = 0 4.37.953.052 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 4.37.953.931 I slot launch_slot_: id 0 | task 17751 | processing task, is_child = 0 4.41.333.007 I slot print_timing: id 0 | task 17751 | n_gen = 230, tg = 76.14 t/s, tg_3s = 76.47 t/s 4.44.340.592 I slot print_timing: id 0 | task 17751 | n_gen = 458, tg = 75.97 t/s, tg_3s = 75.81 t/s 4.47.351.227 I slot print_timing: id 0 | task 17751 | n_gen = 686, tg = 75.89 t/s, tg_3s = 75.73 t/s 4.50.352.047 I slot print_timing: id 0 | task 17751 | n_gen = 913, tg = 75.83 t/s, tg_3s = 75.65 t/s 4.51.820.061 I slot print_timing: id 0 | task 17751 | prompt eval time = 371.30 ms / 200 tokens ( 1.86 ms per token, 538.65 tokens per second) 4.51.820.067 I slot print_timing: id 0 | task 17751 | eval time = 13494.82 ms / 1024 tokens ( 13.19 ms per token, 75.81 tokens per second) 4.51.820.068 I slot print_timing: id 0 | task 17751 | total time = 13866.12 ms / 1224 tokens 4.51.820.068 I slot print_timing: id 0 | task 17751 | graphs reused = 18273 4.51.820.069 I slot print_timing: id 0 | task 17751 | graph reallocs = 0 / 0 (same size) / (changed size) 4.51.820.091 I slot release: id 0 | task 17751 | stop processing: n_tokens = 1223, truncated = 0 4.51.823.490 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.124 (> 0.100 thold), f_keep = 0.017 4.51.826.046 I slot launch_slot_: id 0 | task 18777 | processing task, is_child = 0 4.55.172.360 I slot print_timing: id 0 | task 18777 | n_gen = 229, tg = 75.91 t/s, tg_3s = 76.25 t/s 4.55.185.451 I slot print_timing: id 0 | task 18777 | prompt eval time = 342.94 ms / 170 tokens ( 2.02 ms per token, 495.71 tokens per second) 4.55.185.457 I slot print_timing: id 0 | task 18777 | eval time = 3016.45 ms / 230 tokens ( 13.17 ms per token, 75.92 tokens per second) 4.55.185.457 I slot print_timing: id 0 | task 18777 | total time = 3359.40 ms / 400 tokens 4.55.185.458 I slot print_timing: id 0 | task 18777 | graphs reused = 18500 4.55.185.458 I slot print_timing: id 0 | task 18777 | graph reallocs = 0 / 0 (same size) / (changed size) 4.55.185.479 I slot release: id 0 | task 18777 | stop processing: n_tokens = 399, truncated = 0 4.55.188.717 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 399, t_last = 344351880899 4.55.189.748 I slot launch_slot_: id 0 | task 19009 | processing task, is_child = 0 4.58.600.865 I slot print_timing: id 0 | task 19009 | n_gen = 229, tg = 75.90 t/s, tg_3s = 76.23 t/s 5.01.605.714 I slot print_timing: id 0 | task 19009 | n_gen = 457, tg = 75.89 t/s, tg_3s = 75.88 t/s 5.04.615.683 I slot print_timing: id 0 | task 19009 | n_gen = 685, tg = 75.84 t/s, tg_3s = 75.75 t/s 5.07.618.887 I slot print_timing: id 0 | task 19009 | n_gen = 912, tg = 75.78 t/s, tg_3s = 75.59 t/s 5.07.909.918 I slot print_timing: id 0 | task 19009 | prompt eval time = 407.21 ms / 241 tokens ( 1.69 ms per token, 591.83 tokens per second) 5.07.909.923 I slot print_timing: id 0 | task 19009 | eval time = 12312.95 ms / 934 tokens ( 13.20 ms per token, 75.77 tokens per second) 5.07.909.924 I slot print_timing: id 0 | task 19009 | total time = 12720.16 ms / 1175 tokens 5.07.909.924 I slot print_timing: id 0 | task 19009 | graphs reused = 19428 5.07.909.925 I slot print_timing: id 0 | task 19009 | graph reallocs = 0 / 0 (same size) / (changed size) 5.07.909.951 I slot release: id 0 | task 19009 | stop processing: n_tokens = 1174, truncated = 0 5.07.913.311 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1174, t_last = 344364605371 5.07.915.972 I slot launch_slot_: id 0 | task 19945 | processing task, is_child = 0 5.11.330.231 I slot print_timing: id 0 | task 19945 | n_gen = 230, tg = 76.10 t/s, tg_3s = 76.44 t/s 5.11.841.874 I slot print_timing: id 0 | task 19945 | prompt eval time = 405.16 ms / 237 tokens ( 1.71 ms per token, 584.96 tokens per second) 5.11.841.878 I slot print_timing: id 0 | task 19945 | eval time = 3520.74 ms / 269 tokens ( 13.14 ms per token, 76.12 tokens per second) 5.11.841.879 I slot print_timing: id 0 | task 19945 | total time = 3925.89 ms / 506 tokens 5.11.841.879 I slot print_timing: id 0 | task 19945 | graphs reused = 19694 5.11.841.880 I slot print_timing: id 0 | task 19945 | graph reallocs = 0 / 0 (same size) / (changed size) 5.11.841.904 I slot release: id 0 | task 19945 | stop processing: n_tokens = 505, truncated = 0 5.11.845.364 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 505, t_last = 344368537324 5.11.846.660 I slot launch_slot_: id 0 | task 20216 | processing task, is_child = 0 5.15.325.102 I slot print_timing: id 0 | task 20216 | n_gen = 229, tg = 75.95 t/s, tg_3s = 76.28 t/s 5.17.312.306 I slot print_timing: id 0 | task 20216 | prompt eval time = 476.35 ms / 322 tokens ( 1.48 ms per token, 675.97 tokens per second) 5.17.312.312 I slot print_timing: id 0 | task 20216 | eval time = 4989.29 ms / 380 tokens ( 13.16 ms per token, 75.96 tokens per second) 5.17.312.313 I slot print_timing: id 0 | task 20216 | total time = 5465.64 ms / 702 tokens 5.17.312.313 I slot print_timing: id 0 | task 20216 | graphs reused = 20071 5.17.312.314 I slot print_timing: id 0 | task 20216 | graph reallocs = 0 / 0 (same size) / (changed size) 5.17.312.347 I slot release: id 0 | task 20216 | stop processing: n_tokens = 701, truncated = 0 5.17.315.664 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.120 (> 0.100 thold), f_keep = 0.030 5.17.317.314 I slot launch_slot_: id 0 | task 20598 | processing task, is_child = 0 5.20.673.812 I slot print_timing: id 0 | task 20598 | n_gen = 230, tg = 76.01 t/s, tg_3s = 76.34 t/s 5.22.623.083 I slot print_timing: id 0 | task 20598 | prompt eval time = 343.79 ms / 175 tokens ( 1.96 ms per token, 509.03 tokens per second) 5.22.623.087 I slot print_timing: id 0 | task 20598 | eval time = 4961.97 ms / 378 tokens ( 13.16 ms per token, 75.98 tokens per second) 5.22.623.087 I slot print_timing: id 0 | task 20598 | total time = 5305.76 ms / 553 tokens 5.22.623.088 I slot print_timing: id 0 | task 20598 | graphs reused = 20445 5.22.623.089 I slot print_timing: id 0 | task 20598 | graph reallocs = 0 / 0 (same size) / (changed size) 5.22.623.110 I slot release: id 0 | task 20598 | stop processing: n_tokens = 552, truncated = 0 5.22.626.441 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.117 (> 0.100 thold), f_keep = 0.038 5.22.627.705 I slot launch_slot_: id 0 | task 20978 | processing task, is_child = 0 5.25.983.038 I slot print_timing: id 0 | task 20978 | n_gen = 229, tg = 75.84 t/s, tg_3s = 76.17 t/s 5.28.744.377 I slot print_timing: id 0 | task 20978 | prompt eval time = 349.06 ms / 179 tokens ( 1.95 ms per token, 512.81 tokens per second) 5.28.744.380 I slot print_timing: id 0 | task 20978 | eval time = 5767.60 ms / 439 tokens ( 13.17 ms per token, 75.94 tokens per second) 5.28.744.381 I slot print_timing: id 0 | task 20978 | total time = 6116.66 ms / 618 tokens 5.28.744.381 I slot print_timing: id 0 | task 20978 | graphs reused = 20880 5.28.744.382 I slot print_timing: id 0 | task 20978 | graph reallocs = 0 / 0 (same size) / (changed size) 5.28.744.404 I slot release: id 0 | task 20978 | stop processing: n_tokens = 617, truncated = 0 5.28.747.732 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 617, t_last = 344385439824 5.28.749.409 I slot launch_slot_: id 0 | task 21419 | processing task, is_child = 0 5.32.162.200 I slot print_timing: id 0 | task 21419 | n_gen = 230, tg = 76.05 t/s, tg_3s = 76.38 t/s 5.32.517.610 I slot print_timing: id 0 | task 21419 | prompt eval time = 401.52 ms / 237 tokens ( 1.69 ms per token, 590.26 tokens per second) 5.32.517.617 I slot print_timing: id 0 | task 21419 | eval time = 3366.68 ms / 257 tokens ( 13.15 ms per token, 76.04 tokens per second) 5.32.517.617 I slot print_timing: id 0 | task 21419 | total time = 3768.19 ms / 494 tokens 5.32.517.618 I slot print_timing: id 0 | task 21419 | graphs reused = 21134 5.32.517.619 I slot print_timing: id 0 | task 21419 | graph reallocs = 0 / 0 (same size) / (changed size) 5.32.517.643 I slot release: id 0 | task 21419 | stop processing: n_tokens = 493, truncated = 0 5.32.520.890 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 493, t_last = 344389213063 5.32.521.988 I slot launch_slot_: id 0 | task 21678 | processing task, is_child = 0 5.35.970.059 I slot print_timing: id 0 | task 21678 | n_gen = 229, tg = 75.93 t/s, tg_3s = 76.26 t/s 5.37.962.203 I slot print_timing: id 0 | task 21678 | prompt eval time = 445.11 ms / 287 tokens ( 1.55 ms per token, 644.79 tokens per second) 5.37.962.210 I slot print_timing: id 0 | task 21678 | eval time = 4995.10 ms / 380 tokens ( 13.18 ms per token, 75.87 tokens per second) 5.37.962.210 I slot print_timing: id 0 | task 21678 | total time = 5440.21 ms / 667 tokens 5.37.962.211 I slot print_timing: id 0 | task 21678 | graphs reused = 21511 5.37.962.211 I slot print_timing: id 0 | task 21678 | graph reallocs = 0 / 0 (same size) / (changed size) 5.37.962.243 I slot release: id 0 | task 21678 | stop processing: n_tokens = 666, truncated = 0 5.37.966.080 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.148 (> 0.100 thold), f_keep = 0.054 5.37.968.158 I slot launch_slot_: id 0 | task 22060 | processing task, is_child = 0 5.41.383.352 I slot print_timing: id 0 | task 22060 | n_gen = 229, tg = 75.82 t/s, tg_3s = 76.15 t/s 5.41.634.157 I slot print_timing: id 0 | task 22060 | prompt eval time = 407.99 ms / 243 tokens ( 1.68 ms per token, 595.60 tokens per second) 5.41.634.161 I slot print_timing: id 0 | task 22060 | eval time = 3258.00 ms / 248 tokens ( 13.19 ms per token, 75.81 tokens per second) 5.41.634.162 I slot print_timing: id 0 | task 22060 | total time = 3665.99 ms / 491 tokens 5.41.634.162 I slot print_timing: id 0 | task 22060 | graphs reused = 21756 5.41.634.163 I slot print_timing: id 0 | task 22060 | graph reallocs = 0 / 0 (same size) / (changed size) 5.41.634.189 I slot release: id 0 | task 22060 | stop processing: n_tokens = 490, truncated = 0 5.41.637.520 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 490, t_last = 344398329609 5.41.638.756 I slot launch_slot_: id 0 | task 22310 | processing task, is_child = 0 5.45.056.244 I slot print_timing: id 0 | task 22310 | n_gen = 230, tg = 76.10 t/s, tg_3s = 76.43 t/s 5.47.242.697 I slot print_timing: id 0 | task 22310 | prompt eval time = 408.23 ms / 243 tokens ( 1.68 ms per token, 595.26 tokens per second) 5.47.242.715 I slot print_timing: id 0 | task 22310 | eval time = 5195.70 ms / 396 tokens ( 13.15 ms per token, 76.02 tokens per second) 5.47.242.718 I slot print_timing: id 0 | task 22310 | total time = 5603.93 ms / 639 tokens 5.47.242.718 I slot print_timing: id 0 | task 22310 | graphs reused = 22148 5.47.242.719 I slot print_timing: id 0 | task 22310 | graph reallocs = 0 / 0 (same size) / (changed size) 5.47.242.748 I slot release: id 0 | task 22310 | stop processing: n_tokens = 638, truncated = 0 5.47.246.420 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 638, t_last = 344403938168 5.47.247.969 I slot launch_slot_: id 0 | task 22708 | processing task, is_child = 0 5.50.676.395 I slot print_timing: id 0 | task 22708 | n_gen = 229, tg = 75.97 t/s, tg_3s = 76.30 t/s 5.50.755.313 I slot print_timing: id 0 | task 22708 | prompt eval time = 427.11 ms / 262 tokens ( 1.63 ms per token, 613.43 tokens per second) 5.50.755.318 I slot print_timing: id 0 | task 22708 | eval time = 3080.23 ms / 235 tokens ( 13.16 ms per token, 75.97 tokens per second) 5.50.755.319 I slot print_timing: id 0 | task 22708 | total time = 3507.34 ms / 497 tokens 5.50.755.319 I slot print_timing: id 0 | task 22708 | graphs reused = 22381 5.50.755.320 I slot print_timing: id 0 | task 22708 | graph reallocs = 0 / 0 (same size) / (changed size) 5.50.755.345 I slot release: id 0 | task 22708 | stop processing: n_tokens = 496, truncated = 0 5.50.758.677 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.102 (> 0.100 thold), f_keep = 0.042 5.50.759.854 I slot launch_slot_: id 0 | task 22945 | processing task, is_child = 0 5.53.491.948 I slot print_timing: id 0 | task 22945 | prompt eval time = 374.17 ms / 205 tokens ( 1.83 ms per token, 547.89 tokens per second) 5.53.491.951 I slot print_timing: id 0 | task 22945 | eval time = 2357.92 ms / 180 tokens ( 13.17 ms per token, 75.91 tokens per second) 5.53.491.952 I slot print_timing: id 0 | task 22945 | total time = 2732.09 ms / 385 tokens 5.53.491.953 I slot print_timing: id 0 | task 22945 | graphs reused = 22558 5.53.491.953 I slot print_timing: id 0 | task 22945 | graph reallocs = 0 / 0 (same size) / (changed size) 5.53.491.980 I slot release: id 0 | task 22945 | stop processing: n_tokens = 384, truncated = 0 5.53.495.633 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 384, t_last = 344410187400 5.53.496.641 I slot launch_slot_: id 0 | task 23127 | processing task, is_child = 0 5.56.577.931 I slot print_timing: id 0 | task 23127 | prompt eval time = 439.54 ms / 279 tokens ( 1.58 ms per token, 634.76 tokens per second) 5.56.577.934 I slot print_timing: id 0 | task 23127 | eval time = 2641.74 ms / 202 tokens ( 13.14 ms per token, 76.09 tokens per second) 5.56.577.934 I slot print_timing: id 0 | task 23127 | total time = 3081.28 ms / 481 tokens 5.56.577.935 I slot print_timing: id 0 | task 23127 | graphs reused = 22758 5.56.577.936 I slot print_timing: id 0 | task 23127 | graph reallocs = 0 / 0 (same size) / (changed size) 5.56.577.962 I slot release: id 0 | task 23127 | stop processing: n_tokens = 480, truncated = 0 5.56.581.226 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 5.56.582.349 I slot launch_slot_: id 0 | task 23331 | processing task, is_child = 0 5.59.944.723 I slot print_timing: id 0 | task 23331 | n_gen = 230, tg = 76.17 t/s, tg_3s = 76.50 t/s 6.02.106.302 I slot print_timing: id 0 | task 23331 | prompt eval time = 355.96 ms / 194 tokens ( 1.83 ms per token, 545.00 tokens per second) 6.02.106.308 I slot print_timing: id 0 | task 23331 | eval time = 5167.98 ms / 394 tokens ( 13.15 ms per token, 76.05 tokens per second) 6.02.106.308 I slot print_timing: id 0 | task 23331 | total time = 5523.95 ms / 588 tokens 6.02.106.309 I slot print_timing: id 0 | task 23331 | graphs reused = 23148 6.02.106.309 I slot print_timing: id 0 | task 23331 | graph reallocs = 0 / 0 (same size) / (changed size) 6.02.106.334 I slot release: id 0 | task 23331 | stop processing: n_tokens = 587, truncated = 0 6.02.109.671 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.124 (> 0.100 thold), f_keep = 0.036 6.02.111.065 I slot launch_slot_: id 0 | task 23727 | processing task, is_child = 0 6.05.456.148 I slot print_timing: id 0 | task 23727 | n_gen = 229, tg = 75.91 t/s, tg_3s = 76.24 t/s 6.05.482.383 I slot print_timing: id 0 | task 23727 | prompt eval time = 341.42 ms / 169 tokens ( 2.02 ms per token, 495.00 tokens per second) 6.05.482.388 I slot print_timing: id 0 | task 23727 | eval time = 3029.89 ms / 231 tokens ( 13.17 ms per token, 75.91 tokens per second) 6.05.482.389 I slot print_timing: id 0 | task 23727 | total time = 3371.31 ms / 400 tokens 6.05.482.390 I slot print_timing: id 0 | task 23727 | graphs reused = 23376 6.05.482.390 I slot print_timing: id 0 | task 23727 | graph reallocs = 0 / 0 (same size) / (changed size) 6.05.482.412 I slot release: id 0 | task 23727 | stop processing: n_tokens = 399, truncated = 0 6.05.485.726 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 399, t_last = 344422177832 6.05.486.991 I slot launch_slot_: id 0 | task 23960 | processing task, is_child = 0 6.08.928.956 I slot print_timing: id 0 | task 23960 | n_gen = 230, tg = 76.00 t/s, tg_3s = 76.33 t/s 6.09.574.585 I slot print_timing: id 0 | task 23960 | prompt eval time = 428.79 ms / 263 tokens ( 1.63 ms per token, 613.36 tokens per second) 6.09.574.591 I slot print_timing: id 0 | task 23960 | eval time = 3658.80 ms / 279 tokens ( 13.16 ms per token, 75.98 tokens per second) 6.09.574.592 I slot print_timing: id 0 | task 23960 | total time = 4087.59 ms / 542 tokens 6.09.574.592 I slot print_timing: id 0 | task 23960 | graphs reused = 23652 6.09.574.593 I slot print_timing: id 0 | task 23960 | graph reallocs = 0 / 0 (same size) / (changed size) 6.09.574.619 I slot release: id 0 | task 23960 | stop processing: n_tokens = 541, truncated = 0 6.09.578.087 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.103 (> 0.100 thold), f_keep = 0.039 6.09.579.403 I slot launch_slot_: id 0 | task 24241 | processing task, is_child = 0 6.12.295.039 I slot print_timing: id 0 | task 24241 | prompt eval time = 373.26 ms / 204 tokens ( 1.83 ms per token, 546.54 tokens per second) 6.12.295.044 I slot print_timing: id 0 | task 24241 | eval time = 2342.37 ms / 179 tokens ( 13.16 ms per token, 75.99 tokens per second) 6.12.295.045 I slot print_timing: id 0 | task 24241 | total time = 2715.63 ms / 383 tokens 6.12.295.045 I slot print_timing: id 0 | task 24241 | graphs reused = 23828 6.12.295.046 I slot print_timing: id 0 | task 24241 | graph reallocs = 0 / 0 (same size) / (changed size) 6.12.295.069 I slot release: id 0 | task 24241 | stop processing: n_tokens = 382, truncated = 0 6.12.299.105 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 382, t_last = 344428990489 6.12.300.700 I slot launch_slot_: id 0 | task 24422 | processing task, is_child = 0 6.15.748.216 I slot print_timing: id 0 | task 24422 | n_gen = 230, tg = 76.00 t/s, tg_3s = 76.33 t/s 6.17.186.748 I slot print_timing: id 0 | task 24422 | prompt eval time = 434.42 ms / 272 tokens ( 1.60 ms per token, 626.12 tokens per second) 6.17.186.754 I slot print_timing: id 0 | task 24422 | eval time = 4451.62 ms / 339 tokens ( 13.17 ms per token, 75.93 tokens per second) 6.17.186.755 I slot print_timing: id 0 | task 24422 | total time = 4886.04 ms / 611 tokens 6.17.186.755 I slot print_timing: id 0 | task 24422 | graphs reused = 24164 6.17.186.756 I slot print_timing: id 0 | task 24422 | graph reallocs = 0 / 0 (same size) / (changed size) 6.17.186.780 I slot release: id 0 | task 24422 | stop processing: n_tokens = 610, truncated = 0 6.17.190.094 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 610, t_last = 344433882200 6.17.191.536 I slot launch_slot_: id 0 | task 24763 | processing task, is_child = 0 6.19.711.792 I slot print_timing: id 0 | task 24763 | prompt eval time = 400.40 ms / 231 tokens ( 1.73 ms per token, 576.92 tokens per second) 6.19.711.797 I slot print_timing: id 0 | task 24763 | eval time = 2119.84 ms / 162 tokens ( 13.17 ms per token, 75.95 tokens per second) 6.19.711.798 I slot print_timing: id 0 | task 24763 | total time = 2520.24 ms / 393 tokens 6.19.711.798 I slot print_timing: id 0 | task 24763 | graphs reused = 24323 6.19.711.799 I slot print_timing: id 0 | task 24763 | graph reallocs = 0 / 0 (same size) / (changed size) 6.19.711.822 I slot release: id 0 | task 24763 | stop processing: n_tokens = 392, truncated = 0 6.19.716.028 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 392, t_last = 344436407242 6.19.717.719 I slot launch_slot_: id 0 | task 24927 | processing task, is_child = 0 6.23.154.582 I slot print_timing: id 0 | task 24927 | prompt eval time = 446.53 ms / 291 tokens ( 1.53 ms per token, 651.69 tokens per second) 6.23.154.588 I slot print_timing: id 0 | task 24927 | eval time = 2990.32 ms / 228 tokens ( 13.17 ms per token, 75.91 tokens per second) 6.23.154.588 I slot print_timing: id 0 | task 24927 | total time = 3436.85 ms / 519 tokens 6.23.154.589 I slot print_timing: id 0 | task 24927 | graphs reused = 24548 6.23.154.589 I slot print_timing: id 0 | task 24927 | graph reallocs = 0 / 0 (same size) / (changed size) 6.23.154.616 I slot release: id 0 | task 24927 | stop processing: n_tokens = 518, truncated = 0 6.23.157.942 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 518, t_last = 344439850036 6.23.159.184 I slot launch_slot_: id 0 | task 25157 | processing task, is_child = 0 6.25.480.094 I slot print_timing: id 0 | task 25157 | prompt eval time = 443.51 ms / 285 tokens ( 1.56 ms per token, 642.60 tokens per second) 6.25.480.100 I slot print_timing: id 0 | task 25157 | eval time = 1877.39 ms / 144 tokens ( 13.13 ms per token, 76.17 tokens per second) 6.25.480.101 I slot print_timing: id 0 | task 25157 | total time = 2320.90 ms / 429 tokens 6.25.480.101 I slot print_timing: id 0 | task 25157 | graphs reused = 24690 6.25.480.102 I slot print_timing: id 0 | task 25157 | graph reallocs = 0 / 0 (same size) / (changed size) 6.25.480.129 I slot release: id 0 | task 25157 | stop processing: n_tokens = 428, truncated = 0 6.25.483.519 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 428, t_last = 344442175549 6.25.484.573 I slot launch_slot_: id 0 | task 25303 | processing task, is_child = 0 6.28.941.352 I slot print_timing: id 0 | task 25303 | n_gen = 230, tg = 76.01 t/s, tg_3s = 76.34 t/s 6.30.287.578 I slot print_timing: id 0 | task 25303 | prompt eval time = 443.98 ms / 289 tokens ( 1.54 ms per token, 650.93 tokens per second) 6.30.287.584 I slot print_timing: id 0 | task 25303 | eval time = 4359.01 ms / 332 tokens ( 13.17 ms per token, 75.93 tokens per second) 6.30.287.585 I slot print_timing: id 0 | task 25303 | total time = 4803.00 ms / 621 tokens 6.30.287.585 I slot print_timing: id 0 | task 25303 | graphs reused = 25019 6.30.287.586 I slot print_timing: id 0 | task 25303 | graph reallocs = 0 / 0 (same size) / (changed size) 6.30.287.612 I slot release: id 0 | task 25303 | stop processing: n_tokens = 620, truncated = 0 6.30.290.970 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 620, t_last = 344446983032 6.30.292.410 I slot launch_slot_: id 0 | task 25637 | processing task, is_child = 0 6.33.702.651 I slot print_timing: id 0 | task 25637 | n_gen = 229, tg = 75.88 t/s, tg_3s = 76.21 t/s 6.36.037.617 I slot print_timing: id 0 | task 25637 | prompt eval time = 405.56 ms / 242 tokens ( 1.68 ms per token, 596.70 tokens per second) 6.36.037.623 I slot print_timing: id 0 | task 25637 | eval time = 5339.64 ms / 406 tokens ( 13.18 ms per token, 75.85 tokens per second) 6.36.037.624 I slot print_timing: id 0 | task 25637 | total time = 5745.20 ms / 648 tokens 6.36.037.624 I slot print_timing: id 0 | task 25637 | graphs reused = 25421 6.36.037.625 I slot print_timing: id 0 | task 25637 | graph reallocs = 0 / 0 (same size) / (changed size) 6.36.037.652 I slot release: id 0 | task 25637 | stop processing: n_tokens = 647, truncated = 0 6.36.041.026 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.118 (> 0.100 thold), f_keep = 0.032 6.36.042.546 I slot launch_slot_: id 0 | task 26045 | processing task, is_child = 0 6.39.336.321 I slot print_timing: id 0 | task 26045 | prompt eval time = 347.49 ms / 178 tokens ( 1.95 ms per token, 512.25 tokens per second) 6.39.336.327 I slot print_timing: id 0 | task 26045 | eval time = 2946.28 ms / 225 tokens ( 13.15 ms per token, 76.03 tokens per second) 6.39.336.328 I slot print_timing: id 0 | task 26045 | total time = 3293.76 ms / 403 tokens 6.39.336.328 I slot print_timing: id 0 | task 26045 | graphs reused = 25643 6.39.336.329 I slot print_timing: id 0 | task 26045 | graph reallocs = 0 / 0 (same size) / (changed size) 6.39.336.349 I slot release: id 0 | task 26045 | stop processing: n_tokens = 402, truncated = 0 6.39.339.649 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 402, t_last = 344456031769 6.39.340.647 I slot launch_slot_: id 0 | task 26272 | processing task, is_child = 0 6.42.099.961 I slot print_timing: id 0 | task 26272 | prompt eval time = 429.17 ms / 264 tokens ( 1.63 ms per token, 615.14 tokens per second) 6.42.099.967 I slot print_timing: id 0 | task 26272 | eval time = 2330.13 ms / 178 tokens ( 13.16 ms per token, 75.96 tokens per second) 6.42.099.967 I slot print_timing: id 0 | task 26272 | total time = 2759.31 ms / 442 tokens 6.42.099.968 I slot print_timing: id 0 | task 26272 | graphs reused = 25819 6.42.099.968 I slot print_timing: id 0 | task 26272 | graph reallocs = 0 / 0 (same size) / (changed size) 6.42.099.995 I slot release: id 0 | task 26272 | stop processing: n_tokens = 441, truncated = 0 6.42.103.114 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.138 (> 0.100 thold), f_keep = 0.048 6.42.104.168 I slot launch_slot_: id 0 | task 26452 | processing task, is_child = 0 6.44.159.030 I slot print_timing: id 0 | task 26452 | prompt eval time = 323.55 ms / 152 tokens ( 2.13 ms per token, 469.79 tokens per second) 6.44.159.036 I slot print_timing: id 0 | task 26452 | eval time = 1731.31 ms / 132 tokens ( 13.22 ms per token, 75.67 tokens per second) 6.44.159.037 I slot print_timing: id 0 | task 26452 | total time = 2054.86 ms / 284 tokens 6.44.159.038 I slot print_timing: id 0 | task 26452 | graphs reused = 25948 6.44.159.039 I slot print_timing: id 0 | task 26452 | graph reallocs = 0 / 0 (same size) / (changed size) 6.44.159.058 I slot release: id 0 | task 26452 | stop processing: n_tokens = 283, truncated = 0 6.44.162.212 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.108 (> 0.100 thold), f_keep = 0.074 6.44.162.594 I slot launch_slot_: id 0 | task 26586 | processing task, is_child = 0 6.46.639.441 I slot print_timing: id 0 | task 26586 | prompt eval time = 359.19 ms / 194 tokens ( 1.85 ms per token, 540.10 tokens per second) 6.46.639.447 I slot print_timing: id 0 | task 26586 | eval time = 2117.64 ms / 162 tokens ( 13.15 ms per token, 76.03 tokens per second) 6.46.639.448 I slot print_timing: id 0 | task 26586 | total time = 2476.84 ms / 356 tokens 6.46.639.448 I slot print_timing: id 0 | task 26586 | graphs reused = 26107 6.46.639.449 I slot print_timing: id 0 | task 26586 | graph reallocs = 0 / 0 (same size) / (changed size) 6.46.639.470 I slot release: id 0 | task 26586 | stop processing: n_tokens = 355, truncated = 0 6.46.643.039 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 355, t_last = 344463334890 6.46.643.495 I slot launch_slot_: id 0 | task 26750 | processing task, is_child = 0 6.49.772.891 I slot print_timing: id 0 | task 26750 | prompt eval time = 432.61 ms / 269 tokens ( 1.61 ms per token, 621.80 tokens per second) 6.49.772.894 I slot print_timing: id 0 | task 26750 | eval time = 2696.77 ms / 205 tokens ( 13.22 ms per token, 75.65 tokens per second) 6.49.772.895 I slot print_timing: id 0 | task 26750 | total time = 3129.38 ms / 474 tokens 6.49.772.895 I slot print_timing: id 0 | task 26750 | graphs reused = 26310 6.49.772.896 I slot print_timing: id 0 | task 26750 | graph reallocs = 0 / 0 (same size) / (changed size) 6.49.772.920 I slot release: id 0 | task 26750 | stop processing: n_tokens = 473, truncated = 0 6.49.776.482 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 473, t_last = 344466468340 6.49.777.600 I slot launch_slot_: id 0 | task 26957 | processing task, is_child = 0 6.53.232.179 I slot print_timing: id 0 | task 26957 | n_gen = 229, tg = 75.71 t/s, tg_3s = 76.04 t/s 6.56.241.091 I slot print_timing: id 0 | task 26957 | n_gen = 458, tg = 75.91 t/s, tg_3s = 76.11 t/s 6.59.248.830 I slot print_timing: id 0 | task 26957 | n_gen = 686, tg = 75.87 t/s, tg_3s = 75.80 t/s 7.02.261.088 I slot print_timing: id 0 | task 26957 | n_gen = 914, tg = 75.83 t/s, tg_3s = 75.69 t/s 7.03.717.499 I slot print_timing: id 0 | task 26957 | prompt eval time = 442.89 ms / 283 tokens ( 1.56 ms per token, 638.99 tokens per second) 7.03.717.506 I slot print_timing: id 0 | task 26957 | eval time = 13497.00 ms / 1024 tokens ( 13.19 ms per token, 75.79 tokens per second) 7.03.717.507 I slot print_timing: id 0 | task 26957 | total time = 13939.89 ms / 1307 tokens 7.03.717.508 I slot print_timing: id 0 | task 26957 | graphs reused = 27328 7.03.717.508 I slot print_timing: id 0 | task 26957 | graph reallocs = 0 / 0 (same size) / (changed size) 7.03.717.535 I slot release: id 0 | task 26957 | stop processing: n_tokens = 1306, truncated = 0 7.03.721.173 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1306, t_last = 344480412955 7.03.723.818 I slot launch_slot_: id 0 | task 27983 | processing task, is_child = 0 7.07.011.038 I slot print_timing: id 0 | task 27983 | prompt eval time = 462.75 ms / 306 tokens ( 1.51 ms per token, 661.26 tokens per second) 7.07.011.044 I slot print_timing: id 0 | task 27983 | eval time = 2824.46 ms / 215 tokens ( 13.20 ms per token, 75.77 tokens per second) 7.07.011.044 I slot print_timing: id 0 | task 27983 | total time = 3287.21 ms / 521 tokens 7.07.011.045 I slot print_timing: id 0 | task 27983 | graphs reused = 27540 7.07.011.046 I slot print_timing: id 0 | task 27983 | graph reallocs = 0 / 0 (same size) / (changed size) 7.07.011.073 I slot release: id 0 | task 27983 | stop processing: n_tokens = 520, truncated = 0 7.07.014.644 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 344483706493 7.07.015.885 I slot launch_slot_: id 0 | task 28200 | processing task, is_child = 0 7.08.859.956 I slot print_timing: id 0 | task 28200 | prompt eval time = 473.64 ms / 317 tokens ( 1.49 ms per token, 669.29 tokens per second) 7.08.859.959 I slot print_timing: id 0 | task 28200 | eval time = 1370.42 ms / 105 tokens ( 13.18 ms per token, 75.89 tokens per second) 7.08.859.960 I slot print_timing: id 0 | task 28200 | total time = 1844.06 ms / 422 tokens 7.08.859.961 I slot print_timing: id 0 | task 28200 | graphs reused = 27643 7.08.859.961 I slot print_timing: id 0 | task 28200 | graph reallocs = 0 / 0 (same size) / (changed size) 7.08.859.991 I slot release: id 0 | task 28200 | stop processing: n_tokens = 421, truncated = 0 7.08.863.645 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 421, t_last = 344485555411 7.08.864.701 I slot launch_slot_: id 0 | task 28307 | processing task, is_child = 0 7.12.330.489 I slot print_timing: id 0 | task 28307 | n_gen = 229, tg = 75.87 t/s, tg_3s = 76.20 t/s 7.12.435.776 I slot print_timing: id 0 | task 28307 | prompt eval time = 460.68 ms / 296 tokens ( 1.56 ms per token, 642.53 tokens per second) 7.12.435.782 I slot print_timing: id 0 | task 28307 | eval time = 3110.39 ms / 237 tokens ( 13.18 ms per token, 75.87 tokens per second) 7.12.435.782 I slot print_timing: id 0 | task 28307 | total time = 3571.06 ms / 533 tokens 7.12.435.783 I slot print_timing: id 0 | task 28307 | graphs reused = 27877 7.12.435.784 I slot print_timing: id 0 | task 28307 | graph reallocs = 0 / 0 (same size) / (changed size) 7.12.435.811 I slot release: id 0 | task 28307 | stop processing: n_tokens = 532, truncated = 0 7.12.439.397 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 532, t_last = 344489131231 7.12.440.781 I slot launch_slot_: id 0 | task 28546 | processing task, is_child = 0 7.15.833.276 I slot print_timing: id 0 | task 28546 | prompt eval time = 416.49 ms / 254 tokens ( 1.64 ms per token, 609.86 tokens per second) 7.15.833.279 I slot print_timing: id 0 | task 28546 | eval time = 2976.00 ms / 227 tokens ( 13.17 ms per token, 75.94 tokens per second) 7.15.833.279 I slot print_timing: id 0 | task 28546 | total time = 3392.48 ms / 481 tokens 7.15.833.280 I slot print_timing: id 0 | task 28546 | graphs reused = 28101 7.15.833.280 I slot print_timing: id 0 | task 28546 | graph reallocs = 0 / 0 (same size) / (changed size) 7.15.833.309 I slot release: id 0 | task 28546 | stop processing: n_tokens = 480, truncated = 0 7.15.836.742 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.112 (> 0.100 thold), f_keep = 0.044 7.15.837.912 I slot launch_slot_: id 0 | task 28775 | processing task, is_child = 0 7.18.243.393 I slot print_timing: id 0 | task 28775 | prompt eval time = 353.97 ms / 188 tokens ( 1.88 ms per token, 531.11 tokens per second) 7.18.243.400 I slot print_timing: id 0 | task 28775 | eval time = 2051.50 ms / 157 tokens ( 13.15 ms per token, 76.04 tokens per second) 7.18.243.400 I slot print_timing: id 0 | task 28775 | total time = 2405.47 ms / 345 tokens 7.18.243.401 I slot print_timing: id 0 | task 28775 | graphs reused = 28255 7.18.243.401 I slot print_timing: id 0 | task 28775 | graph reallocs = 0 / 0 (same size) / (changed size) 7.18.243.426 I slot release: id 0 | task 28775 | stop processing: n_tokens = 344, truncated = 0 7.18.248.021 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 344, t_last = 344494938846 7.18.249.520 I slot launch_slot_: id 0 | task 28934 | processing task, is_child = 0 7.21.685.680 I slot print_timing: id 0 | task 28934 | prompt eval time = 554.44 ms / 394 tokens ( 1.41 ms per token, 710.62 tokens per second) 7.21.685.684 I slot print_timing: id 0 | task 28934 | eval time = 2881.71 ms / 219 tokens ( 13.22 ms per token, 75.65 tokens per second) 7.21.685.684 I slot print_timing: id 0 | task 28934 | total time = 3436.15 ms / 613 tokens 7.21.685.685 I slot print_timing: id 0 | task 28934 | graphs reused = 28471 7.21.685.686 I slot print_timing: id 0 | task 28934 | graph reallocs = 0 / 0 (same size) / (changed size) 7.21.685.722 I slot release: id 0 | task 28934 | stop processing: n_tokens = 612, truncated = 0 7.21.689.774 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 612, t_last = 344498381142 7.21.691.176 I slot launch_slot_: id 0 | task 29155 | processing task, is_child = 0 7.25.582.706 I slot print_timing: id 0 | task 29155 | n_gen = 229, tg = 75.69 t/s, tg_3s = 76.02 t/s 7.28.553.637 I slot print_timing: id 0 | task 29155 | prompt eval time = 879.10 ms / 584 tokens ( 1.51 ms per token, 664.31 tokens per second) 7.28.553.639 I slot print_timing: id 0 | task 29155 | eval time = 5983.35 ms / 454 tokens ( 13.21 ms per token, 75.71 tokens per second) 7.28.553.640 I slot print_timing: id 0 | task 29155 | total time = 6862.45 ms / 1038 tokens 7.28.553.640 I slot print_timing: id 0 | task 29155 | graphs reused = 28921 7.28.553.641 I slot print_timing: id 0 | task 29155 | graph reallocs = 0 / 0 (same size) / (changed size) 7.28.553.686 I slot release: id 0 | task 29155 | stop processing: n_tokens = 1037, truncated = 0 7.28.557.788 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1037, t_last = 344505249106 7.28.560.157 I slot launch_slot_: id 0 | task 29612 | processing task, is_child = 0 7.32.256.320 I slot print_timing: id 0 | task 29612 | n_gen = 229, tg = 75.83 t/s, tg_3s = 76.16 t/s 7.34.959.228 I slot print_timing: id 0 | task 29612 | prompt eval time = 689.32 ms / 518 tokens ( 1.33 ms per token, 751.47 tokens per second) 7.34.959.234 I slot print_timing: id 0 | task 29612 | eval time = 5709.75 ms / 434 tokens ( 13.19 ms per token, 75.84 tokens per second) 7.34.959.235 I slot print_timing: id 0 | task 29612 | total time = 6399.06 ms / 952 tokens 7.34.959.236 I slot print_timing: id 0 | task 29612 | graphs reused = 29352 7.34.959.236 I slot print_timing: id 0 | task 29612 | graph reallocs = 0 / 0 (same size) / (changed size) 7.34.959.278 I slot release: id 0 | task 29612 | stop processing: n_tokens = 951, truncated = 0 7.34.964.009 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 951, t_last = 344511654698 7.34.967.472 I slot launch_slot_: id 0 | task 30049 | processing task, is_child = 0 7.38.528.294 I slot print_timing: id 0 | task 30049 | n_gen = 229, tg = 75.91 t/s, tg_3s = 76.24 t/s 7.39.001.402 I slot print_timing: id 0 | task 30049 | prompt eval time = 557.30 ms / 399 tokens ( 1.40 ms per token, 715.96 tokens per second) 7.39.001.409 I slot print_timing: id 0 | task 30049 | eval time = 3476.62 ms / 265 tokens ( 13.17 ms per token, 75.94 tokens per second) 7.39.001.409 I slot print_timing: id 0 | task 30049 | total time = 4033.92 ms / 664 tokens 7.39.001.410 I slot print_timing: id 0 | task 30049 | graphs reused = 29614 7.39.001.411 I slot print_timing: id 0 | task 30049 | graph reallocs = 0 / 0 (same size) / (changed size) 7.39.001.446 I slot release: id 0 | task 30049 | stop processing: n_tokens = 665, truncated = 0 7.39.005.150 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 665, t_last = 344515696866 7.39.006.746 I slot launch_slot_: id 0 | task 30316 | processing task, is_child = 0 7.42.195.441 I slot print_timing: id 0 | task 30316 | prompt eval time = 495.03 ms / 335 tokens ( 1.48 ms per token, 676.73 tokens per second) 7.42.195.450 I slot print_timing: id 0 | task 30316 | eval time = 2693.66 ms / 205 tokens ( 13.20 ms per token, 75.73 tokens per second) 7.42.195.451 I slot print_timing: id 0 | task 30316 | total time = 3188.69 ms / 540 tokens 7.42.195.452 I slot print_timing: id 0 | task 30316 | graphs reused = 29816 7.42.195.452 I slot print_timing: id 0 | task 30316 | graph reallocs = 0 / 0 (same size) / (changed size) 7.42.195.480 I slot release: id 0 | task 30316 | stop processing: n_tokens = 541, truncated = 0 7.42.200.227 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 541, t_last = 344518890900 7.42.202.190 I slot launch_slot_: id 0 | task 30523 | processing task, is_child = 0 7.46.109.090 I slot print_timing: id 0 | task 30523 | n_gen = 229, tg = 75.68 t/s, tg_3s = 76.02 t/s 7.49.120.109 I slot print_timing: id 0 | task 30523 | n_gen = 457, tg = 75.70 t/s, tg_3s = 75.72 t/s 7.52.123.586 I slot print_timing: id 0 | task 30523 | n_gen = 684, tg = 75.66 t/s, tg_3s = 75.58 t/s 7.52.894.558 I slot print_timing: id 0 | task 30523 | prompt eval time = 894.36 ms / 603 tokens ( 1.48 ms per token, 674.23 tokens per second) 7.52.894.565 I slot print_timing: id 0 | task 30523 | eval time = 9798.00 ms / 742 tokens ( 13.22 ms per token, 75.63 tokens per second) 7.52.894.566 I slot print_timing: id 0 | task 30523 | total time = 10692.36 ms / 1345 tokens 7.52.894.566 I slot print_timing: id 0 | task 30523 | graphs reused = 30553 7.52.894.567 I slot print_timing: id 0 | task 30523 | graph reallocs = 0 / 0 (same size) / (changed size) 7.52.894.609 I slot release: id 0 | task 30523 | stop processing: n_tokens = 1346, truncated = 0 7.52.898.470 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1346, t_last = 344529590029 7.52.901.510 I slot launch_slot_: id 0 | task 31268 | processing task, is_child = 0 7.56.396.799 I slot print_timing: id 0 | task 31268 | n_gen = 229, tg = 75.99 t/s, tg_3s = 76.32 t/s 7.57.413.436 I slot print_timing: id 0 | task 31268 | prompt eval time = 494.73 ms / 333 tokens ( 1.49 ms per token, 673.09 tokens per second) 7.57.413.438 I slot print_timing: id 0 | task 31268 | eval time = 4017.18 ms / 306 tokens ( 13.17 ms per token, 75.92 tokens per second) 7.57.413.439 I slot print_timing: id 0 | task 31268 | total time = 4511.91 ms / 639 tokens 7.57.413.440 I slot print_timing: id 0 | task 31268 | graphs reused = 30856 7.57.413.440 I slot print_timing: id 0 | task 31268 | graph reallocs = 0 / 0 (same size) / (changed size) 7.57.413.472 I slot release: id 0 | task 31268 | stop processing: n_tokens = 640, truncated = 0 7.57.417.378 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 640, t_last = 344534108892 7.57.418.919 I slot launch_slot_: id 0 | task 31576 | processing task, is_child = 0 8.01.043.759 I slot print_timing: id 0 | task 31576 | n_gen = 229, tg = 75.82 t/s, tg_3s = 76.15 t/s 8.03.171.453 I slot print_timing: id 0 | task 31576 | prompt eval time = 617.74 ms / 460 tokens ( 1.34 ms per token, 744.65 tokens per second) 8.03.171.459 I slot print_timing: id 0 | task 31576 | eval time = 5134.79 ms / 390 tokens ( 13.20 ms per token, 75.76 tokens per second) 8.03.171.460 I slot print_timing: id 0 | task 31576 | total time = 5752.53 ms / 850 tokens 8.03.171.461 I slot print_timing: id 0 | task 31576 | graphs reused = 31242 8.03.171.461 I slot print_timing: id 0 | task 31576 | graph reallocs = 0 / 0 (same size) / (changed size) 8.03.171.497 I slot release: id 0 | task 31576 | stop processing: n_tokens = 851, truncated = 0 8.03.175.017 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 851, t_last = 344539866918 8.03.176.947 I slot launch_slot_: id 0 | task 31968 | processing task, is_child = 0 8.05.560.918 I slot print_timing: id 0 | task 31968 | prompt eval time = 383.84 ms / 225 tokens ( 1.71 ms per token, 586.18 tokens per second) 8.05.560.921 I slot print_timing: id 0 | task 31968 | eval time = 2000.12 ms / 153 tokens ( 13.16 ms per token, 76.00 tokens per second) 8.05.560.921 I slot print_timing: id 0 | task 31968 | total time = 2383.96 ms / 378 tokens 8.05.560.922 I slot print_timing: id 0 | task 31968 | graphs reused = 31392 8.05.560.922 I slot print_timing: id 0 | task 31968 | graph reallocs = 0 / 0 (same size) / (changed size) 8.05.560.947 I slot release: id 0 | task 31968 | stop processing: n_tokens = 379, truncated = 0 8.05.564.631 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 379, t_last = 344542256367 8.05.565.673 I slot launch_slot_: id 0 | task 32123 | processing task, is_child = 0 8.09.135.901 I slot print_timing: id 0 | task 32123 | n_gen = 229, tg = 75.96 t/s, tg_3s = 76.29 t/s 8.10.018.717 I slot print_timing: id 0 | task 32123 | prompt eval time = 568.69 ms / 415 tokens ( 1.37 ms per token, 729.75 tokens per second) 8.10.018.720 I slot print_timing: id 0 | task 32123 | eval time = 3884.34 ms / 296 tokens ( 13.17 ms per token, 75.95 tokens per second) 8.10.018.720 I slot print_timing: id 0 | task 32123 | total time = 4453.03 ms / 711 tokens 8.10.018.721 I slot print_timing: id 0 | task 32123 | graphs reused = 31685 8.10.018.721 I slot print_timing: id 0 | task 32123 | graph reallocs = 0 / 0 (same size) / (changed size) 8.10.018.754 I slot release: id 0 | task 32123 | stop processing: n_tokens = 712, truncated = 0 8.10.022.567 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 712, t_last = 344546714174 8.10.024.363 I slot launch_slot_: id 0 | task 32421 | processing task, is_child = 0 8.13.727.050 I slot print_timing: id 0 | task 32421 | n_gen = 229, tg = 75.88 t/s, tg_3s = 76.22 t/s 8.15.086.605 I slot print_timing: id 0 | task 32421 | prompt eval time = 698.11 ms / 519 tokens ( 1.35 ms per token, 743.44 tokens per second) 8.15.086.608 I slot print_timing: id 0 | task 32421 | eval time = 4364.12 ms / 332 tokens ( 13.18 ms per token, 75.85 tokens per second) 8.15.086.608 I slot print_timing: id 0 | task 32421 | total time = 5062.23 ms / 851 tokens 8.15.086.609 I slot print_timing: id 0 | task 32421 | graphs reused = 32014 8.15.086.610 I slot print_timing: id 0 | task 32421 | graph reallocs = 0 / 0 (same size) / (changed size) 8.15.086.651 I slot release: id 0 | task 32421 | stop processing: n_tokens = 852, truncated = 0 8.15.090.827 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 852, t_last = 344551782071 8.15.092.783 I slot launch_slot_: id 0 | task 32756 | processing task, is_child = 0 8.18.998.564 I slot print_timing: id 0 | task 32756 | n_gen = 229, tg = 75.77 t/s, tg_3s = 76.10 t/s 8.22.002.492 I slot print_timing: id 0 | task 32756 | n_gen = 457, tg = 75.83 t/s, tg_3s = 75.90 t/s 8.25.003.676 I slot print_timing: id 0 | task 32756 | n_gen = 684, tg = 75.77 t/s, tg_3s = 75.64 t/s 8.28.004.016 I slot print_timing: id 0 | task 32756 | n_gen = 910, tg = 75.66 t/s, tg_3s = 75.32 t/s 8.28.270.855 I slot print_timing: id 0 | task 32756 | prompt eval time = 896.52 ms / 602 tokens ( 1.49 ms per token, 671.48 tokens per second) 8.28.270.861 I slot print_timing: id 0 | task 32756 | eval time = 12281.54 ms / 930 tokens ( 13.22 ms per token, 75.64 tokens per second) 8.28.270.861 I slot print_timing: id 0 | task 32756 | total time = 13178.06 ms / 1532 tokens 8.28.270.862 I slot print_timing: id 0 | task 32756 | graphs reused = 32939 8.28.270.863 I slot print_timing: id 0 | task 32756 | graph reallocs = 0 / 0 (same size) / (changed size) 8.28.270.909 I slot release: id 0 | task 32756 | stop processing: n_tokens = 1536, truncated = 0 8.28.274.744 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1536, t_last = 344564966329 8.28.278.320 I slot launch_slot_: id 0 | task 33689 | processing task, is_child = 0 8.31.849.454 I slot print_timing: id 0 | task 33689 | n_gen = 229, tg = 75.79 t/s, tg_3s = 76.12 t/s 8.32.127.145 I slot print_timing: id 0 | task 33689 | prompt eval time = 562.80 ms / 407 tokens ( 1.38 ms per token, 723.17 tokens per second) 8.32.127.150 I slot print_timing: id 0 | task 33689 | eval time = 3286.02 ms / 250 tokens ( 13.20 ms per token, 75.78 tokens per second) 8.32.127.151 I slot print_timing: id 0 | task 33689 | total time = 3848.82 ms / 657 tokens 8.32.127.152 I slot print_timing: id 0 | task 33689 | graphs reused = 33186 8.32.127.152 I slot print_timing: id 0 | task 33689 | graph reallocs = 0 / 0 (same size) / (changed size) 8.32.127.187 I slot release: id 0 | task 33689 | stop processing: n_tokens = 661, truncated = 0 8.32.131.049 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 661, t_last = 344568822607 8.32.132.663 I slot launch_slot_: id 0 | task 33941 | processing task, is_child = 0 8.35.775.485 I slot print_timing: id 0 | task 33941 | n_gen = 229, tg = 75.79 t/s, tg_3s = 76.13 t/s 8.38.782.282 I slot print_timing: id 0 | task 33941 | n_gen = 457, tg = 75.81 t/s, tg_3s = 75.83 t/s 8.38.927.164 I slot print_timing: id 0 | task 33941 | prompt eval time = 634.65 ms / 484 tokens ( 1.31 ms per token, 762.62 tokens per second) 8.38.927.170 I slot print_timing: id 0 | task 33941 | eval time = 6159.84 ms / 468 tokens ( 13.19 ms per token, 75.81 tokens per second) 8.38.927.170 I slot print_timing: id 0 | task 33941 | total time = 6794.49 ms / 952 tokens 8.38.927.171 I slot print_timing: id 0 | task 33941 | graphs reused = 33650 8.38.927.171 I slot print_timing: id 0 | task 33941 | graph reallocs = 0 / 0 (same size) / (changed size) 8.38.927.213 I slot release: id 0 | task 33941 | stop processing: n_tokens = 956, truncated = 0 8.38.931.335 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 956, t_last = 344575622633 8.38.933.628 I slot launch_slot_: id 0 | task 34411 | processing task, is_child = 0 8.42.555.244 I slot print_timing: id 0 | task 34411 | n_gen = 228, tg = 75.51 t/s, tg_3s = 75.84 t/s 8.42.567.955 I slot print_timing: id 0 | task 34411 | prompt eval time = 615.40 ms / 457 tokens ( 1.35 ms per token, 742.60 tokens per second) 8.42.567.958 I slot print_timing: id 0 | task 34411 | eval time = 3018.92 ms / 229 tokens ( 13.24 ms per token, 75.52 tokens per second) 8.42.567.959 I slot print_timing: id 0 | task 34411 | total time = 3634.32 ms / 686 tokens 8.42.567.960 I slot print_timing: id 0 | task 34411 | graphs reused = 33876 8.42.567.960 I slot print_timing: id 0 | task 34411 | graph reallocs = 0 / 0 (same size) / (changed size) 8.42.567.999 I slot release: id 0 | task 34411 | stop processing: n_tokens = 690, truncated = 0 8.42.572.229 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 690, t_last = 344579263419 8.42.574.253 I slot launch_slot_: id 0 | task 34642 | processing task, is_child = 0 8.46.470.652 I slot print_timing: id 0 | task 34642 | n_gen = 228, tg = 75.56 t/s, tg_3s = 75.89 t/s 8.48.952.722 I slot print_timing: id 0 | task 34642 | prompt eval time = 892.04 ms / 597 tokens ( 1.49 ms per token, 669.25 tokens per second) 8.48.952.725 I slot print_timing: id 0 | task 34642 | eval time = 5486.42 ms / 416 tokens ( 13.22 ms per token, 75.64 tokens per second) 8.48.952.726 I slot print_timing: id 0 | task 34642 | total time = 6378.46 ms / 1013 tokens 8.48.952.726 I slot print_timing: id 0 | task 34642 | graphs reused = 34289 8.48.952.727 I slot print_timing: id 0 | task 34642 | graph reallocs = 0 / 0 (same size) / (changed size) 8.48.952.772 I slot release: id 0 | task 34642 | stop processing: n_tokens = 1012, truncated = 0 8.48.956.906 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1012, t_last = 344585648192 8.48.959.015 I slot launch_slot_: id 0 | task 35061 | processing task, is_child = 0 8.52.945.546 I slot print_timing: id 0 | task 35061 | n_gen = 228, tg = 75.59 t/s, tg_3s = 75.93 t/s 8.53.820.578 I slot print_timing: id 0 | task 35061 | prompt eval time = 983.63 ms / 688 tokens ( 1.43 ms per token, 699.45 tokens per second) 8.53.820.581 I slot print_timing: id 0 | task 35061 | eval time = 3877.93 ms / 294 tokens ( 13.24 ms per token, 75.56 tokens per second) 8.53.820.582 I slot print_timing: id 0 | task 35061 | total time = 4861.56 ms / 982 tokens 8.53.820.582 I slot print_timing: id 0 | task 35061 | graphs reused = 34580 8.53.820.583 I slot print_timing: id 0 | task 35061 | graph reallocs = 0 / 0 (same size) / (changed size) 8.53.820.637 I slot release: id 0 | task 35061 | stop processing: n_tokens = 981, truncated = 0 8.53.824.783 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 981, t_last = 344590516058 8.53.827.410 I slot launch_slot_: id 0 | task 35358 | processing task, is_child = 0 8.57.475.675 I slot print_timing: id 0 | task 35358 | n_gen = 228, tg = 75.67 t/s, tg_3s = 76.00 t/s 8.58.179.777 I slot print_timing: id 0 | task 35358 | prompt eval time = 648.25 ms / 489 tokens ( 1.33 ms per token, 754.34 tokens per second) 8.58.179.780 I slot print_timing: id 0 | task 35358 | eval time = 3704.11 ms / 281 tokens ( 13.23 ms per token, 75.59 tokens per second) 8.58.179.780 I slot print_timing: id 0 | task 35358 | total time = 4352.35 ms / 770 tokens 8.58.179.781 I slot print_timing: id 0 | task 35358 | graphs reused = 34857 8.58.179.782 I slot print_timing: id 0 | task 35358 | graph reallocs = 0 / 0 (same size) / (changed size) 8.58.179.821 I slot release: id 0 | task 35358 | stop processing: n_tokens = 769, truncated = 0 8.58.184.047 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 769, t_last = 344594875241 8.58.186.088 I slot launch_slot_: id 0 | task 35641 | processing task, is_child = 0 9.02.017.927 I slot print_timing: id 0 | task 35641 | n_gen = 228, tg = 75.57 t/s, tg_3s = 75.90 t/s 9.03.155.354 I slot print_timing: id 0 | task 35641 | prompt eval time = 827.97 ms / 550 tokens ( 1.51 ms per token, 664.28 tokens per second) 9.03.155.357 I slot print_timing: id 0 | task 35641 | eval time = 4141.29 ms / 314 tokens ( 13.23 ms per token, 75.58 tokens per second) 9.03.155.358 I slot print_timing: id 0 | task 35641 | total time = 4969.26 ms / 864 tokens 9.03.155.359 I slot print_timing: id 0 | task 35641 | graphs reused = 35168 9.03.155.359 I slot print_timing: id 0 | task 35641 | graph reallocs = 0 / 0 (same size) / (changed size) 9.03.155.407 I slot release: id 0 | task 35641 | stop processing: n_tokens = 863, truncated = 0 9.03.159.105 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 863, t_last = 344599850827 9.03.161.127 I slot launch_slot_: id 0 | task 35958 | processing task, is_child = 0 9.06.656.886 I slot print_timing: id 0 | task 35958 | n_gen = 229, tg = 75.92 t/s, tg_3s = 76.26 t/s 9.07.884.555 I slot print_timing: id 0 | task 35958 | prompt eval time = 492.73 ms / 334 tokens ( 1.48 ms per token, 677.86 tokens per second) 9.07.884.561 I slot print_timing: id 0 | task 35958 | eval time = 4230.69 ms / 322 tokens ( 13.18 ms per token, 75.87 tokens per second) 9.07.884.562 I slot print_timing: id 0 | task 35958 | total time = 4723.42 ms / 656 tokens 9.07.884.562 I slot print_timing: id 0 | task 35958 | graphs reused = 35487 9.07.884.563 I slot print_timing: id 0 | task 35958 | graph reallocs = 0 / 0 (same size) / (changed size) 9.07.884.595 I slot release: id 0 | task 35958 | stop processing: n_tokens = 655, truncated = 0 9.07.888.324 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 655, t_last = 344604580015 9.07.889.824 I slot launch_slot_: id 0 | task 36282 | processing task, is_child = 0 9.11.469.120 I slot print_timing: id 0 | task 36282 | n_gen = 229, tg = 75.75 t/s, tg_3s = 76.09 t/s 9.13.504.515 I slot print_timing: id 0 | task 36282 | prompt eval time = 569.56 ms / 416 tokens ( 1.37 ms per token, 730.38 tokens per second) 9.13.504.519 I slot print_timing: id 0 | task 36282 | eval time = 5045.12 ms / 383 tokens ( 13.21 ms per token, 75.72 tokens per second) 9.13.504.520 I slot print_timing: id 0 | task 36282 | total time = 5614.68 ms / 799 tokens 9.13.504.520 I slot print_timing: id 0 | task 36282 | graphs reused = 35866 9.13.504.521 I slot print_timing: id 0 | task 36282 | graph reallocs = 0 / 0 (same size) / (changed size) 9.13.504.553 I slot release: id 0 | task 36282 | stop processing: n_tokens = 798, truncated = 0 9.13.509.312 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 798, t_last = 344610199973 9.13.511.529 I slot launch_slot_: id 0 | task 36667 | processing task, is_child = 0 9.16.735.263 I slot print_timing: id 0 | task 36667 | prompt eval time = 1040.35 ms / 754 tokens ( 1.38 ms per token, 724.76 tokens per second) 9.16.735.269 I slot print_timing: id 0 | task 36667 | eval time = 2183.38 ms / 166 tokens ( 13.23 ms per token, 75.57 tokens per second) 9.16.735.269 I slot print_timing: id 0 | task 36667 | total time = 3223.73 ms / 920 tokens 9.16.735.270 I slot print_timing: id 0 | task 36667 | graphs reused = 36029 9.16.735.271 I slot print_timing: id 0 | task 36667 | graph reallocs = 0 / 0 (same size) / (changed size) 9.16.735.323 I slot release: id 0 | task 36667 | stop processing: n_tokens = 919, truncated = 0 9.16.739.504 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 919, t_last = 344613430743 9.16.741.605 I slot launch_slot_: id 0 | task 36836 | processing task, is_child = 0 9.20.736.219 I slot print_timing: id 0 | task 36836 | n_gen = 228, tg = 75.60 t/s, tg_3s = 75.93 t/s 9.22.738.791 I slot print_timing: id 0 | task 36836 | prompt eval time = 991.79 ms / 706 tokens ( 1.40 ms per token, 711.84 tokens per second) 9.22.738.796 I slot print_timing: id 0 | task 36836 | eval time = 5005.39 ms / 379 tokens ( 13.24 ms per token, 75.52 tokens per second) 9.22.738.797 I slot print_timing: id 0 | task 36836 | total time = 5997.18 ms / 1085 tokens 9.22.738.798 I slot print_timing: id 0 | task 36836 | graphs reused = 36404 9.22.738.798 I slot print_timing: id 0 | task 36836 | graph reallocs = 0 / 0 (same size) / (changed size) 9.22.738.845 I slot release: id 0 | task 36836 | stop processing: n_tokens = 1084, truncated = 0 9.22.742.269 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1084, t_last = 344619434266 9.22.744.567 I slot launch_slot_: id 0 | task 37218 | processing task, is_child = 0 9.26.143.590 I slot print_timing: id 0 | task 37218 | n_gen = 229, tg = 75.99 t/s, tg_3s = 76.33 t/s 9.29.147.178 I slot print_timing: id 0 | task 37218 | n_gen = 457, tg = 75.95 t/s, tg_3s = 75.91 t/s 9.29.278.508 I slot print_timing: id 0 | task 37218 | prompt eval time = 398.70 ms / 233 tokens ( 1.71 ms per token, 584.40 tokens per second) 9.29.278.514 I slot print_timing: id 0 | task 37218 | eval time = 6135.23 ms / 467 tokens ( 13.17 ms per token, 75.95 tokens per second) 9.29.278.515 I slot print_timing: id 0 | task 37218 | total time = 6533.93 ms / 700 tokens 9.29.278.515 I slot print_timing: id 0 | task 37218 | graphs reused = 36867 9.29.278.516 I slot print_timing: id 0 | task 37218 | graph reallocs = 0 / 0 (same size) / (changed size) 9.29.278.541 I slot release: id 0 | task 37218 | stop processing: n_tokens = 699, truncated = 0 9.29.281.824 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.133 (> 0.100 thold), f_keep = 0.033 9.29.283.430 I slot launch_slot_: id 0 | task 37687 | processing task, is_child = 0 9.31.913.491 I slot print_timing: id 0 | task 37687 | prompt eval time = 343.55 ms / 173 tokens ( 1.99 ms per token, 503.57 tokens per second) 9.31.913.497 I slot print_timing: id 0 | task 37687 | eval time = 2286.50 ms / 175 tokens ( 13.14 ms per token, 76.10 tokens per second) 9.31.913.498 I slot print_timing: id 0 | task 37687 | total time = 2630.05 ms / 348 tokens 9.31.913.498 I slot print_timing: id 0 | task 37687 | graphs reused = 37039 9.31.913.499 I slot print_timing: id 0 | task 37687 | graph reallocs = 0 / 0 (same size) / (changed size) 9.31.913.518 I slot release: id 0 | task 37687 | stop processing: n_tokens = 347, truncated = 0 9.31.916.711 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.111 (> 0.100 thold), f_keep = 0.063 9.31.917.139 I slot launch_slot_: id 0 | task 37864 | processing task, is_child = 0 9.35.297.332 I slot print_timing: id 0 | task 37864 | n_gen = 230, tg = 76.05 t/s, tg_3s = 76.38 t/s 9.38.305.211 I slot print_timing: id 0 | task 37864 | n_gen = 458, tg = 75.93 t/s, tg_3s = 75.80 t/s 9.41.318.187 I slot print_timing: id 0 | task 37864 | n_gen = 686, tg = 75.84 t/s, tg_3s = 75.67 t/s 9.44.322.125 I slot print_timing: id 0 | task 37864 | n_gen = 913, tg = 75.77 t/s, tg_3s = 75.57 t/s 9.45.793.497 I slot print_timing: id 0 | task 37864 | prompt eval time = 369.02 ms / 199 tokens ( 1.85 ms per token, 539.26 tokens per second) 9.45.793.503 I slot print_timing: id 0 | task 37864 | eval time = 13507.33 ms / 1024 tokens ( 13.20 ms per token, 75.74 tokens per second) 9.45.793.504 I slot print_timing: id 0 | task 37864 | total time = 13876.35 ms / 1223 tokens 9.45.793.505 I slot print_timing: id 0 | task 37864 | graphs reused = 38057 9.45.793.505 I slot print_timing: id 0 | task 37864 | graph reallocs = 0 / 0 (same size) / (changed size) 9.45.793.536 I slot release: id 0 | task 37864 | stop processing: n_tokens = 1222, truncated = 0 9.45.796.971 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.148 (> 0.100 thold), f_keep = 0.018 9.45.799.530 I slot launch_slot_: id 0 | task 38890 | processing task, is_child = 0 9.49.124.804 I slot print_timing: id 0 | task 38890 | n_gen = 229, tg = 75.91 t/s, tg_3s = 76.24 t/s 9.49.428.466 I slot print_timing: id 0 | task 38890 | prompt eval time = 321.57 ms / 149 tokens ( 2.16 ms per token, 463.35 tokens per second) 9.49.428.472 I slot print_timing: id 0 | task 38890 | eval time = 3307.35 ms / 252 tokens ( 13.18 ms per token, 75.89 tokens per second) 9.49.428.473 I slot print_timing: id 0 | task 38890 | total time = 3628.92 ms / 401 tokens 9.49.428.473 I slot print_timing: id 0 | task 38890 | graphs reused = 38306 9.49.428.474 I slot print_timing: id 0 | task 38890 | graph reallocs = 0 / 0 (same size) / (changed size) 9.49.428.493 I slot release: id 0 | task 38890 | stop processing: n_tokens = 400, truncated = 0 9.49.431.925 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 344646123913 9.49.432.409 I slot launch_slot_: id 0 | task 39144 | processing task, is_child = 0 9.52.825.233 I slot print_timing: id 0 | task 39144 | n_gen = 230, tg = 76.03 t/s, tg_3s = 76.36 t/s 9.55.833.119 I slot print_timing: id 0 | task 39144 | n_gen = 458, tg = 75.92 t/s, tg_3s = 75.80 t/s 9.58.839.896 I slot print_timing: id 0 | task 39144 | n_gen = 686, tg = 75.89 t/s, tg_3s = 75.83 t/s 10.01.850.136 I slot print_timing: id 0 | task 39144 | n_gen = 914, tg = 75.85 t/s, tg_3s = 75.74 t/s 10.03.307.464 I slot print_timing: id 0 | task 39144 | prompt eval time = 380.88 ms / 216 tokens ( 1.76 ms per token, 567.11 tokens per second) 10.03.307.470 I slot print_timing: id 0 | task 39144 | eval time = 13494.17 ms / 1024 tokens ( 13.19 ms per token, 75.81 tokens per second) 10.03.307.471 I slot print_timing: id 0 | task 39144 | total time = 13875.05 ms / 1240 tokens 10.03.307.471 I slot print_timing: id 0 | task 39144 | graphs reused = 39324 10.03.307.472 I slot print_timing: id 0 | task 39144 | graph reallocs = 0 / 0 (same size) / (changed size) 10.03.307.495 I slot release: id 0 | task 39144 | stop processing: n_tokens = 1239, truncated = 0 10.03.310.792 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.160 (> 0.100 thold), f_keep = 0.017 10.03.313.291 I slot launch_slot_: id 0 | task 40170 | processing task, is_child = 0 10.05.050.800 I slot print_timing: id 0 | task 40170 | prompt eval time = 300.51 ms / 131 tokens ( 2.29 ms per token, 435.93 tokens per second) 10.05.050.805 I slot print_timing: id 0 | task 40170 | eval time = 1436.99 ms / 110 tokens ( 13.18 ms per token, 75.85 tokens per second) 10.05.050.806 I slot print_timing: id 0 | task 40170 | total time = 1737.50 ms / 241 tokens 10.05.050.807 I slot print_timing: id 0 | task 40170 | graphs reused = 39432 10.05.050.807 I slot print_timing: id 0 | task 40170 | graph reallocs = 0 / 0 (same size) / (changed size) 10.05.050.825 I slot release: id 0 | task 40170 | stop processing: n_tokens = 240, truncated = 0 10.05.053.888 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.121 (> 0.100 thold), f_keep = 0.087 10.05.054.237 I slot launch_slot_: id 0 | task 40282 | processing task, is_child = 0 10.08.408.258 I slot print_timing: id 0 | task 40282 | n_gen = 229, tg = 75.83 t/s, tg_3s = 76.16 t/s 10.11.420.592 I slot print_timing: id 0 | task 40282 | n_gen = 457, tg = 75.76 t/s, tg_3s = 75.69 t/s 10.13.351.530 I slot print_timing: id 0 | task 40282 | prompt eval time = 347.24 ms / 174 tokens ( 2.00 ms per token, 501.10 tokens per second) 10.13.351.535 I slot print_timing: id 0 | task 40282 | eval time = 7950.05 ms / 603 tokens ( 13.21 ms per token, 75.72 tokens per second) 10.13.351.536 I slot print_timing: id 0 | task 40282 | total time = 8297.28 ms / 777 tokens 10.13.351.537 I slot print_timing: id 0 | task 40282 | graphs reused = 40030 10.13.351.537 I slot print_timing: id 0 | task 40282 | graph reallocs = 0 / 0 (same size) / (changed size) 10.13.351.558 I slot release: id 0 | task 40282 | stop processing: n_tokens = 776, truncated = 0 10.13.354.813 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.129 (> 0.100 thold), f_keep = 0.027 10.13.356.514 I slot launch_slot_: id 0 | task 40887 | processing task, is_child = 0 10.16.698.704 I slot print_timing: id 0 | task 40887 | n_gen = 230, tg = 76.01 t/s, tg_3s = 76.34 t/s 10.17.330.893 I slot print_timing: id 0 | task 40887 | prompt eval time = 329.36 ms / 163 tokens ( 2.02 ms per token, 494.90 tokens per second) 10.17.330.899 I slot print_timing: id 0 | task 40887 | eval time = 3645.01 ms / 278 tokens ( 13.16 ms per token, 75.99 tokens per second) 10.17.330.900 I slot print_timing: id 0 | task 40887 | total time = 3974.37 ms / 441 tokens 10.17.330.901 I slot print_timing: id 0 | task 40887 | graphs reused = 40305 10.17.330.901 I slot print_timing: id 0 | task 40887 | graph reallocs = 0 / 0 (same size) / (changed size) 10.17.330.922 I slot release: id 0 | task 40887 | stop processing: n_tokens = 440, truncated = 0 10.17.334.298 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.208 (> 0.100 thold), f_keep = 0.048 10.17.335.003 I slot launch_slot_: id 0 | task 41167 | processing task, is_child = 0 10.20.624.326 I slot print_timing: id 0 | task 41167 | n_gen = 229, tg = 75.91 t/s, tg_3s = 76.25 t/s 10.23.625.369 I slot print_timing: id 0 | task 41167 | n_gen = 457, tg = 75.94 t/s, tg_3s = 75.97 t/s 10.24.178.079 I slot print_timing: id 0 | task 41167 | prompt eval time = 285.86 ms / 101 tokens ( 2.83 ms per token, 353.32 tokens per second) 10.24.178.086 I slot print_timing: id 0 | task 41167 | eval time = 6557.20 ms / 499 tokens ( 13.17 ms per token, 75.95 tokens per second) 10.24.178.086 I slot print_timing: id 0 | task 41167 | total time = 6843.06 ms / 600 tokens 10.24.178.087 I slot print_timing: id 0 | task 41167 | graphs reused = 40800 10.24.178.088 I slot print_timing: id 0 | task 41167 | graph reallocs = 0 / 0 (same size) / (changed size) 10.24.178.106 I slot release: id 0 | task 41167 | stop processing: n_tokens = 599, truncated = 0 10.24.181.468 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.126 (> 0.100 thold), f_keep = 0.035 10.24.182.932 I slot launch_slot_: id 0 | task 41668 | processing task, is_child = 0 10.27.536.276 I slot print_timing: id 0 | task 41668 | n_gen = 230, tg = 76.08 t/s, tg_3s = 76.41 t/s 10.30.545.835 I slot print_timing: id 0 | task 41668 | n_gen = 458, tg = 75.92 t/s, tg_3s = 75.76 t/s 10.31.892.850 I slot print_timing: id 0 | task 41668 | prompt eval time = 343.16 ms / 167 tokens ( 2.05 ms per token, 486.66 tokens per second) 10.31.892.856 I slot print_timing: id 0 | task 41668 | eval time = 7366.75 ms / 560 tokens ( 13.18 ms per token, 75.88 tokens per second) 10.31.892.857 I slot print_timing: id 0 | task 41668 | total time = 7709.91 ms / 727 tokens 10.31.892.857 I slot print_timing: id 0 | task 41668 | graphs reused = 41356 10.31.892.858 I slot print_timing: id 0 | task 41668 | graph reallocs = 0 / 0 (same size) / (changed size) 10.31.892.880 I slot release: id 0 | task 41668 | stop processing: n_tokens = 726, truncated = 0 10.31.896.215 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.123 (> 0.100 thold), f_keep = 0.029 10.31.897.896 I slot launch_slot_: id 0 | task 42230 | processing task, is_child = 0 10.35.253.397 I slot print_timing: id 0 | task 42230 | n_gen = 230, tg = 76.07 t/s, tg_3s = 76.40 t/s 10.36.148.929 I slot print_timing: id 0 | task 42230 | prompt eval time = 345.07 ms / 171 tokens ( 2.02 ms per token, 495.55 tokens per second) 10.36.148.934 I slot print_timing: id 0 | task 42230 | eval time = 3905.95 ms / 298 tokens ( 13.15 ms per token, 76.04 tokens per second) 10.36.148.935 I slot print_timing: id 0 | task 42230 | total time = 4251.03 ms / 469 tokens 10.36.148.936 I slot print_timing: id 0 | task 42230 | graphs reused = 41651 10.36.148.936 I slot print_timing: id 0 | task 42230 | graph reallocs = 0 / 0 (same size) / (changed size) 10.36.148.957 I slot release: id 0 | task 42230 | stop processing: n_tokens = 468, truncated = 0 10.36.151.944 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.117 (> 0.100 thold), f_keep = 0.045 10.36.153.026 I slot launch_slot_: id 0 | task 42530 | processing task, is_child = 0 10.39.510.914 I slot print_timing: id 0 | task 42530 | n_gen = 230, tg = 76.09 t/s, tg_3s = 76.43 t/s 10.42.515.625 I slot print_timing: id 0 | task 42530 | n_gen = 458, tg = 75.99 t/s, tg_3s = 75.88 t/s 10.43.019.296 I slot print_timing: id 0 | task 42530 | prompt eval time = 348.47 ms / 179 tokens ( 1.95 ms per token, 513.68 tokens per second) 10.43.019.302 I slot print_timing: id 0 | task 42530 | eval time = 6517.79 ms / 496 tokens ( 13.17 ms per token, 75.95 tokens per second) 10.43.019.303 I slot print_timing: id 0 | task 42530 | total time = 6866.26 ms / 675 tokens 10.43.019.303 I slot print_timing: id 0 | task 42530 | graphs reused = 42143 10.43.019.304 I slot print_timing: id 0 | task 42530 | graph reallocs = 0 / 0 (same size) / (changed size) 10.43.019.324 I slot release: id 0 | task 42530 | stop processing: n_tokens = 674, truncated = 0 10.43.022.630 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.127 (> 0.100 thold), f_keep = 0.031 10.43.024.182 I slot launch_slot_: id 0 | task 43028 | processing task, is_child = 0 10.45.803.556 I slot print_timing: id 0 | task 43028 | prompt eval time = 340.19 ms / 165 tokens ( 2.06 ms per token, 485.02 tokens per second) 10.45.803.562 I slot print_timing: id 0 | task 43028 | eval time = 2439.17 ms / 186 tokens ( 13.18 ms per token, 75.85 tokens per second) 10.45.803.563 I slot print_timing: id 0 | task 43028 | total time = 2779.37 ms / 351 tokens 10.45.803.564 I slot print_timing: id 0 | task 43028 | graphs reused = 42326 10.45.803.564 I slot print_timing: id 0 | task 43028 | graph reallocs = 0 / 0 (same size) / (changed size) 10.45.803.585 I slot release: id 0 | task 43028 | stop processing: n_tokens = 350, truncated = 0 10.45.807.491 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.132 (> 0.100 thold), f_keep = 0.060 10.45.808.986 I slot launch_slot_: id 0 | task 43216 | processing task, is_child = 0 10.49.149.152 I slot print_timing: id 0 | task 43216 | n_gen = 230, tg = 76.04 t/s, tg_3s = 76.37 t/s 10.49.427.638 I slot print_timing: id 0 | task 43216 | prompt eval time = 328.63 ms / 159 tokens ( 2.07 ms per token, 483.82 tokens per second) 10.49.427.643 I slot print_timing: id 0 | task 43216 | eval time = 3290.01 ms / 251 tokens ( 13.16 ms per token, 75.99 tokens per second) 10.49.427.644 I slot print_timing: id 0 | task 43216 | total time = 3618.64 ms / 410 tokens 10.49.427.644 I slot print_timing: id 0 | task 43216 | graphs reused = 42574 10.49.427.645 I slot print_timing: id 0 | task 43216 | graph reallocs = 0 / 0 (same size) / (changed size) 10.49.427.665 I slot release: id 0 | task 43216 | stop processing: n_tokens = 409, truncated = 0 10.49.430.770 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.118 (> 0.100 thold), f_keep = 0.051 10.49.431.843 I slot launch_slot_: id 0 | task 43469 | processing task, is_child = 0 10.51.966.495 I slot print_timing: id 0 | task 43469 | prompt eval time = 349.41 ms / 178 tokens ( 1.96 ms per token, 509.43 tokens per second) 10.51.966.501 I slot print_timing: id 0 | task 43469 | eval time = 2185.23 ms / 167 tokens ( 13.16 ms per token, 75.96 tokens per second) 10.51.966.502 I slot print_timing: id 0 | task 43469 | total time = 2534.64 ms / 345 tokens 10.51.966.503 I slot print_timing: id 0 | task 43469 | graphs reused = 42738 10.51.966.503 I slot print_timing: id 0 | task 43469 | graph reallocs = 0 / 0 (same size) / (changed size) 10.51.966.528 I slot release: id 0 | task 43469 | stop processing: n_tokens = 344, truncated = 0 10.51.969.812 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.112 (> 0.100 thold), f_keep = 0.061 10.51.970.745 I slot launch_slot_: id 0 | task 43638 | processing task, is_child = 0 10.55.329.860 I slot print_timing: id 0 | task 43638 | n_gen = 229, tg = 75.94 t/s, tg_3s = 76.27 t/s 10.58.335.330 I slot print_timing: id 0 | task 43638 | n_gen = 457, tg = 75.90 t/s, tg_3s = 75.86 t/s 11.01.346.497 I slot print_timing: id 0 | task 43638 | n_gen = 685, tg = 75.84 t/s, tg_3s = 75.72 t/s 11.04.353.541 I slot print_timing: id 0 | task 43638 | n_gen = 912, tg = 75.75 t/s, tg_3s = 75.49 t/s 11.05.838.462 I slot print_timing: id 0 | task 43638 | prompt eval time = 356.58 ms / 188 tokens ( 1.90 ms per token, 527.23 tokens per second) 11.05.838.467 I slot print_timing: id 0 | task 43638 | eval time = 13511.12 ms / 1024 tokens ( 13.21 ms per token, 75.72 tokens per second) 11.05.838.469 I slot print_timing: id 0 | task 43638 | total time = 13867.70 ms / 1212 tokens 11.05.838.469 I slot print_timing: id 0 | task 43638 | graphs reused = 43756 11.05.838.470 I slot print_timing: id 0 | task 43638 | graph reallocs = 0 / 0 (same size) / (changed size) 11.05.838.492 I slot release: id 0 | task 43638 | stop processing: n_tokens = 1211, truncated = 0 11.05.841.847 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.128 (> 0.100 thold), f_keep = 0.017 11.05.844.467 I slot launch_slot_: id 0 | task 44664 | processing task, is_child = 0 11.09.175.597 I slot print_timing: id 0 | task 44664 | n_gen = 229, tg = 75.97 t/s, tg_3s = 76.30 t/s 11.11.395.459 I slot print_timing: id 0 | task 44664 | prompt eval time = 329.90 ms / 164 tokens ( 2.01 ms per token, 497.12 tokens per second) 11.11.395.465 I slot print_timing: id 0 | task 44664 | eval time = 5221.08 ms / 397 tokens ( 13.18 ms per token, 75.85 tokens per second) 11.11.395.465 I slot print_timing: id 0 | task 44664 | total time = 5550.98 ms / 561 tokens 11.11.395.466 I slot print_timing: id 0 | task 44664 | graphs reused = 44149 11.11.395.466 I slot print_timing: id 0 | task 44664 | graph reallocs = 0 / 0 (same size) / (changed size) 11.11.395.492 I slot release: id 0 | task 44664 | stop processing: n_tokens = 560, truncated = 0 11.11.398.698 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.116 (> 0.100 thold), f_keep = 0.038 11.11.399.980 I slot launch_slot_: id 0 | task 45063 | processing task, is_child = 0 11.14.758.789 I slot print_timing: id 0 | task 45063 | n_gen = 229, tg = 75.82 t/s, tg_3s = 76.15 t/s 11.17.768.047 I slot print_timing: id 0 | task 45063 | n_gen = 457, tg = 75.79 t/s, tg_3s = 75.77 t/s 11.20.768.624 I slot print_timing: id 0 | task 45063 | n_gen = 684, tg = 75.75 t/s, tg_3s = 75.65 t/s 11.20.992.366 I slot print_timing: id 0 | task 45063 | prompt eval time = 351.72 ms / 181 tokens ( 1.94 ms per token, 514.61 tokens per second) 11.20.992.372 I slot print_timing: id 0 | task 45063 | eval time = 9240.66 ms / 701 tokens ( 13.20 ms per token, 75.75 tokens per second) 11.20.992.373 I slot print_timing: id 0 | task 45063 | total time = 9592.38 ms / 882 tokens 11.20.992.374 I slot print_timing: id 0 | task 45063 | graphs reused = 44845 11.20.992.374 I slot print_timing: id 0 | task 45063 | graph reallocs = 0 / 0 (same size) / (changed size) 11.20.992.397 I slot release: id 0 | task 45063 | stop processing: n_tokens = 881, truncated = 0 11.20.995.794 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.136 (> 0.100 thold), f_keep = 0.024 11.20.997.721 I slot launch_slot_: id 0 | task 45766 | processing task, is_child = 0 11.23.474.002 I slot print_timing: id 0 | task 45766 | prompt eval time = 324.32 ms / 154 tokens ( 2.11 ms per token, 474.83 tokens per second) 11.23.474.009 I slot print_timing: id 0 | task 45766 | eval time = 2151.95 ms / 164 tokens ( 13.20 ms per token, 75.75 tokens per second) 11.23.474.009 I slot print_timing: id 0 | task 45766 | total time = 2476.27 ms / 318 tokens 11.23.474.010 I slot print_timing: id 0 | task 45766 | graphs reused = 45006 11.23.474.010 I slot print_timing: id 0 | task 45766 | graph reallocs = 0 / 0 (same size) / (changed size) 11.23.474.030 I slot release: id 0 | task 45766 | stop processing: n_tokens = 317, truncated = 0 11.23.477.251 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.066 11.23.477.681 I slot launch_slot_: id 0 | task 45932 | processing task, is_child = 0 11.24.971.765 I slot print_timing: id 0 | task 45932 | prompt eval time = 312.52 ms / 135 tokens ( 2.31 ms per token, 431.97 tokens per second) 11.24.971.771 I slot print_timing: id 0 | task 45932 | eval time = 1181.56 ms / 91 tokens ( 13.13 ms per token, 76.17 tokens per second) 11.24.971.772 I slot print_timing: id 0 | task 45932 | total time = 1494.08 ms / 226 tokens 11.24.971.773 I slot print_timing: id 0 | task 45932 | graphs reused = 45095 11.24.971.773 I slot print_timing: id 0 | task 45932 | graph reallocs = 0 / 0 (same size) / (changed size) 11.24.971.792 I slot release: id 0 | task 45932 | stop processing: n_tokens = 225, truncated = 0 11.24.974.987 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.117 (> 0.100 thold), f_keep = 0.093 11.24.975.662 I slot launch_slot_: id 0 | task 46025 | processing task, is_child = 0 11.28.324.432 I slot print_timing: id 0 | task 46025 | n_gen = 229, tg = 75.98 t/s, tg_3s = 76.31 t/s 11.30.499.282 I slot print_timing: id 0 | task 46025 | prompt eval time = 347.78 ms / 179 tokens ( 1.94 ms per token, 514.70 tokens per second) 11.30.499.288 I slot print_timing: id 0 | task 46025 | eval time = 5175.84 ms / 394 tokens ( 13.17 ms per token, 75.93 tokens per second) 11.30.499.288 I slot print_timing: id 0 | task 46025 | total time = 5523.61 ms / 573 tokens 11.30.499.289 I slot print_timing: id 0 | task 46025 | graphs reused = 45485 11.30.499.289 I slot print_timing: id 0 | task 46025 | graph reallocs = 0 / 0 (same size) / (changed size) 11.30.499.311 I slot release: id 0 | task 46025 | stop processing: n_tokens = 572, truncated = 0 11.30.502.593 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.119 (> 0.100 thold), f_keep = 0.044 11.30.503.888 I slot launch_slot_: id 0 | task 46421 | processing task, is_child = 0 11.33.885.240 I slot print_timing: id 0 | task 46421 | n_gen = 229, tg = 75.89 t/s, tg_3s = 76.22 t/s 11.36.898.290 I slot print_timing: id 0 | task 46421 | n_gen = 457, tg = 75.78 t/s, tg_3s = 75.67 t/s 11.37.557.948 I slot print_timing: id 0 | task 46421 | prompt eval time = 376.84 ms / 210 tokens ( 1.79 ms per token, 557.27 tokens per second) 11.37.557.954 I slot print_timing: id 0 | task 46421 | eval time = 6677.22 ms / 507 tokens ( 13.20 ms per token, 75.78 tokens per second) 11.37.557.955 I slot print_timing: id 0 | task 46421 | total time = 7054.05 ms / 717 tokens 11.37.557.955 I slot print_timing: id 0 | task 46421 | graphs reused = 45988 11.37.557.956 I slot print_timing: id 0 | task 46421 | graph reallocs = 0 / 0 (same size) / (changed size) 11.37.557.978 I slot release: id 0 | task 46421 | stop processing: n_tokens = 716, truncated = 0 11.37.561.060 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 11.37.562.585 I slot launch_slot_: id 0 | task 46930 | processing task, is_child = 0 11.40.462.113 I slot print_timing: id 0 | task 46930 | prompt eval time = 301.87 ms / 127 tokens ( 2.38 ms per token, 420.71 tokens per second) 11.40.462.119 I slot print_timing: id 0 | task 46930 | eval time = 2597.65 ms / 198 tokens ( 13.19 ms per token, 75.84 tokens per second) 11.40.462.119 I slot print_timing: id 0 | task 46930 | total time = 2899.52 ms / 325 tokens 11.40.462.120 I slot print_timing: id 0 | task 46930 | graphs reused = 46183 11.40.462.121 I slot print_timing: id 0 | task 46930 | graph reallocs = 0 / 0 (same size) / (changed size) 11.40.462.142 I slot release: id 0 | task 46930 | stop processing: n_tokens = 324, truncated = 0 11.40.465.300 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.152 (> 0.100 thold), f_keep = 0.065 11.40.466.183 I slot launch_slot_: id 0 | task 47130 | processing task, is_child = 0 11.43.784.548 I slot print_timing: id 0 | task 47130 | n_gen = 229, tg = 75.96 t/s, tg_3s = 76.30 t/s 11.44.389.193 I slot print_timing: id 0 | task 47130 | prompt eval time = 316.85 ms / 138 tokens ( 2.30 ms per token, 435.53 tokens per second) 11.44.389.198 I slot print_timing: id 0 | task 47130 | eval time = 3606.15 ms / 275 tokens ( 13.16 ms per token, 75.98 tokens per second) 11.44.389.199 I slot print_timing: id 0 | task 47130 | total time = 3923.00 ms / 413 tokens 11.44.389.200 I slot print_timing: id 0 | task 47130 | graphs reused = 46455 11.44.389.200 I slot print_timing: id 0 | task 47130 | graph reallocs = 0 / 0 (same size) / (changed size) 11.44.389.220 I slot release: id 0 | task 47130 | stop processing: n_tokens = 412, truncated = 0 11.44.392.431 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.151 (> 0.100 thold), f_keep = 0.051 11.44.393.491 I slot launch_slot_: id 0 | task 47407 | processing task, is_child = 0 11.47.712.618 I slot print_timing: id 0 | task 47407 | n_gen = 229, tg = 75.89 t/s, tg_3s = 76.22 t/s 11.48.937.364 I slot print_timing: id 0 | task 47407 | prompt eval time = 314.75 ms / 139 tokens ( 2.26 ms per token, 441.61 tokens per second) 11.48.937.370 I slot print_timing: id 0 | task 47407 | eval time = 4229.11 ms / 322 tokens ( 13.17 ms per token, 75.90 tokens per second) 11.48.937.370 I slot print_timing: id 0 | task 47407 | total time = 4543.87 ms / 461 tokens 11.48.937.371 I slot print_timing: id 0 | task 47407 | graphs reused = 46774 11.48.937.371 I slot print_timing: id 0 | task 47407 | graph reallocs = 0 / 0 (same size) / (changed size) 11.48.937.389 I slot release: id 0 | task 47407 | stop processing: n_tokens = 460, truncated = 0 11.48.940.448 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.134 (> 0.100 thold), f_keep = 0.046 11.48.941.553 I slot launch_slot_: id 0 | task 47731 | processing task, is_child = 0 11.52.272.211 I slot print_timing: id 0 | task 47731 | n_gen = 229, tg = 75.87 t/s, tg_3s = 76.20 t/s 11.54.724.113 I slot print_timing: id 0 | task 47731 | prompt eval time = 325.54 ms / 157 tokens ( 2.07 ms per token, 482.28 tokens per second) 11.54.724.118 I slot print_timing: id 0 | task 47731 | eval time = 5457.01 ms / 415 tokens ( 13.18 ms per token, 75.87 tokens per second) 11.54.724.118 I slot print_timing: id 0 | task 47731 | total time = 5782.55 ms / 572 tokens 11.54.724.119 I slot print_timing: id 0 | task 47731 | graphs reused = 47185 11.54.724.119 I slot print_timing: id 0 | task 47731 | graph reallocs = 0 / 0 (same size) / (changed size) 11.54.724.140 I slot release: id 0 | task 47731 | stop processing: n_tokens = 571, truncated = 0 11.54.727.543 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.129 (> 0.100 thold), f_keep = 0.037 11.54.728.961 I slot launch_slot_: id 0 | task 48148 | processing task, is_child = 0 11.58.063.912 I slot print_timing: id 0 | task 48148 | n_gen = 229, tg = 75.95 t/s, tg_3s = 76.28 t/s 12.00.361.572 I slot print_timing: id 0 | task 48148 | prompt eval time = 332.94 ms / 163 tokens ( 2.04 ms per token, 489.57 tokens per second) 12.00.361.577 I slot print_timing: id 0 | task 48148 | eval time = 5299.66 ms / 403 tokens ( 13.18 ms per token, 75.85 tokens per second) 12.00.361.578 I slot print_timing: id 0 | task 48148 | total time = 5632.60 ms / 566 tokens 12.00.361.578 I slot print_timing: id 0 | task 48148 | graphs reused = 47584 12.00.361.579 I slot print_timing: id 0 | task 48148 | graph reallocs = 0 / 0 (same size) / (changed size) 12.00.361.602 I slot release: id 0 | task 48148 | stop processing: n_tokens = 565, truncated = 0 12.00.365.131 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.134 (> 0.100 thold), f_keep = 0.037 12.00.366.780 I slot launch_slot_: id 0 | task 48553 | processing task, is_child = 0 12.03.706.373 I slot print_timing: id 0 | task 48553 | n_gen = 230, tg = 76.02 t/s, tg_3s = 76.36 t/s 12.04.062.168 I slot print_timing: id 0 | task 48553 | prompt eval time = 327.39 ms / 157 tokens ( 2.09 ms per token, 479.55 tokens per second) 12.04.062.174 I slot print_timing: id 0 | task 48553 | eval time = 3367.99 ms / 257 tokens ( 13.16 ms per token, 76.01 tokens per second) 12.04.062.175 I slot print_timing: id 0 | task 48553 | total time = 3695.38 ms / 414 tokens 12.04.062.176 I slot print_timing: id 0 | task 48553 | graphs reused = 47838 12.04.062.176 I slot print_timing: id 0 | task 48553 | graph reallocs = 0 / 0 (same size) / (changed size) 12.04.062.196 I slot release: id 0 | task 48553 | stop processing: n_tokens = 413, truncated = 0 12.04.065.359 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.134 (> 0.100 thold), f_keep = 0.051 12.04.066.450 I slot launch_slot_: id 0 | task 48812 | processing task, is_child = 0 12.07.404.512 I slot print_timing: id 0 | task 48812 | n_gen = 230, tg = 76.04 t/s, tg_3s = 76.37 t/s 12.10.412.528 I slot print_timing: id 0 | task 48812 | n_gen = 458, tg = 75.92 t/s, tg_3s = 75.80 t/s 12.13.424.250 I slot print_timing: id 0 | task 48812 | n_gen = 686, tg = 75.85 t/s, tg_3s = 75.70 t/s 12.13.913.141 I slot print_timing: id 0 | task 48812 | prompt eval time = 326.39 ms / 157 tokens ( 2.08 ms per token, 481.02 tokens per second) 12.13.913.146 I slot print_timing: id 0 | task 48812 | eval time = 9520.29 ms / 723 tokens ( 13.19 ms per token, 75.84 tokens per second) 12.13.913.147 I slot print_timing: id 0 | task 48812 | total time = 9846.68 ms / 880 tokens 12.13.913.148 I slot print_timing: id 0 | task 48812 | graphs reused = 48556 12.13.913.148 I slot print_timing: id 0 | task 48812 | graph reallocs = 0 / 0 (same size) / (changed size) 12.13.913.172 I slot release: id 0 | task 48812 | stop processing: n_tokens = 879, truncated = 0 12.13.916.553 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.134 (> 0.100 thold), f_keep = 0.024 12.13.918.530 I slot launch_slot_: id 0 | task 49537 | processing task, is_child = 0 12.17.248.076 I slot print_timing: id 0 | task 49537 | n_gen = 229, tg = 75.98 t/s, tg_3s = 76.32 t/s 12.18.500.458 I slot print_timing: id 0 | task 49537 | prompt eval time = 328.93 ms / 157 tokens ( 2.10 ms per token, 477.30 tokens per second) 12.18.500.464 I slot print_timing: id 0 | task 49537 | eval time = 4252.99 ms / 324 tokens ( 13.17 ms per token, 75.95 tokens per second) 12.18.500.465 I slot print_timing: id 0 | task 49537 | total time = 4581.92 ms / 481 tokens 12.18.500.465 I slot print_timing: id 0 | task 49537 | graphs reused = 48877 12.18.500.466 I slot print_timing: id 0 | task 49537 | graph reallocs = 0 / 0 (same size) / (changed size) 12.18.500.486 I slot release: id 0 | task 49537 | stop processing: n_tokens = 480, truncated = 0 12.18.503.686 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.122 (> 0.100 thold), f_keep = 0.044 12.18.504.834 I slot launch_slot_: id 0 | task 49863 | processing task, is_child = 0 12.19.918.457 I slot print_timing: id 0 | task 49863 | prompt eval time = 346.65 ms / 172 tokens ( 2.02 ms per token, 496.17 tokens per second) 12.19.918.460 I slot print_timing: id 0 | task 49863 | eval time = 1066.96 ms / 82 tokens ( 13.17 ms per token, 75.92 tokens per second) 12.19.918.460 I slot print_timing: id 0 | task 49863 | total time = 1413.61 ms / 254 tokens 12.19.918.461 I slot print_timing: id 0 | task 49863 | graphs reused = 48957 12.19.918.462 I slot print_timing: id 0 | task 49863 | graph reallocs = 0 / 0 (same size) / (changed size) 12.19.918.482 I slot release: id 0 | task 49863 | stop processing: n_tokens = 253, truncated = 0 12.19.922.118 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.135 (> 0.100 thold), f_keep = 0.087 12.19.922.905 I slot launch_slot_: id 0 | task 49947 | processing task, is_child = 0 12.23.092.239 I slot print_timing: id 0 | task 49947 | prompt eval time = 328.30 ms / 163 tokens ( 2.01 ms per token, 496.50 tokens per second) 12.23.092.245 I slot print_timing: id 0 | task 49947 | eval time = 2841.03 ms / 217 tokens ( 13.15 ms per token, 76.03 tokens per second) 12.23.092.246 I slot print_timing: id 0 | task 49947 | total time = 3169.33 ms / 380 tokens 12.23.092.246 I slot print_timing: id 0 | task 49947 | graphs reused = 49171 12.23.092.247 I slot print_timing: id 0 | task 49947 | graph reallocs = 0 / 0 (same size) / (changed size) 12.23.092.267 I slot release: id 0 | task 49947 | stop processing: n_tokens = 379, truncated = 0 12.23.095.408 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.127 (> 0.100 thold), f_keep = 0.055 12.23.096.421 I slot launch_slot_: id 0 | task 50166 | processing task, is_child = 0 12.26.449.968 I slot print_timing: id 0 | task 50166 | n_gen = 230, tg = 76.04 t/s, tg_3s = 76.38 t/s 12.29.337.015 I slot print_timing: id 0 | task 50166 | prompt eval time = 342.14 ms / 165 tokens ( 2.07 ms per token, 482.26 tokens per second) 12.29.337.021 I slot print_timing: id 0 | task 50166 | eval time = 5898.44 ms / 449 tokens ( 13.17 ms per token, 75.95 tokens per second) 12.29.337.021 I slot print_timing: id 0 | task 50166 | total time = 6240.58 ms / 614 tokens 12.29.337.022 I slot print_timing: id 0 | task 50166 | graphs reused = 49616 12.29.337.022 I slot print_timing: id 0 | task 50166 | graph reallocs = 0 / 0 (same size) / (changed size) 12.29.337.043 I slot release: id 0 | task 50166 | stop processing: n_tokens = 613, truncated = 0 12.29.340.442 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.121 (> 0.100 thold), f_keep = 0.034 12.29.341.973 I slot launch_slot_: id 0 | task 50617 | processing task, is_child = 0 12.32.321.255 I slot print_timing: id 0 | task 50617 | prompt eval time = 346.83 ms / 173 tokens ( 2.00 ms per token, 498.81 tokens per second) 12.32.321.259 I slot print_timing: id 0 | task 50617 | eval time = 2632.45 ms / 201 tokens ( 13.16 ms per token, 75.97 tokens per second) 12.32.321.260 I slot print_timing: id 0 | task 50617 | total time = 2979.27 ms / 374 tokens 12.32.321.261 I slot print_timing: id 0 | task 50617 | graphs reused = 49814 12.32.321.261 I slot print_timing: id 0 | task 50617 | graph reallocs = 0 / 0 (same size) / (changed size) 12.32.321.285 I slot release: id 0 | task 50617 | stop processing: n_tokens = 373, truncated = 0 12.32.324.630 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.111 (> 0.100 thold), f_keep = 0.056 12.32.325.623 I slot launch_slot_: id 0 | task 50820 | processing task, is_child = 0 12.34.840.704 I slot print_timing: id 0 | task 50820 | prompt eval time = 357.48 ms / 190 tokens ( 1.88 ms per token, 531.50 tokens per second) 12.34.840.709 I slot print_timing: id 0 | task 50820 | eval time = 2157.59 ms / 165 tokens ( 13.16 ms per token, 76.01 tokens per second) 12.34.840.710 I slot print_timing: id 0 | task 50820 | total time = 2515.07 ms / 355 tokens 12.34.840.710 I slot print_timing: id 0 | task 50820 | graphs reused = 49976 12.34.840.711 I slot print_timing: id 0 | task 50820 | graph reallocs = 0 / 0 (same size) / (changed size) 12.34.840.734 I slot release: id 0 | task 50820 | stop processing: n_tokens = 354, truncated = 0 12.34.843.970 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 12.34.844.953 I slot launch_slot_: id 0 | task 50987 | processing task, is_child = 0 12.38.202.528 I slot print_timing: id 0 | task 50987 | n_gen = 230, tg = 76.05 t/s, tg_3s = 76.38 t/s 12.39.890.766 I slot print_timing: id 0 | task 50987 | prompt eval time = 346.20 ms / 173 tokens ( 2.00 ms per token, 499.71 tokens per second) 12.39.890.770 I slot print_timing: id 0 | task 50987 | eval time = 4699.61 ms / 358 tokens ( 13.16 ms per token, 75.96 tokens per second) 12.39.890.771 I slot print_timing: id 0 | task 50987 | total time = 5045.81 ms / 531 tokens 12.39.890.771 I slot print_timing: id 0 | task 50987 | graphs reused = 50330 12.39.890.772 I slot print_timing: id 0 | task 50987 | graph reallocs = 0 / 0 (same size) / (changed size) 12.39.890.795 I slot release: id 0 | task 50987 | stop processing: n_tokens = 530, truncated = 0 12.39.894.110 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.111 (> 0.100 thold), f_keep = 0.040 12.39.895.408 I slot launch_slot_: id 0 | task 51347 | processing task, is_child = 0 12.43.253.068 I slot print_timing: id 0 | task 51347 | n_gen = 229, tg = 75.91 t/s, tg_3s = 76.24 t/s 12.44.796.279 I slot print_timing: id 0 | task 51347 | prompt eval time = 353.91 ms / 190 tokens ( 1.86 ms per token, 536.87 tokens per second) 12.44.796.282 I slot print_timing: id 0 | task 51347 | eval time = 4546.95 ms / 346 tokens ( 13.18 ms per token, 75.87 tokens per second) 12.44.796.283 I slot print_timing: id 0 | task 51347 | total time = 4900.86 ms / 536 tokens 12.44.796.284 I slot print_timing: id 0 | task 51347 | graphs reused = 50672 12.44.796.284 I slot print_timing: id 0 | task 51347 | graph reallocs = 0 / 0 (same size) / (changed size) 12.44.796.307 I slot release: id 0 | task 51347 | stop processing: n_tokens = 535, truncated = 0 12.44.799.588 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.126 (> 0.100 thold), f_keep = 0.043 12.44.800.928 I slot launch_slot_: id 0 | task 51695 | processing task, is_child = 0 12.48.163.871 I slot print_timing: id 0 | task 51695 | n_gen = 230, tg = 76.02 t/s, tg_3s = 76.35 t/s 12.51.169.253 I slot print_timing: id 0 | task 51695 | n_gen = 458, tg = 75.94 t/s, tg_3s = 75.86 t/s 12.53.373.814 I slot print_timing: id 0 | task 51695 | prompt eval time = 350.60 ms / 183 tokens ( 1.92 ms per token, 521.97 tokens per second) 12.53.373.820 I slot print_timing: id 0 | task 51695 | eval time = 8222.28 ms / 625 tokens ( 13.18 ms per token, 75.89 tokens per second) 12.53.373.822 I slot print_timing: id 0 | task 51695 | total time = 8572.88 ms / 808 tokens 12.53.373.822 I slot print_timing: id 0 | task 51695 | graphs reused = 51292 12.53.373.823 I slot print_timing: id 0 | task 51695 | graph reallocs = 0 / 0 (same size) / (changed size) 12.53.373.843 I slot release: id 0 | task 51695 | stop processing: n_tokens = 807, truncated = 0 12.53.377.090 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 807, t_last = 344830069263 12.53.378.862 I slot launch_slot_: id 0 | task 52322 | processing task, is_child = 0 12.55.794.793 I slot print_timing: id 0 | task 52322 | prompt eval time = 384.75 ms / 222 tokens ( 1.73 ms per token, 576.99 tokens per second) 12.55.794.796 I slot print_timing: id 0 | task 52322 | eval time = 2031.17 ms / 155 tokens ( 13.19 ms per token, 75.82 tokens per second) 12.55.794.797 I slot print_timing: id 0 | task 52322 | total time = 2415.92 ms / 377 tokens 12.55.794.797 I slot print_timing: id 0 | task 52322 | graphs reused = 51444 12.55.794.798 I slot print_timing: id 0 | task 52322 | graph reallocs = 0 / 0 (same size) / (changed size) 12.55.794.825 I slot release: id 0 | task 52322 | stop processing: n_tokens = 376, truncated = 0 12.55.797.906 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.129 (> 0.100 thold), f_keep = 0.056 12.55.798.938 I slot launch_slot_: id 0 | task 52479 | processing task, is_child = 0 12.59.129.744 I slot print_timing: id 0 | task 52479 | n_gen = 229, tg = 75.93 t/s, tg_3s = 76.27 t/s 12.59.156.034 I slot print_timing: id 0 | task 52479 | prompt eval time = 328.13 ms / 163 tokens ( 2.01 ms per token, 496.75 tokens per second) 12.59.156.039 I slot print_timing: id 0 | task 52479 | eval time = 3028.96 ms / 231 tokens ( 13.17 ms per token, 75.93 tokens per second) 12.59.156.040 I slot print_timing: id 0 | task 52479 | total time = 3357.09 ms / 394 tokens 12.59.156.041 I slot print_timing: id 0 | task 52479 | graphs reused = 51672 12.59.156.041 I slot print_timing: id 0 | task 52479 | graph reallocs = 0 / 0 (same size) / (changed size) 12.59.156.061 I slot release: id 0 | task 52479 | stop processing: n_tokens = 393, truncated = 0 12.59.312.300 I srv operator(): operator(): cleaning up before exit...