0.00.000.177 I srv llama_server: initializing ... 0.00.111.184 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.111.414 W srv llama_server: security: no API key is set and CORS allows all origins (see https://github.com/ggml-org/llama.cpp/pull/25655) 0.00.113.078 I srv load_model: loading model '/workspace/models/gguf/Qwen3.8-27B-Q4_K_M.gguf' 0.01.839.446 I cmn init: llama threadpool init, n_threads = 12 0.01.924.735 I srv load_model: initializing, n_slots = 16, n_ctx_slot = 8192, kv_unified = 'false' 0.01.927.410 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.01.927.447 I srv llama_server: model loaded 0.01.927.450 I srv llama_server: listening on http://0.0.0.0:8001 0.11.789.132 I slot get_availabl: id 15 | task -1 | selected slot by LRU, t_last = -1 0.11.789.223 I slot launch_slot_: id 15 | task 0 | processing task, is_child = 0 0.11.789.226 I slot get_availabl: id 14 | task -1 | selected slot by LRU, t_last = -1 0.11.789.256 I slot launch_slot_: id 14 | task 1 | processing task, is_child = 0 0.11.823.413 I slot get_availabl: id 13 | task -1 | selected slot by LRU, t_last = -1 0.11.823.458 I slot launch_slot_: id 13 | task 4 | processing task, is_child = 0 0.11.823.460 I slot get_availabl: id 12 | task -1 | selected slot by LRU, t_last = -1 0.11.823.479 I slot launch_slot_: id 12 | task 3 | processing task, is_child = 0 0.11.823.481 I slot get_availabl: id 11 | task -1 | selected slot by LRU, t_last = -1 0.11.823.498 I slot launch_slot_: id 11 | task 5 | processing task, is_child = 0 0.11.823.499 I slot get_availabl: id 10 | task -1 | selected slot by LRU, t_last = -1 0.11.823.516 I slot launch_slot_: id 10 | task 6 | processing task, is_child = 0 0.11.823.517 I slot get_availabl: id 9 | task -1 | selected slot by LRU, t_last = -1 0.11.823.552 I slot launch_slot_: id 9 | task 7 | processing task, is_child = 0 0.11.823.553 I slot get_availabl: id 8 | task -1 | selected slot by LRU, t_last = -1 0.11.823.572 I slot launch_slot_: id 8 | task 8 | processing task, is_child = 0 0.11.823.573 I slot get_availabl: id 7 | task -1 | selected slot by LRU, t_last = -1 0.11.823.591 I slot launch_slot_: id 7 | task 9 | processing task, is_child = 0 0.11.823.591 I slot get_availabl: id 6 | task -1 | selected slot by LRU, t_last = -1 0.11.823.610 I slot launch_slot_: id 6 | task 10 | processing task, is_child = 0 0.11.823.611 I slot get_availabl: id 5 | task -1 | selected slot by LRU, t_last = -1 0.11.823.679 I slot launch_slot_: id 5 | task 11 | processing task, is_child = 0 0.11.823.680 I slot get_availabl: id 4 | task -1 | selected slot by LRU, t_last = -1 0.11.823.699 I slot launch_slot_: id 4 | task 12 | processing task, is_child = 0 0.11.823.699 I slot get_availabl: id 3 | task -1 | selected slot by LRU, t_last = -1 0.11.823.716 I slot launch_slot_: id 3 | task 13 | processing task, is_child = 0 0.11.823.717 I slot get_availabl: id 2 | task -1 | selected slot by LRU, t_last = -1 0.11.823.734 I slot launch_slot_: id 2 | task 14 | processing task, is_child = 0 0.11.823.735 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = -1 0.11.823.803 I slot launch_slot_: id 1 | task 15 | processing task, is_child = 0 0.11.823.804 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = -1 0.11.823.822 I slot launch_slot_: id 0 | task 16 | processing task, is_child = 0 0.15.309.304 I slot print_timing: id 5 | task 11 | prompt processing, n_tokens = 1072, progress = 1.00, t = 3.48 s / 307.75 tokens per second 0.15.345.826 I slot print_timing: id 6 | task 10 | prompt processing, n_tokens = 969, progress = 1.00, t = 3.48 s / 278.19 tokens per second 0.15.381.059 I slot print_timing: id 7 | task 9 | prompt processing, n_tokens = 433, progress = 0.46, t = 3.48 s / 124.31 tokens per second 0.15.416.222 I slot print_timing: id 8 | task 8 | prompt processing, n_tokens = 453, progress = 0.47, t = 3.48 s / 130.05 tokens per second 0.15.451.099 I slot print_timing: id 9 | task 7 | prompt processing, n_tokens = 394, progress = 0.37, t = 3.48 s / 113.11 tokens per second 0.16.111.496 I slot print_timing: id 7 | task 9 | prompt processing, n_tokens = 945, progress = 1.00, t = 4.29 s / 220.52 tokens per second 0.16.146.913 I slot print_timing: id 8 | task 8 | prompt processing, n_tokens = 965, progress = 1.00, t = 4.29 s / 225.19 tokens per second 0.16.181.941 I slot print_timing: id 9 | task 7 | prompt processing, n_tokens = 560, progress = 0.52, t = 4.29 s / 130.68 tokens per second 0.16.216.741 I slot print_timing: id 10 | task 6 | prompt processing, n_tokens = 477, progress = 0.48, t = 4.29 s / 111.31 tokens per second 0.16.251.535 I slot print_timing: id 11 | task 5 | prompt processing, n_tokens = 452, progress = 0.46, t = 4.29 s / 105.48 tokens per second 0.16.967.840 I slot print_timing: id 9 | task 7 | prompt processing, n_tokens = 1072, progress = 1.00, t = 5.14 s / 208.52 tokens per second 0.17.002.877 I slot print_timing: id 10 | task 6 | prompt processing, n_tokens = 989, progress = 1.00, t = 5.14 s / 192.37 tokens per second 0.17.037.400 I slot print_timing: id 11 | task 5 | prompt processing, n_tokens = 468, progress = 0.48, t = 5.14 s / 91.03 tokens per second 0.17.071.980 I slot print_timing: id 12 | task 3 | prompt processing, n_tokens = 560, progress = 0.52, t = 5.14 s / 108.93 tokens per second 0.17.106.550 I slot print_timing: id 13 | task 4 | prompt processing, n_tokens = 413, progress = 0.44, t = 5.14 s / 80.33 tokens per second 0.17.141.196 I slot print_timing: id 14 | task 1 | prompt processing, n_tokens = 664, progress = 0.62, t = 5.18 s / 128.29 tokens per second 0.17.800.594 I slot print_timing: id 11 | task 5 | prompt processing, n_tokens = 980, progress = 1.00, t = 5.97 s / 164.06 tokens per second 0.17.835.547 I slot print_timing: id 12 | task 3 | prompt processing, n_tokens = 1072, progress = 1.00, t = 5.97 s / 179.46 tokens per second 0.17.870.253 I slot print_timing: id 13 | task 4 | prompt processing, n_tokens = 925, progress = 1.00, t = 5.97 s / 154.85 tokens per second 0.17.904.910 I slot print_timing: id 14 | task 1 | prompt processing, n_tokens = 1072, progress = 1.00, t = 6.01 s / 178.42 tokens per second 0.17.939.647 I slot print_timing: id 15 | task 0 | prompt processing, n_tokens = 556, progress = 0.56, t = 6.01 s / 92.54 tokens per second 0.18.143.522 I slot print_timing: id 15 | task 0 | prompt processing, n_tokens = 981, progress = 1.00, t = 6.35 s / 154.50 tokens per second 0.21.205.232 I slot print_timing: id 0 | task 16 | n_gen = 100, tg = 14.74 t/s, tg_3s = 14.89 t/s 0.21.205.432 I slot print_timing: id 1 | task 15 | n_gen = 100, tg = 14.74 t/s, tg_3s = 14.89 t/s 0.21.205.647 I slot print_timing: id 2 | task 14 | n_gen = 100, tg = 14.74 t/s, tg_3s = 14.89 t/s 0.21.237.780 I slot print_timing: id 3 | task 13 | n_gen = 100, tg = 16.70 t/s, tg_3s = 16.87 t/s 0.21.237.987 I slot print_timing: id 4 | task 12 | n_gen = 100, tg = 16.70 t/s, tg_3s = 16.87 t/s 0.21.270.141 I slot print_timing: id 5 | task 11 | n_gen = 100, tg = 19.19 t/s, tg_3s = 19.38 t/s 0.21.270.348 I slot print_timing: id 6 | task 10 | n_gen = 100, tg = 19.19 t/s, tg_3s = 19.38 t/s 0.21.302.426 I slot print_timing: id 7 | task 9 | n_gen = 100, tg = 22.84 t/s, tg_3s = 23.07 t/s 0.21.302.634 I slot print_timing: id 8 | task 8 | n_gen = 100, tg = 22.84 t/s, tg_3s = 23.07 t/s 0.21.334.697 I slot print_timing: id 9 | task 7 | n_gen = 100, tg = 28.01 t/s, tg_3s = 28.29 t/s 0.21.334.902 I slot print_timing: id 10 | task 6 | n_gen = 100, tg = 28.01 t/s, tg_3s = 28.29 t/s 0.21.367.887 I slot print_timing: id 11 | task 5 | n_gen = 100, tg = 30.69 t/s, tg_3s = 31.00 t/s 0.21.368.252 I slot print_timing: id 12 | task 3 | n_gen = 100, tg = 30.69 t/s, tg_3s = 31.00 t/s 0.21.368.630 I slot print_timing: id 13 | task 4 | n_gen = 100, tg = 30.69 t/s, tg_3s = 31.00 t/s 0.21.369.000 I slot print_timing: id 14 | task 1 | n_gen = 100, tg = 30.69 t/s, tg_3s = 31.00 t/s 0.21.402.599 I slot print_timing: id 15 | task 0 | n_gen = 100, tg = 31.22 t/s, tg_3s = 31.53 t/s 0.24.215.248 I slot print_timing: id 0 | task 16 | n_gen = 194, tg = 19.84 t/s, tg_3s = 31.23 t/s 0.24.215.447 I slot print_timing: id 1 | task 15 | n_gen = 194, tg = 19.84 t/s, tg_3s = 31.23 t/s 0.24.215.690 I slot print_timing: id 2 | task 14 | n_gen = 194, tg = 19.84 t/s, tg_3s = 31.23 t/s 0.24.249.123 I slot print_timing: id 3 | task 13 | n_gen = 194, tg = 21.59 t/s, tg_3s = 31.22 t/s 0.24.249.331 I slot print_timing: id 4 | task 12 | n_gen = 194, tg = 21.59 t/s, tg_3s = 31.22 t/s 0.24.281.478 I slot print_timing: id 5 | task 11 | n_gen = 194, tg = 23.62 t/s, tg_3s = 31.22 t/s 0.24.281.687 I slot print_timing: id 6 | task 10 | n_gen = 194, tg = 23.62 t/s, tg_3s = 31.22 t/s 0.24.313.992 I slot print_timing: id 7 | task 9 | n_gen = 194, tg = 26.27 t/s, tg_3s = 31.21 t/s 0.24.314.193 I slot print_timing: id 8 | task 8 | n_gen = 194, tg = 26.27 t/s, tg_3s = 31.21 t/s 0.24.346.338 I slot print_timing: id 9 | task 7 | n_gen = 194, tg = 29.48 t/s, tg_3s = 31.21 t/s 0.24.346.540 I slot print_timing: id 10 | task 6 | n_gen = 194, tg = 29.48 t/s, tg_3s = 31.21 t/s 0.24.378.676 I slot print_timing: id 11 | task 5 | n_gen = 194, tg = 30.94 t/s, tg_3s = 31.22 t/s 0.24.378.885 I slot print_timing: id 12 | task 3 | n_gen = 194, tg = 30.95 t/s, tg_3s = 31.22 t/s 0.24.379.099 I slot print_timing: id 13 | task 4 | n_gen = 194, tg = 30.95 t/s, tg_3s = 31.22 t/s 0.24.379.314 I slot print_timing: id 14 | task 1 | n_gen = 194, tg = 30.95 t/s, tg_3s = 31.23 t/s 0.24.411.815 I slot print_timing: id 15 | task 0 | n_gen = 194, tg = 31.23 t/s, tg_3s = 31.24 t/s 0.26.211.466 I slot print_timing: id 0 | task 16 | prompt eval time = 2663.22 ms / 1076 tokens ( 2.48 ms per token, 404.02 tokens per second) 0.26.211.469 I slot print_timing: id 0 | task 16 | eval time = 11724.39 ms / 256 tokens ( 45.98 ms per token, 21.75 tokens per second) 0.26.211.470 I slot print_timing: id 0 | task 16 | total time = 14387.61 ms / 1332 tokens 0.26.211.476 I slot print_timing: id 0 | task 16 | graphs reused = 252 0.26.211.535 I slot release: id 0 | task 16 | stop processing: n_tokens = 1331, truncated = 0 0.26.211.744 I slot print_timing: id 1 | task 15 | prompt eval time = 2663.85 ms / 1076 tokens ( 2.48 ms per token, 403.93 tokens per second) 0.26.211.745 I slot print_timing: id 1 | task 15 | eval time = 11724.01 ms / 256 tokens ( 45.98 ms per token, 21.75 tokens per second) 0.26.211.746 I slot print_timing: id 1 | task 15 | total time = 14387.86 ms / 1332 tokens 0.26.211.746 I slot print_timing: id 1 | task 15 | graphs reused = 252 0.26.211.789 I slot release: id 1 | task 15 | stop processing: n_tokens = 1331, truncated = 0 0.26.211.995 I slot print_timing: id 2 | task 14 | prompt eval time = 2664.49 ms / 1076 tokens ( 2.48 ms per token, 403.83 tokens per second) 0.26.211.996 I slot print_timing: id 2 | task 14 | eval time = 11723.60 ms / 256 tokens ( 45.97 ms per token, 21.75 tokens per second) 0.26.211.996 I slot print_timing: id 2 | task 14 | total time = 14388.09 ms / 1332 tokens 0.26.211.997 I slot print_timing: id 2 | task 14 | graphs reused = 252 0.26.212.037 I slot release: id 2 | task 14 | stop processing: n_tokens = 1331, truncated = 0 0.26.244.117 I slot print_timing: id 3 | task 13 | prompt eval time = 3484.74 ms / 1076 tokens ( 3.24 ms per token, 308.77 tokens per second) 0.26.244.120 I slot print_timing: id 3 | task 13 | eval time = 10935.45 ms / 256 tokens ( 42.88 ms per token, 23.32 tokens per second) 0.26.244.120 I slot print_timing: id 3 | task 13 | total time = 14420.19 ms / 1332 tokens 0.26.244.121 I slot print_timing: id 3 | task 13 | graphs reused = 252 0.26.244.172 I slot release: id 3 | task 13 | stop processing: n_tokens = 1331, truncated = 0 0.26.244.374 I slot print_timing: id 4 | task 12 | prompt eval time = 3485.35 ms / 984 tokens ( 3.54 ms per token, 282.32 tokens per second) 0.26.244.375 I slot print_timing: id 4 | task 12 | eval time = 10935.10 ms / 256 tokens ( 42.88 ms per token, 23.32 tokens per second) 0.26.244.375 I slot print_timing: id 4 | task 12 | total time = 14420.44 ms / 1240 tokens 0.26.244.376 I slot print_timing: id 4 | task 12 | graphs reused = 252 0.26.244.410 I slot release: id 4 | task 12 | stop processing: n_tokens = 1239, truncated = 0 0.26.246.675 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 680025551976 0.26.380.244 I slot launch_slot_: id 0 | task 277 | processing task, is_child = 0 0.26.909.750 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 680025552229 0.26.909.922 I slot launch_slot_: id 1 | task 279 | processing task, is_child = 0 0.26.910.143 I slot get_availabl: id 2 | task -1 | selected slot by LRU, t_last = 680025552476 0.26.910.252 I slot launch_slot_: id 2 | task 278 | processing task, is_child = 0 0.26.910.391 I slot get_availabl: id 3 | task -1 | selected slot by LRU, t_last = 680025584612 0.26.910.484 I slot launch_slot_: id 3 | task 280 | processing task, is_child = 0 0.26.910.562 I slot get_availabl: id 4 | task -1 | selected slot by LRU, t_last = 680025584850 0.26.910.651 I slot launch_slot_: id 4 | task 281 | processing task, is_child = 0 0.27.734.208 I slot print_timing: id 5 | task 11 | prompt eval time = 4286.93 ms / 1076 tokens ( 3.98 ms per token, 251.00 tokens per second) 0.27.734.211 I slot print_timing: id 5 | task 11 | eval time = 11623.31 ms / 256 tokens ( 45.58 ms per token, 21.94 tokens per second) 0.27.734.211 I slot print_timing: id 5 | task 11 | total time = 15910.24 ms / 1332 tokens 0.27.734.212 I slot print_timing: id 5 | task 11 | graphs reused = 253 0.27.734.258 I slot release: id 5 | task 11 | stop processing: n_tokens = 1331, truncated = 0 0.27.734.500 I slot print_timing: id 6 | task 10 | prompt eval time = 4287.51 ms / 973 tokens ( 4.41 ms per token, 226.94 tokens per second) 0.27.734.502 I slot print_timing: id 6 | task 10 | eval time = 11623.03 ms / 256 tokens ( 45.58 ms per token, 21.94 tokens per second) 0.27.734.502 I slot print_timing: id 6 | task 10 | total time = 15910.53 ms / 1229 tokens 0.27.734.503 I slot print_timing: id 6 | task 10 | graphs reused = 253 0.27.734.539 I slot release: id 6 | task 10 | stop processing: n_tokens = 1228, truncated = 0 0.27.734.781 I slot print_timing: id 7 | task 9 | n_gen = 255, tg = 23.59 t/s, tg_3s = 17.83 t/s 0.27.735.006 I slot print_timing: id 8 | task 8 | n_gen = 255, tg = 23.59 t/s, tg_3s = 17.83 t/s 0.27.735.246 I slot print_timing: id 9 | task 7 | n_gen = 254, tg = 25.46 t/s, tg_3s = 17.70 t/s 0.27.735.438 I slot print_timing: id 10 | task 6 | n_gen = 254, tg = 25.47 t/s, tg_3s = 17.70 t/s 0.27.735.671 I slot print_timing: id 11 | task 5 | n_gen = 253, tg = 26.27 t/s, tg_3s = 17.58 t/s 0.27.735.862 I slot print_timing: id 12 | task 3 | n_gen = 253, tg = 26.27 t/s, tg_3s = 17.58 t/s 0.27.736.157 I slot print_timing: id 13 | task 4 | n_gen = 253, tg = 26.27 t/s, tg_3s = 17.57 t/s 0.27.736.344 I slot print_timing: id 14 | task 1 | n_gen = 253, tg = 26.27 t/s, tg_3s = 17.58 t/s 0.27.736.541 I slot print_timing: id 15 | task 0 | n_gen = 252, tg = 26.41 t/s, tg_3s = 17.45 t/s 0.28.427.337 I slot print_timing: id 7 | task 9 | prompt eval time = 5143.26 ms / 949 tokens ( 5.42 ms per token, 184.51 tokens per second) 0.28.427.341 I slot print_timing: id 7 | task 9 | eval time = 11460.08 ms / 256 tokens ( 44.94 ms per token, 22.25 tokens per second) 0.28.427.341 I slot print_timing: id 7 | task 9 | total time = 16603.34 ms / 1205 tokens 0.28.427.342 I slot print_timing: id 7 | task 9 | graphs reused = 254 0.28.427.386 I slot release: id 7 | task 9 | stop processing: n_tokens = 1204, truncated = 0 0.28.427.629 I slot print_timing: id 8 | task 8 | prompt eval time = 5143.84 ms / 969 tokens ( 5.31 ms per token, 188.38 tokens per second) 0.28.427.631 I slot print_timing: id 8 | task 8 | eval time = 11459.81 ms / 256 tokens ( 44.94 ms per token, 22.25 tokens per second) 0.28.427.632 I slot print_timing: id 8 | task 8 | total time = 16603.65 ms / 1225 tokens 0.28.427.632 I slot print_timing: id 8 | task 8 | graphs reused = 254 0.28.427.667 I slot release: id 8 | task 8 | stop processing: n_tokens = 1224, truncated = 0 0.28.429.178 I slot get_availabl: id 5 | task -1 | selected slot by LRU, t_last = 680027074697 0.28.566.378 I slot launch_slot_: id 5 | task 284 | processing task, is_child = 0 0.28.960.392 I slot get_availabl: id 6 | task -1 | selected slot by LRU, t_last = 680027074978 0.28.960.550 I slot launch_slot_: id 6 | task 285 | processing task, is_child = 0 0.28.960.699 I slot get_availabl: id 7 | task -1 | selected slot by LRU, t_last = 680027767825 0.28.960.800 I slot launch_slot_: id 7 | task 286 | processing task, is_child = 0 0.28.960.879 I slot get_availabl: id 8 | task -1 | selected slot by LRU, t_last = 680027768107 0.28.960.978 I slot launch_slot_: id 8 | task 287 | processing task, is_child = 0 0.29.962.251 I slot print_timing: id 9 | task 7 | prompt eval time = 5975.94 ms / 1076 tokens ( 5.55 ms per token, 180.06 tokens per second) 0.29.962.254 I slot print_timing: id 9 | task 7 | eval time = 12162.31 ms / 256 tokens ( 47.70 ms per token, 20.97 tokens per second) 0.29.962.255 I slot print_timing: id 9 | task 7 | total time = 18138.25 ms / 1332 tokens 0.29.962.255 I slot print_timing: id 9 | task 7 | graphs reused = 255 0.29.962.299 I slot release: id 9 | task 7 | stop processing: n_tokens = 1331, truncated = 0 0.29.962.510 I slot print_timing: id 10 | task 6 | prompt eval time = 5976.56 ms / 993 tokens ( 6.02 ms per token, 166.15 tokens per second) 0.29.962.512 I slot print_timing: id 10 | task 6 | eval time = 12161.94 ms / 256 tokens ( 47.69 ms per token, 20.97 tokens per second) 0.29.962.512 I slot print_timing: id 10 | task 6 | total time = 18138.50 ms / 1249 tokens 0.29.962.513 I slot print_timing: id 10 | task 6 | graphs reused = 255 0.29.962.553 I slot release: id 10 | task 6 | stop processing: n_tokens = 1248, truncated = 0 0.30.731.647 I slot print_timing: id 11 | task 5 | prompt eval time = 6317.68 ms / 984 tokens ( 6.42 ms per token, 155.75 tokens per second) 0.30.731.650 I slot print_timing: id 11 | task 5 | eval time = 12589.95 ms / 256 tokens ( 49.37 ms per token, 20.25 tokens per second) 0.30.731.651 I slot print_timing: id 11 | task 5 | total time = 18907.63 ms / 1240 tokens 0.30.731.652 I slot print_timing: id 11 | task 5 | graphs reused = 256 0.30.731.692 I slot release: id 11 | task 5 | stop processing: n_tokens = 1239, truncated = 0 0.30.731.887 I slot print_timing: id 12 | task 3 | prompt eval time = 6318.26 ms / 1076 tokens ( 5.87 ms per token, 170.30 tokens per second) 0.30.731.888 I slot print_timing: id 12 | task 3 | eval time = 12589.60 ms / 256 tokens ( 49.37 ms per token, 20.25 tokens per second) 0.30.731.889 I slot print_timing: id 12 | task 3 | total time = 18907.86 ms / 1332 tokens 0.30.731.889 I slot print_timing: id 12 | task 3 | graphs reused = 256 0.30.731.959 I slot release: id 12 | task 3 | stop processing: n_tokens = 1331, truncated = 0 0.30.732.173 I slot print_timing: id 13 | task 4 | prompt eval time = 6318.86 ms / 929 tokens ( 6.80 ms per token, 147.02 tokens per second) 0.30.732.174 I slot print_timing: id 13 | task 4 | eval time = 12589.27 ms / 256 tokens ( 49.37 ms per token, 20.26 tokens per second) 0.30.732.175 I slot print_timing: id 13 | task 4 | total time = 18908.14 ms / 1185 tokens 0.30.732.175 I slot print_timing: id 13 | task 4 | graphs reused = 256 0.30.732.205 I slot release: id 13 | task 4 | stop processing: n_tokens = 1184, truncated = 0 0.30.732.410 I slot print_timing: id 14 | task 1 | prompt eval time = 6354.21 ms / 1076 tokens ( 5.91 ms per token, 169.34 tokens per second) 0.30.732.411 I slot print_timing: id 14 | task 1 | eval time = 12588.91 ms / 256 tokens ( 49.37 ms per token, 20.26 tokens per second) 0.30.732.411 I slot print_timing: id 14 | task 1 | total time = 18943.12 ms / 1332 tokens 0.30.732.412 I slot print_timing: id 14 | task 1 | graphs reused = 256 0.30.732.448 I slot release: id 14 | task 1 | stop processing: n_tokens = 1331, truncated = 0 0.30.732.668 I slot get_availabl: id 9 | task -1 | selected slot by LRU, t_last = 680029302738 0.30.866.994 I slot launch_slot_: id 9 | task 290 | processing task, is_child = 0 0.31.128.125 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 0.31.272.042 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 0.31.414.119 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 0.31.423.997 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 0.31.594.698 I slot get_availabl: id 10 | task -1 | selected slot by LRU, t_last = 680029302992 0.31.594.863 I slot launch_slot_: id 10 | task 291 | processing task, is_child = 0 0.31.595.159 I slot get_availabl: id 11 | task -1 | selected slot by LRU, t_last = 680030072131 0.31.595.261 I slot launch_slot_: id 11 | task 292 | processing task, is_child = 0 0.31.595.474 I slot get_availabl: id 12 | task -1 | selected slot by LRU, t_last = 680030072399 0.31.595.576 I slot launch_slot_: id 12 | task 293 | processing task, is_child = 0 0.31.595.736 I slot get_availabl: id 13 | task -1 | selected slot by LRU, t_last = 680030072644 0.31.595.839 I slot launch_slot_: id 13 | task 294 | processing task, is_child = 0 0.31.595.911 I slot get_availabl: id 14 | task -1 | selected slot by LRU, t_last = 680030072887 0.31.596.013 I slot launch_slot_: id 14 | task 295 | processing task, is_child = 0 0.31.596.029 I slot print_timing: id 4 | task 281 | prompt processing, n_tokens = 937, progress = 1.00, t = 3.60 s / 260.14 tokens per second 0.32.568.208 I slot print_timing: id 15 | task 0 | prompt eval time = 6441.97 ms / 985 tokens ( 6.54 ms per token, 152.90 tokens per second) 0.32.568.211 I slot print_timing: id 15 | task 0 | eval time = 14336.91 ms / 256 tokens ( 56.22 ms per token, 17.79 tokens per second) 0.32.568.212 I slot print_timing: id 15 | task 0 | total time = 20778.88 ms / 1241 tokens 0.32.568.213 I slot print_timing: id 15 | task 0 | graphs reused = 256 0.32.568.256 I slot release: id 15 | task 0 | stop processing: n_tokens = 1240, truncated = 0 0.32.568.274 I slot print_timing: id 7 | task 286 | prompt processing, n_tokens = 1030, progress = 1.00, t = 3.36 s / 306.43 tokens per second 0.32.603.151 I slot print_timing: id 8 | task 287 | prompt processing, n_tokens = 518, progress = 0.52, t = 3.31 s / 156.61 tokens per second 0.33.319.573 I slot get_availabl: id 15 | task -1 | selected slot by LRU, t_last = 680031908695 0.33.319.679 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 675.971 MiB) 0.33.488.972 I slot launch_slot_: id 15 | task 298 | processing task, is_child = 0 0.33.488.991 I slot print_timing: id 8 | task 287 | prompt processing, n_tokens = 1030, progress = 1.00, t = 4.06 s / 253.75 tokens per second 0.35.012.738 I slot print_timing: id 12 | task 293 | prompt processing, n_tokens = 934, progress = 1.00, t = 3.12 s / 299.50 tokens per second 0.38.259.199 I slot print_timing: id 0 | task 277 | n_gen = 100, tg = 11.93 t/s, tg_3s = 12.05 t/s 0.38.259.413 I slot print_timing: id 1 | task 279 | n_gen = 100, tg = 11.93 t/s, tg_3s = 12.05 t/s 0.38.259.625 I slot print_timing: id 2 | task 278 | n_gen = 100, tg = 11.93 t/s, tg_3s = 12.05 t/s 0.38.291.785 I slot print_timing: id 3 | task 280 | n_gen = 100, tg = 13.09 t/s, tg_3s = 13.23 t/s 0.38.324.007 I slot print_timing: id 4 | task 281 | n_gen = 100, tg = 17.20 t/s, tg_3s = 17.37 t/s 0.38.324.307 I slot print_timing: id 5 | task 284 | n_gen = 100, tg = 17.20 t/s, tg_3s = 17.37 t/s 0.38.324.609 I slot print_timing: id 6 | task 285 | n_gen = 100, tg = 17.20 t/s, tg_3s = 17.37 t/s 0.38.356.724 I slot print_timing: id 7 | task 286 | n_gen = 100, tg = 19.65 t/s, tg_3s = 19.85 t/s 0.38.388.960 I slot print_timing: id 8 | task 287 | n_gen = 100, tg = 24.01 t/s, tg_3s = 24.25 t/s 0.38.389.168 I slot print_timing: id 9 | task 290 | n_gen = 100, tg = 24.01 t/s, tg_3s = 24.25 t/s 0.38.389.372 I slot print_timing: id 10 | task 291 | n_gen = 100, tg = 24.01 t/s, tg_3s = 24.25 t/s 0.38.421.646 I slot print_timing: id 11 | task 292 | n_gen = 100, tg = 29.04 t/s, tg_3s = 29.33 t/s 0.38.453.928 I slot print_timing: id 12 | task 293 | n_gen = 100, tg = 30.69 t/s, tg_3s = 31.00 t/s 0.38.454.145 I slot print_timing: id 13 | task 294 | n_gen = 100, tg = 30.69 t/s, tg_3s = 31.00 t/s 0.38.454.354 I slot print_timing: id 14 | task 295 | n_gen = 100, tg = 30.69 t/s, tg_3s = 31.00 t/s 0.38.486.552 I slot print_timing: id 15 | task 298 | n_gen = 100, tg = 31.23 t/s, tg_3s = 31.55 t/s 0.41.265.360 I slot print_timing: id 0 | task 277 | n_gen = 194, tg = 17.07 t/s, tg_3s = 31.27 t/s 0.41.265.573 I slot print_timing: id 1 | task 279 | n_gen = 194, tg = 17.07 t/s, tg_3s = 31.27 t/s 0.41.265.779 I slot print_timing: id 2 | task 278 | n_gen = 194, tg = 17.07 t/s, tg_3s = 31.27 t/s 0.41.298.214 I slot print_timing: id 3 | task 280 | n_gen = 194, tg = 18.26 t/s, tg_3s = 31.27 t/s 0.41.330.355 I slot print_timing: id 4 | task 281 | n_gen = 194, tg = 22.02 t/s, tg_3s = 31.27 t/s 0.41.330.559 I slot print_timing: id 5 | task 284 | n_gen = 194, tg = 22.02 t/s, tg_3s = 31.27 t/s 0.41.330.768 I slot print_timing: id 6 | task 285 | n_gen = 194, tg = 22.02 t/s, tg_3s = 31.27 t/s 0.41.362.958 I slot print_timing: id 7 | task 286 | n_gen = 194, tg = 23.99 t/s, tg_3s = 31.27 t/s 0.41.395.286 I slot print_timing: id 8 | task 287 | n_gen = 194, tg = 27.07 t/s, tg_3s = 31.27 t/s 0.41.395.488 I slot print_timing: id 9 | task 290 | n_gen = 194, tg = 27.07 t/s, tg_3s = 31.27 t/s 0.41.395.696 I slot print_timing: id 10 | task 291 | n_gen = 194, tg = 27.07 t/s, tg_3s = 31.27 t/s 0.41.427.872 I slot print_timing: id 11 | task 292 | n_gen = 194, tg = 30.09 t/s, tg_3s = 31.27 t/s 0.41.460.110 I slot print_timing: id 12 | task 293 | n_gen = 194, tg = 30.97 t/s, tg_3s = 31.27 t/s 0.41.460.318 I slot print_timing: id 13 | task 294 | n_gen = 194, tg = 30.97 t/s, tg_3s = 31.27 t/s 0.41.460.527 I slot print_timing: id 14 | task 295 | n_gen = 194, tg = 30.97 t/s, tg_3s = 31.27 t/s 0.41.492.712 I slot print_timing: id 15 | task 298 | n_gen = 194, tg = 31.25 t/s, tg_3s = 31.27 t/s 0.43.261.108 I slot print_timing: id 0 | task 277 | prompt eval time = 3050.83 ms / 907 tokens ( 3.36 ms per token, 297.30 tokens per second) 0.43.261.111 I slot print_timing: id 0 | task 277 | eval time = 13299.60 ms / 256 tokens ( 52.16 ms per token, 19.17 tokens per second) 0.43.261.112 I slot print_timing: id 0 | task 277 | total time = 16350.43 ms / 1163 tokens 0.43.261.112 I slot print_timing: id 0 | task 277 | graphs reused = 504 0.43.261.154 I slot release: id 0 | task 277 | stop processing: n_tokens = 1204, truncated = 0 0.43.261.389 I slot print_timing: id 1 | task 279 | prompt eval time = 2996.68 ms / 1034 tokens ( 2.90 ms per token, 345.05 tokens per second) 0.43.261.390 I slot print_timing: id 1 | task 279 | eval time = 13299.62 ms / 256 tokens ( 52.16 ms per token, 19.17 tokens per second) 0.43.261.391 I slot print_timing: id 1 | task 279 | total time = 16296.30 ms / 1290 tokens 0.43.261.391 I slot print_timing: id 1 | task 279 | graphs reused = 504 0.43.261.426 I slot release: id 1 | task 279 | stop processing: n_tokens = 1331, truncated = 0 0.43.261.650 I slot print_timing: id 2 | task 278 | prompt eval time = 2942.93 ms / 1034 tokens ( 2.85 ms per token, 351.35 tokens per second) 0.43.261.651 I slot print_timing: id 2 | task 278 | eval time = 13299.61 ms / 256 tokens ( 52.16 ms per token, 19.17 tokens per second) 0.43.261.651 I slot print_timing: id 2 | task 278 | total time = 16242.54 ms / 1290 tokens 0.43.261.651 I slot print_timing: id 2 | task 278 | graphs reused = 504 0.43.261.683 I slot release: id 2 | task 278 | stop processing: n_tokens = 1331, truncated = 0 0.43.293.507 I slot print_timing: id 3 | task 280 | prompt eval time = 3657.53 ms / 1034 tokens ( 3.54 ms per token, 282.70 tokens per second) 0.43.293.510 I slot print_timing: id 3 | task 280 | eval time = 12562.05 ms / 256 tokens ( 49.26 ms per token, 20.30 tokens per second) 0.43.293.510 I slot print_timing: id 3 | task 280 | total time = 16219.59 ms / 1290 tokens 0.43.293.511 I slot print_timing: id 3 | task 280 | graphs reused = 504 0.43.293.555 I slot release: id 3 | task 280 | stop processing: n_tokens = 1331, truncated = 0 0.43.296.046 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 680042601594 0.43.296.165 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 0.43.444.857 I slot launch_slot_: id 0 | task 552 | processing task, is_child = 0 0.43.444.954 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 675.283 MiB) 0.43.590.024 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 673.782 MiB) 0.43.732.921 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 675.033 MiB) 0.43.901.948 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 680042601865 0.43.902.110 I slot launch_slot_: id 1 | task 553 | processing task, is_child = 0 0.43.902.264 I slot get_availabl: id 2 | task -1 | selected slot by LRU, t_last = 680042602123 0.43.902.361 I slot launch_slot_: id 2 | task 554 | processing task, is_child = 0 0.43.902.442 I slot get_availabl: id 3 | task -1 | selected slot by LRU, t_last = 680042633994 0.43.902.544 I slot launch_slot_: id 3 | task 555 | processing task, is_child = 0 0.44.666.831 I slot print_timing: id 4 | task 281 | prompt eval time = 5438.90 ms / 941 tokens ( 5.78 ms per token, 173.01 tokens per second) 0.44.666.837 I slot print_timing: id 4 | task 281 | eval time = 12099.32 ms / 256 tokens ( 47.45 ms per token, 21.08 tokens per second) 0.44.666.837 I slot print_timing: id 4 | task 281 | total time = 17538.21 ms / 1197 tokens 0.44.666.838 I slot print_timing: id 4 | task 281 | graphs reused = 505 0.44.666.887 I slot release: id 4 | task 281 | stop processing: n_tokens = 1238, truncated = 0 0.44.667.168 I slot print_timing: id 5 | task 284 | prompt eval time = 3468.73 ms / 885 tokens ( 3.92 ms per token, 255.14 tokens per second) 0.44.667.170 I slot print_timing: id 5 | task 284 | eval time = 12099.42 ms / 256 tokens ( 47.45 ms per token, 21.08 tokens per second) 0.44.667.171 I slot print_timing: id 5 | task 284 | total time = 15568.16 ms / 1141 tokens 0.44.667.171 I slot print_timing: id 5 | task 284 | graphs reused = 505 0.44.667.207 I slot release: id 5 | task 284 | stop processing: n_tokens = 1182, truncated = 0 0.44.667.443 I slot print_timing: id 6 | task 285 | prompt eval time = 3416.74 ms / 953 tokens ( 3.59 ms per token, 278.92 tokens per second) 0.44.667.445 I slot print_timing: id 6 | task 285 | eval time = 12099.45 ms / 256 tokens ( 47.45 ms per token, 21.08 tokens per second) 0.44.667.446 I slot print_timing: id 6 | task 285 | total time = 15516.19 ms / 1209 tokens 0.44.667.447 I slot print_timing: id 6 | task 285 | graphs reused = 505 0.44.667.488 I slot release: id 6 | task 285 | stop processing: n_tokens = 1250, truncated = 0 0.44.667.750 I slot print_timing: id 7 | task 286 | n_gen = 255, tg = 22.38 t/s, tg_3s = 18.46 t/s 0.44.667.977 I slot print_timing: id 8 | task 287 | n_gen = 254, tg = 24.32 t/s, tg_3s = 18.33 t/s 0.44.668.170 I slot print_timing: id 9 | task 290 | n_gen = 254, tg = 24.32 t/s, tg_3s = 18.33 t/s 0.44.668.373 I slot print_timing: id 10 | task 291 | n_gen = 254, tg = 24.32 t/s, tg_3s = 18.33 t/s 0.44.668.569 I slot print_timing: id 11 | task 292 | n_gen = 253, tg = 26.10 t/s, tg_3s = 18.21 t/s 0.44.668.770 I slot print_timing: id 12 | task 293 | n_gen = 252, tg = 26.59 t/s, tg_3s = 18.08 t/s 0.44.668.973 I slot print_timing: id 13 | task 294 | n_gen = 252, tg = 26.59 t/s, tg_3s = 18.08 t/s 0.44.669.172 I slot print_timing: id 14 | task 295 | n_gen = 252, tg = 26.59 t/s, tg_3s = 18.08 t/s 0.44.669.371 I slot print_timing: id 15 | task 298 | n_gen = 251, tg = 26.73 t/s, tg_3s = 17.94 t/s 0.45.360.177 I slot print_timing: id 7 | task 286 | prompt eval time = 4114.73 ms / 1034 tokens ( 3.98 ms per token, 251.29 tokens per second) 0.45.360.181 I slot print_timing: id 7 | task 286 | eval time = 12040.59 ms / 256 tokens ( 47.22 ms per token, 21.18 tokens per second) 0.45.360.182 I slot print_timing: id 7 | task 286 | total time = 16155.33 ms / 1290 tokens 0.45.360.183 I slot print_timing: id 7 | task 286 | graphs reused = 506 0.45.360.236 I slot release: id 7 | task 286 | stop processing: n_tokens = 1331, truncated = 0 0.45.361.966 I slot get_availabl: id 4 | task -1 | selected slot by LRU, t_last = 680044007326 0.45.362.075 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 0.45.505.839 I slot launch_slot_: id 4 | task 558 | processing task, is_child = 0 0.45.505.941 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 676.534 MiB) 0.45.647.267 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 675.971 MiB) 0.45.789.110 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 0.45.958.299 I slot get_availabl: id 5 | task -1 | selected slot by LRU, t_last = 680044007647 0.45.958.472 I slot launch_slot_: id 5 | task 559 | processing task, is_child = 0 0.45.958.620 I slot get_availabl: id 6 | task -1 | selected slot by LRU, t_last = 680044007928 0.45.958.717 I slot launch_slot_: id 6 | task 560 | processing task, is_child = 0 0.45.958.789 I slot get_availabl: id 7 | task -1 | selected slot by LRU, t_last = 680044700676 0.45.958.883 I slot launch_slot_: id 7 | task 561 | processing task, is_child = 0 0.46.914.980 I slot print_timing: id 8 | task 287 | prompt eval time = 5006.37 ms / 1034 tokens ( 4.84 ms per token, 206.54 tokens per second) 0.46.914.986 I slot print_timing: id 8 | task 287 | eval time = 12650.05 ms / 256 tokens ( 49.61 ms per token, 20.16 tokens per second) 0.46.914.986 I slot print_timing: id 8 | task 287 | total time = 17656.42 ms / 1290 tokens 0.46.914.987 I slot print_timing: id 8 | task 287 | graphs reused = 507 0.46.915.024 I slot release: id 8 | task 287 | stop processing: n_tokens = 1331, truncated = 0 0.46.915.271 I slot print_timing: id 9 | task 290 | prompt eval time = 2531.31 ms / 939 tokens ( 2.70 ms per token, 370.95 tokens per second) 0.46.915.274 I slot print_timing: id 9 | task 290 | eval time = 12650.09 ms / 256 tokens ( 49.61 ms per token, 20.16 tokens per second) 0.46.915.274 I slot print_timing: id 9 | task 290 | total time = 15181.40 ms / 1195 tokens 0.46.915.275 I slot print_timing: id 9 | task 290 | graphs reused = 507 0.46.915.311 I slot release: id 9 | task 290 | stop processing: n_tokens = 1236, truncated = 0 0.46.915.528 I slot print_timing: id 10 | task 291 | prompt eval time = 2480.06 ms / 1034 tokens ( 2.40 ms per token, 416.93 tokens per second) 0.46.915.530 I slot print_timing: id 10 | task 291 | eval time = 12650.10 ms / 256 tokens ( 49.61 ms per token, 20.16 tokens per second) 0.46.915.530 I slot print_timing: id 10 | task 291 | total time = 15130.16 ms / 1290 tokens 0.46.915.530 I slot print_timing: id 10 | task 291 | graphs reused = 507 0.46.915.564 I slot release: id 10 | task 291 | stop processing: n_tokens = 1331, truncated = 0 0.47.545.868 I slot print_timing: id 11 | task 292 | prompt eval time = 3174.47 ms / 1034 tokens ( 3.07 ms per token, 325.72 tokens per second) 0.47.545.871 I slot print_timing: id 11 | task 292 | eval time = 12533.14 ms / 256 tokens ( 49.15 ms per token, 20.35 tokens per second) 0.47.545.872 I slot print_timing: id 11 | task 292 | total time = 15707.61 ms / 1290 tokens 0.47.545.873 I slot print_timing: id 11 | task 292 | graphs reused = 508 0.47.545.921 I slot release: id 11 | task 292 | stop processing: n_tokens = 1331, truncated = 0 0.47.546.747 I slot get_availabl: id 8 | task -1 | selected slot by LRU, t_last = 680046255462 0.47.546.858 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 672.532 MiB) 0.47.690.750 I slot launch_slot_: id 8 | task 564 | processing task, is_child = 0 0.47.690.848 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 831.349 MiB) 0.47.836.210 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 825.659 MiB) 0.47.982.022 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 673.782 MiB) 0.48.156.534 I slot get_availabl: id 9 | task -1 | selected slot by LRU, t_last = 680046255750 0.48.156.706 I slot launch_slot_: id 9 | task 565 | processing task, is_child = 0 0.48.156.859 I slot get_availabl: id 10 | task -1 | selected slot by LRU, t_last = 680046256004 0.48.156.964 I slot launch_slot_: id 10 | task 566 | processing task, is_child = 0 0.48.157.035 I slot get_availabl: id 11 | task -1 | selected slot by LRU, t_last = 680046886360 0.48.157.130 I slot launch_slot_: id 11 | task 567 | processing task, is_child = 0 0.49.063.220 I slot print_timing: id 12 | task 293 | prompt eval time = 3336.59 ms / 938 tokens ( 3.56 ms per token, 281.13 tokens per second) 0.49.063.223 I slot print_timing: id 12 | task 293 | eval time = 13834.83 ms / 256 tokens ( 54.25 ms per token, 18.43 tokens per second) 0.49.063.223 I slot print_timing: id 12 | task 293 | total time = 17171.42 ms / 1194 tokens 0.49.063.224 I slot print_timing: id 12 | task 293 | graphs reused = 509 0.49.063.267 I slot release: id 12 | task 293 | stop processing: n_tokens = 1235, truncated = 0 0.49.063.510 I slot print_timing: id 13 | task 294 | prompt eval time = 1601.79 ms / 933 tokens ( 1.72 ms per token, 582.47 tokens per second) 0.49.063.512 I slot print_timing: id 13 | task 294 | eval time = 13834.87 ms / 256 tokens ( 54.25 ms per token, 18.43 tokens per second) 0.49.063.512 I slot print_timing: id 13 | task 294 | total time = 15436.66 ms / 1189 tokens 0.49.063.513 I slot print_timing: id 13 | task 294 | graphs reused = 509 0.49.063.550 I slot release: id 13 | task 294 | stop processing: n_tokens = 1230, truncated = 0 0.49.063.772 I slot print_timing: id 14 | task 295 | prompt eval time = 1550.45 ms / 940 tokens ( 1.65 ms per token, 606.27 tokens per second) 0.49.063.773 I slot print_timing: id 14 | task 295 | eval time = 13834.88 ms / 256 tokens ( 54.25 ms per token, 18.43 tokens per second) 0.49.063.773 I slot print_timing: id 14 | task 295 | total time = 15385.33 ms / 1196 tokens 0.49.063.775 I slot print_timing: id 14 | task 295 | graphs reused = 509 0.49.063.810 I slot release: id 14 | task 295 | stop processing: n_tokens = 1237, truncated = 0 0.49.064.029 I slot print_timing: id 15 | task 298 | n_gen = 255, tg = 18.48 t/s, tg_3s = 0.91 t/s 0.49.701.939 I slot print_timing: id 15 | task 298 | prompt eval time = 1581.64 ms / 1035 tokens ( 1.53 ms per token, 654.38 tokens per second) 0.49.701.943 I slot print_timing: id 15 | task 298 | eval time = 14385.41 ms / 256 tokens ( 56.41 ms per token, 17.73 tokens per second) 0.49.701.943 I slot print_timing: id 15 | task 298 | total time = 15967.05 ms / 1291 tokens 0.49.701.944 I slot print_timing: id 15 | task 298 | graphs reused = 509 0.49.702.004 I slot release: id 15 | task 298 | stop processing: n_tokens = 1332, truncated = 0 0.49.702.023 I slot get_availabl: id 12 | task -1 | selected slot by LRU, t_last = 680048403707 0.49.702.146 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 0.49.846.412 I slot launch_slot_: id 12 | task 570 | processing task, is_child = 0 0.49.846.502 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 0.49.987.513 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 831.349 MiB) 0.50.131.954 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 675.908 MiB) 0.50.302.500 I slot get_availabl: id 13 | task -1 | selected slot by LRU, t_last = 680048403989 0.50.302.674 I slot launch_slot_: id 13 | task 571 | processing task, is_child = 0 0.50.302.819 I slot get_availabl: id 14 | task -1 | selected slot by LRU, t_last = 680048404249 0.50.302.914 I slot launch_slot_: id 14 | task 572 | processing task, is_child = 0 0.50.302.993 I slot get_availabl: id 15 | task -1 | selected slot by LRU, t_last = 680049042443 0.50.303.087 I slot launch_slot_: id 15 | task 573 | processing task, is_child = 0 0.55.437.402 I slot print_timing: id 0 | task 552 | n_gen = 100, tg = 11.62 t/s, tg_3s = 11.73 t/s 0.55.437.607 I slot print_timing: id 1 | task 553 | n_gen = 100, tg = 11.62 t/s, tg_3s = 11.73 t/s 0.55.437.812 I slot print_timing: id 2 | task 554 | n_gen = 100, tg = 11.62 t/s, tg_3s = 11.73 t/s 0.55.469.982 I slot print_timing: id 3 | task 555 | n_gen = 100, tg = 12.49 t/s, tg_3s = 12.62 t/s 0.55.502.478 I slot print_timing: id 4 | task 558 | n_gen = 100, tg = 15.37 t/s, tg_3s = 15.53 t/s 0.55.502.684 I slot print_timing: id 5 | task 559 | n_gen = 100, tg = 15.37 t/s, tg_3s = 15.53 t/s 0.55.502.888 I slot print_timing: id 6 | task 560 | n_gen = 100, tg = 15.37 t/s, tg_3s = 15.53 t/s 0.55.535.102 I slot print_timing: id 7 | task 561 | n_gen = 100, tg = 16.97 t/s, tg_3s = 17.14 t/s 0.55.567.342 I slot print_timing: id 8 | task 564 | n_gen = 100, tg = 22.73 t/s, tg_3s = 22.96 t/s 0.55.567.564 I slot print_timing: id 9 | task 565 | n_gen = 100, tg = 22.73 t/s, tg_3s = 22.96 t/s 0.55.599.818 I slot print_timing: id 10 | task 566 | n_gen = 100, tg = 26.96 t/s, tg_3s = 27.23 t/s 0.55.600.040 I slot print_timing: id 11 | task 567 | n_gen = 100, tg = 26.96 t/s, tg_3s = 27.23 t/s 0.55.632.228 I slot print_timing: id 12 | task 570 | n_gen = 100, tg = 30.35 t/s, tg_3s = 30.66 t/s 0.55.632.437 I slot print_timing: id 13 | task 571 | n_gen = 100, tg = 30.35 t/s, tg_3s = 30.66 t/s 0.55.664.623 I slot print_timing: id 14 | task 572 | n_gen = 100, tg = 31.21 t/s, tg_3s = 31.53 t/s 0.55.664.832 I slot print_timing: id 15 | task 573 | n_gen = 100, tg = 31.22 t/s, tg_3s = 31.53 t/s 0.58.447.381 I slot print_timing: id 0 | task 552 | n_gen = 194, tg = 16.73 t/s, tg_3s = 31.23 t/s 0.58.447.590 I slot print_timing: id 1 | task 553 | n_gen = 194, tg = 16.73 t/s, tg_3s = 31.23 t/s 0.58.447.822 I slot print_timing: id 2 | task 554 | n_gen = 194, tg = 16.73 t/s, tg_3s = 31.23 t/s 0.58.479.882 I slot print_timing: id 3 | task 555 | n_gen = 194, tg = 17.65 t/s, tg_3s = 31.23 t/s 0.58.512.225 I slot print_timing: id 4 | task 558 | n_gen = 194, tg = 20.42 t/s, tg_3s = 31.23 t/s 0.58.512.454 I slot print_timing: id 5 | task 559 | n_gen = 194, tg = 20.42 t/s, tg_3s = 31.23 t/s 0.58.512.660 I slot print_timing: id 6 | task 560 | n_gen = 194, tg = 20.42 t/s, tg_3s = 31.23 t/s 0.58.544.832 I slot print_timing: id 7 | task 561 | n_gen = 194, tg = 21.82 t/s, tg_3s = 31.23 t/s 0.58.576.978 I slot print_timing: id 8 | task 564 | n_gen = 194, tg = 26.21 t/s, tg_3s = 31.23 t/s 0.58.577.186 I slot print_timing: id 9 | task 565 | n_gen = 194, tg = 26.21 t/s, tg_3s = 31.23 t/s 0.58.609.352 I slot print_timing: id 10 | task 566 | n_gen = 194, tg = 28.89 t/s, tg_3s = 31.23 t/s 0.58.609.568 I slot print_timing: id 11 | task 567 | n_gen = 194, tg = 28.89 t/s, tg_3s = 31.23 t/s 0.58.641.680 I slot print_timing: id 12 | task 570 | n_gen = 194, tg = 30.78 t/s, tg_3s = 31.23 t/s 0.58.641.895 I slot print_timing: id 13 | task 571 | n_gen = 194, tg = 30.78 t/s, tg_3s = 31.23 t/s 0.58.673.987 I slot print_timing: id 14 | task 572 | n_gen = 194, tg = 31.22 t/s, tg_3s = 31.24 t/s 0.58.674.201 I slot print_timing: id 15 | task 573 | n_gen = 194, tg = 31.23 t/s, tg_3s = 31.24 t/s 1.00.445.860 I slot print_timing: id 0 | task 552 | prompt eval time = 3011.57 ms / 1034 tokens ( 2.91 ms per token, 343.34 tokens per second) 1.00.445.863 I slot print_timing: id 0 | task 552 | eval time = 13531.72 ms / 256 tokens ( 53.07 ms per token, 18.84 tokens per second) 1.00.445.864 I slot print_timing: id 0 | task 552 | total time = 16543.29 ms / 1290 tokens 1.00.445.865 I slot print_timing: id 0 | task 552 | graphs reused = 756 1.00.445.920 I slot release: id 0 | task 552 | stop processing: n_tokens = 1331, truncated = 0 1.00.446.136 I slot print_timing: id 1 | task 553 | prompt eval time = 2959.16 ms / 1034 tokens ( 2.86 ms per token, 349.42 tokens per second) 1.00.446.137 I slot print_timing: id 1 | task 553 | eval time = 13531.69 ms / 256 tokens ( 53.07 ms per token, 18.84 tokens per second) 1.00.446.138 I slot print_timing: id 1 | task 553 | total time = 16490.85 ms / 1290 tokens 1.00.446.138 I slot print_timing: id 1 | task 553 | graphs reused = 756 1.00.446.180 I slot release: id 1 | task 553 | stop processing: n_tokens = 1331, truncated = 0 1.00.446.403 I slot print_timing: id 2 | task 554 | prompt eval time = 2905.60 ms / 938 tokens ( 3.10 ms per token, 322.82 tokens per second) 1.00.446.404 I slot print_timing: id 2 | task 554 | eval time = 13531.66 ms / 256 tokens ( 53.07 ms per token, 18.84 tokens per second) 1.00.446.404 I slot print_timing: id 2 | task 554 | total time = 16437.26 ms / 1194 tokens 1.00.446.405 I slot print_timing: id 2 | task 554 | graphs reused = 756 1.00.446.438 I slot release: id 2 | task 554 | stop processing: n_tokens = 1235, truncated = 0 1.00.478.534 I slot print_timing: id 3 | task 555 | prompt eval time = 3482.63 ms / 1034 tokens ( 3.37 ms per token, 296.90 tokens per second) 1.00.478.536 I slot print_timing: id 3 | task 555 | eval time = 12932.88 ms / 256 tokens ( 50.72 ms per token, 19.72 tokens per second) 1.00.478.536 I slot print_timing: id 3 | task 555 | total time = 16415.51 ms / 1290 tokens 1.00.478.537 I slot print_timing: id 3 | task 555 | graphs reused = 756 1.00.478.579 I slot release: id 3 | task 555 | stop processing: n_tokens = 1331, truncated = 0 1.00.481.052 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 680059786361 1.00.481.185 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 672.407 MiB) 1.00.626.073 I slot launch_slot_: id 0 | task 827 | processing task, is_child = 0 1.00.626.195 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 676.659 MiB) 1.00.768.812 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 831.349 MiB) 1.00.913.898 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 1.01.084.875 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 680059786620 1.01.085.068 I slot launch_slot_: id 1 | task 828 | processing task, is_child = 0 1.01.085.229 I slot get_availabl: id 2 | task -1 | selected slot by LRU, t_last = 680059786877 1.01.085.340 I slot launch_slot_: id 2 | task 829 | processing task, is_child = 0 1.01.085.419 I slot get_availabl: id 3 | task -1 | selected slot by LRU, t_last = 680059819019 1.01.085.522 I slot launch_slot_: id 3 | task 830 | processing task, is_child = 0 1.01.843.917 I slot print_timing: id 4 | task 558 | prompt eval time = 2965.38 ms / 1034 tokens ( 2.87 ms per token, 348.69 tokens per second) 1.01.843.921 I slot print_timing: id 4 | task 558 | eval time = 12781.40 ms / 256 tokens ( 50.12 ms per token, 19.95 tokens per second) 1.01.843.922 I slot print_timing: id 4 | task 558 | total time = 15746.78 ms / 1290 tokens 1.01.843.923 I slot print_timing: id 4 | task 558 | graphs reused = 757 1.01.843.980 I slot release: id 4 | task 558 | stop processing: n_tokens = 1331, truncated = 0 1.01.844.230 I slot print_timing: id 5 | task 559 | prompt eval time = 2913.83 ms / 1036 tokens ( 2.81 ms per token, 355.55 tokens per second) 1.01.844.232 I slot print_timing: id 5 | task 559 | eval time = 12781.48 ms / 256 tokens ( 50.12 ms per token, 19.95 tokens per second) 1.01.844.233 I slot print_timing: id 5 | task 559 | total time = 15695.31 ms / 1292 tokens 1.01.844.234 I slot print_timing: id 5 | task 559 | graphs reused = 757 1.01.844.280 I slot release: id 5 | task 559 | stop processing: n_tokens = 1333, truncated = 0 1.01.844.514 I slot print_timing: id 6 | task 560 | prompt eval time = 2860.70 ms / 1034 tokens ( 2.77 ms per token, 361.45 tokens per second) 1.01.844.515 I slot print_timing: id 6 | task 560 | eval time = 12781.50 ms / 256 tokens ( 50.12 ms per token, 19.95 tokens per second) 1.01.844.516 I slot print_timing: id 6 | task 560 | total time = 15642.21 ms / 1290 tokens 1.01.844.516 I slot print_timing: id 6 | task 560 | graphs reused = 757 1.01.844.559 I slot release: id 6 | task 560 | stop processing: n_tokens = 1331, truncated = 0 1.01.844.766 I slot print_timing: id 7 | task 561 | n_gen = 255, tg = 20.92 t/s, tg_3s = 18.49 t/s 1.01.844.964 I slot print_timing: id 8 | task 564 | n_gen = 254, tg = 23.80 t/s, tg_3s = 18.36 t/s 1.01.845.160 I slot print_timing: id 9 | task 565 | n_gen = 254, tg = 23.80 t/s, tg_3s = 18.36 t/s 1.01.845.354 I slot print_timing: id 10 | task 566 | n_gen = 253, tg = 25.41 t/s, tg_3s = 18.23 t/s 1.01.845.547 I slot print_timing: id 11 | task 567 | n_gen = 253, tg = 25.41 t/s, tg_3s = 18.23 t/s 1.01.845.753 I slot print_timing: id 12 | task 570 | n_gen = 252, tg = 26.49 t/s, tg_3s = 18.10 t/s 1.01.845.957 I slot print_timing: id 13 | task 571 | n_gen = 252, tg = 26.49 t/s, tg_3s = 18.10 t/s 1.01.846.163 I slot print_timing: id 14 | task 572 | n_gen = 251, tg = 26.73 t/s, tg_3s = 17.97 t/s 1.01.846.367 I slot print_timing: id 15 | task 573 | n_gen = 251, tg = 26.73 t/s, tg_3s = 17.97 t/s 1.02.539.648 I slot print_timing: id 7 | task 561 | prompt eval time = 3445.82 ms / 1034 tokens ( 3.33 ms per token, 300.07 tokens per second) 1.02.539.651 I slot print_timing: id 7 | task 561 | eval time = 12837.88 ms / 256 tokens ( 50.34 ms per token, 19.86 tokens per second) 1.02.539.652 I slot print_timing: id 7 | task 561 | total time = 16283.70 ms / 1290 tokens 1.02.539.653 I slot print_timing: id 7 | task 561 | graphs reused = 758 1.02.539.701 I slot release: id 7 | task 561 | stop processing: n_tokens = 1331, truncated = 0 1.02.541.481 I slot get_availabl: id 4 | task -1 | selected slot by LRU, t_last = 680061184420 1.02.541.614 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 675.783 MiB) 1.02.685.820 I slot launch_slot_: id 4 | task 833 | processing task, is_child = 0 1.02.685.933 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 1.02.829.308 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 831.349 MiB) 1.02.980.193 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 675.721 MiB) 1.03.126.275 I slot get_availabl: id 5 | task -1 | selected slot by LRU, t_last = 680061184720 1.03.126.459 I slot launch_slot_: id 5 | task 834 | processing task, is_child = 0 1.03.126.611 I slot get_availabl: id 6 | task -1 | selected slot by LRU, t_last = 680061184998 1.03.126.714 I slot launch_slot_: id 6 | task 835 | processing task, is_child = 0 1.03.126.790 I slot get_availabl: id 7 | task -1 | selected slot by LRU, t_last = 680061880141 1.03.126.889 I slot launch_slot_: id 7 | task 836 | processing task, is_child = 0 1.04.073.166 I slot print_timing: id 8 | task 564 | prompt eval time = 2917.43 ms / 1034 tokens ( 2.82 ms per token, 354.42 tokens per second) 1.04.073.169 I slot print_timing: id 8 | task 564 | eval time = 12860.57 ms / 256 tokens ( 50.43 ms per token, 19.83 tokens per second) 1.04.073.170 I slot print_timing: id 8 | task 564 | total time = 15778.01 ms / 1290 tokens 1.04.073.171 I slot print_timing: id 8 | task 564 | graphs reused = 759 1.04.073.234 I slot release: id 8 | task 564 | stop processing: n_tokens = 1331, truncated = 0 1.04.073.446 I slot print_timing: id 9 | task 565 | prompt eval time = 2866.52 ms / 1034 tokens ( 2.77 ms per token, 360.72 tokens per second) 1.04.073.447 I slot print_timing: id 9 | task 565 | eval time = 12860.60 ms / 256 tokens ( 50.43 ms per token, 19.83 tokens per second) 1.04.073.447 I slot print_timing: id 9 | task 565 | total time = 15727.12 ms / 1290 tokens 1.04.073.448 I slot print_timing: id 9 | task 565 | graphs reused = 759 1.04.073.485 I slot release: id 9 | task 565 | stop processing: n_tokens = 1331, truncated = 0 1.04.835.720 I slot print_timing: id 10 | task 566 | prompt eval time = 3528.90 ms / 1034 tokens ( 3.41 ms per token, 293.01 tokens per second) 1.04.835.724 I slot print_timing: id 10 | task 566 | eval time = 12907.92 ms / 256 tokens ( 50.62 ms per token, 19.76 tokens per second) 1.04.835.724 I slot print_timing: id 10 | task 566 | total time = 16436.82 ms / 1290 tokens 1.04.835.725 I slot print_timing: id 10 | task 566 | graphs reused = 760 1.04.835.771 I slot release: id 10 | task 566 | stop processing: n_tokens = 1331, truncated = 0 1.04.835.971 I slot print_timing: id 11 | task 567 | prompt eval time = 2758.36 ms / 1034 tokens ( 2.67 ms per token, 374.86 tokens per second) 1.04.835.973 I slot print_timing: id 11 | task 567 | eval time = 12907.92 ms / 256 tokens ( 50.62 ms per token, 19.76 tokens per second) 1.04.835.973 I slot print_timing: id 11 | task 567 | total time = 15666.27 ms / 1290 tokens 1.04.835.974 I slot print_timing: id 11 | task 567 | graphs reused = 760 1.04.836.020 I slot release: id 11 | task 567 | stop processing: n_tokens = 1331, truncated = 0 1.04.836.828 I slot get_availabl: id 8 | task -1 | selected slot by LRU, t_last = 680063413674 1.04.836.942 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 675.408 MiB) 1.04.981.999 I slot launch_slot_: id 8 | task 839 | processing task, is_child = 0 1.04.982.108 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 675.846 MiB) 1.05.125.452 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 831.412 MiB) 1.05.274.459 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 1.05.421.032 I slot get_availabl: id 9 | task -1 | selected slot by LRU, t_last = 680063413925 1.05.421.220 I slot launch_slot_: id 9 | task 840 | processing task, is_child = 0 1.05.421.377 I slot get_availabl: id 10 | task -1 | selected slot by LRU, t_last = 680064176210 1.05.421.482 I slot launch_slot_: id 10 | task 841 | processing task, is_child = 0 1.05.421.567 I slot get_availabl: id 11 | task -1 | selected slot by LRU, t_last = 680064176460 1.05.421.677 I slot launch_slot_: id 11 | task 842 | processing task, is_child = 0 1.06.355.271 I slot print_timing: id 12 | task 570 | prompt eval time = 1929.55 ms / 1034 tokens ( 1.87 ms per token, 535.88 tokens per second) 1.06.355.274 I slot print_timing: id 12 | task 570 | eval time = 13984.77 ms / 256 tokens ( 54.84 ms per token, 18.23 tokens per second) 1.06.355.275 I slot print_timing: id 12 | task 570 | total time = 15914.32 ms / 1290 tokens 1.06.355.276 I slot print_timing: id 12 | task 570 | graphs reused = 760 1.06.355.332 I slot release: id 12 | task 570 | stop processing: n_tokens = 1331, truncated = 0 1.06.355.543 I slot print_timing: id 13 | task 571 | prompt eval time = 1878.61 ms / 891 tokens ( 2.11 ms per token, 474.29 tokens per second) 1.06.355.545 I slot print_timing: id 13 | task 571 | eval time = 13984.78 ms / 256 tokens ( 54.84 ms per token, 18.23 tokens per second) 1.06.355.545 I slot print_timing: id 13 | task 571 | total time = 15863.39 ms / 1147 tokens 1.06.355.546 I slot print_timing: id 13 | task 571 | graphs reused = 760 1.06.355.591 I slot release: id 13 | task 571 | stop processing: n_tokens = 1188, truncated = 0 1.06.355.800 I slot print_timing: id 14 | task 572 | n_gen = 255, tg = 18.32 t/s, tg_3s = 0.89 t/s 1.06.356.007 I slot print_timing: id 15 | task 573 | n_gen = 255, tg = 18.32 t/s, tg_3s = 0.89 t/s 1.07.120.390 I slot print_timing: id 14 | task 572 | prompt eval time = 1948.33 ms / 1034 tokens ( 1.88 ms per token, 530.71 tokens per second) 1.07.120.393 I slot print_timing: id 14 | task 572 | eval time = 14627.56 ms / 256 tokens ( 57.36 ms per token, 17.43 tokens per second) 1.07.120.393 I slot print_timing: id 14 | task 572 | total time = 16575.89 ms / 1290 tokens 1.07.120.394 I slot print_timing: id 14 | task 572 | graphs reused = 761 1.07.120.449 I slot release: id 14 | task 572 | stop processing: n_tokens = 1331, truncated = 0 1.07.120.667 I slot print_timing: id 15 | task 573 | prompt eval time = 1140.10 ms / 888 tokens ( 1.28 ms per token, 778.88 tokens per second) 1.07.120.668 I slot print_timing: id 15 | task 573 | eval time = 14627.21 ms / 256 tokens ( 57.36 ms per token, 17.43 tokens per second) 1.07.120.668 I slot print_timing: id 15 | task 573 | total time = 15767.31 ms / 1144 tokens 1.07.120.669 I slot print_timing: id 15 | task 573 | graphs reused = 761 1.07.120.712 I slot release: id 15 | task 573 | stop processing: n_tokens = 1185, truncated = 0 1.07.120.726 I slot get_availabl: id 12 | task -1 | selected slot by LRU, t_last = 680065695771 1.07.120.834 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 1.07.265.905 I slot launch_slot_: id 12 | task 845 | processing task, is_child = 0 1.07.266.018 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 675.721 MiB) 1.07.407.113 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 831.349 MiB) 1.07.685.862 I slot get_availabl: id 13 | task -1 | selected slot by LRU, t_last = 680065696031 1.07.686.042 I slot launch_slot_: id 13 | task 846 | processing task, is_child = 0 1.07.686.194 I slot get_availabl: id 14 | task -1 | selected slot by LRU, t_last = 680066460889 1.07.686.297 I slot launch_slot_: id 14 | task 847 | processing task, is_child = 0 1.07.686.372 I slot get_availabl: id 15 | task -1 | selected slot by LRU, t_last = 680066461152 1.07.686.469 I slot launch_slot_: id 15 | task 848 | processing task, is_child = 0 1.12.639.706 I slot print_timing: id 0 | task 827 | n_gen = 100, tg = 11.56 t/s, tg_3s = 11.67 t/s 1.12.639.910 I slot print_timing: id 1 | task 828 | n_gen = 100, tg = 11.56 t/s, tg_3s = 11.67 t/s 1.12.640.122 I slot print_timing: id 2 | task 829 | n_gen = 100, tg = 11.56 t/s, tg_3s = 11.67 t/s 1.12.672.329 I slot print_timing: id 3 | task 830 | n_gen = 100, tg = 12.63 t/s, tg_3s = 12.76 t/s 1.12.704.517 I slot print_timing: id 4 | task 833 | n_gen = 100, tg = 15.59 t/s, tg_3s = 15.75 t/s 1.12.704.735 I slot print_timing: id 5 | task 834 | n_gen = 100, tg = 15.59 t/s, tg_3s = 15.75 t/s 1.12.704.940 I slot print_timing: id 6 | task 835 | n_gen = 100, tg = 15.59 t/s, tg_3s = 15.75 t/s 1.12.737.063 I slot print_timing: id 7 | task 836 | n_gen = 100, tg = 17.63 t/s, tg_3s = 17.80 t/s 1.12.769.181 I slot print_timing: id 8 | task 839 | n_gen = 100, tg = 23.99 t/s, tg_3s = 24.23 t/s 1.12.769.394 I slot print_timing: id 9 | task 840 | n_gen = 100, tg = 23.99 t/s, tg_3s = 24.23 t/s 1.12.769.601 I slot print_timing: id 10 | task 841 | n_gen = 100, tg = 23.99 t/s, tg_3s = 24.23 t/s 1.12.801.719 I slot print_timing: id 11 | task 842 | n_gen = 100, tg = 29.05 t/s, tg_3s = 29.34 t/s 1.12.834.071 I slot print_timing: id 12 | task 845 | n_gen = 100, tg = 30.70 t/s, tg_3s = 31.01 t/s 1.12.834.285 I slot print_timing: id 13 | task 846 | n_gen = 100, tg = 30.70 t/s, tg_3s = 31.01 t/s 1.12.834.491 I slot print_timing: id 14 | task 847 | n_gen = 100, tg = 30.70 t/s, tg_3s = 31.01 t/s 1.12.866.612 I slot print_timing: id 15 | task 848 | n_gen = 100, tg = 31.23 t/s, tg_3s = 31.55 t/s 1.15.644.834 I slot print_timing: id 0 | task 827 | n_gen = 194, tg = 16.68 t/s, tg_3s = 31.28 t/s 1.15.645.036 I slot print_timing: id 1 | task 828 | n_gen = 194, tg = 16.68 t/s, tg_3s = 31.28 t/s 1.15.645.243 I slot print_timing: id 2 | task 829 | n_gen = 194, tg = 16.68 t/s, tg_3s = 31.28 t/s 1.15.677.372 I slot print_timing: id 3 | task 830 | n_gen = 194, tg = 17.80 t/s, tg_3s = 31.28 t/s 1.15.709.805 I slot print_timing: id 4 | task 833 | n_gen = 194, tg = 20.63 t/s, tg_3s = 31.28 t/s 1.15.710.018 I slot print_timing: id 5 | task 834 | n_gen = 194, tg = 20.63 t/s, tg_3s = 31.28 t/s 1.15.710.220 I slot print_timing: id 6 | task 835 | n_gen = 194, tg = 20.63 t/s, tg_3s = 31.28 t/s 1.15.742.290 I slot print_timing: id 7 | task 836 | n_gen = 194, tg = 22.38 t/s, tg_3s = 31.28 t/s 1.15.774.433 I slot print_timing: id 8 | task 839 | n_gen = 194, tg = 27.06 t/s, tg_3s = 31.28 t/s 1.15.774.646 I slot print_timing: id 9 | task 840 | n_gen = 194, tg = 27.06 t/s, tg_3s = 31.28 t/s 1.15.774.850 I slot print_timing: id 10 | task 841 | n_gen = 194, tg = 27.06 t/s, tg_3s = 31.28 t/s 1.15.807.130 I slot print_timing: id 11 | task 842 | n_gen = 194, tg = 30.09 t/s, tg_3s = 31.28 t/s 1.15.839.313 I slot print_timing: id 12 | task 845 | n_gen = 194, tg = 30.98 t/s, tg_3s = 31.28 t/s 1.15.839.534 I slot print_timing: id 13 | task 846 | n_gen = 194, tg = 30.98 t/s, tg_3s = 31.28 t/s 1.15.839.753 I slot print_timing: id 14 | task 847 | n_gen = 194, tg = 30.98 t/s, tg_3s = 31.28 t/s 1.15.871.902 I slot print_timing: id 15 | task 848 | n_gen = 194, tg = 31.26 t/s, tg_3s = 31.28 t/s 1.17.637.285 I slot print_timing: id 0 | task 827 | prompt eval time = 2986.84 ms / 920 tokens ( 3.25 ms per token, 308.02 tokens per second) 1.17.637.289 I slot print_timing: id 0 | task 827 | eval time = 13564.89 ms / 256 tokens ( 53.20 ms per token, 18.80 tokens per second) 1.17.637.289 I slot print_timing: id 0 | task 827 | total time = 16551.73 ms / 1176 tokens 1.17.637.291 I slot print_timing: id 0 | task 827 | graphs reused = 1009 1.17.637.342 I slot release: id 0 | task 827 | stop processing: n_tokens = 1217, truncated = 0 1.17.637.539 I slot print_timing: id 1 | task 828 | prompt eval time = 2934.26 ms / 1034 tokens ( 2.84 ms per token, 352.39 tokens per second) 1.17.637.540 I slot print_timing: id 1 | task 828 | eval time = 13564.89 ms / 256 tokens ( 53.20 ms per token, 18.80 tokens per second) 1.17.637.541 I slot print_timing: id 1 | task 828 | total time = 16499.14 ms / 1290 tokens 1.17.637.541 I slot print_timing: id 1 | task 828 | graphs reused = 1009 1.17.637.589 I slot release: id 1 | task 828 | stop processing: n_tokens = 1331, truncated = 0 1.17.637.803 I slot print_timing: id 2 | task 829 | prompt eval time = 2881.22 ms / 934 tokens ( 3.08 ms per token, 324.17 tokens per second) 1.17.637.804 I slot print_timing: id 2 | task 829 | eval time = 13564.84 ms / 256 tokens ( 53.20 ms per token, 18.80 tokens per second) 1.17.637.804 I slot print_timing: id 2 | task 829 | total time = 16446.07 ms / 1190 tokens 1.17.637.805 I slot print_timing: id 2 | task 829 | graphs reused = 1009 1.17.637.840 I slot release: id 2 | task 829 | stop processing: n_tokens = 1231, truncated = 0 1.17.669.614 I slot print_timing: id 3 | task 830 | prompt eval time = 3589.67 ms / 1030 tokens ( 3.49 ms per token, 286.93 tokens per second) 1.17.669.617 I slot print_timing: id 3 | task 830 | eval time = 12834.09 ms / 256 tokens ( 50.33 ms per token, 19.87 tokens per second) 1.17.669.618 I slot print_timing: id 3 | task 830 | total time = 16423.76 ms / 1286 tokens 1.17.669.618 I slot print_timing: id 3 | task 830 | graphs reused = 1009 1.17.669.678 I slot release: id 3 | task 830 | stop processing: n_tokens = 1327, truncated = 0 1.17.672.116 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 680076977781 1.17.672.245 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 1.17.817.052 I slot launch_slot_: id 0 | task 1102 | processing task, is_child = 0 1.17.817.166 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.848 MiB) 1.17.960.807 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 1.18.106.174 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 1.18.116.855 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 1.18.289.027 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 680076978028 1.18.289.211 I slot launch_slot_: id 1 | task 1103 | processing task, is_child = 0 1.18.289.367 I slot get_availabl: id 2 | task -1 | selected slot by LRU, t_last = 680076978279 1.18.289.475 I slot launch_slot_: id 2 | task 1104 | processing task, is_child = 0 1.18.289.553 I slot get_availabl: id 3 | task -1 | selected slot by LRU, t_last = 680077010118 1.18.289.658 I slot launch_slot_: id 3 | task 1105 | processing task, is_child = 0 1.19.062.294 I slot print_timing: id 4 | task 833 | prompt eval time = 3088.60 ms / 1029 tokens ( 3.00 ms per token, 333.16 tokens per second) 1.19.062.298 I slot print_timing: id 4 | task 833 | eval time = 12707.83 ms / 256 tokens ( 49.83 ms per token, 20.07 tokens per second) 1.19.062.298 I slot print_timing: id 4 | task 833 | total time = 15796.43 ms / 1285 tokens 1.19.062.299 I slot print_timing: id 4 | task 833 | graphs reused = 1010 1.19.062.364 I slot release: id 4 | task 833 | stop processing: n_tokens = 1326, truncated = 0 1.19.062.604 I slot print_timing: id 5 | task 834 | prompt eval time = 3036.94 ms / 1034 tokens ( 2.94 ms per token, 340.47 tokens per second) 1.19.062.605 I slot print_timing: id 5 | task 834 | eval time = 12707.84 ms / 256 tokens ( 49.83 ms per token, 20.07 tokens per second) 1.19.062.605 I slot print_timing: id 5 | task 834 | total time = 15744.78 ms / 1290 tokens 1.19.062.606 I slot print_timing: id 5 | task 834 | graphs reused = 1010 1.19.062.646 I slot release: id 5 | task 834 | stop processing: n_tokens = 1331, truncated = 0 1.19.062.869 I slot print_timing: id 6 | task 835 | prompt eval time = 2984.08 ms / 953 tokens ( 3.13 ms per token, 319.36 tokens per second) 1.19.062.871 I slot print_timing: id 6 | task 835 | eval time = 12707.80 ms / 256 tokens ( 49.83 ms per token, 20.07 tokens per second) 1.19.062.871 I slot print_timing: id 6 | task 835 | total time = 15691.88 ms / 1209 tokens 1.19.062.872 I slot print_timing: id 6 | task 835 | graphs reused = 1010 1.19.062.908 I slot release: id 6 | task 835 | stop processing: n_tokens = 1250, truncated = 0 1.19.063.137 I slot print_timing: id 7 | task 836 | n_gen = 255, tg = 21.27 t/s, tg_3s = 18.37 t/s 1.19.063.367 I slot print_timing: id 8 | task 839 | n_gen = 254, tg = 24.28 t/s, tg_3s = 18.24 t/s 1.19.063.603 I slot print_timing: id 9 | task 840 | n_gen = 254, tg = 24.28 t/s, tg_3s = 18.24 t/s 1.19.063.825 I slot print_timing: id 10 | task 841 | n_gen = 254, tg = 24.28 t/s, tg_3s = 18.24 t/s 1.19.064.023 I slot print_timing: id 11 | task 842 | n_gen = 253, tg = 26.06 t/s, tg_3s = 18.12 t/s 1.19.064.226 I slot print_timing: id 12 | task 845 | n_gen = 252, tg = 26.55 t/s, tg_3s = 17.98 t/s 1.19.064.425 I slot print_timing: id 13 | task 846 | n_gen = 252, tg = 26.55 t/s, tg_3s = 17.99 t/s 1.19.064.633 I slot print_timing: id 14 | task 847 | n_gen = 252, tg = 26.55 t/s, tg_3s = 17.99 t/s 1.19.064.839 I slot print_timing: id 15 | task 848 | n_gen = 251, tg = 26.69 t/s, tg_3s = 17.85 t/s 1.19.758.683 I slot print_timing: id 7 | task 836 | prompt eval time = 3695.62 ms / 926 tokens ( 3.99 ms per token, 250.57 tokens per second) 1.19.758.685 I slot print_timing: id 7 | task 836 | eval time = 12638.46 ms / 256 tokens ( 49.56 ms per token, 20.18 tokens per second) 1.19.758.686 I slot print_timing: id 7 | task 836 | total time = 16334.08 ms / 1182 tokens 1.19.758.687 I slot print_timing: id 7 | task 836 | graphs reused = 1011 1.19.758.738 I slot release: id 7 | task 836 | stop processing: n_tokens = 1223, truncated = 0 1.19.760.553 I slot get_availabl: id 4 | task -1 | selected slot by LRU, t_last = 680078402804 1.19.760.682 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 1.19.905.426 I slot launch_slot_: id 4 | task 1108 | processing task, is_child = 0 1.19.905.537 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 1.20.049.764 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 1.20.192.019 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 1.20.361.836 I slot get_availabl: id 5 | task -1 | selected slot by LRU, t_last = 680078403085 1.20.362.029 I slot launch_slot_: id 5 | task 1109 | processing task, is_child = 0 1.20.362.184 I slot get_availabl: id 6 | task -1 | selected slot by LRU, t_last = 680078403348 1.20.362.302 I slot launch_slot_: id 6 | task 1110 | processing task, is_child = 0 1.20.362.380 I slot get_availabl: id 7 | task -1 | selected slot by LRU, t_last = 680079099178 1.20.362.486 I slot launch_slot_: id 7 | task 1111 | processing task, is_child = 0 1.21.327.658 I slot print_timing: id 8 | task 839 | prompt eval time = 3081.50 ms / 1018 tokens ( 3.03 ms per token, 330.36 tokens per second) 1.21.327.662 I slot print_timing: id 8 | task 839 | eval time = 12684.85 ms / 256 tokens ( 49.74 ms per token, 20.10 tokens per second) 1.21.327.662 I slot print_timing: id 8 | task 839 | total time = 15766.35 ms / 1274 tokens 1.21.327.664 I slot print_timing: id 8 | task 839 | graphs reused = 1012 1.21.327.725 I slot release: id 8 | task 839 | stop processing: n_tokens = 1315, truncated = 0 1.21.327.971 I slot print_timing: id 9 | task 840 | prompt eval time = 3029.93 ms / 1034 tokens ( 2.93 ms per token, 341.26 tokens per second) 1.21.327.973 I slot print_timing: id 9 | task 840 | eval time = 12684.91 ms / 256 tokens ( 49.74 ms per token, 20.10 tokens per second) 1.21.327.973 I slot print_timing: id 9 | task 840 | total time = 15714.85 ms / 1290 tokens 1.21.327.974 I slot print_timing: id 9 | task 840 | graphs reused = 1012 1.21.328.014 I slot release: id 9 | task 840 | stop processing: n_tokens = 1331, truncated = 0 1.21.328.240 I slot print_timing: id 10 | task 841 | prompt eval time = 2977.22 ms / 932 tokens ( 3.19 ms per token, 313.04 tokens per second) 1.21.328.241 I slot print_timing: id 10 | task 841 | eval time = 12684.92 ms / 256 tokens ( 49.74 ms per token, 20.10 tokens per second) 1.21.328.242 I slot print_timing: id 10 | task 841 | total time = 15662.15 ms / 1188 tokens 1.21.328.242 I slot print_timing: id 10 | task 841 | graphs reused = 1012 1.21.328.276 I slot release: id 10 | task 841 | stop processing: n_tokens = 1229, truncated = 0 1.22.098.336 I slot print_timing: id 11 | task 842 | prompt eval time = 3673.98 ms / 897 tokens ( 4.10 ms per token, 244.15 tokens per second) 1.22.098.339 I slot print_timing: id 11 | task 842 | eval time = 12705.08 ms / 256 tokens ( 49.82 ms per token, 20.07 tokens per second) 1.22.098.340 I slot print_timing: id 11 | task 842 | total time = 16379.06 ms / 1153 tokens 1.22.098.341 I slot print_timing: id 11 | task 842 | graphs reused = 1013 1.22.098.388 I slot release: id 11 | task 842 | stop processing: n_tokens = 1194, truncated = 0 1.22.098.594 I slot print_timing: id 12 | task 845 | n_gen = 255, tg = 20.34 t/s, tg_3s = 0.99 t/s 1.22.098.793 I slot print_timing: id 13 | task 846 | n_gen = 255, tg = 20.34 t/s, tg_3s = 0.99 t/s 1.22.098.987 I slot print_timing: id 14 | task 847 | n_gen = 255, tg = 20.34 t/s, tg_3s = 0.99 t/s 1.22.099.185 I slot print_timing: id 15 | task 848 | n_gen = 254, tg = 20.40 t/s, tg_3s = 0.99 t/s 1.22.099.194 I slot get_availabl: id 8 | task -1 | selected slot by LRU, t_last = 680080668164 1.22.099.301 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 672.782 MiB) 1.22.244.521 I slot launch_slot_: id 8 | task 1114 | processing task, is_child = 0 1.22.244.630 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 1.22.389.046 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 672.595 MiB) 1.22.531.123 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 674.595 MiB) 1.22.700.316 I slot get_availabl: id 9 | task -1 | selected slot by LRU, t_last = 680080668453 1.22.700.500 I slot launch_slot_: id 9 | task 1115 | processing task, is_child = 0 1.22.700.647 I slot get_availabl: id 10 | task -1 | selected slot by LRU, t_last = 680080668715 1.22.700.751 I slot launch_slot_: id 10 | task 1116 | processing task, is_child = 0 1.22.700.824 I slot get_availabl: id 11 | task -1 | selected slot by LRU, t_last = 680081438827 1.22.700.930 I slot launch_slot_: id 11 | task 1117 | processing task, is_child = 0 1.23.661.219 I slot print_timing: id 12 | task 845 | prompt eval time = 1784.56 ms / 1014 tokens ( 1.76 ms per token, 568.21 tokens per second) 1.23.661.223 I slot print_timing: id 12 | task 845 | eval time = 14052.15 ms / 256 tokens ( 55.11 ms per token, 18.15 tokens per second) 1.23.661.223 I slot print_timing: id 12 | task 845 | total time = 15836.70 ms / 1270 tokens 1.23.661.224 I slot print_timing: id 12 | task 845 | graphs reused = 1014 1.23.661.285 I slot release: id 12 | task 845 | stop processing: n_tokens = 1311, truncated = 0 1.23.661.487 I slot print_timing: id 13 | task 846 | prompt eval time = 1733.41 ms / 963 tokens ( 1.80 ms per token, 555.55 tokens per second) 1.23.661.488 I slot print_timing: id 13 | task 846 | eval time = 14052.16 ms / 256 tokens ( 55.11 ms per token, 18.15 tokens per second) 1.23.661.489 I slot print_timing: id 13 | task 846 | total time = 15785.57 ms / 1219 tokens 1.23.661.489 I slot print_timing: id 13 | task 846 | graphs reused = 1014 1.23.661.541 I slot release: id 13 | task 846 | stop processing: n_tokens = 1260, truncated = 0 1.23.661.748 I slot print_timing: id 14 | task 847 | prompt eval time = 1681.28 ms / 1033 tokens ( 1.63 ms per token, 614.41 tokens per second) 1.23.661.750 I slot print_timing: id 14 | task 847 | eval time = 14052.15 ms / 256 tokens ( 55.11 ms per token, 18.15 tokens per second) 1.23.661.750 I slot print_timing: id 14 | task 847 | total time = 15733.43 ms / 1289 tokens 1.23.661.751 I slot print_timing: id 14 | task 847 | graphs reused = 1014 1.23.661.790 I slot release: id 14 | task 847 | stop processing: n_tokens = 1330, truncated = 0 1.24.424.557 I slot print_timing: id 15 | task 848 | prompt eval time = 1715.02 ms / 980 tokens ( 1.75 ms per token, 571.42 tokens per second) 1.24.424.560 I slot print_timing: id 15 | task 848 | eval time = 14727.47 ms / 256 tokens ( 57.75 ms per token, 17.31 tokens per second) 1.24.424.561 I slot print_timing: id 15 | task 848 | total time = 16442.49 ms / 1236 tokens 1.24.424.563 I slot print_timing: id 15 | task 848 | graphs reused = 1015 1.24.424.624 I slot release: id 15 | task 848 | stop processing: n_tokens = 1277, truncated = 0 1.24.424.638 I slot get_availabl: id 12 | task -1 | selected slot by LRU, t_last = 680083001724 1.24.424.748 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 1.24.568.422 I slot launch_slot_: id 12 | task 1120 | processing task, is_child = 0 1.24.568.527 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 675.471 MiB) 1.24.714.831 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 831.099 MiB) 1.24.862.876 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.410 MiB) 1.25.032.450 I slot get_availabl: id 13 | task -1 | selected slot by LRU, t_last = 680083001980 1.25.032.637 I slot launch_slot_: id 13 | task 1121 | processing task, is_child = 0 1.25.032.797 I slot get_availabl: id 14 | task -1 | selected slot by LRU, t_last = 680083002230 1.25.032.905 I slot launch_slot_: id 14 | task 1122 | processing task, is_child = 0 1.25.032.981 I slot get_availabl: id 15 | task -1 | selected slot by LRU, t_last = 680083765063 1.25.033.092 I slot launch_slot_: id 15 | task 1123 | processing task, is_child = 0 1.29.962.276 I slot print_timing: id 0 | task 1102 | n_gen = 100, tg = 11.46 t/s, tg_3s = 11.58 t/s 1.29.962.484 I slot print_timing: id 1 | task 1103 | n_gen = 100, tg = 11.46 t/s, tg_3s = 11.58 t/s 1.29.962.693 I slot print_timing: id 2 | task 1104 | n_gen = 100, tg = 11.46 t/s, tg_3s = 11.58 t/s 1.29.994.937 I slot print_timing: id 3 | task 1105 | n_gen = 100, tg = 12.54 t/s, tg_3s = 12.66 t/s 1.30.027.143 I slot print_timing: id 4 | task 1108 | n_gen = 100, tg = 15.55 t/s, tg_3s = 15.71 t/s 1.30.027.351 I slot print_timing: id 5 | task 1109 | n_gen = 100, tg = 15.55 t/s, tg_3s = 15.71 t/s 1.30.027.564 I slot print_timing: id 6 | task 1110 | n_gen = 100, tg = 15.55 t/s, tg_3s = 15.71 t/s 1.30.059.746 I slot print_timing: id 7 | task 1111 | n_gen = 100, tg = 17.57 t/s, tg_3s = 17.74 t/s 1.30.091.957 I slot print_timing: id 8 | task 1114 | n_gen = 100, tg = 23.94 t/s, tg_3s = 24.19 t/s 1.30.092.167 I slot print_timing: id 9 | task 1115 | n_gen = 100, tg = 23.94 t/s, tg_3s = 24.19 t/s 1.30.092.377 I slot print_timing: id 10 | task 1116 | n_gen = 100, tg = 23.94 t/s, tg_3s = 24.19 t/s 1.30.124.642 I slot print_timing: id 11 | task 1117 | n_gen = 100, tg = 28.98 t/s, tg_3s = 29.28 t/s 1.30.157.082 I slot print_timing: id 12 | task 1120 | n_gen = 100, tg = 30.63 t/s, tg_3s = 30.94 t/s 1.30.157.291 I slot print_timing: id 13 | task 1121 | n_gen = 100, tg = 30.63 t/s, tg_3s = 30.94 t/s 1.30.157.500 I slot print_timing: id 14 | task 1122 | n_gen = 100, tg = 30.63 t/s, tg_3s = 30.94 t/s 1.30.189.667 I slot print_timing: id 15 | task 1123 | n_gen = 100, tg = 31.17 t/s, tg_3s = 31.48 t/s 1.32.969.753 I slot print_timing: id 0 | task 1102 | n_gen = 194, tg = 16.58 t/s, tg_3s = 31.26 t/s 1.32.969.962 I slot print_timing: id 1 | task 1103 | n_gen = 194, tg = 16.58 t/s, tg_3s = 31.26 t/s 1.32.970.172 I slot print_timing: id 2 | task 1104 | n_gen = 194, tg = 16.58 t/s, tg_3s = 31.26 t/s 1.33.002.363 I slot print_timing: id 3 | task 1105 | n_gen = 194, tg = 17.70 t/s, tg_3s = 31.26 t/s 1.33.034.487 I slot print_timing: id 4 | task 1108 | n_gen = 194, tg = 20.59 t/s, tg_3s = 31.26 t/s 1.33.034.699 I slot print_timing: id 5 | task 1109 | n_gen = 194, tg = 20.59 t/s, tg_3s = 31.26 t/s 1.33.034.904 I slot print_timing: id 6 | task 1110 | n_gen = 194, tg = 20.59 t/s, tg_3s = 31.26 t/s 1.33.066.995 I slot print_timing: id 7 | task 1111 | n_gen = 194, tg = 22.33 t/s, tg_3s = 31.26 t/s 1.33.099.320 I slot print_timing: id 8 | task 1114 | n_gen = 194, tg = 27.02 t/s, tg_3s = 31.26 t/s 1.33.099.533 I slot print_timing: id 9 | task 1115 | n_gen = 194, tg = 27.02 t/s, tg_3s = 31.26 t/s 1.33.099.742 I slot print_timing: id 10 | task 1116 | n_gen = 194, tg = 27.02 t/s, tg_3s = 31.26 t/s 1.33.131.851 I slot print_timing: id 11 | task 1117 | n_gen = 194, tg = 30.05 t/s, tg_3s = 31.26 t/s 1.33.164.144 I slot print_timing: id 12 | task 1120 | n_gen = 194, tg = 30.93 t/s, tg_3s = 31.26 t/s 1.33.164.361 I slot print_timing: id 13 | task 1121 | n_gen = 194, tg = 30.93 t/s, tg_3s = 31.26 t/s 1.33.164.572 I slot print_timing: id 14 | task 1122 | n_gen = 194, tg = 30.94 t/s, tg_3s = 31.26 t/s 1.33.196.958 I slot print_timing: id 15 | task 1123 | n_gen = 194, tg = 31.21 t/s, tg_3s = 31.26 t/s 1.34.968.209 I slot print_timing: id 0 | task 1102 | prompt eval time = 3037.15 ms / 1034 tokens ( 2.94 ms per token, 340.45 tokens per second) 1.34.968.212 I slot print_timing: id 0 | task 1102 | eval time = 13641.37 ms / 256 tokens ( 53.50 ms per token, 18.69 tokens per second) 1.34.968.212 I slot print_timing: id 0 | task 1102 | total time = 16678.52 ms / 1290 tokens 1.34.968.213 I slot print_timing: id 0 | task 1102 | graphs reused = 1262 1.34.968.261 I slot release: id 0 | task 1102 | stop processing: n_tokens = 1331, truncated = 0 1.34.968.473 I slot print_timing: id 1 | task 1103 | prompt eval time = 2984.12 ms / 946 tokens ( 3.15 ms per token, 317.01 tokens per second) 1.34.968.475 I slot print_timing: id 1 | task 1103 | eval time = 13641.34 ms / 256 tokens ( 53.50 ms per token, 18.69 tokens per second) 1.34.968.475 I slot print_timing: id 1 | task 1103 | total time = 16625.45 ms / 1202 tokens 1.34.968.475 I slot print_timing: id 1 | task 1103 | graphs reused = 1262 1.34.968.510 I slot release: id 1 | task 1103 | stop processing: n_tokens = 1243, truncated = 0 1.34.968.729 I slot print_timing: id 2 | task 1104 | prompt eval time = 2931.07 ms / 1034 tokens ( 2.83 ms per token, 352.77 tokens per second) 1.34.968.730 I slot print_timing: id 2 | task 1104 | eval time = 13641.32 ms / 256 tokens ( 53.50 ms per token, 18.69 tokens per second) 1.34.968.731 I slot print_timing: id 2 | task 1104 | total time = 16572.39 ms / 1290 tokens 1.34.968.731 I slot print_timing: id 2 | task 1104 | graphs reused = 1262 1.34.968.766 I slot release: id 2 | task 1104 | stop processing: n_tokens = 1331, truncated = 0 1.35.000.621 I slot print_timing: id 3 | task 1105 | prompt eval time = 3647.74 ms / 966 tokens ( 3.78 ms per token, 264.82 tokens per second) 1.35.000.624 I slot print_timing: id 3 | task 1105 | eval time = 12902.51 ms / 256 tokens ( 50.60 ms per token, 19.76 tokens per second) 1.35.000.625 I slot print_timing: id 3 | task 1105 | total time = 16550.25 ms / 1222 tokens 1.35.000.626 I slot print_timing: id 3 | task 1105 | graphs reused = 1262 1.35.000.672 I slot release: id 3 | task 1105 | stop processing: n_tokens = 1263, truncated = 0 1.35.003.156 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 680094308699 1.35.003.278 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 1.35.150.958 I slot launch_slot_: id 0 | task 1377 | processing task, is_child = 0 1.35.151.057 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 676.659 MiB) 1.35.295.251 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 824.597 MiB) 1.35.440.641 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 680.723 MiB) 1.35.611.483 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 680094308950 1.35.611.646 I slot launch_slot_: id 1 | task 1378 | processing task, is_child = 0 1.35.611.807 I slot get_availabl: id 2 | task -1 | selected slot by LRU, t_last = 680094309205 1.35.611.905 I slot launch_slot_: id 2 | task 1379 | processing task, is_child = 0 1.35.611.975 I slot get_availabl: id 3 | task -1 | selected slot by LRU, t_last = 680094341111 1.35.612.077 I slot launch_slot_: id 3 | task 1380 | processing task, is_child = 0 1.36.399.417 I slot print_timing: id 4 | task 1108 | prompt eval time = 3159.28 ms / 1035 tokens ( 3.05 ms per token, 327.61 tokens per second) 1.36.399.420 I slot print_timing: id 4 | task 1108 | eval time = 12738.98 ms / 256 tokens ( 49.96 ms per token, 20.02 tokens per second) 1.36.399.421 I slot print_timing: id 4 | task 1108 | total time = 15898.26 ms / 1291 tokens 1.36.399.422 I slot print_timing: id 4 | task 1108 | graphs reused = 1263 1.36.399.471 I slot release: id 4 | task 1108 | stop processing: n_tokens = 1332, truncated = 0 1.36.399.693 I slot print_timing: id 5 | task 1109 | prompt eval time = 3107.59 ms / 949 tokens ( 3.27 ms per token, 305.38 tokens per second) 1.36.399.694 I slot print_timing: id 5 | task 1109 | eval time = 12739.01 ms / 256 tokens ( 49.96 ms per token, 20.02 tokens per second) 1.36.399.695 I slot print_timing: id 5 | task 1109 | total time = 15846.60 ms / 1205 tokens 1.36.399.695 I slot print_timing: id 5 | task 1109 | graphs reused = 1263 1.36.399.730 I slot release: id 5 | task 1109 | stop processing: n_tokens = 1246, truncated = 0 1.36.399.943 I slot print_timing: id 6 | task 1110 | prompt eval time = 3054.11 ms / 1034 tokens ( 2.95 ms per token, 338.56 tokens per second) 1.36.399.944 I slot print_timing: id 6 | task 1110 | eval time = 12739.01 ms / 256 tokens ( 49.96 ms per token, 20.02 tokens per second) 1.36.399.944 I slot print_timing: id 6 | task 1110 | total time = 15793.12 ms / 1290 tokens 1.36.399.945 I slot print_timing: id 6 | task 1110 | graphs reused = 1263 1.36.399.984 I slot release: id 6 | task 1110 | stop processing: n_tokens = 1331, truncated = 0 1.36.400.197 I slot print_timing: id 7 | task 1111 | n_gen = 255, tg = 21.21 t/s, tg_3s = 18.30 t/s 1.36.400.411 I slot print_timing: id 8 | task 1114 | n_gen = 254, tg = 24.23 t/s, tg_3s = 18.18 t/s 1.36.400.628 I slot print_timing: id 9 | task 1115 | n_gen = 254, tg = 24.23 t/s, tg_3s = 18.18 t/s 1.36.400.833 I slot print_timing: id 10 | task 1116 | n_gen = 254, tg = 24.23 t/s, tg_3s = 18.18 t/s 1.36.401.050 I slot print_timing: id 11 | task 1117 | n_gen = 253, tg = 26.00 t/s, tg_3s = 18.05 t/s 1.36.401.258 I slot print_timing: id 12 | task 1120 | n_gen = 252, tg = 26.49 t/s, tg_3s = 17.92 t/s 1.36.401.465 I slot print_timing: id 13 | task 1121 | n_gen = 252, tg = 26.49 t/s, tg_3s = 17.92 t/s 1.36.401.678 I slot print_timing: id 14 | task 1122 | n_gen = 252, tg = 26.49 t/s, tg_3s = 17.92 t/s 1.36.401.886 I slot print_timing: id 15 | task 1123 | n_gen = 251, tg = 26.63 t/s, tg_3s = 17.79 t/s 1.37.095.083 I slot print_timing: id 7 | task 1111 | prompt eval time = 3764.00 ms / 1035 tokens ( 3.64 ms per token, 274.97 tokens per second) 1.37.095.086 I slot print_timing: id 7 | task 1111 | eval time = 12670.76 ms / 256 tokens ( 49.69 ms per token, 20.13 tokens per second) 1.37.095.087 I slot print_timing: id 7 | task 1111 | total time = 16434.77 ms / 1291 tokens 1.37.095.088 I slot print_timing: id 7 | task 1111 | graphs reused = 1264 1.37.095.140 I slot release: id 7 | task 1111 | stop processing: n_tokens = 1332, truncated = 0 1.37.096.843 I slot get_availabl: id 4 | task -1 | selected slot by LRU, t_last = 680095739910 1.37.096.959 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 1.37.240.462 I slot launch_slot_: id 4 | task 1383 | processing task, is_child = 0 1.37.240.549 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 675.346 MiB) 1.37.380.134 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 822.783 MiB) 1.37.525.252 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 680.472 MiB) 1.37.692.971 I slot get_availabl: id 5 | task -1 | selected slot by LRU, t_last = 680095740170 1.37.693.133 I slot launch_slot_: id 5 | task 1384 | processing task, is_child = 0 1.37.693.277 I slot get_availabl: id 6 | task -1 | selected slot by LRU, t_last = 680095740423 1.37.693.384 I slot launch_slot_: id 6 | task 1385 | processing task, is_child = 0 1.37.693.455 I slot get_availabl: id 7 | task -1 | selected slot by LRU, t_last = 680096435580 1.37.693.557 I slot launch_slot_: id 7 | task 1386 | processing task, is_child = 0 1.38.652.642 I slot print_timing: id 8 | task 1114 | prompt eval time = 3118.15 ms / 967 tokens ( 3.22 ms per token, 310.12 tokens per second) 1.38.652.646 I slot print_timing: id 8 | task 1114 | eval time = 12695.30 ms / 256 tokens ( 49.79 ms per token, 20.09 tokens per second) 1.38.652.646 I slot print_timing: id 8 | task 1114 | total time = 15813.44 ms / 1223 tokens 1.38.652.647 I slot print_timing: id 8 | task 1114 | graphs reused = 1265 1.38.652.694 I slot release: id 8 | task 1114 | stop processing: n_tokens = 1264, truncated = 0 1.38.652.912 I slot print_timing: id 9 | task 1115 | prompt eval time = 3067.26 ms / 1034 tokens ( 2.97 ms per token, 337.11 tokens per second) 1.38.652.914 I slot print_timing: id 9 | task 1115 | eval time = 12695.31 ms / 256 tokens ( 49.79 ms per token, 20.09 tokens per second) 1.38.652.914 I slot print_timing: id 9 | task 1115 | total time = 15762.57 ms / 1290 tokens 1.38.652.915 I slot print_timing: id 9 | task 1115 | graphs reused = 1265 1.38.652.948 I slot release: id 9 | task 1115 | stop processing: n_tokens = 1331, truncated = 0 1.38.653.158 I slot print_timing: id 10 | task 1116 | prompt eval time = 3015.03 ms / 1034 tokens ( 2.92 ms per token, 342.95 tokens per second) 1.38.653.159 I slot print_timing: id 10 | task 1116 | eval time = 12695.30 ms / 256 tokens ( 49.79 ms per token, 20.09 tokens per second) 1.38.653.160 I slot print_timing: id 10 | task 1116 | total time = 15710.32 ms / 1290 tokens 1.38.653.160 I slot print_timing: id 10 | task 1116 | graphs reused = 1265 1.38.653.204 I slot release: id 10 | task 1116 | stop processing: n_tokens = 1331, truncated = 0 1.39.421.712 I slot print_timing: id 11 | task 1117 | prompt eval time = 3713.64 ms / 939 tokens ( 3.95 ms per token, 252.85 tokens per second) 1.39.421.715 I slot print_timing: id 11 | task 1117 | eval time = 12712.75 ms / 256 tokens ( 49.85 ms per token, 20.06 tokens per second) 1.39.421.716 I slot print_timing: id 11 | task 1117 | total time = 16426.40 ms / 1195 tokens 1.39.421.717 I slot print_timing: id 11 | task 1117 | graphs reused = 1266 1.39.421.759 I slot release: id 11 | task 1117 | stop processing: n_tokens = 1236, truncated = 0 1.39.421.982 I slot print_timing: id 12 | task 1120 | n_gen = 255, tg = 20.33 t/s, tg_3s = 0.99 t/s 1.39.422.195 I slot print_timing: id 13 | task 1121 | n_gen = 255, tg = 20.33 t/s, tg_3s = 0.99 t/s 1.39.422.403 I slot print_timing: id 14 | task 1122 | n_gen = 255, tg = 20.33 t/s, tg_3s = 0.99 t/s 1.39.422.619 I slot print_timing: id 15 | task 1123 | n_gen = 254, tg = 20.39 t/s, tg_3s = 0.99 t/s 1.39.422.628 I slot get_availabl: id 8 | task -1 | selected slot by LRU, t_last = 680097993133 1.39.422.742 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 677.284 MiB) 1.39.567.766 I slot launch_slot_: id 8 | task 1389 | processing task, is_child = 0 1.39.567.851 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.660 MiB) 1.39.711.126 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 827.973 MiB) 1.39.855.584 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 1.40.023.766 I slot get_availabl: id 9 | task -1 | selected slot by LRU, t_last = 680097993387 1.40.023.938 I slot launch_slot_: id 9 | task 1390 | processing task, is_child = 0 1.40.024.078 I slot get_availabl: id 10 | task -1 | selected slot by LRU, t_last = 680097993644 1.40.024.177 I slot launch_slot_: id 10 | task 1391 | processing task, is_child = 0 1.40.024.255 I slot get_availabl: id 11 | task -1 | selected slot by LRU, t_last = 680098762198 1.40.024.348 I slot launch_slot_: id 11 | task 1392 | processing task, is_child = 0 1.40.994.413 I slot print_timing: id 12 | task 1120 | prompt eval time = 1753.89 ms / 1034 tokens ( 1.70 ms per token, 589.55 tokens per second) 1.40.994.417 I slot print_timing: id 12 | task 1120 | eval time = 14069.21 ms / 256 tokens ( 55.17 ms per token, 18.12 tokens per second) 1.40.994.417 I slot print_timing: id 12 | task 1120 | total time = 15823.10 ms / 1290 tokens 1.40.994.419 I slot print_timing: id 12 | task 1120 | graphs reused = 1267 1.40.994.469 I slot release: id 12 | task 1120 | stop processing: n_tokens = 1331, truncated = 0 1.40.994.701 I slot print_timing: id 13 | task 1121 | prompt eval time = 1702.85 ms / 939 tokens ( 1.81 ms per token, 551.43 tokens per second) 1.40.994.702 I slot print_timing: id 13 | task 1121 | eval time = 14069.23 ms / 256 tokens ( 55.17 ms per token, 18.12 tokens per second) 1.40.994.703 I slot print_timing: id 13 | task 1121 | total time = 15772.07 ms / 1195 tokens 1.40.994.703 I slot print_timing: id 13 | task 1121 | graphs reused = 1267 1.40.994.741 I slot release: id 13 | task 1121 | stop processing: n_tokens = 1236, truncated = 0 1.40.994.956 I slot print_timing: id 14 | task 1122 | prompt eval time = 1650.54 ms / 1034 tokens ( 1.60 ms per token, 626.46 tokens per second) 1.40.994.958 I slot print_timing: id 14 | task 1122 | eval time = 14069.21 ms / 256 tokens ( 55.17 ms per token, 18.12 tokens per second) 1.40.994.958 I slot print_timing: id 14 | task 1122 | total time = 15719.75 ms / 1290 tokens 1.40.994.958 I slot print_timing: id 14 | task 1122 | graphs reused = 1267 1.40.994.996 I slot release: id 14 | task 1122 | stop processing: n_tokens = 1331, truncated = 0 1.40.995.234 I slot print_timing: id 7 | task 1386 | prompt processing, n_tokens = 929, progress = 1.00, t = 3.01 s / 309.06 tokens per second 1.41.760.684 I slot print_timing: id 15 | task 1123 | prompt eval time = 1684.44 ms / 883 tokens ( 1.91 ms per token, 524.21 tokens per second) 1.41.760.689 I slot print_timing: id 15 | task 1123 | eval time = 14747.30 ms / 256 tokens ( 57.83 ms per token, 17.29 tokens per second) 1.41.760.689 I slot print_timing: id 15 | task 1123 | total time = 16431.74 ms / 1139 tokens 1.41.760.690 I slot print_timing: id 15 | task 1123 | graphs reused = 1268 1.41.760.741 I slot release: id 15 | task 1123 | stop processing: n_tokens = 1180, truncated = 0 1.41.760.759 I slot get_availabl: id 12 | task -1 | selected slot by LRU, t_last = 680100334908 1.41.760.871 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 676.221 MiB) 1.41.904.127 I slot launch_slot_: id 12 | task 1395 | processing task, is_child = 0 1.41.904.222 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 1.42.046.927 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 827.097 MiB) 1.42.192.093 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.785 MiB) 1.42.358.932 I slot get_availabl: id 13 | task -1 | selected slot by LRU, t_last = 680100335180 1.42.359.109 I slot launch_slot_: id 13 | task 1396 | processing task, is_child = 0 1.42.359.275 I slot get_availabl: id 14 | task -1 | selected slot by LRU, t_last = 680100335435 1.42.359.388 I slot launch_slot_: id 14 | task 1397 | processing task, is_child = 0 1.42.359.457 I slot get_availabl: id 15 | task -1 | selected slot by LRU, t_last = 680101101180 1.42.359.554 I slot launch_slot_: id 15 | task 1398 | processing task, is_child = 0 1.47.331.389 I slot print_timing: id 0 | task 1377 | n_gen = 100, tg = 11.41 t/s, tg_3s = 11.52 t/s 1.47.331.601 I slot print_timing: id 1 | task 1378 | n_gen = 100, tg = 11.41 t/s, tg_3s = 11.52 t/s 1.47.331.814 I slot print_timing: id 2 | task 1379 | n_gen = 100, tg = 11.41 t/s, tg_3s = 11.52 t/s 1.47.364.053 I slot print_timing: id 3 | task 1380 | n_gen = 100, tg = 12.46 t/s, tg_3s = 12.59 t/s 1.47.396.259 I slot print_timing: id 4 | task 1383 | n_gen = 100, tg = 15.46 t/s, tg_3s = 15.62 t/s 1.47.396.470 I slot print_timing: id 5 | task 1384 | n_gen = 100, tg = 15.46 t/s, tg_3s = 15.62 t/s 1.47.396.687 I slot print_timing: id 6 | task 1385 | n_gen = 100, tg = 15.46 t/s, tg_3s = 15.62 t/s 1.47.428.937 I slot print_timing: id 7 | task 1386 | n_gen = 100, tg = 17.46 t/s, tg_3s = 17.64 t/s 1.47.461.207 I slot print_timing: id 8 | task 1389 | n_gen = 100, tg = 23.89 t/s, tg_3s = 24.13 t/s 1.47.461.425 I slot print_timing: id 9 | task 1390 | n_gen = 100, tg = 23.89 t/s, tg_3s = 24.13 t/s 1.47.461.643 I slot print_timing: id 10 | task 1391 | n_gen = 100, tg = 23.89 t/s, tg_3s = 24.13 t/s 1.47.493.934 I slot print_timing: id 11 | task 1392 | n_gen = 100, tg = 28.89 t/s, tg_3s = 29.18 t/s 1.47.526.173 I slot print_timing: id 12 | task 1395 | n_gen = 100, tg = 30.52 t/s, tg_3s = 30.83 t/s 1.47.526.383 I slot print_timing: id 13 | task 1396 | n_gen = 100, tg = 30.52 t/s, tg_3s = 30.83 t/s 1.47.526.590 I slot print_timing: id 14 | task 1397 | n_gen = 100, tg = 30.53 t/s, tg_3s = 30.83 t/s 1.47.558.838 I slot print_timing: id 15 | task 1398 | n_gen = 100, tg = 31.07 t/s, tg_3s = 31.38 t/s 1.50.349.536 I slot print_timing: id 0 | task 1377 | n_gen = 194, tg = 16.50 t/s, tg_3s = 31.14 t/s 1.50.349.755 I slot print_timing: id 1 | task 1378 | n_gen = 194, tg = 16.50 t/s, tg_3s = 31.14 t/s 1.50.349.968 I slot print_timing: id 2 | task 1379 | n_gen = 194, tg = 16.50 t/s, tg_3s = 31.14 t/s 1.50.382.209 I slot print_timing: id 3 | task 1380 | n_gen = 194, tg = 17.61 t/s, tg_3s = 31.14 t/s 1.50.414.456 I slot print_timing: id 4 | task 1383 | n_gen = 194, tg = 20.49 t/s, tg_3s = 31.14 t/s 1.50.414.678 I slot print_timing: id 5 | task 1384 | n_gen = 194, tg = 20.49 t/s, tg_3s = 31.14 t/s 1.50.414.907 I slot print_timing: id 6 | task 1385 | n_gen = 194, tg = 20.49 t/s, tg_3s = 31.14 t/s 1.50.447.226 I slot print_timing: id 7 | task 1386 | n_gen = 194, tg = 22.22 t/s, tg_3s = 31.14 t/s 1.50.479.572 I slot print_timing: id 8 | task 1389 | n_gen = 194, tg = 26.94 t/s, tg_3s = 31.14 t/s 1.50.479.783 I slot print_timing: id 9 | task 1390 | n_gen = 194, tg = 26.94 t/s, tg_3s = 31.14 t/s 1.50.479.992 I slot print_timing: id 10 | task 1391 | n_gen = 194, tg = 26.94 t/s, tg_3s = 31.14 t/s 1.50.512.227 I slot print_timing: id 11 | task 1392 | n_gen = 194, tg = 29.94 t/s, tg_3s = 31.14 t/s 1.50.544.418 I slot print_timing: id 12 | task 1395 | n_gen = 194, tg = 30.82 t/s, tg_3s = 31.14 t/s 1.50.544.632 I slot print_timing: id 13 | task 1396 | n_gen = 194, tg = 30.82 t/s, tg_3s = 31.14 t/s 1.50.544.847 I slot print_timing: id 14 | task 1397 | n_gen = 194, tg = 30.82 t/s, tg_3s = 31.14 t/s 1.50.577.431 I slot print_timing: id 15 | task 1398 | n_gen = 194, tg = 31.10 t/s, tg_3s = 31.14 t/s 1.52.357.308 I slot print_timing: id 0 | task 1377 | prompt eval time = 3039.78 ms / 1031 tokens ( 2.95 ms per token, 339.17 tokens per second) 1.52.357.311 I slot print_timing: id 0 | task 1377 | eval time = 13705.42 ms / 256 tokens ( 53.75 ms per token, 18.61 tokens per second) 1.52.357.312 I slot print_timing: id 0 | task 1377 | total time = 16745.20 ms / 1287 tokens 1.52.357.313 I slot print_timing: id 0 | task 1377 | graphs reused = 1516 1.52.357.365 I slot release: id 0 | task 1377 | stop processing: n_tokens = 1328, truncated = 0 1.52.357.584 I slot print_timing: id 1 | task 1378 | prompt eval time = 2987.90 ms / 1035 tokens ( 2.89 ms per token, 346.40 tokens per second) 1.52.357.585 I slot print_timing: id 1 | task 1378 | eval time = 13705.42 ms / 256 tokens ( 53.75 ms per token, 18.61 tokens per second) 1.52.357.585 I slot print_timing: id 1 | task 1378 | total time = 16693.32 ms / 1291 tokens 1.52.357.586 I slot print_timing: id 1 | task 1378 | graphs reused = 1516 1.52.357.625 I slot release: id 1 | task 1378 | stop processing: n_tokens = 1332, truncated = 0 1.52.357.846 I slot print_timing: id 2 | task 1379 | prompt eval time = 2935.47 ms / 1034 tokens ( 2.84 ms per token, 352.24 tokens per second) 1.52.357.847 I slot print_timing: id 2 | task 1379 | eval time = 13705.43 ms / 256 tokens ( 53.75 ms per token, 18.61 tokens per second) 1.52.357.848 I slot print_timing: id 2 | task 1379 | total time = 16640.90 ms / 1290 tokens 1.52.357.848 I slot print_timing: id 2 | task 1379 | graphs reused = 1516 1.52.357.884 I slot release: id 2 | task 1379 | stop processing: n_tokens = 1331, truncated = 0 1.52.389.902 I slot print_timing: id 3 | task 1380 | prompt eval time = 3650.80 ms / 968 tokens ( 3.77 ms per token, 265.15 tokens per second) 1.52.389.905 I slot print_timing: id 3 | task 1380 | eval time = 12968.42 ms / 256 tokens ( 50.86 ms per token, 19.66 tokens per second) 1.52.389.906 I slot print_timing: id 3 | task 1380 | total time = 16619.22 ms / 1224 tokens 1.52.389.906 I slot print_timing: id 3 | task 1380 | graphs reused = 1516 1.52.389.949 I slot release: id 3 | task 1380 | stop processing: n_tokens = 1265, truncated = 0 1.52.392.464 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 680111697805 1.52.392.594 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 676.408 MiB) 1.52.538.603 I slot launch_slot_: id 0 | task 1652 | processing task, is_child = 0 1.52.538.697 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 1.52.684.350 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 831.412 MiB) 1.52.831.817 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 677.534 MiB) 1.53.002.522 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 680111698064 1.53.002.717 I slot launch_slot_: id 1 | task 1653 | processing task, is_child = 0 1.53.002.882 I slot get_availabl: id 2 | task -1 | selected slot by LRU, t_last = 680111698323 1.53.002.980 I slot launch_slot_: id 2 | task 1654 | processing task, is_child = 0 1.53.582.474 I slot print_timing: id 4 | task 1383 | prompt eval time = 3163.76 ms / 1036 tokens ( 3.05 ms per token, 327.46 tokens per second) 1.53.582.477 I slot print_timing: id 4 | task 1383 | eval time = 12588.78 ms / 256 tokens ( 49.37 ms per token, 20.26 tokens per second) 1.53.582.478 I slot print_timing: id 4 | task 1383 | total time = 15752.55 ms / 1292 tokens 1.53.582.479 I slot print_timing: id 4 | task 1383 | graphs reused = 1516 1.53.582.522 I slot release: id 4 | task 1383 | stop processing: n_tokens = 1333, truncated = 0 1.53.582.749 I slot print_timing: id 5 | task 1384 | prompt eval time = 3112.28 ms / 1019 tokens ( 3.05 ms per token, 327.41 tokens per second) 1.53.582.750 I slot print_timing: id 5 | task 1384 | eval time = 12588.81 ms / 256 tokens ( 49.37 ms per token, 20.26 tokens per second) 1.53.582.750 I slot print_timing: id 5 | task 1384 | total time = 15701.09 ms / 1275 tokens 1.53.582.751 I slot print_timing: id 5 | task 1384 | graphs reused = 1516 1.53.582.794 I slot release: id 5 | task 1384 | stop processing: n_tokens = 1316, truncated = 0 1.53.583.004 I slot print_timing: id 6 | task 1385 | prompt eval time = 3060.00 ms / 1034 tokens ( 2.96 ms per token, 337.91 tokens per second) 1.53.583.005 I slot print_timing: id 6 | task 1385 | eval time = 12588.81 ms / 256 tokens ( 49.37 ms per token, 20.26 tokens per second) 1.53.583.006 I slot print_timing: id 6 | task 1385 | total time = 15648.81 ms / 1290 tokens 1.53.583.006 I slot print_timing: id 6 | task 1385 | graphs reused = 1516 1.53.583.038 I slot release: id 6 | task 1385 | stop processing: n_tokens = 1331, truncated = 0 1.53.583.246 I slot print_timing: id 7 | task 1386 | n_gen = 255, tg = 21.48 t/s, tg_3s = 19.45 t/s 1.53.583.478 I slot print_timing: id 8 | task 1389 | n_gen = 254, tg = 24.64 t/s, tg_3s = 19.33 t/s 1.53.583.713 I slot print_timing: id 9 | task 1390 | n_gen = 254, tg = 24.64 t/s, tg_3s = 19.33 t/s 1.53.583.916 I slot print_timing: id 10 | task 1391 | n_gen = 254, tg = 24.64 t/s, tg_3s = 19.33 t/s 1.53.584.129 I slot print_timing: id 11 | task 1392 | n_gen = 253, tg = 26.48 t/s, tg_3s = 19.21 t/s 1.53.584.331 I slot print_timing: id 12 | task 1395 | n_gen = 252, tg = 26.98 t/s, tg_3s = 19.08 t/s 1.53.584.543 I slot print_timing: id 13 | task 1396 | n_gen = 252, tg = 26.99 t/s, tg_3s = 19.08 t/s 1.53.584.768 I slot print_timing: id 14 | task 1397 | n_gen = 252, tg = 26.99 t/s, tg_3s = 19.08 t/s 1.53.585.009 I slot print_timing: id 15 | task 1398 | n_gen = 251, tg = 27.14 t/s, tg_3s = 18.95 t/s 1.54.113.904 I slot print_timing: id 7 | task 1386 | prompt eval time = 3773.80 ms / 933 tokens ( 4.04 ms per token, 247.23 tokens per second) 1.54.113.908 I slot print_timing: id 7 | task 1386 | eval time = 12353.44 ms / 256 tokens ( 48.44 ms per token, 20.64 tokens per second) 1.54.113.909 I slot print_timing: id 7 | task 1386 | total time = 16127.24 ms / 1189 tokens 1.54.113.910 I slot print_timing: id 7 | task 1386 | graphs reused = 1516 1.54.113.952 I slot release: id 7 | task 1386 | stop processing: n_tokens = 1230, truncated = 0 1.54.270.003 I slot print_timing: id 8 | task 1389 | prompt eval time = 3155.02 ms / 1034 tokens ( 3.05 ms per token, 327.73 tokens per second) 1.54.270.007 I slot print_timing: id 8 | task 1389 | eval time = 10953.49 ms / 256 tokens ( 42.95 ms per token, 23.28 tokens per second) 1.54.270.007 I slot print_timing: id 8 | task 1389 | total time = 14108.51 ms / 1290 tokens 1.54.270.008 I slot print_timing: id 8 | task 1389 | graphs reused = 1516 1.54.270.039 I slot release: id 8 | task 1389 | stop processing: n_tokens = 1331, truncated = 0 1.54.270.256 I slot print_timing: id 9 | task 1390 | prompt eval time = 3104.03 ms / 1034 tokens ( 3.00 ms per token, 333.12 tokens per second) 1.54.270.257 I slot print_timing: id 9 | task 1390 | eval time = 10953.49 ms / 256 tokens ( 42.95 ms per token, 23.28 tokens per second) 1.54.270.257 I slot print_timing: id 9 | task 1390 | total time = 14057.51 ms / 1290 tokens 1.54.270.257 I slot print_timing: id 9 | task 1390 | graphs reused = 1516 1.54.270.303 I slot release: id 9 | task 1390 | stop processing: n_tokens = 1331, truncated = 0 1.54.270.507 I slot print_timing: id 10 | task 1391 | prompt eval time = 3051.81 ms / 932 tokens ( 3.27 ms per token, 305.39 tokens per second) 1.54.270.508 I slot print_timing: id 10 | task 1391 | eval time = 10953.47 ms / 256 tokens ( 42.95 ms per token, 23.28 tokens per second) 1.54.270.508 I slot print_timing: id 10 | task 1391 | total time = 14005.28 ms / 1188 tokens 1.54.270.508 I slot print_timing: id 10 | task 1391 | graphs reused = 1516 1.54.270.542 I slot release: id 10 | task 1391 | stop processing: n_tokens = 1229, truncated = 0 1.54.318.664 I slot print_timing: id 11 | task 1392 | prompt eval time = 3748.75 ms / 1035 tokens ( 3.62 ms per token, 276.09 tokens per second) 1.54.318.667 I slot print_timing: id 11 | task 1392 | eval time = 10251.60 ms / 256 tokens ( 40.20 ms per token, 24.87 tokens per second) 1.54.318.667 I slot print_timing: id 11 | task 1392 | total time = 14000.35 ms / 1291 tokens 1.54.318.668 I slot print_timing: id 11 | task 1392 | graphs reused = 1516 1.54.318.710 I slot release: id 11 | task 1392 | stop processing: n_tokens = 1332, truncated = 0 1.54.362.814 I slot print_timing: id 12 | task 1395 | prompt eval time = 1785.23 ms / 934 tokens ( 1.91 ms per token, 523.18 tokens per second) 1.54.362.817 I slot print_timing: id 12 | task 1395 | eval time = 10079.98 ms / 256 tokens ( 39.53 ms per token, 25.30 tokens per second) 1.54.362.817 I slot print_timing: id 12 | task 1395 | total time = 11865.22 ms / 1190 tokens 1.54.362.818 I slot print_timing: id 12 | task 1395 | graphs reused = 1516 1.54.362.857 I slot release: id 12 | task 1395 | stop processing: n_tokens = 1231, truncated = 0 1.54.363.061 I slot print_timing: id 13 | task 1396 | prompt eval time = 1733.87 ms / 1034 tokens ( 1.68 ms per token, 596.35 tokens per second) 1.54.363.062 I slot print_timing: id 13 | task 1396 | eval time = 10079.96 ms / 256 tokens ( 39.53 ms per token, 25.30 tokens per second) 1.54.363.062 I slot print_timing: id 13 | task 1396 | total time = 11813.83 ms / 1290 tokens 1.54.363.062 I slot print_timing: id 13 | task 1396 | graphs reused = 1516 1.54.363.096 I slot release: id 13 | task 1396 | stop processing: n_tokens = 1331, truncated = 0 1.54.363.298 I slot print_timing: id 14 | task 1397 | prompt eval time = 1681.43 ms / 966 tokens ( 1.74 ms per token, 574.51 tokens per second) 1.54.363.300 I slot print_timing: id 14 | task 1397 | eval time = 10079.90 ms / 256 tokens ( 39.53 ms per token, 25.30 tokens per second) 1.54.363.300 I slot print_timing: id 14 | task 1397 | total time = 11761.33 ms / 1222 tokens 1.54.363.300 I slot print_timing: id 14 | task 1397 | graphs reused = 1516 1.54.363.328 I slot release: id 14 | task 1397 | stop processing: n_tokens = 1263, truncated = 0 1.54.399.606 I slot print_timing: id 15 | task 1398 | prompt eval time = 1716.52 ms / 1034 tokens ( 1.66 ms per token, 602.38 tokens per second) 1.54.399.607 I slot print_timing: id 15 | task 1398 | eval time = 10027.37 ms / 256 tokens ( 39.32 ms per token, 25.43 tokens per second) 1.54.399.608 I slot print_timing: id 15 | task 1398 | total time = 11743.89 ms / 1290 tokens 1.54.399.608 I slot print_timing: id 15 | task 1398 | graphs reused = 1516 1.54.399.644 I slot release: id 15 | task 1398 | stop processing: n_tokens = 1331, truncated = 0 1.57.272.245 I slot print_timing: id 0 | task 1652 | n_gen = 154, tg = 50.95 t/s, tg_3s = 51.28 t/s 1.57.272.402 I slot print_timing: id 1 | task 1653 | n_gen = 154, tg = 50.95 t/s, tg_3s = 51.28 t/s 1.57.272.563 I slot print_timing: id 2 | task 1654 | n_gen = 154, tg = 50.95 t/s, tg_3s = 51.29 t/s 1.59.230.998 I slot print_timing: id 0 | task 1652 | prompt eval time = 1266.15 ms / 1034 tokens ( 1.22 ms per token, 816.65 tokens per second) 1.59.231.000 I slot print_timing: id 0 | task 1652 | eval time = 4961.78 ms / 256 tokens ( 19.46 ms per token, 51.39 tokens per second) 1.59.231.000 I slot print_timing: id 0 | task 1652 | total time = 6227.93 ms / 1290 tokens 1.59.231.001 I slot print_timing: id 0 | task 1652 | graphs reused = 1766 1.59.231.036 I slot release: id 0 | task 1652 | stop processing: n_tokens = 1331, truncated = 0 1.59.231.192 I slot print_timing: id 1 | task 1653 | prompt eval time = 1214.04 ms / 1033 tokens ( 1.18 ms per token, 850.88 tokens per second) 1.59.231.193 I slot print_timing: id 1 | task 1653 | eval time = 4961.69 ms / 256 tokens ( 19.46 ms per token, 51.39 tokens per second) 1.59.231.193 I slot print_timing: id 1 | task 1653 | total time = 6175.73 ms / 1289 tokens 1.59.231.193 I slot print_timing: id 1 | task 1653 | graphs reused = 1766 1.59.231.224 I slot release: id 1 | task 1653 | stop processing: n_tokens = 1330, truncated = 0 1.59.231.381 I slot print_timing: id 2 | task 1654 | prompt eval time = 1161.03 ms / 941 tokens ( 1.23 ms per token, 810.49 tokens per second) 1.59.231.382 I slot print_timing: id 2 | task 1654 | eval time = 4961.61 ms / 256 tokens ( 19.46 ms per token, 51.39 tokens per second) 1.59.231.382 I slot print_timing: id 2 | task 1654 | total time = 6122.63 ms / 1197 tokens 1.59.231.382 I slot print_timing: id 2 | task 1654 | graphs reused = 1766 1.59.231.404 I slot release: id 2 | task 1654 | stop processing: n_tokens = 1238, truncated = 0 3.15.482.326 I srv operator(): operator(): cleaning up before exit...