$ /Users/minipro/quantdiff/work/llama-b11869/src/build/bin/llama-server -m /Users/minipro/quantdiff/models/campaign/dd45136a8b26/flint-UD-IQ1_M.gguf --host 127.0.0.1 --port 8089 -c 4096 -np 1 -ngl 999 -fa on --jinja --seed 1234 --no-webui -a quant 0.00.041.261 I srv llama_server: initializing ... 0.00.041.267 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.041.355 I srv init_listene: The UI is disabled 0.00.041.356 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.041.399 W srv server_setup: security: no API key is set and CORS allows all origins (see https://github.com/ggml-org/llama.cpp/pull/25655) 0.00.043.052 I srv load_model: loading model '/Users/minipro/quantdiff/models/campaign/dd45136a8b26/flint-UD-IQ1_M.gguf' 0.00.734.323 I cmn init: llama threadpool init, n_threads = 8 0.00.814.451 I srv load_model: initializing, n_slots = 1, n_ctx_slot = 4096, kv_unified = 'false' 0.00.822.233 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.00.822.241 I srv server_run_i: model loaded 0.00.822.243 I srv server_on_li: listening on http://127.0.0.1:8089 0.02.023.595 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.02.023.843 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.04.091.233 I slot print_timing: id 0 | task 0 | prompt eval time = 667.63 ms / 221 tokens ( 3.02 ms per token, 331.02 tokens per second) 0.04.091.236 I slot print_timing: id 0 | task 0 | eval time = 1399.74 ms / 76 tokens ( 18.66 ms per token, 53.58 tokens per second) 0.04.091.237 I slot print_timing: id 0 | task 0 | total time = 2067.37 ms / 297 tokens 0.04.091.238 I slot print_timing: id 0 | task 0 | graphs reused = 74 0.04.091.238 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.04.091.259 I slot release: id 0 | task 0 | stop processing: n_tokens = 296, truncated = 0 0.04.095.562 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.211 (> 0.100 thold), f_keep = 0.125 0.04.100.802 I slot launch_slot_: id 0 | task 79 | processing task, is_child = 0 0.05.680.101 I slot print_timing: id 0 | task 79 | prompt eval time = 543.08 ms / 175 tokens ( 3.10 ms per token, 322.24 tokens per second) 0.05.680.103 I slot print_timing: id 0 | task 79 | eval time = 1036.20 ms / 57 tokens ( 18.50 ms per token, 54.04 tokens per second) 0.05.680.104 I slot print_timing: id 0 | task 79 | total time = 1579.28 ms / 232 tokens 0.05.680.105 I slot print_timing: id 0 | task 79 | graphs reused = 129 0.05.680.105 I slot print_timing: id 0 | task 79 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.680.128 I slot release: id 0 | task 79 | stop processing: n_tokens = 231, truncated = 0 0.05.684.631 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.174 (> 0.100 thold), f_keep = 0.160 0.05.689.076 I slot launch_slot_: id 0 | task 139 | processing task, is_child = 0 0.07.491.460 I slot print_timing: id 0 | task 139 | prompt eval time = 626.32 ms / 213 tokens ( 2.94 ms per token, 340.08 tokens per second) 0.07.491.463 I slot print_timing: id 0 | task 139 | eval time = 1176.05 ms / 64 tokens ( 18.67 ms per token, 53.57 tokens per second) 0.07.491.464 I slot print_timing: id 0 | task 139 | total time = 1802.37 ms / 277 tokens 0.07.491.465 I slot print_timing: id 0 | task 139 | graphs reused = 190 0.07.491.465 I slot print_timing: id 0 | task 139 | graph reallocs = 0 / 0 (same size) / (changed size) 0.07.491.486 I slot release: id 0 | task 139 | stop processing: n_tokens = 276, truncated = 0 0.07.496.304 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.150 (> 0.100 thold), f_keep = 0.134 0.07.501.494 I slot launch_slot_: id 0 | task 206 | processing task, is_child = 0 0.09.825.497 I slot print_timing: id 0 | task 206 | prompt eval time = 680.43 ms / 247 tokens ( 2.75 ms per token, 363.01 tokens per second) 0.09.825.502 I slot print_timing: id 0 | task 206 | eval time = 1643.57 ms / 89 tokens ( 18.68 ms per token, 53.54 tokens per second) 0.09.825.503 I slot print_timing: id 0 | task 206 | total time = 2323.99 ms / 336 tokens 0.09.825.504 I slot print_timing: id 0 | task 206 | graphs reused = 276 0.09.825.504 I slot print_timing: id 0 | task 206 | graph reallocs = 0 / 0 (same size) / (changed size) 0.09.825.528 I slot release: id 0 | task 206 | stop processing: n_tokens = 335, truncated = 0 0.09.830.321 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.212 (> 0.100 thold), f_keep = 0.149 0.09.836.305 I slot launch_slot_: id 0 | task 298 | processing task, is_child = 0 0.12.477.842 I slot print_timing: id 0 | task 298 | prompt eval time = 758.72 ms / 236 tokens ( 3.21 ms per token, 311.05 tokens per second) 0.12.477.845 I slot print_timing: id 0 | task 298 | eval time = 1882.81 ms / 102 tokens ( 18.64 ms per token, 53.64 tokens per second) 0.12.477.846 I slot print_timing: id 0 | task 298 | total time = 2641.53 ms / 338 tokens 0.12.477.847 I slot print_timing: id 0 | task 298 | graphs reused = 375 0.12.477.847 I slot print_timing: id 0 | task 298 | graph reallocs = 0 / 0 (same size) / (changed size) 0.12.477.867 I slot release: id 0 | task 298 | stop processing: n_tokens = 337, truncated = 0 0.12.482.475 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.164 (> 0.100 thold), f_keep = 0.110 0.12.487.307 I slot launch_slot_: id 0 | task 403 | processing task, is_child = 0 0.14.327.502 I slot print_timing: id 0 | task 403 | prompt eval time = 607.81 ms / 226 tokens ( 2.69 ms per token, 371.83 tokens per second) 0.14.327.508 I slot print_timing: id 0 | task 403 | eval time = 1232.37 ms / 67 tokens ( 18.67 ms per token, 53.56 tokens per second) 0.14.327.508 I slot print_timing: id 0 | task 403 | total time = 1840.18 ms / 293 tokens 0.14.327.509 I slot print_timing: id 0 | task 403 | graphs reused = 439 0.14.327.509 I slot print_timing: id 0 | task 403 | graph reallocs = 0 / 0 (same size) / (changed size) 0.14.327.530 I slot release: id 0 | task 403 | stop processing: n_tokens = 292, truncated = 0 0.14.332.453 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.137 (> 0.100 thold), f_keep = 0.127 0.14.337.757 I slot launch_slot_: id 0 | task 473 | processing task, is_child = 0 0.16.824.879 I slot print_timing: id 0 | task 473 | prompt eval time = 713.86 ms / 270 tokens ( 2.64 ms per token, 378.23 tokens per second) 0.16.824.885 I slot print_timing: id 0 | task 473 | eval time = 1773.25 ms / 96 tokens ( 18.67 ms per token, 53.57 tokens per second) 0.16.824.886 I slot print_timing: id 0 | task 473 | total time = 2487.11 ms / 366 tokens 0.16.824.887 I slot print_timing: id 0 | task 473 | graphs reused = 533 0.16.824.887 I slot print_timing: id 0 | task 473 | graph reallocs = 0 / 0 (same size) / (changed size) 0.16.824.909 I slot release: id 0 | task 473 | stop processing: n_tokens = 365, truncated = 0 0.16.829.932 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.116 (> 0.100 thold), f_keep = 0.101 0.16.836.304 I slot launch_slot_: id 0 | task 572 | processing task, is_child = 0 0.20.193.062 I slot print_timing: id 0 | task 572 | prompt eval time = 775.84 ms / 318 tokens ( 2.44 ms per token, 409.88 tokens per second) 0.20.193.065 I slot print_timing: id 0 | task 572 | eval time = 2580.91 ms / 139 tokens ( 18.70 ms per token, 53.47 tokens per second) 0.20.193.066 I slot print_timing: id 0 | task 572 | total time = 3356.75 ms / 457 tokens 0.20.193.066 I slot print_timing: id 0 | task 572 | graphs reused = 670 0.20.193.067 I slot print_timing: id 0 | task 572 | graph reallocs = 0 / 0 (same size) / (changed size) 0.20.193.090 I slot release: id 0 | task 572 | stop processing: n_tokens = 456, truncated = 0 0.20.197.648 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.081 0.20.205.422 I slot launch_slot_: id 0 | task 714 | processing task, is_child = 0 0.22.105.670 I slot print_timing: id 0 | task 714 | prompt eval time = 615.69 ms / 197 tokens ( 3.13 ms per token, 319.97 tokens per second) 0.22.105.675 I slot print_timing: id 0 | task 714 | eval time = 1284.55 ms / 70 tokens ( 18.62 ms per token, 53.72 tokens per second) 0.22.105.677 I slot print_timing: id 0 | task 714 | total time = 1900.24 ms / 267 tokens 0.22.105.677 I slot print_timing: id 0 | task 714 | graphs reused = 737 0.22.105.678 I slot print_timing: id 0 | task 714 | graph reallocs = 0 / 0 (same size) / (changed size) 0.22.105.701 I slot release: id 0 | task 714 | stop processing: n_tokens = 266, truncated = 0 0.22.110.788 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.139 0.22.113.917 I slot launch_slot_: id 0 | task 787 | processing task, is_child = 0 0.24.385.088 I slot print_timing: id 0 | task 787 | prompt eval time = 633.34 ms / 216 tokens ( 2.93 ms per token, 341.05 tokens per second) 0.24.385.092 I slot print_timing: id 0 | task 787 | eval time = 1637.82 ms / 89 tokens ( 18.61 ms per token, 53.73 tokens per second) 0.24.385.093 I slot print_timing: id 0 | task 787 | total time = 2271.16 ms / 305 tokens 0.24.385.093 I slot print_timing: id 0 | task 787 | graphs reused = 823 0.24.385.094 I slot print_timing: id 0 | task 787 | graph reallocs = 0 / 0 (same size) / (changed size) 0.24.385.113 I slot release: id 0 | task 787 | stop processing: n_tokens = 304, truncated = 0 0.24.389.780 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.165 (> 0.100 thold), f_keep = 0.122 0.24.393.404 I slot launch_slot_: id 0 | task 879 | processing task, is_child = 0 0.27.177.668 I slot print_timing: id 0 | task 879 | prompt eval time = 601.48 ms / 224 tokens ( 2.69 ms per token, 372.42 tokens per second) 0.27.177.674 I slot print_timing: id 0 | task 879 | eval time = 2182.78 ms / 118 tokens ( 18.66 ms per token, 53.60 tokens per second) 0.27.177.676 I slot print_timing: id 0 | task 879 | total time = 2784.26 ms / 342 tokens 0.27.177.676 I slot print_timing: id 0 | task 879 | graphs reused = 938 0.27.177.677 I slot print_timing: id 0 | task 879 | graph reallocs = 0 / 0 (same size) / (changed size) 0.27.177.697 I slot release: id 0 | task 879 | stop processing: n_tokens = 341, truncated = 0 0.27.182.592 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.143 (> 0.100 thold), f_keep = 0.109 0.27.188.378 I slot launch_slot_: id 0 | task 1000 | processing task, is_child = 0 0.29.791.211 I slot print_timing: id 0 | task 1000 | prompt eval time = 702.13 ms / 259 tokens ( 2.71 ms per token, 368.88 tokens per second) 0.29.791.218 I slot print_timing: id 0 | task 1000 | eval time = 1900.70 ms / 103 tokens ( 18.63 ms per token, 53.66 tokens per second) 0.29.791.218 I slot print_timing: id 0 | task 1000 | total time = 2602.83 ms / 362 tokens 0.29.791.219 I slot print_timing: id 0 | task 1000 | graphs reused = 1039 0.29.791.220 I slot print_timing: id 0 | task 1000 | graph reallocs = 0 / 0 (same size) / (changed size) 0.29.791.244 I slot release: id 0 | task 1000 | stop processing: n_tokens = 361, truncated = 0 0.29.795.713 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.165 (> 0.100 thold), f_keep = 0.102 0.29.801.975 I slot launch_slot_: id 0 | task 1106 | processing task, is_child = 0 0.32.353.790 I slot print_timing: id 0 | task 1106 | prompt eval time = 669.81 ms / 224 tokens ( 2.99 ms per token, 334.42 tokens per second) 0.32.353.795 I slot print_timing: id 0 | task 1106 | eval time = 1881.99 ms / 102 tokens ( 18.63 ms per token, 53.67 tokens per second) 0.32.353.796 I slot print_timing: id 0 | task 1106 | total time = 2551.80 ms / 326 tokens 0.32.353.796 I slot print_timing: id 0 | task 1106 | graphs reused = 1138 0.32.353.797 I slot print_timing: id 0 | task 1106 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.353.817 I slot release: id 0 | task 1106 | stop processing: n_tokens = 325, truncated = 0 0.32.358.577 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.163 (> 0.100 thold), f_keep = 0.114 0.32.362.571 I slot launch_slot_: id 0 | task 1211 | processing task, is_child = 0 0.34.717.389 I slot print_timing: id 0 | task 1211 | prompt eval time = 622.61 ms / 227 tokens ( 2.74 ms per token, 364.59 tokens per second) 0.34.717.395 I slot print_timing: id 0 | task 1211 | eval time = 1732.19 ms / 94 tokens ( 18.63 ms per token, 53.69 tokens per second) 0.34.717.396 I slot print_timing: id 0 | task 1211 | total time = 2354.81 ms / 321 tokens 0.34.717.397 I slot print_timing: id 0 | task 1211 | graphs reused = 1229 0.34.717.397 I slot print_timing: id 0 | task 1211 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.717.422 I slot release: id 0 | task 1211 | stop processing: n_tokens = 320, truncated = 0 0.34.722.088 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.167 (> 0.100 thold), f_keep = 0.116 0.34.727.971 I slot launch_slot_: id 0 | task 1308 | processing task, is_child = 0 0.36.824.888 I slot print_timing: id 0 | task 1308 | prompt eval time = 624.10 ms / 222 tokens ( 2.81 ms per token, 355.71 tokens per second) 0.36.824.894 I slot print_timing: id 0 | task 1308 | eval time = 1472.80 ms / 80 tokens ( 18.64 ms per token, 53.64 tokens per second) 0.36.824.895 I slot print_timing: id 0 | task 1308 | total time = 2096.90 ms / 302 tokens 0.36.824.896 I slot print_timing: id 0 | task 1308 | graphs reused = 1306 0.36.824.896 I slot print_timing: id 0 | task 1308 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.824.916 I slot release: id 0 | task 1308 | stop processing: n_tokens = 301, truncated = 0 0.36.829.437 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.123 0.36.835.385 I slot launch_slot_: id 0 | task 1391 | processing task, is_child = 0 0.39.161.888 I slot print_timing: id 0 | task 1391 | prompt eval time = 616.46 ms / 203 tokens ( 3.04 ms per token, 329.30 tokens per second) 0.39.161.893 I slot print_timing: id 0 | task 1391 | eval time = 1710.04 ms / 93 tokens ( 18.59 ms per token, 53.80 tokens per second) 0.39.161.894 I slot print_timing: id 0 | task 1391 | total time = 2326.49 ms / 296 tokens 0.39.161.895 I slot print_timing: id 0 | task 1391 | graphs reused = 1396 0.39.161.895 I slot print_timing: id 0 | task 1391 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.161.914 I slot release: id 0 | task 1391 | stop processing: n_tokens = 295, truncated = 0 0.39.166.372 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.166 (> 0.100 thold), f_keep = 0.125 0.39.171.086 I slot launch_slot_: id 0 | task 1487 | processing task, is_child = 0 0.41.080.408 I slot print_timing: id 0 | task 1487 | prompt eval time = 658.98 ms / 223 tokens ( 2.96 ms per token, 338.40 tokens per second) 0.41.080.414 I slot print_timing: id 0 | task 1487 | eval time = 1250.33 ms / 68 tokens ( 18.66 ms per token, 53.59 tokens per second) 0.41.080.414 I slot print_timing: id 0 | task 1487 | total time = 1909.31 ms / 291 tokens 0.41.080.415 I slot print_timing: id 0 | task 1487 | graphs reused = 1461 0.41.080.416 I slot print_timing: id 0 | task 1487 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.080.435 I slot release: id 0 | task 1487 | stop processing: n_tokens = 290, truncated = 0 0.41.084.910 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.180 (> 0.100 thold), f_keep = 0.128 0.41.090.893 I slot launch_slot_: id 0 | task 1558 | processing task, is_child = 0 0.42.891.145 I slot print_timing: id 0 | task 1558 | prompt eval time = 589.78 ms / 206 tokens ( 2.86 ms per token, 349.28 tokens per second) 0.42.891.149 I slot print_timing: id 0 | task 1558 | eval time = 1210.46 ms / 66 tokens ( 18.62 ms per token, 53.70 tokens per second) 0.42.891.149 I slot print_timing: id 0 | task 1558 | total time = 1800.24 ms / 272 tokens 0.42.891.150 I slot print_timing: id 0 | task 1558 | graphs reused = 1524 0.42.891.151 I slot print_timing: id 0 | task 1558 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.891.177 I slot release: id 0 | task 1558 | stop processing: n_tokens = 271, truncated = 0 0.42.895.953 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.183 (> 0.100 thold), f_keep = 0.137 0.42.901.403 I slot launch_slot_: id 0 | task 1627 | processing task, is_child = 0 0.44.618.695 I slot print_timing: id 0 | task 1627 | prompt eval time = 583.51 ms / 202 tokens ( 2.89 ms per token, 346.18 tokens per second) 0.44.618.701 I slot print_timing: id 0 | task 1627 | eval time = 1133.77 ms / 62 tokens ( 18.59 ms per token, 53.80 tokens per second) 0.44.618.702 I slot print_timing: id 0 | task 1627 | total time = 1717.28 ms / 264 tokens 0.44.618.702 I slot print_timing: id 0 | task 1627 | graphs reused = 1583 0.44.618.703 I slot print_timing: id 0 | task 1627 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.618.722 I slot release: id 0 | task 1627 | stop processing: n_tokens = 263, truncated = 0 0.44.623.109 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.141 0.44.627.978 I slot launch_slot_: id 0 | task 1692 | processing task, is_child = 0 0.46.695.083 I slot print_timing: id 0 | task 1692 | prompt eval time = 684.54 ms / 237 tokens ( 2.89 ms per token, 346.22 tokens per second) 0.46.695.088 I slot print_timing: id 0 | task 1692 | eval time = 1382.55 ms / 75 tokens ( 18.68 ms per token, 53.52 tokens per second) 0.46.695.090 I slot print_timing: id 0 | task 1692 | total time = 2067.10 ms / 312 tokens 0.46.695.091 I slot print_timing: id 0 | task 1692 | graphs reused = 1655 0.46.695.091 I slot print_timing: id 0 | task 1692 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.695.115 I slot release: id 0 | task 1692 | stop processing: n_tokens = 311, truncated = 0 0.46.699.720 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.119 0.46.706.360 I slot launch_slot_: id 0 | task 1770 | processing task, is_child = 0 0.49.747.196 I slot print_timing: id 0 | task 1770 | prompt eval time = 622.86 ms / 208 tokens ( 2.99 ms per token, 333.94 tokens per second) 0.49.747.203 I slot print_timing: id 0 | task 1770 | eval time = 2417.97 ms / 130 tokens ( 18.74 ms per token, 53.35 tokens per second) 0.49.747.204 I slot print_timing: id 0 | task 1770 | total time = 3040.83 ms / 338 tokens 0.49.747.205 I slot print_timing: id 0 | task 1770 | graphs reused = 1782 0.49.747.205 I slot print_timing: id 0 | task 1770 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.747.231 I slot release: id 0 | task 1770 | stop processing: n_tokens = 337, truncated = 0 0.49.752.220 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.142 (> 0.100 thold), f_keep = 0.110 0.49.757.655 I slot launch_slot_: id 0 | task 1903 | processing task, is_child = 0 0.52.069.712 I slot print_timing: id 0 | task 1903 | prompt eval time = 704.45 ms / 261 tokens ( 2.70 ms per token, 370.50 tokens per second) 0.52.069.719 I slot print_timing: id 0 | task 1903 | eval time = 1607.60 ms / 87 tokens ( 18.69 ms per token, 53.50 tokens per second) 0.52.069.720 I slot print_timing: id 0 | task 1903 | total time = 2312.05 ms / 348 tokens 0.52.069.721 I slot print_timing: id 0 | task 1903 | graphs reused = 1867 0.52.069.721 I slot print_timing: id 0 | task 1903 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.069.745 I slot release: id 0 | task 1903 | stop processing: n_tokens = 347, truncated = 0 0.52.074.406 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.155 (> 0.100 thold), f_keep = 0.107 0.52.081.811 I slot launch_slot_: id 0 | task 1993 | processing task, is_child = 0 0.55.313.121 I slot print_timing: id 0 | task 1993 | prompt eval time = 641.66 ms / 238 tokens ( 2.70 ms per token, 370.91 tokens per second) 0.55.313.127 I slot print_timing: id 0 | task 1993 | eval time = 2589.64 ms / 140 tokens ( 18.63 ms per token, 53.68 tokens per second) 0.55.313.129 I slot print_timing: id 0 | task 1993 | total time = 3231.30 ms / 378 tokens 0.55.313.129 I slot print_timing: id 0 | task 1993 | graphs reused = 2004 0.55.313.130 I slot print_timing: id 0 | task 1993 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.313.151 I slot release: id 0 | task 1993 | stop processing: n_tokens = 377, truncated = 0 0.55.318.231 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.150 (> 0.100 thold), f_keep = 0.098 0.55.324.264 I slot launch_slot_: id 0 | task 2136 | processing task, is_child = 0 0.59.091.116 I slot print_timing: id 0 | task 2136 | n_gen = 162, tg = 53.50 t/s, tg_3s = 53.84 t/s 0.59.372.861 I slot print_timing: id 0 | task 2136 | prompt eval time = 757.75 ms / 247 tokens ( 3.07 ms per token, 325.97 tokens per second) 0.59.372.868 I slot print_timing: id 0 | task 2136 | eval time = 3290.84 ms / 177 tokens ( 18.70 ms per token, 53.48 tokens per second) 0.59.372.869 I slot print_timing: id 0 | task 2136 | total time = 4048.59 ms / 424 tokens 0.59.372.869 I slot print_timing: id 0 | task 2136 | graphs reused = 2178 0.59.372.870 I slot print_timing: id 0 | task 2136 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.372.891 I slot release: id 0 | task 2136 | stop processing: n_tokens = 423, truncated = 0 0.59.377.950 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.131 (> 0.100 thold), f_keep = 0.087 0.59.385.099 I slot launch_slot_: id 0 | task 2316 | processing task, is_child = 0 1.01.754.422 I slot print_timing: id 0 | task 2316 | prompt eval time = 787.85 ms / 282 tokens ( 2.79 ms per token, 357.93 tokens per second) 1.01.754.428 I slot print_timing: id 0 | task 2316 | eval time = 1581.46 ms / 85 tokens ( 18.83 ms per token, 53.12 tokens per second) 1.01.754.429 I slot print_timing: id 0 | task 2316 | total time = 2369.31 ms / 367 tokens 1.01.754.430 I slot print_timing: id 0 | task 2316 | graphs reused = 2261 1.01.754.430 I slot print_timing: id 0 | task 2316 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.754.463 I slot release: id 0 | task 2316 | stop processing: n_tokens = 366, truncated = 0 1.01.759.221 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.104 1.01.767.608 I slot launch_slot_: id 0 | task 2404 | processing task, is_child = 0 1.03.771.629 I slot print_timing: id 0 | task 2404 | prompt eval time = 696.43 ms / 243 tokens ( 2.87 ms per token, 348.92 tokens per second) 1.03.771.635 I slot print_timing: id 0 | task 2404 | eval time = 1307.59 ms / 71 tokens ( 18.68 ms per token, 53.53 tokens per second) 1.03.771.636 I slot print_timing: id 0 | task 2404 | total time = 2004.01 ms / 314 tokens 1.03.771.636 I slot print_timing: id 0 | task 2404 | graphs reused = 2329 1.03.771.637 I slot print_timing: id 0 | task 2404 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.771.657 I slot release: id 0 | task 2404 | stop processing: n_tokens = 313, truncated = 0 1.03.776.229 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.118 1.03.781.820 I slot launch_slot_: id 0 | task 2478 | processing task, is_child = 0 1.06.524.392 I slot print_timing: id 0 | task 2478 | prompt eval time = 584.13 ms / 203 tokens ( 2.88 ms per token, 347.52 tokens per second) 1.06.524.398 I slot print_timing: id 0 | task 2478 | eval time = 2158.43 ms / 117 tokens ( 18.61 ms per token, 53.74 tokens per second) 1.06.524.399 I slot print_timing: id 0 | task 2478 | total time = 2742.56 ms / 320 tokens 1.06.524.400 I slot print_timing: id 0 | task 2478 | graphs reused = 2443 1.06.524.400 I slot print_timing: id 0 | task 2478 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.524.420 I slot release: id 0 | task 2478 | stop processing: n_tokens = 319, truncated = 0 1.06.529.168 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.167 (> 0.100 thold), f_keep = 0.119 1.06.534.143 I slot launch_slot_: id 0 | task 2598 | processing task, is_child = 0 1.08.551.398 I slot print_timing: id 0 | task 2598 | prompt eval time = 634.07 ms / 228 tokens ( 2.78 ms per token, 359.58 tokens per second) 1.08.551.405 I slot print_timing: id 0 | task 2598 | eval time = 1383.18 ms / 75 tokens ( 18.69 ms per token, 53.50 tokens per second) 1.08.551.405 I slot print_timing: id 0 | task 2598 | total time = 2017.25 ms / 303 tokens 1.08.551.406 I slot print_timing: id 0 | task 2598 | graphs reused = 2515 1.08.551.407 I slot print_timing: id 0 | task 2598 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.551.427 I slot release: id 0 | task 2598 | stop processing: n_tokens = 302, truncated = 0 1.08.556.391 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.145 (> 0.100 thold), f_keep = 0.123 1.08.562.845 I slot launch_slot_: id 0 | task 2676 | processing task, is_child = 0 1.10.979.673 I slot print_timing: id 0 | task 2676 | prompt eval time = 758.97 ms / 256 tokens ( 2.96 ms per token, 337.30 tokens per second) 1.10.979.679 I slot print_timing: id 0 | task 2676 | eval time = 1657.85 ms / 90 tokens ( 18.63 ms per token, 53.68 tokens per second) 1.10.979.680 I slot print_timing: id 0 | task 2676 | total time = 2416.82 ms / 346 tokens 1.10.979.680 I slot print_timing: id 0 | task 2676 | graphs reused = 2603 1.10.979.681 I slot print_timing: id 0 | task 2676 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.979.703 I slot release: id 0 | task 2676 | stop processing: n_tokens = 345, truncated = 0 1.10.984.487 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.155 (> 0.100 thold), f_keep = 0.107 1.10.991.033 I slot launch_slot_: id 0 | task 2769 | processing task, is_child = 0 1.13.352.870 I slot print_timing: id 0 | task 2769 | prompt eval time = 642.91 ms / 238 tokens ( 2.70 ms per token, 370.19 tokens per second) 1.13.352.876 I slot print_timing: id 0 | task 2769 | eval time = 1718.92 ms / 93 tokens ( 18.68 ms per token, 53.52 tokens per second) 1.13.352.877 I slot print_timing: id 0 | task 2769 | total time = 2361.83 ms / 331 tokens 1.13.352.877 I slot print_timing: id 0 | task 2769 | graphs reused = 2693 1.13.352.878 I slot print_timing: id 0 | task 2769 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.352.899 I slot release: id 0 | task 2769 | stop processing: n_tokens = 330, truncated = 0 1.13.357.535 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.112 1.13.363.793 I slot launch_slot_: id 0 | task 2865 | processing task, is_child = 0 1.15.931.656 I slot print_timing: id 0 | task 2865 | prompt eval time = 608.51 ms / 211 tokens ( 2.88 ms per token, 346.75 tokens per second) 1.15.931.663 I slot print_timing: id 0 | task 2865 | eval time = 1959.34 ms / 106 tokens ( 18.66 ms per token, 53.59 tokens per second) 1.15.931.663 I slot print_timing: id 0 | task 2865 | total time = 2567.85 ms / 317 tokens 1.15.931.664 I slot print_timing: id 0 | task 2865 | graphs reused = 2796 1.15.931.664 I slot print_timing: id 0 | task 2865 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.931.686 I slot release: id 0 | task 2865 | stop processing: n_tokens = 316, truncated = 0 1.15.936.341 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.117 1.15.941.421 I slot launch_slot_: id 0 | task 2974 | processing task, is_child = 0 1.18.243.840 I slot print_timing: id 0 | task 2974 | prompt eval time = 602.46 ms / 211 tokens ( 2.86 ms per token, 350.23 tokens per second) 1.18.243.846 I slot print_timing: id 0 | task 2974 | eval time = 1699.95 ms / 92 tokens ( 18.68 ms per token, 53.53 tokens per second) 1.18.243.847 I slot print_timing: id 0 | task 2974 | total time = 2302.41 ms / 303 tokens 1.18.243.848 I slot print_timing: id 0 | task 2974 | graphs reused = 2885 1.18.243.848 I slot print_timing: id 0 | task 2974 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.243.867 I slot release: id 0 | task 2974 | stop processing: n_tokens = 302, truncated = 0 1.18.248.633 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.154 (> 0.100 thold), f_keep = 0.123 1.18.254.351 I slot launch_slot_: id 0 | task 3069 | processing task, is_child = 0 1.21.136.767 I slot print_timing: id 0 | task 3069 | prompt eval time = 639.33 ms / 240 tokens ( 2.66 ms per token, 375.39 tokens per second) 1.21.136.770 I slot print_timing: id 0 | task 3069 | eval time = 2243.08 ms / 121 tokens ( 18.69 ms per token, 53.50 tokens per second) 1.21.136.771 I slot print_timing: id 0 | task 3069 | total time = 2882.41 ms / 361 tokens 1.21.136.771 I slot print_timing: id 0 | task 3069 | graphs reused = 3003 1.21.136.772 I slot print_timing: id 0 | task 3069 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.136.793 I slot release: id 0 | task 3069 | stop processing: n_tokens = 360, truncated = 0 1.21.141.571 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.142 (> 0.100 thold), f_keep = 0.103 1.21.148.770 I slot launch_slot_: id 0 | task 3193 | processing task, is_child = 0 1.23.033.572 I slot print_timing: id 0 | task 3193 | prompt eval time = 699.01 ms / 260 tokens ( 2.69 ms per token, 371.96 tokens per second) 1.23.033.576 I slot print_timing: id 0 | task 3193 | eval time = 1185.78 ms / 64 tokens ( 18.82 ms per token, 53.13 tokens per second) 1.23.033.576 I slot print_timing: id 0 | task 3193 | total time = 1884.79 ms / 324 tokens 1.23.033.577 I slot print_timing: id 0 | task 3193 | graphs reused = 3065 1.23.033.578 I slot print_timing: id 0 | task 3193 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.033.601 I slot release: id 0 | task 3193 | stop processing: n_tokens = 323, truncated = 0 1.23.038.093 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.181 (> 0.100 thold), f_keep = 0.115 1.23.045.273 I slot launch_slot_: id 0 | task 3260 | processing task, is_child = 0 1.25.273.831 I slot print_timing: id 0 | task 3260 | prompt eval time = 580.16 ms / 204 tokens ( 2.84 ms per token, 351.63 tokens per second) 1.25.273.838 I slot print_timing: id 0 | task 3260 | eval time = 1648.39 ms / 89 tokens ( 18.73 ms per token, 53.39 tokens per second) 1.25.273.839 I slot print_timing: id 0 | task 3260 | total time = 2228.54 ms / 293 tokens 1.25.273.839 I slot print_timing: id 0 | task 3260 | graphs reused = 3151 1.25.273.840 I slot print_timing: id 0 | task 3260 | graph reallocs = 0 / 0 (same size) / (changed size) 1.25.273.859 I slot release: id 0 | task 3260 | stop processing: n_tokens = 292, truncated = 0 1.25.278.784 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.152 (> 0.100 thold), f_keep = 0.127 1.25.282.655 I slot launch_slot_: id 0 | task 3352 | processing task, is_child = 0 1.28.937.874 I slot print_timing: id 0 | task 3352 | n_gen = 162, tg = 53.54 t/s, tg_3s = 53.87 t/s 1.31.955.570 I slot print_timing: id 0 | task 3352 | n_gen = 323, tg = 53.44 t/s, tg_3s = 53.35 t/s 1.32.873.497 I slot print_timing: id 0 | task 3352 | prompt eval time = 647.96 ms / 244 tokens ( 2.66 ms per token, 376.57 tokens per second) 1.32.873.503 I slot print_timing: id 0 | task 3352 | eval time = 6942.87 ms / 372 tokens ( 18.71 ms per token, 53.44 tokens per second) 1.32.873.504 I slot print_timing: id 0 | task 3352 | total time = 7590.83 ms / 616 tokens 1.32.873.505 I slot print_timing: id 0 | task 3352 | graphs reused = 3519 1.32.873.505 I slot print_timing: id 0 | task 3352 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.873.532 I slot release: id 0 | task 3352 | stop processing: n_tokens = 615, truncated = 0 1.32.877.749 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.210 (> 0.100 thold), f_keep = 0.060 1.32.887.052 I slot launch_slot_: id 0 | task 3727 | processing task, is_child = 0 1.36.448.011 I slot print_timing: id 0 | task 3727 | n_gen = 163, tg = 53.81 t/s, tg_3s = 54.15 t/s 1.37.419.954 I slot print_timing: id 0 | task 3727 | prompt eval time = 550.54 ms / 176 tokens ( 3.13 ms per token, 319.69 tokens per second) 1.37.419.960 I slot print_timing: id 0 | task 3727 | eval time = 3982.35 ms / 215 tokens ( 18.61 ms per token, 53.74 tokens per second) 1.37.419.961 I slot print_timing: id 0 | task 3727 | total time = 4532.89 ms / 391 tokens 1.37.419.961 I slot print_timing: id 0 | task 3727 | graphs reused = 3731 1.37.419.962 I slot print_timing: id 0 | task 3727 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.419.985 I slot release: id 0 | task 3727 | stop processing: n_tokens = 390, truncated = 0 1.37.424.523 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.095 1.37.429.392 I slot launch_slot_: id 0 | task 3945 | processing task, is_child = 0 1.41.013.103 I slot print_timing: id 0 | task 3945 | n_gen = 163, tg = 53.82 t/s, tg_3s = 54.16 t/s 1.44.022.358 I slot print_timing: id 0 | task 3945 | n_gen = 324, tg = 53.66 t/s, tg_3s = 53.50 t/s 1.44.097.672 I slot print_timing: id 0 | task 3945 | prompt eval time = 573.90 ms / 185 tokens ( 3.10 ms per token, 322.35 tokens per second) 1.44.097.675 I slot print_timing: id 0 | task 3945 | eval time = 6094.36 ms / 328 tokens ( 18.64 ms per token, 53.66 tokens per second) 1.44.097.676 I slot print_timing: id 0 | task 3945 | total time = 6668.27 ms / 513 tokens 1.44.097.676 I slot print_timing: id 0 | task 3945 | graphs reused = 4056 1.44.097.677 I slot print_timing: id 0 | task 3945 | graph reallocs = 0 / 0 (same size) / (changed size) 1.44.097.699 I slot release: id 0 | task 3945 | stop processing: n_tokens = 512, truncated = 0 1.44.102.381 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.191 (> 0.100 thold), f_keep = 0.072 1.44.109.900 I slot launch_slot_: id 0 | task 4276 | processing task, is_child = 0 1.46.182.845 I slot print_timing: id 0 | task 4276 | prompt eval time = 564.49 ms / 194 tokens ( 2.91 ms per token, 343.67 tokens per second) 1.46.182.851 I slot print_timing: id 0 | task 4276 | eval time = 1508.45 ms / 82 tokens ( 18.62 ms per token, 53.70 tokens per second) 1.46.182.852 I slot print_timing: id 0 | task 4276 | total time = 2072.94 ms / 276 tokens 1.46.182.852 I slot print_timing: id 0 | task 4276 | graphs reused = 4135 1.46.182.853 I slot print_timing: id 0 | task 4276 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.182.871 I slot release: id 0 | task 4276 | stop processing: n_tokens = 275, truncated = 0 1.46.187.426 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.196 (> 0.100 thold), f_keep = 0.135 1.46.192.751 I slot launch_slot_: id 0 | task 4361 | processing task, is_child = 0 1.48.380.237 I slot print_timing: id 0 | task 4361 | prompt eval time = 545.78 ms / 189 tokens ( 2.89 ms per token, 346.29 tokens per second) 1.48.380.243 I slot print_timing: id 0 | task 4361 | eval time = 1641.69 ms / 89 tokens ( 18.66 ms per token, 53.60 tokens per second) 1.48.380.245 I slot print_timing: id 0 | task 4361 | total time = 2187.47 ms / 278 tokens 1.48.380.245 I slot print_timing: id 0 | task 4361 | graphs reused = 4221 1.48.380.246 I slot print_timing: id 0 | task 4361 | graph reallocs = 0 / 0 (same size) / (changed size) 1.48.380.265 I slot release: id 0 | task 4361 | stop processing: n_tokens = 277, truncated = 0 1.48.384.841 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.150 (> 0.100 thold), f_keep = 0.134 1.48.390.081 I slot launch_slot_: id 0 | task 4453 | processing task, is_child = 0 1.51.056.608 I slot print_timing: id 0 | task 4453 | prompt eval time = 695.49 ms / 246 tokens ( 2.83 ms per token, 353.71 tokens per second) 1.51.056.615 I slot print_timing: id 0 | task 4453 | eval time = 1971.03 ms / 106 tokens ( 18.77 ms per token, 53.27 tokens per second) 1.51.056.615 I slot print_timing: id 0 | task 4453 | total time = 2666.52 ms / 352 tokens 1.51.056.616 I slot print_timing: id 0 | task 4453 | graphs reused = 4324 1.51.056.617 I slot print_timing: id 0 | task 4453 | graph reallocs = 0 / 0 (same size) / (changed size) 1.51.056.642 I slot release: id 0 | task 4453 | stop processing: n_tokens = 351, truncated = 0 1.51.061.996 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 351, t_last = 352095625743 1.51.069.035 I slot launch_slot_: id 0 | task 4562 | processing task, is_child = 0 1.54.565.896 I slot print_timing: id 0 | task 4562 | prompt eval time = 928.95 ms / 373 tokens ( 2.49 ms per token, 401.53 tokens per second) 1.54.565.902 I slot print_timing: id 0 | task 4562 | eval time = 2567.90 ms / 138 tokens ( 18.74 ms per token, 53.35 tokens per second) 1.54.565.902 I slot print_timing: id 0 | task 4562 | total time = 3496.85 ms / 511 tokens 1.54.565.903 I slot print_timing: id 0 | task 4562 | graphs reused = 4460 1.54.565.904 I slot print_timing: id 0 | task 4562 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.565.929 I slot release: id 0 | task 4562 | stop processing: n_tokens = 510, truncated = 0 1.54.570.490 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.073 1.54.580.882 I slot launch_slot_: id 0 | task 4703 | processing task, is_child = 0 1.56.912.400 I slot print_timing: id 0 | task 4703 | prompt eval time = 581.36 ms / 197 tokens ( 2.95 ms per token, 338.86 tokens per second) 1.56.912.406 I slot print_timing: id 0 | task 4703 | eval time = 1750.15 ms / 95 tokens ( 18.62 ms per token, 53.71 tokens per second) 1.56.912.407 I slot print_timing: id 0 | task 4703 | total time = 2331.51 ms / 292 tokens 1.56.912.407 I slot print_timing: id 0 | task 4703 | graphs reused = 4552 1.56.912.408 I slot print_timing: id 0 | task 4703 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.912.427 I slot release: id 0 | task 4703 | stop processing: n_tokens = 291, truncated = 0 1.56.917.241 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.163 (> 0.100 thold), f_keep = 0.127 1.56.921.057 I slot launch_slot_: id 0 | task 4801 | processing task, is_child = 0 1.59.067.025 I slot print_timing: id 0 | task 4801 | prompt eval time = 616.51 ms / 227 tokens ( 2.72 ms per token, 368.20 tokens per second) 1.59.067.032 I slot print_timing: id 0 | task 4801 | eval time = 1529.44 ms / 83 tokens ( 18.65 ms per token, 53.61 tokens per second) 1.59.067.033 I slot print_timing: id 0 | task 4801 | total time = 2145.96 ms / 310 tokens 1.59.067.033 I slot print_timing: id 0 | task 4801 | graphs reused = 4632 1.59.067.034 I slot print_timing: id 0 | task 4801 | graph reallocs = 0 / 0 (same size) / (changed size) 1.59.067.055 I slot release: id 0 | task 4801 | stop processing: n_tokens = 309, truncated = 0 1.59.072.022 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.133 (> 0.100 thold), f_keep = 0.120 1.59.078.090 I slot launch_slot_: id 0 | task 4887 | processing task, is_child = 0 2.01.596.842 I slot print_timing: id 0 | task 4887 | prompt eval time = 727.46 ms / 278 tokens ( 2.62 ms per token, 382.15 tokens per second) 2.01.596.848 I slot print_timing: id 0 | task 4887 | eval time = 1791.28 ms / 97 tokens ( 18.66 ms per token, 53.59 tokens per second) 2.01.596.849 I slot print_timing: id 0 | task 4887 | total time = 2518.74 ms / 375 tokens 2.01.596.849 I slot print_timing: id 0 | task 4887 | graphs reused = 4727 2.01.596.850 I slot print_timing: id 0 | task 4887 | graph reallocs = 0 / 0 (same size) / (changed size) 2.01.596.872 I slot release: id 0 | task 4887 | stop processing: n_tokens = 374, truncated = 0 2.01.601.652 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.131 (> 0.100 thold), f_keep = 0.102 2.01.609.349 I slot launch_slot_: id 0 | task 4987 | processing task, is_child = 0 2.04.727.261 I slot print_timing: id 0 | task 4987 | prompt eval time = 743.20 ms / 289 tokens ( 2.57 ms per token, 388.86 tokens per second) 2.04.727.268 I slot print_timing: id 0 | task 4987 | eval time = 2374.70 ms / 128 tokens ( 18.70 ms per token, 53.48 tokens per second) 2.04.727.268 I slot print_timing: id 0 | task 4987 | total time = 3117.90 ms / 417 tokens 2.04.727.269 I slot print_timing: id 0 | task 4987 | graphs reused = 4853 2.04.727.270 I slot print_timing: id 0 | task 4987 | graph reallocs = 0 / 0 (same size) / (changed size) 2.04.727.295 I slot release: id 0 | task 4987 | stop processing: n_tokens = 416, truncated = 0 2.04.731.715 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.195 (> 0.100 thold), f_keep = 0.096 2.04.739.424 I slot launch_slot_: id 0 | task 5118 | processing task, is_child = 0 2.06.517.781 I slot print_timing: id 0 | task 5118 | prompt eval time = 585.26 ms / 205 tokens ( 2.85 ms per token, 350.27 tokens per second) 2.06.517.785 I slot print_timing: id 0 | task 5118 | eval time = 1193.09 ms / 65 tokens ( 18.64 ms per token, 53.64 tokens per second) 2.06.517.786 I slot print_timing: id 0 | task 5118 | total time = 1778.35 ms / 270 tokens 2.06.517.786 I slot print_timing: id 0 | task 5118 | graphs reused = 4915 2.06.517.787 I slot print_timing: id 0 | task 5118 | graph reallocs = 0 / 0 (same size) / (changed size) 2.06.517.809 I slot release: id 0 | task 5118 | stop processing: n_tokens = 269, truncated = 0 2.06.522.528 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.167 (> 0.100 thold), f_keep = 0.138 2.06.526.145 I slot launch_slot_: id 0 | task 5186 | processing task, is_child = 0 2.08.787.900 I slot print_timing: id 0 | task 5186 | prompt eval time = 621.37 ms / 221 tokens ( 2.81 ms per token, 355.67 tokens per second) 2.08.787.906 I slot print_timing: id 0 | task 5186 | eval time = 1640.38 ms / 89 tokens ( 18.64 ms per token, 53.65 tokens per second) 2.08.787.907 I slot print_timing: id 0 | task 5186 | total time = 2261.75 ms / 310 tokens 2.08.787.908 I slot print_timing: id 0 | task 5186 | graphs reused = 5001 2.08.787.908 I slot print_timing: id 0 | task 5186 | graph reallocs = 0 / 0 (same size) / (changed size) 2.08.787.928 I slot release: id 0 | task 5186 | stop processing: n_tokens = 309, truncated = 0 2.08.792.529 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.165 (> 0.100 thold), f_keep = 0.120 2.08.798.875 I slot launch_slot_: id 0 | task 5278 | processing task, is_child = 0 2.10.911.924 I slot print_timing: id 0 | task 5278 | prompt eval time = 619.64 ms / 224 tokens ( 2.77 ms per token, 361.50 tokens per second) 2.10.911.928 I slot print_timing: id 0 | task 5278 | eval time = 1493.40 ms / 81 tokens ( 18.67 ms per token, 53.57 tokens per second) 2.10.911.928 I slot print_timing: id 0 | task 5278 | total time = 2113.04 ms / 305 tokens 2.10.911.929 I slot print_timing: id 0 | task 5278 | graphs reused = 5079 2.10.911.930 I slot print_timing: id 0 | task 5278 | graph reallocs = 0 / 0 (same size) / (changed size) 2.10.911.953 I slot release: id 0 | task 5278 | stop processing: n_tokens = 304, truncated = 0 2.10.916.942 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.146 (> 0.100 thold), f_keep = 0.122 2.10.923.122 I slot launch_slot_: id 0 | task 5362 | processing task, is_child = 0 2.13.469.896 I slot print_timing: id 0 | task 5362 | prompt eval time = 695.70 ms / 254 tokens ( 2.74 ms per token, 365.10 tokens per second) 2.13.469.903 I slot print_timing: id 0 | task 5362 | eval time = 1851.07 ms / 100 tokens ( 18.70 ms per token, 53.48 tokens per second) 2.13.469.903 I slot print_timing: id 0 | task 5362 | total time = 2546.77 ms / 354 tokens 2.13.469.904 I slot print_timing: id 0 | task 5362 | graphs reused = 5176 2.13.469.904 I slot print_timing: id 0 | task 5362 | graph reallocs = 0 / 0 (same size) / (changed size) 2.13.469.925 I slot release: id 0 | task 5362 | stop processing: n_tokens = 353, truncated = 0 2.13.474.535 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.177 (> 0.100 thold), f_keep = 0.105 2.13.481.560 I slot launch_slot_: id 0 | task 5465 | processing task, is_child = 0 2.15.840.619 I slot print_timing: id 0 | task 5465 | prompt eval time = 589.94 ms / 209 tokens ( 2.82 ms per token, 354.27 tokens per second) 2.15.840.626 I slot print_timing: id 0 | task 5465 | eval time = 1769.11 ms / 96 tokens ( 18.62 ms per token, 53.70 tokens per second) 2.15.840.627 I slot print_timing: id 0 | task 5465 | total time = 2359.05 ms / 305 tokens 2.15.840.627 I slot print_timing: id 0 | task 5465 | graphs reused = 5269 2.15.840.628 I slot print_timing: id 0 | task 5465 | graph reallocs = 0 / 0 (same size) / (changed size) 2.15.840.647 I slot release: id 0 | task 5465 | stop processing: n_tokens = 304, truncated = 0 2.15.845.325 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.141 (> 0.100 thold), f_keep = 0.122 2.15.849.369 I slot launch_slot_: id 0 | task 5564 | processing task, is_child = 0 2.18.046.638 I slot print_timing: id 0 | task 5564 | prompt eval time = 702.30 ms / 263 tokens ( 2.67 ms per token, 374.48 tokens per second) 2.18.046.644 I slot print_timing: id 0 | task 5564 | eval time = 1494.96 ms / 81 tokens ( 18.69 ms per token, 53.51 tokens per second) 2.18.046.645 I slot print_timing: id 0 | task 5564 | total time = 2197.26 ms / 344 tokens 2.18.046.646 I slot print_timing: id 0 | task 5564 | graphs reused = 5348 2.18.046.646 I slot print_timing: id 0 | task 5564 | graph reallocs = 0 / 0 (same size) / (changed size) 2.18.046.667 I slot release: id 0 | task 5564 | stop processing: n_tokens = 343, truncated = 0 2.18.051.322 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.167 (> 0.100 thold), f_keep = 0.108 2.18.058.490 I slot launch_slot_: id 0 | task 5648 | processing task, is_child = 0 2.21.656.970 I slot print_timing: id 0 | task 5648 | n_gen = 162, tg = 53.61 t/s, tg_3s = 53.94 t/s 2.24.032.218 I slot print_timing: id 0 | task 5648 | prompt eval time = 595.16 ms / 221 tokens ( 2.69 ms per token, 371.33 tokens per second) 2.24.032.224 I slot print_timing: id 0 | task 5648 | eval time = 5378.56 ms / 289 tokens ( 18.68 ms per token, 53.55 tokens per second) 2.24.032.225 I slot print_timing: id 0 | task 5648 | total time = 5973.72 ms / 510 tokens 2.24.032.225 I slot print_timing: id 0 | task 5648 | graphs reused = 5634 2.24.032.226 I slot print_timing: id 0 | task 5648 | graph reallocs = 0 / 0 (same size) / (changed size) 2.24.032.246 I slot release: id 0 | task 5648 | stop processing: n_tokens = 509, truncated = 0 2.24.036.968 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.073 2.24.043.912 I slot launch_slot_: id 0 | task 5940 | processing task, is_child = 0 2.26.305.661 I slot print_timing: id 0 | task 5940 | prompt eval time = 628.58 ms / 217 tokens ( 2.90 ms per token, 345.22 tokens per second) 2.26.305.665 I slot print_timing: id 0 | task 5940 | eval time = 1633.15 ms / 88 tokens ( 18.77 ms per token, 53.27 tokens per second) 2.26.305.665 I slot print_timing: id 0 | task 5940 | total time = 2261.73 ms / 305 tokens 2.26.305.666 I slot print_timing: id 0 | task 5940 | graphs reused = 5719 2.26.305.666 I slot print_timing: id 0 | task 5940 | graph reallocs = 0 / 0 (same size) / (changed size) 2.26.305.687 I slot release: id 0 | task 5940 | stop processing: n_tokens = 304, truncated = 0 2.26.311.414 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.110 (> 0.100 thold), f_keep = 0.122 2.26.316.923 I slot launch_slot_: id 0 | task 6031 | processing task, is_child = 0 2.30.135.141 I slot print_timing: id 0 | task 6031 | n_gen = 162, tg = 53.40 t/s, tg_3s = 53.73 t/s 2.30.439.650 I slot print_timing: id 0 | task 6031 | prompt eval time = 803.03 ms / 337 tokens ( 2.38 ms per token, 419.66 tokens per second) 2.30.439.655 I slot print_timing: id 0 | task 6031 | eval time = 3319.68 ms / 178 tokens ( 18.76 ms per token, 53.32 tokens per second) 2.30.439.656 I slot print_timing: id 0 | task 6031 | total time = 4122.71 ms / 515 tokens 2.30.439.656 I slot print_timing: id 0 | task 6031 | graphs reused = 5894 2.30.439.657 I slot print_timing: id 0 | task 6031 | graph reallocs = 0 / 0 (same size) / (changed size) 2.30.439.682 I slot release: id 0 | task 6031 | stop processing: n_tokens = 514, truncated = 0 2.30.444.778 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.123 (> 0.100 thold), f_keep = 0.072 2.30.454.605 I slot launch_slot_: id 0 | task 6212 | processing task, is_child = 0 2.34.138.781 I slot print_timing: id 0 | task 6212 | prompt eval time = 748.75 ms / 301 tokens ( 2.49 ms per token, 402.00 tokens per second) 2.34.138.784 I slot print_timing: id 0 | task 6212 | eval time = 2935.40 ms / 158 tokens ( 18.70 ms per token, 53.48 tokens per second) 2.34.138.785 I slot print_timing: id 0 | task 6212 | total time = 3684.16 ms / 459 tokens 2.34.138.785 I slot print_timing: id 0 | task 6212 | graphs reused = 6050 2.34.138.786 I slot print_timing: id 0 | task 6212 | graph reallocs = 0 / 0 (same size) / (changed size) 2.34.138.813 I slot release: id 0 | task 6212 | stop processing: n_tokens = 458, truncated = 0 2.34.143.465 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.081 2.34.151.738 I slot launch_slot_: id 0 | task 6373 | processing task, is_child = 0 2.36.442.841 I slot print_timing: id 0 | task 6373 | prompt eval time = 614.22 ms / 212 tokens ( 2.90 ms per token, 345.15 tokens per second) 2.36.442.846 I slot print_timing: id 0 | task 6373 | eval time = 1676.87 ms / 91 tokens ( 18.63 ms per token, 53.67 tokens per second) 2.36.442.847 I slot print_timing: id 0 | task 6373 | total time = 2291.09 ms / 303 tokens 2.36.442.848 I slot print_timing: id 0 | task 6373 | graphs reused = 6138 2.36.442.848 I slot print_timing: id 0 | task 6373 | graph reallocs = 0 / 0 (same size) / (changed size) 2.36.442.868 I slot release: id 0 | task 6373 | stop processing: n_tokens = 302, truncated = 0 2.36.447.728 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.149 (> 0.100 thold), f_keep = 0.123 2.36.451.677 I slot launch_slot_: id 0 | task 6467 | processing task, is_child = 0 2.38.501.551 I slot print_timing: id 0 | task 6467 | prompt eval time = 664.56 ms / 248 tokens ( 2.68 ms per token, 373.18 tokens per second) 2.38.501.558 I slot print_timing: id 0 | task 6467 | eval time = 1385.31 ms / 75 tokens ( 18.72 ms per token, 53.42 tokens per second) 2.38.501.559 I slot print_timing: id 0 | task 6467 | total time = 2049.86 ms / 323 tokens 2.38.501.559 I slot print_timing: id 0 | task 6467 | graphs reused = 6210 2.38.501.560 I slot print_timing: id 0 | task 6467 | graph reallocs = 0 / 0 (same size) / (changed size) 2.38.501.580 I slot release: id 0 | task 6467 | stop processing: n_tokens = 322, truncated = 0 2.38.506.047 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.181 (> 0.100 thold), f_keep = 0.115 2.38.512.513 I slot launch_slot_: id 0 | task 6545 | processing task, is_child = 0 2.40.511.824 I slot print_timing: id 0 | task 6545 | prompt eval time = 582.95 ms / 204 tokens ( 2.86 ms per token, 349.94 tokens per second) 2.40.511.827 I slot print_timing: id 0 | task 6545 | eval time = 1416.35 ms / 77 tokens ( 18.64 ms per token, 53.66 tokens per second) 2.40.511.828 I slot print_timing: id 0 | task 6545 | total time = 1999.30 ms / 281 tokens 2.40.511.828 I slot print_timing: id 0 | task 6545 | graphs reused = 6284 2.40.511.829 I slot print_timing: id 0 | task 6545 | graph reallocs = 0 / 0 (same size) / (changed size) 2.40.511.848 I slot release: id 0 | task 6545 | stop processing: n_tokens = 280, truncated = 0 2.40.516.789 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.139 (> 0.100 thold), f_keep = 0.132 2.40.520.549 I slot launch_slot_: id 0 | task 6625 | processing task, is_child = 0 2.43.040.105 I slot print_timing: id 0 | task 6625 | prompt eval time = 711.95 ms / 267 tokens ( 2.67 ms per token, 375.02 tokens per second) 2.43.040.111 I slot print_timing: id 0 | task 6625 | eval time = 1807.59 ms / 98 tokens ( 18.63 ms per token, 53.66 tokens per second) 2.43.040.112 I slot print_timing: id 0 | task 6625 | total time = 2519.54 ms / 365 tokens 2.43.040.112 I slot print_timing: id 0 | task 6625 | graphs reused = 6380 2.43.040.113 I slot print_timing: id 0 | task 6625 | graph reallocs = 0 / 0 (same size) / (changed size) 2.43.040.138 I slot release: id 0 | task 6625 | stop processing: n_tokens = 364, truncated = 0 2.43.045.674 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 364, t_last = 352147609239 2.43.053.353 I slot launch_slot_: id 0 | task 6726 | processing task, is_child = 0 2.45.937.848 I slot print_timing: id 0 | task 6726 | prompt eval time = 860.18 ms / 392 tokens ( 2.19 ms per token, 455.72 tokens per second) 2.45.937.854 I slot print_timing: id 0 | task 6726 | eval time = 2024.30 ms / 109 tokens ( 18.74 ms per token, 53.35 tokens per second) 2.45.937.855 I slot print_timing: id 0 | task 6726 | total time = 2884.48 ms / 501 tokens 2.45.937.855 I slot print_timing: id 0 | task 6726 | graphs reused = 6487 2.45.937.856 I slot print_timing: id 0 | task 6726 | graph reallocs = 0 / 0 (same size) / (changed size) 2.45.937.882 I slot release: id 0 | task 6726 | stop processing: n_tokens = 500, truncated = 0 2.45.943.761 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 500, t_last = 352150506983 2.45.955.423 I slot launch_slot_: id 0 | task 6838 | processing task, is_child = 0 2.48.626.776 I slot print_timing: id 0 | task 6838 | prompt eval time = 1029.26 ms / 461 tokens ( 2.23 ms per token, 447.90 tokens per second) 2.48.626.782 I slot print_timing: id 0 | task 6838 | eval time = 1642.09 ms / 88 tokens ( 18.87 ms per token, 52.98 tokens per second) 2.48.626.783 I slot print_timing: id 0 | task 6838 | total time = 2671.34 ms / 549 tokens 2.48.626.783 I slot print_timing: id 0 | task 6838 | graphs reused = 6572 2.48.626.784 I slot print_timing: id 0 | task 6838 | graph reallocs = 0 / 0 (same size) / (changed size) 2.48.626.812 I slot release: id 0 | task 6838 | stop processing: n_tokens = 548, truncated = 0 2.48.633.367 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 548, t_last = 352153195913 2.48.644.218 I slot launch_slot_: id 0 | task 6929 | processing task, is_child = 0 2.51.690.907 I slot print_timing: id 0 | task 6929 | prompt eval time = 1046.60 ms / 505 tokens ( 2.07 ms per token, 482.52 tokens per second) 2.51.690.910 I slot print_timing: id 0 | task 6929 | eval time = 2000.08 ms / 107 tokens ( 18.87 ms per token, 53.00 tokens per second) 2.51.690.911 I slot print_timing: id 0 | task 6929 | total time = 3046.68 ms / 612 tokens 2.51.690.911 I slot print_timing: id 0 | task 6929 | graphs reused = 6676 2.51.690.912 I slot print_timing: id 0 | task 6929 | graph reallocs = 0 / 0 (same size) / (changed size) 2.51.690.946 I slot release: id 0 | task 6929 | stop processing: n_tokens = 611, truncated = 0 2.51.697.269 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 611, t_last = 352156260047 2.51.709.731 I slot launch_slot_: id 0 | task 7039 | processing task, is_child = 0 2.54.813.204 I slot print_timing: id 0 | task 7039 | prompt eval time = 974.45 ms / 493 tokens ( 1.98 ms per token, 505.93 tokens per second) 2.54.813.208 I slot print_timing: id 0 | task 7039 | eval time = 2129.01 ms / 114 tokens ( 18.84 ms per token, 53.08 tokens per second) 2.54.813.208 I slot print_timing: id 0 | task 7039 | total time = 3103.46 ms / 607 tokens 2.54.813.209 I slot print_timing: id 0 | task 7039 | graphs reused = 6787 2.54.813.209 I slot print_timing: id 0 | task 7039 | graph reallocs = 0 / 0 (same size) / (changed size) 2.54.813.246 I slot release: id 0 | task 7039 | stop processing: n_tokens = 606, truncated = 0 2.54.818.604 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 2.54.829.651 I slot launch_slot_: id 0 | task 7156 | processing task, is_child = 0 2.56.951.881 I slot print_timing: id 0 | task 7156 | prompt eval time = 774.65 ms / 331 tokens ( 2.34 ms per token, 427.29 tokens per second) 2.56.951.884 I slot print_timing: id 0 | task 7156 | eval time = 1347.57 ms / 73 tokens ( 18.72 ms per token, 53.43 tokens per second) 2.56.951.885 I slot print_timing: id 0 | task 7156 | total time = 2122.22 ms / 404 tokens 2.56.951.885 I slot print_timing: id 0 | task 7156 | graphs reused = 6858 2.56.951.886 I slot print_timing: id 0 | task 7156 | graph reallocs = 0 / 0 (same size) / (changed size) 2.56.951.909 I slot release: id 0 | task 7156 | stop processing: n_tokens = 403, truncated = 0 2.56.957.766 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 403, t_last = 352161521010 2.56.963.116 I slot launch_slot_: id 0 | task 7232 | processing task, is_child = 0 2.59.683.933 I slot print_timing: id 0 | task 7232 | prompt eval time = 928.19 ms / 455 tokens ( 2.04 ms per token, 490.20 tokens per second) 2.59.683.938 I slot print_timing: id 0 | task 7232 | eval time = 1792.62 ms / 96 tokens ( 18.87 ms per token, 52.99 tokens per second) 2.59.683.939 I slot print_timing: id 0 | task 7232 | total time = 2720.81 ms / 551 tokens 2.59.683.940 I slot print_timing: id 0 | task 7232 | graphs reused = 6951 2.59.683.940 I slot print_timing: id 0 | task 7232 | graph reallocs = 0 / 0 (same size) / (changed size) 2.59.683.975 I slot release: id 0 | task 7232 | stop processing: n_tokens = 550, truncated = 0 2.59.689.367 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 550, t_last = 352164253076 2.59.700.246 I slot launch_slot_: id 0 | task 7331 | processing task, is_child = 0 3.02.581.158 I slot print_timing: id 0 | task 7331 | prompt eval time = 904.36 ms / 439 tokens ( 2.06 ms per token, 485.43 tokens per second) 3.02.581.164 I slot print_timing: id 0 | task 7331 | eval time = 1976.54 ms / 106 tokens ( 18.82 ms per token, 53.12 tokens per second) 3.02.581.164 I slot print_timing: id 0 | task 7331 | total time = 2880.90 ms / 545 tokens 3.02.581.165 I slot print_timing: id 0 | task 7331 | graphs reused = 7054 3.02.581.165 I slot print_timing: id 0 | task 7331 | graph reallocs = 0 / 0 (same size) / (changed size) 3.02.581.200 I slot release: id 0 | task 7331 | stop processing: n_tokens = 544, truncated = 0 3.02.586.834 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 544, t_last = 352167150301 3.02.597.230 I slot launch_slot_: id 0 | task 7440 | processing task, is_child = 0 3.04.497.849 I slot print_timing: id 0 | task 7440 | prompt eval time = 817.28 ms / 379 tokens ( 2.16 ms per token, 463.73 tokens per second) 3.04.497.854 I slot print_timing: id 0 | task 7440 | eval time = 1083.33 ms / 58 tokens ( 19.01 ms per token, 52.62 tokens per second) 3.04.497.855 I slot print_timing: id 0 | task 7440 | total time = 1900.61 ms / 437 tokens 3.04.497.855 I slot print_timing: id 0 | task 7440 | graphs reused = 7110 3.04.497.856 I slot print_timing: id 0 | task 7440 | graph reallocs = 0 / 0 (same size) / (changed size) 3.04.497.882 I slot release: id 0 | task 7440 | stop processing: n_tokens = 436, truncated = 0 3.04.503.462 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.106 (> 0.100 thold), f_keep = 0.085 3.04.509.222 I slot launch_slot_: id 0 | task 7501 | processing task, is_child = 0 3.06.394.085 I slot print_timing: id 0 | task 7501 | prompt eval time = 776.61 ms / 348 tokens ( 2.23 ms per token, 448.10 tokens per second) 3.06.394.089 I slot print_timing: id 0 | task 7501 | eval time = 1108.24 ms / 60 tokens ( 18.78 ms per token, 53.24 tokens per second) 3.06.394.090 I slot print_timing: id 0 | task 7501 | total time = 1884.85 ms / 408 tokens 3.06.394.090 I slot print_timing: id 0 | task 7501 | graphs reused = 7168 3.06.394.091 I slot print_timing: id 0 | task 7501 | graph reallocs = 0 / 0 (same size) / (changed size) 3.06.394.116 I slot release: id 0 | task 7501 | stop processing: n_tokens = 407, truncated = 0 3.06.400.097 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 407, t_last = 352170963217 3.06.408.546 I slot launch_slot_: id 0 | task 7564 | processing task, is_child = 0 3.08.744.766 I slot print_timing: id 0 | task 7564 | prompt eval time = 850.38 ms / 425 tokens ( 2.00 ms per token, 499.78 tokens per second) 3.08.744.770 I slot print_timing: id 0 | task 7564 | eval time = 1485.83 ms / 80 tokens ( 18.81 ms per token, 53.17 tokens per second) 3.08.744.770 I slot print_timing: id 0 | task 7564 | total time = 2336.21 ms / 505 tokens 3.08.744.771 I slot print_timing: id 0 | task 7564 | graphs reused = 7246 3.08.744.771 I slot print_timing: id 0 | task 7564 | graph reallocs = 0 / 0 (same size) / (changed size) 3.08.744.803 I slot release: id 0 | task 7564 | stop processing: n_tokens = 504, truncated = 0 3.08.750.500 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 352173313904 3.08.761.353 I slot launch_slot_: id 0 | task 7647 | processing task, is_child = 0 3.12.561.408 I slot print_timing: id 0 | task 7647 | n_gen = 161, tg = 53.21 t/s, tg_3s = 53.54 t/s 3.12.994.204 I slot print_timing: id 0 | task 7647 | prompt eval time = 793.19 ms / 371 tokens ( 2.14 ms per token, 467.73 tokens per second) 3.12.994.210 I slot print_timing: id 0 | task 7647 | eval time = 3439.65 ms / 184 tokens ( 18.80 ms per token, 53.20 tokens per second) 3.12.994.211 I slot print_timing: id 0 | task 7647 | total time = 4232.84 ms / 555 tokens 3.12.994.212 I slot print_timing: id 0 | task 7647 | graphs reused = 7427 3.12.994.212 I slot print_timing: id 0 | task 7647 | graph reallocs = 0 / 0 (same size) / (changed size) 3.12.994.246 I slot release: id 0 | task 7647 | stop processing: n_tokens = 554, truncated = 0 3.12.999.706 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.121 (> 0.100 thold), f_keep = 0.067 3.13.006.745 I slot launch_slot_: id 0 | task 7834 | processing task, is_child = 0 3.15.237.834 I slot print_timing: id 0 | task 7834 | prompt eval time = 719.61 ms / 306 tokens ( 2.35 ms per token, 425.23 tokens per second) 3.15.237.840 I slot print_timing: id 0 | task 7834 | eval time = 1511.47 ms / 82 tokens ( 18.66 ms per token, 53.59 tokens per second) 3.15.237.841 I slot print_timing: id 0 | task 7834 | total time = 2231.08 ms / 388 tokens 3.15.237.842 I slot print_timing: id 0 | task 7834 | graphs reused = 7507 3.15.237.842 I slot print_timing: id 0 | task 7834 | graph reallocs = 0 / 0 (same size) / (changed size) 3.15.237.866 I slot release: id 0 | task 7834 | stop processing: n_tokens = 387, truncated = 0 3.15.243.735 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 387, t_last = 352179806967 3.15.251.303 I slot launch_slot_: id 0 | task 7919 | processing task, is_child = 0 3.17.904.642 I slot print_timing: id 0 | task 7919 | prompt eval time = 831.08 ms / 397 tokens ( 2.09 ms per token, 477.69 tokens per second) 3.17.904.648 I slot print_timing: id 0 | task 7919 | eval time = 1822.25 ms / 98 tokens ( 18.79 ms per token, 53.23 tokens per second) 3.17.904.649 I slot print_timing: id 0 | task 7919 | total time = 2653.33 ms / 495 tokens 3.17.904.649 I slot print_timing: id 0 | task 7919 | graphs reused = 7603 3.17.904.650 I slot print_timing: id 0 | task 7919 | graph reallocs = 0 / 0 (same size) / (changed size) 3.17.904.678 I slot release: id 0 | task 7919 | stop processing: n_tokens = 494, truncated = 0 3.17.909.828 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.110 (> 0.100 thold), f_keep = 0.075 3.17.920.680 I slot launch_slot_: id 0 | task 8020 | processing task, is_child = 0 3.20.061.473 I slot print_timing: id 0 | task 8020 | prompt eval time = 754.40 ms / 337 tokens ( 2.24 ms per token, 446.71 tokens per second) 3.20.061.478 I slot print_timing: id 0 | task 8020 | eval time = 1386.38 ms / 75 tokens ( 18.73 ms per token, 53.38 tokens per second) 3.20.061.479 I slot print_timing: id 0 | task 8020 | total time = 2140.78 ms / 412 tokens 3.20.061.480 I slot print_timing: id 0 | task 8020 | graphs reused = 7676 3.20.061.480 I slot print_timing: id 0 | task 8020 | graph reallocs = 0 / 0 (same size) / (changed size) 3.20.061.504 I slot release: id 0 | task 8020 | stop processing: n_tokens = 411, truncated = 0 3.20.066.633 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.121 (> 0.100 thold), f_keep = 0.090 3.20.073.693 I slot launch_slot_: id 0 | task 8098 | processing task, is_child = 0 3.22.547.533 I slot print_timing: id 0 | task 8098 | prompt eval time = 718.06 ms / 305 tokens ( 2.35 ms per token, 424.76 tokens per second) 3.22.547.539 I slot print_timing: id 0 | task 8098 | eval time = 1755.77 ms / 95 tokens ( 18.68 ms per token, 53.54 tokens per second) 3.22.547.540 I slot print_timing: id 0 | task 8098 | total time = 2473.83 ms / 400 tokens 3.22.547.541 I slot print_timing: id 0 | task 8098 | graphs reused = 7769 3.22.547.541 I slot print_timing: id 0 | task 8098 | graph reallocs = 0 / 0 (same size) / (changed size) 3.22.547.569 I slot release: id 0 | task 8098 | stop processing: n_tokens = 399, truncated = 0 3.22.552.976 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.112 (> 0.100 thold), f_keep = 0.093 3.22.560.700 I slot launch_slot_: id 0 | task 8196 | processing task, is_child = 0 3.24.662.660 I slot print_timing: id 0 | task 8196 | prompt eval time = 732.04 ms / 329 tokens ( 2.23 ms per token, 449.43 tokens per second) 3.24.662.663 I slot print_timing: id 0 | task 8196 | eval time = 1369.91 ms / 74 tokens ( 18.77 ms per token, 53.29 tokens per second) 3.24.662.663 I slot print_timing: id 0 | task 8196 | total time = 2101.95 ms / 403 tokens 3.24.662.664 I slot print_timing: id 0 | task 8196 | graphs reused = 7841 3.24.662.665 I slot print_timing: id 0 | task 8196 | graph reallocs = 0 / 0 (same size) / (changed size) 3.24.662.690 I slot release: id 0 | task 8196 | stop processing: n_tokens = 402, truncated = 0 3.24.667.784 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.118 (> 0.100 thold), f_keep = 0.092 3.24.675.881 I slot launch_slot_: id 0 | task 8273 | processing task, is_child = 0 3.26.511.203 I slot print_timing: id 0 | task 8273 | prompt eval time = 730.00 ms / 313 tokens ( 2.33 ms per token, 428.76 tokens per second) 3.26.511.206 I slot print_timing: id 0 | task 8273 | eval time = 1105.31 ms / 60 tokens ( 18.73 ms per token, 53.38 tokens per second) 3.26.511.207 I slot print_timing: id 0 | task 8273 | total time = 1835.31 ms / 373 tokens 3.26.511.207 I slot print_timing: id 0 | task 8273 | graphs reused = 7899 3.26.511.208 I slot print_timing: id 0 | task 8273 | graph reallocs = 0 / 0 (same size) / (changed size) 3.26.511.233 I slot release: id 0 | task 8273 | stop processing: n_tokens = 372, truncated = 0 3.26.517.316 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 372, t_last = 352191080334 3.26.524.911 I slot launch_slot_: id 0 | task 8336 | processing task, is_child = 0 3.29.250.124 I slot print_timing: id 0 | task 8336 | prompt eval time = 952.07 ms / 467 tokens ( 2.04 ms per token, 490.51 tokens per second) 3.29.250.130 I slot print_timing: id 0 | task 8336 | eval time = 1773.13 ms / 95 tokens ( 18.86 ms per token, 53.01 tokens per second) 3.29.250.131 I slot print_timing: id 0 | task 8336 | total time = 2725.20 ms / 562 tokens 3.29.250.132 I slot print_timing: id 0 | task 8336 | graphs reused = 7991 3.29.250.132 I slot print_timing: id 0 | task 8336 | graph reallocs = 0 / 0 (same size) / (changed size) 3.29.250.166 I slot release: id 0 | task 8336 | stop processing: n_tokens = 561, truncated = 0 3.29.255.480 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.106 (> 0.100 thold), f_keep = 0.066 3.29.266.962 I slot launch_slot_: id 0 | task 8434 | processing task, is_child = 0 3.31.523.718 I slot print_timing: id 0 | task 8434 | prompt eval time = 811.94 ms / 348 tokens ( 2.33 ms per token, 428.60 tokens per second) 3.31.523.721 I slot print_timing: id 0 | task 8434 | eval time = 1444.80 ms / 78 tokens ( 18.76 ms per token, 53.29 tokens per second) 3.31.523.722 I slot print_timing: id 0 | task 8434 | total time = 2256.74 ms / 426 tokens 3.31.523.722 I slot print_timing: id 0 | task 8434 | graphs reused = 8067 3.31.523.723 I slot print_timing: id 0 | task 8434 | graph reallocs = 0 / 0 (same size) / (changed size) 3.31.523.755 I slot release: id 0 | task 8434 | stop processing: n_tokens = 425, truncated = 0 3.31.531.150 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 425, t_last = 352196092856 3.31.536.690 I slot launch_slot_: id 0 | task 8515 | processing task, is_child = 0 3.36.122.653 I slot print_timing: id 0 | task 8515 | prompt eval time = 1587.18 ms / 690 tokens ( 2.30 ms per token, 434.73 tokens per second) 3.36.122.657 I slot print_timing: id 0 | task 8515 | eval time = 2998.77 ms / 160 tokens ( 18.86 ms per token, 53.02 tokens per second) 3.36.122.657 I slot print_timing: id 0 | task 8515 | total time = 4585.95 ms / 850 tokens 3.36.122.658 I slot print_timing: id 0 | task 8515 | graphs reused = 8224 3.36.122.659 I slot print_timing: id 0 | task 8515 | graph reallocs = 0 / 0 (same size) / (changed size) 3.36.122.698 I slot release: id 0 | task 8515 | stop processing: n_tokens = 849, truncated = 0 3.36.128.332 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.113 (> 0.100 thold), f_keep = 0.044 3.36.143.125 I slot launch_slot_: id 0 | task 8679 | processing task, is_child = 0 3.38.136.543 I slot print_timing: id 0 | task 8679 | prompt eval time = 785.80 ms / 328 tokens ( 2.40 ms per token, 417.41 tokens per second) 3.38.136.546 I slot print_timing: id 0 | task 8679 | eval time = 1207.61 ms / 65 tokens ( 18.87 ms per token, 53.00 tokens per second) 3.38.136.547 I slot print_timing: id 0 | task 8679 | total time = 1993.41 ms / 393 tokens 3.38.136.547 I slot print_timing: id 0 | task 8679 | graphs reused = 8287 3.38.136.548 I slot print_timing: id 0 | task 8679 | graph reallocs = 0 / 0 (same size) / (changed size) 3.38.136.572 I slot release: id 0 | task 8679 | stop processing: n_tokens = 392, truncated = 0 3.38.142.734 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 392, t_last = 352202705673 3.38.147.980 I slot launch_slot_: id 0 | task 8747 | processing task, is_child = 0 3.40.842.579 I slot print_timing: id 0 | task 8747 | prompt eval time = 1111.32 ms / 532 tokens ( 2.09 ms per token, 478.71 tokens per second) 3.40.842.585 I slot print_timing: id 0 | task 8747 | eval time = 1583.26 ms / 85 tokens ( 18.85 ms per token, 53.05 tokens per second) 3.40.842.586 I slot print_timing: id 0 | task 8747 | total time = 2694.59 ms / 617 tokens 3.40.842.586 I slot print_timing: id 0 | task 8747 | graphs reused = 8370 3.40.842.587 I slot print_timing: id 0 | task 8747 | graph reallocs = 0 / 0 (same size) / (changed size) 3.40.842.621 I slot release: id 0 | task 8747 | stop processing: n_tokens = 616, truncated = 0 3.40.850.048 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 616, t_last = 352205411722 3.40.864.296 I slot launch_slot_: id 0 | task 8836 | processing task, is_child = 0 3.44.758.347 I slot print_timing: id 0 | task 8836 | prompt eval time = 1414.59 ms / 624 tokens ( 2.27 ms per token, 441.12 tokens per second) 3.44.758.352 I slot print_timing: id 0 | task 8836 | eval time = 2479.45 ms / 133 tokens ( 18.78 ms per token, 53.24 tokens per second) 3.44.758.353 I slot print_timing: id 0 | task 8836 | total time = 3894.04 ms / 757 tokens 3.44.758.354 I slot print_timing: id 0 | task 8836 | graphs reused = 8501 3.44.758.354 I slot print_timing: id 0 | task 8836 | graph reallocs = 0 / 0 (same size) / (changed size) 3.44.758.399 I slot release: id 0 | task 8836 | stop processing: n_tokens = 756, truncated = 0 3.44.764.503 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 756, t_last = 352209327500 3.44.777.753 I slot launch_slot_: id 0 | task 8973 | processing task, is_child = 0 3.47.294.614 I slot print_timing: id 0 | task 8973 | prompt eval time = 916.21 ms / 445 tokens ( 2.06 ms per token, 485.70 tokens per second) 3.47.294.619 I slot print_timing: id 0 | task 8973 | eval time = 1600.64 ms / 86 tokens ( 18.83 ms per token, 53.10 tokens per second) 3.47.294.620 I slot print_timing: id 0 | task 8973 | total time = 2516.85 ms / 531 tokens 3.47.294.621 I slot print_timing: id 0 | task 8973 | graphs reused = 8584 3.47.294.621 I slot print_timing: id 0 | task 8973 | graph reallocs = 0 / 0 (same size) / (changed size) 3.47.294.655 I slot release: id 0 | task 8973 | stop processing: n_tokens = 530, truncated = 0 3.47.300.076 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.111 (> 0.100 thold), f_keep = 0.070 3.47.308.803 I slot launch_slot_: id 0 | task 9062 | processing task, is_child = 0 3.49.638.892 I slot print_timing: id 0 | task 9062 | prompt eval time = 793.20 ms / 333 tokens ( 2.38 ms per token, 419.82 tokens per second) 3.49.638.898 I slot print_timing: id 0 | task 9062 | eval time = 1536.88 ms / 83 tokens ( 18.74 ms per token, 53.35 tokens per second) 3.49.638.899 I slot print_timing: id 0 | task 9062 | total time = 2330.08 ms / 416 tokens 3.49.638.900 I slot print_timing: id 0 | task 9062 | graphs reused = 8665 3.49.638.900 I slot print_timing: id 0 | task 9062 | graph reallocs = 0 / 0 (same size) / (changed size) 3.49.638.927 I slot release: id 0 | task 9062 | stop processing: n_tokens = 415, truncated = 0 3.49.644.866 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 415, t_last = 352214208028 3.49.650.383 I slot launch_slot_: id 0 | task 9148 | processing task, is_child = 0 3.53.595.730 I slot print_timing: id 0 | task 9148 | n_gen = 162, tg = 53.40 t/s, tg_3s = 53.73 t/s 3.54.307.587 I slot print_timing: id 0 | task 9148 | prompt eval time = 930.21 ms / 474 tokens ( 1.96 ms per token, 509.56 tokens per second) 3.54.307.593 I slot print_timing: id 0 | task 9148 | eval time = 3726.99 ms / 200 tokens ( 18.73 ms per token, 53.39 tokens per second) 3.54.307.594 I slot print_timing: id 0 | task 9148 | total time = 4657.19 ms / 674 tokens 3.54.307.594 I slot print_timing: id 0 | task 9148 | graphs reused = 8862 3.54.307.595 I slot print_timing: id 0 | task 9148 | graph reallocs = 0 / 0 (same size) / (changed size) 3.54.307.627 I slot release: id 0 | task 9148 | stop processing: n_tokens = 673, truncated = 0 3.54.315.014 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 673, t_last = 352218876728 3.54.328.902 I slot launch_slot_: id 0 | task 9351 | processing task, is_child = 0 3.57.598.702 I slot print_timing: id 0 | task 9351 | prompt eval time = 1409.20 ms / 641 tokens ( 2.20 ms per token, 454.87 tokens per second) 3.57.598.705 I slot print_timing: id 0 | task 9351 | eval time = 1860.59 ms / 100 tokens ( 18.79 ms per token, 53.21 tokens per second) 3.57.598.706 I slot print_timing: id 0 | task 9351 | total time = 3269.79 ms / 741 tokens 3.57.598.707 I slot print_timing: id 0 | task 9351 | graphs reused = 8960 3.57.598.707 I slot print_timing: id 0 | task 9351 | graph reallocs = 0 / 0 (same size) / (changed size) 3.57.598.748 I slot release: id 0 | task 9351 | stop processing: n_tokens = 740, truncated = 0 3.57.604.989 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 740, t_last = 352222167849 3.57.619.350 I slot launch_slot_: id 0 | task 9455 | processing task, is_child = 0 4.00.670.760 I slot print_timing: id 0 | task 9455 | prompt eval time = 906.06 ms / 460 tokens ( 1.97 ms per token, 507.69 tokens per second) 4.00.670.766 I slot print_timing: id 0 | task 9455 | eval time = 2145.34 ms / 116 tokens ( 18.66 ms per token, 53.60 tokens per second) 4.00.670.767 I slot print_timing: id 0 | task 9455 | total time = 3051.40 ms / 576 tokens 4.00.670.768 I slot print_timing: id 0 | task 9455 | graphs reused = 9073 4.00.670.768 I slot print_timing: id 0 | task 9455 | graph reallocs = 0 / 0 (same size) / (changed size) 4.00.670.802 I slot release: id 0 | task 9455 | stop processing: n_tokens = 575, truncated = 0 4.00.677.062 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 575, t_last = 352225239903 4.00.684.287 I slot launch_slot_: id 0 | task 9574 | processing task, is_child = 0 4.04.017.656 I slot print_timing: id 0 | task 9574 | prompt eval time = 892.85 ms / 426 tokens ( 2.10 ms per token, 477.13 tokens per second) 4.04.017.662 I slot print_timing: id 0 | task 9574 | eval time = 2440.51 ms / 132 tokens ( 18.63 ms per token, 53.68 tokens per second) 4.04.017.662 I slot print_timing: id 0 | task 9574 | total time = 3333.36 ms / 558 tokens 4.04.017.662 I slot print_timing: id 0 | task 9574 | graphs reused = 9202 4.04.017.663 I slot print_timing: id 0 | task 9574 | graph reallocs = 0 / 0 (same size) / (changed size) 4.04.017.695 I slot release: id 0 | task 9574 | stop processing: n_tokens = 557, truncated = 0 4.04.021.623 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.117 (> 0.100 thold), f_keep = 0.066 4.04.028.230 I slot launch_slot_: id 0 | task 9709 | processing task, is_child = 0 4.06.645.712 I slot print_timing: id 0 | task 9709 | prompt eval time = 729.05 ms / 317 tokens ( 2.30 ms per token, 434.81 tokens per second) 4.06.645.715 I slot print_timing: id 0 | task 9709 | eval time = 1888.43 ms / 102 tokens ( 18.70 ms per token, 53.48 tokens per second) 4.06.645.716 I slot print_timing: id 0 | task 9709 | total time = 2617.47 ms / 419 tokens 4.06.645.717 I slot print_timing: id 0 | task 9709 | graphs reused = 9302 4.06.645.717 I slot print_timing: id 0 | task 9709 | graph reallocs = 0 / 0 (same size) / (changed size) 4.06.645.742 I slot release: id 0 | task 9709 | stop processing: n_tokens = 418, truncated = 0 4.06.650.956 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.104 (> 0.100 thold), f_keep = 0.089 4.06.653.463 I slot launch_slot_: id 0 | task 9814 | processing task, is_child = 0 4.09.546.769 I slot print_timing: id 0 | task 9814 | prompt eval time = 832.77 ms / 355 tokens ( 2.35 ms per token, 426.29 tokens per second) 4.09.546.772 I slot print_timing: id 0 | task 9814 | eval time = 2060.52 ms / 111 tokens ( 18.73 ms per token, 53.38 tokens per second) 4.09.546.773 I slot print_timing: id 0 | task 9814 | total time = 2893.29 ms / 466 tokens 4.09.546.773 I slot print_timing: id 0 | task 9814 | graphs reused = 9411 4.09.546.774 I slot print_timing: id 0 | task 9814 | graph reallocs = 0 / 0 (same size) / (changed size) 4.09.546.803 I slot release: id 0 | task 9814 | stop processing: n_tokens = 465, truncated = 0 4.09.552.584 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 465, t_last = 352234115904 4.09.559.937 I slot launch_slot_: id 0 | task 9928 | processing task, is_child = 0 4.11.874.787 I slot print_timing: id 0 | task 9928 | prompt eval time = 849.46 ms / 383 tokens ( 2.22 ms per token, 450.88 tokens per second) 4.11.874.796 I slot print_timing: id 0 | task 9928 | eval time = 1465.38 ms / 79 tokens ( 18.79 ms per token, 53.23 tokens per second) 4.11.874.797 I slot print_timing: id 0 | task 9928 | total time = 2314.84 ms / 462 tokens 4.11.874.798 I slot print_timing: id 0 | task 9928 | graphs reused = 9488 4.11.874.798 I slot print_timing: id 0 | task 9928 | graph reallocs = 0 / 0 (same size) / (changed size) 4.11.874.829 I slot release: id 0 | task 9928 | stop processing: n_tokens = 461, truncated = 0 4.11.881.250 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 461, t_last = 352236443931 4.11.890.343 I slot launch_slot_: id 0 | task 10010 | processing task, is_child = 0 4.14.539.645 I slot print_timing: id 0 | task 10010 | prompt eval time = 934.55 ms / 489 tokens ( 1.91 ms per token, 523.25 tokens per second) 4.14.539.651 I slot print_timing: id 0 | task 10010 | eval time = 1714.74 ms / 92 tokens ( 18.84 ms per token, 53.07 tokens per second) 4.14.539.652 I slot print_timing: id 0 | task 10010 | total time = 2649.29 ms / 581 tokens 4.14.539.652 I slot print_timing: id 0 | task 10010 | graphs reused = 9577 4.14.539.653 I slot print_timing: id 0 | task 10010 | graph reallocs = 0 / 0 (same size) / (changed size) 4.14.539.689 I slot release: id 0 | task 10010 | stop processing: n_tokens = 580, truncated = 0 4.14.545.741 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 580, t_last = 352239108791 4.14.559.104 I slot launch_slot_: id 0 | task 10105 | processing task, is_child = 0 4.16.946.639 I slot print_timing: id 0 | task 10105 | prompt eval time = 861.54 ms / 431 tokens ( 2.00 ms per token, 500.27 tokens per second) 4.16.946.642 I slot print_timing: id 0 | task 10105 | eval time = 1525.98 ms / 82 tokens ( 18.84 ms per token, 53.08 tokens per second) 4.16.946.643 I slot print_timing: id 0 | task 10105 | total time = 2387.52 ms / 513 tokens 4.16.946.644 I slot print_timing: id 0 | task 10105 | graphs reused = 9657 4.16.946.644 I slot print_timing: id 0 | task 10105 | graph reallocs = 0 / 0 (same size) / (changed size) 4.16.946.673 I slot release: id 0 | task 10105 | stop processing: n_tokens = 512, truncated = 0 4.16.954.215 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 512, t_last = 352241515774 4.16.964.727 I slot launch_slot_: id 0 | task 10190 | processing task, is_child = 0 4.19.985.384 I slot print_timing: id 0 | task 10190 | prompt eval time = 1385.48 ms / 648 tokens ( 2.14 ms per token, 467.71 tokens per second) 4.19.985.390 I slot print_timing: id 0 | task 10190 | eval time = 1635.16 ms / 88 tokens ( 18.79 ms per token, 53.21 tokens per second) 4.19.985.390 I slot print_timing: id 0 | task 10190 | total time = 3020.64 ms / 736 tokens 4.19.985.391 I slot print_timing: id 0 | task 10190 | graphs reused = 9743 4.19.985.392 I slot print_timing: id 0 | task 10190 | graph reallocs = 0 / 0 (same size) / (changed size) 4.19.985.427 I slot release: id 0 | task 10190 | stop processing: n_tokens = 735, truncated = 0 4.19.991.342 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 735, t_last = 352244554528 4.20.004.669 I slot launch_slot_: id 0 | task 10282 | processing task, is_child = 0 4.22.092.830 I slot print_timing: id 0 | task 10282 | prompt eval time = 886.74 ms / 436 tokens ( 2.03 ms per token, 491.69 tokens per second) 4.22.092.836 I slot print_timing: id 0 | task 10282 | eval time = 1201.41 ms / 65 tokens ( 18.77 ms per token, 53.27 tokens per second) 4.22.092.837 I slot print_timing: id 0 | task 10282 | total time = 2088.15 ms / 501 tokens 4.22.092.838 I slot print_timing: id 0 | task 10282 | graphs reused = 9806 4.22.092.838 I slot print_timing: id 0 | task 10282 | graph reallocs = 0 / 0 (same size) / (changed size) 4.22.092.867 I slot release: id 0 | task 10282 | stop processing: n_tokens = 500, truncated = 0 4.22.099.240 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 500, t_last = 352246661968 4.22.105.917 I slot launch_slot_: id 0 | task 10350 | processing task, is_child = 0 4.24.700.016 I slot print_timing: id 0 | task 10350 | prompt eval time = 933.10 ms / 475 tokens ( 1.96 ms per token, 509.06 tokens per second) 4.24.700.022 I slot print_timing: id 0 | task 10350 | eval time = 1660.99 ms / 89 tokens ( 18.87 ms per token, 52.98 tokens per second) 4.24.700.023 I slot print_timing: id 0 | task 10350 | total time = 2594.09 ms / 564 tokens 4.24.700.023 I slot print_timing: id 0 | task 10350 | graphs reused = 9892 4.24.700.024 I slot print_timing: id 0 | task 10350 | graph reallocs = 0 / 0 (same size) / (changed size) 4.24.700.058 I slot release: id 0 | task 10350 | stop processing: n_tokens = 563, truncated = 0 4.24.706.303 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 563, t_last = 352249269159 4.24.717.346 I slot launch_slot_: id 0 | task 10442 | processing task, is_child = 0 4.28.010.746 I slot print_timing: id 0 | task 10442 | prompt eval time = 884.57 ms / 441 tokens ( 2.01 ms per token, 498.55 tokens per second) 4.28.010.749 I slot print_timing: id 0 | task 10442 | eval time = 2408.82 ms / 129 tokens ( 18.82 ms per token, 53.14 tokens per second) 4.28.010.750 I slot print_timing: id 0 | task 10442 | total time = 3293.38 ms / 570 tokens 4.28.010.750 I slot print_timing: id 0 | task 10442 | graphs reused = 10018 4.28.010.751 I slot print_timing: id 0 | task 10442 | graph reallocs = 0 / 0 (same size) / (changed size) 4.28.010.785 I slot release: id 0 | task 10442 | stop processing: n_tokens = 569, truncated = 0 4.28.017.530 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 569, t_last = 352252579886 4.28.028.161 I slot launch_slot_: id 0 | task 10574 | processing task, is_child = 0 4.31.181.457 I slot print_timing: id 0 | task 10574 | prompt eval time = 1251.36 ms / 569 tokens ( 2.20 ms per token, 454.71 tokens per second) 4.31.181.463 I slot print_timing: id 0 | task 10574 | eval time = 1901.93 ms / 102 tokens ( 18.83 ms per token, 53.10 tokens per second) 4.31.181.463 I slot print_timing: id 0 | task 10574 | total time = 3153.29 ms / 671 tokens 4.31.181.464 I slot print_timing: id 0 | task 10574 | graphs reused = 10118 4.31.181.465 I slot print_timing: id 0 | task 10574 | graph reallocs = 0 / 0 (same size) / (changed size) 4.31.181.498 I slot release: id 0 | task 10574 | stop processing: n_tokens = 670, truncated = 0 4.31.188.997 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 670, t_last = 352255750599 4.31.201.569 I slot launch_slot_: id 0 | task 10680 | processing task, is_child = 0 4.35.626.507 I slot print_timing: id 0 | task 10680 | prompt eval time = 1451.83 ms / 646 tokens ( 2.25 ms per token, 444.96 tokens per second) 4.35.626.513 I slot print_timing: id 0 | task 10680 | eval time = 2973.10 ms / 159 tokens ( 18.82 ms per token, 53.14 tokens per second) 4.35.626.513 I slot print_timing: id 0 | task 10680 | total time = 4424.93 ms / 805 tokens 4.35.626.514 I slot print_timing: id 0 | task 10680 | graphs reused = 10274 4.35.626.514 I slot print_timing: id 0 | task 10680 | graph reallocs = 0 / 0 (same size) / (changed size) 4.35.626.552 I slot release: id 0 | task 10680 | stop processing: n_tokens = 804, truncated = 0 4.35.631.554 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.152 (> 0.100 thold), f_keep = 0.046 4.35.644.533 I slot launch_slot_: id 0 | task 10843 | processing task, is_child = 0 4.38.567.681 I slot print_timing: id 0 | task 10843 | prompt eval time = 688.45 ms / 244 tokens ( 2.82 ms per token, 354.42 tokens per second) 4.38.567.687 I slot print_timing: id 0 | task 10843 | eval time = 2234.69 ms / 120 tokens ( 18.78 ms per token, 53.25 tokens per second) 4.38.567.688 I slot print_timing: id 0 | task 10843 | total time = 2923.14 ms / 364 tokens 4.38.567.688 I slot print_timing: id 0 | task 10843 | graphs reused = 10391 4.38.567.689 I slot print_timing: id 0 | task 10843 | graph reallocs = 0 / 0 (same size) / (changed size) 4.38.567.714 I slot release: id 0 | task 10843 | stop processing: n_tokens = 363, truncated = 0 4.38.572.604 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.141 (> 0.100 thold), f_keep = 0.102 4.38.574.641 I slot launch_slot_: id 0 | task 10966 | processing task, is_child = 0 4.41.897.731 I slot print_timing: id 0 | task 10966 | prompt eval time = 768.47 ms / 263 tokens ( 2.92 ms per token, 342.24 tokens per second) 4.41.897.737 I slot print_timing: id 0 | task 10966 | eval time = 2554.61 ms / 138 tokens ( 18.65 ms per token, 53.63 tokens per second) 4.41.897.738 I slot print_timing: id 0 | task 10966 | total time = 3323.08 ms / 401 tokens 4.41.897.738 I slot print_timing: id 0 | task 10966 | graphs reused = 10527 4.41.897.739 I slot print_timing: id 0 | task 10966 | graph reallocs = 0 / 0 (same size) / (changed size) 4.41.897.761 I slot release: id 0 | task 10966 | stop processing: n_tokens = 400, truncated = 0 4.41.902.609 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.149 (> 0.100 thold), f_keep = 0.093 4.41.907.718 I slot launch_slot_: id 0 | task 11107 | processing task, is_child = 0 4.45.556.314 I slot print_timing: id 0 | task 11107 | prompt eval time = 703.27 ms / 248 tokens ( 2.84 ms per token, 352.64 tokens per second) 4.45.556.320 I slot print_timing: id 0 | task 11107 | eval time = 2945.32 ms / 158 tokens ( 18.76 ms per token, 53.30 tokens per second) 4.45.556.321 I slot print_timing: id 0 | task 11107 | total time = 3648.59 ms / 406 tokens 4.45.556.322 I slot print_timing: id 0 | task 11107 | graphs reused = 10682 4.45.556.323 I slot print_timing: id 0 | task 11107 | graph reallocs = 0 / 0 (same size) / (changed size) 4.45.556.345 I slot release: id 0 | task 11107 | stop processing: n_tokens = 405, truncated = 0 4.45.561.128 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.169 (> 0.100 thold), f_keep = 0.091 4.45.567.189 I slot launch_slot_: id 0 | task 11268 | processing task, is_child = 0 4.48.513.262 I slot print_timing: id 0 | task 11268 | prompt eval time = 651.67 ms / 219 tokens ( 2.98 ms per token, 336.06 tokens per second) 4.48.513.268 I slot print_timing: id 0 | task 11268 | eval time = 2294.39 ms / 124 tokens ( 18.65 ms per token, 53.61 tokens per second) 4.48.513.268 I slot print_timing: id 0 | task 11268 | total time = 2946.06 ms / 343 tokens 4.48.513.269 I slot print_timing: id 0 | task 11268 | graphs reused = 10803 4.48.513.270 I slot print_timing: id 0 | task 11268 | graph reallocs = 0 / 0 (same size) / (changed size) 4.48.513.293 I slot release: id 0 | task 11268 | stop processing: n_tokens = 342, truncated = 0 4.48.518.328 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.128 (> 0.100 thold), f_keep = 0.108 4.48.521.286 I slot launch_slot_: id 0 | task 11395 | processing task, is_child = 0 4.52.200.676 I slot print_timing: id 0 | task 11395 | prompt eval time = 741.69 ms / 288 tokens ( 2.58 ms per token, 388.30 tokens per second) 4.52.200.682 I slot print_timing: id 0 | task 11395 | eval time = 2937.69 ms / 158 tokens ( 18.71 ms per token, 53.44 tokens per second) 4.52.200.682 I slot print_timing: id 0 | task 11395 | total time = 3679.38 ms / 446 tokens 4.52.200.683 I slot print_timing: id 0 | task 11395 | graphs reused = 10959 4.52.200.683 I slot print_timing: id 0 | task 11395 | graph reallocs = 0 / 0 (same size) / (changed size) 4.52.200.706 I slot release: id 0 | task 11395 | stop processing: n_tokens = 445, truncated = 0 4.52.205.886 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.129 (> 0.100 thold), f_keep = 0.083 4.52.214.943 I slot launch_slot_: id 0 | task 11556 | processing task, is_child = 0 4.56.033.836 I slot print_timing: id 0 | task 11556 | n_gen = 162, tg = 53.51 t/s, tg_3s = 53.84 t/s 4.56.726.716 I slot print_timing: id 0 | task 11556 | prompt eval time = 809.99 ms / 286 tokens ( 2.83 ms per token, 353.09 tokens per second) 4.56.726.722 I slot print_timing: id 0 | task 11556 | eval time = 3701.77 ms / 199 tokens ( 18.70 ms per token, 53.49 tokens per second) 4.56.726.723 I slot print_timing: id 0 | task 11556 | total time = 4511.77 ms / 485 tokens 4.56.726.723 I slot print_timing: id 0 | task 11556 | graphs reused = 11156 4.56.726.724 I slot print_timing: id 0 | task 11556 | graph reallocs = 0 / 0 (same size) / (changed size) 4.56.726.746 I slot release: id 0 | task 11556 | stop processing: n_tokens = 484, truncated = 0 4.56.732.120 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.106 (> 0.100 thold), f_keep = 0.081 4.56.739.446 I slot launch_slot_: id 0 | task 11758 | processing task, is_child = 0 5.00.655.888 I slot print_timing: id 0 | task 11758 | n_gen = 161, tg = 53.33 t/s, tg_3s = 53.67 t/s 5.01.913.326 I slot print_timing: id 0 | task 11758 | prompt eval time = 916.39 ms / 368 tokens ( 2.49 ms per token, 401.57 tokens per second) 5.01.913.333 I slot print_timing: id 0 | task 11758 | eval time = 4257.47 ms / 228 tokens ( 18.76 ms per token, 53.32 tokens per second) 5.01.913.333 I slot print_timing: id 0 | task 11758 | total time = 5173.87 ms / 596 tokens 5.01.913.334 I slot print_timing: id 0 | task 11758 | graphs reused = 11381 5.01.913.335 I slot print_timing: id 0 | task 11758 | graph reallocs = 0 / 0 (same size) / (changed size) 5.01.913.366 I slot release: id 0 | task 11758 | stop processing: n_tokens = 595, truncated = 0 5.01.918.083 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.164 (> 0.100 thold), f_keep = 0.062 5.01.918.153 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 56.985 MiB) 5.01.927.544 I slot launch_slot_: id 0 | task 11989 | processing task, is_child = 0 5.05.658.756 I slot print_timing: id 0 | task 11989 | n_gen = 162, tg = 53.66 t/s, tg_3s = 53.99 t/s 5.07.361.735 I slot print_timing: id 0 | task 11989 | prompt eval time = 730.60 ms / 226 tokens ( 3.23 ms per token, 309.33 tokens per second) 5.07.361.740 I slot print_timing: id 0 | task 11989 | eval time = 4703.58 ms / 253 tokens ( 18.66 ms per token, 53.58 tokens per second) 5.07.361.741 I slot print_timing: id 0 | task 11989 | total time = 5434.18 ms / 479 tokens 5.07.361.742 I slot print_timing: id 0 | task 11989 | graphs reused = 11631 5.07.361.742 I slot print_timing: id 0 | task 11989 | graph reallocs = 0 / 0 (same size) / (changed size) 5.07.361.766 I slot release: id 0 | task 11989 | stop processing: n_tokens = 478, truncated = 0 5.07.366.446 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.162 (> 0.100 thold), f_keep = 0.077 5.07.366.509 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 44.678 MiB) 5.07.366.512 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 53.908 MiB) 5.07.372.239 I slot launch_slot_: id 0 | task 12245 | processing task, is_child = 0 5.11.116.655 I slot print_timing: id 0 | task 12245 | n_gen = 162, tg = 53.64 t/s, tg_3s = 53.97 t/s 5.11.209.728 I slot print_timing: id 0 | task 12245 | prompt eval time = 742.80 ms / 229 tokens ( 3.24 ms per token, 308.29 tokens per second) 5.11.209.735 I slot print_timing: id 0 | task 12245 | eval time = 3094.68 ms / 167 tokens ( 18.64 ms per token, 53.64 tokens per second) 5.11.209.735 I slot print_timing: id 0 | task 12245 | total time = 3837.48 ms / 396 tokens 5.11.209.736 I slot print_timing: id 0 | task 12245 | graphs reused = 11795 5.11.209.737 I slot print_timing: id 0 | task 12245 | graph reallocs = 0 / 0 (same size) / (changed size) 5.11.209.758 I slot release: id 0 | task 12245 | stop processing: n_tokens = 395, truncated = 0 5.11.214.772 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.130 (> 0.100 thold), f_keep = 0.094 5.11.214.828 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 64.000 MiB) 5.11.219.775 I slot launch_slot_: id 0 | task 12415 | processing task, is_child = 0 5.15.065.438 I slot print_timing: id 0 | task 12415 | n_gen = 162, tg = 53.50 t/s, tg_3s = 53.84 t/s 5.15.140.245 I slot print_timing: id 0 | task 12415 | prompt eval time = 836.57 ms / 285 tokens ( 2.94 ms per token, 340.68 tokens per second) 5.15.140.248 I slot print_timing: id 0 | task 12415 | eval time = 3083.88 ms / 166 tokens ( 18.69 ms per token, 53.50 tokens per second) 5.15.140.249 I slot print_timing: id 0 | task 12415 | total time = 3920.45 ms / 451 tokens 5.15.140.249 I slot print_timing: id 0 | task 12415 | graphs reused = 11959 5.15.140.250 I slot print_timing: id 0 | task 12415 | graph reallocs = 0 / 0 (same size) / (changed size) 5.15.140.275 I slot release: id 0 | task 12415 | stop processing: n_tokens = 450, truncated = 0 5.15.145.298 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.110 (> 0.100 thold), f_keep = 0.082 5.15.145.360 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 61.662 MiB) 5.15.150.971 I slot launch_slot_: id 0 | task 12584 | processing task, is_child = 0 5.18.183.848 I slot print_timing: id 0 | task 12584 | prompt eval time = 953.29 ms / 337 tokens ( 2.83 ms per token, 353.51 tokens per second) 5.18.183.854 I slot print_timing: id 0 | task 12584 | eval time = 2079.58 ms / 111 tokens ( 18.91 ms per token, 52.90 tokens per second) 5.18.183.854 I slot print_timing: id 0 | task 12584 | total time = 3032.87 ms / 448 tokens 5.18.183.855 I slot print_timing: id 0 | task 12584 | graphs reused = 12068 5.18.183.856 I slot print_timing: id 0 | task 12584 | graph reallocs = 0 / 0 (same size) / (changed size) 5.18.183.881 I slot release: id 0 | task 12584 | stop processing: n_tokens = 447, truncated = 0 5.18.188.730 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.179 (> 0.100 thold), f_keep = 0.116 5.18.188.792 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 57.696 MiB) 5.18.194.484 I slot launch_slot_: id 0 | task 12698 | processing task, is_child = 0 5.22.015.271 I slot print_timing: id 0 | task 12698 | prompt eval time = 867.75 ms / 290 tokens ( 2.99 ms per token, 334.20 tokens per second) 5.22.015.277 I slot print_timing: id 0 | task 12698 | eval time = 2953.03 ms / 159 tokens ( 18.69 ms per token, 53.50 tokens per second) 5.22.015.278 I slot print_timing: id 0 | task 12698 | total time = 3820.78 ms / 449 tokens 5.22.015.278 I slot print_timing: id 0 | task 12698 | graphs reused = 12225 5.22.015.279 I slot print_timing: id 0 | task 12698 | graph reallocs = 0 / 0 (same size) / (changed size) 5.22.015.301 I slot release: id 0 | task 12698 | stop processing: n_tokens = 448, truncated = 0 5.22.020.398 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.128 (> 0.100 thold), f_keep = 0.083 5.22.020.459 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.017 MiB) 5.22.020.466 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 84.745 MiB) 5.22.022.777 I slot launch_slot_: id 0 | task 12860 | processing task, is_child = 0 5.25.867.626 I slot print_timing: id 0 | task 12860 | n_gen = 162, tg = 53.55 t/s, tg_3s = 53.88 t/s 5.26.504.373 I slot print_timing: id 0 | task 12860 | prompt eval time = 838.32 ms / 290 tokens ( 2.89 ms per token, 345.93 tokens per second) 5.26.504.379 I slot print_timing: id 0 | task 12860 | eval time = 3643.27 ms / 196 tokens ( 18.68 ms per token, 53.52 tokens per second) 5.26.504.380 I slot print_timing: id 0 | task 12860 | total time = 4481.59 ms / 486 tokens 5.26.504.380 I slot print_timing: id 0 | task 12860 | graphs reused = 12419 5.26.504.381 I slot print_timing: id 0 | task 12860 | graph reallocs = 0 / 0 (same size) / (changed size) 5.26.504.407 I slot release: id 0 | task 12860 | stop processing: n_tokens = 485, truncated = 0 5.26.509.621 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.124 (> 0.100 thold), f_keep = 0.076 5.26.509.696 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 50.695 MiB) 5.26.515.768 I slot launch_slot_: id 0 | task 13059 | processing task, is_child = 0 5.30.386.759 I slot print_timing: id 0 | task 13059 | n_gen = 162, tg = 53.46 t/s, tg_3s = 53.79 t/s 5.31.155.225 I slot print_timing: id 0 | task 13059 | prompt eval time = 859.42 ms / 299 tokens ( 2.87 ms per token, 347.91 tokens per second) 5.31.155.228 I slot print_timing: id 0 | task 13059 | eval time = 3780.02 ms / 203 tokens ( 18.71 ms per token, 53.44 tokens per second) 5.31.155.229 I slot print_timing: id 0 | task 13059 | total time = 4639.44 ms / 502 tokens 5.31.155.229 I slot print_timing: id 0 | task 13059 | graphs reused = 12620 5.31.155.230 I slot print_timing: id 0 | task 13059 | graph reallocs = 0 / 0 (same size) / (changed size) 5.31.155.256 I slot release: id 0 | task 13059 | stop processing: n_tokens = 501, truncated = 0 5.31.159.842 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.154 (> 0.100 thold), f_keep = 0.074 5.31.159.907 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 56.657 MiB) 5.31.166.144 I slot launch_slot_: id 0 | task 13265 | processing task, is_child = 0 5.34.316.007 I slot print_timing: id 0 | task 13265 | prompt eval time = 742.32 ms / 241 tokens ( 3.08 ms per token, 324.66 tokens per second) 5.34.316.010 I slot print_timing: id 0 | task 13265 | eval time = 2407.53 ms / 130 tokens ( 18.66 ms per token, 53.58 tokens per second) 5.34.316.011 I slot print_timing: id 0 | task 13265 | total time = 3149.85 ms / 371 tokens 5.34.316.011 I slot print_timing: id 0 | task 13265 | graphs reused = 12747 5.34.316.012 I slot print_timing: id 0 | task 13265 | graph reallocs = 0 / 0 (same size) / (changed size) 5.34.316.033 I slot release: id 0 | task 13265 | stop processing: n_tokens = 370, truncated = 0 5.34.321.191 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.115 (> 0.100 thold), f_keep = 0.100 5.34.321.260 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 62.182 MiB) 5.34.326.027 I slot launch_slot_: id 0 | task 13398 | processing task, is_child = 0 5.37.678.760 I slot print_timing: id 0 | task 13398 | prompt eval time = 902.38 ms / 323 tokens ( 2.79 ms per token, 357.94 tokens per second) 5.37.678.763 I slot print_timing: id 0 | task 13398 | eval time = 2450.34 ms / 132 tokens ( 18.70 ms per token, 53.46 tokens per second) 5.37.678.763 I slot print_timing: id 0 | task 13398 | total time = 3352.72 ms / 455 tokens 5.37.678.764 I slot print_timing: id 0 | task 13398 | graphs reused = 12877 5.37.678.765 I slot print_timing: id 0 | task 13398 | graph reallocs = 0 / 0 (same size) / (changed size) 5.37.678.792 I slot release: id 0 | task 13398 | stop processing: n_tokens = 454, truncated = 0 5.37.683.296 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.081 5.37.683.358 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 68.267 MiB) 5.37.689.321 I slot launch_slot_: id 0 | task 13533 | processing task, is_child = 0 5.41.448.698 I slot print_timing: id 0 | task 13533 | n_gen = 162, tg = 53.63 t/s, tg_3s = 53.97 t/s 5.44.463.158 I slot print_timing: id 0 | task 13533 | n_gen = 323, tg = 53.52 t/s, tg_3s = 53.41 t/s 5.47.468.619 I slot print_timing: id 0 | task 13533 | n_gen = 485, tg = 53.65 t/s, tg_3s = 53.90 t/s 5.50.485.531 I slot print_timing: id 0 | task 13533 | n_gen = 646, tg = 53.58 t/s, tg_3s = 53.37 t/s 5.53.496.247 I slot print_timing: id 0 | task 13533 | n_gen = 805, tg = 53.42 t/s, tg_3s = 52.81 t/s 5.56.510.986 I slot print_timing: id 0 | task 13533 | n_gen = 964, tg = 53.31 t/s, tg_3s = 52.74 t/s 5.57.559.455 I slot print_timing: id 0 | task 13533 | prompt eval time = 757.46 ms / 237 tokens ( 3.20 ms per token, 312.89 tokens per second) 5.57.559.465 I slot print_timing: id 0 | task 13533 | eval time = 19112.66 ms / 1019 tokens ( 18.77 ms per token, 53.26 tokens per second) 5.57.559.465 I slot print_timing: id 0 | task 13533 | total time = 19870.12 ms / 1256 tokens 5.57.559.466 I slot print_timing: id 0 | task 13533 | graphs reused = 13890 5.57.559.467 I slot print_timing: id 0 | task 13533 | graph reallocs = 0 / 0 (same size) / (changed size) 5.57.559.488 I slot release: id 0 | task 13533 | stop processing: n_tokens = 1255, truncated = 0 5.57.564.473 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.029 5.57.564.578 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 59.488 MiB) 5.57.564.582 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 60.240 MiB) 5.57.573.002 I slot launch_slot_: id 0 | task 14555 | processing task, is_child = 0 6.01.214.998 I slot print_timing: id 0 | task 14555 | n_gen = 162, tg = 53.64 t/s, tg_3s = 53.97 t/s 6.01.307.622 I slot print_timing: id 0 | task 14555 | prompt eval time = 640.29 ms / 217 tokens ( 2.95 ms per token, 338.91 tokens per second) 6.01.307.629 I slot print_timing: id 0 | task 14555 | eval time = 3094.33 ms / 167 tokens ( 18.64 ms per token, 53.65 tokens per second) 6.01.307.629 I slot print_timing: id 0 | task 14555 | total time = 3734.61 ms / 384 tokens 6.01.307.630 I slot print_timing: id 0 | task 14555 | graphs reused = 14054 6.01.307.631 I slot print_timing: id 0 | task 14555 | graph reallocs = 0 / 0 (same size) / (changed size) 6.01.307.670 I slot release: id 0 | task 14555 | stop processing: n_tokens = 383, truncated = 0 6.01.312.811 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.121 (> 0.100 thold), f_keep = 0.097 6.01.312.868 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 57.737 MiB) 6.01.318.636 I slot launch_slot_: id 0 | task 14725 | processing task, is_child = 0 6.05.203.214 I slot print_timing: id 0 | task 14725 | n_gen = 162, tg = 53.48 t/s, tg_3s = 53.81 t/s 6.05.464.935 I slot print_timing: id 0 | task 14725 | prompt eval time = 874.08 ms / 306 tokens ( 2.86 ms per token, 350.08 tokens per second) 6.05.464.941 I slot print_timing: id 0 | task 14725 | eval time = 3272.21 ms / 176 tokens ( 18.70 ms per token, 53.48 tokens per second) 6.05.464.942 I slot print_timing: id 0 | task 14725 | total time = 4146.29 ms / 482 tokens 6.05.464.942 I slot print_timing: id 0 | task 14725 | graphs reused = 14228 6.05.464.943 I slot print_timing: id 0 | task 14725 | graph reallocs = 0 / 0 (same size) / (changed size) 6.05.464.967 I slot release: id 0 | task 14725 | stop processing: n_tokens = 481, truncated = 0 6.05.469.993 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.149 (> 0.100 thold), f_keep = 0.077 6.05.470.062 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 54.086 MiB) 6.05.470.069 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 56.411 MiB) 6.05.476.325 I slot launch_slot_: id 0 | task 14904 | processing task, is_child = 0 6.09.188.053 I slot print_timing: id 0 | task 14904 | prompt eval time = 779.44 ms / 248 tokens ( 3.14 ms per token, 318.18 tokens per second) 6.09.188.059 I slot print_timing: id 0 | task 14904 | eval time = 2932.27 ms / 158 tokens ( 18.68 ms per token, 53.54 tokens per second) 6.09.188.059 I slot print_timing: id 0 | task 14904 | total time = 3711.71 ms / 406 tokens 6.09.188.060 I slot print_timing: id 0 | task 14904 | graphs reused = 14383 6.09.188.061 I slot print_timing: id 0 | task 14904 | graph reallocs = 0 / 0 (same size) / (changed size) 6.09.188.082 I slot release: id 0 | task 14904 | stop processing: n_tokens = 405, truncated = 0 6.09.193.181 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.115 (> 0.100 thold), f_keep = 0.091 6.09.193.237 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 52.678 MiB) 6.09.198.378 I slot launch_slot_: id 0 | task 15065 | processing task, is_child = 0 6.13.096.929 I slot print_timing: id 0 | task 15065 | n_gen = 162, tg = 53.48 t/s, tg_3s = 53.81 t/s 6.14.113.429 I slot print_timing: id 0 | task 15065 | prompt eval time = 887.81 ms / 322 tokens ( 2.76 ms per token, 362.69 tokens per second) 6.14.113.435 I slot print_timing: id 0 | task 15065 | eval time = 4027.23 ms / 216 tokens ( 18.73 ms per token, 53.39 tokens per second) 6.14.113.436 I slot print_timing: id 0 | task 15065 | total time = 4915.04 ms / 538 tokens 6.14.113.437 I slot print_timing: id 0 | task 15065 | graphs reused = 14596 6.14.113.437 I slot print_timing: id 0 | task 15065 | graph reallocs = 0 / 0 (same size) / (changed size) 6.14.113.463 I slot release: id 0 | task 15065 | stop processing: n_tokens = 537, truncated = 0 6.14.118.276 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.137 (> 0.100 thold), f_keep = 0.071 6.14.118.344 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 51.502 MiB) 6.14.125.136 I slot launch_slot_: id 0 | task 15284 | processing task, is_child = 0 6.17.909.421 I slot print_timing: id 0 | task 15284 | prompt eval time = 854.22 ms / 278 tokens ( 3.07 ms per token, 325.44 tokens per second) 6.17.909.427 I slot print_timing: id 0 | task 15284 | eval time = 2930.05 ms / 158 tokens ( 18.66 ms per token, 53.58 tokens per second) 6.17.909.429 I slot print_timing: id 0 | task 15284 | total time = 3784.28 ms / 436 tokens 6.17.909.429 I slot print_timing: id 0 | task 15284 | graphs reused = 14752 6.17.909.430 I slot print_timing: id 0 | task 15284 | graph reallocs = 0 / 0 (same size) / (changed size) 6.17.909.452 I slot release: id 0 | task 15284 | stop processing: n_tokens = 435, truncated = 0 6.17.914.507 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.109 (> 0.100 thold), f_keep = 0.085 6.17.914.568 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 59.652 MiB) 6.17.914.572 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 58.790 MiB) 6.17.920.033 I slot launch_slot_: id 0 | task 15445 | processing task, is_child = 0 6.21.821.674 I slot print_timing: id 0 | task 15445 | n_gen = 162, tg = 53.46 t/s, tg_3s = 53.79 t/s 6.22.930.821 I slot print_timing: id 0 | task 15445 | prompt eval time = 889.95 ms / 338 tokens ( 2.63 ms per token, 379.80 tokens per second) 6.22.930.824 I slot print_timing: id 0 | task 15445 | eval time = 4120.83 ms / 221 tokens ( 18.73 ms per token, 53.39 tokens per second) 6.22.930.825 I slot print_timing: id 0 | task 15445 | total time = 5010.78 ms / 559 tokens 6.22.930.825 I slot print_timing: id 0 | task 15445 | graphs reused = 14970 6.22.930.826 I slot print_timing: id 0 | task 15445 | graph reallocs = 0 / 0 (same size) / (changed size) 6.22.930.853 I slot release: id 0 | task 15445 | stop processing: n_tokens = 558, truncated = 0 6.22.936.087 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.109 (> 0.100 thold), f_keep = 0.066 6.22.936.165 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 66.721 MiB) 6.22.943.394 I slot launch_slot_: id 0 | task 15669 | processing task, is_child = 0 6.26.454.173 I slot print_timing: id 0 | task 15669 | prompt eval time = 948.92 ms / 338 tokens ( 2.81 ms per token, 356.19 tokens per second) 6.26.454.181 I slot print_timing: id 0 | task 15669 | eval time = 2561.84 ms / 138 tokens ( 18.70 ms per token, 53.48 tokens per second) 6.26.454.182 I slot print_timing: id 0 | task 15669 | total time = 3510.77 ms / 476 tokens 6.26.454.182 I slot print_timing: id 0 | task 15669 | graphs reused = 15106 6.26.454.183 I slot print_timing: id 0 | task 15669 | graph reallocs = 0 / 0 (same size) / (changed size) 6.26.454.213 I slot release: id 0 | task 15669 | stop processing: n_tokens = 475, truncated = 0 6.26.459.405 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.111 (> 0.100 thold), f_keep = 0.078 6.26.459.467 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 67.064 MiB) 6.26.465.864 I slot launch_slot_: id 0 | task 15810 | processing task, is_child = 0 6.30.398.939 I slot print_timing: id 0 | task 15810 | n_gen = 162, tg = 53.41 t/s, tg_3s = 53.74 t/s 6.31.321.807 I slot print_timing: id 0 | task 15810 | prompt eval time = 918.40 ms / 333 tokens ( 2.76 ms per token, 362.59 tokens per second) 6.31.321.813 I slot print_timing: id 0 | task 15810 | eval time = 3937.53 ms / 211 tokens ( 18.75 ms per token, 53.33 tokens per second) 6.31.321.813 I slot print_timing: id 0 | task 15810 | total time = 4855.93 ms / 544 tokens 6.31.321.814 I slot print_timing: id 0 | task 15810 | graphs reused = 15314 6.31.321.815 I slot print_timing: id 0 | task 15810 | graph reallocs = 0 / 0 (same size) / (changed size) 6.31.321.842 I slot release: id 0 | task 15810 | stop processing: n_tokens = 543, truncated = 0 6.31.327.074 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.129 (> 0.100 thold), f_keep = 0.068 6.31.327.141 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 71.399 MiB) 6.31.327.146 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.865 MiB) 6.31.334.363 I slot launch_slot_: id 0 | task 16024 | processing task, is_child = 0 6.35.035.509 I slot print_timing: id 0 | task 16024 | prompt eval time = 863.75 ms / 287 tokens ( 3.01 ms per token, 332.27 tokens per second) 6.35.035.515 I slot print_timing: id 0 | task 16024 | eval time = 2837.39 ms / 153 tokens ( 18.67 ms per token, 53.57 tokens per second) 6.35.035.516 I slot print_timing: id 0 | task 16024 | total time = 3701.14 ms / 440 tokens 6.35.035.516 I slot print_timing: id 0 | task 16024 | graphs reused = 15465 6.35.035.517 I slot print_timing: id 0 | task 16024 | graph reallocs = 0 / 0 (same size) / (changed size) 6.35.035.539 I slot release: id 0 | task 16024 | stop processing: n_tokens = 439, truncated = 0 6.35.040.307 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.162 (> 0.100 thold), f_keep = 0.084 6.35.040.365 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 60.527 MiB) 6.35.046.373 I slot launch_slot_: id 0 | task 16180 | processing task, is_child = 0 6.38.005.602 I slot print_timing: id 0 | task 16180 | prompt eval time = 683.19 ms / 229 tokens ( 2.98 ms per token, 335.19 tokens per second) 6.38.005.607 I slot print_timing: id 0 | task 16180 | eval time = 2276.03 ms / 123 tokens ( 18.66 ms per token, 53.60 tokens per second) 6.38.005.608 I slot print_timing: id 0 | task 16180 | total time = 2959.22 ms / 352 tokens 6.38.005.609 I slot print_timing: id 0 | task 16180 | graphs reused = 15585 6.38.005.609 I slot print_timing: id 0 | task 16180 | graph reallocs = 0 / 0 (same size) / (changed size) 6.38.005.629 I slot release: id 0 | task 16180 | stop processing: n_tokens = 351, truncated = 0 6.38.010.436 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.117 (> 0.100 thold), f_keep = 0.105 6.38.010.489 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 56.931 MiB) 6.38.012.702 I slot launch_slot_: id 0 | task 16306 | processing task, is_child = 0 6.40.564.123 I slot print_timing: id 0 | task 16306 | prompt eval time = 889.40 ms / 315 tokens ( 2.82 ms per token, 354.17 tokens per second) 6.40.564.129 I slot print_timing: id 0 | task 16306 | eval time = 1662.01 ms / 90 tokens ( 18.67 ms per token, 53.55 tokens per second) 6.40.564.129 I slot print_timing: id 0 | task 16306 | total time = 2551.41 ms / 405 tokens 6.40.564.130 I slot print_timing: id 0 | task 16306 | graphs reused = 15673 6.40.564.131 I slot print_timing: id 0 | task 16306 | graph reallocs = 0 / 0 (same size) / (changed size) 6.40.564.155 I slot release: id 0 | task 16306 | stop processing: n_tokens = 404, truncated = 0 6.40.568.769 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.183 (> 0.100 thold), f_keep = 0.092 6.40.568.825 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 58.448 MiB) 6.40.571.035 I slot launch_slot_: id 0 | task 16399 | processing task, is_child = 0 6.43.204.383 I slot print_timing: id 0 | task 16399 | prompt eval time = 644.73 ms / 202 tokens ( 3.19 ms per token, 313.31 tokens per second) 6.43.204.389 I slot print_timing: id 0 | task 16399 | eval time = 1988.61 ms / 108 tokens ( 18.59 ms per token, 53.81 tokens per second) 6.43.204.390 I slot print_timing: id 0 | task 16399 | total time = 2633.34 ms / 310 tokens 6.43.204.391 I slot print_timing: id 0 | task 16399 | graphs reused = 15778 6.43.204.392 I slot print_timing: id 0 | task 16399 | graph reallocs = 0 / 0 (same size) / (changed size) 6.43.204.411 I slot release: id 0 | task 16399 | stop processing: n_tokens = 309, truncated = 0 6.43.209.176 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.154 (> 0.100 thold), f_keep = 0.120 6.43.209.226 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.163 MiB) 6.43.211.147 I slot launch_slot_: id 0 | task 16510 | processing task, is_child = 0 6.45.731.483 I slot print_timing: id 0 | task 16510 | prompt eval time = 747.87 ms / 240 tokens ( 3.12 ms per token, 320.91 tokens per second) 6.45.731.489 I slot print_timing: id 0 | task 16510 | eval time = 1772.46 ms / 96 tokens ( 18.66 ms per token, 53.60 tokens per second) 6.45.731.491 I slot print_timing: id 0 | task 16510 | total time = 2520.33 ms / 336 tokens 6.45.731.491 I slot print_timing: id 0 | task 16510 | graphs reused = 15871 6.45.731.492 I slot print_timing: id 0 | task 16510 | graph reallocs = 0 / 0 (same size) / (changed size) 6.45.731.512 I slot release: id 0 | task 16510 | stop processing: n_tokens = 335, truncated = 0 6.45.736.546 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.119 (> 0.100 thold), f_keep = 0.110 6.45.736.597 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 62.564 MiB) 6.45.739.182 I slot launch_slot_: id 0 | task 16609 | processing task, is_child = 0 6.49.524.356 I slot print_timing: id 0 | task 16609 | n_gen = 162, tg = 53.48 t/s, tg_3s = 53.81 t/s 6.50.217.426 I slot print_timing: id 0 | task 16609 | prompt eval time = 774.80 ms / 312 tokens ( 2.48 ms per token, 402.68 tokens per second) 6.50.217.431 I slot print_timing: id 0 | task 16609 | eval time = 3703.43 ms / 199 tokens ( 18.70 ms per token, 53.46 tokens per second) 6.50.217.432 I slot print_timing: id 0 | task 16609 | total time = 4478.23 ms / 511 tokens 6.50.217.432 I slot print_timing: id 0 | task 16609 | graphs reused = 16068 6.50.217.433 I slot print_timing: id 0 | task 16609 | graph reallocs = 0 / 0 (same size) / (changed size) 6.50.217.456 I slot release: id 0 | task 16609 | stop processing: n_tokens = 510, truncated = 0 6.50.222.816 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.118 (> 0.100 thold), f_keep = 0.073 6.50.222.887 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 57.737 MiB) 6.50.229.926 I slot launch_slot_: id 0 | task 16811 | processing task, is_child = 0 6.54.000.735 I slot print_timing: id 0 | task 16811 | n_gen = 162, tg = 53.55 t/s, tg_3s = 53.88 t/s 6.56.282.042 I slot print_timing: id 0 | task 16811 | prompt eval time = 763.99 ms / 314 tokens ( 2.43 ms per token, 411.00 tokens per second) 6.56.282.048 I slot print_timing: id 0 | task 16811 | eval time = 5288.11 ms / 283 tokens ( 18.75 ms per token, 53.33 tokens per second) 6.56.282.049 I slot print_timing: id 0 | task 16811 | total time = 6052.10 ms / 597 tokens 6.56.282.050 I slot print_timing: id 0 | task 16811 | graphs reused = 16348 6.56.282.050 I slot print_timing: id 0 | task 16811 | graph reallocs = 0 / 0 (same size) / (changed size) 6.56.282.077 I slot release: id 0 | task 16811 | stop processing: n_tokens = 596, truncated = 0 6.56.287.417 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.109 (> 0.100 thold), f_keep = 0.062 6.56.287.487 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 56.602 MiB) 6.56.287.496 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.778 MiB) 6.56.294.071 I slot launch_slot_: id 0 | task 17097 | processing task, is_child = 0 6.59.692.581 I slot print_timing: id 0 | task 17097 | prompt eval time = 872.51 ms / 339 tokens ( 2.57 ms per token, 388.53 tokens per second) 6.59.692.583 I slot print_timing: id 0 | task 17097 | eval time = 2525.99 ms / 136 tokens ( 18.71 ms per token, 53.44 tokens per second) 6.59.692.584 I slot print_timing: id 0 | task 17097 | total time = 3398.50 ms / 475 tokens 6.59.692.585 I slot print_timing: id 0 | task 17097 | graphs reused = 16482 6.59.692.585 I slot print_timing: id 0 | task 17097 | graph reallocs = 0 / 0 (same size) / (changed size) 6.59.692.610 I slot release: id 0 | task 17097 | stop processing: n_tokens = 474, truncated = 0 6.59.698.083 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.105 (> 0.100 thold), f_keep = 0.078 6.59.698.145 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 64.698 MiB) 6.59.704.169 I slot launch_slot_: id 0 | task 17236 | processing task, is_child = 0 7.02.371.344 I slot print_timing: id 0 | task 17236 | prompt eval time = 888.87 ms / 352 tokens ( 2.53 ms per token, 396.01 tokens per second) 7.02.371.350 I slot print_timing: id 0 | task 17236 | eval time = 1778.29 ms / 96 tokens ( 18.72 ms per token, 53.42 tokens per second) 7.02.371.351 I slot print_timing: id 0 | task 17236 | total time = 2667.17 ms / 448 tokens 7.02.371.351 I slot print_timing: id 0 | task 17236 | graphs reused = 16576 7.02.371.352 I slot print_timing: id 0 | task 17236 | graph reallocs = 0 / 0 (same size) / (changed size) 7.02.371.379 I slot release: id 0 | task 17236 | stop processing: n_tokens = 447, truncated = 0 7.02.376.707 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.113 (> 0.100 thold), f_keep = 0.083 7.02.376.767 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 54.619 MiB) 7.02.376.772 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 83.966 MiB) 7.02.380.189 I slot launch_slot_: id 0 | task 17335 | processing task, is_child = 0 7.05.243.989 I slot print_timing: id 0 | task 17335 | prompt eval time = 862.39 ms / 328 tokens ( 2.63 ms per token, 380.34 tokens per second) 7.05.243.995 I slot print_timing: id 0 | task 17335 | eval time = 2001.40 ms / 108 tokens ( 18.70 ms per token, 53.46 tokens per second) 7.05.243.995 I slot print_timing: id 0 | task 17335 | total time = 2863.79 ms / 436 tokens 7.05.243.996 I slot print_timing: id 0 | task 17335 | graphs reused = 16682 7.05.243.997 I slot print_timing: id 0 | task 17335 | graph reallocs = 0 / 0 (same size) / (changed size) 7.05.244.021 I slot release: id 0 | task 17335 | stop processing: n_tokens = 435, truncated = 0 7.05.249.201 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.127 (> 0.100 thold), f_keep = 0.085 7.05.249.259 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 60.309 MiB) 7.05.254.922 I slot launch_slot_: id 0 | task 17446 | processing task, is_child = 0 7.08.242.242 I slot print_timing: id 0 | task 17446 | prompt eval time = 746.49 ms / 292 tokens ( 2.56 ms per token, 391.17 tokens per second) 7.08.242.248 I slot print_timing: id 0 | task 17446 | eval time = 2240.82 ms / 121 tokens ( 18.67 ms per token, 53.55 tokens per second) 7.08.242.249 I slot print_timing: id 0 | task 17446 | total time = 2987.31 ms / 413 tokens 7.08.242.250 I slot print_timing: id 0 | task 17446 | graphs reused = 16801 7.08.242.250 I slot print_timing: id 0 | task 17446 | graph reallocs = 0 / 0 (same size) / (changed size) 7.08.242.274 I slot release: id 0 | task 17446 | stop processing: n_tokens = 412, truncated = 0 7.08.246.927 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.164 (> 0.100 thold), f_keep = 0.090 7.08.246.984 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 72.944 MiB) 7.08.249.282 I slot launch_slot_: id 0 | task 17570 | processing task, is_child = 0 7.11.925.557 I slot print_timing: id 0 | task 17570 | n_gen = 163, tg = 53.70 t/s, tg_3s = 54.03 t/s 7.13.643.976 I slot print_timing: id 0 | task 17570 | prompt eval time = 659.63 ms / 225 tokens ( 2.93 ms per token, 341.10 tokens per second) 7.13.643.979 I slot print_timing: id 0 | task 17570 | eval time = 4735.05 ms / 255 tokens ( 18.64 ms per token, 53.64 tokens per second) 7.13.643.980 I slot print_timing: id 0 | task 17570 | total time = 5394.68 ms / 480 tokens 7.13.643.981 I slot print_timing: id 0 | task 17570 | graphs reused = 17053 7.13.643.981 I slot print_timing: id 0 | task 17570 | graph reallocs = 0 / 0 (same size) / (changed size) 7.13.644.003 I slot release: id 0 | task 17570 | stop processing: n_tokens = 479, truncated = 0 7.13.649.902 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 479, t_last = 352418213104 7.13.649.975 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 51.761 MiB) 7.13.656.317 I slot launch_slot_: id 0 | task 17828 | processing task, is_child = 0 7.17.647.308 I slot print_timing: id 0 | task 17828 | n_gen = 161, tg = 53.22 t/s, tg_3s = 53.55 t/s 7.17.967.286 I slot print_timing: id 0 | task 17828 | prompt eval time = 984.35 ms / 425 tokens ( 2.32 ms per token, 431.76 tokens per second) 7.17.967.289 I slot print_timing: id 0 | task 17828 | eval time = 3326.61 ms / 178 tokens ( 18.79 ms per token, 53.21 tokens per second) 7.17.967.290 I slot print_timing: id 0 | task 17828 | total time = 4310.96 ms / 603 tokens 7.17.967.291 I slot print_timing: id 0 | task 17828 | graphs reused = 17228 7.17.967.291 I slot print_timing: id 0 | task 17828 | graph reallocs = 0 / 0 (same size) / (changed size) 7.17.967.324 I slot release: id 0 | task 17828 | stop processing: n_tokens = 602, truncated = 0 7.17.974.109 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 602, t_last = 352422536426 7.17.974.179 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 51.543 MiB) 7.17.974.183 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 64.643 MiB) 7.17.981.048 I slot launch_slot_: id 0 | task 18009 | processing task, is_child = 0 7.22.484.571 I slot print_timing: id 0 | task 18009 | n_gen = 162, tg = 53.41 t/s, tg_3s = 53.74 t/s 7.23.219.901 I slot print_timing: id 0 | task 18009 | prompt eval time = 1489.00 ms / 597 tokens ( 2.49 ms per token, 400.94 tokens per second) 7.23.219.907 I slot print_timing: id 0 | task 18009 | eval time = 3749.85 ms / 201 tokens ( 18.75 ms per token, 53.34 tokens per second) 7.23.219.908 I slot print_timing: id 0 | task 18009 | total time = 5238.84 ms / 798 tokens 7.23.219.909 I slot print_timing: id 0 | task 18009 | graphs reused = 17426 7.23.219.909 I slot print_timing: id 0 | task 18009 | graph reallocs = 0 / 0 (same size) / (changed size) 7.23.219.947 I slot release: id 0 | task 18009 | stop processing: n_tokens = 797, truncated = 0 7.23.226.748 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 797, t_last = 352427789048 7.23.226.830 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 96.272 MiB) 7.23.226.834 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 53.361 MiB) 7.23.235.733 I slot launch_slot_: id 0 | task 18214 | processing task, is_child = 0 7.27.506.223 I slot print_timing: id 0 | task 18214 | n_gen = 161, tg = 53.26 t/s, tg_3s = 53.59 t/s 7.28.069.630 I slot print_timing: id 0 | task 18214 | prompt eval time = 1266.28 ms / 547 tokens ( 2.31 ms per token, 431.97 tokens per second) 7.28.069.636 I slot print_timing: id 0 | task 18214 | eval time = 3567.61 ms / 191 tokens ( 18.78 ms per token, 53.26 tokens per second) 7.28.069.637 I slot print_timing: id 0 | task 18214 | total time = 4833.89 ms / 738 tokens 7.28.069.638 I slot print_timing: id 0 | task 18214 | graphs reused = 17615 7.28.069.638 I slot print_timing: id 0 | task 18214 | graph reallocs = 0 / 0 (same size) / (changed size) 7.28.069.673 I slot release: id 0 | task 18214 | stop processing: n_tokens = 737, truncated = 0 7.28.075.728 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 737, t_last = 352432638774 7.28.075.806 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 59.323 MiB) 7.28.076.085 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 71.562 MiB) 7.28.083.200 I slot launch_slot_: id 0 | task 18409 | processing task, is_child = 0 7.32.104.285 I slot print_timing: id 0 | task 18409 | n_gen = 161, tg = 53.21 t/s, tg_3s = 53.54 t/s 7.33.171.363 I slot print_timing: id 0 | task 18409 | prompt eval time = 1014.23 ms / 414 tokens ( 2.45 ms per token, 408.19 tokens per second) 7.33.171.368 I slot print_timing: id 0 | task 18409 | eval time = 4073.92 ms / 218 tokens ( 18.77 ms per token, 53.27 tokens per second) 7.33.171.369 I slot print_timing: id 0 | task 18409 | total time = 5088.15 ms / 632 tokens 7.33.171.370 I slot print_timing: id 0 | task 18409 | graphs reused = 17830 7.33.171.370 I slot print_timing: id 0 | task 18409 | graph reallocs = 0 / 0 (same size) / (changed size) 7.33.171.404 I slot release: id 0 | task 18409 | stop processing: n_tokens = 661, truncated = 0 7.33.177.158 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.100 (> 0.100 thold), f_keep = 0.056 7.33.177.231 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.497 MiB) 7.33.184.793 I slot launch_slot_: id 0 | task 18630 | processing task, is_child = 0 7.37.061.394 I slot print_timing: id 0 | task 18630 | n_gen = 161, tg = 53.29 t/s, tg_3s = 53.62 t/s 7.37.773.163 I slot print_timing: id 0 | task 18630 | prompt eval time = 874.23 ms / 340 tokens ( 2.57 ms per token, 388.91 tokens per second) 7.37.773.170 I slot print_timing: id 0 | task 18630 | eval time = 3714.13 ms / 199 tokens ( 18.76 ms per token, 53.31 tokens per second) 7.37.773.171 I slot print_timing: id 0 | task 18630 | total time = 4588.36 ms / 539 tokens 7.37.773.171 I slot print_timing: id 0 | task 18630 | graphs reused = 18026 7.37.773.172 I slot print_timing: id 0 | task 18630 | graph reallocs = 0 / 0 (same size) / (changed size) 7.37.773.198 I slot release: id 0 | task 18630 | stop processing: n_tokens = 567, truncated = 0 7.37.780.277 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 567, t_last = 352442342299 7.37.780.346 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 52.760 MiB) 7.37.780.487 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 58.366 MiB) 7.37.788.498 I slot launch_slot_: id 0 | task 18832 | processing task, is_child = 0 7.42.286.883 I slot print_timing: id 0 | task 18832 | n_gen = 161, tg = 53.19 t/s, tg_3s = 53.52 t/s 7.45.289.163 I slot print_timing: id 0 | task 18832 | n_gen = 320, tg = 53.07 t/s, tg_3s = 52.96 t/s 7.47.789.958 I slot print_timing: id 0 | task 18832 | prompt eval time = 1490.25 ms / 608 tokens ( 2.45 ms per token, 407.98 tokens per second) 7.47.789.961 I slot print_timing: id 0 | task 18832 | eval time = 8511.20 ms / 452 tokens ( 18.87 ms per token, 52.99 tokens per second) 7.47.789.962 I slot print_timing: id 0 | task 18832 | total time = 10001.45 ms / 1060 tokens 7.47.789.963 I slot print_timing: id 0 | task 18832 | graphs reused = 18474 7.47.789.963 I slot print_timing: id 0 | task 18832 | graph reallocs = 0 / 0 (same size) / (changed size) 7.47.789.998 I slot release: id 0 | task 18832 | stop processing: n_tokens = 1087, truncated = 0 7.47.795.621 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1087, t_last = 352452359099 7.47.795.724 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 66.544 MiB) 7.47.795.730 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 56.247 MiB) 7.47.805.151 I slot launch_slot_: id 0 | task 19288 | processing task, is_child = 0 7.51.693.487 I slot print_timing: id 0 | task 19288 | n_gen = 161, tg = 53.23 t/s, tg_3s = 53.57 t/s 7.52.931.969 I slot print_timing: id 0 | task 19288 | prompt eval time = 882.72 ms / 349 tokens ( 2.53 ms per token, 395.37 tokens per second) 7.52.931.972 I slot print_timing: id 0 | task 19288 | eval time = 4244.09 ms / 227 tokens ( 18.78 ms per token, 53.25 tokens per second) 7.52.931.973 I slot print_timing: id 0 | task 19288 | total time = 5126.81 ms / 576 tokens 7.52.931.974 I slot print_timing: id 0 | task 19288 | graphs reused = 18698 7.52.931.974 I slot print_timing: id 0 | task 19288 | graph reallocs = 0 / 0 (same size) / (changed size) 7.52.932.002 I slot release: id 0 | task 19288 | stop processing: n_tokens = 603, truncated = 0 7.52.938.371 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 603, t_last = 352457501103 7.52.938.449 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 67.091 MiB) 7.52.938.708 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 57.204 MiB) 7.52.946.835 I slot launch_slot_: id 0 | task 19518 | processing task, is_child = 0 7.57.036.558 I slot print_timing: id 0 | task 19518 | n_gen = 161, tg = 53.23 t/s, tg_3s = 53.56 t/s 8.00.042.224 I slot print_timing: id 0 | task 19518 | n_gen = 321, tg = 53.23 t/s, tg_3s = 53.23 t/s 8.03.049.425 I slot print_timing: id 0 | task 19518 | n_gen = 480, tg = 53.11 t/s, tg_3s = 52.87 t/s 8.06.057.449 I slot print_timing: id 0 | task 19518 | n_gen = 639, tg = 53.05 t/s, tg_3s = 52.86 t/s 8.09.064.099 I slot print_timing: id 0 | task 19518 | n_gen = 797, tg = 52.95 t/s, tg_3s = 52.55 t/s 8.12.068.042 I slot print_timing: id 0 | task 19518 | n_gen = 955, tg = 52.89 t/s, tg_3s = 52.60 t/s 8.13.385.430 I slot print_timing: id 0 | task 19518 | prompt eval time = 1083.64 ms / 469 tokens ( 2.31 ms per token, 432.80 tokens per second) 8.13.385.433 I slot print_timing: id 0 | task 19518 | eval time = 19354.94 ms / 1024 tokens ( 18.92 ms per token, 52.85 tokens per second) 8.13.385.434 I slot print_timing: id 0 | task 19518 | total time = 20438.58 ms / 1493 tokens 8.13.385.435 I slot print_timing: id 0 | task 19518 | graphs reused = 19716 8.13.385.435 I slot print_timing: id 0 | task 19518 | graph reallocs = 0 / 0 (same size) / (changed size) 8.13.385.473 I slot release: id 0 | task 19518 | stop processing: n_tokens = 1519, truncated = 0 8.13.390.660 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.141 (> 0.100 thold), f_keep = 0.024 8.13.390.776 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 92.827 MiB) 8.13.391.000 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 82.817 MiB) 8.13.401.520 I slot launch_slot_: id 0 | task 20545 | processing task, is_child = 0 8.16.070.154 I slot print_timing: id 0 | task 20545 | prompt eval time = 748.73 ms / 237 tokens ( 3.16 ms per token, 316.54 tokens per second) 8.16.070.160 I slot print_timing: id 0 | task 20545 | eval time = 1919.90 ms / 104 tokens ( 18.64 ms per token, 53.65 tokens per second) 8.16.070.160 I slot print_timing: id 0 | task 20545 | total time = 2668.62 ms / 341 tokens 8.16.070.161 I slot print_timing: id 0 | task 20545 | graphs reused = 19818 8.16.070.162 I slot print_timing: id 0 | task 20545 | graph reallocs = 0 / 0 (same size) / (changed size) 8.16.070.183 I slot release: id 0 | task 20545 | stop processing: n_tokens = 366, truncated = 0 8.16.076.131 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 366, t_last = 352480639285 8.16.076.185 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 56.397 MiB) 8.16.079.208 I slot launch_slot_: id 0 | task 20652 | processing task, is_child = 0 8.20.093.371 I slot print_timing: id 0 | task 20652 | n_gen = 161, tg = 53.16 t/s, tg_3s = 53.49 t/s 8.20.748.816 I slot print_timing: id 0 | task 20652 | prompt eval time = 1004.36 ms / 428 tokens ( 2.35 ms per token, 426.14 tokens per second) 8.20.748.822 I slot print_timing: id 0 | task 20652 | eval time = 3665.24 ms / 196 tokens ( 18.80 ms per token, 53.20 tokens per second) 8.20.748.823 I slot print_timing: id 0 | task 20652 | total time = 4669.60 ms / 624 tokens 8.20.748.823 I slot print_timing: id 0 | task 20652 | graphs reused = 20011 8.20.748.824 I slot print_timing: id 0 | task 20652 | graph reallocs = 0 / 0 (same size) / (changed size) 8.20.748.857 I slot release: id 0 | task 20652 | stop processing: n_tokens = 648, truncated = 0 8.20.755.869 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 648, t_last = 352485317959 8.20.755.955 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 63.166 MiB) 8.20.763.576 I slot launch_slot_: id 0 | task 20851 | processing task, is_child = 0 8.25.007.134 I slot print_timing: id 0 | task 20851 | n_gen = 161, tg = 53.33 t/s, tg_3s = 53.66 t/s 8.28.021.412 I slot print_timing: id 0 | task 20851 | n_gen = 321, tg = 53.20 t/s, tg_3s = 53.08 t/s 8.31.036.236 I slot print_timing: id 0 | task 20851 | n_gen = 480, tg = 53.05 t/s, tg_3s = 52.74 t/s 8.31.433.944 I slot print_timing: id 0 | task 20851 | prompt eval time = 1243.32 ms / 530 tokens ( 2.35 ms per token, 426.28 tokens per second) 8.31.433.950 I slot print_timing: id 0 | task 20851 | eval time = 9427.04 ms / 501 tokens ( 18.85 ms per token, 53.04 tokens per second) 8.31.433.951 I slot print_timing: id 0 | task 20851 | total time = 10670.36 ms / 1031 tokens 8.31.433.952 I slot print_timing: id 0 | task 20851 | graphs reused = 20508 8.31.433.953 I slot print_timing: id 0 | task 20851 | graph reallocs = 0 / 0 (same size) / (changed size) 8.31.433.991 I slot release: id 0 | task 20851 | stop processing: n_tokens = 1054, truncated = 0 8.31.441.068 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1054, t_last = 352496003092 8.31.441.163 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 53.334 MiB) 8.31.441.167 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 69.306 MiB) 8.31.441.189 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 99.349 MiB) 8.31.449.835 I slot launch_slot_: id 0 | task 21356 | processing task, is_child = 0 8.35.875.638 I slot print_timing: id 0 | task 21356 | n_gen = 161, tg = 53.23 t/s, tg_3s = 53.57 t/s 8.38.881.353 I slot print_timing: id 0 | task 21356 | n_gen = 320, tg = 53.07 t/s, tg_3s = 52.90 t/s 8.40.806.977 I slot print_timing: id 0 | task 21356 | prompt eval time = 1420.20 ms / 579 tokens ( 2.45 ms per token, 407.69 tokens per second) 8.40.806.983 I slot print_timing: id 0 | task 21356 | eval time = 7936.93 ms / 421 tokens ( 18.90 ms per token, 52.92 tokens per second) 8.40.806.984 I slot print_timing: id 0 | task 21356 | total time = 9357.13 ms / 1000 tokens 8.40.806.985 I slot print_timing: id 0 | task 21356 | graphs reused = 20925 8.40.806.985 I slot print_timing: id 0 | task 21356 | graph reallocs = 0 / 0 (same size) / (changed size) 8.40.807.021 I slot release: id 0 | task 21356 | stop processing: n_tokens = 1036, truncated = 0 8.40.813.177 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1036, t_last = 352505376122 8.40.813.270 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 109.961 MiB) 8.40.824.599 I slot launch_slot_: id 0 | task 21781 | processing task, is_child = 0 8.44.831.474 I slot print_timing: id 0 | task 21781 | n_gen = 161, tg = 53.24 t/s, tg_3s = 53.57 t/s 8.46.143.730 I slot print_timing: id 0 | task 21781 | prompt eval time = 1001.46 ms / 427 tokens ( 2.35 ms per token, 426.38 tokens per second) 8.46.143.735 I slot print_timing: id 0 | task 21781 | eval time = 4317.66 ms / 230 tokens ( 18.85 ms per token, 53.04 tokens per second) 8.46.143.736 I slot print_timing: id 0 | task 21781 | total time = 5319.12 ms / 657 tokens 8.46.143.736 I slot print_timing: id 0 | task 21781 | graphs reused = 21152 8.46.143.737 I slot print_timing: id 0 | task 21781 | graph reallocs = 0 / 0 (same size) / (changed size) 8.46.143.769 I slot release: id 0 | task 21781 | stop processing: n_tokens = 680, truncated = 0 8.46.149.999 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 680, t_last = 352510712870 8.46.150.073 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 118.111 MiB) 8.46.158.020 I slot launch_slot_: id 0 | task 22014 | processing task, is_child = 0 8.50.271.510 I slot print_timing: id 0 | task 22014 | n_gen = 161, tg = 53.22 t/s, tg_3s = 53.55 t/s 8.53.277.919 I slot print_timing: id 0 | task 22014 | n_gen = 321, tg = 53.22 t/s, tg_3s = 53.22 t/s 8.56.285.103 I slot print_timing: id 0 | task 22014 | n_gen = 480, tg = 53.10 t/s, tg_3s = 52.87 t/s 8.57.007.728 I slot print_timing: id 0 | task 22014 | prompt eval time = 1106.93 ms / 508 tokens ( 2.18 ms per token, 458.93 tokens per second) 8.57.007.733 I slot print_timing: id 0 | task 22014 | eval time = 9742.77 ms / 518 tokens ( 18.84 ms per token, 53.07 tokens per second) 8.57.007.734 I slot print_timing: id 0 | task 22014 | total time = 10849.69 ms / 1026 tokens 8.57.007.735 I slot print_timing: id 0 | task 22014 | graphs reused = 21666 8.57.007.735 I slot print_timing: id 0 | task 22014 | graph reallocs = 0 / 0 (same size) / (changed size) 8.57.007.773 I slot release: id 0 | task 22014 | stop processing: n_tokens = 1048, truncated = 0 8.57.014.281 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1048, t_last = 352521576874 8.57.014.381 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 117.085 MiB) 8.57.023.249 I slot launch_slot_: id 0 | task 22535 | processing task, is_child = 0 9.01.133.775 I slot print_timing: id 0 | task 22535 | n_gen = 161, tg = 53.14 t/s, tg_3s = 53.47 t/s 9.01.658.379 I slot print_timing: id 0 | task 22535 | prompt eval time = 1099.60 ms / 454 tokens ( 2.42 ms per token, 412.88 tokens per second) 9.01.658.385 I slot print_timing: id 0 | task 22535 | eval time = 3535.52 ms / 189 tokens ( 18.81 ms per token, 53.17 tokens per second) 9.01.658.386 I slot print_timing: id 0 | task 22535 | total time = 4635.12 ms / 643 tokens 9.01.658.386 I slot print_timing: id 0 | task 22535 | graphs reused = 21852 9.01.658.387 I slot print_timing: id 0 | task 22535 | graph reallocs = 0 / 0 (same size) / (changed size) 9.01.658.421 I slot release: id 0 | task 22535 | stop processing: n_tokens = 664, truncated = 0 9.01.665.435 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 664, t_last = 352526227522 9.01.665.512 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 81.928 MiB) 9.01.674.565 I slot launch_slot_: id 0 | task 22727 | processing task, is_child = 0 9.06.175.548 I slot print_timing: id 0 | task 22727 | n_gen = 161, tg = 53.21 t/s, tg_3s = 53.54 t/s 9.07.043.477 I slot print_timing: id 0 | task 22727 | prompt eval time = 1493.84 ms / 606 tokens ( 2.47 ms per token, 405.67 tokens per second) 9.07.043.480 I slot print_timing: id 0 | task 22727 | eval time = 3875.06 ms / 207 tokens ( 18.81 ms per token, 53.16 tokens per second) 9.07.043.480 I slot print_timing: id 0 | task 22727 | total time = 5368.90 ms / 813 tokens 9.07.043.481 I slot print_timing: id 0 | task 22727 | graphs reused = 22056 9.07.043.482 I slot print_timing: id 0 | task 22727 | graph reallocs = 0 / 0 (same size) / (changed size) 9.07.043.520 I slot release: id 0 | task 22727 | stop processing: n_tokens = 833, truncated = 0 9.07.051.283 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 833, t_last = 352531612621 9.07.051.371 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 110.631 MiB) 9.07.051.380 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 108.142 MiB) 9.07.060.069 I slot launch_slot_: id 0 | task 22938 | processing task, is_child = 0 9.11.681.536 I slot print_timing: id 0 | task 22938 | n_gen = 161, tg = 53.02 t/s, tg_3s = 53.35 t/s 9.12.949.492 I slot print_timing: id 0 | task 22938 | prompt eval time = 1603.76 ms / 672 tokens ( 2.39 ms per token, 419.02 tokens per second) 9.12.949.498 I slot print_timing: id 0 | task 22938 | eval time = 4285.65 ms / 228 tokens ( 18.88 ms per token, 52.97 tokens per second) 9.12.949.499 I slot print_timing: id 0 | task 22938 | total time = 5889.41 ms / 900 tokens 9.12.949.499 I slot print_timing: id 0 | task 22938 | graphs reused = 22281 9.12.949.500 I slot print_timing: id 0 | task 22938 | graph reallocs = 0 / 0 (same size) / (changed size) 9.12.949.550 I slot release: id 0 | task 22938 | stop processing: n_tokens = 920, truncated = 0 9.12.956.190 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 920, t_last = 352537518652 9.12.956.281 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 91.924 MiB) 9.12.968.080 I slot launch_slot_: id 0 | task 23170 | processing task, is_child = 0 9.17.081.125 I slot print_timing: id 0 | task 23170 | prompt eval time = 1185.11 ms / 517 tokens ( 2.29 ms per token, 436.25 tokens per second) 9.17.081.131 I slot print_timing: id 0 | task 23170 | eval time = 2927.93 ms / 157 tokens ( 18.77 ms per token, 53.28 tokens per second) 9.17.081.131 I slot print_timing: id 0 | task 23170 | total time = 4113.03 ms / 674 tokens 9.17.081.132 I slot print_timing: id 0 | task 23170 | graphs reused = 22436 9.17.081.133 I slot print_timing: id 0 | task 23170 | graph reallocs = 0 / 0 (same size) / (changed size) 9.17.081.164 I slot release: id 0 | task 23170 | stop processing: n_tokens = 673, truncated = 0 9.17.088.007 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 673, t_last = 352541650265 9.17.095.355 I slot launch_slot_: id 0 | task 23331 | processing task, is_child = 0 9.21.565.799 I slot print_timing: id 0 | task 23331 | n_gen = 161, tg = 53.09 t/s, tg_3s = 53.42 t/s 9.21.938.953 I slot print_timing: id 0 | task 23331 | prompt eval time = 1456.84 ms / 578 tokens ( 2.52 ms per token, 396.75 tokens per second) 9.21.938.957 I slot print_timing: id 0 | task 23331 | eval time = 3386.75 ms / 181 tokens ( 18.82 ms per token, 53.15 tokens per second) 9.21.938.957 I slot print_timing: id 0 | task 23331 | total time = 4843.59 ms / 759 tokens 9.21.938.958 I slot print_timing: id 0 | task 23331 | graphs reused = 22615 9.21.938.959 I slot print_timing: id 0 | task 23331 | graph reallocs = 0 / 0 (same size) / (changed size) 9.21.938.995 I slot release: id 0 | task 23331 | stop processing: n_tokens = 759, truncated = 0 9.21.944.607 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 759, t_last = 352546508097 9.21.944.686 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 85.045 MiB) 9.21.952.152 I slot launch_slot_: id 0 | task 23516 | processing task, is_child = 0 9.25.896.872 I slot print_timing: id 0 | task 23516 | n_gen = 161, tg = 53.33 t/s, tg_3s = 53.66 t/s 9.28.913.401 I slot print_timing: id 0 | task 23516 | n_gen = 322, tg = 53.35 t/s, tg_3s = 53.37 t/s 9.29.757.181 I slot print_timing: id 0 | task 23516 | prompt eval time = 944.56 ms / 373 tokens ( 2.53 ms per token, 394.89 tokens per second) 9.29.757.186 I slot print_timing: id 0 | task 23516 | eval time = 6860.46 ms / 367 tokens ( 18.74 ms per token, 53.35 tokens per second) 9.29.757.186 I slot print_timing: id 0 | task 23516 | total time = 7805.02 ms / 740 tokens 9.29.757.187 I slot print_timing: id 0 | task 23516 | graphs reused = 22979 9.29.757.188 I slot print_timing: id 0 | task 23516 | graph reallocs = 0 / 0 (same size) / (changed size) 9.29.757.220 I slot release: id 0 | task 23516 | stop processing: n_tokens = 740, truncated = 0 9.29.763.624 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 740, t_last = 352554326321 9.29.763.705 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.133 MiB) 9.29.773.545 I slot launch_slot_: id 0 | task 23886 | processing task, is_child = 0 9.33.832.677 I slot print_timing: id 0 | task 23886 | n_gen = 161, tg = 53.13 t/s, tg_3s = 53.46 t/s 9.34.583.416 I slot print_timing: id 0 | task 23886 | prompt eval time = 1047.37 ms / 450 tokens ( 2.33 ms per token, 429.65 tokens per second) 9.34.583.422 I slot print_timing: id 0 | task 23886 | eval time = 3762.49 ms / 201 tokens ( 18.81 ms per token, 53.16 tokens per second) 9.34.583.422 I slot print_timing: id 0 | task 23886 | total time = 4809.86 ms / 651 tokens 9.34.583.423 I slot print_timing: id 0 | task 23886 | graphs reused = 23177 9.34.583.424 I slot print_timing: id 0 | task 23886 | graph reallocs = 0 / 0 (same size) / (changed size) 9.34.583.458 I slot release: id 0 | task 23886 | stop processing: n_tokens = 650, truncated = 0 9.34.591.535 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 650, t_last = 352559152559 9.34.591.611 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 99.390 MiB) 9.34.599.293 I slot launch_slot_: id 0 | task 24090 | processing task, is_child = 0 9.39.345.996 I slot print_timing: id 0 | task 24090 | n_gen = 160, tg = 52.83 t/s, tg_3s = 53.16 t/s 9.41.472.099 I slot print_timing: id 0 | task 24090 | prompt eval time = 1736.88 ms / 754 tokens ( 2.30 ms per token, 434.11 tokens per second) 9.41.472.105 I slot print_timing: id 0 | task 24090 | eval time = 5135.92 ms / 272 tokens ( 18.95 ms per token, 52.77 tokens per second) 9.41.472.106 I slot print_timing: id 0 | task 24090 | total time = 6872.80 ms / 1026 tokens 9.41.472.107 I slot print_timing: id 0 | task 24090 | graphs reused = 23445 9.41.472.107 I slot print_timing: id 0 | task 24090 | graph reallocs = 0 / 0 (same size) / (changed size) 9.41.472.149 I slot release: id 0 | task 24090 | stop processing: n_tokens = 1025, truncated = 0 9.41.480.982 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1025, t_last = 352566041250 9.41.481.073 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.593 MiB) 9.41.491.582 I slot launch_slot_: id 0 | task 24366 | processing task, is_child = 0 9.46.176.602 I slot print_timing: id 0 | task 24366 | n_gen = 160, tg = 52.91 t/s, tg_3s = 53.24 t/s 9.47.559.013 I slot print_timing: id 0 | task 24366 | prompt eval time = 1679.94 ms / 721 tokens ( 2.33 ms per token, 429.18 tokens per second) 9.47.559.018 I slot print_timing: id 0 | task 24366 | eval time = 4387.48 ms / 233 tokens ( 18.91 ms per token, 52.88 tokens per second) 9.47.559.019 I slot print_timing: id 0 | task 24366 | total time = 6067.42 ms / 954 tokens 9.47.559.020 I slot print_timing: id 0 | task 24366 | graphs reused = 23675 9.47.559.020 I slot print_timing: id 0 | task 24366 | graph reallocs = 0 / 0 (same size) / (changed size) 9.47.559.060 I slot release: id 0 | task 24366 | stop processing: n_tokens = 953, truncated = 0 9.47.564.359 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.135 (> 0.100 thold), f_keep = 0.039 9.47.564.448 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 100.005 MiB) 9.47.564.452 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 84.266 MiB) 9.47.573.491 I slot launch_slot_: id 0 | task 24603 | processing task, is_child = 0 9.50.513.191 I slot print_timing: id 0 | task 24603 | prompt eval time = 661.48 ms / 274 tokens ( 2.41 ms per token, 414.22 tokens per second) 9.50.513.197 I slot print_timing: id 0 | task 24603 | eval time = 2278.20 ms / 123 tokens ( 18.67 ms per token, 53.55 tokens per second) 9.50.513.198 I slot print_timing: id 0 | task 24603 | total time = 2939.69 ms / 397 tokens 9.50.513.198 I slot print_timing: id 0 | task 24603 | graphs reused = 23796 9.50.513.199 I slot print_timing: id 0 | task 24603 | graph reallocs = 0 / 0 (same size) / (changed size) 9.50.513.222 I slot release: id 0 | task 24603 | stop processing: n_tokens = 396, truncated = 0 9.50.517.786 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.176 (> 0.100 thold), f_keep = 0.096 9.50.517.842 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 78.331 MiB) 9.50.521.246 I slot launch_slot_: id 0 | task 24729 | processing task, is_child = 0 9.54.108.851 I slot print_timing: id 0 | task 24729 | n_gen = 162, tg = 53.65 t/s, tg_3s = 53.98 t/s 9.57.125.971 I slot print_timing: id 0 | task 24729 | n_gen = 323, tg = 53.50 t/s, tg_3s = 53.36 t/s 9.57.389.318 I slot print_timing: id 0 | task 24729 | prompt eval time = 586.48 ms / 216 tokens ( 2.72 ms per token, 368.30 tokens per second) 9.57.389.325 I slot print_timing: id 0 | task 24729 | eval time = 6281.59 ms / 337 tokens ( 18.70 ms per token, 53.49 tokens per second) 9.57.389.326 I slot print_timing: id 0 | task 24729 | total time = 6868.06 ms / 553 tokens 9.57.389.327 I slot print_timing: id 0 | task 24729 | graphs reused = 24129 9.57.389.327 I slot print_timing: id 0 | task 24729 | graph reallocs = 0 / 0 (same size) / (changed size) 9.57.389.351 I slot release: id 0 | task 24729 | stop processing: n_tokens = 552, truncated = 0 9.57.394.078 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.069 9.57.394.149 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 82.242 MiB) 9.57.398.715 I slot launch_slot_: id 0 | task 25069 | processing task, is_child = 0 10.01.093.363 I slot print_timing: id 0 | task 25069 | n_gen = 163, tg = 53.70 t/s, tg_3s = 54.03 t/s 10.01.968.681 I slot print_timing: id 0 | task 25069 | prompt eval time = 677.64 ms / 243 tokens ( 2.79 ms per token, 358.60 tokens per second) 10.01.968.686 I slot print_timing: id 0 | task 25069 | eval time = 3892.32 ms / 210 tokens ( 18.62 ms per token, 53.70 tokens per second) 10.01.968.687 I slot print_timing: id 0 | task 25069 | total time = 4569.95 ms / 453 tokens 10.01.968.688 I slot print_timing: id 0 | task 25069 | graphs reused = 24336 10.01.968.688 I slot print_timing: id 0 | task 25069 | graph reallocs = 0 / 0 (same size) / (changed size) 10.01.968.710 I slot release: id 0 | task 25069 | stop processing: n_tokens = 452, truncated = 0 10.01.973.147 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.195 (> 0.100 thold), f_keep = 0.084 10.01.973.210 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.046 MiB) 10.01.975.624 I slot launch_slot_: id 0 | task 25282 | processing task, is_child = 0 10.05.537.046 I slot print_timing: id 0 | task 25282 | n_gen = 163, tg = 53.87 t/s, tg_3s = 54.20 t/s 10.05.630.634 I slot print_timing: id 0 | task 25282 | prompt eval time = 554.22 ms / 195 tokens ( 2.84 ms per token, 351.85 tokens per second) 10.05.630.639 I slot print_timing: id 0 | task 25282 | eval time = 3100.78 ms / 168 tokens ( 18.57 ms per token, 53.86 tokens per second) 10.05.630.640 I slot print_timing: id 0 | task 25282 | total time = 3655.00 ms / 363 tokens 10.05.630.640 I slot print_timing: id 0 | task 25282 | graphs reused = 24501 10.05.630.641 I slot print_timing: id 0 | task 25282 | graph reallocs = 0 / 0 (same size) / (changed size) 10.05.630.667 I slot release: id 0 | task 25282 | stop processing: n_tokens = 362, truncated = 0 10.05.635.753 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.142 (> 0.100 thold), f_keep = 0.102 10.05.638.153 I slot launch_slot_: id 0 | task 25453 | processing task, is_child = 0 10.08.784.378 I slot print_timing: id 0 | task 25453 | prompt eval time = 715.02 ms / 261 tokens ( 2.74 ms per token, 365.03 tokens per second) 10.08.784.382 I slot print_timing: id 0 | task 25453 | eval time = 2431.20 ms / 131 tokens ( 18.70 ms per token, 53.47 tokens per second) 10.08.784.382 I slot print_timing: id 0 | task 25453 | total time = 3146.22 ms / 392 tokens 10.08.784.383 I slot print_timing: id 0 | task 25453 | graphs reused = 24630 10.08.784.384 I slot print_timing: id 0 | task 25453 | graph reallocs = 0 / 0 (same size) / (changed size) 10.08.784.409 I slot release: id 0 | task 25453 | stop processing: n_tokens = 391, truncated = 0 10.08.788.962 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.095 10.08.789.017 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 112.025 MiB) 10.08.791.994 I slot launch_slot_: id 0 | task 25587 | processing task, is_child = 0 10.10.392.477 I slot print_timing: id 0 | task 25587 | prompt eval time = 543.37 ms / 179 tokens ( 3.04 ms per token, 329.42 tokens per second) 10.10.392.480 I slot print_timing: id 0 | task 25587 | eval time = 1057.10 ms / 58 tokens ( 18.55 ms per token, 53.92 tokens per second) 10.10.392.481 I slot print_timing: id 0 | task 25587 | total time = 1600.47 ms / 237 tokens 10.10.392.481 I slot print_timing: id 0 | task 25587 | graphs reused = 24686 10.10.392.482 I slot print_timing: id 0 | task 25587 | graph reallocs = 0 / 0 (same size) / (changed size) 10.10.392.501 I slot release: id 0 | task 25587 | stop processing: n_tokens = 236, truncated = 0 10.10.397.188 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.168 (> 0.100 thold), f_keep = 0.157 10.10.399.730 I slot launch_slot_: id 0 | task 25648 | processing task, is_child = 0 10.13.721.882 I slot print_timing: id 0 | task 25648 | prompt eval time = 591.60 ms / 220 tokens ( 2.69 ms per token, 371.87 tokens per second) 10.13.721.888 I slot print_timing: id 0 | task 25648 | eval time = 2730.54 ms / 151 tokens ( 18.20 ms per token, 54.93 tokens per second) 10.13.721.888 I slot print_timing: id 0 | task 25648 | total time = 3322.14 ms / 371 tokens 10.13.721.889 I slot print_timing: id 0 | task 25648 | graphs reused = 24834 10.13.721.890 I slot print_timing: id 0 | task 25648 | graph reallocs = 0 / 0 (same size) / (changed size) 10.13.721.914 I slot release: id 0 | task 25648 | stop processing: n_tokens = 370, truncated = 0 10.13.726.614 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.100 10.13.726.690 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 86.290 MiB) 10.13.729.160 I slot launch_slot_: id 0 | task 25802 | processing task, is_child = 0 10.17.347.394 I slot print_timing: id 0 | task 25802 | n_gen = 163, tg = 53.76 t/s, tg_3s = 54.09 t/s 10.18.093.378 I slot print_timing: id 0 | task 25802 | prompt eval time = 604.95 ms / 212 tokens ( 2.85 ms per token, 350.44 tokens per second) 10.18.093.384 I slot print_timing: id 0 | task 25802 | eval time = 3759.26 ms / 203 tokens ( 18.61 ms per token, 53.73 tokens per second) 10.18.093.385 I slot print_timing: id 0 | task 25802 | total time = 4364.21 ms / 415 tokens 10.18.093.385 I slot print_timing: id 0 | task 25802 | graphs reused = 25034 10.18.093.386 I slot print_timing: id 0 | task 25802 | graph reallocs = 0 / 0 (same size) / (changed size) 10.18.093.406 I slot release: id 0 | task 25802 | stop processing: n_tokens = 414, truncated = 0 10.18.097.614 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.245 (> 0.100 thold), f_keep = 0.089 10.18.097.672 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 140.347 MiB) 10.18.100.085 I slot launch_slot_: id 0 | task 26008 | processing task, is_child = 0 10.21.623.557 I slot print_timing: id 0 | task 26008 | n_gen = 163, tg = 53.92 t/s, tg_3s = 54.25 t/s 10.24.641.350 I slot print_timing: id 0 | task 26008 | n_gen = 325, tg = 53.80 t/s, tg_3s = 53.68 t/s 10.27.658.120 I slot print_timing: id 0 | task 26008 | n_gen = 486, tg = 53.66 t/s, tg_3s = 53.37 t/s 10.30.661.194 I slot print_timing: id 0 | task 26008 | n_gen = 646, tg = 53.56 t/s, tg_3s = 53.28 t/s 10.33.666.839 I slot print_timing: id 0 | task 26008 | n_gen = 805, tg = 53.43 t/s, tg_3s = 52.90 t/s 10.36.432.605 I slot print_timing: id 0 | task 26008 | prompt eval time = 519.11 ms / 151 tokens ( 3.44 ms per token, 290.88 tokens per second) 10.36.432.611 I slot print_timing: id 0 | task 26008 | eval time = 17813.39 ms / 951 tokens ( 18.75 ms per token, 53.33 tokens per second) 10.36.432.612 I slot print_timing: id 0 | task 26008 | total time = 18332.51 ms / 1102 tokens 10.36.432.612 I slot print_timing: id 0 | task 26008 | graphs reused = 25979 10.36.432.613 I slot print_timing: id 0 | task 26008 | graph reallocs = 0 / 0 (same size) / (changed size) 10.36.432.636 I slot release: id 0 | task 26008 | stop processing: n_tokens = 1101, truncated = 0 10.36.437.631 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.034 10.36.445.894 I slot launch_slot_: id 0 | task 26962 | processing task, is_child = 0 10.39.262.891 I slot print_timing: id 0 | task 26962 | prompt eval time = 618.32 ms / 217 tokens ( 2.85 ms per token, 350.95 tokens per second) 10.39.262.895 I slot print_timing: id 0 | task 26962 | eval time = 2198.66 ms / 119 tokens ( 18.63 ms per token, 53.67 tokens per second) 10.39.262.896 I slot print_timing: id 0 | task 26962 | total time = 2816.99 ms / 336 tokens 10.39.262.896 I slot print_timing: id 0 | task 26962 | graphs reused = 26095 10.39.262.897 I slot print_timing: id 0 | task 26962 | graph reallocs = 0 / 0 (same size) / (changed size) 10.39.262.917 I slot release: id 0 | task 26962 | stop processing: n_tokens = 335, truncated = 0 10.39.267.379 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.170 (> 0.100 thold), f_keep = 0.110 10.39.267.433 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 80.259 MiB) 10.39.269.464 I slot launch_slot_: id 0 | task 27084 | processing task, is_child = 0 10.42.891.307 I slot print_timing: id 0 | task 27084 | n_gen = 163, tg = 53.72 t/s, tg_3s = 54.05 t/s 10.44.086.767 I slot print_timing: id 0 | task 27084 | prompt eval time = 606.11 ms / 218 tokens ( 2.78 ms per token, 359.67 tokens per second) 10.44.086.771 I slot print_timing: id 0 | task 27084 | eval time = 4211.18 ms / 227 tokens ( 18.63 ms per token, 53.67 tokens per second) 10.44.086.771 I slot print_timing: id 0 | task 27084 | total time = 4817.29 ms / 445 tokens 10.44.086.772 I slot print_timing: id 0 | task 27084 | graphs reused = 26319 10.44.086.772 I slot print_timing: id 0 | task 27084 | graph reallocs = 0 / 0 (same size) / (changed size) 10.44.086.793 I slot release: id 0 | task 27084 | stop processing: n_tokens = 444, truncated = 0 10.44.091.259 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.165 (> 0.100 thold), f_keep = 0.083 10.44.091.319 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 122.624 MiB) 10.44.094.423 I slot launch_slot_: id 0 | task 27314 | processing task, is_child = 0 10.47.514.845 I slot print_timing: id 0 | task 27314 | prompt eval time = 680.48 ms / 224 tokens ( 3.04 ms per token, 329.18 tokens per second) 10.47.514.851 I slot print_timing: id 0 | task 27314 | eval time = 2739.93 ms / 148 tokens ( 18.64 ms per token, 53.65 tokens per second) 10.47.514.852 I slot print_timing: id 0 | task 27314 | total time = 3420.41 ms / 372 tokens 10.47.514.852 I slot print_timing: id 0 | task 27314 | graphs reused = 26464 10.47.514.853 I slot print_timing: id 0 | task 27314 | graph reallocs = 0 / 0 (same size) / (changed size) 10.47.514.874 I slot release: id 0 | task 27314 | stop processing: n_tokens = 371, truncated = 0 10.47.519.725 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.176 (> 0.100 thold), f_keep = 0.100 10.47.523.049 I slot launch_slot_: id 0 | task 27465 | processing task, is_child = 0 10.51.125.858 I slot print_timing: id 0 | task 27465 | n_gen = 163, tg = 53.71 t/s, tg_3s = 54.04 t/s 10.51.163.212 I slot print_timing: id 0 | task 27465 | prompt eval time = 586.63 ms / 210 tokens ( 2.79 ms per token, 357.98 tokens per second) 10.51.163.218 I slot print_timing: id 0 | task 27465 | eval time = 3053.52 ms / 165 tokens ( 18.62 ms per token, 53.71 tokens per second) 10.51.163.219 I slot print_timing: id 0 | task 27465 | total time = 3640.15 ms / 375 tokens 10.51.163.220 I slot print_timing: id 0 | task 27465 | graphs reused = 26626 10.51.163.220 I slot print_timing: id 0 | task 27465 | graph reallocs = 0 / 0 (same size) / (changed size) 10.51.163.240 I slot release: id 0 | task 27465 | stop processing: n_tokens = 374, truncated = 0 10.51.167.798 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.099 10.51.167.852 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 133.291 MiB) 10.51.171.729 I slot launch_slot_: id 0 | task 27633 | processing task, is_child = 0 10.54.774.334 I slot print_timing: id 0 | task 27633 | n_gen = 163, tg = 53.74 t/s, tg_3s = 54.07 t/s 10.54.904.189 I slot print_timing: id 0 | task 27633 | prompt eval time = 587.88 ms / 208 tokens ( 2.83 ms per token, 353.81 tokens per second) 10.54.904.195 I slot print_timing: id 0 | task 27633 | eval time = 3144.57 ms / 170 tokens ( 18.61 ms per token, 53.74 tokens per second) 10.54.904.196 I slot print_timing: id 0 | task 27633 | total time = 3732.45 ms / 378 tokens 10.54.904.196 I slot print_timing: id 0 | task 27633 | graphs reused = 26793 10.54.904.197 I slot print_timing: id 0 | task 27633 | graph reallocs = 0 / 0 (same size) / (changed size) 10.54.904.217 I slot release: id 0 | task 27633 | stop processing: n_tokens = 377, truncated = 0 10.54.908.817 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.166 (> 0.100 thold), f_keep = 0.098 10.54.912.732 I slot launch_slot_: id 0 | task 27806 | processing task, is_child = 0 10.58.516.359 I slot print_timing: id 0 | task 27806 | n_gen = 162, tg = 53.62 t/s, tg_3s = 53.95 t/s 11.01.531.654 I slot print_timing: id 0 | task 27806 | n_gen = 323, tg = 53.51 t/s, tg_3s = 53.39 t/s 11.01.663.039 I slot print_timing: id 0 | task 27806 | prompt eval time = 600.82 ms / 223 tokens ( 2.69 ms per token, 371.16 tokens per second) 11.01.663.044 I slot print_timing: id 0 | task 27806 | eval time = 6149.48 ms / 330 tokens ( 18.69 ms per token, 53.50 tokens per second) 11.01.663.045 I slot print_timing: id 0 | task 27806 | total time = 6750.30 ms / 553 tokens 11.01.663.046 I slot print_timing: id 0 | task 27806 | graphs reused = 27119 11.01.663.046 I slot print_timing: id 0 | task 27806 | graph reallocs = 0 / 0 (same size) / (changed size) 11.01.663.066 I slot release: id 0 | task 27806 | stop processing: n_tokens = 552, truncated = 0 11.01.667.752 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.159 (> 0.100 thold), f_keep = 0.067 11.01.667.820 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 83.008 MiB) 11.01.671.031 I slot launch_slot_: id 0 | task 28139 | processing task, is_child = 0 11.05.303.054 I slot print_timing: id 0 | task 28139 | n_gen = 162, tg = 53.61 t/s, tg_3s = 53.94 t/s 11.08.318.623 I slot print_timing: id 0 | task 28139 | n_gen = 323, tg = 53.50 t/s, tg_3s = 53.39 t/s 11.11.336.089 I slot print_timing: id 0 | task 28139 | n_gen = 484, tg = 53.45 t/s, tg_3s = 53.36 t/s 11.14.353.835 I slot print_timing: id 0 | task 28139 | n_gen = 644, tg = 53.34 t/s, tg_3s = 53.02 t/s 11.17.365.478 I slot print_timing: id 0 | task 28139 | n_gen = 803, tg = 53.23 t/s, tg_3s = 52.80 t/s 11.20.374.230 I slot print_timing: id 0 | task 28139 | n_gen = 962, tg = 53.17 t/s, tg_3s = 52.85 t/s 11.21.552.738 I slot print_timing: id 0 | task 28139 | prompt eval time = 628.79 ms / 232 tokens ( 2.71 ms per token, 368.96 tokens per second) 11.21.552.742 I slot print_timing: id 0 | task 28139 | eval time = 19252.90 ms / 1024 tokens ( 18.82 ms per token, 53.13 tokens per second) 11.21.552.743 I slot print_timing: id 0 | task 28139 | total time = 19881.69 ms / 1256 tokens 11.21.552.743 I slot print_timing: id 0 | task 28139 | graphs reused = 28137 11.21.552.744 I slot print_timing: id 0 | task 28139 | graph reallocs = 0 / 0 (same size) / (changed size) 11.21.552.766 I slot release: id 0 | task 28139 | stop processing: n_tokens = 1255, truncated = 0 11.21.557.584 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.172 (> 0.100 thold), f_keep = 0.029 11.21.557.692 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 116.867 MiB) 11.21.567.650 I slot launch_slot_: id 0 | task 29166 | processing task, is_child = 0 11.25.182.362 I slot print_timing: id 0 | task 29166 | n_gen = 162, tg = 53.64 t/s, tg_3s = 53.98 t/s 11.28.197.656 I slot print_timing: id 0 | task 29166 | n_gen = 323, tg = 53.52 t/s, tg_3s = 53.39 t/s 11.31.212.587 I slot print_timing: id 0 | task 29166 | n_gen = 484, tg = 53.48 t/s, tg_3s = 53.40 t/s 11.32.921.629 I slot print_timing: id 0 | task 29166 | prompt eval time = 613.44 ms / 215 tokens ( 2.85 ms per token, 350.48 tokens per second) 11.32.921.635 I slot print_timing: id 0 | task 29166 | eval time = 10740.52 ms / 575 tokens ( 18.71 ms per token, 53.44 tokens per second) 11.32.921.635 I slot print_timing: id 0 | task 29166 | total time = 11353.96 ms / 790 tokens 11.32.921.636 I slot print_timing: id 0 | task 29166 | graphs reused = 28707 11.32.921.637 I slot print_timing: id 0 | task 29166 | graph reallocs = 0 / 0 (same size) / (changed size) 11.32.921.657 I slot release: id 0 | task 29166 | stop processing: n_tokens = 789, truncated = 0 11.32.926.446 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.164 (> 0.100 thold), f_keep = 0.047 11.32.926.525 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 134.016 MiB) 11.32.930.457 I slot launch_slot_: id 0 | task 29744 | processing task, is_child = 0 11.36.549.699 I slot print_timing: id 0 | task 29744 | n_gen = 162, tg = 53.66 t/s, tg_3s = 53.99 t/s 11.38.850.552 I slot print_timing: id 0 | task 29744 | prompt eval time = 618.60 ms / 226 tokens ( 2.74 ms per token, 365.34 tokens per second) 11.38.850.558 I slot print_timing: id 0 | task 29744 | eval time = 5301.49 ms / 285 tokens ( 18.67 ms per token, 53.57 tokens per second) 11.38.850.559 I slot print_timing: id 0 | task 29744 | total time = 5920.09 ms / 511 tokens 11.38.850.560 I slot print_timing: id 0 | task 29744 | graphs reused = 28989 11.38.850.561 I slot print_timing: id 0 | task 29744 | graph reallocs = 0 / 0 (same size) / (changed size) 11.38.850.586 I slot release: id 0 | task 29744 | stop processing: n_tokens = 510, truncated = 0 11.38.855.157 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.073 11.38.859.413 I slot launch_slot_: id 0 | task 30032 | processing task, is_child = 0 11.42.440.417 I slot print_timing: id 0 | task 30032 | n_gen = 163, tg = 53.80 t/s, tg_3s = 54.13 t/s 11.44.812.954 I slot print_timing: id 0 | task 30032 | prompt eval time = 569.98 ms / 203 tokens ( 2.81 ms per token, 356.16 tokens per second) 11.44.812.960 I slot print_timing: id 0 | task 30032 | eval time = 5383.56 ms / 290 tokens ( 18.63 ms per token, 53.68 tokens per second) 11.44.812.961 I slot print_timing: id 0 | task 30032 | total time = 5953.53 ms / 493 tokens 11.44.812.961 I slot print_timing: id 0 | task 30032 | graphs reused = 29276 11.44.812.962 I slot print_timing: id 0 | task 30032 | graph reallocs = 0 / 0 (same size) / (changed size) 11.44.812.985 I slot release: id 0 | task 30032 | stop processing: n_tokens = 492, truncated = 0 11.44.817.530 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.075 11.44.817.600 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.651 MiB) 11.44.821.744 I slot launch_slot_: id 0 | task 30325 | processing task, is_child = 0 11.46.770.683 I slot print_timing: id 0 | task 30325 | prompt eval time = 543.57 ms / 179 tokens ( 3.04 ms per token, 329.31 tokens per second) 11.46.770.686 I slot print_timing: id 0 | task 30325 | eval time = 1405.36 ms / 77 tokens ( 18.49 ms per token, 54.08 tokens per second) 11.46.770.687 I slot print_timing: id 0 | task 30325 | total time = 1948.93 ms / 256 tokens 11.46.770.688 I slot print_timing: id 0 | task 30325 | graphs reused = 29351 11.46.770.688 I slot print_timing: id 0 | task 30325 | graph reallocs = 0 / 0 (same size) / (changed size) 11.46.770.710 I slot release: id 0 | task 30325 | stop processing: n_tokens = 255, truncated = 0 11.46.775.361 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.165 (> 0.100 thold), f_keep = 0.145 11.46.778.499 I slot launch_slot_: id 0 | task 30405 | processing task, is_child = 0 11.50.416.991 I slot print_timing: id 0 | task 30405 | n_gen = 163, tg = 53.67 t/s, tg_3s = 54.00 t/s 11.51.145.235 I slot print_timing: id 0 | task 30405 | prompt eval time = 619.79 ms / 224 tokens ( 2.77 ms per token, 361.41 tokens per second) 11.51.145.242 I slot print_timing: id 0 | task 30405 | eval time = 3746.94 ms / 202 tokens ( 18.64 ms per token, 53.64 tokens per second) 11.51.145.243 I slot print_timing: id 0 | task 30405 | total time = 4366.73 ms / 426 tokens 11.51.145.243 I slot print_timing: id 0 | task 30405 | graphs reused = 29550 11.51.145.244 I slot print_timing: id 0 | task 30405 | graph reallocs = 0 / 0 (same size) / (changed size) 11.51.145.265 I slot release: id 0 | task 30405 | stop processing: n_tokens = 425, truncated = 0 11.51.150.133 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.163 (> 0.100 thold), f_keep = 0.096 11.51.150.196 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 81.996 MiB) 11.51.153.351 I slot launch_slot_: id 0 | task 30610 | processing task, is_child = 0 11.54.014.762 I slot print_timing: id 0 | task 30610 | prompt eval time = 638.09 ms / 252 tokens ( 2.53 ms per token, 394.93 tokens per second) 11.54.014.768 I slot print_timing: id 0 | task 30610 | eval time = 2223.31 ms / 120 tokens ( 18.68 ms per token, 53.52 tokens per second) 11.54.014.769 I slot print_timing: id 0 | task 30610 | total time = 2861.40 ms / 372 tokens 11.54.014.769 I slot print_timing: id 0 | task 30610 | graphs reused = 29667 11.54.014.770 I slot print_timing: id 0 | task 30610 | graph reallocs = 0 / 0 (same size) / (changed size) 11.54.014.793 I slot release: id 0 | task 30610 | stop processing: n_tokens = 371, truncated = 0 11.54.019.278 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.208 (> 0.100 thold), f_keep = 0.100 11.54.019.333 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 90.666 MiB) 11.54.023.111 I slot launch_slot_: id 0 | task 30733 | processing task, is_child = 0 11.56.828.271 I slot print_timing: id 0 | task 30733 | prompt eval time = 559.25 ms / 178 tokens ( 3.14 ms per token, 318.28 tokens per second) 11.56.828.276 I slot print_timing: id 0 | task 30733 | eval time = 2245.89 ms / 122 tokens ( 18.56 ms per token, 53.88 tokens per second) 11.56.828.277 I slot print_timing: id 0 | task 30733 | total time = 2805.15 ms / 300 tokens 11.56.828.278 I slot print_timing: id 0 | task 30733 | graphs reused = 29786 11.56.828.278 I slot print_timing: id 0 | task 30733 | graph reallocs = 0 / 0 (same size) / (changed size) 11.56.828.297 I slot release: id 0 | task 30733 | stop processing: n_tokens = 299, truncated = 0 11.56.832.844 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.124 11.56.832.897 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 116.442 MiB) 11.56.836.163 I slot launch_slot_: id 0 | task 30858 | processing task, is_child = 0 11.58.758.058 I slot print_timing: id 0 | task 30858 | prompt eval time = 545.84 ms / 186 tokens ( 2.93 ms per token, 340.76 tokens per second) 11.58.758.064 I slot print_timing: id 0 | task 30858 | eval time = 1376.05 ms / 75 tokens ( 18.60 ms per token, 53.78 tokens per second) 11.58.758.064 I slot print_timing: id 0 | task 30858 | total time = 1921.89 ms / 261 tokens 11.58.758.065 I slot print_timing: id 0 | task 30858 | graphs reused = 29858 11.58.758.066 I slot print_timing: id 0 | task 30858 | graph reallocs = 0 / 0 (same size) / (changed size) 11.58.758.085 I slot release: id 0 | task 30858 | stop processing: n_tokens = 260, truncated = 0 11.58.762.457 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.196 (> 0.100 thold), f_keep = 0.142 11.58.765.661 I slot launch_slot_: id 0 | task 30936 | processing task, is_child = 0 12.02.330.579 I slot print_timing: id 0 | task 30936 | n_gen = 163, tg = 53.77 t/s, tg_3s = 54.10 t/s 12.05.338.887 I slot print_timing: id 0 | task 30936 | n_gen = 324, tg = 53.65 t/s, tg_3s = 53.52 t/s 12.08.342.559 I slot print_timing: id 0 | task 30936 | n_gen = 484, tg = 53.52 t/s, tg_3s = 53.27 t/s 12.11.350.720 I slot print_timing: id 0 | task 30936 | n_gen = 644, tg = 53.44 t/s, tg_3s = 53.19 t/s 12.14.358.956 I slot print_timing: id 0 | task 30936 | n_gen = 803, tg = 53.32 t/s, tg_3s = 52.85 t/s 12.14.889.354 I slot print_timing: id 0 | task 30936 | prompt eval time = 552.23 ms / 189 tokens ( 2.92 ms per token, 342.25 tokens per second) 12.14.889.362 I slot print_timing: id 0 | task 30936 | eval time = 15571.45 ms / 831 tokens ( 18.76 ms per token, 53.30 tokens per second) 12.14.889.363 I slot print_timing: id 0 | task 30936 | total time = 16123.68 ms / 1020 tokens 12.14.889.363 I slot print_timing: id 0 | task 30936 | graphs reused = 30684 12.14.889.364 I slot print_timing: id 0 | task 30936 | graph reallocs = 0 / 0 (same size) / (changed size) 12.14.889.387 I slot release: id 0 | task 30936 | stop processing: n_tokens = 1019, truncated = 0 12.14.894.241 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.177 (> 0.100 thold), f_keep = 0.036 12.14.894.349 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.514 MiB) 12.14.903.590 I slot launch_slot_: id 0 | task 31770 | processing task, is_child = 0 12.17.263.734 I slot print_timing: id 0 | task 31770 | prompt eval time = 592.27 ms / 209 tokens ( 2.83 ms per token, 352.88 tokens per second) 12.17.263.741 I slot print_timing: id 0 | task 31770 | eval time = 1767.86 ms / 96 tokens ( 18.61 ms per token, 53.74 tokens per second) 12.17.263.741 I slot print_timing: id 0 | task 31770 | total time = 2360.13 ms / 305 tokens 12.17.263.742 I slot print_timing: id 0 | task 31770 | graphs reused = 30777 12.17.263.742 I slot print_timing: id 0 | task 31770 | graph reallocs = 0 / 0 (same size) / (changed size) 12.17.263.763 I slot release: id 0 | task 31770 | stop processing: n_tokens = 304, truncated = 0 12.17.268.272 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.177 (> 0.100 thold), f_keep = 0.122 12.17.272.455 I slot launch_slot_: id 0 | task 31869 | processing task, is_child = 0 12.19.380.888 I slot print_timing: id 0 | task 31869 | prompt eval time = 598.52 ms / 209 tokens ( 2.86 ms per token, 349.19 tokens per second) 12.19.380.892 I slot print_timing: id 0 | task 31869 | eval time = 1509.90 ms / 82 tokens ( 18.64 ms per token, 53.65 tokens per second) 12.19.380.892 I slot print_timing: id 0 | task 31869 | total time = 2108.42 ms / 291 tokens 12.19.380.893 I slot print_timing: id 0 | task 31869 | graphs reused = 30856 12.19.380.893 I slot print_timing: id 0 | task 31869 | graph reallocs = 0 / 0 (same size) / (changed size) 12.19.380.914 I slot release: id 0 | task 31869 | stop processing: n_tokens = 290, truncated = 0 12.19.385.286 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.128 12.19.385.334 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 134.357 MiB) 12.19.388.461 I slot launch_slot_: id 0 | task 31954 | processing task, is_child = 0 12.22.437.912 I slot print_timing: id 0 | task 31954 | prompt eval time = 593.15 ms / 208 tokens ( 2.85 ms per token, 350.67 tokens per second) 12.22.437.918 I slot print_timing: id 0 | task 31954 | eval time = 2456.29 ms / 133 tokens ( 18.61 ms per token, 53.74 tokens per second) 12.22.437.919 I slot print_timing: id 0 | task 31954 | total time = 3049.44 ms / 341 tokens 12.22.437.920 I slot print_timing: id 0 | task 31954 | graphs reused = 30986 12.22.437.920 I slot print_timing: id 0 | task 31954 | graph reallocs = 0 / 0 (same size) / (changed size) 12.22.437.940 I slot release: id 0 | task 31954 | stop processing: n_tokens = 340, truncated = 0 12.22.442.559 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.180 (> 0.100 thold), f_keep = 0.109 12.22.447.767 I slot launch_slot_: id 0 | task 32090 | processing task, is_child = 0 12.26.048.979 I slot print_timing: id 0 | task 32090 | n_gen = 163, tg = 53.74 t/s, tg_3s = 54.07 t/s 12.29.064.315 I slot print_timing: id 0 | task 32090 | n_gen = 324, tg = 53.56 t/s, tg_3s = 53.39 t/s 12.30.208.956 I slot print_timing: id 0 | task 32090 | prompt eval time = 586.47 ms / 206 tokens ( 2.85 ms per token, 351.25 tokens per second) 12.30.208.963 I slot print_timing: id 0 | task 32090 | eval time = 7174.71 ms / 385 tokens ( 18.68 ms per token, 53.52 tokens per second) 12.30.208.963 I slot print_timing: id 0 | task 32090 | total time = 7761.18 ms / 591 tokens 12.30.208.964 I slot print_timing: id 0 | task 32090 | graphs reused = 31367 12.30.208.965 I slot print_timing: id 0 | task 32090 | graph reallocs = 0 / 0 (same size) / (changed size) 12.30.208.986 I slot release: id 0 | task 32090 | stop processing: n_tokens = 590, truncated = 0 12.30.213.578 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.063 12.30.213.650 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.981 MiB) 12.30.221.607 I slot launch_slot_: id 0 | task 32478 | processing task, is_child = 0 12.33.554.748 I slot print_timing: id 0 | task 32478 | prompt eval time = 579.93 ms / 208 tokens ( 2.79 ms per token, 358.66 tokens per second) 12.33.554.754 I slot print_timing: id 0 | task 32478 | eval time = 2753.20 ms / 149 tokens ( 18.60 ms per token, 53.76 tokens per second) 12.33.554.754 I slot print_timing: id 0 | task 32478 | total time = 3333.13 ms / 357 tokens 12.33.554.755 I slot print_timing: id 0 | task 32478 | graphs reused = 31513 12.33.554.755 I slot print_timing: id 0 | task 32478 | graph reallocs = 0 / 0 (same size) / (changed size) 12.33.554.776 I slot release: id 0 | task 32478 | stop processing: n_tokens = 356, truncated = 0 12.33.559.590 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.167 (> 0.100 thold), f_keep = 0.104 12.33.563.327 I slot launch_slot_: id 0 | task 32630 | processing task, is_child = 0 12.35.906.649 I slot print_timing: id 0 | task 32630 | prompt eval time = 610.09 ms / 221 tokens ( 2.76 ms per token, 362.24 tokens per second) 12.35.906.652 I slot print_timing: id 0 | task 32630 | eval time = 1733.23 ms / 94 tokens ( 18.64 ms per token, 53.66 tokens per second) 12.35.906.653 I slot print_timing: id 0 | task 32630 | total time = 2343.31 ms / 315 tokens 12.35.906.653 I slot print_timing: id 0 | task 32630 | graphs reused = 31604 12.35.906.654 I slot print_timing: id 0 | task 32630 | graph reallocs = 0 / 0 (same size) / (changed size) 12.35.906.674 I slot release: id 0 | task 32630 | stop processing: n_tokens = 314, truncated = 0 12.35.911.107 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.180 (> 0.100 thold), f_keep = 0.121 12.35.911.161 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 113.926 MiB) 12.35.915.484 I slot launch_slot_: id 0 | task 32727 | processing task, is_child = 0 12.37.778.664 I slot print_timing: id 0 | task 32727 | prompt eval time = 591.65 ms / 211 tokens ( 2.80 ms per token, 356.63 tokens per second) 12.37.778.670 I slot print_timing: id 0 | task 32727 | eval time = 1271.52 ms / 69 tokens ( 18.70 ms per token, 53.48 tokens per second) 12.37.778.671 I slot print_timing: id 0 | task 32727 | total time = 1863.17 ms / 280 tokens 12.37.778.671 I slot print_timing: id 0 | task 32727 | graphs reused = 31670 12.37.778.672 I slot print_timing: id 0 | task 32727 | graph reallocs = 0 / 0 (same size) / (changed size) 12.37.778.692 I slot release: id 0 | task 32727 | stop processing: n_tokens = 279, truncated = 0 12.37.783.538 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.133 12.37.788.161 I slot launch_slot_: id 0 | task 32799 | processing task, is_child = 0 12.39.729.087 I slot print_timing: id 0 | task 32799 | prompt eval time = 614.75 ms / 217 tokens ( 2.83 ms per token, 352.99 tokens per second) 12.39.729.090 I slot print_timing: id 0 | task 32799 | eval time = 1326.16 ms / 72 tokens ( 18.68 ms per token, 53.54 tokens per second) 12.39.729.091 I slot print_timing: id 0 | task 32799 | total time = 1940.92 ms / 289 tokens 12.39.729.091 I slot print_timing: id 0 | task 32799 | graphs reused = 31739 12.39.729.092 I slot print_timing: id 0 | task 32799 | graph reallocs = 0 / 0 (same size) / (changed size) 12.39.729.116 I slot release: id 0 | task 32799 | stop processing: n_tokens = 288, truncated = 0 12.39.733.556 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.167 (> 0.100 thold), f_keep = 0.128 12.39.733.607 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 109.509 MiB) 12.39.737.806 I slot launch_slot_: id 0 | task 32874 | processing task, is_child = 0 12.41.650.853 I slot print_timing: id 0 | task 32874 | prompt eval time = 587.40 ms / 221 tokens ( 2.66 ms per token, 376.23 tokens per second) 12.41.650.858 I slot print_timing: id 0 | task 32874 | eval time = 1325.64 ms / 72 tokens ( 18.67 ms per token, 53.56 tokens per second) 12.41.650.859 I slot print_timing: id 0 | task 32874 | total time = 1913.04 ms / 293 tokens 12.41.650.860 I slot print_timing: id 0 | task 32874 | graphs reused = 31808 12.41.650.860 I slot print_timing: id 0 | task 32874 | graph reallocs = 0 / 0 (same size) / (changed size) 12.41.650.881 I slot release: id 0 | task 32874 | stop processing: n_tokens = 292, truncated = 0 12.41.655.128 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.159 (> 0.100 thold), f_keep = 0.127 12.41.659.476 I slot launch_slot_: id 0 | task 32949 | processing task, is_child = 0 12.43.460.643 I slot print_timing: id 0 | task 32949 | prompt eval time = 621.23 ms / 232 tokens ( 2.68 ms per token, 373.45 tokens per second) 12.43.460.646 I slot print_timing: id 0 | task 32949 | eval time = 1179.93 ms / 64 tokens ( 18.73 ms per token, 53.39 tokens per second) 12.43.460.647 I slot print_timing: id 0 | task 32949 | total time = 1801.16 ms / 296 tokens 12.43.460.648 I slot print_timing: id 0 | task 32949 | graphs reused = 31869 12.43.460.648 I slot print_timing: id 0 | task 32949 | graph reallocs = 0 / 0 (same size) / (changed size) 12.43.460.668 I slot release: id 0 | task 32949 | stop processing: n_tokens = 295, truncated = 0 12.43.465.433 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.165 (> 0.100 thold), f_keep = 0.125 12.43.465.489 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.178 MiB) 12.43.469.737 I slot launch_slot_: id 0 | task 33016 | processing task, is_child = 0 12.47.062.617 I slot print_timing: id 0 | task 33016 | n_gen = 162, tg = 53.64 t/s, tg_3s = 53.97 t/s 12.50.080.768 I slot print_timing: id 0 | task 33016 | n_gen = 323, tg = 53.49 t/s, tg_3s = 53.34 t/s 12.53.098.236 I slot print_timing: id 0 | task 33016 | n_gen = 484, tg = 53.45 t/s, tg_3s = 53.36 t/s 12.55.603.833 I slot print_timing: id 0 | task 33016 | prompt eval time = 591.35 ms / 224 tokens ( 2.64 ms per token, 378.79 tokens per second) 12.55.603.839 I slot print_timing: id 0 | task 33016 | eval time = 11542.73 ms / 617 tokens ( 18.74 ms per token, 53.37 tokens per second) 12.55.603.840 I slot print_timing: id 0 | task 33016 | total time = 12134.09 ms / 841 tokens 12.55.603.840 I slot print_timing: id 0 | task 33016 | graphs reused = 32481 12.55.603.841 I slot print_timing: id 0 | task 33016 | graph reallocs = 0 / 0 (same size) / (changed size) 12.55.603.864 I slot release: id 0 | task 33016 | stop processing: n_tokens = 840, truncated = 0 12.55.608.799 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.159 (> 0.100 thold), f_keep = 0.044 12.55.608.888 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 136.108 MiB) 12.55.617.136 I slot launch_slot_: id 0 | task 33636 | processing task, is_child = 0 12.59.223.870 I slot print_timing: id 0 | task 33636 | n_gen = 162, tg = 53.61 t/s, tg_3s = 53.95 t/s 12.59.785.779 I slot print_timing: id 0 | task 33636 | prompt eval time = 603.70 ms / 233 tokens ( 2.59 ms per token, 385.96 tokens per second) 12.59.785.785 I slot print_timing: id 0 | task 33636 | eval time = 3564.93 ms / 192 tokens ( 18.66 ms per token, 53.58 tokens per second) 12.59.785.786 I slot print_timing: id 0 | task 33636 | total time = 4168.63 ms / 425 tokens 12.59.785.787 I slot print_timing: id 0 | task 33636 | graphs reused = 32670 12.59.785.787 I slot print_timing: id 0 | task 33636 | graph reallocs = 0 / 0 (same size) / (changed size) 12.59.785.810 I slot release: id 0 | task 33636 | stop processing: n_tokens = 424, truncated = 0 12.59.790.815 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.167 (> 0.100 thold), f_keep = 0.092 12.59.796.193 I slot launch_slot_: id 0 | task 33831 | processing task, is_child = 0 13.03.399.698 I slot print_timing: id 0 | task 33831 | n_gen = 162, tg = 53.64 t/s, tg_3s = 53.97 t/s 13.04.388.697 I slot print_timing: id 0 | task 33831 | prompt eval time = 601.85 ms / 233 tokens ( 2.58 ms per token, 387.14 tokens per second) 13.04.388.703 I slot print_timing: id 0 | task 33831 | eval time = 3990.64 ms / 215 tokens ( 18.65 ms per token, 53.63 tokens per second) 13.04.388.703 I slot print_timing: id 0 | task 33831 | total time = 4592.49 ms / 448 tokens 13.04.388.704 I slot print_timing: id 0 | task 33831 | graphs reused = 32882 13.04.388.705 I slot print_timing: id 0 | task 33831 | graph reallocs = 0 / 0 (same size) / (changed size) 13.04.388.729 I slot release: id 0 | task 33831 | stop processing: n_tokens = 447, truncated = 0 13.04.393.616 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.143 (> 0.100 thold), f_keep = 0.083 13.04.393.675 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.723 MiB) 13.04.396.132 I slot launch_slot_: id 0 | task 34049 | processing task, is_child = 0 13.06.752.475 I slot print_timing: id 0 | task 34049 | prompt eval time = 639.75 ms / 259 tokens ( 2.47 ms per token, 404.85 tokens per second) 13.06.752.481 I slot print_timing: id 0 | task 34049 | eval time = 1716.58 ms / 93 tokens ( 18.66 ms per token, 53.59 tokens per second) 13.06.752.481 I slot print_timing: id 0 | task 34049 | total time = 2356.33 ms / 352 tokens 13.06.752.482 I slot print_timing: id 0 | task 34049 | graphs reused = 32973 13.06.752.483 I slot print_timing: id 0 | task 34049 | graph reallocs = 0 / 0 (same size) / (changed size) 13.06.752.508 I slot release: id 0 | task 34049 | stop processing: n_tokens = 351, truncated = 0 13.06.757.066 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.173 (> 0.100 thold), f_keep = 0.105 13.06.757.120 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 71.111 MiB) 13.06.759.738 I slot launch_slot_: id 0 | task 34145 | processing task, is_child = 0 13.08.600.502 I slot print_timing: id 0 | task 34145 | prompt eval time = 607.55 ms / 214 tokens ( 2.84 ms per token, 352.24 tokens per second) 13.08.600.505 I slot print_timing: id 0 | task 34145 | eval time = 1233.21 ms / 67 tokens ( 18.68 ms per token, 53.52 tokens per second) 13.08.600.506 I slot print_timing: id 0 | task 34145 | total time = 1840.75 ms / 281 tokens 13.08.600.506 I slot print_timing: id 0 | task 34145 | graphs reused = 33037 13.08.600.507 I slot print_timing: id 0 | task 34145 | graph reallocs = 0 / 0 (same size) / (changed size) 13.08.600.529 I slot release: id 0 | task 34145 | stop processing: n_tokens = 280, truncated = 0 13.08.764.955 I srv operator(): operator(): cleaning up before exit...