$ /Users/minipro/quantdiff/llama.cpp/llama-b11770/llama-server -m /Users/minipro/quantdiff/models/campaign/37455964b1ab/Spark-X2.6-4B.i1-Q4_K_M.gguf --host 127.0.0.1 --port 8089 -c 4096 -np 1 -ngl 999 -fa on --jinja --seed 1234 --no-webui -a quant 0.00.042.585 I srv llama_server: initializing ... 0.00.042.592 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.042.676 I srv init_listene: The UI is disabled 0.00.042.677 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.042.711 W srv llama_server: security: no API key is set and CORS allows all origins (see https://github.com/ggml-org/llama.cpp/pull/25655) 0.00.044.381 I srv load_model: loading model '/Users/minipro/quantdiff/models/campaign/37455964b1ab/Spark-X2.6-4B.i1-Q4_K_M.gguf' 0.00.424.075 I cmn init: llama threadpool init, n_threads = 8 0.00.511.077 I srv load_model: initializing, n_slots = 1, n_ctx_slot = 4096, kv_unified = 'false' 0.00.518.552 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.00.518.562 I srv llama_server: model loaded 0.00.518.564 I srv llama_server: listening on http://127.0.0.1:8089 0.02.021.293 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.02.021.531 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.02.929.741 I slot print_timing: id 0 | task 0 | prompt eval time = 441.37 ms / 172 tokens ( 2.57 ms per token, 389.69 tokens per second) 0.02.929.745 I slot print_timing: id 0 | task 0 | eval time = 466.81 ms / 24 tokens ( 20.30 ms per token, 49.27 tokens per second) 0.02.929.746 I slot print_timing: id 0 | task 0 | total time = 908.19 ms / 196 tokens 0.02.929.746 I slot print_timing: id 0 | task 0 | graphs reused = 23 0.02.929.747 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.02.929.767 I slot release: id 0 | task 0 | stop processing: n_tokens = 195, truncated = 0 0.02.933.595 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.236 (> 0.100 thold), f_keep = 0.154 0.02.939.069 I slot launch_slot_: id 0 | task 27 | processing task, is_child = 0 0.03.712.275 I slot print_timing: id 0 | task 27 | prompt eval time = 349.85 ms / 127 tokens ( 2.75 ms per token, 363.02 tokens per second) 0.03.712.284 I slot print_timing: id 0 | task 27 | eval time = 423.35 ms / 22 tokens ( 20.16 ms per token, 49.60 tokens per second) 0.03.712.285 I slot print_timing: id 0 | task 27 | total time = 773.20 ms / 149 tokens 0.03.712.286 I slot print_timing: id 0 | task 27 | graphs reused = 43 0.03.712.286 I slot print_timing: id 0 | task 27 | graph reallocs = 0 / 0 (same size) / (changed size) 0.03.712.303 I slot release: id 0 | task 27 | stop processing: n_tokens = 148, truncated = 0 0.03.716.156 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.203 0.03.720.311 I slot launch_slot_: id 0 | task 52 | processing task, is_child = 0 0.04.528.191 I slot print_timing: id 0 | task 52 | prompt eval time = 403.01 ms / 171 tokens ( 2.36 ms per token, 424.31 tokens per second) 0.04.528.193 I slot print_timing: id 0 | task 52 | eval time = 404.86 ms / 21 tokens ( 20.24 ms per token, 49.40 tokens per second) 0.04.528.195 I slot print_timing: id 0 | task 52 | total time = 807.87 ms / 192 tokens 0.04.528.196 I slot print_timing: id 0 | task 52 | graphs reused = 62 0.04.528.196 I slot print_timing: id 0 | task 52 | graph reallocs = 0 / 0 (same size) / (changed size) 0.04.528.218 I slot release: id 0 | task 52 | stop processing: n_tokens = 191, truncated = 0 0.04.532.229 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.147 (> 0.100 thold), f_keep = 0.157 0.04.537.804 I slot launch_slot_: id 0 | task 76 | processing task, is_child = 0 0.05.447.857 I slot print_timing: id 0 | task 76 | prompt eval time = 464.91 ms / 204 tokens ( 2.28 ms per token, 438.80 tokens per second) 0.05.447.863 I slot print_timing: id 0 | task 76 | eval time = 445.13 ms / 23 tokens ( 20.23 ms per token, 49.42 tokens per second) 0.05.447.864 I slot print_timing: id 0 | task 76 | total time = 910.04 ms / 227 tokens 0.05.447.864 I slot print_timing: id 0 | task 76 | graphs reused = 83 0.05.447.865 I slot print_timing: id 0 | task 76 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.447.884 I slot release: id 0 | task 76 | stop processing: n_tokens = 226, truncated = 0 0.05.451.845 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.190 0.05.458.624 I slot launch_slot_: id 0 | task 102 | processing task, is_child = 0 0.08.086.712 I slot print_timing: id 0 | task 102 | prompt eval time = 449.98 ms / 187 tokens ( 2.41 ms per token, 415.57 tokens per second) 0.08.086.716 I slot print_timing: id 0 | task 102 | eval time = 2178.10 ms / 109 tokens ( 20.17 ms per token, 49.58 tokens per second) 0.08.086.716 I slot print_timing: id 0 | task 102 | total time = 2628.08 ms / 296 tokens 0.08.086.717 I slot print_timing: id 0 | task 102 | graphs reused = 189 0.08.086.718 I slot print_timing: id 0 | task 102 | graph reallocs = 0 / 0 (same size) / (changed size) 0.08.086.740 I slot release: id 0 | task 102 | stop processing: n_tokens = 295, truncated = 0 0.08.090.849 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.102 0.08.097.019 I slot launch_slot_: id 0 | task 214 | processing task, is_child = 0 0.09.074.516 I slot print_timing: id 0 | task 214 | prompt eval time = 371.09 ms / 171 tokens ( 2.17 ms per token, 460.81 tokens per second) 0.09.074.522 I slot print_timing: id 0 | task 214 | eval time = 606.40 ms / 31 tokens ( 20.21 ms per token, 49.47 tokens per second) 0.09.074.523 I slot print_timing: id 0 | task 214 | total time = 977.49 ms / 202 tokens 0.09.074.524 I slot print_timing: id 0 | task 214 | graphs reused = 218 0.09.074.524 I slot print_timing: id 0 | task 214 | graph reallocs = 0 / 0 (same size) / (changed size) 0.09.074.541 I slot release: id 0 | task 214 | stop processing: n_tokens = 201, truncated = 0 0.09.078.537 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.136 (> 0.100 thold), f_keep = 0.149 0.09.084.051 I slot launch_slot_: id 0 | task 248 | processing task, is_child = 0 0.12.605.820 I slot print_timing: id 0 | task 248 | n_gen = 150, tg = 49.54 t/s, tg_3s = 49.87 t/s 0.12.929.719 I slot print_timing: id 0 | task 248 | prompt eval time = 514.17 ms / 221 tokens ( 2.33 ms per token, 429.81 tokens per second) 0.12.929.725 I slot print_timing: id 0 | task 248 | eval time = 3331.48 ms / 166 tokens ( 20.19 ms per token, 49.53 tokens per second) 0.12.929.725 I slot print_timing: id 0 | task 248 | total time = 3845.66 ms / 387 tokens 0.12.929.726 I slot print_timing: id 0 | task 248 | graphs reused = 381 0.12.929.727 I slot print_timing: id 0 | task 248 | graph reallocs = 0 / 0 (same size) / (changed size) 0.12.929.750 I slot release: id 0 | task 248 | stop processing: n_tokens = 386, truncated = 0 0.12.934.164 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 0.12.942.814 I slot launch_slot_: id 0 | task 417 | processing task, is_child = 0 0.16.571.614 I slot print_timing: id 0 | task 417 | n_gen = 150, tg = 49.44 t/s, tg_3s = 49.77 t/s 0.19.380.601 I slot print_timing: id 0 | task 417 | prompt eval time = 614.84 ms / 270 tokens ( 2.28 ms per token, 439.14 tokens per second) 0.19.380.605 I slot print_timing: id 0 | task 417 | eval time = 5822.94 ms / 287 tokens ( 20.36 ms per token, 49.12 tokens per second) 0.19.380.606 I slot print_timing: id 0 | task 417 | total time = 6437.78 ms / 557 tokens 0.19.380.606 I slot print_timing: id 0 | task 417 | graphs reused = 665 0.19.380.607 I slot print_timing: id 0 | task 417 | graph reallocs = 0 / 0 (same size) / (changed size) 0.19.380.635 I slot release: id 0 | task 417 | stop processing: n_tokens = 556, truncated = 0 0.19.384.476 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.054 0.19.395.764 I slot launch_slot_: id 0 | task 707 | processing task, is_child = 0 0.20.295.099 I slot print_timing: id 0 | task 707 | prompt eval time = 353.25 ms / 150 tokens ( 2.36 ms per token, 424.63 tokens per second) 0.20.295.102 I slot print_timing: id 0 | task 707 | eval time = 546.08 ms / 28 tokens ( 20.23 ms per token, 49.44 tokens per second) 0.20.295.103 I slot print_timing: id 0 | task 707 | total time = 899.33 ms / 178 tokens 0.20.295.104 I slot print_timing: id 0 | task 707 | graphs reused = 691 0.20.295.104 I slot print_timing: id 0 | task 707 | graph reallocs = 0 / 0 (same size) / (changed size) 0.20.295.124 I slot release: id 0 | task 707 | stop processing: n_tokens = 177, truncated = 0 0.20.299.551 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.180 (> 0.100 thold), f_keep = 0.169 0.20.301.162 I slot launch_slot_: id 0 | task 738 | processing task, is_child = 0 0.21.087.227 I slot print_timing: id 0 | task 738 | prompt eval time = 401.81 ms / 167 tokens ( 2.41 ms per token, 415.62 tokens per second) 0.21.087.232 I slot print_timing: id 0 | task 738 | eval time = 384.25 ms / 20 tokens ( 20.22 ms per token, 49.45 tokens per second) 0.21.087.233 I slot print_timing: id 0 | task 738 | total time = 786.06 ms / 187 tokens 0.21.087.234 I slot print_timing: id 0 | task 738 | graphs reused = 709 0.21.087.234 I slot print_timing: id 0 | task 738 | graph reallocs = 0 / 0 (same size) / (changed size) 0.21.087.251 I slot release: id 0 | task 738 | stop processing: n_tokens = 186, truncated = 0 0.21.091.134 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.161 0.21.095.536 I slot launch_slot_: id 0 | task 761 | processing task, is_child = 0 0.24.465.149 I slot print_timing: id 0 | task 761 | n_gen = 150, tg = 49.67 t/s, tg_3s = 50.00 t/s 0.26.830.074 I slot print_timing: id 0 | task 761 | prompt eval time = 369.51 ms / 171 tokens ( 2.16 ms per token, 462.78 tokens per second) 0.26.830.077 I slot print_timing: id 0 | task 761 | eval time = 5365.02 ms / 267 tokens ( 20.17 ms per token, 49.58 tokens per second) 0.26.830.078 I slot print_timing: id 0 | task 761 | total time = 5734.53 ms / 438 tokens 0.26.830.078 I slot print_timing: id 0 | task 761 | graphs reused = 973 0.26.830.079 I slot print_timing: id 0 | task 761 | graph reallocs = 0 / 0 (same size) / (changed size) 0.26.830.102 I slot release: id 0 | task 761 | stop processing: n_tokens = 437, truncated = 0 0.26.834.921 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.140 (> 0.100 thold), f_keep = 0.069 0.26.843.555 I slot launch_slot_: id 0 | task 1031 | processing task, is_child = 0 0.30.319.940 I slot print_timing: id 0 | task 1031 | n_gen = 150, tg = 49.50 t/s, tg_3s = 49.84 t/s 0.30.866.715 I slot print_timing: id 0 | task 1031 | prompt eval time = 466.50 ms / 214 tokens ( 2.18 ms per token, 458.74 tokens per second) 0.30.866.721 I slot print_timing: id 0 | task 1031 | eval time = 3556.66 ms / 177 tokens ( 20.21 ms per token, 49.48 tokens per second) 0.30.866.722 I slot print_timing: id 0 | task 1031 | total time = 4023.15 ms / 391 tokens 0.30.866.722 I slot print_timing: id 0 | task 1031 | graphs reused = 1147 0.30.866.723 I slot print_timing: id 0 | task 1031 | graph reallocs = 0 / 0 (same size) / (changed size) 0.30.866.743 I slot release: id 0 | task 1031 | stop processing: n_tokens = 390, truncated = 0 0.30.870.596 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.164 (> 0.100 thold), f_keep = 0.077 0.30.879.248 I slot launch_slot_: id 0 | task 1211 | processing task, is_child = 0 0.32.077.869 I slot print_timing: id 0 | task 1211 | prompt eval time = 451.00 ms / 183 tokens ( 2.46 ms per token, 405.77 tokens per second) 0.32.077.872 I slot print_timing: id 0 | task 1211 | eval time = 747.61 ms / 38 tokens ( 20.21 ms per token, 49.49 tokens per second) 0.32.077.873 I slot print_timing: id 0 | task 1211 | total time = 1198.61 ms / 221 tokens 0.32.077.874 I slot print_timing: id 0 | task 1211 | graphs reused = 1183 0.32.077.874 I slot print_timing: id 0 | task 1211 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.077.899 I slot release: id 0 | task 1211 | stop processing: n_tokens = 220, truncated = 0 0.32.082.056 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.164 (> 0.100 thold), f_keep = 0.136 0.32.085.967 I slot launch_slot_: id 0 | task 1252 | processing task, is_child = 0 0.33.074.965 I slot print_timing: id 0 | task 1252 | prompt eval time = 463.53 ms / 183 tokens ( 2.53 ms per token, 394.80 tokens per second) 0.33.074.971 I slot print_timing: id 0 | task 1252 | eval time = 525.46 ms / 27 tokens ( 20.21 ms per token, 49.48 tokens per second) 0.33.074.972 I slot print_timing: id 0 | task 1252 | total time = 988.98 ms / 210 tokens 0.33.074.973 I slot print_timing: id 0 | task 1252 | graphs reused = 1208 0.33.074.973 I slot print_timing: id 0 | task 1252 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.074.991 I slot release: id 0 | task 1252 | stop processing: n_tokens = 209, truncated = 0 0.33.078.947 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.176 (> 0.100 thold), f_keep = 0.144 0.33.084.668 I slot launch_slot_: id 0 | task 1282 | processing task, is_child = 0 0.34.176.687 I slot print_timing: id 0 | task 1282 | prompt eval time = 403.60 ms / 170 tokens ( 2.37 ms per token, 421.21 tokens per second) 0.34.176.692 I slot print_timing: id 0 | task 1282 | eval time = 688.41 ms / 35 tokens ( 20.25 ms per token, 49.39 tokens per second) 0.34.176.693 I slot print_timing: id 0 | task 1282 | total time = 1092.01 ms / 205 tokens 0.34.176.694 I slot print_timing: id 0 | task 1282 | graphs reused = 1241 0.34.176.695 I slot print_timing: id 0 | task 1282 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.176.716 I slot release: id 0 | task 1282 | stop processing: n_tokens = 204, truncated = 0 0.34.180.594 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.147 0.34.186.192 I slot launch_slot_: id 0 | task 1320 | processing task, is_child = 0 0.35.165.496 I slot print_timing: id 0 | task 1320 | prompt eval time = 352.61 ms / 150 tokens ( 2.35 ms per token, 425.40 tokens per second) 0.35.165.508 I slot print_timing: id 0 | task 1320 | eval time = 626.68 ms / 32 tokens ( 20.22 ms per token, 49.47 tokens per second) 0.35.165.509 I slot print_timing: id 0 | task 1320 | total time = 979.29 ms / 182 tokens 0.35.165.509 I slot print_timing: id 0 | task 1320 | graphs reused = 1271 0.35.165.513 I slot print_timing: id 0 | task 1320 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.165.527 I slot release: id 0 | task 1320 | stop processing: n_tokens = 181, truncated = 0 0.35.169.301 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.172 (> 0.100 thold), f_keep = 0.166 0.35.173.434 I slot launch_slot_: id 0 | task 1355 | processing task, is_child = 0 0.35.980.569 I slot print_timing: id 0 | task 1355 | prompt eval time = 402.23 ms / 174 tokens ( 2.31 ms per token, 432.59 tokens per second) 0.35.980.576 I slot print_timing: id 0 | task 1355 | eval time = 404.89 ms / 21 tokens ( 20.24 ms per token, 49.40 tokens per second) 0.35.980.576 I slot print_timing: id 0 | task 1355 | total time = 807.12 ms / 195 tokens 0.35.980.577 I slot print_timing: id 0 | task 1355 | graphs reused = 1290 0.35.980.578 I slot print_timing: id 0 | task 1355 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.980.595 I slot release: id 0 | task 1355 | stop processing: n_tokens = 194, truncated = 0 0.35.984.456 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.192 (> 0.100 thold), f_keep = 0.155 0.35.989.870 I slot launch_slot_: id 0 | task 1379 | processing task, is_child = 0 0.36.777.905 I slot print_timing: id 0 | task 1379 | prompt eval time = 403.09 ms / 156 tokens ( 2.58 ms per token, 387.01 tokens per second) 0.36.777.908 I slot print_timing: id 0 | task 1379 | eval time = 384.93 ms / 20 tokens ( 20.26 ms per token, 49.36 tokens per second) 0.36.777.908 I slot print_timing: id 0 | task 1379 | total time = 788.02 ms / 176 tokens 0.36.777.909 I slot print_timing: id 0 | task 1379 | graphs reused = 1308 0.36.777.909 I slot print_timing: id 0 | task 1379 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.777.933 I slot release: id 0 | task 1379 | stop processing: n_tokens = 175, truncated = 0 0.36.781.716 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.197 (> 0.100 thold), f_keep = 0.171 0.36.786.742 I slot launch_slot_: id 0 | task 1402 | processing task, is_child = 0 0.37.500.820 I slot print_timing: id 0 | task 1402 | prompt eval time = 368.72 ms / 152 tokens ( 2.43 ms per token, 412.24 tokens per second) 0.37.500.823 I slot print_timing: id 0 | task 1402 | eval time = 345.35 ms / 18 tokens ( 20.31 ms per token, 49.22 tokens per second) 0.37.500.824 I slot print_timing: id 0 | task 1402 | total time = 714.07 ms / 170 tokens 0.37.500.824 I slot print_timing: id 0 | task 1402 | graphs reused = 1324 0.37.500.825 I slot print_timing: id 0 | task 1402 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.500.843 I slot release: id 0 | task 1402 | stop processing: n_tokens = 169, truncated = 0 0.37.505.147 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.160 (> 0.100 thold), f_keep = 0.178 0.37.509.839 I slot launch_slot_: id 0 | task 1423 | processing task, is_child = 0 0.38.727.666 I slot print_timing: id 0 | task 1423 | prompt eval time = 451.00 ms / 187 tokens ( 2.41 ms per token, 414.64 tokens per second) 0.38.727.670 I slot print_timing: id 0 | task 1423 | eval time = 766.82 ms / 39 tokens ( 20.18 ms per token, 49.56 tokens per second) 0.38.727.670 I slot print_timing: id 0 | task 1423 | total time = 1217.82 ms / 226 tokens 0.38.727.671 I slot print_timing: id 0 | task 1423 | graphs reused = 1361 0.38.727.672 I slot print_timing: id 0 | task 1423 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.727.693 I slot release: id 0 | task 1423 | stop processing: n_tokens = 225, truncated = 0 0.38.731.472 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.133 0.38.736.671 I slot launch_slot_: id 0 | task 1465 | processing task, is_child = 0 0.39.819.121 I slot print_timing: id 0 | task 1465 | prompt eval time = 401.71 ms / 160 tokens ( 2.51 ms per token, 398.30 tokens per second) 0.39.819.131 I slot print_timing: id 0 | task 1465 | eval time = 680.73 ms / 34 tokens ( 20.63 ms per token, 48.48 tokens per second) 0.39.819.132 I slot print_timing: id 0 | task 1465 | total time = 1082.44 ms / 194 tokens 0.39.819.133 I slot print_timing: id 0 | task 1465 | graphs reused = 1393 0.39.819.136 I slot print_timing: id 0 | task 1465 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.819.152 I slot release: id 0 | task 1465 | stop processing: n_tokens = 193, truncated = 0 0.39.823.009 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.144 (> 0.100 thold), f_keep = 0.155 0.39.828.105 I slot launch_slot_: id 0 | task 1502 | processing task, is_child = 0 0.41.041.430 I slot print_timing: id 0 | task 1502 | prompt eval time = 465.55 ms / 208 tokens ( 2.24 ms per token, 446.79 tokens per second) 0.41.041.433 I slot print_timing: id 0 | task 1502 | eval time = 747.76 ms / 38 tokens ( 20.21 ms per token, 49.48 tokens per second) 0.41.041.434 I slot print_timing: id 0 | task 1502 | total time = 1213.31 ms / 246 tokens 0.41.041.435 I slot print_timing: id 0 | task 1502 | graphs reused = 1429 0.41.041.435 I slot print_timing: id 0 | task 1502 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.041.454 I slot release: id 0 | task 1502 | stop processing: n_tokens = 245, truncated = 0 0.41.045.264 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.122 0.41.051.651 I slot launch_slot_: id 0 | task 1543 | processing task, is_child = 0 0.44.522.274 I slot print_timing: id 0 | task 1543 | n_gen = 150, tg = 49.53 t/s, tg_3s = 49.86 t/s 0.44.562.785 I slot print_timing: id 0 | task 1543 | prompt eval time = 462.08 ms / 192 tokens ( 2.41 ms per token, 415.52 tokens per second) 0.44.562.787 I slot print_timing: id 0 | task 1543 | eval time = 3049.05 ms / 152 tokens ( 20.19 ms per token, 49.52 tokens per second) 0.44.562.788 I slot print_timing: id 0 | task 1543 | total time = 3511.13 ms / 344 tokens 0.44.562.788 I slot print_timing: id 0 | task 1543 | graphs reused = 1578 0.44.562.789 I slot print_timing: id 0 | task 1543 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.562.810 I slot release: id 0 | task 1543 | stop processing: n_tokens = 343, truncated = 0 0.44.567.113 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.152 (> 0.100 thold), f_keep = 0.087 0.44.575.153 I slot launch_slot_: id 0 | task 1698 | processing task, is_child = 0 0.45.997.359 I slot print_timing: id 0 | task 1698 | prompt eval time = 453.10 ms / 198 tokens ( 2.29 ms per token, 436.99 tokens per second) 0.45.997.364 I slot print_timing: id 0 | task 1698 | eval time = 969.10 ms / 49 tokens ( 20.19 ms per token, 49.53 tokens per second) 0.45.997.365 I slot print_timing: id 0 | task 1698 | total time = 1422.20 ms / 247 tokens 0.45.997.366 I slot print_timing: id 0 | task 1698 | graphs reused = 1625 0.45.997.367 I slot print_timing: id 0 | task 1698 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.997.386 I slot release: id 0 | task 1698 | stop processing: n_tokens = 246, truncated = 0 0.46.001.605 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.128 (> 0.100 thold), f_keep = 0.122 0.46.008.033 I slot launch_slot_: id 0 | task 1750 | processing task, is_child = 0 0.47.273.143 I slot print_timing: id 0 | task 1750 | prompt eval time = 515.22 ms / 235 tokens ( 2.19 ms per token, 456.12 tokens per second) 0.47.273.150 I slot print_timing: id 0 | task 1750 | eval time = 749.88 ms / 38 tokens ( 20.27 ms per token, 49.34 tokens per second) 0.47.273.151 I slot print_timing: id 0 | task 1750 | total time = 1265.10 ms / 273 tokens 0.47.273.151 I slot print_timing: id 0 | task 1750 | graphs reused = 1660 0.47.273.152 I slot print_timing: id 0 | task 1750 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.273.171 I slot release: id 0 | task 1750 | stop processing: n_tokens = 272, truncated = 0 0.47.277.027 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.114 0.47.284.484 I slot launch_slot_: id 0 | task 1791 | processing task, is_child = 0 0.48.424.562 I slot print_timing: id 0 | task 1791 | prompt eval time = 452.52 ms / 199 tokens ( 2.27 ms per token, 439.76 tokens per second) 0.48.424.568 I slot print_timing: id 0 | task 1791 | eval time = 687.55 ms / 35 tokens ( 20.22 ms per token, 49.45 tokens per second) 0.48.424.569 I slot print_timing: id 0 | task 1791 | total time = 1140.07 ms / 234 tokens 0.48.424.570 I slot print_timing: id 0 | task 1791 | graphs reused = 1693 0.48.424.570 I slot print_timing: id 0 | task 1791 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.424.589 I slot release: id 0 | task 1791 | stop processing: n_tokens = 233, truncated = 0 0.48.428.213 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.191 (> 0.100 thold), f_keep = 0.129 0.48.433.427 I slot launch_slot_: id 0 | task 1829 | processing task, is_child = 0 0.49.441.531 I slot print_timing: id 0 | task 1829 | prompt eval time = 402.58 ms / 157 tokens ( 2.56 ms per token, 389.99 tokens per second) 0.49.441.537 I slot print_timing: id 0 | task 1829 | eval time = 605.51 ms / 31 tokens ( 20.18 ms per token, 49.55 tokens per second) 0.49.441.538 I slot print_timing: id 0 | task 1829 | total time = 1008.09 ms / 188 tokens 0.49.441.539 I slot print_timing: id 0 | task 1829 | graphs reused = 1722 0.49.441.539 I slot print_timing: id 0 | task 1829 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.441.558 I slot release: id 0 | task 1829 | stop processing: n_tokens = 187, truncated = 0 0.49.445.671 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.168 (> 0.100 thold), f_keep = 0.166 0.49.450.162 I slot launch_slot_: id 0 | task 1863 | processing task, is_child = 0 0.50.582.004 I slot print_timing: id 0 | task 1863 | prompt eval time = 404.72 ms / 184 tokens ( 2.20 ms per token, 454.63 tokens per second) 0.50.582.007 I slot print_timing: id 0 | task 1863 | eval time = 727.11 ms / 37 tokens ( 20.20 ms per token, 49.51 tokens per second) 0.50.582.008 I slot print_timing: id 0 | task 1863 | total time = 1131.83 ms / 221 tokens 0.50.582.009 I slot print_timing: id 0 | task 1863 | graphs reused = 1757 0.50.582.009 I slot print_timing: id 0 | task 1863 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.582.031 I slot release: id 0 | task 1863 | stop processing: n_tokens = 220, truncated = 0 0.50.586.259 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.140 (> 0.100 thold), f_keep = 0.136 0.50.592.293 I slot launch_slot_: id 0 | task 1903 | processing task, is_child = 0 0.52.118.296 I slot print_timing: id 0 | task 1903 | prompt eval time = 512.25 ms / 214 tokens ( 2.39 ms per token, 417.77 tokens per second) 0.52.118.302 I slot print_timing: id 0 | task 1903 | eval time = 1013.75 ms / 51 tokens ( 20.27 ms per token, 49.32 tokens per second) 0.52.118.303 I slot print_timing: id 0 | task 1903 | total time = 1525.99 ms / 265 tokens 0.52.118.303 I slot print_timing: id 0 | task 1903 | graphs reused = 1805 0.52.118.304 I slot print_timing: id 0 | task 1903 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.118.324 I slot release: id 0 | task 1903 | stop processing: n_tokens = 264, truncated = 0 0.52.122.242 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.161 (> 0.100 thold), f_keep = 0.114 0.52.128.182 I slot launch_slot_: id 0 | task 1957 | processing task, is_child = 0 0.53.297.096 I slot print_timing: id 0 | task 1957 | prompt eval time = 461.54 ms / 186 tokens ( 2.48 ms per token, 403.00 tokens per second) 0.53.297.099 I slot print_timing: id 0 | task 1957 | eval time = 707.37 ms / 36 tokens ( 20.21 ms per token, 49.48 tokens per second) 0.53.297.100 I slot print_timing: id 0 | task 1957 | total time = 1168.91 ms / 222 tokens 0.53.297.101 I slot print_timing: id 0 | task 1957 | graphs reused = 1839 0.53.297.101 I slot print_timing: id 0 | task 1957 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.297.122 I slot release: id 0 | task 1957 | stop processing: n_tokens = 221, truncated = 0 0.53.301.041 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.184 (> 0.100 thold), f_keep = 0.136 0.53.306.936 I slot launch_slot_: id 0 | task 1996 | processing task, is_child = 0 0.54.417.827 I slot print_timing: id 0 | task 1996 | prompt eval time = 403.88 ms / 163 tokens ( 2.48 ms per token, 403.58 tokens per second) 0.54.417.834 I slot print_timing: id 0 | task 1996 | eval time = 707.00 ms / 36 tokens ( 20.20 ms per token, 49.51 tokens per second) 0.54.417.834 I slot print_timing: id 0 | task 1996 | total time = 1110.88 ms / 199 tokens 0.54.417.835 I slot print_timing: id 0 | task 1996 | graphs reused = 1873 0.54.417.836 I slot print_timing: id 0 | task 1996 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.417.854 I slot release: id 0 | task 1996 | stop processing: n_tokens = 198, truncated = 0 0.54.422.075 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.184 (> 0.100 thold), f_keep = 0.152 0.54.426.831 I slot launch_slot_: id 0 | task 2035 | processing task, is_child = 0 0.55.441.603 I slot print_timing: id 0 | task 2035 | prompt eval time = 368.63 ms / 163 tokens ( 2.26 ms per token, 442.18 tokens per second) 0.55.441.608 I slot print_timing: id 0 | task 2035 | eval time = 646.14 ms / 33 tokens ( 20.19 ms per token, 49.53 tokens per second) 0.55.441.609 I slot print_timing: id 0 | task 2035 | total time = 1014.76 ms / 196 tokens 0.55.441.610 I slot print_timing: id 0 | task 2035 | graphs reused = 1904 0.55.441.610 I slot print_timing: id 0 | task 2035 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.441.630 I slot release: id 0 | task 2035 | stop processing: n_tokens = 195, truncated = 0 0.55.445.816 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.160 (> 0.100 thold), f_keep = 0.154 0.55.451.139 I slot launch_slot_: id 0 | task 2071 | processing task, is_child = 0 0.56.621.641 I slot print_timing: id 0 | task 2071 | prompt eval time = 463.82 ms / 187 tokens ( 2.48 ms per token, 403.17 tokens per second) 0.56.621.648 I slot print_timing: id 0 | task 2071 | eval time = 706.66 ms / 36 tokens ( 20.19 ms per token, 49.53 tokens per second) 0.56.621.648 I slot print_timing: id 0 | task 2071 | total time = 1170.49 ms / 223 tokens 0.56.621.649 I slot print_timing: id 0 | task 2071 | graphs reused = 1938 0.56.621.650 I slot print_timing: id 0 | task 2071 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.621.668 I slot release: id 0 | task 2071 | stop processing: n_tokens = 222, truncated = 0 0.56.625.704 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.146 (> 0.100 thold), f_keep = 0.135 0.56.631.749 I slot launch_slot_: id 0 | task 2110 | processing task, is_child = 0 0.57.785.219 I slot print_timing: id 0 | task 2110 | prompt eval time = 464.76 ms / 205 tokens ( 2.27 ms per token, 441.09 tokens per second) 0.57.785.225 I slot print_timing: id 0 | task 2110 | eval time = 688.70 ms / 35 tokens ( 20.26 ms per token, 49.37 tokens per second) 0.57.785.226 I slot print_timing: id 0 | task 2110 | total time = 1153.46 ms / 240 tokens 0.57.785.226 I slot print_timing: id 0 | task 2110 | graphs reused = 1971 0.57.785.227 I slot print_timing: id 0 | task 2110 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.785.245 I slot release: id 0 | task 2110 | stop processing: n_tokens = 239, truncated = 0 0.57.789.068 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.190 (> 0.100 thold), f_keep = 0.126 0.57.794.540 I slot launch_slot_: id 0 | task 2148 | processing task, is_child = 0 0.58.792.109 I slot print_timing: id 0 | task 2148 | prompt eval time = 369.16 ms / 158 tokens ( 2.34 ms per token, 428.00 tokens per second) 0.58.792.115 I slot print_timing: id 0 | task 2148 | eval time = 628.40 ms / 32 tokens ( 20.27 ms per token, 49.33 tokens per second) 0.58.792.116 I slot print_timing: id 0 | task 2148 | total time = 997.56 ms / 190 tokens 0.58.792.116 I slot print_timing: id 0 | task 2148 | graphs reused = 2001 0.58.792.117 I slot print_timing: id 0 | task 2148 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.792.134 I slot release: id 0 | task 2148 | stop processing: n_tokens = 189, truncated = 0 0.58.796.285 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.153 (> 0.100 thold), f_keep = 0.159 0.58.800.955 I slot launch_slot_: id 0 | task 2183 | processing task, is_child = 0 0.59.821.848 I slot print_timing: id 0 | task 2183 | prompt eval time = 432.78 ms / 196 tokens ( 2.21 ms per token, 452.88 tokens per second) 0.59.821.853 I slot print_timing: id 0 | task 2183 | eval time = 588.10 ms / 30 tokens ( 20.28 ms per token, 49.31 tokens per second) 0.59.821.854 I slot print_timing: id 0 | task 2183 | total time = 1020.88 ms / 226 tokens 0.59.821.855 I slot print_timing: id 0 | task 2183 | graphs reused = 2029 0.59.821.855 I slot print_timing: id 0 | task 2183 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.821.878 I slot release: id 0 | task 2183 | stop processing: n_tokens = 225, truncated = 0 0.59.825.603 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.236 (> 0.100 thold), f_keep = 0.133 0.59.831.934 I slot launch_slot_: id 0 | task 2216 | processing task, is_child = 0 1.00.613.698 I slot print_timing: id 0 | task 2216 | prompt eval time = 315.80 ms / 127 tokens ( 2.49 ms per token, 402.15 tokens per second) 1.00.613.701 I slot print_timing: id 0 | task 2216 | eval time = 465.95 ms / 24 tokens ( 20.26 ms per token, 49.36 tokens per second) 1.00.613.702 I slot print_timing: id 0 | task 2216 | total time = 781.75 ms / 151 tokens 1.00.613.702 I slot print_timing: id 0 | task 2216 | graphs reused = 2051 1.00.613.703 I slot print_timing: id 0 | task 2216 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.613.725 I slot release: id 0 | task 2216 | stop processing: n_tokens = 150, truncated = 0 1.00.617.407 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.224 (> 0.100 thold), f_keep = 0.200 1.00.621.221 I slot launch_slot_: id 0 | task 2243 | processing task, is_child = 0 1.03.954.253 I slot print_timing: id 0 | task 2243 | n_gen = 151, tg = 49.77 t/s, tg_3s = 50.11 t/s 1.04.511.384 I slot print_timing: id 0 | task 2243 | prompt eval time = 319.36 ms / 134 tokens ( 2.38 ms per token, 419.60 tokens per second) 1.04.511.388 I slot print_timing: id 0 | task 2243 | eval time = 3570.80 ms / 179 tokens ( 20.06 ms per token, 49.85 tokens per second) 1.04.511.389 I slot print_timing: id 0 | task 2243 | total time = 3890.15 ms / 313 tokens 1.04.511.389 I slot print_timing: id 0 | task 2243 | graphs reused = 2227 1.04.511.390 I slot print_timing: id 0 | task 2243 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.511.408 I slot release: id 0 | task 2243 | stop processing: n_tokens = 312, truncated = 0 1.04.515.499 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.096 1.04.523.070 I slot launch_slot_: id 0 | task 2425 | processing task, is_child = 0 1.05.212.876 I slot print_timing: id 0 | task 2425 | prompt eval time = 365.40 ms / 148 tokens ( 2.47 ms per token, 405.03 tokens per second) 1.05.212.879 I slot print_timing: id 0 | task 2425 | eval time = 324.40 ms / 17 tokens ( 20.27 ms per token, 49.32 tokens per second) 1.05.212.880 I slot print_timing: id 0 | task 2425 | total time = 689.80 ms / 165 tokens 1.05.212.880 I slot print_timing: id 0 | task 2425 | graphs reused = 2242 1.05.212.881 I slot print_timing: id 0 | task 2425 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.212.902 I slot release: id 0 | task 2425 | stop processing: n_tokens = 164, truncated = 0 1.05.216.537 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.183 1.05.221.778 I slot launch_slot_: id 0 | task 2445 | processing task, is_child = 0 1.06.131.588 I slot print_timing: id 0 | task 2445 | prompt eval time = 363.52 ms / 145 tokens ( 2.51 ms per token, 398.88 tokens per second) 1.06.131.594 I slot print_timing: id 0 | task 2445 | eval time = 546.28 ms / 28 tokens ( 20.23 ms per token, 49.42 tokens per second) 1.06.131.594 I slot print_timing: id 0 | task 2445 | total time = 909.80 ms / 173 tokens 1.06.131.595 I slot print_timing: id 0 | task 2445 | graphs reused = 2268 1.06.131.596 I slot print_timing: id 0 | task 2445 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.131.612 I slot release: id 0 | task 2445 | stop processing: n_tokens = 172, truncated = 0 1.06.135.564 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.150 (> 0.100 thold), f_keep = 0.174 1.06.140.994 I slot launch_slot_: id 0 | task 2476 | processing task, is_child = 0 1.07.227.131 I slot print_timing: id 0 | task 2476 | prompt eval time = 452.87 ms / 200 tokens ( 2.26 ms per token, 441.63 tokens per second) 1.07.227.134 I slot print_timing: id 0 | task 2476 | eval time = 633.26 ms / 32 tokens ( 20.43 ms per token, 48.95 tokens per second) 1.07.227.134 I slot print_timing: id 0 | task 2476 | total time = 1086.13 ms / 232 tokens 1.07.227.134 I slot print_timing: id 0 | task 2476 | graphs reused = 2298 1.07.227.135 I slot print_timing: id 0 | task 2476 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.227.174 I slot release: id 0 | task 2476 | stop processing: n_tokens = 231, truncated = 0 1.07.230.893 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 231, t_last = 333262034556 1.07.236.787 I slot launch_slot_: id 0 | task 2511 | processing task, is_child = 0 1.09.090.932 I slot print_timing: id 0 | task 2511 | prompt eval time = 678.05 ms / 326 tokens ( 2.08 ms per token, 480.79 tokens per second) 1.09.090.936 I slot print_timing: id 0 | task 2511 | eval time = 1176.09 ms / 59 tokens ( 20.28 ms per token, 49.32 tokens per second) 1.09.090.936 I slot print_timing: id 0 | task 2511 | total time = 1854.13 ms / 385 tokens 1.09.090.937 I slot print_timing: id 0 | task 2511 | graphs reused = 2355 1.09.090.938 I slot print_timing: id 0 | task 2511 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.090.967 I slot release: id 0 | task 2511 | stop processing: n_tokens = 384, truncated = 0 1.09.094.879 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.078 1.09.107.279 I slot launch_slot_: id 0 | task 2573 | processing task, is_child = 0 1.09.921.174 I slot print_timing: id 0 | task 2573 | prompt eval time = 354.08 ms / 148 tokens ( 2.39 ms per token, 417.99 tokens per second) 1.09.921.180 I slot print_timing: id 0 | task 2573 | eval time = 459.81 ms / 24 tokens ( 19.99 ms per token, 50.02 tokens per second) 1.09.921.180 I slot print_timing: id 0 | task 2573 | total time = 813.89 ms / 172 tokens 1.09.921.181 I slot print_timing: id 0 | task 2573 | graphs reused = 2377 1.09.921.182 I slot print_timing: id 0 | task 2573 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.921.199 I slot release: id 0 | task 2573 | stop processing: n_tokens = 171, truncated = 0 1.09.925.233 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.175 1.09.927.799 I slot launch_slot_: id 0 | task 2600 | processing task, is_child = 0 1.10.845.571 I slot print_timing: id 0 | task 2600 | prompt eval time = 371.71 ms / 175 tokens ( 2.12 ms per token, 470.80 tokens per second) 1.10.845.575 I slot print_timing: id 0 | task 2600 | eval time = 546.05 ms / 28 tokens ( 20.22 ms per token, 49.45 tokens per second) 1.10.845.576 I slot print_timing: id 0 | task 2600 | total time = 917.76 ms / 203 tokens 1.10.845.577 I slot print_timing: id 0 | task 2600 | graphs reused = 2403 1.10.845.577 I slot print_timing: id 0 | task 2600 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.845.598 I slot release: id 0 | task 2600 | stop processing: n_tokens = 202, truncated = 0 1.10.849.948 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.131 (> 0.100 thold), f_keep = 0.149 1.10.856.302 I slot launch_slot_: id 0 | task 2631 | processing task, is_child = 0 1.12.161.507 I slot print_timing: id 0 | task 2631 | prompt eval time = 515.94 ms / 229 tokens ( 2.25 ms per token, 443.85 tokens per second) 1.12.161.510 I slot print_timing: id 0 | task 2631 | eval time = 789.25 ms / 40 tokens ( 20.24 ms per token, 49.41 tokens per second) 1.12.161.510 I slot print_timing: id 0 | task 2631 | total time = 1305.19 ms / 269 tokens 1.12.161.511 I slot print_timing: id 0 | task 2631 | graphs reused = 2440 1.12.161.512 I slot print_timing: id 0 | task 2631 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.161.534 I slot release: id 0 | task 2631 | stop processing: n_tokens = 268, truncated = 0 1.12.165.759 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.130 (> 0.100 thold), f_keep = 0.116 1.12.173.894 I slot launch_slot_: id 0 | task 2674 | processing task, is_child = 0 1.13.239.224 I slot print_timing: id 0 | task 2674 | prompt eval time = 516.86 ms / 238 tokens ( 2.17 ms per token, 460.48 tokens per second) 1.13.239.229 I slot print_timing: id 0 | task 2674 | eval time = 548.46 ms / 28 tokens ( 20.31 ms per token, 49.23 tokens per second) 1.13.239.230 I slot print_timing: id 0 | task 2674 | total time = 1065.32 ms / 266 tokens 1.13.239.231 I slot print_timing: id 0 | task 2674 | graphs reused = 2465 1.13.239.231 I slot print_timing: id 0 | task 2674 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.239.251 I slot release: id 0 | task 2674 | stop processing: n_tokens = 265, truncated = 0 1.13.242.971 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.204 (> 0.100 thold), f_keep = 0.125 1.13.250.966 I slot launch_slot_: id 0 | task 2705 | processing task, is_child = 0 1.13.881.204 I slot print_timing: id 0 | task 2705 | prompt eval time = 365.97 ms / 162 tokens ( 2.26 ms per token, 442.66 tokens per second) 1.13.881.210 I slot print_timing: id 0 | task 2705 | eval time = 264.26 ms / 14 tokens ( 20.33 ms per token, 49.19 tokens per second) 1.13.881.211 I slot print_timing: id 0 | task 2705 | total time = 630.23 ms / 176 tokens 1.13.881.211 I slot print_timing: id 0 | task 2705 | graphs reused = 2477 1.13.881.212 I slot print_timing: id 0 | task 2705 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.881.229 I slot release: id 0 | task 2705 | stop processing: n_tokens = 175, truncated = 0 1.13.885.076 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.171 1.13.887.997 I slot launch_slot_: id 0 | task 2722 | processing task, is_child = 0 1.14.799.192 I slot print_timing: id 0 | task 2722 | prompt eval time = 404.81 ms / 169 tokens ( 2.40 ms per token, 417.48 tokens per second) 1.14.799.195 I slot print_timing: id 0 | task 2722 | eval time = 506.37 ms / 26 tokens ( 20.25 ms per token, 49.37 tokens per second) 1.14.799.196 I slot print_timing: id 0 | task 2722 | total time = 911.18 ms / 195 tokens 1.14.799.197 I slot print_timing: id 0 | task 2722 | graphs reused = 2501 1.14.799.197 I slot print_timing: id 0 | task 2722 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.799.215 I slot release: id 0 | task 2722 | stop processing: n_tokens = 194, truncated = 0 1.14.803.151 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.167 (> 0.100 thold), f_keep = 0.155 1.14.809.198 I slot launch_slot_: id 0 | task 2751 | processing task, is_child = 0 1.15.784.711 I slot print_timing: id 0 | task 2751 | prompt eval time = 428.44 ms / 180 tokens ( 2.38 ms per token, 420.13 tokens per second) 1.15.784.715 I slot print_timing: id 0 | task 2751 | eval time = 547.07 ms / 28 tokens ( 20.26 ms per token, 49.35 tokens per second) 1.15.784.716 I slot print_timing: id 0 | task 2751 | total time = 975.50 ms / 208 tokens 1.15.784.717 I slot print_timing: id 0 | task 2751 | graphs reused = 2527 1.15.784.717 I slot print_timing: id 0 | task 2751 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.784.740 I slot release: id 0 | task 2751 | stop processing: n_tokens = 207, truncated = 0 1.15.789.248 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.148 (> 0.100 thold), f_keep = 0.145 1.15.796.687 I slot launch_slot_: id 0 | task 2782 | processing task, is_child = 0 1.17.151.834 I slot print_timing: id 0 | task 2782 | prompt eval time = 464.94 ms / 203 tokens ( 2.29 ms per token, 436.62 tokens per second) 1.17.151.837 I slot print_timing: id 0 | task 2782 | eval time = 890.19 ms / 45 tokens ( 20.23 ms per token, 49.43 tokens per second) 1.17.151.838 I slot print_timing: id 0 | task 2782 | total time = 1355.13 ms / 248 tokens 1.17.151.839 I slot print_timing: id 0 | task 2782 | graphs reused = 2570 1.17.151.839 I slot print_timing: id 0 | task 2782 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.151.864 I slot release: id 0 | task 2782 | stop processing: n_tokens = 247, truncated = 0 1.17.155.851 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.191 (> 0.100 thold), f_keep = 0.121 1.17.163.173 I slot launch_slot_: id 0 | task 2830 | processing task, is_child = 0 1.18.151.794 I slot print_timing: id 0 | task 2830 | prompt eval time = 402.64 ms / 157 tokens ( 2.56 ms per token, 389.93 tokens per second) 1.18.151.800 I slot print_timing: id 0 | task 2830 | eval time = 585.97 ms / 30 tokens ( 20.21 ms per token, 49.49 tokens per second) 1.18.151.801 I slot print_timing: id 0 | task 2830 | total time = 988.61 ms / 187 tokens 1.18.151.801 I slot print_timing: id 0 | task 2830 | graphs reused = 2598 1.18.151.802 I slot print_timing: id 0 | task 2830 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.151.818 I slot release: id 0 | task 2830 | stop processing: n_tokens = 186, truncated = 0 1.18.156.057 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.140 (> 0.100 thold), f_keep = 0.161 1.18.160.762 I slot launch_slot_: id 0 | task 2863 | processing task, is_child = 0 1.19.113.571 I slot print_timing: id 0 | task 2863 | prompt eval time = 466.84 ms / 214 tokens ( 2.18 ms per token, 458.41 tokens per second) 1.19.113.577 I slot print_timing: id 0 | task 2863 | eval time = 485.95 ms / 25 tokens ( 20.25 ms per token, 49.39 tokens per second) 1.19.113.578 I slot print_timing: id 0 | task 2863 | total time = 952.79 ms / 239 tokens 1.19.113.578 I slot print_timing: id 0 | task 2863 | graphs reused = 2621 1.19.113.579 I slot print_timing: id 0 | task 2863 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.113.598 I slot release: id 0 | task 2863 | stop processing: n_tokens = 238, truncated = 0 1.19.117.557 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.183 (> 0.100 thold), f_keep = 0.126 1.19.125.090 I slot launch_slot_: id 0 | task 2891 | processing task, is_child = 0 1.20.220.333 I slot print_timing: id 0 | task 2891 | prompt eval time = 367.10 ms / 164 tokens ( 2.24 ms per token, 446.74 tokens per second) 1.20.220.340 I slot print_timing: id 0 | task 2891 | eval time = 728.13 ms / 37 tokens ( 20.23 ms per token, 49.44 tokens per second) 1.20.220.340 I slot print_timing: id 0 | task 2891 | total time = 1095.23 ms / 201 tokens 1.20.220.341 I slot print_timing: id 0 | task 2891 | graphs reused = 2656 1.20.220.342 I slot print_timing: id 0 | task 2891 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.220.365 I slot release: id 0 | task 2891 | stop processing: n_tokens = 200, truncated = 0 1.20.226.324 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.181 (> 0.100 thold), f_keep = 0.150 1.20.230.258 I slot launch_slot_: id 0 | task 2931 | processing task, is_child = 0 1.21.259.322 I slot print_timing: id 0 | task 2931 | prompt eval time = 402.36 ms / 166 tokens ( 2.42 ms per token, 412.57 tokens per second) 1.21.259.328 I slot print_timing: id 0 | task 2931 | eval time = 626.70 ms / 32 tokens ( 20.22 ms per token, 49.47 tokens per second) 1.21.259.328 I slot print_timing: id 0 | task 2931 | total time = 1029.05 ms / 198 tokens 1.21.259.329 I slot print_timing: id 0 | task 2931 | graphs reused = 2686 1.21.259.330 I slot print_timing: id 0 | task 2931 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.259.346 I slot release: id 0 | task 2931 | stop processing: n_tokens = 197, truncated = 0 1.21.263.930 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.108 (> 0.100 thold), f_keep = 0.152 1.21.269.776 I slot launch_slot_: id 0 | task 2966 | processing task, is_child = 0 1.23.019.819 I slot print_timing: id 0 | task 2966 | prompt eval time = 617.15 ms / 277 tokens ( 2.23 ms per token, 448.83 tokens per second) 1.23.019.825 I slot print_timing: id 0 | task 2966 | eval time = 1132.88 ms / 57 tokens ( 20.23 ms per token, 49.43 tokens per second) 1.23.019.826 I slot print_timing: id 0 | task 2966 | total time = 1750.03 ms / 334 tokens 1.23.019.827 I slot print_timing: id 0 | task 2966 | graphs reused = 2741 1.23.019.827 I slot print_timing: id 0 | task 2966 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.019.859 I slot release: id 0 | task 2966 | stop processing: n_tokens = 333, truncated = 0 1.23.024.245 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 1.23.034.600 I slot launch_slot_: id 0 | task 3026 | processing task, is_child = 0 1.24.911.541 I slot print_timing: id 0 | task 3026 | prompt eval time = 519.18 ms / 248 tokens ( 2.09 ms per token, 477.68 tokens per second) 1.24.911.547 I slot print_timing: id 0 | task 3026 | eval time = 1357.75 ms / 68 tokens ( 20.26 ms per token, 49.35 tokens per second) 1.24.911.548 I slot print_timing: id 0 | task 3026 | total time = 1876.93 ms / 316 tokens 1.24.911.549 I slot print_timing: id 0 | task 3026 | graphs reused = 2806 1.24.911.549 I slot print_timing: id 0 | task 3026 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.911.570 I slot release: id 0 | task 3026 | stop processing: n_tokens = 315, truncated = 0 1.24.915.430 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.189 (> 0.100 thold), f_keep = 0.095 1.24.924.402 I slot launch_slot_: id 0 | task 3097 | processing task, is_child = 0 1.25.913.474 I slot print_timing: id 0 | task 3097 | prompt eval time = 403.64 ms / 159 tokens ( 2.54 ms per token, 393.92 tokens per second) 1.25.913.480 I slot print_timing: id 0 | task 3097 | eval time = 585.42 ms / 30 tokens ( 20.19 ms per token, 49.54 tokens per second) 1.25.913.481 I slot print_timing: id 0 | task 3097 | total time = 989.06 ms / 189 tokens 1.25.913.481 I slot print_timing: id 0 | task 3097 | graphs reused = 2834 1.25.913.482 I slot print_timing: id 0 | task 3097 | graph reallocs = 0 / 0 (same size) / (changed size) 1.25.913.498 I slot release: id 0 | task 3097 | stop processing: n_tokens = 188, truncated = 0 1.25.917.627 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.153 (> 0.100 thold), f_keep = 0.160 1.25.920.516 I slot launch_slot_: id 0 | task 3130 | processing task, is_child = 0 1.26.990.643 I slot print_timing: id 0 | task 3130 | prompt eval time = 464.14 ms / 196 tokens ( 2.37 ms per token, 422.28 tokens per second) 1.26.990.648 I slot print_timing: id 0 | task 3130 | eval time = 605.97 ms / 31 tokens ( 20.20 ms per token, 49.51 tokens per second) 1.26.990.649 I slot print_timing: id 0 | task 3130 | total time = 1070.12 ms / 227 tokens 1.26.990.650 I slot print_timing: id 0 | task 3130 | graphs reused = 2863 1.26.990.650 I slot print_timing: id 0 | task 3130 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.990.668 I slot release: id 0 | task 3130 | stop processing: n_tokens = 226, truncated = 0 1.26.994.462 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.133 1.27.001.653 I slot launch_slot_: id 0 | task 3164 | processing task, is_child = 0 1.27.876.122 I slot print_timing: id 0 | task 3164 | prompt eval time = 369.36 ms / 150 tokens ( 2.46 ms per token, 406.11 tokens per second) 1.27.876.128 I slot print_timing: id 0 | task 3164 | eval time = 505.10 ms / 26 tokens ( 20.20 ms per token, 49.50 tokens per second) 1.27.876.128 I slot print_timing: id 0 | task 3164 | total time = 874.46 ms / 176 tokens 1.27.876.129 I slot print_timing: id 0 | task 3164 | graphs reused = 2887 1.27.876.130 I slot print_timing: id 0 | task 3164 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.876.147 I slot release: id 0 | task 3164 | stop processing: n_tokens = 175, truncated = 0 1.27.880.377 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.140 (> 0.100 thold), f_keep = 0.171 1.27.884.963 I slot launch_slot_: id 0 | task 3193 | processing task, is_child = 0 1.29.179.967 I slot print_timing: id 0 | task 3193 | prompt eval time = 466.79 ms / 215 tokens ( 2.17 ms per token, 460.59 tokens per second) 1.29.179.973 I slot print_timing: id 0 | task 3193 | eval time = 828.20 ms / 42 tokens ( 20.20 ms per token, 49.50 tokens per second) 1.29.179.974 I slot print_timing: id 0 | task 3193 | total time = 1295.00 ms / 257 tokens 1.29.179.974 I slot print_timing: id 0 | task 3193 | graphs reused = 2927 1.29.179.975 I slot print_timing: id 0 | task 3193 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.179.994 I slot release: id 0 | task 3193 | stop processing: n_tokens = 256, truncated = 0 1.29.184.620 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 256, t_last = 333283987376 1.29.192.371 I slot launch_slot_: id 0 | task 3238 | processing task, is_child = 0 1.30.482.039 I slot print_timing: id 0 | task 3238 | prompt eval time = 680.30 ms / 327 tokens ( 2.08 ms per token, 480.67 tokens per second) 1.30.482.045 I slot print_timing: id 0 | task 3238 | eval time = 609.35 ms / 31 tokens ( 20.31 ms per token, 49.23 tokens per second) 1.30.482.045 I slot print_timing: id 0 | task 3238 | total time = 1289.66 ms / 358 tokens 1.30.482.046 I slot print_timing: id 0 | task 3238 | graphs reused = 2956 1.30.482.046 I slot print_timing: id 0 | task 3238 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.482.069 I slot release: id 0 | task 3238 | stop processing: n_tokens = 357, truncated = 0 1.30.487.244 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 357, t_last = 333285289451 1.30.498.202 I slot launch_slot_: id 0 | task 3272 | processing task, is_child = 0 1.31.916.755 I slot print_timing: id 0 | task 3272 | prompt eval time = 787.21 ms / 399 tokens ( 1.97 ms per token, 506.86 tokens per second) 1.31.916.761 I slot print_timing: id 0 | task 3272 | eval time = 631.34 ms / 32 tokens ( 20.37 ms per token, 49.10 tokens per second) 1.31.916.762 I slot print_timing: id 0 | task 3272 | total time = 1418.54 ms / 431 tokens 1.31.916.763 I slot print_timing: id 0 | task 3272 | graphs reused = 2986 1.31.916.763 I slot print_timing: id 0 | task 3272 | graph reallocs = 0 / 0 (same size) / (changed size) 1.31.916.787 I slot release: id 0 | task 3272 | stop processing: n_tokens = 430, truncated = 0 1.31.922.378 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 430, t_last = 333286724169 1.31.935.646 I slot launch_slot_: id 0 | task 3307 | processing task, is_child = 0 1.33.543.469 I slot print_timing: id 0 | task 3307 | prompt eval time = 891.03 ms / 439 tokens ( 2.03 ms per token, 492.69 tokens per second) 1.33.543.475 I slot print_timing: id 0 | task 3307 | eval time = 716.79 ms / 36 tokens ( 20.48 ms per token, 48.83 tokens per second) 1.33.543.475 I slot print_timing: id 0 | task 3307 | total time = 1607.81 ms / 475 tokens 1.33.543.476 I slot print_timing: id 0 | task 3307 | graphs reused = 3020 1.33.543.477 I slot print_timing: id 0 | task 3307 | graph reallocs = 0 / 0 (same size) / (changed size) 1.33.543.505 I slot release: id 0 | task 3307 | stop processing: n_tokens = 474, truncated = 0 1.33.548.963 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 474, t_last = 333288350887 1.33.563.869 I slot launch_slot_: id 0 | task 3346 | processing task, is_child = 0 1.35.040.831 I slot print_timing: id 0 | task 3346 | prompt eval time = 783.25 ms / 413 tokens ( 1.90 ms per token, 527.29 tokens per second) 1.35.040.837 I slot print_timing: id 0 | task 3346 | eval time = 693.69 ms / 35 tokens ( 20.40 ms per token, 49.01 tokens per second) 1.35.040.838 I slot print_timing: id 0 | task 3346 | total time = 1476.95 ms / 448 tokens 1.35.040.838 I slot print_timing: id 0 | task 3346 | graphs reused = 3053 1.35.040.839 I slot print_timing: id 0 | task 3346 | graph reallocs = 0 / 0 (same size) / (changed size) 1.35.040.873 I slot release: id 0 | task 3346 | stop processing: n_tokens = 447, truncated = 0 1.35.045.437 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.112 (> 0.100 thold), f_keep = 0.067 1.35.059.282 I slot launch_slot_: id 0 | task 3384 | processing task, is_child = 0 1.38.641.322 I slot print_timing: id 0 | task 3384 | n_gen = 150, tg = 49.43 t/s, tg_3s = 49.77 t/s 1.39.229.737 I slot print_timing: id 0 | task 3384 | prompt eval time = 567.96 ms / 268 tokens ( 2.12 ms per token, 471.86 tokens per second) 1.39.229.743 I slot print_timing: id 0 | task 3384 | eval time = 3602.48 ms / 179 tokens ( 20.24 ms per token, 49.41 tokens per second) 1.39.229.743 I slot print_timing: id 0 | task 3384 | total time = 4170.44 ms / 447 tokens 1.39.229.744 I slot print_timing: id 0 | task 3384 | graphs reused = 3230 1.39.229.745 I slot print_timing: id 0 | task 3384 | graph reallocs = 0 / 0 (same size) / (changed size) 1.39.229.765 I slot release: id 0 | task 3384 | stop processing: n_tokens = 446, truncated = 0 1.39.234.854 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 446, t_last = 333294037147 1.39.242.746 I slot launch_slot_: id 0 | task 3566 | processing task, is_child = 0 1.42.940.026 I slot print_timing: id 0 | task 3566 | prompt eval time = 788.24 ms / 395 tokens ( 2.00 ms per token, 501.12 tokens per second) 1.42.940.032 I slot print_timing: id 0 | task 3566 | eval time = 2909.03 ms / 143 tokens ( 20.49 ms per token, 48.81 tokens per second) 1.42.940.032 I slot print_timing: id 0 | task 3566 | total time = 3697.27 ms / 538 tokens 1.42.940.033 I slot print_timing: id 0 | task 3566 | graphs reused = 3370 1.42.940.034 I slot print_timing: id 0 | task 3566 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.940.061 I slot release: id 0 | task 3566 | stop processing: n_tokens = 537, truncated = 0 1.42.945.021 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 537, t_last = 333297747443 1.42.960.641 I slot launch_slot_: id 0 | task 3712 | processing task, is_child = 0 1.46.757.118 I slot print_timing: id 0 | task 3712 | n_gen = 148, tg = 48.85 t/s, tg_3s = 49.19 t/s 1.47.334.099 I slot print_timing: id 0 | task 3712 | prompt eval time = 787.54 ms / 390 tokens ( 2.02 ms per token, 495.21 tokens per second) 1.47.334.105 I slot print_timing: id 0 | task 3712 | eval time = 3585.90 ms / 176 tokens ( 20.49 ms per token, 48.80 tokens per second) 1.47.334.106 I slot print_timing: id 0 | task 3712 | total time = 4373.45 ms / 566 tokens 1.47.334.106 I slot print_timing: id 0 | task 3712 | graphs reused = 3543 1.47.334.107 I slot print_timing: id 0 | task 3712 | graph reallocs = 0 / 0 (same size) / (changed size) 1.47.334.138 I slot release: id 0 | task 3712 | stop processing: n_tokens = 565, truncated = 0 1.47.339.294 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 565, t_last = 333302141520 1.47.354.140 I slot launch_slot_: id 0 | task 3891 | processing task, is_child = 0 1.48.467.506 I slot print_timing: id 0 | task 3891 | prompt eval time = 626.13 ms / 304 tokens ( 2.06 ms per token, 485.52 tokens per second) 1.48.467.512 I slot print_timing: id 0 | task 3891 | eval time = 487.23 ms / 25 tokens ( 20.30 ms per token, 49.26 tokens per second) 1.48.467.513 I slot print_timing: id 0 | task 3891 | total time = 1113.36 ms / 329 tokens 1.48.467.514 I slot print_timing: id 0 | task 3891 | graphs reused = 3566 1.48.467.515 I slot print_timing: id 0 | task 3891 | graph reallocs = 0 / 0 (same size) / (changed size) 1.48.467.537 I slot release: id 0 | task 3891 | stop processing: n_tokens = 328, truncated = 0 1.48.472.043 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.104 (> 0.100 thold), f_keep = 0.091 1.48.478.455 I slot launch_slot_: id 0 | task 3919 | processing task, is_child = 0 1.49.717.040 I slot print_timing: id 0 | task 3919 | prompt eval time = 626.22 ms / 289 tokens ( 2.17 ms per token, 461.50 tokens per second) 1.49.717.045 I slot print_timing: id 0 | task 3919 | eval time = 612.36 ms / 31 tokens ( 20.41 ms per token, 48.99 tokens per second) 1.49.717.046 I slot print_timing: id 0 | task 3919 | total time = 1238.57 ms / 320 tokens 1.49.717.047 I slot print_timing: id 0 | task 3919 | graphs reused = 3595 1.49.717.047 I slot print_timing: id 0 | task 3919 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.717.067 I slot release: id 0 | task 3919 | stop processing: n_tokens = 319, truncated = 0 1.49.722.066 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 319, t_last = 333304524449 1.49.731.938 I slot launch_slot_: id 0 | task 3953 | processing task, is_child = 0 1.50.861.545 I slot print_timing: id 0 | task 3953 | prompt eval time = 700.74 ms / 360 tokens ( 1.95 ms per token, 513.74 tokens per second) 1.50.861.548 I slot print_timing: id 0 | task 3953 | eval time = 428.86 ms / 22 tokens ( 20.42 ms per token, 48.97 tokens per second) 1.50.861.549 I slot print_timing: id 0 | task 3953 | total time = 1129.60 ms / 382 tokens 1.50.861.549 I slot print_timing: id 0 | task 3953 | graphs reused = 3615 1.50.861.550 I slot print_timing: id 0 | task 3953 | graph reallocs = 0 / 0 (same size) / (changed size) 1.50.861.582 I slot release: id 0 | task 3953 | stop processing: n_tokens = 381, truncated = 0 1.50.866.731 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 381, t_last = 333305668964 1.50.879.341 I slot launch_slot_: id 0 | task 3978 | processing task, is_child = 0 1.52.279.768 I slot print_timing: id 0 | task 3978 | prompt eval time = 678.18 ms / 317 tokens ( 2.14 ms per token, 467.43 tokens per second) 1.52.279.774 I slot print_timing: id 0 | task 3978 | eval time = 722.24 ms / 36 tokens ( 20.64 ms per token, 48.46 tokens per second) 1.52.279.776 I slot print_timing: id 0 | task 3978 | total time = 1400.41 ms / 353 tokens 1.52.279.777 I slot print_timing: id 0 | task 3978 | graphs reused = 3649 1.52.279.777 I slot print_timing: id 0 | task 3978 | graph reallocs = 0 / 0 (same size) / (changed size) 1.52.279.807 I slot release: id 0 | task 3978 | stop processing: n_tokens = 352, truncated = 0 1.52.284.218 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.121 (> 0.100 thold), f_keep = 0.085 1.52.291.130 I slot launch_slot_: id 0 | task 4017 | processing task, is_child = 0 1.53.191.442 I slot print_timing: id 0 | task 4017 | prompt eval time = 533.52 ms / 248 tokens ( 2.15 ms per token, 464.84 tokens per second) 1.53.191.448 I slot print_timing: id 0 | task 4017 | eval time = 366.78 ms / 19 tokens ( 20.38 ms per token, 49.08 tokens per second) 1.53.191.449 I slot print_timing: id 0 | task 4017 | total time = 900.30 ms / 267 tokens 1.53.191.449 I slot print_timing: id 0 | task 4017 | graphs reused = 3665 1.53.191.450 I slot print_timing: id 0 | task 4017 | graph reallocs = 0 / 0 (same size) / (changed size) 1.53.191.470 I slot release: id 0 | task 4017 | stop processing: n_tokens = 266, truncated = 0 1.53.196.343 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 266, t_last = 333307998852 1.53.204.537 I slot launch_slot_: id 0 | task 4039 | processing task, is_child = 0 1.55.126.458 I slot print_timing: id 0 | task 4039 | prompt eval time = 683.51 ms / 331 tokens ( 2.06 ms per token, 484.27 tokens per second) 1.55.126.461 I slot print_timing: id 0 | task 4039 | eval time = 1238.41 ms / 62 tokens ( 20.30 ms per token, 49.26 tokens per second) 1.55.126.462 I slot print_timing: id 0 | task 4039 | total time = 1921.91 ms / 393 tokens 1.55.126.463 I slot print_timing: id 0 | task 4039 | graphs reused = 3725 1.55.126.463 I slot print_timing: id 0 | task 4039 | graph reallocs = 0 / 0 (same size) / (changed size) 1.55.126.489 I slot release: id 0 | task 4039 | stop processing: n_tokens = 392, truncated = 0 1.55.131.131 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.107 (> 0.100 thold), f_keep = 0.077 1.55.144.038 I slot launch_slot_: id 0 | task 4104 | processing task, is_child = 0 1.56.201.042 I slot print_timing: id 0 | task 4104 | prompt eval time = 590.56 ms / 280 tokens ( 2.11 ms per token, 474.12 tokens per second) 1.56.201.048 I slot print_timing: id 0 | task 4104 | eval time = 466.43 ms / 24 tokens ( 20.28 ms per token, 49.31 tokens per second) 1.56.201.049 I slot print_timing: id 0 | task 4104 | total time = 1056.99 ms / 304 tokens 1.56.201.049 I slot print_timing: id 0 | task 4104 | graphs reused = 3747 1.56.201.050 I slot print_timing: id 0 | task 4104 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.201.071 I slot release: id 0 | task 4104 | stop processing: n_tokens = 303, truncated = 0 1.56.205.507 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.119 (> 0.100 thold), f_keep = 0.099 1.56.213.747 I slot launch_slot_: id 0 | task 4131 | processing task, is_child = 0 1.57.229.027 I slot print_timing: id 0 | task 4131 | prompt eval time = 567.68 ms / 252 tokens ( 2.25 ms per token, 443.91 tokens per second) 1.57.229.033 I slot print_timing: id 0 | task 4131 | eval time = 447.59 ms / 23 tokens ( 20.34 ms per token, 49.15 tokens per second) 1.57.229.034 I slot print_timing: id 0 | task 4131 | total time = 1015.27 ms / 275 tokens 1.57.229.035 I slot print_timing: id 0 | task 4131 | graphs reused = 3767 1.57.229.035 I slot print_timing: id 0 | task 4131 | graph reallocs = 0 / 0 (same size) / (changed size) 1.57.229.055 I slot release: id 0 | task 4131 | stop processing: n_tokens = 274, truncated = 0 1.57.233.559 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.112 (> 0.100 thold), f_keep = 0.109 1.57.242.077 I slot launch_slot_: id 0 | task 4157 | processing task, is_child = 0 1.58.205.519 I slot print_timing: id 0 | task 4157 | prompt eval time = 537.15 ms / 267 tokens ( 2.01 ms per token, 497.06 tokens per second) 1.58.205.522 I slot print_timing: id 0 | task 4157 | eval time = 426.28 ms / 22 tokens ( 20.30 ms per token, 49.26 tokens per second) 1.58.205.523 I slot print_timing: id 0 | task 4157 | total time = 963.43 ms / 289 tokens 1.58.205.523 I slot print_timing: id 0 | task 4157 | graphs reused = 3787 1.58.205.524 I slot print_timing: id 0 | task 4157 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.205.549 I slot release: id 0 | task 4157 | stop processing: n_tokens = 288, truncated = 0 1.58.210.012 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.118 (> 0.100 thold), f_keep = 0.104 1.58.219.116 I slot launch_slot_: id 0 | task 4182 | processing task, is_child = 0 1.59.211.528 I slot print_timing: id 0 | task 4182 | prompt eval time = 565.67 ms / 255 tokens ( 2.22 ms per token, 450.80 tokens per second) 1.59.211.534 I slot print_timing: id 0 | task 4182 | eval time = 426.73 ms / 22 tokens ( 20.32 ms per token, 49.21 tokens per second) 1.59.211.535 I slot print_timing: id 0 | task 4182 | total time = 992.40 ms / 277 tokens 1.59.211.535 I slot print_timing: id 0 | task 4182 | graphs reused = 3806 1.59.211.536 I slot print_timing: id 0 | task 4182 | graph reallocs = 0 / 0 (same size) / (changed size) 1.59.211.556 I slot release: id 0 | task 4182 | stop processing: n_tokens = 276, truncated = 0 1.59.216.839 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 276, t_last = 333314018938 1.59.225.565 I slot launch_slot_: id 0 | task 4207 | processing task, is_child = 0 2.00.607.300 I slot print_timing: id 0 | task 4207 | prompt eval time = 789.77 ms / 397 tokens ( 1.99 ms per token, 502.68 tokens per second) 2.00.607.306 I slot print_timing: id 0 | task 4207 | eval time = 591.96 ms / 30 tokens ( 20.41 ms per token, 48.99 tokens per second) 2.00.607.307 I slot print_timing: id 0 | task 4207 | total time = 1381.72 ms / 427 tokens 2.00.607.308 I slot print_timing: id 0 | task 4207 | graphs reused = 3834 2.00.607.308 I slot print_timing: id 0 | task 4207 | graph reallocs = 0 / 0 (same size) / (changed size) 2.00.607.334 I slot release: id 0 | task 4207 | stop processing: n_tokens = 426, truncated = 0 2.00.612.170 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.103 (> 0.100 thold), f_keep = 0.070 2.00.626.221 I slot launch_slot_: id 0 | task 4240 | processing task, is_child = 0 2.03.030.832 I slot print_timing: id 0 | task 4240 | prompt eval time = 625.12 ms / 290 tokens ( 2.16 ms per token, 463.91 tokens per second) 2.03.030.838 I slot print_timing: id 0 | task 4240 | eval time = 1779.49 ms / 89 tokens ( 20.22 ms per token, 49.45 tokens per second) 2.03.030.839 I slot print_timing: id 0 | task 4240 | total time = 2404.60 ms / 379 tokens 2.03.030.840 I slot print_timing: id 0 | task 4240 | graphs reused = 3921 2.03.030.841 I slot print_timing: id 0 | task 4240 | graph reallocs = 0 / 0 (same size) / (changed size) 2.03.030.862 I slot release: id 0 | task 4240 | stop processing: n_tokens = 378, truncated = 0 2.03.037.129 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 378, t_last = 333317838244 2.03.044.182 I slot launch_slot_: id 0 | task 4332 | processing task, is_child = 0 2.06.881.523 I slot print_timing: id 0 | task 4332 | prompt eval time = 1199.34 ms / 612 tokens ( 1.96 ms per token, 510.28 tokens per second) 2.06.881.530 I slot print_timing: id 0 | task 4332 | eval time = 2637.99 ms / 129 tokens ( 20.61 ms per token, 48.52 tokens per second) 2.06.881.531 I slot print_timing: id 0 | task 4332 | total time = 3837.33 ms / 741 tokens 2.06.881.532 I slot print_timing: id 0 | task 4332 | graphs reused = 4048 2.06.881.532 I slot print_timing: id 0 | task 4332 | graph reallocs = 0 / 0 (same size) / (changed size) 2.06.881.567 I slot release: id 0 | task 4332 | stop processing: n_tokens = 740, truncated = 0 2.06.886.214 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.109 (> 0.100 thold), f_keep = 0.041 2.06.907.344 I slot launch_slot_: id 0 | task 4465 | processing task, is_child = 0 2.07.883.114 I slot print_timing: id 0 | task 4465 | prompt eval time = 569.03 ms / 275 tokens ( 2.07 ms per token, 483.27 tokens per second) 2.07.883.121 I slot print_timing: id 0 | task 4465 | eval time = 406.71 ms / 21 tokens ( 20.34 ms per token, 49.17 tokens per second) 2.07.883.121 I slot print_timing: id 0 | task 4465 | total time = 975.75 ms / 296 tokens 2.07.883.122 I slot print_timing: id 0 | task 4465 | graphs reused = 4067 2.07.883.123 I slot print_timing: id 0 | task 4465 | graph reallocs = 0 / 0 (same size) / (changed size) 2.07.883.148 I slot release: id 0 | task 4465 | stop processing: n_tokens = 295, truncated = 0 2.07.888.637 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 295, t_last = 333322690530 2.07.893.003 I slot launch_slot_: id 0 | task 4489 | processing task, is_child = 0 2.09.293.193 I slot print_timing: id 0 | task 4489 | prompt eval time = 905.69 ms / 456 tokens ( 1.99 ms per token, 503.48 tokens per second) 2.09.293.199 I slot print_timing: id 0 | task 4489 | eval time = 494.49 ms / 25 tokens ( 20.60 ms per token, 48.53 tokens per second) 2.09.293.200 I slot print_timing: id 0 | task 4489 | total time = 1400.18 ms / 481 tokens 2.09.293.200 I slot print_timing: id 0 | task 4489 | graphs reused = 4090 2.09.293.201 I slot print_timing: id 0 | task 4489 | graph reallocs = 0 / 0 (same size) / (changed size) 2.09.293.237 I slot release: id 0 | task 4489 | stop processing: n_tokens = 480, truncated = 0 2.09.299.511 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 480, t_last = 333324100619 2.09.315.698 I slot launch_slot_: id 0 | task 4517 | processing task, is_child = 0 2.11.196.136 I slot print_timing: id 0 | task 4517 | prompt eval time = 1095.92 ms / 542 tokens ( 2.02 ms per token, 494.56 tokens per second) 2.11.196.139 I slot print_timing: id 0 | task 4517 | eval time = 784.51 ms / 39 tokens ( 20.64 ms per token, 48.44 tokens per second) 2.11.196.140 I slot print_timing: id 0 | task 4517 | total time = 1880.42 ms / 581 tokens 2.11.196.141 I slot print_timing: id 0 | task 4517 | graphs reused = 4127 2.11.196.141 I slot print_timing: id 0 | task 4517 | graph reallocs = 0 / 0 (same size) / (changed size) 2.11.196.193 I slot release: id 0 | task 4517 | stop processing: n_tokens = 580, truncated = 0 2.11.201.442 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 580, t_last = 333326003575 2.11.218.580 I slot launch_slot_: id 0 | task 4560 | processing task, is_child = 0 2.12.875.301 I slot print_timing: id 0 | task 4560 | prompt eval time = 781.02 ms / 361 tokens ( 2.16 ms per token, 462.22 tokens per second) 2.12.875.307 I slot print_timing: id 0 | task 4560 | eval time = 875.70 ms / 44 tokens ( 20.37 ms per token, 49.10 tokens per second) 2.12.875.308 I slot print_timing: id 0 | task 4560 | total time = 1656.71 ms / 405 tokens 2.12.875.309 I slot print_timing: id 0 | task 4560 | graphs reused = 4169 2.12.875.309 I slot print_timing: id 0 | task 4560 | graph reallocs = 0 / 0 (same size) / (changed size) 2.12.875.335 I slot release: id 0 | task 4560 | stop processing: n_tokens = 429, truncated = 0 2.12.879.821 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.106 (> 0.100 thold), f_keep = 0.070 2.12.888.159 I slot launch_slot_: id 0 | task 4607 | processing task, is_child = 0 2.14.225.633 I slot print_timing: id 0 | task 4607 | prompt eval time = 568.93 ms / 258 tokens ( 2.21 ms per token, 453.48 tokens per second) 2.14.225.636 I slot print_timing: id 0 | task 4607 | eval time = 768.53 ms / 39 tokens ( 20.22 ms per token, 49.45 tokens per second) 2.14.225.637 I slot print_timing: id 0 | task 4607 | total time = 1337.46 ms / 297 tokens 2.14.225.637 I slot print_timing: id 0 | task 4607 | graphs reused = 4206 2.14.225.638 I slot print_timing: id 0 | task 4607 | graph reallocs = 0 / 0 (same size) / (changed size) 2.14.225.659 I slot release: id 0 | task 4607 | stop processing: n_tokens = 320, truncated = 0 2.14.230.913 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 320, t_last = 333329033041 2.14.234.279 I slot launch_slot_: id 0 | task 4649 | processing task, is_child = 0 2.15.452.621 I slot print_timing: id 0 | task 4649 | prompt eval time = 790.11 ms / 379 tokens ( 2.08 ms per token, 479.68 tokens per second) 2.15.452.627 I slot print_timing: id 0 | task 4649 | eval time = 428.23 ms / 22 tokens ( 20.39 ms per token, 49.04 tokens per second) 2.15.452.628 I slot print_timing: id 0 | task 4649 | total time = 1218.33 ms / 401 tokens 2.15.452.632 I slot print_timing: id 0 | task 4649 | graphs reused = 4226 2.15.452.637 I slot print_timing: id 0 | task 4649 | graph reallocs = 0 / 0 (same size) / (changed size) 2.15.452.664 I slot release: id 0 | task 4649 | stop processing: n_tokens = 423, truncated = 0 2.15.458.901 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 423, t_last = 333330260047 2.15.472.660 I slot launch_slot_: id 0 | task 4674 | processing task, is_child = 0 2.17.113.487 I slot print_timing: id 0 | task 4674 | prompt eval time = 1102.92 ms / 540 tokens ( 2.04 ms per token, 489.61 tokens per second) 2.17.113.489 I slot print_timing: id 0 | task 4674 | eval time = 537.89 ms / 27 tokens ( 20.69 ms per token, 48.34 tokens per second) 2.17.113.490 I slot print_timing: id 0 | task 4674 | total time = 1640.82 ms / 567 tokens 2.17.113.491 I slot print_timing: id 0 | task 4674 | graphs reused = 4251 2.17.113.492 I slot print_timing: id 0 | task 4674 | graph reallocs = 0 / 0 (same size) / (changed size) 2.17.113.525 I slot release: id 0 | task 4674 | stop processing: n_tokens = 588, truncated = 0 2.17.118.844 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 588, t_last = 333331920907 2.17.139.073 I slot launch_slot_: id 0 | task 4705 | processing task, is_child = 0 2.18.445.970 I slot print_timing: id 0 | task 4705 | prompt eval time = 736.15 ms / 370 tokens ( 1.99 ms per token, 502.61 tokens per second) 2.18.445.977 I slot print_timing: id 0 | task 4705 | eval time = 570.73 ms / 29 tokens ( 20.38 ms per token, 49.06 tokens per second) 2.18.445.977 I slot print_timing: id 0 | task 4705 | total time = 1306.89 ms / 399 tokens 2.18.445.978 I slot print_timing: id 0 | task 4705 | graphs reused = 4278 2.18.445.978 I slot print_timing: id 0 | task 4705 | graph reallocs = 0 / 0 (same size) / (changed size) 2.18.446.008 I slot release: id 0 | task 4705 | stop processing: n_tokens = 422, truncated = 0 2.18.451.137 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 422, t_last = 333333253390 2.18.455.092 I slot launch_slot_: id 0 | task 4737 | processing task, is_child = 0 2.19.626.311 I slot print_timing: id 0 | task 4737 | prompt eval time = 682.89 ms / 336 tokens ( 2.03 ms per token, 492.03 tokens per second) 2.19.626.317 I slot print_timing: id 0 | task 4737 | eval time = 488.32 ms / 25 tokens ( 20.35 ms per token, 49.15 tokens per second) 2.19.626.318 I slot print_timing: id 0 | task 4737 | total time = 1171.21 ms / 361 tokens 2.19.626.318 I slot print_timing: id 0 | task 4737 | graphs reused = 4301 2.19.626.319 I slot print_timing: id 0 | task 4737 | graph reallocs = 0 / 0 (same size) / (changed size) 2.19.626.344 I slot release: id 0 | task 4737 | stop processing: n_tokens = 383, truncated = 0 2.19.630.886 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.115 (> 0.100 thold), f_keep = 0.078 2.19.638.055 I slot launch_slot_: id 0 | task 4765 | processing task, is_child = 0 2.20.642.943 I slot print_timing: id 0 | task 4765 | prompt eval time = 537.79 ms / 261 tokens ( 2.06 ms per token, 485.32 tokens per second) 2.20.642.946 I slot print_timing: id 0 | task 4765 | eval time = 467.09 ms / 24 tokens ( 20.31 ms per token, 49.24 tokens per second) 2.20.642.946 I slot print_timing: id 0 | task 4765 | total time = 1004.88 ms / 285 tokens 2.20.642.947 I slot print_timing: id 0 | task 4765 | graphs reused = 4323 2.20.642.948 I slot print_timing: id 0 | task 4765 | graph reallocs = 0 / 0 (same size) / (changed size) 2.20.642.973 I slot release: id 0 | task 4765 | stop processing: n_tokens = 284, truncated = 0 2.20.647.786 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.100 (> 0.100 thold), f_keep = 0.106 2.20.650.642 I slot launch_slot_: id 0 | task 4792 | processing task, is_child = 0 2.22.113.127 I slot print_timing: id 0 | task 4792 | prompt eval time = 672.31 ms / 299 tokens ( 2.25 ms per token, 444.73 tokens per second) 2.22.113.133 I slot print_timing: id 0 | task 4792 | eval time = 790.16 ms / 40 tokens ( 20.26 ms per token, 49.36 tokens per second) 2.22.113.134 I slot print_timing: id 0 | task 4792 | total time = 1462.48 ms / 339 tokens 2.22.113.135 I slot print_timing: id 0 | task 4792 | graphs reused = 4361 2.22.113.135 I slot print_timing: id 0 | task 4792 | graph reallocs = 0 / 0 (same size) / (changed size) 2.22.113.166 I slot release: id 0 | task 4792 | stop processing: n_tokens = 338, truncated = 0 2.22.118.162 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 338, t_last = 333336920548 2.22.127.264 I slot launch_slot_: id 0 | task 4835 | processing task, is_child = 0 2.23.313.097 I slot print_timing: id 0 | task 4835 | prompt eval time = 677.66 ms / 319 tokens ( 2.12 ms per token, 470.74 tokens per second) 2.23.313.103 I slot print_timing: id 0 | task 4835 | eval time = 508.16 ms / 26 tokens ( 20.33 ms per token, 49.20 tokens per second) 2.23.313.104 I slot print_timing: id 0 | task 4835 | total time = 1185.82 ms / 345 tokens 2.23.313.105 I slot print_timing: id 0 | task 4835 | graphs reused = 4385 2.23.313.106 I slot print_timing: id 0 | task 4835 | graph reallocs = 0 / 0 (same size) / (changed size) 2.23.313.145 I slot release: id 0 | task 4835 | stop processing: n_tokens = 344, truncated = 0 2.23.319.179 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 344, t_last = 333338120527 2.23.330.505 I slot launch_slot_: id 0 | task 4864 | processing task, is_child = 0 2.24.857.958 I slot print_timing: id 0 | task 4864 | prompt eval time = 811.91 ms / 423 tokens ( 1.92 ms per token, 520.99 tokens per second) 2.24.857.963 I slot print_timing: id 0 | task 4864 | eval time = 715.53 ms / 36 tokens ( 20.44 ms per token, 48.91 tokens per second) 2.24.857.964 I slot print_timing: id 0 | task 4864 | total time = 1527.44 ms / 459 tokens 2.24.857.965 I slot print_timing: id 0 | task 4864 | graphs reused = 4419 2.24.857.965 I slot print_timing: id 0 | task 4864 | graph reallocs = 0 / 0 (same size) / (changed size) 2.24.857.998 I slot release: id 0 | task 4864 | stop processing: n_tokens = 458, truncated = 0 2.24.863.153 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 333339665380 2.24.878.072 I slot launch_slot_: id 0 | task 4903 | processing task, is_child = 0 2.26.183.228 I slot print_timing: id 0 | task 4903 | prompt eval time = 735.59 ms / 366 tokens ( 2.01 ms per token, 497.56 tokens per second) 2.26.183.233 I slot print_timing: id 0 | task 4903 | eval time = 569.56 ms / 29 tokens ( 20.34 ms per token, 49.16 tokens per second) 2.26.183.233 I slot print_timing: id 0 | task 4903 | total time = 1305.14 ms / 395 tokens 2.26.183.234 I slot print_timing: id 0 | task 4903 | graphs reused = 4446 2.26.183.235 I slot print_timing: id 0 | task 4903 | graph reallocs = 0 / 0 (same size) / (changed size) 2.26.183.258 I slot release: id 0 | task 4903 | stop processing: n_tokens = 394, truncated = 0 2.26.189.575 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 394, t_last = 333340990640 2.26.189.624 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 60.760 MiB) 2.26.201.545 I slot launch_slot_: id 0 | task 4935 | processing task, is_child = 0 2.27.900.838 I slot print_timing: id 0 | task 4935 | prompt eval time = 1116.69 ms / 560 tokens ( 1.99 ms per token, 501.48 tokens per second) 2.27.900.842 I slot print_timing: id 0 | task 4935 | eval time = 582.59 ms / 29 tokens ( 20.81 ms per token, 48.06 tokens per second) 2.27.900.843 I slot print_timing: id 0 | task 4935 | total time = 1699.28 ms / 589 tokens 2.27.900.843 I slot print_timing: id 0 | task 4935 | graphs reused = 4473 2.27.900.844 I slot print_timing: id 0 | task 4935 | graph reallocs = 0 / 0 (same size) / (changed size) 2.27.900.893 I slot release: id 0 | task 4935 | stop processing: n_tokens = 588, truncated = 0 2.27.906.979 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 588, t_last = 333342708275 2.27.907.058 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 44.657 MiB) 2.27.907.064 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 59.776 MiB) 2.27.907.067 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 71.238 MiB) 2.27.926.644 I slot launch_slot_: id 0 | task 4968 | processing task, is_child = 0 2.29.107.871 I slot print_timing: id 0 | task 4968 | prompt eval time = 733.03 ms / 366 tokens ( 2.00 ms per token, 499.30 tokens per second) 2.29.107.874 I slot print_timing: id 0 | task 4968 | eval time = 448.18 ms / 23 tokens ( 20.37 ms per token, 49.09 tokens per second) 2.29.107.875 I slot print_timing: id 0 | task 4968 | total time = 1181.21 ms / 389 tokens 2.29.107.875 I slot print_timing: id 0 | task 4968 | graphs reused = 4494 2.29.107.876 I slot print_timing: id 0 | task 4968 | graph reallocs = 0 / 0 (same size) / (changed size) 2.29.107.908 I slot release: id 0 | task 4968 | stop processing: n_tokens = 388, truncated = 0 2.29.113.320 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 388, t_last = 333343915290 2.29.113.376 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 75.985 MiB) 2.29.113.383 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 62.132 MiB) 2.29.120.924 I slot launch_slot_: id 0 | task 4994 | processing task, is_child = 0 2.30.524.236 I slot print_timing: id 0 | task 4994 | prompt eval time = 790.10 ms / 406 tokens ( 1.95 ms per token, 513.86 tokens per second) 2.30.524.242 I slot print_timing: id 0 | task 4994 | eval time = 613.20 ms / 31 tokens ( 20.44 ms per token, 48.92 tokens per second) 2.30.524.242 I slot print_timing: id 0 | task 4994 | total time = 1403.30 ms / 437 tokens 2.30.524.243 I slot print_timing: id 0 | task 4994 | graphs reused = 4523 2.30.524.244 I slot print_timing: id 0 | task 4994 | graph reallocs = 0 / 0 (same size) / (changed size) 2.30.524.278 I slot release: id 0 | task 4994 | stop processing: n_tokens = 436, truncated = 0 2.30.529.549 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 436, t_last = 333345331660 2.30.529.619 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 97.539 MiB) 2.30.529.630 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 125.668 MiB) 2.30.533.584 I slot launch_slot_: id 0 | task 5028 | processing task, is_child = 0 2.32.114.009 I slot print_timing: id 0 | task 5028 | prompt eval time = 786.71 ms / 379 tokens ( 2.08 ms per token, 481.75 tokens per second) 2.32.114.015 I slot print_timing: id 0 | task 5028 | eval time = 793.70 ms / 40 tokens ( 20.35 ms per token, 49.14 tokens per second) 2.32.114.016 I slot print_timing: id 0 | task 5028 | total time = 1580.41 ms / 419 tokens 2.32.114.016 I slot print_timing: id 0 | task 5028 | graphs reused = 4561 2.32.114.017 I slot print_timing: id 0 | task 5028 | graph reallocs = 0 / 0 (same size) / (changed size) 2.32.114.048 I slot release: id 0 | task 5028 | stop processing: n_tokens = 418, truncated = 0 2.32.119.907 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 418, t_last = 333346921430 2.32.119.958 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 53.271 MiB) 2.32.132.868 I slot launch_slot_: id 0 | task 5071 | processing task, is_child = 0 2.33.669.369 I slot print_timing: id 0 | task 5071 | prompt eval time = 955.75 ms / 487 tokens ( 1.96 ms per token, 509.55 tokens per second) 2.33.669.375 I slot print_timing: id 0 | task 5071 | eval time = 580.74 ms / 29 tokens ( 20.74 ms per token, 48.21 tokens per second) 2.33.669.376 I slot print_timing: id 0 | task 5071 | total time = 1536.49 ms / 516 tokens 2.33.669.377 I slot print_timing: id 0 | task 5071 | graphs reused = 4587 2.33.669.377 I slot print_timing: id 0 | task 5071 | graph reallocs = 0 / 0 (same size) / (changed size) 2.33.669.409 I slot release: id 0 | task 5071 | stop processing: n_tokens = 515, truncated = 0 2.33.675.750 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 515, t_last = 333348476791 2.33.675.807 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 57.701 MiB) 2.33.675.810 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 95.324 MiB) 2.33.690.060 I slot launch_slot_: id 0 | task 5103 | processing task, is_child = 0 2.36.077.922 I slot print_timing: id 0 | task 5103 | prompt eval time = 1148.55 ms / 565 tokens ( 2.03 ms per token, 491.92 tokens per second) 2.36.077.928 I slot print_timing: id 0 | task 5103 | eval time = 1239.30 ms / 61 tokens ( 20.66 ms per token, 48.41 tokens per second) 2.36.077.929 I slot print_timing: id 0 | task 5103 | total time = 2387.85 ms / 626 tokens 2.36.077.930 I slot print_timing: id 0 | task 5103 | graphs reused = 4646 2.36.077.930 I slot print_timing: id 0 | task 5103 | graph reallocs = 0 / 0 (same size) / (changed size) 2.36.077.969 I slot release: id 0 | task 5103 | stop processing: n_tokens = 625, truncated = 0 2.36.082.053 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.153 (> 0.100 thold), f_keep = 0.048 2.36.082.130 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 96.730 MiB) 2.36.082.137 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 64.909 MiB) 2.36.082.139 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.261 MiB) 2.36.097.145 I slot launch_slot_: id 0 | task 5168 | processing task, is_child = 0 2.37.134.538 I slot print_timing: id 0 | task 5168 | prompt eval time = 451.94 ms / 196 tokens ( 2.31 ms per token, 433.69 tokens per second) 2.37.134.544 I slot print_timing: id 0 | task 5168 | eval time = 585.44 ms / 30 tokens ( 20.19 ms per token, 49.54 tokens per second) 2.37.134.544 I slot print_timing: id 0 | task 5168 | total time = 1037.38 ms / 226 tokens 2.37.134.545 I slot print_timing: id 0 | task 5168 | graphs reused = 4674 2.37.134.546 I slot print_timing: id 0 | task 5168 | graph reallocs = 0 / 0 (same size) / (changed size) 2.37.134.564 I slot release: id 0 | task 5168 | stop processing: n_tokens = 225, truncated = 0 2.37.138.621 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.140 (> 0.100 thold), f_keep = 0.133 2.37.138.660 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 61.921 MiB) 2.37.140.837 I slot launch_slot_: id 0 | task 5201 | processing task, is_child = 0 2.38.863.497 I slot print_timing: id 0 | task 5201 | prompt eval time = 511.17 ms / 214 tokens ( 2.39 ms per token, 418.65 tokens per second) 2.38.863.501 I slot print_timing: id 0 | task 5201 | eval time = 1211.48 ms / 61 tokens ( 20.19 ms per token, 49.53 tokens per second) 2.38.863.501 I slot print_timing: id 0 | task 5201 | total time = 1722.64 ms / 275 tokens 2.38.863.502 I slot print_timing: id 0 | task 5201 | graphs reused = 4732 2.38.863.503 I slot print_timing: id 0 | task 5201 | graph reallocs = 0 / 0 (same size) / (changed size) 2.38.863.533 I slot release: id 0 | task 5201 | stop processing: n_tokens = 274, truncated = 0 2.38.868.120 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.149 (> 0.100 thold), f_keep = 0.109 2.38.868.164 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 53.728 MiB) 2.38.870.669 I slot launch_slot_: id 0 | task 5265 | processing task, is_child = 0 2.41.088.971 I slot print_timing: id 0 | task 5265 | prompt eval time = 509.91 ms / 201 tokens ( 2.54 ms per token, 394.19 tokens per second) 2.41.088.978 I slot print_timing: id 0 | task 5265 | eval time = 1708.38 ms / 85 tokens ( 20.34 ms per token, 49.17 tokens per second) 2.41.088.978 I slot print_timing: id 0 | task 5265 | total time = 2218.29 ms / 286 tokens 2.41.088.979 I slot print_timing: id 0 | task 5265 | graphs reused = 4814 2.41.088.980 I slot print_timing: id 0 | task 5265 | graph reallocs = 0 / 0 (same size) / (changed size) 2.41.089.003 I slot release: id 0 | task 5265 | stop processing: n_tokens = 285, truncated = 0 2.41.093.107 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.179 (> 0.100 thold), f_keep = 0.105 2.41.093.151 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 60.620 MiB) 2.41.095.428 I slot launch_slot_: id 0 | task 5353 | processing task, is_child = 0 2.42.935.540 I slot print_timing: id 0 | task 5353 | prompt eval time = 448.81 ms / 168 tokens ( 2.67 ms per token, 374.32 tokens per second) 2.42.935.543 I slot print_timing: id 0 | task 5353 | eval time = 1391.28 ms / 70 tokens ( 20.16 ms per token, 49.59 tokens per second) 2.42.935.545 I slot print_timing: id 0 | task 5353 | total time = 1840.09 ms / 238 tokens 2.42.935.545 I slot print_timing: id 0 | task 5353 | graphs reused = 4882 2.42.935.546 I slot print_timing: id 0 | task 5353 | graph reallocs = 0 / 0 (same size) / (changed size) 2.42.935.563 I slot release: id 0 | task 5353 | stop processing: n_tokens = 237, truncated = 0 2.42.939.924 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.129 (> 0.100 thold), f_keep = 0.127 2.42.939.965 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 54.677 MiB) 2.42.941.963 I slot launch_slot_: id 0 | task 5426 | processing task, is_child = 0 2.44.289.765 I slot print_timing: id 0 | task 5426 | prompt eval time = 516.37 ms / 232 tokens ( 2.23 ms per token, 449.29 tokens per second) 2.44.289.770 I slot print_timing: id 0 | task 5426 | eval time = 831.42 ms / 42 tokens ( 20.28 ms per token, 49.31 tokens per second) 2.44.289.771 I slot print_timing: id 0 | task 5426 | total time = 1347.79 ms / 274 tokens 2.44.289.772 I slot print_timing: id 0 | task 5426 | graphs reused = 4921 2.44.289.777 I slot print_timing: id 0 | task 5426 | graph reallocs = 0 / 0 (same size) / (changed size) 2.44.289.798 I slot release: id 0 | task 5426 | stop processing: n_tokens = 273, truncated = 0 2.44.293.896 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.120 (> 0.100 thold), f_keep = 0.110 2.44.293.937 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 53.306 MiB) 2.44.293.941 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 66.562 MiB) 2.44.296.327 I slot launch_slot_: id 0 | task 5471 | processing task, is_child = 0 2.47.348.896 I slot print_timing: id 0 | task 5471 | prompt eval time = 564.49 ms / 249 tokens ( 2.27 ms per token, 441.11 tokens per second) 2.47.348.901 I slot print_timing: id 0 | task 5471 | eval time = 2488.07 ms / 124 tokens ( 20.23 ms per token, 49.44 tokens per second) 2.47.348.901 I slot print_timing: id 0 | task 5471 | total time = 3052.56 ms / 373 tokens 2.47.348.902 I slot print_timing: id 0 | task 5471 | graphs reused = 5042 2.47.348.903 I slot print_timing: id 0 | task 5471 | graph reallocs = 0 / 0 (same size) / (changed size) 2.47.348.926 I slot release: id 0 | task 5471 | stop processing: n_tokens = 372, truncated = 0 2.47.353.587 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.106 (> 0.100 thold), f_keep = 0.091 2.47.353.642 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 57.315 MiB) 2.47.353.645 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 74.227 MiB) 2.47.357.135 I slot launch_slot_: id 0 | task 5598 | processing task, is_child = 0 2.50.823.890 I slot print_timing: id 0 | task 5598 | prompt eval time = 621.58 ms / 320 tokens ( 1.94 ms per token, 514.82 tokens per second) 2.50.823.895 I slot print_timing: id 0 | task 5598 | eval time = 2845.16 ms / 141 tokens ( 20.32 ms per token, 49.21 tokens per second) 2.50.823.896 I slot print_timing: id 0 | task 5598 | total time = 3466.74 ms / 461 tokens 2.50.823.897 I slot print_timing: id 0 | task 5598 | graphs reused = 5181 2.50.823.897 I slot print_timing: id 0 | task 5598 | graph reallocs = 0 / 0 (same size) / (changed size) 2.50.823.928 I slot release: id 0 | task 5598 | stop processing: n_tokens = 460, truncated = 0 2.50.827.980 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.167 (> 0.100 thold), f_keep = 0.065 2.50.828.039 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 85.795 MiB) 2.50.836.224 I slot launch_slot_: id 0 | task 5742 | processing task, is_child = 0 2.54.245.744 I slot print_timing: id 0 | task 5742 | n_gen = 150, tg = 49.57 t/s, tg_3s = 49.90 t/s 2.57.249.625 I slot print_timing: id 0 | task 5742 | n_gen = 298, tg = 49.42 t/s, tg_3s = 49.27 t/s 2.58.527.572 I slot print_timing: id 0 | task 5742 | prompt eval time = 403.55 ms / 180 tokens ( 2.24 ms per token, 446.05 tokens per second) 2.58.527.575 I slot print_timing: id 0 | task 5742 | eval time = 7287.79 ms / 360 tokens ( 20.30 ms per token, 49.26 tokens per second) 2.58.527.577 I slot print_timing: id 0 | task 5742 | total time = 7691.34 ms / 540 tokens 2.58.527.578 I slot print_timing: id 0 | task 5742 | graphs reused = 5537 2.58.527.579 I slot print_timing: id 0 | task 5742 | graph reallocs = 0 / 0 (same size) / (changed size) 2.58.527.597 I slot release: id 0 | task 5742 | stop processing: n_tokens = 539, truncated = 0 2.58.531.868 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.163 (> 0.100 thold), f_keep = 0.056 2.58.531.933 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 71.414 MiB) 2.58.540.774 I slot launch_slot_: id 0 | task 6105 | processing task, is_child = 0 3.01.047.611 I slot print_timing: id 0 | task 6105 | prompt eval time = 449.90 ms / 184 tokens ( 2.45 ms per token, 408.98 tokens per second) 3.01.047.615 I slot print_timing: id 0 | task 6105 | eval time = 2056.93 ms / 103 tokens ( 20.17 ms per token, 49.59 tokens per second) 3.01.047.615 I slot print_timing: id 0 | task 6105 | total time = 2506.83 ms / 287 tokens 3.01.047.616 I slot print_timing: id 0 | task 6105 | graphs reused = 5637 3.01.047.617 I slot print_timing: id 0 | task 6105 | graph reallocs = 0 / 0 (same size) / (changed size) 3.01.047.636 I slot release: id 0 | task 6105 | stop processing: n_tokens = 286, truncated = 0 3.01.051.951 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.128 (> 0.100 thold), f_keep = 0.105 3.01.051.996 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 82.771 MiB) 3.01.055.931 I slot launch_slot_: id 0 | task 6211 | processing task, is_child = 0 3.02.310.427 I slot print_timing: id 0 | task 6211 | prompt eval time = 505.56 ms / 235 tokens ( 2.15 ms per token, 464.83 tokens per second) 3.02.310.430 I slot print_timing: id 0 | task 6211 | eval time = 748.93 ms / 38 tokens ( 20.24 ms per token, 49.40 tokens per second) 3.02.310.431 I slot print_timing: id 0 | task 6211 | total time = 1254.49 ms / 273 tokens 3.02.310.431 I slot print_timing: id 0 | task 6211 | graphs reused = 5672 3.02.310.432 I slot print_timing: id 0 | task 6211 | graph reallocs = 0 / 0 (same size) / (changed size) 3.02.310.450 I slot release: id 0 | task 6211 | stop processing: n_tokens = 272, truncated = 0 3.02.314.855 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.104 (> 0.100 thold), f_keep = 0.110 3.02.314.901 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 69.480 MiB) 3.02.317.263 I slot launch_slot_: id 0 | task 6252 | processing task, is_child = 0 3.05.957.292 I slot print_timing: id 0 | task 6252 | n_gen = 150, tg = 49.35 t/s, tg_3s = 49.69 t/s 3.08.958.240 I slot print_timing: id 0 | task 6252 | n_gen = 296, tg = 49.00 t/s, tg_3s = 48.65 t/s 3.09.411.594 I slot print_timing: id 0 | task 6252 | prompt eval time = 621.04 ms / 289 tokens ( 2.15 ms per token, 465.35 tokens per second) 3.09.411.600 I slot print_timing: id 0 | task 6252 | eval time = 6473.28 ms / 318 tokens ( 20.42 ms per token, 48.97 tokens per second) 3.09.411.601 I slot print_timing: id 0 | task 6252 | total time = 7094.32 ms / 607 tokens 3.09.411.602 I slot print_timing: id 0 | task 6252 | graphs reused = 5987 3.09.411.602 I slot print_timing: id 0 | task 6252 | graph reallocs = 0 / 0 (same size) / (changed size) 3.09.411.624 I slot release: id 0 | task 6252 | stop processing: n_tokens = 606, truncated = 0 3.09.415.971 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.183 (> 0.100 thold), f_keep = 0.073 3.09.416.040 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 56.682 MiB) 3.09.416.044 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 66.175 MiB) 3.09.426.358 I slot launch_slot_: id 0 | task 6573 | processing task, is_child = 0 3.12.945.118 I slot print_timing: id 0 | task 6573 | n_gen = 150, tg = 49.45 t/s, tg_3s = 49.78 t/s 3.13.574.502 I slot print_timing: id 0 | task 6573 | prompt eval time = 505.71 ms / 241 tokens ( 2.10 ms per token, 476.56 tokens per second) 3.13.574.508 I slot print_timing: id 0 | task 6573 | eval time = 3642.43 ms / 181 tokens ( 20.24 ms per token, 49.42 tokens per second) 3.13.574.509 I slot print_timing: id 0 | task 6573 | total time = 4148.14 ms / 422 tokens 3.13.574.510 I slot print_timing: id 0 | task 6573 | graphs reused = 6165 3.13.574.510 I slot print_timing: id 0 | task 6573 | graph reallocs = 0 / 0 (same size) / (changed size) 3.13.574.531 I slot release: id 0 | task 6573 | stop processing: n_tokens = 421, truncated = 0 3.13.578.949 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.126 (> 0.100 thold), f_keep = 0.071 3.13.579.009 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 76.583 MiB) 3.13.580.059 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 67.265 MiB) 3.13.588.035 I slot launch_slot_: id 0 | task 6757 | processing task, is_child = 0 3.16.400.968 I slot print_timing: id 0 | task 6757 | prompt eval time = 506.75 ms / 239 tokens ( 2.12 ms per token, 471.63 tokens per second) 3.16.400.974 I slot print_timing: id 0 | task 6757 | eval time = 2306.17 ms / 115 tokens ( 20.23 ms per token, 49.43 tokens per second) 3.16.400.975 I slot print_timing: id 0 | task 6757 | total time = 2812.92 ms / 354 tokens 3.16.400.976 I slot print_timing: id 0 | task 6757 | graphs reused = 6277 3.16.400.976 I slot print_timing: id 0 | task 6757 | graph reallocs = 0 / 0 (same size) / (changed size) 3.16.400.997 I slot release: id 0 | task 6757 | stop processing: n_tokens = 353, truncated = 0 3.16.405.334 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.110 (> 0.100 thold), f_keep = 0.085 3.16.405.385 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 59.389 MiB) 3.16.411.574 I slot launch_slot_: id 0 | task 6875 | processing task, is_child = 0 3.17.900.140 I slot print_timing: id 0 | task 6875 | prompt eval time = 619.74 ms / 273 tokens ( 2.27 ms per token, 440.50 tokens per second) 3.17.900.146 I slot print_timing: id 0 | task 6875 | eval time = 868.81 ms / 44 tokens ( 20.20 ms per token, 49.49 tokens per second) 3.17.900.147 I slot print_timing: id 0 | task 6875 | total time = 1488.56 ms / 317 tokens 3.17.900.148 I slot print_timing: id 0 | task 6875 | graphs reused = 6319 3.17.900.149 I slot print_timing: id 0 | task 6875 | graph reallocs = 0 / 0 (same size) / (changed size) 3.17.900.177 I slot release: id 0 | task 6875 | stop processing: n_tokens = 316, truncated = 0 3.17.904.108 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.142 (> 0.100 thold), f_keep = 0.095 3.17.904.154 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 59.494 MiB) 3.17.904.312 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 67.828 MiB) 3.17.910.388 I slot launch_slot_: id 0 | task 6922 | processing task, is_child = 0 3.21.369.721 I slot print_timing: id 0 | task 6922 | n_gen = 149, tg = 49.27 t/s, tg_3s = 49.60 t/s 3.23.253.469 I slot print_timing: id 0 | task 6922 | prompt eval time = 455.53 ms / 212 tokens ( 2.15 ms per token, 465.39 tokens per second) 3.23.253.474 I slot print_timing: id 0 | task 6922 | eval time = 4887.54 ms / 242 tokens ( 20.28 ms per token, 49.31 tokens per second) 3.23.253.474 I slot print_timing: id 0 | task 6922 | total time = 5343.07 ms / 454 tokens 3.23.253.475 I slot print_timing: id 0 | task 6922 | graphs reused = 6558 3.23.253.476 I slot print_timing: id 0 | task 6922 | graph reallocs = 0 / 0 (same size) / (changed size) 3.23.253.495 I slot release: id 0 | task 6922 | stop processing: n_tokens = 453, truncated = 0 3.23.257.989 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.105 (> 0.100 thold), f_keep = 0.066 3.23.258.051 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 73.278 MiB) 3.23.265.721 I slot launch_slot_: id 0 | task 7167 | processing task, is_child = 0 3.26.237.890 I slot print_timing: id 0 | task 7167 | prompt eval time = 561.77 ms / 285 tokens ( 1.97 ms per token, 507.32 tokens per second) 3.26.237.893 I slot print_timing: id 0 | task 7167 | eval time = 2410.39 ms / 120 tokens ( 20.26 ms per token, 49.37 tokens per second) 3.26.237.894 I slot print_timing: id 0 | task 7167 | total time = 2972.16 ms / 405 tokens 3.26.237.895 I slot print_timing: id 0 | task 7167 | graphs reused = 6676 3.26.237.895 I slot print_timing: id 0 | task 7167 | graph reallocs = 0 / 0 (same size) / (changed size) 3.26.237.918 I slot release: id 0 | task 7167 | stop processing: n_tokens = 404, truncated = 0 3.26.242.095 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.157 (> 0.100 thold), f_keep = 0.074 3.26.242.149 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 57.490 MiB) 3.26.242.337 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.465 MiB) 3.26.249.998 I slot launch_slot_: id 0 | task 7290 | processing task, is_child = 0 3.27.993.895 I slot print_timing: id 0 | task 7290 | prompt eval time = 451.81 ms / 191 tokens ( 2.37 ms per token, 422.75 tokens per second) 3.27.993.901 I slot print_timing: id 0 | task 7290 | eval time = 1292.08 ms / 65 tokens ( 20.19 ms per token, 49.53 tokens per second) 3.27.993.902 I slot print_timing: id 0 | task 7290 | total time = 1743.89 ms / 256 tokens 3.27.993.902 I slot print_timing: id 0 | task 7290 | graphs reused = 6739 3.27.993.903 I slot print_timing: id 0 | task 7290 | graph reallocs = 0 / 0 (same size) / (changed size) 3.27.993.926 I slot release: id 0 | task 7290 | stop processing: n_tokens = 255, truncated = 0 3.27.997.798 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.118 3.27.997.841 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 45.676 MiB) 3.28.000.091 I slot launch_slot_: id 0 | task 7358 | processing task, is_child = 0 3.29.948.243 I slot print_timing: id 0 | task 7358 | prompt eval time = 403.19 ms / 171 tokens ( 2.36 ms per token, 424.12 tokens per second) 3.29.948.248 I slot print_timing: id 0 | task 7358 | eval time = 1544.96 ms / 78 tokens ( 20.06 ms per token, 49.84 tokens per second) 3.29.948.249 I slot print_timing: id 0 | task 7358 | total time = 1948.14 ms / 249 tokens 3.29.948.250 I slot print_timing: id 0 | task 7358 | graphs reused = 6815 3.29.948.250 I slot print_timing: id 0 | task 7358 | graph reallocs = 0 / 0 (same size) / (changed size) 3.29.948.268 I slot release: id 0 | task 7358 | stop processing: n_tokens = 248, truncated = 0 3.29.952.622 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.115 (> 0.100 thold), f_keep = 0.121 3.29.952.661 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 69.621 MiB) 3.29.954.665 I slot launch_slot_: id 0 | task 7439 | processing task, is_child = 0 3.32.550.343 I slot print_timing: id 0 | task 7439 | prompt eval time = 566.11 ms / 260 tokens ( 2.18 ms per token, 459.28 tokens per second) 3.32.550.349 I slot print_timing: id 0 | task 7439 | eval time = 2029.56 ms / 101 tokens ( 20.30 ms per token, 49.27 tokens per second) 3.32.550.349 I slot print_timing: id 0 | task 7439 | total time = 2595.67 ms / 361 tokens 3.32.550.350 I slot print_timing: id 0 | task 7439 | graphs reused = 6914 3.32.550.351 I slot print_timing: id 0 | task 7439 | graph reallocs = 0 / 0 (same size) / (changed size) 3.32.550.373 I slot release: id 0 | task 7439 | stop processing: n_tokens = 360, truncated = 0 3.32.554.634 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.147 (> 0.100 thold), f_keep = 0.083 3.32.554.685 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 52.075 MiB) 3.32.554.689 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 52.884 MiB) 3.32.560.699 I slot launch_slot_: id 0 | task 7543 | processing task, is_child = 0 3.36.024.985 I slot print_timing: id 0 | task 7543 | n_gen = 150, tg = 49.49 t/s, tg_3s = 49.82 t/s 3.39.041.311 I slot print_timing: id 0 | task 7543 | n_gen = 298, tg = 49.28 t/s, tg_3s = 49.07 t/s 3.42.048.511 I slot print_timing: id 0 | task 7543 | n_gen = 444, tg = 49.04 t/s, tg_3s = 48.55 t/s 3.44.414.786 I slot print_timing: id 0 | task 7543 | prompt eval time = 453.55 ms / 204 tokens ( 2.22 ms per token, 449.79 tokens per second) 3.44.414.789 I slot print_timing: id 0 | task 7543 | eval time = 11400.52 ms / 559 tokens ( 20.43 ms per token, 48.95 tokens per second) 3.44.414.790 I slot print_timing: id 0 | task 7543 | total time = 11854.07 ms / 763 tokens 3.44.414.790 I slot print_timing: id 0 | task 7543 | graphs reused = 7469 3.44.414.791 I slot print_timing: id 0 | task 7543 | graph reallocs = 0 / 0 (same size) / (changed size) 3.44.414.811 I slot release: id 0 | task 7543 | stop processing: n_tokens = 762, truncated = 0 3.44.419.334 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.101 (> 0.100 thold), f_keep = 0.039 3.44.419.411 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 69.726 MiB) 3.44.419.415 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 115.928 MiB) 3.44.428.071 I slot launch_slot_: id 0 | task 8105 | processing task, is_child = 0 3.48.041.986 I slot print_timing: id 0 | task 8105 | n_gen = 149, tg = 49.30 t/s, tg_3s = 49.63 t/s 3.51.046.696 I slot print_timing: id 0 | task 8105 | n_gen = 295, tg = 48.94 t/s, tg_3s = 48.59 t/s 3.51.108.507 I slot print_timing: id 0 | task 8105 | prompt eval time = 611.87 ms / 296 tokens ( 2.07 ms per token, 483.77 tokens per second) 3.51.108.513 I slot print_timing: id 0 | task 8105 | eval time = 6068.56 ms / 298 tokens ( 20.43 ms per token, 48.94 tokens per second) 3.51.108.513 I slot print_timing: id 0 | task 8105 | total time = 6680.43 ms / 594 tokens 3.51.108.514 I slot print_timing: id 0 | task 8105 | graphs reused = 7764 3.51.108.514 I slot print_timing: id 0 | task 8105 | graph reallocs = 0 / 0 (same size) / (changed size) 3.51.108.541 I slot release: id 0 | task 8105 | stop processing: n_tokens = 593, truncated = 0 3.51.112.844 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.131 (> 0.100 thold), f_keep = 0.052 3.51.112.915 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 52.638 MiB) 3.51.120.775 I slot launch_slot_: id 0 | task 8406 | processing task, is_child = 0 3.54.642.039 I slot print_timing: id 0 | task 8406 | n_gen = 150, tg = 49.46 t/s, tg_3s = 49.79 t/s 3.57.647.862 I slot print_timing: id 0 | task 8406 | n_gen = 297, tg = 49.18 t/s, tg_3s = 48.91 t/s 4.00.656.655 I slot print_timing: id 0 | task 8406 | n_gen = 443, tg = 48.96 t/s, tg_3s = 48.52 t/s 4.01.442.175 I slot print_timing: id 0 | task 8406 | prompt eval time = 508.61 ms / 236 tokens ( 2.16 ms per token, 464.01 tokens per second) 4.01.442.179 I slot print_timing: id 0 | task 8406 | eval time = 9812.78 ms / 481 tokens ( 20.44 ms per token, 48.92 tokens per second) 4.01.442.180 I slot print_timing: id 0 | task 8406 | total time = 10321.39 ms / 717 tokens 4.01.442.181 I slot print_timing: id 0 | task 8406 | graphs reused = 8241 4.01.442.182 I slot print_timing: id 0 | task 8406 | graph reallocs = 0 / 0 (same size) / (changed size) 4.01.442.222 I slot release: id 0 | task 8406 | stop processing: n_tokens = 716, truncated = 0 4.01.448.189 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.102 (> 0.100 thold), f_keep = 0.042 4.01.448.276 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 62.905 MiB) 4.01.448.283 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 81.787 MiB) 4.01.458.693 I slot launch_slot_: id 0 | task 8890 | processing task, is_child = 0 4.03.843.907 I slot print_timing: id 0 | task 8890 | prompt eval time = 623.50 ms / 294 tokens ( 2.12 ms per token, 471.54 tokens per second) 4.03.843.910 I slot print_timing: id 0 | task 8890 | eval time = 1761.70 ms / 88 tokens ( 20.25 ms per token, 49.38 tokens per second) 4.03.843.911 I slot print_timing: id 0 | task 8890 | total time = 2385.20 ms / 382 tokens 4.03.843.911 I slot print_timing: id 0 | task 8890 | graphs reused = 8327 4.03.843.912 I slot print_timing: id 0 | task 8890 | graph reallocs = 0 / 0 (same size) / (changed size) 4.03.843.940 I slot release: id 0 | task 8890 | stop processing: n_tokens = 381, truncated = 0 4.03.848.837 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.103 (> 0.100 thold), f_keep = 0.079 4.03.848.891 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 84.213 MiB) 4.03.853.748 I slot launch_slot_: id 0 | task 8981 | processing task, is_child = 0 4.07.465.059 I slot print_timing: id 0 | task 8981 | n_gen = 149, tg = 49.33 t/s, tg_3s = 49.66 t/s 4.10.467.066 I slot print_timing: id 0 | task 8981 | n_gen = 295, tg = 48.98 t/s, tg_3s = 48.63 t/s 4.11.908.861 I slot print_timing: id 0 | task 8981 | prompt eval time = 611.17 ms / 291 tokens ( 2.10 ms per token, 476.14 tokens per second) 4.11.908.864 I slot print_timing: id 0 | task 8981 | eval time = 7443.94 ms / 365 tokens ( 20.45 ms per token, 48.90 tokens per second) 4.11.908.865 I slot print_timing: id 0 | task 8981 | total time = 8055.10 ms / 656 tokens 4.11.908.866 I slot print_timing: id 0 | task 8981 | graphs reused = 8689 4.11.908.866 I slot print_timing: id 0 | task 8981 | graph reallocs = 0 / 0 (same size) / (changed size) 4.11.908.890 I slot release: id 0 | task 8981 | stop processing: n_tokens = 655, truncated = 0 4.11.913.564 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.105 (> 0.100 thold), f_keep = 0.046 4.11.913.655 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 56.787 MiB) 4.11.913.663 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 60.092 MiB) 4.11.922.553 I slot launch_slot_: id 0 | task 9349 | processing task, is_child = 0 4.13.334.100 I slot print_timing: id 0 | task 9349 | prompt eval time = 621.88 ms / 287 tokens ( 2.17 ms per token, 461.51 tokens per second) 4.13.334.103 I slot print_timing: id 0 | task 9349 | eval time = 789.66 ms / 40 tokens ( 20.25 ms per token, 49.39 tokens per second) 4.13.334.104 I slot print_timing: id 0 | task 9349 | total time = 1411.53 ms / 327 tokens 4.13.334.104 I slot print_timing: id 0 | task 9349 | graphs reused = 8727 4.13.334.105 I slot print_timing: id 0 | task 9349 | graph reallocs = 0 / 0 (same size) / (changed size) 4.13.334.127 I slot release: id 0 | task 9349 | stop processing: n_tokens = 326, truncated = 0 4.13.338.376 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.123 (> 0.100 thold), f_keep = 0.092 4.13.338.424 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 74.086 MiB) 4.13.344.292 I slot launch_slot_: id 0 | task 9392 | processing task, is_child = 0 4.15.872.782 I slot print_timing: id 0 | task 9392 | prompt eval time = 506.81 ms / 243 tokens ( 2.09 ms per token, 479.47 tokens per second) 4.15.872.785 I slot print_timing: id 0 | task 9392 | eval time = 2021.66 ms / 101 tokens ( 20.22 ms per token, 49.46 tokens per second) 4.15.872.786 I slot print_timing: id 0 | task 9392 | total time = 2528.47 ms / 344 tokens 4.15.872.787 I slot print_timing: id 0 | task 9392 | graphs reused = 8825 4.15.872.788 I slot print_timing: id 0 | task 9392 | graph reallocs = 0 / 0 (same size) / (changed size) 4.15.872.809 I slot release: id 0 | task 9392 | stop processing: n_tokens = 343, truncated = 0 4.15.876.948 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.166 (> 0.100 thold), f_keep = 0.087 4.15.877.005 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 56.541 MiB) 4.15.877.008 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 75.352 MiB) 4.15.883.373 I slot launch_slot_: id 0 | task 9496 | processing task, is_child = 0 4.16.920.071 I slot print_timing: id 0 | task 9496 | prompt eval time = 450.11 ms / 181 tokens ( 2.49 ms per token, 402.12 tokens per second) 4.16.920.075 I slot print_timing: id 0 | task 9496 | eval time = 586.58 ms / 30 tokens ( 20.23 ms per token, 49.44 tokens per second) 4.16.920.075 I slot print_timing: id 0 | task 9496 | total time = 1036.69 ms / 211 tokens 4.16.920.076 I slot print_timing: id 0 | task 9496 | graphs reused = 8853 4.16.920.077 I slot print_timing: id 0 | task 9496 | graph reallocs = 0 / 0 (same size) / (changed size) 4.16.920.094 I slot release: id 0 | task 9496 | stop processing: n_tokens = 210, truncated = 0 4.16.924.147 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.113 (> 0.100 thold), f_keep = 0.143 4.16.924.181 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 59.776 MiB) 4.16.926.348 I slot launch_slot_: id 0 | task 9529 | processing task, is_child = 0 4.18.033.886 I slot print_timing: id 0 | task 9529 | prompt eval time = 558.25 ms / 265 tokens ( 2.11 ms per token, 474.69 tokens per second) 4.18.033.889 I slot print_timing: id 0 | task 9529 | eval time = 549.27 ms / 28 tokens ( 20.34 ms per token, 49.16 tokens per second) 4.18.033.890 I slot print_timing: id 0 | task 9529 | total time = 1107.53 ms / 293 tokens 4.18.033.891 I slot print_timing: id 0 | task 9529 | graphs reused = 8879 4.18.033.892 I slot print_timing: id 0 | task 9529 | graph reallocs = 0 / 0 (same size) / (changed size) 4.18.033.925 I slot release: id 0 | task 9529 | stop processing: n_tokens = 292, truncated = 0 4.18.038.017 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.197 (> 0.100 thold), f_keep = 0.103 4.18.038.068 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 100.844 MiB) 4.18.041.302 I slot launch_slot_: id 0 | task 9560 | processing task, is_child = 0 4.19.267.870 I slot print_timing: id 0 | task 9560 | prompt eval time = 398.98 ms / 152 tokens ( 2.62 ms per token, 380.97 tokens per second) 4.19.267.873 I slot print_timing: id 0 | task 9560 | eval time = 827.58 ms / 42 tokens ( 20.18 ms per token, 49.54 tokens per second) 4.19.267.874 I slot print_timing: id 0 | task 9560 | total time = 1226.56 ms / 194 tokens 4.19.267.875 I slot print_timing: id 0 | task 9560 | graphs reused = 8919 4.19.267.875 I slot print_timing: id 0 | task 9560 | graph reallocs = 0 / 0 (same size) / (changed size) 4.19.267.893 I slot release: id 0 | task 9560 | stop processing: n_tokens = 193, truncated = 0 4.19.271.917 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.158 (> 0.100 thold), f_keep = 0.155 4.19.274.226 I slot launch_slot_: id 0 | task 9605 | processing task, is_child = 0 4.20.794.883 I slot print_timing: id 0 | task 9605 | prompt eval time = 451.69 ms / 190 tokens ( 2.38 ms per token, 420.64 tokens per second) 4.20.794.889 I slot print_timing: id 0 | task 9605 | eval time = 1068.95 ms / 54 tokens ( 20.17 ms per token, 49.58 tokens per second) 4.20.794.890 I slot print_timing: id 0 | task 9605 | total time = 1520.65 ms / 244 tokens 4.20.794.891 I slot print_timing: id 0 | task 9605 | graphs reused = 8971 4.20.794.891 I slot print_timing: id 0 | task 9605 | graph reallocs = 0 / 0 (same size) / (changed size) 4.20.794.909 I slot release: id 0 | task 9605 | stop processing: n_tokens = 243, truncated = 0 4.20.799.173 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.117 (> 0.100 thold), f_keep = 0.123 4.20.799.212 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 92.616 MiB) 4.20.801.686 I slot launch_slot_: id 0 | task 9662 | processing task, is_child = 0 4.22.439.723 I slot print_timing: id 0 | task 9662 | prompt eval time = 566.18 ms / 256 tokens ( 2.21 ms per token, 452.15 tokens per second) 4.22.439.730 I slot print_timing: id 0 | task 9662 | eval time = 1071.85 ms / 54 tokens ( 20.22 ms per token, 49.45 tokens per second) 4.22.439.731 I slot print_timing: id 0 | task 9662 | total time = 1638.03 ms / 310 tokens 4.22.439.731 I slot print_timing: id 0 | task 9662 | graphs reused = 9023 4.22.439.732 I slot print_timing: id 0 | task 9662 | graph reallocs = 0 / 0 (same size) / (changed size) 4.22.439.752 I slot release: id 0 | task 9662 | stop processing: n_tokens = 309, truncated = 0 4.22.444.224 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.114 (> 0.100 thold), f_keep = 0.097 4.22.444.264 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 57.244 MiB) 4.22.447.499 I slot launch_slot_: id 0 | task 9719 | processing task, is_child = 0 4.23.461.774 I slot print_timing: id 0 | task 9719 | prompt eval time = 567.66 ms / 264 tokens ( 2.15 ms per token, 465.07 tokens per second) 4.23.461.780 I slot print_timing: id 0 | task 9719 | eval time = 446.61 ms / 23 tokens ( 20.30 ms per token, 49.26 tokens per second) 4.23.461.781 I slot print_timing: id 0 | task 9719 | total time = 1014.27 ms / 287 tokens 4.23.461.781 I slot print_timing: id 0 | task 9719 | graphs reused = 9044 4.23.461.782 I slot print_timing: id 0 | task 9719 | graph reallocs = 0 / 0 (same size) / (changed size) 4.23.461.803 I slot release: id 0 | task 9719 | stop processing: n_tokens = 286, truncated = 0 4.23.466.342 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.104 (> 0.100 thold), f_keep = 0.105 4.23.466.383 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.183 MiB) 4.23.466.386 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 53.728 MiB) 4.23.472.283 I slot launch_slot_: id 0 | task 9745 | processing task, is_child = 0 4.27.109.335 I slot print_timing: id 0 | task 9745 | n_gen = 150, tg = 49.36 t/s, tg_3s = 49.69 t/s 4.30.129.849 I slot print_timing: id 0 | task 9745 | n_gen = 297, tg = 49.01 t/s, tg_3s = 48.67 t/s 4.33.136.398 I slot print_timing: id 0 | task 9745 | n_gen = 443, tg = 48.86 t/s, tg_3s = 48.56 t/s 4.34.722.678 I slot print_timing: id 0 | task 9745 | prompt eval time = 618.17 ms / 289 tokens ( 2.14 ms per token, 467.51 tokens per second) 4.34.722.682 I slot print_timing: id 0 | task 9745 | eval time = 10632.21 ms / 520 tokens ( 20.49 ms per token, 48.81 tokens per second) 4.34.722.683 I slot print_timing: id 0 | task 9745 | total time = 11250.38 ms / 809 tokens 4.34.722.684 I slot print_timing: id 0 | task 9745 | graphs reused = 9560 4.34.722.685 I slot print_timing: id 0 | task 9745 | graph reallocs = 0 / 0 (same size) / (changed size) 4.34.722.706 I slot release: id 0 | task 9745 | stop processing: n_tokens = 808, truncated = 0 4.34.727.504 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.102 (> 0.100 thold), f_keep = 0.037 4.34.727.583 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.778 MiB) 4.34.727.589 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 115.400 MiB) 4.34.737.979 I slot launch_slot_: id 0 | task 10268 | processing task, is_child = 0 4.35.622.769 I slot print_timing: id 0 | task 10268 | prompt eval time = 619.45 ms / 294 tokens ( 2.11 ms per token, 474.62 tokens per second) 4.35.622.776 I slot print_timing: id 0 | task 10268 | eval time = 265.33 ms / 14 tokens ( 20.41 ms per token, 48.99 tokens per second) 4.35.622.777 I slot print_timing: id 0 | task 10268 | total time = 884.78 ms / 308 tokens 4.35.622.778 I slot print_timing: id 0 | task 10268 | graphs reused = 9572 4.35.622.778 I slot print_timing: id 0 | task 10268 | graph reallocs = 0 / 0 (same size) / (changed size) 4.35.622.800 I slot release: id 0 | task 10268 | stop processing: n_tokens = 307, truncated = 0 4.35.627.310 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.103 (> 0.100 thold), f_keep = 0.098 4.35.630.133 I slot launch_slot_: id 0 | task 10285 | processing task, is_child = 0 4.36.939.602 I slot print_timing: id 0 | task 10285 | prompt eval time = 620.25 ms / 292 tokens ( 2.12 ms per token, 470.77 tokens per second) 4.36.939.609 I slot print_timing: id 0 | task 10285 | eval time = 689.20 ms / 35 tokens ( 20.27 ms per token, 49.33 tokens per second) 4.36.939.610 I slot print_timing: id 0 | task 10285 | total time = 1309.45 ms / 327 tokens 4.36.939.610 I slot print_timing: id 0 | task 10285 | graphs reused = 9605 4.36.939.611 I slot print_timing: id 0 | task 10285 | graph reallocs = 0 / 0 (same size) / (changed size) 4.36.939.633 I slot release: id 0 | task 10285 | stop processing: n_tokens = 326, truncated = 0 4.36.944.052 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.122 (> 0.100 thold), f_keep = 0.092 4.36.944.095 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 138.958 MiB) 4.36.947.455 I slot launch_slot_: id 0 | task 10323 | processing task, is_child = 0 4.38.437.137 I slot print_timing: id 0 | task 10323 | prompt eval time = 517.80 ms / 245 tokens ( 2.11 ms per token, 473.15 tokens per second) 4.38.437.142 I slot print_timing: id 0 | task 10323 | eval time = 971.87 ms / 49 tokens ( 20.25 ms per token, 49.39 tokens per second) 4.38.437.143 I slot print_timing: id 0 | task 10323 | total time = 1489.67 ms / 294 tokens 4.38.437.144 I slot print_timing: id 0 | task 10323 | graphs reused = 9651 4.38.437.144 I slot print_timing: id 0 | task 10323 | graph reallocs = 0 / 0 (same size) / (changed size) 4.38.437.164 I slot release: id 0 | task 10323 | stop processing: n_tokens = 293, truncated = 0 4.38.441.260 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.169 (> 0.100 thold), f_keep = 0.102 4.38.441.304 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 154.218 MiB) 4.38.444.552 I slot launch_slot_: id 0 | task 10375 | processing task, is_child = 0 4.39.615.681 I slot print_timing: id 0 | task 10375 | prompt eval time = 404.56 ms / 178 tokens ( 2.27 ms per token, 439.98 tokens per second) 4.39.615.688 I slot print_timing: id 0 | task 10375 | eval time = 766.55 ms / 39 tokens ( 20.17 ms per token, 49.57 tokens per second) 4.39.615.688 I slot print_timing: id 0 | task 10375 | total time = 1171.12 ms / 217 tokens 4.39.615.689 I slot print_timing: id 0 | task 10375 | graphs reused = 9688 4.39.615.690 I slot print_timing: id 0 | task 10375 | graph reallocs = 0 / 0 (same size) / (changed size) 4.39.615.706 I slot release: id 0 | task 10375 | stop processing: n_tokens = 216, truncated = 0 4.39.620.810 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 216, t_last = 333474423089 4.39.623.037 I slot launch_slot_: id 0 | task 10417 | processing task, is_child = 0 4.42.041.205 I slot print_timing: id 0 | task 10417 | prompt eval time = 731.04 ms / 355 tokens ( 2.06 ms per token, 485.61 tokens per second) 4.42.041.208 I slot print_timing: id 0 | task 10417 | eval time = 1687.11 ms / 84 tokens ( 20.33 ms per token, 49.20 tokens per second) 4.42.041.209 I slot print_timing: id 0 | task 10417 | total time = 2418.15 ms / 439 tokens 4.42.041.210 I slot print_timing: id 0 | task 10417 | graphs reused = 9770 4.42.041.210 I slot print_timing: id 0 | task 10417 | graph reallocs = 0 / 0 (same size) / (changed size) 4.42.041.235 I slot release: id 0 | task 10417 | stop processing: n_tokens = 438, truncated = 0 4.42.046.979 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 438, t_last = 333476848617 4.42.047.030 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 146.518 MiB) 4.42.051.045 I slot launch_slot_: id 0 | task 10504 | processing task, is_child = 0 4.46.213.572 I slot print_timing: id 0 | task 10504 | n_gen = 147, tg = 48.45 t/s, tg_3s = 48.78 t/s 4.46.234.218 I slot print_timing: id 0 | task 10504 | prompt eval time = 1148.93 ms / 567 tokens ( 2.03 ms per token, 493.50 tokens per second) 4.46.234.224 I slot print_timing: id 0 | task 10504 | eval time = 3034.23 ms / 148 tokens ( 20.64 ms per token, 48.45 tokens per second) 4.46.234.225 I slot print_timing: id 0 | task 10504 | total time = 4183.17 ms / 715 tokens 4.46.234.226 I slot print_timing: id 0 | task 10504 | graphs reused = 9916 4.46.234.226 I slot print_timing: id 0 | task 10504 | graph reallocs = 0 / 0 (same size) / (changed size) 4.46.234.265 I slot release: id 0 | task 10504 | stop processing: n_tokens = 714, truncated = 0 4.46.239.996 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 714, t_last = 333481041647 4.46.240.066 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 115.893 MiB) 4.46.240.069 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 153.058 MiB) 4.46.252.429 I slot launch_slot_: id 0 | task 10656 | processing task, is_child = 0 4.48.993.276 I slot print_timing: id 0 | task 10656 | prompt eval time = 945.57 ms / 473 tokens ( 2.00 ms per token, 500.23 tokens per second) 4.48.993.278 I slot print_timing: id 0 | task 10656 | eval time = 1795.27 ms / 88 tokens ( 20.64 ms per token, 48.46 tokens per second) 4.48.993.279 I slot print_timing: id 0 | task 10656 | total time = 2740.84 ms / 561 tokens 4.48.993.280 I slot print_timing: id 0 | task 10656 | graphs reused = 10001 4.48.993.280 I slot print_timing: id 0 | task 10656 | graph reallocs = 0 / 0 (same size) / (changed size) 4.48.993.313 I slot release: id 0 | task 10656 | stop processing: n_tokens = 560, truncated = 0 4.48.998.458 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 333483800695 4.48.998.526 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 152.671 MiB) 4.49.003.639 I slot launch_slot_: id 0 | task 10747 | processing task, is_child = 0 4.52.800.647 I slot print_timing: id 0 | task 10747 | n_gen = 148, tg = 48.82 t/s, tg_3s = 49.16 t/s 4.55.806.002 I slot print_timing: id 0 | task 10747 | n_gen = 294, tg = 48.70 t/s, tg_3s = 48.58 t/s 4.58.812.190 I slot print_timing: id 0 | task 10747 | n_gen = 440, tg = 48.66 t/s, tg_3s = 48.57 t/s 5.01.821.348 I slot print_timing: id 0 | task 10747 | n_gen = 586, tg = 48.62 t/s, tg_3s = 48.52 t/s 5.04.823.664 I slot print_timing: id 0 | task 10747 | n_gen = 731, tg = 48.56 t/s, tg_3s = 48.30 t/s 5.07.841.475 I slot print_timing: id 0 | task 10747 | n_gen = 877, tg = 48.53 t/s, tg_3s = 48.38 t/s 5.09.064.369 I slot print_timing: id 0 | task 10747 | prompt eval time = 786.18 ms / 399 tokens ( 1.97 ms per token, 507.52 tokens per second) 5.09.064.375 I slot print_timing: id 0 | task 10747 | eval time = 19274.54 ms / 936 tokens ( 20.61 ms per token, 48.51 tokens per second) 5.09.064.380 I slot print_timing: id 0 | task 10747 | total time = 20060.72 ms / 1335 tokens 5.09.064.380 I slot print_timing: id 0 | task 10747 | graphs reused = 10931 5.09.064.382 I slot print_timing: id 0 | task 10747 | graph reallocs = 0 / 0 (same size) / (changed size) 5.09.064.414 I slot release: id 0 | task 10747 | stop processing: n_tokens = 1334, truncated = 0 5.09.069.490 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1334, t_last = 333503871796 5.09.069.601 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 107.313 MiB) 5.09.082.398 I slot launch_slot_: id 0 | task 11686 | processing task, is_child = 0 5.11.094.547 I slot print_timing: id 0 | task 11686 | prompt eval time = 674.49 ms / 312 tokens ( 2.16 ms per token, 462.57 tokens per second) 5.11.094.552 I slot print_timing: id 0 | task 11686 | eval time = 1337.64 ms / 67 tokens ( 20.27 ms per token, 49.34 tokens per second) 5.11.094.553 I slot print_timing: id 0 | task 11686 | total time = 2012.14 ms / 379 tokens 5.11.094.554 I slot print_timing: id 0 | task 11686 | graphs reused = 10996 5.11.094.554 I slot print_timing: id 0 | task 11686 | graph reallocs = 0 / 0 (same size) / (changed size) 5.11.094.576 I slot release: id 0 | task 11686 | stop processing: n_tokens = 378, truncated = 0 5.11.100.363 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 378, t_last = 333505901958 5.11.100.412 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 103.094 MiB) 5.11.103.939 I slot launch_slot_: id 0 | task 11756 | processing task, is_child = 0 5.14.536.246 I slot print_timing: id 0 | task 11756 | prompt eval time = 1140.67 ms / 561 tokens ( 2.03 ms per token, 491.82 tokens per second) 5.14.536.249 I slot print_timing: id 0 | task 11756 | eval time = 2291.63 ms / 112 tokens ( 20.65 ms per token, 48.44 tokens per second) 5.14.536.250 I slot print_timing: id 0 | task 11756 | total time = 3432.30 ms / 673 tokens 5.14.536.250 I slot print_timing: id 0 | task 11756 | graphs reused = 11106 5.14.536.251 I slot print_timing: id 0 | task 11756 | graph reallocs = 0 / 0 (same size) / (changed size) 5.14.536.282 I slot release: id 0 | task 11756 | stop processing: n_tokens = 672, truncated = 0 5.14.541.296 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 672, t_last = 333509343664 5.14.541.373 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.109 MiB) 5.14.556.577 I slot launch_slot_: id 0 | task 11872 | processing task, is_child = 0 5.17.246.015 I slot print_timing: id 0 | task 11872 | prompt eval time = 671.79 ms / 317 tokens ( 2.12 ms per token, 471.87 tokens per second) 5.17.246.018 I slot print_timing: id 0 | task 11872 | eval time = 2017.63 ms / 100 tokens ( 20.38 ms per token, 49.07 tokens per second) 5.17.246.019 I slot print_timing: id 0 | task 11872 | total time = 2689.42 ms / 417 tokens 5.17.246.019 I slot print_timing: id 0 | task 11872 | graphs reused = 11204 5.17.246.020 I slot print_timing: id 0 | task 11872 | graph reallocs = 0 / 0 (same size) / (changed size) 5.17.246.047 I slot release: id 0 | task 11872 | stop processing: n_tokens = 416, truncated = 0 5.17.251.294 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 333512053429 5.17.251.343 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 113.431 MiB) 5.17.258.836 I slot launch_slot_: id 0 | task 11975 | processing task, is_child = 0 5.20.010.312 I slot print_timing: id 0 | task 11975 | prompt eval time = 841.30 ms / 428 tokens ( 1.97 ms per token, 508.74 tokens per second) 5.20.010.323 I slot print_timing: id 0 | task 11975 | eval time = 1910.17 ms / 94 tokens ( 20.54 ms per token, 48.69 tokens per second) 5.20.010.323 I slot print_timing: id 0 | task 11975 | total time = 2751.47 ms / 522 tokens 5.20.010.324 I slot print_timing: id 0 | task 11975 | graphs reused = 11295 5.20.010.327 I slot print_timing: id 0 | task 11975 | graph reallocs = 0 / 0 (same size) / (changed size) 5.20.010.353 I slot release: id 0 | task 11975 | stop processing: n_tokens = 521, truncated = 0 5.20.014.667 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.133 (> 0.100 thold), f_keep = 0.058 5.20.014.729 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 87.201 MiB) 5.20.014.732 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 122.116 MiB) 5.20.025.796 I slot launch_slot_: id 0 | task 12072 | processing task, is_child = 0 5.22.114.337 I slot print_timing: id 0 | task 12072 | prompt eval time = 511.71 ms / 226 tokens ( 2.26 ms per token, 441.66 tokens per second) 5.22.114.342 I slot print_timing: id 0 | task 12072 | eval time = 1576.82 ms / 79 tokens ( 20.22 ms per token, 49.47 tokens per second) 5.22.114.343 I slot print_timing: id 0 | task 12072 | total time = 2088.53 ms / 305 tokens 5.22.114.343 I slot print_timing: id 0 | task 12072 | graphs reused = 11371 5.22.114.344 I slot print_timing: id 0 | task 12072 | graph reallocs = 0 / 0 (same size) / (changed size) 5.22.114.363 I slot release: id 0 | task 12072 | stop processing: n_tokens = 304, truncated = 0 5.22.119.579 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 304, t_last = 333516921745 5.22.119.621 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 99.261 MiB) 5.22.122.397 I slot launch_slot_: id 0 | task 12154 | processing task, is_child = 0 5.25.068.490 I slot print_timing: id 0 | task 12154 | prompt eval time = 783.17 ms / 386 tokens ( 2.03 ms per token, 492.87 tokens per second) 5.25.068.497 I slot print_timing: id 0 | task 12154 | eval time = 2162.91 ms / 107 tokens ( 20.40 ms per token, 49.01 tokens per second) 5.25.068.497 I slot print_timing: id 0 | task 12154 | total time = 2946.08 ms / 493 tokens 5.25.068.498 I slot print_timing: id 0 | task 12154 | graphs reused = 11476 5.25.068.499 I slot print_timing: id 0 | task 12154 | graph reallocs = 0 / 0 (same size) / (changed size) 5.25.068.525 I slot release: id 0 | task 12154 | stop processing: n_tokens = 492, truncated = 0 5.25.074.060 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 492, t_last = 333519875907 5.25.074.117 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 88.854 MiB) 5.25.082.964 I slot launch_slot_: id 0 | task 12264 | processing task, is_child = 0 5.28.769.068 I slot print_timing: id 0 | task 12264 | prompt eval time = 1005.30 ms / 508 tokens ( 1.98 ms per token, 505.32 tokens per second) 5.28.769.074 I slot print_timing: id 0 | task 12264 | eval time = 2680.80 ms / 131 tokens ( 20.62 ms per token, 48.49 tokens per second) 5.28.769.075 I slot print_timing: id 0 | task 12264 | total time = 3686.09 ms / 639 tokens 5.28.769.075 I slot print_timing: id 0 | task 12264 | graphs reused = 11604 5.28.769.076 I slot print_timing: id 0 | task 12264 | graph reallocs = 0 / 0 (same size) / (changed size) 5.28.769.105 I slot release: id 0 | task 12264 | stop processing: n_tokens = 638, truncated = 0 5.28.775.217 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 638, t_last = 333523576487 5.28.775.283 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 94.304 MiB) 5.28.775.286 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 89.662 MiB) 5.28.785.268 I slot launch_slot_: id 0 | task 12398 | processing task, is_child = 0 5.31.186.398 I slot print_timing: id 0 | task 12398 | prompt eval time = 1139.88 ms / 567 tokens ( 2.01 ms per token, 497.42 tokens per second) 5.31.186.404 I slot print_timing: id 0 | task 12398 | eval time = 1261.23 ms / 62 tokens ( 20.68 ms per token, 48.37 tokens per second) 5.31.186.405 I slot print_timing: id 0 | task 12398 | total time = 2401.12 ms / 629 tokens 5.31.186.405 I slot print_timing: id 0 | task 12398 | graphs reused = 11664 5.31.186.406 I slot print_timing: id 0 | task 12398 | graph reallocs = 0 / 0 (same size) / (changed size) 5.31.186.439 I slot release: id 0 | task 12398 | stop processing: n_tokens = 628, truncated = 0 5.31.191.584 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 628, t_last = 333525993821 5.31.191.649 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 139.450 MiB) 5.31.203.206 I slot launch_slot_: id 0 | task 12464 | processing task, is_child = 0 5.33.533.397 I slot print_timing: id 0 | task 12464 | prompt eval time = 783.31 ms / 384 tokens ( 2.04 ms per token, 490.23 tokens per second) 5.33.533.403 I slot print_timing: id 0 | task 12464 | eval time = 1546.87 ms / 77 tokens ( 20.35 ms per token, 49.13 tokens per second) 5.33.533.404 I slot print_timing: id 0 | task 12464 | total time = 2330.18 ms / 461 tokens 5.33.533.405 I slot print_timing: id 0 | task 12464 | graphs reused = 11739 5.33.533.405 I slot print_timing: id 0 | task 12464 | graph reallocs = 0 / 0 (same size) / (changed size) 5.33.533.430 I slot release: id 0 | task 12464 | stop processing: n_tokens = 460, truncated = 0 5.33.538.917 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 460, t_last = 333528340812 5.33.538.974 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 110.654 MiB) 5.33.538.978 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 198.171 MiB) 5.33.542.767 I slot launch_slot_: id 0 | task 12544 | processing task, is_child = 0 5.36.419.446 I slot print_timing: id 0 | task 12544 | prompt eval time = 940.63 ms / 457 tokens ( 2.06 ms per token, 485.84 tokens per second) 5.36.419.453 I slot print_timing: id 0 | task 12544 | eval time = 1936.03 ms / 95 tokens ( 20.60 ms per token, 48.55 tokens per second) 5.36.419.453 I slot print_timing: id 0 | task 12544 | total time = 2876.67 ms / 552 tokens 5.36.419.454 I slot print_timing: id 0 | task 12544 | graphs reused = 11831 5.36.419.455 I slot print_timing: id 0 | task 12544 | graph reallocs = 0 / 0 (same size) / (changed size) 5.36.419.489 I slot release: id 0 | task 12544 | stop processing: n_tokens = 551, truncated = 0 5.36.425.129 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 551, t_last = 333531226871 5.36.434.909 I slot launch_slot_: id 0 | task 12642 | processing task, is_child = 0 5.38.402.354 I slot print_timing: id 0 | task 12642 | prompt eval time = 841.84 ms / 428 tokens ( 1.97 ms per token, 508.41 tokens per second) 5.38.402.362 I slot print_timing: id 0 | task 12642 | eval time = 1125.60 ms / 56 tokens ( 20.47 ms per token, 48.86 tokens per second) 5.38.402.363 I slot print_timing: id 0 | task 12642 | total time = 1967.44 ms / 484 tokens 5.38.402.363 I slot print_timing: id 0 | task 12642 | graphs reused = 11885 5.38.402.364 I slot print_timing: id 0 | task 12642 | graph reallocs = 0 / 0 (same size) / (changed size) 5.38.402.395 I slot release: id 0 | task 12642 | stop processing: n_tokens = 483, truncated = 0 5.38.408.359 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 483, t_last = 333533209777 5.38.408.413 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 95.288 MiB) 5.38.408.416 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 159.703 MiB) 5.38.418.162 I slot launch_slot_: id 0 | task 12701 | processing task, is_child = 0 5.42.238.722 I slot print_timing: id 0 | task 12701 | prompt eval time = 1140.12 ms / 555 tokens ( 2.05 ms per token, 486.79 tokens per second) 5.42.238.726 I slot print_timing: id 0 | task 12701 | eval time = 2680.43 ms / 131 tokens ( 20.62 ms per token, 48.50 tokens per second) 5.42.238.727 I slot print_timing: id 0 | task 12701 | total time = 3820.55 ms / 686 tokens 5.42.238.728 I slot print_timing: id 0 | task 12701 | graphs reused = 12014 5.42.238.728 I slot print_timing: id 0 | task 12701 | graph reallocs = 0 / 0 (same size) / (changed size) 5.42.238.766 I slot release: id 0 | task 12701 | stop processing: n_tokens = 685, truncated = 0 5.42.245.488 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 685, t_last = 333537046148 5.42.245.563 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 184.211 MiB) 5.42.257.995 I slot launch_slot_: id 0 | task 12836 | processing task, is_child = 0 5.45.948.891 I slot print_timing: id 0 | task 12836 | prompt eval time = 1257.97 ms / 643 tokens ( 1.96 ms per token, 511.14 tokens per second) 5.45.948.898 I slot print_timing: id 0 | task 12836 | eval time = 2432.91 ms / 119 tokens ( 20.62 ms per token, 48.50 tokens per second) 5.45.948.898 I slot print_timing: id 0 | task 12836 | total time = 3690.88 ms / 762 tokens 5.45.948.899 I slot print_timing: id 0 | task 12836 | graphs reused = 12131 5.45.948.900 I slot print_timing: id 0 | task 12836 | graph reallocs = 0 / 0 (same size) / (changed size) 5.45.948.934 I slot release: id 0 | task 12836 | stop processing: n_tokens = 761, truncated = 0 5.45.954.404 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 761, t_last = 333540756316 5.45.954.493 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.345 MiB) 5.45.968.957 I slot launch_slot_: id 0 | task 12959 | processing task, is_child = 0 5.48.346.285 I slot print_timing: id 0 | task 12959 | prompt eval time = 892.15 ms / 437 tokens ( 2.04 ms per token, 489.83 tokens per second) 5.48.346.291 I slot print_timing: id 0 | task 12959 | eval time = 1485.17 ms / 73 tokens ( 20.63 ms per token, 48.48 tokens per second) 5.48.346.292 I slot print_timing: id 0 | task 12959 | total time = 2377.32 ms / 510 tokens 5.48.346.293 I slot print_timing: id 0 | task 12959 | graphs reused = 12201 5.48.346.293 I slot print_timing: id 0 | task 12959 | graph reallocs = 0 / 0 (same size) / (changed size) 5.48.346.326 I slot release: id 0 | task 12959 | stop processing: n_tokens = 532, truncated = 0 5.48.352.245 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 532, t_last = 333543153708 5.48.357.154 I slot launch_slot_: id 0 | task 13035 | processing task, is_child = 0 5.52.017.577 I slot print_timing: id 0 | task 13035 | prompt eval time = 999.32 ms / 494 tokens ( 2.02 ms per token, 494.34 tokens per second) 5.52.017.580 I slot print_timing: id 0 | task 13035 | eval time = 2661.09 ms / 130 tokens ( 20.63 ms per token, 48.48 tokens per second) 5.52.017.580 I slot print_timing: id 0 | task 13035 | total time = 3660.41 ms / 624 tokens 5.52.017.581 I slot print_timing: id 0 | task 13035 | graphs reused = 12329 5.52.017.582 I slot print_timing: id 0 | task 13035 | graph reallocs = 0 / 0 (same size) / (changed size) 5.52.017.612 I slot release: id 0 | task 13035 | stop processing: n_tokens = 645, truncated = 0 5.52.022.848 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 645, t_last = 333546824994 5.52.022.932 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 146.624 MiB) 5.52.022.941 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 189.978 MiB) 5.52.036.646 I slot launch_slot_: id 0 | task 13168 | processing task, is_child = 0 5.55.082.071 I slot print_timing: id 0 | task 13168 | prompt eval time = 622.00 ms / 304 tokens ( 2.05 ms per token, 488.74 tokens per second) 5.55.082.075 I slot print_timing: id 0 | task 13168 | eval time = 2423.41 ms / 120 tokens ( 20.36 ms per token, 49.10 tokens per second) 5.55.082.076 I slot print_timing: id 0 | task 13168 | total time = 3045.42 ms / 424 tokens 5.55.082.076 I slot print_timing: id 0 | task 13168 | graphs reused = 12447 5.55.082.077 I slot print_timing: id 0 | task 13168 | graph reallocs = 0 / 0 (same size) / (changed size) 5.55.082.104 I slot release: id 0 | task 13168 | stop processing: n_tokens = 444, truncated = 0 5.55.087.529 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 444, t_last = 333549889486 5.55.093.011 I slot launch_slot_: id 0 | task 13291 | processing task, is_child = 0 5.58.876.779 I slot print_timing: id 0 | task 13291 | n_gen = 147, tg = 48.65 t/s, tg_3s = 48.98 t/s 5.59.371.573 I slot print_timing: id 0 | task 13291 | prompt eval time = 782.43 ms / 393 tokens ( 1.99 ms per token, 502.28 tokens per second) 5.59.371.579 I slot print_timing: id 0 | task 13291 | eval time = 3496.12 ms / 171 tokens ( 20.57 ms per token, 48.63 tokens per second) 5.59.371.579 I slot print_timing: id 0 | task 13291 | total time = 4278.55 ms / 564 tokens 5.59.371.580 I slot print_timing: id 0 | task 13291 | graphs reused = 12615 5.59.371.581 I slot print_timing: id 0 | task 13291 | graph reallocs = 0 / 0 (same size) / (changed size) 5.59.371.615 I slot release: id 0 | task 13291 | stop processing: n_tokens = 563, truncated = 0 5.59.378.644 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 563, t_last = 333554178997 5.59.388.414 I slot launch_slot_: id 0 | task 13465 | processing task, is_child = 0 6.02.843.848 I slot print_timing: id 0 | task 13465 | prompt eval time = 1372.13 ms / 695 tokens ( 1.97 ms per token, 506.51 tokens per second) 6.02.843.853 I slot print_timing: id 0 | task 13465 | eval time = 2083.29 ms / 102 tokens ( 20.63 ms per token, 48.48 tokens per second) 6.02.843.854 I slot print_timing: id 0 | task 13465 | total time = 3455.42 ms / 797 tokens 6.02.843.855 I slot print_timing: id 0 | task 13465 | graphs reused = 12714 6.02.843.855 I slot print_timing: id 0 | task 13465 | graph reallocs = 0 / 0 (same size) / (changed size) 6.02.843.892 I slot release: id 0 | task 13465 | stop processing: n_tokens = 796, truncated = 0 6.02.850.615 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 796, t_last = 333557651274 6.02.850.686 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 130.872 MiB) 6.02.850.692 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 92.475 MiB) 6.02.861.294 I slot launch_slot_: id 0 | task 13571 | processing task, is_child = 0 6.07.179.173 I slot print_timing: id 0 | task 13571 | n_gen = 147, tg = 48.46 t/s, tg_3s = 48.79 t/s 6.07.652.503 I slot print_timing: id 0 | task 13571 | prompt eval time = 1305.01 ms / 657 tokens ( 1.99 ms per token, 503.44 tokens per second) 6.07.652.506 I slot print_timing: id 0 | task 13571 | eval time = 3486.18 ms / 170 tokens ( 20.63 ms per token, 48.48 tokens per second) 6.07.652.507 I slot print_timing: id 0 | task 13571 | total time = 4791.20 ms / 827 tokens 6.07.652.507 I slot print_timing: id 0 | task 13571 | graphs reused = 12881 6.07.652.508 I slot print_timing: id 0 | task 13571 | graph reallocs = 0 / 0 (same size) / (changed size) 6.07.652.547 I slot release: id 0 | task 13571 | stop processing: n_tokens = 826, truncated = 0 6.07.656.986 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.130 (> 0.100 thold), f_keep = 0.036 6.07.657.068 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.294 MiB) 6.07.657.072 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 151.124 MiB) 6.07.667.456 I slot launch_slot_: id 0 | task 13745 | processing task, is_child = 0 6.09.039.998 I slot print_timing: id 0 | task 13745 | prompt eval time = 482.74 ms / 231 tokens ( 2.09 ms per token, 478.51 tokens per second) 6.09.040.005 I slot print_timing: id 0 | task 13745 | eval time = 889.79 ms / 45 tokens ( 20.22 ms per token, 49.45 tokens per second) 6.09.040.005 I slot print_timing: id 0 | task 13745 | total time = 1372.53 ms / 276 tokens 6.09.040.006 I slot print_timing: id 0 | task 13745 | graphs reused = 12923 6.09.040.007 I slot print_timing: id 0 | task 13745 | graph reallocs = 0 / 0 (same size) / (changed size) 6.09.040.025 I slot release: id 0 | task 13745 | stop processing: n_tokens = 275, truncated = 0 6.09.043.930 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.187 (> 0.100 thold), f_keep = 0.113 6.09.046.461 I slot launch_slot_: id 0 | task 13793 | processing task, is_child = 0 6.12.428.325 I slot print_timing: id 0 | task 13793 | n_gen = 151, tg = 49.74 t/s, tg_3s = 50.07 t/s 6.13.013.720 I slot print_timing: id 0 | task 13793 | prompt eval time = 366.29 ms / 166 tokens ( 2.21 ms per token, 453.19 tokens per second) 6.13.013.726 I slot print_timing: id 0 | task 13793 | eval time = 3600.96 ms / 180 tokens ( 20.12 ms per token, 49.71 tokens per second) 6.13.013.726 I slot print_timing: id 0 | task 13793 | total time = 3967.25 ms / 346 tokens 6.13.013.727 I slot print_timing: id 0 | task 13793 | graphs reused = 13100 6.13.013.728 I slot print_timing: id 0 | task 13793 | graph reallocs = 0 / 0 (same size) / (changed size) 6.13.013.749 I slot release: id 0 | task 13793 | stop processing: n_tokens = 345, truncated = 0 6.13.017.782 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.160 (> 0.100 thold), f_keep = 0.090 6.13.017.831 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.781 MiB) 6.13.021.102 I slot launch_slot_: id 0 | task 13976 | processing task, is_child = 0 6.16.489.780 I slot print_timing: id 0 | task 13976 | n_gen = 150, tg = 49.58 t/s, tg_3s = 49.91 t/s 6.18.883.207 I slot print_timing: id 0 | task 13976 | prompt eval time = 463.43 ms / 194 tokens ( 2.39 ms per token, 418.62 tokens per second) 6.18.883.213 I slot print_timing: id 0 | task 13976 | eval time = 5398.67 ms / 268 tokens ( 20.22 ms per token, 49.46 tokens per second) 6.18.883.213 I slot print_timing: id 0 | task 13976 | total time = 5862.10 ms / 462 tokens 6.18.883.214 I slot print_timing: id 0 | task 13976 | graphs reused = 13365 6.18.883.215 I slot print_timing: id 0 | task 13976 | graph reallocs = 0 / 0 (same size) / (changed size) 6.18.883.238 I slot release: id 0 | task 13976 | stop processing: n_tokens = 461, truncated = 0 6.18.887.179 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.208 (> 0.100 thold), f_keep = 0.067 6.18.887.240 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 187.340 MiB) 6.18.890.768 I slot launch_slot_: id 0 | task 14247 | processing task, is_child = 0 6.20.463.663 I slot print_timing: id 0 | task 14247 | prompt eval time = 364.81 ms / 149 tokens ( 2.45 ms per token, 408.44 tokens per second) 6.20.463.666 I slot print_timing: id 0 | task 14247 | eval time = 1208.08 ms / 61 tokens ( 20.13 ms per token, 49.67 tokens per second) 6.20.463.667 I slot print_timing: id 0 | task 14247 | total time = 1572.89 ms / 210 tokens 6.20.463.668 I slot print_timing: id 0 | task 14247 | graphs reused = 13424 6.20.463.668 I slot print_timing: id 0 | task 14247 | graph reallocs = 0 / 0 (same size) / (changed size) 6.20.463.686 I slot release: id 0 | task 14247 | stop processing: n_tokens = 209, truncated = 0 6.20.467.778 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.137 (> 0.100 thold), f_keep = 0.144 6.20.471.363 I slot launch_slot_: id 0 | task 14311 | processing task, is_child = 0 6.23.873.602 I slot print_timing: id 0 | task 14311 | prompt eval time = 512.74 ms / 219 tokens ( 2.34 ms per token, 427.12 tokens per second) 6.23.873.605 I slot print_timing: id 0 | task 14311 | eval time = 2889.49 ms / 144 tokens ( 20.21 ms per token, 49.49 tokens per second) 6.23.873.605 I slot print_timing: id 0 | task 14311 | total time = 3402.23 ms / 363 tokens 6.23.873.606 I slot print_timing: id 0 | task 14311 | graphs reused = 13565 6.23.873.607 I slot print_timing: id 0 | task 14311 | graph reallocs = 0 / 0 (same size) / (changed size) 6.23.873.630 I slot release: id 0 | task 14311 | stop processing: n_tokens = 362, truncated = 0 6.23.877.320 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.227 (> 0.100 thold), f_keep = 0.083 6.23.877.371 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.726 MiB) 6.23.880.607 I slot launch_slot_: id 0 | task 14458 | processing task, is_child = 0 6.24.461.030 I slot print_timing: id 0 | task 14458 | prompt eval time = 315.78 ms / 132 tokens ( 2.39 ms per token, 418.01 tokens per second) 6.24.461.036 I slot print_timing: id 0 | task 14458 | eval time = 264.62 ms / 14 tokens ( 20.36 ms per token, 49.13 tokens per second) 6.24.461.036 I slot print_timing: id 0 | task 14458 | total time = 580.41 ms / 146 tokens 6.24.461.037 I slot print_timing: id 0 | task 14458 | graphs reused = 13577 6.24.461.037 I slot print_timing: id 0 | task 14458 | graph reallocs = 0 / 0 (same size) / (changed size) 6.24.461.052 I slot release: id 0 | task 14458 | stop processing: n_tokens = 145, truncated = 0 6.24.464.796 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.207 6.24.467.812 I slot launch_slot_: id 0 | task 14475 | processing task, is_child = 0 6.25.332.877 I slot print_timing: id 0 | task 14475 | prompt eval time = 368.20 ms / 169 tokens ( 2.18 ms per token, 458.99 tokens per second) 6.25.332.881 I slot print_timing: id 0 | task 14475 | eval time = 496.85 ms / 25 tokens ( 20.70 ms per token, 48.30 tokens per second) 6.25.332.882 I slot print_timing: id 0 | task 14475 | total time = 865.05 ms / 194 tokens 6.25.332.882 I slot print_timing: id 0 | task 14475 | graphs reused = 13600 6.25.332.883 I slot print_timing: id 0 | task 14475 | graph reallocs = 0 / 0 (same size) / (changed size) 6.25.332.901 I slot release: id 0 | task 14475 | stop processing: n_tokens = 193, truncated = 0 6.25.337.065 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.155 6.25.341.457 I slot launch_slot_: id 0 | task 14503 | processing task, is_child = 0 6.28.687.959 I slot print_timing: id 0 | task 14503 | prompt eval time = 368.11 ms / 160 tokens ( 2.30 ms per token, 434.65 tokens per second) 6.28.687.962 I slot print_timing: id 0 | task 14503 | eval time = 2978.38 ms / 149 tokens ( 20.12 ms per token, 49.69 tokens per second) 6.28.687.962 I slot print_timing: id 0 | task 14503 | total time = 3346.49 ms / 309 tokens 6.28.687.963 I slot print_timing: id 0 | task 14503 | graphs reused = 13746 6.28.687.964 I slot print_timing: id 0 | task 14503 | graph reallocs = 0 / 0 (same size) / (changed size) 6.28.687.981 I slot release: id 0 | task 14503 | stop processing: n_tokens = 308, truncated = 0 6.28.691.673 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.291 (> 0.100 thold), f_keep = 0.097 6.28.691.721 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 144.021 MiB) 6.28.696.834 I slot launch_slot_: id 0 | task 14655 | processing task, is_child = 0 6.31.352.911 I slot print_timing: id 0 | task 14655 | prompt eval time = 262.88 ms / 103 tokens ( 2.55 ms per token, 391.82 tokens per second) 6.31.352.914 I slot print_timing: id 0 | task 14655 | eval time = 2393.19 ms / 120 tokens ( 20.11 ms per token, 49.72 tokens per second) 6.31.352.916 I slot print_timing: id 0 | task 14655 | total time = 2656.06 ms / 223 tokens 6.31.352.917 I slot print_timing: id 0 | task 14655 | graphs reused = 13864 6.31.352.917 I slot print_timing: id 0 | task 14655 | graph reallocs = 0 / 0 (same size) / (changed size) 6.31.352.935 I slot release: id 0 | task 14655 | stop processing: n_tokens = 222, truncated = 0 6.31.357.002 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.135 6.31.359.282 I slot launch_slot_: id 0 | task 14778 | processing task, is_child = 0 6.31.904.846 I slot print_timing: id 0 | task 14778 | prompt eval time = 402.74 ms / 165 tokens ( 2.44 ms per token, 409.69 tokens per second) 6.31.904.849 I slot print_timing: id 0 | task 14778 | eval time = 142.81 ms / 8 tokens ( 20.40 ms per token, 49.02 tokens per second) 6.31.904.850 I slot print_timing: id 0 | task 14778 | total time = 545.55 ms / 173 tokens 6.31.904.851 I slot print_timing: id 0 | task 14778 | graphs reused = 13870 6.31.904.851 I slot print_timing: id 0 | task 14778 | graph reallocs = 0 / 0 (same size) / (changed size) 6.31.904.871 I slot release: id 0 | task 14778 | stop processing: n_tokens = 172, truncated = 0 6.31.909.283 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.174 6.31.909.327 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 136.004 MiB) 6.31.914.823 I slot launch_slot_: id 0 | task 14789 | processing task, is_child = 0 6.35.255.174 I slot print_timing: id 0 | task 14789 | prompt eval time = 370.01 ms / 165 tokens ( 2.24 ms per token, 445.93 tokens per second) 6.35.255.182 I slot print_timing: id 0 | task 14789 | eval time = 2970.33 ms / 148 tokens ( 20.21 ms per token, 49.49 tokens per second) 6.35.255.183 I slot print_timing: id 0 | task 14789 | total time = 3340.34 ms / 313 tokens 6.35.255.183 I slot print_timing: id 0 | task 14789 | graphs reused = 14015 6.35.255.184 I slot print_timing: id 0 | task 14789 | graph reallocs = 0 / 0 (same size) / (changed size) 6.35.255.205 I slot release: id 0 | task 14789 | stop processing: n_tokens = 312, truncated = 0 6.35.259.250 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.162 (> 0.100 thold), f_keep = 0.096 6.35.264.206 I slot launch_slot_: id 0 | task 14940 | processing task, is_child = 0 6.38.732.866 I slot print_timing: id 0 | task 14940 | n_gen = 151, tg = 49.72 t/s, tg_3s = 50.05 t/s 6.41.734.327 I slot print_timing: id 0 | task 14940 | n_gen = 299, tg = 49.51 t/s, tg_3s = 49.31 t/s 6.44.741.139 I slot print_timing: id 0 | task 14940 | n_gen = 445, tg = 49.20 t/s, tg_3s = 48.56 t/s 6.47.748.155 I slot print_timing: id 0 | task 14940 | n_gen = 591, tg = 49.03 t/s, tg_3s = 48.55 t/s 6.50.757.143 I slot print_timing: id 0 | task 14940 | n_gen = 737, tg = 48.93 t/s, tg_3s = 48.52 t/s 6.50.860.226 I slot print_timing: id 0 | task 14940 | prompt eval time = 451.68 ms / 185 tokens ( 2.44 ms per token, 409.58 tokens per second) 6.50.860.231 I slot print_timing: id 0 | task 14940 | eval time = 15144.32 ms / 742 tokens ( 20.44 ms per token, 48.93 tokens per second) 6.50.860.232 I slot print_timing: id 0 | task 14940 | total time = 15596.00 ms / 927 tokens 6.50.860.233 I slot print_timing: id 0 | task 14940 | graphs reused = 14752 6.50.860.234 I slot print_timing: id 0 | task 14940 | graph reallocs = 0 / 0 (same size) / (changed size) 6.50.860.256 I slot release: id 0 | task 14940 | stop processing: n_tokens = 926, truncated = 0 6.50.864.352 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.032 6.50.864.439 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 172.220 MiB) 6.50.876.518 I slot launch_slot_: id 0 | task 15685 | processing task, is_child = 0 6.52.451.671 I slot print_timing: id 0 | task 15685 | prompt eval time = 366.13 ms / 160 tokens ( 2.29 ms per token, 437.01 tokens per second) 6.52.451.674 I slot print_timing: id 0 | task 15685 | eval time = 1209.02 ms / 61 tokens ( 20.15 ms per token, 49.63 tokens per second) 6.52.451.675 I slot print_timing: id 0 | task 15685 | total time = 1575.14 ms / 221 tokens 6.52.451.676 I slot print_timing: id 0 | task 15685 | graphs reused = 14811 6.52.451.676 I slot print_timing: id 0 | task 15685 | graph reallocs = 0 / 0 (same size) / (changed size) 6.52.451.699 I slot release: id 0 | task 15685 | stop processing: n_tokens = 220, truncated = 0 6.52.455.624 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.191 (> 0.100 thold), f_keep = 0.136 6.52.460.883 I slot launch_slot_: id 0 | task 15749 | processing task, is_child = 0 6.55.846.159 I slot print_timing: id 0 | task 15749 | n_gen = 150, tg = 49.35 t/s, tg_3s = 49.68 t/s 6.58.855.360 I slot print_timing: id 0 | task 15749 | n_gen = 299, tg = 49.43 t/s, tg_3s = 49.51 t/s 7.01.864.456 I slot print_timing: id 0 | task 15749 | n_gen = 445, tg = 49.13 t/s, tg_3s = 48.52 t/s 7.04.874.452 I slot print_timing: id 0 | task 15749 | n_gen = 589, tg = 48.81 t/s, tg_3s = 47.84 t/s 7.07.881.028 I slot print_timing: id 0 | task 15749 | n_gen = 735, tg = 48.76 t/s, tg_3s = 48.56 t/s 7.08.168.204 I slot print_timing: id 0 | task 15749 | prompt eval time = 366.11 ms / 157 tokens ( 2.33 ms per token, 428.83 tokens per second) 7.08.168.211 I slot print_timing: id 0 | task 15749 | eval time = 15341.20 ms / 749 tokens ( 20.51 ms per token, 48.76 tokens per second) 7.08.168.211 I slot print_timing: id 0 | task 15749 | total time = 15707.31 ms / 906 tokens 7.08.168.212 I slot print_timing: id 0 | task 15749 | graphs reused = 15555 7.08.168.213 I slot print_timing: id 0 | task 15749 | graph reallocs = 0 / 0 (same size) / (changed size) 7.08.168.232 I slot release: id 0 | task 15749 | stop processing: n_tokens = 905, truncated = 0 7.08.172.674 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.033 7.08.172.765 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 189.169 MiB) 7.08.184.805 I slot launch_slot_: id 0 | task 16501 | processing task, is_child = 0 7.10.288.408 I slot print_timing: id 0 | task 16501 | prompt eval time = 368.30 ms / 171 tokens ( 2.15 ms per token, 464.30 tokens per second) 7.10.288.415 I slot print_timing: id 0 | task 16501 | eval time = 1735.30 ms / 87 tokens ( 20.18 ms per token, 49.56 tokens per second) 7.10.288.415 I slot print_timing: id 0 | task 16501 | total time = 2103.59 ms / 258 tokens 7.10.288.416 I slot print_timing: id 0 | task 16501 | graphs reused = 15639 7.10.288.417 I slot print_timing: id 0 | task 16501 | graph reallocs = 0 / 0 (same size) / (changed size) 7.10.288.435 I slot release: id 0 | task 16501 | stop processing: n_tokens = 257, truncated = 0 7.10.292.482 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.164 (> 0.100 thold), f_keep = 0.117 7.10.296.746 I slot launch_slot_: id 0 | task 16591 | processing task, is_child = 0 7.13.769.159 I slot print_timing: id 0 | task 16591 | n_gen = 148, tg = 48.86 t/s, tg_3s = 49.19 t/s 7.16.787.682 I slot print_timing: id 0 | task 16591 | n_gen = 291, tg = 48.12 t/s, tg_3s = 47.37 t/s 7.19.800.378 I slot print_timing: id 0 | task 16591 | n_gen = 432, tg = 47.68 t/s, tg_3s = 46.80 t/s 7.22.811.292 I slot print_timing: id 0 | task 16591 | n_gen = 576, tg = 47.71 t/s, tg_3s = 47.83 t/s 7.25.816.779 I slot print_timing: id 0 | task 16591 | n_gen = 719, tg = 47.69 t/s, tg_3s = 47.58 t/s 7.28.662.642 I slot print_timing: id 0 | task 16591 | prompt eval time = 463.77 ms / 183 tokens ( 2.53 ms per token, 394.60 tokens per second) 7.28.662.647 I slot print_timing: id 0 | task 16591 | eval time = 17902.12 ms / 857 tokens ( 20.91 ms per token, 47.82 tokens per second) 7.28.662.649 I slot print_timing: id 0 | task 16591 | total time = 18365.88 ms / 1040 tokens 7.28.662.650 I slot print_timing: id 0 | task 16591 | graphs reused = 16490 7.28.662.650 I slot print_timing: id 0 | task 16591 | graph reallocs = 0 / 0 (same size) / (changed size) 7.28.662.673 I slot release: id 0 | task 16591 | stop processing: n_tokens = 1039, truncated = 0 7.28.666.855 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.184 (> 0.100 thold), f_keep = 0.029 7.28.666.959 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 68.461 MiB) 7.28.666.969 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 78.306 MiB) 7.28.678.651 I slot launch_slot_: id 0 | task 17451 | processing task, is_child = 0 7.32.067.326 I slot print_timing: id 0 | task 17451 | n_gen = 151, tg = 49.71 t/s, tg_3s = 50.04 t/s 7.35.067.738 I slot print_timing: id 0 | task 17451 | n_gen = 299, tg = 49.52 t/s, tg_3s = 49.33 t/s 7.38.076.842 I slot print_timing: id 0 | task 17451 | n_gen = 445, tg = 49.19 t/s, tg_3s = 48.52 t/s 7.41.095.184 I slot print_timing: id 0 | task 17451 | n_gen = 592, tg = 49.06 t/s, tg_3s = 48.70 t/s 7.42.331.550 I slot print_timing: id 0 | task 17451 | prompt eval time = 371.10 ms / 163 tokens ( 2.28 ms per token, 439.23 tokens per second) 7.42.331.556 I slot print_timing: id 0 | task 17451 | eval time = 13281.79 ms / 652 tokens ( 20.40 ms per token, 49.01 tokens per second) 7.42.331.557 I slot print_timing: id 0 | task 17451 | total time = 13652.89 ms / 815 tokens 7.42.331.557 I slot print_timing: id 0 | task 17451 | graphs reused = 17137 7.42.331.558 I slot print_timing: id 0 | task 17451 | graph reallocs = 0 / 0 (same size) / (changed size) 7.42.331.577 I slot release: id 0 | task 17451 | stop processing: n_tokens = 814, truncated = 0 7.42.335.853 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.169 (> 0.100 thold), f_keep = 0.037 7.42.335.943 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.954 MiB) 7.42.344.470 I slot launch_slot_: id 0 | task 18106 | processing task, is_child = 0 7.45.720.350 I slot print_timing: id 0 | task 18106 | n_gen = 150, tg = 49.60 t/s, tg_3s = 49.94 t/s 7.46.771.666 I slot print_timing: id 0 | task 18106 | prompt eval time = 372.11 ms / 177 tokens ( 2.10 ms per token, 475.67 tokens per second) 7.46.771.669 I slot print_timing: id 0 | task 18106 | eval time = 4055.08 ms / 202 tokens ( 20.17 ms per token, 49.57 tokens per second) 7.46.771.669 I slot print_timing: id 0 | task 18106 | total time = 4427.19 ms / 379 tokens 7.46.771.670 I slot print_timing: id 0 | task 18106 | graphs reused = 17336 7.46.771.671 I slot print_timing: id 0 | task 18106 | graph reallocs = 0 / 0 (same size) / (changed size) 7.46.771.689 I slot release: id 0 | task 18106 | stop processing: n_tokens = 378, truncated = 0 7.46.775.736 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.196 (> 0.100 thold), f_keep = 0.079 7.46.775.794 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 64.452 MiB) 7.46.775.801 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 83.650 MiB) 7.46.780.898 I slot launch_slot_: id 0 | task 18311 | processing task, is_child = 0 7.50.033.204 I slot print_timing: id 0 | task 18311 | prompt eval time = 366.28 ms / 153 tokens ( 2.39 ms per token, 417.71 tokens per second) 7.50.033.208 I slot print_timing: id 0 | task 18311 | eval time = 2886.02 ms / 144 tokens ( 20.18 ms per token, 49.55 tokens per second) 7.50.033.208 I slot print_timing: id 0 | task 18311 | total time = 3252.30 ms / 297 tokens 7.50.033.209 I slot print_timing: id 0 | task 18311 | graphs reused = 17477 7.50.033.210 I slot print_timing: id 0 | task 18311 | graph reallocs = 0 / 0 (same size) / (changed size) 7.50.033.230 I slot release: id 0 | task 18311 | stop processing: n_tokens = 296, truncated = 0 7.50.037.104 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.217 (> 0.100 thold), f_keep = 0.101 7.50.037.155 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 96.414 MiB) 7.50.039.304 I slot launch_slot_: id 0 | task 18458 | processing task, is_child = 0 7.50.961.556 I slot print_timing: id 0 | task 18458 | prompt eval time = 315.51 ms / 138 tokens ( 2.29 ms per token, 437.39 tokens per second) 7.50.961.561 I slot print_timing: id 0 | task 18458 | eval time = 606.74 ms / 31 tokens ( 20.22 ms per token, 49.44 tokens per second) 7.50.961.563 I slot print_timing: id 0 | task 18458 | total time = 922.25 ms / 169 tokens 7.50.961.564 I slot print_timing: id 0 | task 18458 | graphs reused = 17506 7.50.961.564 I slot print_timing: id 0 | task 18458 | graph reallocs = 0 / 0 (same size) / (changed size) 7.50.961.580 I slot release: id 0 | task 18458 | stop processing: n_tokens = 168, truncated = 0 7.50.965.568 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.168 (> 0.100 thold), f_keep = 0.179 7.50.967.100 I slot launch_slot_: id 0 | task 18492 | processing task, is_child = 0 7.54.337.540 I slot print_timing: id 0 | task 18492 | n_gen = 150, tg = 49.66 t/s, tg_3s = 49.99 t/s 7.57.354.557 I slot print_timing: id 0 | task 18492 | n_gen = 299, tg = 49.52 t/s, tg_3s = 49.39 t/s 7.58.176.183 I slot print_timing: id 0 | task 18492 | prompt eval time = 369.93 ms / 179 tokens ( 2.07 ms per token, 483.87 tokens per second) 7.58.176.187 I slot print_timing: id 0 | task 18492 | eval time = 6839.14 ms / 339 tokens ( 20.23 ms per token, 49.42 tokens per second) 7.58.176.188 I slot print_timing: id 0 | task 18492 | total time = 7209.07 ms / 518 tokens 7.58.176.188 I slot print_timing: id 0 | task 18492 | graphs reused = 17841 7.58.176.189 I slot print_timing: id 0 | task 18492 | graph reallocs = 0 / 0 (same size) / (changed size) 7.58.176.207 I slot release: id 0 | task 18492 | stop processing: n_tokens = 517, truncated = 0 7.58.180.407 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.169 (> 0.100 thold), f_keep = 0.066 7.58.180.479 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 121.238 MiB) 7.58.186.303 I slot launch_slot_: id 0 | task 18834 | processing task, is_child = 0 8.01.329.052 I slot print_timing: id 0 | task 18834 | prompt eval time = 429.16 ms / 201 tokens ( 2.14 ms per token, 468.35 tokens per second) 8.01.329.056 I slot print_timing: id 0 | task 18834 | eval time = 2713.58 ms / 135 tokens ( 20.25 ms per token, 49.38 tokens per second) 8.01.329.056 I slot print_timing: id 0 | task 18834 | total time = 3142.74 ms / 336 tokens 8.01.329.057 I slot print_timing: id 0 | task 18834 | graphs reused = 17973 8.01.329.057 I slot print_timing: id 0 | task 18834 | graph reallocs = 0 / 0 (same size) / (changed size) 8.01.329.078 I slot release: id 0 | task 18834 | stop processing: n_tokens = 335, truncated = 0 8.01.332.862 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.224 (> 0.100 thold), f_keep = 0.090 8.01.332.907 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 103.764 MiB) 8.01.337.883 I slot launch_slot_: id 0 | task 18972 | processing task, is_child = 0 8.04.668.560 I slot print_timing: id 0 | task 18972 | n_gen = 151, tg = 49.79 t/s, tg_3s = 50.13 t/s 8.06.573.872 I slot print_timing: id 0 | task 18972 | prompt eval time = 318.23 ms / 134 tokens ( 2.37 ms per token, 421.08 tokens per second) 8.06.573.874 I slot print_timing: id 0 | task 18972 | eval time = 4917.75 ms / 246 tokens ( 20.07 ms per token, 49.82 tokens per second) 8.06.573.875 I slot print_timing: id 0 | task 18972 | total time = 5235.98 ms / 380 tokens 8.06.573.876 I slot print_timing: id 0 | task 18972 | graphs reused = 18216 8.06.573.876 I slot print_timing: id 0 | task 18972 | graph reallocs = 0 / 0 (same size) / (changed size) 8.06.573.893 I slot release: id 0 | task 18972 | stop processing: n_tokens = 379, truncated = 0 8.06.577.810 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.205 (> 0.100 thold), f_keep = 0.079 8.06.577.862 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 71.028 MiB) 8.06.580.680 I slot launch_slot_: id 0 | task 19221 | processing task, is_child = 0 8.07.309.579 I slot print_timing: id 0 | task 19221 | prompt eval time = 364.13 ms / 146 tokens ( 2.49 ms per token, 400.96 tokens per second) 8.07.309.585 I slot print_timing: id 0 | task 19221 | eval time = 364.76 ms / 19 tokens ( 20.26 ms per token, 49.35 tokens per second) 8.07.309.585 I slot print_timing: id 0 | task 19221 | total time = 728.89 ms / 165 tokens 8.07.309.586 I slot print_timing: id 0 | task 19221 | graphs reused = 18233 8.07.309.587 I slot print_timing: id 0 | task 19221 | graph reallocs = 0 / 0 (same size) / (changed size) 8.07.309.602 I slot release: id 0 | task 19221 | stop processing: n_tokens = 164, truncated = 0 8.07.313.142 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.217 (> 0.100 thold), f_keep = 0.183 8.07.314.630 I slot launch_slot_: id 0 | task 19243 | processing task, is_child = 0 8.08.838.496 I slot print_timing: id 0 | task 19243 | prompt eval time = 315.61 ms / 138 tokens ( 2.29 ms per token, 437.26 tokens per second) 8.08.838.507 I slot print_timing: id 0 | task 19243 | eval time = 1208.25 ms / 61 tokens ( 20.14 ms per token, 49.66 tokens per second) 8.08.838.507 I slot print_timing: id 0 | task 19243 | total time = 1523.86 ms / 199 tokens 8.08.838.508 I slot print_timing: id 0 | task 19243 | graphs reused = 18292 8.08.838.509 I slot print_timing: id 0 | task 19243 | graph reallocs = 0 / 0 (same size) / (changed size) 8.08.838.526 I slot release: id 0 | task 19243 | stop processing: n_tokens = 198, truncated = 0 8.08.842.341 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.152 8.08.842.376 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 78.130 MiB) 8.08.844.039 I slot launch_slot_: id 0 | task 19307 | processing task, is_child = 0 8.09.736.288 I slot print_timing: id 0 | task 19307 | prompt eval time = 365.89 ms / 155 tokens ( 2.36 ms per token, 423.63 tokens per second) 8.09.736.294 I slot print_timing: id 0 | task 19307 | eval time = 526.35 ms / 27 tokens ( 20.24 ms per token, 49.40 tokens per second) 8.09.736.295 I slot print_timing: id 0 | task 19307 | total time = 892.24 ms / 182 tokens 8.09.736.296 I slot print_timing: id 0 | task 19307 | graphs reused = 18317 8.09.736.296 I slot print_timing: id 0 | task 19307 | graph reallocs = 0 / 0 (same size) / (changed size) 8.09.736.313 I slot release: id 0 | task 19307 | stop processing: n_tokens = 181, truncated = 0 8.09.740.227 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.166 8.09.740.263 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 124.473 MiB) 8.09.742.951 I slot launch_slot_: id 0 | task 19337 | processing task, is_child = 0 8.11.787.208 I slot print_timing: id 0 | task 19337 | prompt eval time = 366.31 ms / 160 tokens ( 2.29 ms per token, 436.79 tokens per second) 8.11.787.215 I slot print_timing: id 0 | task 19337 | eval time = 1677.93 ms / 84 tokens ( 20.22 ms per token, 49.47 tokens per second) 8.11.787.216 I slot print_timing: id 0 | task 19337 | total time = 2044.25 ms / 244 tokens 8.11.787.217 I slot print_timing: id 0 | task 19337 | graphs reused = 18399 8.11.787.217 I slot print_timing: id 0 | task 19337 | graph reallocs = 0 / 0 (same size) / (changed size) 8.11.787.235 I slot release: id 0 | task 19337 | stop processing: n_tokens = 243, truncated = 0 8.11.791.128 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.192 (> 0.100 thold), f_keep = 0.123 8.11.795.177 I slot launch_slot_: id 0 | task 19424 | processing task, is_child = 0 8.15.177.303 I slot print_timing: id 0 | task 19424 | n_gen = 149, tg = 49.08 t/s, tg_3s = 49.41 t/s 8.18.194.563 I slot print_timing: id 0 | task 19424 | n_gen = 298, tg = 49.23 t/s, tg_3s = 49.38 t/s 8.21.198.769 I slot print_timing: id 0 | task 19424 | n_gen = 444, tg = 49.02 t/s, tg_3s = 48.60 t/s 8.24.205.402 I slot print_timing: id 0 | task 19424 | n_gen = 590, tg = 48.91 t/s, tg_3s = 48.56 t/s 8.27.212.011 I slot print_timing: id 0 | task 19424 | n_gen = 736, tg = 48.84 t/s, tg_3s = 48.56 t/s 8.30.228.503 I slot print_timing: id 0 | task 19424 | n_gen = 882, tg = 48.76 t/s, tg_3s = 48.40 t/s 8.33.166.971 I slot print_timing: id 0 | task 19424 | prompt eval time = 366.51 ms / 156 tokens ( 2.35 ms per token, 425.63 tokens per second) 8.33.166.978 I slot print_timing: id 0 | task 19424 | eval time = 21005.27 ms / 1024 tokens ( 20.53 ms per token, 48.70 tokens per second) 8.33.166.978 I slot print_timing: id 0 | task 19424 | total time = 21371.78 ms / 1180 tokens 8.33.166.979 I slot print_timing: id 0 | task 19424 | graphs reused = 19417 8.33.166.980 I slot print_timing: id 0 | task 19424 | graph reallocs = 0 / 0 (same size) / (changed size) 8.33.167.004 I slot release: id 0 | task 19424 | stop processing: n_tokens = 1179, truncated = 0 8.33.171.474 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.190 (> 0.100 thold), f_keep = 0.025 8.33.171.581 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 99.508 MiB) 8.33.181.825 I slot launch_slot_: id 0 | task 20451 | processing task, is_child = 0 8.36.560.082 I slot print_timing: id 0 | task 20451 | n_gen = 151, tg = 49.79 t/s, tg_3s = 50.12 t/s 8.39.565.454 I slot print_timing: id 0 | task 20451 | n_gen = 299, tg = 49.52 t/s, tg_3s = 49.25 t/s 8.42.567.103 I slot print_timing: id 0 | task 20451 | n_gen = 445, tg = 49.23 t/s, tg_3s = 48.64 t/s 8.45.568.122 I slot print_timing: id 0 | task 20451 | n_gen = 590, tg = 49.00 t/s, tg_3s = 48.32 t/s 8.48.569.925 I slot print_timing: id 0 | task 20451 | n_gen = 736, tg = 48.93 t/s, tg_3s = 48.64 t/s 8.50.545.558 I slot print_timing: id 0 | task 20451 | prompt eval time = 365.76 ms / 158 tokens ( 2.31 ms per token, 431.97 tokens per second) 8.50.545.564 I slot print_timing: id 0 | task 20451 | eval time = 16997.96 ms / 832 tokens ( 20.45 ms per token, 48.89 tokens per second) 8.50.545.565 I slot print_timing: id 0 | task 20451 | total time = 17363.72 ms / 990 tokens 8.50.545.566 I slot print_timing: id 0 | task 20451 | graphs reused = 20244 8.50.545.566 I slot print_timing: id 0 | task 20451 | graph reallocs = 0 / 0 (same size) / (changed size) 8.50.545.594 I slot release: id 0 | task 20451 | stop processing: n_tokens = 989, truncated = 0 8.50.550.095 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.030 8.50.550.189 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 90.683 MiB) 8.50.550.193 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 90.014 MiB) 8.50.559.850 I slot launch_slot_: id 0 | task 21286 | processing task, is_child = 0 8.53.716.472 I slot print_timing: id 0 | task 21286 | prompt eval time = 353.25 ms / 155 tokens ( 2.28 ms per token, 438.79 tokens per second) 8.53.716.476 I slot print_timing: id 0 | task 21286 | eval time = 2803.37 ms / 140 tokens ( 20.17 ms per token, 49.58 tokens per second) 8.53.716.477 I slot print_timing: id 0 | task 21286 | total time = 3156.61 ms / 295 tokens 8.53.716.478 I slot print_timing: id 0 | task 21286 | graphs reused = 20381 8.53.716.478 I slot print_timing: id 0 | task 21286 | graph reallocs = 0 / 0 (same size) / (changed size) 8.53.716.495 I slot release: id 0 | task 21286 | stop processing: n_tokens = 294, truncated = 0 8.53.720.443 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.176 (> 0.100 thold), f_keep = 0.102 8.53.720.489 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 101.161 MiB) 8.53.724.174 I slot launch_slot_: id 0 | task 21429 | processing task, is_child = 0 8.55.342.473 I slot print_timing: id 0 | task 21429 | prompt eval time = 370.73 ms / 170 tokens ( 2.18 ms per token, 458.56 tokens per second) 8.55.342.480 I slot print_timing: id 0 | task 21429 | eval time = 1247.57 ms / 63 tokens ( 20.12 ms per token, 49.70 tokens per second) 8.55.342.480 I slot print_timing: id 0 | task 21429 | total time = 1618.29 ms / 233 tokens 8.55.342.481 I slot print_timing: id 0 | task 21429 | graphs reused = 20442 8.55.342.482 I slot print_timing: id 0 | task 21429 | graph reallocs = 0 / 0 (same size) / (changed size) 8.55.342.500 I slot release: id 0 | task 21429 | stop processing: n_tokens = 232, truncated = 0 8.55.346.555 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.134 8.55.349.865 I slot launch_slot_: id 0 | task 21495 | processing task, is_child = 0 8.56.645.758 I slot print_timing: id 0 | task 21495 | prompt eval time = 368.60 ms / 160 tokens ( 2.30 ms per token, 434.07 tokens per second) 8.56.645.765 I slot print_timing: id 0 | task 21495 | eval time = 927.28 ms / 47 tokens ( 20.16 ms per token, 49.61 tokens per second) 8.56.645.767 I slot print_timing: id 0 | task 21495 | total time = 1295.88 ms / 207 tokens 8.56.645.767 I slot print_timing: id 0 | task 21495 | graphs reused = 20487 8.56.645.768 I slot print_timing: id 0 | task 21495 | graph reallocs = 0 / 0 (same size) / (changed size) 8.56.645.786 I slot release: id 0 | task 21495 | stop processing: n_tokens = 206, truncated = 0 8.56.649.800 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.186 (> 0.100 thold), f_keep = 0.146 8.56.649.835 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 103.341 MiB) 8.56.652.733 I slot launch_slot_: id 0 | task 21545 | processing task, is_child = 0 8.58.675.250 I slot print_timing: id 0 | task 21545 | prompt eval time = 369.81 ms / 161 tokens ( 2.30 ms per token, 435.36 tokens per second) 8.58.675.254 I slot print_timing: id 0 | task 21545 | eval time = 1652.70 ms / 83 tokens ( 20.15 ms per token, 49.62 tokens per second) 8.58.675.254 I slot print_timing: id 0 | task 21545 | total time = 2022.51 ms / 244 tokens 8.58.675.255 I slot print_timing: id 0 | task 21545 | graphs reused = 20568 8.58.675.256 I slot print_timing: id 0 | task 21545 | graph reallocs = 0 / 0 (same size) / (changed size) 8.58.675.273 I slot release: id 0 | task 21545 | stop processing: n_tokens = 243, truncated = 0 8.58.679.326 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.123 8.58.684.669 I slot launch_slot_: id 0 | task 21631 | processing task, is_child = 0 9.01.336.045 I slot print_timing: id 0 | task 21631 | prompt eval time = 355.16 ms / 169 tokens ( 2.10 ms per token, 475.85 tokens per second) 9.01.336.048 I slot print_timing: id 0 | task 21631 | eval time = 2296.21 ms / 115 tokens ( 20.14 ms per token, 49.65 tokens per second) 9.01.336.049 I slot print_timing: id 0 | task 21631 | total time = 2651.36 ms / 284 tokens 9.01.336.049 I slot print_timing: id 0 | task 21631 | graphs reused = 20680 9.01.336.050 I slot print_timing: id 0 | task 21631 | graph reallocs = 0 / 0 (same size) / (changed size) 9.01.336.068 I slot release: id 0 | task 21631 | stop processing: n_tokens = 283, truncated = 0 9.01.340.191 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.164 (> 0.100 thold), f_keep = 0.106 9.01.340.235 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.570 MiB) 9.01.345.470 I slot launch_slot_: id 0 | task 21749 | processing task, is_child = 0 9.02.534.087 I slot print_timing: id 0 | task 21749 | prompt eval time = 462.71 ms / 183 tokens ( 2.53 ms per token, 395.50 tokens per second) 9.02.534.093 I slot print_timing: id 0 | task 21749 | eval time = 725.90 ms / 37 tokens ( 20.16 ms per token, 49.59 tokens per second) 9.02.534.094 I slot print_timing: id 0 | task 21749 | total time = 1188.61 ms / 220 tokens 9.02.534.095 I slot print_timing: id 0 | task 21749 | graphs reused = 20715 9.02.534.095 I slot print_timing: id 0 | task 21749 | graph reallocs = 0 / 0 (same size) / (changed size) 9.02.534.114 I slot release: id 0 | task 21749 | stop processing: n_tokens = 219, truncated = 0 9.02.538.070 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.174 (> 0.100 thold), f_keep = 0.137 9.02.538.108 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 67.160 MiB) 9.02.541.291 I slot launch_slot_: id 0 | task 21789 | processing task, is_child = 0 9.05.925.990 I slot print_timing: id 0 | task 21789 | n_gen = 150, tg = 49.37 t/s, tg_3s = 49.70 t/s 9.07.884.389 I slot print_timing: id 0 | task 21789 | prompt eval time = 366.72 ms / 172 tokens ( 2.13 ms per token, 469.03 tokens per second) 9.07.884.393 I slot print_timing: id 0 | task 21789 | eval time = 4976.37 ms / 247 tokens ( 20.23 ms per token, 49.43 tokens per second) 9.07.884.393 I slot print_timing: id 0 | task 21789 | total time = 5343.09 ms / 419 tokens 9.07.884.394 I slot print_timing: id 0 | task 21789 | graphs reused = 20959 9.07.884.395 I slot print_timing: id 0 | task 21789 | graph reallocs = 0 / 0 (same size) / (changed size) 9.07.884.413 I slot release: id 0 | task 21789 | stop processing: n_tokens = 418, truncated = 0 9.07.888.535 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.165 (> 0.100 thold), f_keep = 0.072 9.07.888.597 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 97.047 MiB) 9.07.893.509 I slot launch_slot_: id 0 | task 22039 | processing task, is_child = 0 9.11.335.345 I slot print_timing: id 0 | task 22039 | n_gen = 151, tg = 49.73 t/s, tg_3s = 50.06 t/s 9.14.352.505 I slot print_timing: id 0 | task 22039 | n_gen = 300, tg = 49.56 t/s, tg_3s = 49.38 t/s 9.17.352.647 I slot print_timing: id 0 | task 22039 | n_gen = 446, tg = 49.26 t/s, tg_3s = 48.66 t/s 9.20.381.209 I slot print_timing: id 0 | task 22039 | n_gen = 593, tg = 49.08 t/s, tg_3s = 48.54 t/s 9.23.385.171 I slot print_timing: id 0 | task 22039 | n_gen = 739, tg = 48.98 t/s, tg_3s = 48.60 t/s 9.23.961.942 I slot print_timing: id 0 | task 22039 | prompt eval time = 425.46 ms / 182 tokens ( 2.34 ms per token, 427.77 tokens per second) 9.23.961.948 I slot print_timing: id 0 | task 22039 | eval time = 15642.96 ms / 767 tokens ( 20.42 ms per token, 48.97 tokens per second) 9.23.961.948 I slot print_timing: id 0 | task 22039 | total time = 16068.42 ms / 949 tokens 9.23.961.949 I slot print_timing: id 0 | task 22039 | graphs reused = 21721 9.23.961.950 I slot print_timing: id 0 | task 22039 | graph reallocs = 0 / 0 (same size) / (changed size) 9.23.961.969 I slot release: id 0 | task 22039 | stop processing: n_tokens = 948, truncated = 0 9.23.966.253 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.035 9.23.966.355 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 118.146 MiB) 9.23.977.496 I slot launch_slot_: id 0 | task 22809 | processing task, is_child = 0 9.25.451.936 I slot print_timing: id 0 | task 22809 | prompt eval time = 425.92 ms / 181 tokens ( 2.35 ms per token, 424.96 tokens per second) 9.25.451.942 I slot print_timing: id 0 | task 22809 | eval time = 1048.51 ms / 53 tokens ( 20.16 ms per token, 49.59 tokens per second) 9.25.451.943 I slot print_timing: id 0 | task 22809 | total time = 1474.43 ms / 234 tokens 9.25.451.944 I slot print_timing: id 0 | task 22809 | graphs reused = 21772 9.25.451.944 I slot print_timing: id 0 | task 22809 | graph reallocs = 0 / 0 (same size) / (changed size) 9.25.451.962 I slot release: id 0 | task 22809 | stop processing: n_tokens = 233, truncated = 0 9.25.456.074 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.133 (> 0.100 thold), f_keep = 0.129 9.25.456.113 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 122.118 MiB) 9.25.460.471 I slot launch_slot_: id 0 | task 22865 | processing task, is_child = 0 9.28.742.013 I slot print_timing: id 0 | task 22865 | prompt eval time = 481.53 ms / 226 tokens ( 2.13 ms per token, 469.34 tokens per second) 9.28.742.019 I slot print_timing: id 0 | task 22865 | eval time = 2800.00 ms / 140 tokens ( 20.14 ms per token, 49.64 tokens per second) 9.28.742.020 I slot print_timing: id 0 | task 22865 | total time = 3281.54 ms / 366 tokens 9.28.742.021 I slot print_timing: id 0 | task 22865 | graphs reused = 21909 9.28.742.022 I slot print_timing: id 0 | task 22865 | graph reallocs = 0 / 0 (same size) / (changed size) 9.28.742.041 I slot release: id 0 | task 22865 | stop processing: n_tokens = 365, truncated = 0 9.28.746.014 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.189 (> 0.100 thold), f_keep = 0.082 9.28.746.066 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 116.528 MiB) 9.28.751.236 I slot launch_slot_: id 0 | task 23008 | processing task, is_child = 0 9.29.706.810 I slot print_timing: id 0 | task 23008 | prompt eval time = 368.76 ms / 159 tokens ( 2.32 ms per token, 431.17 tokens per second) 9.29.706.813 I slot print_timing: id 0 | task 23008 | eval time = 586.80 ms / 30 tokens ( 20.23 ms per token, 49.42 tokens per second) 9.29.706.815 I slot print_timing: id 0 | task 23008 | total time = 955.57 ms / 189 tokens 9.29.706.816 I slot print_timing: id 0 | task 23008 | graphs reused = 21937 9.29.706.817 I slot print_timing: id 0 | task 23008 | graph reallocs = 0 / 0 (same size) / (changed size) 9.29.706.835 I slot release: id 0 | task 23008 | stop processing: n_tokens = 188, truncated = 0 9.29.750.501 I srv operator(): operator(): cleaning up before exit...