$ /Users/minipro/quantdiff/work/llama-b11869/src/build/bin/llama-server -m /Users/minipro/quantdiff/models/campaign/7f43dd99e7d5/flint-UD-Q2_K_XL.gguf --host 127.0.0.1 --port 8089 -c 4096 -np 1 -ngl 999 -fa on --jinja --seed 1234 --no-webui -a quant 0.00.042.516 I srv llama_server: initializing ... 0.00.042.523 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.042.607 I srv init_listene: The UI is disabled 0.00.042.608 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.042.651 W srv server_setup: security: no API key is set and CORS allows all origins (see https://github.com/ggml-org/llama.cpp/pull/25655) 0.00.044.306 I srv load_model: loading model '/Users/minipro/quantdiff/models/campaign/7f43dd99e7d5/flint-UD-Q2_K_XL.gguf' 0.00.828.746 I cmn init: llama threadpool init, n_threads = 8 0.01.107.398 I srv load_model: initializing, n_slots = 1, n_ctx_slot = 4096, kv_unified = 'false' 0.01.115.201 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.01.115.210 I srv server_run_i: model loaded 0.01.115.212 I srv server_on_li: listening on http://127.0.0.1:8089 0.02.027.270 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.02.027.503 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.04.453.420 I slot print_timing: id 0 | task 0 | prompt eval time = 1100.50 ms / 221 tokens ( 4.98 ms per token, 200.82 tokens per second) 0.04.453.426 I slot print_timing: id 0 | task 0 | eval time = 1325.40 ms / 71 tokens ( 18.93 ms per token, 52.81 tokens per second) 0.04.453.427 I slot print_timing: id 0 | task 0 | total time = 2425.90 ms / 292 tokens 0.04.453.427 I slot print_timing: id 0 | task 0 | graphs reused = 69 0.04.453.428 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.04.453.448 I slot release: id 0 | task 0 | stop processing: n_tokens = 291, truncated = 0 0.04.457.780 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.211 (> 0.100 thold), f_keep = 0.127 0.04.463.001 I slot launch_slot_: id 0 | task 74 | processing task, is_child = 0 0.06.163.384 I slot print_timing: id 0 | task 74 | prompt eval time = 549.34 ms / 175 tokens ( 3.14 ms per token, 318.57 tokens per second) 0.06.163.389 I slot print_timing: id 0 | task 74 | eval time = 1151.04 ms / 62 tokens ( 18.87 ms per token, 53.00 tokens per second) 0.06.163.390 I slot print_timing: id 0 | task 74 | total time = 1700.37 ms / 237 tokens 0.06.163.391 I slot print_timing: id 0 | task 74 | graphs reused = 129 0.06.163.391 I slot print_timing: id 0 | task 74 | graph reallocs = 0 / 0 (same size) / (changed size) 0.06.163.410 I slot release: id 0 | task 74 | stop processing: n_tokens = 236, truncated = 0 0.06.168.049 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.174 (> 0.100 thold), f_keep = 0.157 0.06.172.381 I slot launch_slot_: id 0 | task 139 | processing task, is_child = 0 0.08.304.640 I slot print_timing: id 0 | task 139 | prompt eval time = 631.77 ms / 213 tokens ( 2.97 ms per token, 337.15 tokens per second) 0.08.304.650 I slot print_timing: id 0 | task 139 | eval time = 1500.48 ms / 80 tokens ( 18.99 ms per token, 52.65 tokens per second) 0.08.304.651 I slot print_timing: id 0 | task 139 | total time = 2132.25 ms / 293 tokens 0.08.304.652 I slot print_timing: id 0 | task 139 | graphs reused = 206 0.08.304.652 I slot print_timing: id 0 | task 139 | graph reallocs = 0 / 0 (same size) / (changed size) 0.08.304.676 I slot release: id 0 | task 139 | stop processing: n_tokens = 292, truncated = 0 0.08.309.336 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.150 (> 0.100 thold), f_keep = 0.127 0.08.314.504 I slot launch_slot_: id 0 | task 222 | processing task, is_child = 0 0.10.711.160 I slot print_timing: id 0 | task 222 | prompt eval time = 686.47 ms / 247 tokens ( 2.78 ms per token, 359.81 tokens per second) 0.10.711.165 I slot print_timing: id 0 | task 222 | eval time = 1710.18 ms / 91 tokens ( 19.00 ms per token, 52.63 tokens per second) 0.10.711.166 I slot print_timing: id 0 | task 222 | total time = 2396.65 ms / 338 tokens 0.10.711.167 I slot print_timing: id 0 | task 222 | graphs reused = 294 0.10.711.167 I slot print_timing: id 0 | task 222 | graph reallocs = 0 / 0 (same size) / (changed size) 0.10.711.191 I slot release: id 0 | task 222 | stop processing: n_tokens = 337, truncated = 0 0.10.715.841 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.212 (> 0.100 thold), f_keep = 0.148 0.10.721.614 I slot launch_slot_: id 0 | task 316 | processing task, is_child = 0 0.13.286.390 I slot print_timing: id 0 | task 316 | prompt eval time = 760.75 ms / 236 tokens ( 3.22 ms per token, 310.22 tokens per second) 0.13.286.397 I slot print_timing: id 0 | task 316 | eval time = 1804.02 ms / 96 tokens ( 18.99 ms per token, 52.66 tokens per second) 0.13.286.397 I slot print_timing: id 0 | task 316 | total time = 2564.76 ms / 332 tokens 0.13.286.398 I slot print_timing: id 0 | task 316 | graphs reused = 387 0.13.286.398 I slot print_timing: id 0 | task 316 | graph reallocs = 0 / 0 (same size) / (changed size) 0.13.286.420 I slot release: id 0 | task 316 | stop processing: n_tokens = 331, truncated = 0 0.13.291.107 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.164 (> 0.100 thold), f_keep = 0.112 0.13.296.026 I slot launch_slot_: id 0 | task 415 | processing task, is_child = 0 0.15.527.151 I slot print_timing: id 0 | task 415 | prompt eval time = 615.99 ms / 226 tokens ( 2.73 ms per token, 366.89 tokens per second) 0.15.527.158 I slot print_timing: id 0 | task 415 | eval time = 1615.13 ms / 86 tokens ( 19.00 ms per token, 52.63 tokens per second) 0.15.527.158 I slot print_timing: id 0 | task 415 | total time = 2231.12 ms / 312 tokens 0.15.527.159 I slot print_timing: id 0 | task 415 | graphs reused = 470 0.15.527.159 I slot print_timing: id 0 | task 415 | graph reallocs = 0 / 0 (same size) / (changed size) 0.15.527.180 I slot release: id 0 | task 415 | stop processing: n_tokens = 311, truncated = 0 0.15.532.196 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.137 (> 0.100 thold), f_keep = 0.119 0.15.537.950 I slot launch_slot_: id 0 | task 504 | processing task, is_child = 0 0.18.576.685 I slot print_timing: id 0 | task 504 | prompt eval time = 721.41 ms / 270 tokens ( 2.67 ms per token, 374.27 tokens per second) 0.18.576.688 I slot print_timing: id 0 | task 504 | eval time = 2317.31 ms / 123 tokens ( 18.99 ms per token, 52.65 tokens per second) 0.18.576.689 I slot print_timing: id 0 | task 504 | total time = 3038.72 ms / 393 tokens 0.18.576.690 I slot print_timing: id 0 | task 504 | graphs reused = 591 0.18.576.690 I slot print_timing: id 0 | task 504 | graph reallocs = 0 / 0 (same size) / (changed size) 0.18.576.712 I slot release: id 0 | task 504 | stop processing: n_tokens = 392, truncated = 0 0.18.581.765 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.116 (> 0.100 thold), f_keep = 0.094 0.18.588.298 I slot launch_slot_: id 0 | task 630 | processing task, is_child = 0 0.22.302.702 I slot print_timing: id 0 | task 630 | prompt eval time = 785.01 ms / 318 tokens ( 2.47 ms per token, 405.09 tokens per second) 0.22.302.709 I slot print_timing: id 0 | task 630 | eval time = 2929.39 ms / 155 tokens ( 19.02 ms per token, 52.57 tokens per second) 0.22.302.710 I slot print_timing: id 0 | task 630 | total time = 3714.40 ms / 473 tokens 0.22.302.710 I slot print_timing: id 0 | task 630 | graphs reused = 744 0.22.302.711 I slot print_timing: id 0 | task 630 | graph reallocs = 0 / 0 (same size) / (changed size) 0.22.302.735 I slot release: id 0 | task 630 | stop processing: n_tokens = 472, truncated = 0 0.22.307.420 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.078 0.22.315.483 I slot launch_slot_: id 0 | task 788 | processing task, is_child = 0 0.25.363.509 I slot print_timing: id 0 | task 788 | prompt eval time = 622.93 ms / 197 tokens ( 3.16 ms per token, 316.25 tokens per second) 0.25.363.512 I slot print_timing: id 0 | task 788 | eval time = 2425.08 ms / 129 tokens ( 18.95 ms per token, 52.78 tokens per second) 0.25.363.513 I slot print_timing: id 0 | task 788 | total time = 3048.01 ms / 326 tokens 0.25.363.513 I slot print_timing: id 0 | task 788 | graphs reused = 870 0.25.363.514 I slot print_timing: id 0 | task 788 | graph reallocs = 0 / 0 (same size) / (changed size) 0.25.363.534 I slot release: id 0 | task 788 | stop processing: n_tokens = 325, truncated = 0 0.25.368.852 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.114 0.25.372.658 I slot launch_slot_: id 0 | task 920 | processing task, is_child = 0 0.28.636.136 I slot print_timing: id 0 | task 920 | prompt eval time = 642.12 ms / 216 tokens ( 2.97 ms per token, 336.38 tokens per second) 0.28.636.143 I slot print_timing: id 0 | task 920 | eval time = 2621.35 ms / 139 tokens ( 19.00 ms per token, 52.64 tokens per second) 0.28.636.143 I slot print_timing: id 0 | task 920 | total time = 3263.47 ms / 355 tokens 0.28.636.144 I slot print_timing: id 0 | task 920 | graphs reused = 1006 0.28.636.145 I slot print_timing: id 0 | task 920 | graph reallocs = 0 / 0 (same size) / (changed size) 0.28.636.164 I slot release: id 0 | task 920 | stop processing: n_tokens = 354, truncated = 0 0.28.640.974 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.165 (> 0.100 thold), f_keep = 0.105 0.28.645.092 I slot launch_slot_: id 0 | task 1062 | processing task, is_child = 0 0.31.362.949 I slot print_timing: id 0 | task 1062 | prompt eval time = 607.17 ms / 224 tokens ( 2.71 ms per token, 368.92 tokens per second) 0.31.362.955 I slot print_timing: id 0 | task 1062 | eval time = 2110.68 ms / 112 tokens ( 19.02 ms per token, 52.59 tokens per second) 0.31.362.955 I slot print_timing: id 0 | task 1062 | total time = 2717.85 ms / 336 tokens 0.31.362.956 I slot print_timing: id 0 | task 1062 | graphs reused = 1115 0.31.362.956 I slot print_timing: id 0 | task 1062 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.362.977 I slot release: id 0 | task 1062 | stop processing: n_tokens = 335, truncated = 0 0.31.368.071 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.143 (> 0.100 thold), f_keep = 0.110 0.31.374.406 I slot launch_slot_: id 0 | task 1177 | processing task, is_child = 0 0.33.923.747 I slot print_timing: id 0 | task 1177 | prompt eval time = 708.52 ms / 259 tokens ( 2.74 ms per token, 365.55 tokens per second) 0.33.923.754 I slot print_timing: id 0 | task 1177 | eval time = 1840.82 ms / 98 tokens ( 18.98 ms per token, 52.69 tokens per second) 0.33.923.755 I slot print_timing: id 0 | task 1177 | total time = 2549.33 ms / 357 tokens 0.33.923.755 I slot print_timing: id 0 | task 1177 | graphs reused = 1211 0.33.923.756 I slot print_timing: id 0 | task 1177 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.923.781 I slot release: id 0 | task 1177 | stop processing: n_tokens = 356, truncated = 0 0.33.928.381 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.165 (> 0.100 thold), f_keep = 0.104 0.33.934.486 I slot launch_slot_: id 0 | task 1278 | processing task, is_child = 0 0.36.682.040 I slot print_timing: id 0 | task 1278 | prompt eval time = 677.02 ms / 224 tokens ( 3.02 ms per token, 330.86 tokens per second) 0.36.682.046 I slot print_timing: id 0 | task 1278 | eval time = 2070.52 ms / 110 tokens ( 19.00 ms per token, 52.64 tokens per second) 0.36.682.047 I slot print_timing: id 0 | task 1278 | total time = 2747.54 ms / 334 tokens 0.36.682.048 I slot print_timing: id 0 | task 1278 | graphs reused = 1318 0.36.682.048 I slot print_timing: id 0 | task 1278 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.682.069 I slot release: id 0 | task 1278 | stop processing: n_tokens = 333, truncated = 0 0.36.686.988 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.163 (> 0.100 thold), f_keep = 0.111 0.36.691.005 I slot launch_slot_: id 0 | task 1391 | processing task, is_child = 0 0.39.015.173 I slot print_timing: id 0 | task 1391 | prompt eval time = 629.65 ms / 227 tokens ( 2.77 ms per token, 360.52 tokens per second) 0.39.015.179 I slot print_timing: id 0 | task 1391 | eval time = 1694.50 ms / 90 tokens ( 19.04 ms per token, 52.52 tokens per second) 0.39.015.180 I slot print_timing: id 0 | task 1391 | total time = 2324.16 ms / 317 tokens 0.39.015.180 I slot print_timing: id 0 | task 1391 | graphs reused = 1405 0.39.015.181 I slot print_timing: id 0 | task 1391 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.015.201 I slot release: id 0 | task 1391 | stop processing: n_tokens = 316, truncated = 0 0.39.019.985 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.167 (> 0.100 thold), f_keep = 0.117 0.39.025.415 I slot launch_slot_: id 0 | task 1484 | processing task, is_child = 0 0.41.480.532 I slot print_timing: id 0 | task 1484 | prompt eval time = 631.05 ms / 222 tokens ( 2.84 ms per token, 351.80 tokens per second) 0.41.480.538 I slot print_timing: id 0 | task 1484 | eval time = 1824.06 ms / 97 tokens ( 19.00 ms per token, 52.63 tokens per second) 0.41.480.539 I slot print_timing: id 0 | task 1484 | total time = 2455.11 ms / 319 tokens 0.41.480.539 I slot print_timing: id 0 | task 1484 | graphs reused = 1499 0.41.480.540 I slot print_timing: id 0 | task 1484 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.480.560 I slot release: id 0 | task 1484 | stop processing: n_tokens = 318, truncated = 0 0.41.485.139 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.116 0.41.490.721 I slot launch_slot_: id 0 | task 1584 | processing task, is_child = 0 0.43.915.679 I slot print_timing: id 0 | task 1584 | prompt eval time = 623.72 ms / 203 tokens ( 3.07 ms per token, 325.47 tokens per second) 0.43.915.685 I slot print_timing: id 0 | task 1584 | eval time = 1801.23 ms / 96 tokens ( 18.96 ms per token, 52.74 tokens per second) 0.43.915.686 I slot print_timing: id 0 | task 1584 | total time = 2424.95 ms / 299 tokens 0.43.915.686 I slot print_timing: id 0 | task 1584 | graphs reused = 1592 0.43.915.687 I slot print_timing: id 0 | task 1584 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.915.706 I slot release: id 0 | task 1584 | stop processing: n_tokens = 298, truncated = 0 0.43.920.338 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.166 (> 0.100 thold), f_keep = 0.124 0.43.924.802 I slot launch_slot_: id 0 | task 1683 | processing task, is_child = 0 0.45.976.041 I slot print_timing: id 0 | task 1683 | prompt eval time = 663.42 ms / 223 tokens ( 2.97 ms per token, 336.14 tokens per second) 0.45.976.046 I slot print_timing: id 0 | task 1683 | eval time = 1387.81 ms / 74 tokens ( 19.01 ms per token, 52.60 tokens per second) 0.45.976.047 I slot print_timing: id 0 | task 1683 | total time = 2051.22 ms / 297 tokens 0.45.976.047 I slot print_timing: id 0 | task 1683 | graphs reused = 1663 0.45.976.048 I slot print_timing: id 0 | task 1683 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.976.069 I slot release: id 0 | task 1683 | stop processing: n_tokens = 296, truncated = 0 0.45.980.846 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.180 (> 0.100 thold), f_keep = 0.125 0.45.986.255 I slot launch_slot_: id 0 | task 1760 | processing task, is_child = 0 0.48.345.814 I slot print_timing: id 0 | task 1760 | prompt eval time = 595.83 ms / 206 tokens ( 2.89 ms per token, 345.74 tokens per second) 0.48.345.820 I slot print_timing: id 0 | task 1760 | eval time = 1763.71 ms / 94 tokens ( 18.96 ms per token, 52.73 tokens per second) 0.48.345.821 I slot print_timing: id 0 | task 1760 | total time = 2359.55 ms / 300 tokens 0.48.345.822 I slot print_timing: id 0 | task 1760 | graphs reused = 1754 0.48.345.823 I slot print_timing: id 0 | task 1760 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.345.841 I slot release: id 0 | task 1760 | stop processing: n_tokens = 299, truncated = 0 0.48.350.217 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.183 (> 0.100 thold), f_keep = 0.124 0.48.355.297 I slot launch_slot_: id 0 | task 1857 | processing task, is_child = 0 0.50.220.391 I slot print_timing: id 0 | task 1857 | prompt eval time = 590.71 ms / 202 tokens ( 2.92 ms per token, 341.96 tokens per second) 0.50.220.397 I slot print_timing: id 0 | task 1857 | eval time = 1274.38 ms / 68 tokens ( 19.02 ms per token, 52.57 tokens per second) 0.50.220.398 I slot print_timing: id 0 | task 1857 | total time = 1865.08 ms / 270 tokens 0.50.220.399 I slot print_timing: id 0 | task 1857 | graphs reused = 1819 0.50.220.399 I slot print_timing: id 0 | task 1857 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.220.418 I slot release: id 0 | task 1857 | stop processing: n_tokens = 269, truncated = 0 0.50.225.054 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.138 0.50.229.945 I slot launch_slot_: id 0 | task 1928 | processing task, is_child = 0 0.52.429.479 I slot print_timing: id 0 | task 1928 | prompt eval time = 695.90 ms / 237 tokens ( 2.94 ms per token, 340.57 tokens per second) 0.52.429.485 I slot print_timing: id 0 | task 1928 | eval time = 1503.63 ms / 80 tokens ( 19.03 ms per token, 52.54 tokens per second) 0.52.429.486 I slot print_timing: id 0 | task 1928 | total time = 2199.53 ms / 317 tokens 0.52.429.487 I slot print_timing: id 0 | task 1928 | graphs reused = 1896 0.52.429.487 I slot print_timing: id 0 | task 1928 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.429.508 I slot release: id 0 | task 1928 | stop processing: n_tokens = 316, truncated = 0 0.52.433.994 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.117 0.52.439.617 I slot launch_slot_: id 0 | task 2011 | processing task, is_child = 0 0.54.741.393 I slot print_timing: id 0 | task 2011 | prompt eval time = 631.61 ms / 208 tokens ( 3.04 ms per token, 329.32 tokens per second) 0.54.741.400 I slot print_timing: id 0 | task 2011 | eval time = 1670.14 ms / 88 tokens ( 19.20 ms per token, 52.09 tokens per second) 0.54.741.401 I slot print_timing: id 0 | task 2011 | total time = 2301.75 ms / 296 tokens 0.54.741.402 I slot print_timing: id 0 | task 2011 | graphs reused = 1981 0.54.741.403 I slot print_timing: id 0 | task 2011 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.741.427 I slot release: id 0 | task 2011 | stop processing: n_tokens = 295, truncated = 0 0.54.746.755 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.142 (> 0.100 thold), f_keep = 0.125 0.54.751.339 I slot launch_slot_: id 0 | task 2102 | processing task, is_child = 0 0.57.323.350 I slot print_timing: id 0 | task 2102 | prompt eval time = 710.14 ms / 261 tokens ( 2.72 ms per token, 367.53 tokens per second) 0.57.323.353 I slot print_timing: id 0 | task 2102 | eval time = 1861.86 ms / 99 tokens ( 19.00 ms per token, 52.64 tokens per second) 0.57.323.354 I slot print_timing: id 0 | task 2102 | total time = 2572.00 ms / 360 tokens 0.57.323.355 I slot print_timing: id 0 | task 2102 | graphs reused = 2078 0.57.323.355 I slot print_timing: id 0 | task 2102 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.323.381 I slot release: id 0 | task 2102 | stop processing: n_tokens = 359, truncated = 0 0.57.328.114 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.155 (> 0.100 thold), f_keep = 0.103 0.57.334.298 I slot launch_slot_: id 0 | task 2204 | processing task, is_child = 0 1.00.988.047 I slot print_timing: id 0 | task 2204 | n_gen = 159, tg = 52.58 t/s, tg_3s = 52.91 t/s 1.01.483.028 I slot print_timing: id 0 | task 2204 | prompt eval time = 648.82 ms / 238 tokens ( 2.73 ms per token, 366.82 tokens per second) 1.01.483.034 I slot print_timing: id 0 | task 2204 | eval time = 3499.90 ms / 185 tokens ( 19.02 ms per token, 52.57 tokens per second) 1.01.483.035 I slot print_timing: id 0 | task 2204 | total time = 4148.72 ms / 423 tokens 1.01.483.035 I slot print_timing: id 0 | task 2204 | graphs reused = 2260 1.01.483.036 I slot print_timing: id 0 | task 2204 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.483.057 I slot release: id 0 | task 2204 | stop processing: n_tokens = 422, truncated = 0 1.01.488.183 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.150 (> 0.100 thold), f_keep = 0.088 1.01.493.928 I slot launch_slot_: id 0 | task 2392 | processing task, is_child = 0 1.05.264.460 I slot print_timing: id 0 | task 2392 | n_gen = 159, tg = 52.58 t/s, tg_3s = 52.92 t/s 1.08.280.926 I slot print_timing: id 0 | task 2392 | n_gen = 317, tg = 52.48 t/s, tg_3s = 52.38 t/s 1.11.293.965 I slot print_timing: id 0 | task 2392 | n_gen = 475, tg = 52.47 t/s, tg_3s = 52.44 t/s 1.14.308.123 I slot print_timing: id 0 | task 2392 | n_gen = 632, tg = 52.37 t/s, tg_3s = 52.09 t/s 1.16.502.643 I slot print_timing: id 0 | task 2392 | prompt eval time = 765.75 ms / 247 tokens ( 3.10 ms per token, 322.56 tokens per second) 1.16.502.651 I slot print_timing: id 0 | task 2392 | eval time = 14242.95 ms / 746 tokens ( 19.12 ms per token, 52.31 tokens per second) 1.16.502.652 I slot print_timing: id 0 | task 2392 | total time = 15008.70 ms / 993 tokens 1.16.502.653 I slot print_timing: id 0 | task 2392 | graphs reused = 3001 1.16.502.653 I slot print_timing: id 0 | task 2392 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.502.676 I slot release: id 0 | task 2392 | stop processing: n_tokens = 992, truncated = 0 1.16.507.926 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.131 (> 0.100 thold), f_keep = 0.037 1.16.516.604 I slot launch_slot_: id 0 | task 3141 | processing task, is_child = 0 1.19.097.994 I slot print_timing: id 0 | task 3141 | prompt eval time = 794.52 ms / 282 tokens ( 2.82 ms per token, 354.93 tokens per second) 1.19.097.997 I slot print_timing: id 0 | task 3141 | eval time = 1786.85 ms / 95 tokens ( 19.01 ms per token, 52.61 tokens per second) 1.19.097.998 I slot print_timing: id 0 | task 3141 | total time = 2581.38 ms / 377 tokens 1.19.097.999 I slot print_timing: id 0 | task 3141 | graphs reused = 3094 1.19.097.999 I slot print_timing: id 0 | task 3141 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.098.023 I slot release: id 0 | task 3141 | stop processing: n_tokens = 376, truncated = 0 1.19.102.831 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.101 1.19.109.552 I slot launch_slot_: id 0 | task 3239 | processing task, is_child = 0 1.21.755.024 I slot print_timing: id 0 | task 3239 | prompt eval time = 703.94 ms / 243 tokens ( 2.90 ms per token, 345.20 tokens per second) 1.21.755.030 I slot print_timing: id 0 | task 3239 | eval time = 1941.52 ms / 103 tokens ( 19.03 ms per token, 52.54 tokens per second) 1.21.755.031 I slot print_timing: id 0 | task 3239 | total time = 2645.46 ms / 346 tokens 1.21.755.032 I slot print_timing: id 0 | task 3239 | graphs reused = 3194 1.21.755.032 I slot print_timing: id 0 | task 3239 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.755.055 I slot release: id 0 | task 3239 | stop processing: n_tokens = 345, truncated = 0 1.21.759.796 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.107 1.21.764.908 I slot launch_slot_: id 0 | task 3345 | processing task, is_child = 0 1.23.746.992 I slot print_timing: id 0 | task 3345 | prompt eval time = 594.28 ms / 203 tokens ( 2.93 ms per token, 341.59 tokens per second) 1.23.746.998 I slot print_timing: id 0 | task 3345 | eval time = 1387.79 ms / 74 tokens ( 19.01 ms per token, 52.60 tokens per second) 1.23.747.000 I slot print_timing: id 0 | task 3345 | total time = 1982.07 ms / 277 tokens 1.23.747.000 I slot print_timing: id 0 | task 3345 | graphs reused = 3265 1.23.747.001 I slot print_timing: id 0 | task 3345 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.747.023 I slot release: id 0 | task 3345 | stop processing: n_tokens = 276, truncated = 0 1.23.751.844 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.167 (> 0.100 thold), f_keep = 0.138 1.23.756.078 I slot launch_slot_: id 0 | task 3422 | processing task, is_child = 0 1.26.072.273 I slot print_timing: id 0 | task 3422 | prompt eval time = 643.68 ms / 228 tokens ( 2.82 ms per token, 354.21 tokens per second) 1.26.072.279 I slot print_timing: id 0 | task 3422 | eval time = 1672.50 ms / 89 tokens ( 19.01 ms per token, 52.62 tokens per second) 1.26.072.280 I slot print_timing: id 0 | task 3422 | total time = 2316.18 ms / 317 tokens 1.26.072.281 I slot print_timing: id 0 | task 3422 | graphs reused = 3351 1.26.072.281 I slot print_timing: id 0 | task 3422 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.072.307 I slot release: id 0 | task 3422 | stop processing: n_tokens = 316, truncated = 0 1.26.077.161 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.145 (> 0.100 thold), f_keep = 0.117 1.26.082.744 I slot launch_slot_: id 0 | task 3514 | processing task, is_child = 0 1.29.072.066 I slot print_timing: id 0 | task 3514 | prompt eval time = 765.97 ms / 256 tokens ( 2.99 ms per token, 334.22 tokens per second) 1.29.072.072 I slot print_timing: id 0 | task 3514 | eval time = 2223.34 ms / 118 tokens ( 19.00 ms per token, 52.62 tokens per second) 1.29.072.073 I slot print_timing: id 0 | task 3514 | total time = 2989.31 ms / 374 tokens 1.29.072.073 I slot print_timing: id 0 | task 3514 | graphs reused = 3467 1.29.072.074 I slot print_timing: id 0 | task 3514 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.072.096 I slot release: id 0 | task 3514 | stop processing: n_tokens = 373, truncated = 0 1.29.076.652 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.155 (> 0.100 thold), f_keep = 0.099 1.29.082.070 I slot launch_slot_: id 0 | task 3635 | processing task, is_child = 0 1.31.635.642 I slot print_timing: id 0 | task 3635 | prompt eval time = 650.24 ms / 238 tokens ( 2.73 ms per token, 366.02 tokens per second) 1.31.635.648 I slot print_timing: id 0 | task 3635 | eval time = 1903.33 ms / 101 tokens ( 19.03 ms per token, 52.54 tokens per second) 1.31.635.649 I slot print_timing: id 0 | task 3635 | total time = 2553.56 ms / 339 tokens 1.31.635.650 I slot print_timing: id 0 | task 3635 | graphs reused = 3565 1.31.635.650 I slot print_timing: id 0 | task 3635 | graph reallocs = 0 / 0 (same size) / (changed size) 1.31.635.672 I slot release: id 0 | task 3635 | stop processing: n_tokens = 338, truncated = 0 1.31.640.448 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.109 1.31.646.312 I slot launch_slot_: id 0 | task 3739 | processing task, is_child = 0 1.34.063.375 I slot print_timing: id 0 | task 3739 | prompt eval time = 614.16 ms / 211 tokens ( 2.91 ms per token, 343.56 tokens per second) 1.34.063.379 I slot print_timing: id 0 | task 3739 | eval time = 1802.89 ms / 96 tokens ( 18.98 ms per token, 52.69 tokens per second) 1.34.063.379 I slot print_timing: id 0 | task 3739 | total time = 2417.05 ms / 307 tokens 1.34.063.380 I slot print_timing: id 0 | task 3739 | graphs reused = 3658 1.34.063.380 I slot print_timing: id 0 | task 3739 | graph reallocs = 0 / 0 (same size) / (changed size) 1.34.063.400 I slot release: id 0 | task 3739 | stop processing: n_tokens = 306, truncated = 0 1.34.068.067 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.121 1.34.072.423 I slot launch_slot_: id 0 | task 3838 | processing task, is_child = 0 1.36.143.098 I slot print_timing: id 0 | task 3838 | prompt eval time = 607.68 ms / 211 tokens ( 2.88 ms per token, 347.22 tokens per second) 1.36.143.104 I slot print_timing: id 0 | task 3838 | eval time = 1462.98 ms / 78 tokens ( 19.00 ms per token, 52.63 tokens per second) 1.36.143.105 I slot print_timing: id 0 | task 3838 | total time = 2070.67 ms / 289 tokens 1.36.143.105 I slot print_timing: id 0 | task 3838 | graphs reused = 3733 1.36.143.106 I slot print_timing: id 0 | task 3838 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.143.126 I slot release: id 0 | task 3838 | stop processing: n_tokens = 288, truncated = 0 1.36.147.946 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.154 (> 0.100 thold), f_keep = 0.128 1.36.153.037 I slot launch_slot_: id 0 | task 3919 | processing task, is_child = 0 1.39.804.000 I slot print_timing: id 0 | task 3919 | n_gen = 159, tg = 52.56 t/s, tg_3s = 52.89 t/s 1.39.841.983 I slot print_timing: id 0 | task 3919 | prompt eval time = 644.69 ms / 240 tokens ( 2.69 ms per token, 372.27 tokens per second) 1.39.841.986 I slot print_timing: id 0 | task 3919 | eval time = 3044.24 ms / 161 tokens ( 19.03 ms per token, 52.56 tokens per second) 1.39.841.987 I slot print_timing: id 0 | task 3919 | total time = 3688.94 ms / 401 tokens 1.39.841.988 I slot print_timing: id 0 | task 3919 | graphs reused = 3891 1.39.841.988 I slot print_timing: id 0 | task 3919 | graph reallocs = 0 / 0 (same size) / (changed size) 1.39.842.010 I slot release: id 0 | task 3919 | stop processing: n_tokens = 400, truncated = 0 1.39.847.010 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.142 (> 0.100 thold), f_keep = 0.093 1.39.853.524 I slot launch_slot_: id 0 | task 4083 | processing task, is_child = 0 1.42.052.597 I slot print_timing: id 0 | task 4083 | prompt eval time = 706.16 ms / 260 tokens ( 2.72 ms per token, 368.19 tokens per second) 1.42.052.602 I slot print_timing: id 0 | task 4083 | eval time = 1492.90 ms / 79 tokens ( 19.14 ms per token, 52.25 tokens per second) 1.42.052.603 I slot print_timing: id 0 | task 4083 | total time = 2199.06 ms / 339 tokens 1.42.052.604 I slot print_timing: id 0 | task 4083 | graphs reused = 3968 1.42.052.604 I slot print_timing: id 0 | task 4083 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.052.626 I slot release: id 0 | task 4083 | stop processing: n_tokens = 338, truncated = 0 1.42.057.047 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.181 (> 0.100 thold), f_keep = 0.109 1.42.063.118 I slot launch_slot_: id 0 | task 4165 | processing task, is_child = 0 1.44.110.618 I slot print_timing: id 0 | task 4165 | prompt eval time = 585.47 ms / 204 tokens ( 2.87 ms per token, 348.44 tokens per second) 1.44.110.621 I slot print_timing: id 0 | task 4165 | eval time = 1462.02 ms / 78 tokens ( 18.99 ms per token, 52.67 tokens per second) 1.44.110.622 I slot print_timing: id 0 | task 4165 | total time = 2047.49 ms / 282 tokens 1.44.110.623 I slot print_timing: id 0 | task 4165 | graphs reused = 4043 1.44.110.623 I slot print_timing: id 0 | task 4165 | graph reallocs = 0 / 0 (same size) / (changed size) 1.44.110.646 I slot release: id 0 | task 4165 | stop processing: n_tokens = 281, truncated = 0 1.44.115.463 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.152 (> 0.100 thold), f_keep = 0.132 1.44.118.856 I slot launch_slot_: id 0 | task 4246 | processing task, is_child = 0 1.47.773.549 I slot print_timing: id 0 | task 4246 | n_gen = 159, tg = 52.64 t/s, tg_3s = 52.97 t/s 1.48.876.449 I slot print_timing: id 0 | task 4246 | prompt eval time = 653.18 ms / 244 tokens ( 2.68 ms per token, 373.56 tokens per second) 1.48.876.455 I slot print_timing: id 0 | task 4246 | eval time = 4104.40 ms / 217 tokens ( 19.00 ms per token, 52.63 tokens per second) 1.48.876.455 I slot print_timing: id 0 | task 4246 | total time = 4757.58 ms / 461 tokens 1.48.876.456 I slot print_timing: id 0 | task 4246 | graphs reused = 4257 1.48.876.457 I slot print_timing: id 0 | task 4246 | graph reallocs = 0 / 0 (same size) / (changed size) 1.48.876.481 I slot release: id 0 | task 4246 | stop processing: n_tokens = 460, truncated = 0 1.48.880.943 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.210 (> 0.100 thold), f_keep = 0.080 1.48.887.955 I slot launch_slot_: id 0 | task 4466 | processing task, is_child = 0 1.51.978.413 I slot print_timing: id 0 | task 4466 | prompt eval time = 556.03 ms / 176 tokens ( 3.16 ms per token, 316.53 tokens per second) 1.51.978.419 I slot print_timing: id 0 | task 4466 | eval time = 2534.42 ms / 135 tokens ( 18.91 ms per token, 52.87 tokens per second) 1.51.978.420 I slot print_timing: id 0 | task 4466 | total time = 3090.45 ms / 311 tokens 1.51.978.421 I slot print_timing: id 0 | task 4466 | graphs reused = 4389 1.51.978.421 I slot print_timing: id 0 | task 4466 | graph reallocs = 0 / 0 (same size) / (changed size) 1.51.978.444 I slot release: id 0 | task 4466 | stop processing: n_tokens = 310, truncated = 0 1.51.983.046 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.119 1.51.986.633 I slot launch_slot_: id 0 | task 4604 | processing task, is_child = 0 1.54.214.409 I slot print_timing: id 0 | task 4604 | prompt eval time = 577.56 ms / 185 tokens ( 3.12 ms per token, 320.31 tokens per second) 1.54.214.416 I slot print_timing: id 0 | task 4604 | eval time = 1650.21 ms / 88 tokens ( 18.97 ms per token, 52.72 tokens per second) 1.54.214.416 I slot print_timing: id 0 | task 4604 | total time = 2227.77 ms / 273 tokens 1.54.214.417 I slot print_timing: id 0 | task 4604 | graphs reused = 4474 1.54.214.418 I slot print_timing: id 0 | task 4604 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.214.436 I slot release: id 0 | task 4604 | stop processing: n_tokens = 272, truncated = 0 1.54.218.822 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.191 (> 0.100 thold), f_keep = 0.136 1.54.223.510 I slot launch_slot_: id 0 | task 4695 | processing task, is_child = 0 1.56.180.137 I slot print_timing: id 0 | task 4695 | prompt eval time = 569.87 ms / 194 tokens ( 2.94 ms per token, 340.43 tokens per second) 1.56.180.144 I slot print_timing: id 0 | task 4695 | eval time = 1386.75 ms / 74 tokens ( 19.00 ms per token, 52.64 tokens per second) 1.56.180.144 I slot print_timing: id 0 | task 4695 | total time = 1956.62 ms / 268 tokens 1.56.180.145 I slot print_timing: id 0 | task 4695 | graphs reused = 4545 1.56.180.145 I slot print_timing: id 0 | task 4695 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.180.165 I slot release: id 0 | task 4695 | stop processing: n_tokens = 267, truncated = 0 1.56.184.684 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.196 (> 0.100 thold), f_keep = 0.139 1.56.189.325 I slot launch_slot_: id 0 | task 4772 | processing task, is_child = 0 1.58.088.488 I slot print_timing: id 0 | task 4772 | prompt eval time = 550.38 ms / 189 tokens ( 2.91 ms per token, 343.40 tokens per second) 1.58.088.494 I slot print_timing: id 0 | task 4772 | eval time = 1348.78 ms / 72 tokens ( 19.00 ms per token, 52.64 tokens per second) 1.58.088.496 I slot print_timing: id 0 | task 4772 | total time = 1899.16 ms / 261 tokens 1.58.088.496 I slot print_timing: id 0 | task 4772 | graphs reused = 4614 1.58.088.497 I slot print_timing: id 0 | task 4772 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.088.516 I slot release: id 0 | task 4772 | stop processing: n_tokens = 260, truncated = 0 1.58.093.181 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.150 (> 0.100 thold), f_keep = 0.142 1.58.097.756 I slot launch_slot_: id 0 | task 4847 | processing task, is_child = 0 2.00.572.980 I slot print_timing: id 0 | task 4847 | prompt eval time = 705.65 ms / 246 tokens ( 2.87 ms per token, 348.61 tokens per second) 2.00.572.986 I slot print_timing: id 0 | task 4847 | eval time = 1769.56 ms / 94 tokens ( 19.03 ms per token, 52.56 tokens per second) 2.00.572.988 I slot print_timing: id 0 | task 4847 | total time = 2475.22 ms / 340 tokens 2.00.572.988 I slot print_timing: id 0 | task 4847 | graphs reused = 4705 2.00.572.989 I slot print_timing: id 0 | task 4847 | graph reallocs = 0 / 0 (same size) / (changed size) 2.00.573.009 I slot release: id 0 | task 4847 | stop processing: n_tokens = 339, truncated = 0 2.00.578.553 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 339, t_last = 350174758587 2.00.584.570 I slot launch_slot_: id 0 | task 4944 | processing task, is_child = 0 2.04.309.168 I slot print_timing: id 0 | task 4944 | prompt eval time = 933.19 ms / 373 tokens ( 2.50 ms per token, 399.70 tokens per second) 2.04.309.172 I slot print_timing: id 0 | task 4944 | eval time = 2791.39 ms / 147 tokens ( 19.12 ms per token, 52.30 tokens per second) 2.04.309.173 I slot print_timing: id 0 | task 4944 | total time = 3724.58 ms / 520 tokens 2.04.309.173 I slot print_timing: id 0 | task 4944 | graphs reused = 4849 2.04.309.174 I slot print_timing: id 0 | task 4944 | graph reallocs = 0 / 0 (same size) / (changed size) 2.04.309.205 I slot release: id 0 | task 4944 | stop processing: n_tokens = 519, truncated = 0 2.04.313.891 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.071 2.04.322.435 I slot launch_slot_: id 0 | task 5094 | processing task, is_child = 0 2.06.752.394 I slot print_timing: id 0 | task 5094 | prompt eval time = 590.22 ms / 197 tokens ( 3.00 ms per token, 333.78 tokens per second) 2.06.752.398 I slot print_timing: id 0 | task 5094 | eval time = 1839.73 ms / 98 tokens ( 18.97 ms per token, 52.72 tokens per second) 2.06.752.399 I slot print_timing: id 0 | task 5094 | total time = 2429.95 ms / 295 tokens 2.06.752.400 I slot print_timing: id 0 | task 5094 | graphs reused = 4944 2.06.752.400 I slot print_timing: id 0 | task 5094 | graph reallocs = 0 / 0 (same size) / (changed size) 2.06.752.420 I slot release: id 0 | task 5094 | stop processing: n_tokens = 294, truncated = 0 2.06.757.205 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.163 (> 0.100 thold), f_keep = 0.126 2.06.760.740 I slot launch_slot_: id 0 | task 5195 | processing task, is_child = 0 2.09.548.625 I slot print_timing: id 0 | task 5195 | prompt eval time = 621.59 ms / 227 tokens ( 2.74 ms per token, 365.19 tokens per second) 2.09.548.631 I slot print_timing: id 0 | task 5195 | eval time = 2166.29 ms / 115 tokens ( 19.00 ms per token, 52.62 tokens per second) 2.09.548.632 I slot print_timing: id 0 | task 5195 | total time = 2787.88 ms / 342 tokens 2.09.548.633 I slot print_timing: id 0 | task 5195 | graphs reused = 5056 2.09.548.633 I slot print_timing: id 0 | task 5195 | graph reallocs = 0 / 0 (same size) / (changed size) 2.09.548.657 I slot release: id 0 | task 5195 | stop processing: n_tokens = 341, truncated = 0 2.09.553.658 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.133 (> 0.100 thold), f_keep = 0.109 2.09.559.410 I slot launch_slot_: id 0 | task 5313 | processing task, is_child = 0 2.12.195.364 I slot print_timing: id 0 | task 5313 | prompt eval time = 734.86 ms / 278 tokens ( 2.64 ms per token, 378.30 tokens per second) 2.12.195.370 I slot print_timing: id 0 | task 5313 | eval time = 1901.08 ms / 101 tokens ( 19.01 ms per token, 52.60 tokens per second) 2.12.195.371 I slot print_timing: id 0 | task 5313 | total time = 2635.95 ms / 379 tokens 2.12.195.371 I slot print_timing: id 0 | task 5313 | graphs reused = 5155 2.12.195.372 I slot print_timing: id 0 | task 5313 | graph reallocs = 0 / 0 (same size) / (changed size) 2.12.195.394 I slot release: id 0 | task 5313 | stop processing: n_tokens = 378, truncated = 0 2.12.200.574 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.131 (> 0.100 thold), f_keep = 0.101 2.12.207.422 I slot launch_slot_: id 0 | task 5417 | processing task, is_child = 0 2.15.961.948 I slot print_timing: id 0 | task 5417 | n_gen = 159, tg = 52.58 t/s, tg_3s = 52.91 t/s 2.16.229.007 I slot print_timing: id 0 | task 5417 | prompt eval time = 749.37 ms / 289 tokens ( 2.59 ms per token, 385.66 tokens per second) 2.16.229.010 I slot print_timing: id 0 | task 5417 | eval time = 3272.21 ms / 173 tokens ( 19.02 ms per token, 52.56 tokens per second) 2.16.229.021 I slot print_timing: id 0 | task 5417 | total time = 4021.58 ms / 462 tokens 2.16.229.023 I slot print_timing: id 0 | task 5417 | graphs reused = 5326 2.16.229.024 I slot print_timing: id 0 | task 5417 | graph reallocs = 0 / 0 (same size) / (changed size) 2.16.229.050 I slot release: id 0 | task 5417 | stop processing: n_tokens = 461, truncated = 0 2.16.233.641 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.195 (> 0.100 thold), f_keep = 0.087 2.16.241.198 I slot launch_slot_: id 0 | task 5593 | processing task, is_child = 0 2.18.219.001 I slot print_timing: id 0 | task 5593 | prompt eval time = 591.40 ms / 205 tokens ( 2.88 ms per token, 346.64 tokens per second) 2.18.219.007 I slot print_timing: id 0 | task 5593 | eval time = 1386.40 ms / 74 tokens ( 18.99 ms per token, 52.65 tokens per second) 2.18.219.009 I slot print_timing: id 0 | task 5593 | total time = 1977.80 ms / 279 tokens 2.18.219.010 I slot print_timing: id 0 | task 5593 | graphs reused = 5397 2.18.219.010 I slot print_timing: id 0 | task 5593 | graph reallocs = 0 / 0 (same size) / (changed size) 2.18.219.030 I slot release: id 0 | task 5593 | stop processing: n_tokens = 278, truncated = 0 2.18.223.649 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.167 (> 0.100 thold), f_keep = 0.133 2.18.227.025 I slot launch_slot_: id 0 | task 5670 | processing task, is_child = 0 2.20.547.813 I slot print_timing: id 0 | task 5670 | prompt eval time = 629.83 ms / 221 tokens ( 2.85 ms per token, 350.89 tokens per second) 2.20.547.819 I slot print_timing: id 0 | task 5670 | eval time = 1690.95 ms / 90 tokens ( 19.00 ms per token, 52.63 tokens per second) 2.20.547.820 I slot print_timing: id 0 | task 5670 | total time = 2320.78 ms / 311 tokens 2.20.547.821 I slot print_timing: id 0 | task 5670 | graphs reused = 5484 2.20.547.821 I slot print_timing: id 0 | task 5670 | graph reallocs = 0 / 0 (same size) / (changed size) 2.20.547.841 I slot release: id 0 | task 5670 | stop processing: n_tokens = 310, truncated = 0 2.20.552.435 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.165 (> 0.100 thold), f_keep = 0.119 2.20.557.914 I slot launch_slot_: id 0 | task 5763 | processing task, is_child = 0 2.22.555.017 I slot print_timing: id 0 | task 5763 | prompt eval time = 625.69 ms / 224 tokens ( 2.79 ms per token, 358.01 tokens per second) 2.22.555.020 I slot print_timing: id 0 | task 5763 | eval time = 1371.40 ms / 73 tokens ( 19.05 ms per token, 52.50 tokens per second) 2.22.555.021 I slot print_timing: id 0 | task 5763 | total time = 1997.09 ms / 297 tokens 2.22.555.022 I slot print_timing: id 0 | task 5763 | graphs reused = 5554 2.22.555.022 I slot print_timing: id 0 | task 5763 | graph reallocs = 0 / 0 (same size) / (changed size) 2.22.555.042 I slot release: id 0 | task 5763 | stop processing: n_tokens = 296, truncated = 0 2.22.559.870 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.146 (> 0.100 thold), f_keep = 0.125 2.22.565.370 I slot launch_slot_: id 0 | task 5839 | processing task, is_child = 0 2.25.245.397 I slot print_timing: id 0 | task 5839 | prompt eval time = 702.63 ms / 254 tokens ( 2.77 ms per token, 361.50 tokens per second) 2.25.245.404 I slot print_timing: id 0 | task 5839 | eval time = 1977.39 ms / 105 tokens ( 19.01 ms per token, 52.59 tokens per second) 2.25.245.404 I slot print_timing: id 0 | task 5839 | total time = 2680.02 ms / 359 tokens 2.25.245.405 I slot print_timing: id 0 | task 5839 | graphs reused = 5656 2.25.245.406 I slot print_timing: id 0 | task 5839 | graph reallocs = 0 / 0 (same size) / (changed size) 2.25.245.428 I slot release: id 0 | task 5839 | stop processing: n_tokens = 358, truncated = 0 2.25.249.985 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.177 (> 0.100 thold), f_keep = 0.103 2.25.256.309 I slot launch_slot_: id 0 | task 5947 | processing task, is_child = 0 2.27.455.219 I slot print_timing: id 0 | task 5947 | prompt eval time = 595.32 ms / 209 tokens ( 2.85 ms per token, 351.07 tokens per second) 2.27.455.224 I slot print_timing: id 0 | task 5947 | eval time = 1603.58 ms / 85 tokens ( 19.09 ms per token, 52.38 tokens per second) 2.27.455.225 I slot print_timing: id 0 | task 5947 | total time = 2198.90 ms / 294 tokens 2.27.455.226 I slot print_timing: id 0 | task 5947 | graphs reused = 5738 2.27.455.226 I slot print_timing: id 0 | task 5947 | graph reallocs = 0 / 0 (same size) / (changed size) 2.27.455.246 I slot release: id 0 | task 5947 | stop processing: n_tokens = 293, truncated = 0 2.27.460.273 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.141 (> 0.100 thold), f_keep = 0.126 2.27.463.874 I slot launch_slot_: id 0 | task 6035 | processing task, is_child = 0 2.29.826.958 I slot print_timing: id 0 | task 6035 | prompt eval time = 709.07 ms / 263 tokens ( 2.70 ms per token, 370.91 tokens per second) 2.29.826.964 I slot print_timing: id 0 | task 6035 | eval time = 1654.00 ms / 88 tokens ( 19.01 ms per token, 52.60 tokens per second) 2.29.826.965 I slot print_timing: id 0 | task 6035 | total time = 2363.08 ms / 351 tokens 2.29.826.966 I slot print_timing: id 0 | task 6035 | graphs reused = 5824 2.29.826.966 I slot print_timing: id 0 | task 6035 | graph reallocs = 0 / 0 (same size) / (changed size) 2.29.826.988 I slot release: id 0 | task 6035 | stop processing: n_tokens = 350, truncated = 0 2.29.831.239 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.167 (> 0.100 thold), f_keep = 0.106 2.29.837.771 I slot launch_slot_: id 0 | task 6126 | processing task, is_child = 0 2.32.243.325 I slot print_timing: id 0 | task 6126 | prompt eval time = 600.48 ms / 221 tokens ( 2.72 ms per token, 368.04 tokens per second) 2.32.243.328 I slot print_timing: id 0 | task 6126 | eval time = 1805.06 ms / 96 tokens ( 19.00 ms per token, 52.63 tokens per second) 2.32.243.329 I slot print_timing: id 0 | task 6126 | total time = 2405.54 ms / 317 tokens 2.32.243.330 I slot print_timing: id 0 | task 6126 | graphs reused = 5917 2.32.243.330 I slot print_timing: id 0 | task 6126 | graph reallocs = 0 / 0 (same size) / (changed size) 2.32.243.350 I slot release: id 0 | task 6126 | stop processing: n_tokens = 316, truncated = 0 2.32.247.940 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.117 2.32.252.828 I slot launch_slot_: id 0 | task 6225 | processing task, is_child = 0 2.34.693.226 I slot print_timing: id 0 | task 6225 | prompt eval time = 635.13 ms / 217 tokens ( 2.93 ms per token, 341.66 tokens per second) 2.34.693.233 I slot print_timing: id 0 | task 6225 | eval time = 1805.26 ms / 96 tokens ( 19.00 ms per token, 52.62 tokens per second) 2.34.693.234 I slot print_timing: id 0 | task 6225 | total time = 2440.39 ms / 313 tokens 2.34.693.234 I slot print_timing: id 0 | task 6225 | graphs reused = 6010 2.34.693.235 I slot print_timing: id 0 | task 6225 | graph reallocs = 0 / 0 (same size) / (changed size) 2.34.693.256 I slot release: id 0 | task 6225 | stop processing: n_tokens = 312, truncated = 0 2.34.698.661 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.110 (> 0.100 thold), f_keep = 0.119 2.34.703.681 I slot launch_slot_: id 0 | task 6324 | processing task, is_child = 0 2.38.447.053 I slot print_timing: id 0 | task 6324 | prompt eval time = 808.78 ms / 337 tokens ( 2.40 ms per token, 416.67 tokens per second) 2.38.447.059 I slot print_timing: id 0 | task 6324 | eval time = 2934.57 ms / 155 tokens ( 19.06 ms per token, 52.48 tokens per second) 2.38.447.060 I slot print_timing: id 0 | task 6324 | total time = 3743.36 ms / 492 tokens 2.38.447.060 I slot print_timing: id 0 | task 6324 | graphs reused = 6163 2.38.447.061 I slot print_timing: id 0 | task 6324 | graph reallocs = 0 / 0 (same size) / (changed size) 2.38.447.090 I slot release: id 0 | task 6324 | stop processing: n_tokens = 491, truncated = 0 2.38.452.237 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.123 (> 0.100 thold), f_keep = 0.075 2.38.461.654 I slot launch_slot_: id 0 | task 6482 | processing task, is_child = 0 2.41.713.535 I slot print_timing: id 0 | task 6482 | prompt eval time = 758.04 ms / 301 tokens ( 2.52 ms per token, 397.07 tokens per second) 2.41.713.543 I slot print_timing: id 0 | task 6482 | eval time = 2493.82 ms / 132 tokens ( 19.04 ms per token, 52.53 tokens per second) 2.41.713.543 I slot print_timing: id 0 | task 6482 | total time = 3251.87 ms / 433 tokens 2.41.713.544 I slot print_timing: id 0 | task 6482 | graphs reused = 6293 2.41.713.545 I slot print_timing: id 0 | task 6482 | graph reallocs = 0 / 0 (same size) / (changed size) 2.41.713.571 I slot release: id 0 | task 6482 | stop processing: n_tokens = 432, truncated = 0 2.41.717.952 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.086 2.41.725.384 I slot launch_slot_: id 0 | task 6617 | processing task, is_child = 0 2.44.092.760 I slot print_timing: id 0 | task 6617 | prompt eval time = 620.99 ms / 212 tokens ( 2.93 ms per token, 341.39 tokens per second) 2.44.092.766 I slot print_timing: id 0 | task 6617 | eval time = 1746.38 ms / 93 tokens ( 18.98 ms per token, 52.68 tokens per second) 2.44.092.766 I slot print_timing: id 0 | task 6617 | total time = 2367.37 ms / 305 tokens 2.44.092.767 I slot print_timing: id 0 | task 6617 | graphs reused = 6383 2.44.092.768 I slot print_timing: id 0 | task 6617 | graph reallocs = 0 / 0 (same size) / (changed size) 2.44.092.787 I slot release: id 0 | task 6617 | stop processing: n_tokens = 304, truncated = 0 2.44.097.599 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.149 (> 0.100 thold), f_keep = 0.122 2.44.101.297 I slot launch_slot_: id 0 | task 6713 | processing task, is_child = 0 2.46.523.022 I slot print_timing: id 0 | task 6713 | prompt eval time = 672.27 ms / 248 tokens ( 2.71 ms per token, 368.90 tokens per second) 2.46.523.028 I slot print_timing: id 0 | task 6713 | eval time = 1749.45 ms / 93 tokens ( 19.02 ms per token, 52.59 tokens per second) 2.46.523.029 I slot print_timing: id 0 | task 6713 | total time = 2421.72 ms / 341 tokens 2.46.523.029 I slot print_timing: id 0 | task 6713 | graphs reused = 6473 2.46.523.030 I slot print_timing: id 0 | task 6713 | graph reallocs = 0 / 0 (same size) / (changed size) 2.46.523.053 I slot release: id 0 | task 6713 | stop processing: n_tokens = 340, truncated = 0 2.46.527.649 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.181 (> 0.100 thold), f_keep = 0.109 2.46.533.902 I slot launch_slot_: id 0 | task 6809 | processing task, is_child = 0 2.48.850.958 I slot print_timing: id 0 | task 6809 | prompt eval time = 588.38 ms / 204 tokens ( 2.88 ms per token, 346.72 tokens per second) 2.48.850.962 I slot print_timing: id 0 | task 6809 | eval time = 1728.67 ms / 92 tokens ( 19.00 ms per token, 52.64 tokens per second) 2.48.850.963 I slot print_timing: id 0 | task 6809 | total time = 2317.05 ms / 296 tokens 2.48.850.964 I slot print_timing: id 0 | task 6809 | graphs reused = 6562 2.48.850.964 I slot print_timing: id 0 | task 6809 | graph reallocs = 0 / 0 (same size) / (changed size) 2.48.850.988 I slot release: id 0 | task 6809 | stop processing: n_tokens = 295, truncated = 0 2.48.856.501 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.139 (> 0.100 thold), f_keep = 0.125 2.48.860.209 I slot launch_slot_: id 0 | task 6904 | processing task, is_child = 0 2.51.739.848 I slot print_timing: id 0 | task 6904 | prompt eval time = 717.46 ms / 267 tokens ( 2.69 ms per token, 372.15 tokens per second) 2.51.739.850 I slot print_timing: id 0 | task 6904 | eval time = 2162.17 ms / 115 tokens ( 18.97 ms per token, 52.72 tokens per second) 2.51.739.851 I slot print_timing: id 0 | task 6904 | total time = 2879.62 ms / 382 tokens 2.51.739.852 I slot print_timing: id 0 | task 6904 | graphs reused = 6675 2.51.739.852 I slot print_timing: id 0 | task 6904 | graph reallocs = 0 / 0 (same size) / (changed size) 2.51.739.874 I slot release: id 0 | task 6904 | stop processing: n_tokens = 381, truncated = 0 2.51.745.417 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 381, t_last = 350225925452 2.51.751.786 I slot launch_slot_: id 0 | task 7022 | processing task, is_child = 0 2.54.358.502 I slot print_timing: id 0 | task 7022 | prompt eval time = 866.31 ms / 392 tokens ( 2.21 ms per token, 452.49 tokens per second) 2.54.358.508 I slot print_timing: id 0 | task 7022 | eval time = 1740.39 ms / 92 tokens ( 19.13 ms per token, 52.29 tokens per second) 2.54.358.509 I slot print_timing: id 0 | task 7022 | total time = 2606.71 ms / 484 tokens 2.54.358.510 I slot print_timing: id 0 | task 7022 | graphs reused = 6765 2.54.358.510 I slot print_timing: id 0 | task 7022 | graph reallocs = 0 / 0 (same size) / (changed size) 2.54.358.539 I slot release: id 0 | task 7022 | stop processing: n_tokens = 483, truncated = 0 2.54.364.451 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 483, t_last = 350228544117 2.54.373.839 I slot launch_slot_: id 0 | task 7117 | processing task, is_child = 0 2.57.153.405 I slot print_timing: id 0 | task 7117 | prompt eval time = 1034.17 ms / 461 tokens ( 2.24 ms per token, 445.77 tokens per second) 2.57.153.411 I slot print_timing: id 0 | task 7117 | eval time = 1745.39 ms / 92 tokens ( 19.18 ms per token, 52.14 tokens per second) 2.57.153.413 I slot print_timing: id 0 | task 7117 | total time = 2779.55 ms / 553 tokens 2.57.153.413 I slot print_timing: id 0 | task 7117 | graphs reused = 6854 2.57.153.414 I slot print_timing: id 0 | task 7117 | graph reallocs = 0 / 0 (same size) / (changed size) 2.57.153.444 I slot release: id 0 | task 7117 | stop processing: n_tokens = 552, truncated = 0 2.57.159.983 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 552, t_last = 350231339022 2.57.170.019 I slot launch_slot_: id 0 | task 7212 | processing task, is_child = 0 3.00.063.451 I slot print_timing: id 0 | task 7212 | prompt eval time = 1050.95 ms / 505 tokens ( 2.08 ms per token, 480.52 tokens per second) 3.00.063.457 I slot print_timing: id 0 | task 7212 | eval time = 1842.48 ms / 97 tokens ( 19.19 ms per token, 52.10 tokens per second) 3.00.063.458 I slot print_timing: id 0 | task 7212 | total time = 2893.43 ms / 602 tokens 3.00.063.459 I slot print_timing: id 0 | task 7212 | graphs reused = 6948 3.00.063.459 I slot print_timing: id 0 | task 7212 | graph reallocs = 0 / 0 (same size) / (changed size) 3.00.063.490 I slot release: id 0 | task 7212 | stop processing: n_tokens = 601, truncated = 0 3.00.069.397 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 601, t_last = 350234249068 3.00.080.121 I slot launch_slot_: id 0 | task 7312 | processing task, is_child = 0 3.02.831.284 I slot print_timing: id 0 | task 7312 | prompt eval time = 980.28 ms / 493 tokens ( 1.99 ms per token, 502.92 tokens per second) 3.02.831.290 I slot print_timing: id 0 | task 7312 | eval time = 1770.87 ms / 93 tokens ( 19.25 ms per token, 51.95 tokens per second) 3.02.831.291 I slot print_timing: id 0 | task 7312 | total time = 2751.15 ms / 586 tokens 3.02.831.291 I slot print_timing: id 0 | task 7312 | graphs reused = 7038 3.02.831.292 I slot print_timing: id 0 | task 7312 | graph reallocs = 0 / 0 (same size) / (changed size) 3.02.831.324 I slot release: id 0 | task 7312 | stop processing: n_tokens = 585, truncated = 0 3.02.836.642 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.112 (> 0.100 thold), f_keep = 0.063 3.02.847.396 I slot launch_slot_: id 0 | task 7408 | processing task, is_child = 0 3.05.115.970 I slot print_timing: id 0 | task 7408 | prompt eval time = 781.54 ms / 331 tokens ( 2.36 ms per token, 423.52 tokens per second) 3.05.115.974 I slot print_timing: id 0 | task 7408 | eval time = 1487.02 ms / 79 tokens ( 19.06 ms per token, 52.45 tokens per second) 3.05.115.974 I slot print_timing: id 0 | task 7408 | total time = 2268.56 ms / 410 tokens 3.05.115.975 I slot print_timing: id 0 | task 7408 | graphs reused = 7115 3.05.115.975 I slot print_timing: id 0 | task 7408 | graph reallocs = 0 / 0 (same size) / (changed size) 3.05.116.000 I slot release: id 0 | task 7408 | stop processing: n_tokens = 409, truncated = 0 3.05.121.942 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 350239301578 3.05.126.925 I slot launch_slot_: id 0 | task 7490 | processing task, is_child = 0 3.08.516.146 I slot print_timing: id 0 | task 7490 | prompt eval time = 933.91 ms / 455 tokens ( 2.05 ms per token, 487.20 tokens per second) 3.08.516.149 I slot print_timing: id 0 | task 7490 | eval time = 2455.30 ms / 129 tokens ( 19.18 ms per token, 52.13 tokens per second) 3.08.516.150 I slot print_timing: id 0 | task 7490 | total time = 3389.21 ms / 584 tokens 3.08.516.150 I slot print_timing: id 0 | task 7490 | graphs reused = 7241 3.08.516.151 I slot print_timing: id 0 | task 7490 | graph reallocs = 0 / 0 (same size) / (changed size) 3.08.516.183 I slot release: id 0 | task 7490 | stop processing: n_tokens = 583, truncated = 0 3.08.521.766 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 583, t_last = 350242701761 3.08.532.111 I slot launch_slot_: id 0 | task 7622 | processing task, is_child = 0 3.11.798.306 I slot print_timing: id 0 | task 7622 | prompt eval time = 911.79 ms / 439 tokens ( 2.08 ms per token, 481.47 tokens per second) 3.11.798.312 I slot print_timing: id 0 | task 7622 | eval time = 2354.40 ms / 124 tokens ( 19.14 ms per token, 52.24 tokens per second) 3.11.798.313 I slot print_timing: id 0 | task 7622 | total time = 3266.18 ms / 563 tokens 3.11.798.313 I slot print_timing: id 0 | task 7622 | graphs reused = 7362 3.11.798.314 I slot print_timing: id 0 | task 7622 | graph reallocs = 0 / 0 (same size) / (changed size) 3.11.798.345 I slot release: id 0 | task 7622 | stop processing: n_tokens = 562, truncated = 0 3.11.804.157 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 562, t_last = 350245983923 3.11.814.310 I slot launch_slot_: id 0 | task 7749 | processing task, is_child = 0 3.13.860.763 I slot print_timing: id 0 | task 7749 | prompt eval time = 821.71 ms / 379 tokens ( 2.17 ms per token, 461.23 tokens per second) 3.13.860.772 I slot print_timing: id 0 | task 7749 | eval time = 1224.73 ms / 65 tokens ( 19.14 ms per token, 52.26 tokens per second) 3.13.860.773 I slot print_timing: id 0 | task 7749 | total time = 2046.44 ms / 444 tokens 3.13.860.773 I slot print_timing: id 0 | task 7749 | graphs reused = 7425 3.13.860.774 I slot print_timing: id 0 | task 7749 | graph reallocs = 0 / 0 (same size) / (changed size) 3.13.860.799 I slot release: id 0 | task 7749 | stop processing: n_tokens = 443, truncated = 0 3.13.866.517 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.106 (> 0.100 thold), f_keep = 0.084 3.13.871.837 I slot launch_slot_: id 0 | task 7817 | processing task, is_child = 0 3.16.011.284 I slot print_timing: id 0 | task 7817 | prompt eval time = 784.11 ms / 348 tokens ( 2.25 ms per token, 443.81 tokens per second) 3.16.011.287 I slot print_timing: id 0 | task 7817 | eval time = 1355.32 ms / 72 tokens ( 19.09 ms per token, 52.39 tokens per second) 3.16.011.288 I slot print_timing: id 0 | task 7817 | total time = 2139.44 ms / 420 tokens 3.16.011.288 I slot print_timing: id 0 | task 7817 | graphs reused = 7495 3.16.011.289 I slot print_timing: id 0 | task 7817 | graph reallocs = 0 / 0 (same size) / (changed size) 3.16.011.315 I slot release: id 0 | task 7817 | stop processing: n_tokens = 419, truncated = 0 3.16.017.780 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 350250196893 3.16.026.013 I slot launch_slot_: id 0 | task 7892 | processing task, is_child = 0 3.18.624.708 I slot print_timing: id 0 | task 7892 | prompt eval time = 854.44 ms / 425 tokens ( 2.01 ms per token, 497.40 tokens per second) 3.18.624.714 I slot print_timing: id 0 | task 7892 | eval time = 1744.24 ms / 92 tokens ( 19.17 ms per token, 52.17 tokens per second) 3.18.624.715 I slot print_timing: id 0 | task 7892 | total time = 2598.69 ms / 517 tokens 3.18.624.716 I slot print_timing: id 0 | task 7892 | graphs reused = 7584 3.18.624.716 I slot print_timing: id 0 | task 7892 | graph reallocs = 0 / 0 (same size) / (changed size) 3.18.624.748 I slot release: id 0 | task 7892 | stop processing: n_tokens = 516, truncated = 0 3.18.630.300 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 516, t_last = 350252810327 3.18.639.963 I slot launch_slot_: id 0 | task 7987 | processing task, is_child = 0 3.22.440.372 I slot print_timing: id 0 | task 7987 | n_gen = 158, tg = 52.32 t/s, tg_3s = 52.65 t/s 3.22.803.918 I slot print_timing: id 0 | task 7987 | prompt eval time = 799.59 ms / 371 tokens ( 2.16 ms per token, 463.99 tokens per second) 3.22.803.924 I slot print_timing: id 0 | task 7987 | eval time = 3364.36 ms / 177 tokens ( 19.12 ms per token, 52.31 tokens per second) 3.22.803.925 I slot print_timing: id 0 | task 7987 | total time = 4163.95 ms / 548 tokens 3.22.803.925 I slot print_timing: id 0 | task 7987 | graphs reused = 7758 3.22.803.926 I slot print_timing: id 0 | task 7987 | graph reallocs = 0 / 0 (same size) / (changed size) 3.22.803.952 I slot release: id 0 | task 7987 | stop processing: n_tokens = 547, truncated = 0 3.22.809.317 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.121 (> 0.100 thold), f_keep = 0.068 3.22.815.590 I slot launch_slot_: id 0 | task 8167 | processing task, is_child = 0 3.24.838.417 I slot print_timing: id 0 | task 8167 | prompt eval time = 726.07 ms / 306 tokens ( 2.37 ms per token, 421.45 tokens per second) 3.24.838.424 I slot print_timing: id 0 | task 8167 | eval time = 1296.75 ms / 69 tokens ( 19.07 ms per token, 52.44 tokens per second) 3.24.838.424 I slot print_timing: id 0 | task 8167 | total time = 2022.82 ms / 375 tokens 3.24.838.425 I slot print_timing: id 0 | task 8167 | graphs reused = 7825 3.24.838.426 I slot print_timing: id 0 | task 8167 | graph reallocs = 0 / 0 (same size) / (changed size) 3.24.838.449 I slot release: id 0 | task 8167 | stop processing: n_tokens = 374, truncated = 0 3.24.844.219 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 374, t_last = 350259024027 3.24.851.409 I slot launch_slot_: id 0 | task 8239 | processing task, is_child = 0 3.27.559.062 I slot print_timing: id 0 | task 8239 | prompt eval time = 834.40 ms / 397 tokens ( 2.10 ms per token, 475.79 tokens per second) 3.27.559.069 I slot print_timing: id 0 | task 8239 | eval time = 1873.24 ms / 99 tokens ( 19.11 ms per token, 52.32 tokens per second) 3.27.559.069 I slot print_timing: id 0 | task 8239 | total time = 2707.64 ms / 496 tokens 3.27.559.070 I slot print_timing: id 0 | task 8239 | graphs reused = 7922 3.27.559.070 I slot print_timing: id 0 | task 8239 | graph reallocs = 0 / 0 (same size) / (changed size) 3.27.559.101 I slot release: id 0 | task 8239 | stop processing: n_tokens = 495, truncated = 0 3.27.564.522 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.110 (> 0.100 thold), f_keep = 0.075 3.27.573.862 I slot launch_slot_: id 0 | task 8341 | processing task, is_child = 0 3.29.820.855 I slot print_timing: id 0 | task 8341 | prompt eval time = 758.03 ms / 337 tokens ( 2.25 ms per token, 444.57 tokens per second) 3.29.820.861 I slot print_timing: id 0 | task 8341 | eval time = 1488.95 ms / 79 tokens ( 19.09 ms per token, 52.39 tokens per second) 3.29.820.861 I slot print_timing: id 0 | task 8341 | total time = 2246.98 ms / 416 tokens 3.29.820.862 I slot print_timing: id 0 | task 8341 | graphs reused = 7999 3.29.820.863 I slot print_timing: id 0 | task 8341 | graph reallocs = 0 / 0 (same size) / (changed size) 3.29.820.887 I slot release: id 0 | task 8341 | stop processing: n_tokens = 415, truncated = 0 3.29.826.246 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.121 (> 0.100 thold), f_keep = 0.089 3.29.832.758 I slot launch_slot_: id 0 | task 8423 | processing task, is_child = 0 3.32.359.906 I slot print_timing: id 0 | task 8423 | prompt eval time = 721.02 ms / 305 tokens ( 2.36 ms per token, 423.01 tokens per second) 3.32.359.913 I slot print_timing: id 0 | task 8423 | eval time = 1806.12 ms / 96 tokens ( 19.01 ms per token, 52.60 tokens per second) 3.32.359.913 I slot print_timing: id 0 | task 8423 | total time = 2527.14 ms / 401 tokens 3.32.359.914 I slot print_timing: id 0 | task 8423 | graphs reused = 8093 3.32.359.914 I slot print_timing: id 0 | task 8423 | graph reallocs = 0 / 0 (same size) / (changed size) 3.32.359.939 I slot release: id 0 | task 8423 | stop processing: n_tokens = 400, truncated = 0 3.32.365.196 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.112 (> 0.100 thold), f_keep = 0.093 3.32.372.611 I slot launch_slot_: id 0 | task 8522 | processing task, is_child = 0 3.34.331.340 I slot print_timing: id 0 | task 8522 | prompt eval time = 737.43 ms / 329 tokens ( 2.24 ms per token, 446.15 tokens per second) 3.34.331.346 I slot print_timing: id 0 | task 8522 | eval time = 1221.29 ms / 65 tokens ( 19.08 ms per token, 52.40 tokens per second) 3.34.331.347 I slot print_timing: id 0 | task 8522 | total time = 1958.72 ms / 394 tokens 3.34.331.347 I slot print_timing: id 0 | task 8522 | graphs reused = 8156 3.34.331.348 I slot print_timing: id 0 | task 8522 | graph reallocs = 0 / 0 (same size) / (changed size) 3.34.331.372 I slot release: id 0 | task 8522 | stop processing: n_tokens = 393, truncated = 0 3.34.336.539 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.118 (> 0.100 thold), f_keep = 0.094 3.34.344.361 I slot launch_slot_: id 0 | task 8590 | processing task, is_child = 0 3.36.341.218 I slot print_timing: id 0 | task 8590 | prompt eval time = 737.54 ms / 313 tokens ( 2.36 ms per token, 424.38 tokens per second) 3.36.341.224 I slot print_timing: id 0 | task 8590 | eval time = 1259.31 ms / 67 tokens ( 19.08 ms per token, 52.41 tokens per second) 3.36.341.225 I slot print_timing: id 0 | task 8590 | total time = 1996.85 ms / 380 tokens 3.36.341.226 I slot print_timing: id 0 | task 8590 | graphs reused = 8221 3.36.341.226 I slot print_timing: id 0 | task 8590 | graph reallocs = 0 / 0 (same size) / (changed size) 3.36.341.250 I slot release: id 0 | task 8590 | stop processing: n_tokens = 379, truncated = 0 3.36.347.348 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 379, t_last = 350270526828 3.36.354.759 I slot launch_slot_: id 0 | task 8660 | processing task, is_child = 0 3.39.651.878 I slot print_timing: id 0 | task 8660 | prompt eval time = 958.00 ms / 467 tokens ( 2.05 ms per token, 487.47 tokens per second) 3.39.651.884 I slot print_timing: id 0 | task 8660 | eval time = 2339.11 ms / 123 tokens ( 19.17 ms per token, 52.16 tokens per second) 3.39.651.885 I slot print_timing: id 0 | task 8660 | total time = 3297.11 ms / 590 tokens 3.39.651.885 I slot print_timing: id 0 | task 8660 | graphs reused = 8341 3.39.651.886 I slot print_timing: id 0 | task 8660 | graph reallocs = 0 / 0 (same size) / (changed size) 3.39.651.920 I slot release: id 0 | task 8660 | stop processing: n_tokens = 589, truncated = 0 3.39.657.767 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.106 (> 0.100 thold), f_keep = 0.063 3.39.669.109 I slot launch_slot_: id 0 | task 8786 | processing task, is_child = 0 3.41.636.821 I slot print_timing: id 0 | task 8786 | prompt eval time = 818.41 ms / 348 tokens ( 2.35 ms per token, 425.21 tokens per second) 3.41.636.826 I slot print_timing: id 0 | task 8786 | eval time = 1149.29 ms / 61 tokens ( 19.15 ms per token, 52.21 tokens per second) 3.41.636.826 I slot print_timing: id 0 | task 8786 | total time = 1967.70 ms / 409 tokens 3.41.636.827 I slot print_timing: id 0 | task 8786 | graphs reused = 8400 3.41.636.828 I slot print_timing: id 0 | task 8786 | graph reallocs = 0 / 0 (same size) / (changed size) 3.41.636.853 I slot release: id 0 | task 8786 | stop processing: n_tokens = 408, truncated = 0 3.41.644.244 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 408, t_last = 350275822431 3.41.649.337 I slot launch_slot_: id 0 | task 8850 | processing task, is_child = 0 3.45.542.984 I slot print_timing: id 0 | task 8850 | prompt eval time = 1590.92 ms / 690 tokens ( 2.31 ms per token, 433.71 tokens per second) 3.45.542.990 I slot print_timing: id 0 | task 8850 | eval time = 2302.72 ms / 121 tokens ( 19.19 ms per token, 52.11 tokens per second) 3.45.542.991 I slot print_timing: id 0 | task 8850 | total time = 3893.64 ms / 811 tokens 3.45.542.992 I slot print_timing: id 0 | task 8850 | graphs reused = 8518 3.45.542.992 I slot print_timing: id 0 | task 8850 | graph reallocs = 0 / 0 (same size) / (changed size) 3.45.543.038 I slot release: id 0 | task 8850 | stop processing: n_tokens = 810, truncated = 0 3.45.548.513 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.113 (> 0.100 thold), f_keep = 0.046 3.45.560.907 I slot launch_slot_: id 0 | task 8975 | processing task, is_child = 0 3.47.414.411 I slot print_timing: id 0 | task 8975 | prompt eval time = 793.67 ms / 328 tokens ( 2.42 ms per token, 413.27 tokens per second) 3.47.414.416 I slot print_timing: id 0 | task 8975 | eval time = 1059.82 ms / 56 tokens ( 19.27 ms per token, 51.90 tokens per second) 3.47.414.416 I slot print_timing: id 0 | task 8975 | total time = 1853.49 ms / 384 tokens 3.47.414.417 I slot print_timing: id 0 | task 8975 | graphs reused = 8572 3.47.414.417 I slot print_timing: id 0 | task 8975 | graph reallocs = 0 / 0 (same size) / (changed size) 3.47.414.443 I slot release: id 0 | task 8975 | stop processing: n_tokens = 383, truncated = 0 3.47.421.083 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 383, t_last = 350281600021 3.47.425.992 I slot launch_slot_: id 0 | task 9034 | processing task, is_child = 0 3.49.964.965 I slot print_timing: id 0 | task 9034 | prompt eval time = 1119.85 ms / 532 tokens ( 2.10 ms per token, 475.07 tokens per second) 3.49.964.971 I slot print_timing: id 0 | task 9034 | eval time = 1419.11 ms / 75 tokens ( 19.18 ms per token, 52.15 tokens per second) 3.49.964.971 I slot print_timing: id 0 | task 9034 | total time = 2538.96 ms / 607 tokens 3.49.964.972 I slot print_timing: id 0 | task 9034 | graphs reused = 8645 3.49.964.972 I slot print_timing: id 0 | task 9034 | graph reallocs = 0 / 0 (same size) / (changed size) 3.49.965.008 I slot release: id 0 | task 9034 | stop processing: n_tokens = 606, truncated = 0 3.49.972.391 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 606, t_last = 350284150586 3.49.984.416 I slot launch_slot_: id 0 | task 9113 | processing task, is_child = 0 3.53.394.706 I slot print_timing: id 0 | task 9113 | prompt eval time = 1422.83 ms / 624 tokens ( 2.28 ms per token, 438.56 tokens per second) 3.53.394.712 I slot print_timing: id 0 | task 9113 | eval time = 1987.45 ms / 105 tokens ( 19.11 ms per token, 52.33 tokens per second) 3.53.394.713 I slot print_timing: id 0 | task 9113 | total time = 3410.28 ms / 729 tokens 3.53.394.714 I slot print_timing: id 0 | task 9113 | graphs reused = 8748 3.53.394.714 I slot print_timing: id 0 | task 9113 | graph reallocs = 0 / 0 (same size) / (changed size) 3.53.394.756 I slot release: id 0 | task 9113 | stop processing: n_tokens = 728, truncated = 0 3.53.400.777 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 728, t_last = 350287580335 3.53.412.880 I slot launch_slot_: id 0 | task 9222 | processing task, is_child = 0 3.56.160.490 I slot print_timing: id 0 | task 9222 | prompt eval time = 924.38 ms / 445 tokens ( 2.08 ms per token, 481.40 tokens per second) 3.56.160.493 I slot print_timing: id 0 | task 9222 | eval time = 1823.22 ms / 96 tokens ( 19.19 ms per token, 52.11 tokens per second) 3.56.160.494 I slot print_timing: id 0 | task 9222 | total time = 2747.60 ms / 541 tokens 3.56.160.495 I slot print_timing: id 0 | task 9222 | graphs reused = 8841 3.56.160.495 I slot print_timing: id 0 | task 9222 | graph reallocs = 0 / 0 (same size) / (changed size) 3.56.160.526 I slot release: id 0 | task 9222 | stop processing: n_tokens = 540, truncated = 0 3.56.166.023 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.111 (> 0.100 thold), f_keep = 0.069 3.56.172.409 I slot launch_slot_: id 0 | task 9321 | processing task, is_child = 0 3.58.745.465 I slot print_timing: id 0 | task 9321 | prompt eval time = 802.64 ms / 333 tokens ( 2.41 ms per token, 414.88 tokens per second) 3.58.745.471 I slot print_timing: id 0 | task 9321 | eval time = 1770.41 ms / 94 tokens ( 19.04 ms per token, 52.53 tokens per second) 3.58.745.472 I slot print_timing: id 0 | task 9321 | total time = 2573.04 ms / 427 tokens 3.58.745.473 I slot print_timing: id 0 | task 9321 | graphs reused = 8933 3.58.745.473 I slot print_timing: id 0 | task 9321 | graph reallocs = 0 / 0 (same size) / (changed size) 3.58.745.497 I slot release: id 0 | task 9321 | stop processing: n_tokens = 426, truncated = 0 3.58.751.908 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 350292931075 3.58.757.222 I slot launch_slot_: id 0 | task 9418 | processing task, is_child = 0 4.02.694.617 I slot print_timing: id 0 | task 9418 | n_gen = 158, tg = 52.26 t/s, tg_3s = 52.59 t/s 4.03.113.138 I slot print_timing: id 0 | task 9418 | prompt eval time = 933.28 ms / 474 tokens ( 1.97 ms per token, 507.88 tokens per second) 4.03.113.141 I slot print_timing: id 0 | task 9418 | eval time = 3422.62 ms / 180 tokens ( 19.12 ms per token, 52.30 tokens per second) 4.03.113.143 I slot print_timing: id 0 | task 9418 | total time = 4355.90 ms / 654 tokens 4.03.113.143 I slot print_timing: id 0 | task 9418 | graphs reused = 9110 4.03.113.144 I slot print_timing: id 0 | task 9418 | graph reallocs = 0 / 0 (same size) / (changed size) 4.03.113.177 I slot release: id 0 | task 9418 | stop processing: n_tokens = 653, truncated = 0 4.03.120.346 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 653, t_last = 350297298756 4.03.131.024 I slot launch_slot_: id 0 | task 9601 | processing task, is_child = 0 4.06.345.540 I slot print_timing: id 0 | task 9601 | prompt eval time = 1416.19 ms / 641 tokens ( 2.21 ms per token, 452.62 tokens per second) 4.06.345.546 I slot print_timing: id 0 | task 9601 | eval time = 1798.32 ms / 95 tokens ( 19.13 ms per token, 52.27 tokens per second) 4.06.345.546 I slot print_timing: id 0 | task 9601 | total time = 3214.51 ms / 736 tokens 4.06.345.547 I slot print_timing: id 0 | task 9601 | graphs reused = 9203 4.06.345.548 I slot print_timing: id 0 | task 9601 | graph reallocs = 0 / 0 (same size) / (changed size) 4.06.345.585 I slot release: id 0 | task 9601 | stop processing: n_tokens = 735, truncated = 0 4.06.351.725 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 735, t_last = 350300531163 4.06.365.224 I slot launch_slot_: id 0 | task 9700 | processing task, is_child = 0 4.08.948.633 I slot print_timing: id 0 | task 9700 | prompt eval time = 910.95 ms / 460 tokens ( 1.98 ms per token, 504.97 tokens per second) 4.08.948.640 I slot print_timing: id 0 | task 9700 | eval time = 1672.44 ms / 88 tokens ( 19.22 ms per token, 52.02 tokens per second) 4.08.948.641 I slot print_timing: id 0 | task 9700 | total time = 2583.40 ms / 548 tokens 4.08.948.641 I slot print_timing: id 0 | task 9700 | graphs reused = 9288 4.08.948.642 I slot print_timing: id 0 | task 9700 | graph reallocs = 0 / 0 (same size) / (changed size) 4.08.948.672 I slot release: id 0 | task 9700 | stop processing: n_tokens = 547, truncated = 0 4.08.954.722 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 547, t_last = 350303134251 4.08.961.226 I slot launch_slot_: id 0 | task 9791 | processing task, is_child = 0 4.12.863.098 I slot print_timing: id 0 | task 9791 | n_gen = 158, tg = 52.28 t/s, tg_3s = 52.61 t/s 4.14.310.508 I slot print_timing: id 0 | task 9791 | prompt eval time = 898.84 ms / 426 tokens ( 2.11 ms per token, 473.94 tokens per second) 4.14.310.514 I slot print_timing: id 0 | task 9791 | eval time = 4450.43 ms / 234 tokens ( 19.10 ms per token, 52.35 tokens per second) 4.14.310.515 I slot print_timing: id 0 | task 9791 | total time = 5349.27 ms / 660 tokens 4.14.310.515 I slot print_timing: id 0 | task 9791 | graphs reused = 9519 4.14.310.516 I slot print_timing: id 0 | task 9791 | graph reallocs = 0 / 0 (same size) / (changed size) 4.14.310.549 I slot release: id 0 | task 9791 | stop processing: n_tokens = 659, truncated = 0 4.14.315.930 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.117 (> 0.100 thold), f_keep = 0.056 4.14.323.508 I slot launch_slot_: id 0 | task 10028 | processing task, is_child = 0 4.16.585.908 I slot print_timing: id 0 | task 10028 | prompt eval time = 738.68 ms / 317 tokens ( 2.33 ms per token, 429.14 tokens per second) 4.16.585.914 I slot print_timing: id 0 | task 10028 | eval time = 1523.70 ms / 81 tokens ( 19.05 ms per token, 52.50 tokens per second) 4.16.585.915 I slot print_timing: id 0 | task 10028 | total time = 2262.39 ms / 398 tokens 4.16.585.915 I slot print_timing: id 0 | task 10028 | graphs reused = 9598 4.16.585.916 I slot print_timing: id 0 | task 10028 | graph reallocs = 0 / 0 (same size) / (changed size) 4.16.585.941 I slot release: id 0 | task 10028 | stop processing: n_tokens = 397, truncated = 0 4.16.591.375 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.104 (> 0.100 thold), f_keep = 0.093 4.16.593.828 I slot launch_slot_: id 0 | task 10112 | processing task, is_child = 0 4.19.456.072 I slot print_timing: id 0 | task 10112 | prompt eval time = 839.45 ms / 355 tokens ( 2.36 ms per token, 422.90 tokens per second) 4.19.456.077 I slot print_timing: id 0 | task 10112 | eval time = 2022.79 ms / 107 tokens ( 19.08 ms per token, 52.40 tokens per second) 4.19.456.077 I slot print_timing: id 0 | task 10112 | total time = 2862.24 ms / 462 tokens 4.19.456.078 I slot print_timing: id 0 | task 10112 | graphs reused = 9703 4.19.456.078 I slot print_timing: id 0 | task 10112 | graph reallocs = 0 / 0 (same size) / (changed size) 4.19.456.105 I slot release: id 0 | task 10112 | stop processing: n_tokens = 461, truncated = 0 4.19.462.030 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 461, t_last = 350313641683 4.19.469.268 I slot launch_slot_: id 0 | task 10222 | processing task, is_child = 0 4.22.217.044 I slot print_timing: id 0 | task 10222 | prompt eval time = 856.98 ms / 383 tokens ( 2.24 ms per token, 446.92 tokens per second) 4.22.217.050 I slot print_timing: id 0 | task 10222 | eval time = 1890.79 ms / 100 tokens ( 19.10 ms per token, 52.36 tokens per second) 4.22.217.050 I slot print_timing: id 0 | task 10222 | total time = 2747.77 ms / 483 tokens 4.22.217.051 I slot print_timing: id 0 | task 10222 | graphs reused = 9801 4.22.217.052 I slot print_timing: id 0 | task 10222 | graph reallocs = 0 / 0 (same size) / (changed size) 4.22.217.079 I slot release: id 0 | task 10222 | stop processing: n_tokens = 482, truncated = 0 4.22.223.316 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 482, t_last = 350316402657 4.22.232.308 I slot launch_slot_: id 0 | task 10325 | processing task, is_child = 0 4.25.187.665 I slot print_timing: id 0 | task 10325 | prompt eval time = 940.61 ms / 489 tokens ( 1.92 ms per token, 519.88 tokens per second) 4.25.187.669 I slot print_timing: id 0 | task 10325 | eval time = 2014.74 ms / 106 tokens ( 19.19 ms per token, 52.12 tokens per second) 4.25.187.669 I slot print_timing: id 0 | task 10325 | total time = 2955.35 ms / 595 tokens 4.25.187.670 I slot print_timing: id 0 | task 10325 | graphs reused = 9904 4.25.187.671 I slot print_timing: id 0 | task 10325 | graph reallocs = 0 / 0 (same size) / (changed size) 4.25.187.705 I slot release: id 0 | task 10325 | stop processing: n_tokens = 594, truncated = 0 4.25.193.670 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 594, t_last = 350319373283 4.25.204.683 I slot launch_slot_: id 0 | task 10434 | processing task, is_child = 0 4.27.354.019 I slot print_timing: id 0 | task 10434 | prompt eval time = 867.67 ms / 431 tokens ( 2.01 ms per token, 496.73 tokens per second) 4.27.354.023 I slot print_timing: id 0 | task 10434 | eval time = 1281.65 ms / 68 tokens ( 19.13 ms per token, 52.28 tokens per second) 4.27.354.024 I slot print_timing: id 0 | task 10434 | total time = 2149.32 ms / 499 tokens 4.27.354.024 I slot print_timing: id 0 | task 10434 | graphs reused = 9970 4.27.354.025 I slot print_timing: id 0 | task 10434 | graph reallocs = 0 / 0 (same size) / (changed size) 4.27.354.057 I slot release: id 0 | task 10434 | stop processing: n_tokens = 498, truncated = 0 4.27.361.747 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 498, t_last = 350321539635 4.27.373.422 I slot launch_slot_: id 0 | task 10505 | processing task, is_child = 0 4.30.431.872 I slot print_timing: id 0 | task 10505 | prompt eval time = 1395.66 ms / 648 tokens ( 2.15 ms per token, 464.30 tokens per second) 4.30.431.878 I slot print_timing: id 0 | task 10505 | eval time = 1662.78 ms / 88 tokens ( 19.11 ms per token, 52.32 tokens per second) 4.30.431.878 I slot print_timing: id 0 | task 10505 | total time = 3058.44 ms / 736 tokens 4.30.431.879 I slot print_timing: id 0 | task 10505 | graphs reused = 10056 4.30.431.879 I slot print_timing: id 0 | task 10505 | graph reallocs = 0 / 0 (same size) / (changed size) 4.30.431.916 I slot release: id 0 | task 10505 | stop processing: n_tokens = 735, truncated = 0 4.30.437.912 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 735, t_last = 350324617494 4.30.455.045 I slot launch_slot_: id 0 | task 10597 | processing task, is_child = 0 4.32.610.745 I slot print_timing: id 0 | task 10597 | prompt eval time = 890.66 ms / 436 tokens ( 2.04 ms per token, 489.53 tokens per second) 4.32.610.751 I slot print_timing: id 0 | task 10597 | eval time = 1265.03 ms / 67 tokens ( 19.17 ms per token, 52.17 tokens per second) 4.32.610.752 I slot print_timing: id 0 | task 10597 | total time = 2155.69 ms / 503 tokens 4.32.610.753 I slot print_timing: id 0 | task 10597 | graphs reused = 10121 4.32.610.753 I slot print_timing: id 0 | task 10597 | graph reallocs = 0 / 0 (same size) / (changed size) 4.32.610.783 I slot release: id 0 | task 10597 | stop processing: n_tokens = 502, truncated = 0 4.32.617.119 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 502, t_last = 350326796361 4.32.626.988 I slot launch_slot_: id 0 | task 10667 | processing task, is_child = 0 4.35.366.804 I slot print_timing: id 0 | task 10667 | prompt eval time = 936.72 ms / 475 tokens ( 1.97 ms per token, 507.09 tokens per second) 4.35.366.810 I slot print_timing: id 0 | task 10667 | eval time = 1803.08 ms / 95 tokens ( 19.18 ms per token, 52.13 tokens per second) 4.35.366.811 I slot print_timing: id 0 | task 10667 | total time = 2739.80 ms / 570 tokens 4.35.366.811 I slot print_timing: id 0 | task 10667 | graphs reused = 10213 4.35.366.812 I slot print_timing: id 0 | task 10667 | graph reallocs = 0 / 0 (same size) / (changed size) 4.35.366.845 I slot release: id 0 | task 10667 | stop processing: n_tokens = 569, truncated = 0 4.35.373.019 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 569, t_last = 350329552423 4.35.388.473 I slot launch_slot_: id 0 | task 10765 | processing task, is_child = 0 4.38.673.325 I slot print_timing: id 0 | task 10765 | prompt eval time = 890.04 ms / 441 tokens ( 2.02 ms per token, 495.48 tokens per second) 4.38.673.328 I slot print_timing: id 0 | task 10765 | eval time = 2394.80 ms / 126 tokens ( 19.16 ms per token, 52.20 tokens per second) 4.38.673.329 I slot print_timing: id 0 | task 10765 | total time = 3284.84 ms / 567 tokens 4.38.673.330 I slot print_timing: id 0 | task 10765 | graphs reused = 10336 4.38.673.330 I slot print_timing: id 0 | task 10765 | graph reallocs = 0 / 0 (same size) / (changed size) 4.38.673.363 I slot release: id 0 | task 10765 | stop processing: n_tokens = 566, truncated = 0 4.38.680.523 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 566, t_last = 350332858942 4.38.696.441 I slot launch_slot_: id 0 | task 10894 | processing task, is_child = 0 4.41.472.427 I slot print_timing: id 0 | task 10894 | prompt eval time = 1260.06 ms / 569 tokens ( 2.21 ms per token, 451.56 tokens per second) 4.41.472.433 I slot print_timing: id 0 | task 10894 | eval time = 1515.91 ms / 80 tokens ( 19.19 ms per token, 52.11 tokens per second) 4.41.472.433 I slot print_timing: id 0 | task 10894 | total time = 2775.97 ms / 649 tokens 4.41.472.434 I slot print_timing: id 0 | task 10894 | graphs reused = 10414 4.41.472.435 I slot print_timing: id 0 | task 10894 | graph reallocs = 0 / 0 (same size) / (changed size) 4.41.472.472 I slot release: id 0 | task 10894 | stop processing: n_tokens = 648, truncated = 0 4.41.479.747 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 648, t_last = 350335658050 4.41.496.504 I slot launch_slot_: id 0 | task 10978 | processing task, is_child = 0 4.45.968.677 I slot print_timing: id 0 | task 10978 | n_gen = 158, tg = 52.18 t/s, tg_3s = 52.51 t/s 4.46.103.425 I slot print_timing: id 0 | task 10978 | prompt eval time = 1463.10 ms / 646 tokens ( 2.26 ms per token, 441.53 tokens per second) 4.46.103.430 I slot print_timing: id 0 | task 10978 | eval time = 3143.81 ms / 165 tokens ( 19.17 ms per token, 52.17 tokens per second) 4.46.103.431 I slot print_timing: id 0 | task 10978 | total time = 4606.91 ms / 811 tokens 4.46.103.431 I slot print_timing: id 0 | task 10978 | graphs reused = 10576 4.46.103.432 I slot print_timing: id 0 | task 10978 | graph reallocs = 0 / 0 (same size) / (changed size) 4.46.103.472 I slot release: id 0 | task 10978 | stop processing: n_tokens = 810, truncated = 0 4.46.108.343 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.152 (> 0.100 thold), f_keep = 0.046 4.46.125.571 I slot launch_slot_: id 0 | task 11147 | processing task, is_child = 0 4.49.348.802 I slot print_timing: id 0 | task 11147 | prompt eval time = 697.29 ms / 244 tokens ( 2.86 ms per token, 349.93 tokens per second) 4.49.348.807 I slot print_timing: id 0 | task 11147 | eval time = 2525.93 ms / 134 tokens ( 18.99 ms per token, 52.65 tokens per second) 4.49.348.809 I slot print_timing: id 0 | task 11147 | total time = 3223.22 ms / 378 tokens 4.49.348.809 I slot print_timing: id 0 | task 11147 | graphs reused = 10707 4.49.348.810 I slot print_timing: id 0 | task 11147 | graph reallocs = 0 / 0 (same size) / (changed size) 4.49.348.831 I slot release: id 0 | task 11147 | stop processing: n_tokens = 377, truncated = 0 4.49.353.733 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.141 (> 0.100 thold), f_keep = 0.098 4.49.360.976 I slot launch_slot_: id 0 | task 11284 | processing task, is_child = 0 4.52.582.796 I slot print_timing: id 0 | task 11284 | prompt eval time = 774.01 ms / 263 tokens ( 2.94 ms per token, 339.79 tokens per second) 4.52.582.802 I slot print_timing: id 0 | task 11284 | eval time = 2447.80 ms / 130 tokens ( 18.98 ms per token, 52.70 tokens per second) 4.52.582.802 I slot print_timing: id 0 | task 11284 | total time = 3221.81 ms / 393 tokens 4.52.582.803 I slot print_timing: id 0 | task 11284 | graphs reused = 10835 4.52.582.804 I slot print_timing: id 0 | task 11284 | graph reallocs = 0 / 0 (same size) / (changed size) 4.52.582.825 I slot release: id 0 | task 11284 | stop processing: n_tokens = 392, truncated = 0 4.52.587.603 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.149 (> 0.100 thold), f_keep = 0.094 4.52.594.896 I slot launch_slot_: id 0 | task 11417 | processing task, is_child = 0 4.56.320.735 I slot print_timing: id 0 | task 11417 | n_gen = 159, tg = 52.45 t/s, tg_3s = 52.79 t/s 4.56.453.554 I slot print_timing: id 0 | task 11417 | prompt eval time = 713.69 ms / 248 tokens ( 2.88 ms per token, 347.49 tokens per second) 4.56.453.559 I slot print_timing: id 0 | task 11417 | eval time = 3144.95 ms / 166 tokens ( 19.06 ms per token, 52.47 tokens per second) 4.56.453.560 I slot print_timing: id 0 | task 11417 | total time = 3858.65 ms / 414 tokens 4.56.453.561 I slot print_timing: id 0 | task 11417 | graphs reused = 10998 4.56.453.561 I slot print_timing: id 0 | task 11417 | graph reallocs = 0 / 0 (same size) / (changed size) 4.56.453.583 I slot release: id 0 | task 11417 | stop processing: n_tokens = 413, truncated = 0 4.56.458.344 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.169 (> 0.100 thold), f_keep = 0.090 4.56.467.701 I slot launch_slot_: id 0 | task 11586 | processing task, is_child = 0 4.59.501.979 I slot print_timing: id 0 | task 11586 | prompt eval time = 661.96 ms / 219 tokens ( 3.02 ms per token, 330.83 tokens per second) 4.59.501.986 I slot print_timing: id 0 | task 11586 | eval time = 2372.31 ms / 126 tokens ( 18.98 ms per token, 52.69 tokens per second) 4.59.501.987 I slot print_timing: id 0 | task 11586 | total time = 3034.27 ms / 345 tokens 4.59.501.987 I slot print_timing: id 0 | task 11586 | graphs reused = 11121 4.59.501.988 I slot print_timing: id 0 | task 11586 | graph reallocs = 0 / 0 (same size) / (changed size) 4.59.502.009 I slot release: id 0 | task 11586 | stop processing: n_tokens = 344, truncated = 0 4.59.507.240 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.128 (> 0.100 thold), f_keep = 0.108 4.59.510.344 I slot launch_slot_: id 0 | task 11715 | processing task, is_child = 0 5.03.265.298 I slot print_timing: id 0 | task 11715 | n_gen = 159, tg = 52.56 t/s, tg_3s = 52.90 t/s 5.03.971.630 I slot print_timing: id 0 | task 11715 | prompt eval time = 749.11 ms / 288 tokens ( 2.60 ms per token, 384.46 tokens per second) 5.03.971.636 I slot print_timing: id 0 | task 11715 | eval time = 3712.17 ms / 196 tokens ( 19.04 ms per token, 52.53 tokens per second) 5.03.971.637 I slot print_timing: id 0 | task 11715 | total time = 4461.27 ms / 484 tokens 5.03.971.638 I slot print_timing: id 0 | task 11715 | graphs reused = 11315 5.03.971.638 I slot print_timing: id 0 | task 11715 | graph reallocs = 0 / 0 (same size) / (changed size) 5.03.971.662 I slot release: id 0 | task 11715 | stop processing: n_tokens = 483, truncated = 0 5.03.976.838 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.129 (> 0.100 thold), f_keep = 0.077 5.03.988.947 I slot launch_slot_: id 0 | task 11914 | processing task, is_child = 0 5.07.425.971 I slot print_timing: id 0 | task 11914 | prompt eval time = 811.73 ms / 286 tokens ( 2.84 ms per token, 352.34 tokens per second) 5.07.425.975 I slot print_timing: id 0 | task 11914 | eval time = 2625.29 ms / 139 tokens ( 19.02 ms per token, 52.57 tokens per second) 5.07.425.976 I slot print_timing: id 0 | task 11914 | total time = 3437.01 ms / 425 tokens 5.07.425.976 I slot print_timing: id 0 | task 11914 | graphs reused = 11452 5.07.425.977 I slot print_timing: id 0 | task 11914 | graph reallocs = 0 / 0 (same size) / (changed size) 5.07.426.001 I slot release: id 0 | task 11914 | stop processing: n_tokens = 424, truncated = 0 5.07.431.468 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.106 (> 0.100 thold), f_keep = 0.092 5.07.441.515 I slot launch_slot_: id 0 | task 12056 | processing task, is_child = 0 5.11.381.661 I slot print_timing: id 0 | task 12056 | n_gen = 159, tg = 52.35 t/s, tg_3s = 52.68 t/s 5.12.891.726 I slot print_timing: id 0 | task 12056 | prompt eval time = 921.88 ms / 368 tokens ( 2.51 ms per token, 399.18 tokens per second) 5.12.891.732 I slot print_timing: id 0 | task 12056 | eval time = 4528.32 ms / 238 tokens ( 19.11 ms per token, 52.34 tokens per second) 5.12.891.733 I slot print_timing: id 0 | task 12056 | total time = 5450.20 ms / 606 tokens 5.12.891.733 I slot print_timing: id 0 | task 12056 | graphs reused = 11687 5.12.891.734 I slot print_timing: id 0 | task 12056 | graph reallocs = 0 / 0 (same size) / (changed size) 5.12.891.769 I slot release: id 0 | task 12056 | stop processing: n_tokens = 605, truncated = 0 5.12.896.611 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.164 (> 0.100 thold), f_keep = 0.061 5.12.896.685 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 56.506 MiB) 5.12.896.693 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 45.157 MiB) 5.12.907.228 I slot launch_slot_: id 0 | task 12297 | processing task, is_child = 0 5.16.645.197 I slot print_timing: id 0 | task 12297 | n_gen = 159, tg = 52.65 t/s, tg_3s = 52.98 t/s 5.17.102.408 I slot print_timing: id 0 | task 12297 | prompt eval time = 737.09 ms / 226 tokens ( 3.26 ms per token, 306.61 tokens per second) 5.17.102.414 I slot print_timing: id 0 | task 12297 | eval time = 3458.08 ms / 183 tokens ( 19.00 ms per token, 52.63 tokens per second) 5.17.102.415 I slot print_timing: id 0 | task 12297 | total time = 4195.17 ms / 409 tokens 5.17.102.415 I slot print_timing: id 0 | task 12297 | graphs reused = 11867 5.17.102.416 I slot print_timing: id 0 | task 12297 | graph reallocs = 0 / 0 (same size) / (changed size) 5.17.102.441 I slot release: id 0 | task 12297 | stop processing: n_tokens = 408, truncated = 0 5.17.107.295 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.162 (> 0.100 thold), f_keep = 0.091 5.17.107.354 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 55.440 MiB) 5.17.114.818 I slot launch_slot_: id 0 | task 12483 | processing task, is_child = 0 5.20.865.499 I slot print_timing: id 0 | task 12483 | n_gen = 159, tg = 52.63 t/s, tg_3s = 52.96 t/s 5.23.631.257 I slot print_timing: id 0 | task 12483 | prompt eval time = 748.59 ms / 229 tokens ( 3.27 ms per token, 305.91 tokens per second) 5.23.631.260 I slot print_timing: id 0 | task 12483 | eval time = 5767.83 ms / 304 tokens ( 19.04 ms per token, 52.53 tokens per second) 5.23.631.261 I slot print_timing: id 0 | task 12483 | total time = 6516.43 ms / 533 tokens 5.23.631.261 I slot print_timing: id 0 | task 12483 | graphs reused = 12167 5.23.631.262 I slot print_timing: id 0 | task 12483 | graph reallocs = 0 / 0 (same size) / (changed size) 5.23.631.290 I slot release: id 0 | task 12483 | stop processing: n_tokens = 532, truncated = 0 5.23.636.445 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.130 (> 0.100 thold), f_keep = 0.070 5.23.636.518 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 64.192 MiB) 5.23.646.272 I slot launch_slot_: id 0 | task 12790 | processing task, is_child = 0 5.27.492.244 I slot print_timing: id 0 | task 12790 | n_gen = 159, tg = 52.61 t/s, tg_3s = 52.95 t/s 5.28.388.421 I slot print_timing: id 0 | task 12790 | prompt eval time = 842.90 ms / 285 tokens ( 2.96 ms per token, 338.12 tokens per second) 5.28.388.428 I slot print_timing: id 0 | task 12790 | eval time = 3899.23 ms / 206 tokens ( 19.02 ms per token, 52.57 tokens per second) 5.28.388.428 I slot print_timing: id 0 | task 12790 | total time = 4742.13 ms / 491 tokens 5.28.388.429 I slot print_timing: id 0 | task 12790 | graphs reused = 12371 5.28.388.430 I slot print_timing: id 0 | task 12790 | graph reallocs = 0 / 0 (same size) / (changed size) 5.28.388.453 I slot release: id 0 | task 12790 | stop processing: n_tokens = 490, truncated = 0 5.28.393.725 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.110 (> 0.100 thold), f_keep = 0.076 5.28.393.789 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 61.088 MiB) 5.28.393.795 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 59.515 MiB) 5.28.402.731 I slot launch_slot_: id 0 | task 12999 | processing task, is_child = 0 5.31.312.601 I slot print_timing: id 0 | task 12999 | prompt eval time = 956.20 ms / 337 tokens ( 2.84 ms per token, 352.44 tokens per second) 5.31.312.604 I slot print_timing: id 0 | task 12999 | eval time = 1953.65 ms / 103 tokens ( 19.15 ms per token, 52.21 tokens per second) 5.31.312.606 I slot print_timing: id 0 | task 12999 | total time = 2909.86 ms / 440 tokens 5.31.312.606 I slot print_timing: id 0 | task 12999 | graphs reused = 12472 5.31.312.607 I slot print_timing: id 0 | task 12999 | graph reallocs = 0 / 0 (same size) / (changed size) 5.31.312.637 I slot release: id 0 | task 12999 | stop processing: n_tokens = 439, truncated = 0 5.31.317.685 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.179 (> 0.100 thold), f_keep = 0.118 5.31.317.757 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 72.602 MiB) 5.31.326.301 I slot launch_slot_: id 0 | task 13105 | processing task, is_child = 0 5.33.763.245 I slot print_timing: id 0 | task 13105 | prompt eval time = 876.16 ms / 290 tokens ( 3.02 ms per token, 330.99 tokens per second) 5.33.763.249 I slot print_timing: id 0 | task 13105 | eval time = 1560.77 ms / 83 tokens ( 19.03 ms per token, 52.54 tokens per second) 5.33.763.250 I slot print_timing: id 0 | task 13105 | total time = 2436.93 ms / 373 tokens 5.33.763.251 I slot print_timing: id 0 | task 13105 | graphs reused = 12553 5.33.763.251 I slot print_timing: id 0 | task 13105 | graph reallocs = 0 / 0 (same size) / (changed size) 5.33.763.278 I slot release: id 0 | task 13105 | stop processing: n_tokens = 372, truncated = 0 5.33.768.338 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.128 (> 0.100 thold), f_keep = 0.099 5.33.768.393 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 86.276 MiB) 5.33.770.490 I slot launch_slot_: id 0 | task 13191 | processing task, is_child = 0 5.37.618.051 I slot print_timing: id 0 | task 13191 | n_gen = 159, tg = 52.58 t/s, tg_3s = 52.91 t/s 5.40.618.809 I slot print_timing: id 0 | task 13191 | n_gen = 316, tg = 52.45 t/s, tg_3s = 52.32 t/s 5.42.241.094 I slot print_timing: id 0 | task 13191 | prompt eval time = 842.42 ms / 290 tokens ( 2.90 ms per token, 344.25 tokens per second) 5.42.241.098 I slot print_timing: id 0 | task 13191 | eval time = 7628.17 ms / 401 tokens ( 19.07 ms per token, 52.44 tokens per second) 5.42.241.098 I slot print_timing: id 0 | task 13191 | total time = 8470.59 ms / 691 tokens 5.42.241.099 I slot print_timing: id 0 | task 13191 | graphs reused = 12951 5.42.241.100 I slot print_timing: id 0 | task 13191 | graph reallocs = 0 / 0 (same size) / (changed size) 5.42.241.124 I slot release: id 0 | task 13191 | stop processing: n_tokens = 690, truncated = 0 5.42.246.320 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.124 (> 0.100 thold), f_keep = 0.054 5.42.246.405 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 56.343 MiB) 5.42.257.418 I slot launch_slot_: id 0 | task 13595 | processing task, is_child = 0 5.46.128.251 I slot print_timing: id 0 | task 13595 | n_gen = 159, tg = 52.54 t/s, tg_3s = 52.87 t/s 5.46.621.973 I slot print_timing: id 0 | task 13595 | prompt eval time = 863.69 ms / 299 tokens ( 2.89 ms per token, 346.19 tokens per second) 5.46.621.980 I slot print_timing: id 0 | task 13595 | eval time = 3500.86 ms / 185 tokens ( 19.03 ms per token, 52.56 tokens per second) 5.46.621.981 I slot print_timing: id 0 | task 13595 | total time = 4364.55 ms / 484 tokens 5.46.621.981 I slot print_timing: id 0 | task 13595 | graphs reused = 13134 5.46.621.982 I slot print_timing: id 0 | task 13595 | graph reallocs = 0 / 0 (same size) / (changed size) 5.46.622.006 I slot release: id 0 | task 13595 | stop processing: n_tokens = 483, truncated = 0 5.46.626.582 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.154 (> 0.100 thold), f_keep = 0.077 5.46.626.646 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 61.443 MiB) 5.46.635.717 I slot launch_slot_: id 0 | task 13783 | processing task, is_child = 0 5.50.389.603 I slot print_timing: id 0 | task 13783 | n_gen = 159, tg = 52.60 t/s, tg_3s = 52.93 t/s 5.51.189.097 I slot print_timing: id 0 | task 13783 | prompt eval time = 750.15 ms / 241 tokens ( 3.11 ms per token, 321.27 tokens per second) 5.51.189.102 I slot print_timing: id 0 | task 13783 | eval time = 3803.22 ms / 201 tokens ( 19.02 ms per token, 52.59 tokens per second) 5.51.189.103 I slot print_timing: id 0 | task 13783 | total time = 4553.37 ms / 442 tokens 5.51.189.104 I slot print_timing: id 0 | task 13783 | graphs reused = 13332 5.51.189.104 I slot print_timing: id 0 | task 13783 | graph reallocs = 0 / 0 (same size) / (changed size) 5.51.189.127 I slot release: id 0 | task 13783 | stop processing: n_tokens = 441, truncated = 0 5.51.194.262 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.115 (> 0.100 thold), f_keep = 0.084 5.51.194.323 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 61.607 MiB) 5.51.196.570 I slot launch_slot_: id 0 | task 13987 | processing task, is_child = 0 5.54.848.554 I slot print_timing: id 0 | task 13987 | prompt eval time = 908.32 ms / 323 tokens ( 2.81 ms per token, 355.60 tokens per second) 5.54.848.560 I slot print_timing: id 0 | task 13987 | eval time = 2743.66 ms / 145 tokens ( 19.05 ms per token, 52.48 tokens per second) 5.54.848.561 I slot print_timing: id 0 | task 13987 | total time = 3651.98 ms / 468 tokens 5.54.848.561 I slot print_timing: id 0 | task 13987 | graphs reused = 13475 5.54.848.562 I slot print_timing: id 0 | task 13987 | graph reallocs = 0 / 0 (same size) / (changed size) 5.54.848.587 I slot release: id 0 | task 13987 | stop processing: n_tokens = 467, truncated = 0 5.54.853.454 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.079 5.54.853.516 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 67.788 MiB) 5.54.853.520 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 60.253 MiB) 5.54.862.284 I slot launch_slot_: id 0 | task 14135 | processing task, is_child = 0 5.58.630.335 I slot print_timing: id 0 | task 14135 | n_gen = 159, tg = 52.59 t/s, tg_3s = 52.92 t/s 6.01.645.436 I slot print_timing: id 0 | task 14135 | n_gen = 317, tg = 52.50 t/s, tg_3s = 52.40 t/s 6.02.981.695 I slot print_timing: id 0 | task 14135 | prompt eval time = 763.69 ms / 237 tokens ( 3.22 ms per token, 310.33 tokens per second) 6.02.981.698 I slot print_timing: id 0 | task 14135 | eval time = 7355.71 ms / 387 tokens ( 19.06 ms per token, 52.48 tokens per second) 6.02.981.699 I slot print_timing: id 0 | task 14135 | total time = 8119.40 ms / 624 tokens 6.02.981.700 I slot print_timing: id 0 | task 14135 | graphs reused = 13858 6.02.981.700 I slot print_timing: id 0 | task 14135 | graph reallocs = 0 / 0 (same size) / (changed size) 6.02.981.722 I slot release: id 0 | task 14135 | stop processing: n_tokens = 623, truncated = 0 6.02.986.549 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.059 6.02.986.625 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 59.857 MiB) 6.02.996.559 I slot launch_slot_: id 0 | task 14525 | processing task, is_child = 0 6.06.060.655 I slot print_timing: id 0 | task 14525 | prompt eval time = 648.23 ms / 217 tokens ( 2.99 ms per token, 334.76 tokens per second) 6.06.060.661 I slot print_timing: id 0 | task 14525 | eval time = 2415.85 ms / 128 tokens ( 19.02 ms per token, 52.57 tokens per second) 6.06.060.662 I slot print_timing: id 0 | task 14525 | total time = 3064.09 ms / 345 tokens 6.06.060.662 I slot print_timing: id 0 | task 14525 | graphs reused = 13983 6.06.060.663 I slot print_timing: id 0 | task 14525 | graph reallocs = 0 / 0 (same size) / (changed size) 6.06.060.683 I slot release: id 0 | task 14525 | stop processing: n_tokens = 344, truncated = 0 6.06.065.653 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.121 (> 0.100 thold), f_keep = 0.108 6.06.065.710 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 59.365 MiB) 6.06.067.648 I slot launch_slot_: id 0 | task 14656 | processing task, is_child = 0 6.09.948.219 I slot print_timing: id 0 | task 14656 | n_gen = 159, tg = 52.64 t/s, tg_3s = 52.97 t/s 6.10.884.459 I slot print_timing: id 0 | task 14656 | prompt eval time = 878.85 ms / 306 tokens ( 2.87 ms per token, 348.18 tokens per second) 6.10.884.465 I slot print_timing: id 0 | task 14656 | eval time = 3937.95 ms / 208 tokens ( 19.02 ms per token, 52.57 tokens per second) 6.10.884.466 I slot print_timing: id 0 | task 14656 | total time = 4816.80 ms / 514 tokens 6.10.884.467 I slot print_timing: id 0 | task 14656 | graphs reused = 14188 6.10.884.467 I slot print_timing: id 0 | task 14656 | graph reallocs = 0 / 0 (same size) / (changed size) 6.10.884.492 I slot release: id 0 | task 14656 | stop processing: n_tokens = 513, truncated = 0 6.10.889.363 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.149 (> 0.100 thold), f_keep = 0.072 6.10.889.431 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 54.373 MiB) 6.10.889.435 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 56.985 MiB) 6.10.898.880 I slot launch_slot_: id 0 | task 14867 | processing task, is_child = 0 6.14.687.163 I slot print_timing: id 0 | task 14867 | n_gen = 159, tg = 52.59 t/s, tg_3s = 52.92 t/s 6.14.743.952 I slot print_timing: id 0 | task 14867 | prompt eval time = 783.64 ms / 248 tokens ( 3.16 ms per token, 316.47 tokens per second) 6.14.743.955 I slot print_timing: id 0 | task 14867 | eval time = 3061.42 ms / 162 tokens ( 19.02 ms per token, 52.59 tokens per second) 6.14.743.956 I slot print_timing: id 0 | task 14867 | total time = 3845.06 ms / 410 tokens 6.14.743.957 I slot print_timing: id 0 | task 14867 | graphs reused = 14347 6.14.743.957 I slot print_timing: id 0 | task 14867 | graph reallocs = 0 / 0 (same size) / (changed size) 6.14.743.982 I slot release: id 0 | task 14867 | stop processing: n_tokens = 409, truncated = 0 6.14.749.056 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.115 (> 0.100 thold), f_keep = 0.090 6.14.749.114 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 55.358 MiB) 6.14.756.638 I slot launch_slot_: id 0 | task 15032 | processing task, is_child = 0 6.18.660.415 I slot print_timing: id 0 | task 15032 | n_gen = 159, tg = 52.46 t/s, tg_3s = 52.79 t/s 6.20.361.588 I slot print_timing: id 0 | task 15032 | prompt eval time = 891.99 ms / 322 tokens ( 2.77 ms per token, 360.99 tokens per second) 6.20.361.594 I slot print_timing: id 0 | task 15032 | eval time = 4712.95 ms / 248 tokens ( 19.08 ms per token, 52.41 tokens per second) 6.20.361.595 I slot print_timing: id 0 | task 15032 | total time = 5604.94 ms / 570 tokens 6.20.361.595 I slot print_timing: id 0 | task 15032 | graphs reused = 14592 6.20.361.596 I slot print_timing: id 0 | task 15032 | graph reallocs = 0 / 0 (same size) / (changed size) 6.20.361.621 I slot release: id 0 | task 15032 | stop processing: n_tokens = 569, truncated = 0 6.20.366.732 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.137 (> 0.100 thold), f_keep = 0.067 6.20.366.814 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 52.076 MiB) 6.20.377.263 I slot launch_slot_: id 0 | task 15283 | processing task, is_child = 0 6.23.688.006 I slot print_timing: id 0 | task 15283 | prompt eval time = 858.75 ms / 278 tokens ( 3.09 ms per token, 323.73 tokens per second) 6.23.688.010 I slot print_timing: id 0 | task 15283 | eval time = 2451.98 ms / 130 tokens ( 19.01 ms per token, 52.61 tokens per second) 6.23.688.011 I slot print_timing: id 0 | task 15283 | total time = 3310.73 ms / 408 tokens 6.23.688.011 I slot print_timing: id 0 | task 15283 | graphs reused = 14720 6.23.688.012 I slot print_timing: id 0 | task 15283 | graph reallocs = 0 / 0 (same size) / (changed size) 6.23.688.039 I slot release: id 0 | task 15283 | stop processing: n_tokens = 407, truncated = 0 6.23.693.269 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.109 (> 0.100 thold), f_keep = 0.091 6.23.693.327 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 60.130 MiB) 6.23.693.331 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 54.770 MiB) 6.23.701.031 I slot launch_slot_: id 0 | task 15416 | processing task, is_child = 0 6.27.510.482 I slot print_timing: id 0 | task 15416 | prompt eval time = 893.96 ms / 338 tokens ( 2.64 ms per token, 378.09 tokens per second) 6.27.510.486 I slot print_timing: id 0 | task 15416 | eval time = 2915.48 ms / 154 tokens ( 19.06 ms per token, 52.48 tokens per second) 6.27.510.487 I slot print_timing: id 0 | task 15416 | total time = 3809.44 ms / 492 tokens 6.27.510.487 I slot print_timing: id 0 | task 15416 | graphs reused = 14872 6.27.510.488 I slot print_timing: id 0 | task 15416 | graph reallocs = 0 / 0 (same size) / (changed size) 6.27.510.514 I slot release: id 0 | task 15416 | stop processing: n_tokens = 491, truncated = 0 6.27.515.767 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.109 (> 0.100 thold), f_keep = 0.075 6.27.515.835 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 67.870 MiB) 6.27.525.317 I slot launch_slot_: id 0 | task 15573 | processing task, is_child = 0 6.31.492.099 I slot print_timing: id 0 | task 15573 | n_gen = 159, tg = 52.46 t/s, tg_3s = 52.79 t/s 6.31.683.085 I slot print_timing: id 0 | task 15573 | prompt eval time = 954.98 ms / 338 tokens ( 2.83 ms per token, 353.93 tokens per second) 6.31.683.091 I slot print_timing: id 0 | task 15573 | eval time = 3202.78 ms / 169 tokens ( 19.06 ms per token, 52.45 tokens per second) 6.31.683.092 I slot print_timing: id 0 | task 15573 | total time = 4157.76 ms / 507 tokens 6.31.683.092 I slot print_timing: id 0 | task 15573 | graphs reused = 15039 6.31.683.093 I slot print_timing: id 0 | task 15573 | graph reallocs = 0 / 0 (same size) / (changed size) 6.31.683.117 I slot release: id 0 | task 15573 | stop processing: n_tokens = 506, truncated = 0 6.31.688.235 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.111 (> 0.100 thold), f_keep = 0.073 6.31.688.300 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 71.371 MiB) 6.31.697.849 I slot launch_slot_: id 0 | task 15745 | processing task, is_child = 0 6.35.634.346 I slot print_timing: id 0 | task 15745 | n_gen = 159, tg = 52.49 t/s, tg_3s = 52.82 t/s 6.38.577.948 I slot print_timing: id 0 | task 15745 | prompt eval time = 926.34 ms / 333 tokens ( 2.78 ms per token, 359.48 tokens per second) 6.38.577.952 I slot print_timing: id 0 | task 15745 | eval time = 5953.75 ms / 313 tokens ( 19.08 ms per token, 52.40 tokens per second) 6.38.577.952 I slot print_timing: id 0 | task 15745 | total time = 6880.09 ms / 646 tokens 6.38.577.953 I slot print_timing: id 0 | task 15745 | graphs reused = 15349 6.38.577.954 I slot print_timing: id 0 | task 15745 | graph reallocs = 0 / 0 (same size) / (changed size) 6.38.577.978 I slot release: id 0 | task 15745 | stop processing: n_tokens = 645, truncated = 0 6.38.583.001 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.129 (> 0.100 thold), f_keep = 0.057 6.38.583.075 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 93.117 MiB) 6.38.585.823 I slot launch_slot_: id 0 | task 16061 | processing task, is_child = 0 6.42.047.909 I slot print_timing: id 0 | task 16061 | prompt eval time = 871.64 ms / 287 tokens ( 3.04 ms per token, 329.27 tokens per second) 6.42.047.915 I slot print_timing: id 0 | task 16061 | eval time = 2590.43 ms / 137 tokens ( 19.05 ms per token, 52.50 tokens per second) 6.42.047.916 I slot print_timing: id 0 | task 16061 | total time = 3462.07 ms / 424 tokens 6.42.047.917 I slot print_timing: id 0 | task 16061 | graphs reused = 15484 6.42.047.917 I slot print_timing: id 0 | task 16061 | graph reallocs = 0 / 0 (same size) / (changed size) 6.42.047.944 I slot release: id 0 | task 16061 | stop processing: n_tokens = 423, truncated = 0 6.42.052.640 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.162 (> 0.100 thold), f_keep = 0.087 6.42.052.703 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 71.822 MiB) 6.42.060.836 I slot launch_slot_: id 0 | task 16201 | processing task, is_child = 0 6.45.263.338 I slot print_timing: id 0 | task 16201 | prompt eval time = 693.32 ms / 229 tokens ( 3.03 ms per token, 330.29 tokens per second) 6.45.263.344 I slot print_timing: id 0 | task 16201 | eval time = 2509.17 ms / 133 tokens ( 19.01 ms per token, 52.61 tokens per second) 6.45.263.345 I slot print_timing: id 0 | task 16201 | total time = 3202.49 ms / 362 tokens 6.45.263.345 I slot print_timing: id 0 | task 16201 | graphs reused = 15614 6.45.263.346 I slot print_timing: id 0 | task 16201 | graph reallocs = 0 / 0 (same size) / (changed size) 6.45.263.368 I slot release: id 0 | task 16201 | stop processing: n_tokens = 361, truncated = 0 6.45.268.249 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.117 (> 0.100 thold), f_keep = 0.102 6.45.268.302 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 63.590 MiB) 6.45.270.259 I slot launch_slot_: id 0 | task 16337 | processing task, is_child = 0 6.49.172.994 I slot print_timing: id 0 | task 16337 | n_gen = 159, tg = 52.50 t/s, tg_3s = 52.83 t/s 6.50.204.958 I slot print_timing: id 0 | task 16337 | prompt eval time = 893.21 ms / 315 tokens ( 2.84 ms per token, 352.66 tokens per second) 6.50.204.965 I slot print_timing: id 0 | task 16337 | eval time = 4041.48 ms / 213 tokens ( 19.06 ms per token, 52.46 tokens per second) 6.50.204.965 I slot print_timing: id 0 | task 16337 | total time = 4934.69 ms / 528 tokens 6.50.204.966 I slot print_timing: id 0 | task 16337 | graphs reused = 15824 6.50.204.966 I slot print_timing: id 0 | task 16337 | graph reallocs = 0 / 0 (same size) / (changed size) 6.50.204.990 I slot release: id 0 | task 16337 | stop processing: n_tokens = 527, truncated = 0 6.50.209.669 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.183 (> 0.100 thold), f_keep = 0.070 6.50.209.734 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 52.814 MiB) 6.50.209.740 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 59.788 MiB) 6.50.219.350 I slot launch_slot_: id 0 | task 16553 | processing task, is_child = 0 6.53.036.091 I slot print_timing: id 0 | task 16553 | prompt eval time = 653.70 ms / 202 tokens ( 3.24 ms per token, 309.01 tokens per second) 6.53.036.094 I slot print_timing: id 0 | task 16553 | eval time = 2163.03 ms / 115 tokens ( 18.97 ms per token, 52.70 tokens per second) 6.53.036.095 I slot print_timing: id 0 | task 16553 | total time = 2816.73 ms / 317 tokens 6.53.036.095 I slot print_timing: id 0 | task 16553 | graphs reused = 15936 6.53.036.096 I slot print_timing: id 0 | task 16553 | graph reallocs = 0 / 0 (same size) / (changed size) 6.53.036.120 I slot release: id 0 | task 16553 | stop processing: n_tokens = 316, truncated = 0 6.53.041.033 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.154 (> 0.100 thold), f_keep = 0.117 6.53.041.090 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 67.843 MiB) 6.53.043.033 I slot launch_slot_: id 0 | task 16671 | processing task, is_child = 0 6.55.830.550 I slot print_timing: id 0 | task 16671 | prompt eval time = 752.44 ms / 240 tokens ( 3.14 ms per token, 318.96 tokens per second) 6.55.830.556 I slot print_timing: id 0 | task 16671 | eval time = 2035.07 ms / 108 tokens ( 19.02 ms per token, 52.58 tokens per second) 6.55.830.556 I slot print_timing: id 0 | task 16671 | total time = 2787.51 ms / 348 tokens 6.55.830.557 I slot print_timing: id 0 | task 16671 | graphs reused = 16041 6.55.830.558 I slot print_timing: id 0 | task 16671 | graph reallocs = 0 / 0 (same size) / (changed size) 6.55.830.583 I slot release: id 0 | task 16671 | stop processing: n_tokens = 347, truncated = 0 6.55.835.667 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.119 (> 0.100 thold), f_keep = 0.107 6.55.835.719 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 63.330 MiB) 6.55.837.644 I slot launch_slot_: id 0 | task 16782 | processing task, is_child = 0 6.59.632.029 I slot print_timing: id 0 | task 16782 | n_gen = 159, tg = 52.48 t/s, tg_3s = 52.81 t/s 7.02.633.856 I slot print_timing: id 0 | task 16782 | n_gen = 316, tg = 52.39 t/s, tg_3s = 52.30 t/s 7.05.636.353 I slot print_timing: id 0 | task 16782 | n_gen = 473, tg = 52.36 t/s, tg_3s = 52.29 t/s 7.08.641.906 I slot print_timing: id 0 | task 16782 | n_gen = 629, tg = 52.24 t/s, tg_3s = 51.90 t/s 7.08.777.149 I slot print_timing: id 0 | task 16782 | prompt eval time = 783.62 ms / 312 tokens ( 2.51 ms per token, 398.15 tokens per second) 7.08.777.155 I slot print_timing: id 0 | task 16782 | eval time = 12155.87 ms / 636 tokens ( 19.14 ms per token, 52.24 tokens per second) 7.08.777.157 I slot print_timing: id 0 | task 16782 | total time = 12939.49 ms / 948 tokens 7.08.777.157 I slot print_timing: id 0 | task 16782 | graphs reused = 16673 7.08.777.158 I slot print_timing: id 0 | task 16782 | graph reallocs = 0 / 0 (same size) / (changed size) 7.08.777.184 I slot release: id 0 | task 16782 | stop processing: n_tokens = 947, truncated = 0 7.08.782.411 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.118 (> 0.100 thold), f_keep = 0.039 7.08.782.502 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 56.780 MiB) 7.08.794.353 I slot launch_slot_: id 0 | task 17421 | processing task, is_child = 0 7.12.573.926 I slot print_timing: id 0 | task 17421 | n_gen = 159, tg = 52.51 t/s, tg_3s = 52.84 t/s 7.14.466.730 I slot print_timing: id 0 | task 17421 | prompt eval time = 770.47 ms / 314 tokens ( 2.45 ms per token, 407.55 tokens per second) 7.14.466.735 I slot print_timing: id 0 | task 17421 | eval time = 4901.90 ms / 258 tokens ( 19.07 ms per token, 52.43 tokens per second) 7.14.466.736 I slot print_timing: id 0 | task 17421 | total time = 5672.37 ms / 572 tokens 7.14.466.737 I slot print_timing: id 0 | task 17421 | graphs reused = 16928 7.14.466.737 I slot print_timing: id 0 | task 17421 | graph reallocs = 0 / 0 (same size) / (changed size) 7.14.466.763 I slot release: id 0 | task 17421 | stop processing: n_tokens = 571, truncated = 0 7.14.472.112 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.109 (> 0.100 thold), f_keep = 0.065 7.14.472.179 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 55.262 MiB) 7.14.472.184 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 69.607 MiB) 7.14.482.362 I slot launch_slot_: id 0 | task 17682 | processing task, is_child = 0 7.17.551.739 I slot print_timing: id 0 | task 17682 | prompt eval time = 877.30 ms / 339 tokens ( 2.59 ms per token, 386.41 tokens per second) 7.17.551.745 I slot print_timing: id 0 | task 17682 | eval time = 2192.07 ms / 116 tokens ( 19.06 ms per token, 52.46 tokens per second) 7.17.551.745 I slot print_timing: id 0 | task 17682 | total time = 3069.37 ms / 455 tokens 7.17.551.746 I slot print_timing: id 0 | task 17682 | graphs reused = 17042 7.17.551.747 I slot print_timing: id 0 | task 17682 | graph reallocs = 0 / 0 (same size) / (changed size) 7.17.551.771 I slot release: id 0 | task 17682 | stop processing: n_tokens = 454, truncated = 0 7.17.557.296 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.105 (> 0.100 thold), f_keep = 0.081 7.17.557.359 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 66.133 MiB) 7.17.566.151 I slot launch_slot_: id 0 | task 17801 | processing task, is_child = 0 7.21.418.085 I slot print_timing: id 0 | task 17801 | prompt eval time = 892.82 ms / 352 tokens ( 2.54 ms per token, 394.26 tokens per second) 7.21.418.089 I slot print_timing: id 0 | task 17801 | eval time = 2959.10 ms / 156 tokens ( 19.09 ms per token, 52.38 tokens per second) 7.21.418.089 I slot print_timing: id 0 | task 17801 | total time = 3851.92 ms / 508 tokens 7.21.418.090 I slot print_timing: id 0 | task 17801 | graphs reused = 17196 7.21.418.090 I slot print_timing: id 0 | task 17801 | graph reallocs = 0 / 0 (same size) / (changed size) 7.21.418.124 I slot release: id 0 | task 17801 | stop processing: n_tokens = 507, truncated = 0 7.21.423.514 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.113 (> 0.100 thold), f_keep = 0.073 7.21.423.601 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 53.566 MiB) 7.21.423.605 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 76.103 MiB) 7.21.433.251 I slot launch_slot_: id 0 | task 17960 | processing task, is_child = 0 7.24.417.694 I slot print_timing: id 0 | task 17960 | prompt eval time = 867.10 ms / 328 tokens ( 2.64 ms per token, 378.27 tokens per second) 7.24.417.698 I slot print_timing: id 0 | task 17960 | eval time = 2117.34 ms / 112 tokens ( 19.08 ms per token, 52.42 tokens per second) 7.24.417.699 I slot print_timing: id 0 | task 17960 | total time = 2984.44 ms / 440 tokens 7.24.417.699 I slot print_timing: id 0 | task 17960 | graphs reused = 17306 7.24.417.700 I slot print_timing: id 0 | task 17960 | graph reallocs = 0 / 0 (same size) / (changed size) 7.24.417.724 I slot release: id 0 | task 17960 | stop processing: n_tokens = 439, truncated = 0 7.24.422.903 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.127 (> 0.100 thold), f_keep = 0.084 7.24.422.963 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 52.650 MiB) 7.24.425.444 I slot launch_slot_: id 0 | task 18075 | processing task, is_child = 0 7.28.034.162 I slot print_timing: id 0 | task 18075 | prompt eval time = 753.71 ms / 292 tokens ( 2.58 ms per token, 387.42 tokens per second) 7.28.034.165 I slot print_timing: id 0 | task 18075 | eval time = 2855.00 ms / 151 tokens ( 19.03 ms per token, 52.54 tokens per second) 7.28.034.166 I slot print_timing: id 0 | task 18075 | total time = 3608.70 ms / 443 tokens 7.28.034.166 I slot print_timing: id 0 | task 18075 | graphs reused = 17455 7.28.034.167 I slot print_timing: id 0 | task 18075 | graph reallocs = 0 / 0 (same size) / (changed size) 7.28.034.189 I slot release: id 0 | task 18075 | stop processing: n_tokens = 442, truncated = 0 7.28.038.932 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.164 (> 0.100 thold), f_keep = 0.084 7.28.038.988 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 49.970 MiB) 7.28.047.185 I slot launch_slot_: id 0 | task 18229 | processing task, is_child = 0 7.30.572.448 I slot print_timing: id 0 | task 18229 | prompt eval time = 666.28 ms / 225 tokens ( 2.96 ms per token, 337.70 tokens per second) 7.30.572.453 I slot print_timing: id 0 | task 18229 | eval time = 1858.97 ms / 100 tokens ( 18.78 ms per token, 53.26 tokens per second) 7.30.572.454 I slot print_timing: id 0 | task 18229 | total time = 2525.25 ms / 325 tokens 7.30.572.455 I slot print_timing: id 0 | task 18229 | graphs reused = 17552 7.30.572.455 I slot print_timing: id 0 | task 18229 | graph reallocs = 0 / 0 (same size) / (changed size) 7.30.572.475 I slot release: id 0 | task 18229 | stop processing: n_tokens = 324, truncated = 0 7.30.578.341 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 324, t_last = 350504758053 7.30.578.395 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 50.996 MiB) 7.30.578.399 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 49.915 MiB) 7.30.580.315 I slot launch_slot_: id 0 | task 18332 | processing task, is_child = 0 7.34.058.169 I slot print_timing: id 0 | task 18332 | prompt eval time = 987.55 ms / 425 tokens ( 2.32 ms per token, 430.36 tokens per second) 7.34.058.174 I slot print_timing: id 0 | task 18332 | eval time = 2490.29 ms / 131 tokens ( 19.16 ms per token, 52.20 tokens per second) 7.34.058.174 I slot print_timing: id 0 | task 18332 | total time = 3477.84 ms / 556 tokens 7.34.058.175 I slot print_timing: id 0 | task 18332 | graphs reused = 17680 7.34.058.175 I slot print_timing: id 0 | task 18332 | graph reallocs = 0 / 0 (same size) / (changed size) 7.34.058.207 I slot release: id 0 | task 18332 | stop processing: n_tokens = 555, truncated = 0 7.34.064.875 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 555, t_last = 350508243785 7.34.064.942 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 63.494 MiB) 7.34.074.563 I slot launch_slot_: id 0 | task 18466 | processing task, is_child = 0 7.38.571.676 I slot print_timing: id 0 | task 18466 | n_gen = 158, tg = 52.31 t/s, tg_3s = 52.64 t/s 7.39.706.079 I slot print_timing: id 0 | task 18466 | prompt eval time = 1495.70 ms / 597 tokens ( 2.51 ms per token, 399.14 tokens per second) 7.39.706.085 I slot print_timing: id 0 | task 18466 | eval time = 4135.80 ms / 217 tokens ( 19.15 ms per token, 52.23 tokens per second) 7.39.706.086 I slot print_timing: id 0 | task 18466 | total time = 5631.50 ms / 814 tokens 7.39.706.086 I slot print_timing: id 0 | task 18466 | graphs reused = 17894 7.39.706.087 I slot print_timing: id 0 | task 18466 | graph reallocs = 0 / 0 (same size) / (changed size) 7.39.706.124 I slot release: id 0 | task 18466 | stop processing: n_tokens = 813, truncated = 0 7.39.712.833 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 813, t_last = 350513891702 7.39.712.917 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 96.724 MiB) 7.39.712.924 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 53.649 MiB) 7.39.721.176 I slot launch_slot_: id 0 | task 18687 | processing task, is_child = 0 7.43.997.348 I slot print_timing: id 0 | task 18687 | n_gen = 158, tg = 52.32 t/s, tg_3s = 52.65 t/s 7.44.646.623 I slot print_timing: id 0 | task 18687 | prompt eval time = 1275.12 ms / 547 tokens ( 2.33 ms per token, 428.98 tokens per second) 7.44.646.629 I slot print_timing: id 0 | task 18687 | eval time = 3650.31 ms / 192 tokens ( 19.11 ms per token, 52.32 tokens per second) 7.44.646.630 I slot print_timing: id 0 | task 18687 | total time = 4925.43 ms / 739 tokens 7.44.646.630 I slot print_timing: id 0 | task 18687 | graphs reused = 18084 7.44.646.631 I slot print_timing: id 0 | task 18687 | graph reallocs = 0 / 0 (same size) / (changed size) 7.44.646.667 I slot release: id 0 | task 18687 | stop processing: n_tokens = 738, truncated = 0 7.44.652.641 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 738, t_last = 350518832245 7.44.652.714 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 62.387 MiB) 7.44.652.717 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 71.945 MiB) 7.44.663.219 I slot launch_slot_: id 0 | task 18883 | processing task, is_child = 0 7.48.688.577 I slot print_timing: id 0 | task 18883 | n_gen = 158, tg = 52.19 t/s, tg_3s = 52.52 t/s 7.49.052.270 I slot print_timing: id 0 | task 18883 | prompt eval time = 1017.13 ms / 414 tokens ( 2.46 ms per token, 407.03 tokens per second) 7.49.052.276 I slot print_timing: id 0 | task 18883 | eval time = 3371.91 ms / 177 tokens ( 19.16 ms per token, 52.20 tokens per second) 7.49.052.277 I slot print_timing: id 0 | task 18883 | total time = 4389.04 ms / 591 tokens 7.49.052.277 I slot print_timing: id 0 | task 18883 | graphs reused = 18258 7.49.052.278 I slot print_timing: id 0 | task 18883 | graph reallocs = 0 / 0 (same size) / (changed size) 7.49.052.310 I slot release: id 0 | task 18883 | stop processing: n_tokens = 620, truncated = 0 7.49.058.138 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.100 (> 0.100 thold), f_keep = 0.060 7.49.058.217 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 81.805 MiB) 7.49.068.581 I slot launch_slot_: id 0 | task 19063 | processing task, is_child = 0 7.52.812.375 I slot print_timing: id 0 | task 19063 | prompt eval time = 876.91 ms / 340 tokens ( 2.58 ms per token, 387.73 tokens per second) 7.52.812.378 I slot print_timing: id 0 | task 19063 | eval time = 2866.88 ms / 151 tokens ( 19.11 ms per token, 52.32 tokens per second) 7.52.812.380 I slot print_timing: id 0 | task 19063 | total time = 3743.79 ms / 491 tokens 7.52.812.381 I slot print_timing: id 0 | task 19063 | graphs reused = 18406 7.52.812.381 I slot print_timing: id 0 | task 19063 | graph reallocs = 0 / 0 (same size) / (changed size) 7.52.812.409 I slot release: id 0 | task 19063 | stop processing: n_tokens = 519, truncated = 0 7.52.819.527 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 519, t_last = 350526997987 7.52.819.594 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 53.621 MiB) 7.52.819.664 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 58.462 MiB) 7.52.823.052 I slot launch_slot_: id 0 | task 19217 | processing task, is_child = 0 7.57.320.344 I slot print_timing: id 0 | task 19217 | n_gen = 158, tg = 52.28 t/s, tg_3s = 52.61 t/s 8.00.339.253 I slot print_timing: id 0 | task 19217 | n_gen = 315, tg = 52.14 t/s, tg_3s = 52.01 t/s 8.01.708.546 I slot print_timing: id 0 | task 19217 | prompt eval time = 1494.25 ms / 608 tokens ( 2.46 ms per token, 406.89 tokens per second) 8.01.708.553 I slot print_timing: id 0 | task 19217 | eval time = 7391.23 ms / 386 tokens ( 19.20 ms per token, 52.09 tokens per second) 8.01.708.554 I slot print_timing: id 0 | task 19217 | total time = 8885.48 ms / 994 tokens 8.01.708.555 I slot print_timing: id 0 | task 19217 | graphs reused = 18789 8.01.708.555 I slot print_timing: id 0 | task 19217 | graph reallocs = 0 / 0 (same size) / (changed size) 8.01.708.591 I slot release: id 0 | task 19217 | stop processing: n_tokens = 1021, truncated = 0 8.01.714.482 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1021, t_last = 350535894169 8.01.714.573 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 67.022 MiB) 8.01.714.577 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 55.194 MiB) 8.01.725.078 I slot launch_slot_: id 0 | task 19607 | processing task, is_child = 0 8.05.613.875 I slot print_timing: id 0 | task 19607 | n_gen = 158, tg = 52.31 t/s, tg_3s = 52.65 t/s 8.06.493.750 I slot print_timing: id 0 | task 19607 | prompt eval time = 887.66 ms / 349 tokens ( 2.54 ms per token, 393.17 tokens per second) 8.06.493.756 I slot print_timing: id 0 | task 19607 | eval time = 3881.01 ms / 204 tokens ( 19.12 ms per token, 52.31 tokens per second) 8.06.493.757 I slot print_timing: id 0 | task 19607 | total time = 4768.66 ms / 553 tokens 8.06.493.758 I slot print_timing: id 0 | task 19607 | graphs reused = 18990 8.06.493.758 I slot print_timing: id 0 | task 19607 | graph reallocs = 0 / 0 (same size) / (changed size) 8.06.493.785 I slot release: id 0 | task 19607 | stop processing: n_tokens = 580, truncated = 0 8.06.500.276 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 580, t_last = 350540679363 8.06.500.346 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 67.761 MiB) 8.06.500.472 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 57.970 MiB) 8.06.507.339 I slot launch_slot_: id 0 | task 19814 | processing task, is_child = 0 8.10.600.131 I slot print_timing: id 0 | task 19814 | n_gen = 158, tg = 52.18 t/s, tg_3s = 52.51 t/s 8.12.256.928 I slot print_timing: id 0 | task 19814 | prompt eval time = 1083.91 ms / 469 tokens ( 2.31 ms per token, 432.69 tokens per second) 8.12.256.935 I slot print_timing: id 0 | task 19814 | eval time = 4665.67 ms / 245 tokens ( 19.12 ms per token, 52.30 tokens per second) 8.12.256.935 I slot print_timing: id 0 | task 19814 | total time = 5749.58 ms / 714 tokens 8.12.256.936 I slot print_timing: id 0 | task 19814 | graphs reused = 19232 8.12.256.936 I slot print_timing: id 0 | task 19814 | graph reallocs = 0 / 0 (same size) / (changed size) 8.12.256.970 I slot release: id 0 | task 19814 | stop processing: n_tokens = 740, truncated = 0 8.12.262.096 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.141 (> 0.100 thold), f_keep = 0.050 8.12.262.174 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 90.693 MiB) 8.12.262.328 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 80.328 MiB) 8.12.269.770 I slot launch_slot_: id 0 | task 20062 | processing task, is_child = 0 8.14.599.341 I slot print_timing: id 0 | task 20062 | prompt eval time = 751.40 ms / 237 tokens ( 3.17 ms per token, 315.41 tokens per second) 8.14.599.347 I slot print_timing: id 0 | task 20062 | eval time = 1578.15 ms / 84 tokens ( 19.01 ms per token, 52.59 tokens per second) 8.14.599.348 I slot print_timing: id 0 | task 20062 | total time = 2329.55 ms / 321 tokens 8.14.599.349 I slot print_timing: id 0 | task 20062 | graphs reused = 19314 8.14.599.350 I slot print_timing: id 0 | task 20062 | graph reallocs = 0 / 0 (same size) / (changed size) 8.14.599.374 I slot release: id 0 | task 20062 | stop processing: n_tokens = 346, truncated = 0 8.14.605.128 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 346, t_last = 350548784952 8.14.607.597 I slot launch_slot_: id 0 | task 20149 | processing task, is_child = 0 8.18.626.434 I slot print_timing: id 0 | task 20149 | n_gen = 158, tg = 52.19 t/s, tg_3s = 52.52 t/s 8.20.000.865 I slot print_timing: id 0 | task 20149 | prompt eval time = 1010.54 ms / 428 tokens ( 2.36 ms per token, 423.54 tokens per second) 8.20.000.871 I slot print_timing: id 0 | task 20149 | eval time = 4382.72 ms / 230 tokens ( 19.14 ms per token, 52.25 tokens per second) 8.20.000.872 I slot print_timing: id 0 | task 20149 | total time = 5393.26 ms / 658 tokens 8.20.000.873 I slot print_timing: id 0 | task 20149 | graphs reused = 19541 8.20.000.873 I slot print_timing: id 0 | task 20149 | graph reallocs = 0 / 0 (same size) / (changed size) 8.20.000.902 I slot release: id 0 | task 20149 | stop processing: n_tokens = 682, truncated = 0 8.20.007.445 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 682, t_last = 350554186480 8.20.007.519 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 56.589 MiB) 8.20.007.522 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 64.889 MiB) 8.20.016.946 I slot launch_slot_: id 0 | task 20382 | processing task, is_child = 0 8.24.268.627 I slot print_timing: id 0 | task 20382 | n_gen = 158, tg = 52.33 t/s, tg_3s = 52.66 t/s 8.26.518.518 I slot print_timing: id 0 | task 20382 | prompt eval time = 1251.54 ms / 530 tokens ( 2.36 ms per token, 423.48 tokens per second) 8.26.518.521 I slot print_timing: id 0 | task 20382 | eval time = 5250.01 ms / 274 tokens ( 19.23 ms per token, 52.00 tokens per second) 8.26.518.522 I slot print_timing: id 0 | task 20382 | total time = 6501.56 ms / 804 tokens 8.26.518.522 I slot print_timing: id 0 | task 20382 | graphs reused = 19812 8.26.518.523 I slot print_timing: id 0 | task 20382 | graph reallocs = 0 / 0 (same size) / (changed size) 8.26.518.558 I slot release: id 0 | task 20382 | stop processing: n_tokens = 827, truncated = 0 8.26.525.880 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 827, t_last = 350560704136 8.26.525.970 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 54.770 MiB) 8.26.526.399 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.933 MiB) 8.26.533.930 I slot launch_slot_: id 0 | task 20660 | processing task, is_child = 0 8.30.963.228 I slot print_timing: id 0 | task 20660 | n_gen = 158, tg = 52.28 t/s, tg_3s = 52.61 t/s 8.32.674.215 I slot print_timing: id 0 | task 20660 | prompt eval time = 1426.20 ms / 579 tokens ( 2.46 ms per token, 405.97 tokens per second) 8.32.674.222 I slot print_timing: id 0 | task 20660 | eval time = 4714.07 ms / 247 tokens ( 19.16 ms per token, 52.18 tokens per second) 8.32.674.222 I slot print_timing: id 0 | task 20660 | total time = 6140.27 ms / 826 tokens 8.32.674.223 I slot print_timing: id 0 | task 20660 | graphs reused = 20056 8.32.674.223 I slot print_timing: id 0 | task 20660 | graph reallocs = 0 / 0 (same size) / (changed size) 8.32.674.260 I slot release: id 0 | task 20660 | stop processing: n_tokens = 862, truncated = 0 8.32.680.453 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 862, t_last = 350566859838 8.32.680.538 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 97.722 MiB) 8.32.680.541 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 110.070 MiB) 8.32.688.479 I slot launch_slot_: id 0 | task 20911 | processing task, is_child = 0 8.36.549.304 I slot print_timing: id 0 | task 20911 | prompt eval time = 1007.02 ms / 427 tokens ( 2.36 ms per token, 424.02 tokens per second) 8.36.549.310 I slot print_timing: id 0 | task 20911 | eval time = 2853.79 ms / 149 tokens ( 19.28 ms per token, 51.86 tokens per second) 8.36.549.311 I slot print_timing: id 0 | task 20911 | total time = 3860.82 ms / 576 tokens 8.36.549.311 I slot print_timing: id 0 | task 20911 | graphs reused = 20202 8.36.549.312 I slot print_timing: id 0 | task 20911 | graph reallocs = 0 / 0 (same size) / (changed size) 8.36.549.342 I slot release: id 0 | task 20911 | stop processing: n_tokens = 599, truncated = 0 8.36.555.680 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 599, t_last = 350570734920 8.36.555.753 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 117.837 MiB) 8.36.559.552 I slot launch_slot_: id 0 | task 21063 | processing task, is_child = 0 8.40.672.349 I slot print_timing: id 0 | task 21063 | n_gen = 158, tg = 52.32 t/s, tg_3s = 52.65 t/s 8.42.660.904 I slot print_timing: id 0 | task 21063 | prompt eval time = 1111.79 ms / 508 tokens ( 2.19 ms per token, 456.92 tokens per second) 8.42.660.908 I slot print_timing: id 0 | task 21063 | eval time = 4989.56 ms / 262 tokens ( 19.12 ms per token, 52.31 tokens per second) 8.42.660.909 I slot print_timing: id 0 | task 21063 | total time = 6101.34 ms / 770 tokens 8.42.660.909 I slot print_timing: id 0 | task 21063 | graphs reused = 20461 8.42.660.910 I slot print_timing: id 0 | task 21063 | graph reallocs = 0 / 0 (same size) / (changed size) 8.42.660.946 I slot release: id 0 | task 21063 | stop processing: n_tokens = 792, truncated = 0 8.42.667.102 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 792, t_last = 350576846524 8.42.667.184 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 116.511 MiB) 8.42.674.386 I slot launch_slot_: id 0 | task 21328 | processing task, is_child = 0 8.45.927.296 I slot print_timing: id 0 | task 21328 | prompt eval time = 1102.30 ms / 454 tokens ( 2.43 ms per token, 411.87 tokens per second) 8.45.927.302 I slot print_timing: id 0 | task 21328 | eval time = 2150.60 ms / 113 tokens ( 19.20 ms per token, 52.08 tokens per second) 8.45.927.303 I slot print_timing: id 0 | task 21328 | total time = 3252.90 ms / 567 tokens 8.45.927.303 I slot print_timing: id 0 | task 21328 | graphs reused = 20571 8.45.927.304 I slot print_timing: id 0 | task 21328 | graph reallocs = 0 / 0 (same size) / (changed size) 8.45.927.336 I slot release: id 0 | task 21328 | stop processing: n_tokens = 588, truncated = 0 8.45.934.241 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 588, t_last = 350580112914 8.45.934.312 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 82.502 MiB) 8.45.943.133 I slot launch_slot_: id 0 | task 21444 | processing task, is_child = 0 8.50.448.393 I slot print_timing: id 0 | task 21444 | n_gen = 158, tg = 52.25 t/s, tg_3s = 52.58 t/s 8.50.831.290 I slot print_timing: id 0 | task 21444 | prompt eval time = 1500.56 ms / 606 tokens ( 2.48 ms per token, 403.85 tokens per second) 8.50.831.296 I slot print_timing: id 0 | task 21444 | eval time = 3387.59 ms / 178 tokens ( 19.14 ms per token, 52.25 tokens per second) 8.50.831.296 I slot print_timing: id 0 | task 21444 | total time = 4888.15 ms / 784 tokens 8.50.831.297 I slot print_timing: id 0 | task 21444 | graphs reused = 20746 8.50.831.298 I slot print_timing: id 0 | task 21444 | graph reallocs = 0 / 0 (same size) / (changed size) 8.50.831.339 I slot release: id 0 | task 21444 | stop processing: n_tokens = 804, truncated = 0 8.50.838.923 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 804, t_last = 350585016917 8.50.839.003 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 111.533 MiB) 8.50.850.480 I slot launch_slot_: id 0 | task 21626 | processing task, is_child = 0 8.55.206.941 I slot print_timing: id 0 | task 21626 | prompt eval time = 1607.72 ms / 672 tokens ( 2.39 ms per token, 417.98 tokens per second) 8.55.206.946 I slot print_timing: id 0 | task 21626 | eval time = 2748.73 ms / 143 tokens ( 19.36 ms per token, 51.66 tokens per second) 8.55.206.947 I slot print_timing: id 0 | task 21626 | total time = 4356.45 ms / 815 tokens 8.55.206.948 I slot print_timing: id 0 | task 21626 | graphs reused = 20886 8.55.206.948 I slot print_timing: id 0 | task 21626 | graph reallocs = 0 / 0 (same size) / (changed size) 8.55.206.990 I slot release: id 0 | task 21626 | stop processing: n_tokens = 835, truncated = 0 8.55.213.529 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 835, t_last = 350589392568 8.55.213.625 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 108.634 MiB) 8.55.227.973 I slot launch_slot_: id 0 | task 21773 | processing task, is_child = 0 8.58.756.128 I slot print_timing: id 0 | task 21773 | prompt eval time = 1191.38 ms / 517 tokens ( 2.30 ms per token, 433.95 tokens per second) 8.58.756.133 I slot print_timing: id 0 | task 21773 | eval time = 2336.76 ms / 123 tokens ( 19.15 ms per token, 52.21 tokens per second) 8.58.756.134 I slot print_timing: id 0 | task 21773 | total time = 3528.14 ms / 640 tokens 8.58.756.135 I slot print_timing: id 0 | task 21773 | graphs reused = 21007 8.58.756.135 I slot print_timing: id 0 | task 21773 | graph reallocs = 0 / 0 (same size) / (changed size) 8.58.756.172 I slot release: id 0 | task 21773 | stop processing: n_tokens = 639, truncated = 0 8.58.763.010 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 639, t_last = 350592941750 8.58.763.083 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 92.594 MiB) 8.58.769.700 I slot launch_slot_: id 0 | task 21900 | processing task, is_child = 0 9.03.251.676 I slot print_timing: id 0 | task 21900 | n_gen = 158, tg = 52.13 t/s, tg_3s = 52.46 t/s 9.03.903.676 I slot print_timing: id 0 | task 21900 | prompt eval time = 1470.11 ms / 578 tokens ( 2.54 ms per token, 393.17 tokens per second) 9.03.903.680 I slot print_timing: id 0 | task 21900 | eval time = 3663.86 ms / 192 tokens ( 19.18 ms per token, 52.13 tokens per second) 9.03.903.681 I slot print_timing: id 0 | task 21900 | total time = 5133.96 ms / 770 tokens 9.03.903.682 I slot print_timing: id 0 | task 21900 | graphs reused = 21196 9.03.903.682 I slot print_timing: id 0 | task 21900 | graph reallocs = 0 / 0 (same size) / (changed size) 9.03.903.718 I slot release: id 0 | task 21900 | stop processing: n_tokens = 770, truncated = 0 9.03.909.358 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 770, t_last = 350598089296 9.03.909.436 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 86.194 MiB) 9.03.918.740 I slot launch_slot_: id 0 | task 22096 | processing task, is_child = 0 9.07.884.199 I slot print_timing: id 0 | task 22096 | n_gen = 159, tg = 52.37 t/s, tg_3s = 52.70 t/s 9.09.737.443 I slot print_timing: id 0 | task 22096 | prompt eval time = 948.39 ms / 373 tokens ( 2.54 ms per token, 393.30 tokens per second) 9.09.737.449 I slot print_timing: id 0 | task 22096 | eval time = 4870.30 ms / 256 tokens ( 19.10 ms per token, 52.36 tokens per second) 9.09.737.450 I slot print_timing: id 0 | task 22096 | total time = 5818.69 ms / 629 tokens 9.09.737.451 I slot print_timing: id 0 | task 22096 | graphs reused = 21449 9.09.737.451 I slot print_timing: id 0 | task 22096 | graph reallocs = 0 / 0 (same size) / (changed size) 9.09.737.481 I slot release: id 0 | task 22096 | stop processing: n_tokens = 629, truncated = 0 9.09.743.690 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 629, t_last = 350603923059 9.09.743.760 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.077 MiB) 9.09.754.703 I slot launch_slot_: id 0 | task 22355 | processing task, is_child = 0 9.13.814.188 I slot print_timing: id 0 | task 22355 | n_gen = 158, tg = 52.22 t/s, tg_3s = 52.56 t/s 9.15.169.869 I slot print_timing: id 0 | task 22355 | prompt eval time = 1053.17 ms / 450 tokens ( 2.34 ms per token, 427.28 tokens per second) 9.15.169.872 I slot print_timing: id 0 | task 22355 | eval time = 4361.98 ms / 229 tokens ( 19.13 ms per token, 52.27 tokens per second) 9.15.169.874 I slot print_timing: id 0 | task 22355 | total time = 5415.15 ms / 679 tokens 9.15.169.874 I slot print_timing: id 0 | task 22355 | graphs reused = 21675 9.15.169.875 I slot print_timing: id 0 | task 22355 | graph reallocs = 0 / 0 (same size) / (changed size) 9.15.169.906 I slot release: id 0 | task 22355 | stop processing: n_tokens = 678, truncated = 0 9.15.177.861 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 678, t_last = 350609355485 9.15.184.444 I slot launch_slot_: id 0 | task 22587 | processing task, is_child = 0 9.19.942.880 I slot print_timing: id 0 | task 22587 | n_gen = 157, tg = 51.81 t/s, tg_3s = 52.14 t/s 9.21.847.834 I slot print_timing: id 0 | task 22587 | prompt eval time = 1747.23 ms / 754 tokens ( 2.32 ms per token, 431.54 tokens per second) 9.21.847.840 I slot print_timing: id 0 | task 22587 | eval time = 4916.15 ms / 256 tokens ( 19.28 ms per token, 51.87 tokens per second) 9.21.847.841 I slot print_timing: id 0 | task 22587 | total time = 6663.38 ms / 1010 tokens 9.21.847.841 I slot print_timing: id 0 | task 22587 | graphs reused = 21928 9.21.847.842 I slot print_timing: id 0 | task 22587 | graph reallocs = 0 / 0 (same size) / (changed size) 9.21.847.887 I slot release: id 0 | task 22587 | stop processing: n_tokens = 1009, truncated = 0 9.21.855.650 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1009, t_last = 350616033465 9.21.855.739 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 99.199 MiB) 9.21.855.743 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 76.348 MiB) 9.21.867.893 I slot launch_slot_: id 0 | task 22847 | processing task, is_child = 0 9.26.557.101 I slot print_timing: id 0 | task 22847 | n_gen = 157, tg = 51.95 t/s, tg_3s = 52.29 t/s 9.28.196.734 I slot print_timing: id 0 | task 22847 | prompt eval time = 1686.53 ms / 721 tokens ( 2.34 ms per token, 427.51 tokens per second) 9.28.196.741 I slot print_timing: id 0 | task 22847 | eval time = 4642.30 ms / 242 tokens ( 19.26 ms per token, 51.91 tokens per second) 9.28.196.742 I slot print_timing: id 0 | task 22847 | total time = 6328.83 ms / 963 tokens 9.28.196.742 I slot print_timing: id 0 | task 22847 | graphs reused = 22167 9.28.196.743 I slot print_timing: id 0 | task 22847 | graph reallocs = 0 / 0 (same size) / (changed size) 9.28.196.784 I slot release: id 0 | task 22847 | stop processing: n_tokens = 962, truncated = 0 9.28.202.150 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.135 (> 0.100 thold), f_keep = 0.038 9.28.202.242 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 100.101 MiB) 9.28.215.052 I slot launch_slot_: id 0 | task 23093 | processing task, is_child = 0 9.31.886.355 I slot print_timing: id 0 | task 23093 | n_gen = 159, tg = 52.59 t/s, tg_3s = 52.93 t/s 9.32.534.780 I slot print_timing: id 0 | task 23093 | prompt eval time = 667.12 ms / 274 tokens ( 2.43 ms per token, 410.72 tokens per second) 9.32.534.790 I slot print_timing: id 0 | task 23093 | eval time = 3652.60 ms / 193 tokens ( 19.02 ms per token, 52.57 tokens per second) 9.32.534.790 I slot print_timing: id 0 | task 23093 | total time = 4319.72 ms / 467 tokens 9.32.534.791 I slot print_timing: id 0 | task 23093 | graphs reused = 22358 9.32.534.791 I slot print_timing: id 0 | task 23093 | graph reallocs = 0 / 0 (same size) / (changed size) 9.32.534.821 I slot release: id 0 | task 23093 | stop processing: n_tokens = 466, truncated = 0 9.32.539.771 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.176 (> 0.100 thold), f_keep = 0.082 9.32.539.835 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 84.649 MiB) 9.32.542.733 I slot launch_slot_: id 0 | task 23289 | processing task, is_child = 0 9.35.054.657 I slot print_timing: id 0 | task 23289 | prompt eval time = 591.33 ms / 216 tokens ( 2.74 ms per token, 365.28 tokens per second) 9.35.054.663 I slot print_timing: id 0 | task 23289 | eval time = 1920.59 ms / 102 tokens ( 19.02 ms per token, 52.59 tokens per second) 9.35.054.664 I slot print_timing: id 0 | task 23289 | total time = 2511.92 ms / 318 tokens 9.35.054.664 I slot print_timing: id 0 | task 23289 | graphs reused = 22457 9.35.054.665 I slot print_timing: id 0 | task 23289 | graph reallocs = 0 / 0 (same size) / (changed size) 9.35.054.684 I slot release: id 0 | task 23289 | stop processing: n_tokens = 317, truncated = 0 9.35.059.368 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.120 9.35.059.418 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 78.427 MiB) 9.35.061.300 I slot launch_slot_: id 0 | task 23394 | processing task, is_child = 0 9.38.749.947 I slot print_timing: id 0 | task 23394 | n_gen = 159, tg = 52.61 t/s, tg_3s = 52.95 t/s 9.41.768.608 I slot print_timing: id 0 | task 23394 | n_gen = 317, tg = 52.48 t/s, tg_3s = 52.34 t/s 9.44.716.671 I slot print_timing: id 0 | task 23394 | prompt eval time = 685.57 ms / 243 tokens ( 2.82 ms per token, 354.45 tokens per second) 9.44.716.677 I slot print_timing: id 0 | task 23394 | eval time = 8969.80 ms / 471 tokens ( 19.08 ms per token, 52.40 tokens per second) 9.44.716.678 I slot print_timing: id 0 | task 23394 | total time = 9655.36 ms / 714 tokens 9.44.716.679 I slot print_timing: id 0 | task 23394 | graphs reused = 22924 9.44.716.679 I slot print_timing: id 0 | task 23394 | graph reallocs = 0 / 0 (same size) / (changed size) 9.44.716.701 I slot release: id 0 | task 23394 | stop processing: n_tokens = 713, truncated = 0 9.44.721.228 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.195 (> 0.100 thold), f_keep = 0.053 9.44.721.306 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 81.380 MiB) 9.44.730.860 I slot launch_slot_: id 0 | task 23868 | processing task, is_child = 0 9.47.924.094 I slot print_timing: id 0 | task 23868 | prompt eval time = 557.75 ms / 195 tokens ( 2.86 ms per token, 349.62 tokens per second) 9.47.924.097 I slot print_timing: id 0 | task 23868 | eval time = 2635.48 ms / 140 tokens ( 18.96 ms per token, 52.74 tokens per second) 9.47.924.099 I slot print_timing: id 0 | task 23868 | total time = 3193.23 ms / 335 tokens 9.47.924.099 I slot print_timing: id 0 | task 23868 | graphs reused = 23061 9.47.924.100 I slot print_timing: id 0 | task 23868 | graph reallocs = 0 / 0 (same size) / (changed size) 9.47.924.123 I slot release: id 0 | task 23868 | stop processing: n_tokens = 334, truncated = 0 9.47.929.165 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.142 (> 0.100 thold), f_keep = 0.111 9.47.929.218 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.716 MiB) 9.47.931.227 I slot launch_slot_: id 0 | task 24011 | processing task, is_child = 0 9.51.657.607 I slot print_timing: id 0 | task 24011 | n_gen = 159, tg = 52.65 t/s, tg_3s = 52.99 t/s 9.52.515.800 I slot print_timing: id 0 | task 24011 | prompt eval time = 725.59 ms / 261 tokens ( 2.78 ms per token, 359.71 tokens per second) 9.52.515.807 I slot print_timing: id 0 | task 24011 | eval time = 3858.97 ms / 204 tokens ( 19.01 ms per token, 52.60 tokens per second) 9.52.515.807 I slot print_timing: id 0 | task 24011 | total time = 4584.56 ms / 465 tokens 9.52.515.808 I slot print_timing: id 0 | task 24011 | graphs reused = 23263 9.52.515.809 I slot print_timing: id 0 | task 24011 | graph reallocs = 0 / 0 (same size) / (changed size) 9.52.515.830 I slot release: id 0 | task 24011 | stop processing: n_tokens = 464, truncated = 0 9.52.520.450 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.080 9.52.520.511 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 112.791 MiB) 9.52.522.960 I slot launch_slot_: id 0 | task 24218 | processing task, is_child = 0 9.54.397.046 I slot print_timing: id 0 | task 24218 | prompt eval time = 550.27 ms / 179 tokens ( 3.07 ms per token, 325.29 tokens per second) 9.54.397.052 I slot print_timing: id 0 | task 24218 | eval time = 1323.81 ms / 71 tokens ( 18.91 ms per token, 52.88 tokens per second) 9.54.397.053 I slot print_timing: id 0 | task 24218 | total time = 1874.08 ms / 250 tokens 9.54.397.054 I slot print_timing: id 0 | task 24218 | graphs reused = 23332 9.54.397.054 I slot print_timing: id 0 | task 24218 | graph reallocs = 0 / 0 (same size) / (changed size) 9.54.397.073 I slot release: id 0 | task 24218 | stop processing: n_tokens = 249, truncated = 0 9.54.401.699 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.168 (> 0.100 thold), f_keep = 0.149 9.54.403.251 I slot launch_slot_: id 0 | task 24292 | processing task, is_child = 0 9.58.019.380 I slot print_timing: id 0 | task 24292 | n_gen = 160, tg = 52.68 t/s, tg_3s = 53.01 t/s 9.59.197.986 I slot print_timing: id 0 | task 24292 | prompt eval time = 598.02 ms / 220 tokens ( 2.72 ms per token, 367.88 tokens per second) 9.59.197.993 I slot print_timing: id 0 | task 24292 | eval time = 4196.70 ms / 222 tokens ( 18.99 ms per token, 52.66 tokens per second) 9.59.197.994 I slot print_timing: id 0 | task 24292 | total time = 4794.73 ms / 442 tokens 9.59.197.994 I slot print_timing: id 0 | task 24292 | graphs reused = 23551 9.59.197.995 I slot print_timing: id 0 | task 24292 | graph reallocs = 0 / 0 (same size) / (changed size) 9.59.198.017 I slot release: id 0 | task 24292 | stop processing: n_tokens = 441, truncated = 0 9.59.202.578 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.084 9.59.202.638 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 84.662 MiB) 9.59.204.877 I slot launch_slot_: id 0 | task 24517 | processing task, is_child = 0 10.02.829.168 I slot print_timing: id 0 | task 24517 | n_gen = 160, tg = 52.74 t/s, tg_3s = 53.08 t/s 10.04.407.010 I slot print_timing: id 0 | task 24517 | prompt eval time = 609.76 ms / 212 tokens ( 2.88 ms per token, 347.68 tokens per second) 10.04.407.016 I slot print_timing: id 0 | task 24517 | eval time = 4592.36 ms / 243 tokens ( 18.98 ms per token, 52.70 tokens per second) 10.04.407.017 I slot print_timing: id 0 | task 24517 | total time = 5202.12 ms / 455 tokens 10.04.407.018 I slot print_timing: id 0 | task 24517 | graphs reused = 23791 10.04.407.018 I slot print_timing: id 0 | task 24517 | graph reallocs = 0 / 0 (same size) / (changed size) 10.04.407.042 I slot release: id 0 | task 24517 | stop processing: n_tokens = 454, truncated = 0 10.04.411.300 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.245 (> 0.100 thold), f_keep = 0.081 10.04.411.365 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 139.281 MiB) 10.04.413.568 I slot launch_slot_: id 0 | task 24763 | processing task, is_child = 0 10.07.943.317 I slot print_timing: id 0 | task 24763 | n_gen = 160, tg = 52.93 t/s, tg_3s = 53.26 t/s 10.10.961.034 I slot print_timing: id 0 | task 24763 | n_gen = 319, tg = 52.81 t/s, tg_3s = 52.69 t/s 10.13.978.172 I slot print_timing: id 0 | task 24763 | n_gen = 477, tg = 52.66 t/s, tg_3s = 52.37 t/s 10.14.187.791 I slot print_timing: id 0 | task 24763 | prompt eval time = 525.83 ms / 151 tokens ( 3.48 ms per token, 287.16 tokens per second) 10.14.187.798 I slot print_timing: id 0 | task 24763 | eval time = 9248.38 ms / 488 tokens ( 18.99 ms per token, 52.66 tokens per second) 10.14.187.799 I slot print_timing: id 0 | task 24763 | total time = 9774.21 ms / 639 tokens 10.14.187.799 I slot print_timing: id 0 | task 24763 | graphs reused = 24275 10.14.187.800 I slot print_timing: id 0 | task 24763 | graph reallocs = 0 / 0 (same size) / (changed size) 10.14.187.826 I slot release: id 0 | task 24763 | stop processing: n_tokens = 638, truncated = 0 10.14.192.585 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.058 10.14.195.033 I slot launch_slot_: id 0 | task 25254 | processing task, is_child = 0 10.17.061.595 I slot print_timing: id 0 | task 25254 | prompt eval time = 626.86 ms / 217 tokens ( 2.89 ms per token, 346.17 tokens per second) 10.17.061.601 I slot print_timing: id 0 | task 25254 | eval time = 2239.69 ms / 119 tokens ( 18.98 ms per token, 52.69 tokens per second) 10.17.061.601 I slot print_timing: id 0 | task 25254 | total time = 2866.55 ms / 336 tokens 10.17.061.602 I slot print_timing: id 0 | task 25254 | graphs reused = 24391 10.17.061.603 I slot print_timing: id 0 | task 25254 | graph reallocs = 0 / 0 (same size) / (changed size) 10.17.061.626 I slot release: id 0 | task 25254 | stop processing: n_tokens = 335, truncated = 0 10.17.066.103 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.170 (> 0.100 thold), f_keep = 0.110 10.17.068.010 I slot launch_slot_: id 0 | task 25376 | processing task, is_child = 0 10.20.682.394 I slot print_timing: id 0 | task 25376 | n_gen = 159, tg = 52.66 t/s, tg_3s = 52.99 t/s 10.20.948.085 I slot print_timing: id 0 | task 25376 | prompt eval time = 613.91 ms / 218 tokens ( 2.82 ms per token, 355.10 tokens per second) 10.20.948.092 I slot print_timing: id 0 | task 25376 | eval time = 3266.16 ms / 173 tokens ( 18.99 ms per token, 52.66 tokens per second) 10.20.948.092 I slot print_timing: id 0 | task 25376 | total time = 3880.07 ms / 391 tokens 10.20.948.093 I slot print_timing: id 0 | task 25376 | graphs reused = 24561 10.20.948.094 I slot print_timing: id 0 | task 25376 | graph reallocs = 0 / 0 (same size) / (changed size) 10.20.948.115 I slot release: id 0 | task 25376 | stop processing: n_tokens = 390, truncated = 0 10.20.952.818 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.165 (> 0.100 thold), f_keep = 0.095 10.20.952.879 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 79.398 MiB) 10.20.954.968 I slot launch_slot_: id 0 | task 25552 | processing task, is_child = 0 10.24.660.022 I slot print_timing: id 0 | task 25552 | n_gen = 160, tg = 52.69 t/s, tg_3s = 53.03 t/s 10.26.999.638 I slot print_timing: id 0 | task 25552 | prompt eval time = 687.61 ms / 224 tokens ( 3.07 ms per token, 325.76 tokens per second) 10.26.999.644 I slot print_timing: id 0 | task 25552 | eval time = 5357.04 ms / 283 tokens ( 19.00 ms per token, 52.64 tokens per second) 10.26.999.646 I slot print_timing: id 0 | task 25552 | total time = 6044.66 ms / 507 tokens 10.26.999.646 I slot print_timing: id 0 | task 25552 | graphs reused = 24841 10.26.999.647 I slot print_timing: id 0 | task 25552 | graph reallocs = 0 / 0 (same size) / (changed size) 10.26.999.668 I slot release: id 0 | task 25552 | stop processing: n_tokens = 506, truncated = 0 10.27.004.428 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.176 (> 0.100 thold), f_keep = 0.073 10.27.004.494 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 122.351 MiB) 10.27.006.926 I slot launch_slot_: id 0 | task 25838 | processing task, is_child = 0 10.30.598.513 I slot print_timing: id 0 | task 25838 | n_gen = 159, tg = 52.65 t/s, tg_3s = 52.98 t/s 10.31.128.185 I slot print_timing: id 0 | task 25838 | prompt eval time = 590.71 ms / 210 tokens ( 2.81 ms per token, 355.51 tokens per second) 10.31.128.190 I slot print_timing: id 0 | task 25838 | eval time = 3530.54 ms / 187 tokens ( 18.98 ms per token, 52.68 tokens per second) 10.31.128.191 I slot print_timing: id 0 | task 25838 | total time = 4121.25 ms / 397 tokens 10.31.128.191 I slot print_timing: id 0 | task 25838 | graphs reused = 25025 10.31.128.192 I slot print_timing: id 0 | task 25838 | graph reallocs = 0 / 0 (same size) / (changed size) 10.31.128.217 I slot release: id 0 | task 25838 | stop processing: n_tokens = 396, truncated = 0 10.31.132.742 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.093 10.31.132.798 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 132.525 MiB) 10.31.134.876 I slot launch_slot_: id 0 | task 26028 | processing task, is_child = 0 10.34.743.615 I slot print_timing: id 0 | task 26028 | n_gen = 160, tg = 52.70 t/s, tg_3s = 53.03 t/s 10.35.065.845 I slot print_timing: id 0 | task 26028 | prompt eval time = 591.50 ms / 208 tokens ( 2.84 ms per token, 351.65 tokens per second) 10.35.065.849 I slot print_timing: id 0 | task 26028 | eval time = 3339.45 ms / 177 tokens ( 18.97 ms per token, 52.70 tokens per second) 10.35.065.850 I slot print_timing: id 0 | task 26028 | total time = 3930.95 ms / 385 tokens 10.35.065.850 I slot print_timing: id 0 | task 26028 | graphs reused = 25199 10.35.065.851 I slot print_timing: id 0 | task 26028 | graph reallocs = 0 / 0 (same size) / (changed size) 10.35.065.872 I slot release: id 0 | task 26028 | stop processing: n_tokens = 384, truncated = 0 10.35.070.376 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.166 (> 0.100 thold), f_keep = 0.096 10.35.072.413 I slot launch_slot_: id 0 | task 26208 | processing task, is_child = 0 10.37.224.898 I slot print_timing: id 0 | task 26208 | prompt eval time = 611.95 ms / 223 tokens ( 2.74 ms per token, 364.41 tokens per second) 10.37.224.902 I slot print_timing: id 0 | task 26208 | eval time = 1540.53 ms / 82 tokens ( 19.02 ms per token, 52.58 tokens per second) 10.37.224.903 I slot print_timing: id 0 | task 26208 | total time = 2152.48 ms / 305 tokens 10.37.224.903 I slot print_timing: id 0 | task 26208 | graphs reused = 25278 10.37.224.904 I slot print_timing: id 0 | task 26208 | graph reallocs = 0 / 0 (same size) / (changed size) 10.37.224.925 I slot release: id 0 | task 26208 | stop processing: n_tokens = 304, truncated = 0 10.37.229.771 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.159 (> 0.100 thold), f_keep = 0.122 10.37.231.696 I slot launch_slot_: id 0 | task 26293 | processing task, is_child = 0 10.40.866.978 I slot print_timing: id 0 | task 26293 | n_gen = 159, tg = 52.66 t/s, tg_3s = 53.00 t/s 10.43.878.917 I slot print_timing: id 0 | task 26293 | n_gen = 317, tg = 52.56 t/s, tg_3s = 52.46 t/s 10.46.892.497 I slot print_timing: id 0 | task 26293 | n_gen = 475, tg = 52.52 t/s, tg_3s = 52.43 t/s 10.49.903.467 I slot print_timing: id 0 | task 26293 | n_gen = 632, tg = 52.42 t/s, tg_3s = 52.14 t/s 10.52.904.723 I slot print_timing: id 0 | task 26293 | n_gen = 788, tg = 52.33 t/s, tg_3s = 51.98 t/s 10.55.913.174 I slot print_timing: id 0 | task 26293 | n_gen = 944, tg = 52.25 t/s, tg_3s = 51.85 t/s 10.57.461.157 I slot print_timing: id 0 | task 26293 | prompt eval time = 635.03 ms / 232 tokens ( 2.74 ms per token, 365.34 tokens per second) 10.57.461.162 I slot print_timing: id 0 | task 26293 | eval time = 19594.43 ms / 1024 tokens ( 19.15 ms per token, 52.21 tokens per second) 10.57.461.163 I slot print_timing: id 0 | task 26293 | total time = 20229.45 ms / 1256 tokens 10.57.461.164 I slot print_timing: id 0 | task 26293 | graphs reused = 26296 10.57.461.164 I slot print_timing: id 0 | task 26293 | graph reallocs = 0 / 0 (same size) / (changed size) 10.57.461.189 I slot release: id 0 | task 26293 | stop processing: n_tokens = 1255, truncated = 0 10.57.465.994 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.172 (> 0.100 thold), f_keep = 0.029 10.57.466.098 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 84.061 MiB) 10.57.466.107 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 116.320 MiB) 10.57.473.406 I slot launch_slot_: id 0 | task 27320 | processing task, is_child = 0 11.01.095.650 I slot print_timing: id 0 | task 27320 | n_gen = 159, tg = 52.65 t/s, tg_3s = 52.99 t/s 11.04.110.386 I slot print_timing: id 0 | task 27320 | n_gen = 317, tg = 52.53 t/s, tg_3s = 52.41 t/s 11.07.122.054 I slot print_timing: id 0 | task 27320 | n_gen = 475, tg = 52.51 t/s, tg_3s = 52.46 t/s 11.07.255.106 I slot print_timing: id 0 | task 27320 | prompt eval time = 621.43 ms / 215 tokens ( 2.89 ms per token, 345.98 tokens per second) 11.07.255.112 I slot print_timing: id 0 | task 27320 | eval time = 9160.26 ms / 482 tokens ( 19.04 ms per token, 52.51 tokens per second) 11.07.255.113 I slot print_timing: id 0 | task 27320 | total time = 9781.69 ms / 697 tokens 11.07.255.114 I slot print_timing: id 0 | task 27320 | graphs reused = 26774 11.07.255.114 I slot print_timing: id 0 | task 27320 | graph reallocs = 0 / 0 (same size) / (changed size) 11.07.255.135 I slot release: id 0 | task 27320 | stop processing: n_tokens = 696, truncated = 0 11.07.259.936 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.164 (> 0.100 thold), f_keep = 0.053 11.07.262.636 I slot launch_slot_: id 0 | task 27805 | processing task, is_child = 0 11.10.811.144 I slot print_timing: id 0 | task 27805 | prompt eval time = 624.00 ms / 226 tokens ( 2.76 ms per token, 362.18 tokens per second) 11.10.811.150 I slot print_timing: id 0 | task 27805 | eval time = 2924.50 ms / 155 tokens ( 18.99 ms per token, 52.66 tokens per second) 11.10.811.151 I slot print_timing: id 0 | task 27805 | total time = 3548.50 ms / 381 tokens 11.10.811.152 I slot print_timing: id 0 | task 27805 | graphs reused = 26926 11.10.811.152 I slot print_timing: id 0 | task 27805 | graph reallocs = 0 / 0 (same size) / (changed size) 11.10.811.173 I slot release: id 0 | task 27805 | stop processing: n_tokens = 380, truncated = 0 11.10.815.752 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.097 11.10.815.806 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 133.879 MiB) 11.10.818.013 I slot launch_slot_: id 0 | task 27963 | processing task, is_child = 0 11.14.405.144 I slot print_timing: id 0 | task 27963 | n_gen = 160, tg = 52.75 t/s, tg_3s = 53.08 t/s 11.14.975.143 I slot print_timing: id 0 | task 27963 | prompt eval time = 572.65 ms / 203 tokens ( 2.82 ms per token, 354.49 tokens per second) 11.14.975.149 I slot print_timing: id 0 | task 27963 | eval time = 3584.47 ms / 190 tokens ( 18.97 ms per token, 52.73 tokens per second) 11.14.975.150 I slot print_timing: id 0 | task 27963 | total time = 4157.12 ms / 393 tokens 11.14.975.150 I slot print_timing: id 0 | task 27963 | graphs reused = 27113 11.14.975.151 I slot print_timing: id 0 | task 27963 | graph reallocs = 0 / 0 (same size) / (changed size) 11.14.975.171 I slot release: id 0 | task 27963 | stop processing: n_tokens = 392, truncated = 0 11.14.979.729 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.094 11.14.983.513 I slot launch_slot_: id 0 | task 28156 | processing task, is_child = 0 11.18.543.204 I slot print_timing: id 0 | task 28156 | n_gen = 160, tg = 52.80 t/s, tg_3s = 53.13 t/s 11.19.188.491 I slot print_timing: id 0 | task 28156 | prompt eval time = 548.48 ms / 179 tokens ( 3.06 ms per token, 326.35 tokens per second) 11.19.188.497 I slot print_timing: id 0 | task 28156 | eval time = 3656.48 ms / 194 tokens ( 18.95 ms per token, 52.78 tokens per second) 11.19.188.498 I slot print_timing: id 0 | task 28156 | total time = 4204.97 ms / 373 tokens 11.19.188.499 I slot print_timing: id 0 | task 28156 | graphs reused = 27304 11.19.188.499 I slot print_timing: id 0 | task 28156 | graph reallocs = 0 / 0 (same size) / (changed size) 11.19.188.521 I slot release: id 0 | task 28156 | stop processing: n_tokens = 372, truncated = 0 11.19.193.388 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.165 (> 0.100 thold), f_keep = 0.099 11.19.193.443 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 109.442 MiB) 11.19.196.077 I slot launch_slot_: id 0 | task 28353 | processing task, is_child = 0 11.22.178.020 I slot print_timing: id 0 | task 28353 | prompt eval time = 624.80 ms / 224 tokens ( 2.79 ms per token, 358.52 tokens per second) 11.22.178.026 I slot print_timing: id 0 | task 28353 | eval time = 2357.13 ms / 125 tokens ( 19.01 ms per token, 52.61 tokens per second) 11.22.178.026 I slot print_timing: id 0 | task 28353 | total time = 2981.93 ms / 349 tokens 11.22.178.027 I slot print_timing: id 0 | task 28353 | graphs reused = 27426 11.22.178.027 I slot print_timing: id 0 | task 28353 | graph reallocs = 0 / 0 (same size) / (changed size) 11.22.178.051 I slot release: id 0 | task 28353 | stop processing: n_tokens = 348, truncated = 0 11.22.183.049 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.163 (> 0.100 thold), f_keep = 0.118 11.22.186.807 I slot launch_slot_: id 0 | task 28481 | processing task, is_child = 0 11.24.257.486 I slot print_timing: id 0 | task 28481 | prompt eval time = 642.65 ms / 252 tokens ( 2.55 ms per token, 392.13 tokens per second) 11.24.257.491 I slot print_timing: id 0 | task 28481 | eval time = 1428.02 ms / 76 tokens ( 19.04 ms per token, 52.52 tokens per second) 11.24.257.492 I slot print_timing: id 0 | task 28481 | total time = 2070.67 ms / 328 tokens 11.24.257.493 I slot print_timing: id 0 | task 28481 | graphs reused = 27499 11.24.257.493 I slot print_timing: id 0 | task 28481 | graph reallocs = 0 / 0 (same size) / (changed size) 11.24.257.519 I slot release: id 0 | task 28481 | stop processing: n_tokens = 327, truncated = 0 11.24.262.017 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.208 (> 0.100 thold), f_keep = 0.113 11.24.262.076 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 79.986 MiB) 11.24.264.041 I slot launch_slot_: id 0 | task 28560 | processing task, is_child = 0 11.26.648.940 I slot print_timing: id 0 | task 28560 | prompt eval time = 564.36 ms / 178 tokens ( 3.17 ms per token, 315.40 tokens per second) 11.26.648.946 I slot print_timing: id 0 | task 28560 | eval time = 1820.53 ms / 97 tokens ( 18.96 ms per token, 52.73 tokens per second) 11.26.648.947 I slot print_timing: id 0 | task 28560 | total time = 2384.89 ms / 275 tokens 11.26.648.947 I slot print_timing: id 0 | task 28560 | graphs reused = 27593 11.26.648.948 I slot print_timing: id 0 | task 28560 | graph reallocs = 0 / 0 (same size) / (changed size) 11.26.648.967 I slot release: id 0 | task 28560 | stop processing: n_tokens = 274, truncated = 0 11.26.653.564 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.135 11.26.653.612 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 90.283 MiB) 11.26.655.991 I slot launch_slot_: id 0 | task 28660 | processing task, is_child = 0 11.28.308.490 I slot print_timing: id 0 | task 28660 | prompt eval time = 554.70 ms / 186 tokens ( 2.98 ms per token, 335.32 tokens per second) 11.28.308.495 I slot print_timing: id 0 | task 28660 | eval time = 1097.79 ms / 59 tokens ( 18.93 ms per token, 52.83 tokens per second) 11.28.308.496 I slot print_timing: id 0 | task 28660 | total time = 1652.49 ms / 245 tokens 11.28.308.497 I slot print_timing: id 0 | task 28660 | graphs reused = 27650 11.28.308.497 I slot print_timing: id 0 | task 28660 | graph reallocs = 0 / 0 (same size) / (changed size) 11.28.308.518 I slot release: id 0 | task 28660 | stop processing: n_tokens = 244, truncated = 0 11.28.312.885 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.196 (> 0.100 thold), f_keep = 0.152 11.28.315.963 I slot launch_slot_: id 0 | task 28722 | processing task, is_child = 0 11.31.888.764 I slot print_timing: id 0 | task 28722 | n_gen = 160, tg = 52.74 t/s, tg_3s = 53.07 t/s 11.34.894.706 I slot print_timing: id 0 | task 28722 | n_gen = 318, tg = 52.65 t/s, tg_3s = 52.56 t/s 11.37.911.689 I slot print_timing: id 0 | task 28722 | n_gen = 476, tg = 52.56 t/s, tg_3s = 52.37 t/s 11.40.916.948 I slot print_timing: id 0 | task 28722 | n_gen = 633, tg = 52.48 t/s, tg_3s = 52.24 t/s 11.43.035.282 I slot print_timing: id 0 | task 28722 | prompt eval time = 558.04 ms / 189 tokens ( 2.95 ms per token, 338.68 tokens per second) 11.43.035.289 I slot print_timing: id 0 | task 28722 | eval time = 14161.27 ms / 743 tokens ( 19.09 ms per token, 52.40 tokens per second) 11.43.035.289 I slot print_timing: id 0 | task 28722 | total time = 14719.31 ms / 932 tokens 11.43.035.290 I slot print_timing: id 0 | task 28722 | graphs reused = 28388 11.43.035.290 I slot print_timing: id 0 | task 28722 | graph reallocs = 0 / 0 (same size) / (changed size) 11.43.035.311 I slot release: id 0 | task 28722 | stop processing: n_tokens = 931, truncated = 0 11.43.039.899 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.177 (> 0.100 thold), f_keep = 0.040 11.43.039.989 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 116.825 MiB) 11.43.047.860 I slot launch_slot_: id 0 | task 29468 | processing task, is_child = 0 11.45.407.745 I slot print_timing: id 0 | task 29468 | prompt eval time = 597.64 ms / 209 tokens ( 2.86 ms per token, 349.71 tokens per second) 11.45.407.751 I slot print_timing: id 0 | task 29468 | eval time = 1762.24 ms / 94 tokens ( 18.95 ms per token, 52.77 tokens per second) 11.45.407.751 I slot print_timing: id 0 | task 29468 | total time = 2359.88 ms / 303 tokens 11.45.407.752 I slot print_timing: id 0 | task 29468 | graphs reused = 28479 11.45.407.753 I slot print_timing: id 0 | task 29468 | graph reallocs = 0 / 0 (same size) / (changed size) 11.45.407.773 I slot release: id 0 | task 29468 | stop processing: n_tokens = 302, truncated = 0 11.45.412.469 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.177 (> 0.100 thold), f_keep = 0.123 11.45.412.519 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.174 MiB) 11.45.417.393 I slot launch_slot_: id 0 | task 29565 | processing task, is_child = 0 11.47.388.167 I slot print_timing: id 0 | task 29565 | prompt eval time = 603.22 ms / 209 tokens ( 2.89 ms per token, 346.48 tokens per second) 11.47.388.175 I slot print_timing: id 0 | task 29565 | eval time = 1367.55 ms / 73 tokens ( 18.99 ms per token, 52.65 tokens per second) 11.47.388.176 I slot print_timing: id 0 | task 29565 | total time = 1970.76 ms / 282 tokens 11.47.388.176 I slot print_timing: id 0 | task 29565 | graphs reused = 28549 11.47.388.177 I slot print_timing: id 0 | task 29565 | graph reallocs = 0 / 0 (same size) / (changed size) 11.47.388.198 I slot release: id 0 | task 29565 | stop processing: n_tokens = 281, truncated = 0 11.47.392.763 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.132 11.47.397.761 I slot launch_slot_: id 0 | task 29641 | processing task, is_child = 0 11.50.602.283 I slot print_timing: id 0 | task 29641 | prompt eval time = 599.32 ms / 208 tokens ( 2.88 ms per token, 347.06 tokens per second) 11.50.602.286 I slot print_timing: id 0 | task 29641 | eval time = 2605.19 ms / 138 tokens ( 19.02 ms per token, 52.59 tokens per second) 11.50.602.286 I slot print_timing: id 0 | task 29641 | total time = 3204.51 ms / 346 tokens 11.50.602.287 I slot print_timing: id 0 | task 29641 | graphs reused = 28684 11.50.602.287 I slot print_timing: id 0 | task 29641 | graph reallocs = 0 / 0 (same size) / (changed size) 11.50.602.313 I slot release: id 0 | task 29641 | stop processing: n_tokens = 345, truncated = 0 11.50.606.657 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.180 (> 0.100 thold), f_keep = 0.107 11.50.606.714 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 134.357 MiB) 11.50.609.401 I slot launch_slot_: id 0 | task 29782 | processing task, is_child = 0 11.54.213.759 I slot print_timing: id 0 | task 29782 | n_gen = 160, tg = 52.73 t/s, tg_3s = 53.06 t/s 11.57.226.389 I slot print_timing: id 0 | task 29782 | n_gen = 318, tg = 52.59 t/s, tg_3s = 52.45 t/s 11.58.504.343 I slot print_timing: id 0 | task 29782 | prompt eval time = 588.78 ms / 206 tokens ( 2.86 ms per token, 349.87 tokens per second) 11.58.504.349 I slot print_timing: id 0 | task 29782 | eval time = 7306.15 ms / 385 tokens ( 19.03 ms per token, 52.56 tokens per second) 11.58.504.349 I slot print_timing: id 0 | task 29782 | total time = 7894.93 ms / 591 tokens 11.58.504.350 I slot print_timing: id 0 | task 29782 | graphs reused = 29065 11.58.504.351 I slot print_timing: id 0 | task 29782 | graph reallocs = 0 / 0 (same size) / (changed size) 11.58.504.372 I slot release: id 0 | task 29782 | stop processing: n_tokens = 590, truncated = 0 11.58.509.001 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.063 11.58.513.332 I slot launch_slot_: id 0 | task 30170 | processing task, is_child = 0 12.02.097.759 I slot print_timing: id 0 | task 30170 | n_gen = 159, tg = 52.66 t/s, tg_3s = 52.99 t/s 12.04.074.513 I slot print_timing: id 0 | task 30170 | prompt eval time = 583.86 ms / 208 tokens ( 2.81 ms per token, 356.25 tokens per second) 12.04.074.516 I slot print_timing: id 0 | task 30170 | eval time = 4977.31 ms / 263 tokens ( 19.00 ms per token, 52.64 tokens per second) 12.04.074.517 I slot print_timing: id 0 | task 30170 | total time = 5561.17 ms / 471 tokens 12.04.074.518 I slot print_timing: id 0 | task 30170 | graphs reused = 29325 12.04.074.518 I slot print_timing: id 0 | task 30170 | graph reallocs = 0 / 0 (same size) / (changed size) 12.04.074.541 I slot release: id 0 | task 30170 | stop processing: n_tokens = 470, truncated = 0 12.04.079.239 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.167 (> 0.100 thold), f_keep = 0.079 12.04.079.303 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.172 MiB) 12.04.083.301 I slot launch_slot_: id 0 | task 30436 | processing task, is_child = 0 12.06.315.839 I slot print_timing: id 0 | task 30436 | prompt eval time = 617.16 ms / 221 tokens ( 2.79 ms per token, 358.09 tokens per second) 12.06.315.843 I slot print_timing: id 0 | task 30436 | eval time = 1615.36 ms / 86 tokens ( 19.00 ms per token, 52.62 tokens per second) 12.06.315.844 I slot print_timing: id 0 | task 30436 | total time = 2232.52 ms / 307 tokens 12.06.315.844 I slot print_timing: id 0 | task 30436 | graphs reused = 29408 12.06.315.845 I slot print_timing: id 0 | task 30436 | graph reallocs = 0 / 0 (same size) / (changed size) 12.06.315.865 I slot release: id 0 | task 30436 | stop processing: n_tokens = 306, truncated = 0 12.06.320.492 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.180 (> 0.100 thold), f_keep = 0.124 12.06.324.108 I slot launch_slot_: id 0 | task 30525 | processing task, is_child = 0 12.08.763.466 I slot print_timing: id 0 | task 30525 | prompt eval time = 598.12 ms / 211 tokens ( 2.83 ms per token, 352.77 tokens per second) 12.08.763.473 I slot print_timing: id 0 | task 30525 | eval time = 1841.22 ms / 98 tokens ( 18.98 ms per token, 52.68 tokens per second) 12.08.763.474 I slot print_timing: id 0 | task 30525 | total time = 2439.34 ms / 309 tokens 12.08.763.474 I slot print_timing: id 0 | task 30525 | graphs reused = 29503 12.08.763.475 I slot print_timing: id 0 | task 30525 | graph reallocs = 0 / 0 (same size) / (changed size) 12.08.763.497 I slot release: id 0 | task 30525 | stop processing: n_tokens = 308, truncated = 0 12.08.768.168 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.120 12.08.768.217 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 114.090 MiB) 12.08.772.344 I slot launch_slot_: id 0 | task 30626 | processing task, is_child = 0 12.10.839.289 I slot print_timing: id 0 | task 30626 | prompt eval time = 624.56 ms / 217 tokens ( 2.88 ms per token, 347.45 tokens per second) 12.10.839.295 I slot print_timing: id 0 | task 30626 | eval time = 1442.38 ms / 77 tokens ( 18.98 ms per token, 52.69 tokens per second) 12.10.839.296 I slot print_timing: id 0 | task 30626 | total time = 2066.93 ms / 294 tokens 12.10.839.297 I slot print_timing: id 0 | task 30626 | graphs reused = 29577 12.10.839.297 I slot print_timing: id 0 | task 30626 | graph reallocs = 0 / 0 (same size) / (changed size) 12.10.839.321 I slot release: id 0 | task 30626 | stop processing: n_tokens = 293, truncated = 0 12.10.843.911 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.167 (> 0.100 thold), f_keep = 0.126 12.10.848.879 I slot launch_slot_: id 0 | task 30706 | processing task, is_child = 0 12.13.967.736 I slot print_timing: id 0 | task 30706 | prompt eval time = 590.76 ms / 221 tokens ( 2.67 ms per token, 374.09 tokens per second) 12.13.967.742 I slot print_timing: id 0 | task 30706 | eval time = 2528.09 ms / 134 tokens ( 19.01 ms per token, 52.61 tokens per second) 12.13.967.743 I slot print_timing: id 0 | task 30706 | total time = 3118.85 ms / 355 tokens 12.13.967.743 I slot print_timing: id 0 | task 30706 | graphs reused = 29708 12.13.967.744 I slot print_timing: id 0 | task 30706 | graph reallocs = 0 / 0 (same size) / (changed size) 12.13.967.766 I slot release: id 0 | task 30706 | stop processing: n_tokens = 354, truncated = 0 12.13.972.411 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.159 (> 0.100 thold), f_keep = 0.105 12.13.972.464 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 109.427 MiB) 12.13.975.993 I slot launch_slot_: id 0 | task 30843 | processing task, is_child = 0 12.15.767.062 I slot print_timing: id 0 | task 30843 | prompt eval time = 628.66 ms / 232 tokens ( 2.71 ms per token, 369.04 tokens per second) 12.15.767.068 I slot print_timing: id 0 | task 30843 | eval time = 1162.40 ms / 62 tokens ( 19.06 ms per token, 52.48 tokens per second) 12.15.767.069 I slot print_timing: id 0 | task 30843 | total time = 1791.06 ms / 294 tokens 12.15.767.069 I slot print_timing: id 0 | task 30843 | graphs reused = 29767 12.15.767.070 I slot print_timing: id 0 | task 30843 | graph reallocs = 0 / 0 (same size) / (changed size) 12.15.767.094 I slot release: id 0 | task 30843 | stop processing: n_tokens = 293, truncated = 0 12.15.771.746 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.165 (> 0.100 thold), f_keep = 0.126 12.15.774.643 I slot launch_slot_: id 0 | task 30908 | processing task, is_child = 0 12.19.389.209 I slot print_timing: id 0 | task 30908 | n_gen = 160, tg = 52.67 t/s, tg_3s = 53.00 t/s 12.20.815.325 I slot print_timing: id 0 | task 30908 | prompt eval time = 595.90 ms / 224 tokens ( 2.66 ms per token, 375.90 tokens per second) 12.20.815.331 I slot print_timing: id 0 | task 30908 | eval time = 4444.77 ms / 235 tokens ( 18.99 ms per token, 52.65 tokens per second) 12.20.815.332 I slot print_timing: id 0 | task 30908 | total time = 5040.67 ms / 459 tokens 12.20.815.333 I slot print_timing: id 0 | task 30908 | graphs reused = 29999 12.20.815.333 I slot print_timing: id 0 | task 30908 | graph reallocs = 0 / 0 (same size) / (changed size) 12.20.815.354 I slot release: id 0 | task 30908 | stop processing: n_tokens = 458, truncated = 0 12.20.820.150 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.159 (> 0.100 thold), f_keep = 0.081 12.20.820.212 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 126.576 MiB) 12.20.824.314 I slot launch_slot_: id 0 | task 31146 | processing task, is_child = 0 12.24.451.025 I slot print_timing: id 0 | task 31146 | n_gen = 160, tg = 52.68 t/s, tg_3s = 53.01 t/s 12.24.831.719 I slot print_timing: id 0 | task 31146 | prompt eval time = 608.20 ms / 233 tokens ( 2.61 ms per token, 383.10 tokens per second) 12.24.831.722 I slot print_timing: id 0 | task 31146 | eval time = 3399.20 ms / 180 tokens ( 18.99 ms per token, 52.66 tokens per second) 12.24.831.723 I slot print_timing: id 0 | task 31146 | total time = 4007.40 ms / 413 tokens 12.24.831.723 I slot print_timing: id 0 | task 31146 | graphs reused = 30176 12.24.831.724 I slot print_timing: id 0 | task 31146 | graph reallocs = 0 / 0 (same size) / (changed size) 12.24.831.746 I slot release: id 0 | task 31146 | stop processing: n_tokens = 412, truncated = 0 12.24.836.657 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.167 (> 0.100 thold), f_keep = 0.095 12.24.836.718 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 136.272 MiB) 12.24.840.883 I slot launch_slot_: id 0 | task 31329 | processing task, is_child = 0 12.28.451.399 I slot print_timing: id 0 | task 31329 | n_gen = 159, tg = 52.63 t/s, tg_3s = 52.96 t/s 12.29.154.936 I slot print_timing: id 0 | task 31329 | prompt eval time = 608.26 ms / 233 tokens ( 2.61 ms per token, 383.06 tokens per second) 12.29.154.939 I slot print_timing: id 0 | task 31329 | eval time = 3705.79 ms / 196 tokens ( 19.00 ms per token, 52.62 tokens per second) 12.29.154.939 I slot print_timing: id 0 | task 31329 | total time = 4314.04 ms / 429 tokens 12.29.154.940 I slot print_timing: id 0 | task 31329 | graphs reused = 30369 12.29.154.941 I slot print_timing: id 0 | task 31329 | graph reallocs = 0 / 0 (same size) / (changed size) 12.29.154.965 I slot release: id 0 | task 31329 | stop processing: n_tokens = 428, truncated = 0 12.29.159.930 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.143 (> 0.100 thold), f_keep = 0.086 12.29.164.399 I slot launch_slot_: id 0 | task 31528 | processing task, is_child = 0 12.31.882.475 I slot print_timing: id 0 | task 31528 | prompt eval time = 645.73 ms / 259 tokens ( 2.49 ms per token, 401.09 tokens per second) 12.31.882.479 I slot print_timing: id 0 | task 31528 | eval time = 2072.33 ms / 110 tokens ( 19.01 ms per token, 52.60 tokens per second) 12.31.882.479 I slot print_timing: id 0 | task 31528 | total time = 2718.06 ms / 369 tokens 12.31.882.480 I slot print_timing: id 0 | task 31528 | graphs reused = 30477 12.31.882.480 I slot print_timing: id 0 | task 31528 | graph reallocs = 0 / 0 (same size) / (changed size) 12.31.882.503 I slot release: id 0 | task 31528 | stop processing: n_tokens = 368, truncated = 0 12.31.887.224 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.173 (> 0.100 thold), f_keep = 0.101 12.31.887.285 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 67.064 MiB) 12.31.889.503 I slot launch_slot_: id 0 | task 31641 | processing task, is_child = 0 12.34.022.314 I slot print_timing: id 0 | task 31641 | prompt eval time = 612.48 ms / 214 tokens ( 2.86 ms per token, 349.40 tokens per second) 12.34.022.317 I slot print_timing: id 0 | task 31641 | eval time = 1520.32 ms / 81 tokens ( 19.00 ms per token, 52.62 tokens per second) 12.34.022.318 I slot print_timing: id 0 | task 31641 | total time = 2132.80 ms / 295 tokens 12.34.022.318 I slot print_timing: id 0 | task 31641 | graphs reused = 30555 12.34.022.319 I slot print_timing: id 0 | task 31641 | graph reallocs = 0 / 0 (same size) / (changed size) 12.34.022.338 I slot release: id 0 | task 31641 | stop processing: n_tokens = 294, truncated = 0 12.34.397.582 I srv operator(): operator(): cleaning up before exit...