$ /Users/minipro/quantdiff/work/llama-b11869/src/build/bin/llama-server -m /Users/minipro/quantdiff/models/campaign/91b8d85ab6ff/flint-UD-Q3_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 0.00.042.557 I srv llama_server: initializing ... 0.00.042.564 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.044.461 I srv init_listene: The UI is disabled 0.00.044.463 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.044.869 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) 0.00.046.953 I srv load_model: loading model '/Users/minipro/quantdiff/models/campaign/91b8d85ab6ff/flint-UD-Q3_K_XL.gguf' 0.01.046.000 I cmn init: llama threadpool init, n_threads = 8 0.01.532.053 I srv load_model: initializing, n_slots = 1, n_ctx_slot = 4096, kv_unified = 'false' 0.01.541.755 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.01.541.774 I srv server_run_i: model loaded 0.01.541.778 I srv server_on_li: listening on http://127.0.0.1:8089 0.02.020.011 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.02.020.433 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.06.224.720 I slot print_timing: id 0 | task 0 | prompt eval time = 1429.84 ms / 221 tokens ( 6.47 ms per token, 154.56 tokens per second) 0.06.224.726 I slot print_timing: id 0 | task 0 | eval time = 2774.41 ms / 136 tokens ( 20.55 ms per token, 48.66 tokens per second) 0.06.224.727 I slot print_timing: id 0 | task 0 | total time = 4204.25 ms / 357 tokens 0.06.224.728 I slot print_timing: id 0 | task 0 | graphs reused = 134 0.06.224.728 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.06.224.748 I slot release: id 0 | task 0 | stop processing: n_tokens = 356, truncated = 0 0.06.230.023 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.211 (> 0.100 thold), f_keep = 0.104 0.06.235.891 I slot launch_slot_: id 0 | task 139 | processing task, is_child = 0 0.08.361.377 I slot print_timing: id 0 | task 139 | prompt eval time = 549.28 ms / 175 tokens ( 3.14 ms per token, 318.60 tokens per second) 0.08.361.380 I slot print_timing: id 0 | task 139 | eval time = 1576.19 ms / 78 tokens ( 20.47 ms per token, 48.85 tokens per second) 0.08.361.381 I slot print_timing: id 0 | task 139 | total time = 2125.47 ms / 253 tokens 0.08.361.381 I slot print_timing: id 0 | task 139 | graphs reused = 210 0.08.361.382 I slot print_timing: id 0 | task 139 | graph reallocs = 0 / 0 (same size) / (changed size) 0.08.361.400 I slot release: id 0 | task 139 | stop processing: n_tokens = 252, truncated = 0 0.08.366.076 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.174 (> 0.100 thold), f_keep = 0.147 0.08.370.599 I slot launch_slot_: id 0 | task 220 | processing task, is_child = 0 0.10.521.841 I slot print_timing: id 0 | task 220 | prompt eval time = 626.41 ms / 213 tokens ( 2.94 ms per token, 340.03 tokens per second) 0.10.521.847 I slot print_timing: id 0 | task 220 | eval time = 1524.83 ms / 75 tokens ( 20.61 ms per token, 48.53 tokens per second) 0.10.521.848 I slot print_timing: id 0 | task 220 | total time = 2151.23 ms / 288 tokens 0.10.521.848 I slot print_timing: id 0 | task 220 | graphs reused = 282 0.10.521.849 I slot print_timing: id 0 | task 220 | graph reallocs = 0 / 0 (same size) / (changed size) 0.10.521.869 I slot release: id 0 | task 220 | stop processing: n_tokens = 287, truncated = 0 0.10.526.812 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.150 (> 0.100 thold), f_keep = 0.129 0.10.532.043 I slot launch_slot_: id 0 | task 298 | processing task, is_child = 0 0.13.091.963 I slot print_timing: id 0 | task 298 | prompt eval time = 681.42 ms / 247 tokens ( 2.76 ms per token, 362.48 tokens per second) 0.13.091.969 I slot print_timing: id 0 | task 298 | eval time = 1878.49 ms / 92 tokens ( 20.64 ms per token, 48.44 tokens per second) 0.13.091.970 I slot print_timing: id 0 | task 298 | total time = 2559.91 ms / 339 tokens 0.13.091.970 I slot print_timing: id 0 | task 298 | graphs reused = 371 0.13.091.971 I slot print_timing: id 0 | task 298 | graph reallocs = 0 / 0 (same size) / (changed size) 0.13.091.993 I slot release: id 0 | task 298 | stop processing: n_tokens = 338, truncated = 0 0.13.096.825 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 0.13.102.832 I slot launch_slot_: id 0 | task 393 | processing task, is_child = 0 0.16.861.151 I slot print_timing: id 0 | task 393 | n_gen = 147, tg = 48.54 t/s, tg_3s = 48.87 t/s 0.18.676.326 I slot print_timing: id 0 | task 393 | prompt eval time = 750.33 ms / 236 tokens ( 3.18 ms per token, 314.53 tokens per second) 0.18.676.332 I slot print_timing: id 0 | task 393 | eval time = 4823.15 ms / 235 tokens ( 20.61 ms per token, 48.52 tokens per second) 0.18.676.333 I slot print_timing: id 0 | task 393 | total time = 5573.48 ms / 471 tokens 0.18.676.334 I slot print_timing: id 0 | task 393 | graphs reused = 603 0.18.676.334 I slot print_timing: id 0 | task 393 | graph reallocs = 0 / 0 (same size) / (changed size) 0.18.676.356 I slot release: id 0 | task 393 | stop processing: n_tokens = 470, truncated = 0 0.18.681.198 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.164 (> 0.100 thold), f_keep = 0.079 0.18.687.501 I slot launch_slot_: id 0 | task 631 | processing task, is_child = 0 0.20.964.296 I slot print_timing: id 0 | task 631 | prompt eval time = 606.01 ms / 226 tokens ( 2.68 ms per token, 372.93 tokens per second) 0.20.964.301 I slot print_timing: id 0 | task 631 | eval time = 1670.78 ms / 82 tokens ( 20.63 ms per token, 48.48 tokens per second) 0.20.964.302 I slot print_timing: id 0 | task 631 | total time = 2276.78 ms / 308 tokens 0.20.964.302 I slot print_timing: id 0 | task 631 | graphs reused = 682 0.20.964.303 I slot print_timing: id 0 | task 631 | graph reallocs = 0 / 0 (same size) / (changed size) 0.20.964.323 I slot release: id 0 | task 631 | stop processing: n_tokens = 307, truncated = 0 0.20.969.331 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.137 (> 0.100 thold), f_keep = 0.121 0.20.975.005 I slot launch_slot_: id 0 | task 716 | processing task, is_child = 0 0.23.687.754 I slot print_timing: id 0 | task 716 | prompt eval time = 711.74 ms / 270 tokens ( 2.64 ms per token, 379.35 tokens per second) 0.23.687.758 I slot print_timing: id 0 | task 716 | eval time = 2000.99 ms / 98 tokens ( 20.63 ms per token, 48.48 tokens per second) 0.23.687.760 I slot print_timing: id 0 | task 716 | total time = 2712.74 ms / 368 tokens 0.23.687.760 I slot print_timing: id 0 | task 716 | graphs reused = 778 0.23.687.761 I slot print_timing: id 0 | task 716 | graph reallocs = 0 / 0 (same size) / (changed size) 0.23.687.782 I slot release: id 0 | task 716 | stop processing: n_tokens = 367, truncated = 0 0.23.693.034 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.116 (> 0.100 thold), f_keep = 0.101 0.23.699.671 I slot launch_slot_: id 0 | task 817 | processing task, is_child = 0 0.27.491.795 I slot print_timing: id 0 | task 817 | n_gen = 147, tg = 48.44 t/s, tg_3s = 48.77 t/s 0.29.956.303 I slot print_timing: id 0 | task 817 | prompt eval time = 777.88 ms / 318 tokens ( 2.45 ms per token, 408.80 tokens per second) 0.29.956.310 I slot print_timing: id 0 | task 817 | eval time = 5478.74 ms / 266 tokens ( 20.67 ms per token, 48.37 tokens per second) 0.29.956.310 I slot print_timing: id 0 | task 817 | total time = 6256.62 ms / 584 tokens 0.29.956.311 I slot print_timing: id 0 | task 817 | graphs reused = 1041 0.29.956.312 I slot print_timing: id 0 | task 817 | graph reallocs = 0 / 0 (same size) / (changed size) 0.29.956.336 I slot release: id 0 | task 817 | stop processing: n_tokens = 583, truncated = 0 0.29.961.040 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.063 0.29.969.934 I slot launch_slot_: id 0 | task 1086 | processing task, is_child = 0 0.32.419.004 I slot print_timing: id 0 | task 1086 | prompt eval time = 618.12 ms / 197 tokens ( 3.14 ms per token, 318.71 tokens per second) 0.32.419.010 I slot print_timing: id 0 | task 1086 | eval time = 1830.95 ms / 90 tokens ( 20.57 ms per token, 48.61 tokens per second) 0.32.419.011 I slot print_timing: id 0 | task 1086 | total time = 2449.06 ms / 287 tokens 0.32.419.012 I slot print_timing: id 0 | task 1086 | graphs reused = 1128 0.32.419.012 I slot print_timing: id 0 | task 1086 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.419.032 I slot release: id 0 | task 1086 | stop processing: n_tokens = 286, truncated = 0 0.32.425.519 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.129 0.32.429.030 I slot launch_slot_: id 0 | task 1179 | processing task, is_child = 0 0.35.166.447 I slot print_timing: id 0 | task 1179 | prompt eval time = 639.33 ms / 216 tokens ( 2.96 ms per token, 337.86 tokens per second) 0.35.166.453 I slot print_timing: id 0 | task 1179 | eval time = 2098.08 ms / 103 tokens ( 20.57 ms per token, 48.62 tokens per second) 0.35.166.454 I slot print_timing: id 0 | task 1179 | total time = 2737.40 ms / 319 tokens 0.35.166.454 I slot print_timing: id 0 | task 1179 | graphs reused = 1228 0.35.166.455 I slot print_timing: id 0 | task 1179 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.166.477 I slot release: id 0 | task 1179 | stop processing: n_tokens = 318, truncated = 0 0.35.171.407 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.165 (> 0.100 thold), f_keep = 0.116 0.35.175.296 I slot launch_slot_: id 0 | task 1285 | processing task, is_child = 0 0.38.781.056 I slot print_timing: id 0 | task 1285 | n_gen = 147, tg = 48.57 t/s, tg_3s = 48.91 t/s 0.41.669.441 I slot print_timing: id 0 | task 1285 | prompt eval time = 599.93 ms / 224 tokens ( 2.68 ms per token, 373.38 tokens per second) 0.41.669.448 I slot print_timing: id 0 | task 1285 | eval time = 5894.20 ms / 287 tokens ( 20.61 ms per token, 48.52 tokens per second) 0.41.669.449 I slot print_timing: id 0 | task 1285 | total time = 6494.13 ms / 511 tokens 0.41.669.449 I slot print_timing: id 0 | task 1285 | graphs reused = 1512 0.41.669.450 I slot print_timing: id 0 | task 1285 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.669.473 I slot release: id 0 | task 1285 | stop processing: n_tokens = 510, truncated = 0 0.41.674.602 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.143 (> 0.100 thold), f_keep = 0.073 0.41.682.338 I slot launch_slot_: id 0 | task 1575 | processing task, is_child = 0 0.44.669.431 I slot print_timing: id 0 | task 1575 | prompt eval time = 701.11 ms / 259 tokens ( 2.71 ms per token, 369.41 tokens per second) 0.44.669.434 I slot print_timing: id 0 | task 1575 | eval time = 2285.97 ms / 112 tokens ( 20.59 ms per token, 48.56 tokens per second) 0.44.669.434 I slot print_timing: id 0 | task 1575 | total time = 2987.08 ms / 371 tokens 0.44.669.435 I slot print_timing: id 0 | task 1575 | graphs reused = 1622 0.44.669.436 I slot print_timing: id 0 | task 1575 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.669.458 I slot release: id 0 | task 1575 | stop processing: n_tokens = 370, truncated = 0 0.44.674.326 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.165 (> 0.100 thold), f_keep = 0.100 0.44.681.252 I slot launch_slot_: id 0 | task 1690 | processing task, is_child = 0 0.47.827.206 I slot print_timing: id 0 | task 1690 | prompt eval time = 671.75 ms / 224 tokens ( 3.00 ms per token, 333.46 tokens per second) 0.47.827.212 I slot print_timing: id 0 | task 1690 | eval time = 2474.19 ms / 121 tokens ( 20.62 ms per token, 48.50 tokens per second) 0.47.827.213 I slot print_timing: id 0 | task 1690 | total time = 3145.94 ms / 345 tokens 0.47.827.213 I slot print_timing: id 0 | task 1690 | graphs reused = 1740 0.47.827.214 I slot print_timing: id 0 | task 1690 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.827.234 I slot release: id 0 | task 1690 | stop processing: n_tokens = 344, truncated = 0 0.47.832.520 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.163 (> 0.100 thold), f_keep = 0.108 0.47.837.141 I slot launch_slot_: id 0 | task 1814 | processing task, is_child = 0 0.50.758.295 I slot print_timing: id 0 | task 1814 | prompt eval time = 622.87 ms / 227 tokens ( 2.74 ms per token, 364.44 tokens per second) 0.50.758.299 I slot print_timing: id 0 | task 1814 | eval time = 2298.28 ms / 112 tokens ( 20.71 ms per token, 48.30 tokens per second) 0.50.758.299 I slot print_timing: id 0 | task 1814 | total time = 2921.15 ms / 339 tokens 0.50.758.300 I slot print_timing: id 0 | task 1814 | graphs reused = 1849 0.50.758.300 I slot print_timing: id 0 | task 1814 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.758.323 I slot release: id 0 | task 1814 | stop processing: n_tokens = 338, truncated = 0 0.50.763.164 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.167 (> 0.100 thold), f_keep = 0.109 0.50.769.410 I slot launch_slot_: id 0 | task 1929 | processing task, is_child = 0 0.53.126.137 I slot print_timing: id 0 | task 1929 | prompt eval time = 624.48 ms / 222 tokens ( 2.81 ms per token, 355.50 tokens per second) 0.53.126.144 I slot print_timing: id 0 | task 1929 | eval time = 1732.24 ms / 85 tokens ( 20.62 ms per token, 48.49 tokens per second) 0.53.126.144 I slot print_timing: id 0 | task 1929 | total time = 2356.72 ms / 307 tokens 0.53.126.145 I slot print_timing: id 0 | task 1929 | graphs reused = 1931 0.53.126.146 I slot print_timing: id 0 | task 1929 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.126.166 I slot release: id 0 | task 1929 | stop processing: n_tokens = 306, truncated = 0 0.53.130.744 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.121 0.53.136.418 I slot launch_slot_: id 0 | task 2017 | processing task, is_child = 0 0.55.834.930 I slot print_timing: id 0 | task 2017 | prompt eval time = 620.62 ms / 203 tokens ( 3.06 ms per token, 327.09 tokens per second) 0.55.834.933 I slot print_timing: id 0 | task 2017 | eval time = 2077.88 ms / 102 tokens ( 20.57 ms per token, 48.61 tokens per second) 0.55.834.934 I slot print_timing: id 0 | task 2017 | total time = 2698.50 ms / 305 tokens 0.55.834.934 I slot print_timing: id 0 | task 2017 | graphs reused = 2030 0.55.834.935 I slot print_timing: id 0 | task 2017 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.834.954 I slot release: id 0 | task 2017 | stop processing: n_tokens = 304, truncated = 0 0.55.840.234 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.166 (> 0.100 thold), f_keep = 0.122 0.55.844.904 I slot launch_slot_: id 0 | task 2122 | processing task, is_child = 0 0.58.869.842 I slot print_timing: id 0 | task 2122 | prompt eval time = 659.63 ms / 223 tokens ( 2.96 ms per token, 338.07 tokens per second) 0.58.869.847 I slot print_timing: id 0 | task 2122 | eval time = 2365.29 ms / 116 tokens ( 20.57 ms per token, 48.62 tokens per second) 0.58.869.848 I slot print_timing: id 0 | task 2122 | total time = 3024.92 ms / 339 tokens 0.58.869.849 I slot print_timing: id 0 | task 2122 | graphs reused = 2143 0.58.869.849 I slot print_timing: id 0 | task 2122 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.869.870 I slot release: id 0 | task 2122 | stop processing: n_tokens = 338, truncated = 0 0.58.874.897 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.180 (> 0.100 thold), f_keep = 0.109 0.58.881.178 I slot launch_slot_: id 0 | task 2241 | processing task, is_child = 0 1.01.467.361 I slot print_timing: id 0 | task 2241 | prompt eval time = 591.86 ms / 206 tokens ( 2.87 ms per token, 348.06 tokens per second) 1.01.467.365 I slot print_timing: id 0 | task 2241 | eval time = 1994.32 ms / 98 tokens ( 20.56 ms per token, 48.64 tokens per second) 1.01.467.365 I slot print_timing: id 0 | task 2241 | total time = 2586.17 ms / 304 tokens 1.01.467.366 I slot print_timing: id 0 | task 2241 | graphs reused = 2238 1.01.467.367 I slot print_timing: id 0 | task 2241 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.467.387 I slot release: id 0 | task 2241 | stop processing: n_tokens = 303, truncated = 0 1.01.472.069 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.183 (> 0.100 thold), f_keep = 0.122 1.01.477.688 I slot launch_slot_: id 0 | task 2342 | processing task, is_child = 0 1.03.590.962 I slot print_timing: id 0 | task 2342 | prompt eval time = 587.08 ms / 202 tokens ( 2.91 ms per token, 344.07 tokens per second) 1.03.590.969 I slot print_timing: id 0 | task 2342 | eval time = 1526.18 ms / 75 tokens ( 20.62 ms per token, 48.49 tokens per second) 1.03.590.970 I slot print_timing: id 0 | task 2342 | total time = 2113.27 ms / 277 tokens 1.03.590.971 I slot print_timing: id 0 | task 2342 | graphs reused = 2310 1.03.590.971 I slot print_timing: id 0 | task 2342 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.590.990 I slot release: id 0 | task 2342 | stop processing: n_tokens = 276, truncated = 0 1.03.595.858 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.134 1.03.601.087 I slot launch_slot_: id 0 | task 2420 | processing task, is_child = 0 1.06.254.831 I slot print_timing: id 0 | task 2420 | prompt eval time = 694.15 ms / 237 tokens ( 2.93 ms per token, 341.42 tokens per second) 1.06.254.838 I slot print_timing: id 0 | task 2420 | eval time = 1959.58 ms / 96 tokens ( 20.63 ms per token, 48.48 tokens per second) 1.06.254.839 I slot print_timing: id 0 | task 2420 | total time = 2653.73 ms / 333 tokens 1.06.254.839 I slot print_timing: id 0 | task 2420 | graphs reused = 2403 1.06.254.840 I slot print_timing: id 0 | task 2420 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.254.861 I slot release: id 0 | task 2420 | stop processing: n_tokens = 332, truncated = 0 1.06.259.541 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.111 1.06.265.705 I slot launch_slot_: id 0 | task 2519 | processing task, is_child = 0 1.08.919.108 I slot print_timing: id 0 | task 2519 | prompt eval time = 625.94 ms / 208 tokens ( 3.01 ms per token, 332.30 tokens per second) 1.08.919.112 I slot print_timing: id 0 | task 2519 | eval time = 2027.45 ms / 98 tokens ( 20.90 ms per token, 47.84 tokens per second) 1.08.919.113 I slot print_timing: id 0 | task 2519 | total time = 2653.39 ms / 306 tokens 1.08.919.113 I slot print_timing: id 0 | task 2519 | graphs reused = 2498 1.08.919.114 I slot print_timing: id 0 | task 2519 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.919.136 I slot release: id 0 | task 2519 | stop processing: n_tokens = 305, truncated = 0 1.08.923.811 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.142 (> 0.100 thold), f_keep = 0.121 1.08.928.401 I slot launch_slot_: id 0 | task 2620 | processing task, is_child = 0 1.12.137.834 I slot print_timing: id 0 | task 2620 | prompt eval time = 707.28 ms / 261 tokens ( 2.71 ms per token, 369.02 tokens per second) 1.12.137.837 I slot print_timing: id 0 | task 2620 | eval time = 2502.14 ms / 122 tokens ( 20.68 ms per token, 48.36 tokens per second) 1.12.137.838 I slot print_timing: id 0 | task 2620 | total time = 3209.42 ms / 383 tokens 1.12.137.838 I slot print_timing: id 0 | task 2620 | graphs reused = 2618 1.12.137.839 I slot print_timing: id 0 | task 2620 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.137.860 I slot release: id 0 | task 2620 | stop processing: n_tokens = 382, truncated = 0 1.12.142.762 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.155 (> 0.100 thold), f_keep = 0.097 1.12.150.143 I slot launch_slot_: id 0 | task 2745 | processing task, is_child = 0 1.15.801.003 I slot print_timing: id 0 | task 2745 | n_gen = 147, tg = 48.55 t/s, tg_3s = 48.89 t/s 1.17.658.073 I slot print_timing: id 0 | task 2745 | prompt eval time = 643.82 ms / 238 tokens ( 2.71 ms per token, 369.67 tokens per second) 1.17.658.078 I slot print_timing: id 0 | task 2745 | eval time = 4864.09 ms / 237 tokens ( 20.61 ms per token, 48.52 tokens per second) 1.17.658.079 I slot print_timing: id 0 | task 2745 | total time = 5507.91 ms / 475 tokens 1.17.658.079 I slot print_timing: id 0 | task 2745 | graphs reused = 2852 1.17.658.080 I slot print_timing: id 0 | task 2745 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.658.101 I slot release: id 0 | task 2745 | stop processing: n_tokens = 474, truncated = 0 1.17.663.261 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.150 (> 0.100 thold), f_keep = 0.078 1.17.669.865 I slot launch_slot_: id 0 | task 2985 | processing task, is_child = 0 1.21.083.613 I slot print_timing: id 0 | task 2985 | prompt eval time = 753.79 ms / 247 tokens ( 3.05 ms per token, 327.68 tokens per second) 1.21.083.617 I slot print_timing: id 0 | task 2985 | eval time = 2659.95 ms / 130 tokens ( 20.62 ms per token, 48.50 tokens per second) 1.21.083.618 I slot print_timing: id 0 | task 2985 | total time = 3413.74 ms / 377 tokens 1.21.083.618 I slot print_timing: id 0 | task 2985 | graphs reused = 2979 1.21.083.619 I slot print_timing: id 0 | task 2985 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.083.641 I slot release: id 0 | task 2985 | stop processing: n_tokens = 376, truncated = 0 1.21.088.876 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.131 (> 0.100 thold), f_keep = 0.098 1.21.095.518 I slot launch_slot_: id 0 | task 3118 | processing task, is_child = 0 1.23.776.448 I slot print_timing: id 0 | task 3118 | prompt eval time = 785.11 ms / 282 tokens ( 2.78 ms per token, 359.18 tokens per second) 1.23.776.455 I slot print_timing: id 0 | task 3118 | eval time = 1895.81 ms / 93 tokens ( 20.61 ms per token, 48.53 tokens per second) 1.23.776.456 I slot print_timing: id 0 | task 3118 | total time = 2680.92 ms / 375 tokens 1.23.776.457 I slot print_timing: id 0 | task 3118 | graphs reused = 3070 1.23.776.457 I slot print_timing: id 0 | task 3118 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.776.482 I slot release: id 0 | task 3118 | stop processing: n_tokens = 374, truncated = 0 1.23.781.377 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.102 1.23.788.413 I slot launch_slot_: id 0 | task 3214 | processing task, is_child = 0 1.27.502.845 I slot print_timing: id 0 | task 3214 | n_gen = 147, tg = 48.50 t/s, tg_3s = 48.83 t/s 1.29.215.691 I slot print_timing: id 0 | task 3214 | prompt eval time = 704.18 ms / 243 tokens ( 2.90 ms per token, 345.08 tokens per second) 1.29.215.697 I slot print_timing: id 0 | task 3214 | eval time = 4723.09 ms / 230 tokens ( 20.62 ms per token, 48.49 tokens per second) 1.29.215.698 I slot print_timing: id 0 | task 3214 | total time = 5427.27 ms / 473 tokens 1.29.215.699 I slot print_timing: id 0 | task 3214 | graphs reused = 3297 1.29.215.699 I slot print_timing: id 0 | task 3214 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.215.720 I slot release: id 0 | task 3214 | stop processing: n_tokens = 472, truncated = 0 1.29.220.512 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.078 1.29.227.140 I slot launch_slot_: id 0 | task 3447 | processing task, is_child = 0 1.31.419.715 I slot print_timing: id 0 | task 3447 | prompt eval time = 588.26 ms / 203 tokens ( 2.90 ms per token, 345.09 tokens per second) 1.31.419.721 I slot print_timing: id 0 | task 3447 | eval time = 1604.30 ms / 79 tokens ( 20.57 ms per token, 48.62 tokens per second) 1.31.419.722 I slot print_timing: id 0 | task 3447 | total time = 2192.56 ms / 282 tokens 1.31.419.722 I slot print_timing: id 0 | task 3447 | graphs reused = 3373 1.31.419.723 I slot print_timing: id 0 | task 3447 | graph reallocs = 0 / 0 (same size) / (changed size) 1.31.419.743 I slot release: id 0 | task 3447 | stop processing: n_tokens = 281, truncated = 0 1.31.424.740 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.167 (> 0.100 thold), f_keep = 0.135 1.31.429.581 I slot launch_slot_: id 0 | task 3529 | processing task, is_child = 0 1.35.069.747 I slot print_timing: id 0 | task 3529 | n_gen = 147, tg = 48.60 t/s, tg_3s = 48.93 t/s 1.35.502.802 I slot print_timing: id 0 | task 3529 | prompt eval time = 636.07 ms / 228 tokens ( 2.79 ms per token, 358.45 tokens per second) 1.35.502.808 I slot print_timing: id 0 | task 3529 | eval time = 3437.15 ms / 168 tokens ( 20.58 ms per token, 48.59 tokens per second) 1.35.502.809 I slot print_timing: id 0 | task 3529 | total time = 4073.21 ms / 396 tokens 1.35.502.810 I slot print_timing: id 0 | task 3529 | graphs reused = 3538 1.35.502.810 I slot print_timing: id 0 | task 3529 | graph reallocs = 0 / 0 (same size) / (changed size) 1.35.502.836 I slot release: id 0 | task 3529 | stop processing: n_tokens = 395, truncated = 0 1.35.507.982 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.145 (> 0.100 thold), f_keep = 0.094 1.35.514.747 I slot launch_slot_: id 0 | task 3700 | processing task, is_child = 0 1.38.862.162 I slot print_timing: id 0 | task 3700 | prompt eval time = 752.39 ms / 256 tokens ( 2.94 ms per token, 340.25 tokens per second) 1.38.862.166 I slot print_timing: id 0 | task 3700 | eval time = 2595.01 ms / 127 tokens ( 20.60 ms per token, 48.55 tokens per second) 1.38.862.167 I slot print_timing: id 0 | task 3700 | total time = 3347.40 ms / 383 tokens 1.38.862.168 I slot print_timing: id 0 | task 3700 | graphs reused = 3663 1.38.862.168 I slot print_timing: id 0 | task 3700 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.862.190 I slot release: id 0 | task 3700 | stop processing: n_tokens = 382, truncated = 0 1.38.867.095 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.155 (> 0.100 thold), f_keep = 0.097 1.38.872.925 I slot launch_slot_: id 0 | task 3830 | processing task, is_child = 0 1.42.235.824 I slot print_timing: id 0 | task 3830 | prompt eval time = 643.53 ms / 238 tokens ( 2.70 ms per token, 369.83 tokens per second) 1.42.235.827 I slot print_timing: id 0 | task 3830 | eval time = 2719.35 ms / 133 tokens ( 20.60 ms per token, 48.54 tokens per second) 1.42.235.828 I slot print_timing: id 0 | task 3830 | total time = 3362.89 ms / 371 tokens 1.42.235.828 I slot print_timing: id 0 | task 3830 | graphs reused = 3793 1.42.235.829 I slot print_timing: id 0 | task 3830 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.235.851 I slot release: id 0 | task 3830 | stop processing: n_tokens = 370, truncated = 0 1.42.240.690 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.100 1.42.247.307 I slot launch_slot_: id 0 | task 3966 | processing task, is_child = 0 1.44.573.353 I slot print_timing: id 0 | task 3966 | prompt eval time = 605.87 ms / 211 tokens ( 2.87 ms per token, 348.26 tokens per second) 1.44.573.359 I slot print_timing: id 0 | task 3966 | eval time = 1720.17 ms / 84 tokens ( 20.72 ms per token, 48.25 tokens per second) 1.44.573.360 I slot print_timing: id 0 | task 3966 | total time = 2326.04 ms / 295 tokens 1.44.573.360 I slot print_timing: id 0 | task 3966 | graphs reused = 3874 1.44.573.361 I slot print_timing: id 0 | task 3966 | graph reallocs = 0 / 0 (same size) / (changed size) 1.44.573.381 I slot release: id 0 | task 3966 | stop processing: n_tokens = 294, truncated = 0 1.44.578.200 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.126 1.44.582.830 I slot launch_slot_: id 0 | task 4053 | processing task, is_child = 0 1.47.549.501 I slot print_timing: id 0 | task 4053 | prompt eval time = 599.85 ms / 211 tokens ( 2.84 ms per token, 351.76 tokens per second) 1.47.549.508 I slot print_timing: id 0 | task 4053 | eval time = 2366.81 ms / 116 tokens ( 20.58 ms per token, 48.59 tokens per second) 1.47.549.508 I slot print_timing: id 0 | task 4053 | total time = 2966.66 ms / 327 tokens 1.47.549.509 I slot print_timing: id 0 | task 4053 | graphs reused = 3987 1.47.549.510 I slot print_timing: id 0 | task 4053 | graph reallocs = 0 / 0 (same size) / (changed size) 1.47.549.529 I slot release: id 0 | task 4053 | stop processing: n_tokens = 326, truncated = 0 1.47.554.519 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.154 (> 0.100 thold), f_keep = 0.113 1.47.560.379 I slot launch_slot_: id 0 | task 4172 | processing task, is_child = 0 1.50.734.443 I slot print_timing: id 0 | task 4172 | prompt eval time = 638.44 ms / 240 tokens ( 2.66 ms per token, 375.92 tokens per second) 1.50.734.447 I slot print_timing: id 0 | task 4172 | eval time = 2535.61 ms / 124 tokens ( 20.61 ms per token, 48.51 tokens per second) 1.50.734.447 I slot print_timing: id 0 | task 4172 | total time = 3174.05 ms / 364 tokens 1.50.734.448 I slot print_timing: id 0 | task 4172 | graphs reused = 4108 1.50.734.449 I slot print_timing: id 0 | task 4172 | graph reallocs = 0 / 0 (same size) / (changed size) 1.50.734.474 I slot release: id 0 | task 4172 | stop processing: n_tokens = 363, truncated = 0 1.50.739.456 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.142 (> 0.100 thold), f_keep = 0.102 1.50.745.931 I slot launch_slot_: id 0 | task 4299 | processing task, is_child = 0 1.53.248.301 I slot print_timing: id 0 | task 4299 | prompt eval time = 698.42 ms / 260 tokens ( 2.69 ms per token, 372.27 tokens per second) 1.53.248.304 I slot print_timing: id 0 | task 4299 | eval time = 1803.94 ms / 88 tokens ( 20.73 ms per token, 48.23 tokens per second) 1.53.248.305 I slot print_timing: id 0 | task 4299 | total time = 2502.36 ms / 348 tokens 1.53.248.305 I slot print_timing: id 0 | task 4299 | graphs reused = 4194 1.53.248.306 I slot print_timing: id 0 | task 4299 | graph reallocs = 0 / 0 (same size) / (changed size) 1.53.248.329 I slot release: id 0 | task 4299 | stop processing: n_tokens = 347, truncated = 0 1.53.253.102 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.181 (> 0.100 thold), f_keep = 0.107 1.53.259.719 I slot launch_slot_: id 0 | task 4390 | processing task, is_child = 0 1.55.541.052 I slot print_timing: id 0 | task 4390 | prompt eval time = 579.92 ms / 204 tokens ( 2.84 ms per token, 351.77 tokens per second) 1.55.541.057 I slot print_timing: id 0 | task 4390 | eval time = 1701.40 ms / 83 tokens ( 20.75 ms per token, 48.20 tokens per second) 1.55.541.057 I slot print_timing: id 0 | task 4390 | total time = 2281.32 ms / 287 tokens 1.55.541.058 I slot print_timing: id 0 | task 4390 | graphs reused = 4274 1.55.541.058 I slot print_timing: id 0 | task 4390 | graph reallocs = 0 / 0 (same size) / (changed size) 1.55.541.079 I slot release: id 0 | task 4390 | stop processing: n_tokens = 286, truncated = 0 1.55.546.052 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.152 (> 0.100 thold), f_keep = 0.129 1.55.549.603 I slot launch_slot_: id 0 | task 4476 | processing task, is_child = 0 1.59.202.574 I slot print_timing: id 0 | task 4476 | n_gen = 147, tg = 48.53 t/s, tg_3s = 48.86 t/s 2.02.211.208 I slot print_timing: id 0 | task 4476 | n_gen = 292, tg = 48.36 t/s, tg_3s = 48.19 t/s 2.03.288.566 I slot print_timing: id 0 | task 4476 | prompt eval time = 644.53 ms / 244 tokens ( 2.64 ms per token, 378.57 tokens per second) 2.03.288.572 I slot print_timing: id 0 | task 4476 | eval time = 7094.42 ms / 344 tokens ( 20.68 ms per token, 48.35 tokens per second) 2.03.288.573 I slot print_timing: id 0 | task 4476 | total time = 7738.95 ms / 588 tokens 2.03.288.573 I slot print_timing: id 0 | task 4476 | graphs reused = 4614 2.03.288.574 I slot print_timing: id 0 | task 4476 | graph reallocs = 0 / 0 (same size) / (changed size) 2.03.288.598 I slot release: id 0 | task 4476 | stop processing: n_tokens = 587, truncated = 0 2.03.293.358 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.210 (> 0.100 thold), f_keep = 0.063 2.03.301.973 I slot launch_slot_: id 0 | task 4823 | processing task, is_child = 0 2.06.107.409 I slot print_timing: id 0 | task 4823 | prompt eval time = 549.56 ms / 176 tokens ( 3.12 ms per token, 320.26 tokens per second) 2.06.107.415 I slot print_timing: id 0 | task 4823 | eval time = 2255.87 ms / 111 tokens ( 20.51 ms per token, 48.76 tokens per second) 2.06.107.416 I slot print_timing: id 0 | task 4823 | total time = 2805.43 ms / 287 tokens 2.06.107.416 I slot print_timing: id 0 | task 4823 | graphs reused = 4722 2.06.107.417 I slot print_timing: id 0 | task 4823 | graph reallocs = 0 / 0 (same size) / (changed size) 2.06.107.436 I slot release: id 0 | task 4823 | stop processing: n_tokens = 286, truncated = 0 2.06.112.037 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.129 2.06.115.607 I slot launch_slot_: id 0 | task 4937 | processing task, is_child = 0 2.09.523.137 I slot print_timing: id 0 | task 4937 | prompt eval time = 573.41 ms / 185 tokens ( 3.10 ms per token, 322.63 tokens per second) 2.09.523.141 I slot print_timing: id 0 | task 4937 | eval time = 2834.11 ms / 139 tokens ( 20.54 ms per token, 48.69 tokens per second) 2.09.523.141 I slot print_timing: id 0 | task 4937 | total time = 3407.52 ms / 324 tokens 2.09.523.142 I slot print_timing: id 0 | task 4937 | graphs reused = 4858 2.09.523.143 I slot print_timing: id 0 | task 4937 | graph reallocs = 0 / 0 (same size) / (changed size) 2.09.523.162 I slot release: id 0 | task 4937 | stop processing: n_tokens = 323, truncated = 0 2.09.527.846 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.191 (> 0.100 thold), f_keep = 0.115 2.09.533.163 I slot launch_slot_: id 0 | task 5079 | processing task, is_child = 0 2.12.093.437 I slot print_timing: id 0 | task 5079 | prompt eval time = 564.13 ms / 194 tokens ( 2.91 ms per token, 343.89 tokens per second) 2.12.093.443 I slot print_timing: id 0 | task 5079 | eval time = 1996.13 ms / 98 tokens ( 20.58 ms per token, 48.59 tokens per second) 2.12.093.444 I slot print_timing: id 0 | task 5079 | total time = 2560.27 ms / 292 tokens 2.12.093.444 I slot print_timing: id 0 | task 5079 | graphs reused = 4953 2.12.093.445 I slot print_timing: id 0 | task 5079 | graph reallocs = 0 / 0 (same size) / (changed size) 2.12.093.468 I slot release: id 0 | task 5079 | stop processing: n_tokens = 291, truncated = 0 2.12.098.093 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.196 (> 0.100 thold), f_keep = 0.127 2.12.103.498 I slot launch_slot_: id 0 | task 5180 | processing task, is_child = 0 2.14.620.861 I slot print_timing: id 0 | task 5180 | prompt eval time = 542.64 ms / 189 tokens ( 2.87 ms per token, 348.30 tokens per second) 2.14.620.867 I slot print_timing: id 0 | task 5180 | eval time = 1974.71 ms / 97 tokens ( 20.57 ms per token, 48.61 tokens per second) 2.14.620.869 I slot print_timing: id 0 | task 5180 | total time = 2517.36 ms / 286 tokens 2.14.620.869 I slot print_timing: id 0 | task 5180 | graphs reused = 5047 2.14.620.870 I slot print_timing: id 0 | task 5180 | graph reallocs = 0 / 0 (same size) / (changed size) 2.14.620.889 I slot release: id 0 | task 5180 | stop processing: n_tokens = 285, truncated = 0 2.14.625.859 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.150 (> 0.100 thold), f_keep = 0.130 2.14.631.334 I slot launch_slot_: id 0 | task 5280 | processing task, is_child = 0 2.17.264.012 I slot print_timing: id 0 | task 5280 | prompt eval time = 701.64 ms / 246 tokens ( 2.85 ms per token, 350.61 tokens per second) 2.17.264.019 I slot print_timing: id 0 | task 5280 | eval time = 1931.03 ms / 94 tokens ( 20.76 ms per token, 48.16 tokens per second) 2.17.264.019 I slot print_timing: id 0 | task 5280 | total time = 2632.67 ms / 340 tokens 2.17.264.020 I slot print_timing: id 0 | task 5280 | graphs reused = 5138 2.17.264.021 I slot print_timing: id 0 | task 5280 | graph reallocs = 0 / 0 (same size) / (changed size) 2.17.264.042 I slot release: id 0 | task 5280 | stop processing: n_tokens = 339, truncated = 0 2.17.269.985 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 339, t_last = 348306119919 2.17.276.829 I slot launch_slot_: id 0 | task 5377 | processing task, is_child = 0 2.20.385.134 I slot print_timing: id 0 | task 5377 | prompt eval time = 914.62 ms / 373 tokens ( 2.45 ms per token, 407.82 tokens per second) 2.20.385.137 I slot print_timing: id 0 | task 5377 | eval time = 2193.67 ms / 107 tokens ( 20.70 ms per token, 48.32 tokens per second) 2.20.385.138 I slot print_timing: id 0 | task 5377 | total time = 3108.29 ms / 480 tokens 2.20.385.138 I slot print_timing: id 0 | task 5377 | graphs reused = 5243 2.20.385.139 I slot print_timing: id 0 | task 5377 | graph reallocs = 0 / 0 (same size) / (changed size) 2.20.385.167 I slot release: id 0 | task 5377 | stop processing: n_tokens = 479, truncated = 0 2.20.389.903 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.077 2.20.398.837 I slot launch_slot_: id 0 | task 5487 | processing task, is_child = 0 2.23.493.697 I slot print_timing: id 0 | task 5487 | prompt eval time = 586.53 ms / 197 tokens ( 2.98 ms per token, 335.87 tokens per second) 2.23.493.700 I slot print_timing: id 0 | task 5487 | eval time = 2508.31 ms / 123 tokens ( 20.56 ms per token, 48.64 tokens per second) 2.23.493.701 I slot print_timing: id 0 | task 5487 | total time = 3094.85 ms / 320 tokens 2.23.493.701 I slot print_timing: id 0 | task 5487 | graphs reused = 5363 2.23.493.702 I slot print_timing: id 0 | task 5487 | graph reallocs = 0 / 0 (same size) / (changed size) 2.23.493.722 I slot release: id 0 | task 5487 | stop processing: n_tokens = 319, truncated = 0 2.23.498.493 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.163 (> 0.100 thold), f_keep = 0.116 2.23.502.185 I slot launch_slot_: id 0 | task 5613 | processing task, is_child = 0 2.26.116.698 I slot print_timing: id 0 | task 5613 | prompt eval time = 613.17 ms / 227 tokens ( 2.70 ms per token, 370.21 tokens per second) 2.26.116.704 I slot print_timing: id 0 | task 5613 | eval time = 2001.33 ms / 98 tokens ( 20.63 ms per token, 48.47 tokens per second) 2.26.116.705 I slot print_timing: id 0 | task 5613 | total time = 2614.50 ms / 325 tokens 2.26.116.706 I slot print_timing: id 0 | task 5613 | graphs reused = 5458 2.26.116.706 I slot print_timing: id 0 | task 5613 | graph reallocs = 0 / 0 (same size) / (changed size) 2.26.116.727 I slot release: id 0 | task 5613 | stop processing: n_tokens = 324, truncated = 0 2.26.121.871 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.133 (> 0.100 thold), f_keep = 0.114 2.26.127.770 I slot launch_slot_: id 0 | task 5714 | processing task, is_child = 0 2.28.836.345 I slot print_timing: id 0 | task 5714 | prompt eval time = 729.65 ms / 278 tokens ( 2.62 ms per token, 381.00 tokens per second) 2.28.836.351 I slot print_timing: id 0 | task 5714 | eval time = 1978.91 ms / 97 tokens ( 20.61 ms per token, 48.51 tokens per second) 2.28.836.352 I slot print_timing: id 0 | task 5714 | total time = 2708.56 ms / 375 tokens 2.28.836.352 I slot print_timing: id 0 | task 5714 | graphs reused = 5553 2.28.836.353 I slot print_timing: id 0 | task 5714 | graph reallocs = 0 / 0 (same size) / (changed size) 2.28.836.379 I slot release: id 0 | task 5714 | stop processing: n_tokens = 374, truncated = 0 2.28.841.478 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.131 (> 0.100 thold), f_keep = 0.102 2.28.848.602 I slot launch_slot_: id 0 | task 5814 | processing task, is_child = 0 2.32.598.257 I slot print_timing: id 0 | task 5814 | n_gen = 147, tg = 48.51 t/s, tg_3s = 48.84 t/s 2.33.134.673 I slot print_timing: id 0 | task 5814 | prompt eval time = 739.86 ms / 289 tokens ( 2.56 ms per token, 390.61 tokens per second) 2.33.134.679 I slot print_timing: id 0 | task 5814 | eval time = 3546.20 ms / 173 tokens ( 20.62 ms per token, 48.50 tokens per second) 2.33.134.680 I slot print_timing: id 0 | task 5814 | total time = 4286.06 ms / 462 tokens 2.33.134.681 I slot print_timing: id 0 | task 5814 | graphs reused = 5724 2.33.134.681 I slot print_timing: id 0 | task 5814 | graph reallocs = 0 / 0 (same size) / (changed size) 2.33.134.705 I slot release: id 0 | task 5814 | stop processing: n_tokens = 461, truncated = 0 2.33.139.381 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 2.33.147.440 I slot launch_slot_: id 0 | task 5990 | processing task, is_child = 0 2.35.334.947 I slot print_timing: id 0 | task 5990 | prompt eval time = 582.49 ms / 205 tokens ( 2.84 ms per token, 351.94 tokens per second) 2.35.334.951 I slot print_timing: id 0 | task 5990 | eval time = 1605.01 ms / 79 tokens ( 20.58 ms per token, 48.60 tokens per second) 2.35.334.951 I slot print_timing: id 0 | task 5990 | total time = 2187.50 ms / 284 tokens 2.35.334.952 I slot print_timing: id 0 | task 5990 | graphs reused = 5800 2.35.334.953 I slot print_timing: id 0 | task 5990 | graph reallocs = 0 / 0 (same size) / (changed size) 2.35.334.972 I slot release: id 0 | task 5990 | stop processing: n_tokens = 283, truncated = 0 2.35.339.814 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.167 (> 0.100 thold), f_keep = 0.131 2.35.343.427 I slot launch_slot_: id 0 | task 6072 | processing task, is_child = 0 2.38.005.189 I slot print_timing: id 0 | task 6072 | prompt eval time = 620.90 ms / 221 tokens ( 2.81 ms per token, 355.93 tokens per second) 2.38.005.195 I slot print_timing: id 0 | task 6072 | eval time = 2040.85 ms / 100 tokens ( 20.61 ms per token, 48.51 tokens per second) 2.38.005.196 I slot print_timing: id 0 | task 6072 | total time = 2661.75 ms / 321 tokens 2.38.005.197 I slot print_timing: id 0 | task 6072 | graphs reused = 5897 2.38.005.197 I slot print_timing: id 0 | task 6072 | graph reallocs = 0 / 0 (same size) / (changed size) 2.38.005.218 I slot release: id 0 | task 6072 | stop processing: n_tokens = 320, truncated = 0 2.38.010.375 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.165 (> 0.100 thold), f_keep = 0.116 2.38.016.248 I slot launch_slot_: id 0 | task 6175 | processing task, is_child = 0 2.40.212.541 I slot print_timing: id 0 | task 6175 | prompt eval time = 618.55 ms / 224 tokens ( 2.76 ms per token, 362.14 tokens per second) 2.40.212.547 I slot print_timing: id 0 | task 6175 | eval time = 1577.73 ms / 77 tokens ( 20.76 ms per token, 48.17 tokens per second) 2.40.212.547 I slot print_timing: id 0 | task 6175 | total time = 2196.28 ms / 301 tokens 2.40.212.548 I slot print_timing: id 0 | task 6175 | graphs reused = 5971 2.40.212.548 I slot print_timing: id 0 | task 6175 | graph reallocs = 0 / 0 (same size) / (changed size) 2.40.212.569 I slot release: id 0 | task 6175 | stop processing: n_tokens = 300, truncated = 0 2.40.217.653 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.146 (> 0.100 thold), f_keep = 0.123 2.40.223.478 I slot launch_slot_: id 0 | task 6255 | processing task, is_child = 0 2.43.330.932 I slot print_timing: id 0 | task 6255 | prompt eval time = 696.30 ms / 254 tokens ( 2.74 ms per token, 364.79 tokens per second) 2.43.330.939 I slot print_timing: id 0 | task 6255 | eval time = 2411.15 ms / 118 tokens ( 20.61 ms per token, 48.52 tokens per second) 2.43.330.940 I slot print_timing: id 0 | task 6255 | total time = 3107.45 ms / 372 tokens 2.43.330.940 I slot print_timing: id 0 | task 6255 | graphs reused = 6086 2.43.330.941 I slot print_timing: id 0 | task 6255 | graph reallocs = 0 / 0 (same size) / (changed size) 2.43.330.962 I slot release: id 0 | task 6255 | stop processing: n_tokens = 371, truncated = 0 2.43.335.663 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.177 (> 0.100 thold), f_keep = 0.100 2.43.342.571 I slot launch_slot_: id 0 | task 6376 | processing task, is_child = 0 2.45.737.320 I slot print_timing: id 0 | task 6376 | prompt eval time = 592.55 ms / 209 tokens ( 2.84 ms per token, 352.71 tokens per second) 2.45.737.324 I slot print_timing: id 0 | task 6376 | eval time = 1802.19 ms / 88 tokens ( 20.71 ms per token, 48.27 tokens per second) 2.45.737.325 I slot print_timing: id 0 | task 6376 | total time = 2394.74 ms / 297 tokens 2.45.737.325 I slot print_timing: id 0 | task 6376 | graphs reused = 6171 2.45.737.326 I slot print_timing: id 0 | task 6376 | graph reallocs = 0 / 0 (same size) / (changed size) 2.45.737.345 I slot release: id 0 | task 6376 | stop processing: n_tokens = 296, truncated = 0 2.45.742.350 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.141 (> 0.100 thold), f_keep = 0.125 2.45.746.596 I slot launch_slot_: id 0 | task 6467 | processing task, is_child = 0 2.48.428.519 I slot print_timing: id 0 | task 6467 | prompt eval time = 701.44 ms / 263 tokens ( 2.67 ms per token, 374.94 tokens per second) 2.48.428.522 I slot print_timing: id 0 | task 6467 | eval time = 1980.47 ms / 97 tokens ( 20.63 ms per token, 48.47 tokens per second) 2.48.428.523 I slot print_timing: id 0 | task 6467 | total time = 2681.91 ms / 360 tokens 2.48.428.523 I slot print_timing: id 0 | task 6467 | graphs reused = 6266 2.48.428.524 I slot print_timing: id 0 | task 6467 | graph reallocs = 0 / 0 (same size) / (changed size) 2.48.428.552 I slot release: id 0 | task 6467 | stop processing: n_tokens = 359, truncated = 0 2.48.433.696 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.167 (> 0.100 thold), f_keep = 0.103 2.48.444.287 I slot launch_slot_: id 0 | task 6567 | processing task, is_child = 0 2.52.040.996 I slot print_timing: id 0 | task 6567 | n_gen = 147, tg = 48.57 t/s, tg_3s = 48.90 t/s 2.53.011.218 I slot print_timing: id 0 | task 6567 | prompt eval time = 590.56 ms / 221 tokens ( 2.67 ms per token, 374.22 tokens per second) 2.53.011.226 I slot print_timing: id 0 | task 6567 | eval time = 3976.36 ms / 194 tokens ( 20.60 ms per token, 48.54 tokens per second) 2.53.011.226 I slot print_timing: id 0 | task 6567 | total time = 4566.92 ms / 415 tokens 2.53.011.227 I slot print_timing: id 0 | task 6567 | graphs reused = 6457 2.53.011.227 I slot print_timing: id 0 | task 6567 | graph reallocs = 0 / 0 (same size) / (changed size) 2.53.011.249 I slot release: id 0 | task 6567 | stop processing: n_tokens = 414, truncated = 0 2.53.016.280 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.089 2.53.025.961 I slot launch_slot_: id 0 | task 6764 | processing task, is_child = 0 2.55.625.936 I slot print_timing: id 0 | task 6764 | prompt eval time = 629.36 ms / 217 tokens ( 2.90 ms per token, 344.80 tokens per second) 2.55.625.942 I slot print_timing: id 0 | task 6764 | eval time = 1970.61 ms / 96 tokens ( 20.74 ms per token, 48.21 tokens per second) 2.55.625.943 I slot print_timing: id 0 | task 6764 | total time = 2599.96 ms / 313 tokens 2.55.625.944 I slot print_timing: id 0 | task 6764 | graphs reused = 6550 2.55.625.944 I slot print_timing: id 0 | task 6764 | graph reallocs = 0 / 0 (same size) / (changed size) 2.55.625.965 I slot release: id 0 | task 6764 | stop processing: n_tokens = 312, truncated = 0 2.55.631.424 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 2.55.639.206 I slot launch_slot_: id 0 | task 6863 | processing task, is_child = 0 2.59.108.912 I slot print_timing: id 0 | task 6863 | prompt eval time = 802.18 ms / 337 tokens ( 2.38 ms per token, 420.10 tokens per second) 2.59.108.916 I slot print_timing: id 0 | task 6863 | eval time = 2667.51 ms / 130 tokens ( 20.68 ms per token, 48.36 tokens per second) 2.59.108.916 I slot print_timing: id 0 | task 6863 | total time = 3469.69 ms / 467 tokens 2.59.108.917 I slot print_timing: id 0 | task 6863 | graphs reused = 6678 2.59.108.917 I slot print_timing: id 0 | task 6863 | graph reallocs = 0 / 0 (same size) / (changed size) 2.59.108.947 I slot release: id 0 | task 6863 | stop processing: n_tokens = 466, truncated = 0 2.59.114.386 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.123 (> 0.100 thold), f_keep = 0.079 2.59.128.262 I slot launch_slot_: id 0 | task 6996 | processing task, is_child = 0 3.02.880.298 I slot print_timing: id 0 | task 6996 | n_gen = 146, tg = 48.31 t/s, tg_3s = 48.64 t/s 3.02.983.579 I slot print_timing: id 0 | task 6996 | prompt eval time = 750.67 ms / 301 tokens ( 2.49 ms per token, 400.97 tokens per second) 3.02.983.586 I slot print_timing: id 0 | task 6996 | eval time = 3104.63 ms / 151 tokens ( 20.70 ms per token, 48.31 tokens per second) 3.02.983.587 I slot print_timing: id 0 | task 6996 | total time = 3855.31 ms / 452 tokens 3.02.983.588 I slot print_timing: id 0 | task 6996 | graphs reused = 6827 3.02.983.588 I slot print_timing: id 0 | task 6996 | graph reallocs = 0 / 0 (same size) / (changed size) 3.02.983.618 I slot release: id 0 | task 6996 | stop processing: n_tokens = 451, truncated = 0 3.02.988.484 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.082 3.03.001.922 I slot launch_slot_: id 0 | task 7150 | processing task, is_child = 0 3.05.344.988 I slot print_timing: id 0 | task 7150 | prompt eval time = 613.11 ms / 212 tokens ( 2.89 ms per token, 345.78 tokens per second) 3.05.344.994 I slot print_timing: id 0 | task 7150 | eval time = 1729.95 ms / 85 tokens ( 20.59 ms per token, 48.56 tokens per second) 3.05.344.995 I slot print_timing: id 0 | task 7150 | total time = 2343.06 ms / 297 tokens 3.05.344.995 I slot print_timing: id 0 | task 7150 | graphs reused = 6909 3.05.344.996 I slot print_timing: id 0 | task 7150 | graph reallocs = 0 / 0 (same size) / (changed size) 3.05.345.016 I slot release: id 0 | task 7150 | stop processing: n_tokens = 296, truncated = 0 3.05.350.044 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.149 (> 0.100 thold), f_keep = 0.125 3.05.356.063 I slot launch_slot_: id 0 | task 7238 | processing task, is_child = 0 3.07.551.655 I slot print_timing: id 0 | task 7238 | prompt eval time = 664.86 ms / 248 tokens ( 2.68 ms per token, 373.01 tokens per second) 3.07.551.662 I slot print_timing: id 0 | task 7238 | eval time = 1530.72 ms / 75 tokens ( 20.69 ms per token, 48.34 tokens per second) 3.07.551.662 I slot print_timing: id 0 | task 7238 | total time = 2195.58 ms / 323 tokens 3.07.551.663 I slot print_timing: id 0 | task 7238 | graphs reused = 6981 3.07.551.663 I slot print_timing: id 0 | task 7238 | graph reallocs = 0 / 0 (same size) / (changed size) 3.07.551.689 I slot release: id 0 | task 7238 | stop processing: n_tokens = 322, truncated = 0 3.07.556.376 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.181 (> 0.100 thold), f_keep = 0.115 3.07.566.191 I slot launch_slot_: id 0 | task 7316 | processing task, is_child = 0 3.10.158.224 I slot print_timing: id 0 | task 7316 | prompt eval time = 585.18 ms / 204 tokens ( 2.87 ms per token, 348.61 tokens per second) 3.10.158.231 I slot print_timing: id 0 | task 7316 | eval time = 2006.84 ms / 98 tokens ( 20.69 ms per token, 48.33 tokens per second) 3.10.158.231 I slot print_timing: id 0 | task 7316 | total time = 2592.02 ms / 302 tokens 3.10.158.232 I slot print_timing: id 0 | task 7316 | graphs reused = 7076 3.10.158.232 I slot print_timing: id 0 | task 7316 | graph reallocs = 0 / 0 (same size) / (changed size) 3.10.158.253 I slot release: id 0 | task 7316 | stop processing: n_tokens = 301, truncated = 0 3.10.163.432 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.139 (> 0.100 thold), f_keep = 0.123 3.10.169.379 I slot launch_slot_: id 0 | task 7417 | processing task, is_child = 0 3.13.126.789 I slot print_timing: id 0 | task 7417 | prompt eval time = 712.68 ms / 267 tokens ( 2.67 ms per token, 374.64 tokens per second) 3.13.126.795 I slot print_timing: id 0 | task 7417 | eval time = 2244.72 ms / 110 tokens ( 20.59 ms per token, 48.56 tokens per second) 3.13.126.797 I slot print_timing: id 0 | task 7417 | total time = 2957.39 ms / 377 tokens 3.13.126.797 I slot print_timing: id 0 | task 7417 | graphs reused = 7184 3.13.126.798 I slot print_timing: id 0 | task 7417 | graph reallocs = 0 / 0 (same size) / (changed size) 3.13.126.820 I slot release: id 0 | task 7417 | stop processing: n_tokens = 376, truncated = 0 3.13.132.697 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 376, t_last = 348361982697 3.13.143.834 I slot launch_slot_: id 0 | task 7530 | processing task, is_child = 0 3.16.460.684 I slot print_timing: id 0 | task 7530 | prompt eval time = 854.58 ms / 392 tokens ( 2.18 ms per token, 458.71 tokens per second) 3.16.460.690 I slot print_timing: id 0 | task 7530 | eval time = 2462.26 ms / 120 tokens ( 20.69 ms per token, 48.33 tokens per second) 3.16.460.691 I slot print_timing: id 0 | task 7530 | total time = 3316.84 ms / 512 tokens 3.16.460.691 I slot print_timing: id 0 | task 7530 | graphs reused = 7302 3.16.460.692 I slot print_timing: id 0 | task 7530 | graph reallocs = 0 / 0 (same size) / (changed size) 3.16.460.719 I slot release: id 0 | task 7530 | stop processing: n_tokens = 511, truncated = 0 3.16.466.902 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 511, t_last = 348365316596 3.16.481.720 I slot launch_slot_: id 0 | task 7653 | processing task, is_child = 0 3.19.112.614 I slot print_timing: id 0 | task 7653 | prompt eval time = 1012.93 ms / 461 tokens ( 2.20 ms per token, 455.11 tokens per second) 3.19.112.622 I slot print_timing: id 0 | task 7653 | eval time = 1617.95 ms / 78 tokens ( 21.01 ms per token, 47.59 tokens per second) 3.19.112.623 I slot print_timing: id 0 | task 7653 | total time = 2630.88 ms / 539 tokens 3.19.112.623 I slot print_timing: id 0 | task 7653 | graphs reused = 7377 3.19.112.624 I slot print_timing: id 0 | task 7653 | graph reallocs = 0 / 0 (same size) / (changed size) 3.19.112.656 I slot release: id 0 | task 7653 | stop processing: n_tokens = 538, truncated = 0 3.19.119.344 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 538, t_last = 348367968533 3.19.134.803 I slot launch_slot_: id 0 | task 7734 | processing task, is_child = 0 3.22.160.963 I slot print_timing: id 0 | task 7734 | prompt eval time = 1027.94 ms / 505 tokens ( 2.04 ms per token, 491.27 tokens per second) 3.22.160.969 I slot print_timing: id 0 | task 7734 | eval time = 1998.20 ms / 97 tokens ( 20.81 ms per token, 48.04 tokens per second) 3.22.160.969 I slot print_timing: id 0 | task 7734 | total time = 3026.15 ms / 602 tokens 3.22.160.970 I slot print_timing: id 0 | task 7734 | graphs reused = 7471 3.22.160.971 I slot print_timing: id 0 | task 7734 | graph reallocs = 0 / 0 (same size) / (changed size) 3.22.161.006 I slot release: id 0 | task 7734 | stop processing: n_tokens = 601, truncated = 0 3.22.167.700 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 601, t_last = 348371016883 3.22.183.501 I slot launch_slot_: id 0 | task 7834 | processing task, is_child = 0 3.25.601.001 I slot print_timing: id 0 | task 7834 | prompt eval time = 960.15 ms / 493 tokens ( 1.95 ms per token, 513.46 tokens per second) 3.25.601.004 I slot print_timing: id 0 | task 7834 | eval time = 2457.34 ms / 119 tokens ( 20.82 ms per token, 48.02 tokens per second) 3.25.601.005 I slot print_timing: id 0 | task 7834 | total time = 3417.48 ms / 612 tokens 3.25.601.006 I slot print_timing: id 0 | task 7834 | graphs reused = 7587 3.25.601.006 I slot print_timing: id 0 | task 7834 | graph reallocs = 0 / 0 (same size) / (changed size) 3.25.601.037 I slot release: id 0 | task 7834 | stop processing: n_tokens = 611, truncated = 0 3.25.606.594 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.112 (> 0.100 thold), f_keep = 0.061 3.25.623.094 I slot launch_slot_: id 0 | task 7956 | processing task, is_child = 0 3.28.752.974 I slot print_timing: id 0 | task 7956 | prompt eval time = 772.48 ms / 331 tokens ( 2.33 ms per token, 428.49 tokens per second) 3.28.752.980 I slot print_timing: id 0 | task 7956 | eval time = 2357.39 ms / 115 tokens ( 20.68 ms per token, 48.36 tokens per second) 3.28.752.981 I slot print_timing: id 0 | task 7956 | total time = 3129.87 ms / 446 tokens 3.28.752.981 I slot print_timing: id 0 | task 7956 | graphs reused = 7700 3.28.752.982 I slot print_timing: id 0 | task 7956 | graph reallocs = 0 / 0 (same size) / (changed size) 3.28.753.009 I slot release: id 0 | task 7956 | stop processing: n_tokens = 445, truncated = 0 3.28.759.249 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 445, t_last = 348377608886 3.28.768.247 I slot launch_slot_: id 0 | task 8074 | processing task, is_child = 0 3.32.692.265 I slot print_timing: id 0 | task 8074 | n_gen = 146, tg = 48.15 t/s, tg_3s = 48.49 t/s 3.34.400.039 I slot print_timing: id 0 | task 8074 | prompt eval time = 912.84 ms / 455 tokens ( 2.01 ms per token, 498.45 tokens per second) 3.34.400.041 I slot print_timing: id 0 | task 8074 | eval time = 4718.94 ms / 228 tokens ( 20.79 ms per token, 48.10 tokens per second) 3.34.400.042 I slot print_timing: id 0 | task 8074 | total time = 5631.78 ms / 683 tokens 3.34.400.043 I slot print_timing: id 0 | task 8074 | graphs reused = 7925 3.34.400.043 I slot print_timing: id 0 | task 8074 | graph reallocs = 0 / 0 (same size) / (changed size) 3.34.400.072 I slot release: id 0 | task 8074 | stop processing: n_tokens = 682, truncated = 0 3.34.405.902 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 682, t_last = 348383255949 3.34.422.252 I slot launch_slot_: id 0 | task 8305 | processing task, is_child = 0 3.38.324.638 I slot print_timing: id 0 | task 8305 | n_gen = 146, tg = 48.16 t/s, tg_3s = 48.49 t/s 3.41.304.793 I slot print_timing: id 0 | task 8305 | prompt eval time = 891.46 ms / 439 tokens ( 2.03 ms per token, 492.45 tokens per second) 3.41.304.800 I slot print_timing: id 0 | task 8305 | eval time = 5991.07 ms / 290 tokens ( 20.73 ms per token, 48.24 tokens per second) 3.41.304.800 I slot print_timing: id 0 | task 8305 | total time = 6882.53 ms / 729 tokens 3.41.304.801 I slot print_timing: id 0 | task 8305 | graphs reused = 8212 3.41.304.802 I slot print_timing: id 0 | task 8305 | graph reallocs = 0 / 0 (same size) / (changed size) 3.41.304.831 I slot release: id 0 | task 8305 | stop processing: n_tokens = 728, truncated = 0 3.41.311.010 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 728, t_last = 348390160708 3.41.327.562 I slot launch_slot_: id 0 | task 8598 | processing task, is_child = 0 3.43.400.076 I slot print_timing: id 0 | task 8598 | prompt eval time = 808.17 ms / 379 tokens ( 2.13 ms per token, 468.96 tokens per second) 3.43.400.082 I slot print_timing: id 0 | task 8598 | eval time = 1264.33 ms / 62 tokens ( 20.73 ms per token, 48.25 tokens per second) 3.43.400.082 I slot print_timing: id 0 | task 8598 | total time = 2072.50 ms / 441 tokens 3.43.400.083 I slot print_timing: id 0 | task 8598 | graphs reused = 8272 3.43.400.084 I slot print_timing: id 0 | task 8598 | graph reallocs = 0 / 0 (same size) / (changed size) 3.43.400.109 I slot release: id 0 | task 8598 | stop processing: n_tokens = 440, truncated = 0 3.43.405.440 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 3.43.413.912 I slot launch_slot_: id 0 | task 8663 | processing task, is_child = 0 3.46.419.160 I slot print_timing: id 0 | task 8663 | prompt eval time = 770.16 ms / 348 tokens ( 2.21 ms per token, 451.86 tokens per second) 3.46.419.166 I slot print_timing: id 0 | task 8663 | eval time = 2235.08 ms / 109 tokens ( 20.70 ms per token, 48.32 tokens per second) 3.46.419.167 I slot print_timing: id 0 | task 8663 | total time = 3005.24 ms / 457 tokens 3.46.419.168 I slot print_timing: id 0 | task 8663 | graphs reused = 8379 3.46.419.169 I slot print_timing: id 0 | task 8663 | graph reallocs = 0 / 0 (same size) / (changed size) 3.46.419.194 I slot release: id 0 | task 8663 | stop processing: n_tokens = 456, truncated = 0 3.46.425.404 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 456, t_last = 348395275071 3.46.437.755 I slot launch_slot_: id 0 | task 8775 | processing task, is_child = 0 3.48.790.462 I slot print_timing: id 0 | task 8775 | prompt eval time = 836.55 ms / 425 tokens ( 1.97 ms per token, 508.04 tokens per second) 3.48.790.469 I slot print_timing: id 0 | task 8775 | eval time = 1516.14 ms / 74 tokens ( 20.77 ms per token, 48.15 tokens per second) 3.48.790.470 I slot print_timing: id 0 | task 8775 | total time = 2352.70 ms / 499 tokens 3.48.790.471 I slot print_timing: id 0 | task 8775 | graphs reused = 8451 3.48.790.471 I slot print_timing: id 0 | task 8775 | graph reallocs = 0 / 0 (same size) / (changed size) 3.48.790.503 I slot release: id 0 | task 8775 | stop processing: n_tokens = 498, truncated = 0 3.48.796.306 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 498, t_last = 348397646380 3.48.811.583 I slot launch_slot_: id 0 | task 8852 | processing task, is_child = 0 3.52.250.409 I slot print_timing: id 0 | task 8852 | prompt eval time = 785.74 ms / 371 tokens ( 2.12 ms per token, 472.17 tokens per second) 3.52.250.416 I slot print_timing: id 0 | task 8852 | eval time = 2653.07 ms / 129 tokens ( 20.73 ms per token, 48.25 tokens per second) 3.52.250.417 I slot print_timing: id 0 | task 8852 | total time = 3438.82 ms / 500 tokens 3.52.250.418 I slot print_timing: id 0 | task 8852 | graphs reused = 8578 3.52.250.419 I slot print_timing: id 0 | task 8852 | graph reallocs = 0 / 0 (same size) / (changed size) 3.52.250.448 I slot release: id 0 | task 8852 | stop processing: n_tokens = 499, truncated = 0 3.52.255.820 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.121 (> 0.100 thold), f_keep = 0.074 3.52.265.501 I slot launch_slot_: id 0 | task 8984 | processing task, is_child = 0 3.54.363.232 I slot print_timing: id 0 | task 8984 | prompt eval time = 713.30 ms / 306 tokens ( 2.33 ms per token, 428.99 tokens per second) 3.54.363.238 I slot print_timing: id 0 | task 8984 | eval time = 1384.41 ms / 68 tokens ( 20.66 ms per token, 48.40 tokens per second) 3.54.363.239 I slot print_timing: id 0 | task 8984 | total time = 2097.72 ms / 374 tokens 3.54.363.239 I slot print_timing: id 0 | task 8984 | graphs reused = 8644 3.54.363.240 I slot print_timing: id 0 | task 8984 | graph reallocs = 0 / 0 (same size) / (changed size) 3.54.363.266 I slot release: id 0 | task 8984 | stop processing: n_tokens = 373, truncated = 0 3.54.369.405 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 373, t_last = 348403219143 3.54.380.045 I slot launch_slot_: id 0 | task 9055 | processing task, is_child = 0 3.57.189.585 I slot print_timing: id 0 | task 9055 | prompt eval time = 820.97 ms / 397 tokens ( 2.07 ms per token, 483.57 tokens per second) 3.57.189.589 I slot print_timing: id 0 | task 9055 | eval time = 1988.56 ms / 97 tokens ( 20.71 ms per token, 48.28 tokens per second) 3.57.189.589 I slot print_timing: id 0 | task 9055 | total time = 2809.53 ms / 494 tokens 3.57.189.590 I slot print_timing: id 0 | task 9055 | graphs reused = 8739 3.57.189.591 I slot print_timing: id 0 | task 9055 | graph reallocs = 0 / 0 (same size) / (changed size) 3.57.189.621 I slot release: id 0 | task 9055 | stop processing: n_tokens = 493, truncated = 0 3.57.194.987 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 3.57.208.754 I slot launch_slot_: id 0 | task 9155 | processing task, is_child = 0 3.59.378.091 I slot print_timing: id 0 | task 9155 | prompt eval time = 742.55 ms / 337 tokens ( 2.20 ms per token, 453.84 tokens per second) 3.59.378.098 I slot print_timing: id 0 | task 9155 | eval time = 1426.78 ms / 70 tokens ( 20.68 ms per token, 48.36 tokens per second) 3.59.378.099 I slot print_timing: id 0 | task 9155 | total time = 2169.33 ms / 407 tokens 3.59.378.099 I slot print_timing: id 0 | task 9155 | graphs reused = 8807 3.59.378.100 I slot print_timing: id 0 | task 9155 | graph reallocs = 0 / 0 (same size) / (changed size) 3.59.378.127 I slot release: id 0 | task 9155 | stop processing: n_tokens = 406, truncated = 0 3.59.383.531 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.121 (> 0.100 thold), f_keep = 0.091 3.59.393.810 I slot launch_slot_: id 0 | task 9228 | processing task, is_child = 0 4.02.073.155 I slot print_timing: id 0 | task 9228 | prompt eval time = 716.57 ms / 305 tokens ( 2.35 ms per token, 425.64 tokens per second) 4.02.073.159 I slot print_timing: id 0 | task 9228 | eval time = 1962.76 ms / 96 tokens ( 20.66 ms per token, 48.40 tokens per second) 4.02.073.159 I slot print_timing: id 0 | task 9228 | total time = 2679.33 ms / 401 tokens 4.02.073.160 I slot print_timing: id 0 | task 9228 | graphs reused = 8901 4.02.073.160 I slot print_timing: id 0 | task 9228 | graph reallocs = 0 / 0 (same size) / (changed size) 4.02.073.188 I slot release: id 0 | task 9228 | stop processing: n_tokens = 400, truncated = 0 4.02.078.744 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 4.02.090.243 I slot launch_slot_: id 0 | task 9327 | processing task, is_child = 0 4.04.510.171 I slot print_timing: id 0 | task 9327 | prompt eval time = 725.26 ms / 329 tokens ( 2.20 ms per token, 453.63 tokens per second) 4.04.510.177 I slot print_timing: id 0 | task 9327 | eval time = 1694.66 ms / 83 tokens ( 20.67 ms per token, 48.39 tokens per second) 4.04.510.178 I slot print_timing: id 0 | task 9327 | total time = 2419.92 ms / 412 tokens 4.04.510.178 I slot print_timing: id 0 | task 9327 | graphs reused = 8982 4.04.510.179 I slot print_timing: id 0 | task 9327 | graph reallocs = 0 / 0 (same size) / (changed size) 4.04.510.204 I slot release: id 0 | task 9327 | stop processing: n_tokens = 411, truncated = 0 4.04.515.652 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.118 (> 0.100 thold), f_keep = 0.090 4.04.526.833 I slot launch_slot_: id 0 | task 9413 | processing task, is_child = 0 4.07.069.987 I slot print_timing: id 0 | task 9413 | prompt eval time = 726.02 ms / 313 tokens ( 2.32 ms per token, 431.11 tokens per second) 4.07.069.993 I slot print_timing: id 0 | task 9413 | eval time = 1817.12 ms / 89 tokens ( 20.65 ms per token, 48.43 tokens per second) 4.07.069.994 I slot print_timing: id 0 | task 9413 | total time = 2543.14 ms / 402 tokens 4.07.069.995 I slot print_timing: id 0 | task 9413 | graphs reused = 9069 4.07.069.995 I slot print_timing: id 0 | task 9413 | graph reallocs = 0 / 0 (same size) / (changed size) 4.07.070.020 I slot release: id 0 | task 9413 | stop processing: n_tokens = 401, truncated = 0 4.07.076.449 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 401, t_last = 348415925897 4.07.088.429 I slot launch_slot_: id 0 | task 9505 | processing task, is_child = 0 4.09.995.354 I slot print_timing: id 0 | task 9505 | prompt eval time = 941.11 ms / 467 tokens ( 2.02 ms per token, 496.22 tokens per second) 4.09.995.360 I slot print_timing: id 0 | task 9505 | eval time = 1965.80 ms / 95 tokens ( 20.91 ms per token, 47.82 tokens per second) 4.09.995.361 I slot print_timing: id 0 | task 9505 | total time = 2906.92 ms / 562 tokens 4.09.995.361 I slot print_timing: id 0 | task 9505 | graphs reused = 9161 4.09.995.362 I slot print_timing: id 0 | task 9505 | graph reallocs = 0 / 0 (same size) / (changed size) 4.09.995.394 I slot release: id 0 | task 9505 | stop processing: n_tokens = 561, truncated = 0 4.10.001.027 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.106 (> 0.100 thold), f_keep = 0.066 4.10.015.526 I slot launch_slot_: id 0 | task 9603 | processing task, is_child = 0 4.13.820.897 I slot print_timing: id 0 | task 9603 | prompt eval time = 805.56 ms / 348 tokens ( 2.31 ms per token, 432.00 tokens per second) 4.13.820.900 I slot print_timing: id 0 | task 9603 | eval time = 2999.79 ms / 146 tokens ( 20.69 ms per token, 48.34 tokens per second) 4.13.820.901 I slot print_timing: id 0 | task 9603 | total time = 3805.35 ms / 494 tokens 4.13.820.902 I slot print_timing: id 0 | task 9603 | graphs reused = 9305 4.13.820.902 I slot print_timing: id 0 | task 9603 | graph reallocs = 0 / 0 (same size) / (changed size) 4.13.820.931 I slot release: id 0 | task 9603 | stop processing: n_tokens = 493, truncated = 0 4.13.828.563 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 493, t_last = 348422676808 4.13.838.117 I slot launch_slot_: id 0 | task 9752 | processing task, is_child = 0 4.17.420.237 I slot print_timing: id 0 | task 9752 | prompt eval time = 1559.74 ms / 690 tokens ( 2.26 ms per token, 442.38 tokens per second) 4.17.420.240 I slot print_timing: id 0 | task 9752 | eval time = 2022.37 ms / 98 tokens ( 20.85 ms per token, 47.96 tokens per second) 4.17.420.240 I slot print_timing: id 0 | task 9752 | total time = 3582.11 ms / 788 tokens 4.17.420.241 I slot print_timing: id 0 | task 9752 | graphs reused = 9400 4.17.420.242 I slot print_timing: id 0 | task 9752 | graph reallocs = 0 / 0 (same size) / (changed size) 4.17.420.288 I slot release: id 0 | task 9752 | stop processing: n_tokens = 787, truncated = 0 4.17.425.872 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.113 (> 0.100 thold), f_keep = 0.047 4.17.443.803 I slot launch_slot_: id 0 | task 9854 | processing task, is_child = 0 4.19.584.229 I slot print_timing: id 0 | task 9854 | prompt eval time = 782.47 ms / 328 tokens ( 2.39 ms per token, 419.19 tokens per second) 4.19.584.235 I slot print_timing: id 0 | task 9854 | eval time = 1357.95 ms / 66 tokens ( 20.89 ms per token, 47.87 tokens per second) 4.19.584.235 I slot print_timing: id 0 | task 9854 | total time = 2140.41 ms / 394 tokens 4.19.584.236 I slot print_timing: id 0 | task 9854 | graphs reused = 9464 4.19.584.237 I slot print_timing: id 0 | task 9854 | graph reallocs = 0 / 0 (same size) / (changed size) 4.19.584.265 I slot release: id 0 | task 9854 | stop processing: n_tokens = 393, truncated = 0 4.19.590.967 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 348428440142 4.19.598.717 I slot launch_slot_: id 0 | task 9923 | processing task, is_child = 0 4.22.067.204 I slot print_timing: id 0 | task 9923 | prompt eval time = 1103.26 ms / 532 tokens ( 2.07 ms per token, 482.21 tokens per second) 4.22.067.208 I slot print_timing: id 0 | task 9923 | eval time = 1365.22 ms / 66 tokens ( 21.00 ms per token, 47.61 tokens per second) 4.22.067.208 I slot print_timing: id 0 | task 9923 | total time = 2468.48 ms / 598 tokens 4.22.067.213 I slot print_timing: id 0 | task 9923 | graphs reused = 9528 4.22.067.215 I slot print_timing: id 0 | task 9923 | graph reallocs = 0 / 0 (same size) / (changed size) 4.22.067.251 I slot release: id 0 | task 9923 | stop processing: n_tokens = 597, truncated = 0 4.22.074.719 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 597, t_last = 348430923128 4.22.093.707 I slot launch_slot_: id 0 | task 9993 | processing task, is_child = 0 4.25.323.581 I slot print_timing: id 0 | task 9993 | prompt eval time = 1401.63 ms / 624 tokens ( 2.25 ms per token, 445.19 tokens per second) 4.25.323.587 I slot print_timing: id 0 | task 9993 | eval time = 1828.22 ms / 89 tokens ( 20.78 ms per token, 48.13 tokens per second) 4.25.323.587 I slot print_timing: id 0 | task 9993 | total time = 3229.86 ms / 713 tokens 4.25.323.588 I slot print_timing: id 0 | task 9993 | graphs reused = 9615 4.25.323.588 I slot print_timing: id 0 | task 9993 | graph reallocs = 0 / 0 (same size) / (changed size) 4.25.323.632 I slot release: id 0 | task 9993 | stop processing: n_tokens = 712, truncated = 0 4.25.329.970 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 712, t_last = 348434179509 4.25.347.657 I slot launch_slot_: id 0 | task 10086 | processing task, is_child = 0 4.28.120.557 I slot print_timing: id 0 | task 10086 | prompt eval time = 908.01 ms / 445 tokens ( 2.04 ms per token, 490.08 tokens per second) 4.28.120.561 I slot print_timing: id 0 | task 10086 | eval time = 1864.87 ms / 90 tokens ( 20.95 ms per token, 47.72 tokens per second) 4.28.120.561 I slot print_timing: id 0 | task 10086 | total time = 2772.89 ms / 535 tokens 4.28.120.562 I slot print_timing: id 0 | task 10086 | graphs reused = 9702 4.28.120.563 I slot print_timing: id 0 | task 10086 | graph reallocs = 0 / 0 (same size) / (changed size) 4.28.120.595 I slot release: id 0 | task 10086 | stop processing: n_tokens = 534, truncated = 0 4.28.126.166 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 4.28.139.266 I slot launch_slot_: id 0 | task 10179 | processing task, is_child = 0 4.30.903.730 I slot print_timing: id 0 | task 10179 | prompt eval time = 788.95 ms / 333 tokens ( 2.37 ms per token, 422.08 tokens per second) 4.30.903.737 I slot print_timing: id 0 | task 10179 | eval time = 1975.50 ms / 96 tokens ( 20.79 ms per token, 48.09 tokens per second) 4.30.903.737 I slot print_timing: id 0 | task 10179 | total time = 2764.45 ms / 429 tokens 4.30.903.738 I slot print_timing: id 0 | task 10179 | graphs reused = 9796 4.30.903.738 I slot print_timing: id 0 | task 10179 | graph reallocs = 0 / 0 (same size) / (changed size) 4.30.903.763 I slot release: id 0 | task 10179 | stop processing: n_tokens = 428, truncated = 0 4.30.910.220 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 428, t_last = 348439759640 4.30.919.372 I slot launch_slot_: id 0 | task 10278 | processing task, is_child = 0 4.34.849.672 I slot print_timing: id 0 | task 10278 | n_gen = 146, tg = 48.08 t/s, tg_3s = 48.41 t/s 4.35.284.839 I slot print_timing: id 0 | task 10278 | prompt eval time = 914.24 ms / 474 tokens ( 1.93 ms per token, 518.46 tokens per second) 4.35.284.846 I slot print_timing: id 0 | task 10278 | eval time = 3451.22 ms / 167 tokens ( 20.79 ms per token, 48.10 tokens per second) 4.35.284.846 I slot print_timing: id 0 | task 10278 | total time = 4365.46 ms / 641 tokens 4.35.284.847 I slot print_timing: id 0 | task 10278 | graphs reused = 9960 4.35.284.847 I slot print_timing: id 0 | task 10278 | graph reallocs = 0 / 0 (same size) / (changed size) 4.35.284.881 I slot release: id 0 | task 10278 | stop processing: n_tokens = 640, truncated = 0 4.35.292.385 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 640, t_last = 348444140758 4.35.308.526 I slot launch_slot_: id 0 | task 10448 | processing task, is_child = 0 4.38.778.773 I slot print_timing: id 0 | task 10448 | prompt eval time = 1392.79 ms / 641 tokens ( 2.17 ms per token, 460.23 tokens per second) 4.38.778.779 I slot print_timing: id 0 | task 10448 | eval time = 2077.44 ms / 101 tokens ( 20.77 ms per token, 48.14 tokens per second) 4.38.778.780 I slot print_timing: id 0 | task 10448 | total time = 3470.23 ms / 742 tokens 4.38.778.780 I slot print_timing: id 0 | task 10448 | graphs reused = 10059 4.38.778.781 I slot print_timing: id 0 | task 10448 | graph reallocs = 0 / 0 (same size) / (changed size) 4.38.778.821 I slot release: id 0 | task 10448 | stop processing: n_tokens = 741, truncated = 0 4.38.785.194 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 741, t_last = 348447634698 4.38.804.433 I slot launch_slot_: id 0 | task 10553 | processing task, is_child = 0 4.41.525.926 I slot print_timing: id 0 | task 10553 | prompt eval time = 891.21 ms / 460 tokens ( 1.94 ms per token, 516.16 tokens per second) 4.41.525.932 I slot print_timing: id 0 | task 10553 | eval time = 1830.27 ms / 89 tokens ( 20.80 ms per token, 48.08 tokens per second) 4.41.525.933 I slot print_timing: id 0 | task 10553 | total time = 2721.48 ms / 549 tokens 4.41.525.933 I slot print_timing: id 0 | task 10553 | graphs reused = 10145 4.41.525.934 I slot print_timing: id 0 | task 10553 | graph reallocs = 0 / 0 (same size) / (changed size) 4.41.525.968 I slot release: id 0 | task 10553 | stop processing: n_tokens = 548, truncated = 0 4.41.532.300 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 548, t_last = 348450381845 4.41.542.987 I slot launch_slot_: id 0 | task 10645 | processing task, is_child = 0 4.45.434.609 I slot print_timing: id 0 | task 10645 | n_gen = 146, tg = 48.18 t/s, tg_3s = 48.51 t/s 4.46.594.198 I slot print_timing: id 0 | task 10645 | prompt eval time = 881.84 ms / 426 tokens ( 2.07 ms per token, 483.08 tokens per second) 4.46.594.205 I slot print_timing: id 0 | task 10645 | eval time = 4169.36 ms / 202 tokens ( 20.74 ms per token, 48.21 tokens per second) 4.46.594.205 I slot print_timing: id 0 | task 10645 | total time = 5051.20 ms / 628 tokens 4.46.594.206 I slot print_timing: id 0 | task 10645 | graphs reused = 10344 4.46.594.207 I slot print_timing: id 0 | task 10645 | graph reallocs = 0 / 0 (same size) / (changed size) 4.46.594.241 I slot release: id 0 | task 10645 | stop processing: n_tokens = 627, truncated = 0 4.46.599.801 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.117 (> 0.100 thold), f_keep = 0.059 4.46.611.492 I slot launch_slot_: id 0 | task 10850 | processing task, is_child = 0 4.49.878.795 I slot print_timing: id 0 | task 10850 | prompt eval time = 726.83 ms / 317 tokens ( 2.29 ms per token, 436.14 tokens per second) 4.49.878.799 I slot print_timing: id 0 | task 10850 | eval time = 2540.46 ms / 124 tokens ( 20.65 ms per token, 48.42 tokens per second) 4.49.878.799 I slot print_timing: id 0 | task 10850 | total time = 3267.29 ms / 441 tokens 4.49.878.800 I slot print_timing: id 0 | task 10850 | graphs reused = 10466 4.49.878.801 I slot print_timing: id 0 | task 10850 | graph reallocs = 0 / 0 (same size) / (changed size) 4.49.878.833 I slot release: id 0 | task 10850 | stop processing: n_tokens = 440, truncated = 0 4.49.884.670 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.104 (> 0.100 thold), f_keep = 0.084 4.49.887.284 I slot launch_slot_: id 0 | task 10977 | processing task, is_child = 0 4.53.284.715 I slot print_timing: id 0 | task 10977 | prompt eval time = 830.55 ms / 355 tokens ( 2.34 ms per token, 427.43 tokens per second) 4.53.284.722 I slot print_timing: id 0 | task 10977 | eval time = 2566.88 ms / 125 tokens ( 20.70 ms per token, 48.31 tokens per second) 4.53.284.723 I slot print_timing: id 0 | task 10977 | total time = 3397.42 ms / 480 tokens 4.53.284.724 I slot print_timing: id 0 | task 10977 | graphs reused = 10589 4.53.284.724 I slot print_timing: id 0 | task 10977 | graph reallocs = 0 / 0 (same size) / (changed size) 4.53.284.751 I slot release: id 0 | task 10977 | stop processing: n_tokens = 479, truncated = 0 4.53.290.660 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 479, t_last = 348462140628 4.53.302.619 I slot launch_slot_: id 0 | task 11105 | processing task, is_child = 0 4.56.481.401 I slot print_timing: id 0 | task 11105 | prompt eval time = 841.94 ms / 383 tokens ( 2.20 ms per token, 454.90 tokens per second) 4.56.481.405 I slot print_timing: id 0 | task 11105 | eval time = 2336.83 ms / 114 tokens ( 20.68 ms per token, 48.36 tokens per second) 4.56.481.405 I slot print_timing: id 0 | task 11105 | total time = 3178.77 ms / 497 tokens 4.56.481.406 I slot print_timing: id 0 | task 11105 | graphs reused = 10701 4.56.481.407 I slot print_timing: id 0 | task 11105 | graph reallocs = 0 / 0 (same size) / (changed size) 4.56.481.436 I slot release: id 0 | task 11105 | stop processing: n_tokens = 496, truncated = 0 4.56.488.127 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 496, t_last = 348465337313 4.56.501.656 I slot launch_slot_: id 0 | task 11222 | processing task, is_child = 0 4.59.501.690 I slot print_timing: id 0 | task 11222 | prompt eval time = 919.86 ms / 489 tokens ( 1.88 ms per token, 531.60 tokens per second) 4.59.501.694 I slot print_timing: id 0 | task 11222 | eval time = 2080.16 ms / 101 tokens ( 20.80 ms per token, 48.07 tokens per second) 4.59.501.695 I slot print_timing: id 0 | task 11222 | total time = 3000.02 ms / 590 tokens 4.59.501.695 I slot print_timing: id 0 | task 11222 | graphs reused = 10799 4.59.501.696 I slot print_timing: id 0 | task 11222 | graph reallocs = 0 / 0 (same size) / (changed size) 4.59.501.731 I slot release: id 0 | task 11222 | stop processing: n_tokens = 589, truncated = 0 4.59.507.802 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 589, t_last = 348468357608 4.59.524.032 I slot launch_slot_: id 0 | task 11326 | processing task, is_child = 0 5.02.639.112 I slot print_timing: id 0 | task 11326 | prompt eval time = 849.39 ms / 431 tokens ( 1.97 ms per token, 507.42 tokens per second) 5.02.639.118 I slot print_timing: id 0 | task 11326 | eval time = 2265.68 ms / 110 tokens ( 20.79 ms per token, 48.11 tokens per second) 5.02.639.118 I slot print_timing: id 0 | task 11326 | total time = 3115.07 ms / 541 tokens 5.02.639.119 I slot print_timing: id 0 | task 11326 | graphs reused = 10906 5.02.639.120 I slot print_timing: id 0 | task 11326 | graph reallocs = 0 / 0 (same size) / (changed size) 5.02.639.152 I slot release: id 0 | task 11326 | stop processing: n_tokens = 540, truncated = 0 5.02.646.976 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 540, t_last = 348471495029 5.02.661.936 I slot launch_slot_: id 0 | task 11439 | processing task, is_child = 0 5.05.956.230 I slot print_timing: id 0 | task 11439 | prompt eval time = 1364.06 ms / 648 tokens ( 2.11 ms per token, 475.05 tokens per second) 5.05.956.233 I slot print_timing: id 0 | task 11439 | eval time = 1930.22 ms / 94 tokens ( 20.76 ms per token, 48.18 tokens per second) 5.05.956.234 I slot print_timing: id 0 | task 11439 | total time = 3294.28 ms / 742 tokens 5.05.956.235 I slot print_timing: id 0 | task 11439 | graphs reused = 10998 5.05.956.235 I slot print_timing: id 0 | task 11439 | graph reallocs = 0 / 0 (same size) / (changed size) 5.05.956.281 I slot release: id 0 | task 11439 | stop processing: n_tokens = 741, truncated = 0 5.05.962.491 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 741, t_last = 348474812158 5.05.980.851 I slot launch_slot_: id 0 | task 11537 | processing task, is_child = 0 5.08.890.909 I slot print_timing: id 0 | task 11537 | prompt eval time = 871.67 ms / 436 tokens ( 2.00 ms per token, 500.19 tokens per second) 5.08.890.915 I slot print_timing: id 0 | task 11537 | eval time = 2038.38 ms / 99 tokens ( 20.80 ms per token, 48.08 tokens per second) 5.08.890.916 I slot print_timing: id 0 | task 11537 | total time = 2910.04 ms / 535 tokens 5.08.890.916 I slot print_timing: id 0 | task 11537 | graphs reused = 11094 5.08.890.917 I slot print_timing: id 0 | task 11537 | graph reallocs = 0 / 0 (same size) / (changed size) 5.08.890.946 I slot release: id 0 | task 11537 | stop processing: n_tokens = 534, truncated = 0 5.08.897.434 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 534, t_last = 348477746823 5.08.907.662 I slot launch_slot_: id 0 | task 11639 | processing task, is_child = 0 5.11.944.167 I slot print_timing: id 0 | task 11639 | prompt eval time = 915.78 ms / 475 tokens ( 1.93 ms per token, 518.68 tokens per second) 5.11.944.170 I slot print_timing: id 0 | task 11639 | eval time = 2120.71 ms / 103 tokens ( 20.79 ms per token, 48.10 tokens per second) 5.11.944.170 I slot print_timing: id 0 | task 11639 | total time = 3036.49 ms / 578 tokens 5.11.944.171 I slot print_timing: id 0 | task 11639 | graphs reused = 11194 5.11.944.172 I slot print_timing: id 0 | task 11639 | graph reallocs = 0 / 0 (same size) / (changed size) 5.11.944.202 I slot release: id 0 | task 11639 | stop processing: n_tokens = 577, truncated = 0 5.11.950.669 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 577, t_last = 348480800079 5.11.965.848 I slot launch_slot_: id 0 | task 11745 | processing task, is_child = 0 5.15.844.958 I slot print_timing: id 0 | task 11745 | n_gen = 146, tg = 48.19 t/s, tg_3s = 48.52 t/s 5.16.383.285 I slot print_timing: id 0 | task 11745 | prompt eval time = 869.93 ms / 441 tokens ( 1.97 ms per token, 506.94 tokens per second) 5.16.383.291 I slot print_timing: id 0 | task 11745 | eval time = 3547.49 ms / 172 tokens ( 20.75 ms per token, 48.20 tokens per second) 5.16.383.292 I slot print_timing: id 0 | task 11745 | total time = 4417.43 ms / 613 tokens 5.16.383.293 I slot print_timing: id 0 | task 11745 | graphs reused = 11363 5.16.383.293 I slot print_timing: id 0 | task 11745 | graph reallocs = 0 / 0 (same size) / (changed size) 5.16.383.322 I slot release: id 0 | task 11745 | stop processing: n_tokens = 612, truncated = 0 5.16.390.542 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 612, t_last = 348485239199 5.16.405.492 I slot launch_slot_: id 0 | task 11920 | processing task, is_child = 0 5.19.634.219 I slot print_timing: id 0 | task 11920 | prompt eval time = 1233.76 ms / 569 tokens ( 2.17 ms per token, 461.19 tokens per second) 5.19.634.226 I slot print_timing: id 0 | task 11920 | eval time = 1994.95 ms / 97 tokens ( 20.78 ms per token, 48.12 tokens per second) 5.19.634.227 I slot print_timing: id 0 | task 11920 | total time = 3228.72 ms / 666 tokens 5.19.634.228 I slot print_timing: id 0 | task 11920 | graphs reused = 11458 5.19.634.228 I slot print_timing: id 0 | task 11920 | graph reallocs = 0 / 0 (same size) / (changed size) 5.19.634.266 I slot release: id 0 | task 11920 | stop processing: n_tokens = 665, truncated = 0 5.19.641.775 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 665, t_last = 348488490143 5.19.660.208 I slot launch_slot_: id 0 | task 12021 | processing task, is_child = 0 5.24.109.677 I slot print_timing: id 0 | task 12021 | n_gen = 146, tg = 48.14 t/s, tg_3s = 48.47 t/s 5.24.440.972 I slot print_timing: id 0 | task 12021 | prompt eval time = 1437.27 ms / 646 tokens ( 2.22 ms per token, 449.46 tokens per second) 5.24.440.975 I slot print_timing: id 0 | task 12021 | eval time = 3343.48 ms / 162 tokens ( 20.77 ms per token, 48.15 tokens per second) 5.24.440.977 I slot print_timing: id 0 | task 12021 | total time = 4780.76 ms / 808 tokens 5.24.440.977 I slot print_timing: id 0 | task 12021 | graphs reused = 11617 5.24.440.978 I slot print_timing: id 0 | task 12021 | graph reallocs = 0 / 0 (same size) / (changed size) 5.24.441.021 I slot release: id 0 | task 12021 | stop processing: n_tokens = 807, truncated = 0 5.24.446.153 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 5.24.469.897 I slot launch_slot_: id 0 | task 12187 | processing task, is_child = 0 5.28.164.493 I slot print_timing: id 0 | task 12187 | n_gen = 146, tg = 48.33 t/s, tg_3s = 48.66 t/s 5.28.494.848 I slot print_timing: id 0 | task 12187 | prompt eval time = 694.17 ms / 244 tokens ( 2.84 ms per token, 351.50 tokens per second) 5.28.494.854 I slot print_timing: id 0 | task 12187 | eval time = 3330.77 ms / 162 tokens ( 20.69 ms per token, 48.34 tokens per second) 5.28.494.855 I slot print_timing: id 0 | task 12187 | total time = 4024.94 ms / 406 tokens 5.28.494.855 I slot print_timing: id 0 | task 12187 | graphs reused = 11776 5.28.494.856 I slot print_timing: id 0 | task 12187 | graph reallocs = 0 / 0 (same size) / (changed size) 5.28.494.877 I slot release: id 0 | task 12187 | stop processing: n_tokens = 405, truncated = 0 5.28.499.969 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.141 (> 0.100 thold), f_keep = 0.091 5.28.508.443 I slot launch_slot_: id 0 | task 12352 | processing task, is_child = 0 5.32.280.845 I slot print_timing: id 0 | task 12352 | prompt eval time = 763.99 ms / 263 tokens ( 2.90 ms per token, 344.25 tokens per second) 5.32.280.851 I slot print_timing: id 0 | task 12352 | eval time = 3008.41 ms / 147 tokens ( 20.61 ms per token, 48.53 tokens per second) 5.32.280.851 I slot print_timing: id 0 | task 12352 | total time = 3772.39 ms / 410 tokens 5.32.280.852 I slot print_timing: id 0 | task 12352 | graphs reused = 11921 5.32.280.852 I slot print_timing: id 0 | task 12352 | graph reallocs = 0 / 0 (same size) / (changed size) 5.32.280.877 I slot release: id 0 | task 12352 | stop processing: n_tokens = 409, truncated = 0 5.32.285.959 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.149 (> 0.100 thold), f_keep = 0.090 5.32.294.523 I slot launch_slot_: id 0 | task 12502 | processing task, is_child = 0 5.36.016.674 I slot print_timing: id 0 | task 12502 | n_gen = 147, tg = 48.53 t/s, tg_3s = 48.86 t/s 5.37.494.801 I slot print_timing: id 0 | task 12502 | prompt eval time = 713.79 ms / 248 tokens ( 2.88 ms per token, 347.44 tokens per second) 5.37.494.807 I slot print_timing: id 0 | task 12502 | eval time = 4486.48 ms / 218 tokens ( 20.68 ms per token, 48.37 tokens per second) 5.37.494.808 I slot print_timing: id 0 | task 12502 | total time = 5200.27 ms / 466 tokens 5.37.494.808 I slot print_timing: id 0 | task 12502 | graphs reused = 12136 5.37.494.809 I slot print_timing: id 0 | task 12502 | graph reallocs = 0 / 0 (same size) / (changed size) 5.37.494.834 I slot release: id 0 | task 12502 | stop processing: n_tokens = 465, truncated = 0 5.37.499.802 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.169 (> 0.100 thold), f_keep = 0.080 5.37.845.585 I slot launch_slot_: id 0 | task 12723 | processing task, is_child = 0 5.41.543.706 I slot print_timing: id 0 | task 12723 | n_gen = 147, tg = 48.62 t/s, tg_3s = 48.96 t/s 5.41.831.699 I slot print_timing: id 0 | task 12723 | prompt eval time = 695.43 ms / 219 tokens ( 3.18 ms per token, 314.91 tokens per second) 5.41.831.705 I slot print_timing: id 0 | task 12723 | eval time = 3290.66 ms / 161 tokens ( 20.57 ms per token, 48.62 tokens per second) 5.41.831.706 I slot print_timing: id 0 | task 12723 | total time = 3986.10 ms / 380 tokens 5.41.831.707 I slot print_timing: id 0 | task 12723 | graphs reused = 12294 5.41.831.707 I slot print_timing: id 0 | task 12723 | graph reallocs = 0 / 0 (same size) / (changed size) 5.41.831.763 I slot release: id 0 | task 12723 | stop processing: n_tokens = 379, truncated = 0 5.41.838.722 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.128 (> 0.100 thold), f_keep = 0.098 5.41.848.688 I slot launch_slot_: id 0 | task 12887 | processing task, is_child = 0 5.45.602.065 I slot print_timing: id 0 | task 12887 | n_gen = 147, tg = 48.49 t/s, tg_3s = 48.82 t/s 5.48.084.028 I slot print_timing: id 0 | task 12887 | prompt eval time = 742.17 ms / 288 tokens ( 2.58 ms per token, 388.05 tokens per second) 5.48.084.034 I slot print_timing: id 0 | task 12887 | eval time = 5493.16 ms / 267 tokens ( 20.65 ms per token, 48.42 tokens per second) 5.48.084.034 I slot print_timing: id 0 | task 12887 | total time = 6235.33 ms / 555 tokens 5.48.084.035 I slot print_timing: id 0 | task 12887 | graphs reused = 12558 5.48.084.035 I slot print_timing: id 0 | task 12887 | graph reallocs = 0 / 0 (same size) / (changed size) 5.48.084.075 I slot release: id 0 | task 12887 | stop processing: n_tokens = 554, truncated = 0 5.48.090.250 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.129 (> 0.100 thold), f_keep = 0.067 5.48.090.329 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 62.729 MiB) 5.48.108.429 I slot launch_slot_: id 0 | task 13157 | processing task, is_child = 0 5.51.920.022 I slot print_timing: id 0 | task 13157 | n_gen = 147, tg = 48.50 t/s, tg_3s = 48.83 t/s 5.53.097.220 I slot print_timing: id 0 | task 13157 | prompt eval time = 801.27 ms / 286 tokens ( 2.80 ms per token, 356.93 tokens per second) 5.53.097.223 I slot print_timing: id 0 | task 13157 | eval time = 4187.51 ms / 204 tokens ( 20.63 ms per token, 48.48 tokens per second) 5.53.097.223 I slot print_timing: id 0 | task 13157 | total time = 4988.78 ms / 490 tokens 5.53.097.224 I slot print_timing: id 0 | task 13157 | graphs reused = 12760 5.53.097.224 I slot print_timing: id 0 | task 13157 | graph reallocs = 0 / 0 (same size) / (changed size) 5.53.097.258 I slot release: id 0 | task 13157 | stop processing: n_tokens = 489, truncated = 0 5.53.103.103 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.106 (> 0.100 thold), f_keep = 0.080 5.53.103.172 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 46.688 MiB) 5.53.114.163 I slot launch_slot_: id 0 | task 13364 | processing task, is_child = 0 5.57.024.319 I slot print_timing: id 0 | task 13364 | n_gen = 146, tg = 48.30 t/s, tg_3s = 48.63 t/s 6.00.025.031 I slot print_timing: id 0 | task 13364 | n_gen = 291, tg = 48.31 t/s, tg_3s = 48.32 t/s 6.01.019.038 I slot print_timing: id 0 | task 13364 | prompt eval time = 908.13 ms / 368 tokens ( 2.47 ms per token, 405.23 tokens per second) 6.01.019.045 I slot print_timing: id 0 | task 13364 | eval time = 6996.74 ms / 339 tokens ( 20.70 ms per token, 48.31 tokens per second) 6.01.019.045 I slot print_timing: id 0 | task 13364 | total time = 7904.87 ms / 707 tokens 6.01.019.046 I slot print_timing: id 0 | task 13364 | graphs reused = 13096 6.01.019.047 I slot print_timing: id 0 | task 13364 | graph reallocs = 0 / 0 (same size) / (changed size) 6.01.019.074 I slot release: id 0 | task 13364 | stop processing: n_tokens = 706, truncated = 0 6.01.024.110 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.164 (> 0.100 thold), f_keep = 0.052 6.01.024.195 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 54.961 MiB) 6.01.024.209 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 64.287 MiB) 6.01.043.055 I slot launch_slot_: id 0 | task 13706 | processing task, is_child = 0 6.04.205.217 I slot print_timing: id 0 | task 13706 | prompt eval time = 730.71 ms / 226 tokens ( 3.23 ms per token, 309.29 tokens per second) 6.04.205.220 I slot print_timing: id 0 | task 13706 | eval time = 2431.43 ms / 119 tokens ( 20.61 ms per token, 48.53 tokens per second) 6.04.205.221 I slot print_timing: id 0 | task 13706 | total time = 3162.15 ms / 345 tokens 6.04.205.221 I slot print_timing: id 0 | task 13706 | graphs reused = 13212 6.04.205.229 I slot print_timing: id 0 | task 13706 | graph reallocs = 0 / 0 (same size) / (changed size) 6.04.205.258 I slot release: id 0 | task 13706 | stop processing: n_tokens = 344, truncated = 0 6.04.210.179 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.162 (> 0.100 thold), f_keep = 0.108 6.04.210.242 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 74.394 MiB) 6.04.216.319 I slot launch_slot_: id 0 | task 13828 | processing task, is_child = 0 6.07.968.267 I slot print_timing: id 0 | task 13828 | n_gen = 147, tg = 48.53 t/s, tg_3s = 48.86 t/s 6.09.205.081 I slot print_timing: id 0 | task 13828 | prompt eval time = 743.27 ms / 229 tokens ( 3.25 ms per token, 308.10 tokens per second) 6.09.205.087 I slot print_timing: id 0 | task 13828 | eval time = 4245.48 ms / 207 tokens ( 20.61 ms per token, 48.52 tokens per second) 6.09.205.088 I slot print_timing: id 0 | task 13828 | total time = 4988.75 ms / 436 tokens 6.09.205.089 I slot print_timing: id 0 | task 13828 | graphs reused = 13416 6.09.205.089 I slot print_timing: id 0 | task 13828 | graph reallocs = 0 / 0 (same size) / (changed size) 6.09.205.126 I slot release: id 0 | task 13828 | stop processing: n_tokens = 435, truncated = 0 6.09.210.625 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.130 (> 0.100 thold), f_keep = 0.085 6.09.210.692 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 59.132 MiB) 6.09.216.676 I slot launch_slot_: id 0 | task 14038 | processing task, is_child = 0 6.13.062.360 I slot print_timing: id 0 | task 14038 | n_gen = 147, tg = 48.46 t/s, tg_3s = 48.79 t/s 6.14.404.102 I slot print_timing: id 0 | task 14038 | prompt eval time = 833.01 ms / 285 tokens ( 2.92 ms per token, 342.13 tokens per second) 6.14.404.105 I slot print_timing: id 0 | task 14038 | eval time = 4354.41 ms / 212 tokens ( 20.64 ms per token, 48.46 tokens per second) 6.14.404.106 I slot print_timing: id 0 | task 14038 | total time = 5187.41 ms / 497 tokens 6.14.404.107 I slot print_timing: id 0 | task 14038 | graphs reused = 13626 6.14.404.107 I slot print_timing: id 0 | task 14038 | graph reallocs = 0 / 0 (same size) / (changed size) 6.14.404.148 I slot release: id 0 | task 14038 | stop processing: n_tokens = 496, truncated = 0 6.14.409.755 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 6.14.409.835 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.209 MiB) 6.14.421.613 I slot launch_slot_: id 0 | task 14253 | processing task, is_child = 0 6.18.076.719 I slot print_timing: id 0 | task 14253 | prompt eval time = 942.32 ms / 337 tokens ( 2.80 ms per token, 357.63 tokens per second) 6.18.076.724 I slot print_timing: id 0 | task 14253 | eval time = 2712.77 ms / 131 tokens ( 20.87 ms per token, 47.92 tokens per second) 6.18.076.725 I slot print_timing: id 0 | task 14253 | total time = 3655.09 ms / 468 tokens 6.18.076.725 I slot print_timing: id 0 | task 14253 | graphs reused = 13755 6.18.076.726 I slot print_timing: id 0 | task 14253 | graph reallocs = 0 / 0 (same size) / (changed size) 6.18.076.756 I slot release: id 0 | task 14253 | stop processing: n_tokens = 467, truncated = 0 6.18.081.949 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.179 (> 0.100 thold), f_keep = 0.111 6.18.082.021 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 92.116 MiB) 6.18.088.935 I slot launch_slot_: id 0 | task 14387 | processing task, is_child = 0 6.21.966.877 I slot print_timing: id 0 | task 14387 | n_gen = 147, tg = 48.47 t/s, tg_3s = 48.80 t/s 6.22.090.893 I slot print_timing: id 0 | task 14387 | prompt eval time = 865.82 ms / 290 tokens ( 2.99 ms per token, 334.94 tokens per second) 6.22.090.900 I slot print_timing: id 0 | task 14387 | eval time = 3136.12 ms / 153 tokens ( 20.63 ms per token, 48.47 tokens per second) 6.22.090.900 I slot print_timing: id 0 | task 14387 | total time = 4001.95 ms / 443 tokens 6.22.090.901 I slot print_timing: id 0 | task 14387 | graphs reused = 13906 6.22.090.902 I slot print_timing: id 0 | task 14387 | graph reallocs = 0 / 0 (same size) / (changed size) 6.22.090.933 I slot release: id 0 | task 14387 | stop processing: n_tokens = 442, truncated = 0 6.22.096.660 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.128 (> 0.100 thold), f_keep = 0.084 6.22.096.736 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 52.609 MiB) 6.22.116.430 I slot launch_slot_: id 0 | task 14543 | processing task, is_child = 0 6.25.963.045 I slot print_timing: id 0 | task 14543 | n_gen = 147, tg = 48.41 t/s, tg_3s = 48.74 t/s 6.27.009.095 I slot print_timing: id 0 | task 14543 | prompt eval time = 830.78 ms / 290 tokens ( 2.86 ms per token, 349.07 tokens per second) 6.27.009.099 I slot print_timing: id 0 | task 14543 | eval time = 4061.87 ms / 197 tokens ( 20.72 ms per token, 48.25 tokens per second) 6.27.009.099 I slot print_timing: id 0 | task 14543 | total time = 4892.65 ms / 487 tokens 6.27.009.100 I slot print_timing: id 0 | task 14543 | graphs reused = 14101 6.27.009.100 I slot print_timing: id 0 | task 14543 | graph reallocs = 0 / 0 (same size) / (changed size) 6.27.009.137 I slot release: id 0 | task 14543 | stop processing: n_tokens = 486, truncated = 0 6.27.014.285 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.124 (> 0.100 thold), f_keep = 0.076 6.27.014.359 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 57.997 MiB) 6.27.035.370 I slot launch_slot_: id 0 | task 14743 | processing task, is_child = 0 6.30.898.613 I slot print_timing: id 0 | task 14743 | n_gen = 147, tg = 48.61 t/s, tg_3s = 48.95 t/s 6.33.917.203 I slot print_timing: id 0 | task 14743 | n_gen = 293, tg = 48.49 t/s, tg_3s = 48.37 t/s 6.34.021.099 I slot print_timing: id 0 | task 14743 | prompt eval time = 859.89 ms / 299 tokens ( 2.88 ms per token, 347.72 tokens per second) 6.34.021.104 I slot print_timing: id 0 | task 14743 | eval time = 6125.83 ms / 298 tokens ( 20.63 ms per token, 48.48 tokens per second) 6.34.021.106 I slot print_timing: id 0 | task 14743 | total time = 6985.72 ms / 597 tokens 6.34.021.106 I slot print_timing: id 0 | task 14743 | graphs reused = 14396 6.34.021.107 I slot print_timing: id 0 | task 14743 | graph reallocs = 0 / 0 (same size) / (changed size) 6.34.021.141 I slot release: id 0 | task 14743 | stop processing: n_tokens = 596, truncated = 0 6.34.026.125 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.154 (> 0.100 thold), f_keep = 0.062 6.34.026.205 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 78.359 MiB) 6.34.026.231 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 69.128 MiB) 6.34.044.849 I slot launch_slot_: id 0 | task 15044 | processing task, is_child = 0 6.37.805.296 I slot print_timing: id 0 | task 15044 | n_gen = 147, tg = 48.42 t/s, tg_3s = 48.75 t/s 6.38.342.591 I slot print_timing: id 0 | task 15044 | prompt eval time = 745.35 ms / 241 tokens ( 3.09 ms per token, 323.34 tokens per second) 6.38.342.595 I slot print_timing: id 0 | task 15044 | eval time = 3552.38 ms / 173 tokens ( 20.65 ms per token, 48.42 tokens per second) 6.38.342.596 I slot print_timing: id 0 | task 15044 | total time = 4297.73 ms / 414 tokens 6.38.342.596 I slot print_timing: id 0 | task 15044 | graphs reused = 14566 6.38.342.597 I slot print_timing: id 0 | task 15044 | graph reallocs = 0 / 0 (same size) / (changed size) 6.38.342.637 I slot release: id 0 | task 15044 | stop processing: n_tokens = 413, truncated = 0 6.38.348.511 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 6.38.348.579 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 61.306 MiB) 6.38.358.560 I slot launch_slot_: id 0 | task 15220 | processing task, is_child = 0 6.42.260.245 I slot print_timing: id 0 | task 15220 | n_gen = 146, tg = 48.23 t/s, tg_3s = 48.56 t/s 6.42.485.795 I slot print_timing: id 0 | task 15220 | prompt eval time = 895.33 ms / 323 tokens ( 2.77 ms per token, 360.76 tokens per second) 6.42.485.801 I slot print_timing: id 0 | task 15220 | eval time = 3231.89 ms / 157 tokens ( 20.72 ms per token, 48.27 tokens per second) 6.42.485.802 I slot print_timing: id 0 | task 15220 | total time = 4127.23 ms / 480 tokens 6.42.485.803 I slot print_timing: id 0 | task 15220 | graphs reused = 14721 6.42.485.803 I slot print_timing: id 0 | task 15220 | graph reallocs = 0 / 0 (same size) / (changed size) 6.42.485.843 I slot release: id 0 | task 15220 | stop processing: n_tokens = 479, truncated = 0 6.42.491.012 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.077 6.42.491.080 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 61.963 MiB) 6.42.507.731 I slot launch_slot_: id 0 | task 15380 | processing task, is_child = 0 6.46.276.321 I slot print_timing: id 0 | task 15380 | n_gen = 147, tg = 48.42 t/s, tg_3s = 48.76 t/s 6.49.278.106 I slot print_timing: id 0 | task 15380 | n_gen = 292, tg = 48.36 t/s, tg_3s = 48.30 t/s 6.52.037.365 I slot print_timing: id 0 | task 15380 | prompt eval time = 753.56 ms / 237 tokens ( 3.18 ms per token, 314.51 tokens per second) 6.52.037.369 I slot print_timing: id 0 | task 15380 | eval time = 8776.06 ms / 425 tokens ( 20.70 ms per token, 48.31 tokens per second) 6.52.037.370 I slot print_timing: id 0 | task 15380 | total time = 9529.62 ms / 662 tokens 6.52.037.370 I slot print_timing: id 0 | task 15380 | graphs reused = 15142 6.52.037.371 I slot print_timing: id 0 | task 15380 | graph reallocs = 0 / 0 (same size) / (changed size) 6.52.037.409 I slot release: id 0 | task 15380 | stop processing: n_tokens = 661, truncated = 0 6.52.043.003 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.056 6.52.043.091 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 58.216 MiB) 6.52.062.080 I slot launch_slot_: id 0 | task 15808 | processing task, is_child = 0 6.55.717.188 I slot print_timing: id 0 | task 15808 | n_gen = 147, tg = 48.57 t/s, tg_3s = 48.90 t/s 6.56.027.252 I slot print_timing: id 0 | task 15808 | prompt eval time = 648.88 ms / 217 tokens ( 2.99 ms per token, 334.42 tokens per second) 6.56.027.258 I slot print_timing: id 0 | task 15808 | eval time = 3316.28 ms / 162 tokens ( 20.60 ms per token, 48.55 tokens per second) 6.56.027.258 I slot print_timing: id 0 | task 15808 | total time = 3965.16 ms / 379 tokens 6.56.027.259 I slot print_timing: id 0 | task 15808 | graphs reused = 15301 6.56.027.260 I slot print_timing: id 0 | task 15808 | graph reallocs = 0 / 0 (same size) / (changed size) 6.56.027.279 I slot release: id 0 | task 15808 | stop processing: n_tokens = 378, truncated = 0 6.56.033.229 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.121 (> 0.100 thold), f_keep = 0.098 6.56.033.293 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 54.948 MiB) 6.56.045.052 I slot launch_slot_: id 0 | task 15973 | processing task, is_child = 0 6.59.923.902 I slot print_timing: id 0 | task 15973 | n_gen = 147, tg = 48.46 t/s, tg_3s = 48.79 t/s 7.02.599.443 I slot print_timing: id 0 | task 15973 | prompt eval time = 866.02 ms / 306 tokens ( 2.83 ms per token, 353.34 tokens per second) 7.02.599.447 I slot print_timing: id 0 | task 15973 | eval time = 5688.36 ms / 276 tokens ( 20.68 ms per token, 48.34 tokens per second) 7.02.599.447 I slot print_timing: id 0 | task 15973 | total time = 6554.38 ms / 582 tokens 7.02.599.448 I slot print_timing: id 0 | task 15973 | graphs reused = 15574 7.02.599.449 I slot print_timing: id 0 | task 15973 | graph reallocs = 0 / 0 (same size) / (changed size) 7.02.599.477 I slot release: id 0 | task 15973 | stop processing: n_tokens = 581, truncated = 0 7.02.604.635 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.149 (> 0.100 thold), f_keep = 0.064 7.02.604.710 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 61.006 MiB) 7.02.604.735 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 55.741 MiB) 7.02.620.320 I slot launch_slot_: id 0 | task 16252 | processing task, is_child = 0 7.06.399.740 I slot print_timing: id 0 | task 16252 | prompt eval time = 777.02 ms / 248 tokens ( 3.13 ms per token, 319.17 tokens per second) 7.06.399.743 I slot print_timing: id 0 | task 16252 | eval time = 3002.39 ms / 146 tokens ( 20.71 ms per token, 48.29 tokens per second) 7.06.399.744 I slot print_timing: id 0 | task 16252 | total time = 3779.41 ms / 394 tokens 7.06.399.744 I slot print_timing: id 0 | task 16252 | graphs reused = 15717 7.06.399.753 I slot print_timing: id 0 | task 16252 | graph reallocs = 0 / 0 (same size) / (changed size) 7.06.399.780 I slot release: id 0 | task 16252 | stop processing: n_tokens = 393, truncated = 0 7.06.405.036 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.115 (> 0.100 thold), f_keep = 0.094 7.06.405.106 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 52.746 MiB) 7.06.420.710 I slot launch_slot_: id 0 | task 16401 | processing task, is_child = 0 7.10.302.863 I slot print_timing: id 0 | task 16401 | n_gen = 146, tg = 48.32 t/s, tg_3s = 48.65 t/s 7.13.310.360 I slot print_timing: id 0 | task 16401 | n_gen = 291, tg = 48.27 t/s, tg_3s = 48.21 t/s 7.16.229.859 I slot print_timing: id 0 | task 16401 | prompt eval time = 881.37 ms / 322 tokens ( 2.74 ms per token, 365.34 tokens per second) 7.16.229.864 I slot print_timing: id 0 | task 16401 | eval time = 8927.77 ms / 432 tokens ( 20.71 ms per token, 48.28 tokens per second) 7.16.229.864 I slot print_timing: id 0 | task 16401 | total time = 9809.14 ms / 754 tokens 7.16.229.865 I slot print_timing: id 0 | task 16401 | graphs reused = 16146 7.16.229.866 I slot print_timing: id 0 | task 16401 | graph reallocs = 0 / 0 (same size) / (changed size) 7.16.229.908 I slot release: id 0 | task 16401 | stop processing: n_tokens = 753, truncated = 0 7.16.235.170 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.137 (> 0.100 thold), f_keep = 0.050 7.16.235.271 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 61.662 MiB) 7.16.235.289 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 55.727 MiB) 7.16.250.950 I slot launch_slot_: id 0 | task 16836 | processing task, is_child = 0 7.19.470.908 I slot print_timing: id 0 | task 16836 | prompt eval time = 847.90 ms / 278 tokens ( 3.05 ms per token, 327.87 tokens per second) 7.19.470.914 I slot print_timing: id 0 | task 16836 | eval time = 2372.04 ms / 116 tokens ( 20.63 ms per token, 48.48 tokens per second) 7.19.470.914 I slot print_timing: id 0 | task 16836 | total time = 3219.95 ms / 394 tokens 7.19.470.915 I slot print_timing: id 0 | task 16836 | graphs reused = 16260 7.19.470.915 I slot print_timing: id 0 | task 16836 | graph reallocs = 0 / 0 (same size) / (changed size) 7.19.470.953 I slot release: id 0 | task 16836 | stop processing: n_tokens = 393, truncated = 0 7.19.476.313 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.109 (> 0.100 thold), f_keep = 0.094 7.19.476.377 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.072 MiB) 7.19.488.263 I slot launch_slot_: id 0 | task 16955 | processing task, is_child = 0 7.23.386.691 I slot print_timing: id 0 | task 16955 | n_gen = 146, tg = 48.10 t/s, tg_3s = 48.43 t/s 7.23.985.965 I slot print_timing: id 0 | task 16955 | prompt eval time = 883.97 ms / 338 tokens ( 2.62 ms per token, 382.36 tokens per second) 7.23.985.971 I slot print_timing: id 0 | task 16955 | eval time = 3613.72 ms / 175 tokens ( 20.77 ms per token, 48.15 tokens per second) 7.23.985.972 I slot print_timing: id 0 | task 16955 | total time = 4497.69 ms / 513 tokens 7.23.985.973 I slot print_timing: id 0 | task 16955 | graphs reused = 16433 7.23.985.973 I slot print_timing: id 0 | task 16955 | graph reallocs = 0 / 0 (same size) / (changed size) 7.23.986.020 I slot release: id 0 | task 16955 | stop processing: n_tokens = 512, truncated = 0 7.23.991.495 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.109 (> 0.100 thold), f_keep = 0.072 7.23.991.565 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 76.349 MiB) 7.24.004.626 I slot launch_slot_: id 0 | task 17133 | processing task, is_child = 0 7.27.604.905 I slot print_timing: id 0 | task 17133 | prompt eval time = 949.46 ms / 338 tokens ( 2.81 ms per token, 355.99 tokens per second) 7.27.604.909 I slot print_timing: id 0 | task 17133 | eval time = 2650.80 ms / 129 tokens ( 20.71 ms per token, 48.29 tokens per second) 7.27.604.909 I slot print_timing: id 0 | task 17133 | total time = 3600.26 ms / 467 tokens 7.27.604.910 I slot print_timing: id 0 | task 17133 | graphs reused = 16560 7.27.604.911 I slot print_timing: id 0 | task 17133 | graph reallocs = 0 / 0 (same size) / (changed size) 7.27.604.940 I slot release: id 0 | task 17133 | stop processing: n_tokens = 466, truncated = 0 7.27.610.218 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.111 (> 0.100 thold), f_keep = 0.079 7.27.610.288 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 66.899 MiB) 7.27.627.206 I slot launch_slot_: id 0 | task 17265 | processing task, is_child = 0 7.31.544.721 I slot print_timing: id 0 | task 17265 | n_gen = 146, tg = 48.29 t/s, tg_3s = 48.62 t/s 7.34.554.830 I slot print_timing: id 0 | task 17265 | n_gen = 291, tg = 48.23 t/s, tg_3s = 48.17 t/s 7.34.596.457 I slot print_timing: id 0 | task 17265 | prompt eval time = 914.65 ms / 333 tokens ( 2.75 ms per token, 364.07 tokens per second) 7.34.596.464 I slot print_timing: id 0 | task 17265 | eval time = 6054.59 ms / 293 tokens ( 20.73 ms per token, 48.23 tokens per second) 7.34.596.464 I slot print_timing: id 0 | task 17265 | total time = 6969.24 ms / 626 tokens 7.34.596.465 I slot print_timing: id 0 | task 17265 | graphs reused = 16850 7.34.596.465 I slot print_timing: id 0 | task 17265 | graph reallocs = 0 / 0 (same size) / (changed size) 7.34.596.505 I slot release: id 0 | task 17265 | stop processing: n_tokens = 625, truncated = 0 7.34.601.807 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.129 (> 0.100 thold), f_keep = 0.059 7.34.601.884 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 71.631 MiB) 7.34.601.900 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 75.747 MiB) 7.34.616.033 I slot launch_slot_: id 0 | task 17561 | processing task, is_child = 0 7.38.485.103 I slot print_timing: id 0 | task 17561 | n_gen = 146, tg = 48.17 t/s, tg_3s = 48.51 t/s 7.38.587.826 I slot print_timing: id 0 | task 17561 | prompt eval time = 859.08 ms / 287 tokens ( 2.99 ms per token, 334.08 tokens per second) 7.38.587.831 I slot print_timing: id 0 | task 17561 | eval time = 3112.70 ms / 151 tokens ( 20.75 ms per token, 48.19 tokens per second) 7.38.587.832 I slot print_timing: id 0 | task 17561 | total time = 3971.79 ms / 438 tokens 7.38.587.833 I slot print_timing: id 0 | task 17561 | graphs reused = 16999 7.38.587.833 I slot print_timing: id 0 | task 17561 | graph reallocs = 0 / 0 (same size) / (changed size) 7.38.587.857 I slot release: id 0 | task 17561 | stop processing: n_tokens = 437, truncated = 0 7.38.593.149 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.162 (> 0.100 thold), f_keep = 0.085 7.38.593.211 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 53.293 MiB) 7.38.608.496 I slot launch_slot_: id 0 | task 17715 | processing task, is_child = 0 7.42.003.488 I slot print_timing: id 0 | task 17715 | prompt eval time = 691.57 ms / 229 tokens ( 3.02 ms per token, 331.13 tokens per second) 7.42.003.494 I slot print_timing: id 0 | task 17715 | eval time = 2703.41 ms / 132 tokens ( 20.64 ms per token, 48.46 tokens per second) 7.42.003.495 I slot print_timing: id 0 | task 17715 | total time = 3394.98 ms / 361 tokens 7.42.003.504 I slot print_timing: id 0 | task 17715 | graphs reused = 17128 7.42.003.506 I slot print_timing: id 0 | task 17715 | graph reallocs = 0 / 0 (same size) / (changed size) 7.42.003.537 I slot release: id 0 | task 17715 | stop processing: n_tokens = 360, truncated = 0 7.42.008.674 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.117 (> 0.100 thold), f_keep = 0.103 7.42.008.740 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 67.351 MiB) 7.42.022.762 I slot launch_slot_: id 0 | task 17850 | processing task, is_child = 0 7.45.926.867 I slot print_timing: id 0 | task 17850 | n_gen = 147, tg = 48.41 t/s, tg_3s = 48.74 t/s 7.48.458.771 I slot print_timing: id 0 | task 17850 | prompt eval time = 888.34 ms / 315 tokens ( 2.82 ms per token, 354.60 tokens per second) 7.48.458.777 I slot print_timing: id 0 | task 17850 | eval time = 5547.66 ms / 269 tokens ( 20.70 ms per token, 48.31 tokens per second) 7.48.458.778 I slot print_timing: id 0 | task 17850 | total time = 6436.00 ms / 584 tokens 7.48.458.778 I slot print_timing: id 0 | task 17850 | graphs reused = 17394 7.48.458.779 I slot print_timing: id 0 | task 17850 | graph reallocs = 0 / 0 (same size) / (changed size) 7.48.458.806 I slot release: id 0 | task 17850 | stop processing: n_tokens = 583, truncated = 0 7.48.463.686 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.183 (> 0.100 thold), f_keep = 0.063 7.48.463.762 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 68.704 MiB) 7.48.476.989 I slot launch_slot_: id 0 | task 18122 | processing task, is_child = 0 7.51.564.606 I slot print_timing: id 0 | task 18122 | prompt eval time = 656.53 ms / 202 tokens ( 3.25 ms per token, 307.68 tokens per second) 7.51.564.609 I slot print_timing: id 0 | task 18122 | eval time = 2431.08 ms / 119 tokens ( 20.60 ms per token, 48.54 tokens per second) 7.51.564.610 I slot print_timing: id 0 | task 18122 | total time = 3087.61 ms / 321 tokens 7.51.564.611 I slot print_timing: id 0 | task 18122 | graphs reused = 17510 7.51.564.611 I slot print_timing: id 0 | task 18122 | graph reallocs = 0 / 0 (same size) / (changed size) 7.51.564.632 I slot release: id 0 | task 18122 | stop processing: n_tokens = 320, truncated = 0 7.51.569.541 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.154 (> 0.100 thold), f_keep = 0.116 7.51.569.596 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 66.393 MiB) 7.51.581.036 I slot launch_slot_: id 0 | task 18244 | processing task, is_child = 0 7.54.986.343 I slot print_timing: id 0 | task 18244 | prompt eval time = 743.28 ms / 240 tokens ( 3.10 ms per token, 322.89 tokens per second) 7.54.986.347 I slot print_timing: id 0 | task 18244 | eval time = 2662.01 ms / 130 tokens ( 20.64 ms per token, 48.46 tokens per second) 7.54.986.348 I slot print_timing: id 0 | task 18244 | total time = 3405.29 ms / 370 tokens 7.54.986.348 I slot print_timing: id 0 | task 18244 | graphs reused = 17637 7.54.986.349 I slot print_timing: id 0 | task 18244 | graph reallocs = 0 / 0 (same size) / (changed size) 7.54.986.373 I slot release: id 0 | task 18244 | stop processing: n_tokens = 369, truncated = 0 7.54.992.036 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.119 (> 0.100 thold), f_keep = 0.100 7.54.992.098 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 55.631 MiB) 7.55.000.228 I slot launch_slot_: id 0 | task 18377 | processing task, is_child = 0 7.58.801.383 I slot print_timing: id 0 | task 18377 | n_gen = 147, tg = 48.35 t/s, tg_3s = 48.68 t/s 8.00.399.948 I slot print_timing: id 0 | task 18377 | prompt eval time = 781.36 ms / 312 tokens ( 2.50 ms per token, 399.30 tokens per second) 8.00.399.954 I slot print_timing: id 0 | task 18377 | eval time = 4618.35 ms / 224 tokens ( 20.71 ms per token, 48.29 tokens per second) 8.00.399.955 I slot print_timing: id 0 | task 18377 | total time = 5399.71 ms / 536 tokens 8.00.399.955 I slot print_timing: id 0 | task 18377 | graphs reused = 17858 8.00.399.956 I slot print_timing: id 0 | task 18377 | graph reallocs = 0 / 0 (same size) / (changed size) 8.00.399.980 I slot release: id 0 | task 18377 | stop processing: n_tokens = 535, truncated = 0 8.00.405.335 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.118 (> 0.100 thold), f_keep = 0.069 8.00.405.413 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 58.900 MiB) 8.00.418.834 I slot launch_slot_: id 0 | task 18604 | processing task, is_child = 0 8.04.201.949 I slot print_timing: id 0 | task 18604 | n_gen = 147, tg = 48.35 t/s, tg_3s = 48.68 t/s 8.07.211.185 I slot print_timing: id 0 | task 18604 | n_gen = 292, tg = 48.27 t/s, tg_3s = 48.18 t/s 8.09.134.503 I slot print_timing: id 0 | task 18604 | prompt eval time = 763.34 ms / 314 tokens ( 2.43 ms per token, 411.35 tokens per second) 8.09.134.509 I slot print_timing: id 0 | task 18604 | eval time = 7952.32 ms / 385 tokens ( 20.71 ms per token, 48.29 tokens per second) 8.09.134.510 I slot print_timing: id 0 | task 18604 | total time = 8715.66 ms / 699 tokens 8.09.134.510 I slot print_timing: id 0 | task 18604 | graphs reused = 18240 8.09.134.511 I slot print_timing: id 0 | task 18604 | graph reallocs = 0 / 0 (same size) / (changed size) 8.09.134.547 I slot release: id 0 | task 18604 | stop processing: n_tokens = 698, truncated = 0 8.09.140.187 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.109 (> 0.100 thold), f_keep = 0.053 8.09.140.271 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 66.065 MiB) 8.09.140.284 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 66.995 MiB) 8.09.158.696 I slot launch_slot_: id 0 | task 18992 | processing task, is_child = 0 8.13.027.153 I slot print_timing: id 0 | task 18992 | n_gen = 146, tg = 48.29 t/s, tg_3s = 48.63 t/s 8.14.358.035 I slot print_timing: id 0 | task 18992 | prompt eval time = 865.90 ms / 339 tokens ( 2.55 ms per token, 391.50 tokens per second) 8.14.358.039 I slot print_timing: id 0 | task 18992 | eval time = 4333.42 ms / 210 tokens ( 20.73 ms per token, 48.23 tokens per second) 8.14.358.044 I slot print_timing: id 0 | task 18992 | total time = 5199.32 ms / 549 tokens 8.14.358.045 I slot print_timing: id 0 | task 18992 | graphs reused = 18447 8.14.358.045 I slot print_timing: id 0 | task 18992 | graph reallocs = 0 / 0 (same size) / (changed size) 8.14.358.073 I slot release: id 0 | task 18992 | stop processing: n_tokens = 548, truncated = 0 8.14.364.032 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.105 (> 0.100 thold), f_keep = 0.068 8.14.364.119 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 54.045 MiB) 8.14.384.431 I slot launch_slot_: id 0 | task 19205 | processing task, is_child = 0 8.17.233.631 I slot print_timing: id 0 | task 19205 | prompt eval time = 880.62 ms / 352 tokens ( 2.50 ms per token, 399.72 tokens per second) 8.17.233.635 I slot print_timing: id 0 | task 19205 | eval time = 1968.56 ms / 96 tokens ( 20.72 ms per token, 48.26 tokens per second) 8.17.233.635 I slot print_timing: id 0 | task 19205 | total time = 2849.18 ms / 448 tokens 8.17.233.636 I slot print_timing: id 0 | task 19205 | graphs reused = 18541 8.17.233.637 I slot print_timing: id 0 | task 19205 | graph reallocs = 0 / 0 (same size) / (changed size) 8.17.233.680 I slot release: id 0 | task 19205 | stop processing: n_tokens = 447, truncated = 0 8.17.239.229 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.113 (> 0.100 thold), f_keep = 0.083 8.17.239.301 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 83.200 MiB) 8.17.253.635 I slot launch_slot_: id 0 | task 19304 | processing task, is_child = 0 8.20.323.303 I slot print_timing: id 0 | task 19304 | prompt eval time = 856.45 ms / 328 tokens ( 2.61 ms per token, 382.98 tokens per second) 8.20.323.309 I slot print_timing: id 0 | task 19304 | eval time = 2213.21 ms / 108 tokens ( 20.68 ms per token, 48.35 tokens per second) 8.20.323.311 I slot print_timing: id 0 | task 19304 | total time = 3069.65 ms / 436 tokens 8.20.323.311 I slot print_timing: id 0 | task 19304 | graphs reused = 18647 8.20.323.312 I slot print_timing: id 0 | task 19304 | graph reallocs = 0 / 0 (same size) / (changed size) 8.20.323.338 I slot release: id 0 | task 19304 | stop processing: n_tokens = 435, truncated = 0 8.20.328.808 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.127 (> 0.100 thold), f_keep = 0.085 8.20.328.875 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 50.353 MiB) 8.20.328.893 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 54.852 MiB) 8.20.347.483 I slot launch_slot_: id 0 | task 19415 | processing task, is_child = 0 8.23.759.779 I slot print_timing: id 0 | task 19415 | prompt eval time = 746.97 ms / 292 tokens ( 2.56 ms per token, 390.91 tokens per second) 8.23.759.785 I slot print_timing: id 0 | task 19415 | eval time = 2665.32 ms / 130 tokens ( 20.66 ms per token, 48.40 tokens per second) 8.23.759.786 I slot print_timing: id 0 | task 19415 | total time = 3412.28 ms / 422 tokens 8.23.759.787 I slot print_timing: id 0 | task 19415 | graphs reused = 18775 8.23.759.787 I slot print_timing: id 0 | task 19415 | graph reallocs = 0 / 0 (same size) / (changed size) 8.23.759.811 I slot release: id 0 | task 19415 | stop processing: n_tokens = 421, truncated = 0 8.23.764.799 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.164 (> 0.100 thold), f_keep = 0.088 8.23.764.863 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 53.293 MiB) 8.23.779.042 I slot launch_slot_: id 0 | task 19548 | processing task, is_child = 0 8.26.037.261 I slot print_timing: id 0 | task 19548 | prompt eval time = 669.44 ms / 225 tokens ( 2.98 ms per token, 336.10 tokens per second) 8.26.037.265 I slot print_timing: id 0 | task 19548 | eval time = 1588.76 ms / 78 tokens ( 20.63 ms per token, 48.47 tokens per second) 8.26.037.266 I slot print_timing: id 0 | task 19548 | total time = 2258.20 ms / 303 tokens 8.26.037.267 I slot print_timing: id 0 | task 19548 | graphs reused = 18850 8.26.037.267 I slot print_timing: id 0 | task 19548 | graph reallocs = 0 / 0 (same size) / (changed size) 8.26.037.310 I slot release: id 0 | task 19548 | stop processing: n_tokens = 302, truncated = 0 8.26.043.575 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 302, t_last = 348674893187 8.26.043.634 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 52.308 MiB) 8.26.043.650 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 63.494 MiB) 8.26.056.779 I slot launch_slot_: id 0 | task 19629 | processing task, is_child = 0 8.30.040.520 I slot print_timing: id 0 | task 19629 | n_gen = 146, tg = 48.15 t/s, tg_3s = 48.48 t/s 8.30.206.456 I slot print_timing: id 0 | task 19629 | prompt eval time = 972.42 ms / 425 tokens ( 2.29 ms per token, 437.05 tokens per second) 8.30.206.463 I slot print_timing: id 0 | task 19629 | eval time = 3177.25 ms / 154 tokens ( 20.77 ms per token, 48.15 tokens per second) 8.30.206.463 I slot print_timing: id 0 | task 19629 | total time = 4149.67 ms / 579 tokens 8.30.206.464 I slot print_timing: id 0 | task 19629 | graphs reused = 19001 8.30.206.464 I slot print_timing: id 0 | task 19629 | graph reallocs = 0 / 0 (same size) / (changed size) 8.30.206.525 I slot release: id 0 | task 19629 | stop processing: n_tokens = 578, truncated = 0 8.30.213.677 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 578, t_last = 348679062402 8.30.213.756 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 93.305 MiB) 8.30.244.012 I slot launch_slot_: id 0 | task 19786 | processing task, is_child = 0 8.34.740.608 I slot print_timing: id 0 | task 19786 | n_gen = 146, tg = 48.06 t/s, tg_3s = 48.39 t/s 8.37.113.709 I slot print_timing: id 0 | task 19786 | prompt eval time = 1479.36 ms / 597 tokens ( 2.48 ms per token, 403.55 tokens per second) 8.37.113.716 I slot print_timing: id 0 | task 19786 | eval time = 5390.32 ms / 260 tokens ( 20.81 ms per token, 48.05 tokens per second) 8.37.113.716 I slot print_timing: id 0 | task 19786 | total time = 6869.69 ms / 857 tokens 8.37.113.717 I slot print_timing: id 0 | task 19786 | graphs reused = 19258 8.37.113.718 I slot print_timing: id 0 | task 19786 | graph reallocs = 0 / 0 (same size) / (changed size) 8.37.113.771 I slot release: id 0 | task 19786 | stop processing: n_tokens = 856, truncated = 0 8.37.120.807 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 856, t_last = 348685969648 8.37.120.899 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 56.042 MiB) 8.37.120.930 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 60.759 MiB) 8.37.138.885 I slot launch_slot_: id 0 | task 20050 | processing task, is_child = 0 8.41.403.239 I slot print_timing: id 0 | task 20050 | n_gen = 145, tg = 47.91 t/s, tg_3s = 48.24 t/s 8.41.899.498 I slot print_timing: id 0 | task 20050 | prompt eval time = 1258.67 ms / 547 tokens ( 2.30 ms per token, 434.59 tokens per second) 8.41.899.505 I slot print_timing: id 0 | task 20050 | eval time = 3501.93 ms / 169 tokens ( 20.84 ms per token, 47.97 tokens per second) 8.41.899.512 I slot print_timing: id 0 | task 20050 | total time = 4760.60 ms / 716 tokens 8.41.899.515 I slot print_timing: id 0 | task 20050 | graphs reused = 19425 8.41.899.515 I slot print_timing: id 0 | task 20050 | graph reallocs = 0 / 0 (same size) / (changed size) 8.41.899.563 I slot release: id 0 | task 20050 | stop processing: n_tokens = 715, truncated = 0 8.41.905.915 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 715, t_last = 348690755440 8.41.906.000 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 71.562 MiB) 8.41.906.020 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 81.805 MiB) 8.41.925.690 I slot launch_slot_: id 0 | task 20223 | processing task, is_child = 0 8.45.944.797 I slot print_timing: id 0 | task 20223 | n_gen = 146, tg = 48.08 t/s, tg_3s = 48.41 t/s 8.46.834.646 I slot print_timing: id 0 | task 20223 | prompt eval time = 1003.35 ms / 414 tokens ( 2.42 ms per token, 412.62 tokens per second) 8.46.834.652 I slot print_timing: id 0 | task 20223 | eval time = 3905.59 ms / 189 tokens ( 20.77 ms per token, 48.14 tokens per second) 8.46.834.653 I slot print_timing: id 0 | task 20223 | total time = 4908.94 ms / 603 tokens 8.46.834.653 I slot print_timing: id 0 | task 20223 | graphs reused = 19611 8.46.834.654 I slot print_timing: id 0 | task 20223 | graph reallocs = 0 / 0 (same size) / (changed size) 8.46.834.690 I slot release: id 0 | task 20223 | stop processing: n_tokens = 632, truncated = 0 8.46.840.408 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.100 (> 0.100 thold), f_keep = 0.059 8.46.840.482 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 54.100 MiB) 8.46.855.794 I slot launch_slot_: id 0 | task 20415 | processing task, is_child = 0 8.50.721.875 I slot print_timing: id 0 | task 20415 | n_gen = 146, tg = 48.23 t/s, tg_3s = 48.56 t/s 8.51.054.073 I slot print_timing: id 0 | task 20415 | prompt eval time = 859.75 ms / 340 tokens ( 2.53 ms per token, 395.47 tokens per second) 8.51.054.079 I slot print_timing: id 0 | task 20415 | eval time = 3338.52 ms / 162 tokens ( 20.74 ms per token, 48.22 tokens per second) 8.51.054.080 I slot print_timing: id 0 | task 20415 | total time = 4198.27 ms / 502 tokens 8.51.054.080 I slot print_timing: id 0 | task 20415 | graphs reused = 19770 8.51.054.081 I slot print_timing: id 0 | task 20415 | graph reallocs = 0 / 0 (same size) / (changed size) 8.51.054.106 I slot release: id 0 | task 20415 | stop processing: n_tokens = 530, truncated = 0 8.51.061.345 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 530, t_last = 348699909983 8.51.061.425 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 59.419 MiB) 8.51.061.443 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 68.267 MiB) 8.51.070.362 I slot launch_slot_: id 0 | task 20580 | processing task, is_child = 0 8.55.555.117 I slot print_timing: id 0 | task 20580 | n_gen = 146, tg = 48.15 t/s, tg_3s = 48.48 t/s 8.58.555.459 I slot print_timing: id 0 | task 20580 | n_gen = 290, tg = 48.07 t/s, tg_3s = 47.99 t/s 9.01.566.695 I slot print_timing: id 0 | task 20580 | n_gen = 434, tg = 47.99 t/s, tg_3s = 47.82 t/s 9.04.557.006 I slot print_timing: id 0 | task 20580 | prompt eval time = 1473.01 ms / 608 tokens ( 2.42 ms per token, 412.76 tokens per second) 9.04.557.010 I slot print_timing: id 0 | task 20580 | eval time = 12013.62 ms / 577 tokens ( 20.86 ms per token, 47.95 tokens per second) 9.04.557.011 I slot print_timing: id 0 | task 20580 | total time = 13486.63 ms / 1185 tokens 9.04.557.011 I slot print_timing: id 0 | task 20580 | graphs reused = 20343 9.04.557.012 I slot print_timing: id 0 | task 20580 | graph reallocs = 0 / 0 (same size) / (changed size) 9.04.557.069 I slot release: id 0 | task 20580 | stop processing: n_tokens = 1212, truncated = 0 9.04.563.178 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1212, t_last = 348713412946 9.04.563.291 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 55.481 MiB) 9.04.563.305 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 68.622 MiB) 9.04.580.558 I slot launch_slot_: id 0 | task 21161 | processing task, is_child = 0 9.08.462.454 I slot print_timing: id 0 | task 21161 | n_gen = 146, tg = 48.20 t/s, tg_3s = 48.54 t/s 9.10.670.605 I slot print_timing: id 0 | task 21161 | prompt eval time = 873.87 ms / 349 tokens ( 2.50 ms per token, 399.37 tokens per second) 9.10.670.610 I slot print_timing: id 0 | task 21161 | eval time = 5216.17 ms / 252 tokens ( 20.78 ms per token, 48.12 tokens per second) 9.10.670.610 I slot print_timing: id 0 | task 21161 | total time = 6090.04 ms / 601 tokens 9.10.670.611 I slot print_timing: id 0 | task 21161 | graphs reused = 20592 9.10.670.612 I slot print_timing: id 0 | task 21161 | graph reallocs = 0 / 0 (same size) / (changed size) 9.10.670.644 I slot release: id 0 | task 21161 | stop processing: n_tokens = 628, truncated = 0 9.10.677.437 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 628, t_last = 348719526521 9.10.677.514 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 57.970 MiB) 9.10.677.529 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 88.300 MiB) 9.10.691.334 I slot launch_slot_: id 0 | task 21416 | processing task, is_child = 0 9.14.404.622 I slot print_timing: id 0 | task 21416 | prompt eval time = 1068.48 ms / 469 tokens ( 2.28 ms per token, 438.94 tokens per second) 9.14.404.626 I slot print_timing: id 0 | task 21416 | eval time = 2644.79 ms / 128 tokens ( 20.83 ms per token, 48.02 tokens per second) 9.14.404.627 I slot print_timing: id 0 | task 21416 | total time = 3713.28 ms / 597 tokens 9.14.404.627 I slot print_timing: id 0 | task 21416 | graphs reused = 20717 9.14.404.628 I slot print_timing: id 0 | task 21416 | graph reallocs = 0 / 0 (same size) / (changed size) 9.14.404.678 I slot release: id 0 | task 21416 | stop processing: n_tokens = 623, truncated = 0 9.14.409.742 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.141 (> 0.100 thold), f_keep = 0.059 9.14.409.827 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 82.147 MiB) 9.14.418.340 I slot launch_slot_: id 0 | task 21547 | processing task, is_child = 0 9.18.091.463 I slot print_timing: id 0 | task 21547 | prompt eval time = 743.57 ms / 237 tokens ( 3.14 ms per token, 318.73 tokens per second) 9.18.091.466 I slot print_timing: id 0 | task 21547 | eval time = 2929.54 ms / 143 tokens ( 20.63 ms per token, 48.47 tokens per second) 9.18.091.474 I slot print_timing: id 0 | task 21547 | total time = 3673.11 ms / 380 tokens 9.18.091.476 I slot print_timing: id 0 | task 21547 | graphs reused = 20858 9.18.091.477 I slot print_timing: id 0 | task 21547 | graph reallocs = 0 / 0 (same size) / (changed size) 9.18.091.509 I slot release: id 0 | task 21547 | stop processing: n_tokens = 405, truncated = 0 9.18.097.903 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 405, t_last = 348726947386 9.18.097.965 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 55.823 MiB) 9.18.108.233 I slot launch_slot_: id 0 | task 21693 | processing task, is_child = 0 9.22.114.820 I slot print_timing: id 0 | task 21693 | n_gen = 146, tg = 48.14 t/s, tg_3s = 48.47 t/s 9.23.771.105 I slot print_timing: id 0 | task 21693 | prompt eval time = 994.26 ms / 428 tokens ( 2.32 ms per token, 430.47 tokens per second) 9.23.771.112 I slot print_timing: id 0 | task 21693 | eval time = 4668.60 ms / 227 tokens ( 20.66 ms per token, 48.41 tokens per second) 9.23.771.112 I slot print_timing: id 0 | task 21693 | total time = 5662.86 ms / 655 tokens 9.23.771.113 I slot print_timing: id 0 | task 21693 | graphs reused = 21082 9.23.771.113 I slot print_timing: id 0 | task 21693 | graph reallocs = 0 / 0 (same size) / (changed size) 9.23.771.169 I slot release: id 0 | task 21693 | stop processing: n_tokens = 679, truncated = 0 9.23.778.069 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 679, t_last = 348732627046 9.23.778.151 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 63.166 MiB) 9.23.778.159 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 55.344 MiB) 9.23.786.077 I slot launch_slot_: id 0 | task 21923 | processing task, is_child = 0 9.28.037.206 I slot print_timing: id 0 | task 21923 | n_gen = 146, tg = 48.11 t/s, tg_3s = 48.44 t/s 9.31.046.644 I slot print_timing: id 0 | task 21923 | n_gen = 290, tg = 47.98 t/s, tg_3s = 47.85 t/s 9.33.067.923 I slot print_timing: id 0 | task 21923 | prompt eval time = 1237.07 ms / 530 tokens ( 2.33 ms per token, 428.43 tokens per second) 9.33.067.926 I slot print_timing: id 0 | task 21923 | eval time = 8044.76 ms / 387 tokens ( 20.84 ms per token, 47.98 tokens per second) 9.33.067.926 I slot print_timing: id 0 | task 21923 | total time = 9281.83 ms / 917 tokens 9.33.067.927 I slot print_timing: id 0 | task 21923 | graphs reused = 21466 9.33.067.928 I slot print_timing: id 0 | task 21923 | graph reallocs = 0 / 0 (same size) / (changed size) 9.33.067.964 I slot release: id 0 | task 21923 | stop processing: n_tokens = 940, truncated = 0 9.33.075.709 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 940, t_last = 348741923841 9.33.075.807 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.455 MiB) 9.33.075.820 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 100.402 MiB) 9.33.085.847 I slot launch_slot_: id 0 | task 22314 | processing task, is_child = 0 9.37.493.577 I slot print_timing: id 0 | task 22314 | n_gen = 145, tg = 47.92 t/s, tg_3s = 48.26 t/s 9.38.558.512 I slot print_timing: id 0 | task 22314 | prompt eval time = 1402.88 ms / 579 tokens ( 2.42 ms per token, 412.72 tokens per second) 9.38.558.518 I slot print_timing: id 0 | task 22314 | eval time = 4069.78 ms / 196 tokens ( 20.87 ms per token, 47.91 tokens per second) 9.38.558.518 I slot print_timing: id 0 | task 22314 | total time = 5472.66 ms / 775 tokens 9.38.558.519 I slot print_timing: id 0 | task 22314 | graphs reused = 21659 9.38.558.520 I slot print_timing: id 0 | task 22314 | graph reallocs = 0 / 0 (same size) / (changed size) 9.38.558.559 I slot release: id 0 | task 22314 | stop processing: n_tokens = 811, truncated = 0 9.38.565.009 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 811, t_last = 348747414436 9.38.565.100 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 109.687 MiB) 9.38.584.329 I slot launch_slot_: id 0 | task 22514 | processing task, is_child = 0 9.42.588.472 I slot print_timing: id 0 | task 22514 | n_gen = 144, tg = 47.41 t/s, tg_3s = 47.75 t/s 9.42.650.420 I slot print_timing: id 0 | task 22514 | prompt eval time = 988.19 ms / 427 tokens ( 2.31 ms per token, 432.10 tokens per second) 9.42.650.425 I slot print_timing: id 0 | task 22514 | eval time = 3077.89 ms / 147 tokens ( 21.08 ms per token, 47.44 tokens per second) 9.42.650.426 I slot print_timing: id 0 | task 22514 | total time = 4066.08 ms / 574 tokens 9.42.650.426 I slot print_timing: id 0 | task 22514 | graphs reused = 21803 9.42.650.427 I slot print_timing: id 0 | task 22514 | graph reallocs = 0 / 0 (same size) / (changed size) 9.42.650.475 I slot release: id 0 | task 22514 | stop processing: n_tokens = 597, truncated = 0 9.42.656.936 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 597, t_last = 348751506353 9.42.657.009 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 117.837 MiB) 9.42.677.609 I slot launch_slot_: id 0 | task 22664 | processing task, is_child = 0 9.46.783.986 I slot print_timing: id 0 | task 22664 | n_gen = 146, tg = 48.12 t/s, tg_3s = 48.45 t/s 9.49.800.571 I slot print_timing: id 0 | task 22664 | n_gen = 291, tg = 48.09 t/s, tg_3s = 48.07 t/s 9.51.885.520 I slot print_timing: id 0 | task 22664 | prompt eval time = 1092.98 ms / 508 tokens ( 2.15 ms per token, 464.78 tokens per second) 9.51.885.526 I slot print_timing: id 0 | task 22664 | eval time = 8114.91 ms / 391 tokens ( 20.81 ms per token, 48.06 tokens per second) 9.51.885.527 I slot print_timing: id 0 | task 22664 | total time = 9207.90 ms / 899 tokens 9.51.885.527 I slot print_timing: id 0 | task 22664 | graphs reused = 22191 9.51.885.528 I slot print_timing: id 0 | task 22664 | graph reallocs = 0 / 0 (same size) / (changed size) 9.51.885.561 I slot release: id 0 | task 22664 | stop processing: n_tokens = 921, truncated = 0 9.51.892.137 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 921, t_last = 348760741438 9.51.892.236 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 117.222 MiB) 9.51.911.085 I slot launch_slot_: id 0 | task 23058 | processing task, is_child = 0 9.56.015.478 I slot print_timing: id 0 | task 23058 | n_gen = 146, tg = 48.06 t/s, tg_3s = 48.39 t/s 9.59.021.732 I slot print_timing: id 0 | task 23058 | n_gen = 291, tg = 48.15 t/s, tg_3s = 48.23 t/s 10.01.152.332 I slot print_timing: id 0 | task 23058 | prompt eval time = 1087.17 ms / 454 tokens ( 2.39 ms per token, 417.60 tokens per second) 10.01.152.338 I slot print_timing: id 0 | task 23058 | eval time = 8154.06 ms / 393 tokens ( 20.80 ms per token, 48.07 tokens per second) 10.01.152.338 I slot print_timing: id 0 | task 23058 | total time = 9241.23 ms / 847 tokens 10.01.152.339 I slot print_timing: id 0 | task 23058 | graphs reused = 22580 10.01.152.340 I slot print_timing: id 0 | task 23058 | graph reallocs = 0 / 0 (same size) / (changed size) 10.01.152.385 I slot release: id 0 | task 23058 | stop processing: n_tokens = 868, truncated = 0 10.01.159.393 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 868, t_last = 348770008262 10.01.159.482 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 85.948 MiB) 10.01.159.498 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 114.241 MiB) 10.01.189.758 I slot launch_slot_: id 0 | task 23454 | processing task, is_child = 0 10.05.676.866 I slot print_timing: id 0 | task 23454 | n_gen = 146, tg = 48.14 t/s, tg_3s = 48.47 t/s 10.06.965.982 I slot print_timing: id 0 | task 23454 | prompt eval time = 1475.01 ms / 606 tokens ( 2.43 ms per token, 410.84 tokens per second) 10.06.965.987 I slot print_timing: id 0 | task 23454 | eval time = 4301.19 ms / 208 tokens ( 20.78 ms per token, 48.13 tokens per second) 10.06.965.987 I slot print_timing: id 0 | task 23454 | total time = 5776.21 ms / 814 tokens 10.06.965.988 I slot print_timing: id 0 | task 23454 | graphs reused = 22785 10.06.965.989 I slot print_timing: id 0 | task 23454 | graph reallocs = 0 / 0 (same size) / (changed size) 10.06.966.040 I slot release: id 0 | task 23454 | stop processing: n_tokens = 834, truncated = 0 10.06.973.977 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 834, t_last = 348775821918 10.06.974.064 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 113.175 MiB) 10.07.002.540 I slot launch_slot_: id 0 | task 23666 | processing task, is_child = 0 10.11.585.135 I slot print_timing: id 0 | task 23666 | n_gen = 145, tg = 48.00 t/s, tg_3s = 48.33 t/s 10.13.619.391 I slot print_timing: id 0 | task 23666 | prompt eval time = 1582.33 ms / 672 tokens ( 2.35 ms per token, 424.69 tokens per second) 10.13.619.394 I slot print_timing: id 0 | task 23666 | eval time = 5034.51 ms / 241 tokens ( 20.98 ms per token, 47.67 tokens per second) 10.13.619.395 I slot print_timing: id 0 | task 23666 | total time = 6616.83 ms / 913 tokens 10.13.619.395 I slot print_timing: id 0 | task 23666 | graphs reused = 23023 10.13.619.396 I slot print_timing: id 0 | task 23666 | graph reallocs = 0 / 0 (same size) / (changed size) 10.13.619.441 I slot release: id 0 | task 23666 | stop processing: n_tokens = 933, truncated = 0 10.13.626.187 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 933, t_last = 348782475318 10.13.626.280 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 92.306 MiB) 10.13.666.216 I slot launch_slot_: id 0 | task 23911 | processing task, is_child = 0 10.17.499.158 I slot print_timing: id 0 | task 23911 | prompt eval time = 1163.53 ms / 517 tokens ( 2.25 ms per token, 444.34 tokens per second) 10.17.499.162 I slot print_timing: id 0 | task 23911 | eval time = 2669.40 ms / 129 tokens ( 20.85 ms per token, 47.95 tokens per second) 10.17.499.163 I slot print_timing: id 0 | task 23911 | total time = 3832.92 ms / 646 tokens 10.17.499.163 I slot print_timing: id 0 | task 23911 | graphs reused = 23150 10.17.499.164 I slot print_timing: id 0 | task 23911 | graph reallocs = 0 / 0 (same size) / (changed size) 10.17.499.234 I slot release: id 0 | task 23911 | stop processing: n_tokens = 645, truncated = 0 10.17.506.196 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 645, t_last = 348786355111 10.17.526.085 I slot launch_slot_: id 0 | task 24044 | processing task, is_child = 0 10.21.978.482 I slot print_timing: id 0 | task 24044 | n_gen = 145, tg = 47.83 t/s, tg_3s = 48.16 t/s 10.22.727.036 I slot print_timing: id 0 | task 24044 | prompt eval time = 1441.42 ms / 578 tokens ( 2.49 ms per token, 400.99 tokens per second) 10.22.727.043 I slot print_timing: id 0 | task 24044 | eval time = 3759.51 ms / 181 tokens ( 20.89 ms per token, 47.88 tokens per second) 10.22.727.044 I slot print_timing: id 0 | task 24044 | total time = 5200.93 ms / 759 tokens 10.22.727.044 I slot print_timing: id 0 | task 24044 | graphs reused = 23329 10.22.727.045 I slot print_timing: id 0 | task 24044 | graph reallocs = 0 / 0 (same size) / (changed size) 10.22.727.085 I slot release: id 0 | task 24044 | stop processing: n_tokens = 759, truncated = 0 10.22.733.107 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 759, t_last = 348791582962 10.22.733.205 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 89.736 MiB) 10.22.733.223 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.559 MiB) 10.22.881.418 I slot launch_slot_: id 0 | task 24229 | processing task, is_child = 0 10.26.835.552 I slot print_timing: id 0 | task 24229 | n_gen = 146, tg = 48.21 t/s, tg_3s = 48.54 t/s 10.29.003.235 I slot print_timing: id 0 | task 24229 | prompt eval time = 946.29 ms / 373 tokens ( 2.54 ms per token, 394.17 tokens per second) 10.29.003.242 I slot print_timing: id 0 | task 24229 | eval time = 5175.50 ms / 250 tokens ( 20.79 ms per token, 48.11 tokens per second) 10.29.003.242 I slot print_timing: id 0 | task 24229 | total time = 6121.79 ms / 623 tokens 10.29.003.243 I slot print_timing: id 0 | task 24229 | graphs reused = 23576 10.29.003.243 I slot print_timing: id 0 | task 24229 | graph reallocs = 0 / 0 (same size) / (changed size) 10.29.003.278 I slot release: id 0 | task 24229 | stop processing: n_tokens = 623, truncated = 0 10.29.009.835 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 623, t_last = 348797859155 10.29.009.911 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 96.929 MiB) 10.29.034.915 I slot launch_slot_: id 0 | task 24482 | processing task, is_child = 0 10.33.074.199 I slot print_timing: id 0 | task 24482 | n_gen = 146, tg = 48.18 t/s, tg_3s = 48.52 t/s 10.35.402.120 I slot print_timing: id 0 | task 24482 | prompt eval time = 1029.94 ms / 450 tokens ( 2.29 ms per token, 436.92 tokens per second) 10.35.402.123 I slot print_timing: id 0 | task 24482 | eval time = 5337.24 ms / 258 tokens ( 20.77 ms per token, 48.15 tokens per second) 10.35.402.123 I slot print_timing: id 0 | task 24482 | total time = 6367.19 ms / 708 tokens 10.35.402.124 I slot print_timing: id 0 | task 24482 | graphs reused = 23831 10.35.402.125 I slot print_timing: id 0 | task 24482 | graph reallocs = 0 / 0 (same size) / (changed size) 10.35.402.171 I slot release: id 0 | task 24482 | stop processing: n_tokens = 707, truncated = 0 10.35.410.531 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 707, t_last = 348804258048 10.35.426.990 I slot launch_slot_: id 0 | task 24743 | processing task, is_child = 0 10.40.148.960 I slot print_timing: id 0 | task 24743 | n_gen = 145, tg = 47.91 t/s, tg_3s = 48.24 t/s 10.43.149.019 I slot print_timing: id 0 | task 24743 | n_gen = 288, tg = 47.79 t/s, tg_3s = 47.67 t/s 10.44.296.262 I slot print_timing: id 0 | task 24743 | prompt eval time = 1716.21 ms / 754 tokens ( 2.28 ms per token, 439.34 tokens per second) 10.44.296.268 I slot print_timing: id 0 | task 24743 | eval time = 7153.05 ms / 343 tokens ( 20.92 ms per token, 47.81 tokens per second) 10.44.296.269 I slot print_timing: id 0 | task 24743 | total time = 8869.26 ms / 1097 tokens 10.44.296.269 I slot print_timing: id 0 | task 24743 | graphs reused = 24170 10.44.296.270 I slot print_timing: id 0 | task 24743 | graph reallocs = 0 / 0 (same size) / (changed size) 10.44.296.336 I slot release: id 0 | task 24743 | stop processing: n_tokens = 1096, truncated = 0 10.44.304.590 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1096, t_last = 348813152213 10.44.304.701 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 76.253 MiB) 10.44.331.686 I slot launch_slot_: id 0 | task 25090 | processing task, is_child = 0 10.48.988.154 I slot print_timing: id 0 | task 25090 | n_gen = 145, tg = 47.99 t/s, tg_3s = 48.32 t/s 10.50.770.729 I slot print_timing: id 0 | task 25090 | prompt eval time = 1655.79 ms / 721 tokens ( 2.30 ms per token, 435.44 tokens per second) 10.50.770.733 I slot print_timing: id 0 | task 25090 | eval time = 4783.23 ms / 230 tokens ( 20.89 ms per token, 47.88 tokens per second) 10.50.770.734 I slot print_timing: id 0 | task 25090 | total time = 6439.02 ms / 951 tokens 10.50.770.734 I slot print_timing: id 0 | task 25090 | graphs reused = 24397 10.50.770.735 I slot print_timing: id 0 | task 25090 | graph reallocs = 0 / 0 (same size) / (changed size) 10.50.770.800 I slot release: id 0 | task 25090 | stop processing: n_tokens = 950, truncated = 0 10.50.776.215 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.135 (> 0.100 thold), f_keep = 0.039 10.50.776.311 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 99.910 MiB) 10.50.776.325 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 83.787 MiB) 10.50.798.554 I slot launch_slot_: id 0 | task 25324 | processing task, is_child = 0 10.54.427.475 I slot print_timing: id 0 | task 25324 | prompt eval time = 656.67 ms / 274 tokens ( 2.40 ms per token, 417.26 tokens per second) 10.54.427.482 I slot print_timing: id 0 | task 25324 | eval time = 2972.24 ms / 145 tokens ( 20.64 ms per token, 48.45 tokens per second) 10.54.427.482 I slot print_timing: id 0 | task 25324 | total time = 3628.91 ms / 419 tokens 10.54.427.483 I slot print_timing: id 0 | task 25324 | graphs reused = 24540 10.54.427.483 I slot print_timing: id 0 | task 25324 | graph reallocs = 0 / 0 (same size) / (changed size) 10.54.427.519 I slot release: id 0 | task 25324 | stop processing: n_tokens = 418, truncated = 0 10.54.432.593 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.176 (> 0.100 thold), f_keep = 0.091 10.54.432.661 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 78.427 MiB) 10.54.444.011 I slot launch_slot_: id 0 | task 25472 | processing task, is_child = 0 10.58.040.629 I slot print_timing: id 0 | task 25472 | n_gen = 147, tg = 48.44 t/s, tg_3s = 48.77 t/s 10.58.330.157 I slot print_timing: id 0 | task 25472 | prompt eval time = 582.70 ms / 216 tokens ( 2.70 ms per token, 370.69 tokens per second) 10.58.330.163 I slot print_timing: id 0 | task 25472 | eval time = 3303.44 ms / 161 tokens ( 20.65 ms per token, 48.43 tokens per second) 10.58.330.164 I slot print_timing: id 0 | task 25472 | total time = 3886.14 ms / 377 tokens 10.58.330.165 I slot print_timing: id 0 | task 25472 | graphs reused = 24698 10.58.330.165 I slot print_timing: id 0 | task 25472 | graph reallocs = 0 / 0 (same size) / (changed size) 10.58.330.199 I slot release: id 0 | task 25472 | stop processing: n_tokens = 376, truncated = 0 10.58.335.102 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 10.58.335.161 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 83.104 MiB) 10.58.349.066 I slot launch_slot_: id 0 | task 25636 | processing task, is_child = 0 11.02.041.051 I slot print_timing: id 0 | task 25636 | n_gen = 147, tg = 48.48 t/s, tg_3s = 48.82 t/s 11.05.061.494 I slot print_timing: id 0 | task 25636 | n_gen = 293, tg = 48.41 t/s, tg_3s = 48.34 t/s 11.06.131.039 I slot print_timing: id 0 | task 25636 | prompt eval time = 680.66 ms / 243 tokens ( 2.80 ms per token, 357.01 tokens per second) 11.06.131.042 I slot print_timing: id 0 | task 25636 | eval time = 7101.30 ms / 344 tokens ( 20.70 ms per token, 48.30 tokens per second) 11.06.131.043 I slot print_timing: id 0 | task 25636 | total time = 7781.96 ms / 587 tokens 11.06.131.043 I slot print_timing: id 0 | task 25636 | graphs reused = 25038 11.06.131.044 I slot print_timing: id 0 | task 25636 | graph reallocs = 0 / 0 (same size) / (changed size) 11.06.131.065 I slot release: id 0 | task 25636 | stop processing: n_tokens = 586, truncated = 0 11.06.135.845 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.195 (> 0.100 thold), f_keep = 0.065 11.06.135.920 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 79.822 MiB) 11.06.147.858 I slot launch_slot_: id 0 | task 25983 | processing task, is_child = 0 11.09.690.245 I slot print_timing: id 0 | task 25983 | prompt eval time = 551.75 ms / 195 tokens ( 2.83 ms per token, 353.42 tokens per second) 11.09.690.252 I slot print_timing: id 0 | task 25983 | eval time = 2990.62 ms / 146 tokens ( 20.62 ms per token, 48.48 tokens per second) 11.09.690.252 I slot print_timing: id 0 | task 25983 | total time = 3542.38 ms / 341 tokens 11.09.690.253 I slot print_timing: id 0 | task 25983 | graphs reused = 25181 11.09.690.254 I slot print_timing: id 0 | task 25983 | graph reallocs = 0 / 0 (same size) / (changed size) 11.09.690.287 I slot release: id 0 | task 25983 | stop processing: n_tokens = 340, truncated = 0 11.09.695.326 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.142 (> 0.100 thold), f_keep = 0.109 11.09.707.604 I slot launch_slot_: id 0 | task 26132 | processing task, is_child = 0 11.13.442.929 I slot print_timing: id 0 | task 26132 | n_gen = 147, tg = 48.44 t/s, tg_3s = 48.77 t/s 11.15.958.876 I slot print_timing: id 0 | task 26132 | prompt eval time = 721.43 ms / 261 tokens ( 2.76 ms per token, 361.78 tokens per second) 11.15.958.883 I slot print_timing: id 0 | task 26132 | eval time = 5529.83 ms / 268 tokens ( 20.71 ms per token, 48.28 tokens per second) 11.15.958.883 I slot print_timing: id 0 | task 26132 | total time = 6251.26 ms / 529 tokens 11.15.958.884 I slot print_timing: id 0 | task 26132 | graphs reused = 25446 11.15.958.884 I slot print_timing: id 0 | task 26132 | graph reallocs = 0 / 0 (same size) / (changed size) 11.15.958.906 I slot release: id 0 | task 26132 | stop processing: n_tokens = 528, truncated = 0 11.15.963.651 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.070 11.15.963.726 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 112.025 MiB) 11.15.978.677 I slot launch_slot_: id 0 | task 26403 | processing task, is_child = 0 11.18.106.069 I slot print_timing: id 0 | task 26403 | prompt eval time = 546.50 ms / 179 tokens ( 3.05 ms per token, 327.54 tokens per second) 11.18.106.074 I slot print_timing: id 0 | task 26403 | eval time = 1580.88 ms / 78 tokens ( 20.53 ms per token, 48.71 tokens per second) 11.18.106.075 I slot print_timing: id 0 | task 26403 | total time = 2127.38 ms / 257 tokens 11.18.106.076 I slot print_timing: id 0 | task 26403 | graphs reused = 25522 11.18.106.076 I slot print_timing: id 0 | task 26403 | graph reallocs = 0 / 0 (same size) / (changed size) 11.18.106.098 I slot release: id 0 | task 26403 | stop processing: n_tokens = 256, truncated = 0 11.18.111.002 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.168 (> 0.100 thold), f_keep = 0.145 11.18.111.054 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 92.799 MiB) 11.18.118.844 I slot launch_slot_: id 0 | task 26484 | processing task, is_child = 0 11.21.719.129 I slot print_timing: id 0 | task 26484 | prompt eval time = 592.65 ms / 220 tokens ( 2.69 ms per token, 371.22 tokens per second) 11.21.719.136 I slot print_timing: id 0 | task 26484 | eval time = 3007.63 ms / 147 tokens ( 20.60 ms per token, 48.54 tokens per second) 11.21.719.136 I slot print_timing: id 0 | task 26484 | total time = 3600.28 ms / 367 tokens 11.21.719.137 I slot print_timing: id 0 | task 26484 | graphs reused = 25666 11.21.719.137 I slot print_timing: id 0 | task 26484 | graph reallocs = 0 / 0 (same size) / (changed size) 11.21.719.160 I slot release: id 0 | task 26484 | stop processing: n_tokens = 366, truncated = 0 11.21.723.879 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.101 11.21.737.196 I slot launch_slot_: id 0 | task 26634 | processing task, is_child = 0 11.25.308.341 I slot print_timing: id 0 | task 26634 | prompt eval time = 601.35 ms / 212 tokens ( 2.84 ms per token, 352.54 tokens per second) 11.25.308.347 I slot print_timing: id 0 | task 26634 | eval time = 2969.78 ms / 145 tokens ( 20.62 ms per token, 48.49 tokens per second) 11.25.308.347 I slot print_timing: id 0 | task 26634 | total time = 3571.13 ms / 357 tokens 11.25.308.348 I slot print_timing: id 0 | task 26634 | graphs reused = 25808 11.25.308.349 I slot print_timing: id 0 | task 26634 | graph reallocs = 0 / 0 (same size) / (changed size) 11.25.308.370 I slot release: id 0 | task 26634 | stop processing: n_tokens = 356, truncated = 0 11.25.312.704 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.245 (> 0.100 thold), f_keep = 0.104 11.25.312.760 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 138.651 MiB) 11.25.324.388 I slot launch_slot_: id 0 | task 26782 | processing task, is_child = 0 11.28.849.084 I slot print_timing: id 0 | task 26782 | n_gen = 147, tg = 48.62 t/s, tg_3s = 48.96 t/s 11.31.858.778 I slot print_timing: id 0 | task 26782 | n_gen = 293, tg = 48.57 t/s, tg_3s = 48.51 t/s 11.34.868.636 I slot print_timing: id 0 | task 26782 | n_gen = 438, tg = 48.44 t/s, tg_3s = 48.18 t/s 11.36.111.394 I slot print_timing: id 0 | task 26782 | prompt eval time = 522.00 ms / 151 tokens ( 3.46 ms per token, 289.27 tokens per second) 11.36.111.400 I slot print_timing: id 0 | task 26782 | eval time = 10264.99 ms / 498 tokens ( 20.65 ms per token, 48.42 tokens per second) 11.36.111.401 I slot print_timing: id 0 | task 26782 | total time = 10786.99 ms / 649 tokens 11.36.111.402 I slot print_timing: id 0 | task 26782 | graphs reused = 26302 11.36.111.402 I slot print_timing: id 0 | task 26782 | graph reallocs = 0 / 0 (same size) / (changed size) 11.36.111.425 I slot release: id 0 | task 26782 | stop processing: n_tokens = 648, truncated = 0 11.36.116.389 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.057 11.36.130.195 I slot launch_slot_: id 0 | task 27283 | processing task, is_child = 0 11.39.763.852 I slot print_timing: id 0 | task 27283 | n_gen = 147, tg = 48.49 t/s, tg_3s = 48.82 t/s 11.40.216.931 I slot print_timing: id 0 | task 27283 | prompt eval time = 622.53 ms / 217 tokens ( 2.87 ms per token, 348.57 tokens per second) 11.40.216.935 I slot print_timing: id 0 | task 27283 | eval time = 3464.19 ms / 169 tokens ( 20.62 ms per token, 48.50 tokens per second) 11.40.216.936 I slot print_timing: id 0 | task 27283 | total time = 4086.72 ms / 386 tokens 11.40.216.936 I slot print_timing: id 0 | task 27283 | graphs reused = 26468 11.40.216.937 I slot print_timing: id 0 | task 27283 | graph reallocs = 0 / 0 (same size) / (changed size) 11.40.216.971 I slot release: id 0 | task 27283 | stop processing: n_tokens = 385, truncated = 0 11.40.221.688 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.170 (> 0.100 thold), f_keep = 0.096 11.40.221.757 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 80.355 MiB) 11.40.233.775 I slot launch_slot_: id 0 | task 27455 | processing task, is_child = 0 11.43.853.586 I slot print_timing: id 0 | task 27455 | n_gen = 147, tg = 48.45 t/s, tg_3s = 48.79 t/s 11.44.782.447 I slot print_timing: id 0 | task 27455 | prompt eval time = 606.60 ms / 218 tokens ( 2.78 ms per token, 359.38 tokens per second) 11.44.782.452 I slot print_timing: id 0 | task 27455 | eval time = 3942.07 ms / 192 tokens ( 20.64 ms per token, 48.45 tokens per second) 11.44.782.452 I slot print_timing: id 0 | task 27455 | total time = 4548.66 ms / 410 tokens 11.44.782.453 I slot print_timing: id 0 | task 27455 | graphs reused = 26657 11.44.782.453 I slot print_timing: id 0 | task 27455 | graph reallocs = 0 / 0 (same size) / (changed size) 11.44.782.475 I slot release: id 0 | task 27455 | stop processing: n_tokens = 409, truncated = 0 11.44.787.268 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.165 (> 0.100 thold), f_keep = 0.090 11.44.787.357 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 122.104 MiB) 11.44.798.354 I slot launch_slot_: id 0 | task 27650 | processing task, is_child = 0 11.48.495.998 I slot print_timing: id 0 | task 27650 | n_gen = 147, tg = 48.50 t/s, tg_3s = 48.83 t/s 11.48.867.440 I slot print_timing: id 0 | task 27650 | prompt eval time = 687.04 ms / 224 tokens ( 3.07 ms per token, 326.04 tokens per second) 11.48.867.445 I slot print_timing: id 0 | task 27650 | eval time = 3382.04 ms / 165 tokens ( 20.62 ms per token, 48.49 tokens per second) 11.48.867.446 I slot print_timing: id 0 | task 27650 | total time = 4069.07 ms / 389 tokens 11.48.867.447 I slot print_timing: id 0 | task 27650 | graphs reused = 26819 11.48.867.447 I slot print_timing: id 0 | task 27650 | graph reallocs = 0 / 0 (same size) / (changed size) 11.48.867.484 I slot release: id 0 | task 27650 | stop processing: n_tokens = 388, truncated = 0 11.48.872.117 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.176 (> 0.100 thold), f_keep = 0.095 11.48.879.229 I slot launch_slot_: id 0 | task 27818 | processing task, is_child = 0 11.52.409.108 I slot print_timing: id 0 | task 27818 | prompt eval time = 583.68 ms / 210 tokens ( 2.78 ms per token, 359.78 tokens per second) 11.52.409.114 I slot print_timing: id 0 | task 27818 | eval time = 2946.18 ms / 144 tokens ( 20.60 ms per token, 48.54 tokens per second) 11.52.409.114 I slot print_timing: id 0 | task 27818 | total time = 3529.87 ms / 354 tokens 11.52.409.115 I slot print_timing: id 0 | task 27818 | graphs reused = 26960 11.52.409.116 I slot print_timing: id 0 | task 27818 | graph reallocs = 0 / 0 (same size) / (changed size) 11.52.409.153 I slot release: id 0 | task 27818 | stop processing: n_tokens = 353, truncated = 0 11.52.413.578 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.105 11.52.413.636 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 132.087 MiB) 11.52.423.456 I slot launch_slot_: id 0 | task 27965 | processing task, is_child = 0 11.56.023.522 I slot print_timing: id 0 | task 27965 | n_gen = 147, tg = 48.41 t/s, tg_3s = 48.74 t/s 11.57.511.467 I slot print_timing: id 0 | task 27965 | prompt eval time = 583.91 ms / 208 tokens ( 2.81 ms per token, 356.22 tokens per second) 11.57.511.473 I slot print_timing: id 0 | task 27965 | eval time = 4504.09 ms / 219 tokens ( 20.66 ms per token, 48.40 tokens per second) 11.57.511.474 I slot print_timing: id 0 | task 27965 | total time = 5088.00 ms / 427 tokens 11.57.511.474 I slot print_timing: id 0 | task 27965 | graphs reused = 27176 11.57.511.475 I slot print_timing: id 0 | task 27965 | graph reallocs = 0 / 0 (same size) / (changed size) 11.57.511.495 I slot release: id 0 | task 27965 | stop processing: n_tokens = 426, truncated = 0 11.57.516.382 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.166 (> 0.100 thold), f_keep = 0.087 11.57.528.599 I slot launch_slot_: id 0 | task 28187 | processing task, is_child = 0 12.01.144.495 I slot print_timing: id 0 | task 28187 | n_gen = 147, tg = 48.39 t/s, tg_3s = 48.72 t/s 12.03.465.709 I slot print_timing: id 0 | task 28187 | prompt eval time = 598.63 ms / 223 tokens ( 2.68 ms per token, 372.52 tokens per second) 12.03.465.715 I slot print_timing: id 0 | task 28187 | eval time = 5338.46 ms / 259 tokens ( 20.69 ms per token, 48.33 tokens per second) 12.03.465.716 I slot print_timing: id 0 | task 28187 | total time = 5937.10 ms / 482 tokens 12.03.465.717 I slot print_timing: id 0 | task 28187 | graphs reused = 27432 12.03.465.717 I slot print_timing: id 0 | task 28187 | graph reallocs = 0 / 0 (same size) / (changed size) 12.03.465.741 I slot release: id 0 | task 28187 | stop processing: n_tokens = 481, truncated = 0 12.03.470.712 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.159 (> 0.100 thold), f_keep = 0.077 12.03.470.783 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 84.252 MiB) 12.03.478.650 I slot launch_slot_: id 0 | task 28449 | processing task, is_child = 0 12.07.110.607 I slot print_timing: id 0 | task 28449 | n_gen = 146, tg = 48.32 t/s, tg_3s = 48.65 t/s 12.10.113.060 I slot print_timing: id 0 | task 28449 | n_gen = 290, tg = 48.14 t/s, tg_3s = 47.96 t/s 12.11.464.977 I slot print_timing: id 0 | task 28449 | prompt eval time = 631.05 ms / 232 tokens ( 2.72 ms per token, 367.64 tokens per second) 12.11.464.981 I slot print_timing: id 0 | task 28449 | eval time = 7355.27 ms / 355 tokens ( 20.78 ms per token, 48.13 tokens per second) 12.11.464.982 I slot print_timing: id 0 | task 28449 | total time = 7986.31 ms / 587 tokens 12.11.464.982 I slot print_timing: id 0 | task 28449 | graphs reused = 27783 12.11.464.983 I slot print_timing: id 0 | task 28449 | graph reallocs = 0 / 0 (same size) / (changed size) 12.11.465.025 I slot release: id 0 | task 28449 | stop processing: n_tokens = 586, truncated = 0 12.11.470.418 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.172 (> 0.100 thold), f_keep = 0.063 12.11.470.505 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 115.964 MiB) 12.11.485.591 I slot launch_slot_: id 0 | task 28807 | processing task, is_child = 0 12.14.895.459 I slot print_timing: id 0 | task 28807 | prompt eval time = 613.44 ms / 215 tokens ( 2.85 ms per token, 350.48 tokens per second) 12.14.895.462 I slot print_timing: id 0 | task 28807 | eval time = 2796.42 ms / 136 tokens ( 20.71 ms per token, 48.28 tokens per second) 12.14.895.463 I slot print_timing: id 0 | task 28807 | total time = 3409.86 ms / 351 tokens 12.14.895.464 I slot print_timing: id 0 | task 28807 | graphs reused = 27916 12.14.895.464 I slot print_timing: id 0 | task 28807 | graph reallocs = 0 / 0 (same size) / (changed size) 12.14.895.484 I slot release: id 0 | task 28807 | stop processing: n_tokens = 350, truncated = 0 12.14.900.121 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.164 (> 0.100 thold), f_keep = 0.106 12.14.909.857 I slot launch_slot_: id 0 | task 28946 | processing task, is_child = 0 12.17.797.966 I slot print_timing: id 0 | task 28946 | prompt eval time = 616.30 ms / 226 tokens ( 2.73 ms per token, 366.70 tokens per second) 12.17.797.972 I slot print_timing: id 0 | task 28946 | eval time = 2271.79 ms / 111 tokens ( 20.65 ms per token, 48.42 tokens per second) 12.17.797.973 I slot print_timing: id 0 | task 28946 | total time = 2888.10 ms / 337 tokens 12.17.797.974 I slot print_timing: id 0 | task 28946 | graphs reused = 28024 12.17.797.974 I slot print_timing: id 0 | task 28946 | graph reallocs = 0 / 0 (same size) / (changed size) 12.17.797.999 I slot release: id 0 | task 28946 | stop processing: n_tokens = 336, truncated = 0 12.17.802.690 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.110 12.17.802.744 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 134.043 MiB) 12.17.812.937 I slot launch_slot_: id 0 | task 29060 | processing task, is_child = 0 12.21.388.949 I slot print_timing: id 0 | task 29060 | n_gen = 147, tg = 48.58 t/s, tg_3s = 48.91 t/s 12.21.740.612 I slot print_timing: id 0 | task 29060 | prompt eval time = 570.38 ms / 203 tokens ( 2.81 ms per token, 355.90 tokens per second) 12.21.740.618 I slot print_timing: id 0 | task 29060 | eval time = 3357.28 ms / 164 tokens ( 20.60 ms per token, 48.55 tokens per second) 12.21.740.619 I slot print_timing: id 0 | task 29060 | total time = 3927.66 ms / 367 tokens 12.21.740.620 I slot print_timing: id 0 | task 29060 | graphs reused = 28185 12.21.740.620 I slot print_timing: id 0 | task 29060 | graph reallocs = 0 / 0 (same size) / (changed size) 12.21.740.641 I slot release: id 0 | task 29060 | stop processing: n_tokens = 366, truncated = 0 12.21.745.358 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.101 12.21.755.498 I slot launch_slot_: id 0 | task 29227 | processing task, is_child = 0 12.23.968.119 I slot print_timing: id 0 | task 29227 | prompt eval time = 544.19 ms / 179 tokens ( 3.04 ms per token, 328.93 tokens per second) 12.23.968.125 I slot print_timing: id 0 | task 29227 | eval time = 1668.42 ms / 82 tokens ( 20.60 ms per token, 48.55 tokens per second) 12.23.968.126 I slot print_timing: id 0 | task 29227 | total time = 2212.61 ms / 261 tokens 12.23.968.127 I slot print_timing: id 0 | task 29227 | graphs reused = 28264 12.23.968.127 I slot print_timing: id 0 | task 29227 | graph reallocs = 0 / 0 (same size) / (changed size) 12.23.968.149 I slot release: id 0 | task 29227 | stop processing: n_tokens = 260, truncated = 0 12.23.972.929 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.165 (> 0.100 thold), f_keep = 0.142 12.23.972.973 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 108.566 MiB) 12.23.981.292 I slot launch_slot_: id 0 | task 29312 | processing task, is_child = 0 12.27.613.426 I slot print_timing: id 0 | task 29312 | n_gen = 147, tg = 48.43 t/s, tg_3s = 48.76 t/s 12.28.214.162 I slot print_timing: id 0 | task 29312 | prompt eval time = 617.37 ms / 224 tokens ( 2.76 ms per token, 362.83 tokens per second) 12.28.214.165 I slot print_timing: id 0 | task 29312 | eval time = 3615.49 ms / 176 tokens ( 20.66 ms per token, 48.40 tokens per second) 12.28.214.166 I slot print_timing: id 0 | task 29312 | total time = 4232.86 ms / 400 tokens 12.28.214.166 I slot print_timing: id 0 | task 29312 | graphs reused = 28437 12.28.214.167 I slot print_timing: id 0 | task 29312 | graph reallocs = 0 / 0 (same size) / (changed size) 12.28.214.199 I slot release: id 0 | task 29312 | stop processing: n_tokens = 399, truncated = 0 12.28.219.212 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.163 (> 0.100 thold), f_keep = 0.103 12.28.225.345 I slot launch_slot_: id 0 | task 29491 | processing task, is_child = 0 12.31.118.093 I slot print_timing: id 0 | task 29491 | prompt eval time = 636.74 ms / 252 tokens ( 2.53 ms per token, 395.77 tokens per second) 12.31.118.099 I slot print_timing: id 0 | task 29491 | eval time = 2256.00 ms / 110 tokens ( 20.70 ms per token, 48.32 tokens per second) 12.31.118.100 I slot print_timing: id 0 | task 29491 | total time = 2892.74 ms / 362 tokens 12.31.118.100 I slot print_timing: id 0 | task 29491 | graphs reused = 28544 12.31.118.101 I slot print_timing: id 0 | task 29491 | graph reallocs = 0 / 0 (same size) / (changed size) 12.31.118.137 I slot release: id 0 | task 29491 | stop processing: n_tokens = 361, truncated = 0 12.31.122.708 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.208 (> 0.100 thold), f_keep = 0.102 12.31.122.768 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 84.102 MiB) 12.31.136.757 I slot launch_slot_: id 0 | task 29604 | processing task, is_child = 0 12.34.449.886 I slot print_timing: id 0 | task 29604 | prompt eval time = 559.19 ms / 178 tokens ( 3.14 ms per token, 318.32 tokens per second) 12.34.449.892 I slot print_timing: id 0 | task 29604 | eval time = 2753.92 ms / 135 tokens ( 20.55 ms per token, 48.66 tokens per second) 12.34.449.893 I slot print_timing: id 0 | task 29604 | total time = 3313.12 ms / 313 tokens 12.34.449.893 I slot print_timing: id 0 | task 29604 | graphs reused = 28676 12.34.449.894 I slot print_timing: id 0 | task 29604 | graph reallocs = 0 / 0 (same size) / (changed size) 12.34.449.913 I slot release: id 0 | task 29604 | stop processing: n_tokens = 312, truncated = 0 12.34.454.891 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.119 12.34.454.951 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 92.006 MiB) 12.34.464.256 I slot launch_slot_: id 0 | task 29742 | processing task, is_child = 0 12.38.019.895 I slot print_timing: id 0 | task 29742 | n_gen = 147, tg = 48.54 t/s, tg_3s = 48.87 t/s 12.38.723.766 I slot print_timing: id 0 | task 29742 | prompt eval time = 547.72 ms / 186 tokens ( 2.94 ms per token, 339.59 tokens per second) 12.38.723.772 I slot print_timing: id 0 | task 29742 | eval time = 3711.78 ms / 181 tokens ( 20.62 ms per token, 48.49 tokens per second) 12.38.723.772 I slot print_timing: id 0 | task 29742 | total time = 4259.50 ms / 367 tokens 12.38.723.773 I slot print_timing: id 0 | task 29742 | graphs reused = 28854 12.38.723.773 I slot print_timing: id 0 | task 29742 | graph reallocs = 0 / 0 (same size) / (changed size) 12.38.723.803 I slot release: id 0 | task 29742 | stop processing: n_tokens = 366, truncated = 0 12.38.728.779 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.196 (> 0.100 thold), f_keep = 0.101 12.38.740.377 I slot launch_slot_: id 0 | task 29926 | processing task, is_child = 0 12.42.296.634 I slot print_timing: id 0 | task 29926 | n_gen = 147, tg = 48.63 t/s, tg_3s = 48.96 t/s 12.45.311.764 I slot print_timing: id 0 | task 29926 | n_gen = 293, tg = 48.53 t/s, tg_3s = 48.42 t/s 12.45.696.361 I slot print_timing: id 0 | task 29926 | prompt eval time = 553.96 ms / 189 tokens ( 2.93 ms per token, 341.18 tokens per second) 12.45.696.367 I slot print_timing: id 0 | task 29926 | eval time = 6402.01 ms / 311 tokens ( 20.65 ms per token, 48.42 tokens per second) 12.45.696.367 I slot print_timing: id 0 | task 29926 | total time = 6955.97 ms / 500 tokens 12.45.696.368 I slot print_timing: id 0 | task 29926 | graphs reused = 29162 12.45.696.369 I slot print_timing: id 0 | task 29926 | graph reallocs = 0 / 0 (same size) / (changed size) 12.45.696.392 I slot release: id 0 | task 29926 | stop processing: n_tokens = 499, truncated = 0 12.45.701.221 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.177 (> 0.100 thold), f_keep = 0.074 12.45.701.289 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 116.689 MiB) 12.45.713.878 I slot launch_slot_: id 0 | task 30240 | processing task, is_child = 0 12.47.813.267 I slot print_timing: id 0 | task 30240 | prompt eval time = 592.16 ms / 209 tokens ( 2.83 ms per token, 352.95 tokens per second) 12.47.813.271 I slot print_timing: id 0 | task 30240 | eval time = 1507.22 ms / 74 tokens ( 20.65 ms per token, 48.43 tokens per second) 12.47.813.272 I slot print_timing: id 0 | task 30240 | total time = 2099.38 ms / 283 tokens 12.47.813.273 I slot print_timing: id 0 | task 30240 | graphs reused = 29233 12.47.813.273 I slot print_timing: id 0 | task 30240 | graph reallocs = 0 / 0 (same size) / (changed size) 12.47.813.296 I slot release: id 0 | task 30240 | stop processing: n_tokens = 282, truncated = 0 12.47.818.092 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.177 (> 0.100 thold), f_keep = 0.131 12.47.818.145 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 107.349 MiB) 12.47.826.631 I slot launch_slot_: id 0 | task 30317 | processing task, is_child = 0 12.50.262.382 I slot print_timing: id 0 | task 30317 | prompt eval time = 597.78 ms / 209 tokens ( 2.86 ms per token, 349.62 tokens per second) 12.50.262.388 I slot print_timing: id 0 | task 30317 | eval time = 1837.96 ms / 90 tokens ( 20.65 ms per token, 48.42 tokens per second) 12.50.262.389 I slot print_timing: id 0 | task 30317 | total time = 2435.74 ms / 299 tokens 12.50.262.389 I slot print_timing: id 0 | task 30317 | graphs reused = 29320 12.50.262.390 I slot print_timing: id 0 | task 30317 | graph reallocs = 0 / 0 (same size) / (changed size) 12.50.262.410 I slot release: id 0 | task 30317 | stop processing: n_tokens = 298, truncated = 0 12.50.267.012 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.124 12.50.276.255 I slot launch_slot_: id 0 | task 30410 | processing task, is_child = 0 12.53.441.763 I slot print_timing: id 0 | task 30410 | prompt eval time = 590.41 ms / 208 tokens ( 2.84 ms per token, 352.30 tokens per second) 12.53.441.766 I slot print_timing: id 0 | task 30410 | eval time = 2575.09 ms / 126 tokens ( 20.60 ms per token, 48.54 tokens per second) 12.53.441.767 I slot print_timing: id 0 | task 30410 | total time = 3165.50 ms / 334 tokens 12.53.441.768 I slot print_timing: id 0 | task 30410 | graphs reused = 29443 12.53.441.768 I slot print_timing: id 0 | task 30410 | graph reallocs = 0 / 0 (same size) / (changed size) 12.53.441.792 I slot release: id 0 | task 30410 | stop processing: n_tokens = 333, truncated = 0 12.53.446.482 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.180 (> 0.100 thold), f_keep = 0.111 12.53.446.541 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 134.522 MiB) 12.53.457.491 I slot launch_slot_: id 0 | task 30539 | processing task, is_child = 0 12.57.055.695 I slot print_timing: id 0 | task 30539 | n_gen = 147, tg = 48.42 t/s, tg_3s = 48.75 t/s 13.00.070.304 I slot print_timing: id 0 | task 30539 | n_gen = 292, tg = 48.26 t/s, tg_3s = 48.10 t/s 13.02.451.845 I slot print_timing: id 0 | task 30539 | prompt eval time = 582.93 ms / 206 tokens ( 2.83 ms per token, 353.38 tokens per second) 13.02.451.849 I slot print_timing: id 0 | task 30539 | eval time = 8411.41 ms / 406 tokens ( 20.77 ms per token, 48.15 tokens per second) 13.02.451.849 I slot print_timing: id 0 | task 30539 | total time = 8994.34 ms / 612 tokens 13.02.451.850 I slot print_timing: id 0 | task 30539 | graphs reused = 29845 13.02.451.851 I slot print_timing: id 0 | task 30539 | graph reallocs = 0 / 0 (same size) / (changed size) 13.02.451.872 I slot release: id 0 | task 30539 | stop processing: n_tokens = 611, truncated = 0 13.02.456.782 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.061 13.02.470.253 I slot launch_slot_: id 0 | task 30948 | processing task, is_child = 0 13.05.598.175 I slot print_timing: id 0 | task 30948 | prompt eval time = 574.79 ms / 208 tokens ( 2.76 ms per token, 361.87 tokens per second) 13.05.598.180 I slot print_timing: id 0 | task 30948 | eval time = 2553.12 ms / 125 tokens ( 20.59 ms per token, 48.57 tokens per second) 13.05.598.181 I slot print_timing: id 0 | task 30948 | total time = 3127.91 ms / 333 tokens 13.05.598.181 I slot print_timing: id 0 | task 30948 | graphs reused = 29967 13.05.598.182 I slot print_timing: id 0 | task 30948 | graph reallocs = 0 / 0 (same size) / (changed size) 13.05.598.202 I slot release: id 0 | task 30948 | stop processing: n_tokens = 332, truncated = 0 13.05.602.897 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.167 (> 0.100 thold), f_keep = 0.111 13.05.602.958 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 107.800 MiB) 13.05.612.937 I slot launch_slot_: id 0 | task 31076 | processing task, is_child = 0 13.07.753.099 I slot print_timing: id 0 | task 31076 | prompt eval time = 611.68 ms / 221 tokens ( 2.77 ms per token, 361.30 tokens per second) 13.07.753.106 I slot print_timing: id 0 | task 31076 | eval time = 1528.47 ms / 75 tokens ( 20.66 ms per token, 48.41 tokens per second) 13.07.753.108 I slot print_timing: id 0 | task 31076 | total time = 2140.15 ms / 296 tokens 13.07.753.108 I slot print_timing: id 0 | task 31076 | graphs reused = 30039 13.07.753.109 I slot print_timing: id 0 | task 31076 | graph reallocs = 0 / 0 (same size) / (changed size) 13.07.753.132 I slot release: id 0 | task 31076 | stop processing: n_tokens = 295, truncated = 0 13.07.757.824 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.180 (> 0.100 thold), f_keep = 0.129 13.07.768.143 I slot launch_slot_: id 0 | task 31154 | processing task, is_child = 0 13.10.252.894 I slot print_timing: id 0 | task 31154 | prompt eval time = 589.73 ms / 211 tokens ( 2.79 ms per token, 357.79 tokens per second) 13.10.252.901 I slot print_timing: id 0 | task 31154 | eval time = 1895.02 ms / 93 tokens ( 20.60 ms per token, 48.55 tokens per second) 13.10.252.901 I slot print_timing: id 0 | task 31154 | total time = 2484.74 ms / 304 tokens 13.10.252.902 I slot print_timing: id 0 | task 31154 | graphs reused = 30129 13.10.252.902 I slot print_timing: id 0 | task 31154 | graph reallocs = 0 / 0 (same size) / (changed size) 13.10.252.923 I slot release: id 0 | task 31154 | stop processing: n_tokens = 303, truncated = 0 13.10.257.689 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.122 13.10.257.740 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 114.309 MiB) 13.10.272.674 I slot launch_slot_: id 0 | task 31250 | processing task, is_child = 0 13.13.110.661 I slot print_timing: id 0 | task 31250 | prompt eval time = 612.93 ms / 217 tokens ( 2.82 ms per token, 354.03 tokens per second) 13.13.110.664 I slot print_timing: id 0 | task 31250 | eval time = 2225.04 ms / 109 tokens ( 20.60 ms per token, 48.54 tokens per second) 13.13.110.665 I slot print_timing: id 0 | task 31250 | total time = 2837.97 ms / 326 tokens 13.13.110.666 I slot print_timing: id 0 | task 31250 | graphs reused = 30235 13.13.110.666 I slot print_timing: id 0 | task 31250 | graph reallocs = 0 / 0 (same size) / (changed size) 13.13.110.687 I slot release: id 0 | task 31250 | stop processing: n_tokens = 325, truncated = 0 13.13.115.549 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.167 (> 0.100 thold), f_keep = 0.114 13.13.126.300 I slot launch_slot_: id 0 | task 31362 | processing task, is_child = 0 13.16.726.512 I slot print_timing: id 0 | task 31362 | n_gen = 147, tg = 48.41 t/s, tg_3s = 48.74 t/s 13.16.831.142 I slot print_timing: id 0 | task 31362 | prompt eval time = 584.25 ms / 221 tokens ( 2.64 ms per token, 378.26 tokens per second) 13.16.831.146 I slot print_timing: id 0 | task 31362 | eval time = 3120.58 ms / 152 tokens ( 20.67 ms per token, 48.39 tokens per second) 13.16.831.147 I slot print_timing: id 0 | task 31362 | total time = 3704.83 ms / 373 tokens 13.16.831.147 I slot print_timing: id 0 | task 31362 | graphs reused = 30384 13.16.831.148 I slot print_timing: id 0 | task 31362 | graph reallocs = 0 / 0 (same size) / (changed size) 13.16.831.228 I slot release: id 0 | task 31362 | stop processing: n_tokens = 372, truncated = 0 13.16.837.606 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.159 (> 0.100 thold), f_keep = 0.099 13.16.837.680 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 110.686 MiB) 13.16.849.615 I slot launch_slot_: id 0 | task 31517 | processing task, is_child = 0 13.18.733.901 I slot print_timing: id 0 | task 31517 | prompt eval time = 622.34 ms / 232 tokens ( 2.68 ms per token, 372.79 tokens per second) 13.18.733.907 I slot print_timing: id 0 | task 31517 | eval time = 1261.93 ms / 62 tokens ( 20.69 ms per token, 48.34 tokens per second) 13.18.733.908 I slot print_timing: id 0 | task 31517 | total time = 1884.28 ms / 294 tokens 13.18.733.908 I slot print_timing: id 0 | task 31517 | graphs reused = 30443 13.18.733.909 I slot print_timing: id 0 | task 31517 | graph reallocs = 0 / 0 (same size) / (changed size) 13.18.733.962 I slot release: id 0 | task 31517 | stop processing: n_tokens = 293, truncated = 0 13.18.738.726 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 13.18.756.055 I slot launch_slot_: id 0 | task 31582 | processing task, is_child = 0 13.22.354.851 I slot print_timing: id 0 | task 31582 | n_gen = 147, tg = 48.44 t/s, tg_3s = 48.77 t/s 13.25.361.701 I slot print_timing: id 0 | task 31582 | n_gen = 291, tg = 48.17 t/s, tg_3s = 47.89 t/s 13.26.631.024 I slot print_timing: id 0 | task 31582 | prompt eval time = 584.68 ms / 224 tokens ( 2.61 ms per token, 383.11 tokens per second) 13.26.631.031 I slot print_timing: id 0 | task 31582 | eval time = 7290.27 ms / 352 tokens ( 20.77 ms per token, 48.15 tokens per second) 13.26.631.031 I slot print_timing: id 0 | task 31582 | total time = 7874.96 ms / 576 tokens 13.26.631.032 I slot print_timing: id 0 | task 31582 | graphs reused = 30791 13.26.631.033 I slot print_timing: id 0 | task 31582 | graph reallocs = 0 / 0 (same size) / (changed size) 13.26.631.063 I slot release: id 0 | task 31582 | stop processing: n_tokens = 575, truncated = 0 13.26.636.363 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.159 (> 0.100 thold), f_keep = 0.064 13.26.636.440 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 127.041 MiB) 13.26.650.736 I slot launch_slot_: id 0 | task 31937 | processing task, is_child = 0 13.30.256.702 I slot print_timing: id 0 | task 31937 | n_gen = 146, tg = 48.24 t/s, tg_3s = 48.58 t/s 13.33.275.549 I slot print_timing: id 0 | task 31937 | n_gen = 291, tg = 48.14 t/s, tg_3s = 48.03 t/s 13.33.609.877 I slot print_timing: id 0 | task 31937 | prompt eval time = 600.34 ms / 233 tokens ( 2.58 ms per token, 388.12 tokens per second) 13.33.609.880 I slot print_timing: id 0 | task 31937 | eval time = 6358.80 ms / 307 tokens ( 20.78 ms per token, 48.12 tokens per second) 13.33.609.881 I slot print_timing: id 0 | task 31937 | total time = 6959.13 ms / 540 tokens 13.33.609.882 I slot print_timing: id 0 | task 31937 | graphs reused = 31094 13.33.609.882 I slot print_timing: id 0 | task 31937 | graph reallocs = 0 / 0 (same size) / (changed size) 13.33.609.935 I slot release: id 0 | task 31937 | stop processing: n_tokens = 539, truncated = 0 13.33.614.781 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.167 (> 0.100 thold), f_keep = 0.072 13.33.614.852 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 136.190 MiB) 13.33.628.135 I slot launch_slot_: id 0 | task 32247 | processing task, is_child = 0 13.37.239.303 I slot print_timing: id 0 | task 32247 | n_gen = 147, tg = 48.49 t/s, tg_3s = 48.82 t/s 13.38.167.139 I slot print_timing: id 0 | task 32247 | prompt eval time = 600.27 ms / 233 tokens ( 2.58 ms per token, 388.16 tokens per second) 13.38.167.144 I slot print_timing: id 0 | task 32247 | eval time = 3938.71 ms / 192 tokens ( 20.62 ms per token, 48.49 tokens per second) 13.38.167.145 I slot print_timing: id 0 | task 32247 | total time = 4538.99 ms / 425 tokens 13.38.167.146 I slot print_timing: id 0 | task 32247 | graphs reused = 31283 13.38.167.146 I slot print_timing: id 0 | task 32247 | graph reallocs = 0 / 0 (same size) / (changed size) 13.38.167.179 I slot release: id 0 | task 32247 | stop processing: n_tokens = 424, truncated = 0 13.38.172.404 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.143 (> 0.100 thold), f_keep = 0.087 13.38.180.562 I slot launch_slot_: id 0 | task 32442 | processing task, is_child = 0 13.41.828.038 I slot print_timing: id 0 | task 32442 | n_gen = 147, tg = 48.50 t/s, tg_3s = 48.83 t/s 13.43.192.262 I slot print_timing: id 0 | task 32442 | prompt eval time = 637.01 ms / 259 tokens ( 2.46 ms per token, 406.59 tokens per second) 13.43.192.268 I slot print_timing: id 0 | task 32442 | eval time = 4374.68 ms / 213 tokens ( 20.64 ms per token, 48.46 tokens per second) 13.43.192.269 I slot print_timing: id 0 | task 32442 | total time = 5011.69 ms / 472 tokens 13.43.192.269 I slot print_timing: id 0 | task 32442 | graphs reused = 31494 13.43.192.278 I slot print_timing: id 0 | task 32442 | graph reallocs = 0 / 0 (same size) / (changed size) 13.43.192.320 I slot release: id 0 | task 32442 | stop processing: n_tokens = 471, truncated = 0 13.43.197.231 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.173 (> 0.100 thold), f_keep = 0.079 13.43.197.299 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 69.744 MiB) 13.43.210.822 I slot launch_slot_: id 0 | task 32658 | processing task, is_child = 0 13.46.106.066 I slot print_timing: id 0 | task 32658 | prompt eval time = 602.81 ms / 214 tokens ( 2.82 ms per token, 355.00 tokens per second) 13.46.106.070 I slot print_timing: id 0 | task 32658 | eval time = 2292.42 ms / 112 tokens ( 20.65 ms per token, 48.42 tokens per second) 13.46.106.070 I slot print_timing: id 0 | task 32658 | total time = 2895.23 ms / 326 tokens 13.46.106.071 I slot print_timing: id 0 | task 32658 | graphs reused = 31603 13.46.106.071 I slot print_timing: id 0 | task 32658 | graph reallocs = 0 / 0 (same size) / (changed size) 13.46.106.099 I slot release: id 0 | task 32658 | stop processing: n_tokens = 325, truncated = 0 13.46.209.458 I srv operator(): operator(): cleaning up before exit...