0.00.022.854 W Setting 'enable_thinking' via --chat-template-kwargs is deprecated. Use --reasoning on / --reasoning off instead. 0.00.023.186 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.023.307 I srv init: The UI is disabled 0.00.023.309 I srv init: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.023.393 W srv llama_server: ----------------- 0.00.023.395 W srv llama_server: CORS is set to allow all origins ('*') and no API key is set 0.00.023.396 W srv llama_server: this can be a security risk (cross-origin attacks) 0.00.023.396 W srv llama_server: more info: https://github.com/ggml-org/llama.cpp/pull/25655 0.00.023.396 W srv llama_server: ----------------- 0.00.024.615 I srv load_model: loading model '~/.cache/huggingface/hub/models--unsloth--Qwen3.8-Flash-Next-GGUF/snapshots/8bdc666649440e9bdc97e16f3f75782c98478ff5/UD-IQ1_M/Qwen3.8-Flash-Next-UD-IQ1_M-00001-of-00003.gguf' 0.19.338.531 I cmn init: llama threadpool init, n_threads = 16 0.19.557.583 I srv load_model: initializing, n_slots = 1, n_ctx_slot = 131072, kv_unified = 'false' 0.19.560.440 I srv init: chat template supports preserving reasoning, consider enabling it via --reasoning-preserve 0.19.560.448 I srv llama_server: model loaded 0.19.560.452 I srv llama_server: listening on http://127.0.0.1:8899 0.20.012.300 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = -1 0.20.012.378 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.21.175.443 I slot print_timing: id 0 | task 0 | prompt eval time = 906.17 ms / 13 tokens ( 69.71 ms per token, 14.35 tokens per second) 0.21.175.446 I slot print_timing: id 0 | task 0 | eval time = 256.88 ms / 8 tokens ( 36.70 ms per token, 27.25 tokens per second) 0.21.175.447 I slot print_timing: id 0 | task 0 | total time = 1163.05 ms / 21 tokens 0.21.175.448 I slot print_timing: id 0 | task 0 | graphs reused = 0 0.21.175.462 I slot release: id 0 | task 0 | stop processing: n_tokens = 20, truncated = 0 0.21.184.559 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 515527280458 0.21.818.469 I slot launch_slot_: id 0 | task 10 | processing task, is_child = 0 0.27.144.363 I slot print_timing: id 0 | task 10 | n_gen = 100, tg = 27.34 t/s, tg_3s = 27.62 t/s 0.30.167.193 I slot print_timing: id 0 | task 10 | n_gen = 183, tg = 27.40 t/s, tg_3s = 27.46 t/s 0.33.177.452 I slot print_timing: id 0 | task 10 | n_gen = 266, tg = 27.45 t/s, tg_3s = 27.57 t/s 0.36.208.619 I slot print_timing: id 0 | task 10 | n_gen = 349, tg = 27.43 t/s, tg_3s = 27.38 t/s 0.39.217.120 I slot print_timing: id 0 | task 10 | n_gen = 431, tg = 27.40 t/s, tg_3s = 27.26 t/s 0.42.236.746 I slot print_timing: id 0 | task 10 | n_gen = 513, tg = 27.36 t/s, tg_3s = 27.16 t/s 0.45.271.044 I slot print_timing: id 0 | task 10 | n_gen = 592, tg = 27.18 t/s, tg_3s = 26.04 t/s 0.48.284.495 I slot print_timing: id 0 | task 10 | n_gen = 666, tg = 26.86 t/s, tg_3s = 24.56 t/s 0.51.308.403 I slot print_timing: id 0 | task 10 | n_gen = 741, tg = 26.63 t/s, tg_3s = 24.80 t/s 0.54.322.522 I slot print_timing: id 0 | task 10 | n_gen = 815, tg = 26.43 t/s, tg_3s = 24.55 t/s 0.57.349.998 I slot print_timing: id 0 | task 10 | n_gen = 889, tg = 26.25 t/s, tg_3s = 24.44 t/s 1.00.386.267 I slot print_timing: id 0 | task 10 | n_gen = 964, tg = 26.12 t/s, tg_3s = 24.70 t/s 1.03.388.039 I slot print_timing: id 0 | task 10 | n_gen = 1037, tg = 25.99 t/s, tg_3s = 24.32 t/s 1.06.401.052 I slot print_timing: id 0 | task 10 | n_gen = 1111, tg = 25.89 t/s, tg_3s = 24.56 t/s 1.09.434.095 I slot print_timing: id 0 | task 10 | n_gen = 1185, tg = 25.79 t/s, tg_3s = 24.40 t/s 1.12.453.016 I slot print_timing: id 0 | task 10 | n_gen = 1258, tg = 25.69 t/s, tg_3s = 24.18 t/s 1.15.475.662 I slot print_timing: id 0 | task 10 | n_gen = 1331, tg = 25.60 t/s, tg_3s = 24.15 t/s 1.18.489.888 I slot print_timing: id 0 | task 10 | n_gen = 1404, tg = 25.52 t/s, tg_3s = 24.22 t/s 1.21.491.143 I slot print_timing: id 0 | task 10 | n_gen = 1477, tg = 25.46 t/s, tg_3s = 24.32 t/s 1.24.495.875 I slot print_timing: id 0 | task 10 | n_gen = 1551, tg = 25.42 t/s, tg_3s = 24.63 t/s 1.27.526.046 I slot print_timing: id 0 | task 10 | n_gen = 1625, tg = 25.37 t/s, tg_3s = 24.42 t/s 1.30.532.891 I slot print_timing: id 0 | task 10 | n_gen = 1699, tg = 25.34 t/s, tg_3s = 24.61 t/s 1.33.572.621 I slot print_timing: id 0 | task 10 | n_gen = 1774, tg = 25.31 t/s, tg_3s = 24.67 t/s 1.36.596.630 I slot print_timing: id 0 | task 10 | n_gen = 1848, tg = 25.28 t/s, tg_3s = 24.47 t/s 1.39.612.573 I slot print_timing: id 0 | task 10 | n_gen = 1922, tg = 25.25 t/s, tg_3s = 24.54 t/s 1.42.635.824 I slot print_timing: id 0 | task 10 | n_gen = 1996, tg = 25.22 t/s, tg_3s = 24.48 t/s 1.45.655.199 I slot print_timing: id 0 | task 10 | n_gen = 2070, tg = 25.19 t/s, tg_3s = 24.51 t/s 1.48.686.545 I slot print_timing: id 0 | task 10 | n_gen = 2143, tg = 25.15 t/s, tg_3s = 24.08 t/s 1.51.707.697 I slot print_timing: id 0 | task 10 | n_gen = 2217, tg = 25.13 t/s, tg_3s = 24.49 t/s 1.54.722.565 I slot print_timing: id 0 | task 10 | n_gen = 2289, tg = 25.09 t/s, tg_3s = 23.88 t/s 1.57.746.454 I slot print_timing: id 0 | task 10 | n_gen = 2362, tg = 25.06 t/s, tg_3s = 24.14 t/s 2.00.768.834 I slot print_timing: id 0 | task 10 | n_gen = 2435, tg = 25.03 t/s, tg_3s = 24.15 t/s 2.03.791.533 I slot print_timing: id 0 | task 10 | n_gen = 2508, tg = 25.00 t/s, tg_3s = 24.15 t/s 2.06.800.343 I slot print_timing: id 0 | task 10 | n_gen = 2581, tg = 24.98 t/s, tg_3s = 24.26 t/s 2.09.826.690 I slot print_timing: id 0 | task 10 | n_gen = 2654, tg = 24.96 t/s, tg_3s = 24.12 t/s 2.12.843.799 I slot print_timing: id 0 | task 10 | n_gen = 2727, tg = 24.94 t/s, tg_3s = 24.20 t/s 2.15.856.101 I slot print_timing: id 0 | task 10 | n_gen = 2800, tg = 24.92 t/s, tg_3s = 24.23 t/s 2.18.886.322 I slot print_timing: id 0 | task 10 | n_gen = 2873, tg = 24.90 t/s, tg_3s = 24.09 t/s 2.21.899.374 I slot print_timing: id 0 | task 10 | n_gen = 2945, tg = 24.87 t/s, tg_3s = 23.90 t/s 2.24.935.217 I slot print_timing: id 0 | task 10 | n_gen = 3017, tg = 24.84 t/s, tg_3s = 23.72 t/s 2.27.967.515 I slot print_timing: id 0 | task 10 | n_gen = 3089, tg = 24.81 t/s, tg_3s = 23.74 t/s 2.31.002.358 I slot print_timing: id 0 | task 10 | n_gen = 3161, tg = 24.79 t/s, tg_3s = 23.72 t/s 2.34.007.682 I slot print_timing: id 0 | task 10 | n_gen = 3232, tg = 24.76 t/s, tg_3s = 23.62 t/s 2.37.036.861 I slot print_timing: id 0 | task 10 | n_gen = 3303, tg = 24.73 t/s, tg_3s = 23.44 t/s 2.40.044.346 I slot print_timing: id 0 | task 10 | n_gen = 3374, tg = 24.71 t/s, tg_3s = 23.61 t/s 2.43.058.353 I slot print_timing: id 0 | task 10 | n_gen = 3445, tg = 24.68 t/s, tg_3s = 23.56 t/s 2.46.089.357 I slot print_timing: id 0 | task 10 | n_gen = 3517, tg = 24.66 t/s, tg_3s = 23.75 t/s 2.49.101.766 I slot print_timing: id 0 | task 10 | n_gen = 3588, tg = 24.64 t/s, tg_3s = 23.57 t/s 2.52.129.137 I slot print_timing: id 0 | task 10 | n_gen = 3659, tg = 24.62 t/s, tg_3s = 23.45 t/s 2.55.135.407 I slot print_timing: id 0 | task 10 | n_gen = 3729, tg = 24.59 t/s, tg_3s = 23.28 t/s 2.58.155.039 I slot print_timing: id 0 | task 10 | n_gen = 3799, tg = 24.56 t/s, tg_3s = 23.18 t/s 3.01.166.707 I slot print_timing: id 0 | task 10 | n_gen = 3870, tg = 24.54 t/s, tg_3s = 23.57 t/s 3.04.167.154 I slot print_timing: id 0 | task 10 | n_gen = 3940, tg = 24.52 t/s, tg_3s = 23.33 t/s 3.07.206.926 I slot print_timing: id 0 | task 10 | n_gen = 4011, tg = 24.50 t/s, tg_3s = 23.36 t/s 3.10.227.263 I slot print_timing: id 0 | task 10 | n_gen = 4082, tg = 24.48 t/s, tg_3s = 23.51 t/s 3.13.271.578 I slot print_timing: id 0 | task 10 | n_gen = 4153, tg = 24.46 t/s, tg_3s = 23.32 t/s 3.16.290.799 I slot print_timing: id 0 | task 10 | n_gen = 4223, tg = 24.44 t/s, tg_3s = 23.18 t/s 3.19.320.626 I slot print_timing: id 0 | task 10 | n_gen = 4293, tg = 24.41 t/s, tg_3s = 23.10 t/s 3.22.337.791 I slot print_timing: id 0 | task 10 | n_gen = 4363, tg = 24.39 t/s, tg_3s = 23.20 t/s 3.25.362.989 I slot print_timing: id 0 | task 10 | n_gen = 4433, tg = 24.37 t/s, tg_3s = 23.14 t/s 3.28.377.635 I slot print_timing: id 0 | task 10 | n_gen = 4502, tg = 24.35 t/s, tg_3s = 22.89 t/s 3.31.393.085 I slot print_timing: id 0 | task 10 | n_gen = 4572, tg = 24.33 t/s, tg_3s = 23.21 t/s 3.34.435.934 I slot print_timing: id 0 | task 10 | n_gen = 4641, tg = 24.30 t/s, tg_3s = 22.68 t/s 3.37.460.926 I slot print_timing: id 0 | task 10 | n_gen = 4710, tg = 24.28 t/s, tg_3s = 22.81 t/s 3.40.462.729 I slot print_timing: id 0 | task 10 | n_gen = 4779, tg = 24.26 t/s, tg_3s = 22.99 t/s 3.43.502.741 I slot print_timing: id 0 | task 10 | n_gen = 4849, tg = 24.24 t/s, tg_3s = 23.03 t/s 3.46.523.911 I slot print_timing: id 0 | task 10 | n_gen = 4918, tg = 24.22 t/s, tg_3s = 22.84 t/s 3.49.527.192 I slot print_timing: id 0 | task 10 | n_gen = 4987, tg = 24.20 t/s, tg_3s = 22.97 t/s 3.52.555.318 I slot print_timing: id 0 | task 10 | n_gen = 5056, tg = 24.18 t/s, tg_3s = 22.79 t/s 3.55.594.897 I slot print_timing: id 0 | task 10 | n_gen = 5126, tg = 24.17 t/s, tg_3s = 23.03 t/s 3.58.600.631 I slot print_timing: id 0 | task 10 | n_gen = 5195, tg = 24.15 t/s, tg_3s = 22.96 t/s 4.01.633.841 I slot print_timing: id 0 | task 10 | n_gen = 5265, tg = 24.13 t/s, tg_3s = 23.08 t/s 4.04.649.780 I slot print_timing: id 0 | task 10 | n_gen = 5335, tg = 24.12 t/s, tg_3s = 23.21 t/s 4.07.672.936 I slot print_timing: id 0 | task 10 | n_gen = 5405, tg = 24.11 t/s, tg_3s = 23.15 t/s 4.10.674.421 I slot print_timing: id 0 | task 10 | n_gen = 5474, tg = 24.09 t/s, tg_3s = 22.99 t/s 4.12.233.879 I slot print_timing: id 0 | task 10 | prompt eval time = 1705.21 ms / 212 tokens ( 8.04 ms per token, 124.33 tokens per second) 4.12.233.882 I slot print_timing: id 0 | task 10 | eval time = 228710.18 ms / 5510 tokens ( 41.52 ms per token, 24.09 tokens per second) 4.12.233.883 I slot print_timing: id 0 | task 10 | total time = 230415.39 ms / 5722 tokens 4.12.233.884 I slot print_timing: id 0 | task 10 | graphs reused = 0 4.12.233.912 I slot release: id 0 | task 10 | stop processing: n_tokens = 5721, truncated = 0 4.12.237.981 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 515758338908 4.12.909.667 I slot launch_slot_: id 0 | task 5522 | processing task, is_child = 0 4.18.052.212 I slot print_timing: id 0 | task 5522 | n_gen = 100, tg = 27.72 t/s, tg_3s = 28.00 t/s 4.21.079.865 I slot print_timing: id 0 | task 5522 | n_gen = 179, tg = 26.97 t/s, tg_3s = 26.09 t/s 4.24.105.323 I slot print_timing: id 0 | task 5522 | n_gen = 257, tg = 26.60 t/s, tg_3s = 25.78 t/s 4.27.107.267 I slot print_timing: id 0 | task 5522 | n_gen = 335, tg = 26.45 t/s, tg_3s = 25.98 t/s 4.30.137.244 I slot print_timing: id 0 | task 5522 | n_gen = 413, tg = 26.32 t/s, tg_3s = 25.74 t/s 4.33.172.153 I slot print_timing: id 0 | task 5522 | n_gen = 492, tg = 26.27 t/s, tg_3s = 26.03 t/s 4.36.178.477 I slot print_timing: id 0 | task 5522 | n_gen = 568, tg = 26.13 t/s, tg_3s = 25.28 t/s 4.39.211.980 I slot print_timing: id 0 | task 5522 | n_gen = 643, tg = 25.96 t/s, tg_3s = 24.72 t/s 4.42.237.098 I slot print_timing: id 0 | task 5522 | n_gen = 718, tg = 25.83 t/s, tg_3s = 24.79 t/s 4.45.267.648 I slot print_timing: id 0 | task 5522 | n_gen = 793, tg = 25.73 t/s, tg_3s = 24.75 t/s 4.48.293.923 I slot print_timing: id 0 | task 5522 | n_gen = 867, tg = 25.61 t/s, tg_3s = 24.45 t/s 4.51.327.497 I slot print_timing: id 0 | task 5522 | n_gen = 941, tg = 25.51 t/s, tg_3s = 24.39 t/s 4.54.353.127 I slot print_timing: id 0 | task 5522 | n_gen = 1015, tg = 25.43 t/s, tg_3s = 24.46 t/s 4.57.363.097 I slot print_timing: id 0 | task 5522 | n_gen = 1088, tg = 25.35 t/s, tg_3s = 24.25 t/s 5.00.402.225 I slot print_timing: id 0 | task 5522 | n_gen = 1162, tg = 25.28 t/s, tg_3s = 24.35 t/s 5.03.428.037 I slot print_timing: id 0 | task 5522 | n_gen = 1236, tg = 25.23 t/s, tg_3s = 24.46 t/s 5.06.468.701 I slot print_timing: id 0 | task 5522 | n_gen = 1310, tg = 25.18 t/s, tg_3s = 24.34 t/s 5.09.511.106 I slot print_timing: id 0 | task 5522 | n_gen = 1383, tg = 25.11 t/s, tg_3s = 23.99 t/s 5.12.544.258 I slot print_timing: id 0 | task 5522 | n_gen = 1457, tg = 25.08 t/s, tg_3s = 24.40 t/s 5.15.571.709 I slot print_timing: id 0 | task 5522 | n_gen = 1531, tg = 25.04 t/s, tg_3s = 24.44 t/s 5.18.612.488 I slot print_timing: id 0 | task 5522 | n_gen = 1605, tg = 25.01 t/s, tg_3s = 24.34 t/s 5.21.612.941 I slot print_timing: id 0 | task 5522 | n_gen = 1678, tg = 24.98 t/s, tg_3s = 24.33 t/s 5.24.628.354 I slot print_timing: id 0 | task 5522 | n_gen = 1751, tg = 24.95 t/s, tg_3s = 24.21 t/s 5.27.667.893 I slot print_timing: id 0 | task 5522 | n_gen = 1825, tg = 24.92 t/s, tg_3s = 24.35 t/s 5.30.702.986 I slot print_timing: id 0 | task 5522 | n_gen = 1899, tg = 24.90 t/s, tg_3s = 24.38 t/s 5.33.738.216 I slot print_timing: id 0 | task 5522 | n_gen = 1973, tg = 24.88 t/s, tg_3s = 24.38 t/s 5.36.764.755 I slot print_timing: id 0 | task 5522 | n_gen = 2047, tg = 24.87 t/s, tg_3s = 24.45 t/s 5.39.770.614 I slot print_timing: id 0 | task 5522 | n_gen = 2119, tg = 24.83 t/s, tg_3s = 23.95 t/s 5.42.798.263 I slot print_timing: id 0 | task 5522 | n_gen = 2192, tg = 24.81 t/s, tg_3s = 24.11 t/s 5.45.827.482 I slot print_timing: id 0 | task 5522 | n_gen = 2265, tg = 24.78 t/s, tg_3s = 24.10 t/s 5.48.854.281 I slot print_timing: id 0 | task 5522 | n_gen = 2338, tg = 24.76 t/s, tg_3s = 24.12 t/s 5.51.856.691 I slot print_timing: id 0 | task 5522 | n_gen = 2410, tg = 24.74 t/s, tg_3s = 23.98 t/s 5.54.885.542 I slot print_timing: id 0 | task 5522 | n_gen = 2482, tg = 24.71 t/s, tg_3s = 23.77 t/s 5.57.909.215 I slot print_timing: id 0 | task 5522 | n_gen = 2554, tg = 24.68 t/s, tg_3s = 23.81 t/s 6.00.929.231 I slot print_timing: id 0 | task 5522 | n_gen = 2626, tg = 24.66 t/s, tg_3s = 23.84 t/s 6.03.943.259 I slot print_timing: id 0 | task 5522 | n_gen = 2698, tg = 24.64 t/s, tg_3s = 23.89 t/s 6.06.968.367 I slot print_timing: id 0 | task 5522 | n_gen = 2770, tg = 24.62 t/s, tg_3s = 23.80 t/s 6.09.996.872 I slot print_timing: id 0 | task 5522 | n_gen = 2843, tg = 24.60 t/s, tg_3s = 24.10 t/s 6.13.022.609 I slot print_timing: id 0 | task 5522 | n_gen = 2915, tg = 24.58 t/s, tg_3s = 23.80 t/s 6.16.036.027 I slot print_timing: id 0 | task 5522 | n_gen = 2986, tg = 24.56 t/s, tg_3s = 23.56 t/s 6.19.040.440 I slot print_timing: id 0 | task 5522 | n_gen = 3057, tg = 24.53 t/s, tg_3s = 23.63 t/s 6.22.064.961 I slot print_timing: id 0 | task 5522 | n_gen = 3129, tg = 24.52 t/s, tg_3s = 23.81 t/s 6.25.065.141 I slot print_timing: id 0 | task 5522 | n_gen = 3200, tg = 24.50 t/s, tg_3s = 23.67 t/s 6.28.105.210 I slot print_timing: id 0 | task 5522 | n_gen = 3271, tg = 24.47 t/s, tg_3s = 23.35 t/s 6.31.126.341 I slot print_timing: id 0 | task 5522 | n_gen = 3342, tg = 24.45 t/s, tg_3s = 23.50 t/s 6.34.160.379 I slot print_timing: id 0 | task 5522 | n_gen = 3413, tg = 24.43 t/s, tg_3s = 23.40 t/s 6.37.177.440 I slot print_timing: id 0 | task 5522 | n_gen = 3483, tg = 24.40 t/s, tg_3s = 23.20 t/s 6.40.179.423 I slot print_timing: id 0 | task 5522 | n_gen = 3553, tg = 24.38 t/s, tg_3s = 23.32 t/s 6.43.197.715 I slot print_timing: id 0 | task 5522 | n_gen = 3624, tg = 24.36 t/s, tg_3s = 23.52 t/s 6.46.215.366 I slot print_timing: id 0 | task 5522 | n_gen = 3694, tg = 24.34 t/s, tg_3s = 23.20 t/s 6.49.252.788 I slot print_timing: id 0 | task 5522 | n_gen = 3765, tg = 24.32 t/s, tg_3s = 23.38 t/s 6.52.284.393 I slot print_timing: id 0 | task 5522 | n_gen = 3835, tg = 24.30 t/s, tg_3s = 23.09 t/s 6.55.294.810 I slot print_timing: id 0 | task 5522 | n_gen = 3905, tg = 24.28 t/s, tg_3s = 23.25 t/s 6.58.330.876 I slot print_timing: id 0 | task 5522 | n_gen = 3976, tg = 24.26 t/s, tg_3s = 23.39 t/s 7.01.354.372 I slot print_timing: id 0 | task 5522 | n_gen = 4046, tg = 24.24 t/s, tg_3s = 23.15 t/s 7.04.362.624 I slot print_timing: id 0 | task 5522 | n_gen = 4116, tg = 24.22 t/s, tg_3s = 23.27 t/s 7.07.389.734 I slot print_timing: id 0 | task 5522 | n_gen = 4186, tg = 24.20 t/s, tg_3s = 23.12 t/s 7.10.406.083 I slot print_timing: id 0 | task 5522 | n_gen = 4255, tg = 24.18 t/s, tg_3s = 22.88 t/s 7.13.430.782 I slot print_timing: id 0 | task 5522 | n_gen = 4326, tg = 24.17 t/s, tg_3s = 23.47 t/s 7.16.437.039 I slot print_timing: id 0 | task 5522 | n_gen = 4396, tg = 24.15 t/s, tg_3s = 23.28 t/s 7.19.461.388 I slot print_timing: id 0 | task 5522 | n_gen = 4465, tg = 24.13 t/s, tg_3s = 22.81 t/s 7.22.471.391 I slot print_timing: id 0 | task 5522 | n_gen = 4534, tg = 24.11 t/s, tg_3s = 22.92 t/s 7.25.491.659 I slot print_timing: id 0 | task 5522 | n_gen = 4604, tg = 24.10 t/s, tg_3s = 23.18 t/s 7.28.502.636 I slot print_timing: id 0 | task 5522 | n_gen = 4673, tg = 24.08 t/s, tg_3s = 22.92 t/s 7.31.542.912 I slot print_timing: id 0 | task 5522 | n_gen = 4742, tg = 24.06 t/s, tg_3s = 22.70 t/s 7.34.543.755 I slot print_timing: id 0 | task 5522 | n_gen = 4811, tg = 24.04 t/s, tg_3s = 22.99 t/s 7.37.546.036 I slot print_timing: id 0 | task 5522 | n_gen = 4879, tg = 24.02 t/s, tg_3s = 22.65 t/s 7.40.565.823 I slot print_timing: id 0 | task 5522 | n_gen = 4948, tg = 24.00 t/s, tg_3s = 22.85 t/s 7.43.578.806 I slot print_timing: id 0 | task 5522 | n_gen = 5016, tg = 23.98 t/s, tg_3s = 22.57 t/s 7.46.613.546 I slot print_timing: id 0 | task 5522 | n_gen = 5085, tg = 23.97 t/s, tg_3s = 22.74 t/s 7.49.620.520 I slot print_timing: id 0 | task 5522 | n_gen = 5154, tg = 23.95 t/s, tg_3s = 22.95 t/s 7.52.659.586 I slot print_timing: id 0 | task 5522 | n_gen = 5223, tg = 23.93 t/s, tg_3s = 22.70 t/s 7.55.695.810 I slot print_timing: id 0 | task 5522 | n_gen = 5292, tg = 23.92 t/s, tg_3s = 22.73 t/s 7.58.715.405 I slot print_timing: id 0 | task 5522 | n_gen = 5361, tg = 23.90 t/s, tg_3s = 22.85 t/s 8.01.717.935 I slot print_timing: id 0 | task 5522 | n_gen = 5429, tg = 23.89 t/s, tg_3s = 22.65 t/s 8.04.732.831 I slot print_timing: id 0 | task 5522 | n_gen = 5497, tg = 23.87 t/s, tg_3s = 22.55 t/s 8.07.743.580 I slot print_timing: id 0 | task 5522 | n_gen = 5565, tg = 23.85 t/s, tg_3s = 22.59 t/s 8.10.781.320 I slot print_timing: id 0 | task 5522 | n_gen = 5634, tg = 23.84 t/s, tg_3s = 22.71 t/s 8.13.817.989 I slot print_timing: id 0 | task 5522 | n_gen = 5702, tg = 23.82 t/s, tg_3s = 22.39 t/s 8.16.821.280 I slot print_timing: id 0 | task 5522 | n_gen = 5770, tg = 23.81 t/s, tg_3s = 22.64 t/s 8.19.845.762 I slot print_timing: id 0 | task 5522 | n_gen = 5838, tg = 23.79 t/s, tg_3s = 22.48 t/s 8.22.859.342 I slot print_timing: id 0 | task 5522 | n_gen = 5905, tg = 23.77 t/s, tg_3s = 22.23 t/s 8.25.870.248 I slot print_timing: id 0 | task 5522 | n_gen = 5972, tg = 23.75 t/s, tg_3s = 22.25 t/s 8.28.903.142 I slot print_timing: id 0 | task 5522 | n_gen = 6039, tg = 23.73 t/s, tg_3s = 22.09 t/s 8.31.938.213 I slot print_timing: id 0 | task 5522 | n_gen = 6107, tg = 23.72 t/s, tg_3s = 22.40 t/s 8.34.961.767 I slot print_timing: id 0 | task 5522 | n_gen = 6174, tg = 23.70 t/s, tg_3s = 22.16 t/s 8.37.971.983 I slot print_timing: id 0 | task 5522 | n_gen = 6241, tg = 23.68 t/s, tg_3s = 22.26 t/s 8.40.987.960 I slot print_timing: id 0 | task 5522 | n_gen = 6308, tg = 23.67 t/s, tg_3s = 22.22 t/s 8.44.031.973 I slot print_timing: id 0 | task 5522 | n_gen = 6376, tg = 23.65 t/s, tg_3s = 22.34 t/s 8.47.055.566 I slot print_timing: id 0 | task 5522 | n_gen = 6444, tg = 23.64 t/s, tg_3s = 22.49 t/s 8.50.068.381 I slot print_timing: id 0 | task 5522 | n_gen = 6511, tg = 23.62 t/s, tg_3s = 22.24 t/s 8.53.073.630 I slot print_timing: id 0 | task 5522 | n_gen = 6577, tg = 23.60 t/s, tg_3s = 21.96 t/s 8.56.076.452 I slot print_timing: id 0 | task 5522 | n_gen = 6643, tg = 23.59 t/s, tg_3s = 21.98 t/s 8.59.095.728 I slot print_timing: id 0 | task 5522 | n_gen = 6710, tg = 23.57 t/s, tg_3s = 22.19 t/s 9.02.139.856 I slot print_timing: id 0 | task 5522 | n_gen = 6778, tg = 23.56 t/s, tg_3s = 22.34 t/s 9.05.146.740 I slot print_timing: id 0 | task 5522 | n_gen = 6845, tg = 23.55 t/s, tg_3s = 22.28 t/s 9.08.171.599 I slot print_timing: id 0 | task 5522 | n_gen = 6912, tg = 23.53 t/s, tg_3s = 22.15 t/s 9.11.190.152 I slot print_timing: id 0 | task 5522 | n_gen = 6979, tg = 23.52 t/s, tg_3s = 22.20 t/s 9.14.230.630 I slot print_timing: id 0 | task 5522 | n_gen = 7046, tg = 23.50 t/s, tg_3s = 22.04 t/s 9.17.257.716 I slot print_timing: id 0 | task 5522 | n_gen = 7112, tg = 23.49 t/s, tg_3s = 21.80 t/s 9.20.263.570 I slot print_timing: id 0 | task 5522 | n_gen = 7178, tg = 23.47 t/s, tg_3s = 21.96 t/s 9.23.281.245 I slot print_timing: id 0 | task 5522 | n_gen = 7244, tg = 23.46 t/s, tg_3s = 21.87 t/s 9.26.319.464 I slot print_timing: id 0 | task 5522 | n_gen = 7310, tg = 23.44 t/s, tg_3s = 21.72 t/s 9.29.345.028 I slot print_timing: id 0 | task 5522 | n_gen = 7376, tg = 23.42 t/s, tg_3s = 21.81 t/s 9.32.381.216 I slot print_timing: id 0 | task 5522 | n_gen = 7443, tg = 23.41 t/s, tg_3s = 22.07 t/s 9.32.971.951 I slot print_timing: id 0 | task 5522 | prompt eval time = 1571.38 ms / 236 tokens ( 6.66 ms per token, 150.19 tokens per second) 9.32.971.955 I slot print_timing: id 0 | task 5522 | eval time = 318490.88 ms / 7456 tokens ( 42.72 ms per token, 23.41 tokens per second) 9.32.971.955 I slot print_timing: id 0 | task 5522 | total time = 320062.27 ms / 7692 tokens 9.32.971.956 I slot print_timing: id 0 | task 5522 | graphs reused = 0 9.32.971.984 I slot release: id 0 | task 5522 | stop processing: n_tokens = 7691, truncated = 0 9.32.976.935 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 516079076981 9.33.683.610 I slot launch_slot_: id 0 | task 12980 | processing task, is_child = 0 9.38.219.230 I slot print_timing: id 0 | task 12980 | prompt processing, n_tokens = 1156, progress = 1.00, t = 4.54 s / 254.87 tokens per second 9.43.008.811 I slot print_timing: id 0 | task 12980 | n_gen = 100, tg = 24.21 t/s, tg_3s = 24.45 t/s 9.46.013.907 I slot print_timing: id 0 | task 12980 | n_gen = 172, tg = 24.10 t/s, tg_3s = 23.96 t/s 9.49.014.052 I slot print_timing: id 0 | task 12980 | n_gen = 244, tg = 24.07 t/s, tg_3s = 24.00 t/s 9.52.050.418 I slot print_timing: id 0 | task 12980 | n_gen = 317, tg = 24.07 t/s, tg_3s = 24.04 t/s 9.55.054.878 I slot print_timing: id 0 | task 12980 | n_gen = 389, tg = 24.05 t/s, tg_3s = 23.96 t/s 9.58.078.821 I slot print_timing: id 0 | task 12980 | n_gen = 461, tg = 24.01 t/s, tg_3s = 23.81 t/s 10.01.094.310 I slot print_timing: id 0 | task 12980 | n_gen = 533, tg = 23.99 t/s, tg_3s = 23.88 t/s 10.04.094.764 I slot print_timing: id 0 | task 12980 | n_gen = 605, tg = 23.99 t/s, tg_3s = 24.00 t/s 10.07.129.129 I slot print_timing: id 0 | task 12980 | n_gen = 678, tg = 24.00 t/s, tg_3s = 24.06 t/s 10.10.169.365 I slot print_timing: id 0 | task 12980 | n_gen = 751, tg = 24.00 t/s, tg_3s = 24.01 t/s 10.13.192.288 I slot print_timing: id 0 | task 12980 | n_gen = 824, tg = 24.01 t/s, tg_3s = 24.15 t/s 10.16.212.480 I slot print_timing: id 0 | task 12980 | n_gen = 897, tg = 24.03 t/s, tg_3s = 24.17 t/s 10.19.223.742 I slot print_timing: id 0 | task 12980 | n_gen = 970, tg = 24.04 t/s, tg_3s = 24.24 t/s 10.22.243.061 I slot print_timing: id 0 | task 12980 | n_gen = 1043, tg = 24.05 t/s, tg_3s = 24.18 t/s 10.25.261.112 I slot print_timing: id 0 | task 12980 | n_gen = 1116, tg = 24.06 t/s, tg_3s = 24.19 t/s 10.28.296.594 I slot print_timing: id 0 | task 12980 | n_gen = 1189, tg = 24.06 t/s, tg_3s = 24.05 t/s 10.31.298.642 I slot print_timing: id 0 | task 12980 | n_gen = 1261, tg = 24.06 t/s, tg_3s = 23.98 t/s 10.34.333.202 I slot print_timing: id 0 | task 12980 | n_gen = 1334, tg = 24.06 t/s, tg_3s = 24.06 t/s 10.37.336.238 I slot print_timing: id 0 | task 12980 | n_gen = 1406, tg = 24.05 t/s, tg_3s = 23.98 t/s 10.40.358.755 I slot print_timing: id 0 | task 12980 | n_gen = 1478, tg = 24.04 t/s, tg_3s = 23.82 t/s 10.43.372.412 I slot print_timing: id 0 | task 12980 | n_gen = 1550, tg = 24.03 t/s, tg_3s = 23.89 t/s 10.46.386.319 I slot print_timing: id 0 | task 12980 | n_gen = 1622, tg = 24.03 t/s, tg_3s = 23.89 t/s 10.49.414.297 I slot print_timing: id 0 | task 12980 | n_gen = 1694, tg = 24.02 t/s, tg_3s = 23.78 t/s 10.52.422.625 I slot print_timing: id 0 | task 12980 | n_gen = 1766, tg = 24.01 t/s, tg_3s = 23.93 t/s 10.55.432.094 I slot print_timing: id 0 | task 12980 | n_gen = 1837, tg = 24.00 t/s, tg_3s = 23.59 t/s 10.58.447.497 I slot print_timing: id 0 | task 12980 | n_gen = 1908, tg = 23.98 t/s, tg_3s = 23.55 t/s 11.01.482.860 I slot print_timing: id 0 | task 12980 | n_gen = 1980, tg = 23.97 t/s, tg_3s = 23.72 t/s 11.04.512.475 I slot print_timing: id 0 | task 12980 | n_gen = 2051, tg = 23.95 t/s, tg_3s = 23.44 t/s 11.07.528.316 I slot print_timing: id 0 | task 12980 | n_gen = 2122, tg = 23.94 t/s, tg_3s = 23.54 t/s 11.10.537.212 I slot print_timing: id 0 | task 12980 | n_gen = 2193, tg = 23.93 t/s, tg_3s = 23.60 t/s 11.13.573.428 I slot print_timing: id 0 | task 12980 | n_gen = 2264, tg = 23.91 t/s, tg_3s = 23.38 t/s 11.16.579.093 I slot print_timing: id 0 | task 12980 | n_gen = 2334, tg = 23.89 t/s, tg_3s = 23.29 t/s 11.19.590.245 I slot print_timing: id 0 | task 12980 | n_gen = 2404, tg = 23.87 t/s, tg_3s = 23.25 t/s 11.22.597.321 I slot print_timing: id 0 | task 12980 | n_gen = 2474, tg = 23.85 t/s, tg_3s = 23.28 t/s 11.25.623.518 I slot print_timing: id 0 | task 12980 | n_gen = 2545, tg = 23.84 t/s, tg_3s = 23.46 t/s 11.28.657.672 I slot print_timing: id 0 | task 12980 | n_gen = 2616, tg = 23.83 t/s, tg_3s = 23.40 t/s 11.31.691.951 I slot print_timing: id 0 | task 12980 | n_gen = 2687, tg = 23.82 t/s, tg_3s = 23.40 t/s 11.34.723.734 I slot print_timing: id 0 | task 12980 | n_gen = 2758, tg = 23.81 t/s, tg_3s = 23.42 t/s 11.37.755.548 I slot print_timing: id 0 | task 12980 | n_gen = 2828, tg = 23.79 t/s, tg_3s = 23.09 t/s 11.40.795.514 I slot print_timing: id 0 | task 12980 | n_gen = 2898, tg = 23.77 t/s, tg_3s = 23.03 t/s 11.43.805.739 I slot print_timing: id 0 | task 12980 | n_gen = 2968, tg = 23.76 t/s, tg_3s = 23.25 t/s 11.46.847.794 I slot print_timing: id 0 | task 12980 | n_gen = 3039, tg = 23.75 t/s, tg_3s = 23.34 t/s 11.49.885.731 I slot print_timing: id 0 | task 12980 | n_gen = 3109, tg = 23.73 t/s, tg_3s = 23.04 t/s 11.52.893.617 I slot print_timing: id 0 | task 12980 | n_gen = 3179, tg = 23.72 t/s, tg_3s = 23.27 t/s 11.55.906.587 I slot print_timing: id 0 | task 12980 | n_gen = 3249, tg = 23.71 t/s, tg_3s = 23.23 t/s 11.58.921.868 I slot print_timing: id 0 | task 12980 | n_gen = 3319, tg = 23.70 t/s, tg_3s = 23.22 t/s 12.01.932.182 I slot print_timing: id 0 | task 12980 | n_gen = 3389, tg = 23.69 t/s, tg_3s = 23.25 t/s 12.04.972.536 I slot print_timing: id 0 | task 12980 | n_gen = 3459, tg = 23.68 t/s, tg_3s = 23.02 t/s 12.08.014.248 I slot print_timing: id 0 | task 12980 | n_gen = 3529, tg = 23.66 t/s, tg_3s = 23.01 t/s 12.11.048.412 I slot print_timing: id 0 | task 12980 | n_gen = 3599, tg = 23.65 t/s, tg_3s = 23.07 t/s 12.14.085.762 I slot print_timing: id 0 | task 12980 | n_gen = 3669, tg = 23.64 t/s, tg_3s = 23.05 t/s 12.17.090.706 I slot print_timing: id 0 | task 12980 | n_gen = 3738, tg = 23.63 t/s, tg_3s = 22.96 t/s 12.20.117.755 I slot print_timing: id 0 | task 12980 | n_gen = 3808, tg = 23.62 t/s, tg_3s = 23.12 t/s 12.23.131.297 I slot print_timing: id 0 | task 12980 | n_gen = 3877, tg = 23.60 t/s, tg_3s = 22.90 t/s 12.26.154.144 I slot print_timing: id 0 | task 12980 | n_gen = 3946, tg = 23.59 t/s, tg_3s = 22.83 t/s 12.29.155.419 I slot print_timing: id 0 | task 12980 | n_gen = 4015, tg = 23.58 t/s, tg_3s = 22.99 t/s 12.32.155.769 I slot print_timing: id 0 | task 12980 | n_gen = 4084, tg = 23.57 t/s, tg_3s = 23.00 t/s 12.35.187.331 I slot print_timing: id 0 | task 12980 | n_gen = 4154, tg = 23.56 t/s, tg_3s = 23.09 t/s 12.38.197.991 I slot print_timing: id 0 | task 12980 | n_gen = 4223, tg = 23.55 t/s, tg_3s = 22.92 t/s 12.41.215.988 I slot print_timing: id 0 | task 12980 | n_gen = 4291, tg = 23.53 t/s, tg_3s = 22.53 t/s 12.44.217.925 I slot print_timing: id 0 | task 12980 | n_gen = 4359, tg = 23.52 t/s, tg_3s = 22.65 t/s 12.47.255.681 I slot print_timing: id 0 | task 12980 | n_gen = 4428, tg = 23.51 t/s, tg_3s = 22.71 t/s 12.50.270.633 I slot print_timing: id 0 | task 12980 | n_gen = 4496, tg = 23.49 t/s, tg_3s = 22.55 t/s 12.53.277.171 I slot print_timing: id 0 | task 12980 | n_gen = 4564, tg = 23.48 t/s, tg_3s = 22.62 t/s 12.56.280.922 I slot print_timing: id 0 | task 12980 | n_gen = 4632, tg = 23.46 t/s, tg_3s = 22.64 t/s 12.59.285.192 I slot print_timing: id 0 | task 12980 | n_gen = 4700, tg = 23.45 t/s, tg_3s = 22.63 t/s 13.02.325.561 I slot print_timing: id 0 | task 12980 | n_gen = 4768, tg = 23.44 t/s, tg_3s = 22.37 t/s 13.05.361.396 I slot print_timing: id 0 | task 12980 | n_gen = 4836, tg = 23.42 t/s, tg_3s = 22.40 t/s 13.08.368.850 I slot print_timing: id 0 | task 12980 | n_gen = 4903, tg = 23.40 t/s, tg_3s = 22.28 t/s 13.11.381.885 I slot print_timing: id 0 | task 12980 | n_gen = 4970, tg = 23.39 t/s, tg_3s = 22.24 t/s 13.14.415.239 I slot print_timing: id 0 | task 12980 | n_gen = 5038, tg = 23.37 t/s, tg_3s = 22.42 t/s 13.17.439.322 I slot print_timing: id 0 | task 12980 | n_gen = 5106, tg = 23.36 t/s, tg_3s = 22.49 t/s 13.20.477.310 I slot print_timing: id 0 | task 12980 | n_gen = 5174, tg = 23.35 t/s, tg_3s = 22.38 t/s 13.23.504.346 I slot print_timing: id 0 | task 12980 | n_gen = 5241, tg = 23.33 t/s, tg_3s = 22.13 t/s 13.26.532.608 I slot print_timing: id 0 | task 12980 | n_gen = 5308, tg = 23.32 t/s, tg_3s = 22.12 t/s 13.29.573.814 I slot print_timing: id 0 | task 12980 | n_gen = 5375, tg = 23.30 t/s, tg_3s = 22.03 t/s 13.32.598.093 I slot print_timing: id 0 | task 12980 | n_gen = 5442, tg = 23.28 t/s, tg_3s = 22.15 t/s 13.35.599.879 I slot print_timing: id 0 | task 12980 | n_gen = 5509, tg = 23.27 t/s, tg_3s = 22.32 t/s 13.38.617.965 I slot print_timing: id 0 | task 12980 | n_gen = 5575, tg = 23.25 t/s, tg_3s = 21.87 t/s 13.41.647.408 I slot print_timing: id 0 | task 12980 | n_gen = 5642, tg = 23.24 t/s, tg_3s = 22.12 t/s 13.44.651.985 I slot print_timing: id 0 | task 12980 | n_gen = 5709, tg = 23.23 t/s, tg_3s = 22.30 t/s 13.47.682.491 I slot print_timing: id 0 | task 12980 | n_gen = 5776, tg = 23.21 t/s, tg_3s = 22.11 t/s 13.50.692.192 I slot print_timing: id 0 | task 12980 | n_gen = 5843, tg = 23.20 t/s, tg_3s = 22.26 t/s 13.53.736.746 I slot print_timing: id 0 | task 12980 | n_gen = 5911, tg = 23.19 t/s, tg_3s = 22.33 t/s 13.56.752.124 I slot print_timing: id 0 | task 12980 | n_gen = 5978, tg = 23.18 t/s, tg_3s = 22.22 t/s 13.59.773.160 I slot print_timing: id 0 | task 12980 | n_gen = 6045, tg = 23.17 t/s, tg_3s = 22.18 t/s 14.02.788.188 I slot print_timing: id 0 | task 12980 | n_gen = 6112, tg = 23.16 t/s, tg_3s = 22.22 t/s 14.05.826.755 I slot print_timing: id 0 | task 12980 | n_gen = 6179, tg = 23.15 t/s, tg_3s = 22.05 t/s 14.08.842.219 I slot print_timing: id 0 | task 12980 | n_gen = 6245, tg = 23.13 t/s, tg_3s = 21.89 t/s 14.11.849.122 I slot print_timing: id 0 | task 12980 | n_gen = 6311, tg = 23.12 t/s, tg_3s = 21.95 t/s 14.14.861.170 I slot print_timing: id 0 | task 12980 | n_gen = 6377, tg = 23.11 t/s, tg_3s = 21.91 t/s 14.17.889.898 I slot print_timing: id 0 | task 12980 | n_gen = 6443, tg = 23.09 t/s, tg_3s = 21.79 t/s 14.20.919.162 I slot print_timing: id 0 | task 12980 | n_gen = 6509, tg = 23.08 t/s, tg_3s = 21.79 t/s 14.23.939.667 I slot print_timing: id 0 | task 12980 | n_gen = 6575, tg = 23.07 t/s, tg_3s = 21.85 t/s 14.26.982.240 I slot print_timing: id 0 | task 12980 | n_gen = 6640, tg = 23.05 t/s, tg_3s = 21.36 t/s 14.29.982.756 I slot print_timing: id 0 | task 12980 | n_gen = 6705, tg = 23.03 t/s, tg_3s = 21.66 t/s 14.32.985.979 I slot print_timing: id 0 | task 12980 | n_gen = 6770, tg = 23.02 t/s, tg_3s = 21.64 t/s 14.36.029.625 I slot print_timing: id 0 | task 12980 | n_gen = 6836, tg = 23.00 t/s, tg_3s = 21.68 t/s 14.39.071.238 I slot print_timing: id 0 | task 12980 | n_gen = 6902, tg = 22.99 t/s, tg_3s = 21.70 t/s 14.42.103.479 I slot print_timing: id 0 | task 12980 | n_gen = 6968, tg = 22.98 t/s, tg_3s = 21.77 t/s 14.45.136.705 I slot print_timing: id 0 | task 12980 | n_gen = 7033, tg = 22.96 t/s, tg_3s = 21.43 t/s 14.48.155.433 I slot print_timing: id 0 | task 12980 | n_gen = 7098, tg = 22.95 t/s, tg_3s = 21.53 t/s 14.51.159.110 I slot print_timing: id 0 | task 12980 | n_gen = 7163, tg = 22.94 t/s, tg_3s = 21.64 t/s 14.54.199.607 I slot print_timing: id 0 | task 12980 | n_gen = 7229, tg = 22.93 t/s, tg_3s = 21.71 t/s 14.57.212.061 I slot print_timing: id 0 | task 12980 | n_gen = 7294, tg = 22.91 t/s, tg_3s = 21.58 t/s 15.00.231.583 I slot print_timing: id 0 | task 12980 | n_gen = 7359, tg = 22.90 t/s, tg_3s = 21.53 t/s 15.03.269.984 I slot print_timing: id 0 | task 12980 | n_gen = 7426, tg = 22.89 t/s, tg_3s = 22.05 t/s 15.06.310.596 I slot print_timing: id 0 | task 12980 | n_gen = 7494, tg = 22.89 t/s, tg_3s = 22.36 t/s 15.09.319.296 I slot print_timing: id 0 | task 12980 | n_gen = 7561, tg = 22.88 t/s, tg_3s = 22.27 t/s 15.12.324.149 I slot print_timing: id 0 | task 12980 | n_gen = 7627, tg = 22.87 t/s, tg_3s = 21.96 t/s 15.15.340.075 I slot print_timing: id 0 | task 12980 | n_gen = 7693, tg = 22.86 t/s, tg_3s = 21.88 t/s 15.18.353.061 I slot print_timing: id 0 | task 12980 | n_gen = 7759, tg = 22.86 t/s, tg_3s = 21.91 t/s 15.21.370.593 I slot print_timing: id 0 | task 12980 | n_gen = 7824, tg = 22.84 t/s, tg_3s = 21.54 t/s 15.24.392.690 I slot print_timing: id 0 | task 12980 | n_gen = 7890, tg = 22.84 t/s, tg_3s = 21.84 t/s 15.27.422.597 I slot print_timing: id 0 | task 12980 | n_gen = 7956, tg = 22.83 t/s, tg_3s = 21.78 t/s 15.30.453.907 I slot print_timing: id 0 | task 12980 | n_gen = 8022, tg = 22.82 t/s, tg_3s = 21.77 t/s 15.33.471.515 I slot print_timing: id 0 | task 12980 | n_gen = 8088, tg = 22.81 t/s, tg_3s = 21.87 t/s 15.36.514.634 I slot print_timing: id 0 | task 12980 | n_gen = 8154, tg = 22.80 t/s, tg_3s = 21.69 t/s 15.39.535.912 I slot print_timing: id 0 | task 12980 | n_gen = 8219, tg = 22.79 t/s, tg_3s = 21.51 t/s 15.42.557.131 I slot print_timing: id 0 | task 12980 | n_gen = 8284, tg = 22.78 t/s, tg_3s = 21.51 t/s 15.45.588.020 I slot print_timing: id 0 | task 12980 | n_gen = 8348, tg = 22.76 t/s, tg_3s = 21.12 t/s 15.48.625.579 I slot print_timing: id 0 | task 12980 | n_gen = 8412, tg = 22.75 t/s, tg_3s = 21.07 t/s 15.51.652.552 I slot print_timing: id 0 | task 12980 | n_gen = 8476, tg = 22.74 t/s, tg_3s = 21.14 t/s 15.54.672.904 I slot print_timing: id 0 | task 12980 | n_gen = 8541, tg = 22.73 t/s, tg_3s = 21.52 t/s 15.57.701.551 I slot print_timing: id 0 | task 12980 | n_gen = 8606, tg = 22.72 t/s, tg_3s = 21.46 t/s 16.00.731.438 I slot print_timing: id 0 | task 12980 | n_gen = 8671, tg = 22.71 t/s, tg_3s = 21.45 t/s 16.03.733.332 I slot print_timing: id 0 | task 12980 | n_gen = 8736, tg = 22.70 t/s, tg_3s = 21.65 t/s 16.06.777.359 I slot print_timing: id 0 | task 12980 | n_gen = 8800, tg = 22.69 t/s, tg_3s = 21.02 t/s 16.09.813.338 I slot print_timing: id 0 | task 12980 | n_gen = 8863, tg = 22.67 t/s, tg_3s = 20.75 t/s 16.12.818.012 I slot print_timing: id 0 | task 12980 | n_gen = 8926, tg = 22.66 t/s, tg_3s = 20.97 t/s 16.15.837.997 I slot print_timing: id 0 | task 12980 | n_gen = 8990, tg = 22.65 t/s, tg_3s = 21.19 t/s 16.18.867.176 I slot print_timing: id 0 | task 12980 | n_gen = 9054, tg = 22.64 t/s, tg_3s = 21.13 t/s 16.21.895.467 I slot print_timing: id 0 | task 12980 | n_gen = 9118, tg = 22.62 t/s, tg_3s = 21.13 t/s 16.24.929.369 I slot print_timing: id 0 | task 12980 | n_gen = 9182, tg = 22.61 t/s, tg_3s = 21.09 t/s 16.27.965.232 I slot print_timing: id 0 | task 12980 | n_gen = 9246, tg = 22.60 t/s, tg_3s = 21.08 t/s 16.30.995.372 I slot print_timing: id 0 | task 12980 | n_gen = 9310, tg = 22.59 t/s, tg_3s = 21.12 t/s 16.34.009.838 I slot print_timing: id 0 | task 12980 | n_gen = 9373, tg = 22.58 t/s, tg_3s = 20.90 t/s 16.37.031.517 I slot print_timing: id 0 | task 12980 | n_gen = 9436, tg = 22.57 t/s, tg_3s = 20.85 t/s 16.40.058.041 I slot print_timing: id 0 | task 12980 | n_gen = 9499, tg = 22.55 t/s, tg_3s = 20.82 t/s 16.43.078.136 I slot print_timing: id 0 | task 12980 | n_gen = 9562, tg = 22.54 t/s, tg_3s = 20.86 t/s 16.46.086.157 I slot print_timing: id 0 | task 12980 | n_gen = 9625, tg = 22.53 t/s, tg_3s = 20.94 t/s 16.49.124.942 I slot print_timing: id 0 | task 12980 | n_gen = 9689, tg = 22.52 t/s, tg_3s = 21.06 t/s 16.52.136.046 I slot print_timing: id 0 | task 12980 | n_gen = 9752, tg = 22.51 t/s, tg_3s = 20.92 t/s 16.55.166.847 I slot print_timing: id 0 | task 12980 | n_gen = 9815, tg = 22.50 t/s, tg_3s = 20.79 t/s 16.58.184.348 I slot print_timing: id 0 | task 12980 | n_gen = 9878, tg = 22.49 t/s, tg_3s = 20.88 t/s 17.01.229.760 I slot print_timing: id 0 | task 12980 | n_gen = 9941, tg = 22.47 t/s, tg_3s = 20.69 t/s 17.04.259.210 I slot print_timing: id 0 | task 12980 | n_gen = 10004, tg = 22.46 t/s, tg_3s = 20.80 t/s 17.07.297.041 I slot print_timing: id 0 | task 12980 | n_gen = 10067, tg = 22.45 t/s, tg_3s = 20.74 t/s 17.10.322.957 I slot print_timing: id 0 | task 12980 | n_gen = 10130, tg = 22.44 t/s, tg_3s = 20.82 t/s 17.13.344.160 I slot print_timing: id 0 | task 12980 | n_gen = 10192, tg = 22.43 t/s, tg_3s = 20.52 t/s 17.16.379.590 I slot print_timing: id 0 | task 12980 | n_gen = 10255, tg = 22.42 t/s, tg_3s = 20.75 t/s 17.16.999.786 I slot print_timing: id 0 | task 12980 | prompt eval time = 5235.80 ms / 1160 tokens ( 4.51 ms per token, 221.55 tokens per second) 17.16.999.789 I slot print_timing: id 0 | task 12980 | eval time = 458080.36 ms / 10268 tokens ( 44.62 ms per token, 22.41 tokens per second) 17.16.999.789 I slot print_timing: id 0 | task 12980 | total time = 463316.16 ms / 11428 tokens 17.16.999.790 I slot print_timing: id 0 | task 12980 | graphs reused = 0 17.16.999.839 I slot release: id 0 | task 12980 | stop processing: n_tokens = 11427, truncated = 0 17.17.003.976 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 516543104835 17.17.699.119 I slot launch_slot_: id 0 | task 23251 | processing task, is_child = 0 17.22.826.644 I slot print_timing: id 0 | task 23251 | n_gen = 100, tg = 27.37 t/s, tg_3s = 27.64 t/s 17.25.827.246 I slot print_timing: id 0 | task 23251 | n_gen = 179, tg = 26.90 t/s, tg_3s = 26.33 t/s 17.28.834.117 I slot print_timing: id 0 | task 23251 | n_gen = 256, tg = 26.49 t/s, tg_3s = 25.61 t/s 17.31.845.663 I slot print_timing: id 0 | task 23251 | n_gen = 333, tg = 26.27 t/s, tg_3s = 25.57 t/s 17.34.853.861 I slot print_timing: id 0 | task 23251 | n_gen = 410, tg = 26.14 t/s, tg_3s = 25.60 t/s 17.37.872.472 I slot print_timing: id 0 | task 23251 | n_gen = 487, tg = 26.04 t/s, tg_3s = 25.51 t/s 17.40.885.838 I slot print_timing: id 0 | task 23251 | n_gen = 563, tg = 25.93 t/s, tg_3s = 25.22 t/s 17.43.926.023 I slot print_timing: id 0 | task 23251 | n_gen = 638, tg = 25.77 t/s, tg_3s = 24.67 t/s 17.46.932.692 I slot print_timing: id 0 | task 23251 | n_gen = 712, tg = 25.65 t/s, tg_3s = 24.61 t/s 17.49.951.341 I slot print_timing: id 0 | task 23251 | n_gen = 787, tg = 25.57 t/s, tg_3s = 24.85 t/s 17.52.958.758 I slot print_timing: id 0 | task 23251 | n_gen = 861, tg = 25.48 t/s, tg_3s = 24.61 t/s 17.55.994.935 I slot print_timing: id 0 | task 23251 | n_gen = 935, tg = 25.39 t/s, tg_3s = 24.37 t/s 17.59.023.019 I slot print_timing: id 0 | task 23251 | n_gen = 1009, tg = 25.32 t/s, tg_3s = 24.44 t/s 18.02.059.938 I slot print_timing: id 0 | task 23251 | n_gen = 1083, tg = 25.25 t/s, tg_3s = 24.37 t/s 18.05.072.540 I slot print_timing: id 0 | task 23251 | n_gen = 1156, tg = 25.18 t/s, tg_3s = 24.23 t/s 18.08.091.661 I slot print_timing: id 0 | task 23251 | n_gen = 1228, tg = 25.10 t/s, tg_3s = 23.85 t/s 18.11.103.521 I slot print_timing: id 0 | task 23251 | n_gen = 1300, tg = 25.03 t/s, tg_3s = 23.91 t/s 18.14.120.690 I slot print_timing: id 0 | task 23251 | n_gen = 1372, tg = 24.97 t/s, tg_3s = 23.86 t/s 18.17.141.843 I slot print_timing: id 0 | task 23251 | n_gen = 1445, tg = 24.93 t/s, tg_3s = 24.16 t/s 18.20.156.501 I slot print_timing: id 0 | task 23251 | n_gen = 1519, tg = 24.91 t/s, tg_3s = 24.55 t/s 18.23.192.227 I slot print_timing: id 0 | task 23251 | n_gen = 1593, tg = 24.88 t/s, tg_3s = 24.38 t/s 18.26.223.704 I slot print_timing: id 0 | task 23251 | n_gen = 1667, tg = 24.86 t/s, tg_3s = 24.41 t/s 18.29.256.755 I slot print_timing: id 0 | task 23251 | n_gen = 1741, tg = 24.84 t/s, tg_3s = 24.40 t/s 18.32.269.904 I slot print_timing: id 0 | task 23251 | n_gen = 1815, tg = 24.83 t/s, tg_3s = 24.56 t/s 18.35.313.360 I slot print_timing: id 0 | task 23251 | n_gen = 1889, tg = 24.81 t/s, tg_3s = 24.31 t/s 18.38.319.315 I slot print_timing: id 0 | task 23251 | n_gen = 1962, tg = 24.79 t/s, tg_3s = 24.29 t/s 18.41.340.257 I slot print_timing: id 0 | task 23251 | n_gen = 2035, tg = 24.77 t/s, tg_3s = 24.16 t/s 18.44.346.795 I slot print_timing: id 0 | task 23251 | n_gen = 2107, tg = 24.74 t/s, tg_3s = 23.95 t/s 18.47.366.285 I slot print_timing: id 0 | task 23251 | n_gen = 2179, tg = 24.71 t/s, tg_3s = 23.85 t/s 18.50.380.182 I slot print_timing: id 0 | task 23251 | n_gen = 2252, tg = 24.69 t/s, tg_3s = 24.22 t/s 18.53.387.502 I slot print_timing: id 0 | task 23251 | n_gen = 2324, tg = 24.67 t/s, tg_3s = 23.94 t/s 18.56.394.960 I slot print_timing: id 0 | task 23251 | n_gen = 2396, tg = 24.64 t/s, tg_3s = 23.94 t/s 18.59.425.019 I slot print_timing: id 0 | task 23251 | n_gen = 2469, tg = 24.63 t/s, tg_3s = 24.09 t/s 19.02.438.740 I slot print_timing: id 0 | task 23251 | n_gen = 2542, tg = 24.62 t/s, tg_3s = 24.22 t/s 19.05.454.191 I slot print_timing: id 0 | task 23251 | n_gen = 2615, tg = 24.60 t/s, tg_3s = 24.21 t/s 19.08.463.008 I slot print_timing: id 0 | task 23251 | n_gen = 2687, tg = 24.58 t/s, tg_3s = 23.93 t/s 19.11.494.268 I slot print_timing: id 0 | task 23251 | n_gen = 2759, tg = 24.56 t/s, tg_3s = 23.75 t/s 19.14.531.024 I slot print_timing: id 0 | task 23251 | n_gen = 2831, tg = 24.54 t/s, tg_3s = 23.71 t/s 19.17.536.438 I slot print_timing: id 0 | task 23251 | n_gen = 2902, tg = 24.52 t/s, tg_3s = 23.62 t/s 19.20.545.417 I slot print_timing: id 0 | task 23251 | n_gen = 2973, tg = 24.49 t/s, tg_3s = 23.60 t/s 19.23.584.075 I slot print_timing: id 0 | task 23251 | n_gen = 3045, tg = 24.47 t/s, tg_3s = 23.69 t/s 19.26.591.429 I slot print_timing: id 0 | task 23251 | n_gen = 3116, tg = 24.45 t/s, tg_3s = 23.61 t/s 19.29.597.844 I slot print_timing: id 0 | task 23251 | n_gen = 3186, tg = 24.43 t/s, tg_3s = 23.28 t/s 19.32.599.020 I slot print_timing: id 0 | task 23251 | n_gen = 3256, tg = 24.40 t/s, tg_3s = 23.32 t/s 19.35.633.915 I slot print_timing: id 0 | task 23251 | n_gen = 3327, tg = 24.38 t/s, tg_3s = 23.39 t/s 19.38.661.946 I slot print_timing: id 0 | task 23251 | n_gen = 3398, tg = 24.36 t/s, tg_3s = 23.45 t/s 19.41.674.071 I slot print_timing: id 0 | task 23251 | n_gen = 3468, tg = 24.34 t/s, tg_3s = 23.24 t/s 19.44.703.144 I slot print_timing: id 0 | task 23251 | n_gen = 3539, tg = 24.32 t/s, tg_3s = 23.44 t/s 19.47.724.216 I slot print_timing: id 0 | task 23251 | n_gen = 3610, tg = 24.30 t/s, tg_3s = 23.50 t/s 19.50.745.983 I slot print_timing: id 0 | task 23251 | n_gen = 3680, tg = 24.28 t/s, tg_3s = 23.17 t/s 19.53.786.739 I slot print_timing: id 0 | task 23251 | n_gen = 3750, tg = 24.25 t/s, tg_3s = 23.02 t/s 19.56.791.643 I slot print_timing: id 0 | task 23251 | n_gen = 3820, tg = 24.23 t/s, tg_3s = 23.30 t/s 19.59.799.430 I slot print_timing: id 0 | task 23251 | n_gen = 3889, tg = 24.21 t/s, tg_3s = 22.94 t/s 20.02.837.604 I slot print_timing: id 0 | task 23251 | n_gen = 3959, tg = 24.19 t/s, tg_3s = 23.04 t/s 20.05.861.754 I slot print_timing: id 0 | task 23251 | n_gen = 4029, tg = 24.17 t/s, tg_3s = 23.15 t/s 20.08.897.596 I slot print_timing: id 0 | task 23251 | n_gen = 4100, tg = 24.16 t/s, tg_3s = 23.39 t/s 20.11.910.898 I slot print_timing: id 0 | task 23251 | n_gen = 4170, tg = 24.14 t/s, tg_3s = 23.23 t/s 20.14.949.220 I slot print_timing: id 0 | task 23251 | n_gen = 4240, tg = 24.12 t/s, tg_3s = 23.04 t/s 20.17.950.014 I slot print_timing: id 0 | task 23251 | n_gen = 4309, tg = 24.10 t/s, tg_3s = 22.99 t/s 20.20.985.160 I slot print_timing: id 0 | task 23251 | n_gen = 4379, tg = 24.08 t/s, tg_3s = 23.06 t/s 20.24.015.199 I slot print_timing: id 0 | task 23251 | n_gen = 4448, tg = 24.06 t/s, tg_3s = 22.77 t/s 20.27.023.144 I slot print_timing: id 0 | task 23251 | n_gen = 4517, tg = 24.05 t/s, tg_3s = 22.94 t/s 20.30.062.287 I slot print_timing: id 0 | task 23251 | n_gen = 4587, tg = 24.03 t/s, tg_3s = 23.03 t/s 20.33.069.610 I slot print_timing: id 0 | task 23251 | n_gen = 4656, tg = 24.01 t/s, tg_3s = 22.94 t/s 20.36.091.736 I slot print_timing: id 0 | task 23251 | n_gen = 4725, tg = 23.99 t/s, tg_3s = 22.83 t/s 20.39.130.586 I slot print_timing: id 0 | task 23251 | n_gen = 4794, tg = 23.97 t/s, tg_3s = 22.71 t/s 20.42.159.223 I slot print_timing: id 0 | task 23251 | n_gen = 4863, tg = 23.96 t/s, tg_3s = 22.78 t/s 20.45.177.779 I slot print_timing: id 0 | task 23251 | n_gen = 4932, tg = 23.94 t/s, tg_3s = 22.86 t/s 20.48.177.859 I slot print_timing: id 0 | task 23251 | n_gen = 5001, tg = 23.93 t/s, tg_3s = 23.00 t/s 20.51.193.074 I slot print_timing: id 0 | task 23251 | n_gen = 5070, tg = 23.91 t/s, tg_3s = 22.88 t/s 20.54.195.134 I slot print_timing: id 0 | task 23251 | n_gen = 5139, tg = 23.90 t/s, tg_3s = 22.98 t/s 20.57.234.536 I slot print_timing: id 0 | task 23251 | n_gen = 5208, tg = 23.88 t/s, tg_3s = 22.70 t/s 21.00.261.366 I slot print_timing: id 0 | task 23251 | n_gen = 5277, tg = 23.87 t/s, tg_3s = 22.80 t/s 21.03.280.584 I slot print_timing: id 0 | task 23251 | n_gen = 5346, tg = 23.85 t/s, tg_3s = 22.85 t/s 21.06.285.740 I slot print_timing: id 0 | task 23251 | n_gen = 5415, tg = 23.84 t/s, tg_3s = 22.96 t/s 21.09.310.392 I slot print_timing: id 0 | task 23251 | n_gen = 5484, tg = 23.83 t/s, tg_3s = 22.81 t/s 21.12.312.262 I slot print_timing: id 0 | task 23251 | n_gen = 5552, tg = 23.81 t/s, tg_3s = 22.65 t/s 21.15.329.155 I slot print_timing: id 0 | task 23251 | n_gen = 5620, tg = 23.80 t/s, tg_3s = 22.54 t/s 21.18.341.679 I slot print_timing: id 0 | task 23251 | n_gen = 5688, tg = 23.78 t/s, tg_3s = 22.57 t/s 21.21.356.744 I slot print_timing: id 0 | task 23251 | n_gen = 5755, tg = 23.76 t/s, tg_3s = 22.22 t/s 21.24.357.680 I slot print_timing: id 0 | task 23251 | n_gen = 5822, tg = 23.74 t/s, tg_3s = 22.33 t/s 21.27.387.332 I slot print_timing: id 0 | task 23251 | n_gen = 5891, tg = 23.73 t/s, tg_3s = 22.77 t/s 21.30.422.716 I slot print_timing: id 0 | task 23251 | n_gen = 5960, tg = 23.72 t/s, tg_3s = 22.73 t/s 21.33.424.996 I slot print_timing: id 0 | task 23251 | n_gen = 6028, tg = 23.71 t/s, tg_3s = 22.65 t/s 21.36.465.732 I slot print_timing: id 0 | task 23251 | n_gen = 6096, tg = 23.69 t/s, tg_3s = 22.36 t/s 21.39.474.903 I slot print_timing: id 0 | task 23251 | n_gen = 6164, tg = 23.68 t/s, tg_3s = 22.60 t/s 21.42.482.922 I slot print_timing: id 0 | task 23251 | n_gen = 6232, tg = 23.67 t/s, tg_3s = 22.61 t/s 21.45.516.088 I slot print_timing: id 0 | task 23251 | n_gen = 6299, tg = 23.65 t/s, tg_3s = 22.09 t/s 21.48.527.301 I slot print_timing: id 0 | task 23251 | n_gen = 6367, tg = 23.64 t/s, tg_3s = 22.58 t/s 21.51.556.607 I slot print_timing: id 0 | task 23251 | n_gen = 6435, tg = 23.62 t/s, tg_3s = 22.45 t/s 21.54.603.249 I slot print_timing: id 0 | task 23251 | n_gen = 6503, tg = 23.61 t/s, tg_3s = 22.32 t/s 21.57.625.999 I slot print_timing: id 0 | task 23251 | n_gen = 6570, tg = 23.59 t/s, tg_3s = 22.17 t/s 22.00.635.533 I slot print_timing: id 0 | task 23251 | n_gen = 6636, tg = 23.58 t/s, tg_3s = 21.93 t/s 22.03.649.827 I slot print_timing: id 0 | task 23251 | n_gen = 6703, tg = 23.56 t/s, tg_3s = 22.23 t/s 22.06.660.930 I slot print_timing: id 0 | task 23251 | n_gen = 6769, tg = 23.54 t/s, tg_3s = 21.92 t/s 22.09.671.504 I slot print_timing: id 0 | task 23251 | n_gen = 6835, tg = 23.53 t/s, tg_3s = 21.92 t/s 22.12.677.703 I slot print_timing: id 0 | task 23251 | n_gen = 6901, tg = 23.51 t/s, tg_3s = 21.95 t/s 22.15.718.796 I slot print_timing: id 0 | task 23251 | n_gen = 6968, tg = 23.50 t/s, tg_3s = 22.03 t/s 22.18.739.075 I slot print_timing: id 0 | task 23251 | n_gen = 7034, tg = 23.48 t/s, tg_3s = 21.85 t/s 22.21.760.835 I slot print_timing: id 0 | task 23251 | n_gen = 7101, tg = 23.47 t/s, tg_3s = 22.17 t/s 22.24.793.325 I slot print_timing: id 0 | task 23251 | n_gen = 7168, tg = 23.45 t/s, tg_3s = 22.09 t/s 22.27.815.969 I slot print_timing: id 0 | task 23251 | n_gen = 7234, tg = 23.44 t/s, tg_3s = 21.84 t/s 22.30.834.562 I slot print_timing: id 0 | task 23251 | n_gen = 7300, tg = 23.42 t/s, tg_3s = 21.86 t/s 22.33.842.301 I slot print_timing: id 0 | task 23251 | n_gen = 7366, tg = 23.41 t/s, tg_3s = 21.94 t/s 22.36.853.176 I slot print_timing: id 0 | task 23251 | n_gen = 7432, tg = 23.39 t/s, tg_3s = 21.92 t/s 22.39.893.856 I slot print_timing: id 0 | task 23251 | n_gen = 7498, tg = 23.38 t/s, tg_3s = 21.71 t/s 22.42.916.961 I slot print_timing: id 0 | task 23251 | n_gen = 7564, tg = 23.36 t/s, tg_3s = 21.83 t/s 22.45.937.967 I slot print_timing: id 0 | task 23251 | n_gen = 7630, tg = 23.35 t/s, tg_3s = 21.85 t/s 22.48.939.314 I slot print_timing: id 0 | task 23251 | n_gen = 7696, tg = 23.34 t/s, tg_3s = 21.99 t/s 22.51.947.718 I slot print_timing: id 0 | task 23251 | n_gen = 7762, tg = 23.32 t/s, tg_3s = 21.94 t/s 22.54.977.901 I slot print_timing: id 0 | task 23251 | n_gen = 7827, tg = 23.31 t/s, tg_3s = 21.45 t/s 22.57.986.177 I slot print_timing: id 0 | task 23251 | n_gen = 7893, tg = 23.30 t/s, tg_3s = 21.94 t/s 23.01.008.475 I slot print_timing: id 0 | task 23251 | n_gen = 7959, tg = 23.28 t/s, tg_3s = 21.84 t/s 23.04.043.322 I slot print_timing: id 0 | task 23251 | n_gen = 8026, tg = 23.27 t/s, tg_3s = 22.08 t/s 23.07.070.725 I slot print_timing: id 0 | task 23251 | n_gen = 8093, tg = 23.26 t/s, tg_3s = 22.13 t/s 23.10.099.058 I slot print_timing: id 0 | task 23251 | n_gen = 8160, tg = 23.25 t/s, tg_3s = 22.12 t/s 23.13.129.908 I slot print_timing: id 0 | task 23251 | n_gen = 8227, tg = 23.24 t/s, tg_3s = 22.11 t/s 23.16.156.337 I slot print_timing: id 0 | task 23251 | n_gen = 8292, tg = 23.23 t/s, tg_3s = 21.48 t/s 23.19.172.297 I slot print_timing: id 0 | task 23251 | n_gen = 8357, tg = 23.21 t/s, tg_3s = 21.55 t/s 23.22.186.275 I slot print_timing: id 0 | task 23251 | n_gen = 8423, tg = 23.20 t/s, tg_3s = 21.90 t/s 23.25.216.624 I slot print_timing: id 0 | task 23251 | n_gen = 8489, tg = 23.19 t/s, tg_3s = 21.78 t/s 23.28.254.797 I slot print_timing: id 0 | task 23251 | n_gen = 8555, tg = 23.18 t/s, tg_3s = 21.72 t/s 23.31.267.414 I slot print_timing: id 0 | task 23251 | n_gen = 8620, tg = 23.17 t/s, tg_3s = 21.58 t/s 23.34.302.205 I slot print_timing: id 0 | task 23251 | n_gen = 8685, tg = 23.15 t/s, tg_3s = 21.42 t/s 23.37.347.852 I slot print_timing: id 0 | task 23251 | n_gen = 8750, tg = 23.14 t/s, tg_3s = 21.34 t/s 23.40.365.669 I slot print_timing: id 0 | task 23251 | n_gen = 8815, tg = 23.12 t/s, tg_3s = 21.54 t/s 23.43.394.686 I slot print_timing: id 0 | task 23251 | n_gen = 8880, tg = 23.11 t/s, tg_3s = 21.46 t/s 23.46.402.217 I slot print_timing: id 0 | task 23251 | n_gen = 8944, tg = 23.10 t/s, tg_3s = 21.28 t/s 23.49.412.920 I slot print_timing: id 0 | task 23251 | n_gen = 9008, tg = 23.08 t/s, tg_3s = 21.26 t/s 23.52.445.496 I slot print_timing: id 0 | task 23251 | n_gen = 9073, tg = 23.07 t/s, tg_3s = 21.43 t/s 23.55.459.970 I slot print_timing: id 0 | task 23251 | n_gen = 9138, tg = 23.06 t/s, tg_3s = 21.56 t/s 23.58.505.604 I slot print_timing: id 0 | task 23251 | n_gen = 9204, tg = 23.05 t/s, tg_3s = 21.67 t/s 24.01.529.690 I slot print_timing: id 0 | task 23251 | n_gen = 9269, tg = 23.04 t/s, tg_3s = 21.49 t/s 24.04.532.800 I slot print_timing: id 0 | task 23251 | n_gen = 9333, tg = 23.02 t/s, tg_3s = 21.31 t/s 24.07.533.529 I slot print_timing: id 0 | task 23251 | n_gen = 9397, tg = 23.01 t/s, tg_3s = 21.33 t/s 24.10.559.376 I slot print_timing: id 0 | task 23251 | n_gen = 9462, tg = 23.00 t/s, tg_3s = 21.48 t/s 24.13.596.231 I slot print_timing: id 0 | task 23251 | n_gen = 9527, tg = 22.99 t/s, tg_3s = 21.40 t/s 24.16.640.915 I slot print_timing: id 0 | task 23251 | n_gen = 9592, tg = 22.98 t/s, tg_3s = 21.35 t/s 24.19.643.627 I slot print_timing: id 0 | task 23251 | n_gen = 9656, tg = 22.96 t/s, tg_3s = 21.31 t/s 24.22.679.358 I slot print_timing: id 0 | task 23251 | n_gen = 9720, tg = 22.95 t/s, tg_3s = 21.08 t/s 24.25.688.659 I slot print_timing: id 0 | task 23251 | n_gen = 9784, tg = 22.94 t/s, tg_3s = 21.27 t/s 24.28.696.007 I slot print_timing: id 0 | task 23251 | n_gen = 9848, tg = 22.93 t/s, tg_3s = 21.28 t/s 24.31.701.077 I slot print_timing: id 0 | task 23251 | n_gen = 9912, tg = 22.92 t/s, tg_3s = 21.30 t/s 24.34.730.414 I slot print_timing: id 0 | task 23251 | n_gen = 9976, tg = 22.90 t/s, tg_3s = 21.13 t/s 24.37.765.880 I slot print_timing: id 0 | task 23251 | n_gen = 10041, tg = 22.89 t/s, tg_3s = 21.41 t/s 24.40.804.632 I slot print_timing: id 0 | task 23251 | n_gen = 10105, tg = 22.88 t/s, tg_3s = 21.06 t/s 24.43.839.781 I slot print_timing: id 0 | task 23251 | n_gen = 10169, tg = 22.87 t/s, tg_3s = 21.09 t/s 24.46.851.776 I slot print_timing: id 0 | task 23251 | n_gen = 10233, tg = 22.86 t/s, tg_3s = 21.25 t/s 24.49.873.741 I slot print_timing: id 0 | task 23251 | n_gen = 10297, tg = 22.85 t/s, tg_3s = 21.18 t/s 24.52.909.772 I slot print_timing: id 0 | task 23251 | n_gen = 10362, tg = 22.84 t/s, tg_3s = 21.41 t/s 24.55.947.856 I slot print_timing: id 0 | task 23251 | n_gen = 10427, tg = 22.83 t/s, tg_3s = 21.40 t/s 24.58.951.648 I slot print_timing: id 0 | task 23251 | n_gen = 10491, tg = 22.82 t/s, tg_3s = 21.31 t/s 25.01.993.333 I slot print_timing: id 0 | task 23251 | n_gen = 10556, tg = 22.81 t/s, tg_3s = 21.37 t/s 25.05.019.713 I slot print_timing: id 0 | task 23251 | n_gen = 10620, tg = 22.80 t/s, tg_3s = 21.15 t/s 25.08.039.815 I slot print_timing: id 0 | task 23251 | n_gen = 10683, tg = 22.78 t/s, tg_3s = 20.86 t/s 25.11.074.748 I slot print_timing: id 0 | task 23251 | n_gen = 10747, tg = 22.77 t/s, tg_3s = 21.09 t/s 25.14.075.047 I slot print_timing: id 0 | task 23251 | n_gen = 10810, tg = 22.76 t/s, tg_3s = 21.00 t/s 25.17.105.779 I slot print_timing: id 0 | task 23251 | n_gen = 10873, tg = 22.75 t/s, tg_3s = 20.79 t/s 25.20.119.645 I slot print_timing: id 0 | task 23251 | n_gen = 10936, tg = 22.74 t/s, tg_3s = 20.90 t/s 25.23.130.383 I slot print_timing: id 0 | task 23251 | n_gen = 10999, tg = 22.73 t/s, tg_3s = 20.93 t/s 25.26.174.686 I slot print_timing: id 0 | task 23251 | n_gen = 11063, tg = 22.72 t/s, tg_3s = 21.02 t/s 25.29.179.111 I slot print_timing: id 0 | task 23251 | n_gen = 11126, tg = 22.71 t/s, tg_3s = 20.97 t/s 25.32.201.776 I slot print_timing: id 0 | task 23251 | n_gen = 11189, tg = 22.69 t/s, tg_3s = 20.84 t/s 25.35.205.634 I slot print_timing: id 0 | task 23251 | n_gen = 11252, tg = 22.68 t/s, tg_3s = 20.97 t/s 25.38.243.203 I slot print_timing: id 0 | task 23251 | n_gen = 11316, tg = 22.67 t/s, tg_3s = 21.07 t/s 25.41.276.624 I slot print_timing: id 0 | task 23251 | n_gen = 11379, tg = 22.66 t/s, tg_3s = 20.77 t/s 25.42.134.535 I slot print_timing: id 0 | task 23251 | prompt eval time = 1510.03 ms / 190 tokens ( 7.95 ms per token, 125.83 tokens per second) 25.42.134.538 I slot print_timing: id 0 | task 23251 | eval time = 502925.37 ms / 11397 tokens ( 44.13 ms per token, 22.66 tokens per second) 25.42.134.539 I slot print_timing: id 0 | task 23251 | total time = 504435.40 ms / 11587 tokens 25.42.134.539 I slot print_timing: id 0 | task 23251 | graphs reused = 0 25.42.134.560 I slot release: id 0 | task 23251 | stop processing: n_tokens = 11586, truncated = 0 25.42.136.592 I srv operator(): operator(): cleaning up before exit...