$ /Users/minipro/quantdiff/llama.cpp/llama-b11770/llama-server -m /Users/minipro/quantdiff/models/campaign/8d1b680a697c/Spark-X2.6-4B-Q3_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 0.00.044.410 I srv llama_server: initializing ... 0.00.044.416 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.044.515 I srv init_listene: The UI is disabled 0.00.044.518 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.044.551 W srv llama_server: security: no API key is set and CORS allows all origins (see https://github.com/ggml-org/llama.cpp/pull/25655) 0.00.046.222 I srv load_model: loading model '/Users/minipro/quantdiff/models/campaign/8d1b680a697c/Spark-X2.6-4B-Q3_K_M.gguf' 0.00.406.251 I cmn init: llama threadpool init, n_threads = 8 0.00.495.027 I srv load_model: initializing, n_slots = 1, n_ctx_slot = 4096, kv_unified = 'false' 0.00.502.645 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.00.502.655 I srv llama_server: model loaded 0.00.502.657 I srv llama_server: listening on http://127.0.0.1:8089 0.02.015.871 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.02.016.092 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.04.553.413 I slot print_timing: id 0 | task 0 | prompt eval time = 450.94 ms / 172 tokens ( 2.62 ms per token, 381.42 tokens per second) 0.04.553.420 I slot print_timing: id 0 | task 0 | eval time = 2086.36 ms / 92 tokens ( 22.93 ms per token, 43.62 tokens per second) 0.04.553.421 I slot print_timing: id 0 | task 0 | total time = 2537.30 ms / 264 tokens 0.04.553.421 I slot print_timing: id 0 | task 0 | graphs reused = 90 0.04.553.423 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.04.553.455 I slot release: id 0 | task 0 | stop processing: n_tokens = 263, truncated = 0 0.04.557.569 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.236 (> 0.100 thold), f_keep = 0.114 0.04.563.854 I slot launch_slot_: id 0 | task 95 | processing task, is_child = 0 0.07.961.579 I slot print_timing: id 0 | task 95 | n_gen = 133, tg = 43.67 t/s, tg_3s = 44.00 t/s 0.09.109.610 I slot print_timing: id 0 | task 95 | prompt eval time = 375.14 ms / 127 tokens ( 2.95 ms per token, 338.54 tokens per second) 0.09.109.614 I slot print_timing: id 0 | task 95 | eval time = 4170.61 ms / 183 tokens ( 22.92 ms per token, 43.64 tokens per second) 0.09.109.615 I slot print_timing: id 0 | task 95 | total time = 4545.75 ms / 310 tokens 0.09.109.616 I slot print_timing: id 0 | task 95 | graphs reused = 270 0.09.109.616 I slot print_timing: id 0 | task 95 | graph reallocs = 0 / 0 (same size) / (changed size) 0.09.109.633 I slot release: id 0 | task 95 | stop processing: n_tokens = 309, truncated = 0 0.09.113.754 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.097 0.09.120.169 I slot launch_slot_: id 0 | task 281 | processing task, is_child = 0 0.09.999.556 I slot print_timing: id 0 | task 281 | prompt eval time = 418.68 ms / 171 tokens ( 2.45 ms per token, 408.43 tokens per second) 0.09.999.561 I slot print_timing: id 0 | task 281 | eval time = 460.70 ms / 21 tokens ( 23.04 ms per token, 43.41 tokens per second) 0.09.999.561 I slot print_timing: id 0 | task 281 | total time = 879.38 ms / 192 tokens 0.09.999.562 I slot print_timing: id 0 | task 281 | graphs reused = 289 0.09.999.563 I slot print_timing: id 0 | task 281 | graph reallocs = 0 / 0 (same size) / (changed size) 0.09.999.588 I slot release: id 0 | task 281 | stop processing: n_tokens = 191, truncated = 0 0.10.003.880 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 0.10.009.549 I slot launch_slot_: id 0 | task 305 | processing task, is_child = 0 0.11.000.332 I slot print_timing: id 0 | task 305 | prompt eval time = 483.37 ms / 204 tokens ( 2.37 ms per token, 422.04 tokens per second) 0.11.000.338 I slot print_timing: id 0 | task 305 | eval time = 507.40 ms / 23 tokens ( 23.06 ms per token, 43.36 tokens per second) 0.11.000.340 I slot print_timing: id 0 | task 305 | total time = 990.77 ms / 227 tokens 0.11.000.340 I slot print_timing: id 0 | task 305 | graphs reused = 310 0.11.000.341 I slot print_timing: id 0 | task 305 | graph reallocs = 0 / 0 (same size) / (changed size) 0.11.000.360 I slot release: id 0 | task 305 | stop processing: n_tokens = 226, truncated = 0 0.11.004.462 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 0.11.010.791 I slot launch_slot_: id 0 | task 331 | processing task, is_child = 0 0.14.484.849 I slot print_timing: id 0 | task 331 | n_gen = 132, tg = 43.58 t/s, tg_3s = 43.91 t/s 0.15.614.656 I slot print_timing: id 0 | task 331 | prompt eval time = 467.86 ms / 187 tokens ( 2.50 ms per token, 399.69 tokens per second) 0.15.614.660 I slot print_timing: id 0 | task 331 | eval time = 4136.00 ms / 181 tokens ( 22.98 ms per token, 43.52 tokens per second) 0.15.614.661 I slot print_timing: id 0 | task 331 | total time = 4603.86 ms / 368 tokens 0.15.614.661 I slot print_timing: id 0 | task 331 | graphs reused = 488 0.15.614.662 I slot print_timing: id 0 | task 331 | graph reallocs = 0 / 0 (same size) / (changed size) 0.15.614.681 I slot release: id 0 | task 331 | stop processing: n_tokens = 367, truncated = 0 0.15.618.883 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.082 0.15.625.899 I slot launch_slot_: id 0 | task 515 | processing task, is_child = 0 0.16.724.100 I slot print_timing: id 0 | task 515 | prompt eval time = 407.59 ms / 171 tokens ( 2.38 ms per token, 419.54 tokens per second) 0.16.724.103 I slot print_timing: id 0 | task 515 | eval time = 690.60 ms / 31 tokens ( 23.02 ms per token, 43.44 tokens per second) 0.16.724.104 I slot print_timing: id 0 | task 515 | total time = 1098.19 ms / 202 tokens 0.16.724.105 I slot print_timing: id 0 | task 515 | graphs reused = 517 0.16.724.106 I slot print_timing: id 0 | task 515 | graph reallocs = 0 / 0 (same size) / (changed size) 0.16.724.131 I slot release: id 0 | task 515 | stop processing: n_tokens = 201, truncated = 0 0.16.728.472 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 0.16.734.517 I slot launch_slot_: id 0 | task 549 | processing task, is_child = 0 0.17.881.306 I slot print_timing: id 0 | task 549 | prompt eval time = 547.24 ms / 221 tokens ( 2.48 ms per token, 403.85 tokens per second) 0.17.881.314 I slot print_timing: id 0 | task 549 | eval time = 599.54 ms / 27 tokens ( 23.06 ms per token, 43.37 tokens per second) 0.17.881.320 I slot print_timing: id 0 | task 549 | total time = 1146.78 ms / 248 tokens 0.17.881.320 I slot print_timing: id 0 | task 549 | graphs reused = 542 0.17.881.321 I slot print_timing: id 0 | task 549 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.881.344 I slot release: id 0 | task 549 | stop processing: n_tokens = 247, truncated = 0 0.17.885.837 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.111 (> 0.100 thold), f_keep = 0.121 0.17.893.020 I slot launch_slot_: id 0 | task 579 | processing task, is_child = 0 0.19.450.233 I slot print_timing: id 0 | task 579 | prompt eval time = 636.00 ms / 270 tokens ( 2.36 ms per token, 424.52 tokens per second) 0.19.450.236 I slot print_timing: id 0 | task 579 | eval time = 921.19 ms / 41 tokens ( 23.03 ms per token, 43.42 tokens per second) 0.19.450.237 I slot print_timing: id 0 | task 579 | total time = 1557.20 ms / 311 tokens 0.19.450.238 I slot print_timing: id 0 | task 579 | graphs reused = 581 0.19.450.238 I slot print_timing: id 0 | task 579 | graph reallocs = 0 / 0 (same size) / (changed size) 0.19.450.260 I slot release: id 0 | task 579 | stop processing: n_tokens = 310, truncated = 0 0.19.454.192 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.097 0.19.462.659 I slot launch_slot_: id 0 | task 623 | processing task, is_child = 0 0.20.464.499 I slot print_timing: id 0 | task 623 | prompt eval time = 379.81 ms / 150 tokens ( 2.53 ms per token, 394.94 tokens per second) 0.20.464.502 I slot print_timing: id 0 | task 623 | eval time = 622.02 ms / 28 tokens ( 23.04 ms per token, 43.41 tokens per second) 0.20.464.503 I slot print_timing: id 0 | task 623 | total time = 1001.83 ms / 178 tokens 0.20.464.503 I slot print_timing: id 0 | task 623 | graphs reused = 607 0.20.464.504 I slot print_timing: id 0 | task 623 | graph reallocs = 0 / 0 (same size) / (changed size) 0.20.464.525 I slot release: id 0 | task 623 | stop processing: n_tokens = 177, truncated = 0 0.20.469.040 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 0.20.470.604 I slot launch_slot_: id 0 | task 654 | processing task, is_child = 0 0.21.325.371 I slot print_timing: id 0 | task 654 | prompt eval time = 417.03 ms / 167 tokens ( 2.50 ms per token, 400.45 tokens per second) 0.21.325.377 I slot print_timing: id 0 | task 654 | eval time = 437.73 ms / 20 tokens ( 23.04 ms per token, 43.41 tokens per second) 0.21.325.379 I slot print_timing: id 0 | task 654 | total time = 854.75 ms / 187 tokens 0.21.325.379 I slot print_timing: id 0 | task 654 | graphs reused = 625 0.21.325.380 I slot print_timing: id 0 | task 654 | graph reallocs = 0 / 0 (same size) / (changed size) 0.21.325.402 I slot release: id 0 | task 654 | stop processing: n_tokens = 186, truncated = 0 0.21.329.805 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 0.21.334.117 I slot launch_slot_: id 0 | task 677 | processing task, is_child = 0 0.22.534.205 I slot print_timing: id 0 | task 677 | prompt eval time = 395.58 ms / 171 tokens ( 2.31 ms per token, 432.28 tokens per second) 0.22.534.209 I slot print_timing: id 0 | task 677 | eval time = 804.50 ms / 36 tokens ( 22.99 ms per token, 43.51 tokens per second) 0.22.534.214 I slot print_timing: id 0 | task 677 | total time = 1200.08 ms / 207 tokens 0.22.534.215 I slot print_timing: id 0 | task 677 | graphs reused = 659 0.22.534.215 I slot print_timing: id 0 | task 677 | graph reallocs = 0 / 0 (same size) / (changed size) 0.22.534.241 I slot release: id 0 | task 677 | stop processing: n_tokens = 206, truncated = 0 0.22.538.414 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.140 (> 0.100 thold), f_keep = 0.146 0.22.544.208 I slot launch_slot_: id 0 | task 716 | processing task, is_child = 0 0.23.639.569 I slot print_timing: id 0 | task 716 | prompt eval time = 484.20 ms / 214 tokens ( 2.26 ms per token, 441.96 tokens per second) 0.23.639.575 I slot print_timing: id 0 | task 716 | eval time = 611.15 ms / 27 tokens ( 23.51 ms per token, 42.54 tokens per second) 0.23.639.576 I slot print_timing: id 0 | task 716 | total time = 1095.35 ms / 241 tokens 0.23.639.577 I slot print_timing: id 0 | task 716 | graphs reused = 684 0.23.639.579 I slot print_timing: id 0 | task 716 | graph reallocs = 0 / 0 (same size) / (changed size) 0.23.639.601 I slot release: id 0 | task 716 | stop processing: n_tokens = 240, truncated = 0 0.23.643.590 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.164 (> 0.100 thold), f_keep = 0.125 0.23.650.171 I slot launch_slot_: id 0 | task 746 | processing task, is_child = 0 0.24.966.678 I slot print_timing: id 0 | task 746 | prompt eval time = 466.37 ms / 183 tokens ( 2.55 ms per token, 392.39 tokens per second) 0.24.966.685 I slot print_timing: id 0 | task 746 | eval time = 850.13 ms / 38 tokens ( 22.98 ms per token, 43.52 tokens per second) 0.24.966.686 I slot print_timing: id 0 | task 746 | total time = 1316.49 ms / 221 tokens 0.24.966.687 I slot print_timing: id 0 | task 746 | graphs reused = 720 0.24.966.688 I slot print_timing: id 0 | task 746 | graph reallocs = 0 / 0 (same size) / (changed size) 0.24.966.707 I slot release: id 0 | task 746 | stop processing: n_tokens = 220, truncated = 0 0.24.970.744 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 0.24.974.600 I slot launch_slot_: id 0 | task 787 | processing task, is_child = 0 0.26.054.744 I slot print_timing: id 0 | task 787 | prompt eval time = 481.56 ms / 183 tokens ( 2.63 ms per token, 380.01 tokens per second) 0.26.054.750 I slot print_timing: id 0 | task 787 | eval time = 598.57 ms / 27 tokens ( 23.02 ms per token, 43.44 tokens per second) 0.26.054.750 I slot print_timing: id 0 | task 787 | total time = 1080.13 ms / 210 tokens 0.26.054.751 I slot print_timing: id 0 | task 787 | graphs reused = 745 0.26.054.752 I slot print_timing: id 0 | task 787 | graph reallocs = 0 / 0 (same size) / (changed size) 0.26.054.777 I slot release: id 0 | task 787 | stop processing: n_tokens = 209, truncated = 0 0.26.058.811 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 0.26.064.572 I slot launch_slot_: id 0 | task 817 | processing task, is_child = 0 0.27.264.494 I slot print_timing: id 0 | task 817 | prompt eval time = 419.31 ms / 170 tokens ( 2.47 ms per token, 405.43 tokens per second) 0.27.264.498 I slot print_timing: id 0 | task 817 | eval time = 780.61 ms / 35 tokens ( 22.96 ms per token, 43.56 tokens per second) 0.27.264.499 I slot print_timing: id 0 | task 817 | total time = 1199.91 ms / 205 tokens 0.27.264.500 I slot print_timing: id 0 | task 817 | graphs reused = 778 0.27.264.500 I slot print_timing: id 0 | task 817 | graph reallocs = 0 / 0 (same size) / (changed size) 0.27.264.519 I slot release: id 0 | task 817 | stop processing: n_tokens = 204, truncated = 0 0.27.268.360 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 0.27.274.367 I slot launch_slot_: id 0 | task 855 | processing task, is_child = 0 0.28.000.805 I slot print_timing: id 0 | task 855 | prompt eval time = 380.11 ms / 150 tokens ( 2.53 ms per token, 394.62 tokens per second) 0.28.000.818 I slot print_timing: id 0 | task 855 | eval time = 346.32 ms / 16 tokens ( 23.09 ms per token, 43.31 tokens per second) 0.28.000.819 I slot print_timing: id 0 | task 855 | total time = 726.43 ms / 166 tokens 0.28.000.819 I slot print_timing: id 0 | task 855 | graphs reused = 792 0.28.000.820 I slot print_timing: id 0 | task 855 | graph reallocs = 0 / 0 (same size) / (changed size) 0.28.000.858 I slot release: id 0 | task 855 | stop processing: n_tokens = 165, truncated = 0 0.28.005.242 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.172 (> 0.100 thold), f_keep = 0.182 0.28.009.491 I slot launch_slot_: id 0 | task 874 | processing task, is_child = 0 0.28.925.166 I slot print_timing: id 0 | task 874 | prompt eval time = 431.22 ms / 174 tokens ( 2.48 ms per token, 403.51 tokens per second) 0.28.925.170 I slot print_timing: id 0 | task 874 | eval time = 484.45 ms / 22 tokens ( 23.07 ms per token, 43.35 tokens per second) 0.28.925.171 I slot print_timing: id 0 | task 874 | total time = 915.67 ms / 196 tokens 0.28.925.171 I slot print_timing: id 0 | task 874 | graphs reused = 812 0.28.925.172 I slot print_timing: id 0 | task 874 | graph reallocs = 0 / 0 (same size) / (changed size) 0.28.925.190 I slot release: id 0 | task 874 | stop processing: n_tokens = 195, truncated = 0 0.28.929.112 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.192 (> 0.100 thold), f_keep = 0.154 0.28.934.641 I slot launch_slot_: id 0 | task 899 | processing task, is_child = 0 0.31.686.290 I slot print_timing: id 0 | task 899 | prompt eval time = 433.79 ms / 156 tokens ( 2.78 ms per token, 359.62 tokens per second) 0.31.686.294 I slot print_timing: id 0 | task 899 | eval time = 2317.84 ms / 102 tokens ( 22.95 ms per token, 43.57 tokens per second) 0.31.686.295 I slot print_timing: id 0 | task 899 | total time = 2751.64 ms / 258 tokens 0.31.686.296 I slot print_timing: id 0 | task 899 | graphs reused = 911 0.31.686.296 I slot print_timing: id 0 | task 899 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.686.314 I slot release: id 0 | task 899 | stop processing: n_tokens = 257, truncated = 0 0.31.690.312 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.197 (> 0.100 thold), f_keep = 0.117 0.31.696.525 I slot launch_slot_: id 0 | task 1004 | processing task, is_child = 0 0.33.316.253 I slot print_timing: id 0 | task 1004 | prompt eval time = 403.83 ms / 152 tokens ( 2.66 ms per token, 376.39 tokens per second) 0.33.316.260 I slot print_timing: id 0 | task 1004 | eval time = 1215.88 ms / 54 tokens ( 22.94 ms per token, 43.59 tokens per second) 0.33.316.260 I slot print_timing: id 0 | task 1004 | total time = 1619.71 ms / 206 tokens 0.33.316.261 I slot print_timing: id 0 | task 1004 | graphs reused = 963 0.33.316.262 I slot print_timing: id 0 | task 1004 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.316.280 I slot release: id 0 | task 1004 | stop processing: n_tokens = 205, truncated = 0 0.33.320.562 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.160 (> 0.100 thold), f_keep = 0.146 0.33.325.946 I slot launch_slot_: id 0 | task 1061 | processing task, is_child = 0 0.34.682.484 I slot print_timing: id 0 | task 1061 | prompt eval time = 482.26 ms / 187 tokens ( 2.58 ms per token, 387.75 tokens per second) 0.34.682.491 I slot print_timing: id 0 | task 1061 | eval time = 874.26 ms / 39 tokens ( 23.01 ms per token, 43.47 tokens per second) 0.34.682.492 I slot print_timing: id 0 | task 1061 | total time = 1356.53 ms / 226 tokens 0.34.682.492 I slot print_timing: id 0 | task 1061 | graphs reused = 1000 0.34.682.493 I slot print_timing: id 0 | task 1061 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.682.517 I slot release: id 0 | task 1061 | stop processing: n_tokens = 225, truncated = 0 0.34.686.714 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 0.34.691.880 I slot launch_slot_: id 0 | task 1103 | processing task, is_child = 0 0.35.881.193 I slot print_timing: id 0 | task 1103 | prompt eval time = 416.62 ms / 160 tokens ( 2.60 ms per token, 384.04 tokens per second) 0.35.881.197 I slot print_timing: id 0 | task 1103 | eval time = 772.68 ms / 34 tokens ( 23.41 ms per token, 42.71 tokens per second) 0.35.881.197 I slot print_timing: id 0 | task 1103 | total time = 1189.30 ms / 194 tokens 0.35.881.198 I slot print_timing: id 0 | task 1103 | graphs reused = 1032 0.35.881.199 I slot print_timing: id 0 | task 1103 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.881.216 I slot release: id 0 | task 1103 | stop processing: n_tokens = 193, truncated = 0 0.35.885.494 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 0.35.890.750 I slot launch_slot_: id 0 | task 1140 | processing task, is_child = 0 0.37.237.743 I slot print_timing: id 0 | task 1140 | prompt eval time = 495.53 ms / 208 tokens ( 2.38 ms per token, 419.75 tokens per second) 0.37.237.747 I slot print_timing: id 0 | task 1140 | eval time = 851.45 ms / 38 tokens ( 23.01 ms per token, 43.46 tokens per second) 0.37.237.748 I slot print_timing: id 0 | task 1140 | total time = 1346.98 ms / 246 tokens 0.37.237.753 I slot print_timing: id 0 | task 1140 | graphs reused = 1068 0.37.237.753 I slot print_timing: id 0 | task 1140 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.237.773 I slot release: id 0 | task 1140 | stop processing: n_tokens = 245, truncated = 0 0.37.241.734 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 0.37.248.600 I slot launch_slot_: id 0 | task 1181 | processing task, is_child = 0 0.40.751.441 I slot print_timing: id 0 | task 1181 | n_gen = 132, tg = 43.55 t/s, tg_3s = 43.88 t/s 0.42.859.369 I slot print_timing: id 0 | task 1181 | prompt eval time = 494.62 ms / 192 tokens ( 2.58 ms per token, 388.18 tokens per second) 0.42.859.373 I slot print_timing: id 0 | task 1181 | eval time = 5116.14 ms / 223 tokens ( 23.05 ms per token, 43.39 tokens per second) 0.42.859.373 I slot print_timing: id 0 | task 1181 | total time = 5610.76 ms / 415 tokens 0.42.859.374 I slot print_timing: id 0 | task 1181 | graphs reused = 1288 0.42.859.375 I slot print_timing: id 0 | task 1181 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.859.405 I slot release: id 0 | task 1181 | stop processing: n_tokens = 414, truncated = 0 0.42.863.726 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.152 (> 0.100 thold), f_keep = 0.072 0.42.872.371 I slot launch_slot_: id 0 | task 1407 | processing task, is_child = 0 0.44.407.306 I slot print_timing: id 0 | task 1407 | prompt eval time = 469.05 ms / 198 tokens ( 2.37 ms per token, 422.13 tokens per second) 0.44.407.312 I slot print_timing: id 0 | task 1407 | eval time = 1065.87 ms / 47 tokens ( 23.17 ms per token, 43.16 tokens per second) 0.44.407.314 I slot print_timing: id 0 | task 1407 | total time = 1534.93 ms / 245 tokens 0.44.407.314 I slot print_timing: id 0 | task 1407 | graphs reused = 1333 0.44.407.315 I slot print_timing: id 0 | task 1407 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.407.336 I slot release: id 0 | task 1407 | stop processing: n_tokens = 244, truncated = 0 0.44.411.619 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.128 (> 0.100 thold), f_keep = 0.123 0.44.418.199 I slot launch_slot_: id 0 | task 1457 | processing task, is_child = 0 0.45.805.843 I slot print_timing: id 0 | task 1457 | prompt eval time = 535.56 ms / 235 tokens ( 2.28 ms per token, 438.79 tokens per second) 0.45.805.849 I slot print_timing: id 0 | task 1457 | eval time = 852.07 ms / 38 tokens ( 23.03 ms per token, 43.42 tokens per second) 0.45.805.849 I slot print_timing: id 0 | task 1457 | total time = 1387.63 ms / 273 tokens 0.45.805.850 I slot print_timing: id 0 | task 1457 | graphs reused = 1368 0.45.805.850 I slot print_timing: id 0 | task 1457 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.805.875 I slot release: id 0 | task 1457 | stop processing: n_tokens = 272, truncated = 0 0.45.809.909 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 0.45.817.411 I slot launch_slot_: id 0 | task 1498 | processing task, is_child = 0 0.47.068.683 I slot print_timing: id 0 | task 1498 | prompt eval time = 469.48 ms / 199 tokens ( 2.36 ms per token, 423.88 tokens per second) 0.47.068.689 I slot print_timing: id 0 | task 1498 | eval time = 781.78 ms / 35 tokens ( 22.99 ms per token, 43.49 tokens per second) 0.47.068.690 I slot print_timing: id 0 | task 1498 | total time = 1251.26 ms / 234 tokens 0.47.068.691 I slot print_timing: id 0 | task 1498 | graphs reused = 1401 0.47.068.691 I slot print_timing: id 0 | task 1498 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.068.714 I slot release: id 0 | task 1498 | stop processing: n_tokens = 233, truncated = 0 0.47.072.513 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 0.47.077.812 I slot launch_slot_: id 0 | task 1536 | processing task, is_child = 0 0.48.322.687 I slot print_timing: id 0 | task 1536 | prompt eval time = 418.40 ms / 157 tokens ( 2.66 ms per token, 375.24 tokens per second) 0.48.322.690 I slot print_timing: id 0 | task 1536 | eval time = 826.47 ms / 37 tokens ( 22.96 ms per token, 43.56 tokens per second) 0.48.322.691 I slot print_timing: id 0 | task 1536 | total time = 1244.86 ms / 194 tokens 0.48.322.692 I slot print_timing: id 0 | task 1536 | graphs reused = 1436 0.48.322.692 I slot print_timing: id 0 | task 1536 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.322.717 I slot release: id 0 | task 1536 | stop processing: n_tokens = 193, truncated = 0 0.48.326.725 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.168 (> 0.100 thold), f_keep = 0.161 0.48.331.139 I slot launch_slot_: id 0 | task 1576 | processing task, is_child = 0 0.49.578.646 I slot print_timing: id 0 | task 1576 | prompt eval time = 420.52 ms / 184 tokens ( 2.29 ms per token, 437.56 tokens per second) 0.49.578.650 I slot print_timing: id 0 | task 1576 | eval time = 826.98 ms / 37 tokens ( 22.97 ms per token, 43.53 tokens per second) 0.49.578.650 I slot print_timing: id 0 | task 1576 | total time = 1247.49 ms / 221 tokens 0.49.578.651 I slot print_timing: id 0 | task 1576 | graphs reused = 1471 0.49.578.652 I slot print_timing: id 0 | task 1576 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.578.672 I slot release: id 0 | task 1576 | stop processing: n_tokens = 220, truncated = 0 0.49.582.934 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 0.49.589.049 I slot launch_slot_: id 0 | task 1616 | processing task, is_child = 0 0.51.291.942 I slot print_timing: id 0 | task 1616 | prompt eval time = 531.07 ms / 214 tokens ( 2.48 ms per token, 402.96 tokens per second) 0.51.291.945 I slot print_timing: id 0 | task 1616 | eval time = 1171.82 ms / 52 tokens ( 22.98 ms per token, 43.52 tokens per second) 0.51.291.946 I slot print_timing: id 0 | task 1616 | total time = 1702.88 ms / 266 tokens 0.51.291.947 I slot print_timing: id 0 | task 1616 | graphs reused = 1520 0.51.291.947 I slot print_timing: id 0 | task 1616 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.291.968 I slot release: id 0 | task 1616 | stop processing: n_tokens = 265, truncated = 0 0.51.296.083 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.161 (> 0.100 thold), f_keep = 0.113 0.51.302.006 I slot launch_slot_: id 0 | task 1671 | processing task, is_child = 0 0.52.587.827 I slot print_timing: id 0 | task 1671 | prompt eval time = 480.94 ms / 186 tokens ( 2.59 ms per token, 386.75 tokens per second) 0.52.587.833 I slot print_timing: id 0 | task 1671 | eval time = 804.88 ms / 36 tokens ( 23.00 ms per token, 43.49 tokens per second) 0.52.587.834 I slot print_timing: id 0 | task 1671 | total time = 1285.81 ms / 222 tokens 0.52.587.834 I slot print_timing: id 0 | task 1671 | graphs reused = 1554 0.52.587.836 I slot print_timing: id 0 | task 1671 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.587.860 I slot release: id 0 | task 1671 | stop processing: n_tokens = 221, truncated = 0 0.52.592.065 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 0.52.598.245 I slot launch_slot_: id 0 | task 1710 | processing task, is_child = 0 0.53.839.549 I slot print_timing: id 0 | task 1710 | prompt eval time = 427.24 ms / 163 tokens ( 2.62 ms per token, 381.52 tokens per second) 0.53.839.556 I slot print_timing: id 0 | task 1710 | eval time = 814.06 ms / 36 tokens ( 23.26 ms per token, 42.99 tokens per second) 0.53.839.557 I slot print_timing: id 0 | task 1710 | total time = 1241.30 ms / 199 tokens 0.53.839.557 I slot print_timing: id 0 | task 1710 | graphs reused = 1588 0.53.839.558 I slot print_timing: id 0 | task 1710 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.839.577 I slot release: id 0 | task 1710 | stop processing: n_tokens = 198, truncated = 0 0.53.843.551 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 0.53.848.076 I slot launch_slot_: id 0 | task 1749 | processing task, is_child = 0 0.54.590.969 I slot print_timing: id 0 | task 1749 | prompt eval time = 395.49 ms / 163 tokens ( 2.43 ms per token, 412.15 tokens per second) 0.54.590.976 I slot print_timing: id 0 | task 1749 | eval time = 347.39 ms / 16 tokens ( 23.16 ms per token, 43.18 tokens per second) 0.54.590.977 I slot print_timing: id 0 | task 1749 | total time = 742.88 ms / 179 tokens 0.54.590.978 I slot print_timing: id 0 | task 1749 | graphs reused = 1602 0.54.590.978 I slot print_timing: id 0 | task 1749 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.590.995 I slot release: id 0 | task 1749 | stop processing: n_tokens = 178, truncated = 0 0.54.595.041 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.160 (> 0.100 thold), f_keep = 0.169 0.54.600.524 I slot launch_slot_: id 0 | task 1768 | processing task, is_child = 0 0.55.888.821 I slot print_timing: id 0 | task 1768 | prompt eval time = 482.97 ms / 187 tokens ( 2.58 ms per token, 387.19 tokens per second) 0.55.888.825 I slot print_timing: id 0 | task 1768 | eval time = 805.32 ms / 36 tokens ( 23.01 ms per token, 43.46 tokens per second) 0.55.888.827 I slot print_timing: id 0 | task 1768 | total time = 1288.28 ms / 223 tokens 0.55.888.827 I slot print_timing: id 0 | task 1768 | graphs reused = 1636 0.55.888.828 I slot print_timing: id 0 | task 1768 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.888.855 I slot release: id 0 | task 1768 | stop processing: n_tokens = 222, truncated = 0 0.55.893.124 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 0.55.899.556 I slot launch_slot_: id 0 | task 1807 | processing task, is_child = 0 0.57.165.728 I slot print_timing: id 0 | task 1807 | prompt eval time = 483.20 ms / 205 tokens ( 2.36 ms per token, 424.26 tokens per second) 0.57.165.735 I slot print_timing: id 0 | task 1807 | eval time = 782.97 ms / 35 tokens ( 23.03 ms per token, 43.42 tokens per second) 0.57.165.736 I slot print_timing: id 0 | task 1807 | total time = 1266.16 ms / 240 tokens 0.57.165.736 I slot print_timing: id 0 | task 1807 | graphs reused = 1669 0.57.165.737 I slot print_timing: id 0 | task 1807 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.165.756 I slot release: id 0 | task 1807 | stop processing: n_tokens = 239, truncated = 0 0.57.169.661 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 0.57.175.164 I slot launch_slot_: id 0 | task 1845 | processing task, is_child = 0 0.58.286.441 I slot print_timing: id 0 | task 1845 | prompt eval time = 397.78 ms / 158 tokens ( 2.52 ms per token, 397.21 tokens per second) 0.58.286.445 I slot print_timing: id 0 | task 1845 | eval time = 713.48 ms / 32 tokens ( 23.02 ms per token, 43.45 tokens per second) 0.58.286.446 I slot print_timing: id 0 | task 1845 | total time = 1111.26 ms / 190 tokens 0.58.286.446 I slot print_timing: id 0 | task 1845 | graphs reused = 1699 0.58.286.447 I slot print_timing: id 0 | task 1845 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.286.469 I slot release: id 0 | task 1845 | stop processing: n_tokens = 189, truncated = 0 0.58.290.842 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 0.58.295.315 I slot launch_slot_: id 0 | task 1880 | processing task, is_child = 0 0.59.426.478 I slot print_timing: id 0 | task 1880 | prompt eval time = 463.01 ms / 196 tokens ( 2.36 ms per token, 423.32 tokens per second) 0.59.426.481 I slot print_timing: id 0 | task 1880 | eval time = 668.14 ms / 30 tokens ( 23.04 ms per token, 43.40 tokens per second) 0.59.426.482 I slot print_timing: id 0 | task 1880 | total time = 1131.15 ms / 226 tokens 0.59.426.483 I slot print_timing: id 0 | task 1880 | graphs reused = 1727 0.59.426.483 I slot print_timing: id 0 | task 1880 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.426.502 I slot release: id 0 | task 1880 | stop processing: n_tokens = 225, truncated = 0 0.59.430.367 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 0.59.436.694 I slot launch_slot_: id 0 | task 1913 | processing task, is_child = 0 1.00.193.759 I slot print_timing: id 0 | task 1913 | prompt eval time = 341.01 ms / 127 tokens ( 2.69 ms per token, 372.43 tokens per second) 1.00.193.766 I slot print_timing: id 0 | task 1913 | eval time = 416.05 ms / 19 tokens ( 23.11 ms per token, 43.26 tokens per second) 1.00.193.767 I slot print_timing: id 0 | task 1913 | total time = 757.06 ms / 146 tokens 1.00.193.768 I slot print_timing: id 0 | task 1913 | graphs reused = 1744 1.00.193.768 I slot print_timing: id 0 | task 1913 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.193.787 I slot release: id 0 | task 1913 | stop processing: n_tokens = 145, truncated = 0 1.00.197.651 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.224 (> 0.100 thold), f_keep = 0.207 1.00.201.258 I slot launch_slot_: id 0 | task 1935 | processing task, is_child = 0 1.01.838.097 I slot print_timing: id 0 | task 1935 | prompt eval time = 353.36 ms / 134 tokens ( 2.64 ms per token, 379.21 tokens per second) 1.01.838.101 I slot print_timing: id 0 | task 1935 | eval time = 1283.47 ms / 57 tokens ( 22.92 ms per token, 43.63 tokens per second) 1.01.838.101 I slot print_timing: id 0 | task 1935 | total time = 1636.83 ms / 191 tokens 1.01.838.102 I slot print_timing: id 0 | task 1935 | graphs reused = 1799 1.01.838.103 I slot print_timing: id 0 | task 1935 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.838.127 I slot release: id 0 | task 1935 | stop processing: n_tokens = 190, truncated = 0 1.01.842.023 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.158 1.01.846.746 I slot launch_slot_: id 0 | task 1995 | processing task, is_child = 0 1.02.608.131 I slot print_timing: id 0 | task 1995 | prompt eval time = 392.02 ms / 148 tokens ( 2.65 ms per token, 377.53 tokens per second) 1.02.608.133 I slot print_timing: id 0 | task 1995 | eval time = 369.36 ms / 17 tokens ( 23.08 ms per token, 43.32 tokens per second) 1.02.608.134 I slot print_timing: id 0 | task 1995 | total time = 761.38 ms / 165 tokens 1.02.608.135 I slot print_timing: id 0 | task 1995 | graphs reused = 1814 1.02.608.135 I slot print_timing: id 0 | task 1995 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.608.154 I slot release: id 0 | task 1995 | stop processing: n_tokens = 164, truncated = 0 1.02.611.911 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 1.02.616.669 I slot launch_slot_: id 0 | task 2015 | processing task, is_child = 0 1.03.705.019 I slot print_timing: id 0 | task 2015 | prompt eval time = 389.81 ms / 145 tokens ( 2.69 ms per token, 371.98 tokens per second) 1.03.705.025 I slot print_timing: id 0 | task 2015 | eval time = 698.53 ms / 31 tokens ( 23.28 ms per token, 42.95 tokens per second) 1.03.705.026 I slot print_timing: id 0 | task 2015 | total time = 1088.34 ms / 176 tokens 1.03.705.027 I slot print_timing: id 0 | task 2015 | graphs reused = 1843 1.03.705.027 I slot print_timing: id 0 | task 2015 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.705.045 I slot release: id 0 | task 2015 | stop processing: n_tokens = 175, truncated = 0 1.03.705.066 W common_chat_peg_parse: unparsed peg-native output: {"religion_name": "Buddhism", "detail_level": "full"} 1.03.706.098 W srv stop: cancel task, id_task = 2015 1.03.706.300 W srv operator(): got exception: {"error":{"code":500,"message":"The model produced output that does not match the expected peg-native format","type":"server_error"}} 1.03.710.007 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.150 (> 0.100 thold), f_keep = 0.171 1.03.714.929 I slot launch_slot_: id 0 | task 2050 | processing task, is_child = 0 1.04.922.348 I slot print_timing: id 0 | task 2050 | prompt eval time = 483.68 ms / 200 tokens ( 2.42 ms per token, 413.49 tokens per second) 1.04.922.355 I slot print_timing: id 0 | task 2050 | eval time = 723.73 ms / 32 tokens ( 23.35 ms per token, 42.83 tokens per second) 1.04.922.355 I slot print_timing: id 0 | task 2050 | total time = 1207.41 ms / 232 tokens 1.04.922.356 I slot print_timing: id 0 | task 2050 | graphs reused = 1873 1.04.922.357 I slot print_timing: id 0 | task 2050 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.922.375 I slot release: id 0 | task 2050 | stop processing: n_tokens = 231, truncated = 0 1.04.927.037 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 231, t_last = 326051194710 1.04.933.896 I slot launch_slot_: id 0 | task 2085 | processing task, is_child = 0 1.07.199.109 I slot print_timing: id 0 | task 2085 | prompt eval time = 703.21 ms / 326 tokens ( 2.16 ms per token, 463.59 tokens per second) 1.07.199.115 I slot print_timing: id 0 | task 2085 | eval time = 1561.99 ms / 64 tokens ( 24.79 ms per token, 40.33 tokens per second) 1.07.199.116 I slot print_timing: id 0 | task 2085 | total time = 2265.20 ms / 390 tokens 1.07.199.117 I slot print_timing: id 0 | task 2085 | graphs reused = 1935 1.07.199.117 I slot print_timing: id 0 | task 2085 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.199.152 I slot release: id 0 | task 2085 | stop processing: n_tokens = 389, truncated = 0 1.07.203.016 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.077 1.07.213.981 I slot launch_slot_: id 0 | task 2152 | processing task, is_child = 0 1.08.114.829 I slot print_timing: id 0 | task 2152 | prompt eval time = 372.29 ms / 148 tokens ( 2.52 ms per token, 397.54 tokens per second) 1.08.114.833 I slot print_timing: id 0 | task 2152 | eval time = 528.55 ms / 24 tokens ( 22.98 ms per token, 43.52 tokens per second) 1.08.114.834 I slot print_timing: id 0 | task 2152 | total time = 900.84 ms / 172 tokens 1.08.114.834 I slot print_timing: id 0 | task 2152 | graphs reused = 1957 1.08.114.835 I slot print_timing: id 0 | task 2152 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.114.857 I slot release: id 0 | task 2152 | stop processing: n_tokens = 171, truncated = 0 1.08.118.923 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 1.08.121.531 I slot launch_slot_: id 0 | task 2179 | processing task, is_child = 0 1.09.151.690 I slot print_timing: id 0 | task 2179 | prompt eval time = 398.52 ms / 175 tokens ( 2.28 ms per token, 439.13 tokens per second) 1.09.151.696 I slot print_timing: id 0 | task 2179 | eval time = 631.63 ms / 28 tokens ( 23.39 ms per token, 42.75 tokens per second) 1.09.151.697 I slot print_timing: id 0 | task 2179 | total time = 1030.15 ms / 203 tokens 1.09.151.698 I slot print_timing: id 0 | task 2179 | graphs reused = 1983 1.09.151.698 I slot print_timing: id 0 | task 2179 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.151.717 I slot release: id 0 | task 2179 | stop processing: n_tokens = 202, truncated = 0 1.09.156.008 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 1.09.161.839 I slot launch_slot_: id 0 | task 2210 | processing task, is_child = 0 1.10.594.905 I slot print_timing: id 0 | task 2210 | prompt eval time = 534.84 ms / 229 tokens ( 2.34 ms per token, 428.17 tokens per second) 1.10.594.909 I slot print_timing: id 0 | task 2210 | eval time = 898.22 ms / 40 tokens ( 23.03 ms per token, 43.42 tokens per second) 1.10.594.910 I slot print_timing: id 0 | task 2210 | total time = 1433.05 ms / 269 tokens 1.10.594.911 I slot print_timing: id 0 | task 2210 | graphs reused = 2020 1.10.594.911 I slot print_timing: id 0 | task 2210 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.594.931 I slot release: id 0 | task 2210 | stop processing: n_tokens = 268, truncated = 0 1.10.599.135 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 1.10.606.501 I slot launch_slot_: id 0 | task 2253 | processing task, is_child = 0 1.11.235.454 I slot print_timing: id 0 | task 2253 | prompt eval time = 535.70 ms / 238 tokens ( 2.25 ms per token, 444.28 tokens per second) 1.11.235.461 I slot print_timing: id 0 | task 2253 | eval time = 93.24 ms / 5 tokens ( 23.31 ms per token, 42.90 tokens per second) 1.11.235.462 I slot print_timing: id 0 | task 2253 | total time = 628.94 ms / 243 tokens 1.11.235.463 I slot print_timing: id 0 | task 2253 | graphs reused = 2023 1.11.235.463 I slot print_timing: id 0 | task 2253 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.235.489 I slot release: id 0 | task 2253 | stop processing: n_tokens = 242, truncated = 0 1.11.240.209 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.204 (> 0.100 thold), f_keep = 0.136 1.11.250.085 I slot launch_slot_: id 0 | task 2261 | processing task, is_child = 0 1.12.216.136 I slot print_timing: id 0 | task 2261 | prompt eval time = 393.23 ms / 162 tokens ( 2.43 ms per token, 411.98 tokens per second) 1.12.216.139 I slot print_timing: id 0 | task 2261 | eval time = 572.81 ms / 26 tokens ( 22.91 ms per token, 43.64 tokens per second) 1.12.216.140 I slot print_timing: id 0 | task 2261 | total time = 966.04 ms / 188 tokens 1.12.216.140 I slot print_timing: id 0 | task 2261 | graphs reused = 2047 1.12.216.141 I slot print_timing: id 0 | task 2261 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.216.165 I slot release: id 0 | task 2261 | stop processing: n_tokens = 187, truncated = 0 1.12.220.107 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.160 1.12.222.950 I slot launch_slot_: id 0 | task 2290 | processing task, is_child = 0 1.13.218.868 I slot print_timing: id 0 | task 2290 | prompt eval time = 419.93 ms / 169 tokens ( 2.48 ms per token, 402.45 tokens per second) 1.13.218.875 I slot print_timing: id 0 | task 2290 | eval time = 575.98 ms / 26 tokens ( 23.04 ms per token, 43.40 tokens per second) 1.13.218.875 I slot print_timing: id 0 | task 2290 | total time = 995.91 ms / 195 tokens 1.13.218.876 I slot print_timing: id 0 | task 2290 | graphs reused = 2071 1.13.218.877 I slot print_timing: id 0 | task 2290 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.218.896 I slot release: id 0 | task 2290 | stop processing: n_tokens = 194, truncated = 0 1.13.223.017 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 1.13.228.495 I slot launch_slot_: id 0 | task 2319 | processing task, is_child = 0 1.14.309.344 I slot print_timing: id 0 | task 2319 | prompt eval time = 460.26 ms / 180 tokens ( 2.56 ms per token, 391.08 tokens per second) 1.14.309.350 I slot print_timing: id 0 | task 2319 | eval time = 620.58 ms / 28 tokens ( 22.98 ms per token, 43.51 tokens per second) 1.14.309.351 I slot print_timing: id 0 | task 2319 | total time = 1080.84 ms / 208 tokens 1.14.309.352 I slot print_timing: id 0 | task 2319 | graphs reused = 2097 1.14.309.352 I slot print_timing: id 0 | task 2319 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.309.377 I slot release: id 0 | task 2319 | stop processing: n_tokens = 207, truncated = 0 1.14.313.299 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 1.14.319.146 I slot launch_slot_: id 0 | task 2350 | processing task, is_child = 0 1.15.813.007 I slot print_timing: id 0 | task 2350 | prompt eval time = 482.75 ms / 203 tokens ( 2.38 ms per token, 420.51 tokens per second) 1.15.813.014 I slot print_timing: id 0 | task 2350 | eval time = 1011.09 ms / 45 tokens ( 22.98 ms per token, 43.52 tokens per second) 1.15.813.015 I slot print_timing: id 0 | task 2350 | total time = 1493.84 ms / 248 tokens 1.15.813.015 I slot print_timing: id 0 | task 2350 | graphs reused = 2140 1.15.813.016 I slot print_timing: id 0 | task 2350 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.813.036 I slot release: id 0 | task 2350 | stop processing: n_tokens = 247, truncated = 0 1.15.816.997 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 1.15.822.773 I slot launch_slot_: id 0 | task 2398 | processing task, is_child = 0 1.17.428.346 I slot print_timing: id 0 | task 2398 | prompt eval time = 432.27 ms / 157 tokens ( 2.75 ms per token, 363.20 tokens per second) 1.17.428.350 I slot print_timing: id 0 | task 2398 | eval time = 1173.29 ms / 51 tokens ( 23.47 ms per token, 42.62 tokens per second) 1.17.428.350 I slot print_timing: id 0 | task 2398 | total time = 1605.56 ms / 208 tokens 1.17.428.351 I slot print_timing: id 0 | task 2398 | graphs reused = 2189 1.17.428.352 I slot print_timing: id 0 | task 2398 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.428.375 I slot release: id 0 | task 2398 | stop processing: n_tokens = 207, truncated = 0 1.17.432.585 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.140 (> 0.100 thold), f_keep = 0.145 1.17.437.248 I slot launch_slot_: id 0 | task 2452 | processing task, is_child = 0 1.18.749.763 I slot print_timing: id 0 | task 2452 | prompt eval time = 484.87 ms / 214 tokens ( 2.27 ms per token, 441.35 tokens per second) 1.18.749.769 I slot print_timing: id 0 | task 2452 | eval time = 827.63 ms / 37 tokens ( 22.99 ms per token, 43.50 tokens per second) 1.18.749.770 I slot print_timing: id 0 | task 2452 | total time = 1312.51 ms / 251 tokens 1.18.749.771 I slot print_timing: id 0 | task 2452 | graphs reused = 2224 1.18.749.771 I slot print_timing: id 0 | task 2452 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.749.795 I slot release: id 0 | task 2452 | stop processing: n_tokens = 250, truncated = 0 1.18.753.897 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.183 (> 0.100 thold), f_keep = 0.120 1.18.760.940 I slot launch_slot_: id 0 | task 2492 | processing task, is_child = 0 1.20.001.172 I slot print_timing: id 0 | task 2492 | prompt eval time = 393.00 ms / 164 tokens ( 2.40 ms per token, 417.30 tokens per second) 1.20.001.178 I slot print_timing: id 0 | task 2492 | eval time = 847.22 ms / 37 tokens ( 23.53 ms per token, 42.49 tokens per second) 1.20.001.179 I slot print_timing: id 0 | task 2492 | total time = 1240.22 ms / 201 tokens 1.20.001.180 I slot print_timing: id 0 | task 2492 | graphs reused = 2259 1.20.001.180 I slot print_timing: id 0 | task 2492 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.001.204 I slot release: id 0 | task 2492 | stop processing: n_tokens = 200, truncated = 0 1.20.005.414 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 1.20.008.893 I slot launch_slot_: id 0 | task 2532 | processing task, is_child = 0 1.21.117.668 I slot print_timing: id 0 | task 2532 | prompt eval time = 417.48 ms / 166 tokens ( 2.51 ms per token, 397.62 tokens per second) 1.21.117.674 I slot print_timing: id 0 | task 2532 | eval time = 691.28 ms / 31 tokens ( 23.04 ms per token, 43.40 tokens per second) 1.21.117.675 I slot print_timing: id 0 | task 2532 | total time = 1108.77 ms / 197 tokens 1.21.117.676 I slot print_timing: id 0 | task 2532 | graphs reused = 2288 1.21.117.676 I slot print_timing: id 0 | task 2532 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.117.695 I slot release: id 0 | task 2532 | stop processing: n_tokens = 196, truncated = 0 1.21.122.527 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.108 (> 0.100 thold), f_keep = 0.153 1.21.128.708 I slot launch_slot_: id 0 | task 2566 | processing task, is_child = 0 1.23.058.685 I slot print_timing: id 0 | task 2566 | prompt eval time = 638.28 ms / 277 tokens ( 2.30 ms per token, 433.98 tokens per second) 1.23.058.689 I slot print_timing: id 0 | task 2566 | eval time = 1291.68 ms / 57 tokens ( 23.07 ms per token, 43.35 tokens per second) 1.23.058.690 I slot print_timing: id 0 | task 2566 | total time = 1929.96 ms / 334 tokens 1.23.058.691 I slot print_timing: id 0 | task 2566 | graphs reused = 2343 1.23.058.691 I slot print_timing: id 0 | task 2566 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.058.726 I slot release: id 0 | task 2566 | stop processing: n_tokens = 333, truncated = 0 1.23.063.526 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 1.23.073.947 I slot launch_slot_: id 0 | task 2626 | processing task, is_child = 0 1.24.950.212 I slot print_timing: id 0 | task 2626 | prompt eval time = 539.98 ms / 248 tokens ( 2.18 ms per token, 459.28 tokens per second) 1.24.950.216 I slot print_timing: id 0 | task 2626 | eval time = 1336.27 ms / 59 tokens ( 23.04 ms per token, 43.40 tokens per second) 1.24.950.217 I slot print_timing: id 0 | task 2626 | total time = 1876.25 ms / 307 tokens 1.24.950.217 I slot print_timing: id 0 | task 2626 | graphs reused = 2399 1.24.950.218 I slot print_timing: id 0 | task 2626 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.950.249 I slot release: id 0 | task 2626 | stop processing: n_tokens = 306, truncated = 0 1.24.954.098 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.189 (> 0.100 thold), f_keep = 0.098 1.24.963.041 I slot launch_slot_: id 0 | task 2688 | processing task, is_child = 0 1.26.059.081 I slot print_timing: id 0 | task 2688 | prompt eval time = 418.76 ms / 159 tokens ( 2.63 ms per token, 379.69 tokens per second) 1.26.059.085 I slot print_timing: id 0 | task 2688 | eval time = 677.27 ms / 30 tokens ( 23.35 ms per token, 42.82 tokens per second) 1.26.059.086 I slot print_timing: id 0 | task 2688 | total time = 1096.03 ms / 189 tokens 1.26.059.086 I slot print_timing: id 0 | task 2688 | graphs reused = 2427 1.26.059.087 I slot print_timing: id 0 | task 2688 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.059.105 I slot release: id 0 | task 2688 | stop processing: n_tokens = 188, truncated = 0 1.26.063.303 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 1.26.066.149 I slot launch_slot_: id 0 | task 2721 | processing task, is_child = 0 1.27.263.920 I slot print_timing: id 0 | task 2721 | prompt eval time = 496.62 ms / 196 tokens ( 2.53 ms per token, 394.67 tokens per second) 1.27.263.927 I slot print_timing: id 0 | task 2721 | eval time = 701.14 ms / 31 tokens ( 23.37 ms per token, 42.79 tokens per second) 1.27.263.928 I slot print_timing: id 0 | task 2721 | total time = 1197.76 ms / 227 tokens 1.27.263.929 I slot print_timing: id 0 | task 2721 | graphs reused = 2456 1.27.263.929 I slot print_timing: id 0 | task 2721 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.263.953 I slot release: id 0 | task 2721 | stop processing: n_tokens = 226, truncated = 0 1.27.267.857 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 1.27.274.836 I slot launch_slot_: id 0 | task 2755 | processing task, is_child = 0 1.28.246.953 I slot print_timing: id 0 | task 2755 | prompt eval time = 396.92 ms / 150 tokens ( 2.65 ms per token, 377.91 tokens per second) 1.28.246.956 I slot print_timing: id 0 | task 2755 | eval time = 575.18 ms / 26 tokens ( 23.01 ms per token, 43.46 tokens per second) 1.28.246.957 I slot print_timing: id 0 | task 2755 | total time = 972.10 ms / 176 tokens 1.28.246.958 I slot print_timing: id 0 | task 2755 | graphs reused = 2480 1.28.246.958 I slot print_timing: id 0 | task 2755 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.246.982 I slot release: id 0 | task 2755 | stop processing: n_tokens = 175, truncated = 0 1.28.251.190 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 1.28.255.693 I slot launch_slot_: id 0 | task 2784 | processing task, is_child = 0 1.29.683.779 I slot print_timing: id 0 | task 2784 | prompt eval time = 484.76 ms / 215 tokens ( 2.25 ms per token, 443.52 tokens per second) 1.29.683.785 I slot print_timing: id 0 | task 2784 | eval time = 943.31 ms / 42 tokens ( 23.01 ms per token, 43.46 tokens per second) 1.29.683.785 I slot print_timing: id 0 | task 2784 | total time = 1428.07 ms / 257 tokens 1.29.683.786 I slot print_timing: id 0 | task 2784 | graphs reused = 2520 1.29.683.787 I slot print_timing: id 0 | task 2784 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.683.808 I slot release: id 0 | task 2784 | stop processing: n_tokens = 256, truncated = 0 1.29.688.617 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 256, t_last = 326075956143 1.29.696.260 I slot launch_slot_: id 0 | task 2829 | processing task, is_child = 0 1.31.677.523 I slot print_timing: id 0 | task 2829 | prompt eval time = 705.76 ms / 327 tokens ( 2.16 ms per token, 463.33 tokens per second) 1.31.677.527 I slot print_timing: id 0 | task 2829 | eval time = 1275.49 ms / 56 tokens ( 23.19 ms per token, 43.12 tokens per second) 1.31.677.527 I slot print_timing: id 0 | task 2829 | total time = 1981.25 ms / 383 tokens 1.31.677.528 I slot print_timing: id 0 | task 2829 | graphs reused = 2574 1.31.677.529 I slot print_timing: id 0 | task 2829 | graph reallocs = 0 / 0 (same size) / (changed size) 1.31.677.557 I slot release: id 0 | task 2829 | stop processing: n_tokens = 382, truncated = 0 1.31.682.970 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 382, t_last = 326077949892 1.31.695.216 I slot launch_slot_: id 0 | task 2888 | processing task, is_child = 0 1.33.236.657 I slot print_timing: id 0 | task 2888 | prompt eval time = 816.58 ms / 399 tokens ( 2.05 ms per token, 488.62 tokens per second) 1.33.236.663 I slot print_timing: id 0 | task 2888 | eval time = 724.85 ms / 32 tokens ( 23.38 ms per token, 42.77 tokens per second) 1.33.236.664 I slot print_timing: id 0 | task 2888 | total time = 1541.43 ms / 431 tokens 1.33.236.664 I slot print_timing: id 0 | task 2888 | graphs reused = 2604 1.33.236.665 I slot print_timing: id 0 | task 2888 | graph reallocs = 0 / 0 (same size) / (changed size) 1.33.236.696 I slot release: id 0 | task 2888 | stop processing: n_tokens = 430, truncated = 0 1.33.242.480 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 430, t_last = 326079509031 1.33.255.570 I slot launch_slot_: id 0 | task 2923 | processing task, is_child = 0 1.34.999.423 I slot print_timing: id 0 | task 2923 | prompt eval time = 925.43 ms / 439 tokens ( 2.11 ms per token, 474.38 tokens per second) 1.34.999.427 I slot print_timing: id 0 | task 2923 | eval time = 818.41 ms / 36 tokens ( 23.38 ms per token, 42.77 tokens per second) 1.34.999.428 I slot print_timing: id 0 | task 2923 | total time = 1743.84 ms / 475 tokens 1.34.999.428 I slot print_timing: id 0 | task 2923 | graphs reused = 2638 1.34.999.429 I slot print_timing: id 0 | task 2923 | graph reallocs = 0 / 0 (same size) / (changed size) 1.34.999.466 I slot release: id 0 | task 2923 | stop processing: n_tokens = 474, truncated = 0 1.35.005.044 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 474, t_last = 326081271801 1.35.020.101 I slot launch_slot_: id 0 | task 2962 | processing task, is_child = 0 1.36.634.948 I slot print_timing: id 0 | task 2962 | prompt eval time = 818.60 ms / 413 tokens ( 1.98 ms per token, 504.52 tokens per second) 1.36.634.955 I slot print_timing: id 0 | task 2962 | eval time = 796.24 ms / 35 tokens ( 23.42 ms per token, 42.70 tokens per second) 1.36.634.955 I slot print_timing: id 0 | task 2962 | total time = 1614.84 ms / 448 tokens 1.36.634.956 I slot print_timing: id 0 | task 2962 | graphs reused = 2671 1.36.634.957 I slot print_timing: id 0 | task 2962 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.634.988 I slot release: id 0 | task 2962 | stop processing: n_tokens = 447, truncated = 0 1.36.639.555 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 1.36.654.096 I slot launch_slot_: id 0 | task 3000 | processing task, is_child = 0 1.40.241.759 I slot print_timing: id 0 | task 3000 | n_gen = 131, tg = 43.33 t/s, tg_3s = 43.67 t/s 1.43.247.656 I slot print_timing: id 0 | task 3000 | n_gen = 260, tg = 43.12 t/s, tg_3s = 42.92 t/s 1.43.643.686 I slot print_timing: id 0 | task 3000 | prompt eval time = 587.61 ms / 268 tokens ( 2.19 ms per token, 456.08 tokens per second) 1.43.643.692 I slot print_timing: id 0 | task 3000 | eval time = 6401.97 ms / 277 tokens ( 23.20 ms per token, 43.11 tokens per second) 1.43.643.693 I slot print_timing: id 0 | task 3000 | total time = 6989.58 ms / 545 tokens 1.43.643.694 I slot print_timing: id 0 | task 3000 | graphs reused = 2945 1.43.643.694 I slot print_timing: id 0 | task 3000 | graph reallocs = 0 / 0 (same size) / (changed size) 1.43.643.721 I slot release: id 0 | task 3000 | stop processing: n_tokens = 544, truncated = 0 1.43.648.822 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 544, t_last = 326089916056 1.43.658.041 I slot launch_slot_: id 0 | task 3280 | processing task, is_child = 0 1.47.503.683 I slot print_timing: id 0 | task 3280 | n_gen = 130, tg = 42.86 t/s, tg_3s = 43.19 t/s 1.49.490.127 I slot print_timing: id 0 | task 3280 | prompt eval time = 835.87 ms / 395 tokens ( 2.12 ms per token, 472.56 tokens per second) 1.49.490.132 I slot print_timing: id 0 | task 3280 | eval time = 4996.20 ms / 215 tokens ( 23.35 ms per token, 42.83 tokens per second) 1.49.490.132 I slot print_timing: id 0 | task 3280 | total time = 5832.08 ms / 610 tokens 1.49.490.133 I slot print_timing: id 0 | task 3280 | graphs reused = 3157 1.49.490.134 I slot print_timing: id 0 | task 3280 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.490.162 I slot release: id 0 | task 3280 | stop processing: n_tokens = 609, truncated = 0 1.49.495.220 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 609, t_last = 326095762497 1.49.510.196 I slot launch_slot_: id 0 | task 3498 | processing task, is_child = 0 1.53.360.677 I slot print_timing: id 0 | task 3498 | n_gen = 130, tg = 42.74 t/s, tg_3s = 43.07 t/s 1.56.375.654 I slot print_timing: id 0 | task 3498 | n_gen = 259, tg = 42.76 t/s, tg_3s = 42.79 t/s 1.56.656.889 I slot print_timing: id 0 | task 3498 | prompt eval time = 832.45 ms / 390 tokens ( 2.13 ms per token, 468.50 tokens per second) 1.56.656.895 I slot print_timing: id 0 | task 3498 | eval time = 6314.23 ms / 271 tokens ( 23.39 ms per token, 42.76 tokens per second) 1.56.656.896 I slot print_timing: id 0 | task 3498 | total time = 7146.68 ms / 661 tokens 1.56.656.897 I slot print_timing: id 0 | task 3498 | graphs reused = 3425 1.56.656.897 I slot print_timing: id 0 | task 3498 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.656.929 I slot release: id 0 | task 3498 | stop processing: n_tokens = 660, truncated = 0 1.56.661.878 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 660, t_last = 326102929264 1.56.676.771 I slot launch_slot_: id 0 | task 3772 | processing task, is_child = 0 1.57.744.452 I slot print_timing: id 0 | task 3772 | prompt eval time = 650.07 ms / 304 tokens ( 2.14 ms per token, 467.64 tokens per second) 1.57.744.458 I slot print_timing: id 0 | task 3772 | eval time = 417.60 ms / 19 tokens ( 23.20 ms per token, 43.10 tokens per second) 1.57.744.459 I slot print_timing: id 0 | task 3772 | total time = 1067.67 ms / 323 tokens 1.57.744.459 I slot print_timing: id 0 | task 3772 | graphs reused = 3442 1.57.744.460 I slot print_timing: id 0 | task 3772 | graph reallocs = 0 / 0 (same size) / (changed size) 1.57.744.483 I slot release: id 0 | task 3772 | stop processing: n_tokens = 322, truncated = 0 1.57.749.148 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.104 (> 0.100 thold), f_keep = 0.093 1.57.754.230 I slot launch_slot_: id 0 | task 3794 | processing task, is_child = 0 1.59.158.508 I slot print_timing: id 0 | task 3794 | prompt eval time = 663.62 ms / 289 tokens ( 2.30 ms per token, 435.49 tokens per second) 1.59.158.514 I slot print_timing: id 0 | task 3794 | eval time = 740.65 ms / 33 tokens ( 23.15 ms per token, 43.21 tokens per second) 1.59.158.515 I slot print_timing: id 0 | task 3794 | total time = 1404.27 ms / 322 tokens 1.59.158.516 I slot print_timing: id 0 | task 3794 | graphs reused = 3473 1.59.158.516 I slot print_timing: id 0 | task 3794 | graph reallocs = 0 / 0 (same size) / (changed size) 1.59.158.541 I slot release: id 0 | task 3794 | stop processing: n_tokens = 321, truncated = 0 1.59.164.004 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 321, t_last = 326105430876 1.59.174.403 I slot launch_slot_: id 0 | task 3830 | processing task, is_child = 0 2.00.406.342 I slot print_timing: id 0 | task 3830 | prompt eval time = 741.12 ms / 360 tokens ( 2.06 ms per token, 485.75 tokens per second) 2.00.406.349 I slot print_timing: id 0 | task 3830 | eval time = 490.80 ms / 22 tokens ( 23.37 ms per token, 42.79 tokens per second) 2.00.406.350 I slot print_timing: id 0 | task 3830 | total time = 1231.92 ms / 382 tokens 2.00.406.351 I slot print_timing: id 0 | task 3830 | graphs reused = 3493 2.00.406.351 I slot print_timing: id 0 | task 3830 | graph reallocs = 0 / 0 (same size) / (changed size) 2.00.406.381 I slot release: id 0 | task 3830 | stop processing: n_tokens = 381, truncated = 0 2.00.411.103 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 381, t_last = 326106678716 2.00.422.503 I slot launch_slot_: id 0 | task 3855 | processing task, is_child = 0 2.04.151.115 I slot print_timing: id 0 | task 3855 | n_gen = 131, tg = 43.10 t/s, tg_3s = 43.44 t/s 2.07.161.208 I slot print_timing: id 0 | task 3855 | n_gen = 260, tg = 42.98 t/s, tg_3s = 42.86 t/s 2.09.586.365 I slot print_timing: id 0 | task 3855 | prompt eval time = 712.68 ms / 317 tokens ( 2.25 ms per token, 444.80 tokens per second) 2.09.586.368 I slot print_timing: id 0 | task 3855 | eval time = 8451.17 ms / 364 tokens ( 23.28 ms per token, 42.95 tokens per second) 2.09.586.368 I slot print_timing: id 0 | task 3855 | total time = 9163.85 ms / 681 tokens 2.09.586.369 I slot print_timing: id 0 | task 3855 | graphs reused = 3854 2.09.586.370 I slot print_timing: id 0 | task 3855 | graph reallocs = 0 / 0 (same size) / (changed size) 2.09.586.397 I slot release: id 0 | task 3855 | stop processing: n_tokens = 680, truncated = 0 2.09.591.080 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.121 (> 0.100 thold), f_keep = 0.044 2.09.601.119 I slot launch_slot_: id 0 | task 4222 | processing task, is_child = 0 2.10.596.581 I slot print_timing: id 0 | task 4222 | prompt eval time = 577.80 ms / 248 tokens ( 2.33 ms per token, 429.21 tokens per second) 2.10.596.585 I slot print_timing: id 0 | task 4222 | eval time = 417.65 ms / 19 tokens ( 23.20 ms per token, 43.10 tokens per second) 2.10.596.586 I slot print_timing: id 0 | task 4222 | total time = 995.45 ms / 267 tokens 2.10.596.586 I slot print_timing: id 0 | task 4222 | graphs reused = 3870 2.10.596.587 I slot print_timing: id 0 | task 4222 | graph reallocs = 0 / 0 (same size) / (changed size) 2.10.596.607 I slot release: id 0 | task 4222 | stop processing: n_tokens = 266, truncated = 0 2.10.601.680 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 266, t_last = 326116868942 2.10.609.927 I slot launch_slot_: id 0 | task 4244 | processing task, is_child = 0 2.12.222.371 I slot print_timing: id 0 | task 4244 | prompt eval time = 708.59 ms / 331 tokens ( 2.14 ms per token, 467.12 tokens per second) 2.12.222.374 I slot print_timing: id 0 | task 4244 | eval time = 903.84 ms / 40 tokens ( 23.18 ms per token, 43.15 tokens per second) 2.12.222.375 I slot print_timing: id 0 | task 4244 | total time = 1612.43 ms / 371 tokens 2.12.222.375 I slot print_timing: id 0 | task 4244 | graphs reused = 3908 2.12.222.376 I slot print_timing: id 0 | task 4244 | graph reallocs = 0 / 0 (same size) / (changed size) 2.12.222.405 I slot release: id 0 | task 4244 | stop processing: n_tokens = 370, truncated = 0 2.12.227.009 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.107 (> 0.100 thold), f_keep = 0.081 2.12.238.921 I slot launch_slot_: id 0 | task 4287 | processing task, is_child = 0 2.13.431.142 I slot print_timing: id 0 | task 4287 | prompt eval time = 637.97 ms / 280 tokens ( 2.28 ms per token, 438.89 tokens per second) 2.13.431.149 I slot print_timing: id 0 | task 4287 | eval time = 554.24 ms / 25 tokens ( 23.09 ms per token, 43.30 tokens per second) 2.13.431.149 I slot print_timing: id 0 | task 4287 | total time = 1192.21 ms / 305 tokens 2.13.431.150 I slot print_timing: id 0 | task 4287 | graphs reused = 3931 2.13.431.151 I slot print_timing: id 0 | task 4287 | graph reallocs = 0 / 0 (same size) / (changed size) 2.13.431.174 I slot release: id 0 | task 4287 | stop processing: n_tokens = 304, truncated = 0 2.13.435.612 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 2.13.443.278 I slot launch_slot_: id 0 | task 4315 | processing task, is_child = 0 2.14.550.854 I slot print_timing: id 0 | task 4315 | prompt eval time = 587.19 ms / 252 tokens ( 2.33 ms per token, 429.16 tokens per second) 2.14.550.859 I slot print_timing: id 0 | task 4315 | eval time = 520.37 ms / 23 tokens ( 23.65 ms per token, 42.28 tokens per second) 2.14.550.860 I slot print_timing: id 0 | task 4315 | total time = 1107.56 ms / 275 tokens 2.14.550.861 I slot print_timing: id 0 | task 4315 | graphs reused = 3951 2.14.550.862 I slot print_timing: id 0 | task 4315 | graph reallocs = 0 / 0 (same size) / (changed size) 2.14.550.887 I slot release: id 0 | task 4315 | stop processing: n_tokens = 274, truncated = 0 2.14.555.442 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 2.14.564.248 I slot launch_slot_: id 0 | task 4341 | processing task, is_child = 0 2.15.617.810 I slot print_timing: id 0 | task 4341 | prompt eval time = 568.43 ms / 267 tokens ( 2.13 ms per token, 469.71 tokens per second) 2.15.617.817 I slot print_timing: id 0 | task 4341 | eval time = 485.12 ms / 22 tokens ( 23.10 ms per token, 43.29 tokens per second) 2.15.617.817 I slot print_timing: id 0 | task 4341 | total time = 1053.55 ms / 289 tokens 2.15.617.818 I slot print_timing: id 0 | task 4341 | graphs reused = 3971 2.15.617.819 I slot print_timing: id 0 | task 4341 | graph reallocs = 0 / 0 (same size) / (changed size) 2.15.617.854 I slot release: id 0 | task 4341 | stop processing: n_tokens = 288, truncated = 0 2.15.622.295 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 2.15.631.355 I slot launch_slot_: id 0 | task 4366 | processing task, is_child = 0 2.16.703.421 I slot print_timing: id 0 | task 4366 | prompt eval time = 585.40 ms / 255 tokens ( 2.30 ms per token, 435.60 tokens per second) 2.16.703.429 I slot print_timing: id 0 | task 4366 | eval time = 486.65 ms / 22 tokens ( 23.17 ms per token, 43.15 tokens per second) 2.16.703.429 I slot print_timing: id 0 | task 4366 | total time = 1072.05 ms / 277 tokens 2.16.703.430 I slot print_timing: id 0 | task 4366 | graphs reused = 3990 2.16.703.431 I slot print_timing: id 0 | task 4366 | graph reallocs = 0 / 0 (same size) / (changed size) 2.16.703.452 I slot release: id 0 | task 4366 | stop processing: n_tokens = 276, truncated = 0 2.16.708.837 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 276, t_last = 326122975787 2.16.717.844 I slot launch_slot_: id 0 | task 4391 | processing task, is_child = 0 2.20.546.056 I slot print_timing: id 0 | task 4391 | n_gen = 130, tg = 42.85 t/s, tg_3s = 43.19 t/s 2.21.385.309 I slot print_timing: id 0 | task 4391 | prompt eval time = 818.00 ms / 397 tokens ( 2.06 ms per token, 485.33 tokens per second) 2.21.385.315 I slot print_timing: id 0 | task 4391 | eval time = 3849.45 ms / 166 tokens ( 23.33 ms per token, 42.86 tokens per second) 2.21.385.316 I slot print_timing: id 0 | task 4391 | total time = 4667.45 ms / 563 tokens 2.21.385.317 I slot print_timing: id 0 | task 4391 | graphs reused = 4153 2.21.385.317 I slot print_timing: id 0 | task 4391 | graph reallocs = 0 / 0 (same size) / (changed size) 2.21.385.348 I slot release: id 0 | task 4391 | stop processing: n_tokens = 562, truncated = 0 2.21.390.097 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.103 (> 0.100 thold), f_keep = 0.053 2.21.404.756 I slot launch_slot_: id 0 | task 4560 | processing task, is_child = 0 2.22.494.792 I slot print_timing: id 0 | task 4560 | prompt eval time = 649.97 ms / 290 tokens ( 2.24 ms per token, 446.17 tokens per second) 2.22.494.798 I slot print_timing: id 0 | task 4560 | eval time = 440.05 ms / 20 tokens ( 23.16 ms per token, 43.18 tokens per second) 2.22.494.799 I slot print_timing: id 0 | task 4560 | total time = 1090.03 ms / 310 tokens 2.22.494.799 I slot print_timing: id 0 | task 4560 | graphs reused = 4171 2.22.494.800 I slot print_timing: id 0 | task 4560 | graph reallocs = 0 / 0 (same size) / (changed size) 2.22.494.828 I slot release: id 0 | task 4560 | stop processing: n_tokens = 309, truncated = 0 2.22.501.354 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 309, t_last = 326128767163 2.22.507.252 I slot launch_slot_: id 0 | task 4583 | processing task, is_child = 0 2.24.670.668 I slot print_timing: id 0 | task 4583 | prompt eval time = 1272.93 ms / 612 tokens ( 2.08 ms per token, 480.78 tokens per second) 2.24.670.675 I slot print_timing: id 0 | task 4583 | eval time = 890.47 ms / 39 tokens ( 23.43 ms per token, 42.67 tokens per second) 2.24.670.675 I slot print_timing: id 0 | task 4583 | total time = 2163.40 ms / 651 tokens 2.24.670.676 I slot print_timing: id 0 | task 4583 | graphs reused = 4208 2.24.670.677 I slot print_timing: id 0 | task 4583 | graph reallocs = 0 / 0 (same size) / (changed size) 2.24.670.714 I slot release: id 0 | task 4583 | stop processing: n_tokens = 650, truncated = 0 2.24.675.479 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.109 (> 0.100 thold), f_keep = 0.046 2.24.694.434 I slot launch_slot_: id 0 | task 4626 | processing task, is_child = 0 2.25.756.494 I slot print_timing: id 0 | task 4626 | prompt eval time = 587.27 ms / 275 tokens ( 2.14 ms per token, 468.27 tokens per second) 2.25.756.497 I slot print_timing: id 0 | task 4626 | eval time = 474.78 ms / 21 tokens ( 23.74 ms per token, 42.12 tokens per second) 2.25.756.498 I slot print_timing: id 0 | task 4626 | total time = 1062.05 ms / 296 tokens 2.25.756.499 I slot print_timing: id 0 | task 4626 | graphs reused = 4227 2.25.756.499 I slot print_timing: id 0 | task 4626 | graph reallocs = 0 / 0 (same size) / (changed size) 2.25.756.523 I slot release: id 0 | task 4626 | stop processing: n_tokens = 295, truncated = 0 2.25.762.138 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 295, t_last = 326132028858 2.25.766.743 I slot launch_slot_: id 0 | task 4650 | processing task, is_child = 0 2.27.285.606 I slot print_timing: id 0 | task 4650 | prompt eval time = 955.95 ms / 456 tokens ( 2.10 ms per token, 477.01 tokens per second) 2.27.285.610 I slot print_timing: id 0 | task 4650 | eval time = 562.90 ms / 25 tokens ( 23.45 ms per token, 42.64 tokens per second) 2.27.285.610 I slot print_timing: id 0 | task 4650 | total time = 1518.85 ms / 481 tokens 2.27.285.611 I slot print_timing: id 0 | task 4650 | graphs reused = 4250 2.27.285.611 I slot print_timing: id 0 | task 4650 | graph reallocs = 0 / 0 (same size) / (changed size) 2.27.285.645 I slot release: id 0 | task 4650 | stop processing: n_tokens = 480, truncated = 0 2.27.291.534 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 480, t_last = 326133557980 2.27.307.416 I slot launch_slot_: id 0 | task 4678 | processing task, is_child = 0 2.29.348.121 I slot print_timing: id 0 | task 4678 | prompt eval time = 1150.95 ms / 542 tokens ( 2.12 ms per token, 470.92 tokens per second) 2.29.348.127 I slot print_timing: id 0 | task 4678 | eval time = 889.74 ms / 39 tokens ( 23.41 ms per token, 42.71 tokens per second) 2.29.348.128 I slot print_timing: id 0 | task 4678 | total time = 2040.69 ms / 581 tokens 2.29.348.129 I slot print_timing: id 0 | task 4678 | graphs reused = 4287 2.29.348.129 I slot print_timing: id 0 | task 4678 | graph reallocs = 0 / 0 (same size) / (changed size) 2.29.348.166 I slot release: id 0 | task 4678 | stop processing: n_tokens = 580, truncated = 0 2.29.353.529 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 580, t_last = 326135620501 2.29.370.955 I slot launch_slot_: id 0 | task 4721 | processing task, is_child = 0 2.31.186.650 I slot print_timing: id 0 | task 4721 | prompt eval time = 812.24 ms / 361 tokens ( 2.25 ms per token, 444.45 tokens per second) 2.31.186.657 I slot print_timing: id 0 | task 4721 | eval time = 1003.45 ms / 44 tokens ( 23.34 ms per token, 42.85 tokens per second) 2.31.186.658 I slot print_timing: id 0 | task 4721 | total time = 1815.68 ms / 405 tokens 2.31.186.659 I slot print_timing: id 0 | task 4721 | graphs reused = 4329 2.31.186.659 I slot print_timing: id 0 | task 4721 | graph reallocs = 0 / 0 (same size) / (changed size) 2.31.186.690 I slot release: id 0 | task 4721 | stop processing: n_tokens = 429, truncated = 0 2.31.191.518 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 2.31.199.900 I slot launch_slot_: id 0 | task 4768 | processing task, is_child = 0 2.32.612.688 I slot print_timing: id 0 | task 4768 | prompt eval time = 603.39 ms / 258 tokens ( 2.34 ms per token, 427.58 tokens per second) 2.32.612.692 I slot print_timing: id 0 | task 4768 | eval time = 809.38 ms / 36 tokens ( 23.13 ms per token, 43.24 tokens per second) 2.32.612.693 I slot print_timing: id 0 | task 4768 | total time = 1412.78 ms / 294 tokens 2.32.612.698 I slot print_timing: id 0 | task 4768 | graphs reused = 4363 2.32.612.698 I slot print_timing: id 0 | task 4768 | graph reallocs = 0 / 0 (same size) / (changed size) 2.32.612.723 I slot release: id 0 | task 4768 | stop processing: n_tokens = 317, truncated = 0 2.32.618.084 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 317, t_last = 326138885058 2.32.621.393 I slot launch_slot_: id 0 | task 4807 | processing task, is_child = 0 2.33.962.402 I slot print_timing: id 0 | task 4807 | prompt eval time = 836.16 ms / 379 tokens ( 2.21 ms per token, 453.26 tokens per second) 2.33.962.406 I slot print_timing: id 0 | task 4807 | eval time = 504.84 ms / 22 tokens ( 24.04 ms per token, 41.60 tokens per second) 2.33.962.406 I slot print_timing: id 0 | task 4807 | total time = 1341.00 ms / 401 tokens 2.33.962.407 I slot print_timing: id 0 | task 4807 | graphs reused = 4383 2.33.962.408 I slot print_timing: id 0 | task 4807 | graph reallocs = 0 / 0 (same size) / (changed size) 2.33.962.441 I slot release: id 0 | task 4807 | stop processing: n_tokens = 423, truncated = 0 2.33.968.727 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 423, t_last = 326140234776 2.33.983.063 I slot launch_slot_: id 0 | task 4832 | processing task, is_child = 0 2.35.920.941 I slot print_timing: id 0 | task 4832 | prompt eval time = 1140.42 ms / 540 tokens ( 2.11 ms per token, 473.51 tokens per second) 2.35.920.947 I slot print_timing: id 0 | task 4832 | eval time = 797.45 ms / 35 tokens ( 23.45 ms per token, 42.64 tokens per second) 2.35.920.947 I slot print_timing: id 0 | task 4832 | total time = 1937.86 ms / 575 tokens 2.35.920.948 I slot print_timing: id 0 | task 4832 | graphs reused = 4416 2.35.920.949 I slot print_timing: id 0 | task 4832 | graph reallocs = 0 / 0 (same size) / (changed size) 2.35.920.987 I slot release: id 0 | task 4832 | stop processing: n_tokens = 596, truncated = 0 2.35.926.537 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 596, t_last = 326142193322 2.35.946.545 I slot launch_slot_: id 0 | task 4871 | processing task, is_child = 0 2.37.366.731 I slot print_timing: id 0 | task 4871 | prompt eval time = 764.25 ms / 370 tokens ( 2.07 ms per token, 484.14 tokens per second) 2.37.366.737 I slot print_timing: id 0 | task 4871 | eval time = 655.93 ms / 29 tokens ( 23.43 ms per token, 42.69 tokens per second) 2.37.366.737 I slot print_timing: id 0 | task 4871 | total time = 1420.17 ms / 399 tokens 2.37.366.738 I slot print_timing: id 0 | task 4871 | graphs reused = 4443 2.37.366.739 I slot print_timing: id 0 | task 4871 | graph reallocs = 0 / 0 (same size) / (changed size) 2.37.366.770 I slot release: id 0 | task 4871 | stop processing: n_tokens = 422, truncated = 0 2.37.371.962 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 422, t_last = 326143639105 2.37.375.964 I slot launch_slot_: id 0 | task 4903 | processing task, is_child = 0 2.38.644.800 I slot print_timing: id 0 | task 4903 | prompt eval time = 709.37 ms / 336 tokens ( 2.11 ms per token, 473.66 tokens per second) 2.38.644.804 I slot print_timing: id 0 | task 4903 | eval time = 559.46 ms / 25 tokens ( 23.31 ms per token, 42.90 tokens per second) 2.38.644.805 I slot print_timing: id 0 | task 4903 | total time = 1268.83 ms / 361 tokens 2.38.644.806 I slot print_timing: id 0 | task 4903 | graphs reused = 4466 2.38.644.806 I slot print_timing: id 0 | task 4903 | graph reallocs = 0 / 0 (same size) / (changed size) 2.38.644.839 I slot release: id 0 | task 4903 | stop processing: n_tokens = 383, truncated = 0 2.38.649.482 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 2.38.656.515 I slot launch_slot_: id 0 | task 4931 | processing task, is_child = 0 2.39.756.117 I slot print_timing: id 0 | task 4931 | prompt eval time = 567.60 ms / 261 tokens ( 2.17 ms per token, 459.83 tokens per second) 2.39.756.124 I slot print_timing: id 0 | task 4931 | eval time = 531.99 ms / 24 tokens ( 23.13 ms per token, 43.23 tokens per second) 2.39.756.124 I slot print_timing: id 0 | task 4931 | total time = 1099.59 ms / 285 tokens 2.39.756.125 I slot print_timing: id 0 | task 4931 | graphs reused = 4488 2.39.756.126 I slot print_timing: id 0 | task 4931 | graph reallocs = 0 / 0 (same size) / (changed size) 2.39.756.152 I slot release: id 0 | task 4931 | stop processing: n_tokens = 284, truncated = 0 2.39.760.932 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 2.39.763.611 I slot launch_slot_: id 0 | task 4958 | processing task, is_child = 0 2.41.363.233 I slot print_timing: id 0 | task 4958 | prompt eval time = 698.15 ms / 299 tokens ( 2.33 ms per token, 428.27 tokens per second) 2.41.363.239 I slot print_timing: id 0 | task 4958 | eval time = 901.46 ms / 40 tokens ( 23.11 ms per token, 43.26 tokens per second) 2.41.363.244 I slot print_timing: id 0 | task 4958 | total time = 1599.61 ms / 339 tokens 2.41.363.245 I slot print_timing: id 0 | task 4958 | graphs reused = 4526 2.41.363.247 I slot print_timing: id 0 | task 4958 | graph reallocs = 0 / 0 (same size) / (changed size) 2.41.363.273 I slot release: id 0 | task 4958 | stop processing: n_tokens = 338, truncated = 0 2.41.368.323 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 338, t_last = 326147635608 2.41.376.512 I slot launch_slot_: id 0 | task 5001 | processing task, is_child = 0 2.42.659.011 I slot print_timing: id 0 | task 5001 | prompt eval time = 702.46 ms / 319 tokens ( 2.20 ms per token, 454.12 tokens per second) 2.42.659.017 I slot print_timing: id 0 | task 5001 | eval time = 580.02 ms / 26 tokens ( 23.20 ms per token, 43.10 tokens per second) 2.42.659.018 I slot print_timing: id 0 | task 5001 | total time = 1282.48 ms / 345 tokens 2.42.659.019 I slot print_timing: id 0 | task 5001 | graphs reused = 4550 2.42.659.019 I slot print_timing: id 0 | task 5001 | graph reallocs = 0 / 0 (same size) / (changed size) 2.42.659.043 I slot release: id 0 | task 5001 | stop processing: n_tokens = 344, truncated = 0 2.42.664.703 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 344, t_last = 326148931378 2.42.675.205 I slot launch_slot_: id 0 | task 5030 | processing task, is_child = 0 2.44.361.670 I slot print_timing: id 0 | task 5030 | prompt eval time = 856.83 ms / 423 tokens ( 2.03 ms per token, 493.68 tokens per second) 2.44.361.674 I slot print_timing: id 0 | task 5030 | eval time = 829.62 ms / 36 tokens ( 23.70 ms per token, 42.19 tokens per second) 2.44.361.674 I slot print_timing: id 0 | task 5030 | total time = 1686.45 ms / 459 tokens 2.44.361.675 I slot print_timing: id 0 | task 5030 | graphs reused = 4584 2.44.361.676 I slot print_timing: id 0 | task 5030 | graph reallocs = 0 / 0 (same size) / (changed size) 2.44.361.705 I slot release: id 0 | task 5030 | stop processing: n_tokens = 458, truncated = 0 2.44.366.801 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 326150634040 2.44.380.612 I slot launch_slot_: id 0 | task 5069 | processing task, is_child = 0 2.45.825.937 I slot print_timing: id 0 | task 5069 | prompt eval time = 779.58 ms / 366 tokens ( 2.13 ms per token, 469.49 tokens per second) 2.45.825.940 I slot print_timing: id 0 | task 5069 | eval time = 665.74 ms / 29 tokens ( 23.78 ms per token, 42.06 tokens per second) 2.45.825.941 I slot print_timing: id 0 | task 5069 | total time = 1445.32 ms / 395 tokens 2.45.825.942 I slot print_timing: id 0 | task 5069 | graphs reused = 4611 2.45.825.943 I slot print_timing: id 0 | task 5069 | graph reallocs = 0 / 0 (same size) / (changed size) 2.45.825.972 I slot release: id 0 | task 5069 | stop processing: n_tokens = 394, truncated = 0 2.45.832.369 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 394, t_last = 326152098307 2.45.832.437 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.324 MiB) 2.45.842.314 I slot launch_slot_: id 0 | task 5101 | processing task, is_child = 0 2.47.682.517 I slot print_timing: id 0 | task 5101 | prompt eval time = 1184.32 ms / 560 tokens ( 2.11 ms per token, 472.85 tokens per second) 2.47.682.523 I slot print_timing: id 0 | task 5101 | eval time = 655.87 ms / 29 tokens ( 23.42 ms per token, 42.69 tokens per second) 2.47.682.524 I slot print_timing: id 0 | task 5101 | total time = 1840.19 ms / 589 tokens 2.47.682.524 I slot print_timing: id 0 | task 5101 | graphs reused = 4638 2.47.682.525 I slot print_timing: id 0 | task 5101 | graph reallocs = 0 / 0 (same size) / (changed size) 2.47.682.561 I slot release: id 0 | task 5101 | stop processing: n_tokens = 588, truncated = 0 2.47.687.692 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 588, t_last = 326153954896 2.47.687.764 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 67.301 MiB) 2.47.687.768 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 59.776 MiB) 2.47.705.553 I slot launch_slot_: id 0 | task 5134 | processing task, is_child = 0 2.48.854.469 I slot print_timing: id 0 | task 5134 | prompt eval time = 774.09 ms / 366 tokens ( 2.12 ms per token, 472.81 tokens per second) 2.48.854.476 I slot print_timing: id 0 | task 5134 | eval time = 374.81 ms / 17 tokens ( 23.43 ms per token, 42.69 tokens per second) 2.48.854.477 I slot print_timing: id 0 | task 5134 | total time = 1148.90 ms / 383 tokens 2.48.854.478 I slot print_timing: id 0 | task 5134 | graphs reused = 4653 2.48.854.478 I slot print_timing: id 0 | task 5134 | graph reallocs = 0 / 0 (same size) / (changed size) 2.48.854.509 I slot release: id 0 | task 5134 | stop processing: n_tokens = 382, truncated = 0 2.48.859.999 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 382, t_last = 326155126844 2.48.860.052 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 71.238 MiB) 2.48.860.056 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 86.112 MiB) 2.48.863.606 I slot launch_slot_: id 0 | task 5154 | processing task, is_child = 0 2.50.386.655 I slot print_timing: id 0 | task 5154 | prompt eval time = 820.95 ms / 406 tokens ( 2.02 ms per token, 494.55 tokens per second) 2.50.386.659 I slot print_timing: id 0 | task 5154 | eval time = 702.09 ms / 31 tokens ( 23.40 ms per token, 42.73 tokens per second) 2.50.386.659 I slot print_timing: id 0 | task 5154 | total time = 1523.04 ms / 437 tokens 2.50.386.660 I slot print_timing: id 0 | task 5154 | graphs reused = 4682 2.50.386.661 I slot print_timing: id 0 | task 5154 | graph reallocs = 0 / 0 (same size) / (changed size) 2.50.386.690 I slot release: id 0 | task 5154 | stop processing: n_tokens = 436, truncated = 0 2.50.392.002 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 436, t_last = 326156659025 2.50.392.058 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 62.132 MiB) 2.50.392.061 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.989 MiB) 2.50.403.100 I slot launch_slot_: id 0 | task 5188 | processing task, is_child = 0 2.52.131.666 I slot print_timing: id 0 | task 5188 | prompt eval time = 818.51 ms / 379 tokens ( 2.16 ms per token, 463.04 tokens per second) 2.52.131.672 I slot print_timing: id 0 | task 5188 | eval time = 910.04 ms / 40 tokens ( 23.33 ms per token, 42.86 tokens per second) 2.52.131.673 I slot print_timing: id 0 | task 5188 | total time = 1728.55 ms / 419 tokens 2.52.131.674 I slot print_timing: id 0 | task 5188 | graphs reused = 4720 2.52.131.674 I slot print_timing: id 0 | task 5188 | graph reallocs = 0 / 0 (same size) / (changed size) 2.52.131.706 I slot release: id 0 | task 5188 | stop processing: n_tokens = 418, truncated = 0 2.52.137.762 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 418, t_last = 326158404041 2.52.137.820 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 95.710 MiB) 2.52.137.823 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 53.271 MiB) 2.52.147.687 I slot launch_slot_: id 0 | task 5231 | processing task, is_child = 0 2.53.798.838 I slot print_timing: id 0 | task 5231 | prompt eval time = 993.03 ms / 487 tokens ( 2.04 ms per token, 490.42 tokens per second) 2.53.798.844 I slot print_timing: id 0 | task 5231 | eval time = 658.11 ms / 29 tokens ( 23.50 ms per token, 42.55 tokens per second) 2.53.798.845 I slot print_timing: id 0 | task 5231 | total time = 1651.14 ms / 516 tokens 2.53.798.846 I slot print_timing: id 0 | task 5231 | graphs reused = 4746 2.53.798.846 I slot print_timing: id 0 | task 5231 | graph reallocs = 0 / 0 (same size) / (changed size) 2.53.798.882 I slot release: id 0 | task 5231 | stop processing: n_tokens = 515, truncated = 0 2.53.805.260 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 515, t_last = 326160071217 2.53.805.324 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 57.701 MiB) 2.53.805.328 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 62.835 MiB) 2.53.805.330 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 75.633 MiB) 2.53.821.783 I slot launch_slot_: id 0 | task 5263 | processing task, is_child = 0 2.56.415.193 I slot print_timing: id 0 | task 5263 | prompt eval time = 1190.03 ms / 565 tokens ( 2.11 ms per token, 474.78 tokens per second) 2.56.415.196 I slot print_timing: id 0 | task 5263 | eval time = 1403.37 ms / 61 tokens ( 23.39 ms per token, 42.75 tokens per second) 2.56.415.197 I slot print_timing: id 0 | task 5263 | total time = 2593.40 ms / 626 tokens 2.56.415.198 I slot print_timing: id 0 | task 5263 | graphs reused = 4805 2.56.415.198 I slot print_timing: id 0 | task 5263 | graph reallocs = 0 / 0 (same size) / (changed size) 2.56.415.231 I slot release: id 0 | task 5263 | stop processing: n_tokens = 625, truncated = 0 2.56.419.398 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 2.56.419.475 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 64.909 MiB) 2.56.419.482 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.261 MiB) 2.56.437.287 I slot launch_slot_: id 0 | task 5328 | processing task, is_child = 0 2.57.586.700 I slot print_timing: id 0 | task 5328 | prompt eval time = 469.53 ms / 196 tokens ( 2.40 ms per token, 417.44 tokens per second) 2.57.586.704 I slot print_timing: id 0 | task 5328 | eval time = 679.87 ms / 30 tokens ( 23.44 ms per token, 42.66 tokens per second) 2.57.586.705 I slot print_timing: id 0 | task 5328 | total time = 1149.40 ms / 226 tokens 2.57.586.705 I slot print_timing: id 0 | task 5328 | graphs reused = 4833 2.57.586.706 I slot print_timing: id 0 | task 5328 | graph reallocs = 0 / 0 (same size) / (changed size) 2.57.586.730 I slot release: id 0 | task 5328 | stop processing: n_tokens = 225, truncated = 0 2.57.591.048 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 2.57.591.091 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 61.921 MiB) 2.57.593.068 I slot launch_slot_: id 0 | task 5361 | processing task, is_child = 0 2.58.828.490 I slot print_timing: id 0 | task 5361 | prompt eval time = 532.58 ms / 214 tokens ( 2.49 ms per token, 401.81 tokens per second) 2.58.828.501 I slot print_timing: id 0 | task 5361 | eval time = 702.83 ms / 31 tokens ( 23.43 ms per token, 42.68 tokens per second) 2.58.828.506 I slot print_timing: id 0 | task 5361 | total time = 1235.41 ms / 245 tokens 2.58.828.512 I slot print_timing: id 0 | task 5361 | graphs reused = 4862 2.58.828.513 I slot print_timing: id 0 | task 5361 | graph reallocs = 0 / 0 (same size) / (changed size) 2.58.828.534 I slot release: id 0 | task 5361 | stop processing: n_tokens = 244, truncated = 0 2.58.832.699 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.149 (> 0.100 thold), f_keep = 0.123 2.58.832.739 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 51.478 MiB) 2.58.832.743 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 60.760 MiB) 2.58.834.946 I slot launch_slot_: id 0 | task 5395 | processing task, is_child = 0 3.01.306.797 I slot print_timing: id 0 | task 5395 | prompt eval time = 530.18 ms / 201 tokens ( 2.64 ms per token, 379.12 tokens per second) 3.01.306.800 I slot print_timing: id 0 | task 5395 | eval time = 1941.66 ms / 85 tokens ( 23.11 ms per token, 43.26 tokens per second) 3.01.306.801 I slot print_timing: id 0 | task 5395 | total time = 2471.84 ms / 286 tokens 3.01.306.801 I slot print_timing: id 0 | task 5395 | graphs reused = 4944 3.01.306.802 I slot print_timing: id 0 | task 5395 | graph reallocs = 0 / 0 (same size) / (changed size) 3.01.306.823 I slot release: id 0 | task 5395 | stop processing: n_tokens = 285, truncated = 0 3.01.310.941 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 3.01.311.019 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 66.211 MiB) 3.01.313.367 I slot launch_slot_: id 0 | task 5483 | processing task, is_child = 0 3.03.372.783 I slot print_timing: id 0 | task 5483 | prompt eval time = 466.33 ms / 168 tokens ( 2.78 ms per token, 360.26 tokens per second) 3.03.372.787 I slot print_timing: id 0 | task 5483 | eval time = 1593.07 ms / 70 tokens ( 23.09 ms per token, 43.31 tokens per second) 3.03.372.788 I slot print_timing: id 0 | task 5483 | total time = 2059.40 ms / 238 tokens 3.03.372.788 I slot print_timing: id 0 | task 5483 | graphs reused = 5012 3.03.372.789 I slot print_timing: id 0 | task 5483 | graph reallocs = 0 / 0 (same size) / (changed size) 3.03.372.807 I slot release: id 0 | task 5483 | stop processing: n_tokens = 237, truncated = 0 3.03.377.391 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 3.03.377.436 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 58.369 MiB) 3.03.379.462 I slot launch_slot_: id 0 | task 5556 | processing task, is_child = 0 3.04.860.629 I slot print_timing: id 0 | task 5556 | prompt eval time = 536.43 ms / 232 tokens ( 2.31 ms per token, 432.49 tokens per second) 3.04.860.634 I slot print_timing: id 0 | task 5556 | eval time = 944.73 ms / 42 tokens ( 23.04 ms per token, 43.40 tokens per second) 3.04.860.635 I slot print_timing: id 0 | task 5556 | total time = 1481.16 ms / 274 tokens 3.04.860.635 I slot print_timing: id 0 | task 5556 | graphs reused = 5051 3.04.860.636 I slot print_timing: id 0 | task 5556 | graph reallocs = 0 / 0 (same size) / (changed size) 3.04.860.661 I slot release: id 0 | task 5556 | stop processing: n_tokens = 273, truncated = 0 3.04.865.035 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 3.04.865.079 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 66.562 MiB) 3.04.867.498 I slot launch_slot_: id 0 | task 5601 | processing task, is_child = 0 3.08.293.120 I slot print_timing: id 0 | task 5601 | prompt eval time = 591.05 ms / 249 tokens ( 2.37 ms per token, 421.28 tokens per second) 3.08.293.124 I slot print_timing: id 0 | task 5601 | eval time = 2834.55 ms / 124 tokens ( 23.05 ms per token, 43.39 tokens per second) 3.08.293.125 I slot print_timing: id 0 | task 5601 | total time = 3425.60 ms / 373 tokens 3.08.293.125 I slot print_timing: id 0 | task 5601 | graphs reused = 5172 3.08.293.126 I slot print_timing: id 0 | task 5601 | graph reallocs = 0 / 0 (same size) / (changed size) 3.08.293.151 I slot release: id 0 | task 5601 | stop processing: n_tokens = 372, truncated = 0 3.08.298.086 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 3.08.298.141 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 57.315 MiB) 3.08.298.146 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 74.227 MiB) 3.08.301.451 I slot launch_slot_: id 0 | task 5728 | processing task, is_child = 0 3.11.984.427 I slot print_timing: id 0 | task 5728 | n_gen = 131, tg = 43.07 t/s, tg_3s = 43.40 t/s 3.12.217.657 I slot print_timing: id 0 | task 5728 | prompt eval time = 664.28 ms / 320 tokens ( 2.08 ms per token, 481.72 tokens per second) 3.12.217.662 I slot print_timing: id 0 | task 5728 | eval time = 3251.91 ms / 141 tokens ( 23.23 ms per token, 43.05 tokens per second) 3.12.217.663 I slot print_timing: id 0 | task 5728 | total time = 3916.19 ms / 461 tokens 3.12.217.663 I slot print_timing: id 0 | task 5728 | graphs reused = 5311 3.12.217.664 I slot print_timing: id 0 | task 5728 | graph reallocs = 0 / 0 (same size) / (changed size) 3.12.217.691 I slot release: id 0 | task 5728 | stop processing: n_tokens = 460, truncated = 0 3.12.221.937 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 3.12.222.003 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 95.781 MiB) 3.12.229.693 I slot launch_slot_: id 0 | task 5872 | processing task, is_child = 0 3.14.781.043 I slot print_timing: id 0 | task 5872 | prompt eval time = 417.30 ms / 180 tokens ( 2.32 ms per token, 431.35 tokens per second) 3.14.781.047 I slot print_timing: id 0 | task 5872 | eval time = 2134.04 ms / 94 tokens ( 22.95 ms per token, 43.58 tokens per second) 3.14.781.047 I slot print_timing: id 0 | task 5872 | total time = 2551.34 ms / 274 tokens 3.14.781.048 I slot print_timing: id 0 | task 5872 | graphs reused = 5402 3.14.781.049 I slot print_timing: id 0 | task 5872 | graph reallocs = 0 / 0 (same size) / (changed size) 3.14.781.068 I slot release: id 0 | task 5872 | stop processing: n_tokens = 273, truncated = 0 3.14.785.177 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.163 (> 0.100 thold), f_keep = 0.110 3.14.785.228 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 71.133 MiB) 3.14.787.538 I slot launch_slot_: id 0 | task 5969 | processing task, is_child = 0 3.15.696.284 I slot print_timing: id 0 | task 5969 | prompt eval time = 470.21 ms / 184 tokens ( 2.56 ms per token, 391.31 tokens per second) 3.15.696.288 I slot print_timing: id 0 | task 5969 | eval time = 438.53 ms / 20 tokens ( 23.08 ms per token, 43.33 tokens per second) 3.15.696.288 I slot print_timing: id 0 | task 5969 | total time = 908.74 ms / 204 tokens 3.15.696.289 I slot print_timing: id 0 | task 5969 | graphs reused = 5420 3.15.696.289 I slot print_timing: id 0 | task 5969 | graph reallocs = 0 / 0 (same size) / (changed size) 3.15.696.309 I slot release: id 0 | task 5969 | stop processing: n_tokens = 203, truncated = 0 3.15.700.524 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.128 (> 0.100 thold), f_keep = 0.148 3.15.700.562 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 82.771 MiB) 3.15.702.327 I slot launch_slot_: id 0 | task 5992 | processing task, is_child = 0 3.19.246.504 I slot print_timing: id 0 | task 5992 | n_gen = 132, tg = 43.44 t/s, tg_3s = 43.77 t/s 3.22.248.736 I slot print_timing: id 0 | task 5992 | n_gen = 261, tg = 43.21 t/s, tg_3s = 42.97 t/s 3.22.598.326 I slot print_timing: id 0 | task 5992 | prompt eval time = 528.63 ms / 235 tokens ( 2.25 ms per token, 444.55 tokens per second) 3.22.598.332 I slot print_timing: id 0 | task 5992 | eval time = 6367.36 ms / 276 tokens ( 23.15 ms per token, 43.19 tokens per second) 3.22.598.333 I slot print_timing: id 0 | task 5992 | total time = 6895.99 ms / 511 tokens 3.22.598.333 I slot print_timing: id 0 | task 5992 | graphs reused = 5693 3.22.598.334 I slot print_timing: id 0 | task 5992 | graph reallocs = 0 / 0 (same size) / (changed size) 3.22.598.356 I slot release: id 0 | task 5992 | stop processing: n_tokens = 510, truncated = 0 3.22.602.928 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.104 (> 0.100 thold), f_keep = 0.059 3.22.602.994 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 69.480 MiB) 3.22.602.999 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 57.526 MiB) 3.22.611.633 I slot launch_slot_: id 0 | task 6271 | processing task, is_child = 0 3.26.279.519 I slot print_timing: id 0 | task 6271 | n_gen = 131, tg = 43.21 t/s, tg_3s = 43.54 t/s 3.29.287.422 I slot print_timing: id 0 | task 6271 | n_gen = 260, tg = 43.05 t/s, tg_3s = 42.89 t/s 3.32.298.762 I slot print_timing: id 0 | task 6271 | n_gen = 389, tg = 42.98 t/s, tg_3s = 42.84 t/s 3.35.309.682 I slot print_timing: id 0 | task 6271 | n_gen = 518, tg = 42.94 t/s, tg_3s = 42.84 t/s 3.37.224.909 I slot print_timing: id 0 | task 6271 | prompt eval time = 659.30 ms / 289 tokens ( 2.28 ms per token, 438.34 tokens per second) 3.37.224.916 I slot print_timing: id 0 | task 6271 | eval time = 13953.96 ms / 600 tokens ( 23.30 ms per token, 42.93 tokens per second) 3.37.224.916 I slot print_timing: id 0 | task 6271 | total time = 14613.27 ms / 889 tokens 3.37.224.917 I slot print_timing: id 0 | task 6271 | graphs reused = 6289 3.37.224.918 I slot print_timing: id 0 | task 6271 | graph reallocs = 0 / 0 (same size) / (changed size) 3.37.224.944 I slot release: id 0 | task 6271 | stop processing: n_tokens = 888, truncated = 0 3.37.229.382 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.183 (> 0.100 thold), f_keep = 0.050 3.37.229.467 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 66.175 MiB) 3.37.229.628 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 76.723 MiB) 3.37.239.237 I slot launch_slot_: id 0 | task 6874 | processing task, is_child = 0 3.40.778.401 I slot print_timing: id 0 | task 6874 | n_gen = 132, tg = 43.52 t/s, tg_3s = 43.86 t/s 3.43.779.883 I slot print_timing: id 0 | task 6874 | n_gen = 261, tg = 43.25 t/s, tg_3s = 42.98 t/s 3.46.797.913 I slot print_timing: id 0 | task 6874 | n_gen = 390, tg = 43.08 t/s, tg_3s = 42.74 t/s 3.48.317.141 I slot print_timing: id 0 | task 6874 | prompt eval time = 529.38 ms / 241 tokens ( 2.20 ms per token, 455.25 tokens per second) 3.48.317.144 I slot print_timing: id 0 | task 6874 | eval time = 10548.51 ms / 455 tokens ( 23.23 ms per token, 43.04 tokens per second) 3.48.317.145 I slot print_timing: id 0 | task 6874 | total time = 11077.89 ms / 696 tokens 3.48.317.145 I slot print_timing: id 0 | task 6874 | graphs reused = 6740 3.48.317.146 I slot print_timing: id 0 | task 6874 | graph reallocs = 0 / 0 (same size) / (changed size) 3.48.317.169 I slot release: id 0 | task 6874 | stop processing: n_tokens = 695, truncated = 0 3.48.321.788 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.126 (> 0.100 thold), f_keep = 0.043 3.48.321.864 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 67.265 MiB) 3.48.330.563 I slot launch_slot_: id 0 | task 7332 | processing task, is_child = 0 3.51.875.347 I slot print_timing: id 0 | task 7332 | n_gen = 132, tg = 43.45 t/s, tg_3s = 43.78 t/s 3.53.737.262 I slot print_timing: id 0 | task 7332 | prompt eval time = 529.91 ms / 239 tokens ( 2.22 ms per token, 451.02 tokens per second) 3.53.737.269 I slot print_timing: id 0 | task 7332 | eval time = 4876.77 ms / 212 tokens ( 23.11 ms per token, 43.27 tokens per second) 3.53.737.269 I slot print_timing: id 0 | task 7332 | total time = 5406.69 ms / 451 tokens 3.53.737.270 I slot print_timing: id 0 | task 7332 | graphs reused = 6949 3.53.737.271 I slot print_timing: id 0 | task 7332 | graph reallocs = 0 / 0 (same size) / (changed size) 3.53.737.293 I slot release: id 0 | task 7332 | stop processing: n_tokens = 450, truncated = 0 3.53.741.547 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.110 (> 0.100 thold), f_keep = 0.067 3.53.741.608 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 59.389 MiB) 3.53.741.612 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 57.103 MiB) 3.53.748.581 I slot launch_slot_: id 0 | task 7547 | processing task, is_child = 0 3.56.386.128 I slot print_timing: id 0 | task 7547 | prompt eval time = 645.15 ms / 273 tokens ( 2.36 ms per token, 423.16 tokens per second) 3.56.386.135 I slot print_timing: id 0 | task 7547 | eval time = 1992.38 ms / 87 tokens ( 23.17 ms per token, 43.16 tokens per second) 3.56.386.136 I slot print_timing: id 0 | task 7547 | total time = 2637.53 ms / 360 tokens 3.56.386.137 I slot print_timing: id 0 | task 7547 | graphs reused = 7034 3.56.386.138 I slot print_timing: id 0 | task 7547 | graph reallocs = 0 / 0 (same size) / (changed size) 3.56.386.161 I slot release: id 0 | task 7547 | stop processing: n_tokens = 359, truncated = 0 3.56.390.325 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.142 (> 0.100 thold), f_keep = 0.084 3.56.390.379 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 67.828 MiB) 3.56.390.382 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 73.278 MiB) 3.56.393.218 I slot launch_slot_: id 0 | task 7637 | processing task, is_child = 0 3.59.875.629 I slot print_timing: id 0 | task 7637 | n_gen = 131, tg = 43.18 t/s, tg_3s = 43.51 t/s 4.02.896.962 I slot print_timing: id 0 | task 7637 | n_gen = 261, tg = 43.10 t/s, tg_3s = 43.03 t/s 4.03.013.111 I slot print_timing: id 0 | task 7637 | prompt eval time = 471.61 ms / 212 tokens ( 2.22 ms per token, 449.53 tokens per second) 4.03.013.114 I slot print_timing: id 0 | task 7637 | eval time = 6148.27 ms / 266 tokens ( 23.20 ms per token, 43.10 tokens per second) 4.03.013.115 I slot print_timing: id 0 | task 7637 | total time = 6619.88 ms / 478 tokens 4.03.013.116 I slot print_timing: id 0 | task 7637 | graphs reused = 7297 4.03.013.116 I slot print_timing: id 0 | task 7637 | graph reallocs = 0 / 0 (same size) / (changed size) 4.03.013.144 I slot release: id 0 | task 7637 | stop processing: n_tokens = 477, truncated = 0 4.03.017.789 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.105 (> 0.100 thold), f_keep = 0.063 4.03.017.849 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 57.490 MiB) 4.03.025.095 I slot launch_slot_: id 0 | task 7906 | processing task, is_child = 0 4.06.630.109 I slot print_timing: id 0 | task 7906 | n_gen = 131, tg = 43.21 t/s, tg_3s = 43.54 t/s 4.09.637.760 I slot print_timing: id 0 | task 7906 | n_gen = 260, tg = 43.05 t/s, tg_3s = 42.89 t/s 4.11.551.271 I slot print_timing: id 0 | task 7906 | prompt eval time = 596.42 ms / 285 tokens ( 2.09 ms per token, 477.85 tokens per second) 4.11.551.274 I slot print_timing: id 0 | task 7906 | eval time = 7929.74 ms / 342 tokens ( 23.25 ms per token, 43.00 tokens per second) 4.11.551.276 I slot print_timing: id 0 | task 7906 | total time = 8526.17 ms / 627 tokens 4.11.551.277 I slot print_timing: id 0 | task 7906 | graphs reused = 7636 4.11.551.277 I slot print_timing: id 0 | task 7906 | graph reallocs = 0 / 0 (same size) / (changed size) 4.11.551.302 I slot release: id 0 | task 7906 | stop processing: n_tokens = 626, truncated = 0 4.11.555.561 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.157 (> 0.100 thold), f_keep = 0.048 4.11.555.634 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.465 MiB) 4.11.555.639 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 44.973 MiB) 4.11.563.859 I slot launch_slot_: id 0 | task 8251 | processing task, is_child = 0 4.14.927.905 I slot print_timing: id 0 | task 8251 | prompt eval time = 469.35 ms / 191 tokens ( 2.46 ms per token, 406.95 tokens per second) 4.14.927.909 I slot print_timing: id 0 | task 8251 | eval time = 2894.69 ms / 127 tokens ( 22.97 ms per token, 43.53 tokens per second) 4.14.927.909 I slot print_timing: id 0 | task 8251 | total time = 3364.03 ms / 318 tokens 4.14.927.910 I slot print_timing: id 0 | task 8251 | graphs reused = 7760 4.14.927.910 I slot print_timing: id 0 | task 8251 | graph reallocs = 0 / 0 (same size) / (changed size) 4.14.927.930 I slot release: id 0 | task 8251 | stop processing: n_tokens = 317, truncated = 0 4.14.932.090 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.095 4.14.932.141 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 52.462 MiB) 4.14.932.150 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 52.075 MiB) 4.14.937.157 I slot launch_slot_: id 0 | task 8381 | processing task, is_child = 0 4.17.135.868 I slot print_timing: id 0 | task 8381 | prompt eval time = 432.73 ms / 171 tokens ( 2.53 ms per token, 395.16 tokens per second) 4.17.135.873 I slot print_timing: id 0 | task 8381 | eval time = 1765.97 ms / 78 tokens ( 22.93 ms per token, 43.60 tokens per second) 4.17.135.873 I slot print_timing: id 0 | task 8381 | total time = 2198.70 ms / 249 tokens 4.17.135.874 I slot print_timing: id 0 | task 8381 | graphs reused = 7836 4.17.135.875 I slot print_timing: id 0 | task 8381 | graph reallocs = 0 / 0 (same size) / (changed size) 4.17.135.898 I slot release: id 0 | task 8381 | stop processing: n_tokens = 248, truncated = 0 4.17.140.488 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 4.17.140.532 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 53.306 MiB) 4.17.142.604 I slot launch_slot_: id 0 | task 8462 | processing task, is_child = 0 4.20.036.824 I slot print_timing: id 0 | task 8462 | prompt eval time = 591.95 ms / 260 tokens ( 2.28 ms per token, 439.22 tokens per second) 4.20.036.828 I slot print_timing: id 0 | task 8462 | eval time = 2302.25 ms / 101 tokens ( 23.02 ms per token, 43.44 tokens per second) 4.20.036.829 I slot print_timing: id 0 | task 8462 | total time = 2894.20 ms / 361 tokens 4.20.036.830 I slot print_timing: id 0 | task 8462 | graphs reused = 7935 4.20.036.830 I slot print_timing: id 0 | task 8462 | graph reallocs = 0 / 0 (same size) / (changed size) 4.20.036.852 I slot release: id 0 | task 8462 | stop processing: n_tokens = 360, truncated = 0 4.20.041.177 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 4.20.041.227 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 69.726 MiB) 4.20.041.234 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 116.631 MiB) 4.20.044.082 I slot launch_slot_: id 0 | task 8566 | processing task, is_child = 0 4.23.524.452 I slot print_timing: id 0 | task 8566 | n_gen = 132, tg = 43.52 t/s, tg_3s = 43.86 t/s 4.24.725.786 I slot print_timing: id 0 | task 8566 | prompt eval time = 470.59 ms / 204 tokens ( 2.31 ms per token, 433.50 tokens per second) 4.24.725.789 I slot print_timing: id 0 | task 8566 | eval time = 4211.10 ms / 184 tokens ( 23.01 ms per token, 43.46 tokens per second) 4.24.725.790 I slot print_timing: id 0 | task 8566 | total time = 4681.69 ms / 388 tokens 4.24.725.791 I slot print_timing: id 0 | task 8566 | graphs reused = 8116 4.24.725.791 I slot print_timing: id 0 | task 8566 | graph reallocs = 0 / 0 (same size) / (changed size) 4.24.725.816 I slot release: id 0 | task 8566 | stop processing: n_tokens = 387, truncated = 0 4.24.730.283 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.101 (> 0.100 thold), f_keep = 0.078 4.24.736.534 I slot launch_slot_: id 0 | task 8753 | processing task, is_child = 0 4.28.397.271 I slot print_timing: id 0 | task 8753 | n_gen = 131, tg = 43.18 t/s, tg_3s = 43.51 t/s 4.31.405.313 I slot print_timing: id 0 | task 8753 | n_gen = 260, tg = 43.03 t/s, tg_3s = 42.89 t/s 4.34.415.554 I slot print_timing: id 0 | task 8753 | n_gen = 389, tg = 42.97 t/s, tg_3s = 42.85 t/s 4.35.255.747 I slot print_timing: id 0 | task 8753 | prompt eval time = 650.14 ms / 296 tokens ( 2.20 ms per token, 455.29 tokens per second) 4.35.255.754 I slot print_timing: id 0 | task 8753 | eval time = 9869.06 ms / 425 tokens ( 23.28 ms per token, 42.96 tokens per second) 4.35.255.755 I slot print_timing: id 0 | task 8753 | total time = 10519.20 ms / 721 tokens 4.35.255.755 I slot print_timing: id 0 | task 8753 | graphs reused = 8538 4.35.255.756 I slot print_timing: id 0 | task 8753 | graph reallocs = 0 / 0 (same size) / (changed size) 4.35.255.778 I slot release: id 0 | task 8753 | stop processing: n_tokens = 720, truncated = 0 4.35.260.053 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.131 (> 0.100 thold), f_keep = 0.043 4.35.260.126 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 52.638 MiB) 4.35.260.130 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 62.905 MiB) 4.35.269.095 I slot launch_slot_: id 0 | task 9181 | processing task, is_child = 0 4.38.809.325 I slot print_timing: id 0 | task 9181 | n_gen = 132, tg = 43.47 t/s, tg_3s = 43.80 t/s 4.41.809.635 I slot print_timing: id 0 | task 9181 | n_gen = 261, tg = 43.23 t/s, tg_3s = 43.00 t/s 4.44.445.946 I slot print_timing: id 0 | task 9181 | prompt eval time = 526.68 ms / 236 tokens ( 2.23 ms per token, 448.09 tokens per second) 4.44.445.949 I slot print_timing: id 0 | task 9181 | eval time = 8650.16 ms / 374 tokens ( 23.19 ms per token, 43.12 tokens per second) 4.44.445.950 I slot print_timing: id 0 | task 9181 | total time = 9176.84 ms / 610 tokens 4.44.445.950 I slot print_timing: id 0 | task 9181 | graphs reused = 8908 4.44.445.951 I slot print_timing: id 0 | task 9181 | graph reallocs = 0 / 0 (same size) / (changed size) 4.44.445.972 I slot release: id 0 | task 9181 | stop processing: n_tokens = 609, truncated = 0 4.44.450.712 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.102 (> 0.100 thold), f_keep = 0.049 4.44.450.780 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 81.787 MiB) 4.44.450.784 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 80.978 MiB) 4.44.459.471 I slot launch_slot_: id 0 | task 9558 | processing task, is_child = 0 4.46.111.799 I slot print_timing: id 0 | task 9558 | prompt eval time = 647.55 ms / 294 tokens ( 2.20 ms per token, 454.02 tokens per second) 4.46.111.806 I slot print_timing: id 0 | task 9558 | eval time = 1004.77 ms / 44 tokens ( 23.37 ms per token, 42.80 tokens per second) 4.46.111.806 I slot print_timing: id 0 | task 9558 | total time = 1652.32 ms / 338 tokens 4.46.111.807 I slot print_timing: id 0 | task 9558 | graphs reused = 8950 4.46.111.808 I slot print_timing: id 0 | task 9558 | graph reallocs = 0 / 0 (same size) / (changed size) 4.46.111.840 I slot release: id 0 | task 9558 | stop processing: n_tokens = 337, truncated = 0 4.46.116.469 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.103 (> 0.100 thold), f_keep = 0.089 4.46.116.518 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 58.475 MiB) 4.46.122.697 I slot launch_slot_: id 0 | task 9605 | processing task, is_child = 0 4.49.766.476 I slot print_timing: id 0 | task 9605 | n_gen = 131, tg = 43.20 t/s, tg_3s = 43.54 t/s 4.52.775.019 I slot print_timing: id 0 | task 9605 | n_gen = 260, tg = 43.04 t/s, tg_3s = 42.88 t/s 4.53.335.032 I slot print_timing: id 0 | task 9605 | prompt eval time = 634.72 ms / 291 tokens ( 2.18 ms per token, 458.47 tokens per second) 4.53.335.035 I slot print_timing: id 0 | task 9605 | eval time = 6577.60 ms / 284 tokens ( 23.24 ms per token, 43.02 tokens per second) 4.53.335.036 I slot print_timing: id 0 | task 9605 | total time = 7212.33 ms / 575 tokens 4.53.335.037 I slot print_timing: id 0 | task 9605 | graphs reused = 9231 4.53.335.038 I slot print_timing: id 0 | task 9605 | graph reallocs = 0 / 0 (same size) / (changed size) 4.53.335.063 I slot release: id 0 | task 9605 | stop processing: n_tokens = 574, truncated = 0 4.53.339.391 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.105 (> 0.100 thold), f_keep = 0.052 4.53.339.467 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 60.092 MiB) 4.53.339.473 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 74.086 MiB) 4.53.347.590 I slot launch_slot_: id 0 | task 9892 | processing task, is_child = 0 4.57.002.576 I slot print_timing: id 0 | task 9892 | n_gen = 131, tg = 43.21 t/s, tg_3s = 43.54 t/s 5.00.013.171 I slot print_timing: id 0 | task 9892 | n_gen = 260, tg = 43.03 t/s, tg_3s = 42.85 t/s 5.03.022.198 I slot print_timing: id 0 | task 9892 | n_gen = 389, tg = 42.98 t/s, tg_3s = 42.87 t/s 5.06.034.689 I slot print_timing: id 0 | task 9892 | n_gen = 518, tg = 42.94 t/s, tg_3s = 42.82 t/s 5.09.049.275 I slot print_timing: id 0 | task 9892 | n_gen = 647, tg = 42.91 t/s, tg_3s = 42.79 t/s 5.12.063.283 I slot print_timing: id 0 | task 9892 | n_gen = 777, tg = 42.95 t/s, tg_3s = 43.13 t/s 5.14.385.365 I slot print_timing: id 0 | task 9892 | prompt eval time = 646.12 ms / 287 tokens ( 2.25 ms per token, 444.19 tokens per second) 5.14.385.372 I slot print_timing: id 0 | task 9892 | eval time = 20391.65 ms / 876 tokens ( 23.30 ms per token, 42.91 tokens per second) 5.14.385.373 I slot print_timing: id 0 | task 9892 | total time = 21037.77 ms / 1163 tokens 5.14.385.373 I slot print_timing: id 0 | task 9892 | graphs reused = 10102 5.14.385.374 I slot print_timing: id 0 | task 9892 | graph reallocs = 0 / 0 (same size) / (changed size) 5.14.385.405 I slot release: id 0 | task 9892 | stop processing: n_tokens = 1162, truncated = 0 5.14.389.836 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.123 (> 0.100 thold), f_keep = 0.026 5.14.389.930 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 59.495 MiB) 5.14.389.934 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.040 MiB) 5.14.400.645 I slot launch_slot_: id 0 | task 10771 | processing task, is_child = 0 5.17.941.396 I slot print_timing: id 0 | task 10771 | n_gen = 131, tg = 43.18 t/s, tg_3s = 43.51 t/s 5.20.944.337 I slot print_timing: id 0 | task 10771 | n_gen = 260, tg = 43.07 t/s, tg_3s = 42.96 t/s 5.23.955.464 I slot print_timing: id 0 | task 10771 | n_gen = 389, tg = 42.99 t/s, tg_3s = 42.84 t/s 5.26.711.910 I slot print_timing: id 0 | task 10771 | prompt eval time = 530.07 ms / 243 tokens ( 2.18 ms per token, 458.43 tokens per second) 5.26.711.914 I slot print_timing: id 0 | task 10771 | eval time = 11781.18 ms / 507 tokens ( 23.28 ms per token, 42.95 tokens per second) 5.26.711.915 I slot print_timing: id 0 | task 10771 | total time = 12311.25 ms / 750 tokens 5.26.711.916 I slot print_timing: id 0 | task 10771 | graphs reused = 10605 5.26.711.916 I slot print_timing: id 0 | task 10771 | graph reallocs = 0 / 0 (same size) / (changed size) 5.26.711.939 I slot release: id 0 | task 10771 | stop processing: n_tokens = 749, truncated = 0 5.26.716.176 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.166 (> 0.100 thold), f_keep = 0.040 5.26.716.253 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 59.635 MiB) 5.26.716.257 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 100.844 MiB) 5.26.725.029 I slot launch_slot_: id 0 | task 11281 | processing task, is_child = 0 5.28.479.849 I slot print_timing: id 0 | task 11281 | prompt eval time = 467.56 ms / 181 tokens ( 2.58 ms per token, 387.12 tokens per second) 5.28.479.853 I slot print_timing: id 0 | task 11281 | eval time = 1287.25 ms / 57 tokens ( 22.99 ms per token, 43.50 tokens per second) 5.28.479.854 I slot print_timing: id 0 | task 11281 | total time = 1754.81 ms / 238 tokens 5.28.479.854 I slot print_timing: id 0 | task 11281 | graphs reused = 10660 5.28.479.855 I slot print_timing: id 0 | task 11281 | graph reallocs = 0 / 0 (same size) / (changed size) 5.28.479.876 I slot release: id 0 | task 11281 | stop processing: n_tokens = 237, truncated = 0 5.28.484.152 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.113 (> 0.100 thold), f_keep = 0.127 5.28.486.297 I slot launch_slot_: id 0 | task 11341 | processing task, is_child = 0 5.32.088.479 I slot print_timing: id 0 | task 11341 | n_gen = 131, tg = 43.22 t/s, tg_3s = 43.55 t/s 5.35.095.835 I slot print_timing: id 0 | task 11341 | n_gen = 260, tg = 43.06 t/s, tg_3s = 42.89 t/s 5.38.105.277 I slot print_timing: id 0 | task 11341 | n_gen = 389, tg = 42.99 t/s, tg_3s = 42.87 t/s 5.41.116.917 I slot print_timing: id 0 | task 11341 | n_gen = 518, tg = 42.95 t/s, tg_3s = 42.83 t/s 5.44.131.468 I slot print_timing: id 0 | task 11341 | n_gen = 647, tg = 42.92 t/s, tg_3s = 42.79 t/s 5.47.151.943 I slot print_timing: id 0 | task 11341 | n_gen = 776, tg = 42.89 t/s, tg_3s = 42.71 t/s 5.50.153.056 I slot print_timing: id 0 | task 11341 | n_gen = 904, tg = 42.85 t/s, tg_3s = 42.65 t/s 5.52.967.265 I slot print_timing: id 0 | task 11341 | prompt eval time = 594.05 ms / 265 tokens ( 2.24 ms per token, 446.09 tokens per second) 5.52.967.268 I slot print_timing: id 0 | task 11341 | eval time = 23886.90 ms / 1024 tokens ( 23.35 ms per token, 42.83 tokens per second) 5.52.967.269 I slot print_timing: id 0 | task 11341 | total time = 24480.95 ms / 1289 tokens 5.52.967.270 I slot print_timing: id 0 | task 11341 | graphs reused = 11678 5.52.967.275 I slot print_timing: id 0 | task 11341 | graph reallocs = 0 / 0 (same size) / (changed size) 5.52.967.301 I slot release: id 0 | task 11341 | stop processing: n_tokens = 1288, truncated = 0 5.52.971.255 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.197 (> 0.100 thold), f_keep = 0.023 5.52.971.359 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 91.350 MiB) 5.52.971.363 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 57.244 MiB) 5.52.982.401 I slot launch_slot_: id 0 | task 12368 | processing task, is_child = 0 5.54.337.982 I slot print_timing: id 0 | task 12368 | prompt eval time = 413.32 ms / 152 tokens ( 2.72 ms per token, 367.75 tokens per second) 5.54.337.994 I slot print_timing: id 0 | task 12368 | eval time = 942.25 ms / 42 tokens ( 22.98 ms per token, 43.51 tokens per second) 5.54.337.995 I slot print_timing: id 0 | task 12368 | total time = 1355.57 ms / 194 tokens 5.54.337.997 I slot print_timing: id 0 | task 12368 | graphs reused = 11718 5.54.337.998 I slot print_timing: id 0 | task 12368 | graph reallocs = 0 / 0 (same size) / (changed size) 5.54.338.015 I slot release: id 0 | task 12368 | stop processing: n_tokens = 193, truncated = 0 5.54.342.082 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 5.54.342.120 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.183 MiB) 5.54.343.792 I slot launch_slot_: id 0 | task 12413 | processing task, is_child = 0 5.56.029.008 I slot print_timing: id 0 | task 12413 | prompt eval time = 468.49 ms / 190 tokens ( 2.47 ms per token, 405.56 tokens per second) 5.56.029.011 I slot print_timing: id 0 | task 12413 | eval time = 1216.72 ms / 54 tokens ( 22.96 ms per token, 43.56 tokens per second) 5.56.029.012 I slot print_timing: id 0 | task 12413 | total time = 1685.21 ms / 244 tokens 5.56.029.013 I slot print_timing: id 0 | task 12413 | graphs reused = 11770 5.56.029.013 I slot print_timing: id 0 | task 12413 | graph reallocs = 0 / 0 (same size) / (changed size) 5.56.029.036 I slot release: id 0 | task 12413 | stop processing: n_tokens = 243, truncated = 0 5.56.033.447 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 5.56.033.489 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 53.728 MiB) 5.56.035.543 I slot launch_slot_: id 0 | task 12470 | processing task, is_child = 0 5.59.644.045 I slot print_timing: id 0 | task 12470 | n_gen = 132, tg = 43.36 t/s, tg_3s = 43.69 t/s 6.02.653.234 I slot print_timing: id 0 | task 12470 | n_gen = 261, tg = 43.12 t/s, tg_3s = 42.87 t/s 6.05.663.950 I slot print_timing: id 0 | task 12470 | n_gen = 390, tg = 43.03 t/s, tg_3s = 42.85 t/s 6.06.585.745 I slot print_timing: id 0 | task 12470 | prompt eval time = 587.39 ms / 256 tokens ( 2.29 ms per token, 435.83 tokens per second) 6.06.585.751 I slot print_timing: id 0 | task 12470 | eval time = 9962.81 ms / 429 tokens ( 23.28 ms per token, 42.96 tokens per second) 6.06.585.752 I slot print_timing: id 0 | task 12470 | total time = 10550.19 ms / 685 tokens 6.06.585.753 I slot print_timing: id 0 | task 12470 | graphs reused = 12196 6.06.585.753 I slot print_timing: id 0 | task 12470 | graph reallocs = 0 / 0 (same size) / (changed size) 6.06.585.783 I slot release: id 0 | task 12470 | stop processing: n_tokens = 684, truncated = 0 6.06.590.310 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.114 (> 0.100 thold), f_keep = 0.044 6.06.590.381 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.778 MiB) 6.06.590.384 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 118.916 MiB) 6.06.599.093 I slot launch_slot_: id 0 | task 12902 | processing task, is_child = 0 6.10.187.529 I slot print_timing: id 0 | task 12902 | n_gen = 131, tg = 43.32 t/s, tg_3s = 43.65 t/s 6.13.194.230 I slot print_timing: id 0 | task 12902 | n_gen = 260, tg = 43.11 t/s, tg_3s = 42.90 t/s 6.15.783.445 I slot print_timing: id 0 | task 12902 | prompt eval time = 587.31 ms / 264 tokens ( 2.22 ms per token, 449.51 tokens per second) 6.15.783.450 I slot print_timing: id 0 | task 12902 | eval time = 8597.04 ms / 371 tokens ( 23.24 ms per token, 43.04 tokens per second) 6.15.783.451 I slot print_timing: id 0 | task 12902 | total time = 9184.34 ms / 635 tokens 6.15.783.451 I slot print_timing: id 0 | task 12902 | graphs reused = 12564 6.15.783.452 I slot print_timing: id 0 | task 12902 | graph reallocs = 0 / 0 (same size) / (changed size) 6.15.783.474 I slot release: id 0 | task 12902 | stop processing: n_tokens = 634, truncated = 0 6.15.788.012 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.104 (> 0.100 thold), f_keep = 0.047 6.15.788.081 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 138.958 MiB) 6.15.796.908 I slot launch_slot_: id 0 | task 13276 | processing task, is_child = 0 6.19.447.289 I slot print_timing: id 0 | task 13276 | n_gen = 131, tg = 43.18 t/s, tg_3s = 43.51 t/s 6.22.454.812 I slot print_timing: id 0 | task 13276 | n_gen = 260, tg = 43.03 t/s, tg_3s = 42.89 t/s 6.25.465.022 I slot print_timing: id 0 | task 13276 | n_gen = 389, tg = 42.97 t/s, tg_3s = 42.85 t/s 6.28.477.483 I slot print_timing: id 0 | task 13276 | n_gen = 518, tg = 42.94 t/s, tg_3s = 42.82 t/s 6.31.492.894 I slot print_timing: id 0 | task 13276 | n_gen = 647, tg = 42.91 t/s, tg_3s = 42.78 t/s 6.32.287.805 I slot print_timing: id 0 | task 13276 | prompt eval time = 639.46 ms / 289 tokens ( 2.21 ms per token, 451.94 tokens per second) 6.32.287.813 I slot print_timing: id 0 | task 13276 | eval time = 15851.42 ms / 681 tokens ( 23.31 ms per token, 42.90 tokens per second) 6.32.287.814 I slot print_timing: id 0 | task 13276 | total time = 16490.89 ms / 970 tokens 6.32.287.815 I slot print_timing: id 0 | task 13276 | graphs reused = 13241 6.32.287.816 I slot print_timing: id 0 | task 13276 | graph reallocs = 0 / 0 (same size) / (changed size) 6.32.287.843 I slot release: id 0 | task 13276 | stop processing: n_tokens = 969, truncated = 0 6.32.292.563 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.102 (> 0.100 thold), f_keep = 0.031 6.32.292.660 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 154.218 MiB) 6.32.302.748 I slot launch_slot_: id 0 | task 13960 | processing task, is_child = 0 6.33.637.830 I slot print_timing: id 0 | task 13960 | prompt eval time = 641.40 ms / 294 tokens ( 2.18 ms per token, 458.37 tokens per second) 6.33.637.837 I slot print_timing: id 0 | task 13960 | eval time = 693.67 ms / 31 tokens ( 23.12 ms per token, 43.25 tokens per second) 6.33.637.838 I slot print_timing: id 0 | task 13960 | total time = 1335.07 ms / 325 tokens 6.33.637.838 I slot print_timing: id 0 | task 13960 | graphs reused = 13270 6.33.637.839 I slot print_timing: id 0 | task 13960 | graph reallocs = 0 / 0 (same size) / (changed size) 6.33.637.862 I slot release: id 0 | task 13960 | stop processing: n_tokens = 324, truncated = 0 6.33.642.296 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.103 (> 0.100 thold), f_keep = 0.093 6.33.645.186 I slot launch_slot_: id 0 | task 13994 | processing task, is_child = 0 6.37.302.166 I slot print_timing: id 0 | task 13994 | n_gen = 131, tg = 43.19 t/s, tg_3s = 43.52 t/s 6.40.308.685 I slot print_timing: id 0 | task 13994 | n_gen = 260, tg = 43.05 t/s, tg_3s = 42.91 t/s 6.43.318.081 I slot print_timing: id 0 | task 13994 | n_gen = 389, tg = 42.99 t/s, tg_3s = 42.87 t/s 6.46.331.618 I slot print_timing: id 0 | task 13994 | n_gen = 518, tg = 42.94 t/s, tg_3s = 42.81 t/s 6.49.345.653 I slot print_timing: id 0 | task 13994 | n_gen = 647, tg = 42.91 t/s, tg_3s = 42.80 t/s 6.52.365.323 I slot print_timing: id 0 | task 13994 | n_gen = 776, tg = 42.88 t/s, tg_3s = 42.72 t/s 6.54.849.325 I slot print_timing: id 0 | task 13994 | prompt eval time = 647.17 ms / 292 tokens ( 2.22 ms per token, 451.20 tokens per second) 6.54.849.332 I slot print_timing: id 0 | task 13994 | eval time = 20556.97 ms / 882 tokens ( 23.33 ms per token, 42.86 tokens per second) 6.54.849.333 I slot print_timing: id 0 | task 13994 | total time = 21204.13 ms / 1174 tokens 6.54.849.333 I slot print_timing: id 0 | task 13994 | graphs reused = 14147 6.54.849.334 I slot print_timing: id 0 | task 13994 | graph reallocs = 0 / 0 (same size) / (changed size) 6.54.849.356 I slot release: id 0 | task 13994 | stop processing: n_tokens = 1173, truncated = 0 6.54.853.926 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.122 (> 0.100 thold), f_keep = 0.026 6.54.854.022 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 146.518 MiB) 6.54.864.613 I slot launch_slot_: id 0 | task 14879 | processing task, is_child = 0 6.56.509.102 I slot print_timing: id 0 | task 14879 | prompt eval time = 537.92 ms / 245 tokens ( 2.20 ms per token, 455.46 tokens per second) 6.56.509.105 I slot print_timing: id 0 | task 14879 | eval time = 1106.56 ms / 49 tokens ( 23.05 ms per token, 43.38 tokens per second) 6.56.509.106 I slot print_timing: id 0 | task 14879 | total time = 1644.48 ms / 294 tokens 6.56.509.106 I slot print_timing: id 0 | task 14879 | graphs reused = 14193 6.56.509.107 I slot print_timing: id 0 | task 14879 | graph reallocs = 0 / 0 (same size) / (changed size) 6.56.509.128 I slot release: id 0 | task 14879 | stop processing: n_tokens = 293, truncated = 0 6.56.513.039 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 6.56.513.090 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 126.301 MiB) 6.56.515.731 I slot launch_slot_: id 0 | task 14931 | processing task, is_child = 0 6.57.808.651 I slot print_timing: id 0 | task 14931 | prompt eval time = 418.87 ms / 178 tokens ( 2.35 ms per token, 424.96 tokens per second) 6.57.808.659 I slot print_timing: id 0 | task 14931 | eval time = 874.04 ms / 39 tokens ( 23.00 ms per token, 43.48 tokens per second) 6.57.808.660 I slot print_timing: id 0 | task 14931 | total time = 1292.91 ms / 217 tokens 6.57.808.660 I slot print_timing: id 0 | task 14931 | graphs reused = 14230 6.57.808.661 I slot print_timing: id 0 | task 14931 | graph reallocs = 0 / 0 (same size) / (changed size) 6.57.808.679 I slot release: id 0 | task 14931 | stop processing: n_tokens = 216, truncated = 0 6.57.813.778 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 216, t_last = 326404081015 6.57.813.819 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 155.590 MiB) 6.57.815.765 I slot launch_slot_: id 0 | task 14973 | processing task, is_child = 0 7.00.523.040 I slot print_timing: id 0 | task 14973 | prompt eval time = 772.89 ms / 355 tokens ( 2.18 ms per token, 459.31 tokens per second) 7.00.523.044 I slot print_timing: id 0 | task 14973 | eval time = 1934.37 ms / 84 tokens ( 23.31 ms per token, 42.91 tokens per second) 7.00.523.045 I slot print_timing: id 0 | task 14973 | total time = 2707.26 ms / 439 tokens 7.00.523.046 I slot print_timing: id 0 | task 14973 | graphs reused = 14312 7.00.523.046 I slot print_timing: id 0 | task 14973 | graph reallocs = 0 / 0 (same size) / (changed size) 7.00.523.075 I slot release: id 0 | task 14973 | stop processing: n_tokens = 438, truncated = 0 7.00.529.001 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 438, t_last = 326406795410 7.00.529.060 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 156.012 MiB) 7.00.532.842 I slot launch_slot_: id 0 | task 15060 | processing task, is_child = 0 7.04.739.154 I slot print_timing: id 0 | task 15060 | n_gen = 130, tg = 42.80 t/s, tg_3s = 43.13 t/s 7.07.757.436 I slot print_timing: id 0 | task 15060 | n_gen = 259, tg = 42.77 t/s, tg_3s = 42.74 t/s 7.10.770.553 I slot print_timing: id 0 | task 15060 | n_gen = 388, tg = 42.78 t/s, tg_3s = 42.81 t/s 7.13.777.961 I slot print_timing: id 0 | task 15060 | n_gen = 516, tg = 42.73 t/s, tg_3s = 42.56 t/s 7.14.855.530 I slot print_timing: id 0 | task 15060 | prompt eval time = 1192.09 ms / 567 tokens ( 2.10 ms per token, 475.64 tokens per second) 7.14.855.534 I slot print_timing: id 0 | task 15060 | eval time = 13130.58 ms / 562 tokens ( 23.41 ms per token, 42.72 tokens per second) 7.14.855.535 I slot print_timing: id 0 | task 15060 | total time = 14322.67 ms / 1129 tokens 7.14.855.536 I slot print_timing: id 0 | task 15060 | graphs reused = 14870 7.14.855.536 I slot print_timing: id 0 | task 15060 | graph reallocs = 0 / 0 (same size) / (changed size) 7.14.855.568 I slot release: id 0 | task 15060 | stop processing: n_tokens = 1128, truncated = 0 7.14.861.308 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1128, t_last = 326421127903 7.14.861.404 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.469 MiB) 7.14.873.285 I slot launch_slot_: id 0 | task 15626 | processing task, is_child = 0 7.17.892.156 I slot print_timing: id 0 | task 15626 | prompt eval time = 981.87 ms / 473 tokens ( 2.08 ms per token, 481.73 tokens per second) 7.17.892.159 I slot print_timing: id 0 | task 15626 | eval time = 2036.99 ms / 88 tokens ( 23.41 ms per token, 42.71 tokens per second) 7.17.892.160 I slot print_timing: id 0 | task 15626 | total time = 3018.86 ms / 561 tokens 7.17.892.161 I slot print_timing: id 0 | task 15626 | graphs reused = 14955 7.17.892.161 I slot print_timing: id 0 | task 15626 | graph reallocs = 0 / 0 (same size) / (changed size) 7.17.892.198 I slot release: id 0 | task 15626 | stop processing: n_tokens = 560, truncated = 0 7.17.897.450 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 326424164533 7.17.897.520 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 103.375 MiB) 7.17.906.575 I slot launch_slot_: id 0 | task 15717 | processing task, is_child = 0 7.21.733.103 I slot print_timing: id 0 | task 15717 | n_gen = 130, tg = 42.86 t/s, tg_3s = 43.19 t/s 7.24.742.063 I slot print_timing: id 0 | task 15717 | n_gen = 259, tg = 42.87 t/s, tg_3s = 42.87 t/s 7.27.753.557 I slot print_timing: id 0 | task 15717 | n_gen = 388, tg = 42.86 t/s, tg_3s = 42.84 t/s 7.30.767.398 I slot print_timing: id 0 | task 15717 | n_gen = 517, tg = 42.84 t/s, tg_3s = 42.80 t/s 7.33.782.217 I slot print_timing: id 0 | task 15717 | n_gen = 646, tg = 42.83 t/s, tg_3s = 42.79 t/s 7.36.803.942 I slot print_timing: id 0 | task 15717 | n_gen = 775, tg = 42.81 t/s, tg_3s = 42.69 t/s 7.39.827.281 I slot print_timing: id 0 | task 15717 | n_gen = 904, tg = 42.79 t/s, tg_3s = 42.67 t/s 7.40.272.548 I slot print_timing: id 0 | task 15717 | prompt eval time = 816.68 ms / 399 tokens ( 2.05 ms per token, 488.56 tokens per second) 7.40.272.552 I slot print_timing: id 0 | task 15717 | eval time = 21549.28 ms / 923 tokens ( 23.37 ms per token, 42.79 tokens per second) 7.40.272.553 I slot print_timing: id 0 | task 15717 | total time = 22365.96 ms / 1322 tokens 7.40.272.553 I slot print_timing: id 0 | task 15717 | graphs reused = 15872 7.40.272.554 I slot print_timing: id 0 | task 15717 | graph reallocs = 0 / 0 (same size) / (changed size) 7.40.272.585 I slot release: id 0 | task 15717 | stop processing: n_tokens = 1321, truncated = 0 7.40.277.587 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1321, t_last = 326446544920 7.40.277.696 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.109 MiB) 7.40.277.699 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 141.843 MiB) 7.40.288.979 I slot launch_slot_: id 0 | task 16643 | processing task, is_child = 0 7.42.516.791 I slot print_timing: id 0 | task 16643 | prompt eval time = 700.72 ms / 312 tokens ( 2.25 ms per token, 445.26 tokens per second) 7.42.516.800 I slot print_timing: id 0 | task 16643 | eval time = 1527.09 ms / 67 tokens ( 23.14 ms per token, 43.22 tokens per second) 7.42.516.801 I slot print_timing: id 0 | task 16643 | total time = 2227.80 ms / 379 tokens 7.42.516.801 I slot print_timing: id 0 | task 16643 | graphs reused = 15937 7.42.516.802 I slot print_timing: id 0 | task 16643 | graph reallocs = 0 / 0 (same size) / (changed size) 7.42.516.825 I slot release: id 0 | task 16643 | stop processing: n_tokens = 378, truncated = 0 7.42.522.788 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 378, t_last = 326448789160 7.42.522.840 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 87.201 MiB) 7.42.526.079 I slot launch_slot_: id 0 | task 16713 | processing task, is_child = 0 7.46.724.500 I slot print_timing: id 0 | task 16713 | n_gen = 130, tg = 42.80 t/s, tg_3s = 43.13 t/s 7.49.735.629 I slot print_timing: id 0 | task 16713 | n_gen = 259, tg = 42.82 t/s, tg_3s = 42.84 t/s 7.52.749.756 I slot print_timing: id 0 | task 16713 | n_gen = 388, tg = 42.81 t/s, tg_3s = 42.80 t/s 7.55.770.528 I slot print_timing: id 0 | task 16713 | n_gen = 517, tg = 42.79 t/s, tg_3s = 42.70 t/s 7.58.793.815 I slot print_timing: id 0 | task 16713 | n_gen = 646, tg = 42.76 t/s, tg_3s = 42.67 t/s 8.01.796.397 I slot print_timing: id 0 | task 16713 | n_gen = 774, tg = 42.74 t/s, tg_3s = 42.63 t/s 8.04.806.986 I slot print_timing: id 0 | task 16713 | n_gen = 902, tg = 42.71 t/s, tg_3s = 42.52 t/s 8.05.910.803 I slot print_timing: id 0 | task 16713 | prompt eval time = 1184.40 ms / 561 tokens ( 2.11 ms per token, 473.66 tokens per second) 8.05.910.810 I slot print_timing: id 0 | task 16713 | eval time = 22200.31 ms / 949 tokens ( 23.42 ms per token, 42.70 tokens per second) 8.05.910.811 I slot print_timing: id 0 | task 16713 | total time = 23384.72 ms / 1510 tokens 8.05.910.812 I slot print_timing: id 0 | task 16713 | graphs reused = 16881 8.05.910.812 I slot print_timing: id 0 | task 16713 | graph reallocs = 0 / 0 (same size) / (changed size) 8.05.910.843 I slot release: id 0 | task 16713 | stop processing: n_tokens = 1509, truncated = 0 8.05.915.905 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1509, t_last = 326472183178 8.05.916.015 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 119.022 MiB) 8.05.916.019 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 99.402 MiB) 8.05.929.959 I slot launch_slot_: id 0 | task 17666 | processing task, is_child = 0 8.08.922.210 I slot print_timing: id 0 | task 17666 | prompt eval time = 696.79 ms / 317 tokens ( 2.20 ms per token, 454.94 tokens per second) 8.08.922.216 I slot print_timing: id 0 | task 17666 | eval time = 2295.45 ms / 100 tokens ( 23.19 ms per token, 43.13 tokens per second) 8.08.922.216 I slot print_timing: id 0 | task 17666 | total time = 2992.24 ms / 417 tokens 8.08.922.217 I slot print_timing: id 0 | task 17666 | graphs reused = 16979 8.08.922.217 I slot print_timing: id 0 | task 17666 | graph reallocs = 0 / 0 (same size) / (changed size) 8.08.922.244 I slot release: id 0 | task 17666 | stop processing: n_tokens = 416, truncated = 0 8.08.927.465 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 326475194579 8.08.927.514 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 88.854 MiB) 8.08.930.857 I slot launch_slot_: id 0 | task 17769 | processing task, is_child = 0 8.12.258.153 I slot print_timing: id 0 | task 17769 | prompt eval time = 873.83 ms / 428 tokens ( 2.04 ms per token, 489.80 tokens per second) 8.12.258.156 I slot print_timing: id 0 | task 17769 | eval time = 2453.46 ms / 106 tokens ( 23.37 ms per token, 42.80 tokens per second) 8.12.258.157 I slot print_timing: id 0 | task 17769 | total time = 3327.29 ms / 534 tokens 8.12.258.158 I slot print_timing: id 0 | task 17769 | graphs reused = 17082 8.12.258.158 I slot print_timing: id 0 | task 17769 | graph reallocs = 0 / 0 (same size) / (changed size) 8.12.258.190 I slot release: id 0 | task 17769 | stop processing: n_tokens = 533, truncated = 0 8.12.262.689 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.133 (> 0.100 thold), f_keep = 0.056 8.12.262.757 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 94.304 MiB) 8.12.271.508 I slot launch_slot_: id 0 | task 17878 | processing task, is_child = 0 8.14.599.157 I slot print_timing: id 0 | task 17878 | prompt eval time = 534.50 ms / 226 tokens ( 2.37 ms per token, 422.83 tokens per second) 8.14.599.161 I slot print_timing: id 0 | task 17878 | eval time = 1793.13 ms / 79 tokens ( 22.99 ms per token, 43.50 tokens per second) 8.14.599.162 I slot print_timing: id 0 | task 17878 | total time = 2327.63 ms / 305 tokens 8.14.599.163 I slot print_timing: id 0 | task 17878 | graphs reused = 17158 8.14.599.163 I slot print_timing: id 0 | task 17878 | graph reallocs = 0 / 0 (same size) / (changed size) 8.14.599.190 I slot release: id 0 | task 17878 | stop processing: n_tokens = 304, truncated = 0 8.14.604.513 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 304, t_last = 326480871525 8.14.604.563 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 89.662 MiB) 8.14.607.236 I slot launch_slot_: id 0 | task 17960 | processing task, is_child = 0 8.17.900.602 I slot print_timing: id 0 | task 17960 | prompt eval time = 817.65 ms / 386 tokens ( 2.12 ms per token, 472.09 tokens per second) 8.17.900.606 I slot print_timing: id 0 | task 17960 | eval time = 2475.71 ms / 107 tokens ( 23.36 ms per token, 42.82 tokens per second) 8.17.900.606 I slot print_timing: id 0 | task 17960 | total time = 3293.36 ms / 493 tokens 8.17.900.607 I slot print_timing: id 0 | task 17960 | graphs reused = 17263 8.17.900.607 I slot print_timing: id 0 | task 17960 | graph reallocs = 0 / 0 (same size) / (changed size) 8.17.900.637 I slot release: id 0 | task 17960 | stop processing: n_tokens = 492, truncated = 0 8.17.906.597 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 492, t_last = 326484172972 8.17.906.661 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 153.304 MiB) 8.17.910.747 I slot launch_slot_: id 0 | task 18070 | processing task, is_child = 0 8.21.956.929 I slot print_timing: id 0 | task 18070 | n_gen = 128, tg = 42.33 t/s, tg_3s = 42.66 t/s 8.24.961.773 I slot print_timing: id 0 | task 18070 | n_gen = 255, tg = 42.30 t/s, tg_3s = 42.27 t/s 8.27.973.857 I slot print_timing: id 0 | task 18070 | n_gen = 384, tg = 42.47 t/s, tg_3s = 42.83 t/s 8.30.500.548 I slot print_timing: id 0 | task 18070 | prompt eval time = 1045.97 ms / 508 tokens ( 2.06 ms per token, 485.67 tokens per second) 8.30.500.556 I slot print_timing: id 0 | task 18070 | eval time = 11543.82 ms / 492 tokens ( 23.51 ms per token, 42.53 tokens per second) 8.30.500.557 I slot print_timing: id 0 | task 18070 | total time = 12589.79 ms / 1000 tokens 8.30.500.558 I slot print_timing: id 0 | task 18070 | graphs reused = 17751 8.30.500.558 I slot print_timing: id 0 | task 18070 | graph reallocs = 0 / 0 (same size) / (changed size) 8.30.500.592 I slot release: id 0 | task 18070 | stop processing: n_tokens = 999, truncated = 0 8.30.506.748 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 999, t_last = 326496772927 8.30.506.838 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 100.949 MiB) 8.30.506.845 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 195.006 MiB) 8.30.517.986 I slot launch_slot_: id 0 | task 18565 | processing task, is_child = 0 8.34.360.642 I slot print_timing: id 0 | task 18565 | prompt eval time = 1203.34 ms / 567 tokens ( 2.12 ms per token, 471.19 tokens per second) 8.34.360.649 I slot print_timing: id 0 | task 18565 | eval time = 2639.31 ms / 114 tokens ( 23.36 ms per token, 42.81 tokens per second) 8.34.360.649 I slot print_timing: id 0 | task 18565 | total time = 3842.65 ms / 681 tokens 8.34.360.650 I slot print_timing: id 0 | task 18565 | graphs reused = 17863 8.34.360.651 I slot print_timing: id 0 | task 18565 | graph reallocs = 0 / 0 (same size) / (changed size) 8.34.360.684 I slot release: id 0 | task 18565 | stop processing: n_tokens = 680, truncated = 0 8.34.366.002 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 680, t_last = 326500633019 8.34.366.073 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 95.288 MiB) 8.34.377.408 I slot launch_slot_: id 0 | task 18683 | processing task, is_child = 0 8.36.969.055 I slot print_timing: id 0 | task 18683 | prompt eval time = 817.45 ms / 384 tokens ( 2.13 ms per token, 469.75 tokens per second) 8.36.969.058 I slot print_timing: id 0 | task 18683 | eval time = 1774.19 ms / 77 tokens ( 23.34 ms per token, 42.84 tokens per second) 8.36.969.059 I slot print_timing: id 0 | task 18683 | total time = 2591.64 ms / 461 tokens 8.36.969.059 I slot print_timing: id 0 | task 18683 | graphs reused = 17938 8.36.969.060 I slot print_timing: id 0 | task 18683 | graph reallocs = 0 / 0 (same size) / (changed size) 8.36.969.087 I slot release: id 0 | task 18683 | stop processing: n_tokens = 460, truncated = 0 8.36.974.300 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 460, t_last = 326503241422 8.36.974.356 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 159.703 MiB) 8.36.978.196 I slot launch_slot_: id 0 | task 18763 | processing task, is_child = 0 8.38.970.798 I slot print_timing: id 0 | task 18763 | prompt eval time = 976.99 ms / 457 tokens ( 2.14 ms per token, 467.76 tokens per second) 8.38.970.802 I slot print_timing: id 0 | task 18763 | eval time = 1015.60 ms / 44 tokens ( 23.62 ms per token, 42.34 tokens per second) 8.38.970.803 I slot print_timing: id 0 | task 18763 | total time = 1992.59 ms / 501 tokens 8.38.970.803 I slot print_timing: id 0 | task 18763 | graphs reused = 17980 8.38.970.804 I slot print_timing: id 0 | task 18763 | graph reallocs = 0 / 0 (same size) / (changed size) 8.38.970.843 I slot release: id 0 | task 18763 | stop processing: n_tokens = 500, truncated = 0 8.38.976.188 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 500, t_last = 326505243178 8.38.976.254 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 184.211 MiB) 8.38.980.469 I slot launch_slot_: id 0 | task 18810 | processing task, is_child = 0 8.42.872.852 I slot print_timing: id 0 | task 18810 | n_gen = 130, tg = 42.73 t/s, tg_3s = 43.07 t/s 8.45.882.055 I slot print_timing: id 0 | task 18810 | n_gen = 259, tg = 42.80 t/s, tg_3s = 42.87 t/s 8.48.894.847 I slot print_timing: id 0 | task 18810 | n_gen = 388, tg = 42.81 t/s, tg_3s = 42.82 t/s 8.48.918.190 I slot print_timing: id 0 | task 18810 | prompt eval time = 873.72 ms / 428 tokens ( 2.04 ms per token, 489.86 tokens per second) 8.48.918.194 I slot print_timing: id 0 | task 18810 | eval time = 9064.00 ms / 389 tokens ( 23.36 ms per token, 42.81 tokens per second) 8.48.918.195 I slot print_timing: id 0 | task 18810 | total time = 9937.71 ms / 817 tokens 8.48.918.195 I slot print_timing: id 0 | task 18810 | graphs reused = 18365 8.48.918.196 I slot print_timing: id 0 | task 18810 | graph reallocs = 0 / 0 (same size) / (changed size) 8.48.918.226 I slot release: id 0 | task 18810 | stop processing: n_tokens = 816, truncated = 0 8.48.924.380 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 816, t_last = 326515190561 8.48.924.458 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.924 MiB) 8.48.935.500 I slot launch_slot_: id 0 | task 19202 | processing task, is_child = 0 8.53.132.970 I slot print_timing: id 0 | task 19202 | n_gen = 130, tg = 42.80 t/s, tg_3s = 43.13 t/s 8.56.144.106 I slot print_timing: id 0 | task 19202 | n_gen = 259, tg = 42.82 t/s, tg_3s = 42.84 t/s 8.59.156.090 I slot print_timing: id 0 | task 19202 | n_gen = 388, tg = 42.82 t/s, tg_3s = 42.83 t/s 9.02.176.456 I slot print_timing: id 0 | task 19202 | n_gen = 517, tg = 42.79 t/s, tg_3s = 42.71 t/s 9.05.198.473 I slot print_timing: id 0 | task 19202 | n_gen = 646, tg = 42.77 t/s, tg_3s = 42.69 t/s 9.08.221.349 I slot print_timing: id 0 | task 19202 | n_gen = 775, tg = 42.76 t/s, tg_3s = 42.67 t/s 9.11.224.854 I slot print_timing: id 0 | task 19202 | n_gen = 903, tg = 42.74 t/s, tg_3s = 42.62 t/s 9.14.074.803 I slot print_timing: id 0 | task 19202 | prompt eval time = 1183.13 ms / 555 tokens ( 2.13 ms per token, 469.10 tokens per second) 9.14.074.814 I slot print_timing: id 0 | task 19202 | eval time = 23956.17 ms / 1024 tokens ( 23.42 ms per token, 42.70 tokens per second) 9.14.074.814 I slot print_timing: id 0 | task 19202 | total time = 25139.29 ms / 1579 tokens 9.14.074.815 I slot print_timing: id 0 | task 19202 | graphs reused = 19383 9.14.074.816 I slot print_timing: id 0 | task 19202 | graph reallocs = 0 / 0 (same size) / (changed size) 9.14.074.861 I slot release: id 0 | task 19202 | stop processing: n_tokens = 1578, truncated = 0 9.14.081.562 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1578, t_last = 326540347197 9.14.081.673 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 146.624 MiB) 9.14.081.690 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 190.259 MiB) 9.14.094.529 I slot launch_slot_: id 0 | task 20230 | processing task, is_child = 0 9.18.416.402 I slot print_timing: id 0 | task 20230 | n_gen = 130, tg = 42.79 t/s, tg_3s = 43.13 t/s 9.21.428.835 I slot print_timing: id 0 | task 20230 | n_gen = 259, tg = 42.81 t/s, tg_3s = 42.82 t/s 9.24.446.249 I slot print_timing: id 0 | task 20230 | n_gen = 388, tg = 42.79 t/s, tg_3s = 42.75 t/s 9.25.101.179 I slot print_timing: id 0 | task 20230 | prompt eval time = 1307.40 ms / 643 tokens ( 2.03 ms per token, 491.82 tokens per second) 9.25.101.186 I slot print_timing: id 0 | task 20230 | eval time = 9699.24 ms / 416 tokens ( 23.37 ms per token, 42.79 tokens per second) 9.25.101.186 I slot print_timing: id 0 | task 20230 | total time = 11006.64 ms / 1059 tokens 9.25.101.187 I slot print_timing: id 0 | task 20230 | graphs reused = 19795 9.25.101.188 I slot print_timing: id 0 | task 20230 | graph reallocs = 0 / 0 (same size) / (changed size) 9.25.101.224 I slot release: id 0 | task 20230 | stop processing: n_tokens = 1058, truncated = 0 9.25.106.876 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1058, t_last = 326551373559 9.25.106.962 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 144.585 MiB) 9.25.118.419 I slot launch_slot_: id 0 | task 20650 | processing task, is_child = 0 9.29.057.798 I slot print_timing: id 0 | task 20650 | n_gen = 130, tg = 42.85 t/s, tg_3s = 43.18 t/s 9.32.069.341 I slot print_timing: id 0 | task 20650 | n_gen = 259, tg = 42.84 t/s, tg_3s = 42.84 t/s 9.35.081.307 I slot print_timing: id 0 | task 20650 | n_gen = 388, tg = 42.84 t/s, tg_3s = 42.83 t/s 9.38.095.093 I slot print_timing: id 0 | task 20650 | n_gen = 517, tg = 42.83 t/s, tg_3s = 42.80 t/s 9.39.194.820 I slot print_timing: id 0 | task 20650 | prompt eval time = 928.90 ms / 460 tokens ( 2.02 ms per token, 495.21 tokens per second) 9.39.194.823 I slot print_timing: id 0 | task 20650 | eval time = 13147.49 ms / 564 tokens ( 23.35 ms per token, 42.82 tokens per second) 9.39.194.824 I slot print_timing: id 0 | task 20650 | total time = 14076.39 ms / 1024 tokens 9.39.194.825 I slot print_timing: id 0 | task 20650 | graphs reused = 20355 9.39.194.826 I slot print_timing: id 0 | task 20650 | graph reallocs = 0 / 0 (same size) / (changed size) 9.39.194.857 I slot release: id 0 | task 20650 | stop processing: n_tokens = 1023, truncated = 0 9.39.200.953 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1023, t_last = 326565467192 9.39.201.044 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 130.872 MiB) 9.39.212.340 I slot launch_slot_: id 0 | task 21217 | processing task, is_child = 0 9.43.269.514 I slot print_timing: id 0 | task 21217 | n_gen = 130, tg = 42.79 t/s, tg_3s = 43.12 t/s 9.46.278.219 I slot print_timing: id 0 | task 21217 | n_gen = 259, tg = 42.83 t/s, tg_3s = 42.88 t/s 9.49.285.880 I slot print_timing: id 0 | task 21217 | n_gen = 387, tg = 42.74 t/s, tg_3s = 42.56 t/s 9.49.800.214 I slot print_timing: id 0 | task 21217 | prompt eval time = 1042.45 ms / 516 tokens ( 2.02 ms per token, 494.99 tokens per second) 9.49.800.217 I slot print_timing: id 0 | task 21217 | eval time = 9545.41 ms / 409 tokens ( 23.40 ms per token, 42.74 tokens per second) 9.49.800.218 I slot print_timing: id 0 | task 21217 | total time = 10587.87 ms / 925 tokens 9.49.800.219 I slot print_timing: id 0 | task 21217 | graphs reused = 20761 9.49.800.220 I slot print_timing: id 0 | task 21217 | graph reallocs = 0 / 0 (same size) / (changed size) 9.49.800.256 I slot release: id 0 | task 21217 | stop processing: n_tokens = 924, truncated = 0 9.49.805.585 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 924, t_last = 326576072591 9.49.805.675 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 92.475 MiB) 9.49.805.683 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.294 MiB) 9.49.818.791 I slot launch_slot_: id 0 | task 21629 | processing task, is_child = 0 9.53.294.695 I slot print_timing: id 0 | task 21629 | prompt eval time = 710.06 ms / 325 tokens ( 2.18 ms per token, 457.71 tokens per second) 9.53.294.699 I slot print_timing: id 0 | task 21629 | eval time = 2765.82 ms / 120 tokens ( 23.24 ms per token, 43.03 tokens per second) 9.53.294.700 I slot print_timing: id 0 | task 21629 | total time = 3475.88 ms / 445 tokens 9.53.294.700 I slot print_timing: id 0 | task 21629 | graphs reused = 20879 9.53.294.701 I slot print_timing: id 0 | task 21629 | graph reallocs = 0 / 0 (same size) / (changed size) 9.53.294.733 I slot release: id 0 | task 21629 | stop processing: n_tokens = 444, truncated = 0 9.53.300.171 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 444, t_last = 326579567068 9.53.300.231 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 112.306 MiB) 9.53.303.814 I slot launch_slot_: id 0 | task 21752 | processing task, is_child = 0 9.57.141.212 I slot print_timing: id 0 | task 21752 | n_gen = 130, tg = 42.70 t/s, tg_3s = 43.03 t/s 9.57.258.011 I slot print_timing: id 0 | task 21752 | prompt eval time = 816.58 ms / 393 tokens ( 2.08 ms per token, 481.28 tokens per second) 9.57.258.014 I slot print_timing: id 0 | task 21752 | eval time = 3137.61 ms / 135 tokens ( 23.42 ms per token, 42.71 tokens per second) 9.57.258.015 I slot print_timing: id 0 | task 21752 | total time = 3954.19 ms / 528 tokens 9.57.258.015 I slot print_timing: id 0 | task 21752 | graphs reused = 21011 9.57.258.016 I slot print_timing: id 0 | task 21752 | graph reallocs = 0 / 0 (same size) / (changed size) 9.57.258.047 I slot release: id 0 | task 21752 | stop processing: n_tokens = 527, truncated = 0 9.57.265.100 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 527, t_last = 326583530382 9.57.265.181 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 151.124 MiB) 9.57.273.866 I slot launch_slot_: id 0 | task 21890 | processing task, is_child = 0 10.01.719.708 I slot print_timing: id 0 | task 21890 | n_gen = 130, tg = 42.76 t/s, tg_3s = 43.09 t/s 10.04.730.138 I slot print_timing: id 0 | task 21890 | n_gen = 257, tg = 42.47 t/s, tg_3s = 42.19 t/s 10.07.748.368 I slot print_timing: id 0 | task 21890 | n_gen = 386, tg = 42.56 t/s, tg_3s = 42.74 t/s 10.10.748.585 I slot print_timing: id 0 | task 21890 | n_gen = 514, tg = 42.59 t/s, tg_3s = 42.66 t/s 10.13.750.058 I slot print_timing: id 0 | task 21890 | n_gen = 642, tg = 42.60 t/s, tg_3s = 42.65 t/s 10.13.797.050 I slot print_timing: id 0 | task 21890 | prompt eval time = 1428.89 ms / 695 tokens ( 2.06 ms per token, 486.39 tokens per second) 10.13.797.053 I slot print_timing: id 0 | task 21890 | eval time = 15094.29 ms / 644 tokens ( 23.47 ms per token, 42.60 tokens per second) 10.13.797.054 I slot print_timing: id 0 | task 21890 | total time = 16523.18 ms / 1339 tokens 10.13.797.055 I slot print_timing: id 0 | task 21890 | graphs reused = 21650 10.13.797.055 I slot print_timing: id 0 | task 21890 | graph reallocs = 0 / 0 (same size) / (changed size) 10.13.797.107 I slot release: id 0 | task 21890 | stop processing: n_tokens = 1338, truncated = 0 10.13.804.046 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1338, t_last = 326600069442 10.13.804.159 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.781 MiB) 10.13.804.163 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 187.340 MiB) 10.13.818.474 I slot launch_slot_: id 0 | task 22538 | processing task, is_child = 0 10.18.190.804 I slot print_timing: id 0 | task 22538 | n_gen = 130, tg = 42.76 t/s, tg_3s = 43.09 t/s 10.18.518.077 I slot print_timing: id 0 | task 22538 | prompt eval time = 1355.18 ms / 657 tokens ( 2.06 ms per token, 484.81 tokens per second) 10.18.518.081 I slot print_timing: id 0 | task 22538 | eval time = 3344.41 ms / 144 tokens ( 23.39 ms per token, 42.76 tokens per second) 10.18.518.082 I slot print_timing: id 0 | task 22538 | total time = 4699.59 ms / 801 tokens 10.18.518.082 I slot print_timing: id 0 | task 22538 | graphs reused = 21791 10.18.518.083 I slot print_timing: id 0 | task 22538 | graph reallocs = 0 / 0 (same size) / (changed size) 10.18.518.119 I slot release: id 0 | task 22538 | stop processing: n_tokens = 800, truncated = 0 10.18.522.631 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.130 (> 0.100 thold), f_keep = 0.038 10.18.522.712 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.882 MiB) 10.18.533.254 I slot launch_slot_: id 0 | task 22686 | processing task, is_child = 0 10.22.058.671 I slot print_timing: id 0 | task 22686 | n_gen = 132, tg = 43.49 t/s, tg_3s = 43.82 t/s 10.23.359.196 I slot print_timing: id 0 | task 22686 | prompt eval time = 513.39 ms / 231 tokens ( 2.22 ms per token, 449.95 tokens per second) 10.23.359.200 I slot print_timing: id 0 | task 22686 | eval time = 4312.54 ms / 188 tokens ( 23.06 ms per token, 43.36 tokens per second) 10.23.359.201 I slot print_timing: id 0 | task 22686 | total time = 4825.93 ms / 419 tokens 10.23.359.201 I slot print_timing: id 0 | task 22686 | graphs reused = 21976 10.23.359.202 I slot print_timing: id 0 | task 22686 | graph reallocs = 0 / 0 (same size) / (changed size) 10.23.359.229 I slot release: id 0 | task 22686 | stop processing: n_tokens = 418, truncated = 0 10.23.363.219 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.187 (> 0.100 thold), f_keep = 0.074 10.23.363.274 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 144.021 MiB) 10.23.366.405 I slot launch_slot_: id 0 | task 22877 | processing task, is_child = 0 10.26.779.361 I slot print_timing: id 0 | task 22877 | n_gen = 133, tg = 43.69 t/s, tg_3s = 44.02 t/s 10.29.795.446 I slot print_timing: id 0 | task 22877 | prompt eval time = 391.78 ms / 166 tokens ( 2.36 ms per token, 423.70 tokens per second) 10.29.795.450 I slot print_timing: id 0 | task 22877 | eval time = 6037.25 ms / 263 tokens ( 23.04 ms per token, 43.40 tokens per second) 10.29.795.450 I slot print_timing: id 0 | task 22877 | total time = 6429.03 ms / 429 tokens 10.29.795.451 I slot print_timing: id 0 | task 22877 | graphs reused = 22236 10.29.795.452 I slot print_timing: id 0 | task 22877 | graph reallocs = 0 / 0 (same size) / (changed size) 10.29.795.470 I slot release: id 0 | task 22877 | stop processing: n_tokens = 428, truncated = 0 10.29.799.679 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.160 (> 0.100 thold), f_keep = 0.072 10.29.803.642 I slot launch_slot_: id 0 | task 23143 | processing task, is_child = 0 10.33.292.156 I slot print_timing: id 0 | task 23143 | n_gen = 132, tg = 43.57 t/s, tg_3s = 43.90 t/s 10.36.308.042 I slot print_timing: id 0 | task 23143 | n_gen = 262, tg = 43.34 t/s, tg_3s = 43.11 t/s 10.39.316.532 I slot print_timing: id 0 | task 23143 | n_gen = 391, tg = 43.18 t/s, tg_3s = 42.88 t/s 10.39.876.257 I slot print_timing: id 0 | task 23143 | prompt eval time = 481.82 ms / 194 tokens ( 2.48 ms per token, 402.64 tokens per second) 10.39.876.260 I slot print_timing: id 0 | task 23143 | eval time = 9590.78 ms / 415 tokens ( 23.17 ms per token, 43.17 tokens per second) 10.39.876.261 I slot print_timing: id 0 | task 23143 | total time = 10072.61 ms / 609 tokens 10.39.876.262 I slot print_timing: id 0 | task 23143 | graphs reused = 22647 10.39.876.262 I slot print_timing: id 0 | task 23143 | graph reallocs = 0 / 0 (same size) / (changed size) 10.39.876.293 I slot release: id 0 | task 23143 | stop processing: n_tokens = 608, truncated = 0 10.39.880.533 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.208 (> 0.100 thold), f_keep = 0.051 10.39.880.603 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 136.004 MiB) 10.39.890.256 I slot launch_slot_: id 0 | task 23561 | processing task, is_child = 0 10.43.025.461 I slot print_timing: id 0 | task 23561 | prompt eval time = 389.46 ms / 149 tokens ( 2.61 ms per token, 382.58 tokens per second) 10.43.025.468 I slot print_timing: id 0 | task 23561 | eval time = 2745.73 ms / 121 tokens ( 22.88 ms per token, 43.70 tokens per second) 10.43.025.468 I slot print_timing: id 0 | task 23561 | total time = 3135.19 ms / 270 tokens 10.43.025.469 I slot print_timing: id 0 | task 23561 | graphs reused = 22765 10.43.025.470 I slot print_timing: id 0 | task 23561 | graph reallocs = 0 / 0 (same size) / (changed size) 10.43.025.487 I slot release: id 0 | task 23561 | stop processing: n_tokens = 269, truncated = 0 10.43.029.681 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.137 (> 0.100 thold), f_keep = 0.112 10.43.029.726 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 172.220 MiB) 10.43.033.781 I slot launch_slot_: id 0 | task 23685 | processing task, is_child = 0 10.46.576.514 I slot print_timing: id 0 | task 23685 | n_gen = 132, tg = 43.53 t/s, tg_3s = 43.86 t/s 10.49.595.144 I slot print_timing: id 0 | task 23685 | n_gen = 262, tg = 43.30 t/s, tg_3s = 43.07 t/s 10.51.833.031 I slot print_timing: id 0 | task 23685 | prompt eval time = 533.37 ms / 219 tokens ( 2.44 ms per token, 410.60 tokens per second) 10.51.833.035 I slot print_timing: id 0 | task 23685 | eval time = 8265.87 ms / 358 tokens ( 23.15 ms per token, 43.19 tokens per second) 10.51.833.036 I slot print_timing: id 0 | task 23685 | total time = 8799.24 ms / 577 tokens 10.51.833.036 I slot print_timing: id 0 | task 23685 | graphs reused = 23119 10.51.833.037 I slot print_timing: id 0 | task 23685 | graph reallocs = 0 / 0 (same size) / (changed size) 10.51.833.057 I slot release: id 0 | task 23685 | stop processing: n_tokens = 576, truncated = 0 10.51.837.024 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.227 (> 0.100 thold), f_keep = 0.052 10.51.841.838 I slot launch_slot_: id 0 | task 24046 | processing task, is_child = 0 10.52.482.618 I slot print_timing: id 0 | task 24046 | prompt eval time = 339.14 ms / 132 tokens ( 2.57 ms per token, 389.22 tokens per second) 10.52.482.622 I slot print_timing: id 0 | task 24046 | eval time = 301.63 ms / 14 tokens ( 23.20 ms per token, 43.10 tokens per second) 10.52.482.622 I slot print_timing: id 0 | task 24046 | total time = 640.77 ms / 146 tokens 10.52.482.623 I slot print_timing: id 0 | task 24046 | graphs reused = 23131 10.52.482.624 I slot print_timing: id 0 | task 24046 | graph reallocs = 0 / 0 (same size) / (changed size) 10.52.482.641 I slot release: id 0 | task 24046 | stop processing: n_tokens = 145, truncated = 0 10.52.486.682 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 10.52.489.913 I slot launch_slot_: id 0 | task 24063 | processing task, is_child = 0 10.53.446.673 I slot print_timing: id 0 | task 24063 | prompt eval time = 392.48 ms / 169 tokens ( 2.32 ms per token, 430.59 tokens per second) 10.53.446.679 I slot print_timing: id 0 | task 24063 | eval time = 564.27 ms / 25 tokens ( 23.51 ms per token, 42.53 tokens per second) 10.53.446.680 I slot print_timing: id 0 | task 24063 | total time = 956.75 ms / 194 tokens 10.53.446.680 I slot print_timing: id 0 | task 24063 | graphs reused = 23154 10.53.446.681 I slot print_timing: id 0 | task 24063 | graph reallocs = 0 / 0 (same size) / (changed size) 10.53.446.701 I slot release: id 0 | task 24063 | stop processing: n_tokens = 193, truncated = 0 10.53.450.613 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 10.53.450.654 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 189.169 MiB) 10.53.454.793 I slot launch_slot_: id 0 | task 24091 | processing task, is_child = 0 10.56.858.992 I slot print_timing: id 0 | task 24091 | n_gen = 132, tg = 43.52 t/s, tg_3s = 43.86 t/s 10.59.872.592 I slot print_timing: id 0 | task 24091 | n_gen = 261, tg = 43.16 t/s, tg_3s = 42.81 t/s 11.00.105.260 I slot print_timing: id 0 | task 24091 | prompt eval time = 394.33 ms / 160 tokens ( 2.46 ms per token, 405.76 tokens per second) 11.00.105.263 I slot print_timing: id 0 | task 24091 | eval time = 6256.13 ms / 271 tokens ( 23.17 ms per token, 43.16 tokens per second) 11.00.105.264 I slot print_timing: id 0 | task 24091 | total time = 6650.46 ms / 431 tokens 11.00.105.268 I slot print_timing: id 0 | task 24091 | graphs reused = 23422 11.00.105.270 I slot print_timing: id 0 | task 24091 | graph reallocs = 0 / 0 (same size) / (changed size) 11.00.105.293 I slot release: id 0 | task 24091 | stop processing: n_tokens = 430, truncated = 0 11.00.109.045 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.291 (> 0.100 thold), f_keep = 0.070 11.00.113.137 I slot launch_slot_: id 0 | task 24365 | processing task, is_child = 0 11.03.009.744 I slot print_timing: id 0 | task 24365 | prompt eval time = 288.45 ms / 103 tokens ( 2.80 ms per token, 357.08 tokens per second) 11.03.009.747 I slot print_timing: id 0 | task 24365 | eval time = 2608.15 ms / 115 tokens ( 22.88 ms per token, 43.71 tokens per second) 11.03.009.748 I slot print_timing: id 0 | task 24365 | total time = 2896.60 ms / 218 tokens 11.03.009.749 I slot print_timing: id 0 | task 24365 | graphs reused = 23535 11.03.009.749 I slot print_timing: id 0 | task 24365 | graph reallocs = 0 / 0 (same size) / (changed size) 11.03.009.765 I slot release: id 0 | task 24365 | stop processing: n_tokens = 217, truncated = 0 11.03.013.818 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.138 11.03.013.859 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 68.461 MiB) 11.03.016.329 I slot launch_slot_: id 0 | task 24483 | processing task, is_child = 0 11.04.970.817 I slot print_timing: id 0 | task 24483 | prompt eval time = 418.79 ms / 165 tokens ( 2.54 ms per token, 393.99 tokens per second) 11.04.970.820 I slot print_timing: id 0 | task 24483 | eval time = 1535.69 ms / 68 tokens ( 22.92 ms per token, 43.63 tokens per second) 11.04.970.821 I slot print_timing: id 0 | task 24483 | total time = 1954.48 ms / 233 tokens 11.04.970.822 I slot print_timing: id 0 | task 24483 | graphs reused = 23601 11.04.970.822 I slot print_timing: id 0 | task 24483 | graph reallocs = 0 / 0 (same size) / (changed size) 11.04.970.841 I slot release: id 0 | task 24483 | stop processing: n_tokens = 232, truncated = 0 11.04.974.692 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.129 11.04.974.734 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 74.086 MiB) 11.04.976.625 I slot launch_slot_: id 0 | task 24554 | processing task, is_child = 0 11.08.386.057 I slot print_timing: id 0 | task 24554 | n_gen = 132, tg = 43.50 t/s, tg_3s = 43.83 t/s 11.10.681.523 I slot print_timing: id 0 | task 24554 | prompt eval time = 397.89 ms / 165 tokens ( 2.41 ms per token, 414.68 tokens per second) 11.10.681.527 I slot print_timing: id 0 | task 24554 | eval time = 5307.00 ms / 231 tokens ( 23.07 ms per token, 43.34 tokens per second) 11.10.681.528 I slot print_timing: id 0 | task 24554 | total time = 5704.89 ms / 396 tokens 11.10.681.528 I slot print_timing: id 0 | task 24554 | graphs reused = 23829 11.10.681.529 I slot print_timing: id 0 | task 24554 | graph reallocs = 0 / 0 (same size) / (changed size) 11.10.681.561 I slot release: id 0 | task 24554 | stop processing: n_tokens = 395, truncated = 0 11.10.685.611 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.162 (> 0.100 thold), f_keep = 0.076 11.10.685.700 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.954 MiB) 11.10.688.387 I slot launch_slot_: id 0 | task 24788 | processing task, is_child = 0 11.12.021.543 I slot print_timing: id 0 | task 24788 | prompt eval time = 482.64 ms / 185 tokens ( 2.61 ms per token, 383.31 tokens per second) 11.12.021.547 I slot print_timing: id 0 | task 24788 | eval time = 850.50 ms / 38 tokens ( 22.99 ms per token, 43.50 tokens per second) 11.12.021.548 I slot print_timing: id 0 | task 24788 | total time = 1333.14 ms / 223 tokens 11.12.021.548 I slot print_timing: id 0 | task 24788 | graphs reused = 23865 11.12.021.549 I slot print_timing: id 0 | task 24788 | graph reallocs = 0 / 0 (same size) / (changed size) 11.12.021.573 I slot release: id 0 | task 24788 | stop processing: n_tokens = 222, truncated = 0 11.12.025.603 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.135 11.12.025.647 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 64.452 MiB) 11.12.028.926 I slot launch_slot_: id 0 | task 24829 | processing task, is_child = 0 11.15.423.911 I slot print_timing: id 0 | task 24829 | n_gen = 132, tg = 43.63 t/s, tg_3s = 43.97 t/s 11.16.964.598 I slot print_timing: id 0 | task 24829 | prompt eval time = 392.59 ms / 160 tokens ( 2.45 ms per token, 407.55 tokens per second) 11.16.964.608 I slot print_timing: id 0 | task 24829 | eval time = 4543.07 ms / 199 tokens ( 22.94 ms per token, 43.58 tokens per second) 11.16.964.608 I slot print_timing: id 0 | task 24829 | total time = 4935.66 ms / 359 tokens 11.16.964.609 I slot print_timing: id 0 | task 24829 | graphs reused = 24061 11.16.964.610 I slot print_timing: id 0 | task 24829 | graph reallocs = 0 / 0 (same size) / (changed size) 11.16.964.629 I slot release: id 0 | task 24829 | stop processing: n_tokens = 358, truncated = 0 11.16.968.658 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.191 (> 0.100 thold), f_keep = 0.084 11.16.968.712 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 83.650 MiB) 11.16.971.208 I slot launch_slot_: id 0 | task 25031 | processing task, is_child = 0 11.20.376.550 I slot print_timing: id 0 | task 25031 | n_gen = 132, tg = 43.50 t/s, tg_3s = 43.83 t/s 11.23.408.808 I slot print_timing: id 0 | task 25031 | n_gen = 260, tg = 42.86 t/s, tg_3s = 42.21 t/s 11.26.415.068 I slot print_timing: id 0 | task 25031 | n_gen = 385, tg = 42.43 t/s, tg_3s = 41.58 t/s 11.28.345.418 I slot print_timing: id 0 | task 25031 | prompt eval time = 394.00 ms / 157 tokens ( 2.51 ms per token, 398.48 tokens per second) 11.28.345.422 I slot print_timing: id 0 | task 25031 | eval time = 10980.20 ms / 467 tokens ( 23.56 ms per token, 42.44 tokens per second) 11.28.345.423 I slot print_timing: id 0 | task 25031 | total time = 11374.20 ms / 624 tokens 11.28.345.424 I slot print_timing: id 0 | task 25031 | graphs reused = 24524 11.28.345.424 I slot print_timing: id 0 | task 25031 | graph reallocs = 0 / 0 (same size) / (changed size) 11.28.345.444 I slot release: id 0 | task 25031 | stop processing: n_tokens = 623, truncated = 0 11.28.349.617 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.048 11.28.349.692 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 96.414 MiB) 11.28.352.997 I slot launch_slot_: id 0 | task 25501 | processing task, is_child = 0 11.31.768.367 I slot print_timing: id 0 | task 25501 | n_gen = 130, tg = 42.71 t/s, tg_3s = 43.05 t/s 11.34.768.640 I slot print_timing: id 0 | task 25501 | n_gen = 256, tg = 42.36 t/s, tg_3s = 42.00 t/s 11.36.202.292 I slot print_timing: id 0 | task 25501 | prompt eval time = 395.31 ms / 171 tokens ( 2.31 ms per token, 432.57 tokens per second) 11.36.202.295 I slot print_timing: id 0 | task 25501 | eval time = 7453.97 ms / 317 tokens ( 23.59 ms per token, 42.39 tokens per second) 11.36.202.295 I slot print_timing: id 0 | task 25501 | total time = 7849.28 ms / 488 tokens 11.36.202.296 I slot print_timing: id 0 | task 25501 | graphs reused = 24838 11.36.202.296 I slot print_timing: id 0 | task 25501 | graph reallocs = 0 / 0 (same size) / (changed size) 11.36.202.314 I slot release: id 0 | task 25501 | stop processing: n_tokens = 487, truncated = 0 11.36.205.622 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.164 (> 0.100 thold), f_keep = 0.062 11.36.205.668 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 121.238 MiB) 11.36.209.624 I slot launch_slot_: id 0 | task 25821 | processing task, is_child = 0 11.39.706.595 I slot print_timing: id 0 | task 25821 | n_gen = 131, tg = 43.14 t/s, tg_3s = 43.47 t/s 11.42.722.897 I slot print_timing: id 0 | task 25821 | n_gen = 259, tg = 42.79 t/s, tg_3s = 42.44 t/s 11.45.724.586 I slot print_timing: id 0 | task 25821 | n_gen = 382, tg = 42.19 t/s, tg_3s = 40.98 t/s 11.48.725.026 I slot print_timing: id 0 | task 25821 | n_gen = 507, tg = 42.06 t/s, tg_3s = 41.66 t/s 11.50.915.849 I slot print_timing: id 0 | task 25821 | prompt eval time = 483.55 ms / 183 tokens ( 2.64 ms per token, 378.45 tokens per second) 11.50.915.852 I slot print_timing: id 0 | task 25821 | eval time = 14222.67 ms / 601 tokens ( 23.70 ms per token, 42.19 tokens per second) 11.50.915.853 I slot print_timing: id 0 | task 25821 | total time = 14706.22 ms / 784 tokens 11.50.915.853 I slot print_timing: id 0 | task 25821 | graphs reused = 25434 11.50.915.854 I slot print_timing: id 0 | task 25821 | graph reallocs = 0 / 0 (same size) / (changed size) 11.50.915.882 I slot release: id 0 | task 25821 | stop processing: n_tokens = 783, truncated = 0 11.50.920.118 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.184 (> 0.100 thold), f_keep = 0.038 11.50.920.197 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 69.199 MiB) 11.50.928.960 I slot launch_slot_: id 0 | task 26425 | processing task, is_child = 0 11.54.343.761 I slot print_timing: id 0 | task 26425 | n_gen = 132, tg = 43.57 t/s, tg_3s = 43.90 t/s 11.57.366.609 I slot print_timing: id 0 | task 26425 | n_gen = 263, tg = 43.45 t/s, tg_3s = 43.34 t/s 12.00.373.256 I slot print_timing: id 0 | task 26425 | n_gen = 391, tg = 43.16 t/s, tg_3s = 42.57 t/s 12.03.378.516 I slot print_timing: id 0 | task 26425 | n_gen = 520, tg = 43.10 t/s, tg_3s = 42.92 t/s 12.06.384.833 I slot print_timing: id 0 | task 26425 | n_gen = 649, tg = 43.06 t/s, tg_3s = 42.91 t/s 12.08.389.288 I slot print_timing: id 0 | task 26425 | prompt eval time = 407.96 ms / 163 tokens ( 2.50 ms per token, 399.55 tokens per second) 12.08.389.292 I slot print_timing: id 0 | task 26425 | eval time = 17052.35 ms / 735 tokens ( 23.23 ms per token, 43.04 tokens per second) 12.08.389.293 I slot print_timing: id 0 | task 26425 | total time = 17460.32 ms / 898 tokens 12.08.389.293 I slot print_timing: id 0 | task 26425 | graphs reused = 26164 12.08.389.294 I slot print_timing: id 0 | task 26425 | graph reallocs = 0 / 0 (same size) / (changed size) 12.08.389.315 I slot release: id 0 | task 26425 | stop processing: n_tokens = 897, truncated = 0 12.08.393.668 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.169 (> 0.100 thold), f_keep = 0.033 12.08.393.749 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 59.354 MiB) 12.08.393.753 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 111.604 MiB) 12.08.403.310 I slot launch_slot_: id 0 | task 27163 | processing task, is_child = 0 12.09.375.051 I slot print_timing: id 0 | task 27163 | prompt eval time = 409.34 ms / 177 tokens ( 2.31 ms per token, 432.41 tokens per second) 12.09.375.054 I slot print_timing: id 0 | task 27163 | eval time = 562.39 ms / 25 tokens ( 23.43 ms per token, 42.68 tokens per second) 12.09.375.054 I slot print_timing: id 0 | task 27163 | total time = 971.73 ms / 202 tokens 12.09.375.055 I slot print_timing: id 0 | task 27163 | graphs reused = 26187 12.09.375.056 I slot print_timing: id 0 | task 27163 | graph reallocs = 0 / 0 (same size) / (changed size) 12.09.375.075 I slot release: id 0 | task 27163 | stop processing: n_tokens = 201, truncated = 0 12.09.379.030 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.196 (> 0.100 thold), f_keep = 0.149 12.09.382.289 I slot launch_slot_: id 0 | task 27191 | processing task, is_child = 0 12.12.805.374 I slot print_timing: id 0 | task 27191 | n_gen = 133, tg = 43.71 t/s, tg_3s = 44.04 t/s 12.14.154.139 I slot print_timing: id 0 | task 27191 | prompt eval time = 403.13 ms / 153 tokens ( 2.63 ms per token, 379.53 tokens per second) 12.14.154.143 I slot print_timing: id 0 | task 27191 | eval time = 4368.71 ms / 192 tokens ( 22.87 ms per token, 43.72 tokens per second) 12.14.154.143 I slot print_timing: id 0 | task 27191 | total time = 4771.84 ms / 345 tokens 12.14.154.144 I slot print_timing: id 0 | task 27191 | graphs reused = 26376 12.14.154.144 I slot print_timing: id 0 | task 27191 | graph reallocs = 0 / 0 (same size) / (changed size) 12.14.154.164 I slot release: id 0 | task 27191 | stop processing: n_tokens = 344, truncated = 0 12.14.158.096 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.217 (> 0.100 thold), f_keep = 0.087 12.14.158.146 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 134.391 MiB) 12.14.160.541 I slot launch_slot_: id 0 | task 27386 | processing task, is_child = 0 12.15.193.539 I slot print_timing: id 0 | task 27386 | prompt eval time = 344.63 ms / 138 tokens ( 2.50 ms per token, 400.43 tokens per second) 12.15.193.547 I slot print_timing: id 0 | task 27386 | eval time = 688.36 ms / 31 tokens ( 22.95 ms per token, 43.58 tokens per second) 12.15.193.548 I slot print_timing: id 0 | task 27386 | total time = 1032.99 ms / 169 tokens 12.15.193.549 I slot print_timing: id 0 | task 27386 | graphs reused = 26405 12.15.193.549 I slot print_timing: id 0 | task 27386 | graph reallocs = 0 / 0 (same size) / (changed size) 12.15.193.574 I slot release: id 0 | task 27386 | stop processing: n_tokens = 168, truncated = 0 12.15.197.540 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 12.15.199.076 I slot launch_slot_: id 0 | task 27420 | processing task, is_child = 0 12.18.621.255 I slot print_timing: id 0 | task 27420 | n_gen = 132, tg = 43.47 t/s, tg_3s = 43.80 t/s 12.21.624.841 I slot print_timing: id 0 | task 27420 | n_gen = 262, tg = 43.37 t/s, tg_3s = 43.28 t/s 12.24.640.111 I slot print_timing: id 0 | task 27420 | n_gen = 391, tg = 43.18 t/s, tg_3s = 42.78 t/s 12.25.805.704 I slot print_timing: id 0 | task 27420 | prompt eval time = 408.43 ms / 179 tokens ( 2.28 ms per token, 438.26 tokens per second) 12.25.805.711 I slot print_timing: id 0 | task 27420 | eval time = 10198.18 ms / 441 tokens ( 23.18 ms per token, 43.14 tokens per second) 12.25.805.712 I slot print_timing: id 0 | task 27420 | total time = 10606.61 ms / 620 tokens 12.25.805.712 I slot print_timing: id 0 | task 27420 | graphs reused = 26842 12.25.805.713 I slot print_timing: id 0 | task 27420 | graph reallocs = 0 / 0 (same size) / (changed size) 12.25.805.733 I slot release: id 0 | task 27420 | stop processing: n_tokens = 619, truncated = 0 12.25.810.067 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.169 (> 0.100 thold), f_keep = 0.055 12.25.810.136 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 118.743 MiB) 12.25.814.747 I slot launch_slot_: id 0 | task 27864 | processing task, is_child = 0 12.29.285.565 I slot print_timing: id 0 | task 27864 | n_gen = 130, tg = 42.95 t/s, tg_3s = 43.29 t/s 12.30.056.083 I slot print_timing: id 0 | task 27864 | prompt eval time = 467.63 ms / 201 tokens ( 2.33 ms per token, 429.83 tokens per second) 12.30.056.086 I slot print_timing: id 0 | task 27864 | eval time = 3773.70 ms / 162 tokens ( 23.44 ms per token, 42.66 tokens per second) 12.30.056.091 I slot print_timing: id 0 | task 27864 | total time = 4241.33 ms / 363 tokens 12.30.056.092 I slot print_timing: id 0 | task 27864 | graphs reused = 27001 12.30.056.093 I slot print_timing: id 0 | task 27864 | graph reallocs = 0 / 0 (same size) / (changed size) 12.30.056.114 I slot release: id 0 | task 27864 | stop processing: n_tokens = 362, truncated = 0 12.30.059.953 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.224 (> 0.100 thold), f_keep = 0.083 12.30.060.009 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.326 MiB) 12.30.064.170 I slot launch_slot_: id 0 | task 28029 | processing task, is_child = 0 12.33.442.945 I slot print_timing: id 0 | task 28029 | n_gen = 131, tg = 42.98 t/s, tg_3s = 43.31 t/s 12.36.463.970 I slot print_timing: id 0 | task 28029 | n_gen = 261, tg = 43.00 t/s, tg_3s = 43.03 t/s 12.36.579.809 I slot print_timing: id 0 | task 28029 | prompt eval time = 353.87 ms / 134 tokens ( 2.64 ms per token, 378.67 tokens per second) 12.36.579.811 I slot print_timing: id 0 | task 28029 | eval time = 6161.76 ms / 266 tokens ( 23.25 ms per token, 43.01 tokens per second) 12.36.579.812 I slot print_timing: id 0 | task 28029 | total time = 6515.63 ms / 400 tokens 12.36.579.813 I slot print_timing: id 0 | task 28029 | graphs reused = 27264 12.36.579.813 I slot print_timing: id 0 | task 28029 | graph reallocs = 0 / 0 (same size) / (changed size) 12.36.579.835 I slot release: id 0 | task 28029 | stop processing: n_tokens = 399, truncated = 0 12.36.583.744 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.205 (> 0.100 thold), f_keep = 0.075 12.36.583.801 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 96.062 MiB) 12.36.586.394 I slot launch_slot_: id 0 | task 28298 | processing task, is_child = 0 12.38.020.070 I slot print_timing: id 0 | task 28298 | prompt eval time = 389.73 ms / 146 tokens ( 2.67 ms per token, 374.62 tokens per second) 12.38.020.076 I slot print_timing: id 0 | task 28298 | eval time = 1043.94 ms / 45 tokens ( 23.73 ms per token, 42.15 tokens per second) 12.38.020.077 I slot print_timing: id 0 | task 28298 | total time = 1433.66 ms / 191 tokens 12.38.020.078 I slot print_timing: id 0 | task 28298 | graphs reused = 27307 12.38.020.078 I slot print_timing: id 0 | task 28298 | graph reallocs = 0 / 0 (same size) / (changed size) 12.38.020.096 I slot release: id 0 | task 28298 | stop processing: n_tokens = 190, truncated = 0 12.38.023.771 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.217 (> 0.100 thold), f_keep = 0.158 12.38.023.810 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.537 MiB) 12.38.025.470 I slot launch_slot_: id 0 | task 28346 | processing task, is_child = 0 12.39.492.898 I slot print_timing: id 0 | task 28346 | prompt eval time = 339.92 ms / 138 tokens ( 2.46 ms per token, 405.97 tokens per second) 12.39.492.902 I slot print_timing: id 0 | task 28346 | eval time = 1127.49 ms / 50 tokens ( 23.01 ms per token, 43.46 tokens per second) 12.39.492.902 I slot print_timing: id 0 | task 28346 | total time = 1467.42 ms / 188 tokens 12.39.492.903 I slot print_timing: id 0 | task 28346 | graphs reused = 27355 12.39.492.903 I slot print_timing: id 0 | task 28346 | graph reallocs = 0 / 0 (same size) / (changed size) 12.39.492.924 I slot release: id 0 | task 28346 | stop processing: n_tokens = 187, truncated = 0 12.39.496.871 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.160 12.39.498.524 I slot launch_slot_: id 0 | task 28399 | processing task, is_child = 0 12.42.894.586 I slot print_timing: id 0 | task 28399 | n_gen = 132, tg = 43.63 t/s, tg_3s = 43.96 t/s 12.45.898.212 I slot print_timing: id 0 | task 28399 | n_gen = 262, tg = 43.45 t/s, tg_3s = 43.28 t/s 12.48.907.161 I slot print_timing: id 0 | task 28399 | n_gen = 391, tg = 43.26 t/s, tg_3s = 42.87 t/s 12.51.812.942 I slot print_timing: id 0 | task 28399 | prompt eval time = 393.33 ms / 155 tokens ( 2.54 ms per token, 394.07 tokens per second) 12.51.812.945 I slot print_timing: id 0 | task 28399 | eval time = 11921.07 ms / 512 tokens ( 23.33 ms per token, 42.87 tokens per second) 12.51.812.946 I slot print_timing: id 0 | task 28399 | total time = 12314.40 ms / 667 tokens 12.51.812.947 I slot print_timing: id 0 | task 28399 | graphs reused = 27863 12.51.812.947 I slot print_timing: id 0 | task 28399 | graph reallocs = 0 / 0 (same size) / (changed size) 12.51.812.968 I slot release: id 0 | task 28399 | stop processing: n_tokens = 666, truncated = 0 12.51.816.895 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.045 12.51.816.965 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 122.540 MiB) 12.51.820.255 I slot launch_slot_: id 0 | task 28914 | processing task, is_child = 0 12.53.882.740 I slot print_timing: id 0 | task 28914 | prompt eval time = 394.67 ms / 160 tokens ( 2.47 ms per token, 405.40 tokens per second) 12.53.882.743 I slot print_timing: id 0 | task 28914 | eval time = 1667.80 ms / 73 tokens ( 23.16 ms per token, 43.17 tokens per second) 12.53.882.744 I slot print_timing: id 0 | task 28914 | total time = 2062.47 ms / 233 tokens 12.53.882.744 I slot print_timing: id 0 | task 28914 | graphs reused = 27934 12.53.882.745 I slot print_timing: id 0 | task 28914 | graph reallocs = 0 / 0 (same size) / (changed size) 12.53.882.764 I slot release: id 0 | task 28914 | stop processing: n_tokens = 232, truncated = 0 12.53.886.421 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.192 (> 0.100 thold), f_keep = 0.129 12.53.886.460 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 79.291 MiB) 12.53.888.367 I slot launch_slot_: id 0 | task 28990 | processing task, is_child = 0 12.54.863.745 I slot print_timing: id 0 | task 28990 | prompt eval time = 401.65 ms / 156 tokens ( 2.57 ms per token, 388.39 tokens per second) 12.54.863.750 I slot print_timing: id 0 | task 28990 | eval time = 573.71 ms / 26 tokens ( 22.95 ms per token, 43.58 tokens per second) 12.54.863.751 I slot print_timing: id 0 | task 28990 | total time = 975.36 ms / 182 tokens 12.54.863.751 I slot print_timing: id 0 | task 28990 | graphs reused = 27958 12.54.863.752 I slot print_timing: id 0 | task 28990 | graph reallocs = 0 / 0 (same size) / (changed size) 12.54.863.771 I slot release: id 0 | task 28990 | stop processing: n_tokens = 181, truncated = 0 12.54.867.552 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.190 (> 0.100 thold), f_keep = 0.166 12.54.869.239 I slot launch_slot_: id 0 | task 29019 | processing task, is_child = 0 12.58.276.079 I slot print_timing: id 0 | task 29019 | n_gen = 132, tg = 43.43 t/s, tg_3s = 43.76 t/s 13.01.287.183 I slot print_timing: id 0 | task 29019 | n_gen = 261, tg = 43.13 t/s, tg_3s = 42.84 t/s 13.04.306.678 I slot print_timing: id 0 | task 29019 | n_gen = 390, tg = 43.00 t/s, tg_3s = 42.72 t/s 13.07.318.355 I slot print_timing: id 0 | task 29019 | n_gen = 519, tg = 42.96 t/s, tg_3s = 42.83 t/s 13.10.335.745 I slot print_timing: id 0 | task 29019 | n_gen = 647, tg = 42.85 t/s, tg_3s = 42.42 t/s 13.13.357.973 I slot print_timing: id 0 | task 29019 | n_gen = 774, tg = 42.71 t/s, tg_3s = 42.02 t/s 13.16.372.531 I slot print_timing: id 0 | task 29019 | n_gen = 903, tg = 42.72 t/s, tg_3s = 42.79 t/s 13.16.606.277 I slot print_timing: id 0 | task 29019 | prompt eval time = 390.19 ms / 158 tokens ( 2.47 ms per token, 404.94 tokens per second) 13.16.606.283 I slot print_timing: id 0 | task 29019 | eval time = 21346.84 ms / 913 tokens ( 23.41 ms per token, 42.72 tokens per second) 13.16.606.284 I slot print_timing: id 0 | task 29019 | total time = 21737.03 ms / 1071 tokens 13.16.606.284 I slot print_timing: id 0 | task 29019 | graphs reused = 28865 13.16.606.285 I slot print_timing: id 0 | task 29019 | graph reallocs = 0 / 0 (same size) / (changed size) 13.16.606.303 I slot release: id 0 | task 29019 | stop processing: n_tokens = 1070, truncated = 0 13.16.610.450 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.028 13.16.610.544 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 67.160 MiB) 13.16.610.549 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 97.047 MiB) 13.16.621.849 I slot launch_slot_: id 0 | task 29935 | processing task, is_child = 0 13.18.729.311 I slot print_timing: id 0 | task 29935 | prompt eval time = 367.36 ms / 155 tokens ( 2.37 ms per token, 421.93 tokens per second) 13.18.729.315 I slot print_timing: id 0 | task 29935 | eval time = 1740.09 ms / 77 tokens ( 22.90 ms per token, 43.68 tokens per second) 13.18.729.315 I slot print_timing: id 0 | task 29935 | total time = 2107.45 ms / 232 tokens 13.18.729.316 I slot print_timing: id 0 | task 29935 | graphs reused = 28940 13.18.729.317 I slot print_timing: id 0 | task 29935 | graph reallocs = 0 / 0 (same size) / (changed size) 13.18.729.344 I slot release: id 0 | task 29935 | stop processing: n_tokens = 231, truncated = 0 13.18.733.179 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.176 (> 0.100 thold), f_keep = 0.130 13.18.733.220 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 91.773 MiB) 13.18.735.121 I slot launch_slot_: id 0 | task 30015 | processing task, is_child = 0 13.19.685.091 I slot print_timing: id 0 | task 30015 | prompt eval time = 398.18 ms / 170 tokens ( 2.34 ms per token, 426.95 tokens per second) 13.19.685.094 I slot print_timing: id 0 | task 30015 | eval time = 551.78 ms / 25 tokens ( 22.99 ms per token, 43.50 tokens per second) 13.19.685.095 I slot print_timing: id 0 | task 30015 | total time = 949.95 ms / 195 tokens 13.19.685.095 I slot print_timing: id 0 | task 30015 | graphs reused = 28963 13.19.685.096 I slot print_timing: id 0 | task 30015 | graph reallocs = 0 / 0 (same size) / (changed size) 13.19.685.117 I slot release: id 0 | task 30015 | stop processing: n_tokens = 194, truncated = 0 13.19.689.167 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.160 13.19.693.572 I slot launch_slot_: id 0 | task 30043 | processing task, is_child = 0 13.20.721.696 I slot print_timing: id 0 | task 30043 | prompt eval time = 396.10 ms / 160 tokens ( 2.48 ms per token, 403.94 tokens per second) 13.20.721.700 I slot print_timing: id 0 | task 30043 | eval time = 632.01 ms / 28 tokens ( 23.41 ms per token, 42.72 tokens per second) 13.20.721.700 I slot print_timing: id 0 | task 30043 | total time = 1028.11 ms / 188 tokens 13.20.721.701 I slot print_timing: id 0 | task 30043 | graphs reused = 28989 13.20.721.702 I slot print_timing: id 0 | task 30043 | graph reallocs = 0 / 0 (same size) / (changed size) 13.20.721.724 I slot release: id 0 | task 30043 | stop processing: n_tokens = 187, truncated = 0 13.20.725.710 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.186 (> 0.100 thold), f_keep = 0.160 13.20.725.746 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 126.584 MiB) 13.20.727.463 I slot launch_slot_: id 0 | task 30074 | processing task, is_child = 0 13.22.093.229 I slot print_timing: id 0 | task 30074 | prompt eval time = 402.59 ms / 161 tokens ( 2.50 ms per token, 399.91 tokens per second) 13.22.093.232 I slot print_timing: id 0 | task 30074 | eval time = 963.17 ms / 43 tokens ( 22.93 ms per token, 43.61 tokens per second) 13.22.093.233 I slot print_timing: id 0 | task 30074 | total time = 1365.76 ms / 204 tokens 13.22.093.234 I slot print_timing: id 0 | task 30074 | graphs reused = 29030 13.22.093.234 I slot print_timing: id 0 | task 30074 | graph reallocs = 0 / 0 (same size) / (changed size) 13.22.093.252 I slot release: id 0 | task 30074 | stop processing: n_tokens = 203, truncated = 0 13.22.097.304 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.148 13.22.101.294 I slot launch_slot_: id 0 | task 30120 | processing task, is_child = 0 13.25.082.217 I slot print_timing: id 0 | task 30120 | prompt eval time = 368.27 ms / 169 tokens ( 2.18 ms per token, 458.90 tokens per second) 13.25.082.223 I slot print_timing: id 0 | task 30120 | eval time = 2612.64 ms / 115 tokens ( 22.92 ms per token, 43.63 tokens per second) 13.25.082.223 I slot print_timing: id 0 | task 30120 | total time = 2980.91 ms / 284 tokens 13.25.082.224 I slot print_timing: id 0 | task 30120 | graphs reused = 29142 13.25.082.224 I slot print_timing: id 0 | task 30120 | graph reallocs = 0 / 0 (same size) / (changed size) 13.25.082.244 I slot release: id 0 | task 30120 | stop processing: n_tokens = 283, truncated = 0 13.25.086.240 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 13.25.086.284 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 112.765 MiB) 13.25.089.764 I slot launch_slot_: id 0 | task 30238 | processing task, is_child = 0 13.26.009.004 I slot print_timing: id 0 | task 30238 | prompt eval time = 481.22 ms / 183 tokens ( 2.63 ms per token, 380.29 tokens per second) 13.26.009.007 I slot print_timing: id 0 | task 30238 | eval time = 438.01 ms / 20 tokens ( 23.05 ms per token, 43.38 tokens per second) 13.26.009.008 I slot print_timing: id 0 | task 30238 | total time = 919.23 ms / 203 tokens 13.26.009.009 I slot print_timing: id 0 | task 30238 | graphs reused = 29160 13.26.009.009 I slot print_timing: id 0 | task 30238 | graph reallocs = 0 / 0 (same size) / (changed size) 13.26.009.032 I slot release: id 0 | task 30238 | stop processing: n_tokens = 202, truncated = 0 13.26.013.047 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.174 (> 0.100 thold), f_keep = 0.149 13.26.017.552 I slot launch_slot_: id 0 | task 30261 | processing task, is_child = 0 13.26.917.229 I slot print_timing: id 0 | task 30261 | prompt eval time = 392.43 ms / 172 tokens ( 2.28 ms per token, 438.30 tokens per second) 13.26.917.232 I slot print_timing: id 0 | task 30261 | eval time = 507.23 ms / 23 tokens ( 23.06 ms per token, 43.37 tokens per second) 13.26.917.233 I slot print_timing: id 0 | task 30261 | total time = 899.66 ms / 195 tokens 13.26.917.234 I slot print_timing: id 0 | task 30261 | graphs reused = 29181 13.26.917.234 I slot print_timing: id 0 | task 30261 | graph reallocs = 0 / 0 (same size) / (changed size) 13.26.917.259 I slot release: id 0 | task 30261 | stop processing: n_tokens = 194, truncated = 0 13.26.921.250 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.165 (> 0.100 thold), f_keep = 0.155 13.26.921.288 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 98.136 MiB) 13.26.923.118 I slot launch_slot_: id 0 | task 30287 | processing task, is_child = 0 13.27.906.727 I slot print_timing: id 0 | task 30287 | prompt eval time = 454.50 ms / 182 tokens ( 2.50 ms per token, 400.44 tokens per second) 13.27.906.734 I slot print_timing: id 0 | task 30287 | eval time = 529.10 ms / 24 tokens ( 23.00 ms per token, 43.47 tokens per second) 13.27.906.735 I slot print_timing: id 0 | task 30287 | total time = 983.60 ms / 206 tokens 13.27.906.735 I slot print_timing: id 0 | task 30287 | graphs reused = 29203 13.27.906.736 I slot print_timing: id 0 | task 30287 | graph reallocs = 0 / 0 (same size) / (changed size) 13.27.906.756 I slot release: id 0 | task 30287 | stop processing: n_tokens = 205, truncated = 0 13.27.910.840 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.161 13.27.910.876 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 119.551 MiB) 13.27.916.288 I slot launch_slot_: id 0 | task 30314 | processing task, is_child = 0 13.29.084.363 I slot print_timing: id 0 | task 30314 | prompt eval time = 454.18 ms / 181 tokens ( 2.51 ms per token, 398.52 tokens per second) 13.29.084.367 I slot print_timing: id 0 | task 30314 | eval time = 713.88 ms / 32 tokens ( 23.03 ms per token, 43.42 tokens per second) 13.29.084.368 I slot print_timing: id 0 | task 30314 | total time = 1168.06 ms / 213 tokens 13.29.084.368 I slot print_timing: id 0 | task 30314 | graphs reused = 29233 13.29.084.369 I slot print_timing: id 0 | task 30314 | graph reallocs = 0 / 0 (same size) / (changed size) 13.29.084.387 I slot release: id 0 | task 30314 | stop processing: n_tokens = 212, truncated = 0 13.29.088.690 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.133 (> 0.100 thold), f_keep = 0.142 13.29.094.102 I slot launch_slot_: id 0 | task 30349 | processing task, is_child = 0 13.32.407.309 I slot print_timing: id 0 | task 30349 | prompt eval time = 512.94 ms / 226 tokens ( 2.27 ms per token, 440.60 tokens per second) 13.32.407.312 I slot print_timing: id 0 | task 30349 | eval time = 2800.26 ms / 123 tokens ( 22.95 ms per token, 43.57 tokens per second) 13.32.407.313 I slot print_timing: id 0 | task 30349 | total time = 3313.20 ms / 349 tokens 13.32.407.314 I slot print_timing: id 0 | task 30349 | graphs reused = 29353 13.32.407.315 I slot print_timing: id 0 | task 30349 | graph reallocs = 0 / 0 (same size) / (changed size) 13.32.407.340 I slot release: id 0 | task 30349 | stop processing: n_tokens = 348, truncated = 0 13.32.411.758 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.189 (> 0.100 thold), f_keep = 0.086 13.32.411.805 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 143.710 MiB) 13.32.417.229 I slot launch_slot_: id 0 | task 30475 | processing task, is_child = 0 13.33.480.014 I slot print_timing: id 0 | task 30475 | prompt eval time = 395.57 ms / 159 tokens ( 2.49 ms per token, 401.95 tokens per second) 13.33.480.017 I slot print_timing: id 0 | task 30475 | eval time = 667.20 ms / 30 tokens ( 23.01 ms per token, 43.47 tokens per second) 13.33.480.018 I slot print_timing: id 0 | task 30475 | total time = 1062.78 ms / 189 tokens 13.33.480.019 I slot print_timing: id 0 | task 30475 | graphs reused = 29381 13.33.480.019 I slot print_timing: id 0 | task 30475 | graph reallocs = 0 / 0 (same size) / (changed size) 13.33.480.042 I slot release: id 0 | task 30475 | stop processing: n_tokens = 188, truncated = 0 13.33.916.180 I srv operator(): operator(): cleaning up before exit...