$ /Users/minipro/quantdiff/llama.cpp/llama-b11770/llama-server -m /Users/minipro/quantdiff/models/campaign/ddff7a731322/Spark-X2.6-4B-IQ2_M.gguf --host 127.0.0.1 --port 8089 -c 4096 -np 1 -ngl 999 -fa on --jinja --seed 1234 --no-webui -a quant 0.00.042.921 I srv llama_server: initializing ... 0.00.042.928 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.043.015 I srv init_listene: The UI is disabled 0.00.043.016 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.043.051 W srv llama_server: security: no API key is set and CORS allows all origins (see https://github.com/ggml-org/llama.cpp/pull/25655) 0.00.044.710 I srv load_model: loading model '/Users/minipro/quantdiff/models/campaign/ddff7a731322/Spark-X2.6-4B-IQ2_M.gguf' 0.00.366.899 I cmn init: llama threadpool init, n_threads = 8 0.00.454.061 I srv load_model: initializing, n_slots = 1, n_ctx_slot = 4096, kv_unified = 'false' 0.00.461.672 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.00.461.686 I srv llama_server: model loaded 0.00.461.688 I srv llama_server: listening on http://127.0.0.1:8089 0.02.022.128 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.02.022.364 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.05.471.987 I slot print_timing: id 0 | task 0 | n_gen = 133, tg = 43.87 t/s, tg_3s = 44.20 t/s 0.06.409.268 I slot print_timing: id 0 | task 0 | prompt eval time = 440.60 ms / 172 tokens ( 2.56 ms per token, 390.38 tokens per second) 0.06.409.272 I slot print_timing: id 0 | task 0 | eval time = 3946.27 ms / 174 tokens ( 22.81 ms per token, 43.84 tokens per second) 0.06.409.272 I slot print_timing: id 0 | task 0 | total time = 4386.87 ms / 346 tokens 0.06.409.273 I slot print_timing: id 0 | task 0 | graphs reused = 172 0.06.409.274 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.06.409.302 I slot release: id 0 | task 0 | stop processing: n_tokens = 345, truncated = 0 0.06.413.451 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.236 (> 0.100 thold), f_keep = 0.087 0.06.421.354 I slot launch_slot_: id 0 | task 177 | processing task, is_child = 0 0.09.784.160 I slot print_timing: id 0 | task 177 | n_gen = 133, tg = 43.88 t/s, tg_3s = 44.21 t/s 0.11.167.618 I slot print_timing: id 0 | task 177 | prompt eval time = 354.69 ms / 127 tokens ( 2.79 ms per token, 358.06 tokens per second) 0.11.167.621 I slot print_timing: id 0 | task 177 | eval time = 4391.56 ms / 193 tokens ( 22.87 ms per token, 43.72 tokens per second) 0.11.167.626 I slot print_timing: id 0 | task 177 | total time = 4746.26 ms / 320 tokens 0.11.167.627 I slot print_timing: id 0 | task 177 | graphs reused = 362 0.11.167.628 I slot print_timing: id 0 | task 177 | graph reallocs = 0 / 0 (same size) / (changed size) 0.11.167.644 I slot release: id 0 | task 177 | stop processing: n_tokens = 319, truncated = 0 0.11.171.799 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.094 0.11.178.062 I slot launch_slot_: id 0 | task 373 | processing task, is_child = 0 0.14.148.935 I slot print_timing: id 0 | task 373 | prompt eval time = 417.90 ms / 171 tokens ( 2.44 ms per token, 409.19 tokens per second) 0.14.148.939 I slot print_timing: id 0 | task 373 | eval time = 2552.96 ms / 113 tokens ( 22.79 ms per token, 43.87 tokens per second) 0.14.148.939 I slot print_timing: id 0 | task 373 | total time = 2970.86 ms / 284 tokens 0.14.148.940 I slot print_timing: id 0 | task 373 | graphs reused = 472 0.14.148.941 I slot print_timing: id 0 | task 373 | graph reallocs = 0 / 0 (same size) / (changed size) 0.14.148.968 I slot release: id 0 | task 373 | stop processing: n_tokens = 283, truncated = 0 0.14.153.165 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.147 (> 0.100 thold), f_keep = 0.106 0.14.159.839 I slot launch_slot_: id 0 | task 489 | processing task, is_child = 0 0.15.349.917 I slot print_timing: id 0 | task 489 | prompt eval time = 481.97 ms / 204 tokens ( 2.36 ms per token, 423.26 tokens per second) 0.15.349.923 I slot print_timing: id 0 | task 489 | eval time = 708.10 ms / 32 tokens ( 22.84 ms per token, 43.78 tokens per second) 0.15.349.924 I slot print_timing: id 0 | task 489 | total time = 1190.07 ms / 236 tokens 0.15.349.925 I slot print_timing: id 0 | task 489 | graphs reused = 502 0.15.349.925 I slot print_timing: id 0 | task 489 | graph reallocs = 0 / 0 (same size) / (changed size) 0.15.349.949 I slot release: id 0 | task 489 | stop processing: n_tokens = 235, truncated = 0 0.15.353.914 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.183 0.15.360.300 I slot launch_slot_: id 0 | task 524 | processing task, is_child = 0 0.15.957.460 I slot print_timing: id 0 | task 524 | prompt eval time = 458.05 ms / 187 tokens ( 2.45 ms per token, 408.25 tokens per second) 0.15.957.468 I slot print_timing: id 0 | task 524 | eval time = 139.10 ms / 7 tokens ( 23.18 ms per token, 43.13 tokens per second) 0.15.957.469 I slot print_timing: id 0 | task 524 | total time = 597.15 ms / 194 tokens 0.15.957.470 I slot print_timing: id 0 | task 524 | graphs reused = 507 0.15.957.471 I slot print_timing: id 0 | task 524 | graph reallocs = 0 / 0 (same size) / (changed size) 0.15.957.501 I slot release: id 0 | task 524 | stop processing: n_tokens = 193, truncated = 0 0.15.962.917 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.155 0.15.969.307 I slot launch_slot_: id 0 | task 534 | processing task, is_child = 0 0.16.924.277 I slot print_timing: id 0 | task 534 | prompt eval time = 382.81 ms / 171 tokens ( 2.24 ms per token, 446.70 tokens per second) 0.16.924.283 I slot print_timing: id 0 | task 534 | eval time = 572.15 ms / 26 tokens ( 22.89 ms per token, 43.69 tokens per second) 0.16.924.284 I slot print_timing: id 0 | task 534 | total time = 954.96 ms / 197 tokens 0.16.924.285 I slot print_timing: id 0 | task 534 | graphs reused = 531 0.16.924.285 I slot print_timing: id 0 | task 534 | graph reallocs = 0 / 0 (same size) / (changed size) 0.16.924.307 I slot release: id 0 | task 534 | stop processing: n_tokens = 196, truncated = 0 0.16.928.524 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.136 (> 0.100 thold), f_keep = 0.153 0.16.934.143 I slot launch_slot_: id 0 | task 563 | processing task, is_child = 0 0.20.474.698 I slot print_timing: id 0 | task 563 | n_gen = 133, tg = 43.73 t/s, tg_3s = 44.06 t/s 0.21.972.366 I slot print_timing: id 0 | task 563 | prompt eval time = 522.02 ms / 221 tokens ( 2.36 ms per token, 423.35 tokens per second) 0.21.972.370 I slot print_timing: id 0 | task 563 | eval time = 4516.19 ms / 198 tokens ( 22.92 ms per token, 43.62 tokens per second) 0.21.972.370 I slot print_timing: id 0 | task 563 | total time = 5038.21 ms / 419 tokens 0.21.972.371 I slot print_timing: id 0 | task 563 | graphs reused = 726 0.21.972.372 I slot print_timing: id 0 | task 563 | graph reallocs = 0 / 0 (same size) / (changed size) 0.21.972.398 I slot release: id 0 | task 563 | stop processing: n_tokens = 418, truncated = 0 0.21.977.086 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.111 (> 0.100 thold), f_keep = 0.072 0.21.986.305 I slot launch_slot_: id 0 | task 764 | processing task, is_child = 0 0.25.616.651 I slot print_timing: id 0 | task 764 | n_gen = 132, tg = 43.60 t/s, tg_3s = 43.93 t/s 0.28.631.582 I slot print_timing: id 0 | task 764 | n_gen = 262, tg = 43.36 t/s, tg_3s = 43.12 t/s 0.31.635.170 I slot print_timing: id 0 | task 764 | n_gen = 391, tg = 43.22 t/s, tg_3s = 42.95 t/s 0.32.606.853 I slot print_timing: id 0 | task 764 | prompt eval time = 625.66 ms / 270 tokens ( 2.32 ms per token, 431.55 tokens per second) 0.32.606.860 I slot print_timing: id 0 | task 764 | eval time = 9994.88 ms / 433 tokens ( 23.14 ms per token, 43.22 tokens per second) 0.32.606.860 I slot print_timing: id 0 | task 764 | total time = 10620.53 ms / 703 tokens 0.32.606.861 I slot print_timing: id 0 | task 764 | graphs reused = 1156 0.32.606.862 I slot print_timing: id 0 | task 764 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.606.886 I slot release: id 0 | task 764 | stop processing: n_tokens = 702, truncated = 0 0.32.610.760 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.043 0.32.622.309 I slot launch_slot_: id 0 | task 1200 | processing task, is_child = 0 0.35.990.287 I slot print_timing: id 0 | task 1200 | n_gen = 134, tg = 44.32 t/s, tg_3s = 44.65 t/s 0.36.013.123 I slot print_timing: id 0 | task 1200 | prompt eval time = 366.84 ms / 150 tokens ( 2.45 ms per token, 408.90 tokens per second) 0.36.013.126 I slot print_timing: id 0 | task 1200 | eval time = 3023.96 ms / 135 tokens ( 22.57 ms per token, 44.31 tokens per second) 0.36.013.127 I slot print_timing: id 0 | task 1200 | total time = 3390.80 ms / 285 tokens 0.36.013.128 I slot print_timing: id 0 | task 1200 | graphs reused = 1288 0.36.013.128 I slot print_timing: id 0 | task 1200 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.013.150 I slot release: id 0 | task 1200 | stop processing: n_tokens = 284, truncated = 0 0.36.017.866 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.180 (> 0.100 thold), f_keep = 0.106 0.36.022.554 I slot launch_slot_: id 0 | task 1338 | processing task, is_child = 0 0.39.209.225 I slot print_timing: id 0 | task 1338 | prompt eval time = 408.52 ms / 167 tokens ( 2.45 ms per token, 408.80 tokens per second) 0.39.209.229 I slot print_timing: id 0 | task 1338 | eval time = 2778.14 ms / 123 tokens ( 22.77 ms per token, 43.91 tokens per second) 0.39.209.230 I slot print_timing: id 0 | task 1338 | total time = 3186.66 ms / 290 tokens 0.39.209.231 I slot print_timing: id 0 | task 1338 | graphs reused = 1408 0.39.209.231 I slot print_timing: id 0 | task 1338 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.209.249 I slot release: id 0 | task 1338 | stop processing: n_tokens = 289, truncated = 0 0.39.213.493 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.104 0.39.218.181 I slot launch_slot_: id 0 | task 1464 | processing task, is_child = 0 0.42.611.058 I slot print_timing: id 0 | task 1464 | n_gen = 130, tg = 42.92 t/s, tg_3s = 43.25 t/s 0.45.632.747 I slot print_timing: id 0 | task 1464 | n_gen = 259, tg = 42.81 t/s, tg_3s = 42.69 t/s 0.48.643.573 I slot print_timing: id 0 | task 1464 | n_gen = 389, tg = 42.93 t/s, tg_3s = 43.18 t/s 0.51.645.382 I slot print_timing: id 0 | task 1464 | n_gen = 518, tg = 42.94 t/s, tg_3s = 42.97 t/s 0.54.660.517 I slot print_timing: id 0 | task 1464 | n_gen = 648, tg = 42.98 t/s, tg_3s = 43.12 t/s 0.57.679.627 I slot print_timing: id 0 | task 1464 | n_gen = 778, tg = 42.99 t/s, tg_3s = 43.06 t/s 1.00.288.266 I slot print_timing: id 0 | task 1464 | prompt eval time = 387.34 ms / 171 tokens ( 2.27 ms per token, 441.48 tokens per second) 1.00.288.269 I slot print_timing: id 0 | task 1464 | eval time = 20682.74 ms / 890 tokens ( 23.27 ms per token, 42.98 tokens per second) 1.00.288.270 I slot print_timing: id 0 | task 1464 | total time = 21070.07 ms / 1061 tokens 1.00.288.271 I slot print_timing: id 0 | task 1464 | graphs reused = 2292 1.00.288.271 I slot print_timing: id 0 | task 1464 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.288.291 I slot release: id 0 | task 1464 | stop processing: n_tokens = 1060, truncated = 0 1.00.292.704 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.140 (> 0.100 thold), f_keep = 0.028 1.00.304.571 I slot launch_slot_: id 0 | task 2357 | processing task, is_child = 0 1.03.141.318 I slot print_timing: id 0 | task 2357 | prompt eval time = 473.86 ms / 214 tokens ( 2.21 ms per token, 451.61 tokens per second) 1.03.141.324 I slot print_timing: id 0 | task 2357 | eval time = 2362.88 ms / 104 tokens ( 22.94 ms per token, 43.59 tokens per second) 1.03.141.325 I slot print_timing: id 0 | task 2357 | total time = 2836.74 ms / 318 tokens 1.03.141.325 I slot print_timing: id 0 | task 2357 | graphs reused = 2393 1.03.141.326 I slot print_timing: id 0 | task 2357 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.141.359 I slot release: id 0 | task 2357 | stop processing: n_tokens = 317, truncated = 0 1.03.145.598 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.164 (> 0.100 thold), f_keep = 0.095 1.03.153.530 I slot launch_slot_: id 0 | task 2464 | processing task, is_child = 0 1.06.617.525 I slot print_timing: id 0 | task 2464 | n_gen = 133, tg = 43.90 t/s, tg_3s = 44.23 t/s 1.08.523.919 I slot print_timing: id 0 | task 2464 | prompt eval time = 457.31 ms / 183 tokens ( 2.50 ms per token, 400.16 tokens per second) 1.08.523.923 I slot print_timing: id 0 | task 2464 | eval time = 4913.06 ms / 216 tokens ( 22.85 ms per token, 43.76 tokens per second) 1.08.523.924 I slot print_timing: id 0 | task 2464 | total time = 5370.38 ms / 399 tokens 1.08.523.925 I slot print_timing: id 0 | task 2464 | graphs reused = 2606 1.08.523.926 I slot print_timing: id 0 | task 2464 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.523.953 I slot release: id 0 | task 2464 | stop processing: n_tokens = 398, truncated = 0 1.08.528.160 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.164 (> 0.100 thold), f_keep = 0.075 1.08.534.525 I slot launch_slot_: id 0 | task 2683 | processing task, is_child = 0 1.09.628.998 I slot print_timing: id 0 | task 2683 | prompt eval time = 485.43 ms / 183 tokens ( 2.65 ms per token, 376.99 tokens per second) 1.09.629.001 I slot print_timing: id 0 | task 2683 | eval time = 609.04 ms / 27 tokens ( 23.42 ms per token, 42.69 tokens per second) 1.09.629.002 I slot print_timing: id 0 | task 2683 | total time = 1094.46 ms / 210 tokens 1.09.629.002 I slot print_timing: id 0 | task 2683 | graphs reused = 2631 1.09.629.003 I slot print_timing: id 0 | task 2683 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.629.021 I slot release: id 0 | task 2683 | stop processing: n_tokens = 209, truncated = 0 1.09.633.415 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 1.09.639.451 I slot launch_slot_: id 0 | task 2713 | processing task, is_child = 0 1.10.837.303 I slot print_timing: id 0 | task 2713 | prompt eval time = 421.98 ms / 170 tokens ( 2.48 ms per token, 402.86 tokens per second) 1.10.837.309 I slot print_timing: id 0 | task 2713 | eval time = 775.86 ms / 35 tokens ( 22.82 ms per token, 43.82 tokens per second) 1.10.837.311 I slot print_timing: id 0 | task 2713 | total time = 1197.85 ms / 205 tokens 1.10.837.311 I slot print_timing: id 0 | task 2713 | graphs reused = 2664 1.10.837.312 I slot print_timing: id 0 | task 2713 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.837.334 I slot release: id 0 | task 2713 | stop processing: n_tokens = 204, truncated = 0 1.10.841.662 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 1.10.847.297 I slot launch_slot_: id 0 | task 2751 | processing task, is_child = 0 1.11.797.547 I slot print_timing: id 0 | task 2751 | prompt eval time = 382.23 ms / 150 tokens ( 2.55 ms per token, 392.44 tokens per second) 1.11.797.551 I slot print_timing: id 0 | task 2751 | eval time = 568.01 ms / 26 tokens ( 22.72 ms per token, 44.01 tokens per second) 1.11.797.552 I slot print_timing: id 0 | task 2751 | total time = 950.24 ms / 176 tokens 1.11.797.552 I slot print_timing: id 0 | task 2751 | graphs reused = 2688 1.11.797.553 I slot print_timing: id 0 | task 2751 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.797.571 I slot release: id 0 | task 2751 | stop processing: n_tokens = 175, truncated = 0 1.11.801.492 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.172 (> 0.100 thold), f_keep = 0.171 1.11.805.400 I slot launch_slot_: id 0 | task 2780 | processing task, is_child = 0 1.15.237.595 I slot print_timing: id 0 | task 2780 | n_gen = 133, tg = 43.87 t/s, tg_3s = 44.20 t/s 1.18.251.532 I slot print_timing: id 0 | task 2780 | n_gen = 264, tg = 43.67 t/s, tg_3s = 43.46 t/s 1.21.262.653 I slot print_timing: id 0 | task 2780 | n_gen = 394, tg = 43.50 t/s, tg_3s = 43.17 t/s 1.24.275.831 I slot print_timing: id 0 | task 2780 | n_gen = 524, tg = 43.41 t/s, tg_3s = 43.14 t/s 1.27.288.984 I slot print_timing: id 0 | task 2780 | n_gen = 654, tg = 43.36 t/s, tg_3s = 43.14 t/s 1.30.309.440 I slot print_timing: id 0 | task 2780 | n_gen = 784, tg = 43.31 t/s, tg_3s = 43.04 t/s 1.33.323.744 I slot print_timing: id 0 | task 2780 | n_gen = 913, tg = 43.23 t/s, tg_3s = 42.80 t/s 1.35.908.239 I slot print_timing: id 0 | task 2780 | prompt eval time = 423.30 ms / 174 tokens ( 2.43 ms per token, 411.06 tokens per second) 1.35.908.243 I slot print_timing: id 0 | task 2780 | eval time = 23679.53 ms / 1024 tokens ( 23.15 ms per token, 43.20 tokens per second) 1.35.908.243 I slot print_timing: id 0 | task 2780 | total time = 24102.83 ms / 1198 tokens 1.35.908.244 I slot print_timing: id 0 | task 2780 | graphs reused = 3706 1.35.908.244 I slot print_timing: id 0 | task 2780 | graph reallocs = 0 / 0 (same size) / (changed size) 1.35.908.265 I slot release: id 0 | task 2780 | stop processing: n_tokens = 1197, truncated = 0 1.35.912.544 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.192 (> 0.100 thold), f_keep = 0.025 1.35.924.745 I slot launch_slot_: id 0 | task 3807 | processing task, is_child = 0 1.38.734.930 I slot print_timing: id 0 | task 3807 | prompt eval time = 418.88 ms / 156 tokens ( 2.69 ms per token, 372.42 tokens per second) 1.38.734.940 I slot print_timing: id 0 | task 3807 | eval time = 2391.30 ms / 106 tokens ( 22.77 ms per token, 43.91 tokens per second) 1.38.734.941 I slot print_timing: id 0 | task 3807 | total time = 2810.18 ms / 262 tokens 1.38.734.942 I slot print_timing: id 0 | task 3807 | graphs reused = 3809 1.38.734.943 I slot print_timing: id 0 | task 3807 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.734.961 I slot release: id 0 | task 3807 | stop processing: n_tokens = 261, truncated = 0 1.38.738.924 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.197 (> 0.100 thold), f_keep = 0.115 1.38.744.938 I slot launch_slot_: id 0 | task 3916 | processing task, is_child = 0 1.41.514.826 I slot print_timing: id 0 | task 3916 | prompt eval time = 379.07 ms / 152 tokens ( 2.49 ms per token, 400.98 tokens per second) 1.41.514.829 I slot print_timing: id 0 | task 3916 | eval time = 2390.80 ms / 106 tokens ( 22.77 ms per token, 43.92 tokens per second) 1.41.514.830 I slot print_timing: id 0 | task 3916 | total time = 2769.88 ms / 258 tokens 1.41.514.830 I slot print_timing: id 0 | task 3916 | graphs reused = 3912 1.41.514.831 I slot print_timing: id 0 | task 3916 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.514.850 I slot release: id 0 | task 3916 | stop processing: n_tokens = 257, truncated = 0 1.41.519.230 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.160 (> 0.100 thold), f_keep = 0.117 1.41.525.519 I slot launch_slot_: id 0 | task 4025 | processing task, is_child = 0 1.45.001.540 I slot print_timing: id 0 | task 4025 | n_gen = 132, tg = 43.63 t/s, tg_3s = 43.96 t/s 1.45.161.549 I slot print_timing: id 0 | task 4025 | prompt eval time = 473.18 ms / 187 tokens ( 2.53 ms per token, 395.20 tokens per second) 1.45.161.555 I slot print_timing: id 0 | task 4025 | eval time = 3162.84 ms / 139 tokens ( 22.92 ms per token, 43.63 tokens per second) 1.45.161.556 I slot print_timing: id 0 | task 4025 | total time = 3636.02 ms / 326 tokens 1.45.161.556 I slot print_timing: id 0 | task 4025 | graphs reused = 4048 1.45.161.557 I slot print_timing: id 0 | task 4025 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.161.584 I slot release: id 0 | task 4025 | stop processing: n_tokens = 325, truncated = 0 1.45.165.583 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.092 1.45.172.048 I slot launch_slot_: id 0 | task 4167 | processing task, is_child = 0 1.46.410.266 I slot print_timing: id 0 | task 4167 | prompt eval time = 438.99 ms / 160 tokens ( 2.74 ms per token, 364.47 tokens per second) 1.46.410.269 I slot print_timing: id 0 | task 4167 | eval time = 799.22 ms / 34 tokens ( 24.22 ms per token, 41.29 tokens per second) 1.46.410.270 I slot print_timing: id 0 | task 4167 | total time = 1238.21 ms / 194 tokens 1.46.410.271 I slot print_timing: id 0 | task 4167 | graphs reused = 4080 1.46.410.271 I slot print_timing: id 0 | task 4167 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.410.289 I slot release: id 0 | task 4167 | stop processing: n_tokens = 193, truncated = 0 1.46.414.666 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 1.46.419.766 I slot launch_slot_: id 0 | task 4204 | processing task, is_child = 0 1.49.484.202 I slot print_timing: id 0 | task 4204 | prompt eval time = 484.00 ms / 208 tokens ( 2.33 ms per token, 429.75 tokens per second) 1.49.484.206 I slot print_timing: id 0 | task 4204 | eval time = 2580.42 ms / 114 tokens ( 22.84 ms per token, 43.79 tokens per second) 1.49.484.207 I slot print_timing: id 0 | task 4204 | total time = 3064.42 ms / 322 tokens 1.49.484.207 I slot print_timing: id 0 | task 4204 | graphs reused = 4191 1.49.484.208 I slot print_timing: id 0 | task 4204 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.484.226 I slot release: id 0 | task 4204 | stop processing: n_tokens = 321, truncated = 0 1.49.488.702 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.093 1.49.496.730 I slot launch_slot_: id 0 | task 4321 | processing task, is_child = 0 1.52.979.496 I slot print_timing: id 0 | task 4321 | n_gen = 133, tg = 43.81 t/s, tg_3s = 44.14 t/s 1.53.504.830 I slot print_timing: id 0 | task 4321 | prompt eval time = 469.56 ms / 192 tokens ( 2.45 ms per token, 408.89 tokens per second) 1.53.504.836 I slot print_timing: id 0 | task 4321 | eval time = 3538.53 ms / 156 tokens ( 22.83 ms per token, 43.80 tokens per second) 1.53.504.837 I slot print_timing: id 0 | task 4321 | total time = 4008.09 ms / 348 tokens 1.53.504.837 I slot print_timing: id 0 | task 4321 | graphs reused = 4344 1.53.504.838 I slot print_timing: id 0 | task 4321 | graph reallocs = 0 / 0 (same size) / (changed size) 1.53.504.864 I slot release: id 0 | task 4321 | stop processing: n_tokens = 347, truncated = 0 1.53.509.352 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.152 (> 0.100 thold), f_keep = 0.086 1.53.517.349 I slot launch_slot_: id 0 | task 4480 | processing task, is_child = 0 1.56.986.918 I slot print_timing: id 0 | task 4480 | n_gen = 133, tg = 43.85 t/s, tg_3s = 44.18 t/s 1.59.994.656 I slot print_timing: id 0 | task 4480 | n_gen = 263, tg = 43.54 t/s, tg_3s = 43.22 t/s 2.03.007.077 I slot print_timing: id 0 | task 4480 | n_gen = 393, tg = 43.41 t/s, tg_3s = 43.15 t/s 2.06.025.094 I slot print_timing: id 0 | task 4480 | n_gen = 525, tg = 43.49 t/s, tg_3s = 43.74 t/s 2.09.033.701 I slot print_timing: id 0 | task 4480 | n_gen = 654, tg = 43.37 t/s, tg_3s = 42.88 t/s 2.12.051.098 I slot print_timing: id 0 | task 4480 | n_gen = 783, tg = 43.27 t/s, tg_3s = 42.75 t/s 2.15.051.835 I slot print_timing: id 0 | task 4480 | n_gen = 911, tg = 43.18 t/s, tg_3s = 42.66 t/s 2.17.715.779 I slot print_timing: id 0 | task 4480 | prompt eval time = 459.36 ms / 198 tokens ( 2.32 ms per token, 431.04 tokens per second) 2.17.715.783 I slot print_timing: id 0 | task 4480 | eval time = 23739.06 ms / 1024 tokens ( 23.21 ms per token, 43.09 tokens per second) 2.17.715.783 I slot print_timing: id 0 | task 4480 | total time = 24198.42 ms / 1222 tokens 2.17.715.784 I slot print_timing: id 0 | task 4480 | graphs reused = 5362 2.17.715.784 I slot print_timing: id 0 | task 4480 | graph reallocs = 0 / 0 (same size) / (changed size) 2.17.715.808 I slot release: id 0 | task 4480 | stop processing: n_tokens = 1221, truncated = 0 2.17.720.472 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.128 (> 0.100 thold), f_keep = 0.025 2.17.732.701 I slot launch_slot_: id 0 | task 5507 | processing task, is_child = 0 2.19.109.475 I slot print_timing: id 0 | task 5507 | prompt eval time = 524.76 ms / 235 tokens ( 2.23 ms per token, 447.82 tokens per second) 2.19.109.480 I slot print_timing: id 0 | task 5507 | eval time = 852.00 ms / 38 tokens ( 23.03 ms per token, 43.43 tokens per second) 2.19.109.481 I slot print_timing: id 0 | task 5507 | total time = 1376.76 ms / 273 tokens 2.19.109.482 I slot print_timing: id 0 | task 5507 | graphs reused = 5397 2.19.109.482 I slot print_timing: id 0 | task 5507 | graph reallocs = 0 / 0 (same size) / (changed size) 2.19.109.502 I slot release: id 0 | task 5507 | stop processing: n_tokens = 272, truncated = 0 2.19.113.597 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 2.19.121.157 I slot launch_slot_: id 0 | task 5548 | processing task, is_child = 0 2.22.589.522 I slot print_timing: id 0 | task 5548 | n_gen = 132, tg = 43.56 t/s, tg_3s = 43.89 t/s 2.24.769.644 I slot print_timing: id 0 | task 5548 | prompt eval time = 460.96 ms / 199 tokens ( 2.32 ms per token, 431.71 tokens per second) 2.24.769.648 I slot print_timing: id 0 | task 5548 | eval time = 5187.51 ms / 226 tokens ( 23.06 ms per token, 43.37 tokens per second) 2.24.769.649 I slot print_timing: id 0 | task 5548 | total time = 5648.47 ms / 425 tokens 2.24.769.650 I slot print_timing: id 0 | task 5548 | graphs reused = 5620 2.24.769.650 I slot print_timing: id 0 | task 5548 | graph reallocs = 0 / 0 (same size) / (changed size) 2.24.769.672 I slot release: id 0 | task 5548 | stop processing: n_tokens = 424, truncated = 0 2.24.773.964 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.191 (> 0.100 thold), f_keep = 0.071 2.24.782.392 I slot launch_slot_: id 0 | task 5777 | processing task, is_child = 0 2.27.083.100 I slot print_timing: id 0 | task 5777 | prompt eval time = 409.40 ms / 157 tokens ( 2.61 ms per token, 383.48 tokens per second) 2.27.083.106 I slot print_timing: id 0 | task 5777 | eval time = 1891.29 ms / 83 tokens ( 23.06 ms per token, 43.36 tokens per second) 2.27.083.107 I slot print_timing: id 0 | task 5777 | total time = 2300.70 ms / 240 tokens 2.27.083.108 I slot print_timing: id 0 | task 5777 | graphs reused = 5701 2.27.083.108 I slot print_timing: id 0 | task 5777 | graph reallocs = 0 / 0 (same size) / (changed size) 2.27.083.126 I slot release: id 0 | task 5777 | stop processing: n_tokens = 239, truncated = 0 2.27.087.184 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.168 (> 0.100 thold), f_keep = 0.130 2.27.092.573 I slot launch_slot_: id 0 | task 5863 | processing task, is_child = 0 2.30.517.074 I slot print_timing: id 0 | task 5863 | n_gen = 132, tg = 43.48 t/s, tg_3s = 43.81 t/s 2.30.769.533 I slot print_timing: id 0 | task 5863 | prompt eval time = 411.77 ms / 184 tokens ( 2.24 ms per token, 446.85 tokens per second) 2.30.769.535 I slot print_timing: id 0 | task 5863 | eval time = 3265.17 ms / 143 tokens ( 22.99 ms per token, 43.49 tokens per second) 2.30.769.536 I slot print_timing: id 0 | task 5863 | total time = 3676.94 ms / 327 tokens 2.30.769.537 I slot print_timing: id 0 | task 5863 | graphs reused = 5841 2.30.769.537 I slot print_timing: id 0 | task 5863 | graph reallocs = 0 / 0 (same size) / (changed size) 2.30.769.566 I slot release: id 0 | task 5863 | stop processing: n_tokens = 326, truncated = 0 2.30.774.138 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.140 (> 0.100 thold), f_keep = 0.092 2.30.782.225 I slot launch_slot_: id 0 | task 6009 | processing task, is_child = 0 2.32.452.151 I slot print_timing: id 0 | task 6009 | prompt eval time = 521.10 ms / 214 tokens ( 2.44 ms per token, 410.67 tokens per second) 2.32.452.158 I slot print_timing: id 0 | task 6009 | eval time = 1148.82 ms / 51 tokens ( 22.98 ms per token, 43.52 tokens per second) 2.32.452.158 I slot print_timing: id 0 | task 6009 | total time = 1669.92 ms / 265 tokens 2.32.452.159 I slot print_timing: id 0 | task 6009 | graphs reused = 5889 2.32.452.159 I slot print_timing: id 0 | task 6009 | graph reallocs = 0 / 0 (same size) / (changed size) 2.32.452.179 I slot release: id 0 | task 6009 | stop processing: n_tokens = 264, truncated = 0 2.32.456.450 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.161 (> 0.100 thold), f_keep = 0.114 2.32.462.524 I slot launch_slot_: id 0 | task 6063 | processing task, is_child = 0 2.33.586.304 I slot print_timing: id 0 | task 6063 | prompt eval time = 469.97 ms / 186 tokens ( 2.53 ms per token, 395.77 tokens per second) 2.33.586.310 I slot print_timing: id 0 | task 6063 | eval time = 653.80 ms / 29 tokens ( 23.35 ms per token, 42.83 tokens per second) 2.33.586.311 I slot print_timing: id 0 | task 6063 | total time = 1123.77 ms / 215 tokens 2.33.586.312 I slot print_timing: id 0 | task 6063 | graphs reused = 5916 2.33.586.312 I slot print_timing: id 0 | task 6063 | graph reallocs = 0 / 0 (same size) / (changed size) 2.33.586.329 I slot release: id 0 | task 6063 | stop processing: n_tokens = 214, truncated = 0 2.33.590.256 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.184 (> 0.100 thold), f_keep = 0.140 2.33.596.950 I slot launch_slot_: id 0 | task 6095 | processing task, is_child = 0 2.34.813.248 I slot print_timing: id 0 | task 6095 | prompt eval time = 410.82 ms / 163 tokens ( 2.52 ms per token, 396.77 tokens per second) 2.34.813.254 I slot print_timing: id 0 | task 6095 | eval time = 805.47 ms / 36 tokens ( 23.01 ms per token, 43.45 tokens per second) 2.34.813.255 I slot print_timing: id 0 | task 6095 | total time = 1216.29 ms / 199 tokens 2.34.813.256 I slot print_timing: id 0 | task 6095 | graphs reused = 5950 2.34.813.256 I slot print_timing: id 0 | task 6095 | graph reallocs = 0 / 0 (same size) / (changed size) 2.34.813.276 I slot release: id 0 | task 6095 | stop processing: n_tokens = 198, truncated = 0 2.34.817.652 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 2.34.823.048 I slot launch_slot_: id 0 | task 6134 | processing task, is_child = 0 2.35.868.181 I slot print_timing: id 0 | task 6134 | prompt eval time = 380.01 ms / 163 tokens ( 2.33 ms per token, 428.94 tokens per second) 2.35.868.189 I slot print_timing: id 0 | task 6134 | eval time = 665.12 ms / 30 tokens ( 22.93 ms per token, 43.60 tokens per second) 2.35.868.190 I slot print_timing: id 0 | task 6134 | total time = 1045.12 ms / 193 tokens 2.35.868.190 I slot print_timing: id 0 | task 6134 | graphs reused = 5978 2.35.868.191 I slot print_timing: id 0 | task 6134 | graph reallocs = 0 / 0 (same size) / (changed size) 2.35.868.210 I slot release: id 0 | task 6134 | stop processing: n_tokens = 192, truncated = 0 2.35.872.484 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.160 (> 0.100 thold), f_keep = 0.156 2.35.878.357 I slot launch_slot_: id 0 | task 6167 | processing task, is_child = 0 2.36.858.087 I slot print_timing: id 0 | task 6167 | prompt eval time = 472.85 ms / 187 tokens ( 2.53 ms per token, 395.48 tokens per second) 2.36.858.091 I slot print_timing: id 0 | task 6167 | eval time = 506.87 ms / 23 tokens ( 23.04 ms per token, 43.40 tokens per second) 2.36.858.091 I slot print_timing: id 0 | task 6167 | total time = 979.72 ms / 210 tokens 2.36.858.092 I slot print_timing: id 0 | task 6167 | graphs reused = 5999 2.36.858.093 I slot print_timing: id 0 | task 6167 | graph reallocs = 0 / 0 (same size) / (changed size) 2.36.858.110 I slot release: id 0 | task 6167 | stop processing: n_tokens = 209, truncated = 0 2.36.862.024 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.146 (> 0.100 thold), f_keep = 0.144 2.36.868.235 I slot launch_slot_: id 0 | task 6193 | processing task, is_child = 0 2.40.287.639 I slot print_timing: id 0 | task 6193 | prompt eval time = 473.08 ms / 205 tokens ( 2.31 ms per token, 433.33 tokens per second) 2.40.287.643 I slot print_timing: id 0 | task 6193 | eval time = 2946.32 ms / 123 tokens ( 24.15 ms per token, 41.41 tokens per second) 2.40.287.644 I slot print_timing: id 0 | task 6193 | total time = 3419.39 ms / 328 tokens 2.40.287.644 I slot print_timing: id 0 | task 6193 | graphs reused = 6119 2.40.287.645 I slot print_timing: id 0 | task 6193 | graph reallocs = 0 / 0 (same size) / (changed size) 2.40.287.663 I slot release: id 0 | task 6193 | stop processing: n_tokens = 327, truncated = 0 2.40.291.499 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.190 (> 0.100 thold), f_keep = 0.092 2.40.298.432 I slot launch_slot_: id 0 | task 6319 | processing task, is_child = 0 2.41.048.452 I slot print_timing: id 0 | task 6319 | prompt eval time = 380.24 ms / 158 tokens ( 2.41 ms per token, 415.53 tokens per second) 2.41.048.455 I slot print_timing: id 0 | task 6319 | eval time = 369.77 ms / 17 tokens ( 23.11 ms per token, 43.27 tokens per second) 2.41.048.456 I slot print_timing: id 0 | task 6319 | total time = 750.00 ms / 175 tokens 2.41.048.457 I slot print_timing: id 0 | task 6319 | graphs reused = 6134 2.41.048.457 I slot print_timing: id 0 | task 6319 | graph reallocs = 0 / 0 (same size) / (changed size) 2.41.048.474 I slot release: id 0 | task 6319 | stop processing: n_tokens = 174, truncated = 0 2.41.052.579 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.153 (> 0.100 thold), f_keep = 0.172 2.41.056.851 I slot launch_slot_: id 0 | task 6339 | processing task, is_child = 0 2.44.507.223 I slot print_timing: id 0 | task 6339 | n_gen = 132, tg = 43.58 t/s, tg_3s = 43.91 t/s 2.47.524.168 I slot print_timing: id 0 | task 6339 | n_gen = 262, tg = 43.33 t/s, tg_3s = 43.09 t/s 2.50.531.154 I slot print_timing: id 0 | task 6339 | n_gen = 391, tg = 43.19 t/s, tg_3s = 42.90 t/s 2.53.540.387 I slot print_timing: id 0 | task 6339 | n_gen = 520, tg = 43.11 t/s, tg_3s = 42.87 t/s 2.56.554.876 I slot print_timing: id 0 | task 6339 | n_gen = 649, tg = 43.05 t/s, tg_3s = 42.79 t/s 2.59.570.886 I slot print_timing: id 0 | task 6339 | n_gen = 778, tg = 43.00 t/s, tg_3s = 42.77 t/s 3.02.594.256 I slot print_timing: id 0 | task 6339 | n_gen = 907, tg = 42.95 t/s, tg_3s = 42.67 t/s 3.05.340.162 I slot print_timing: id 0 | task 6339 | prompt eval time = 444.14 ms / 196 tokens ( 2.27 ms per token, 441.30 tokens per second) 3.05.340.169 I slot print_timing: id 0 | task 6339 | eval time = 23839.15 ms / 1024 tokens ( 23.30 ms per token, 42.91 tokens per second) 3.05.340.169 I slot print_timing: id 0 | task 6339 | total time = 24283.30 ms / 1220 tokens 3.05.340.170 I slot print_timing: id 0 | task 6339 | graphs reused = 7152 3.05.340.170 I slot print_timing: id 0 | task 6339 | graph reallocs = 0 / 0 (same size) / (changed size) 3.05.340.190 I slot release: id 0 | task 6339 | stop processing: n_tokens = 1219, truncated = 0 3.05.344.179 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.236 (> 0.100 thold), f_keep = 0.025 3.05.356.923 I slot launch_slot_: id 0 | task 7366 | processing task, is_child = 0 3.06.119.473 I slot print_timing: id 0 | task 7366 | prompt eval time = 325.64 ms / 127 tokens ( 2.56 ms per token, 390.00 tokens per second) 3.06.119.479 I slot print_timing: id 0 | task 7366 | eval time = 436.90 ms / 20 tokens ( 22.99 ms per token, 43.49 tokens per second) 3.06.119.479 I slot print_timing: id 0 | task 7366 | total time = 762.54 ms / 147 tokens 3.06.119.480 I slot print_timing: id 0 | task 7366 | graphs reused = 7170 3.06.119.481 I slot print_timing: id 0 | task 7366 | graph reallocs = 0 / 0 (same size) / (changed size) 3.06.119.498 I slot release: id 0 | task 7366 | stop processing: n_tokens = 146, truncated = 0 3.06.123.545 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.224 (> 0.100 thold), f_keep = 0.205 3.06.127.311 I slot launch_slot_: id 0 | task 7389 | processing task, is_child = 0 3.09.476.944 I slot print_timing: id 0 | task 7389 | n_gen = 132, tg = 43.37 t/s, tg_3s = 43.70 t/s 3.10.345.120 I slot print_timing: id 0 | task 7389 | prompt eval time = 329.03 ms / 134 tokens ( 2.46 ms per token, 407.26 tokens per second) 3.10.345.127 I slot print_timing: id 0 | task 7389 | eval time = 3888.77 ms / 167 tokens ( 23.43 ms per token, 42.69 tokens per second) 3.10.345.128 I slot print_timing: id 0 | task 7389 | total time = 4217.80 ms / 301 tokens 3.10.345.128 I slot print_timing: id 0 | task 7389 | graphs reused = 7334 3.10.345.129 I slot print_timing: id 0 | task 7389 | graph reallocs = 0 / 0 (same size) / (changed size) 3.10.345.145 I slot release: id 0 | task 7389 | stop processing: n_tokens = 300, truncated = 0 3.10.348.665 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.100 3.10.354.358 I slot launch_slot_: id 0 | task 7559 | processing task, is_child = 0 3.12.656.927 I slot print_timing: id 0 | task 7559 | prompt eval time = 376.54 ms / 148 tokens ( 2.54 ms per token, 393.05 tokens per second) 3.12.656.930 I slot print_timing: id 0 | task 7559 | eval time = 1926.01 ms / 85 tokens ( 22.93 ms per token, 43.61 tokens per second) 3.12.656.931 I slot print_timing: id 0 | task 7559 | total time = 2302.56 ms / 233 tokens 3.12.656.932 I slot print_timing: id 0 | task 7559 | graphs reused = 7417 3.12.656.932 I slot print_timing: id 0 | task 7559 | graph reallocs = 0 / 0 (same size) / (changed size) 3.12.656.963 I slot release: id 0 | task 7559 | stop processing: n_tokens = 232, truncated = 0 3.12.661.284 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.129 3.12.667.710 I slot launch_slot_: id 0 | task 7647 | processing task, is_child = 0 3.16.020.548 I slot print_timing: id 0 | task 7647 | prompt eval time = 373.92 ms / 145 tokens ( 2.58 ms per token, 387.78 tokens per second) 3.16.020.552 I slot print_timing: id 0 | task 7647 | eval time = 2978.90 ms / 131 tokens ( 22.91 ms per token, 43.64 tokens per second) 3.16.020.552 I slot print_timing: id 0 | task 7647 | total time = 3352.83 ms / 276 tokens 3.16.020.553 I slot print_timing: id 0 | task 7647 | graphs reused = 7545 3.16.020.553 I slot print_timing: id 0 | task 7647 | graph reallocs = 0 / 0 (same size) / (changed size) 3.16.020.573 I slot release: id 0 | task 7647 | stop processing: n_tokens = 275, truncated = 0 3.16.024.930 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.150 (> 0.100 thold), f_keep = 0.109 3.16.031.334 I slot launch_slot_: id 0 | task 7781 | processing task, is_child = 0 3.17.255.117 I slot print_timing: id 0 | task 7781 | prompt eval time = 460.63 ms / 200 tokens ( 2.30 ms per token, 434.19 tokens per second) 3.17.255.123 I slot print_timing: id 0 | task 7781 | eval time = 763.14 ms / 33 tokens ( 23.85 ms per token, 41.93 tokens per second) 3.17.255.124 I slot print_timing: id 0 | task 7781 | total time = 1223.77 ms / 233 tokens 3.17.255.125 I slot print_timing: id 0 | task 7781 | graphs reused = 7576 3.17.255.125 I slot print_timing: id 0 | task 7781 | graph reallocs = 0 / 0 (same size) / (changed size) 3.17.255.143 I slot release: id 0 | task 7781 | stop processing: n_tokens = 232, truncated = 0 3.17.259.897 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 232, t_last = 329634637423 3.17.266.460 I slot launch_slot_: id 0 | task 7817 | processing task, is_child = 0 3.20.975.139 I slot print_timing: id 0 | task 7817 | n_gen = 131, tg = 43.05 t/s, tg_3s = 43.38 t/s 3.23.985.983 I slot print_timing: id 0 | task 7817 | n_gen = 260, tg = 42.95 t/s, tg_3s = 42.85 t/s 3.26.999.252 I slot print_timing: id 0 | task 7817 | n_gen = 389, tg = 42.90 t/s, tg_3s = 42.81 t/s 3.30.014.158 I slot print_timing: id 0 | task 7817 | n_gen = 518, tg = 42.87 t/s, tg_3s = 42.79 t/s 3.33.033.418 I slot print_timing: id 0 | task 7817 | n_gen = 647, tg = 42.84 t/s, tg_3s = 42.73 t/s 3.36.034.153 I slot print_timing: id 0 | task 7817 | n_gen = 775, tg = 42.81 t/s, tg_3s = 42.66 t/s 3.39.056.644 I slot print_timing: id 0 | task 7817 | n_gen = 904, tg = 42.79 t/s, tg_3s = 42.68 t/s 3.41.874.665 I slot print_timing: id 0 | task 7817 | prompt eval time = 689.19 ms / 326 tokens ( 2.11 ms per token, 473.02 tokens per second) 3.41.874.671 I slot print_timing: id 0 | task 7817 | eval time = 23919.01 ms / 1024 tokens ( 23.38 ms per token, 42.77 tokens per second) 3.41.874.672 I slot print_timing: id 0 | task 7817 | total time = 24608.20 ms / 1350 tokens 3.41.874.672 I slot print_timing: id 0 | task 7817 | graphs reused = 8594 3.41.874.673 I slot print_timing: id 0 | task 7817 | graph reallocs = 0 / 0 (same size) / (changed size) 3.41.874.704 I slot release: id 0 | task 7817 | stop processing: n_tokens = 1349, truncated = 0 3.41.878.904 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.022 3.41.894.468 I slot launch_slot_: id 0 | task 8844 | processing task, is_child = 0 3.43.818.223 I slot print_timing: id 0 | task 8844 | prompt eval time = 359.96 ms / 148 tokens ( 2.43 ms per token, 411.15 tokens per second) 3.43.818.226 I slot print_timing: id 0 | task 8844 | eval time = 1563.78 ms / 69 tokens ( 23.00 ms per token, 43.48 tokens per second) 3.43.818.227 I slot print_timing: id 0 | task 8844 | total time = 1923.74 ms / 217 tokens 3.43.818.227 I slot print_timing: id 0 | task 8844 | graphs reused = 8661 3.43.818.228 I slot print_timing: id 0 | task 8844 | graph reallocs = 0 / 0 (same size) / (changed size) 3.43.818.253 I slot release: id 0 | task 8844 | stop processing: n_tokens = 216, truncated = 0 3.43.822.283 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.139 3.43.824.133 I slot launch_slot_: id 0 | task 8916 | processing task, is_child = 0 3.47.230.281 I slot print_timing: id 0 | task 8916 | n_gen = 132, tg = 43.45 t/s, tg_3s = 43.79 t/s 3.50.244.706 I slot print_timing: id 0 | task 8916 | n_gen = 262, tg = 43.29 t/s, tg_3s = 43.13 t/s 3.51.108.274 I slot print_timing: id 0 | task 8916 | prompt eval time = 391.44 ms / 175 tokens ( 2.24 ms per token, 447.07 tokens per second) 3.51.108.280 I slot print_timing: id 0 | task 8916 | eval time = 6892.69 ms / 299 tokens ( 23.13 ms per token, 43.23 tokens per second) 3.51.108.281 I slot print_timing: id 0 | task 8916 | total time = 7284.12 ms / 474 tokens 3.51.108.282 I slot print_timing: id 0 | task 8916 | graphs reused = 8957 3.51.108.282 I slot print_timing: id 0 | task 8916 | graph reallocs = 0 / 0 (same size) / (changed size) 3.51.108.300 I slot release: id 0 | task 8916 | stop processing: n_tokens = 473, truncated = 0 3.51.112.710 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.131 (> 0.100 thold), f_keep = 0.063 3.51.121.793 I slot launch_slot_: id 0 | task 9218 | processing task, is_child = 0 3.52.551.183 I slot print_timing: id 0 | task 9218 | prompt eval time = 533.06 ms / 229 tokens ( 2.33 ms per token, 429.59 tokens per second) 3.52.551.188 I slot print_timing: id 0 | task 9218 | eval time = 896.32 ms / 40 tokens ( 22.98 ms per token, 43.51 tokens per second) 3.52.551.189 I slot print_timing: id 0 | task 9218 | total time = 1429.38 ms / 269 tokens 3.52.551.190 I slot print_timing: id 0 | task 9218 | graphs reused = 8994 3.52.551.190 I slot print_timing: id 0 | task 9218 | graph reallocs = 0 / 0 (same size) / (changed size) 3.52.551.210 I slot release: id 0 | task 9218 | stop processing: n_tokens = 268, truncated = 0 3.52.555.564 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 3.52.563.225 I slot launch_slot_: id 0 | task 9261 | processing task, is_child = 0 3.56.097.864 I slot print_timing: id 0 | task 9261 | n_gen = 132, tg = 43.54 t/s, tg_3s = 43.87 t/s 3.59.111.645 I slot print_timing: id 0 | task 9261 | n_gen = 262, tg = 43.34 t/s, tg_3s = 43.14 t/s 4.02.121.650 I slot print_timing: id 0 | task 9261 | n_gen = 391, tg = 43.18 t/s, tg_3s = 42.86 t/s 4.05.133.572 I slot print_timing: id 0 | task 9261 | n_gen = 520, tg = 43.09 t/s, tg_3s = 42.83 t/s 4.08.151.295 I slot print_timing: id 0 | task 9261 | n_gen = 648, tg = 42.96 t/s, tg_3s = 42.42 t/s 4.11.158.513 I slot print_timing: id 0 | task 9261 | n_gen = 776, tg = 42.89 t/s, tg_3s = 42.56 t/s 4.14.159.282 I slot print_timing: id 0 | task 9261 | n_gen = 904, tg = 42.86 t/s, tg_3s = 42.66 t/s 4.16.971.784 I slot print_timing: id 0 | task 9261 | prompt eval time = 525.85 ms / 238 tokens ( 2.21 ms per token, 452.60 tokens per second) 4.16.971.791 I slot print_timing: id 0 | task 9261 | eval time = 23882.70 ms / 1024 tokens ( 23.35 ms per token, 42.83 tokens per second) 4.16.971.791 I slot print_timing: id 0 | task 9261 | total time = 24408.55 ms / 1262 tokens 4.16.971.792 I slot print_timing: id 0 | task 9261 | graphs reused = 10012 4.16.971.792 I slot print_timing: id 0 | task 9261 | graph reallocs = 0 / 0 (same size) / (changed size) 4.16.971.815 I slot release: id 0 | task 9261 | stop processing: n_tokens = 1261, truncated = 0 4.16.976.074 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.204 (> 0.100 thold), f_keep = 0.026 4.16.990.623 I slot launch_slot_: id 0 | task 10288 | processing task, is_child = 0 4.17.648.458 I slot print_timing: id 0 | task 10288 | prompt eval time = 377.64 ms / 162 tokens ( 2.33 ms per token, 428.98 tokens per second) 4.17.648.464 I slot print_timing: id 0 | task 10288 | eval time = 280.19 ms / 12 tokens ( 25.47 ms per token, 39.26 tokens per second) 4.17.648.464 I slot print_timing: id 0 | task 10288 | total time = 657.83 ms / 174 tokens 4.17.648.465 I slot print_timing: id 0 | task 10288 | graphs reused = 10022 4.17.648.466 I slot print_timing: id 0 | task 10288 | graph reallocs = 0 / 0 (same size) / (changed size) 4.17.648.488 I slot release: id 0 | task 10288 | stop processing: n_tokens = 173, truncated = 0 4.17.652.236 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.173 4.17.653.895 I slot launch_slot_: id 0 | task 10303 | processing task, is_child = 0 4.18.641.565 I slot print_timing: id 0 | task 10303 | prompt eval time = 411.15 ms / 169 tokens ( 2.43 ms per token, 411.04 tokens per second) 4.18.641.572 I slot print_timing: id 0 | task 10303 | eval time = 576.51 ms / 26 tokens ( 23.06 ms per token, 43.36 tokens per second) 4.18.641.572 I slot print_timing: id 0 | task 10303 | total time = 987.66 ms / 195 tokens 4.18.641.573 I slot print_timing: id 0 | task 10303 | graphs reused = 10046 4.18.641.573 I slot print_timing: id 0 | task 10303 | graph reallocs = 0 / 0 (same size) / (changed size) 4.18.641.591 I slot release: id 0 | task 10303 | stop processing: n_tokens = 194, truncated = 0 4.18.645.752 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 4.18.650.865 I slot launch_slot_: id 0 | task 10332 | processing task, is_child = 0 4.19.715.725 I slot print_timing: id 0 | task 10332 | prompt eval time = 441.57 ms / 180 tokens ( 2.45 ms per token, 407.63 tokens per second) 4.19.715.731 I slot print_timing: id 0 | task 10332 | eval time = 623.28 ms / 28 tokens ( 23.08 ms per token, 43.32 tokens per second) 4.19.715.732 I slot print_timing: id 0 | task 10332 | total time = 1064.85 ms / 208 tokens 4.19.715.733 I slot print_timing: id 0 | task 10332 | graphs reused = 10072 4.19.715.733 I slot print_timing: id 0 | task 10332 | graph reallocs = 0 / 0 (same size) / (changed size) 4.19.715.751 I slot release: id 0 | task 10332 | stop processing: n_tokens = 207, truncated = 0 4.19.720.137 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 4.19.726.695 I slot launch_slot_: id 0 | task 10363 | processing task, is_child = 0 4.21.233.842 I slot print_timing: id 0 | task 10363 | prompt eval time = 481.92 ms / 203 tokens ( 2.37 ms per token, 421.23 tokens per second) 4.21.233.848 I slot print_timing: id 0 | task 10363 | eval time = 1025.22 ms / 45 tokens ( 23.30 ms per token, 42.92 tokens per second) 4.21.233.849 I slot print_timing: id 0 | task 10363 | total time = 1507.14 ms / 248 tokens 4.21.233.850 I slot print_timing: id 0 | task 10363 | graphs reused = 10115 4.21.233.850 I slot print_timing: id 0 | task 10363 | graph reallocs = 0 / 0 (same size) / (changed size) 4.21.233.869 I slot release: id 0 | task 10363 | stop processing: n_tokens = 247, truncated = 0 4.21.237.766 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 4.21.244.564 I slot launch_slot_: id 0 | task 10411 | processing task, is_child = 0 4.22.129.968 I slot print_timing: id 0 | task 10411 | prompt eval time = 409.49 ms / 157 tokens ( 2.61 ms per token, 383.41 tokens per second) 4.22.129.971 I slot print_timing: id 0 | task 10411 | eval time = 475.90 ms / 21 tokens ( 23.80 ms per token, 42.03 tokens per second) 4.22.129.972 I slot print_timing: id 0 | task 10411 | total time = 885.39 ms / 178 tokens 4.22.129.972 I slot print_timing: id 0 | task 10411 | graphs reused = 10134 4.22.129.973 I slot print_timing: id 0 | task 10411 | graph reallocs = 0 / 0 (same size) / (changed size) 4.22.129.989 I slot release: id 0 | task 10411 | stop processing: n_tokens = 177, truncated = 0 4.22.134.193 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.140 (> 0.100 thold), f_keep = 0.169 4.22.137.532 I slot launch_slot_: id 0 | task 10435 | processing task, is_child = 0 4.24.104.302 I slot print_timing: id 0 | task 10435 | prompt eval time = 473.78 ms / 214 tokens ( 2.21 ms per token, 451.69 tokens per second) 4.24.104.308 I slot print_timing: id 0 | task 10435 | eval time = 1492.98 ms / 65 tokens ( 23.33 ms per token, 42.87 tokens per second) 4.24.104.314 I slot print_timing: id 0 | task 10435 | total time = 1966.76 ms / 279 tokens 4.24.104.315 I slot print_timing: id 0 | task 10435 | graphs reused = 10196 4.24.104.315 I slot print_timing: id 0 | task 10435 | graph reallocs = 0 / 0 (same size) / (changed size) 4.24.104.341 I slot release: id 0 | task 10435 | stop processing: n_tokens = 278, truncated = 0 4.24.108.886 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.183 (> 0.100 thold), f_keep = 0.108 4.24.117.004 I slot launch_slot_: id 0 | task 10503 | processing task, is_child = 0 4.25.423.918 I slot print_timing: id 0 | task 10503 | prompt eval time = 377.78 ms / 164 tokens ( 2.30 ms per token, 434.12 tokens per second) 4.25.423.921 I slot print_timing: id 0 | task 10503 | eval time = 929.13 ms / 41 tokens ( 23.23 ms per token, 43.05 tokens per second) 4.25.423.922 I slot print_timing: id 0 | task 10503 | total time = 1306.91 ms / 205 tokens 4.25.423.923 I slot print_timing: id 0 | task 10503 | graphs reused = 10235 4.25.423.923 I slot print_timing: id 0 | task 10503 | graph reallocs = 0 / 0 (same size) / (changed size) 4.25.423.940 I slot release: id 0 | task 10503 | stop processing: n_tokens = 204, truncated = 0 4.25.427.988 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.181 (> 0.100 thold), f_keep = 0.147 4.25.431.728 I slot launch_slot_: id 0 | task 10547 | processing task, is_child = 0 4.26.554.700 I slot print_timing: id 0 | task 10547 | prompt eval time = 409.41 ms / 166 tokens ( 2.47 ms per token, 405.47 tokens per second) 4.26.554.706 I slot print_timing: id 0 | task 10547 | eval time = 713.56 ms / 32 tokens ( 23.02 ms per token, 43.44 tokens per second) 4.26.554.707 I slot print_timing: id 0 | task 10547 | total time = 1122.97 ms / 198 tokens 4.26.554.708 I slot print_timing: id 0 | task 10547 | graphs reused = 10265 4.26.554.709 I slot print_timing: id 0 | task 10547 | graph reallocs = 0 / 0 (same size) / (changed size) 4.26.554.724 I slot release: id 0 | task 10547 | stop processing: n_tokens = 197, truncated = 0 4.26.559.308 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.108 (> 0.100 thold), f_keep = 0.152 4.26.564.989 I slot launch_slot_: id 0 | task 10582 | processing task, is_child = 0 4.30.195.939 I slot print_timing: id 0 | task 10582 | n_gen = 131, tg = 43.28 t/s, tg_3s = 43.62 t/s 4.32.247.945 I slot print_timing: id 0 | task 10582 | prompt eval time = 627.55 ms / 277 tokens ( 2.27 ms per token, 441.40 tokens per second) 4.32.247.951 I slot print_timing: id 0 | task 10582 | eval time = 5055.40 ms / 219 tokens ( 23.19 ms per token, 43.12 tokens per second) 4.32.247.952 I slot print_timing: id 0 | task 10582 | total time = 5682.95 ms / 496 tokens 4.32.247.953 I slot print_timing: id 0 | task 10582 | graphs reused = 10482 4.32.247.953 I slot print_timing: id 0 | task 10582 | graph reallocs = 0 / 0 (same size) / (changed size) 4.32.247.979 I slot release: id 0 | task 10582 | stop processing: n_tokens = 495, truncated = 0 4.32.252.611 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.121 (> 0.100 thold), f_keep = 0.061 4.32.264.626 I slot launch_slot_: id 0 | task 10804 | processing task, is_child = 0 4.35.812.489 I slot print_timing: id 0 | task 10804 | n_gen = 132, tg = 43.37 t/s, tg_3s = 43.71 t/s 4.36.511.856 I slot print_timing: id 0 | task 10804 | prompt eval time = 527.68 ms / 248 tokens ( 2.13 ms per token, 469.98 tokens per second) 4.36.511.866 I slot print_timing: id 0 | task 10804 | eval time = 3719.54 ms / 162 tokens ( 23.10 ms per token, 43.28 tokens per second) 4.36.511.867 I slot print_timing: id 0 | task 10804 | total time = 4247.22 ms / 410 tokens 4.36.511.868 I slot print_timing: id 0 | task 10804 | graphs reused = 10641 4.36.511.868 I slot print_timing: id 0 | task 10804 | graph reallocs = 0 / 0 (same size) / (changed size) 4.36.511.889 I slot release: id 0 | task 10804 | stop processing: n_tokens = 409, truncated = 0 4.36.515.967 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.189 (> 0.100 thold), f_keep = 0.073 4.36.525.450 I slot launch_slot_: id 0 | task 10969 | processing task, is_child = 0 4.38.630.428 I slot print_timing: id 0 | task 10969 | prompt eval time = 409.38 ms / 159 tokens ( 2.57 ms per token, 388.39 tokens per second) 4.38.630.431 I slot print_timing: id 0 | task 10969 | eval time = 1695.59 ms / 75 tokens ( 22.91 ms per token, 43.64 tokens per second) 4.38.630.432 I slot print_timing: id 0 | task 10969 | total time = 2104.97 ms / 234 tokens 4.38.630.432 I slot print_timing: id 0 | task 10969 | graphs reused = 10714 4.38.630.438 I slot print_timing: id 0 | task 10969 | graph reallocs = 0 / 0 (same size) / (changed size) 4.38.630.456 I slot release: id 0 | task 10969 | stop processing: n_tokens = 233, truncated = 0 4.38.634.647 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.153 (> 0.100 thold), f_keep = 0.129 4.38.638.700 I slot launch_slot_: id 0 | task 11047 | processing task, is_child = 0 4.40.357.987 I slot print_timing: id 0 | task 11047 | prompt eval time = 480.92 ms / 196 tokens ( 2.45 ms per token, 407.55 tokens per second) 4.40.357.994 I slot print_timing: id 0 | task 11047 | eval time = 1238.36 ms / 55 tokens ( 22.93 ms per token, 43.61 tokens per second) 4.40.357.995 I slot print_timing: id 0 | task 11047 | total time = 1719.28 ms / 251 tokens 4.40.357.995 I slot print_timing: id 0 | task 11047 | graphs reused = 10767 4.40.357.996 I slot print_timing: id 0 | task 11047 | graph reallocs = 0 / 0 (same size) / (changed size) 4.40.358.015 I slot release: id 0 | task 11047 | stop processing: n_tokens = 250, truncated = 0 4.40.361.835 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.120 4.40.368.909 I slot launch_slot_: id 0 | task 11105 | processing task, is_child = 0 4.41.322.603 I slot print_timing: id 0 | task 11105 | prompt eval time = 379.40 ms / 150 tokens ( 2.53 ms per token, 395.36 tokens per second) 4.41.322.612 I slot print_timing: id 0 | task 11105 | eval time = 574.28 ms / 26 tokens ( 22.97 ms per token, 43.53 tokens per second) 4.41.322.613 I slot print_timing: id 0 | task 11105 | total time = 953.68 ms / 176 tokens 4.41.322.613 I slot print_timing: id 0 | task 11105 | graphs reused = 10791 4.41.322.614 I slot print_timing: id 0 | task 11105 | graph reallocs = 0 / 0 (same size) / (changed size) 4.41.322.632 I slot release: id 0 | task 11105 | stop processing: n_tokens = 175, truncated = 0 4.41.326.945 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 4.41.330.189 I slot launch_slot_: id 0 | task 11134 | processing task, is_child = 0 4.43.781.278 I slot print_timing: id 0 | task 11134 | prompt eval time = 474.37 ms / 215 tokens ( 2.21 ms per token, 453.23 tokens per second) 4.43.781.282 I slot print_timing: id 0 | task 11134 | eval time = 1976.70 ms / 87 tokens ( 22.98 ms per token, 43.51 tokens per second) 4.43.781.282 I slot print_timing: id 0 | task 11134 | total time = 2451.08 ms / 302 tokens 4.43.781.283 I slot print_timing: id 0 | task 11134 | graphs reused = 10875 4.43.781.283 I slot print_timing: id 0 | task 11134 | graph reallocs = 0 / 0 (same size) / (changed size) 4.43.781.308 I slot release: id 0 | task 11134 | stop processing: n_tokens = 301, truncated = 0 4.43.786.753 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 301, t_last = 329721163588 4.43.794.924 I slot launch_slot_: id 0 | task 11224 | processing task, is_child = 0 4.45.190.207 I slot print_timing: id 0 | task 11224 | prompt eval time = 690.48 ms / 327 tokens ( 2.11 ms per token, 473.58 tokens per second) 4.45.190.214 I slot print_timing: id 0 | task 11224 | eval time = 704.79 ms / 31 tokens ( 23.49 ms per token, 42.57 tokens per second) 4.45.190.215 I slot print_timing: id 0 | task 11224 | total time = 1395.28 ms / 358 tokens 4.45.190.216 I slot print_timing: id 0 | task 11224 | graphs reused = 10904 4.45.190.216 I slot print_timing: id 0 | task 11224 | graph reallocs = 0 / 0 (same size) / (changed size) 4.45.190.239 I slot release: id 0 | task 11224 | stop processing: n_tokens = 357, truncated = 0 4.45.195.486 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 357, t_last = 329722572519 4.45.206.075 I slot launch_slot_: id 0 | task 11258 | processing task, is_child = 0 4.46.730.507 I slot print_timing: id 0 | task 11258 | prompt eval time = 799.12 ms / 399 tokens ( 2.00 ms per token, 499.30 tokens per second) 4.46.730.513 I slot print_timing: id 0 | task 11258 | eval time = 725.31 ms / 32 tokens ( 23.40 ms per token, 42.74 tokens per second) 4.46.730.513 I slot print_timing: id 0 | task 11258 | total time = 1524.42 ms / 431 tokens 4.46.730.514 I slot print_timing: id 0 | task 11258 | graphs reused = 10934 4.46.730.515 I slot print_timing: id 0 | task 11258 | graph reallocs = 0 / 0 (same size) / (changed size) 4.46.730.549 I slot release: id 0 | task 11258 | stop processing: n_tokens = 430, truncated = 0 4.46.736.149 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 430, t_last = 329724112829 4.46.748.801 I slot launch_slot_: id 0 | task 11293 | processing task, is_child = 0 4.50.667.072 I slot print_timing: id 0 | task 11293 | n_gen = 130, tg = 42.83 t/s, tg_3s = 43.16 t/s 4.51.039.734 I slot print_timing: id 0 | task 11293 | prompt eval time = 906.29 ms / 439 tokens ( 2.06 ms per token, 484.39 tokens per second) 4.51.039.738 I slot print_timing: id 0 | task 11293 | eval time = 3384.62 ms / 146 tokens ( 23.34 ms per token, 42.84 tokens per second) 4.51.039.738 I slot print_timing: id 0 | task 11293 | total time = 4290.92 ms / 585 tokens 4.51.039.739 I slot print_timing: id 0 | task 11293 | graphs reused = 11077 4.51.039.740 I slot print_timing: id 0 | task 11293 | graph reallocs = 0 / 0 (same size) / (changed size) 4.51.039.781 I slot release: id 0 | task 11293 | stop processing: n_tokens = 584, truncated = 0 4.51.045.632 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 584, t_last = 329728422061 4.51.060.148 I slot launch_slot_: id 0 | task 11442 | processing task, is_child = 0 4.52.671.611 I slot print_timing: id 0 | task 11442 | prompt eval time = 794.78 ms / 413 tokens ( 1.92 ms per token, 519.64 tokens per second) 4.52.671.618 I slot print_timing: id 0 | task 11442 | eval time = 816.68 ms / 35 tokens ( 24.02 ms per token, 41.63 tokens per second) 4.52.671.619 I slot print_timing: id 0 | task 11442 | total time = 1611.45 ms / 448 tokens 4.52.671.619 I slot print_timing: id 0 | task 11442 | graphs reused = 11110 4.52.671.620 I slot print_timing: id 0 | task 11442 | graph reallocs = 0 / 0 (same size) / (changed size) 4.52.671.645 I slot release: id 0 | task 11442 | stop processing: n_tokens = 447, truncated = 0 4.52.676.401 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 4.52.689.307 I slot launch_slot_: id 0 | task 11480 | processing task, is_child = 0 4.56.269.599 I slot print_timing: id 0 | task 11480 | n_gen = 131, tg = 43.29 t/s, tg_3s = 43.62 t/s 4.59.277.296 I slot print_timing: id 0 | task 11480 | n_gen = 260, tg = 43.09 t/s, tg_3s = 42.89 t/s 4.59.394.105 I slot print_timing: id 0 | task 11480 | prompt eval time = 577.30 ms / 268 tokens ( 2.15 ms per token, 464.23 tokens per second) 4.59.394.111 I slot print_timing: id 0 | task 11480 | eval time = 6127.49 ms / 265 tokens ( 23.21 ms per token, 43.08 tokens per second) 4.59.394.111 I slot print_timing: id 0 | task 11480 | total time = 6704.79 ms / 533 tokens 4.59.394.112 I slot print_timing: id 0 | task 11480 | graphs reused = 11372 4.59.394.112 I slot print_timing: id 0 | task 11480 | graph reallocs = 0 / 0 (same size) / (changed size) 4.59.394.138 I slot release: id 0 | task 11480 | stop processing: n_tokens = 532, truncated = 0 4.59.399.540 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 532, t_last = 329736776418 4.59.407.672 I slot launch_slot_: id 0 | task 11748 | processing task, is_child = 0 5.03.216.517 I slot print_timing: id 0 | task 11748 | n_gen = 130, tg = 42.89 t/s, tg_3s = 43.22 t/s 5.05.570.471 I slot print_timing: id 0 | task 11748 | prompt eval time = 801.23 ms / 395 tokens ( 2.03 ms per token, 492.99 tokens per second) 5.05.570.482 I slot print_timing: id 0 | task 11748 | eval time = 5361.56 ms / 231 tokens ( 23.31 ms per token, 42.90 tokens per second) 5.05.570.482 I slot print_timing: id 0 | task 11748 | total time = 6162.79 ms / 626 tokens 5.05.570.488 I slot print_timing: id 0 | task 11748 | graphs reused = 11600 5.05.570.489 I slot print_timing: id 0 | task 11748 | graph reallocs = 0 / 0 (same size) / (changed size) 5.05.570.515 I slot release: id 0 | task 11748 | stop processing: n_tokens = 625, truncated = 0 5.05.575.641 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 625, t_last = 329742952795 5.05.589.990 I slot launch_slot_: id 0 | task 11982 | processing task, is_child = 0 5.08.206.590 I slot print_timing: id 0 | task 11982 | prompt eval time = 800.93 ms / 390 tokens ( 2.05 ms per token, 486.93 tokens per second) 5.08.206.597 I slot print_timing: id 0 | task 11982 | eval time = 1815.65 ms / 79 tokens ( 23.28 ms per token, 42.96 tokens per second) 5.08.206.597 I slot print_timing: id 0 | task 11982 | total time = 2616.59 ms / 469 tokens 5.08.206.598 I slot print_timing: id 0 | task 11982 | graphs reused = 11677 5.08.206.598 I slot print_timing: id 0 | task 11982 | graph reallocs = 0 / 0 (same size) / (changed size) 5.08.206.632 I slot release: id 0 | task 11982 | stop processing: n_tokens = 468, truncated = 0 5.08.211.705 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 468, t_last = 329745588913 5.08.224.732 I slot launch_slot_: id 0 | task 12064 | processing task, is_child = 0 5.11.876.326 I slot print_timing: id 0 | task 12064 | n_gen = 131, tg = 43.12 t/s, tg_3s = 43.45 t/s 5.14.887.587 I slot print_timing: id 0 | task 12064 | n_gen = 260, tg = 42.98 t/s, tg_3s = 42.84 t/s 5.17.899.875 I slot print_timing: id 0 | task 12064 | n_gen = 389, tg = 42.93 t/s, tg_3s = 42.82 t/s 5.20.915.474 I slot print_timing: id 0 | task 12064 | n_gen = 518, tg = 42.89 t/s, tg_3s = 42.78 t/s 5.23.933.014 I slot print_timing: id 0 | task 12064 | n_gen = 647, tg = 42.86 t/s, tg_3s = 42.75 t/s 5.26.955.880 I slot print_timing: id 0 | task 12064 | n_gen = 776, tg = 42.83 t/s, tg_3s = 42.67 t/s 5.29.956.270 I slot print_timing: id 0 | task 12064 | n_gen = 904, tg = 42.81 t/s, tg_3s = 42.66 t/s 5.32.772.145 I slot print_timing: id 0 | task 12064 | prompt eval time = 636.55 ms / 304 tokens ( 2.09 ms per token, 477.57 tokens per second) 5.32.772.151 I slot print_timing: id 0 | task 12064 | eval time = 23910.85 ms / 1024 tokens ( 23.37 ms per token, 42.78 tokens per second) 5.32.772.152 I slot print_timing: id 0 | task 12064 | total time = 24547.40 ms / 1328 tokens 5.32.772.153 I slot print_timing: id 0 | task 12064 | graphs reused = 12695 5.32.772.153 I slot print_timing: id 0 | task 12064 | graph reallocs = 0 / 0 (same size) / (changed size) 5.32.772.180 I slot release: id 0 | task 12064 | stop processing: n_tokens = 1327, truncated = 0 5.32.777.416 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.104 (> 0.100 thold), f_keep = 0.023 5.32.788.569 I slot launch_slot_: id 0 | task 13091 | processing task, is_child = 0 5.36.445.794 I slot print_timing: id 0 | task 13091 | n_gen = 131, tg = 43.02 t/s, tg_3s = 43.35 t/s 5.38.778.369 I slot print_timing: id 0 | task 13091 | prompt eval time = 635.51 ms / 289 tokens ( 2.20 ms per token, 454.75 tokens per second) 5.38.778.375 I slot print_timing: id 0 | task 13091 | eval time = 5354.28 ms / 231 tokens ( 23.28 ms per token, 42.96 tokens per second) 5.38.778.376 I slot print_timing: id 0 | task 13091 | total time = 5989.79 ms / 520 tokens 5.38.778.377 I slot print_timing: id 0 | task 13091 | graphs reused = 12923 5.38.778.377 I slot print_timing: id 0 | task 13091 | graph reallocs = 0 / 0 (same size) / (changed size) 5.38.778.399 I slot release: id 0 | task 13091 | stop processing: n_tokens = 519, truncated = 0 5.38.783.695 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 519, t_last = 329776160679 5.38.795.899 I slot launch_slot_: id 0 | task 13325 | processing task, is_child = 0 5.40.009.879 I slot print_timing: id 0 | task 13325 | prompt eval time = 725.27 ms / 360 tokens ( 2.01 ms per token, 496.37 tokens per second) 5.40.009.885 I slot print_timing: id 0 | task 13325 | eval time = 488.70 ms / 22 tokens ( 23.27 ms per token, 42.97 tokens per second) 5.40.009.886 I slot print_timing: id 0 | task 13325 | total time = 1213.97 ms / 382 tokens 5.40.009.886 I slot print_timing: id 0 | task 13325 | graphs reused = 12943 5.40.009.887 I slot print_timing: id 0 | task 13325 | graph reallocs = 0 / 0 (same size) / (changed size) 5.40.009.917 I slot release: id 0 | task 13325 | stop processing: n_tokens = 381, truncated = 0 5.40.015.062 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 381, t_last = 329777392197 5.40.026.931 I slot launch_slot_: id 0 | task 13350 | processing task, is_child = 0 5.43.727.763 I slot print_timing: id 0 | task 13350 | n_gen = 131, tg = 43.16 t/s, tg_3s = 43.49 t/s 5.45.705.267 I slot print_timing: id 0 | task 13350 | prompt eval time = 688.95 ms / 317 tokens ( 2.17 ms per token, 460.12 tokens per second) 5.45.705.270 I slot print_timing: id 0 | task 13350 | eval time = 4989.38 ms / 216 tokens ( 23.21 ms per token, 43.09 tokens per second) 5.45.705.272 I slot print_timing: id 0 | task 13350 | total time = 5678.32 ms / 533 tokens 5.45.705.272 I slot print_timing: id 0 | task 13350 | graphs reused = 13156 5.45.705.273 I slot print_timing: id 0 | task 13350 | graph reallocs = 0 / 0 (same size) / (changed size) 5.45.705.299 I slot release: id 0 | task 13350 | stop processing: n_tokens = 532, truncated = 0 5.45.710.183 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.121 (> 0.100 thold), f_keep = 0.056 5.45.718.789 I slot launch_slot_: id 0 | task 13569 | processing task, is_child = 0 5.46.691.286 I slot print_timing: id 0 | task 13569 | prompt eval time = 556.43 ms / 248 tokens ( 2.24 ms per token, 445.70 tokens per second) 5.46.691.290 I slot print_timing: id 0 | task 13569 | eval time = 416.06 ms / 19 tokens ( 23.11 ms per token, 43.26 tokens per second) 5.46.691.291 I slot print_timing: id 0 | task 13569 | total time = 972.49 ms / 267 tokens 5.46.691.291 I slot print_timing: id 0 | task 13569 | graphs reused = 13172 5.46.691.292 I slot print_timing: id 0 | task 13569 | graph reallocs = 0 / 0 (same size) / (changed size) 5.46.691.312 I slot release: id 0 | task 13569 | stop processing: n_tokens = 266, truncated = 0 5.46.696.422 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 266, t_last = 329784073592 5.46.704.567 I slot launch_slot_: id 0 | task 13591 | processing task, is_child = 0 5.48.301.845 I slot print_timing: id 0 | task 13591 | prompt eval time = 693.71 ms / 331 tokens ( 2.10 ms per token, 477.15 tokens per second) 5.48.301.852 I slot print_timing: id 0 | task 13591 | eval time = 903.56 ms / 40 tokens ( 23.17 ms per token, 43.16 tokens per second) 5.48.301.852 I slot print_timing: id 0 | task 13591 | total time = 1597.27 ms / 371 tokens 5.48.301.853 I slot print_timing: id 0 | task 13591 | graphs reused = 13210 5.48.301.853 I slot print_timing: id 0 | task 13591 | graph reallocs = 0 / 0 (same size) / (changed size) 5.48.301.877 I slot release: id 0 | task 13591 | stop processing: n_tokens = 370, truncated = 0 5.48.306.565 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 5.48.317.191 I slot launch_slot_: id 0 | task 13634 | processing task, is_child = 0 5.49.879.748 I slot print_timing: id 0 | task 13634 | prompt eval time = 604.66 ms / 280 tokens ( 2.16 ms per token, 463.07 tokens per second) 5.49.879.756 I slot print_timing: id 0 | task 13634 | eval time = 957.88 ms / 42 tokens ( 23.36 ms per token, 42.80 tokens per second) 5.49.879.757 I slot print_timing: id 0 | task 13634 | total time = 1562.55 ms / 322 tokens 5.49.879.757 I slot print_timing: id 0 | task 13634 | graphs reused = 13250 5.49.879.760 I slot print_timing: id 0 | task 13634 | graph reallocs = 0 / 0 (same size) / (changed size) 5.49.879.790 I slot release: id 0 | task 13634 | stop processing: n_tokens = 321, truncated = 0 5.49.884.477 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.119 (> 0.100 thold), f_keep = 0.093 5.49.892.044 I slot launch_slot_: id 0 | task 13679 | processing task, is_child = 0 5.50.978.325 I slot print_timing: id 0 | task 13679 | prompt eval time = 578.21 ms / 252 tokens ( 2.29 ms per token, 435.82 tokens per second) 5.50.978.329 I slot print_timing: id 0 | task 13679 | eval time = 508.06 ms / 23 tokens ( 23.09 ms per token, 43.30 tokens per second) 5.50.978.330 I slot print_timing: id 0 | task 13679 | total time = 1086.27 ms / 275 tokens 5.50.978.331 I slot print_timing: id 0 | task 13679 | graphs reused = 13270 5.50.978.331 I slot print_timing: id 0 | task 13679 | graph reallocs = 0 / 0 (same size) / (changed size) 5.50.978.359 I slot release: id 0 | task 13679 | stop processing: n_tokens = 274, truncated = 0 5.50.983.075 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 5.50.991.359 I slot launch_slot_: id 0 | task 13705 | processing task, is_child = 0 5.54.564.558 I slot print_timing: id 0 | task 13705 | n_gen = 132, tg = 43.36 t/s, tg_3s = 43.69 t/s 5.57.572.412 I slot print_timing: id 0 | task 13705 | n_gen = 261, tg = 43.12 t/s, tg_3s = 42.89 t/s 6.00.584.773 I slot print_timing: id 0 | task 13705 | n_gen = 390, tg = 43.02 t/s, tg_3s = 42.82 t/s 6.03.598.558 I slot print_timing: id 0 | task 13705 | n_gen = 519, tg = 42.97 t/s, tg_3s = 42.80 t/s 6.06.606.976 I slot print_timing: id 0 | task 13705 | n_gen = 648, tg = 42.95 t/s, tg_3s = 42.88 t/s 6.09.627.875 I slot print_timing: id 0 | task 13705 | n_gen = 777, tg = 42.91 t/s, tg_3s = 42.70 t/s 6.12.649.269 I slot print_timing: id 0 | task 13705 | n_gen = 906, tg = 42.88 t/s, tg_3s = 42.70 t/s 6.15.417.266 I slot print_timing: id 0 | task 13705 | prompt eval time = 551.84 ms / 267 tokens ( 2.07 ms per token, 483.83 tokens per second) 6.15.417.273 I slot print_timing: id 0 | task 13705 | eval time = 23874.06 ms / 1024 tokens ( 23.34 ms per token, 42.85 tokens per second) 6.15.417.274 I slot print_timing: id 0 | task 13705 | total time = 24425.90 ms / 1291 tokens 6.15.417.275 I slot print_timing: id 0 | task 13705 | graphs reused = 14288 6.15.417.276 I slot print_timing: id 0 | task 13705 | graph reallocs = 0 / 0 (same size) / (changed size) 6.15.417.325 I slot release: id 0 | task 13705 | stop processing: n_tokens = 1290, truncated = 0 6.15.422.749 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.118 (> 0.100 thold), f_keep = 0.023 6.15.439.402 I slot launch_slot_: id 0 | task 14732 | processing task, is_child = 0 6.16.500.069 I slot print_timing: id 0 | task 14732 | prompt eval time = 575.55 ms / 255 tokens ( 2.26 ms per token, 443.06 tokens per second) 6.16.500.072 I slot print_timing: id 0 | task 14732 | eval time = 485.11 ms / 22 tokens ( 23.10 ms per token, 43.29 tokens per second) 6.16.500.074 I slot print_timing: id 0 | task 14732 | total time = 1060.65 ms / 277 tokens 6.16.500.074 I slot print_timing: id 0 | task 14732 | graphs reused = 14307 6.16.500.075 I slot print_timing: id 0 | task 14732 | graph reallocs = 0 / 0 (same size) / (changed size) 6.16.500.101 I slot release: id 0 | task 14732 | stop processing: n_tokens = 276, truncated = 0 6.16.505.641 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 276, t_last = 329813882381 6.16.514.041 I slot launch_slot_: id 0 | task 14757 | processing task, is_child = 0 6.18.012.661 I slot print_timing: id 0 | task 14757 | prompt eval time = 810.70 ms / 397 tokens ( 2.04 ms per token, 489.70 tokens per second) 6.18.012.665 I slot print_timing: id 0 | task 14757 | eval time = 687.91 ms / 30 tokens ( 23.72 ms per token, 42.16 tokens per second) 6.18.012.666 I slot print_timing: id 0 | task 14757 | total time = 1498.61 ms / 427 tokens 6.18.012.666 I slot print_timing: id 0 | task 14757 | graphs reused = 14335 6.18.012.667 I slot print_timing: id 0 | task 14757 | graph reallocs = 0 / 0 (same size) / (changed size) 6.18.012.693 I slot release: id 0 | task 14757 | stop processing: n_tokens = 426, truncated = 0 6.18.017.501 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.103 (> 0.100 thold), f_keep = 0.070 6.18.030.307 I slot launch_slot_: id 0 | task 14790 | processing task, is_child = 0 6.20.906.757 I slot print_timing: id 0 | task 14790 | prompt eval time = 635.40 ms / 290 tokens ( 2.19 ms per token, 456.40 tokens per second) 6.20.906.761 I slot print_timing: id 0 | task 14790 | eval time = 2241.04 ms / 98 tokens ( 23.10 ms per token, 43.28 tokens per second) 6.20.906.761 I slot print_timing: id 0 | task 14790 | total time = 2876.44 ms / 388 tokens 6.20.906.762 I slot print_timing: id 0 | task 14790 | graphs reused = 14431 6.20.906.762 I slot print_timing: id 0 | task 14790 | graph reallocs = 0 / 0 (same size) / (changed size) 6.20.906.787 I slot release: id 0 | task 14790 | stop processing: n_tokens = 387, truncated = 0 6.20.913.471 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 387, t_last = 329818289067 6.20.920.868 I slot launch_slot_: id 0 | task 14891 | processing task, is_child = 0 6.25.155.202 I slot print_timing: id 0 | task 14891 | n_gen = 130, tg = 42.81 t/s, tg_3s = 43.14 t/s 6.28.167.559 I slot print_timing: id 0 | task 14891 | n_gen = 257, tg = 42.48 t/s, tg_3s = 42.16 t/s 6.31.176.695 I slot print_timing: id 0 | task 14891 | n_gen = 383, tg = 42.28 t/s, tg_3s = 41.87 t/s 6.34.187.338 I slot print_timing: id 0 | task 14891 | n_gen = 507, tg = 42.01 t/s, tg_3s = 41.19 t/s 6.37.189.064 I slot print_timing: id 0 | task 14891 | n_gen = 634, tg = 42.07 t/s, tg_3s = 42.31 t/s 6.40.201.623 I slot print_timing: id 0 | task 14891 | n_gen = 762, tg = 42.14 t/s, tg_3s = 42.49 t/s 6.43.209.332 I slot print_timing: id 0 | task 14891 | n_gen = 890, tg = 42.20 t/s, tg_3s = 42.56 t/s 6.46.225.583 I slot print_timing: id 0 | task 14891 | n_gen = 1018, tg = 42.23 t/s, tg_3s = 42.44 t/s 6.46.367.033 I slot print_timing: id 0 | task 14891 | prompt eval time = 1220.94 ms / 612 tokens ( 2.00 ms per token, 501.25 tokens per second) 6.46.367.041 I slot print_timing: id 0 | task 14891 | eval time = 24225.22 ms / 1024 tokens ( 23.68 ms per token, 42.23 tokens per second) 6.46.367.041 I slot print_timing: id 0 | task 14891 | total time = 25446.16 ms / 1636 tokens 6.46.367.042 I slot print_timing: id 0 | task 14891 | graphs reused = 15449 6.46.367.042 I slot print_timing: id 0 | task 14891 | graph reallocs = 0 / 0 (same size) / (changed size) 6.46.367.083 I slot release: id 0 | task 14891 | stop processing: n_tokens = 1635, truncated = 0 6.46.371.960 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.109 (> 0.100 thold), f_keep = 0.018 6.46.395.891 I slot launch_slot_: id 0 | task 15919 | processing task, is_child = 0 6.49.954.142 I slot print_timing: id 0 | task 15919 | prompt eval time = 579.05 ms / 275 tokens ( 2.11 ms per token, 474.92 tokens per second) 6.49.954.148 I slot print_timing: id 0 | task 15919 | eval time = 2979.19 ms / 129 tokens ( 23.27 ms per token, 42.96 tokens per second) 6.49.954.149 I slot print_timing: id 0 | task 15919 | total time = 3558.24 ms / 404 tokens 6.49.954.149 I slot print_timing: id 0 | task 15919 | graphs reused = 15576 6.49.954.150 I slot print_timing: id 0 | task 15919 | graph reallocs = 0 / 0 (same size) / (changed size) 6.49.954.173 I slot release: id 0 | task 15919 | stop processing: n_tokens = 403, truncated = 0 6.49.959.881 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 403, t_last = 329847336453 6.49.968.902 I slot launch_slot_: id 0 | task 16051 | processing task, is_child = 0 6.51.467.014 I slot print_timing: id 0 | task 16051 | prompt eval time = 920.97 ms / 456 tokens ( 2.02 ms per token, 495.13 tokens per second) 6.51.467.020 I slot print_timing: id 0 | task 16051 | eval time = 577.13 ms / 25 tokens ( 24.05 ms per token, 41.59 tokens per second) 6.51.467.021 I slot print_timing: id 0 | task 16051 | total time = 1498.10 ms / 481 tokens 6.51.467.022 I slot print_timing: id 0 | task 16051 | graphs reused = 15599 6.51.467.022 I slot print_timing: id 0 | task 16051 | graph reallocs = 0 / 0 (same size) / (changed size) 6.51.467.056 I slot release: id 0 | task 16051 | stop processing: n_tokens = 480, truncated = 0 6.51.473.671 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 480, t_last = 329848849336 6.51.491.025 I slot launch_slot_: id 0 | task 16079 | processing task, is_child = 0 6.53.554.008 I slot print_timing: id 0 | task 16079 | prompt eval time = 1112.44 ms / 542 tokens ( 2.05 ms per token, 487.22 tokens per second) 6.53.554.012 I slot print_timing: id 0 | task 16079 | eval time = 950.53 ms / 41 tokens ( 23.76 ms per token, 42.08 tokens per second) 6.53.554.012 I slot print_timing: id 0 | task 16079 | total time = 2062.97 ms / 583 tokens 6.53.554.013 I slot print_timing: id 0 | task 16079 | graphs reused = 15638 6.53.554.013 I slot print_timing: id 0 | task 16079 | graph reallocs = 0 / 0 (same size) / (changed size) 6.53.554.054 I slot release: id 0 | task 16079 | stop processing: n_tokens = 582, truncated = 0 6.53.559.194 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 582, t_last = 329850936334 6.53.575.968 I slot launch_slot_: id 0 | task 16124 | processing task, is_child = 0 6.57.379.354 I slot print_timing: id 0 | task 16124 | n_gen = 130, tg = 42.87 t/s, tg_3s = 43.20 t/s 7.00.392.377 I slot print_timing: id 0 | task 16124 | n_gen = 259, tg = 42.84 t/s, tg_3s = 42.81 t/s 7.03.264.447 I slot print_timing: id 0 | task 16124 | prompt eval time = 794.35 ms / 361 tokens ( 2.20 ms per token, 454.46 tokens per second) 7.03.264.450 I slot print_timing: id 0 | task 16124 | eval time = 8894.12 ms / 382 tokens ( 23.34 ms per token, 42.84 tokens per second) 7.03.264.451 I slot print_timing: id 0 | task 16124 | total time = 9688.47 ms / 743 tokens 7.03.264.452 I slot print_timing: id 0 | task 16124 | graphs reused = 16017 7.03.264.452 I slot print_timing: id 0 | task 16124 | graph reallocs = 0 / 0 (same size) / (changed size) 7.03.264.489 I slot release: id 0 | task 16124 | stop processing: n_tokens = 767, truncated = 0 7.03.269.424 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.106 (> 0.100 thold), f_keep = 0.039 7.03.282.955 I slot launch_slot_: id 0 | task 16509 | processing task, is_child = 0 7.04.669.143 I slot print_timing: id 0 | task 16509 | prompt eval time = 578.91 ms / 258 tokens ( 2.24 ms per token, 445.66 tokens per second) 7.04.669.146 I slot print_timing: id 0 | task 16509 | eval time = 807.26 ms / 36 tokens ( 23.06 ms per token, 43.36 tokens per second) 7.04.669.147 I slot print_timing: id 0 | task 16509 | total time = 1386.17 ms / 294 tokens 7.04.669.148 I slot print_timing: id 0 | task 16509 | graphs reused = 16051 7.04.669.148 I slot print_timing: id 0 | task 16509 | graph reallocs = 0 / 0 (same size) / (changed size) 7.04.669.171 I slot release: id 0 | task 16509 | stop processing: n_tokens = 317, truncated = 0 7.04.674.727 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 317, t_last = 329862051451 7.04.678.109 I slot launch_slot_: id 0 | task 16548 | processing task, is_child = 0 7.05.985.142 I slot print_timing: id 0 | task 16548 | prompt eval time = 803.68 ms / 379 tokens ( 2.12 ms per token, 471.58 tokens per second) 7.05.985.145 I slot print_timing: id 0 | task 16548 | eval time = 503.34 ms / 22 tokens ( 23.97 ms per token, 41.72 tokens per second) 7.05.985.146 I slot print_timing: id 0 | task 16548 | total time = 1307.02 ms / 401 tokens 7.05.985.147 I slot print_timing: id 0 | task 16548 | graphs reused = 16071 7.05.985.147 I slot print_timing: id 0 | task 16548 | graph reallocs = 0 / 0 (same size) / (changed size) 7.05.985.177 I slot release: id 0 | task 16548 | stop processing: n_tokens = 423, truncated = 0 7.05.991.513 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 423, t_last = 329863367457 7.05.991.570 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 81.857 MiB) 7.06.003.853 I slot launch_slot_: id 0 | task 16573 | processing task, is_child = 0 7.07.921.483 I slot print_timing: id 0 | task 16573 | prompt eval time = 1121.45 ms / 540 tokens ( 2.08 ms per token, 481.52 tokens per second) 7.07.921.489 I slot print_timing: id 0 | task 16573 | eval time = 796.16 ms / 35 tokens ( 23.42 ms per token, 42.70 tokens per second) 7.07.921.490 I slot print_timing: id 0 | task 16573 | total time = 1917.62 ms / 575 tokens 7.07.921.491 I slot print_timing: id 0 | task 16573 | graphs reused = 16104 7.07.921.491 I slot print_timing: id 0 | task 16573 | graph reallocs = 0 / 0 (same size) / (changed size) 7.07.921.526 I slot release: id 0 | task 16573 | stop processing: n_tokens = 596, truncated = 0 7.07.927.192 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 596, t_last = 329865303806 7.07.927.260 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 68.707 MiB) 7.07.927.263 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 72.715 MiB) 7.07.927.265 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 72.504 MiB) 7.07.946.382 I slot launch_slot_: id 0 | task 16612 | processing task, is_child = 0 7.09.552.763 I slot print_timing: id 0 | task 16612 | prompt eval time = 749.17 ms / 372 tokens ( 2.01 ms per token, 496.55 tokens per second) 7.09.552.770 I slot print_timing: id 0 | task 16612 | eval time = 857.21 ms / 37 tokens ( 23.81 ms per token, 42.00 tokens per second) 7.09.552.770 I slot print_timing: id 0 | task 16612 | total time = 1606.37 ms / 409 tokens 7.09.552.771 I slot print_timing: id 0 | task 16612 | graphs reused = 16139 7.09.552.772 I slot print_timing: id 0 | task 16612 | graph reallocs = 0 / 0 (same size) / (changed size) 7.09.552.803 I slot release: id 0 | task 16612 | stop processing: n_tokens = 430, truncated = 0 7.09.558.349 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 430, t_last = 329866935083 7.09.558.403 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 61.639 MiB) 7.09.558.407 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 61.428 MiB) 7.09.567.030 I slot launch_slot_: id 0 | task 16652 | processing task, is_child = 0 7.11.178.546 I slot print_timing: id 0 | task 16652 | prompt eval time = 704.55 ms / 338 tokens ( 2.08 ms per token, 479.74 tokens per second) 7.11.178.553 I slot print_timing: id 0 | task 16652 | eval time = 906.96 ms / 40 tokens ( 23.26 ms per token, 43.00 tokens per second) 7.11.178.554 I slot print_timing: id 0 | task 16652 | total time = 1611.50 ms / 378 tokens 7.11.178.554 I slot print_timing: id 0 | task 16652 | graphs reused = 16177 7.11.178.555 I slot print_timing: id 0 | task 16652 | graph reallocs = 0 / 0 (same size) / (changed size) 7.11.178.584 I slot release: id 0 | task 16652 | stop processing: n_tokens = 398, truncated = 0 7.11.183.411 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.115 (> 0.100 thold), f_keep = 0.075 7.11.183.462 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 102.040 MiB) 7.11.183.466 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 130.803 MiB) 7.11.188.576 I slot launch_slot_: id 0 | task 16695 | processing task, is_child = 0 7.12.303.306 I slot print_timing: id 0 | task 16695 | prompt eval time = 560.38 ms / 261 tokens ( 2.15 ms per token, 465.75 tokens per second) 7.12.303.312 I slot print_timing: id 0 | task 16695 | eval time = 554.34 ms / 24 tokens ( 24.10 ms per token, 41.49 tokens per second) 7.12.303.313 I slot print_timing: id 0 | task 16695 | total time = 1114.72 ms / 285 tokens 7.12.303.313 I slot print_timing: id 0 | task 16695 | graphs reused = 16199 7.12.303.314 I slot print_timing: id 0 | task 16695 | graph reallocs = 0 / 0 (same size) / (changed size) 7.12.303.344 I slot release: id 0 | task 16695 | stop processing: n_tokens = 284, truncated = 0 7.12.307.936 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 7.12.310.584 I slot launch_slot_: id 0 | task 16722 | processing task, is_child = 0 7.13.915.708 I slot print_timing: id 0 | task 16722 | prompt eval time = 693.38 ms / 299 tokens ( 2.32 ms per token, 431.22 tokens per second) 7.13.915.714 I slot print_timing: id 0 | task 16722 | eval time = 911.74 ms / 40 tokens ( 23.38 ms per token, 42.78 tokens per second) 7.13.915.715 I slot print_timing: id 0 | task 16722 | total time = 1605.11 ms / 339 tokens 7.13.915.715 I slot print_timing: id 0 | task 16722 | graphs reused = 16237 7.13.915.716 I slot print_timing: id 0 | task 16722 | graph reallocs = 0 / 0 (same size) / (changed size) 7.13.915.738 I slot release: id 0 | task 16722 | stop processing: n_tokens = 338, truncated = 0 7.13.920.503 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 338, t_last = 329871298018 7.13.920.547 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 68.320 MiB) 7.13.923.508 I slot launch_slot_: id 0 | task 16765 | processing task, is_child = 0 7.15.198.223 I slot print_timing: id 0 | task 16765 | prompt eval time = 697.75 ms / 319 tokens ( 2.19 ms per token, 457.18 tokens per second) 7.15.198.229 I slot print_timing: id 0 | task 16765 | eval time = 576.94 ms / 26 tokens ( 23.08 ms per token, 43.33 tokens per second) 7.15.198.230 I slot print_timing: id 0 | task 16765 | total time = 1274.70 ms / 345 tokens 7.15.198.230 I slot print_timing: id 0 | task 16765 | graphs reused = 16261 7.15.198.231 I slot print_timing: id 0 | task 16765 | graph reallocs = 0 / 0 (same size) / (changed size) 7.15.198.258 I slot release: id 0 | task 16765 | stop processing: n_tokens = 344, truncated = 0 7.15.203.905 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 344, t_last = 329872580538 7.15.203.951 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 72.188 MiB) 7.15.212.985 I slot launch_slot_: id 0 | task 16794 | processing task, is_child = 0 7.16.874.369 I slot print_timing: id 0 | task 16794 | prompt eval time = 829.71 ms / 423 tokens ( 1.96 ms per token, 509.82 tokens per second) 7.16.874.375 I slot print_timing: id 0 | task 16794 | eval time = 831.66 ms / 36 tokens ( 23.76 ms per token, 42.08 tokens per second) 7.16.874.376 I slot print_timing: id 0 | task 16794 | total time = 1661.37 ms / 459 tokens 7.16.874.377 I slot print_timing: id 0 | task 16794 | graphs reused = 16295 7.16.874.377 I slot print_timing: id 0 | task 16794 | graph reallocs = 0 / 0 (same size) / (changed size) 7.16.874.413 I slot release: id 0 | task 16794 | stop processing: n_tokens = 458, truncated = 0 7.16.879.755 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 329874256693 7.16.879.813 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 125.145 MiB) 7.16.879.816 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 86.463 MiB) 7.16.887.459 I slot launch_slot_: id 0 | task 16833 | processing task, is_child = 0 7.18.438.949 I slot print_timing: id 0 | task 16833 | prompt eval time = 747.83 ms / 366 tokens ( 2.04 ms per token, 489.42 tokens per second) 7.18.438.956 I slot print_timing: id 0 | task 16833 | eval time = 803.65 ms / 35 tokens ( 23.64 ms per token, 42.31 tokens per second) 7.18.438.956 I slot print_timing: id 0 | task 16833 | total time = 1551.48 ms / 401 tokens 7.18.438.957 I slot print_timing: id 0 | task 16833 | graphs reused = 16328 7.18.438.958 I slot print_timing: id 0 | task 16833 | graph reallocs = 0 / 0 (same size) / (changed size) 7.18.438.988 I slot release: id 0 | task 16833 | stop processing: n_tokens = 400, truncated = 0 7.18.445.703 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 329875821268 7.18.445.758 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 89.945 MiB) 7.18.454.424 I slot launch_slot_: id 0 | task 16871 | processing task, is_child = 0 7.20.252.152 I slot print_timing: id 0 | task 16871 | prompt eval time = 1141.75 ms / 560 tokens ( 2.04 ms per token, 490.48 tokens per second) 7.20.252.157 I slot print_timing: id 0 | task 16871 | eval time = 655.97 ms / 29 tokens ( 23.43 ms per token, 42.68 tokens per second) 7.20.252.158 I slot print_timing: id 0 | task 16871 | total time = 1797.72 ms / 589 tokens 7.20.252.159 I slot print_timing: id 0 | task 16871 | graphs reused = 16355 7.20.252.159 I slot print_timing: id 0 | task 16871 | graph reallocs = 0 / 0 (same size) / (changed size) 7.20.252.194 I slot release: id 0 | task 16871 | stop processing: n_tokens = 588, truncated = 0 7.20.257.368 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 588, t_last = 329877634474 7.20.257.434 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.261 MiB) 7.20.257.438 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 61.921 MiB) 7.20.257.440 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 52.884 MiB) 7.20.276.237 I slot launch_slot_: id 0 | task 16904 | processing task, is_child = 0 7.21.533.953 I slot print_timing: id 0 | task 16904 | prompt eval time = 745.27 ms / 366 tokens ( 2.04 ms per token, 491.10 tokens per second) 7.21.533.960 I slot print_timing: id 0 | task 16904 | eval time = 512.43 ms / 23 tokens ( 23.29 ms per token, 42.93 tokens per second) 7.21.533.960 I slot print_timing: id 0 | task 16904 | total time = 1257.70 ms / 389 tokens 7.21.533.961 I slot print_timing: id 0 | task 16904 | graphs reused = 16376 7.21.533.961 I slot print_timing: id 0 | task 16904 | graph reallocs = 0 / 0 (same size) / (changed size) 7.21.533.993 I slot release: id 0 | task 16904 | stop processing: n_tokens = 388, truncated = 0 7.21.539.518 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 388, t_last = 329878916273 7.21.539.573 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 129.436 MiB) 7.21.543.137 I slot launch_slot_: id 0 | task 16930 | processing task, is_child = 0 7.23.284.570 I slot print_timing: id 0 | task 16930 | prompt eval time = 805.62 ms / 406 tokens ( 1.98 ms per token, 503.96 tokens per second) 7.23.284.574 I slot print_timing: id 0 | task 16930 | eval time = 935.80 ms / 41 tokens ( 23.40 ms per token, 42.74 tokens per second) 7.23.284.575 I slot print_timing: id 0 | task 16930 | total time = 1741.42 ms / 447 tokens 7.23.284.575 I slot print_timing: id 0 | task 16930 | graphs reused = 16415 7.23.284.576 I slot print_timing: id 0 | task 16930 | graph reallocs = 0 / 0 (same size) / (changed size) 7.23.284.607 I slot release: id 0 | task 16930 | stop processing: n_tokens = 446, truncated = 0 7.23.290.377 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 446, t_last = 329880666887 7.23.290.439 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 66.773 MiB) 7.23.290.446 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.683 MiB) 7.23.304.859 I slot launch_slot_: id 0 | task 16974 | processing task, is_child = 0 7.25.063.041 I slot print_timing: id 0 | task 16974 | prompt eval time = 800.70 ms / 379 tokens ( 2.11 ms per token, 473.33 tokens per second) 7.25.063.047 I slot print_timing: id 0 | task 16974 | eval time = 957.47 ms / 42 tokens ( 23.35 ms per token, 42.82 tokens per second) 7.25.063.047 I slot print_timing: id 0 | task 16974 | total time = 1758.17 ms / 421 tokens 7.25.063.048 I slot print_timing: id 0 | task 16974 | graphs reused = 16455 7.25.063.049 I slot print_timing: id 0 | task 16974 | graph reallocs = 0 / 0 (same size) / (changed size) 7.25.063.074 I slot release: id 0 | task 16974 | stop processing: n_tokens = 420, truncated = 0 7.25.069.304 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 420, t_last = 329882445354 7.25.069.370 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 80.627 MiB) 7.25.069.374 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 57.315 MiB) 7.25.077.854 I slot launch_slot_: id 0 | task 17019 | processing task, is_child = 0 7.26.716.328 I slot print_timing: id 0 | task 17019 | prompt eval time = 982.24 ms / 487 tokens ( 2.02 ms per token, 495.80 tokens per second) 7.26.716.335 I slot print_timing: id 0 | task 17019 | eval time = 656.22 ms / 29 tokens ( 23.44 ms per token, 42.67 tokens per second) 7.26.716.337 I slot print_timing: id 0 | task 17019 | total time = 1638.47 ms / 516 tokens 7.26.716.337 I slot print_timing: id 0 | task 17019 | graphs reused = 16481 7.26.716.338 I slot print_timing: id 0 | task 17019 | graph reallocs = 0 / 0 (same size) / (changed size) 7.26.716.381 I slot release: id 0 | task 17019 | stop processing: n_tokens = 515, truncated = 0 7.26.723.225 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 515, t_last = 329884098661 7.26.723.289 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 84.916 MiB) 7.26.723.813 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 86.358 MiB) 7.26.742.362 I slot launch_slot_: id 0 | task 17051 | processing task, is_child = 0 7.29.128.373 I slot print_timing: id 0 | task 17051 | prompt eval time = 1167.42 ms / 565 tokens ( 2.07 ms per token, 483.97 tokens per second) 7.29.128.377 I slot print_timing: id 0 | task 17051 | eval time = 1218.58 ms / 53 tokens ( 23.43 ms per token, 42.67 tokens per second) 7.29.128.377 I slot print_timing: id 0 | task 17051 | total time = 2386.00 ms / 618 tokens 7.29.128.378 I slot print_timing: id 0 | task 17051 | graphs reused = 16532 7.29.128.378 I slot print_timing: id 0 | task 17051 | graph reallocs = 0 / 0 (same size) / (changed size) 7.29.128.413 I slot release: id 0 | task 17051 | stop processing: n_tokens = 617, truncated = 0 7.29.133.051 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.153 (> 0.100 thold), f_keep = 0.049 7.29.133.122 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 133.760 MiB) 7.29.133.616 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 82.771 MiB) 7.29.148.181 I slot launch_slot_: id 0 | task 17108 | processing task, is_child = 0 7.32.620.533 I slot print_timing: id 0 | task 17108 | n_gen = 132, tg = 43.50 t/s, tg_3s = 43.83 t/s 7.35.627.039 I slot print_timing: id 0 | task 17108 | n_gen = 260, tg = 43.04 t/s, tg_3s = 42.57 t/s 7.38.649.480 I slot print_timing: id 0 | task 17108 | n_gen = 389, tg = 42.92 t/s, tg_3s = 42.68 t/s 7.41.660.935 I slot print_timing: id 0 | task 17108 | n_gen = 518, tg = 42.90 t/s, tg_3s = 42.84 t/s 7.44.677.345 I slot print_timing: id 0 | task 17108 | n_gen = 646, tg = 42.80 t/s, tg_3s = 42.43 t/s 7.47.697.551 I slot print_timing: id 0 | task 17108 | n_gen = 774, tg = 42.73 t/s, tg_3s = 42.38 t/s 7.50.712.034 I slot print_timing: id 0 | task 17108 | n_gen = 902, tg = 42.70 t/s, tg_3s = 42.46 t/s 7.53.584.200 I slot print_timing: id 0 | task 17108 | prompt eval time = 460.69 ms / 196 tokens ( 2.35 ms per token, 425.45 tokens per second) 7.53.584.205 I slot print_timing: id 0 | task 17108 | eval time = 23975.31 ms / 1024 tokens ( 23.44 ms per token, 42.67 tokens per second) 7.53.584.205 I slot print_timing: id 0 | task 17108 | total time = 24436.01 ms / 1220 tokens 7.53.584.206 I slot print_timing: id 0 | task 17108 | graphs reused = 17550 7.53.584.206 I slot print_timing: id 0 | task 17108 | graph reallocs = 0 / 0 (same size) / (changed size) 7.53.584.232 I slot release: id 0 | task 17108 | stop processing: n_tokens = 1219, truncated = 0 7.53.589.225 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.140 (> 0.100 thold), f_keep = 0.025 7.53.589.331 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 96.344 MiB) 7.53.589.546 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 63.995 MiB) 7.53.602.106 I slot launch_slot_: id 0 | task 18135 | processing task, is_child = 0 7.57.135.980 I slot print_timing: id 0 | task 18135 | n_gen = 132, tg = 43.49 t/s, tg_3s = 43.82 t/s 8.00.154.739 I slot print_timing: id 0 | task 18135 | n_gen = 262, tg = 43.28 t/s, tg_3s = 43.06 t/s 8.02.604.744 I slot print_timing: id 0 | task 18135 | prompt eval time = 521.57 ms / 214 tokens ( 2.44 ms per token, 410.30 tokens per second) 8.02.604.747 I slot print_timing: id 0 | task 18135 | eval time = 8481.06 ms / 367 tokens ( 23.17 ms per token, 43.16 tokens per second) 8.02.604.748 I slot print_timing: id 0 | task 18135 | total time = 9002.62 ms / 581 tokens 8.02.604.748 I slot print_timing: id 0 | task 18135 | graphs reused = 17913 8.02.604.749 I slot print_timing: id 0 | task 18135 | graph reallocs = 0 / 0 (same size) / (changed size) 8.02.604.777 I slot release: id 0 | task 18135 | stop processing: n_tokens = 580, truncated = 0 8.02.609.182 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.149 (> 0.100 thold), f_keep = 0.052 8.02.609.251 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 81.084 MiB) 8.02.618.117 I slot launch_slot_: id 0 | task 18505 | processing task, is_child = 0 8.06.143.727 I slot print_timing: id 0 | task 18505 | n_gen = 132, tg = 43.57 t/s, tg_3s = 43.90 t/s 8.09.151.017 I slot print_timing: id 0 | task 18505 | n_gen = 261, tg = 43.23 t/s, tg_3s = 42.90 t/s 8.12.170.870 I slot print_timing: id 0 | task 18505 | n_gen = 390, tg = 43.06 t/s, tg_3s = 42.72 t/s 8.15.184.037 I slot print_timing: id 0 | task 18505 | n_gen = 519, tg = 43.00 t/s, tg_3s = 42.81 t/s 8.18.187.735 I slot print_timing: id 0 | task 18505 | n_gen = 647, tg = 42.92 t/s, tg_3s = 42.61 t/s 8.21.207.692 I slot print_timing: id 0 | task 18505 | n_gen = 776, tg = 42.89 t/s, tg_3s = 42.72 t/s 8.24.221.513 I slot print_timing: id 0 | task 18505 | n_gen = 904, tg = 42.83 t/s, tg_3s = 42.47 t/s 8.27.036.793 I slot print_timing: id 0 | task 18505 | prompt eval time = 518.77 ms / 201 tokens ( 2.58 ms per token, 387.46 tokens per second) 8.27.036.799 I slot print_timing: id 0 | task 18505 | eval time = 23899.90 ms / 1024 tokens ( 23.36 ms per token, 42.80 tokens per second) 8.27.036.800 I slot print_timing: id 0 | task 18505 | total time = 24418.66 ms / 1225 tokens 8.27.036.801 I slot print_timing: id 0 | task 18505 | graphs reused = 18931 8.27.036.801 I slot print_timing: id 0 | task 18505 | graph reallocs = 0 / 0 (same size) / (changed size) 8.27.036.821 I slot release: id 0 | task 18505 | stop processing: n_tokens = 1224, truncated = 0 8.27.041.162 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.179 (> 0.100 thold), f_keep = 0.025 8.27.041.264 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 76.583 MiB) 8.27.041.274 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 66.281 MiB) 8.27.051.345 I slot launch_slot_: id 0 | task 19532 | processing task, is_child = 0 8.30.527.909 I slot print_timing: id 0 | task 19532 | n_gen = 131, tg = 43.04 t/s, tg_3s = 43.37 t/s 8.30.919.560 I slot print_timing: id 0 | task 19532 | prompt eval time = 456.02 ms / 168 tokens ( 2.71 ms per token, 368.40 tokens per second) 8.30.919.566 I slot print_timing: id 0 | task 19532 | eval time = 3412.19 ms / 148 tokens ( 23.21 ms per token, 43.08 tokens per second) 8.30.919.567 I slot print_timing: id 0 | task 19532 | total time = 3868.21 ms / 316 tokens 8.30.919.567 I slot print_timing: id 0 | task 19532 | graphs reused = 19076 8.30.919.568 I slot print_timing: id 0 | task 19532 | graph reallocs = 0 / 0 (same size) / (changed size) 8.30.919.586 I slot release: id 0 | task 19532 | stop processing: n_tokens = 315, truncated = 0 8.30.924.253 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.129 (> 0.100 thold), f_keep = 0.095 8.30.924.301 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 59.389 MiB) 8.30.926.703 I slot launch_slot_: id 0 | task 19683 | processing task, is_child = 0 8.34.464.849 I slot print_timing: id 0 | task 19683 | n_gen = 132, tg = 43.48 t/s, tg_3s = 43.81 t/s 8.37.466.470 I slot print_timing: id 0 | task 19683 | n_gen = 261, tg = 43.23 t/s, tg_3s = 42.98 t/s 8.37.513.109 I slot print_timing: id 0 | task 19683 | prompt eval time = 525.07 ms / 232 tokens ( 2.26 ms per token, 441.85 tokens per second) 8.37.513.115 I slot print_timing: id 0 | task 19683 | eval time = 6061.33 ms / 263 tokens ( 23.13 ms per token, 43.22 tokens per second) 8.37.513.116 I slot print_timing: id 0 | task 19683 | total time = 6586.40 ms / 495 tokens 8.37.513.116 I slot print_timing: id 0 | task 19683 | graphs reused = 19336 8.37.513.117 I slot print_timing: id 0 | task 19683 | graph reallocs = 0 / 0 (same size) / (changed size) 8.37.513.148 I slot release: id 0 | task 19683 | stop processing: n_tokens = 494, truncated = 0 8.37.517.680 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.120 (> 0.100 thold), f_keep = 0.061 8.37.517.745 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 59.073 MiB) 8.37.517.748 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.999 MiB) 8.37.526.100 I slot launch_slot_: id 0 | task 19949 | processing task, is_child = 0 8.41.128.236 I slot print_timing: id 0 | task 19949 | n_gen = 132, tg = 43.41 t/s, tg_3s = 43.74 t/s 8.44.133.955 I slot print_timing: id 0 | task 19949 | n_gen = 261, tg = 43.17 t/s, tg_3s = 42.92 t/s 8.47.150.643 I slot print_timing: id 0 | task 19949 | n_gen = 390, tg = 43.03 t/s, tg_3s = 42.76 t/s 8.50.163.093 I slot print_timing: id 0 | task 19949 | n_gen = 518, tg = 42.90 t/s, tg_3s = 42.49 t/s 8.53.179.831 I slot print_timing: id 0 | task 19949 | n_gen = 647, tg = 42.87 t/s, tg_3s = 42.76 t/s 8.56.190.199 I slot print_timing: id 0 | task 19949 | n_gen = 775, tg = 42.81 t/s, tg_3s = 42.52 t/s 8.59.204.223 I slot print_timing: id 0 | task 19949 | n_gen = 903, tg = 42.76 t/s, tg_3s = 42.47 t/s 9.02.042.456 I slot print_timing: id 0 | task 19949 | prompt eval time = 584.46 ms / 249 tokens ( 2.35 ms per token, 426.04 tokens per second) 9.02.042.461 I slot print_timing: id 0 | task 19949 | eval time = 23931.88 ms / 1024 tokens ( 23.39 ms per token, 42.75 tokens per second) 9.02.042.462 I slot print_timing: id 0 | task 19949 | total time = 24516.34 ms / 1273 tokens 9.02.042.463 I slot print_timing: id 0 | task 19949 | graphs reused = 20354 9.02.042.463 I slot print_timing: id 0 | task 19949 | graph reallocs = 0 / 0 (same size) / (changed size) 9.02.042.497 I slot release: id 0 | task 19949 | stop processing: n_tokens = 1272, truncated = 0 9.02.047.934 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.106 (> 0.100 thold), f_keep = 0.027 9.02.048.041 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 85.655 MiB) 9.02.048.045 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 55.381 MiB) 9.02.059.607 I slot launch_slot_: id 0 | task 20976 | processing task, is_child = 0 9.05.711.788 I slot print_timing: id 0 | task 20976 | n_gen = 131, tg = 43.06 t/s, tg_3s = 43.39 t/s 9.08.723.510 I slot print_timing: id 0 | task 20976 | n_gen = 260, tg = 42.94 t/s, tg_3s = 42.83 t/s 9.11.733.848 I slot print_timing: id 0 | task 20976 | n_gen = 389, tg = 42.91 t/s, tg_3s = 42.85 t/s 9.14.748.405 I slot print_timing: id 0 | task 20976 | n_gen = 518, tg = 42.88 t/s, tg_3s = 42.79 t/s 9.17.765.758 I slot print_timing: id 0 | task 20976 | n_gen = 647, tg = 42.86 t/s, tg_3s = 42.75 t/s 9.20.766.780 I slot print_timing: id 0 | task 20976 | n_gen = 775, tg = 42.82 t/s, tg_3s = 42.65 t/s 9.23.769.870 I slot print_timing: id 0 | task 20976 | n_gen = 903, tg = 42.79 t/s, tg_3s = 42.62 t/s 9.26.610.204 I slot print_timing: id 0 | task 20976 | prompt eval time = 632.78 ms / 320 tokens ( 1.98 ms per token, 505.71 tokens per second) 9.26.610.211 I slot print_timing: id 0 | task 20976 | eval time = 23917.80 ms / 1024 tokens ( 23.38 ms per token, 42.77 tokens per second) 9.26.610.211 I slot print_timing: id 0 | task 20976 | total time = 24550.58 ms / 1344 tokens 9.26.610.212 I slot print_timing: id 0 | task 20976 | graphs reused = 21372 9.26.610.212 I slot print_timing: id 0 | task 20976 | graph reallocs = 0 / 0 (same size) / (changed size) 9.26.610.241 I slot release: id 0 | task 20976 | stop processing: n_tokens = 1343, truncated = 0 9.26.614.434 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.167 (> 0.100 thold), f_keep = 0.022 9.26.614.540 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 135.694 MiB) 9.26.625.360 I slot launch_slot_: id 0 | task 22003 | processing task, is_child = 0 9.30.043.067 I slot print_timing: id 0 | task 22003 | n_gen = 132, tg = 43.56 t/s, tg_3s = 43.89 t/s 9.33.057.747 I slot print_timing: id 0 | task 22003 | n_gen = 262, tg = 43.34 t/s, tg_3s = 43.12 t/s 9.36.068.950 I slot print_timing: id 0 | task 22003 | n_gen = 391, tg = 43.17 t/s, tg_3s = 42.84 t/s 9.39.080.647 I slot print_timing: id 0 | task 22003 | n_gen = 520, tg = 43.09 t/s, tg_3s = 42.83 t/s 9.42.100.352 I slot print_timing: id 0 | task 22003 | n_gen = 649, tg = 43.01 t/s, tg_3s = 42.72 t/s 9.45.117.592 I slot print_timing: id 0 | task 22003 | n_gen = 778, tg = 42.97 t/s, tg_3s = 42.75 t/s 9.48.140.277 I slot print_timing: id 0 | task 22003 | n_gen = 907, tg = 42.93 t/s, tg_3s = 42.68 t/s 9.50.884.351 I slot print_timing: id 0 | task 22003 | prompt eval time = 410.19 ms / 180 tokens ( 2.28 ms per token, 438.82 tokens per second) 9.50.884.360 I slot print_timing: id 0 | task 22003 | eval time = 23848.79 ms / 1024 tokens ( 23.31 ms per token, 42.90 tokens per second) 9.50.884.360 I slot print_timing: id 0 | task 22003 | total time = 24258.98 ms / 1204 tokens 9.50.884.361 I slot print_timing: id 0 | task 22003 | graphs reused = 22390 9.50.884.361 I slot print_timing: id 0 | task 22003 | graph reallocs = 0 / 0 (same size) / (changed size) 9.50.884.380 I slot release: id 0 | task 22003 | stop processing: n_tokens = 1203, truncated = 0 9.50.888.677 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.163 (> 0.100 thold), f_keep = 0.025 9.50.888.776 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 45.114 MiB) 9.50.888.781 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 67.934 MiB) 9.50.888.783 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 61.640 MiB) 9.50.892.772 I slot launch_slot_: id 0 | task 23030 | processing task, is_child = 0 9.54.361.269 I slot print_timing: id 0 | task 23030 | n_gen = 132, tg = 43.51 t/s, tg_3s = 43.85 t/s 9.57.380.072 I slot print_timing: id 0 | task 23030 | n_gen = 262, tg = 43.29 t/s, tg_3s = 43.06 t/s 10.00.393.164 I slot print_timing: id 0 | task 23030 | n_gen = 391, tg = 43.13 t/s, tg_3s = 42.81 t/s 10.03.408.921 I slot print_timing: id 0 | task 23030 | n_gen = 520, tg = 43.04 t/s, tg_3s = 42.78 t/s 10.06.426.624 I slot print_timing: id 0 | task 23030 | n_gen = 649, tg = 42.98 t/s, tg_3s = 42.75 t/s 10.09.445.190 I slot print_timing: id 0 | task 23030 | n_gen = 778, tg = 42.94 t/s, tg_3s = 42.74 t/s 10.12.466.579 I slot print_timing: id 0 | task 23030 | n_gen = 907, tg = 42.91 t/s, tg_3s = 42.70 t/s 10.15.212.102 I slot print_timing: id 0 | task 23030 | prompt eval time = 457.92 ms / 184 tokens ( 2.49 ms per token, 401.82 tokens per second) 10.15.212.106 I slot print_timing: id 0 | task 23030 | eval time = 23861.40 ms / 1024 tokens ( 23.32 ms per token, 42.87 tokens per second) 10.15.212.107 I slot print_timing: id 0 | task 23030 | total time = 24319.32 ms / 1208 tokens 10.15.212.107 I slot print_timing: id 0 | task 23030 | graphs reused = 23408 10.15.212.108 I slot print_timing: id 0 | task 23030 | graph reallocs = 0 / 0 (same size) / (changed size) 10.15.212.127 I slot release: id 0 | task 23030 | stop processing: n_tokens = 1207, truncated = 0 10.15.216.611 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.128 (> 0.100 thold), f_keep = 0.025 10.15.216.715 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 67.371 MiB) 10.15.216.719 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 69.867 MiB) 10.15.226.802 I slot launch_slot_: id 0 | task 24057 | processing task, is_child = 0 10.18.758.337 I slot print_timing: id 0 | task 24057 | n_gen = 132, tg = 43.43 t/s, tg_3s = 43.76 t/s 10.21.763.385 I slot print_timing: id 0 | task 24057 | n_gen = 261, tg = 43.18 t/s, tg_3s = 42.93 t/s 10.21.996.212 I slot print_timing: id 0 | task 24057 | prompt eval time = 514.96 ms / 235 tokens ( 2.19 ms per token, 456.35 tokens per second) 10.21.996.215 I slot print_timing: id 0 | task 24057 | eval time = 6254.44 ms / 271 tokens ( 23.16 ms per token, 43.17 tokens per second) 10.21.996.216 I slot print_timing: id 0 | task 24057 | total time = 6769.40 ms / 506 tokens 10.21.996.216 I slot print_timing: id 0 | task 24057 | graphs reused = 23676 10.21.996.217 I slot print_timing: id 0 | task 24057 | graph reallocs = 0 / 0 (same size) / (changed size) 10.21.996.245 I slot release: id 0 | task 24057 | stop processing: n_tokens = 505, truncated = 0 10.22.000.963 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 10.22.001.033 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.366 MiB) 10.22.004.404 I slot launch_slot_: id 0 | task 24331 | processing task, is_child = 0 10.25.648.254 I slot print_timing: id 0 | task 24331 | n_gen = 131, tg = 43.17 t/s, tg_3s = 43.51 t/s 10.27.617.277 I slot print_timing: id 0 | task 24331 | prompt eval time = 632.83 ms / 289 tokens ( 2.19 ms per token, 456.68 tokens per second) 10.27.617.280 I slot print_timing: id 0 | task 24331 | eval time = 4980.03 ms / 215 tokens ( 23.27 ms per token, 42.97 tokens per second) 10.27.617.281 I slot print_timing: id 0 | task 24331 | total time = 5612.87 ms / 504 tokens 10.27.617.281 I slot print_timing: id 0 | task 24331 | graphs reused = 23889 10.27.617.282 I slot print_timing: id 0 | task 24331 | graph reallocs = 0 / 0 (same size) / (changed size) 10.27.617.305 I slot release: id 0 | task 24331 | stop processing: n_tokens = 503, truncated = 0 10.27.621.844 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.183 (> 0.100 thold), f_keep = 0.087 10.27.621.913 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 58.967 MiB) 10.27.630.105 I slot launch_slot_: id 0 | task 24549 | processing task, is_child = 0 10.31.164.339 I slot print_timing: id 0 | task 24549 | n_gen = 132, tg = 43.40 t/s, tg_3s = 43.73 t/s 10.34.179.703 I slot print_timing: id 0 | task 24549 | n_gen = 261, tg = 43.09 t/s, tg_3s = 42.78 t/s 10.34.717.852 I slot print_timing: id 0 | task 24549 | prompt eval time = 515.72 ms / 241 tokens ( 2.14 ms per token, 467.31 tokens per second) 10.34.717.858 I slot print_timing: id 0 | task 24549 | eval time = 6572.02 ms / 284 tokens ( 23.22 ms per token, 43.06 tokens per second) 10.34.717.859 I slot print_timing: id 0 | task 24549 | total time = 7087.74 ms / 525 tokens 10.34.717.859 I slot print_timing: id 0 | task 24549 | graphs reused = 24169 10.34.717.860 I slot print_timing: id 0 | task 24549 | graph reallocs = 0 / 0 (same size) / (changed size) 10.34.717.881 I slot release: id 0 | task 24549 | stop processing: n_tokens = 524, truncated = 0 10.34.722.627 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.126 (> 0.100 thold), f_keep = 0.057 10.34.722.699 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 101.021 MiB) 10.34.730.606 I slot launch_slot_: id 0 | task 24836 | processing task, is_child = 0 10.38.249.671 I slot print_timing: id 0 | task 24836 | n_gen = 131, tg = 43.28 t/s, tg_3s = 43.62 t/s 10.39.809.363 I slot print_timing: id 0 | task 24836 | prompt eval time = 515.67 ms / 239 tokens ( 2.16 ms per token, 463.47 tokens per second) 10.39.809.369 I slot print_timing: id 0 | task 24836 | eval time = 4563.08 ms / 198 tokens ( 23.16 ms per token, 43.17 tokens per second) 10.39.809.369 I slot print_timing: id 0 | task 24836 | total time = 5078.75 ms / 437 tokens 10.39.809.370 I slot print_timing: id 0 | task 24836 | graphs reused = 24364 10.39.809.370 I slot print_timing: id 0 | task 24836 | graph reallocs = 0 / 0 (same size) / (changed size) 10.39.809.392 I slot release: id 0 | task 24836 | stop processing: n_tokens = 436, truncated = 0 10.39.813.779 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.110 (> 0.100 thold), f_keep = 0.069 10.39.813.835 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 81.787 MiB) 10.39.816.886 I slot launch_slot_: id 0 | task 25037 | processing task, is_child = 0 10.43.453.615 I slot print_timing: id 0 | task 25037 | n_gen = 131, tg = 43.25 t/s, tg_3s = 43.58 t/s 10.46.465.471 I slot print_timing: id 0 | task 25037 | n_gen = 260, tg = 43.04 t/s, tg_3s = 42.83 t/s 10.49.473.688 I slot print_timing: id 0 | task 25037 | n_gen = 389, tg = 42.99 t/s, tg_3s = 42.88 t/s 10.52.491.342 I slot print_timing: id 0 | task 25037 | n_gen = 518, tg = 42.93 t/s, tg_3s = 42.75 t/s 10.55.507.894 I slot print_timing: id 0 | task 25037 | n_gen = 647, tg = 42.89 t/s, tg_3s = 42.76 t/s 10.58.529.951 I slot print_timing: id 0 | task 25037 | n_gen = 776, tg = 42.86 t/s, tg_3s = 42.69 t/s 11.01.530.834 I slot print_timing: id 0 | task 25037 | n_gen = 904, tg = 42.83 t/s, tg_3s = 42.65 t/s 11.04.347.953 I slot print_timing: id 0 | task 25037 | prompt eval time = 630.93 ms / 273 tokens ( 2.31 ms per token, 432.69 tokens per second) 11.04.347.964 I slot print_timing: id 0 | task 25037 | eval time = 23900.13 ms / 1024 tokens ( 23.36 ms per token, 42.80 tokens per second) 11.04.347.965 I slot print_timing: id 0 | task 25037 | total time = 24531.06 ms / 1297 tokens 11.04.347.966 I slot print_timing: id 0 | task 25037 | graphs reused = 25382 11.04.347.966 I slot print_timing: id 0 | task 25037 | graph reallocs = 0 / 0 (same size) / (changed size) 11.04.347.993 I slot release: id 0 | task 25037 | stop processing: n_tokens = 1296, truncated = 0 11.04.352.282 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.142 (> 0.100 thold), f_keep = 0.023 11.04.352.390 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 145.293 MiB) 11.04.362.974 I slot launch_slot_: id 0 | task 26064 | processing task, is_child = 0 11.07.829.322 I slot print_timing: id 0 | task 26064 | n_gen = 131, tg = 43.28 t/s, tg_3s = 43.61 t/s 11.10.843.233 I slot print_timing: id 0 | task 26064 | n_gen = 261, tg = 43.21 t/s, tg_3s = 43.13 t/s 11.11.238.990 I slot print_timing: id 0 | task 26064 | prompt eval time = 462.72 ms / 212 tokens ( 2.18 ms per token, 458.16 tokens per second) 11.11.238.998 I slot print_timing: id 0 | task 26064 | eval time = 6413.29 ms / 278 tokens ( 23.15 ms per token, 43.19 tokens per second) 11.11.239.000 I slot print_timing: id 0 | task 26064 | total time = 6876.01 ms / 490 tokens 11.11.239.000 I slot print_timing: id 0 | task 26064 | graphs reused = 25657 11.11.239.001 I slot print_timing: id 0 | task 26064 | graph reallocs = 0 / 0 (same size) / (changed size) 11.11.239.021 I slot release: id 0 | task 26064 | stop processing: n_tokens = 489, truncated = 0 11.11.243.546 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.105 (> 0.100 thold), f_keep = 0.061 11.11.243.606 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 56.506 MiB) 11.11.243.609 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 60.092 MiB) 11.11.246.819 I slot launch_slot_: id 0 | task 26345 | processing task, is_child = 0 11.14.825.629 I slot print_timing: id 0 | task 26345 | n_gen = 131, tg = 43.23 t/s, tg_3s = 43.56 t/s 11.17.837.139 I slot print_timing: id 0 | task 26345 | n_gen = 260, tg = 43.03 t/s, tg_3s = 42.84 t/s 11.20.849.503 I slot print_timing: id 0 | task 26345 | n_gen = 388, tg = 42.85 t/s, tg_3s = 42.49 t/s 11.23.866.481 I slot print_timing: id 0 | task 26345 | n_gen = 517, tg = 42.83 t/s, tg_3s = 42.76 t/s 11.26.880.636 I slot print_timing: id 0 | task 26345 | n_gen = 646, tg = 42.82 t/s, tg_3s = 42.80 t/s 11.29.902.166 I slot print_timing: id 0 | task 26345 | n_gen = 775, tg = 42.80 t/s, tg_3s = 42.69 t/s 11.32.925.085 I slot print_timing: id 0 | task 26345 | n_gen = 904, tg = 42.78 t/s, tg_3s = 42.67 t/s 11.35.741.332 I slot print_timing: id 0 | task 26345 | prompt eval time = 571.36 ms / 285 tokens ( 2.00 ms per token, 498.81 tokens per second) 11.35.741.339 I slot print_timing: id 0 | task 26345 | eval time = 23923.15 ms / 1024 tokens ( 23.39 ms per token, 42.76 tokens per second) 11.35.741.340 I slot print_timing: id 0 | task 26345 | total time = 24494.50 ms / 1309 tokens 11.35.741.340 I slot print_timing: id 0 | task 26345 | graphs reused = 26675 11.35.741.341 I slot print_timing: id 0 | task 26345 | graph reallocs = 0 / 0 (same size) / (changed size) 11.35.741.364 I slot release: id 0 | task 26345 | stop processing: n_tokens = 1308, truncated = 0 11.35.745.869 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.157 (> 0.100 thold), f_keep = 0.023 11.35.745.974 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 74.086 MiB) 11.35.745.978 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 55.275 MiB) 11.35.756.564 I slot launch_slot_: id 0 | task 27372 | processing task, is_child = 0 11.39.222.238 I slot print_timing: id 0 | task 27372 | n_gen = 132, tg = 43.58 t/s, tg_3s = 43.91 t/s 11.41.180.779 I slot print_timing: id 0 | task 27372 | prompt eval time = 459.65 ms / 191 tokens ( 2.41 ms per token, 415.53 tokens per second) 11.41.180.790 I slot print_timing: id 0 | task 27372 | eval time = 4964.55 ms / 216 tokens ( 23.09 ms per token, 43.31 tokens per second) 11.41.180.790 I slot print_timing: id 0 | task 27372 | total time = 5424.20 ms / 407 tokens 11.41.180.791 I slot print_timing: id 0 | task 27372 | graphs reused = 26888 11.41.180.791 I slot print_timing: id 0 | task 27372 | graph reallocs = 0 / 0 (same size) / (changed size) 11.41.180.813 I slot release: id 0 | task 27372 | stop processing: n_tokens = 406, truncated = 0 11.41.184.868 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.074 11.41.184.921 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 80.978 MiB) 11.41.192.060 I slot launch_slot_: id 0 | task 27591 | processing task, is_child = 0 11.43.515.237 I slot print_timing: id 0 | task 27591 | prompt eval time = 419.18 ms / 171 tokens ( 2.45 ms per token, 407.94 tokens per second) 11.43.515.240 I slot print_timing: id 0 | task 27591 | eval time = 1903.99 ms / 82 tokens ( 23.51 ms per token, 42.54 tokens per second) 11.43.515.241 I slot print_timing: id 0 | task 27591 | total time = 2323.17 ms / 253 tokens 11.43.515.242 I slot print_timing: id 0 | task 27591 | graphs reused = 26968 11.43.515.242 I slot print_timing: id 0 | task 27591 | graph reallocs = 0 / 0 (same size) / (changed size) 11.43.515.263 I slot release: id 0 | task 27591 | stop processing: n_tokens = 252, truncated = 0 11.43.519.949 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.115 (> 0.100 thold), f_keep = 0.119 11.43.519.987 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 59.776 MiB) 11.43.522.102 I slot launch_slot_: id 0 | task 27676 | processing task, is_child = 0 11.47.119.597 I slot print_timing: id 0 | task 27676 | n_gen = 132, tg = 43.36 t/s, tg_3s = 43.69 t/s 11.50.126.596 I slot print_timing: id 0 | task 27676 | n_gen = 261, tg = 43.13 t/s, tg_3s = 42.90 t/s 11.50.803.165 I slot print_timing: id 0 | task 27676 | prompt eval time = 576.15 ms / 260 tokens ( 2.22 ms per token, 451.27 tokens per second) 11.50.803.169 I slot print_timing: id 0 | task 27676 | eval time = 6704.90 ms / 290 tokens ( 23.20 ms per token, 43.10 tokens per second) 11.50.803.170 I slot print_timing: id 0 | task 27676 | total time = 7281.05 ms / 550 tokens 11.50.803.170 I slot print_timing: id 0 | task 27676 | graphs reused = 27255 11.50.803.171 I slot print_timing: id 0 | task 27676 | graph reallocs = 0 / 0 (same size) / (changed size) 11.50.803.198 I slot release: id 0 | task 27676 | stop processing: n_tokens = 549, truncated = 0 11.50.807.532 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.147 (> 0.100 thold), f_keep = 0.055 11.50.807.600 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 123.629 MiB) 11.50.816.781 I slot launch_slot_: id 0 | task 27969 | processing task, is_child = 0 11.54.285.137 I slot print_timing: id 0 | task 27969 | n_gen = 132, tg = 43.57 t/s, tg_3s = 43.91 t/s 11.57.306.801 I slot print_timing: id 0 | task 27969 | n_gen = 262, tg = 43.30 t/s, tg_3s = 43.02 t/s 12.00.317.614 I slot print_timing: id 0 | task 27969 | n_gen = 391, tg = 43.15 t/s, tg_3s = 42.85 t/s 12.01.887.451 I slot print_timing: id 0 | task 27969 | prompt eval time = 461.97 ms / 204 tokens ( 2.26 ms per token, 441.59 tokens per second) 12.01.887.455 I slot print_timing: id 0 | task 27969 | eval time = 10608.68 ms / 458 tokens ( 23.21 ms per token, 43.08 tokens per second) 12.01.887.456 I slot print_timing: id 0 | task 27969 | total time = 11070.65 ms / 662 tokens 12.01.887.457 I slot print_timing: id 0 | task 27969 | graphs reused = 27709 12.01.887.457 I slot print_timing: id 0 | task 27969 | graph reallocs = 0 / 0 (same size) / (changed size) 12.01.887.487 I slot release: id 0 | task 27969 | stop processing: n_tokens = 661, truncated = 0 12.01.892.229 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.101 (> 0.100 thold), f_keep = 0.045 12.01.892.303 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.837 MiB) 12.01.892.307 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 63.573 MiB) 12.01.900.857 I slot launch_slot_: id 0 | task 28430 | processing task, is_child = 0 12.05.535.380 I slot print_timing: id 0 | task 28430 | n_gen = 131, tg = 43.17 t/s, tg_3s = 43.50 t/s 12.08.544.785 I slot print_timing: id 0 | task 28430 | n_gen = 260, tg = 43.02 t/s, tg_3s = 42.87 t/s 12.11.555.050 I slot print_timing: id 0 | task 28430 | n_gen = 389, tg = 42.96 t/s, tg_3s = 42.85 t/s 12.14.569.889 I slot print_timing: id 0 | task 28430 | n_gen = 518, tg = 42.92 t/s, tg_3s = 42.79 t/s 12.17.573.439 I slot print_timing: id 0 | task 28430 | n_gen = 646, tg = 42.86 t/s, tg_3s = 42.62 t/s 12.20.596.104 I slot print_timing: id 0 | task 28430 | n_gen = 775, tg = 42.83 t/s, tg_3s = 42.68 t/s 12.23.619.021 I slot print_timing: id 0 | task 28430 | n_gen = 904, tg = 42.81 t/s, tg_3s = 42.67 t/s 12.26.431.089 I slot print_timing: id 0 | task 28430 | prompt eval time = 622.97 ms / 296 tokens ( 2.10 ms per token, 475.14 tokens per second) 12.26.431.092 I slot print_timing: id 0 | task 28430 | eval time = 23907.25 ms / 1024 tokens ( 23.37 ms per token, 42.79 tokens per second) 12.26.431.092 I slot print_timing: id 0 | task 28430 | total time = 24530.22 ms / 1320 tokens 12.26.431.093 I slot print_timing: id 0 | task 28430 | graphs reused = 28727 12.26.431.094 I slot print_timing: id 0 | task 28430 | graph reallocs = 0 / 0 (same size) / (changed size) 12.26.431.116 I slot release: id 0 | task 28430 | stop processing: n_tokens = 1319, truncated = 0 12.26.435.459 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.131 (> 0.100 thold), f_keep = 0.024 12.26.435.560 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 73.559 MiB) 12.26.435.564 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 53.728 MiB) 12.26.446.882 I slot launch_slot_: id 0 | task 29457 | processing task, is_child = 0 12.29.979.627 I slot print_timing: id 0 | task 29457 | n_gen = 132, tg = 43.45 t/s, tg_3s = 43.78 t/s 12.32.985.180 I slot print_timing: id 0 | task 29457 | n_gen = 261, tg = 43.18 t/s, tg_3s = 42.92 t/s 12.35.040.719 I slot print_timing: id 0 | task 29457 | prompt eval time = 517.60 ms / 236 tokens ( 2.19 ms per token, 455.95 tokens per second) 12.35.040.723 I slot print_timing: id 0 | task 29457 | eval time = 8076.23 ms / 349 tokens ( 23.21 ms per token, 43.09 tokens per second) 12.35.040.724 I slot print_timing: id 0 | task 29457 | total time = 8593.83 ms / 585 tokens 12.35.040.724 I slot print_timing: id 0 | task 29457 | graphs reused = 29072 12.35.040.725 I slot print_timing: id 0 | task 29457 | graph reallocs = 0 / 0 (same size) / (changed size) 12.35.040.746 I slot release: id 0 | task 29457 | stop processing: n_tokens = 584, truncated = 0 12.35.045.401 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.102 (> 0.100 thold), f_keep = 0.051 12.35.045.466 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 84.107 MiB) 12.35.053.494 I slot launch_slot_: id 0 | task 29809 | processing task, is_child = 0 12.37.711.093 I slot print_timing: id 0 | task 29809 | prompt eval time = 633.99 ms / 294 tokens ( 2.16 ms per token, 463.73 tokens per second) 12.37.711.100 I slot print_timing: id 0 | task 29809 | eval time = 2023.60 ms / 88 tokens ( 23.26 ms per token, 42.99 tokens per second) 12.37.711.100 I slot print_timing: id 0 | task 29809 | total time = 2657.59 ms / 382 tokens 12.37.711.101 I slot print_timing: id 0 | task 29809 | graphs reused = 29158 12.37.711.102 I slot print_timing: id 0 | task 29809 | graph reallocs = 0 / 0 (same size) / (changed size) 12.37.711.124 I slot release: id 0 | task 29809 | stop processing: n_tokens = 381, truncated = 0 12.37.715.525 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.103 (> 0.100 thold), f_keep = 0.079 12.37.715.577 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 115.400 MiB) 12.37.718.579 I slot launch_slot_: id 0 | task 29900 | processing task, is_child = 0 12.38.711.068 I slot print_timing: id 0 | task 29900 | prompt eval time = 622.01 ms / 291 tokens ( 2.14 ms per token, 467.84 tokens per second) 12.38.711.074 I slot print_timing: id 0 | task 29900 | eval time = 370.46 ms / 17 tokens ( 23.15 ms per token, 43.19 tokens per second) 12.38.711.075 I slot print_timing: id 0 | task 29900 | total time = 992.48 ms / 308 tokens 12.38.711.076 I slot print_timing: id 0 | task 29900 | graphs reused = 29173 12.38.711.076 I slot print_timing: id 0 | task 29900 | graph reallocs = 0 / 0 (same size) / (changed size) 12.38.711.102 I slot release: id 0 | task 29900 | stop processing: n_tokens = 307, truncated = 0 12.38.715.472 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.105 (> 0.100 thold), f_keep = 0.098 12.38.715.516 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 138.958 MiB) 12.38.718.079 I slot launch_slot_: id 0 | task 29920 | processing task, is_child = 0 12.42.358.613 I slot print_timing: id 0 | task 29920 | n_gen = 131, tg = 43.22 t/s, tg_3s = 43.56 t/s 12.45.381.060 I slot print_timing: id 0 | task 29920 | n_gen = 260, tg = 42.95 t/s, tg_3s = 42.68 t/s 12.48.397.238 I slot print_timing: id 0 | task 29920 | n_gen = 389, tg = 42.89 t/s, tg_3s = 42.77 t/s 12.51.410.211 I slot print_timing: id 0 | task 29920 | n_gen = 518, tg = 42.87 t/s, tg_3s = 42.81 t/s 12.54.426.834 I slot print_timing: id 0 | task 29920 | n_gen = 647, tg = 42.85 t/s, tg_3s = 42.76 t/s 12.57.449.106 I slot print_timing: id 0 | task 29920 | n_gen = 776, tg = 42.82 t/s, tg_3s = 42.68 t/s 13.00.462.788 I slot print_timing: id 0 | task 29920 | n_gen = 904, tg = 42.77 t/s, tg_3s = 42.47 t/s 13.03.288.655 I slot print_timing: id 0 | task 29920 | prompt eval time = 632.98 ms / 287 tokens ( 2.21 ms per token, 453.41 tokens per second) 13.03.288.662 I slot print_timing: id 0 | task 29920 | eval time = 23937.58 ms / 1024 tokens ( 23.40 ms per token, 42.74 tokens per second) 13.03.288.662 I slot print_timing: id 0 | task 29920 | total time = 24570.56 ms / 1311 tokens 13.03.288.663 I slot print_timing: id 0 | task 29920 | graphs reused = 30191 13.03.288.663 I slot print_timing: id 0 | task 29920 | graph reallocs = 0 / 0 (same size) / (changed size) 13.03.288.694 I slot release: id 0 | task 29920 | stop processing: n_tokens = 1310, truncated = 0 13.03.293.451 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.123 (> 0.100 thold), f_keep = 0.023 13.03.293.558 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.095 MiB) 13.03.305.835 I slot launch_slot_: id 0 | task 30947 | processing task, is_child = 0 13.06.840.317 I slot print_timing: id 0 | task 30947 | n_gen = 132, tg = 43.40 t/s, tg_3s = 43.73 t/s 13.09.846.013 I slot print_timing: id 0 | task 30947 | n_gen = 261, tg = 43.16 t/s, tg_3s = 42.92 t/s 13.12.859.507 I slot print_timing: id 0 | task 30947 | n_gen = 390, tg = 43.04 t/s, tg_3s = 42.81 t/s 13.15.861.776 I slot print_timing: id 0 | task 30947 | n_gen = 518, tg = 42.94 t/s, tg_3s = 42.63 t/s 13.18.879.042 I slot print_timing: id 0 | task 30947 | n_gen = 647, tg = 42.90 t/s, tg_3s = 42.75 t/s 13.21.886.042 I slot print_timing: id 0 | task 30947 | n_gen = 775, tg = 42.85 t/s, tg_3s = 42.57 t/s 13.24.908.994 I slot print_timing: id 0 | task 30947 | n_gen = 904, tg = 42.82 t/s, tg_3s = 42.67 t/s 13.27.717.793 I slot print_timing: id 0 | task 30947 | prompt eval time = 516.15 ms / 243 tokens ( 2.12 ms per token, 470.79 tokens per second) 13.27.717.798 I slot print_timing: id 0 | task 30947 | eval time = 23895.80 ms / 1024 tokens ( 23.36 ms per token, 42.81 tokens per second) 13.27.717.799 I slot print_timing: id 0 | task 30947 | total time = 24411.95 ms / 1267 tokens 13.27.717.800 I slot print_timing: id 0 | task 30947 | graphs reused = 31209 13.27.717.800 I slot print_timing: id 0 | task 30947 | graph reallocs = 0 / 0 (same size) / (changed size) 13.27.717.822 I slot release: id 0 | task 30947 | stop processing: n_tokens = 1266, truncated = 0 13.27.722.313 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.166 (> 0.100 thold), f_keep = 0.024 13.27.722.413 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 146.518 MiB) 13.27.734.028 I slot launch_slot_: id 0 | task 31974 | processing task, is_child = 0 13.29.503.136 I slot print_timing: id 0 | task 31974 | prompt eval time = 467.57 ms / 181 tokens ( 2.58 ms per token, 387.11 tokens per second) 13.29.503.143 I slot print_timing: id 0 | task 31974 | eval time = 1301.53 ms / 57 tokens ( 23.24 ms per token, 43.03 tokens per second) 13.29.503.143 I slot print_timing: id 0 | task 31974 | total time = 1769.10 ms / 238 tokens 13.29.503.144 I slot print_timing: id 0 | task 31974 | graphs reused = 31264 13.29.503.145 I slot print_timing: id 0 | task 31974 | graph reallocs = 0 / 0 (same size) / (changed size) 13.29.503.163 I slot release: id 0 | task 31974 | stop processing: n_tokens = 237, truncated = 0 13.29.507.467 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 13.29.509.695 I slot launch_slot_: id 0 | task 32034 | processing task, is_child = 0 13.33.077.315 I slot print_timing: id 0 | task 32034 | n_gen = 131, tg = 43.32 t/s, tg_3s = 43.65 t/s 13.36.086.822 I slot print_timing: id 0 | task 32034 | n_gen = 260, tg = 43.09 t/s, tg_3s = 42.86 t/s 13.39.098.846 I slot print_timing: id 0 | task 32034 | n_gen = 389, tg = 43.00 t/s, tg_3s = 42.83 t/s 13.41.155.454 I slot print_timing: id 0 | task 32034 | prompt eval time = 566.76 ms / 265 tokens ( 2.14 ms per token, 467.57 tokens per second) 13.41.155.458 I slot print_timing: id 0 | task 32034 | eval time = 11078.99 ms / 477 tokens ( 23.28 ms per token, 42.96 tokens per second) 13.41.155.458 I slot print_timing: id 0 | task 32034 | total time = 11645.75 ms / 742 tokens 13.41.155.459 I slot print_timing: id 0 | task 32034 | graphs reused = 31738 13.41.155.459 I slot print_timing: id 0 | task 32034 | graph reallocs = 0 / 0 (same size) / (changed size) 13.41.155.482 I slot release: id 0 | task 32034 | stop processing: n_tokens = 741, truncated = 0 13.41.159.647 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.197 (> 0.100 thold), f_keep = 0.040 13.41.159.726 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 125.879 MiB) 13.41.168.246 I slot launch_slot_: id 0 | task 32514 | processing task, is_child = 0 13.43.337.232 I slot print_timing: id 0 | task 32514 | prompt eval time = 405.91 ms / 152 tokens ( 2.67 ms per token, 374.47 tokens per second) 13.43.337.236 I slot print_timing: id 0 | task 32514 | eval time = 1763.07 ms / 76 tokens ( 23.51 ms per token, 42.54 tokens per second) 13.43.337.236 I slot print_timing: id 0 | task 32514 | total time = 2168.98 ms / 228 tokens 13.43.337.237 I slot print_timing: id 0 | task 32514 | graphs reused = 31812 13.43.337.238 I slot print_timing: id 0 | task 32514 | graph reallocs = 0 / 0 (same size) / (changed size) 13.43.337.255 I slot release: id 0 | task 32514 | stop processing: n_tokens = 227, truncated = 0 13.43.341.488 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.158 (> 0.100 thold), f_keep = 0.132 13.43.341.526 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 156.153 MiB) 13.43.343.370 I slot launch_slot_: id 0 | task 32593 | processing task, is_child = 0 13.46.763.559 I slot print_timing: id 0 | task 32593 | prompt eval time = 458.83 ms / 190 tokens ( 2.41 ms per token, 414.10 tokens per second) 13.46.763.565 I slot print_timing: id 0 | task 32593 | eval time = 2961.35 ms / 130 tokens ( 22.96 ms per token, 43.56 tokens per second) 13.46.763.566 I slot print_timing: id 0 | task 32593 | total time = 3420.18 ms / 320 tokens 13.46.763.567 I slot print_timing: id 0 | task 32593 | graphs reused = 31939 13.46.763.567 I slot print_timing: id 0 | task 32593 | graph reallocs = 0 / 0 (same size) / (changed size) 13.46.763.589 I slot release: id 0 | task 32593 | stop processing: n_tokens = 319, truncated = 0 13.46.768.476 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.117 (> 0.100 thold), f_keep = 0.094 13.46.771.353 I slot launch_slot_: id 0 | task 32726 | processing task, is_child = 0 13.50.367.108 I slot print_timing: id 0 | task 32726 | n_gen = 132, tg = 43.38 t/s, tg_3s = 43.71 t/s 13.53.373.116 I slot print_timing: id 0 | task 32726 | n_gen = 261, tg = 43.15 t/s, tg_3s = 42.91 t/s 13.56.385.253 I slot print_timing: id 0 | task 32726 | n_gen = 390, tg = 43.04 t/s, tg_3s = 42.83 t/s 13.59.398.780 I slot print_timing: id 0 | task 32726 | n_gen = 519, tg = 42.98 t/s, tg_3s = 42.81 t/s 14.02.413.518 I slot print_timing: id 0 | task 32726 | n_gen = 648, tg = 42.94 t/s, tg_3s = 42.79 t/s 14.05.434.996 I slot print_timing: id 0 | task 32726 | n_gen = 777, tg = 42.90 t/s, tg_3s = 42.69 t/s 14.06.816.566 I slot print_timing: id 0 | task 32726 | prompt eval time = 575.74 ms / 256 tokens ( 2.25 ms per token, 444.65 tokens per second) 14.06.816.569 I slot print_timing: id 0 | task 32726 | eval time = 19469.47 ms / 836 tokens ( 23.32 ms per token, 42.89 tokens per second) 14.06.816.570 I slot print_timing: id 0 | task 32726 | total time = 20045.21 ms / 1092 tokens 14.06.816.571 I slot print_timing: id 0 | task 32726 | graphs reused = 32770 14.06.816.571 I slot print_timing: id 0 | task 32726 | graph reallocs = 0 / 0 (same size) / (changed size) 14.06.816.603 I slot release: id 0 | task 32726 | stop processing: n_tokens = 1091, truncated = 0 14.06.821.399 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.114 (> 0.100 thold), f_keep = 0.027 14.06.821.499 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 144.619 MiB) 14.06.831.437 I slot launch_slot_: id 0 | task 33565 | processing task, is_child = 0 14.08.263.909 I slot print_timing: id 0 | task 33565 | prompt eval time = 579.04 ms / 264 tokens ( 2.19 ms per token, 455.93 tokens per second) 14.08.263.915 I slot print_timing: id 0 | task 33565 | eval time = 853.42 ms / 38 tokens ( 23.07 ms per token, 43.35 tokens per second) 14.08.263.916 I slot print_timing: id 0 | task 33565 | total time = 1432.46 ms / 302 tokens 14.08.263.916 I slot print_timing: id 0 | task 33565 | graphs reused = 32806 14.08.263.917 I slot print_timing: id 0 | task 33565 | graph reallocs = 0 / 0 (same size) / (changed size) 14.08.263.936 I slot release: id 0 | task 33565 | stop processing: n_tokens = 301, truncated = 0 14.08.268.670 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.104 (> 0.100 thold), f_keep = 0.100 14.08.268.713 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 161.854 MiB) 14.08.271.372 I slot launch_slot_: id 0 | task 33606 | processing task, is_child = 0 14.11.922.896 I slot print_timing: id 0 | task 33606 | n_gen = 131, tg = 43.02 t/s, tg_3s = 43.35 t/s 14.14.943.694 I slot print_timing: id 0 | task 33606 | n_gen = 260, tg = 42.86 t/s, tg_3s = 42.70 t/s 14.17.947.145 I slot print_timing: id 0 | task 33606 | n_gen = 389, tg = 42.89 t/s, tg_3s = 42.95 t/s 14.20.958.761 I slot print_timing: id 0 | task 33606 | n_gen = 518, tg = 42.88 t/s, tg_3s = 42.83 t/s 14.23.972.860 I slot print_timing: id 0 | task 33606 | n_gen = 647, tg = 42.86 t/s, tg_3s = 42.80 t/s 14.24.089.575 I slot print_timing: id 0 | task 33606 | prompt eval time = 629.50 ms / 289 tokens ( 2.18 ms per token, 459.09 tokens per second) 14.24.089.577 I slot print_timing: id 0 | task 33606 | eval time = 15188.69 ms / 652 tokens ( 23.33 ms per token, 42.86 tokens per second) 14.24.089.578 I slot print_timing: id 0 | task 33606 | total time = 15818.19 ms / 941 tokens 14.24.089.578 I slot print_timing: id 0 | task 33606 | graphs reused = 33454 14.24.089.579 I slot print_timing: id 0 | task 33606 | graph reallocs = 0 / 0 (same size) / (changed size) 14.24.089.602 I slot release: id 0 | task 33606 | stop processing: n_tokens = 940, truncated = 0 14.24.094.762 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.102 (> 0.100 thold), f_keep = 0.032 14.24.094.846 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 130.485 MiB) 14.24.099.077 I slot launch_slot_: id 0 | task 34261 | processing task, is_child = 0 14.25.181.233 I slot print_timing: id 0 | task 34261 | prompt eval time = 631.01 ms / 294 tokens ( 2.15 ms per token, 465.92 tokens per second) 14.25.181.237 I slot print_timing: id 0 | task 34261 | eval time = 451.13 ms / 20 tokens ( 23.74 ms per token, 42.12 tokens per second) 14.25.181.237 I slot print_timing: id 0 | task 34261 | total time = 1082.14 ms / 314 tokens 14.25.181.238 I slot print_timing: id 0 | task 34261 | graphs reused = 33472 14.25.181.239 I slot print_timing: id 0 | task 34261 | graph reallocs = 0 / 0 (same size) / (changed size) 14.25.181.262 I slot release: id 0 | task 34261 | stop processing: n_tokens = 313, truncated = 0 14.25.185.955 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.103 (> 0.100 thold), f_keep = 0.096 14.25.189.185 I slot launch_slot_: id 0 | task 34284 | processing task, is_child = 0 14.28.830.143 I slot print_timing: id 0 | task 34284 | n_gen = 131, tg = 43.19 t/s, tg_3s = 43.52 t/s 14.29.994.306 I slot print_timing: id 0 | task 34284 | prompt eval time = 631.02 ms / 292 tokens ( 2.16 ms per token, 462.74 tokens per second) 14.29.994.313 I slot print_timing: id 0 | task 34284 | eval time = 4174.08 ms / 181 tokens ( 23.19 ms per token, 43.12 tokens per second) 14.29.994.313 I slot print_timing: id 0 | task 34284 | total time = 4805.11 ms / 473 tokens 14.29.994.314 I slot print_timing: id 0 | task 34284 | graphs reused = 33651 14.29.994.315 I slot print_timing: id 0 | task 34284 | graph reallocs = 0 / 0 (same size) / (changed size) 14.29.994.337 I slot release: id 0 | task 34284 | stop processing: n_tokens = 472, truncated = 0 14.29.998.968 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.122 (> 0.100 thold), f_keep = 0.064 14.29.999.034 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.109 MiB) 14.30.002.574 I slot launch_slot_: id 0 | task 34468 | processing task, is_child = 0 14.31.645.739 I slot print_timing: id 0 | task 34468 | prompt eval time = 527.17 ms / 245 tokens ( 2.15 ms per token, 464.74 tokens per second) 14.31.645.742 I slot print_timing: id 0 | task 34468 | eval time = 1115.98 ms / 49 tokens ( 23.25 ms per token, 43.01 tokens per second) 14.31.645.743 I slot print_timing: id 0 | task 34468 | total time = 1643.15 ms / 294 tokens 14.31.645.743 I slot print_timing: id 0 | task 34468 | graphs reused = 33697 14.31.645.744 I slot print_timing: id 0 | task 34468 | graph reallocs = 0 / 0 (same size) / (changed size) 14.31.645.764 I slot release: id 0 | task 34468 | stop processing: n_tokens = 293, truncated = 0 14.31.649.940 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 14.31.649.985 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 136.638 MiB) 14.31.652.537 I slot launch_slot_: id 0 | task 34520 | processing task, is_child = 0 14.35.069.658 I slot print_timing: id 0 | task 34520 | n_gen = 132, tg = 43.58 t/s, tg_3s = 43.91 t/s 14.38.084.009 I slot print_timing: id 0 | task 34520 | n_gen = 262, tg = 43.35 t/s, tg_3s = 43.13 t/s 14.41.091.686 I slot print_timing: id 0 | task 34520 | n_gen = 391, tg = 43.20 t/s, tg_3s = 42.89 t/s 14.42.794.140 I slot print_timing: id 0 | task 34520 | prompt eval time = 410.97 ms / 178 tokens ( 2.31 ms per token, 433.12 tokens per second) 14.42.794.147 I slot print_timing: id 0 | task 34520 | eval time = 10730.62 ms / 464 tokens ( 23.18 ms per token, 43.15 tokens per second) 14.42.794.147 I slot print_timing: id 0 | task 34520 | total time = 11141.60 ms / 642 tokens 14.42.794.148 I slot print_timing: id 0 | task 34520 | graphs reused = 34157 14.42.794.148 I slot print_timing: id 0 | task 34520 | graph reallocs = 0 / 0 (same size) / (changed size) 14.42.794.171 I slot release: id 0 | task 34520 | stop processing: n_tokens = 641, truncated = 0 14.42.799.589 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 641, t_last = 330320176451 14.42.799.660 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 87.201 MiB) 14.42.807.871 I slot launch_slot_: id 0 | task 34987 | processing task, is_child = 0 14.46.570.748 I slot print_timing: id 0 | task 34987 | n_gen = 131, tg = 43.05 t/s, tg_3s = 43.39 t/s 14.49.587.171 I slot print_timing: id 0 | task 34987 | n_gen = 260, tg = 42.91 t/s, tg_3s = 42.77 t/s 14.52.592.312 I slot print_timing: id 0 | task 34987 | n_gen = 389, tg = 42.92 t/s, tg_3s = 42.93 t/s 14.55.601.977 I slot print_timing: id 0 | task 34987 | n_gen = 518, tg = 42.90 t/s, tg_3s = 42.86 t/s 14.58.605.326 I slot print_timing: id 0 | task 34987 | n_gen = 646, tg = 42.85 t/s, tg_3s = 42.62 t/s 15.01.618.174 I slot print_timing: id 0 | task 34987 | n_gen = 774, tg = 42.79 t/s, tg_3s = 42.48 t/s 15.04.641.393 I slot print_timing: id 0 | task 34987 | n_gen = 903, tg = 42.77 t/s, tg_3s = 42.67 t/s 15.07.482.629 I slot print_timing: id 0 | task 34987 | prompt eval time = 743.40 ms / 355 tokens ( 2.09 ms per token, 477.53 tokens per second) 15.07.482.632 I slot print_timing: id 0 | task 34987 | eval time = 23931.35 ms / 1024 tokens ( 23.39 ms per token, 42.75 tokens per second) 15.07.482.633 I slot print_timing: id 0 | task 34987 | total time = 24674.75 ms / 1379 tokens 15.07.482.633 I slot print_timing: id 0 | task 34987 | graphs reused = 35175 15.07.482.634 I slot print_timing: id 0 | task 34987 | graph reallocs = 0 / 0 (same size) / (changed size) 15.07.482.660 I slot release: id 0 | task 34987 | stop processing: n_tokens = 1378, truncated = 0 15.07.488.730 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1378, t_last = 330344864940 15.07.488.846 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 119.022 MiB) 15.07.488.852 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 101.793 MiB) 15.07.500.048 I slot launch_slot_: id 0 | task 36014 | processing task, is_child = 0 15.11.684.339 I slot print_timing: id 0 | task 36014 | n_gen = 130, tg = 42.77 t/s, tg_3s = 43.10 t/s 15.14.696.934 I slot print_timing: id 0 | task 36014 | n_gen = 259, tg = 42.80 t/s, tg_3s = 42.82 t/s 15.17.710.986 I slot print_timing: id 0 | task 36014 | n_gen = 388, tg = 42.80 t/s, tg_3s = 42.80 t/s 15.19.772.004 I slot print_timing: id 0 | task 36014 | prompt eval time = 1168.29 ms / 567 tokens ( 2.06 ms per token, 485.33 tokens per second) 15.19.772.010 I slot print_timing: id 0 | task 36014 | eval time = 11103.66 ms / 476 tokens ( 23.38 ms per token, 42.78 tokens per second) 15.19.772.011 I slot print_timing: id 0 | task 36014 | total time = 12271.95 ms / 1043 tokens 15.19.772.011 I slot print_timing: id 0 | task 36014 | graphs reused = 35647 15.19.772.012 I slot print_timing: id 0 | task 36014 | graph reallocs = 0 / 0 (same size) / (changed size) 15.19.772.048 I slot release: id 0 | task 36014 | stop processing: n_tokens = 1042, truncated = 0 15.19.777.842 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1042, t_last = 330357154328 15.19.777.935 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 88.854 MiB) 15.19.777.941 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 153.169 MiB) 15.19.783.588 I slot launch_slot_: id 0 | task 36494 | processing task, is_child = 0 15.23.757.416 I slot print_timing: id 0 | task 36494 | n_gen = 130, tg = 42.82 t/s, tg_3s = 43.16 t/s 15.26.780.314 I slot print_timing: id 0 | task 36494 | n_gen = 259, tg = 42.75 t/s, tg_3s = 42.67 t/s 15.28.721.784 I slot print_timing: id 0 | task 36494 | prompt eval time = 961.54 ms / 473 tokens ( 2.03 ms per token, 491.92 tokens per second) 15.28.721.787 I slot print_timing: id 0 | task 36494 | eval time = 7976.64 ms / 342 tokens ( 23.39 ms per token, 42.75 tokens per second) 15.28.721.788 I slot print_timing: id 0 | task 36494 | total time = 8938.18 ms / 815 tokens 15.28.721.788 I slot print_timing: id 0 | task 36494 | graphs reused = 35985 15.28.721.789 I slot print_timing: id 0 | task 36494 | graph reallocs = 0 / 0 (same size) / (changed size) 15.28.721.818 I slot release: id 0 | task 36494 | stop processing: n_tokens = 814, truncated = 0 15.28.727.173 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 814, t_last = 330366104098 15.28.727.253 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 89.662 MiB) 15.28.736.958 I slot launch_slot_: id 0 | task 36839 | processing task, is_child = 0 15.32.546.724 I slot print_timing: id 0 | task 36839 | n_gen = 130, tg = 42.86 t/s, tg_3s = 43.20 t/s 15.35.557.047 I slot print_timing: id 0 | task 36839 | n_gen = 259, tg = 42.86 t/s, tg_3s = 42.85 t/s 15.38.568.157 I slot print_timing: id 0 | task 36839 | n_gen = 388, tg = 42.85 t/s, tg_3s = 42.84 t/s 15.41.582.925 I slot print_timing: id 0 | task 36839 | n_gen = 517, tg = 42.84 t/s, tg_3s = 42.79 t/s 15.44.602.289 I slot print_timing: id 0 | task 36839 | n_gen = 646, tg = 42.81 t/s, tg_3s = 42.72 t/s 15.47.623.219 I slot print_timing: id 0 | task 36839 | n_gen = 775, tg = 42.80 t/s, tg_3s = 42.70 t/s 15.50.625.026 I slot print_timing: id 0 | task 36839 | n_gen = 903, tg = 42.77 t/s, tg_3s = 42.64 t/s 15.53.467.518 I slot print_timing: id 0 | task 36839 | prompt eval time = 800.23 ms / 399 tokens ( 2.01 ms per token, 498.60 tokens per second) 15.53.467.521 I slot print_timing: id 0 | task 36839 | eval time = 23930.32 ms / 1024 tokens ( 23.39 ms per token, 42.75 tokens per second) 15.53.467.522 I slot print_timing: id 0 | task 36839 | total time = 24730.55 ms / 1423 tokens 15.53.467.523 I slot print_timing: id 0 | task 36839 | graphs reused = 37003 15.53.467.523 I slot print_timing: id 0 | task 36839 | graph reallocs = 0 / 0 (same size) / (changed size) 15.53.467.553 I slot release: id 0 | task 36839 | stop processing: n_tokens = 1422, truncated = 0 15.53.472.579 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1422, t_last = 330390849834 15.53.472.692 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 139.450 MiB) 15.53.484.089 I slot launch_slot_: id 0 | task 37866 | processing task, is_child = 0 15.57.186.052 I slot print_timing: id 0 | task 37866 | n_gen = 131, tg = 43.11 t/s, tg_3s = 43.44 t/s 15.58.319.346 I slot print_timing: id 0 | task 37866 | prompt eval time = 686.43 ms / 312 tokens ( 2.20 ms per token, 454.53 tokens per second) 15.58.319.350 I slot print_timing: id 0 | task 37866 | eval time = 4148.82 ms / 177 tokens ( 23.57 ms per token, 42.42 tokens per second) 15.58.319.351 I slot print_timing: id 0 | task 37866 | total time = 4835.24 ms / 489 tokens 15.58.319.352 I slot print_timing: id 0 | task 37866 | graphs reused = 37178 15.58.319.352 I slot print_timing: id 0 | task 37866 | graph reallocs = 0 / 0 (same size) / (changed size) 15.58.319.375 I slot release: id 0 | task 37866 | stop processing: n_tokens = 488, truncated = 0 15.58.325.652 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 488, t_last = 330395701655 15.58.325.717 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 111.920 MiB) 15.58.329.491 I slot launch_slot_: id 0 | task 38046 | processing task, is_child = 0 16.02.505.987 I slot print_timing: id 0 | task 38046 | n_gen = 130, tg = 42.77 t/s, tg_3s = 43.11 t/s 16.05.519.560 I slot print_timing: id 0 | task 38046 | n_gen = 259, tg = 42.79 t/s, tg_3s = 42.81 t/s 16.08.533.279 I slot print_timing: id 0 | task 38046 | n_gen = 388, tg = 42.80 t/s, tg_3s = 42.80 t/s 16.11.534.808 I slot print_timing: id 0 | task 38046 | n_gen = 516, tg = 42.76 t/s, tg_3s = 42.64 t/s 16.14.557.774 I slot print_timing: id 0 | task 38046 | n_gen = 645, tg = 42.74 t/s, tg_3s = 42.67 t/s 16.17.561.108 I slot print_timing: id 0 | task 38046 | n_gen = 773, tg = 42.72 t/s, tg_3s = 42.62 t/s 16.20.568.283 I slot print_timing: id 0 | task 38046 | n_gen = 901, tg = 42.70 t/s, tg_3s = 42.56 t/s 16.23.467.920 I slot print_timing: id 0 | task 38046 | prompt eval time = 1160.68 ms / 561 tokens ( 2.07 ms per token, 483.34 tokens per second) 16.23.467.926 I slot print_timing: id 0 | task 38046 | eval time = 23977.74 ms / 1024 tokens ( 23.44 ms per token, 42.66 tokens per second) 16.23.467.927 I slot print_timing: id 0 | task 38046 | total time = 25138.42 ms / 1585 tokens 16.23.467.928 I slot print_timing: id 0 | task 38046 | graphs reused = 38196 16.23.467.928 I slot print_timing: id 0 | task 38046 | graph reallocs = 0 / 0 (same size) / (changed size) 16.23.467.963 I slot release: id 0 | task 38046 | stop processing: n_tokens = 1584, truncated = 0 16.23.473.251 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1584, t_last = 330420850243 16.23.473.365 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 229.646 MiB) 16.23.480.859 I slot launch_slot_: id 0 | task 39074 | processing task, is_child = 0 16.26.474.823 I slot print_timing: id 0 | task 39074 | prompt eval time = 684.01 ms / 317 tokens ( 2.16 ms per token, 463.44 tokens per second) 16.26.474.826 I slot print_timing: id 0 | task 39074 | eval time = 2309.93 ms / 100 tokens ( 23.33 ms per token, 42.86 tokens per second) 16.26.474.827 I slot print_timing: id 0 | task 39074 | total time = 2993.94 ms / 417 tokens 16.26.474.827 I slot print_timing: id 0 | task 39074 | graphs reused = 38294 16.26.474.828 I slot print_timing: id 0 | task 39074 | graph reallocs = 0 / 0 (same size) / (changed size) 16.26.474.859 I slot release: id 0 | task 39074 | stop processing: n_tokens = 416, truncated = 0 16.26.480.389 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 330423857139 16.26.480.444 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 110.478 MiB) 16.26.484.226 I slot launch_slot_: id 0 | task 39177 | processing task, is_child = 0 16.28.601.038 I slot print_timing: id 0 | task 39177 | prompt eval time = 856.45 ms / 428 tokens ( 2.00 ms per token, 499.74 tokens per second) 16.28.601.044 I slot print_timing: id 0 | task 39177 | eval time = 1260.36 ms / 55 tokens ( 23.34 ms per token, 42.85 tokens per second) 16.28.601.046 I slot print_timing: id 0 | task 39177 | total time = 2116.80 ms / 483 tokens 16.28.601.046 I slot print_timing: id 0 | task 39177 | graphs reused = 38347 16.28.601.047 I slot print_timing: id 0 | task 39177 | graph reallocs = 0 / 0 (same size) / (changed size) 16.28.601.077 I slot release: id 0 | task 39177 | stop processing: n_tokens = 482, truncated = 0 16.28.605.508 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.133 (> 0.100 thold), f_keep = 0.062 16.28.605.568 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 159.703 MiB) 16.28.610.466 I slot launch_slot_: id 0 | task 39235 | processing task, is_child = 0 16.32.150.803 I slot print_timing: id 0 | task 39235 | n_gen = 124, tg = 40.76 t/s, tg_3s = 41.09 t/s 16.35.160.910 I slot print_timing: id 0 | task 39235 | n_gen = 251, tg = 41.47 t/s, tg_3s = 42.19 t/s 16.38.178.567 I slot print_timing: id 0 | task 39235 | n_gen = 378, tg = 41.68 t/s, tg_3s = 42.09 t/s 16.41.194.275 I slot print_timing: id 0 | task 39235 | n_gen = 503, tg = 41.62 t/s, tg_3s = 41.45 t/s 16.42.199.336 I slot print_timing: id 0 | task 39235 | prompt eval time = 522.62 ms / 226 tokens ( 2.31 ms per token, 432.44 tokens per second) 16.42.199.342 I slot print_timing: id 0 | task 39235 | eval time = 13066.24 ms / 546 tokens ( 23.97 ms per token, 41.71 tokens per second) 16.42.199.343 I slot print_timing: id 0 | task 39235 | total time = 13588.86 ms / 772 tokens 16.42.199.344 I slot print_timing: id 0 | task 39235 | graphs reused = 38888 16.42.199.344 I slot print_timing: id 0 | task 39235 | graph reallocs = 0 / 0 (same size) / (changed size) 16.42.199.364 I slot release: id 0 | task 39235 | stop processing: n_tokens = 771, truncated = 0 16.42.204.780 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 771, t_last = 330439581644 16.42.204.855 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 184.281 MiB) 16.42.215.046 I slot launch_slot_: id 0 | task 39784 | processing task, is_child = 0 16.46.022.848 I slot print_timing: id 0 | task 39784 | n_gen = 130, tg = 42.85 t/s, tg_3s = 43.18 t/s 16.49.035.597 I slot print_timing: id 0 | task 39784 | n_gen = 259, tg = 42.83 t/s, tg_3s = 42.82 t/s 16.50.927.773 I slot print_timing: id 0 | task 39784 | prompt eval time = 797.23 ms / 386 tokens ( 2.07 ms per token, 484.18 tokens per second) 16.50.927.780 I slot print_timing: id 0 | task 39784 | eval time = 7915.49 ms / 340 tokens ( 23.35 ms per token, 42.83 tokens per second) 16.50.927.780 I slot print_timing: id 0 | task 39784 | total time = 8712.72 ms / 726 tokens 16.50.927.781 I slot print_timing: id 0 | task 39784 | graphs reused = 39225 16.50.927.781 I slot print_timing: id 0 | task 39784 | graph reallocs = 0 / 0 (same size) / (changed size) 16.50.927.808 I slot release: id 0 | task 39784 | stop processing: n_tokens = 725, truncated = 0 16.50.933.707 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 725, t_last = 330448310089 16.50.933.780 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.468 MiB) 16.50.938.896 I slot launch_slot_: id 0 | task 40127 | processing task, is_child = 0 16.54.966.027 I slot print_timing: id 0 | task 40127 | n_gen = 129, tg = 42.61 t/s, tg_3s = 42.95 t/s 16.57.975.243 I slot print_timing: id 0 | task 40127 | n_gen = 257, tg = 42.57 t/s, tg_3s = 42.54 t/s 17.00.989.884 I slot print_timing: id 0 | task 40127 | n_gen = 386, tg = 42.65 t/s, tg_3s = 42.79 t/s 17.03.997.271 I slot print_timing: id 0 | task 40127 | n_gen = 513, tg = 42.54 t/s, tg_3s = 42.23 t/s 17.07.020.152 I slot print_timing: id 0 | task 40127 | n_gen = 639, tg = 42.37 t/s, tg_3s = 41.68 t/s 17.10.042.758 I slot print_timing: id 0 | task 40127 | n_gen = 768, tg = 42.42 t/s, tg_3s = 42.68 t/s 17.13.059.506 I slot print_timing: id 0 | task 40127 | n_gen = 896, tg = 42.42 t/s, tg_3s = 42.43 t/s 17.16.061.767 I slot print_timing: id 0 | task 40127 | n_gen = 1023, tg = 42.41 t/s, tg_3s = 42.30 t/s 17.16.085.294 I slot print_timing: id 0 | task 40127 | prompt eval time = 1023.34 ms / 508 tokens ( 2.01 ms per token, 496.41 tokens per second) 17.16.085.299 I slot print_timing: id 0 | task 40127 | eval time = 24123.04 ms / 1024 tokens ( 23.58 ms per token, 42.41 tokens per second) 17.16.085.300 I slot print_timing: id 0 | task 40127 | total time = 25146.39 ms / 1532 tokens 17.16.085.301 I slot print_timing: id 0 | task 40127 | graphs reused = 40243 17.16.085.301 I slot print_timing: id 0 | task 40127 | graph reallocs = 0 / 0 (same size) / (changed size) 17.16.085.335 I slot release: id 0 | task 40127 | stop processing: n_tokens = 1531, truncated = 0 17.16.091.663 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1531, t_last = 330473467615 17.16.091.781 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.924 MiB) 17.16.105.845 I slot launch_slot_: id 0 | task 41154 | processing task, is_child = 0 17.20.280.337 I slot print_timing: id 0 | task 41154 | n_gen = 130, tg = 42.79 t/s, tg_3s = 43.12 t/s 17.23.293.884 I slot print_timing: id 0 | task 41154 | n_gen = 259, tg = 42.80 t/s, tg_3s = 42.81 t/s 17.26.296.661 I slot print_timing: id 0 | task 41154 | n_gen = 387, tg = 42.74 t/s, tg_3s = 42.63 t/s 17.29.296.872 I slot print_timing: id 0 | task 41154 | n_gen = 515, tg = 42.72 t/s, tg_3s = 42.66 t/s 17.32.319.766 I slot print_timing: id 0 | task 41154 | n_gen = 644, tg = 42.71 t/s, tg_3s = 42.67 t/s 17.35.334.763 I slot print_timing: id 0 | task 41154 | n_gen = 772, tg = 42.67 t/s, tg_3s = 42.45 t/s 17.38.340.261 I slot print_timing: id 0 | task 41154 | n_gen = 900, tg = 42.66 t/s, tg_3s = 42.59 t/s 17.41.262.988 I slot print_timing: id 0 | task 41154 | prompt eval time = 1159.47 ms / 567 tokens ( 2.04 ms per token, 489.02 tokens per second) 17.41.262.994 I slot print_timing: id 0 | task 41154 | eval time = 23997.66 ms / 1024 tokens ( 23.46 ms per token, 42.63 tokens per second) 17.41.262.995 I slot print_timing: id 0 | task 41154 | total time = 25157.13 ms / 1591 tokens 17.41.262.995 I slot print_timing: id 0 | task 41154 | graphs reused = 41261 17.41.262.996 I slot print_timing: id 0 | task 41154 | graph reallocs = 0 / 0 (same size) / (changed size) 17.41.263.033 I slot release: id 0 | task 41154 | stop processing: n_tokens = 1590, truncated = 0 17.41.268.562 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1590, t_last = 330498645313 17.41.268.677 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 146.624 MiB) 17.41.268.681 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 190.259 MiB) 17.41.285.389 I slot launch_slot_: id 0 | task 42182 | processing task, is_child = 0 17.45.008.450 I slot print_timing: id 0 | task 42182 | prompt eval time = 797.57 ms / 384 tokens ( 2.08 ms per token, 481.46 tokens per second) 17.45.008.456 I slot print_timing: id 0 | task 42182 | eval time = 2925.48 ms / 123 tokens ( 23.98 ms per token, 41.70 tokens per second) 17.45.008.458 I slot print_timing: id 0 | task 42182 | total time = 3723.05 ms / 507 tokens 17.45.008.458 I slot print_timing: id 0 | task 42182 | graphs reused = 41382 17.45.008.459 I slot print_timing: id 0 | task 42182 | graph reallocs = 0 / 0 (same size) / (changed size) 17.45.008.488 I slot release: id 0 | task 42182 | stop processing: n_tokens = 506, truncated = 0 17.45.014.087 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 506, t_last = 330502390768 17.45.014.149 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 145.288 MiB) 17.45.018.280 I slot launch_slot_: id 0 | task 42308 | processing task, is_child = 0 17.48.986.699 I slot print_timing: id 0 | task 42308 | n_gen = 130, tg = 42.84 t/s, tg_3s = 43.17 t/s 17.51.998.625 I slot print_timing: id 0 | task 42308 | n_gen = 259, tg = 42.84 t/s, tg_3s = 42.83 t/s 17.55.008.508 I slot print_timing: id 0 | task 42308 | n_gen = 387, tg = 42.73 t/s, tg_3s = 42.53 t/s 17.58.027.181 I slot print_timing: id 0 | task 42308 | n_gen = 516, tg = 42.73 t/s, tg_3s = 42.73 t/s 18.01.041.192 I slot print_timing: id 0 | task 42308 | n_gen = 644, tg = 42.68 t/s, tg_3s = 42.47 t/s 18.04.042.352 I slot print_timing: id 0 | task 42308 | n_gen = 772, tg = 42.68 t/s, tg_3s = 42.65 t/s 18.07.056.405 I slot print_timing: id 0 | task 42308 | n_gen = 900, tg = 42.65 t/s, tg_3s = 42.47 t/s 18.09.971.993 I slot print_timing: id 0 | task 42308 | prompt eval time = 957.34 ms / 457 tokens ( 2.09 ms per token, 477.37 tokens per second) 18.09.971.999 I slot print_timing: id 0 | task 42308 | eval time = 23996.37 ms / 1024 tokens ( 23.46 ms per token, 42.63 tokens per second) 18.09.972.001 I slot print_timing: id 0 | task 42308 | total time = 24953.70 ms / 1481 tokens 18.09.972.002 I slot print_timing: id 0 | task 42308 | graphs reused = 42400 18.09.972.002 I slot print_timing: id 0 | task 42308 | graph reallocs = 0 / 0 (same size) / (changed size) 18.09.972.036 I slot release: id 0 | task 42308 | stop processing: n_tokens = 1480, truncated = 0 18.09.977.632 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1480, t_last = 330527354316 18.09.977.743 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 132.560 MiB) 18.09.989.905 I slot launch_slot_: id 0 | task 43335 | processing task, is_child = 0 18.13.858.769 I slot print_timing: id 0 | task 43335 | n_gen = 130, tg = 42.82 t/s, tg_3s = 43.15 t/s 18.16.860.132 I slot print_timing: id 0 | task 43335 | n_gen = 258, tg = 42.73 t/s, tg_3s = 42.65 t/s 18.19.873.761 I slot print_timing: id 0 | task 43335 | n_gen = 387, tg = 42.76 t/s, tg_3s = 42.81 t/s 18.22.877.183 I slot print_timing: id 0 | task 43335 | n_gen = 515, tg = 42.72 t/s, tg_3s = 42.62 t/s 18.25.877.945 I slot print_timing: id 0 | task 43335 | n_gen = 643, tg = 42.71 t/s, tg_3s = 42.66 t/s 18.28.880.087 I slot print_timing: id 0 | task 43335 | n_gen = 770, tg = 42.64 t/s, tg_3s = 42.30 t/s 18.31.884.192 I slot print_timing: id 0 | task 43335 | n_gen = 898, tg = 42.64 t/s, tg_3s = 42.61 t/s 18.34.856.135 I slot print_timing: id 0 | task 43335 | prompt eval time = 856.07 ms / 428 tokens ( 2.00 ms per token, 499.96 tokens per second) 18.34.856.143 I slot print_timing: id 0 | task 43335 | eval time = 24010.15 ms / 1024 tokens ( 23.47 ms per token, 42.61 tokens per second) 18.34.856.143 I slot print_timing: id 0 | task 43335 | total time = 24866.22 ms / 1452 tokens 18.34.856.144 I slot print_timing: id 0 | task 43335 | graphs reused = 43418 18.34.856.144 I slot print_timing: id 0 | task 43335 | graph reallocs = 0 / 0 (same size) / (changed size) 18.34.856.179 I slot release: id 0 | task 43335 | stop processing: n_tokens = 1451, truncated = 0 18.34.862.454 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1451, t_last = 330552238459 18.34.862.565 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 92.475 MiB) 18.34.862.568 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.294 MiB) 18.34.874.027 I slot launch_slot_: id 0 | task 44362 | processing task, is_child = 0 18.39.046.455 I slot print_timing: id 0 | task 44362 | n_gen = 130, tg = 42.82 t/s, tg_3s = 43.15 t/s 18.42.056.949 I slot print_timing: id 0 | task 44362 | n_gen = 259, tg = 42.83 t/s, tg_3s = 42.85 t/s 18.45.072.300 I slot print_timing: id 0 | task 44362 | n_gen = 388, tg = 42.82 t/s, tg_3s = 42.78 t/s 18.48.094.118 I slot print_timing: id 0 | task 44362 | n_gen = 517, tg = 42.78 t/s, tg_3s = 42.69 t/s 18.51.095.930 I slot print_timing: id 0 | task 44362 | n_gen = 645, tg = 42.76 t/s, tg_3s = 42.64 t/s 18.54.101.087 I slot print_timing: id 0 | task 44362 | n_gen = 773, tg = 42.73 t/s, tg_3s = 42.59 t/s 18.57.109.377 I slot print_timing: id 0 | task 44362 | n_gen = 901, tg = 42.70 t/s, tg_3s = 42.55 t/s 19.00.007.918 I slot print_timing: id 0 | task 44362 | prompt eval time = 1159.49 ms / 555 tokens ( 2.09 ms per token, 478.66 tokens per second) 19.00.007.923 I slot print_timing: id 0 | task 44362 | eval time = 23974.40 ms / 1024 tokens ( 23.44 ms per token, 42.67 tokens per second) 19.00.007.923 I slot print_timing: id 0 | task 44362 | total time = 25133.88 ms / 1579 tokens 19.00.007.924 I slot print_timing: id 0 | task 44362 | graphs reused = 44436 19.00.007.925 I slot print_timing: id 0 | task 44362 | graph reallocs = 0 / 0 (same size) / (changed size) 19.00.007.966 I slot release: id 0 | task 44362 | stop processing: n_tokens = 1578, truncated = 0 19.00.014.964 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1578, t_last = 330577390246 19.00.015.080 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 112.306 MiB) 19.00.015.084 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 151.124 MiB) 19.00.029.546 I slot launch_slot_: id 0 | task 45390 | processing task, is_child = 0 19.04.325.692 I slot print_timing: id 0 | task 45390 | n_gen = 130, tg = 42.76 t/s, tg_3s = 43.09 t/s 19.07.338.794 I slot print_timing: id 0 | task 45390 | n_gen = 259, tg = 42.79 t/s, tg_3s = 42.81 t/s 19.10.358.727 I slot print_timing: id 0 | task 45390 | n_gen = 388, tg = 42.76 t/s, tg_3s = 42.72 t/s 19.13.371.078 I slot print_timing: id 0 | task 45390 | n_gen = 516, tg = 42.70 t/s, tg_3s = 42.49 t/s 19.16.373.484 I slot print_timing: id 0 | task 45390 | n_gen = 644, tg = 42.68 t/s, tg_3s = 42.63 t/s 19.19.378.249 I slot print_timing: id 0 | task 45390 | n_gen = 772, tg = 42.67 t/s, tg_3s = 42.60 t/s 19.22.394.826 I slot print_timing: id 0 | task 45390 | n_gen = 899, tg = 42.59 t/s, tg_3s = 42.10 t/s 19.25.344.483 I slot print_timing: id 0 | task 45390 | prompt eval time = 1279.25 ms / 643 tokens ( 1.99 ms per token, 502.64 tokens per second) 19.25.344.490 I slot print_timing: id 0 | task 45390 | eval time = 24035.68 ms / 1024 tokens ( 23.50 ms per token, 42.56 tokens per second) 19.25.344.491 I slot print_timing: id 0 | task 45390 | total time = 25314.92 ms / 1667 tokens 19.25.344.491 I slot print_timing: id 0 | task 45390 | graphs reused = 45454 19.25.344.492 I slot print_timing: id 0 | task 45390 | graph reallocs = 0 / 0 (same size) / (changed size) 19.25.344.528 I slot release: id 0 | task 45390 | stop processing: n_tokens = 1666, truncated = 0 19.25.350.421 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1666, t_last = 330602726808 19.25.350.544 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 130.625 MiB) 19.25.365.927 I slot launch_slot_: id 0 | task 46418 | processing task, is_child = 0 19.29.282.988 I slot print_timing: id 0 | task 46418 | n_gen = 130, tg = 42.89 t/s, tg_3s = 43.23 t/s 19.32.292.002 I slot print_timing: id 0 | task 46418 | n_gen = 259, tg = 42.88 t/s, tg_3s = 42.87 t/s 19.35.306.746 I slot print_timing: id 0 | task 46418 | n_gen = 388, tg = 42.85 t/s, tg_3s = 42.79 t/s 19.38.311.619 I slot print_timing: id 0 | task 46418 | n_gen = 516, tg = 42.79 t/s, tg_3s = 42.60 t/s 19.41.311.907 I slot print_timing: id 0 | task 46418 | n_gen = 644, tg = 42.76 t/s, tg_3s = 42.66 t/s 19.44.333.935 I slot print_timing: id 0 | task 46418 | n_gen = 773, tg = 42.75 t/s, tg_3s = 42.69 t/s 19.47.336.320 I slot print_timing: id 0 | task 46418 | n_gen = 901, tg = 42.73 t/s, tg_3s = 42.63 t/s 19.48.228.953 I slot print_timing: id 0 | task 46418 | prompt eval time = 909.60 ms / 460 tokens ( 1.98 ms per token, 505.72 tokens per second) 19.48.228.960 I slot print_timing: id 0 | task 46418 | eval time = 21953.41 ms / 939 tokens ( 23.40 ms per token, 42.73 tokens per second) 19.48.228.960 I slot print_timing: id 0 | task 46418 | total time = 22863.02 ms / 1399 tokens 19.48.228.961 I slot print_timing: id 0 | task 46418 | graphs reused = 46387 19.48.228.962 I slot print_timing: id 0 | task 46418 | graph reallocs = 0 / 0 (same size) / (changed size) 19.48.228.998 I slot release: id 0 | task 46418 | stop processing: n_tokens = 1398, truncated = 0 19.48.235.130 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1398, t_last = 330625611278 19.48.235.247 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 187.340 MiB) 19.48.248.320 I slot launch_slot_: id 0 | task 47360 | processing task, is_child = 0 19.52.286.016 I slot print_timing: id 0 | task 47360 | n_gen = 130, tg = 42.76 t/s, tg_3s = 43.09 t/s 19.55.297.848 I slot print_timing: id 0 | task 47360 | n_gen = 259, tg = 42.80 t/s, tg_3s = 42.83 t/s 19.58.319.037 I slot print_timing: id 0 | task 47360 | n_gen = 388, tg = 42.76 t/s, tg_3s = 42.70 t/s 20.01.334.837 I slot print_timing: id 0 | task 47360 | n_gen = 517, tg = 42.77 t/s, tg_3s = 42.77 t/s 20.04.354.128 I slot print_timing: id 0 | task 47360 | n_gen = 646, tg = 42.76 t/s, tg_3s = 42.73 t/s 20.07.363.667 I slot print_timing: id 0 | task 47360 | n_gen = 774, tg = 42.72 t/s, tg_3s = 42.53 t/s 20.10.364.957 I slot print_timing: id 0 | task 47360 | n_gen = 902, tg = 42.71 t/s, tg_3s = 42.65 t/s 20.13.233.341 I slot print_timing: id 0 | task 47360 | prompt eval time = 1020.99 ms / 516 tokens ( 1.98 ms per token, 505.39 tokens per second) 20.13.233.345 I slot print_timing: id 0 | task 47360 | eval time = 23964.03 ms / 1024 tokens ( 23.43 ms per token, 42.69 tokens per second) 20.13.233.346 I slot print_timing: id 0 | task 47360 | total time = 24985.01 ms / 1540 tokens 20.13.233.346 I slot print_timing: id 0 | task 47360 | graphs reused = 47405 20.13.233.347 I slot print_timing: id 0 | task 47360 | graph reallocs = 0 / 0 (same size) / (changed size) 20.13.233.386 I slot release: id 0 | task 47360 | stop processing: n_tokens = 1539, truncated = 0 20.13.238.636 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1539, t_last = 330650615666 20.13.238.753 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 128.726 MiB) 20.13.238.756 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 145.428 MiB) 20.13.253.178 I slot launch_slot_: id 0 | task 48387 | processing task, is_child = 0 20.16.954.727 I slot print_timing: id 0 | task 48387 | n_gen = 131, tg = 43.08 t/s, tg_3s = 43.41 t/s 20.19.978.110 I slot print_timing: id 0 | task 48387 | n_gen = 260, tg = 42.87 t/s, tg_3s = 42.67 t/s 20.22.989.417 I slot print_timing: id 0 | task 48387 | n_gen = 389, tg = 42.86 t/s, tg_3s = 42.84 t/s 20.26.002.996 I slot print_timing: id 0 | task 48387 | n_gen = 518, tg = 42.85 t/s, tg_3s = 42.81 t/s 20.29.021.008 I slot print_timing: id 0 | task 48387 | n_gen = 647, tg = 42.83 t/s, tg_3s = 42.74 t/s 20.31.459.732 I slot print_timing: id 0 | task 48387 | prompt eval time = 683.62 ms / 325 tokens ( 2.10 ms per token, 475.41 tokens per second) 20.31.459.739 I slot print_timing: id 0 | task 48387 | eval time = 17522.93 ms / 751 tokens ( 23.36 ms per token, 42.80 tokens per second) 20.31.459.740 I slot print_timing: id 0 | task 48387 | total time = 18206.54 ms / 1076 tokens 20.31.459.741 I slot print_timing: id 0 | task 48387 | graphs reused = 48151 20.31.459.741 I slot print_timing: id 0 | task 48387 | graph reallocs = 0 / 0 (same size) / (changed size) 20.31.459.766 I slot release: id 0 | task 48387 | stop processing: n_tokens = 1075, truncated = 0 20.31.465.748 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1075, t_last = 330668842046 20.31.465.840 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 136.286 MiB) 20.31.470.498 I slot launch_slot_: id 0 | task 49141 | processing task, is_child = 0 20.35.287.737 I slot print_timing: id 0 | task 49141 | n_gen = 130, tg = 42.70 t/s, tg_3s = 43.03 t/s 20.37.590.384 I slot print_timing: id 0 | task 49141 | prompt eval time = 796.11 ms / 393 tokens ( 2.03 ms per token, 493.65 tokens per second) 20.37.590.390 I slot print_timing: id 0 | task 49141 | eval time = 5323.77 ms / 228 tokens ( 23.45 ms per token, 42.64 tokens per second) 20.37.590.391 I slot print_timing: id 0 | task 49141 | total time = 6119.88 ms / 621 tokens 20.37.590.391 I slot print_timing: id 0 | task 49141 | graphs reused = 48376 20.37.590.392 I slot print_timing: id 0 | task 49141 | graph reallocs = 0 / 0 (same size) / (changed size) 20.37.590.427 I slot release: id 0 | task 49141 | stop processing: n_tokens = 620, truncated = 0 20.37.597.808 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 620, t_last = 330674972707 20.37.597.883 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 172.220 MiB) 20.37.602.963 I slot launch_slot_: id 0 | task 49372 | processing task, is_child = 0 20.42.000.993 I slot print_timing: id 0 | task 49372 | n_gen = 129, tg = 42.66 t/s, tg_3s = 43.00 t/s 20.45.014.307 I slot print_timing: id 0 | task 49372 | n_gen = 258, tg = 42.74 t/s, tg_3s = 42.81 t/s 20.48.030.441 I slot print_timing: id 0 | task 49372 | n_gen = 385, tg = 42.53 t/s, tg_3s = 42.11 t/s 20.51.045.527 I slot print_timing: id 0 | task 49372 | n_gen = 514, tg = 42.59 t/s, tg_3s = 42.78 t/s 20.54.046.948 I slot print_timing: id 0 | task 49372 | n_gen = 642, tg = 42.60 t/s, tg_3s = 42.65 t/s 20.57.051.250 I slot print_timing: id 0 | task 49372 | n_gen = 770, tg = 42.60 t/s, tg_3s = 42.61 t/s 21.00.064.194 I slot print_timing: id 0 | task 49372 | n_gen = 898, tg = 42.59 t/s, tg_3s = 42.48 t/s 21.03.032.408 I slot print_timing: id 0 | task 49372 | prompt eval time = 1397.80 ms / 695 tokens ( 2.01 ms per token, 497.21 tokens per second) 21.03.032.415 I slot print_timing: id 0 | task 49372 | eval time = 24031.64 ms / 1024 tokens ( 23.49 ms per token, 42.57 tokens per second) 21.03.032.415 I slot print_timing: id 0 | task 49372 | total time = 25429.43 ms / 1719 tokens 21.03.032.416 I slot print_timing: id 0 | task 49372 | graphs reused = 49394 21.03.032.416 I slot print_timing: id 0 | task 49372 | graph reallocs = 0 / 0 (same size) / (changed size) 21.03.032.456 I slot release: id 0 | task 49372 | stop processing: n_tokens = 1718, truncated = 0 21.03.039.449 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1718, t_last = 330700414736 21.03.039.577 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 188.887 MiB) 21.03.059.679 I slot launch_slot_: id 0 | task 50400 | processing task, is_child = 0 21.07.402.170 I slot print_timing: id 0 | task 50400 | n_gen = 130, tg = 42.77 t/s, tg_3s = 43.11 t/s 21.10.418.634 I slot print_timing: id 0 | task 50400 | n_gen = 259, tg = 42.77 t/s, tg_3s = 42.77 t/s 21.13.439.337 I slot print_timing: id 0 | task 50400 | n_gen = 388, tg = 42.75 t/s, tg_3s = 42.71 t/s 21.16.441.405 I slot print_timing: id 0 | task 50400 | n_gen = 516, tg = 42.72 t/s, tg_3s = 42.64 t/s 21.19.442.886 I slot print_timing: id 0 | task 50400 | n_gen = 643, tg = 42.64 t/s, tg_3s = 42.31 t/s 21.21.824.731 I slot print_timing: id 0 | task 50400 | prompt eval time = 1326.69 ms / 657 tokens ( 2.02 ms per token, 495.22 tokens per second) 21.21.824.740 I slot print_timing: id 0 | task 50400 | eval time = 17438.35 ms / 744 tokens ( 23.47 ms per token, 42.61 tokens per second) 21.21.824.741 I slot print_timing: id 0 | task 50400 | total time = 18765.04 ms / 1401 tokens 21.21.824.741 I slot print_timing: id 0 | task 50400 | graphs reused = 50133 21.21.824.742 I slot print_timing: id 0 | task 50400 | graph reallocs = 0 / 0 (same size) / (changed size) 21.21.824.785 I slot release: id 0 | task 50400 | stop processing: n_tokens = 1400, truncated = 0 21.21.829.577 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.130 (> 0.100 thold), f_keep = 0.021 21.21.829.698 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 133.690 MiB) 21.21.829.705 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 114.171 MiB) 21.21.844.570 I slot launch_slot_: id 0 | task 51148 | processing task, is_child = 0 21.25.346.161 I slot print_timing: id 0 | task 51148 | n_gen = 132, tg = 43.58 t/s, tg_3s = 43.91 t/s 21.27.225.353 I slot print_timing: id 0 | task 51148 | prompt eval time = 495.61 ms / 231 tokens ( 2.15 ms per token, 466.09 tokens per second) 21.27.225.357 I slot print_timing: id 0 | task 51148 | eval time = 4885.16 ms / 213 tokens ( 23.04 ms per token, 43.40 tokens per second) 21.27.225.358 I slot print_timing: id 0 | task 51148 | total time = 5380.77 ms / 444 tokens 21.27.225.359 I slot print_timing: id 0 | task 51148 | graphs reused = 50343 21.27.225.360 I slot print_timing: id 0 | task 51148 | graph reallocs = 0 / 0 (same size) / (changed size) 21.27.225.381 I slot release: id 0 | task 51148 | stop processing: n_tokens = 443, truncated = 0 21.27.229.598 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.187 (> 0.100 thold), f_keep = 0.070 21.27.229.655 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 134.921 MiB) 21.27.233.139 I slot launch_slot_: id 0 | task 51364 | processing task, is_child = 0 21.30.216.452 I slot print_timing: id 0 | task 51364 | prompt eval time = 376.86 ms / 166 tokens ( 2.27 ms per token, 440.48 tokens per second) 21.30.216.456 I slot print_timing: id 0 | task 51364 | eval time = 2606.43 ms / 114 tokens ( 23.07 ms per token, 43.35 tokens per second) 21.30.216.457 I slot print_timing: id 0 | task 51364 | total time = 2983.30 ms / 280 tokens 21.30.216.457 I slot print_timing: id 0 | task 51364 | graphs reused = 50454 21.30.216.458 I slot print_timing: id 0 | task 51364 | graph reallocs = 0 / 0 (same size) / (changed size) 21.30.216.478 I slot release: id 0 | task 51364 | stop processing: n_tokens = 279, truncated = 0 21.30.221.062 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.160 (> 0.100 thold), f_keep = 0.111 21.30.224.780 I slot launch_slot_: id 0 | task 51481 | processing task, is_child = 0 21.33.715.053 I slot print_timing: id 0 | task 51481 | n_gen = 133, tg = 43.72 t/s, tg_3s = 44.05 t/s 21.36.717.942 I slot print_timing: id 0 | task 51481 | n_gen = 262, tg = 43.34 t/s, tg_3s = 42.96 t/s 21.39.719.080 I slot print_timing: id 0 | task 51481 | n_gen = 390, tg = 43.11 t/s, tg_3s = 42.65 t/s 21.42.727.295 I slot print_timing: id 0 | task 51481 | n_gen = 518, tg = 42.97 t/s, tg_3s = 42.55 t/s 21.45.729.754 I slot print_timing: id 0 | task 51481 | n_gen = 646, tg = 42.90 t/s, tg_3s = 42.63 t/s 21.48.746.485 I slot print_timing: id 0 | task 51481 | n_gen = 775, tg = 42.88 t/s, tg_3s = 42.76 t/s 21.51.746.675 I slot print_timing: id 0 | task 51481 | n_gen = 902, tg = 42.80 t/s, tg_3s = 42.33 t/s 21.54.605.272 I slot print_timing: id 0 | task 51481 | prompt eval time = 471.20 ms / 194 tokens ( 2.43 ms per token, 411.71 tokens per second) 21.54.605.276 I slot print_timing: id 0 | task 51481 | eval time = 23909.28 ms / 1024 tokens ( 23.37 ms per token, 42.79 tokens per second) 21.54.605.277 I slot print_timing: id 0 | task 51481 | total time = 24380.48 ms / 1218 tokens 21.54.605.277 I slot print_timing: id 0 | task 51481 | graphs reused = 51472 21.54.605.278 I slot print_timing: id 0 | task 51481 | graph reallocs = 0 / 0 (same size) / (changed size) 21.54.605.301 I slot release: id 0 | task 51481 | stop processing: n_tokens = 1217, truncated = 0 21.54.609.475 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.208 (> 0.100 thold), f_keep = 0.025 21.54.609.580 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 75.423 MiB) 21.54.609.583 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 114.733 MiB) 21.54.620.608 I slot launch_slot_: id 0 | task 52508 | processing task, is_child = 0 21.56.412.374 I slot print_timing: id 0 | task 52508 | prompt eval time = 373.92 ms / 149 tokens ( 2.51 ms per token, 398.48 tokens per second) 21.56.412.378 I slot print_timing: id 0 | task 52508 | eval time = 1417.83 ms / 63 tokens ( 22.87 ms per token, 43.73 tokens per second) 21.56.412.379 I slot print_timing: id 0 | task 52508 | total time = 1791.76 ms / 212 tokens 21.56.412.380 I slot print_timing: id 0 | task 52508 | graphs reused = 51533 21.56.412.381 I slot print_timing: id 0 | task 52508 | graph reallocs = 0 / 0 (same size) / (changed size) 21.56.412.402 I slot release: id 0 | task 52508 | stop processing: n_tokens = 211, truncated = 0 21.56.417.081 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.137 (> 0.100 thold), f_keep = 0.142 21.56.420.751 I slot launch_slot_: id 0 | task 52574 | processing task, is_child = 0 21.59.946.754 I slot print_timing: id 0 | task 52574 | n_gen = 132, tg = 43.61 t/s, tg_3s = 43.95 t/s 22.02.362.049 I slot print_timing: id 0 | task 52574 | prompt eval time = 522.34 ms / 219 tokens ( 2.39 ms per token, 419.27 tokens per second) 22.02.362.052 I slot print_timing: id 0 | task 52574 | eval time = 5418.95 ms / 236 tokens ( 23.06 ms per token, 43.37 tokens per second) 22.02.362.053 I slot print_timing: id 0 | task 52574 | total time = 5941.29 ms / 455 tokens 22.02.362.054 I slot print_timing: id 0 | task 52574 | graphs reused = 51766 22.02.362.054 I slot print_timing: id 0 | task 52574 | graph reallocs = 0 / 0 (same size) / (changed size) 22.02.362.075 I slot release: id 0 | task 52574 | stop processing: n_tokens = 454, truncated = 0 22.02.366.123 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.227 (> 0.100 thold), f_keep = 0.066 22.02.366.180 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 142.832 MiB) 22.02.369.306 I slot launch_slot_: id 0 | task 52813 | processing task, is_child = 0 22.05.716.289 I slot print_timing: id 0 | task 52813 | n_gen = 132, tg = 43.49 t/s, tg_3s = 43.82 t/s 22.05.739.029 I slot print_timing: id 0 | task 52813 | prompt eval time = 334.65 ms / 132 tokens ( 2.54 ms per token, 394.44 tokens per second) 22.05.739.032 I slot print_timing: id 0 | task 52813 | eval time = 3035.06 ms / 133 tokens ( 22.99 ms per token, 43.49 tokens per second) 22.05.739.033 I slot print_timing: id 0 | task 52813 | total time = 3369.72 ms / 265 tokens 22.05.739.033 I slot print_timing: id 0 | task 52813 | graphs reused = 51896 22.05.739.034 I slot print_timing: id 0 | task 52813 | graph reallocs = 0 / 0 (same size) / (changed size) 22.05.739.051 I slot release: id 0 | task 52813 | stop processing: n_tokens = 264, truncated = 0 22.05.743.184 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.114 22.05.745.212 I slot launch_slot_: id 0 | task 52949 | processing task, is_child = 0 22.09.156.562 I slot print_timing: id 0 | task 52949 | n_gen = 129, tg = 42.19 t/s, tg_3s = 42.52 t/s 22.10.776.987 I slot print_timing: id 0 | task 52949 | prompt eval time = 377.79 ms / 169 tokens ( 2.24 ms per token, 447.34 tokens per second) 22.10.776.991 I slot print_timing: id 0 | task 52949 | eval time = 4653.98 ms / 198 tokens ( 23.62 ms per token, 42.33 tokens per second) 22.10.776.992 I slot print_timing: id 0 | task 52949 | total time = 5031.77 ms / 367 tokens 22.10.776.993 I slot print_timing: id 0 | task 52949 | graphs reused = 52091 22.10.776.993 I slot print_timing: id 0 | task 52949 | graph reallocs = 0 / 0 (same size) / (changed size) 22.10.777.017 I slot release: id 0 | task 52949 | stop processing: n_tokens = 366, truncated = 0 22.10.781.311 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.082 22.10.781.370 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 157.776 MiB) 22.10.785.487 I slot launch_slot_: id 0 | task 53150 | processing task, is_child = 0 22.13.199.325 I slot print_timing: id 0 | task 53150 | prompt eval time = 378.77 ms / 160 tokens ( 2.37 ms per token, 422.41 tokens per second) 22.13.199.328 I slot print_timing: id 0 | task 53150 | eval time = 2035.05 ms / 90 tokens ( 22.87 ms per token, 43.73 tokens per second) 22.13.199.328 I slot print_timing: id 0 | task 53150 | total time = 2413.83 ms / 250 tokens 22.13.199.329 I slot print_timing: id 0 | task 53150 | graphs reused = 52179 22.13.199.329 I slot print_timing: id 0 | task 53150 | graph reallocs = 0 / 0 (same size) / (changed size) 22.13.199.356 I slot release: id 0 | task 53150 | stop processing: n_tokens = 249, truncated = 0 22.13.203.494 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.291 (> 0.100 thold), f_keep = 0.120 22.13.206.809 I slot launch_slot_: id 0 | task 53243 | processing task, is_child = 0 22.16.495.068 I slot print_timing: id 0 | task 53243 | n_gen = 131, tg = 43.10 t/s, tg_3s = 43.43 t/s 22.18.999.237 I slot print_timing: id 0 | task 53243 | prompt eval time = 272.21 ms / 103 tokens ( 2.64 ms per token, 378.39 tokens per second) 22.18.999.245 I slot print_timing: id 0 | task 53243 | eval time = 5520.21 ms / 240 tokens ( 23.10 ms per token, 43.30 tokens per second) 22.18.999.245 I slot print_timing: id 0 | task 53243 | total time = 5792.41 ms / 343 tokens 22.18.999.246 I slot print_timing: id 0 | task 53243 | graphs reused = 52416 22.18.999.247 I slot print_timing: id 0 | task 53243 | graph reallocs = 0 / 0 (same size) / (changed size) 22.18.999.270 I slot release: id 0 | task 53243 | stop processing: n_tokens = 342, truncated = 0 22.19.003.526 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.088 22.19.003.574 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.115 MiB) 22.19.008.821 I slot launch_slot_: id 0 | task 53486 | processing task, is_child = 0 22.20.755.026 I slot print_timing: id 0 | task 53486 | prompt eval time = 410.03 ms / 165 tokens ( 2.49 ms per token, 402.41 tokens per second) 22.20.755.031 I slot print_timing: id 0 | task 53486 | eval time = 1336.17 ms / 55 tokens ( 24.74 ms per token, 40.41 tokens per second) 22.20.755.032 I slot print_timing: id 0 | task 53486 | total time = 1746.20 ms / 220 tokens 22.20.755.033 I slot print_timing: id 0 | task 53486 | graphs reused = 52469 22.20.755.033 I slot print_timing: id 0 | task 53486 | graph reallocs = 0 / 0 (same size) / (changed size) 22.20.755.050 I slot release: id 0 | task 53486 | stop processing: n_tokens = 219, truncated = 0 22.20.758.878 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.137 22.20.764.742 I slot launch_slot_: id 0 | task 53544 | processing task, is_child = 0 22.23.349.693 I slot print_timing: id 0 | task 53544 | prompt eval time = 381.03 ms / 165 tokens ( 2.31 ms per token, 433.03 tokens per second) 22.23.349.699 I slot print_timing: id 0 | task 53544 | eval time = 2203.91 ms / 95 tokens ( 23.45 ms per token, 42.65 tokens per second) 22.23.349.700 I slot print_timing: id 0 | task 53544 | total time = 2584.94 ms / 260 tokens 22.23.349.701 I slot print_timing: id 0 | task 53544 | graphs reused = 52561 22.23.349.701 I slot print_timing: id 0 | task 53544 | graph reallocs = 0 / 0 (same size) / (changed size) 22.23.349.721 I slot release: id 0 | task 53544 | stop processing: n_tokens = 259, truncated = 0 22.23.353.864 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.162 (> 0.100 thold), f_keep = 0.116 22.23.353.967 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.256 MiB) 22.23.360.166 I slot launch_slot_: id 0 | task 53642 | processing task, is_child = 0 22.26.839.659 I slot print_timing: id 0 | task 53642 | n_gen = 131, tg = 43.04 t/s, tg_3s = 43.37 t/s 22.29.852.240 I slot print_timing: id 0 | task 53642 | n_gen = 261, tg = 43.10 t/s, tg_3s = 43.15 t/s 22.32.864.841 I slot print_timing: id 0 | task 53642 | n_gen = 390, tg = 43.00 t/s, tg_3s = 42.82 t/s 22.35.880.632 I slot print_timing: id 0 | task 53642 | n_gen = 519, tg = 42.95 t/s, tg_3s = 42.77 t/s 22.38.896.951 I slot print_timing: id 0 | task 53642 | n_gen = 648, tg = 42.91 t/s, tg_3s = 42.77 t/s 22.41.915.315 I slot print_timing: id 0 | task 53642 | n_gen = 777, tg = 42.88 t/s, tg_3s = 42.74 t/s 22.44.928.178 I slot print_timing: id 0 | task 53642 | n_gen = 905, tg = 42.83 t/s, tg_3s = 42.48 t/s 22.47.718.833 I slot print_timing: id 0 | task 53642 | prompt eval time = 459.07 ms / 185 tokens ( 2.48 ms per token, 402.99 tokens per second) 22.47.718.836 I slot print_timing: id 0 | task 53642 | eval time = 23899.58 ms / 1024 tokens ( 23.36 ms per token, 42.80 tokens per second) 22.47.718.836 I slot print_timing: id 0 | task 53642 | total time = 24358.65 ms / 1209 tokens 22.47.718.837 I slot print_timing: id 0 | task 53642 | graphs reused = 53579 22.47.718.838 I slot print_timing: id 0 | task 53642 | graph reallocs = 0 / 0 (same size) / (changed size) 22.47.718.859 I slot release: id 0 | task 53642 | stop processing: n_tokens = 1208, truncated = 0 22.47.725.094 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.025 22.47.725.195 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 110.901 MiB) 22.47.729.346 I slot launch_slot_: id 0 | task 54669 | processing task, is_child = 0 22.48.612.378 I slot print_timing: id 0 | task 54669 | prompt eval time = 376.93 ms / 160 tokens ( 2.36 ms per token, 424.49 tokens per second) 22.48.612.385 I slot print_timing: id 0 | task 54669 | eval time = 506.09 ms / 23 tokens ( 23.00 ms per token, 43.47 tokens per second) 22.48.612.385 I slot print_timing: id 0 | task 54669 | total time = 883.02 ms / 183 tokens 22.48.612.386 I slot print_timing: id 0 | task 54669 | graphs reused = 53600 22.48.612.386 I slot print_timing: id 0 | task 54669 | graph reallocs = 0 / 0 (same size) / (changed size) 22.48.612.404 I slot release: id 0 | task 54669 | stop processing: n_tokens = 182, truncated = 0 22.48.616.246 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.191 (> 0.100 thold), f_keep = 0.165 22.48.620.630 I slot launch_slot_: id 0 | task 54695 | processing task, is_child = 0 22.51.933.127 I slot print_timing: id 0 | task 54695 | prompt eval time = 386.19 ms / 157 tokens ( 2.46 ms per token, 406.53 tokens per second) 22.51.933.130 I slot print_timing: id 0 | task 54695 | eval time = 2926.29 ms / 129 tokens ( 22.86 ms per token, 43.74 tokens per second) 22.51.933.131 I slot print_timing: id 0 | task 54695 | total time = 3312.48 ms / 286 tokens 22.51.933.132 I slot print_timing: id 0 | task 54695 | graphs reused = 53726 22.51.933.132 I slot print_timing: id 0 | task 54695 | graph reallocs = 0 / 0 (same size) / (changed size) 22.51.933.157 I slot release: id 0 | task 54695 | stop processing: n_tokens = 285, truncated = 0 22.51.937.633 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.105 22.51.937.680 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 119.902 MiB) 22.51.941.350 I slot launch_slot_: id 0 | task 54827 | processing task, is_child = 0 22.54.432.156 I slot print_timing: id 0 | task 54827 | prompt eval time = 389.02 ms / 171 tokens ( 2.27 ms per token, 439.56 tokens per second) 22.54.432.163 I slot print_timing: id 0 | task 54827 | eval time = 2101.77 ms / 93 tokens ( 22.85 ms per token, 43.77 tokens per second) 22.54.432.163 I slot print_timing: id 0 | task 54827 | total time = 2490.80 ms / 264 tokens 22.54.432.164 I slot print_timing: id 0 | task 54827 | graphs reused = 53816 22.54.432.165 I slot print_timing: id 0 | task 54827 | graph reallocs = 0 / 0 (same size) / (changed size) 22.54.432.182 I slot release: id 0 | task 54827 | stop processing: n_tokens = 263, truncated = 0 22.54.436.261 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.164 (> 0.100 thold), f_keep = 0.114 22.54.436.303 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 112.729 MiB) 22.54.439.719 I slot launch_slot_: id 0 | task 54923 | processing task, is_child = 0 22.56.932.970 I slot print_timing: id 0 | task 54923 | prompt eval time = 471.16 ms / 183 tokens ( 2.57 ms per token, 388.40 tokens per second) 22.56.932.975 I slot print_timing: id 0 | task 54923 | eval time = 2022.08 ms / 89 tokens ( 22.98 ms per token, 43.52 tokens per second) 22.56.932.975 I slot print_timing: id 0 | task 54923 | total time = 2493.24 ms / 272 tokens 22.56.932.976 I slot print_timing: id 0 | task 54923 | graphs reused = 53902 22.56.932.977 I slot print_timing: id 0 | task 54923 | graph reallocs = 0 / 0 (same size) / (changed size) 22.56.932.996 I slot release: id 0 | task 54923 | stop processing: n_tokens = 271, truncated = 0 22.56.937.141 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.184 (> 0.100 thold), f_keep = 0.111 22.56.944.036 I slot launch_slot_: id 0 | task 55015 | processing task, is_child = 0 23.00.342.252 I slot print_timing: id 0 | task 55015 | n_gen = 130, tg = 42.90 t/s, tg_3s = 43.23 t/s 23.00.915.046 I slot print_timing: id 0 | task 55015 | prompt eval time = 391.21 ms / 163 tokens ( 2.40 ms per token, 416.65 tokens per second) 23.00.915.051 I slot print_timing: id 0 | task 55015 | eval time = 3579.79 ms / 155 tokens ( 23.25 ms per token, 43.02 tokens per second) 23.00.915.052 I slot print_timing: id 0 | task 55015 | total time = 3971.00 ms / 318 tokens 23.00.915.053 I slot print_timing: id 0 | task 55015 | graphs reused = 54054 23.00.915.053 I slot print_timing: id 0 | task 55015 | graph reallocs = 0 / 0 (same size) / (changed size) 23.00.915.072 I slot release: id 0 | task 55015 | stop processing: n_tokens = 317, truncated = 0 23.00.919.344 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.169 (> 0.100 thold), f_keep = 0.095 23.00.919.388 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 102.356 MiB) 23.00.921.710 I slot launch_slot_: id 0 | task 55173 | processing task, is_child = 0 23.04.305.335 I slot print_timing: id 0 | task 55173 | n_gen = 132, tg = 43.66 t/s, tg_3s = 43.99 t/s 23.04.972.647 I slot print_timing: id 0 | task 55173 | prompt eval time = 383.01 ms / 177 tokens ( 2.16 ms per token, 462.13 tokens per second) 23.04.972.652 I slot print_timing: id 0 | task 55173 | eval time = 3667.92 ms / 161 tokens ( 22.92 ms per token, 43.62 tokens per second) 23.04.972.653 I slot print_timing: id 0 | task 55173 | total time = 4050.93 ms / 338 tokens 23.04.972.654 I slot print_timing: id 0 | task 55173 | graphs reused = 54212 23.04.972.654 I slot print_timing: id 0 | task 55173 | graph reallocs = 0 / 0 (same size) / (changed size) 23.04.972.678 I slot release: id 0 | task 55173 | stop processing: n_tokens = 337, truncated = 0 23.04.976.842 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.196 (> 0.100 thold), f_keep = 0.089 23.04.976.891 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 145.153 MiB) 23.04.982.380 I slot launch_slot_: id 0 | task 55337 | processing task, is_child = 0 23.06.618.707 I slot print_timing: id 0 | task 55337 | prompt eval time = 376.83 ms / 153 tokens ( 2.46 ms per token, 406.02 tokens per second) 23.06.618.713 I slot print_timing: id 0 | task 55337 | eval time = 1259.49 ms / 56 tokens ( 22.90 ms per token, 43.67 tokens per second) 23.06.618.713 I slot print_timing: id 0 | task 55337 | total time = 1636.32 ms / 209 tokens 23.06.618.714 I slot print_timing: id 0 | task 55337 | graphs reused = 54266 23.06.618.714 I slot print_timing: id 0 | task 55337 | graph reallocs = 0 / 0 (same size) / (changed size) 23.06.618.732 I slot release: id 0 | task 55337 | stop processing: n_tokens = 208, truncated = 0 23.06.622.709 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.217 (> 0.100 thold), f_keep = 0.144 23.06.625.617 I slot launch_slot_: id 0 | task 55396 | processing task, is_child = 0 23.08.096.547 I slot print_timing: id 0 | task 55396 | prompt eval time = 325.28 ms / 138 tokens ( 2.36 ms per token, 424.25 tokens per second) 23.08.096.551 I slot print_timing: id 0 | task 55396 | eval time = 1145.64 ms / 51 tokens ( 22.91 ms per token, 43.64 tokens per second) 23.08.096.552 I slot print_timing: id 0 | task 55396 | total time = 1470.92 ms / 189 tokens 23.08.096.552 I slot print_timing: id 0 | task 55396 | graphs reused = 54315 23.08.096.553 I slot print_timing: id 0 | task 55396 | graph reallocs = 0 / 0 (same size) / (changed size) 23.08.096.573 I slot release: id 0 | task 55396 | stop processing: n_tokens = 188, truncated = 0 23.08.100.675 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.168 (> 0.100 thold), f_keep = 0.160 23.08.105.631 I slot launch_slot_: id 0 | task 55450 | processing task, is_child = 0 23.11.149.394 I slot print_timing: id 0 | task 55450 | prompt eval time = 379.89 ms / 179 tokens ( 2.12 ms per token, 471.19 tokens per second) 23.11.149.401 I slot print_timing: id 0 | task 55450 | eval time = 2663.86 ms / 117 tokens ( 22.96 ms per token, 43.55 tokens per second) 23.11.149.403 I slot print_timing: id 0 | task 55450 | total time = 3043.74 ms / 296 tokens 23.11.149.403 I slot print_timing: id 0 | task 55450 | graphs reused = 54429 23.11.149.404 I slot print_timing: id 0 | task 55450 | graph reallocs = 0 / 0 (same size) / (changed size) 23.11.149.426 I slot release: id 0 | task 55450 | stop processing: n_tokens = 295, truncated = 0 23.11.153.855 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.169 (> 0.100 thold), f_keep = 0.115 23.11.153.908 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.224 MiB) 23.11.161.422 I slot launch_slot_: id 0 | task 55570 | processing task, is_child = 0 23.12.827.262 I slot print_timing: id 0 | task 55570 | prompt eval time = 442.00 ms / 201 tokens ( 2.20 ms per token, 454.75 tokens per second) 23.12.827.268 I slot print_timing: id 0 | task 55570 | eval time = 1223.83 ms / 54 tokens ( 23.09 ms per token, 43.31 tokens per second) 23.12.827.269 I slot print_timing: id 0 | task 55570 | total time = 1665.83 ms / 255 tokens 23.12.827.270 I slot print_timing: id 0 | task 55570 | graphs reused = 54481 23.12.827.271 I slot print_timing: id 0 | task 55570 | graph reallocs = 0 / 0 (same size) / (changed size) 23.12.827.291 I slot release: id 0 | task 55570 | stop processing: n_tokens = 254, truncated = 0 23.12.831.197 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.224 (> 0.100 thold), f_keep = 0.118 23.12.831.236 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 146.524 MiB) 23.12.838.238 I slot launch_slot_: id 0 | task 55627 | processing task, is_child = 0 23.16.178.510 I slot print_timing: id 0 | task 55627 | n_gen = 126, tg = 41.51 t/s, tg_3s = 41.84 t/s 23.19.200.630 I slot print_timing: id 0 | task 55627 | n_gen = 257, tg = 42.43 t/s, tg_3s = 43.35 t/s 23.22.209.343 I slot print_timing: id 0 | task 55627 | n_gen = 386, tg = 42.58 t/s, tg_3s = 42.88 t/s 23.25.209.735 I slot print_timing: id 0 | task 55627 | n_gen = 514, tg = 42.60 t/s, tg_3s = 42.66 t/s 23.28.209.794 I slot print_timing: id 0 | task 55627 | n_gen = 641, tg = 42.55 t/s, tg_3s = 42.33 t/s 23.31.224.608 I slot print_timing: id 0 | task 55627 | n_gen = 770, tg = 42.59 t/s, tg_3s = 42.79 t/s 23.34.234.296 I slot print_timing: id 0 | task 55627 | n_gen = 898, tg = 42.58 t/s, tg_3s = 42.53 t/s 23.37.187.520 I slot print_timing: id 0 | task 55627 | prompt eval time = 328.68 ms / 134 tokens ( 2.45 ms per token, 407.69 tokens per second) 23.37.187.526 I slot print_timing: id 0 | task 55627 | eval time = 24020.59 ms / 1024 tokens ( 23.48 ms per token, 42.59 tokens per second) 23.37.187.527 I slot print_timing: id 0 | task 55627 | total time = 24349.27 ms / 1158 tokens 23.37.187.528 I slot print_timing: id 0 | task 55627 | graphs reused = 55499 23.37.187.528 I slot print_timing: id 0 | task 55627 | graph reallocs = 0 / 0 (same size) / (changed size) 23.37.187.550 I slot release: id 0 | task 55627 | stop processing: n_tokens = 1157, truncated = 0 23.37.191.481 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.205 (> 0.100 thold), f_keep = 0.026 23.37.191.577 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 91.808 MiB) 23.37.195.401 I slot launch_slot_: id 0 | task 56654 | processing task, is_child = 0 23.37.959.703 I slot print_timing: id 0 | task 56654 | prompt eval time = 374.44 ms / 146 tokens ( 2.56 ms per token, 389.91 tokens per second) 23.37.959.709 I slot print_timing: id 0 | task 56654 | eval time = 389.85 ms / 18 tokens ( 22.93 ms per token, 43.61 tokens per second) 23.37.959.710 I slot print_timing: id 0 | task 56654 | total time = 764.29 ms / 164 tokens 23.37.959.711 I slot print_timing: id 0 | task 56654 | graphs reused = 55515 23.37.959.711 I slot print_timing: id 0 | task 56654 | graph reallocs = 0 / 0 (same size) / (changed size) 23.37.959.729 I slot release: id 0 | task 56654 | stop processing: n_tokens = 163, truncated = 0 23.37.963.528 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.217 (> 0.100 thold), f_keep = 0.184 23.37.966.913 I slot launch_slot_: id 0 | task 56675 | processing task, is_child = 0 23.39.701.052 I slot print_timing: id 0 | task 56675 | prompt eval time = 325.87 ms / 138 tokens ( 2.36 ms per token, 423.49 tokens per second) 23.39.701.059 I slot print_timing: id 0 | task 56675 | eval time = 1408.26 ms / 62 tokens ( 23.09 ms per token, 43.32 tokens per second) 23.39.701.060 I slot print_timing: id 0 | task 56675 | total time = 1734.13 ms / 200 tokens 23.39.701.060 I slot print_timing: id 0 | task 56675 | graphs reused = 55575 23.39.701.061 I slot print_timing: id 0 | task 56675 | graph reallocs = 0 / 0 (same size) / (changed size) 23.39.701.081 I slot release: id 0 | task 56675 | stop processing: n_tokens = 199, truncated = 0 23.39.705.262 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.151 23.39.705.296 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 67.722 MiB) 23.39.707.126 I slot launch_slot_: id 0 | task 56740 | processing task, is_child = 0 23.43.088.288 I slot print_timing: id 0 | task 56740 | n_gen = 132, tg = 43.60 t/s, tg_3s = 43.94 t/s 23.46.094.510 I slot print_timing: id 0 | task 56740 | n_gen = 262, tg = 43.42 t/s, tg_3s = 43.24 t/s 23.49.103.563 I slot print_timing: id 0 | task 56740 | n_gen = 391, tg = 43.24 t/s, tg_3s = 42.87 t/s 23.52.105.591 I slot print_timing: id 0 | task 56740 | n_gen = 519, tg = 43.09 t/s, tg_3s = 42.64 t/s 23.55.118.616 I slot print_timing: id 0 | task 56740 | n_gen = 648, tg = 43.03 t/s, tg_3s = 42.81 t/s 23.55.702.653 I slot print_timing: id 0 | task 56740 | prompt eval time = 376.75 ms / 155 tokens ( 2.43 ms per token, 411.41 tokens per second) 23.55.702.657 I slot print_timing: id 0 | task 56740 | eval time = 15618.77 ms / 673 tokens ( 23.24 ms per token, 43.03 tokens per second) 23.55.702.657 I slot print_timing: id 0 | task 56740 | total time = 15995.52 ms / 828 tokens 23.55.702.658 I slot print_timing: id 0 | task 56740 | graphs reused = 56243 23.55.702.658 I slot print_timing: id 0 | task 56740 | graph reallocs = 0 / 0 (same size) / (changed size) 23.55.702.679 I slot release: id 0 | task 56740 | stop processing: n_tokens = 827, truncated = 0 23.55.707.143 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.036 23.55.707.229 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 119.726 MiB) 23.55.711.134 I slot launch_slot_: id 0 | task 57416 | processing task, is_child = 0 23.57.340.022 I slot print_timing: id 0 | task 57416 | prompt eval time = 376.54 ms / 160 tokens ( 2.35 ms per token, 424.93 tokens per second) 23.57.340.025 I slot print_timing: id 0 | task 57416 | eval time = 1252.34 ms / 52 tokens ( 24.56 ms per token, 40.72 tokens per second) 23.57.340.025 I slot print_timing: id 0 | task 57416 | total time = 1628.88 ms / 212 tokens 23.57.340.026 I slot print_timing: id 0 | task 57416 | graphs reused = 56293 23.57.340.027 I slot print_timing: id 0 | task 57416 | graph reallocs = 0 / 0 (same size) / (changed size) 23.57.340.048 I slot release: id 0 | task 57416 | stop processing: n_tokens = 211, truncated = 0 23.57.343.948 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.192 (> 0.100 thold), f_keep = 0.142 23.57.343.987 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 114.594 MiB) 23.57.345.850 I slot launch_slot_: id 0 | task 57471 | processing task, is_child = 0 24.00.104.527 I slot print_timing: id 0 | task 57471 | prompt eval time = 377.29 ms / 156 tokens ( 2.42 ms per token, 413.47 tokens per second) 24.00.104.531 I slot print_timing: id 0 | task 57471 | eval time = 2381.37 ms / 103 tokens ( 23.35 ms per token, 42.83 tokens per second) 24.00.104.531 I slot print_timing: id 0 | task 57471 | total time = 2758.66 ms / 259 tokens 24.00.104.532 I slot print_timing: id 0 | task 57471 | graphs reused = 56393 24.00.104.532 I slot print_timing: id 0 | task 57471 | graph reallocs = 0 / 0 (same size) / (changed size) 24.00.104.552 I slot release: id 0 | task 57471 | stop processing: n_tokens = 258, truncated = 0 24.00.108.589 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.190 (> 0.100 thold), f_keep = 0.116 24.00.113.420 I slot launch_slot_: id 0 | task 57577 | processing task, is_child = 0 24.03.501.993 I slot print_timing: id 0 | task 57577 | n_gen = 131, tg = 43.16 t/s, tg_3s = 43.49 t/s 24.06.514.810 I slot print_timing: id 0 | task 57577 | n_gen = 256, tg = 42.32 t/s, tg_3s = 41.49 t/s 24.09.520.917 I slot print_timing: id 0 | task 57577 | n_gen = 382, tg = 42.19 t/s, tg_3s = 41.91 t/s 24.12.542.721 I slot print_timing: id 0 | task 57577 | n_gen = 511, tg = 42.31 t/s, tg_3s = 42.69 t/s 24.15.547.304 I slot print_timing: id 0 | task 57577 | n_gen = 639, tg = 42.37 t/s, tg_3s = 42.60 t/s 24.18.557.477 I slot print_timing: id 0 | task 57577 | n_gen = 768, tg = 42.45 t/s, tg_3s = 42.85 t/s 24.19.095.417 I slot print_timing: id 0 | task 57577 | prompt eval time = 376.24 ms / 158 tokens ( 2.38 ms per token, 419.94 tokens per second) 24.19.095.420 I slot print_timing: id 0 | task 57577 | eval time = 18605.74 ms / 791 tokens ( 23.55 ms per token, 42.46 tokens per second) 24.19.095.421 I slot print_timing: id 0 | task 57577 | total time = 18981.99 ms / 949 tokens 24.19.095.422 I slot print_timing: id 0 | task 57577 | graphs reused = 57179 24.19.095.422 I slot print_timing: id 0 | task 57577 | graph reallocs = 0 / 0 (same size) / (changed size) 24.19.095.444 I slot release: id 0 | task 57577 | stop processing: n_tokens = 948, truncated = 0 24.19.099.750 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.032 24.19.099.838 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 147.649 MiB) 24.19.103.493 I slot launch_slot_: id 0 | task 58371 | processing task, is_child = 0 24.20.563.576 I slot print_timing: id 0 | task 58371 | prompt eval time = 363.51 ms / 155 tokens ( 2.35 ms per token, 426.40 tokens per second) 24.20.563.580 I slot print_timing: id 0 | task 58371 | eval time = 1096.57 ms / 49 tokens ( 22.85 ms per token, 43.77 tokens per second) 24.20.563.582 I slot print_timing: id 0 | task 58371 | total time = 1460.08 ms / 204 tokens 24.20.563.582 I slot print_timing: id 0 | task 58371 | graphs reused = 57226 24.20.563.583 I slot print_timing: id 0 | task 58371 | graph reallocs = 0 / 0 (same size) / (changed size) 24.20.563.604 I slot release: id 0 | task 58371 | stop processing: n_tokens = 203, truncated = 0 24.20.567.613 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.176 (> 0.100 thold), f_keep = 0.148 24.20.567.652 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 111.886 MiB) 24.20.569.583 I slot launch_slot_: id 0 | task 58423 | processing task, is_child = 0 24.23.667.787 I slot print_timing: id 0 | task 58423 | prompt eval time = 390.54 ms / 170 tokens ( 2.30 ms per token, 435.29 tokens per second) 24.23.667.790 I slot print_timing: id 0 | task 58423 | eval time = 2707.65 ms / 119 tokens ( 22.95 ms per token, 43.58 tokens per second) 24.23.667.790 I slot print_timing: id 0 | task 58423 | total time = 3098.19 ms / 289 tokens 24.23.667.791 I slot print_timing: id 0 | task 58423 | graphs reused = 57342 24.23.667.792 I slot print_timing: id 0 | task 58423 | graph reallocs = 0 / 0 (same size) / (changed size) 24.23.667.811 I slot release: id 0 | task 58423 | stop processing: n_tokens = 288, truncated = 0 24.23.672.037 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.108 24.23.677.028 I slot launch_slot_: id 0 | task 58545 | processing task, is_child = 0 24.24.689.234 I slot print_timing: id 0 | task 58545 | prompt eval time = 380.31 ms / 160 tokens ( 2.38 ms per token, 420.70 tokens per second) 24.24.689.237 I slot print_timing: id 0 | task 58545 | eval time = 631.88 ms / 28 tokens ( 23.40 ms per token, 42.73 tokens per second) 24.24.689.239 I slot print_timing: id 0 | task 58545 | total time = 1012.19 ms / 188 tokens 24.24.689.240 I slot print_timing: id 0 | task 58545 | graphs reused = 57368 24.24.689.240 I slot print_timing: id 0 | task 58545 | graph reallocs = 0 / 0 (same size) / (changed size) 24.24.689.262 I slot release: id 0 | task 58545 | stop processing: n_tokens = 187, truncated = 0 24.24.693.475 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 24.24.693.515 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.325 MiB) 24.24.695.831 I slot launch_slot_: id 0 | task 58576 | processing task, is_child = 0 24.27.066.774 I slot print_timing: id 0 | task 58576 | prompt eval time = 379.59 ms / 161 tokens ( 2.36 ms per token, 424.14 tokens per second) 24.27.066.778 I slot print_timing: id 0 | task 58576 | eval time = 1991.34 ms / 86 tokens ( 23.43 ms per token, 42.68 tokens per second) 24.27.066.779 I slot print_timing: id 0 | task 58576 | total time = 2370.93 ms / 247 tokens 24.27.066.779 I slot print_timing: id 0 | task 58576 | graphs reused = 57452 24.27.066.780 I slot print_timing: id 0 | task 58576 | graph reallocs = 0 / 0 (same size) / (changed size) 24.27.066.812 I slot release: id 0 | task 58576 | stop processing: n_tokens = 246, truncated = 0 24.27.071.258 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.122 24.27.075.832 I slot launch_slot_: id 0 | task 58665 | processing task, is_child = 0 24.29.388.861 I slot print_timing: id 0 | task 58665 | prompt eval time = 365.08 ms / 169 tokens ( 2.16 ms per token, 462.91 tokens per second) 24.29.388.864 I slot print_timing: id 0 | task 58665 | eval time = 1947.94 ms / 86 tokens ( 22.92 ms per token, 43.64 tokens per second) 24.29.388.865 I slot print_timing: id 0 | task 58665 | total time = 2313.02 ms / 255 tokens 24.29.388.865 I slot print_timing: id 0 | task 58665 | graphs reused = 57536 24.29.388.866 I slot print_timing: id 0 | task 58665 | graph reallocs = 0 / 0 (same size) / (changed size) 24.29.388.884 I slot release: id 0 | task 58665 | stop processing: n_tokens = 254, truncated = 0 24.29.392.938 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.164 (> 0.100 thold), f_keep = 0.118 24.29.392.987 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 88.538 MiB) 24.29.395.646 I slot launch_slot_: id 0 | task 58754 | processing task, is_child = 0 24.30.271.426 I slot print_timing: id 0 | task 58754 | prompt eval time = 471.03 ms / 183 tokens ( 2.57 ms per token, 388.51 tokens per second) 24.30.271.429 I slot print_timing: id 0 | task 58754 | eval time = 404.74 ms / 18 tokens ( 23.81 ms per token, 42.00 tokens per second) 24.30.271.430 I slot print_timing: id 0 | task 58754 | total time = 875.77 ms / 201 tokens 24.30.271.431 I slot print_timing: id 0 | task 58754 | graphs reused = 57552 24.30.271.431 I slot print_timing: id 0 | task 58754 | graph reallocs = 0 / 0 (same size) / (changed size) 24.30.271.458 I slot release: id 0 | task 58754 | stop processing: n_tokens = 200, truncated = 0 24.30.275.363 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.174 (> 0.100 thold), f_keep = 0.150 24.30.275.400 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 148.915 MiB) 24.30.277.595 I slot launch_slot_: id 0 | task 58775 | processing task, is_child = 0 24.31.915.378 I slot print_timing: id 0 | task 58775 | prompt eval time = 377.94 ms / 172 tokens ( 2.20 ms per token, 455.10 tokens per second) 24.31.915.388 I slot print_timing: id 0 | task 58775 | eval time = 1259.84 ms / 56 tokens ( 22.91 ms per token, 43.66 tokens per second) 24.31.915.390 I slot print_timing: id 0 | task 58775 | total time = 1637.78 ms / 228 tokens 24.31.915.390 I slot print_timing: id 0 | task 58775 | graphs reused = 57606 24.31.915.393 I slot print_timing: id 0 | task 58775 | graph reallocs = 0 / 0 (same size) / (changed size) 24.31.915.415 I slot release: id 0 | task 58775 | stop processing: n_tokens = 227, truncated = 0 24.31.919.691 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.165 (> 0.100 thold), f_keep = 0.132 24.31.927.284 I slot launch_slot_: id 0 | task 58834 | processing task, is_child = 0 24.35.402.406 I slot print_timing: id 0 | task 58834 | n_gen = 126, tg = 41.28 t/s, tg_3s = 41.61 t/s 24.38.428.528 I slot print_timing: id 0 | task 58834 | n_gen = 252, tg = 41.46 t/s, tg_3s = 41.64 t/s 24.41.451.518 I slot print_timing: id 0 | task 58834 | n_gen = 378, tg = 41.53 t/s, tg_3s = 41.68 t/s 24.44.484.234 I slot print_timing: id 0 | task 58834 | n_gen = 505, tg = 41.62 t/s, tg_3s = 41.88 t/s 24.47.498.610 I slot print_timing: id 0 | task 58834 | n_gen = 634, tg = 41.85 t/s, tg_3s = 42.79 t/s 24.50.514.727 I slot print_timing: id 0 | task 58834 | n_gen = 762, tg = 41.95 t/s, tg_3s = 42.44 t/s 24.53.537.949 I slot print_timing: id 0 | task 58834 | n_gen = 890, tg = 42.01 t/s, tg_3s = 42.34 t/s 24.56.538.040 I slot print_timing: id 0 | task 58834 | n_gen = 1018, tg = 42.09 t/s, tg_3s = 42.67 t/s 24.56.691.266 I slot print_timing: id 0 | task 58834 | prompt eval time = 446.84 ms / 182 tokens ( 2.46 ms per token, 407.31 tokens per second) 24.56.691.273 I slot print_timing: id 0 | task 58834 | eval time = 24317.14 ms / 1024 tokens ( 23.77 ms per token, 42.07 tokens per second) 24.56.691.273 I slot print_timing: id 0 | task 58834 | total time = 24763.98 ms / 1206 tokens 24.56.691.274 I slot print_timing: id 0 | task 58834 | graphs reused = 58624 24.56.691.274 I slot print_timing: id 0 | task 58834 | graph reallocs = 0 / 0 (same size) / (changed size) 24.56.691.293 I slot release: id 0 | task 58834 | stop processing: n_tokens = 1205, truncated = 0 24.56.695.673 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.027 24.56.695.770 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 139.035 MiB) 24.56.701.258 I slot launch_slot_: id 0 | task 59861 | processing task, is_child = 0 25.00.140.193 I slot print_timing: id 0 | task 59861 | n_gen = 131, tg = 43.31 t/s, tg_3s = 43.64 t/s 25.01.851.532 I slot print_timing: id 0 | task 59861 | prompt eval time = 437.41 ms / 181 tokens ( 2.42 ms per token, 413.80 tokens per second) 25.01.851.535 I slot print_timing: id 0 | task 59861 | eval time = 4712.86 ms / 205 tokens ( 23.10 ms per token, 43.29 tokens per second) 25.01.851.535 I slot print_timing: id 0 | task 59861 | total time = 5150.26 ms / 386 tokens 25.01.851.536 I slot print_timing: id 0 | task 59861 | graphs reused = 58826 25.01.851.536 I slot print_timing: id 0 | task 59861 | graph reallocs = 0 / 0 (same size) / (changed size) 25.01.851.559 I slot release: id 0 | task 59861 | stop processing: n_tokens = 385, truncated = 0 25.01.855.795 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.133 (> 0.100 thold), f_keep = 0.078 25.01.855.850 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 66.878 MiB) 25.01.858.629 I slot launch_slot_: id 0 | task 60069 | processing task, is_child = 0 25.04.025.851 I slot print_timing: id 0 | task 60069 | prompt eval time = 493.31 ms / 226 tokens ( 2.18 ms per token, 458.13 tokens per second) 25.04.025.857 I slot print_timing: id 0 | task 60069 | eval time = 1673.90 ms / 74 tokens ( 22.93 ms per token, 43.61 tokens per second) 25.04.025.857 I slot print_timing: id 0 | task 60069 | total time = 2167.21 ms / 300 tokens 25.04.025.858 I slot print_timing: id 0 | task 60069 | graphs reused = 58897 25.04.025.859 I slot print_timing: id 0 | task 60069 | graph reallocs = 0 / 0 (same size) / (changed size) 25.04.025.890 I slot release: id 0 | task 60069 | stop processing: n_tokens = 299, truncated = 0 25.04.029.871 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.189 (> 0.100 thold), f_keep = 0.100 25.04.029.916 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 121.626 MiB) 25.04.034.466 I slot launch_slot_: id 0 | task 60146 | processing task, is_child = 0 25.05.100.706 I slot print_timing: id 0 | task 60146 | prompt eval time = 388.45 ms / 159 tokens ( 2.44 ms per token, 409.31 tokens per second) 25.05.100.709 I slot print_timing: id 0 | task 60146 | eval time = 677.77 ms / 30 tokens ( 23.37 ms per token, 42.79 tokens per second) 25.05.100.709 I slot print_timing: id 0 | task 60146 | total time = 1066.23 ms / 189 tokens 25.05.100.710 I slot print_timing: id 0 | task 60146 | graphs reused = 58925 25.05.100.710 I slot print_timing: id 0 | task 60146 | graph reallocs = 0 / 0 (same size) / (changed size) 25.05.100.727 I slot release: id 0 | task 60146 | stop processing: n_tokens = 188, truncated = 0 25.05.535.890 I srv operator(): operator(): cleaning up before exit...