0.00.000.166 I srv llama_server: initializing ... 0.00.100.338 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.100.577 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) 0.00.102.180 I srv load_model: loading model '/workspace/models/gguf/Qwen3.8-27B-Q4_K_M.gguf' 0.01.819.200 I cmn init: llama threadpool init, n_threads = 12 0.01.894.761 I srv load_model: initializing, n_slots = 8, n_ctx_slot = 8192, kv_unified = 'false' 0.01.897.398 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.01.897.435 I srv llama_server: model loaded 0.01.897.439 I srv llama_server: listening on http://0.0.0.0:8001 0.06.814.503 I slot get_availabl: id 7 | task -1 | selected slot by LRU, t_last = -1 0.06.814.609 I slot launch_slot_: id 7 | task 0 | processing task, is_child = 0 0.06.842.810 I slot get_availabl: id 6 | task -1 | selected slot by LRU, t_last = -1 0.06.842.856 I slot launch_slot_: id 6 | task 1 | processing task, is_child = 0 0.06.842.857 I slot get_availabl: id 5 | task -1 | selected slot by LRU, t_last = -1 0.06.842.879 I slot launch_slot_: id 5 | task 3 | processing task, is_child = 0 0.06.842.880 I slot get_availabl: id 4 | task -1 | selected slot by LRU, t_last = -1 0.06.842.899 I slot launch_slot_: id 4 | task 4 | processing task, is_child = 0 0.11.243.651 I slot print_timing: id 7 | task 0 | n_gen = 131, tg = 43.05 t/s, tg_3s = 43.38 t/s 0.11.376.739 I slot print_timing: id 4 | task 4 | n_gen = 136, tg = 44.92 t/s, tg_3s = 45.26 t/s 0.11.376.899 I slot print_timing: id 5 | task 3 | n_gen = 136, tg = 44.93 t/s, tg_3s = 45.26 t/s 0.11.377.056 I slot print_timing: id 6 | task 1 | n_gen = 136, tg = 44.94 t/s, tg_3s = 45.27 t/s 0.14.037.464 I slot print_timing: id 7 | task 0 | prompt eval time = 1409.29 ms / 984 tokens ( 1.43 ms per token, 698.22 tokens per second) 0.14.037.466 I slot print_timing: id 7 | task 0 | eval time = 5813.53 ms / 256 tokens ( 22.80 ms per token, 43.86 tokens per second) 0.14.037.467 I slot print_timing: id 7 | task 0 | total time = 7222.82 ms / 1240 tokens 0.14.037.474 I slot print_timing: id 7 | task 0 | graphs reused = 254 0.14.037.521 I slot release: id 7 | task 0 | stop processing: n_tokens = 1239, truncated = 0 0.14.058.213 I slot print_timing: id 4 | task 4 | prompt eval time = 1528.75 ms / 1076 tokens ( 1.42 ms per token, 703.84 tokens per second) 0.14.058.216 I slot print_timing: id 4 | task 4 | eval time = 5686.55 ms / 256 tokens ( 22.30 ms per token, 44.84 tokens per second) 0.14.058.216 I slot print_timing: id 4 | task 4 | total time = 7215.30 ms / 1332 tokens 0.14.058.217 I slot print_timing: id 4 | task 4 | graphs reused = 254 0.14.058.251 I slot release: id 4 | task 4 | stop processing: n_tokens = 1331, truncated = 0 0.14.058.413 I slot print_timing: id 5 | task 3 | prompt eval time = 1529.42 ms / 969 tokens ( 1.58 ms per token, 633.57 tokens per second) 0.14.058.414 I slot print_timing: id 5 | task 3 | eval time = 5686.07 ms / 256 tokens ( 22.30 ms per token, 44.85 tokens per second) 0.14.058.415 I slot print_timing: id 5 | task 3 | total time = 7215.49 ms / 1225 tokens 0.14.058.415 I slot print_timing: id 5 | task 3 | graphs reused = 254 0.14.058.442 I slot release: id 5 | task 3 | stop processing: n_tokens = 1224, truncated = 0 0.14.058.604 I slot print_timing: id 6 | task 1 | prompt eval time = 1530.01 ms / 1076 tokens ( 1.42 ms per token, 703.26 tokens per second) 0.14.058.605 I slot print_timing: id 6 | task 1 | eval time = 5685.65 ms / 256 tokens ( 22.30 ms per token, 44.85 tokens per second) 0.14.058.606 I slot print_timing: id 6 | task 1 | total time = 7215.66 ms / 1332 tokens 0.14.058.606 I slot print_timing: id 6 | task 1 | graphs reused = 254 0.14.058.638 I slot release: id 6 | task 1 | stop processing: n_tokens = 1331, truncated = 0 0.14.058.644 I slot get_availabl: id 3 | task -1 | selected slot by LRU, t_last = -1 0.14.058.703 I slot launch_slot_: id 3 | task 264 | processing task, is_child = 0 0.14.619.605 I slot get_availabl: id 2 | task -1 | selected slot by LRU, t_last = -1 0.14.619.670 I slot launch_slot_: id 2 | task 265 | processing task, is_child = 0 0.14.619.851 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = -1 0.14.619.875 I slot launch_slot_: id 1 | task 266 | processing task, is_child = 0 0.14.620.038 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = -1 0.14.620.059 I slot launch_slot_: id 0 | task 267 | processing task, is_child = 0 0.19.093.780 I slot print_timing: id 0 | task 267 | n_gen = 134, tg = 44.12 t/s, tg_3s = 44.45 t/s 0.19.093.936 I slot print_timing: id 1 | task 266 | n_gen = 134, tg = 44.13 t/s, tg_3s = 44.46 t/s 0.19.094.091 I slot print_timing: id 2 | task 265 | n_gen = 134, tg = 44.13 t/s, tg_3s = 44.47 t/s 0.19.160.929 I slot print_timing: id 3 | task 264 | n_gen = 136, tg = 44.96 t/s, tg_3s = 45.29 t/s 0.21.813.900 I slot print_timing: id 0 | task 267 | prompt eval time = 1459.05 ms / 1076 tokens ( 1.36 ms per token, 737.47 tokens per second) 0.21.813.904 I slot print_timing: id 0 | task 267 | eval time = 5734.62 ms / 256 tokens ( 22.49 ms per token, 44.47 tokens per second) 0.21.813.905 I slot print_timing: id 0 | task 267 | total time = 7193.66 ms / 1332 tokens 0.21.813.906 I slot print_timing: id 0 | task 267 | graphs reused = 507 0.21.813.948 I slot release: id 0 | task 267 | stop processing: n_tokens = 1331, truncated = 0 0.21.814.108 I slot print_timing: id 1 | task 266 | prompt eval time = 1459.64 ms / 1076 tokens ( 1.36 ms per token, 737.17 tokens per second) 0.21.814.109 I slot print_timing: id 1 | task 266 | eval time = 5734.22 ms / 256 tokens ( 22.49 ms per token, 44.47 tokens per second) 0.21.814.109 I slot print_timing: id 1 | task 266 | total time = 7193.86 ms / 1332 tokens 0.21.814.110 I slot print_timing: id 1 | task 266 | graphs reused = 507 0.21.814.139 I slot release: id 1 | task 266 | stop processing: n_tokens = 1331, truncated = 0 0.21.814.294 I slot print_timing: id 2 | task 265 | prompt eval time = 1460.28 ms / 1076 tokens ( 1.36 ms per token, 736.84 tokens per second) 0.21.814.295 I slot print_timing: id 2 | task 265 | eval time = 5733.77 ms / 256 tokens ( 22.49 ms per token, 44.47 tokens per second) 0.21.814.296 I slot print_timing: id 2 | task 265 | total time = 7194.05 ms / 1332 tokens 0.21.814.296 I slot print_timing: id 2 | task 265 | graphs reused = 507 0.21.814.324 I slot release: id 2 | task 265 | stop processing: n_tokens = 1331, truncated = 0 0.21.830.901 I slot print_timing: id 3 | task 264 | prompt eval time = 1537.97 ms / 1076 tokens ( 1.43 ms per token, 699.63 tokens per second) 0.21.830.902 I slot print_timing: id 3 | task 264 | eval time = 5672.68 ms / 256 tokens ( 22.25 ms per token, 44.95 tokens per second) 0.21.830.903 I slot print_timing: id 3 | task 264 | total time = 7210.65 ms / 1332 tokens 0.21.830.903 I slot print_timing: id 3 | task 264 | graphs reused = 507 0.21.830.930 I slot release: id 3 | task 264 | stop processing: n_tokens = 1331, truncated = 0 0.21.830.935 I slot get_availabl: id 7 | task -1 | selected slot by LRU, t_last = 679608792821 0.21.831.068 I slot launch_slot_: id 7 | task 529 | processing task, is_child = 0 0.22.368.774 I slot get_availabl: id 4 | task -1 | selected slot by LRU, t_last = 679608813551 0.22.368.890 I slot launch_slot_: id 4 | task 528 | processing task, is_child = 0 0.22.369.187 I slot get_availabl: id 5 | task -1 | selected slot by LRU, t_last = 679608813741 0.22.369.260 I slot launch_slot_: id 5 | task 530 | processing task, is_child = 0 0.22.369.504 I slot get_availabl: id 6 | task -1 | selected slot by LRU, t_last = 679608813937 0.22.369.576 I slot launch_slot_: id 6 | task 531 | processing task, is_child = 0 0.26.854.600 I slot print_timing: id 4 | task 528 | n_gen = 136, tg = 44.89 t/s, tg_3s = 45.22 t/s 0.26.854.763 I slot print_timing: id 5 | task 530 | n_gen = 136, tg = 44.89 t/s, tg_3s = 45.22 t/s 0.26.854.925 I slot print_timing: id 6 | task 531 | n_gen = 136, tg = 44.89 t/s, tg_3s = 45.23 t/s 0.26.855.082 I slot print_timing: id 7 | task 529 | n_gen = 136, tg = 44.90 t/s, tg_3s = 45.23 t/s 0.29.533.518 I slot print_timing: id 4 | task 528 | prompt eval time = 1477.46 ms / 1034 tokens ( 1.43 ms per token, 699.85 tokens per second) 0.29.533.521 I slot print_timing: id 4 | task 528 | eval time = 5686.28 ms / 256 tokens ( 22.30 ms per token, 44.84 tokens per second) 0.29.533.521 I slot print_timing: id 4 | task 528 | total time = 7163.75 ms / 1290 tokens 0.29.533.522 I slot print_timing: id 4 | task 528 | graphs reused = 761 0.29.533.562 I slot release: id 4 | task 528 | stop processing: n_tokens = 1331, truncated = 0 0.29.533.728 I slot print_timing: id 5 | task 530 | prompt eval time = 1423.64 ms / 951 tokens ( 1.50 ms per token, 668.00 tokens per second) 0.29.533.729 I slot print_timing: id 5 | task 530 | eval time = 5686.18 ms / 256 tokens ( 22.30 ms per token, 44.85 tokens per second) 0.29.533.729 I slot print_timing: id 5 | task 530 | total time = 7109.83 ms / 1207 tokens 0.29.533.730 I slot print_timing: id 5 | task 530 | graphs reused = 761 0.29.533.756 I slot release: id 5 | task 530 | stop processing: n_tokens = 1248, truncated = 0 0.29.533.919 I slot print_timing: id 6 | task 531 | prompt eval time = 1367.86 ms / 931 tokens ( 1.47 ms per token, 680.62 tokens per second) 0.29.533.920 I slot print_timing: id 6 | task 531 | eval time = 5686.03 ms / 256 tokens ( 22.30 ms per token, 44.85 tokens per second) 0.29.533.920 I slot print_timing: id 6 | task 531 | total time = 7053.89 ms / 1187 tokens 0.29.533.920 I slot print_timing: id 6 | task 531 | graphs reused = 761 0.29.533.942 I slot release: id 6 | task 531 | stop processing: n_tokens = 1228, truncated = 0 0.29.534.099 I slot print_timing: id 7 | task 529 | prompt eval time = 1312.64 ms / 887 tokens ( 1.48 ms per token, 675.74 tokens per second) 0.29.534.101 I slot print_timing: id 7 | task 529 | eval time = 5685.61 ms / 256 tokens ( 22.30 ms per token, 44.85 tokens per second) 0.29.534.101 I slot print_timing: id 7 | task 529 | total time = 6998.25 ms / 1143 tokens 0.29.534.101 I slot print_timing: id 7 | task 529 | graphs reused = 761 0.29.534.122 I slot release: id 7 | task 529 | stop processing: n_tokens = 1184, truncated = 0 0.29.539.858 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 679616569247 0.29.540.055 I slot launch_slot_: id 0 | task 790 | processing task, is_child = 0 0.30.068.636 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 679616569439 0.30.068.764 I slot launch_slot_: id 1 | task 791 | processing task, is_child = 0 0.30.069.035 I slot get_availabl: id 2 | task -1 | selected slot by LRU, t_last = 679616569624 0.30.069.109 I slot launch_slot_: id 2 | task 792 | processing task, is_child = 0 0.30.069.328 I slot get_availabl: id 3 | task -1 | selected slot by LRU, t_last = 679616586229 0.30.069.396 I slot launch_slot_: id 3 | task 793 | processing task, is_child = 0 0.34.550.453 I slot print_timing: id 0 | task 790 | n_gen = 136, tg = 44.87 t/s, tg_3s = 45.20 t/s 0.34.550.611 I slot print_timing: id 1 | task 791 | n_gen = 136, tg = 44.87 t/s, tg_3s = 45.20 t/s 0.34.550.767 I slot print_timing: id 2 | task 792 | n_gen = 136, tg = 44.87 t/s, tg_3s = 45.20 t/s 0.34.550.927 I slot print_timing: id 3 | task 793 | n_gen = 136, tg = 44.87 t/s, tg_3s = 45.20 t/s 0.37.232.684 I slot print_timing: id 0 | task 790 | prompt eval time = 1471.96 ms / 943 tokens ( 1.56 ms per token, 640.64 tokens per second) 0.37.232.687 I slot print_timing: id 0 | task 790 | eval time = 5691.14 ms / 256 tokens ( 22.32 ms per token, 44.81 tokens per second) 0.37.232.687 I slot print_timing: id 0 | task 790 | total time = 7163.10 ms / 1199 tokens 0.37.232.688 I slot print_timing: id 0 | task 790 | graphs reused = 1016 0.37.232.725 I slot release: id 0 | task 790 | stop processing: n_tokens = 1240, truncated = 0 0.37.232.892 I slot print_timing: id 1 | task 791 | prompt eval time = 1419.79 ms / 942 tokens ( 1.51 ms per token, 663.48 tokens per second) 0.37.232.894 I slot print_timing: id 1 | task 791 | eval time = 5691.09 ms / 256 tokens ( 22.32 ms per token, 44.81 tokens per second) 0.37.232.894 I slot print_timing: id 1 | task 791 | total time = 7110.88 ms / 1198 tokens 0.37.232.894 I slot print_timing: id 1 | task 791 | graphs reused = 1016 0.37.232.923 I slot release: id 1 | task 791 | stop processing: n_tokens = 1239, truncated = 0 0.37.233.088 I slot print_timing: id 2 | task 792 | prompt eval time = 1366.45 ms / 907 tokens ( 1.51 ms per token, 663.76 tokens per second) 0.37.233.089 I slot print_timing: id 2 | task 792 | eval time = 5690.99 ms / 256 tokens ( 22.32 ms per token, 44.81 tokens per second) 0.37.233.090 I slot print_timing: id 2 | task 792 | total time = 7057.44 ms / 1163 tokens 0.37.233.090 I slot print_timing: id 2 | task 792 | graphs reused = 1016 0.37.233.115 I slot release: id 2 | task 792 | stop processing: n_tokens = 1204, truncated = 0 0.37.233.275 I slot print_timing: id 3 | task 793 | prompt eval time = 1313.11 ms / 1034 tokens ( 1.27 ms per token, 787.44 tokens per second) 0.37.233.277 I slot print_timing: id 3 | task 793 | eval time = 5690.93 ms / 256 tokens ( 22.32 ms per token, 44.81 tokens per second) 0.37.233.277 I slot print_timing: id 3 | task 793 | total time = 7004.04 ms / 1290 tokens 0.37.233.277 I slot print_timing: id 3 | task 793 | graphs reused = 1016 0.37.233.304 I slot release: id 3 | task 793 | stop processing: n_tokens = 1331, truncated = 0 0.37.239.986 I slot get_availabl: id 4 | task -1 | selected slot by LRU, t_last = 679624288862 0.37.240.179 I slot launch_slot_: id 4 | task 1052 | processing task, is_child = 0 0.37.240.268 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 0.37.407.146 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 675.033 MiB) 0.37.557.912 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 0.37.705.816 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 675.971 MiB) 0.37.853.148 I slot get_availabl: id 5 | task -1 | selected slot by LRU, t_last = 679624289056 0.37.853.271 I slot launch_slot_: id 5 | task 1053 | processing task, is_child = 0 0.37.853.533 I slot get_availabl: id 6 | task -1 | selected slot by LRU, t_last = 679624289241 0.37.853.603 I slot launch_slot_: id 6 | task 1054 | processing task, is_child = 0 0.37.853.842 I slot get_availabl: id 7 | task -1 | selected slot by LRU, t_last = 679624289422 0.37.853.909 I slot launch_slot_: id 7 | task 1055 | processing task, is_child = 0 0.42.362.876 I slot print_timing: id 4 | task 1052 | n_gen = 136, tg = 44.80 t/s, tg_3s = 45.13 t/s 0.42.363.030 I slot print_timing: id 5 | task 1053 | n_gen = 136, tg = 44.80 t/s, tg_3s = 45.13 t/s 0.42.363.188 I slot print_timing: id 6 | task 1054 | n_gen = 136, tg = 44.80 t/s, tg_3s = 45.14 t/s 0.42.363.343 I slot print_timing: id 7 | task 1055 | n_gen = 136, tg = 44.81 t/s, tg_3s = 45.14 t/s 0.45.046.092 I slot print_timing: id 4 | task 1052 | prompt eval time = 1495.41 ms / 907 tokens ( 1.65 ms per token, 606.52 tokens per second) 0.45.046.094 I slot print_timing: id 4 | task 1052 | eval time = 5696.58 ms / 256 tokens ( 22.34 ms per token, 44.76 tokens per second) 0.45.046.095 I slot print_timing: id 4 | task 1052 | total time = 7191.99 ms / 1163 tokens 0.45.046.096 I slot print_timing: id 4 | task 1052 | graphs reused = 1271 0.45.046.130 I slot release: id 4 | task 1052 | stop processing: n_tokens = 1204, truncated = 0 0.45.046.302 I slot print_timing: id 5 | task 1053 | prompt eval time = 1441.44 ms / 941 tokens ( 1.53 ms per token, 652.82 tokens per second) 0.45.046.304 I slot print_timing: id 5 | task 1053 | eval time = 5696.53 ms / 256 tokens ( 22.34 ms per token, 44.76 tokens per second) 0.45.046.304 I slot print_timing: id 5 | task 1053 | total time = 7137.97 ms / 1197 tokens 0.45.046.304 I slot print_timing: id 5 | task 1053 | graphs reused = 1271 0.45.046.333 I slot release: id 5 | task 1053 | stop processing: n_tokens = 1238, truncated = 0 0.45.046.506 I slot print_timing: id 6 | task 1054 | prompt eval time = 1384.78 ms / 1034 tokens ( 1.34 ms per token, 746.69 tokens per second) 0.45.046.507 I slot print_timing: id 6 | task 1054 | eval time = 5696.46 ms / 256 tokens ( 22.34 ms per token, 44.76 tokens per second) 0.45.046.508 I slot print_timing: id 6 | task 1054 | total time = 7081.25 ms / 1290 tokens 0.45.046.508 I slot print_timing: id 6 | task 1054 | graphs reused = 1271 0.45.046.535 I slot release: id 6 | task 1054 | stop processing: n_tokens = 1331, truncated = 0 0.45.046.708 I slot print_timing: id 7 | task 1055 | prompt eval time = 1327.73 ms / 1034 tokens ( 1.28 ms per token, 778.77 tokens per second) 0.45.046.709 I slot print_timing: id 7 | task 1055 | eval time = 5696.42 ms / 256 tokens ( 22.34 ms per token, 44.76 tokens per second) 0.45.046.710 I slot print_timing: id 7 | task 1055 | total time = 7024.16 ms / 1290 tokens 0.45.046.710 I slot print_timing: id 7 | task 1055 | graphs reused = 1271 0.45.046.738 I slot release: id 7 | task 1055 | stop processing: n_tokens = 1331, truncated = 0 0.45.051.536 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 679631988024 0.45.051.680 I slot launch_slot_: id 0 | task 1314 | processing task, is_child = 0 0.45.051.874 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 0.45.199.404 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 0.45.342.900 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 0.45.486.978 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 0.45.630.892 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 679631988223 0.45.631.027 I slot launch_slot_: id 1 | task 1315 | processing task, is_child = 0 0.45.631.296 I slot get_availabl: id 2 | task -1 | selected slot by LRU, t_last = 679631988414 0.45.631.369 I slot launch_slot_: id 2 | task 1316 | processing task, is_child = 0 0.45.631.589 I slot get_availabl: id 3 | task -1 | selected slot by LRU, t_last = 679631988604 0.45.631.658 I slot launch_slot_: id 3 | task 1317 | processing task, is_child = 0 0.50.157.305 I slot print_timing: id 0 | task 1314 | n_gen = 136, tg = 44.77 t/s, tg_3s = 45.10 t/s 0.50.157.459 I slot print_timing: id 1 | task 1315 | n_gen = 136, tg = 44.77 t/s, tg_3s = 45.10 t/s 0.50.157.612 I slot print_timing: id 2 | task 1316 | n_gen = 136, tg = 44.77 t/s, tg_3s = 45.10 t/s 0.50.157.766 I slot print_timing: id 3 | task 1317 | n_gen = 136, tg = 44.77 t/s, tg_3s = 45.10 t/s 0.52.843.200 I slot print_timing: id 0 | task 1314 | prompt eval time = 1509.89 ms / 1034 tokens ( 1.46 ms per token, 684.82 tokens per second) 0.52.843.202 I slot print_timing: id 0 | task 1314 | eval time = 5701.45 ms / 256 tokens ( 22.36 ms per token, 44.73 tokens per second) 0.52.843.203 I slot print_timing: id 0 | task 1314 | total time = 7211.35 ms / 1290 tokens 0.52.843.204 I slot print_timing: id 0 | task 1314 | graphs reused = 1525 0.52.843.247 I slot release: id 0 | task 1314 | stop processing: n_tokens = 1331, truncated = 0 0.52.843.408 I slot print_timing: id 1 | task 1315 | prompt eval time = 1458.21 ms / 953 tokens ( 1.53 ms per token, 653.54 tokens per second) 0.52.843.409 I slot print_timing: id 1 | task 1315 | eval time = 5701.37 ms / 256 tokens ( 22.36 ms per token, 44.73 tokens per second) 0.52.843.409 I slot print_timing: id 1 | task 1315 | total time = 7159.58 ms / 1209 tokens 0.52.843.410 I slot print_timing: id 1 | task 1315 | graphs reused = 1525 0.52.843.439 I slot release: id 1 | task 1315 | stop processing: n_tokens = 1250, truncated = 0 0.52.843.599 I slot print_timing: id 2 | task 1316 | prompt eval time = 1405.15 ms / 1034 tokens ( 1.36 ms per token, 735.87 tokens per second) 0.52.843.600 I slot print_timing: id 2 | task 1316 | eval time = 5701.29 ms / 256 tokens ( 22.36 ms per token, 44.73 tokens per second) 0.52.843.600 I slot print_timing: id 2 | task 1316 | total time = 7106.44 ms / 1290 tokens 0.52.843.600 I slot print_timing: id 2 | task 1316 | graphs reused = 1525 0.52.843.627 I slot release: id 2 | task 1316 | stop processing: n_tokens = 1331, truncated = 0 0.52.843.788 I slot print_timing: id 3 | task 1317 | prompt eval time = 1352.16 ms / 885 tokens ( 1.53 ms per token, 654.51 tokens per second) 0.52.843.789 I slot print_timing: id 3 | task 1317 | eval time = 5701.23 ms / 256 tokens ( 22.36 ms per token, 44.73 tokens per second) 0.52.843.789 I slot print_timing: id 3 | task 1317 | total time = 7053.39 ms / 1141 tokens 0.52.843.789 I slot print_timing: id 3 | task 1317 | graphs reused = 1525 0.52.843.812 I slot release: id 3 | task 1317 | stop processing: n_tokens = 1182, truncated = 0 0.52.849.500 I slot get_availabl: id 4 | task -1 | selected slot by LRU, t_last = 679639801429 0.52.849.697 I slot launch_slot_: id 4 | task 1576 | processing task, is_child = 0 0.52.849.790 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 0.52.997.775 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 676.533 MiB) 0.53.141.321 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 675.283 MiB) 0.53.286.082 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 672.532 MiB) 0.53.427.371 I slot get_availabl: id 5 | task -1 | selected slot by LRU, t_last = 679639801633 0.53.427.495 I slot launch_slot_: id 5 | task 1577 | processing task, is_child = 0 0.53.427.796 I slot get_availabl: id 6 | task -1 | selected slot by LRU, t_last = 679639801835 0.53.427.876 I slot launch_slot_: id 6 | task 1578 | processing task, is_child = 0 0.53.428.097 I slot get_availabl: id 7 | task -1 | selected slot by LRU, t_last = 679639802037 0.53.428.169 I slot launch_slot_: id 7 | task 1579 | processing task, is_child = 0 0.57.975.867 I slot print_timing: id 4 | task 1576 | n_gen = 136, tg = 44.71 t/s, tg_3s = 45.04 t/s 0.57.976.028 I slot print_timing: id 5 | task 1577 | n_gen = 136, tg = 44.71 t/s, tg_3s = 45.04 t/s 0.57.976.191 I slot print_timing: id 6 | task 1578 | n_gen = 136, tg = 44.71 t/s, tg_3s = 45.04 t/s 0.57.976.360 I slot print_timing: id 7 | task 1579 | n_gen = 136, tg = 44.71 t/s, tg_3s = 45.04 t/s 1.00.666.245 I slot print_timing: id 4 | task 1576 | prompt eval time = 1527.99 ms / 1034 tokens ( 1.48 ms per token, 676.71 tokens per second) 1.00.666.248 I slot print_timing: id 4 | task 1576 | eval time = 5709.90 ms / 256 tokens ( 22.39 ms per token, 44.66 tokens per second) 1.00.666.248 I slot print_timing: id 4 | task 1576 | total time = 7237.89 ms / 1290 tokens 1.00.666.249 I slot print_timing: id 4 | task 1576 | graphs reused = 1780 1.00.666.288 I slot release: id 4 | task 1576 | stop processing: n_tokens = 1331, truncated = 0 1.00.666.446 I slot print_timing: id 5 | task 1577 | prompt eval time = 1474.36 ms / 1034 tokens ( 1.43 ms per token, 701.32 tokens per second) 1.00.666.448 I slot print_timing: id 5 | task 1577 | eval time = 5709.85 ms / 256 tokens ( 22.39 ms per token, 44.66 tokens per second) 1.00.666.448 I slot print_timing: id 5 | task 1577 | total time = 7184.21 ms / 1290 tokens 1.00.666.448 I slot print_timing: id 5 | task 1577 | graphs reused = 1780 1.00.666.470 I slot release: id 5 | task 1577 | stop processing: n_tokens = 1331, truncated = 0 1.00.666.630 I slot print_timing: id 6 | task 1578 | prompt eval time = 1418.67 ms / 939 tokens ( 1.51 ms per token, 661.89 tokens per second) 1.00.666.631 I slot print_timing: id 6 | task 1578 | eval time = 5709.78 ms / 256 tokens ( 22.39 ms per token, 44.66 tokens per second) 1.00.666.632 I slot print_timing: id 6 | task 1578 | total time = 7128.46 ms / 1195 tokens 1.00.666.632 I slot print_timing: id 6 | task 1578 | graphs reused = 1780 1.00.666.655 I slot release: id 6 | task 1578 | stop processing: n_tokens = 1236, truncated = 0 1.00.666.819 I slot print_timing: id 7 | task 1579 | prompt eval time = 1361.46 ms / 1034 tokens ( 1.32 ms per token, 759.48 tokens per second) 1.00.666.820 I slot print_timing: id 7 | task 1579 | eval time = 5709.68 ms / 256 tokens ( 22.39 ms per token, 44.66 tokens per second) 1.00.666.821 I slot print_timing: id 7 | task 1579 | total time = 7071.14 ms / 1290 tokens 1.00.666.821 I slot print_timing: id 7 | task 1579 | graphs reused = 1780 1.00.666.846 I slot release: id 7 | task 1579 | stop processing: n_tokens = 1331, truncated = 0 1.00.673.763 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 679647598546 1.00.674.011 I slot launch_slot_: id 0 | task 1838 | processing task, is_child = 0 1.00.674.462 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 676.033 MiB) 1.00.839.261 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 675.971 MiB) 1.00.990.208 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 673.782 MiB) 1.01.134.808 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 1.01.282.790 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 679647598738 1.01.282.930 I slot launch_slot_: id 1 | task 1839 | processing task, is_child = 0 1.01.283.193 I slot get_availabl: id 2 | task -1 | selected slot by LRU, t_last = 679647598927 1.01.283.263 I slot launch_slot_: id 2 | task 1840 | processing task, is_child = 0 1.01.283.477 I slot get_availabl: id 3 | task -1 | selected slot by LRU, t_last = 679647599111 1.01.283.543 I slot launch_slot_: id 3 | task 1841 | processing task, is_child = 0 1.05.809.179 I slot print_timing: id 0 | task 1838 | n_gen = 136, tg = 44.69 t/s, tg_3s = 45.02 t/s 1.05.809.340 I slot print_timing: id 1 | task 1839 | n_gen = 136, tg = 44.69 t/s, tg_3s = 45.02 t/s 1.05.809.500 I slot print_timing: id 2 | task 1840 | n_gen = 136, tg = 44.70 t/s, tg_3s = 45.03 t/s 1.05.809.658 I slot print_timing: id 3 | task 1841 | n_gen = 136, tg = 44.70 t/s, tg_3s = 45.03 t/s 1.08.500.014 I slot print_timing: id 0 | task 1838 | prompt eval time = 1504.80 ms / 1035 tokens ( 1.45 ms per token, 687.80 tokens per second) 1.08.500.016 I slot print_timing: id 0 | task 1838 | eval time = 5711.48 ms / 256 tokens ( 22.40 ms per token, 44.65 tokens per second) 1.08.500.017 I slot print_timing: id 0 | task 1838 | total time = 7216.28 ms / 1291 tokens 1.08.500.017 I slot print_timing: id 0 | task 1838 | graphs reused = 2035 1.08.500.059 I slot release: id 0 | task 1838 | stop processing: n_tokens = 1332, truncated = 0 1.08.500.227 I slot print_timing: id 1 | task 1839 | prompt eval time = 1452.41 ms / 938 tokens ( 1.55 ms per token, 645.82 tokens per second) 1.08.500.228 I slot print_timing: id 1 | task 1839 | eval time = 5711.44 ms / 256 tokens ( 22.40 ms per token, 44.65 tokens per second) 1.08.500.229 I slot print_timing: id 1 | task 1839 | total time = 7163.85 ms / 1194 tokens 1.08.500.229 I slot print_timing: id 1 | task 1839 | graphs reused = 2035 1.08.500.262 I slot release: id 1 | task 1839 | stop processing: n_tokens = 1235, truncated = 0 1.08.500.428 I slot print_timing: id 2 | task 1840 | prompt eval time = 1398.19 ms / 940 tokens ( 1.49 ms per token, 672.30 tokens per second) 1.08.500.429 I slot print_timing: id 2 | task 1840 | eval time = 5711.39 ms / 256 tokens ( 22.40 ms per token, 44.65 tokens per second) 1.08.500.430 I slot print_timing: id 2 | task 1840 | total time = 7109.57 ms / 1196 tokens 1.08.500.430 I slot print_timing: id 2 | task 1840 | graphs reused = 2035 1.08.500.455 I slot release: id 2 | task 1840 | stop processing: n_tokens = 1237, truncated = 0 1.08.500.623 I slot print_timing: id 3 | task 1841 | prompt eval time = 1343.09 ms / 933 tokens ( 1.44 ms per token, 694.67 tokens per second) 1.08.500.624 I slot print_timing: id 3 | task 1841 | eval time = 5711.32 ms / 256 tokens ( 22.40 ms per token, 44.65 tokens per second) 1.08.500.625 I slot print_timing: id 3 | task 1841 | total time = 7054.41 ms / 1189 tokens 1.08.500.625 I slot print_timing: id 3 | task 1841 | graphs reused = 2035 1.08.500.651 I slot release: id 3 | task 1841 | stop processing: n_tokens = 1230, truncated = 0 1.08.506.376 I slot get_availabl: id 4 | task -1 | selected slot by LRU, t_last = 679655421586 1.08.506.569 I slot launch_slot_: id 4 | task 2100 | processing task, is_child = 0 1.08.506.669 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 673.782 MiB) 1.08.656.904 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 675.908 MiB) 1.08.800.005 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 1.08.941.969 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 1.09.086.167 I slot get_availabl: id 5 | task -1 | selected slot by LRU, t_last = 679655421770 1.09.086.288 I slot launch_slot_: id 5 | task 2101 | processing task, is_child = 0 1.09.086.554 I slot get_availabl: id 6 | task -1 | selected slot by LRU, t_last = 679655421955 1.09.086.624 I slot launch_slot_: id 6 | task 2102 | processing task, is_child = 0 1.09.086.845 I slot get_availabl: id 7 | task -1 | selected slot by LRU, t_last = 679655422146 1.09.086.915 I slot launch_slot_: id 7 | task 2103 | processing task, is_child = 0 1.13.630.054 I slot print_timing: id 4 | task 2100 | n_gen = 136, tg = 44.67 t/s, tg_3s = 45.01 t/s 1.13.630.212 I slot print_timing: id 5 | task 2101 | n_gen = 136, tg = 44.68 t/s, tg_3s = 45.01 t/s 1.13.630.370 I slot print_timing: id 6 | task 2102 | n_gen = 136, tg = 44.68 t/s, tg_3s = 45.01 t/s 1.13.630.523 I slot print_timing: id 7 | task 2103 | n_gen = 136, tg = 44.68 t/s, tg_3s = 45.01 t/s 1.16.321.409 I slot print_timing: id 4 | task 2100 | prompt eval time = 1521.10 ms / 1034 tokens ( 1.47 ms per token, 679.77 tokens per second) 1.16.321.412 I slot print_timing: id 4 | task 2100 | eval time = 5713.19 ms / 256 tokens ( 22.40 ms per token, 44.63 tokens per second) 1.16.321.412 I slot print_timing: id 4 | task 2100 | total time = 7234.29 ms / 1290 tokens 1.16.321.413 I slot print_timing: id 4 | task 2100 | graphs reused = 2290 1.16.321.455 I slot release: id 4 | task 2100 | stop processing: n_tokens = 1331, truncated = 0 1.16.321.618 I slot print_timing: id 5 | task 2101 | prompt eval time = 1467.39 ms / 938 tokens ( 1.56 ms per token, 639.23 tokens per second) 1.16.321.620 I slot print_timing: id 5 | task 2101 | eval time = 5713.14 ms / 256 tokens ( 22.40 ms per token, 44.63 tokens per second) 1.16.321.620 I slot print_timing: id 5 | task 2101 | total time = 7180.54 ms / 1194 tokens 1.16.321.620 I slot print_timing: id 5 | task 2101 | graphs reused = 2290 1.16.321.649 I slot release: id 5 | task 2101 | stop processing: n_tokens = 1235, truncated = 0 1.16.321.816 I slot print_timing: id 6 | task 2102 | prompt eval time = 1410.96 ms / 1034 tokens ( 1.36 ms per token, 732.83 tokens per second) 1.16.321.817 I slot print_timing: id 6 | task 2102 | eval time = 5713.09 ms / 256 tokens ( 22.40 ms per token, 44.63 tokens per second) 1.16.321.818 I slot print_timing: id 6 | task 2102 | total time = 7124.05 ms / 1290 tokens 1.16.321.818 I slot print_timing: id 6 | task 2102 | graphs reused = 2290 1.16.321.842 I slot release: id 6 | task 2102 | stop processing: n_tokens = 1331, truncated = 0 1.16.322.007 I slot print_timing: id 7 | task 2103 | prompt eval time = 1353.85 ms / 1034 tokens ( 1.31 ms per token, 763.75 tokens per second) 1.16.322.010 I slot print_timing: id 7 | task 2103 | eval time = 5712.99 ms / 256 tokens ( 22.40 ms per token, 44.64 tokens per second) 1.16.322.011 I slot print_timing: id 7 | task 2103 | total time = 7066.84 ms / 1290 tokens 1.16.322.011 I slot print_timing: id 7 | task 2103 | graphs reused = 2290 1.16.322.045 I slot release: id 7 | task 2103 | stop processing: n_tokens = 1331, truncated = 0 1.16.328.493 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 679663255358 1.16.328.695 I slot launch_slot_: id 0 | task 2362 | processing task, is_child = 0 1.16.329.034 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 1.16.479.258 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 676.659 MiB) 1.16.621.815 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 1.16.765.384 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 672.407 MiB) 1.16.909.334 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 679663255562 1.16.909.468 I slot launch_slot_: id 1 | task 2363 | processing task, is_child = 0 1.16.909.766 I slot get_availabl: id 2 | task -1 | selected slot by LRU, t_last = 679663255755 1.16.909.843 I slot launch_slot_: id 2 | task 2364 | processing task, is_child = 0 1.16.910.064 I slot get_availabl: id 3 | task -1 | selected slot by LRU, t_last = 679663255951 1.16.910.134 I slot launch_slot_: id 3 | task 2365 | processing task, is_child = 0 1.21.469.748 I slot print_timing: id 0 | task 2362 | n_gen = 133, tg = 43.72 t/s, tg_3s = 44.05 t/s 1.21.469.910 I slot print_timing: id 1 | task 2363 | n_gen = 133, tg = 43.72 t/s, tg_3s = 44.05 t/s 1.21.470.069 I slot print_timing: id 2 | task 2364 | n_gen = 133, tg = 43.72 t/s, tg_3s = 44.06 t/s 1.21.537.423 I slot print_timing: id 3 | task 2365 | n_gen = 135, tg = 44.54 t/s, tg_3s = 44.88 t/s 1.24.230.996 I slot print_timing: id 0 | task 2362 | prompt eval time = 1540.25 ms / 1034 tokens ( 1.49 ms per token, 671.32 tokens per second) 1.24.230.998 I slot print_timing: id 0 | task 2362 | eval time = 5780.42 ms / 256 tokens ( 22.67 ms per token, 44.11 tokens per second) 1.24.230.999 I slot print_timing: id 0 | task 2362 | total time = 7320.67 ms / 1290 tokens 1.24.231.000 I slot print_timing: id 0 | task 2362 | graphs reused = 2543 1.24.231.042 I slot release: id 0 | task 2362 | stop processing: n_tokens = 1331, truncated = 0 1.24.231.206 I slot print_timing: id 1 | task 2363 | prompt eval time = 1487.10 ms / 1036 tokens ( 1.44 ms per token, 696.66 tokens per second) 1.24.231.207 I slot print_timing: id 1 | task 2363 | eval time = 5780.35 ms / 256 tokens ( 22.67 ms per token, 44.11 tokens per second) 1.24.231.208 I slot print_timing: id 1 | task 2363 | total time = 7267.45 ms / 1292 tokens 1.24.231.208 I slot print_timing: id 1 | task 2363 | graphs reused = 2543 1.24.231.240 I slot release: id 1 | task 2363 | stop processing: n_tokens = 1333, truncated = 0 1.24.231.401 I slot print_timing: id 2 | task 2364 | prompt eval time = 1432.92 ms / 1034 tokens ( 1.39 ms per token, 721.60 tokens per second) 1.24.231.403 I slot print_timing: id 2 | task 2364 | eval time = 5780.21 ms / 256 tokens ( 22.67 ms per token, 44.12 tokens per second) 1.24.231.403 I slot print_timing: id 2 | task 2364 | total time = 7213.12 ms / 1290 tokens 1.24.231.403 I slot print_timing: id 2 | task 2364 | graphs reused = 2543 1.24.231.424 I slot release: id 2 | task 2364 | stop processing: n_tokens = 1331, truncated = 0 1.24.248.010 I slot print_timing: id 3 | task 2365 | prompt eval time = 1454.95 ms / 1034 tokens ( 1.41 ms per token, 710.68 tokens per second) 1.24.248.012 I slot print_timing: id 3 | task 2365 | eval time = 5718.86 ms / 256 tokens ( 22.43 ms per token, 44.59 tokens per second) 1.24.248.012 I slot print_timing: id 3 | task 2365 | total time = 7173.82 ms / 1290 tokens 1.24.248.012 I slot print_timing: id 3 | task 2365 | graphs reused = 2543 1.24.248.039 I slot release: id 3 | task 2365 | stop processing: n_tokens = 1331, truncated = 0 1.24.248.047 I slot get_availabl: id 4 | task -1 | selected slot by LRU, t_last = 679671076754 1.24.248.178 I slot launch_slot_: id 4 | task 2625 | processing task, is_child = 0 1.24.248.227 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 1.24.417.688 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 1.24.570.938 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 675.783 MiB) 1.24.721.636 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 1.24.872.301 I slot get_availabl: id 5 | task -1 | selected slot by LRU, t_last = 679671076949 1.24.872.428 I slot launch_slot_: id 5 | task 2626 | processing task, is_child = 0 1.24.872.734 I slot get_availabl: id 6 | task -1 | selected slot by LRU, t_last = 679671077141 1.24.872.813 I slot launch_slot_: id 6 | task 2627 | processing task, is_child = 0 1.24.873.039 I slot get_availabl: id 7 | task -1 | selected slot by LRU, t_last = 679671077345 1.24.873.110 I slot launch_slot_: id 7 | task 2628 | processing task, is_child = 0 1.29.410.894 I slot print_timing: id 4 | task 2625 | n_gen = 133, tg = 43.79 t/s, tg_3s = 44.12 t/s 1.29.411.051 I slot print_timing: id 5 | task 2626 | n_gen = 133, tg = 43.79 t/s, tg_3s = 44.12 t/s 1.29.411.215 I slot print_timing: id 6 | task 2627 | n_gen = 133, tg = 43.79 t/s, tg_3s = 44.12 t/s 1.29.478.632 I slot print_timing: id 7 | task 2628 | n_gen = 135, tg = 44.62 t/s, tg_3s = 44.96 t/s 1.32.174.022 I slot print_timing: id 4 | task 2625 | prompt eval time = 1523.16 ms / 1034 tokens ( 1.47 ms per token, 678.85 tokens per second) 1.32.174.025 I slot print_timing: id 4 | task 2625 | eval time = 5777.55 ms / 256 tokens ( 22.66 ms per token, 44.14 tokens per second) 1.32.174.025 I slot print_timing: id 4 | task 2625 | total time = 7300.71 ms / 1290 tokens 1.32.174.026 I slot print_timing: id 4 | task 2625 | graphs reused = 2796 1.32.174.068 I slot release: id 4 | task 2625 | stop processing: n_tokens = 1331, truncated = 0 1.32.174.229 I slot print_timing: id 5 | task 2626 | prompt eval time = 1469.71 ms / 1034 tokens ( 1.42 ms per token, 703.54 tokens per second) 1.32.174.230 I slot print_timing: id 5 | task 2626 | eval time = 5777.51 ms / 256 tokens ( 22.66 ms per token, 44.14 tokens per second) 1.32.174.231 I slot print_timing: id 5 | task 2626 | total time = 7247.22 ms / 1290 tokens 1.32.174.231 I slot print_timing: id 5 | task 2626 | graphs reused = 2796 1.32.174.258 I slot release: id 5 | task 2626 | stop processing: n_tokens = 1331, truncated = 0 1.32.174.424 I slot print_timing: id 6 | task 2627 | prompt eval time = 1412.91 ms / 1034 tokens ( 1.37 ms per token, 731.82 tokens per second) 1.32.174.425 I slot print_timing: id 6 | task 2627 | eval time = 5777.42 ms / 256 tokens ( 22.66 ms per token, 44.14 tokens per second) 1.32.174.425 I slot print_timing: id 6 | task 2627 | total time = 7190.34 ms / 1290 tokens 1.32.174.425 I slot print_timing: id 6 | task 2627 | graphs reused = 2796 1.32.174.445 I slot release: id 6 | task 2627 | stop processing: n_tokens = 1331, truncated = 0 1.32.191.058 I slot print_timing: id 7 | task 2628 | prompt eval time = 1434.17 ms / 1034 tokens ( 1.39 ms per token, 720.97 tokens per second) 1.32.191.059 I slot print_timing: id 7 | task 2628 | eval time = 5715.36 ms / 256 tokens ( 22.41 ms per token, 44.62 tokens per second) 1.32.191.060 I slot print_timing: id 7 | task 2628 | total time = 7149.53 ms / 1290 tokens 1.32.191.060 I slot print_timing: id 7 | task 2628 | graphs reused = 2796 1.32.191.090 I slot release: id 7 | task 2628 | stop processing: n_tokens = 1331, truncated = 0 1.32.191.099 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 679678986344 1.32.191.210 I slot launch_slot_: id 0 | task 2888 | processing task, is_child = 0 1.32.191.391 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.785 MiB) 1.32.344.126 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 675.721 MiB) 1.32.490.165 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 675.846 MiB) 1.32.635.304 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 675.408 MiB) 1.32.780.793 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 679678986540 1.32.780.928 I slot launch_slot_: id 1 | task 2889 | processing task, is_child = 0 1.32.781.203 I slot get_availabl: id 2 | task -1 | selected slot by LRU, t_last = 679678986724 1.32.781.276 I slot launch_slot_: id 2 | task 2890 | processing task, is_child = 0 1.32.781.499 I slot get_availabl: id 3 | task -1 | selected slot by LRU, t_last = 679679003338 1.32.781.574 I slot launch_slot_: id 3 | task 2891 | processing task, is_child = 0 1.37.275.881 I slot print_timing: id 0 | task 2888 | n_gen = 135, tg = 44.59 t/s, tg_3s = 44.92 t/s 1.37.276.046 I slot print_timing: id 1 | task 2889 | n_gen = 135, tg = 44.59 t/s, tg_3s = 44.92 t/s 1.37.276.211 I slot print_timing: id 2 | task 2890 | n_gen = 135, tg = 44.59 t/s, tg_3s = 44.92 t/s 1.37.276.372 I slot print_timing: id 3 | task 2891 | n_gen = 135, tg = 44.59 t/s, tg_3s = 44.92 t/s 1.39.995.548 I slot print_timing: id 0 | task 2888 | prompt eval time = 1488.64 ms / 1034 tokens ( 1.44 ms per token, 694.59 tokens per second) 1.39.995.550 I slot print_timing: id 0 | task 2888 | eval time = 5725.12 ms / 256 tokens ( 22.45 ms per token, 44.54 tokens per second) 1.39.995.551 I slot print_timing: id 0 | task 2888 | total time = 7213.76 ms / 1290 tokens 1.39.995.552 I slot print_timing: id 0 | task 2888 | graphs reused = 3050 1.39.995.589 I slot release: id 0 | task 2888 | stop processing: n_tokens = 1331, truncated = 0 1.39.995.757 I slot print_timing: id 1 | task 2889 | prompt eval time = 1435.66 ms / 891 tokens ( 1.61 ms per token, 620.62 tokens per second) 1.39.995.759 I slot print_timing: id 1 | task 2889 | eval time = 5725.02 ms / 256 tokens ( 22.45 ms per token, 44.54 tokens per second) 1.39.995.759 I slot print_timing: id 1 | task 2889 | total time = 7160.68 ms / 1147 tokens 1.39.995.760 I slot print_timing: id 1 | task 2889 | graphs reused = 3050 1.39.995.787 I slot release: id 1 | task 2889 | stop processing: n_tokens = 1188, truncated = 0 1.39.995.959 I slot print_timing: id 2 | task 2890 | prompt eval time = 1380.66 ms / 1034 tokens ( 1.34 ms per token, 748.92 tokens per second) 1.39.995.960 I slot print_timing: id 2 | task 2890 | eval time = 5724.90 ms / 256 tokens ( 22.45 ms per token, 44.54 tokens per second) 1.39.995.960 I slot print_timing: id 2 | task 2890 | total time = 7105.55 ms / 1290 tokens 1.39.995.961 I slot print_timing: id 2 | task 2890 | graphs reused = 3050 1.39.995.984 I slot release: id 2 | task 2890 | stop processing: n_tokens = 1331, truncated = 0 1.39.996.154 I slot print_timing: id 3 | task 2891 | prompt eval time = 1323.31 ms / 888 tokens ( 1.49 ms per token, 671.05 tokens per second) 1.39.996.155 I slot print_timing: id 3 | task 2891 | eval time = 5724.85 ms / 256 tokens ( 22.45 ms per token, 44.54 tokens per second) 1.39.996.155 I slot print_timing: id 3 | task 2891 | total time = 7048.15 ms / 1144 tokens 1.39.996.155 I slot print_timing: id 3 | task 2891 | graphs reused = 3050 1.39.996.175 I slot release: id 3 | task 2891 | stop processing: n_tokens = 1185, truncated = 0 1.40.002.540 I slot get_availabl: id 4 | task -1 | selected slot by LRU, t_last = 679686929367 1.40.002.655 I slot launch_slot_: id 4 | task 3150 | processing task, is_child = 0 1.40.002.707 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 1.40.156.149 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 675.721 MiB) 1.40.300.539 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 1.40.446.059 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 1.40.590.170 I slot get_availabl: id 5 | task -1 | selected slot by LRU, t_last = 679686929557 1.40.590.294 I slot launch_slot_: id 5 | task 3151 | processing task, is_child = 0 1.40.590.590 I slot get_availabl: id 6 | task -1 | selected slot by LRU, t_last = 679686929744 1.40.590.668 I slot launch_slot_: id 6 | task 3152 | processing task, is_child = 0 1.40.590.912 I slot get_availabl: id 7 | task -1 | selected slot by LRU, t_last = 679686946389 1.40.590.983 I slot launch_slot_: id 7 | task 3153 | processing task, is_child = 0 1.45.128.662 I slot print_timing: id 4 | task 3150 | n_gen = 135, tg = 44.53 t/s, tg_3s = 44.87 t/s 1.45.128.828 I slot print_timing: id 5 | task 3151 | n_gen = 135, tg = 44.54 t/s, tg_3s = 44.87 t/s 1.45.128.997 I slot print_timing: id 6 | task 3152 | n_gen = 135, tg = 44.54 t/s, tg_3s = 44.87 t/s 1.45.129.163 I slot print_timing: id 7 | task 3153 | n_gen = 135, tg = 44.54 t/s, tg_3s = 44.87 t/s 1.47.853.177 I slot print_timing: id 4 | task 3150 | prompt eval time = 1528.57 ms / 1030 tokens ( 1.48 ms per token, 673.83 tokens per second) 1.47.853.180 I slot print_timing: id 4 | task 3150 | eval time = 5733.43 ms / 256 tokens ( 22.48 ms per token, 44.48 tokens per second) 1.47.853.180 I slot print_timing: id 4 | task 3150 | total time = 7262.00 ms / 1286 tokens 1.47.853.181 I slot print_timing: id 4 | task 3150 | graphs reused = 3305 1.47.853.221 I slot release: id 4 | task 3150 | stop processing: n_tokens = 1327, truncated = 0 1.47.853.386 I slot print_timing: id 5 | task 3151 | prompt eval time = 1474.55 ms / 920 tokens ( 1.60 ms per token, 623.92 tokens per second) 1.47.853.388 I slot print_timing: id 5 | task 3151 | eval time = 5733.35 ms / 256 tokens ( 22.48 ms per token, 44.48 tokens per second) 1.47.853.388 I slot print_timing: id 5 | task 3151 | total time = 7207.90 ms / 1176 tokens 1.47.853.389 I slot print_timing: id 5 | task 3151 | graphs reused = 3305 1.47.853.421 I slot release: id 5 | task 3151 | stop processing: n_tokens = 1217, truncated = 0 1.47.853.607 I slot print_timing: id 6 | task 3152 | prompt eval time = 1417.45 ms / 1034 tokens ( 1.37 ms per token, 729.48 tokens per second) 1.47.853.609 I slot print_timing: id 6 | task 3152 | eval time = 5733.26 ms / 256 tokens ( 22.48 ms per token, 44.48 tokens per second) 1.47.853.609 I slot print_timing: id 6 | task 3152 | total time = 7150.71 ms / 1290 tokens 1.47.853.609 I slot print_timing: id 6 | task 3152 | graphs reused = 3305 1.47.853.635 I slot release: id 6 | task 3152 | stop processing: n_tokens = 1331, truncated = 0 1.47.853.805 I slot print_timing: id 7 | task 3153 | prompt eval time = 1359.52 ms / 934 tokens ( 1.46 ms per token, 687.01 tokens per second) 1.47.853.806 I slot print_timing: id 7 | task 3153 | eval time = 5733.16 ms / 256 tokens ( 22.48 ms per token, 44.48 tokens per second) 1.47.853.807 I slot print_timing: id 7 | task 3153 | total time = 7092.67 ms / 1190 tokens 1.47.853.807 I slot print_timing: id 7 | task 3153 | graphs reused = 3305 1.47.853.830 I slot release: id 7 | task 3153 | stop processing: n_tokens = 1231, truncated = 0 1.47.861.077 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 679694750888 1.47.861.187 I slot launch_slot_: id 0 | task 3412 | processing task, is_child = 0 1.47.861.371 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 1.48.030.981 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.848 MiB) 1.48.182.972 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 1.48.332.520 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 1.48.482.088 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 679694751087 1.48.482.223 I slot launch_slot_: id 1 | task 3413 | processing task, is_child = 0 1.48.482.519 I slot get_availabl: id 2 | task -1 | selected slot by LRU, t_last = 679694751283 1.48.482.597 I slot launch_slot_: id 2 | task 3414 | processing task, is_child = 0 1.48.482.816 I slot get_availabl: id 3 | task -1 | selected slot by LRU, t_last = 679694751474 1.48.482.889 I slot launch_slot_: id 3 | task 3415 | processing task, is_child = 0 1.53.017.671 I slot print_timing: id 0 | task 3412 | n_gen = 135, tg = 44.47 t/s, tg_3s = 44.80 t/s 1.53.017.841 I slot print_timing: id 1 | task 3413 | n_gen = 135, tg = 44.47 t/s, tg_3s = 44.80 t/s 1.53.018.005 I slot print_timing: id 2 | task 3414 | n_gen = 135, tg = 44.47 t/s, tg_3s = 44.80 t/s 1.53.018.170 I slot print_timing: id 3 | task 3415 | n_gen = 135, tg = 44.47 t/s, tg_3s = 44.81 t/s 1.55.740.514 I slot print_timing: id 0 | task 3412 | prompt eval time = 1521.15 ms / 1029 tokens ( 1.48 ms per token, 676.46 tokens per second) 1.55.740.518 I slot print_timing: id 0 | task 3412 | eval time = 5736.29 ms / 256 tokens ( 22.50 ms per token, 44.45 tokens per second) 1.55.740.518 I slot print_timing: id 0 | task 3412 | total time = 7257.43 ms / 1285 tokens 1.55.740.519 I slot print_timing: id 0 | task 3412 | graphs reused = 3560 1.55.740.564 I slot release: id 0 | task 3412 | stop processing: n_tokens = 1326, truncated = 0 1.55.740.741 I slot print_timing: id 1 | task 3413 | prompt eval time = 1468.04 ms / 953 tokens ( 1.54 ms per token, 649.17 tokens per second) 1.55.740.743 I slot print_timing: id 1 | task 3413 | eval time = 5736.22 ms / 256 tokens ( 22.49 ms per token, 44.45 tokens per second) 1.55.740.744 I slot print_timing: id 1 | task 3413 | total time = 7204.25 ms / 1209 tokens 1.55.740.744 I slot print_timing: id 1 | task 3413 | graphs reused = 3560 1.55.740.769 I slot release: id 1 | task 3413 | stop processing: n_tokens = 1250, truncated = 0 1.55.740.934 I slot print_timing: id 2 | task 3414 | prompt eval time = 1413.73 ms / 926 tokens ( 1.53 ms per token, 655.00 tokens per second) 1.55.740.936 I slot print_timing: id 2 | task 3414 | eval time = 5736.07 ms / 256 tokens ( 22.49 ms per token, 44.46 tokens per second) 1.55.740.936 I slot print_timing: id 2 | task 3414 | total time = 7149.81 ms / 1182 tokens 1.55.740.937 I slot print_timing: id 2 | task 3414 | graphs reused = 3560 1.55.740.971 I slot release: id 2 | task 3414 | stop processing: n_tokens = 1223, truncated = 0 1.55.741.154 I slot print_timing: id 3 | task 3415 | prompt eval time = 1357.80 ms / 1034 tokens ( 1.31 ms per token, 761.53 tokens per second) 1.55.741.157 I slot print_timing: id 3 | task 3415 | eval time = 5735.99 ms / 256 tokens ( 22.49 ms per token, 44.46 tokens per second) 1.55.741.157 I slot print_timing: id 3 | task 3415 | total time = 7093.78 ms / 1290 tokens 1.55.741.158 I slot print_timing: id 3 | task 3415 | graphs reused = 3560 1.55.741.182 I slot release: id 3 | task 3415 | stop processing: n_tokens = 1331, truncated = 0 1.55.747.679 I slot get_availabl: id 4 | task -1 | selected slot by LRU, t_last = 679702608520 1.55.747.836 I slot launch_slot_: id 4 | task 3674 | processing task, is_child = 0 1.55.747.917 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 1.55.906.965 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 1.56.053.574 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 1.56.197.749 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 1.56.344.543 I slot get_availabl: id 5 | task -1 | selected slot by LRU, t_last = 679702608721 1.56.344.669 I slot launch_slot_: id 5 | task 3675 | processing task, is_child = 0 1.56.344.940 I slot get_availabl: id 6 | task -1 | selected slot by LRU, t_last = 679702608935 1.56.345.012 I slot launch_slot_: id 6 | task 3676 | processing task, is_child = 0 1.56.345.252 I slot get_availabl: id 7 | task -1 | selected slot by LRU, t_last = 679702609130 1.56.345.325 I slot launch_slot_: id 7 | task 3677 | processing task, is_child = 0 2.00.855.335 I slot print_timing: id 4 | task 3674 | n_gen = 135, tg = 44.55 t/s, tg_3s = 44.88 t/s 2.00.855.499 I slot print_timing: id 5 | task 3675 | n_gen = 135, tg = 44.55 t/s, tg_3s = 44.88 t/s 2.00.855.664 I slot print_timing: id 6 | task 3676 | n_gen = 135, tg = 44.55 t/s, tg_3s = 44.89 t/s 2.00.855.833 I slot print_timing: id 7 | task 3677 | n_gen = 135, tg = 44.56 t/s, tg_3s = 44.89 t/s 2.03.575.988 I slot print_timing: id 4 | task 3674 | prompt eval time = 1501.95 ms / 1018 tokens ( 1.48 ms per token, 677.78 tokens per second) 2.03.575.991 I slot print_timing: id 4 | task 3674 | eval time = 5728.52 ms / 256 tokens ( 22.46 ms per token, 44.51 tokens per second) 2.03.575.991 I slot print_timing: id 4 | task 3674 | total time = 7230.47 ms / 1274 tokens 2.03.575.992 I slot print_timing: id 4 | task 3674 | graphs reused = 3814 2.03.576.030 I slot release: id 4 | task 3674 | stop processing: n_tokens = 1315, truncated = 0 2.03.576.196 I slot print_timing: id 5 | task 3675 | prompt eval time = 1447.81 ms / 897 tokens ( 1.61 ms per token, 619.56 tokens per second) 2.03.576.197 I slot print_timing: id 5 | task 3675 | eval time = 5728.44 ms / 256 tokens ( 22.46 ms per token, 44.51 tokens per second) 2.03.576.198 I slot print_timing: id 5 | task 3675 | total time = 7176.24 ms / 1153 tokens 2.03.576.198 I slot print_timing: id 5 | task 3675 | graphs reused = 3814 2.03.576.220 I slot release: id 5 | task 3675 | stop processing: n_tokens = 1194, truncated = 0 2.03.576.385 I slot print_timing: id 6 | task 3676 | prompt eval time = 1390.95 ms / 932 tokens ( 1.49 ms per token, 670.05 tokens per second) 2.03.576.386 I slot print_timing: id 6 | task 3676 | eval time = 5728.32 ms / 256 tokens ( 22.46 ms per token, 44.52 tokens per second) 2.03.576.387 I slot print_timing: id 6 | task 3676 | total time = 7119.27 ms / 1188 tokens 2.03.576.387 I slot print_timing: id 6 | task 3676 | graphs reused = 3814 2.03.576.409 I slot release: id 6 | task 3676 | stop processing: n_tokens = 1229, truncated = 0 2.03.576.579 I slot print_timing: id 7 | task 3677 | prompt eval time = 1333.39 ms / 1034 tokens ( 1.29 ms per token, 775.47 tokens per second) 2.03.576.580 I slot print_timing: id 7 | task 3677 | eval time = 5728.23 ms / 256 tokens ( 22.46 ms per token, 44.52 tokens per second) 2.03.576.580 I slot print_timing: id 7 | task 3677 | total time = 7061.62 ms / 1290 tokens 2.03.576.580 I slot print_timing: id 7 | task 3677 | graphs reused = 3814 2.03.576.605 I slot release: id 7 | task 3677 | stop processing: n_tokens = 1331, truncated = 0 2.03.582.557 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 679710495863 2.03.582.670 I slot launch_slot_: id 0 | task 3936 | processing task, is_child = 0 2.03.582.881 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 2.03.738.031 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 672.782 MiB) 2.03.881.298 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 2.04.024.840 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 672.595 MiB) 2.04.170.415 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 679710496068 2.04.170.552 I slot launch_slot_: id 1 | task 3937 | processing task, is_child = 0 2.04.170.828 I slot get_availabl: id 2 | task -1 | selected slot by LRU, t_last = 679710496270 2.04.170.900 I slot launch_slot_: id 2 | task 3938 | processing task, is_child = 0 2.04.171.120 I slot get_availabl: id 3 | task -1 | selected slot by LRU, t_last = 679710496481 2.04.171.195 I slot launch_slot_: id 3 | task 3939 | processing task, is_child = 0 2.08.715.289 I slot print_timing: id 0 | task 3936 | n_gen = 135, tg = 44.58 t/s, tg_3s = 44.91 t/s 2.08.715.459 I slot print_timing: id 1 | task 3937 | n_gen = 135, tg = 44.58 t/s, tg_3s = 44.91 t/s 2.08.715.623 I slot print_timing: id 2 | task 3938 | n_gen = 135, tg = 44.58 t/s, tg_3s = 44.92 t/s 2.08.715.786 I slot print_timing: id 3 | task 3939 | n_gen = 135, tg = 44.59 t/s, tg_3s = 44.92 t/s 2.11.436.132 I slot print_timing: id 0 | task 3936 | prompt eval time = 1537.98 ms / 1033 tokens ( 1.49 ms per token, 671.66 tokens per second) 2.11.436.135 I slot print_timing: id 0 | task 3936 | eval time = 5726.75 ms / 256 tokens ( 22.46 ms per token, 44.53 tokens per second) 2.11.436.135 I slot print_timing: id 0 | task 3936 | total time = 7264.73 ms / 1289 tokens 2.11.436.136 I slot print_timing: id 0 | task 3936 | graphs reused = 4069 2.11.436.165 I slot release: id 0 | task 3936 | stop processing: n_tokens = 1330, truncated = 0 2.11.436.330 I slot print_timing: id 1 | task 3937 | prompt eval time = 1484.16 ms / 963 tokens ( 1.54 ms per token, 648.85 tokens per second) 2.11.436.331 I slot print_timing: id 1 | task 3937 | eval time = 5726.62 ms / 256 tokens ( 22.46 ms per token, 44.53 tokens per second) 2.11.436.332 I slot print_timing: id 1 | task 3937 | total time = 7210.78 ms / 1219 tokens 2.11.436.332 I slot print_timing: id 1 | task 3937 | graphs reused = 4069 2.11.436.359 I slot release: id 1 | task 3937 | stop processing: n_tokens = 1260, truncated = 0 2.11.436.527 I slot print_timing: id 2 | task 3938 | prompt eval time = 1428.13 ms / 980 tokens ( 1.46 ms per token, 686.21 tokens per second) 2.11.436.529 I slot print_timing: id 2 | task 3938 | eval time = 5726.49 ms / 256 tokens ( 22.46 ms per token, 44.53 tokens per second) 2.11.436.529 I slot print_timing: id 2 | task 3938 | total time = 7154.62 ms / 1236 tokens 2.11.436.529 I slot print_timing: id 2 | task 3938 | graphs reused = 4069 2.11.436.554 I slot release: id 2 | task 3938 | stop processing: n_tokens = 1277, truncated = 0 2.11.436.718 I slot print_timing: id 3 | task 3939 | prompt eval time = 1373.14 ms / 1014 tokens ( 1.35 ms per token, 738.45 tokens per second) 2.11.436.720 I slot print_timing: id 3 | task 3939 | eval time = 5726.39 ms / 256 tokens ( 22.46 ms per token, 44.53 tokens per second) 2.11.436.720 I slot print_timing: id 3 | task 3939 | total time = 7099.53 ms / 1270 tokens 2.11.436.720 I slot print_timing: id 3 | task 3939 | graphs reused = 4069 2.11.436.747 I slot release: id 3 | task 3939 | stop processing: n_tokens = 1311, truncated = 0 2.11.443.710 I slot get_availabl: id 4 | task -1 | selected slot by LRU, t_last = 679718331329 2.11.443.829 I slot launch_slot_: id 4 | task 4198 | processing task, is_child = 0 2.11.443.882 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.473 MiB) 2.11.614.359 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 674.595 MiB) 2.11.767.736 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 2.11.918.952 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 675.471 MiB) 2.12.069.870 I slot get_availabl: id 5 | task -1 | selected slot by LRU, t_last = 679718331519 2.12.069.995 I slot launch_slot_: id 5 | task 4199 | processing task, is_child = 0 2.12.070.266 I slot get_availabl: id 6 | task -1 | selected slot by LRU, t_last = 679718331708 2.12.070.341 I slot launch_slot_: id 6 | task 4200 | processing task, is_child = 0 2.12.070.565 I slot get_availabl: id 7 | task -1 | selected slot by LRU, t_last = 679718331905 2.12.070.636 I slot launch_slot_: id 7 | task 4201 | processing task, is_child = 0 2.16.625.643 I slot print_timing: id 4 | task 4198 | n_gen = 135, tg = 44.54 t/s, tg_3s = 44.87 t/s 2.16.625.808 I slot print_timing: id 5 | task 4199 | n_gen = 135, tg = 44.54 t/s, tg_3s = 44.87 t/s 2.16.625.973 I slot print_timing: id 6 | task 4200 | n_gen = 135, tg = 44.54 t/s, tg_3s = 44.87 t/s 2.16.626.138 I slot print_timing: id 7 | task 4201 | n_gen = 135, tg = 44.54 t/s, tg_3s = 44.88 t/s 2.19.347.822 I slot print_timing: id 4 | task 4198 | prompt eval time = 1546.11 ms / 1034 tokens ( 1.50 ms per token, 668.77 tokens per second) 2.19.347.825 I slot print_timing: id 4 | task 4198 | eval time = 5730.86 ms / 256 tokens ( 22.47 ms per token, 44.50 tokens per second) 2.19.347.826 I slot print_timing: id 4 | task 4198 | total time = 7276.97 ms / 1290 tokens 2.19.347.826 I slot print_timing: id 4 | task 4198 | graphs reused = 4324 2.19.347.865 I slot release: id 4 | task 4198 | stop processing: n_tokens = 1331, truncated = 0 2.19.348.029 I slot print_timing: id 5 | task 4199 | prompt eval time = 1492.77 ms / 946 tokens ( 1.58 ms per token, 633.72 tokens per second) 2.19.348.030 I slot print_timing: id 5 | task 4199 | eval time = 5730.70 ms / 256 tokens ( 22.47 ms per token, 44.50 tokens per second) 2.19.348.031 I slot print_timing: id 5 | task 4199 | total time = 7223.47 ms / 1202 tokens 2.19.348.031 I slot print_timing: id 5 | task 4199 | graphs reused = 4324 2.19.348.062 I slot release: id 5 | task 4199 | stop processing: n_tokens = 1243, truncated = 0 2.19.348.228 I slot print_timing: id 6 | task 4200 | prompt eval time = 1436.23 ms / 966 tokens ( 1.49 ms per token, 672.59 tokens per second) 2.19.348.229 I slot print_timing: id 6 | task 4200 | eval time = 5730.64 ms / 256 tokens ( 22.47 ms per token, 44.50 tokens per second) 2.19.348.229 I slot print_timing: id 6 | task 4200 | total time = 7166.87 ms / 1222 tokens 2.19.348.229 I slot print_timing: id 6 | task 4200 | graphs reused = 4324 2.19.348.258 I slot release: id 6 | task 4200 | stop processing: n_tokens = 1263, truncated = 0 2.19.348.418 I slot print_timing: id 7 | task 4201 | prompt eval time = 1377.53 ms / 1034 tokens ( 1.33 ms per token, 750.62 tokens per second) 2.19.348.419 I slot print_timing: id 7 | task 4201 | eval time = 5730.54 ms / 256 tokens ( 22.47 ms per token, 44.50 tokens per second) 2.19.348.420 I slot print_timing: id 7 | task 4201 | total time = 7108.06 ms / 1290 tokens 2.19.348.420 I slot print_timing: id 7 | task 4201 | graphs reused = 4324 2.19.348.443 I slot release: id 7 | task 4201 | stop processing: n_tokens = 1331, truncated = 0 2.19.355.548 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 679726191464 2.19.355.668 I slot launch_slot_: id 0 | task 4460 | processing task, is_child = 0 2.19.355.855 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.410 MiB) 2.19.515.885 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 676.659 MiB) 2.19.663.305 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 674.970 MiB) 2.19.809.829 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 2.19.957.116 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 679726191659 2.19.957.275 I slot launch_slot_: id 1 | task 4461 | processing task, is_child = 0 2.19.957.588 I slot get_availabl: id 2 | task -1 | selected slot by LRU, t_last = 679726191853 2.19.957.665 I slot launch_slot_: id 2 | task 4462 | processing task, is_child = 0 2.19.957.888 I slot get_availabl: id 3 | task -1 | selected slot by LRU, t_last = 679726192046 2.19.957.959 I slot launch_slot_: id 3 | task 4463 | processing task, is_child = 0 2.24.512.301 I slot print_timing: id 0 | task 4460 | n_gen = 135, tg = 44.43 t/s, tg_3s = 44.76 t/s 2.24.512.470 I slot print_timing: id 1 | task 4461 | n_gen = 135, tg = 44.43 t/s, tg_3s = 44.76 t/s 2.24.512.633 I slot print_timing: id 2 | task 4462 | n_gen = 135, tg = 44.43 t/s, tg_3s = 44.77 t/s 2.24.512.801 I slot print_timing: id 3 | task 4463 | n_gen = 135, tg = 44.44 t/s, tg_3s = 44.77 t/s 2.27.236.044 I slot print_timing: id 0 | task 4460 | prompt eval time = 1538.12 ms / 1035 tokens ( 1.49 ms per token, 672.90 tokens per second) 2.27.236.048 I slot print_timing: id 0 | task 4460 | eval time = 5739.75 ms / 256 tokens ( 22.51 ms per token, 44.43 tokens per second) 2.27.236.048 I slot print_timing: id 0 | task 4460 | total time = 7277.87 ms / 1291 tokens 2.27.236.049 I slot print_timing: id 0 | task 4460 | graphs reused = 4579 2.27.236.097 I slot release: id 0 | task 4460 | stop processing: n_tokens = 1332, truncated = 0 2.27.236.284 I slot print_timing: id 1 | task 4461 | prompt eval time = 1485.63 ms / 1035 tokens ( 1.44 ms per token, 696.67 tokens per second) 2.27.236.285 I slot print_timing: id 1 | task 4461 | eval time = 5739.67 ms / 256 tokens ( 22.51 ms per token, 44.43 tokens per second) 2.27.236.286 I slot print_timing: id 1 | task 4461 | total time = 7225.30 ms / 1291 tokens 2.27.236.286 I slot print_timing: id 1 | task 4461 | graphs reused = 4579 2.27.236.315 I slot release: id 1 | task 4461 | stop processing: n_tokens = 1332, truncated = 0 2.27.236.478 I slot print_timing: id 2 | task 4462 | prompt eval time = 1430.51 ms / 949 tokens ( 1.51 ms per token, 663.40 tokens per second) 2.27.236.479 I slot print_timing: id 2 | task 4462 | eval time = 5739.54 ms / 256 tokens ( 22.51 ms per token, 44.43 tokens per second) 2.27.236.480 I slot print_timing: id 2 | task 4462 | total time = 7170.05 ms / 1205 tokens 2.27.236.480 I slot print_timing: id 2 | task 4462 | graphs reused = 4579 2.27.236.501 I slot release: id 2 | task 4462 | stop processing: n_tokens = 1246, truncated = 0 2.27.236.668 I slot print_timing: id 3 | task 4463 | prompt eval time = 1373.78 ms / 1034 tokens ( 1.33 ms per token, 752.67 tokens per second) 2.27.236.669 I slot print_timing: id 3 | task 4463 | eval time = 5739.46 ms / 256 tokens ( 22.51 ms per token, 44.43 tokens per second) 2.27.236.669 I slot print_timing: id 3 | task 4463 | total time = 7113.25 ms / 1290 tokens 2.27.236.669 I slot print_timing: id 3 | task 4463 | graphs reused = 4579 2.27.236.693 I slot release: id 3 | task 4463 | stop processing: n_tokens = 1331, truncated = 0 2.27.243.991 I slot get_availabl: id 4 | task -1 | selected slot by LRU, t_last = 679734103164 2.27.244.142 I slot launch_slot_: id 4 | task 4723 | processing task, is_child = 0 2.27.244.228 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 680.723 MiB) 2.27.404.495 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 673.157 MiB) 2.27.551.634 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 675.346 MiB) 2.27.698.054 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 2.27.845.798 I slot get_availabl: id 5 | task -1 | selected slot by LRU, t_last = 679734103361 2.27.845.921 I slot launch_slot_: id 5 | task 4722 | processing task, is_child = 0 2.27.846.192 I slot get_availabl: id 6 | task -1 | selected slot by LRU, t_last = 679734103557 2.27.846.269 I slot launch_slot_: id 6 | task 4724 | processing task, is_child = 0 2.27.846.513 I slot get_availabl: id 7 | task -1 | selected slot by LRU, t_last = 679734103743 2.27.846.588 I slot launch_slot_: id 7 | task 4725 | processing task, is_child = 0 2.32.381.896 I slot print_timing: id 4 | task 4723 | n_gen = 135, tg = 44.55 t/s, tg_3s = 44.88 t/s 2.32.382.063 I slot print_timing: id 5 | task 4722 | n_gen = 135, tg = 44.55 t/s, tg_3s = 44.88 t/s 2.32.382.231 I slot print_timing: id 6 | task 4724 | n_gen = 135, tg = 44.55 t/s, tg_3s = 44.88 t/s 2.32.382.399 I slot print_timing: id 7 | task 4725 | n_gen = 135, tg = 44.55 t/s, tg_3s = 44.88 t/s 2.35.104.187 I slot print_timing: id 4 | task 4723 | prompt eval time = 1526.95 ms / 939 tokens ( 1.63 ms per token, 614.95 tokens per second) 2.35.104.190 I slot print_timing: id 4 | task 4723 | eval time = 5730.45 ms / 256 tokens ( 22.47 ms per token, 44.50 tokens per second) 2.35.104.190 I slot print_timing: id 4 | task 4723 | total time = 7257.40 ms / 1195 tokens 2.35.104.191 I slot print_timing: id 4 | task 4723 | graphs reused = 4834 2.35.104.222 I slot release: id 4 | task 4723 | stop processing: n_tokens = 1236, truncated = 0 2.35.104.388 I slot print_timing: id 5 | task 4722 | prompt eval time = 1472.75 ms / 967 tokens ( 1.52 ms per token, 656.59 tokens per second) 2.35.104.390 I slot print_timing: id 5 | task 4722 | eval time = 5730.35 ms / 256 tokens ( 22.47 ms per token, 44.50 tokens per second) 2.35.104.391 I slot print_timing: id 5 | task 4722 | total time = 7203.10 ms / 1223 tokens 2.35.104.391 I slot print_timing: id 5 | task 4722 | graphs reused = 4834 2.35.104.431 I slot release: id 5 | task 4722 | stop processing: n_tokens = 1264, truncated = 0 2.35.104.618 I slot print_timing: id 6 | task 4724 | prompt eval time = 1414.84 ms / 1034 tokens ( 1.37 ms per token, 730.83 tokens per second) 2.35.104.620 I slot print_timing: id 6 | task 4724 | eval time = 5730.27 ms / 256 tokens ( 22.47 ms per token, 44.50 tokens per second) 2.35.104.620 I slot print_timing: id 6 | task 4724 | total time = 7145.11 ms / 1290 tokens 2.35.104.620 I slot print_timing: id 6 | task 4724 | graphs reused = 4834 2.35.104.641 I slot release: id 6 | task 4724 | stop processing: n_tokens = 1331, truncated = 0 2.35.104.816 I slot print_timing: id 7 | task 4725 | prompt eval time = 1356.30 ms / 1034 tokens ( 1.31 ms per token, 762.37 tokens per second) 2.35.104.817 I slot print_timing: id 7 | task 4725 | eval time = 5730.23 ms / 256 tokens ( 22.47 ms per token, 44.50 tokens per second) 2.35.104.818 I slot print_timing: id 7 | task 4725 | total time = 7086.52 ms / 1290 tokens 2.35.104.818 I slot print_timing: id 7 | task 4725 | graphs reused = 4834 2.35.104.842 I slot release: id 7 | task 4725 | stop processing: n_tokens = 1331, truncated = 0 2.35.110.927 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 679741991396 2.35.111.040 I slot launch_slot_: id 0 | task 4984 | processing task, is_child = 0 2.35.111.235 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.660 MiB) 2.35.279.170 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 677.284 MiB) 2.35.431.838 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 678.347 MiB) 2.35.581.944 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 680.472 MiB) 2.35.733.085 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 679741991614 2.35.733.225 I slot launch_slot_: id 1 | task 4985 | processing task, is_child = 0 2.35.733.502 I slot get_availabl: id 2 | task -1 | selected slot by LRU, t_last = 679741991800 2.35.733.574 I slot launch_slot_: id 2 | task 4986 | processing task, is_child = 0 2.35.733.799 I slot get_availabl: id 3 | task -1 | selected slot by LRU, t_last = 679741991993 2.35.733.870 I slot launch_slot_: id 3 | task 4987 | processing task, is_child = 0 2.40.263.118 I slot print_timing: id 0 | task 4984 | n_gen = 135, tg = 44.57 t/s, tg_3s = 44.90 t/s 2.40.263.278 I slot print_timing: id 1 | task 4985 | n_gen = 135, tg = 44.57 t/s, tg_3s = 44.90 t/s 2.40.263.440 I slot print_timing: id 2 | task 4986 | n_gen = 135, tg = 44.57 t/s, tg_3s = 44.90 t/s 2.40.263.597 I slot print_timing: id 3 | task 4987 | n_gen = 135, tg = 44.57 t/s, tg_3s = 44.90 t/s 2.42.984.735 I slot print_timing: id 0 | task 4984 | prompt eval time = 1522.30 ms / 1034 tokens ( 1.47 ms per token, 679.24 tokens per second) 2.42.984.737 I slot print_timing: id 0 | task 4984 | eval time = 5728.38 ms / 256 tokens ( 22.46 ms per token, 44.52 tokens per second) 2.42.984.738 I slot print_timing: id 0 | task 4984 | total time = 7250.67 ms / 1290 tokens 2.42.984.738 I slot print_timing: id 0 | task 4984 | graphs reused = 5089 2.42.984.779 I slot release: id 0 | task 4984 | stop processing: n_tokens = 1331, truncated = 0 2.42.984.946 I slot print_timing: id 1 | task 4985 | prompt eval time = 1469.38 ms / 939 tokens ( 1.56 ms per token, 639.05 tokens per second) 2.42.984.947 I slot print_timing: id 1 | task 4985 | eval time = 5728.31 ms / 256 tokens ( 22.46 ms per token, 44.52 tokens per second) 2.42.984.947 I slot print_timing: id 1 | task 4985 | total time = 7197.69 ms / 1195 tokens 2.42.984.948 I slot print_timing: id 1 | task 4985 | graphs reused = 5089 2.42.984.976 I slot release: id 1 | task 4985 | stop processing: n_tokens = 1236, truncated = 0 2.42.985.140 I slot print_timing: id 2 | task 4986 | prompt eval time = 1414.01 ms / 1034 tokens ( 1.37 ms per token, 731.25 tokens per second) 2.42.985.142 I slot print_timing: id 2 | task 4986 | eval time = 5728.13 ms / 256 tokens ( 22.46 ms per token, 44.52 tokens per second) 2.42.985.142 I slot print_timing: id 2 | task 4986 | total time = 7142.15 ms / 1290 tokens 2.42.985.142 I slot print_timing: id 2 | task 4986 | graphs reused = 5089 2.42.985.171 I slot release: id 2 | task 4986 | stop processing: n_tokens = 1331, truncated = 0 2.42.985.334 I slot print_timing: id 3 | task 4987 | prompt eval time = 1356.88 ms / 1034 tokens ( 1.31 ms per token, 762.04 tokens per second) 2.42.985.335 I slot print_timing: id 3 | task 4987 | eval time = 5728.09 ms / 256 tokens ( 22.46 ms per token, 44.52 tokens per second) 2.42.985.335 I slot print_timing: id 3 | task 4987 | total time = 7084.97 ms / 1290 tokens 2.42.985.336 I slot print_timing: id 3 | task 4987 | graphs reused = 5089 2.42.985.366 I slot release: id 3 | task 4987 | stop processing: n_tokens = 1331, truncated = 0 2.42.992.289 I slot get_availabl: id 4 | task -1 | selected slot by LRU, t_last = 679749859521 2.42.992.424 I slot launch_slot_: id 4 | task 5246 | processing task, is_child = 0 2.42.992.473 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 2.43.156.376 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 676.221 MiB) 2.43.303.890 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 677.471 MiB) 2.43.452.661 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 2.43.599.887 I slot get_availabl: id 5 | task -1 | selected slot by LRU, t_last = 679749859731 2.43.600.019 I slot launch_slot_: id 5 | task 5247 | processing task, is_child = 0 2.43.600.292 I slot get_availabl: id 6 | task -1 | selected slot by LRU, t_last = 679749859940 2.43.600.366 I slot launch_slot_: id 6 | task 5248 | processing task, is_child = 0 2.43.600.588 I slot get_availabl: id 7 | task -1 | selected slot by LRU, t_last = 679749860141 2.43.600.662 I slot launch_slot_: id 7 | task 5249 | processing task, is_child = 0 2.48.138.766 I slot print_timing: id 4 | task 5246 | n_gen = 135, tg = 44.52 t/s, tg_3s = 44.85 t/s 2.48.138.931 I slot print_timing: id 5 | task 5247 | n_gen = 135, tg = 44.52 t/s, tg_3s = 44.85 t/s 2.48.139.104 I slot print_timing: id 6 | task 5248 | n_gen = 135, tg = 44.52 t/s, tg_3s = 44.85 t/s 2.48.139.274 I slot print_timing: id 7 | task 5249 | n_gen = 135, tg = 44.52 t/s, tg_3s = 44.85 t/s 2.50.864.265 I slot print_timing: id 4 | task 5246 | prompt eval time = 1527.83 ms / 1031 tokens ( 1.48 ms per token, 674.81 tokens per second) 2.50.864.267 I slot print_timing: id 4 | task 5246 | eval time = 5735.58 ms / 256 tokens ( 22.49 ms per token, 44.46 tokens per second) 2.50.864.268 I slot print_timing: id 4 | task 5246 | total time = 7263.41 ms / 1287 tokens 2.50.864.269 I slot print_timing: id 4 | task 5246 | graphs reused = 5343 2.50.864.303 I slot release: id 4 | task 5246 | stop processing: n_tokens = 1328, truncated = 0 2.50.864.462 I slot print_timing: id 5 | task 5247 | prompt eval time = 1471.99 ms / 1035 tokens ( 1.42 ms per token, 703.13 tokens per second) 2.50.864.464 I slot print_timing: id 5 | task 5247 | eval time = 5735.47 ms / 256 tokens ( 22.49 ms per token, 44.46 tokens per second) 2.50.864.464 I slot print_timing: id 5 | task 5247 | total time = 7207.46 ms / 1291 tokens 2.50.864.464 I slot print_timing: id 5 | task 5247 | graphs reused = 5343 2.50.864.490 I slot release: id 5 | task 5247 | stop processing: n_tokens = 1332, truncated = 0 2.50.864.647 I slot print_timing: id 6 | task 5248 | prompt eval time = 1413.83 ms / 883 tokens ( 1.60 ms per token, 624.54 tokens per second) 2.50.864.648 I slot print_timing: id 6 | task 5248 | eval time = 5735.36 ms / 256 tokens ( 22.49 ms per token, 44.46 tokens per second) 2.50.864.648 I slot print_timing: id 6 | task 5248 | total time = 7149.19 ms / 1139 tokens 2.50.864.648 I slot print_timing: id 6 | task 5248 | graphs reused = 5343 2.50.864.670 I slot release: id 6 | task 5248 | stop processing: n_tokens = 1180, truncated = 0 2.50.864.834 I slot print_timing: id 7 | task 5249 | prompt eval time = 1357.28 ms / 1034 tokens ( 1.31 ms per token, 761.82 tokens per second) 2.50.864.835 I slot print_timing: id 7 | task 5249 | eval time = 5735.30 ms / 256 tokens ( 22.49 ms per token, 44.46 tokens per second) 2.50.864.835 I slot print_timing: id 7 | task 5249 | total time = 7092.58 ms / 1290 tokens 2.50.864.836 I slot print_timing: id 7 | task 5249 | graphs reused = 5343 2.50.864.859 I slot release: id 7 | task 5249 | stop processing: n_tokens = 1331, truncated = 0 2.50.871.811 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 679757740079 2.50.871.940 I slot launch_slot_: id 0 | task 5508 | processing task, is_child = 0 2.50.872.114 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.785 MiB) 2.51.030.663 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.785 MiB) 2.51.177.302 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 676.408 MiB) 2.51.321.250 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 2.51.467.983 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 679757740276 2.51.468.120 I slot launch_slot_: id 1 | task 5509 | processing task, is_child = 0 2.51.468.395 I slot get_availabl: id 2 | task -1 | selected slot by LRU, t_last = 679757740469 2.51.468.468 I slot launch_slot_: id 2 | task 5510 | processing task, is_child = 0 2.51.468.687 I slot get_availabl: id 3 | task -1 | selected slot by LRU, t_last = 679757740665 2.51.468.759 I slot launch_slot_: id 3 | task 5511 | processing task, is_child = 0 2.56.028.905 I slot print_timing: id 0 | task 5508 | n_gen = 135, tg = 44.55 t/s, tg_3s = 44.88 t/s 2.56.029.134 I slot print_timing: id 1 | task 5509 | n_gen = 135, tg = 44.55 t/s, tg_3s = 44.88 t/s 2.56.029.350 I slot print_timing: id 2 | task 5510 | n_gen = 135, tg = 44.55 t/s, tg_3s = 44.88 t/s 2.56.029.551 I slot print_timing: id 3 | task 5511 | n_gen = 135, tg = 44.55 t/s, tg_3s = 44.88 t/s 2.58.753.311 I slot print_timing: id 0 | task 5508 | prompt eval time = 1552.02 ms / 1036 tokens ( 1.50 ms per token, 667.52 tokens per second) 2.58.753.313 I slot print_timing: id 0 | task 5508 | eval time = 5732.35 ms / 256 tokens ( 22.48 ms per token, 44.48 tokens per second) 2.58.753.314 I slot print_timing: id 0 | task 5508 | total time = 7284.36 ms / 1292 tokens 2.58.753.315 I slot print_timing: id 0 | task 5508 | graphs reused = 5598 2.58.753.353 I slot release: id 0 | task 5508 | stop processing: n_tokens = 1333, truncated = 0 2.58.753.516 I slot print_timing: id 1 | task 5509 | prompt eval time = 1499.35 ms / 968 tokens ( 1.55 ms per token, 645.61 tokens per second) 2.58.753.518 I slot print_timing: id 1 | task 5509 | eval time = 5732.28 ms / 256 tokens ( 22.48 ms per token, 44.48 tokens per second) 2.58.753.518 I slot print_timing: id 1 | task 5509 | total time = 7231.63 ms / 1224 tokens 2.58.753.519 I slot print_timing: id 1 | task 5509 | graphs reused = 5598 2.58.753.549 I slot release: id 1 | task 5509 | stop processing: n_tokens = 1265, truncated = 0 2.58.753.714 I slot print_timing: id 2 | task 5510 | prompt eval time = 1445.05 ms / 1019 tokens ( 1.42 ms per token, 705.17 tokens per second) 2.58.753.716 I slot print_timing: id 2 | task 5510 | eval time = 5732.22 ms / 256 tokens ( 22.48 ms per token, 44.49 tokens per second) 2.58.753.717 I slot print_timing: id 2 | task 5510 | total time = 7177.27 ms / 1275 tokens 2.58.753.717 I slot print_timing: id 2 | task 5510 | graphs reused = 5598 2.58.753.746 I slot release: id 2 | task 5510 | stop processing: n_tokens = 1316, truncated = 0 2.58.753.913 I slot print_timing: id 3 | task 5511 | prompt eval time = 1388.92 ms / 1034 tokens ( 1.34 ms per token, 744.46 tokens per second) 2.58.753.914 I slot print_timing: id 3 | task 5511 | eval time = 5732.17 ms / 256 tokens ( 22.48 ms per token, 44.49 tokens per second) 2.58.753.915 I slot print_timing: id 3 | task 5511 | total time = 7121.09 ms / 1290 tokens 2.58.753.915 I slot print_timing: id 3 | task 5511 | graphs reused = 5598 2.58.753.939 I slot release: id 3 | task 5511 | stop processing: n_tokens = 1331, truncated = 0 2.58.759.736 I slot get_availabl: id 4 | task -1 | selected slot by LRU, t_last = 679765619602 2.58.759.936 I slot launch_slot_: id 4 | task 5770 | processing task, is_child = 0 2.58.760.030 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 675.783 MiB) 2.58.932.940 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 677.534 MiB) 2.59.086.087 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 2.59.239.979 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 2.59.391.876 I slot get_availabl: id 5 | task -1 | selected slot by LRU, t_last = 679765619789 2.59.392.002 I slot launch_slot_: id 5 | task 5771 | processing task, is_child = 0 2.59.392.273 I slot get_availabl: id 6 | task -1 | selected slot by LRU, t_last = 679765619969 2.59.392.343 I slot launch_slot_: id 6 | task 5772 | processing task, is_child = 0 2.59.392.567 I slot get_availabl: id 7 | task -1 | selected slot by LRU, t_last = 679765620158 2.59.392.643 I slot launch_slot_: id 7 | task 5773 | processing task, is_child = 0 3.03.911.371 I slot print_timing: id 4 | task 5770 | n_gen = 135, tg = 44.54 t/s, tg_3s = 44.88 t/s 3.03.911.529 I slot print_timing: id 5 | task 5771 | n_gen = 135, tg = 44.54 t/s, tg_3s = 44.88 t/s 3.03.911.684 I slot print_timing: id 6 | task 5772 | n_gen = 135, tg = 44.55 t/s, tg_3s = 44.88 t/s 3.03.911.844 I slot print_timing: id 7 | task 5773 | n_gen = 135, tg = 44.55 t/s, tg_3s = 44.88 t/s 3.06.634.141 I slot print_timing: id 4 | task 5770 | prompt eval time = 1510.20 ms / 1034 tokens ( 1.46 ms per token, 684.68 tokens per second) 3.06.634.144 I slot print_timing: id 4 | task 5770 | eval time = 5731.11 ms / 256 tokens ( 22.47 ms per token, 44.49 tokens per second) 3.06.634.144 I slot print_timing: id 4 | task 5770 | total time = 7241.30 ms / 1290 tokens 3.06.634.145 I slot print_timing: id 4 | task 5770 | graphs reused = 5853 3.06.634.175 I slot release: id 4 | task 5770 | stop processing: n_tokens = 1331, truncated = 0 3.06.634.345 I slot print_timing: id 5 | task 5771 | prompt eval time = 1456.37 ms / 1034 tokens ( 1.41 ms per token, 709.98 tokens per second) 3.06.634.346 I slot print_timing: id 5 | task 5771 | eval time = 5731.05 ms / 256 tokens ( 22.47 ms per token, 44.49 tokens per second) 3.06.634.347 I slot print_timing: id 5 | task 5771 | total time = 7187.42 ms / 1290 tokens 3.06.634.347 I slot print_timing: id 5 | task 5771 | graphs reused = 5853 3.06.634.379 I slot release: id 5 | task 5771 | stop processing: n_tokens = 1331, truncated = 0 3.06.634.549 I slot print_timing: id 6 | task 5772 | prompt eval time = 1399.60 ms / 933 tokens ( 1.50 ms per token, 666.62 tokens per second) 3.06.634.550 I slot print_timing: id 6 | task 5772 | eval time = 5731.01 ms / 256 tokens ( 22.47 ms per token, 44.49 tokens per second) 3.06.634.550 I slot print_timing: id 6 | task 5772 | total time = 7130.61 ms / 1189 tokens 3.06.634.551 I slot print_timing: id 6 | task 5772 | graphs reused = 5853 3.06.634.580 I slot release: id 6 | task 5772 | stop processing: n_tokens = 1230, truncated = 0 3.06.634.786 I slot print_timing: id 7 | task 5773 | prompt eval time = 1341.63 ms / 932 tokens ( 1.44 ms per token, 694.68 tokens per second) 3.06.634.788 I slot print_timing: id 7 | task 5773 | eval time = 5730.98 ms / 256 tokens ( 22.47 ms per token, 44.49 tokens per second) 3.06.634.788 I slot print_timing: id 7 | task 5773 | total time = 7072.62 ms / 1188 tokens 3.06.634.788 I slot print_timing: id 7 | task 5773 | graphs reused = 5853 3.06.634.811 I slot release: id 7 | task 5773 | stop processing: n_tokens = 1229, truncated = 0 3.06.640.670 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 679773508652 3.06.640.875 I slot launch_slot_: id 0 | task 6032 | processing task, is_child = 0 3.06.641.222 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 3.06.805.548 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 675.783 MiB) 3.06.955.478 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 3.07.102.421 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 3.07.249.905 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 679773508849 3.07.250.042 I slot launch_slot_: id 1 | task 6033 | processing task, is_child = 0 3.07.250.345 I slot get_availabl: id 2 | task -1 | selected slot by LRU, t_last = 679773509046 3.07.250.419 I slot launch_slot_: id 2 | task 6034 | processing task, is_child = 0 3.07.250.663 I slot get_availabl: id 3 | task -1 | selected slot by LRU, t_last = 679773509239 3.07.250.741 I slot launch_slot_: id 3 | task 6035 | processing task, is_child = 0 3.11.798.931 I slot print_timing: id 0 | task 6032 | n_gen = 135, tg = 44.55 t/s, tg_3s = 44.88 t/s 3.11.799.089 I slot print_timing: id 1 | task 6033 | n_gen = 135, tg = 44.55 t/s, tg_3s = 44.88 t/s 3.11.799.246 I slot print_timing: id 2 | task 6034 | n_gen = 135, tg = 44.55 t/s, tg_3s = 44.88 t/s 3.11.799.404 I slot print_timing: id 3 | task 6035 | n_gen = 135, tg = 44.55 t/s, tg_3s = 44.88 t/s 3.14.520.780 I slot print_timing: id 0 | task 6032 | prompt eval time = 1539.95 ms / 1035 tokens ( 1.49 ms per token, 672.10 tokens per second) 3.14.520.783 I slot print_timing: id 0 | task 6032 | eval time = 5729.90 ms / 256 tokens ( 22.47 ms per token, 44.50 tokens per second) 3.14.520.783 I slot print_timing: id 0 | task 6032 | total time = 7269.85 ms / 1291 tokens 3.14.520.784 I slot print_timing: id 0 | task 6032 | graphs reused = 6108 3.14.520.826 I slot release: id 0 | task 6032 | stop processing: n_tokens = 1332, truncated = 0 3.14.520.992 I slot print_timing: id 1 | task 6033 | prompt eval time = 1486.97 ms / 934 tokens ( 1.59 ms per token, 628.12 tokens per second) 3.14.520.993 I slot print_timing: id 1 | task 6033 | eval time = 5729.83 ms / 256 tokens ( 22.47 ms per token, 44.50 tokens per second) 3.14.520.994 I slot print_timing: id 1 | task 6033 | total time = 7216.80 ms / 1190 tokens 3.14.520.994 I slot print_timing: id 1 | task 6033 | graphs reused = 6108 3.14.521.024 I slot release: id 1 | task 6033 | stop processing: n_tokens = 1231, truncated = 0 3.14.521.184 I slot print_timing: id 2 | task 6034 | prompt eval time = 1431.40 ms / 1034 tokens ( 1.38 ms per token, 722.37 tokens per second) 3.14.521.186 I slot print_timing: id 2 | task 6034 | eval time = 5729.78 ms / 256 tokens ( 22.47 ms per token, 44.50 tokens per second) 3.14.521.186 I slot print_timing: id 2 | task 6034 | total time = 7161.18 ms / 1290 tokens 3.14.521.186 I slot print_timing: id 2 | task 6034 | graphs reused = 6108 3.14.521.216 I slot release: id 2 | task 6034 | stop processing: n_tokens = 1331, truncated = 0 3.14.521.378 I slot print_timing: id 3 | task 6035 | prompt eval time = 1374.20 ms / 966 tokens ( 1.42 ms per token, 702.96 tokens per second) 3.14.521.380 I slot print_timing: id 3 | task 6035 | eval time = 5729.73 ms / 256 tokens ( 22.47 ms per token, 44.50 tokens per second) 3.14.521.380 I slot print_timing: id 3 | task 6035 | total time = 7103.92 ms / 1222 tokens 3.14.521.380 I slot print_timing: id 3 | task 6035 | graphs reused = 6108 3.14.521.405 I slot release: id 3 | task 6035 | stop processing: n_tokens = 1263, truncated = 0 3.14.527.056 I slot get_availabl: id 4 | task -1 | selected slot by LRU, t_last = 679781389474 3.14.527.257 I slot launch_slot_: id 4 | task 6294 | processing task, is_child = 0 3.14.527.348 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.535 MiB) 3.14.690.862 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.785 MiB) 3.14.839.272 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 672.282 MiB) 3.14.991.645 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 3.15.142.430 I slot get_availabl: id 5 | task -1 | selected slot by LRU, t_last = 679781389679 3.15.142.564 I slot launch_slot_: id 5 | task 6295 | processing task, is_child = 0 3.15.142.863 I slot get_availabl: id 6 | task -1 | selected slot by LRU, t_last = 679781389879 3.15.142.936 I slot launch_slot_: id 6 | task 6296 | processing task, is_child = 0 3.15.143.155 I slot get_availabl: id 7 | task -1 | selected slot by LRU, t_last = 679781390111 3.15.143.225 I slot launch_slot_: id 7 | task 6297 | processing task, is_child = 0 3.19.712.757 I slot print_timing: id 4 | task 6294 | n_gen = 135, tg = 44.48 t/s, tg_3s = 44.81 t/s 3.19.712.923 I slot print_timing: id 5 | task 6295 | n_gen = 135, tg = 44.48 t/s, tg_3s = 44.81 t/s 3.19.713.094 I slot print_timing: id 6 | task 6296 | n_gen = 135, tg = 44.48 t/s, tg_3s = 44.81 t/s 3.19.713.259 I slot print_timing: id 7 | task 6297 | n_gen = 135, tg = 44.48 t/s, tg_3s = 44.81 t/s 3.22.436.333 I slot print_timing: id 4 | task 6294 | prompt eval time = 1556.50 ms / 1034 tokens ( 1.51 ms per token, 664.31 tokens per second) 3.22.436.336 I slot print_timing: id 4 | task 6294 | eval time = 5736.41 ms / 256 tokens ( 22.50 ms per token, 44.45 tokens per second) 3.22.436.336 I slot print_timing: id 4 | task 6294 | total time = 7292.91 ms / 1290 tokens 3.22.436.337 I slot print_timing: id 4 | task 6294 | graphs reused = 6363 3.22.436.377 I slot release: id 4 | task 6294 | stop processing: n_tokens = 1331, truncated = 0 3.22.436.548 I slot print_timing: id 5 | task 6295 | prompt eval time = 1501.28 ms / 1034 tokens ( 1.45 ms per token, 688.74 tokens per second) 3.22.436.550 I slot print_timing: id 5 | task 6295 | eval time = 5736.33 ms / 256 tokens ( 22.50 ms per token, 44.45 tokens per second) 3.22.436.550 I slot print_timing: id 5 | task 6295 | total time = 7237.61 ms / 1290 tokens 3.22.436.550 I slot print_timing: id 5 | task 6295 | graphs reused = 6363 3.22.436.583 I slot release: id 5 | task 6295 | stop processing: n_tokens = 1331, truncated = 0 3.22.436.764 I slot print_timing: id 6 | task 6296 | prompt eval time = 1443.31 ms / 1033 tokens ( 1.40 ms per token, 715.72 tokens per second) 3.22.436.766 I slot print_timing: id 6 | task 6296 | eval time = 5736.28 ms / 256 tokens ( 22.50 ms per token, 44.45 tokens per second) 3.22.436.767 I slot print_timing: id 6 | task 6296 | total time = 7179.59 ms / 1289 tokens 3.22.436.767 I slot print_timing: id 6 | task 6296 | graphs reused = 6363 3.22.436.797 I slot release: id 6 | task 6296 | stop processing: n_tokens = 1330, truncated = 0 3.22.436.974 I slot print_timing: id 7 | task 6297 | prompt eval time = 1384.22 ms / 941 tokens ( 1.47 ms per token, 679.80 tokens per second) 3.22.436.976 I slot print_timing: id 7 | task 6297 | eval time = 5736.23 ms / 256 tokens ( 22.50 ms per token, 44.45 tokens per second) 3.22.436.976 I slot print_timing: id 7 | task 6297 | total time = 7120.46 ms / 1197 tokens 3.22.436.976 I slot print_timing: id 7 | task 6297 | graphs reused = 6363 3.22.436.999 I slot release: id 7 | task 6297 | stop processing: n_tokens = 1238, truncated = 0 3.27.405.745 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 679789276125 3.27.405.976 I slot launch_slot_: id 0 | task 6556 | processing task, is_child = 0 3.27.406.244 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.848 MiB) 3.27.578.519 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 677.596 MiB) 3.27.733.455 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 680.785 MiB) 3.27.884.478 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 3.28.035.122 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 679789276324 3.28.035.268 I slot launch_slot_: id 1 | task 6557 | processing task, is_child = 0 3.28.035.566 I slot get_availabl: id 2 | task -1 | selected slot by LRU, t_last = 679789276515 3.28.035.640 I slot launch_slot_: id 2 | task 6558 | processing task, is_child = 0 3.28.035.860 I slot get_availabl: id 3 | task -1 | selected slot by LRU, t_last = 679789276705 3.28.035.930 I slot launch_slot_: id 3 | task 6559 | processing task, is_child = 0 3.28.036.106 I slot get_availabl: id 4 | task -1 | selected slot by LRU, t_last = 679797191676 3.28.036.175 I slot launch_slot_: id 4 | task 6560 | processing task, is_child = 0 3.28.036.307 I slot get_availabl: id 5 | task -1 | selected slot by LRU, t_last = 679797191883 3.28.036.381 I slot launch_slot_: id 5 | task 6561 | processing task, is_child = 0 3.28.036.470 I slot get_availabl: id 6 | task -1 | selected slot by LRU, t_last = 679797192097 3.28.036.538 I slot launch_slot_: id 6 | task 6562 | processing task, is_child = 0 3.28.036.588 I slot get_availabl: id 7 | task -1 | selected slot by LRU, t_last = 679797192299 3.28.036.659 I slot launch_slot_: id 7 | task 6563 | processing task, is_child = 0 3.33.442.229 I slot print_timing: id 0 | task 6556 | n_gen = 100, tg = 32.74 t/s, tg_3s = 33.07 t/s 3.33.442.403 I slot print_timing: id 1 | task 6557 | n_gen = 100, tg = 32.74 t/s, tg_3s = 33.07 t/s 3.33.442.575 I slot print_timing: id 2 | task 6558 | n_gen = 100, tg = 32.74 t/s, tg_3s = 33.07 t/s 3.33.986.780 I slot print_timing: id 3 | task 6559 | n_gen = 124, tg = 40.94 t/s, tg_3s = 41.27 t/s 3.33.986.955 I slot print_timing: id 4 | task 6560 | n_gen = 124, tg = 40.94 t/s, tg_3s = 41.28 t/s 3.34.270.222 I slot print_timing: id 5 | task 6561 | n_gen = 136, tg = 44.90 t/s, tg_3s = 45.23 t/s 3.34.270.402 I slot print_timing: id 6 | task 6562 | n_gen = 136, tg = 44.90 t/s, tg_3s = 45.23 t/s 3.34.357.648 I slot print_timing: id 7 | task 6563 | n_gen = 139, tg = 45.77 t/s, tg_3s = 46.10 t/s 3.36.456.399 I slot print_timing: id 0 | task 6556 | n_gen = 238, tg = 39.25 t/s, tg_3s = 45.78 t/s 3.36.456.569 I slot print_timing: id 1 | task 6557 | n_gen = 238, tg = 39.25 t/s, tg_3s = 45.78 t/s 3.36.456.742 I slot print_timing: id 2 | task 6558 | n_gen = 238, tg = 39.25 t/s, tg_3s = 45.78 t/s 3.36.849.613 I slot print_timing: id 0 | task 6556 | prompt eval time = 2381.84 ms / 1034 tokens ( 2.30 ms per token, 434.12 tokens per second) 3.36.849.615 I slot print_timing: id 0 | task 6556 | eval time = 6431.10 ms / 256 tokens ( 25.22 ms per token, 39.65 tokens per second) 3.36.849.616 I slot print_timing: id 0 | task 6556 | total time = 8812.94 ms / 1290 tokens 3.36.849.617 I slot print_timing: id 0 | task 6556 | graphs reused = 6615 3.36.849.660 I slot release: id 0 | task 6556 | stop processing: n_tokens = 1331, truncated = 0 3.36.849.852 I slot print_timing: id 1 | task 6557 | prompt eval time = 2328.32 ms / 1034 tokens ( 2.25 ms per token, 444.10 tokens per second) 3.36.849.854 I slot print_timing: id 1 | task 6557 | eval time = 6431.07 ms / 256 tokens ( 25.22 ms per token, 39.65 tokens per second) 3.36.849.854 I slot print_timing: id 1 | task 6557 | total time = 8759.39 ms / 1290 tokens 3.36.849.854 I slot print_timing: id 1 | task 6557 | graphs reused = 6615 3.36.849.890 I slot release: id 1 | task 6557 | stop processing: n_tokens = 1331, truncated = 0 3.36.850.066 I slot print_timing: id 2 | task 6558 | prompt eval time = 2272.93 ms / 1034 tokens ( 2.20 ms per token, 454.92 tokens per second) 3.36.850.067 I slot print_timing: id 2 | task 6558 | eval time = 6431.02 ms / 256 tokens ( 25.22 ms per token, 39.65 tokens per second) 3.36.850.067 I slot print_timing: id 2 | task 6558 | total time = 8703.95 ms / 1290 tokens 3.36.850.068 I slot print_timing: id 2 | task 6558 | graphs reused = 6615 3.36.850.103 I slot release: id 2 | task 6558 | stop processing: n_tokens = 1331, truncated = 0 3.36.878.110 I slot print_timing: id 3 | task 6559 | prompt eval time = 2778.48 ms / 1034 tokens ( 2.69 ms per token, 372.15 tokens per second) 3.36.878.113 I slot print_timing: id 3 | task 6559 | eval time = 5895.63 ms / 256 tokens ( 23.12 ms per token, 43.25 tokens per second) 3.36.878.114 I slot print_timing: id 3 | task 6559 | total time = 8674.11 ms / 1290 tokens 3.36.878.114 I slot print_timing: id 3 | task 6559 | graphs reused = 6615 3.36.878.149 I slot release: id 3 | task 6559 | stop processing: n_tokens = 1331, truncated = 0 3.36.878.326 I slot print_timing: id 4 | task 6560 | prompt eval time = 2092.69 ms / 927 tokens ( 2.26 ms per token, 442.97 tokens per second) 3.36.878.327 I slot print_timing: id 4 | task 6560 | eval time = 5895.59 ms / 256 tokens ( 23.12 ms per token, 43.25 tokens per second) 3.36.878.327 I slot print_timing: id 4 | task 6560 | total time = 7988.27 ms / 1183 tokens 3.36.878.328 I slot print_timing: id 4 | task 6560 | graphs reused = 6615 3.36.878.356 I slot release: id 4 | task 6560 | stop processing: n_tokens = 1224, truncated = 0 3.36.878.890 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 679811604960 3.36.878.961 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 3.37.046.188 I slot launch_slot_: id 0 | task 6823 | processing task, is_child = 0 3.37.046.250 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 3.37.199.522 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 675.408 MiB) 3.37.349.731 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 675.346 MiB) 3.37.500.102 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.785 MiB) 3.37.657.895 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 679811605189 3.37.658.036 I slot launch_slot_: id 1 | task 6824 | processing task, is_child = 0 3.37.658.177 I slot get_availabl: id 2 | task -1 | selected slot by LRU, t_last = 679811605403 3.37.658.249 I slot launch_slot_: id 2 | task 6825 | processing task, is_child = 0 3.37.658.339 I slot get_availabl: id 3 | task -1 | selected slot by LRU, t_last = 679811633449 3.37.658.414 I slot launch_slot_: id 3 | task 6826 | processing task, is_child = 0 3.37.658.459 I slot get_availabl: id 4 | task -1 | selected slot by LRU, t_last = 679811633656 3.37.658.527 I slot launch_slot_: id 4 | task 6827 | processing task, is_child = 0 3.38.520.415 I slot print_timing: id 5 | task 6561 | prompt eval time = 2318.74 ms / 1034 tokens ( 2.24 ms per token, 445.93 tokens per second) 3.38.520.417 I slot print_timing: id 5 | task 6561 | eval time = 7256.93 ms / 256 tokens ( 28.46 ms per token, 35.14 tokens per second) 3.38.520.418 I slot print_timing: id 5 | task 6561 | total time = 9575.66 ms / 1290 tokens 3.38.520.419 I slot print_timing: id 5 | task 6561 | graphs reused = 6615 3.38.520.457 I slot release: id 5 | task 6561 | stop processing: n_tokens = 1331, truncated = 0 3.38.520.676 I slot print_timing: id 6 | task 6562 | prompt eval time = 1552.93 ms / 942 tokens ( 1.65 ms per token, 606.59 tokens per second) 3.38.520.677 I slot print_timing: id 6 | task 6562 | eval time = 7256.94 ms / 256 tokens ( 28.46 ms per token, 35.14 tokens per second) 3.38.520.677 I slot print_timing: id 6 | task 6562 | total time = 8809.87 ms / 1198 tokens 3.38.520.677 I slot print_timing: id 6 | task 6562 | graphs reused = 6615 3.38.520.709 I slot release: id 6 | task 6562 | stop processing: n_tokens = 1239, truncated = 0 3.38.520.933 I slot print_timing: id 7 | task 6563 | n_gen = 255, tg = 35.38 t/s, tg_3s = 27.86 t/s 3.39.213.496 I slot print_timing: id 7 | task 6563 | prompt eval time = 1576.25 ms / 1034 tokens ( 1.52 ms per token, 655.99 tokens per second) 3.39.213.499 I slot print_timing: id 7 | task 6563 | eval time = 7870.78 ms / 256 tokens ( 30.87 ms per token, 32.40 tokens per second) 3.39.213.500 I slot print_timing: id 7 | task 6563 | total time = 9447.04 ms / 1290 tokens 3.39.213.500 I slot print_timing: id 7 | task 6563 | graphs reused = 6616 3.39.213.539 I slot release: id 7 | task 6563 | stop processing: n_tokens = 1331, truncated = 0 3.39.213.553 I slot get_availabl: id 5 | task -1 | selected slot by LRU, t_last = 679813275757 3.39.213.618 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 675.471 MiB) 3.39.366.201 I slot launch_slot_: id 5 | task 6830 | processing task, is_child = 0 3.39.366.266 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 3.39.515.741 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 677.471 MiB) 3.39.671.401 I slot get_availabl: id 6 | task -1 | selected slot by LRU, t_last = 679813276011 3.39.671.550 I slot launch_slot_: id 6 | task 6831 | processing task, is_child = 0 3.39.671.597 I slot get_availabl: id 7 | task -1 | selected slot by LRU, t_last = 679813968839 3.39.671.673 I slot launch_slot_: id 7 | task 6832 | processing task, is_child = 0 3.41.199.550 I slot print_timing: id 4 | task 6827 | prompt processing, n_tokens = 927, progress = 1.00, t = 3.31 s / 279.72 tokens per second 3.43.582.082 I slot print_timing: id 0 | task 6823 | n_gen = 100, tg = 31.51 t/s, tg_3s = 31.82 t/s 3.43.582.259 I slot print_timing: id 1 | task 6824 | n_gen = 100, tg = 31.51 t/s, tg_3s = 31.82 t/s 3.43.582.432 I slot print_timing: id 2 | task 6825 | n_gen = 100, tg = 31.51 t/s, tg_3s = 31.83 t/s 3.44.213.800 I slot print_timing: id 3 | task 6826 | n_gen = 128, tg = 42.13 t/s, tg_3s = 42.46 t/s 3.44.410.032 I slot print_timing: id 4 | task 6827 | n_gen = 136, tg = 44.96 t/s, tg_3s = 45.29 t/s 3.44.410.203 I slot print_timing: id 5 | task 6830 | n_gen = 136, tg = 44.96 t/s, tg_3s = 45.29 t/s 3.44.410.376 I slot print_timing: id 6 | task 6831 | n_gen = 136, tg = 44.96 t/s, tg_3s = 45.29 t/s 3.44.497.564 I slot print_timing: id 7 | task 6832 | n_gen = 139, tg = 45.82 t/s, tg_3s = 46.15 t/s 3.46.593.692 I slot print_timing: id 0 | task 6823 | n_gen = 238, tg = 38.51 t/s, tg_3s = 45.82 t/s 3.46.593.871 I slot print_timing: id 1 | task 6824 | n_gen = 238, tg = 38.51 t/s, tg_3s = 45.82 t/s 3.46.594.048 I slot print_timing: id 2 | task 6825 | n_gen = 238, tg = 38.51 t/s, tg_3s = 45.82 t/s 3.46.986.117 I slot print_timing: id 0 | task 6823 | prompt eval time = 2781.20 ms / 1034 tokens ( 2.69 ms per token, 371.78 tokens per second) 3.46.986.119 I slot print_timing: id 0 | task 6823 | eval time = 6546.37 ms / 256 tokens ( 25.67 ms per token, 38.95 tokens per second) 3.46.986.120 I slot print_timing: id 0 | task 6823 | total time = 9327.57 ms / 1290 tokens 3.46.986.121 I slot print_timing: id 0 | task 6823 | graphs reused = 6867 3.46.986.166 I slot release: id 0 | task 6823 | stop processing: n_tokens = 1331, truncated = 0 3.46.986.344 I slot print_timing: id 1 | task 6824 | prompt eval time = 2727.97 ms / 887 tokens ( 3.08 ms per token, 325.15 tokens per second) 3.46.986.346 I slot print_timing: id 1 | task 6824 | eval time = 6546.32 ms / 256 tokens ( 25.67 ms per token, 38.95 tokens per second) 3.46.986.347 I slot print_timing: id 1 | task 6824 | total time = 9274.29 ms / 1143 tokens 3.46.986.347 I slot print_timing: id 1 | task 6824 | graphs reused = 6867 3.46.986.374 I slot release: id 1 | task 6824 | stop processing: n_tokens = 1184, truncated = 0 3.46.986.550 I slot print_timing: id 2 | task 6825 | prompt eval time = 2671.10 ms / 951 tokens ( 2.81 ms per token, 356.03 tokens per second) 3.46.986.551 I slot print_timing: id 2 | task 6825 | eval time = 6546.27 ms / 256 tokens ( 25.67 ms per token, 38.95 tokens per second) 3.46.986.552 I slot print_timing: id 2 | task 6825 | total time = 9217.37 ms / 1207 tokens 3.46.986.552 I slot print_timing: id 2 | task 6825 | graphs reused = 6867 3.46.986.578 I slot release: id 2 | task 6825 | stop processing: n_tokens = 1248, truncated = 0 3.47.014.638 I slot print_timing: id 3 | task 6826 | prompt eval time = 3371.67 ms / 1034 tokens ( 3.26 ms per token, 306.67 tokens per second) 3.47.014.642 I slot print_timing: id 3 | task 6826 | eval time = 5815.10 ms / 256 tokens ( 22.80 ms per token, 43.85 tokens per second) 3.47.014.642 I slot print_timing: id 3 | task 6826 | total time = 9186.77 ms / 1290 tokens 3.47.014.643 I slot print_timing: id 3 | task 6826 | graphs reused = 6867 3.47.014.676 I slot release: id 3 | task 6826 | stop processing: n_tokens = 1331, truncated = 0 3.47.015.419 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 679821741466 3.47.015.488 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 3.47.191.073 I slot launch_slot_: id 0 | task 7090 | processing task, is_child = 0 3.47.191.131 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 3.47.344.937 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.660 MiB) 3.47.498.247 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 675.908 MiB) 3.47.512.892 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 3.47.707.160 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 679821741673 3.47.707.284 I slot launch_slot_: id 1 | task 7091 | processing task, is_child = 0 3.47.707.375 I slot get_availabl: id 2 | task -1 | selected slot by LRU, t_last = 679821741878 3.47.707.448 I slot launch_slot_: id 2 | task 7092 | processing task, is_child = 0 3.47.707.498 I slot get_availabl: id 3 | task -1 | selected slot by LRU, t_last = 679821769976 3.47.707.571 I slot launch_slot_: id 3 | task 7093 | processing task, is_child = 0 3.48.459.412 I slot print_timing: id 4 | task 6827 | prompt eval time = 3522.61 ms / 931 tokens ( 3.78 ms per token, 264.29 tokens per second) 3.48.459.417 I slot print_timing: id 4 | task 6827 | eval time = 7052.18 ms / 256 tokens ( 27.66 ms per token, 36.16 tokens per second) 3.48.459.418 I slot print_timing: id 4 | task 6827 | total time = 10574.79 ms / 1187 tokens 3.48.459.419 I slot print_timing: id 4 | task 6827 | graphs reused = 6868 3.48.459.454 I slot release: id 4 | task 6827 | stop processing: n_tokens = 1228, truncated = 0 3.48.459.651 I slot print_timing: id 5 | task 6830 | prompt eval time = 1593.72 ms / 943 tokens ( 1.69 ms per token, 591.70 tokens per second) 3.48.459.652 I slot print_timing: id 5 | task 6830 | eval time = 7052.19 ms / 256 tokens ( 27.66 ms per token, 36.16 tokens per second) 3.48.459.652 I slot print_timing: id 5 | task 6830 | total time = 8645.91 ms / 1199 tokens 3.48.459.653 I slot print_timing: id 5 | task 6830 | graphs reused = 6868 3.48.459.680 I slot release: id 5 | task 6830 | stop processing: n_tokens = 1240, truncated = 0 3.48.459.874 I slot print_timing: id 6 | task 6831 | prompt eval time = 1537.92 ms / 907 tokens ( 1.70 ms per token, 589.76 tokens per second) 3.48.459.875 I slot print_timing: id 6 | task 6831 | eval time = 7052.14 ms / 256 tokens ( 27.66 ms per token, 36.16 tokens per second) 3.48.459.875 I slot print_timing: id 6 | task 6831 | total time = 8590.05 ms / 1163 tokens 3.48.459.875 I slot print_timing: id 6 | task 6831 | graphs reused = 6868 3.48.459.904 I slot release: id 6 | task 6831 | stop processing: n_tokens = 1204, truncated = 0 3.48.460.098 I slot print_timing: id 7 | task 6832 | n_gen = 255, tg = 36.42 t/s, tg_3s = 29.27 t/s 3.49.152.619 I slot print_timing: id 7 | task 6832 | prompt eval time = 1557.85 ms / 942 tokens ( 1.65 ms per token, 604.68 tokens per second) 3.49.152.624 I slot print_timing: id 7 | task 6832 | eval time = 7666.80 ms / 256 tokens ( 30.07 ms per token, 33.26 tokens per second) 3.49.152.625 I slot print_timing: id 7 | task 6832 | total time = 9224.66 ms / 1198 tokens 3.49.152.626 I slot print_timing: id 7 | task 6832 | graphs reused = 6869 3.49.152.664 I slot release: id 7 | task 6832 | stop processing: n_tokens = 1239, truncated = 0 3.49.152.678 I slot get_availabl: id 4 | task -1 | selected slot by LRU, t_last = 679823214754 3.49.152.748 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 3.49.312.334 I slot launch_slot_: id 4 | task 7096 | processing task, is_child = 0 3.49.312.395 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 3.49.461.756 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 3.49.610.587 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 675.033 MiB) 3.49.794.944 I slot get_availabl: id 5 | task -1 | selected slot by LRU, t_last = 679823214979 3.49.795.079 I slot launch_slot_: id 5 | task 7097 | processing task, is_child = 0 3.49.795.178 I slot get_availabl: id 6 | task -1 | selected slot by LRU, t_last = 679823215204 3.49.795.252 I slot launch_slot_: id 6 | task 7098 | processing task, is_child = 0 3.49.795.302 I slot get_availabl: id 7 | task -1 | selected slot by LRU, t_last = 679823907963 3.49.795.370 I slot launch_slot_: id 7 | task 7099 | processing task, is_child = 0 3.53.855.684 I slot print_timing: id 0 | task 7090 | n_gen = 100, tg = 31.50 t/s, tg_3s = 31.82 t/s 3.53.855.861 I slot print_timing: id 1 | task 7091 | n_gen = 100, tg = 31.51 t/s, tg_3s = 31.82 t/s 3.53.856.042 I slot print_timing: id 2 | task 7092 | n_gen = 100, tg = 31.51 t/s, tg_3s = 31.82 t/s 3.54.487.854 I slot print_timing: id 3 | task 7093 | n_gen = 128, tg = 42.14 t/s, tg_3s = 42.47 t/s 3.54.683.996 I slot print_timing: id 4 | task 7096 | n_gen = 136, tg = 44.97 t/s, tg_3s = 45.30 t/s 3.54.684.179 I slot print_timing: id 5 | task 7097 | n_gen = 136, tg = 44.97 t/s, tg_3s = 45.30 t/s 3.54.684.364 I slot print_timing: id 6 | task 7098 | n_gen = 136, tg = 44.97 t/s, tg_3s = 45.30 t/s 3.54.771.670 I slot print_timing: id 7 | task 7099 | n_gen = 139, tg = 45.84 t/s, tg_3s = 46.17 t/s 3.56.869.827 I slot print_timing: id 0 | task 7090 | n_gen = 238, tg = 38.50 t/s, tg_3s = 45.78 t/s 3.56.870.005 I slot print_timing: id 1 | task 7091 | n_gen = 238, tg = 38.50 t/s, tg_3s = 45.78 t/s 3.56.870.178 I slot print_timing: id 2 | task 7092 | n_gen = 238, tg = 38.50 t/s, tg_3s = 45.78 t/s 3.57.262.812 I slot print_timing: id 0 | task 7090 | prompt eval time = 3005.71 ms / 907 tokens ( 3.31 ms per token, 301.76 tokens per second) 3.57.262.815 I slot print_timing: id 0 | task 7090 | eval time = 6549.51 ms / 256 tokens ( 25.68 ms per token, 38.93 tokens per second) 3.57.262.816 I slot print_timing: id 0 | task 7090 | total time = 9555.22 ms / 1163 tokens 3.57.262.817 I slot print_timing: id 0 | task 7090 | graphs reused = 7120 3.57.262.851 I slot release: id 0 | task 7090 | stop processing: n_tokens = 1204, truncated = 0 3.57.263.031 I slot print_timing: id 1 | task 7091 | prompt eval time = 2951.74 ms / 1034 tokens ( 2.85 ms per token, 350.30 tokens per second) 3.57.263.032 I slot print_timing: id 1 | task 7091 | eval time = 6549.46 ms / 256 tokens ( 25.68 ms per token, 38.93 tokens per second) 3.57.263.032 I slot print_timing: id 1 | task 7091 | total time = 9501.19 ms / 1290 tokens 3.57.263.033 I slot print_timing: id 1 | task 7091 | graphs reused = 7120 3.57.263.064 I slot release: id 1 | task 7091 | stop processing: n_tokens = 1331, truncated = 0 3.57.263.237 I slot print_timing: id 2 | task 7092 | prompt eval time = 2896.12 ms / 1034 tokens ( 2.80 ms per token, 357.03 tokens per second) 3.57.263.239 I slot print_timing: id 2 | task 7092 | eval time = 6549.41 ms / 256 tokens ( 25.68 ms per token, 38.93 tokens per second) 3.57.263.239 I slot print_timing: id 2 | task 7092 | total time = 9445.53 ms / 1290 tokens 3.57.263.240 I slot print_timing: id 2 | task 7092 | graphs reused = 7120 3.57.263.269 I slot release: id 2 | task 7092 | stop processing: n_tokens = 1331, truncated = 0 3.57.291.296 I slot print_timing: id 3 | task 7093 | prompt eval time = 3599.70 ms / 941 tokens ( 3.83 ms per token, 261.41 tokens per second) 3.57.291.299 I slot print_timing: id 3 | task 7093 | eval time = 5817.33 ms / 256 tokens ( 22.81 ms per token, 43.83 tokens per second) 3.57.291.300 I slot print_timing: id 3 | task 7093 | total time = 9417.03 ms / 1197 tokens 3.57.291.300 I slot print_timing: id 3 | task 7093 | graphs reused = 7120 3.57.291.334 I slot release: id 3 | task 7093 | stop processing: n_tokens = 1238, truncated = 0 3.57.292.056 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 679832018150 3.57.292.119 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 3.57.444.609 I slot launch_slot_: id 0 | task 7357 | processing task, is_child = 0 3.57.444.675 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 675.971 MiB) 3.57.597.828 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 3.57.750.033 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 3.57.940.537 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 679832018363 3.57.940.678 I slot launch_slot_: id 1 | task 7358 | processing task, is_child = 0 3.57.940.773 I slot get_availabl: id 2 | task -1 | selected slot by LRU, t_last = 679832018568 3.57.940.845 I slot launch_slot_: id 2 | task 7359 | processing task, is_child = 0 3.57.940.891 I slot get_availabl: id 3 | task -1 | selected slot by LRU, t_last = 679832046633 3.57.940.960 I slot launch_slot_: id 3 | task 7360 | processing task, is_child = 0 3.58.717.354 I slot print_timing: id 4 | task 7096 | prompt eval time = 1740.79 ms / 1034 tokens ( 1.68 ms per token, 593.98 tokens per second) 3.58.717.358 I slot print_timing: id 4 | task 7096 | eval time = 7035.66 ms / 256 tokens ( 27.59 ms per token, 36.24 tokens per second) 3.58.717.359 I slot print_timing: id 4 | task 7096 | total time = 8776.46 ms / 1290 tokens 3.58.717.359 I slot print_timing: id 4 | task 7096 | graphs reused = 7121 3.58.717.400 I slot release: id 4 | task 7096 | stop processing: n_tokens = 1331, truncated = 0 3.58.717.609 I slot print_timing: id 5 | task 7097 | prompt eval time = 1687.10 ms / 885 tokens ( 1.91 ms per token, 524.57 tokens per second) 3.58.717.611 I slot print_timing: id 5 | task 7097 | eval time = 7035.60 ms / 256 tokens ( 27.59 ms per token, 36.24 tokens per second) 3.58.717.611 I slot print_timing: id 5 | task 7097 | total time = 8722.70 ms / 1141 tokens 3.58.717.611 I slot print_timing: id 5 | task 7097 | graphs reused = 7121 3.58.717.643 I slot release: id 5 | task 7097 | stop processing: n_tokens = 1182, truncated = 0 3.58.717.857 I slot print_timing: id 6 | task 7098 | prompt eval time = 1629.37 ms / 953 tokens ( 1.71 ms per token, 584.89 tokens per second) 3.58.717.858 I slot print_timing: id 6 | task 7098 | eval time = 7035.60 ms / 256 tokens ( 27.59 ms per token, 36.24 tokens per second) 3.58.717.859 I slot print_timing: id 6 | task 7098 | total time = 8664.97 ms / 1209 tokens 3.58.717.859 I slot print_timing: id 6 | task 7098 | graphs reused = 7121 3.58.717.887 I slot release: id 6 | task 7098 | stop processing: n_tokens = 1250, truncated = 0 3.58.718.098 I slot print_timing: id 7 | task 7099 | n_gen = 255, tg = 36.51 t/s, tg_3s = 29.39 t/s 3.59.411.382 I slot print_timing: id 7 | task 7099 | prompt eval time = 1650.73 ms / 1034 tokens ( 1.60 ms per token, 626.39 tokens per second) 3.59.411.387 I slot print_timing: id 7 | task 7099 | eval time = 7650.31 ms / 256 tokens ( 30.00 ms per token, 33.33 tokens per second) 3.59.411.388 I slot print_timing: id 7 | task 7099 | total time = 9301.04 ms / 1290 tokens 3.59.411.389 I slot print_timing: id 7 | task 7099 | graphs reused = 7122 3.59.411.432 I slot release: id 7 | task 7099 | stop processing: n_tokens = 1331, truncated = 0 3.59.411.447 I slot get_availabl: id 4 | task -1 | selected slot by LRU, t_last = 679833472700 3.59.411.520 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 672.532 MiB) 3.59.567.596 I slot launch_slot_: id 4 | task 7363 | processing task, is_child = 0 3.59.567.654 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 676.533 MiB) 3.59.716.289 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 831.349 MiB) 3.59.883.824 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 675.283 MiB) 4.00.068.252 I slot get_availabl: id 5 | task -1 | selected slot by LRU, t_last = 679833472942 4.00.068.393 I slot launch_slot_: id 5 | task 7364 | processing task, is_child = 0 4.00.068.486 I slot get_availabl: id 6 | task -1 | selected slot by LRU, t_last = 679833473186 4.00.068.557 I slot launch_slot_: id 6 | task 7365 | processing task, is_child = 0 4.00.068.604 I slot get_availabl: id 7 | task -1 | selected slot by LRU, t_last = 679834166730 4.00.068.679 I slot launch_slot_: id 7 | task 7366 | processing task, is_child = 0 4.04.159.766 I slot print_timing: id 0 | task 7357 | n_gen = 100, tg = 31.20 t/s, tg_3s = 31.51 t/s 4.04.159.944 I slot print_timing: id 1 | task 7358 | n_gen = 100, tg = 31.20 t/s, tg_3s = 31.51 t/s 4.04.160.126 I slot print_timing: id 2 | task 7359 | n_gen = 100, tg = 31.20 t/s, tg_3s = 31.51 t/s 4.04.771.095 I slot print_timing: id 3 | task 7360 | n_gen = 127, tg = 41.86 t/s, tg_3s = 42.19 t/s 4.04.989.365 I slot print_timing: id 4 | task 7363 | n_gen = 136, tg = 44.89 t/s, tg_3s = 45.22 t/s 4.04.989.561 I slot print_timing: id 5 | task 7364 | n_gen = 136, tg = 44.89 t/s, tg_3s = 45.22 t/s 4.04.989.745 I slot print_timing: id 6 | task 7365 | n_gen = 136, tg = 44.89 t/s, tg_3s = 45.23 t/s 4.05.077.380 I slot print_timing: id 7 | task 7366 | n_gen = 139, tg = 45.78 t/s, tg_3s = 46.11 t/s 4.07.176.783 I slot print_timing: id 0 | task 7357 | n_gen = 238, tg = 38.28 t/s, tg_3s = 45.74 t/s 4.07.176.956 I slot print_timing: id 1 | task 7358 | n_gen = 238, tg = 38.28 t/s, tg_3s = 45.74 t/s 4.07.177.128 I slot print_timing: id 2 | task 7359 | n_gen = 238, tg = 38.29 t/s, tg_3s = 45.74 t/s 4.07.569.522 I slot print_timing: id 0 | task 7357 | prompt eval time = 3045.30 ms / 1034 tokens ( 2.95 ms per token, 339.54 tokens per second) 4.07.569.524 I slot print_timing: id 0 | task 7357 | eval time = 6583.24 ms / 256 tokens ( 25.82 ms per token, 38.73 tokens per second) 4.07.569.525 I slot print_timing: id 0 | task 7357 | total time = 9628.54 ms / 1290 tokens 4.07.569.526 I slot print_timing: id 0 | task 7357 | graphs reused = 7374 4.07.569.558 I slot release: id 0 | task 7357 | stop processing: n_tokens = 1331, truncated = 0 4.07.569.743 I slot print_timing: id 1 | task 7358 | prompt eval time = 2992.40 ms / 939 tokens ( 3.19 ms per token, 313.80 tokens per second) 4.07.569.745 I slot print_timing: id 1 | task 7358 | eval time = 6583.21 ms / 256 tokens ( 25.82 ms per token, 38.73 tokens per second) 4.07.569.745 I slot print_timing: id 1 | task 7358 | total time = 9575.60 ms / 1195 tokens 4.07.569.745 I slot print_timing: id 1 | task 7358 | graphs reused = 7374 4.07.569.774 I slot release: id 1 | task 7358 | stop processing: n_tokens = 1236, truncated = 0 4.07.569.959 I slot print_timing: id 2 | task 7359 | prompt eval time = 2937.10 ms / 1034 tokens ( 2.84 ms per token, 352.05 tokens per second) 4.07.569.960 I slot print_timing: id 2 | task 7359 | eval time = 6583.17 ms / 256 tokens ( 25.82 ms per token, 38.74 tokens per second) 4.07.569.960 I slot print_timing: id 2 | task 7359 | total time = 9520.27 ms / 1290 tokens 4.07.569.961 I slot print_timing: id 2 | task 7359 | graphs reused = 7374 4.07.569.990 I slot release: id 2 | task 7359 | stop processing: n_tokens = 1331, truncated = 0 4.07.598.028 I slot print_timing: id 3 | task 7360 | prompt eval time = 3654.11 ms / 1034 tokens ( 3.53 ms per token, 282.97 tokens per second) 4.07.598.030 I slot print_timing: id 3 | task 7360 | eval time = 5837.01 ms / 256 tokens ( 22.89 ms per token, 43.69 tokens per second) 4.07.598.031 I slot print_timing: id 3 | task 7360 | total time = 9491.11 ms / 1290 tokens 4.07.598.031 I slot print_timing: id 3 | task 7360 | graphs reused = 7374 4.07.598.065 I slot release: id 3 | task 7360 | stop processing: n_tokens = 1331, truncated = 0 4.07.598.796 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 679842324858 4.07.598.864 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 676.033 MiB) 4.07.753.907 I slot launch_slot_: id 0 | task 7624 | processing task, is_child = 0 4.07.753.967 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 673.782 MiB) 4.07.904.170 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 825.597 MiB) 4.08.069.527 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 673.782 MiB) 4.08.254.081 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 679842325074 4.08.254.216 I slot launch_slot_: id 1 | task 7625 | processing task, is_child = 0 4.08.254.311 I slot get_availabl: id 2 | task -1 | selected slot by LRU, t_last = 679842325290 4.08.254.384 I slot launch_slot_: id 2 | task 7626 | processing task, is_child = 0 4.08.254.437 I slot get_availabl: id 3 | task -1 | selected slot by LRU, t_last = 679842353365 4.08.254.512 I slot launch_slot_: id 3 | task 7627 | processing task, is_child = 0 4.09.030.948 I slot print_timing: id 4 | task 7363 | prompt eval time = 1770.80 ms / 940 tokens ( 1.88 ms per token, 530.83 tokens per second) 4.09.030.950 I slot print_timing: id 4 | task 7363 | eval time = 7048.90 ms / 256 tokens ( 27.64 ms per token, 36.18 tokens per second) 4.09.030.951 I slot print_timing: id 4 | task 7363 | total time = 8819.70 ms / 1196 tokens 4.09.030.951 I slot print_timing: id 4 | task 7363 | graphs reused = 7375 4.09.030.986 I slot release: id 4 | task 7363 | stop processing: n_tokens = 1237, truncated = 0 4.09.031.206 I slot print_timing: id 5 | task 7364 | prompt eval time = 1716.36 ms / 938 tokens ( 1.83 ms per token, 546.51 tokens per second) 4.09.031.207 I slot print_timing: id 5 | task 7364 | eval time = 7048.86 ms / 256 tokens ( 27.64 ms per token, 36.18 tokens per second) 4.09.031.208 I slot print_timing: id 5 | task 7364 | total time = 8765.22 ms / 1194 tokens 4.09.031.208 I slot print_timing: id 5 | task 7364 | graphs reused = 7375 4.09.031.237 I slot release: id 5 | task 7364 | stop processing: n_tokens = 1235, truncated = 0 4.09.031.437 I slot print_timing: id 6 | task 7365 | prompt eval time = 1659.00 ms / 933 tokens ( 1.78 ms per token, 562.39 tokens per second) 4.09.031.438 I slot print_timing: id 6 | task 7365 | eval time = 7048.81 ms / 256 tokens ( 27.64 ms per token, 36.18 tokens per second) 4.09.031.439 I slot print_timing: id 6 | task 7365 | total time = 8707.81 ms / 1189 tokens 4.09.031.439 I slot print_timing: id 6 | task 7365 | graphs reused = 7375 4.09.031.466 I slot release: id 6 | task 7365 | stop processing: n_tokens = 1230, truncated = 0 4.09.031.679 I slot print_timing: id 7 | task 7366 | n_gen = 255, tg = 36.45 t/s, tg_3s = 29.34 t/s 4.09.723.440 I slot print_timing: id 7 | task 7366 | prompt eval time = 1682.51 ms / 1035 tokens ( 1.63 ms per token, 615.15 tokens per second) 4.09.723.443 I slot print_timing: id 7 | task 7366 | eval time = 7660.35 ms / 256 tokens ( 30.04 ms per token, 33.29 tokens per second) 4.09.723.444 I slot print_timing: id 7 | task 7366 | total time = 9342.86 ms / 1291 tokens 4.09.723.444 I slot print_timing: id 7 | task 7366 | graphs reused = 7376 4.09.723.485 I slot release: id 7 | task 7366 | stop processing: n_tokens = 1332, truncated = 0 4.09.723.499 I slot get_availabl: id 4 | task -1 | selected slot by LRU, t_last = 679843786286 4.09.723.564 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 4.09.874.354 I slot launch_slot_: id 4 | task 7630 | processing task, is_child = 0 4.09.874.413 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 4.10.024.490 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 825.534 MiB) 4.10.193.956 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 4.10.380.059 I slot get_availabl: id 5 | task -1 | selected slot by LRU, t_last = 679843786537 4.10.380.191 I slot launch_slot_: id 5 | task 7631 | processing task, is_child = 0 4.10.380.285 I slot get_availabl: id 6 | task -1 | selected slot by LRU, t_last = 679843786767 4.10.380.356 I slot launch_slot_: id 6 | task 7632 | processing task, is_child = 0 4.10.380.403 I slot get_availabl: id 7 | task -1 | selected slot by LRU, t_last = 679844478785 4.10.380.476 I slot launch_slot_: id 7 | task 7633 | processing task, is_child = 0 4.14.455.349 I slot print_timing: id 0 | task 7624 | n_gen = 100, tg = 31.79 t/s, tg_3s = 32.11 t/s 4.14.455.522 I slot print_timing: id 1 | task 7625 | n_gen = 100, tg = 31.79 t/s, tg_3s = 32.11 t/s 4.14.455.694 I slot print_timing: id 2 | task 7626 | n_gen = 100, tg = 31.79 t/s, tg_3s = 32.11 t/s 4.14.978.400 I slot print_timing: id 3 | task 7627 | n_gen = 123, tg = 40.44 t/s, tg_3s = 40.78 t/s 4.15.283.946 I slot print_timing: id 4 | task 7630 | n_gen = 136, tg = 44.92 t/s, tg_3s = 45.25 t/s 4.15.284.122 I slot print_timing: id 5 | task 7631 | n_gen = 136, tg = 44.92 t/s, tg_3s = 45.25 t/s 4.15.284.308 I slot print_timing: id 6 | task 7632 | n_gen = 136, tg = 44.92 t/s, tg_3s = 45.25 t/s 4.15.371.608 I slot print_timing: id 7 | task 7633 | n_gen = 139, tg = 45.79 t/s, tg_3s = 46.13 t/s 4.17.471.500 I slot print_timing: id 0 | task 7624 | n_gen = 238, tg = 38.66 t/s, tg_3s = 45.75 t/s 4.17.471.676 I slot print_timing: id 1 | task 7625 | n_gen = 238, tg = 38.66 t/s, tg_3s = 45.75 t/s 4.17.471.865 I slot print_timing: id 2 | task 7626 | n_gen = 238, tg = 38.66 t/s, tg_3s = 45.75 t/s 4.17.865.748 I slot print_timing: id 0 | task 7624 | prompt eval time = 3086.54 ms / 1034 tokens ( 2.99 ms per token, 335.00 tokens per second) 4.17.865.750 I slot print_timing: id 0 | task 7624 | eval time = 6524.68 ms / 256 tokens ( 25.59 ms per token, 39.08 tokens per second) 4.17.865.751 I slot print_timing: id 0 | task 7624 | total time = 9611.21 ms / 1290 tokens 4.17.865.751 I slot print_timing: id 0 | task 7624 | graphs reused = 7628 4.17.865.791 I slot release: id 0 | task 7624 | stop processing: n_tokens = 1331, truncated = 0 4.17.865.974 I slot print_timing: id 1 | task 7625 | prompt eval time = 3033.36 ms / 1034 tokens ( 2.93 ms per token, 340.88 tokens per second) 4.17.865.976 I slot print_timing: id 1 | task 7625 | eval time = 6524.64 ms / 256 tokens ( 25.59 ms per token, 39.08 tokens per second) 4.17.865.977 I slot print_timing: id 1 | task 7625 | total time = 9558.00 ms / 1290 tokens 4.17.865.977 I slot print_timing: id 1 | task 7625 | graphs reused = 7628 4.17.866.009 I slot release: id 1 | task 7625 | stop processing: n_tokens = 1331, truncated = 0 4.17.866.203 I slot print_timing: id 2 | task 7626 | prompt eval time = 2978.15 ms / 938 tokens ( 3.18 ms per token, 314.96 tokens per second) 4.17.866.205 I slot print_timing: id 2 | task 7626 | eval time = 6524.62 ms / 256 tokens ( 25.59 ms per token, 39.08 tokens per second) 4.17.866.206 I slot print_timing: id 2 | task 7626 | total time = 9502.77 ms / 1194 tokens 4.17.866.206 I slot print_timing: id 2 | task 7626 | graphs reused = 7628 4.17.866.233 I slot release: id 2 | task 7626 | stop processing: n_tokens = 1235, truncated = 0 4.17.894.308 I slot print_timing: id 3 | task 7627 | prompt eval time = 3540.92 ms / 1034 tokens ( 3.42 ms per token, 292.01 tokens per second) 4.17.894.310 I slot print_timing: id 3 | task 7627 | eval time = 5932.42 ms / 256 tokens ( 23.26 ms per token, 42.98 tokens per second) 4.17.894.311 I slot print_timing: id 3 | task 7627 | total time = 9473.34 ms / 1290 tokens 4.17.894.311 I slot print_timing: id 3 | task 7627 | graphs reused = 7628 4.17.894.345 I slot release: id 3 | task 7627 | stop processing: n_tokens = 1331, truncated = 0 4.17.895.078 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 679852621091 4.17.895.145 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 672.407 MiB) 4.18.052.179 I slot launch_slot_: id 0 | task 7891 | processing task, is_child = 0 4.18.052.240 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 676.659 MiB) 4.18.214.529 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 831.349 MiB) 4.18.375.825 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 4.18.560.092 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 679852621309 4.18.560.226 I slot launch_slot_: id 1 | task 7892 | processing task, is_child = 0 4.18.560.319 I slot get_availabl: id 2 | task -1 | selected slot by LRU, t_last = 679852621533 4.18.560.389 I slot launch_slot_: id 2 | task 7893 | processing task, is_child = 0 4.18.560.441 I slot get_availabl: id 3 | task -1 | selected slot by LRU, t_last = 679852649644 4.18.560.515 I slot launch_slot_: id 3 | task 7894 | processing task, is_child = 0 4.19.345.404 I slot print_timing: id 4 | task 7630 | prompt eval time = 1755.37 ms / 1036 tokens ( 1.69 ms per token, 590.19 tokens per second) 4.19.345.408 I slot print_timing: id 4 | task 7630 | eval time = 7066.81 ms / 256 tokens ( 27.71 ms per token, 36.08 tokens per second) 4.19.345.409 I slot print_timing: id 4 | task 7630 | total time = 8822.18 ms / 1292 tokens 4.19.345.410 I slot print_timing: id 4 | task 7630 | graphs reused = 7629 4.19.345.451 I slot release: id 4 | task 7630 | stop processing: n_tokens = 1333, truncated = 0 4.19.345.692 I slot print_timing: id 5 | task 7631 | prompt eval time = 1700.98 ms / 1034 tokens ( 1.65 ms per token, 607.89 tokens per second) 4.19.345.694 I slot print_timing: id 5 | task 7631 | eval time = 7066.87 ms / 256 tokens ( 27.71 ms per token, 36.08 tokens per second) 4.19.345.694 I slot print_timing: id 5 | task 7631 | total time = 8767.84 ms / 1290 tokens 4.19.345.694 I slot print_timing: id 5 | task 7631 | graphs reused = 7629 4.19.345.732 I slot release: id 5 | task 7631 | stop processing: n_tokens = 1331, truncated = 0 4.19.345.956 I slot print_timing: id 6 | task 7632 | prompt eval time = 1642.24 ms / 1034 tokens ( 1.59 ms per token, 629.63 tokens per second) 4.19.345.958 I slot print_timing: id 6 | task 7632 | eval time = 7066.89 ms / 256 tokens ( 27.71 ms per token, 36.08 tokens per second) 4.19.345.958 I slot print_timing: id 6 | task 7632 | total time = 8709.12 ms / 1290 tokens 4.19.345.958 I slot print_timing: id 6 | task 7632 | graphs reused = 7629 4.19.345.997 I slot release: id 6 | task 7632 | stop processing: n_tokens = 1331, truncated = 0 4.19.346.246 I slot print_timing: id 7 | task 7633 | n_gen = 255, tg = 36.35 t/s, tg_3s = 29.19 t/s 4.19.884.682 I slot print_timing: id 7 | task 7633 | prompt eval time = 1662.61 ms / 1034 tokens ( 1.61 ms per token, 621.91 tokens per second) 4.19.884.685 I slot print_timing: id 7 | task 7633 | eval time = 7526.58 ms / 256 tokens ( 29.52 ms per token, 33.88 tokens per second) 4.19.884.685 I slot print_timing: id 7 | task 7633 | total time = 9189.19 ms / 1290 tokens 4.19.884.686 I slot print_timing: id 7 | task 7633 | graphs reused = 7629 4.19.884.722 I slot release: id 7 | task 7633 | stop processing: n_tokens = 1331, truncated = 0 4.19.884.737 I slot get_availabl: id 4 | task -1 | selected slot by LRU, t_last = 679854100751 4.19.884.807 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 675.783 MiB) 4.20.040.004 I slot launch_slot_: id 4 | task 7897 | processing task, is_child = 0 4.20.040.066 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 4.20.197.054 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 831.349 MiB) 4.20.355.771 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 675.846 MiB) 4.20.508.335 I slot get_availabl: id 5 | task -1 | selected slot by LRU, t_last = 679854101034 4.20.508.479 I slot launch_slot_: id 5 | task 7898 | processing task, is_child = 0 4.20.508.572 I slot get_availabl: id 6 | task -1 | selected slot by LRU, t_last = 679854101298 4.20.508.643 I slot launch_slot_: id 6 | task 7899 | processing task, is_child = 0 4.20.508.689 I slot get_availabl: id 7 | task -1 | selected slot by LRU, t_last = 679854640022 4.20.508.760 I slot launch_slot_: id 7 | task 7900 | processing task, is_child = 0 4.24.626.288 I slot print_timing: id 0 | task 7891 | n_gen = 100, tg = 31.55 t/s, tg_3s = 31.87 t/s 4.24.626.461 I slot print_timing: id 1 | task 7892 | n_gen = 100, tg = 31.55 t/s, tg_3s = 31.87 t/s 4.24.626.641 I slot print_timing: id 2 | task 7893 | n_gen = 100, tg = 31.55 t/s, tg_3s = 31.87 t/s 4.25.149.652 I slot print_timing: id 3 | task 7894 | n_gen = 123, tg = 40.46 t/s, tg_3s = 40.79 t/s 4.25.454.908 I slot print_timing: id 4 | task 7897 | n_gen = 136, tg = 44.95 t/s, tg_3s = 45.28 t/s 4.25.455.086 I slot print_timing: id 5 | task 7898 | n_gen = 136, tg = 44.95 t/s, tg_3s = 45.29 t/s 4.25.455.261 I slot print_timing: id 6 | task 7899 | n_gen = 136, tg = 44.95 t/s, tg_3s = 45.29 t/s 4.25.542.516 I slot print_timing: id 7 | task 7900 | n_gen = 139, tg = 45.82 t/s, tg_3s = 46.16 t/s 4.27.643.170 I slot print_timing: id 0 | task 7891 | n_gen = 238, tg = 38.50 t/s, tg_3s = 45.74 t/s 4.27.643.343 I slot print_timing: id 1 | task 7892 | n_gen = 238, tg = 38.51 t/s, tg_3s = 45.74 t/s 4.27.643.521 I slot print_timing: id 2 | task 7893 | n_gen = 238, tg = 38.51 t/s, tg_3s = 45.74 t/s 4.28.036.674 I slot print_timing: id 0 | task 7891 | prompt eval time = 2927.56 ms / 1034 tokens ( 2.83 ms per token, 353.20 tokens per second) 4.28.036.677 I slot print_timing: id 0 | task 7891 | eval time = 6548.58 ms / 256 tokens ( 25.68 ms per token, 38.94 tokens per second) 4.28.036.677 I slot print_timing: id 0 | task 7891 | total time = 9476.14 ms / 1290 tokens 4.28.036.678 I slot print_timing: id 0 | task 7891 | graphs reused = 7880 4.28.036.725 I slot release: id 0 | task 7891 | stop processing: n_tokens = 1331, truncated = 0 4.28.036.904 I slot print_timing: id 1 | task 7892 | prompt eval time = 2875.09 ms / 1034 tokens ( 2.78 ms per token, 359.64 tokens per second) 4.28.036.906 I slot print_timing: id 1 | task 7892 | eval time = 6548.55 ms / 256 tokens ( 25.68 ms per token, 38.94 tokens per second) 4.28.036.906 I slot print_timing: id 1 | task 7892 | total time = 9423.64 ms / 1290 tokens 4.28.036.906 I slot print_timing: id 1 | task 7892 | graphs reused = 7880 4.28.036.938 I slot release: id 1 | task 7892 | stop processing: n_tokens = 1331, truncated = 0 4.28.037.115 I slot print_timing: id 2 | task 7893 | prompt eval time = 2820.13 ms / 1034 tokens ( 2.73 ms per token, 366.65 tokens per second) 4.28.037.117 I slot print_timing: id 2 | task 7893 | eval time = 6548.51 ms / 256 tokens ( 25.68 ms per token, 38.94 tokens per second) 4.28.037.117 I slot print_timing: id 2 | task 7893 | total time = 9368.64 ms / 1290 tokens 4.28.037.117 I slot print_timing: id 2 | task 7893 | graphs reused = 7880 4.28.037.139 I slot release: id 2 | task 7893 | stop processing: n_tokens = 1331, truncated = 0 4.28.065.265 I slot print_timing: id 3 | task 7894 | prompt eval time = 3408.99 ms / 1034 tokens ( 3.30 ms per token, 303.32 tokens per second) 4.28.065.267 I slot print_timing: id 3 | task 7894 | eval time = 5930.97 ms / 256 tokens ( 23.26 ms per token, 42.99 tokens per second) 4.28.065.268 I slot print_timing: id 3 | task 7894 | total time = 9339.96 ms / 1290 tokens 4.28.065.268 I slot print_timing: id 3 | task 7894 | graphs reused = 7880 4.28.065.303 I slot release: id 3 | task 7894 | stop processing: n_tokens = 1331, truncated = 0 4.28.066.011 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 679862792025 4.28.066.076 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 675.721 MiB) 4.28.225.026 I slot launch_slot_: id 0 | task 8158 | processing task, is_child = 0 4.28.225.087 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 675.408 MiB) 4.28.385.420 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 831.412 MiB) 4.28.548.051 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 4.28.702.481 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 679862792238 4.28.702.614 I slot launch_slot_: id 1 | task 8159 | processing task, is_child = 0 4.28.702.710 I slot get_availabl: id 2 | task -1 | selected slot by LRU, t_last = 679862792439 4.28.702.782 I slot launch_slot_: id 2 | task 8160 | processing task, is_child = 0 4.28.702.828 I slot get_availabl: id 3 | task -1 | selected slot by LRU, t_last = 679862820603 4.28.702.898 I slot launch_slot_: id 3 | task 8161 | processing task, is_child = 0 4.29.466.589 I slot print_timing: id 4 | task 7897 | prompt eval time = 1800.20 ms / 1034 tokens ( 1.74 ms per token, 574.38 tokens per second) 4.29.466.592 I slot print_timing: id 4 | task 7897 | eval time = 7014.88 ms / 256 tokens ( 27.51 ms per token, 36.35 tokens per second) 4.29.466.593 I slot print_timing: id 4 | task 7897 | total time = 8815.08 ms / 1290 tokens 4.29.466.594 I slot print_timing: id 4 | task 7897 | graphs reused = 7881 4.29.466.632 I slot release: id 4 | task 7897 | stop processing: n_tokens = 1331, truncated = 0 4.29.466.829 I slot print_timing: id 5 | task 7898 | prompt eval time = 1746.08 ms / 891 tokens ( 1.96 ms per token, 510.29 tokens per second) 4.29.466.830 I slot print_timing: id 5 | task 7898 | eval time = 7014.84 ms / 256 tokens ( 27.51 ms per token, 36.35 tokens per second) 4.29.466.831 I slot print_timing: id 5 | task 7898 | total time = 8760.92 ms / 1147 tokens 4.29.466.831 I slot print_timing: id 5 | task 7898 | graphs reused = 7881 4.29.466.863 I slot release: id 5 | task 7898 | stop processing: n_tokens = 1188, truncated = 0 4.29.467.053 I slot print_timing: id 6 | task 7899 | prompt eval time = 1688.18 ms / 1034 tokens ( 1.63 ms per token, 612.50 tokens per second) 4.29.467.055 I slot print_timing: id 6 | task 7899 | eval time = 7014.80 ms / 256 tokens ( 27.51 ms per token, 36.35 tokens per second) 4.29.467.055 I slot print_timing: id 6 | task 7899 | total time = 8702.98 ms / 1290 tokens 4.29.467.055 I slot print_timing: id 6 | task 7899 | graphs reused = 7881 4.29.467.085 I slot release: id 6 | task 7899 | stop processing: n_tokens = 1331, truncated = 0 4.29.467.271 I slot print_timing: id 7 | task 7900 | n_gen = 255, tg = 36.62 t/s, tg_3s = 29.56 t/s 4.30.160.660 I slot print_timing: id 7 | task 7900 | prompt eval time = 1709.00 ms / 888 tokens ( 1.92 ms per token, 519.60 tokens per second) 4.30.160.663 I slot print_timing: id 7 | task 7900 | eval time = 7629.61 ms / 256 tokens ( 29.92 ms per token, 33.42 tokens per second) 4.30.160.663 I slot print_timing: id 7 | task 7900 | total time = 9338.61 ms / 1144 tokens 4.30.160.664 I slot print_timing: id 7 | task 7900 | graphs reused = 7882 4.30.160.698 I slot release: id 7 | task 7900 | stop processing: n_tokens = 1185, truncated = 0 4.30.160.715 I slot get_availabl: id 4 | task -1 | selected slot by LRU, t_last = 679864221932 4.30.160.784 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 4.30.326.060 I slot launch_slot_: id 4 | task 8164 | processing task, is_child = 0 4.30.326.123 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 675.721 MiB) 4.30.480.565 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 831.349 MiB) 4.30.773.759 I slot get_availabl: id 5 | task -1 | selected slot by LRU, t_last = 679864222163 4.30.773.887 I slot launch_slot_: id 5 | task 8165 | processing task, is_child = 0 4.30.773.985 I slot get_availabl: id 6 | task -1 | selected slot by LRU, t_last = 679864222385 4.30.774.060 I slot launch_slot_: id 6 | task 8166 | processing task, is_child = 0 4.30.774.108 I slot get_availabl: id 7 | task -1 | selected slot by LRU, t_last = 679864915997 4.30.774.176 I slot launch_slot_: id 7 | task 8167 | processing task, is_child = 0 4.34.868.145 I slot print_timing: id 0 | task 8158 | n_gen = 100, tg = 31.37 t/s, tg_3s = 31.69 t/s 4.34.868.328 I slot print_timing: id 1 | task 8159 | n_gen = 100, tg = 31.37 t/s, tg_3s = 31.69 t/s 4.34.868.508 I slot print_timing: id 2 | task 8160 | n_gen = 100, tg = 31.37 t/s, tg_3s = 31.69 t/s 4.35.479.120 I slot print_timing: id 3 | task 8161 | n_gen = 127, tg = 41.94 t/s, tg_3s = 42.27 t/s 4.35.697.331 I slot print_timing: id 4 | task 8164 | n_gen = 136, tg = 44.77 t/s, tg_3s = 45.10 t/s 4.35.697.512 I slot print_timing: id 5 | task 8165 | n_gen = 136, tg = 44.77 t/s, tg_3s = 45.10 t/s 4.35.697.706 I slot print_timing: id 6 | task 8166 | n_gen = 136, tg = 44.77 t/s, tg_3s = 45.10 t/s 4.35.763.356 I slot print_timing: id 7 | task 8167 | n_gen = 138, tg = 45.62 t/s, tg_3s = 45.95 t/s 4.37.883.791 I slot print_timing: id 0 | task 8158 | n_gen = 238, tg = 38.40 t/s, tg_3s = 45.76 t/s 4.37.883.976 I slot print_timing: id 1 | task 8159 | n_gen = 238, tg = 38.40 t/s, tg_3s = 45.76 t/s 4.37.884.159 I slot print_timing: id 2 | task 8160 | n_gen = 238, tg = 38.40 t/s, tg_3s = 45.76 t/s 4.38.277.505 I slot print_timing: id 0 | task 8158 | prompt eval time = 3009.56 ms / 920 tokens ( 3.27 ms per token, 305.69 tokens per second) 4.38.277.508 I slot print_timing: id 0 | task 8158 | eval time = 6565.02 ms / 256 tokens ( 25.75 ms per token, 38.84 tokens per second) 4.38.277.508 I slot print_timing: id 0 | task 8158 | total time = 9574.58 ms / 1176 tokens 4.38.277.509 I slot print_timing: id 0 | task 8158 | graphs reused = 8134 4.38.277.546 I slot release: id 0 | task 8158 | stop processing: n_tokens = 1217, truncated = 0 4.38.277.730 I slot print_timing: id 1 | task 8159 | prompt eval time = 2955.53 ms / 1034 tokens ( 2.86 ms per token, 349.85 tokens per second) 4.38.277.732 I slot print_timing: id 1 | task 8159 | eval time = 6564.95 ms / 256 tokens ( 25.74 ms per token, 38.84 tokens per second) 4.38.277.732 I slot print_timing: id 1 | task 8159 | total time = 9520.48 ms / 1290 tokens 4.38.277.733 I slot print_timing: id 1 | task 8159 | graphs reused = 8134 4.38.277.769 I slot release: id 1 | task 8159 | stop processing: n_tokens = 1331, truncated = 0 4.38.277.956 I slot print_timing: id 2 | task 8160 | prompt eval time = 2900.22 ms / 934 tokens ( 3.11 ms per token, 322.04 tokens per second) 4.38.277.957 I slot print_timing: id 2 | task 8160 | eval time = 6564.89 ms / 256 tokens ( 25.74 ms per token, 38.84 tokens per second) 4.38.277.958 I slot print_timing: id 2 | task 8160 | total time = 9465.11 ms / 1190 tokens 4.38.277.958 I slot print_timing: id 2 | task 8160 | graphs reused = 8134 4.38.277.985 I slot release: id 2 | task 8160 | stop processing: n_tokens = 1231, truncated = 0 4.38.306.078 I slot print_timing: id 3 | task 8161 | prompt eval time = 3605.30 ms / 1030 tokens ( 3.50 ms per token, 285.69 tokens per second) 4.38.306.080 I slot print_timing: id 3 | task 8161 | eval time = 5831.43 ms / 256 tokens ( 22.87 ms per token, 43.73 tokens per second) 4.38.306.080 I slot print_timing: id 3 | task 8161 | total time = 9436.72 ms / 1286 tokens 4.38.306.081 I slot print_timing: id 3 | task 8161 | graphs reused = 8134 4.38.306.118 I slot release: id 3 | task 8161 | stop processing: n_tokens = 1327, truncated = 0 4.38.306.885 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 679873032846 4.38.306.950 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.848 MiB) 4.38.464.595 I slot launch_slot_: id 0 | task 8425 | processing task, is_child = 0 4.38.464.657 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 4.38.626.585 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 4.38.780.333 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 4.38.794.583 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 4.38.982.123 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 679873033069 4.38.982.253 I slot launch_slot_: id 1 | task 8426 | processing task, is_child = 0 4.38.982.345 I slot get_availabl: id 2 | task -1 | selected slot by LRU, t_last = 679873033285 4.38.982.415 I slot launch_slot_: id 2 | task 8427 | processing task, is_child = 0 4.38.982.465 I slot get_availabl: id 3 | task -1 | selected slot by LRU, t_last = 679873061418 4.38.982.536 I slot launch_slot_: id 3 | task 8428 | processing task, is_child = 0 4.39.725.743 I slot print_timing: id 4 | task 8164 | prompt eval time = 1765.57 ms / 1029 tokens ( 1.72 ms per token, 582.81 tokens per second) 4.39.725.746 I slot print_timing: id 4 | task 8164 | eval time = 7043.78 ms / 256 tokens ( 27.62 ms per token, 36.20 tokens per second) 4.39.725.747 I slot print_timing: id 4 | task 8164 | total time = 8809.35 ms / 1285 tokens 4.39.725.748 I slot print_timing: id 4 | task 8164 | graphs reused = 8134 4.39.725.796 I slot release: id 4 | task 8164 | stop processing: n_tokens = 1326, truncated = 0 4.39.726.027 I slot print_timing: id 5 | task 8165 | prompt eval time = 1711.70 ms / 953 tokens ( 1.80 ms per token, 556.76 tokens per second) 4.39.726.030 I slot print_timing: id 5 | task 8165 | eval time = 7043.84 ms / 256 tokens ( 27.62 ms per token, 36.20 tokens per second) 4.39.726.030 I slot print_timing: id 5 | task 8165 | total time = 8755.54 ms / 1209 tokens 4.39.726.031 I slot print_timing: id 5 | task 8165 | graphs reused = 8134 4.39.726.057 I slot release: id 5 | task 8165 | stop processing: n_tokens = 1250, truncated = 0 4.39.726.280 I slot print_timing: id 6 | task 8166 | prompt eval time = 1653.68 ms / 1034 tokens ( 1.60 ms per token, 625.27 tokens per second) 4.39.726.282 I slot print_timing: id 6 | task 8166 | eval time = 7043.84 ms / 256 tokens ( 27.62 ms per token, 36.20 tokens per second) 4.39.726.283 I slot print_timing: id 6 | task 8166 | total time = 8697.52 ms / 1290 tokens 4.39.726.283 I slot print_timing: id 6 | task 8166 | graphs reused = 8134 4.39.726.311 I slot release: id 6 | task 8166 | stop processing: n_tokens = 1331, truncated = 0 4.39.726.547 I slot print_timing: id 7 | task 8167 | n_gen = 255, tg = 36.46 t/s, tg_3s = 29.52 t/s 4.40.415.784 I slot print_timing: id 7 | task 8167 | prompt eval time = 1673.54 ms / 926 tokens ( 1.81 ms per token, 553.32 tokens per second) 4.40.415.788 I slot print_timing: id 7 | task 8167 | eval time = 7655.36 ms / 256 tokens ( 30.02 ms per token, 33.31 tokens per second) 4.40.415.788 I slot print_timing: id 7 | task 8167 | total time = 9328.91 ms / 1182 tokens 4.40.415.789 I slot print_timing: id 7 | task 8167 | graphs reused = 8135 4.40.415.824 I slot release: id 7 | task 8167 | stop processing: n_tokens = 1223, truncated = 0 4.40.415.837 I slot get_availabl: id 4 | task -1 | selected slot by LRU, t_last = 679874481096 4.40.415.904 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 4.40.582.185 I slot launch_slot_: id 4 | task 8431 | processing task, is_child = 0 4.40.582.244 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 4.40.737.185 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 4.40.889.712 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 4.41.077.896 I slot get_availabl: id 5 | task -1 | selected slot by LRU, t_last = 679874481357 4.41.078.046 I slot launch_slot_: id 5 | task 8432 | processing task, is_child = 0 4.41.078.146 I slot get_availabl: id 6 | task -1 | selected slot by LRU, t_last = 679874481612 4.41.078.221 I slot launch_slot_: id 6 | task 8433 | processing task, is_child = 0 4.41.078.265 I slot get_availabl: id 7 | task -1 | selected slot by LRU, t_last = 679875171124 4.41.078.333 I slot launch_slot_: id 7 | task 8434 | processing task, is_child = 0 4.45.169.426 I slot print_timing: id 0 | task 8425 | n_gen = 100, tg = 31.47 t/s, tg_3s = 31.79 t/s 4.45.169.607 I slot print_timing: id 1 | task 8426 | n_gen = 100, tg = 31.47 t/s, tg_3s = 31.79 t/s 4.45.169.791 I slot print_timing: id 2 | task 8427 | n_gen = 100, tg = 31.47 t/s, tg_3s = 31.79 t/s 4.45.780.441 I slot print_timing: id 3 | task 8428 | n_gen = 127, tg = 41.99 t/s, tg_3s = 42.33 t/s 4.45.998.512 I slot print_timing: id 4 | task 8431 | n_gen = 136, tg = 44.84 t/s, tg_3s = 45.17 t/s 4.45.998.688 I slot print_timing: id 5 | task 8432 | n_gen = 136, tg = 44.84 t/s, tg_3s = 45.17 t/s 4.45.998.869 I slot print_timing: id 6 | task 8433 | n_gen = 136, tg = 44.84 t/s, tg_3s = 45.17 t/s 4.46.086.168 I slot print_timing: id 7 | task 8434 | n_gen = 139, tg = 45.70 t/s, tg_3s = 46.03 t/s 4.48.185.135 I slot print_timing: id 0 | task 8425 | n_gen = 238, tg = 38.46 t/s, tg_3s = 45.76 t/s 4.48.185.307 I slot print_timing: id 1 | task 8426 | n_gen = 238, tg = 38.46 t/s, tg_3s = 45.76 t/s 4.48.185.483 I slot print_timing: id 2 | task 8427 | n_gen = 238, tg = 38.47 t/s, tg_3s = 45.76 t/s 4.48.578.440 I slot print_timing: id 0 | task 8425 | prompt eval time = 3040.95 ms / 1018 tokens ( 2.99 ms per token, 334.76 tokens per second) 4.48.578.442 I slot print_timing: id 0 | task 8425 | eval time = 6554.93 ms / 256 tokens ( 25.71 ms per token, 38.90 tokens per second) 4.48.578.442 I slot print_timing: id 0 | task 8425 | total time = 9595.89 ms / 1274 tokens 4.48.578.443 I slot print_timing: id 0 | task 8425 | graphs reused = 8387 4.48.578.487 I slot release: id 0 | task 8425 | stop processing: n_tokens = 1315, truncated = 0 4.48.578.675 I slot print_timing: id 1 | task 8426 | prompt eval time = 2986.21 ms / 1034 tokens ( 2.89 ms per token, 346.26 tokens per second) 4.48.578.676 I slot print_timing: id 1 | task 8426 | eval time = 6554.90 ms / 256 tokens ( 25.71 ms per token, 38.90 tokens per second) 4.48.578.677 I slot print_timing: id 1 | task 8426 | total time = 9541.11 ms / 1290 tokens 4.48.578.677 I slot print_timing: id 1 | task 8426 | graphs reused = 8387 4.48.578.715 I slot release: id 1 | task 8426 | stop processing: n_tokens = 1331, truncated = 0 4.48.578.904 I slot print_timing: id 2 | task 8427 | prompt eval time = 2929.05 ms / 932 tokens ( 3.14 ms per token, 318.19 tokens per second) 4.48.578.906 I slot print_timing: id 2 | task 8427 | eval time = 6554.87 ms / 256 tokens ( 25.71 ms per token, 38.90 tokens per second) 4.48.578.906 I slot print_timing: id 2 | task 8427 | total time = 9483.92 ms / 1188 tokens 4.48.578.906 I slot print_timing: id 2 | task 8427 | graphs reused = 8387 4.48.578.934 I slot release: id 2 | task 8427 | stop processing: n_tokens = 1229, truncated = 0 4.48.606.994 I slot print_timing: id 3 | task 8428 | prompt eval time = 3628.85 ms / 897 tokens ( 4.05 ms per token, 247.19 tokens per second) 4.48.606.996 I slot print_timing: id 3 | task 8428 | eval time = 5826.92 ms / 256 tokens ( 22.85 ms per token, 43.76 tokens per second) 4.48.606.997 I slot print_timing: id 3 | task 8428 | total time = 9455.77 ms / 1153 tokens 4.48.606.997 I slot print_timing: id 3 | task 8428 | graphs reused = 8387 4.48.607.025 I slot release: id 3 | task 8428 | stop processing: n_tokens = 1194, truncated = 0 4.48.607.713 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 679883333786 4.48.607.779 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 672.782 MiB) 4.48.771.566 I slot launch_slot_: id 0 | task 8692 | processing task, is_child = 0 4.48.771.629 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 4.48.927.975 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 672.595 MiB) 4.49.076.225 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 674.595 MiB) 4.49.260.823 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 679883334014 4.49.260.959 I slot launch_slot_: id 1 | task 8693 | processing task, is_child = 0 4.49.261.049 I slot get_availabl: id 2 | task -1 | selected slot by LRU, t_last = 679883334234 4.49.261.123 I slot launch_slot_: id 2 | task 8694 | processing task, is_child = 0 4.49.261.167 I slot get_availabl: id 3 | task -1 | selected slot by LRU, t_last = 679883362324 4.49.261.234 I slot launch_slot_: id 3 | task 8695 | processing task, is_child = 0 4.50.044.488 I slot print_timing: id 4 | task 8431 | prompt eval time = 1765.93 ms / 1014 tokens ( 1.74 ms per token, 574.20 tokens per second) 4.50.044.494 I slot print_timing: id 4 | task 8431 | eval time = 7056.80 ms / 256 tokens ( 27.67 ms per token, 36.14 tokens per second) 4.50.044.494 I slot print_timing: id 4 | task 8431 | total time = 8822.73 ms / 1270 tokens 4.50.044.495 I slot print_timing: id 4 | task 8431 | graphs reused = 8388 4.50.044.538 I slot release: id 4 | task 8431 | stop processing: n_tokens = 1311, truncated = 0 4.50.044.759 I slot print_timing: id 5 | task 8432 | prompt eval time = 1712.33 ms / 980 tokens ( 1.75 ms per token, 572.32 tokens per second) 4.50.044.760 I slot print_timing: id 5 | task 8432 | eval time = 7056.82 ms / 256 tokens ( 27.67 ms per token, 36.14 tokens per second) 4.50.044.760 I slot print_timing: id 5 | task 8432 | total time = 8769.15 ms / 1236 tokens 4.50.044.761 I slot print_timing: id 5 | task 8432 | graphs reused = 8388 4.50.044.790 I slot release: id 5 | task 8432 | stop processing: n_tokens = 1277, truncated = 0 4.50.045.015 I slot print_timing: id 6 | task 8433 | prompt eval time = 1655.21 ms / 963 tokens ( 1.72 ms per token, 581.80 tokens per second) 4.50.045.016 I slot print_timing: id 6 | task 8433 | eval time = 7056.82 ms / 256 tokens ( 27.67 ms per token, 36.14 tokens per second) 4.50.045.017 I slot print_timing: id 6 | task 8433 | total time = 8712.03 ms / 1219 tokens 4.50.045.017 I slot print_timing: id 6 | task 8433 | graphs reused = 8388 4.50.045.046 I slot release: id 6 | task 8433 | stop processing: n_tokens = 1260, truncated = 0 4.50.045.256 I slot print_timing: id 7 | task 8434 | n_gen = 255, tg = 36.40 t/s, tg_3s = 29.30 t/s 4.50.738.300 I slot print_timing: id 7 | task 8434 | prompt eval time = 1675.94 ms / 1033 tokens ( 1.62 ms per token, 616.37 tokens per second) 4.50.738.303 I slot print_timing: id 7 | task 8434 | eval time = 7671.91 ms / 256 tokens ( 30.09 ms per token, 33.24 tokens per second) 4.50.738.303 I slot print_timing: id 7 | task 8434 | total time = 9347.85 ms / 1289 tokens 4.50.738.304 I slot print_timing: id 7 | task 8434 | graphs reused = 8389 4.50.738.335 I slot release: id 7 | task 8434 | stop processing: n_tokens = 1330, truncated = 0 4.50.738.349 I slot get_availabl: id 4 | task -1 | selected slot by LRU, t_last = 679884799837 4.50.738.416 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 4.50.895.575 I slot launch_slot_: id 4 | task 8698 | processing task, is_child = 0 4.50.895.635 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 675.471 MiB) 4.51.050.537 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 831.099 MiB) 4.51.208.813 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.410 MiB) 4.51.398.065 I slot get_availabl: id 5 | task -1 | selected slot by LRU, t_last = 679884800089 4.51.398.201 I slot launch_slot_: id 5 | task 8699 | processing task, is_child = 0 4.51.398.303 I slot get_availabl: id 6 | task -1 | selected slot by LRU, t_last = 679884800345 4.51.398.378 I slot launch_slot_: id 6 | task 8700 | processing task, is_child = 0 4.51.398.425 I slot get_availabl: id 7 | task -1 | selected slot by LRU, t_last = 679885493635 4.51.398.495 I slot launch_slot_: id 7 | task 8701 | processing task, is_child = 0 4.55.512.126 I slot print_timing: id 0 | task 8692 | n_gen = 100, tg = 31.41 t/s, tg_3s = 31.73 t/s 4.55.512.299 I slot print_timing: id 1 | task 8693 | n_gen = 100, tg = 31.41 t/s, tg_3s = 31.73 t/s 4.55.512.469 I slot print_timing: id 2 | task 8694 | n_gen = 100, tg = 31.41 t/s, tg_3s = 31.73 t/s 4.56.143.808 I slot print_timing: id 3 | task 8695 | n_gen = 128, tg = 42.05 t/s, tg_3s = 42.38 t/s 4.56.340.044 I slot print_timing: id 4 | task 8698 | n_gen = 136, tg = 44.88 t/s, tg_3s = 45.21 t/s 4.56.340.235 I slot print_timing: id 5 | task 8699 | n_gen = 136, tg = 44.88 t/s, tg_3s = 45.21 t/s 4.56.340.429 I slot print_timing: id 6 | task 8700 | n_gen = 136, tg = 44.88 t/s, tg_3s = 45.21 t/s 4.56.427.704 I slot print_timing: id 7 | task 8701 | n_gen = 139, tg = 45.75 t/s, tg_3s = 46.08 t/s 4.58.526.034 I slot print_timing: id 0 | task 8692 | n_gen = 238, tg = 38.44 t/s, tg_3s = 45.79 t/s 4.58.526.204 I slot print_timing: id 1 | task 8693 | n_gen = 238, tg = 38.44 t/s, tg_3s = 45.79 t/s 4.58.526.376 I slot print_timing: id 2 | task 8694 | n_gen = 238, tg = 38.44 t/s, tg_3s = 45.79 t/s 4.58.918.650 I slot print_timing: id 0 | task 8692 | prompt eval time = 3099.03 ms / 1034 tokens ( 3.00 ms per token, 333.65 tokens per second) 4.58.918.652 I slot print_timing: id 0 | task 8692 | eval time = 6558.36 ms / 256 tokens ( 25.72 ms per token, 38.88 tokens per second) 4.58.918.652 I slot print_timing: id 0 | task 8692 | total time = 9657.40 ms / 1290 tokens 4.58.918.653 I slot print_timing: id 0 | task 8692 | graphs reused = 8641 4.58.918.698 I slot release: id 0 | task 8692 | stop processing: n_tokens = 1331, truncated = 0 4.58.918.882 I slot print_timing: id 1 | task 8693 | prompt eval time = 3045.32 ms / 946 tokens ( 3.22 ms per token, 310.64 tokens per second) 4.58.918.883 I slot print_timing: id 1 | task 8693 | eval time = 6558.33 ms / 256 tokens ( 25.72 ms per token, 38.88 tokens per second) 4.58.918.884 I slot print_timing: id 1 | task 8693 | total time = 9603.65 ms / 1202 tokens 4.58.918.884 I slot print_timing: id 1 | task 8693 | graphs reused = 8641 4.58.918.916 I slot release: id 1 | task 8693 | stop processing: n_tokens = 1243, truncated = 0 4.58.919.098 I slot print_timing: id 2 | task 8694 | prompt eval time = 2990.21 ms / 1034 tokens ( 2.89 ms per token, 345.79 tokens per second) 4.58.919.100 I slot print_timing: id 2 | task 8694 | eval time = 6558.26 ms / 256 tokens ( 25.72 ms per token, 38.88 tokens per second) 4.58.919.100 I slot print_timing: id 2 | task 8694 | total time = 9548.47 ms / 1290 tokens 4.58.919.100 I slot print_timing: id 2 | task 8694 | graphs reused = 8641 4.58.919.130 I slot release: id 2 | task 8694 | stop processing: n_tokens = 1331, truncated = 0 4.58.947.257 I slot print_timing: id 3 | task 8695 | prompt eval time = 3695.29 ms / 966 tokens ( 3.83 ms per token, 261.41 tokens per second) 4.58.947.259 I slot print_timing: id 3 | task 8695 | eval time = 5823.80 ms / 256 tokens ( 22.84 ms per token, 43.79 tokens per second) 4.58.947.260 I slot print_timing: id 3 | task 8695 | total time = 9519.09 ms / 1222 tokens 4.58.947.260 I slot print_timing: id 3 | task 8695 | graphs reused = 8641 4.58.947.297 I slot release: id 3 | task 8695 | stop processing: n_tokens = 1263, truncated = 0 4.58.948.029 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 679893673997 4.58.948.099 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 676.659 MiB) 4.59.111.594 I slot launch_slot_: id 0 | task 8959 | processing task, is_child = 0 4.59.111.653 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 4.59.266.308 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 824.597 MiB) 4.59.437.089 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 680.723 MiB) 4.59.625.777 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 679893674216 4.59.625.911 I slot launch_slot_: id 1 | task 8960 | processing task, is_child = 0 4.59.626.004 I slot get_availabl: id 2 | task -1 | selected slot by LRU, t_last = 679893674429 4.59.626.078 I slot launch_slot_: id 2 | task 8961 | processing task, is_child = 0 4.59.626.125 I slot get_availabl: id 3 | task -1 | selected slot by LRU, t_last = 679893702598 4.59.626.199 I slot launch_slot_: id 3 | task 8962 | processing task, is_child = 0 5.00.394.159 I slot print_timing: id 4 | task 8698 | prompt eval time = 1789.93 ms / 1035 tokens ( 1.73 ms per token, 578.23 tokens per second) 5.00.394.164 I slot print_timing: id 4 | task 8698 | eval time = 7062.31 ms / 256 tokens ( 27.70 ms per token, 36.11 tokens per second) 5.00.394.164 I slot print_timing: id 4 | task 8698 | total time = 8852.24 ms / 1291 tokens 5.00.394.165 I slot print_timing: id 4 | task 8698 | graphs reused = 8642 5.00.394.209 I slot release: id 4 | task 8698 | stop processing: n_tokens = 1332, truncated = 0 5.00.394.429 I slot print_timing: id 5 | task 8699 | prompt eval time = 1736.52 ms / 949 tokens ( 1.83 ms per token, 546.49 tokens per second) 5.00.394.432 I slot print_timing: id 5 | task 8699 | eval time = 7062.25 ms / 256 tokens ( 27.70 ms per token, 36.11 tokens per second) 5.00.394.433 I slot print_timing: id 5 | task 8699 | total time = 8798.77 ms / 1205 tokens 5.00.394.433 I slot print_timing: id 5 | task 8699 | graphs reused = 8642 5.00.394.461 I slot release: id 5 | task 8699 | stop processing: n_tokens = 1246, truncated = 0 5.00.394.669 I slot print_timing: id 6 | task 8700 | prompt eval time = 1678.97 ms / 1034 tokens ( 1.62 ms per token, 615.85 tokens per second) 5.00.394.670 I slot print_timing: id 6 | task 8700 | eval time = 7062.22 ms / 256 tokens ( 27.69 ms per token, 36.11 tokens per second) 5.00.394.671 I slot print_timing: id 6 | task 8700 | total time = 8741.19 ms / 1290 tokens 5.00.394.671 I slot print_timing: id 6 | task 8700 | graphs reused = 8642 5.00.394.704 I slot release: id 6 | task 8700 | stop processing: n_tokens = 1331, truncated = 0 5.00.394.918 I slot print_timing: id 7 | task 8701 | n_gen = 255, tg = 36.37 t/s, tg_3s = 29.24 t/s 5.01.087.666 I slot print_timing: id 7 | task 8701 | prompt eval time = 1699.77 ms / 1035 tokens ( 1.64 ms per token, 608.91 tokens per second) 5.01.087.671 I slot print_timing: id 7 | task 8701 | eval time = 7676.57 ms / 256 tokens ( 30.10 ms per token, 33.22 tokens per second) 5.01.087.671 I slot print_timing: id 7 | task 8701 | total time = 9376.34 ms / 1291 tokens 5.01.087.672 I slot print_timing: id 7 | task 8701 | graphs reused = 8643 5.01.087.715 I slot release: id 7 | task 8701 | stop processing: n_tokens = 1332, truncated = 0 5.01.087.730 I slot get_availabl: id 4 | task -1 | selected slot by LRU, t_last = 679895149509 5.01.087.798 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 5.01.244.718 I slot launch_slot_: id 4 | task 8965 | processing task, is_child = 0 5.01.244.775 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 675.346 MiB) 5.01.392.088 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 822.783 MiB) 5.01.554.321 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 680.472 MiB) 5.01.744.208 I slot get_availabl: id 5 | task -1 | selected slot by LRU, t_last = 679895149760 5.01.744.360 I slot launch_slot_: id 5 | task 8966 | processing task, is_child = 0 5.01.744.456 I slot get_availabl: id 6 | task -1 | selected slot by LRU, t_last = 679895150004 5.01.744.529 I slot launch_slot_: id 6 | task 8967 | processing task, is_child = 0 5.01.744.576 I slot get_availabl: id 7 | task -1 | selected slot by LRU, t_last = 679895843015 5.01.744.646 I slot launch_slot_: id 7 | task 8968 | processing task, is_child = 0 5.05.833.490 I slot print_timing: id 0 | task 8959 | n_gen = 100, tg = 31.46 t/s, tg_3s = 31.78 t/s 5.05.833.675 I slot print_timing: id 1 | task 8960 | n_gen = 100, tg = 31.46 t/s, tg_3s = 31.78 t/s 5.05.833.880 I slot print_timing: id 2 | task 8961 | n_gen = 100, tg = 31.46 t/s, tg_3s = 31.78 t/s 5.06.466.187 I slot print_timing: id 3 | task 8962 | n_gen = 128, tg = 42.09 t/s, tg_3s = 42.42 t/s 5.06.664.754 I slot print_timing: id 4 | task 8965 | n_gen = 136, tg = 44.89 t/s, tg_3s = 45.22 t/s 5.06.665.058 I slot print_timing: id 5 | task 8966 | n_gen = 136, tg = 44.88 t/s, tg_3s = 45.22 t/s 5.06.665.290 I slot print_timing: id 6 | task 8967 | n_gen = 136, tg = 44.88 t/s, tg_3s = 45.22 t/s 5.06.754.799 I slot print_timing: id 7 | task 8968 | n_gen = 139, tg = 45.71 t/s, tg_3s = 46.05 t/s 5.08.854.519 I slot print_timing: id 0 | task 8959 | n_gen = 238, tg = 38.42 t/s, tg_3s = 45.68 t/s 5.08.854.695 I slot print_timing: id 1 | task 8960 | n_gen = 238, tg = 38.42 t/s, tg_3s = 45.68 t/s 5.08.854.883 I slot print_timing: id 2 | task 8961 | n_gen = 238, tg = 38.42 t/s, tg_3s = 45.68 t/s 5.09.247.743 I slot print_timing: id 0 | task 8959 | prompt eval time = 3060.15 ms / 967 tokens ( 3.16 ms per token, 316.00 tokens per second) 5.09.247.745 I slot print_timing: id 0 | task 8959 | eval time = 6561.38 ms / 256 tokens ( 25.73 ms per token, 38.86 tokens per second) 5.09.247.745 I slot print_timing: id 0 | task 8959 | total time = 9621.52 ms / 1223 tokens 5.09.247.746 I slot print_timing: id 0 | task 8959 | graphs reused = 8895 5.09.247.784 I slot release: id 0 | task 8959 | stop processing: n_tokens = 1264, truncated = 0 5.09.247.965 I slot print_timing: id 1 | task 8960 | prompt eval time = 3007.08 ms / 1034 tokens ( 2.91 ms per token, 343.86 tokens per second) 5.09.247.967 I slot print_timing: id 1 | task 8960 | eval time = 6561.34 ms / 256 tokens ( 25.73 ms per token, 38.86 tokens per second) 5.09.247.967 I slot print_timing: id 1 | task 8960 | total time = 9568.42 ms / 1290 tokens 5.09.247.967 I slot print_timing: id 1 | task 8960 | graphs reused = 8895 5.09.247.996 I slot release: id 1 | task 8960 | stop processing: n_tokens = 1331, truncated = 0 5.09.248.186 I slot print_timing: id 2 | task 8961 | prompt eval time = 2951.34 ms / 1034 tokens ( 2.85 ms per token, 350.35 tokens per second) 5.09.248.187 I slot print_timing: id 2 | task 8961 | eval time = 6561.30 ms / 256 tokens ( 25.73 ms per token, 38.86 tokens per second) 5.09.248.188 I slot print_timing: id 2 | task 8961 | total time = 9512.64 ms / 1290 tokens 5.09.248.188 I slot print_timing: id 2 | task 8961 | graphs reused = 8895 5.09.248.214 I slot release: id 2 | task 8961 | stop processing: n_tokens = 1331, truncated = 0 5.09.276.378 I slot print_timing: id 3 | task 8962 | prompt eval time = 3655.10 ms / 939 tokens ( 3.89 ms per token, 256.90 tokens per second) 5.09.276.380 I slot print_timing: id 3 | task 8962 | eval time = 5827.82 ms / 256 tokens ( 22.85 ms per token, 43.76 tokens per second) 5.09.276.381 I slot print_timing: id 3 | task 8962 | total time = 9482.92 ms / 1195 tokens 5.09.276.381 I slot print_timing: id 3 | task 8962 | graphs reused = 8895 5.09.276.413 I slot release: id 3 | task 8962 | stop processing: n_tokens = 1236, truncated = 0 5.09.277.158 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 679904003084 5.09.277.223 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 678.347 MiB) 5.09.443.749 I slot launch_slot_: id 0 | task 9226 | processing task, is_child = 0 5.09.443.812 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 677.284 MiB) 5.09.601.482 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 831.286 MiB) 5.09.773.279 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 5.09.962.706 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 679904003296 5.09.962.840 I slot launch_slot_: id 1 | task 9227 | processing task, is_child = 0 5.09.962.931 I slot get_availabl: id 2 | task -1 | selected slot by LRU, t_last = 679904003514 5.09.963.005 I slot launch_slot_: id 2 | task 9228 | processing task, is_child = 0 5.09.963.051 I slot get_availabl: id 3 | task -1 | selected slot by LRU, t_last = 679904031713 5.09.963.121 I slot launch_slot_: id 3 | task 9229 | processing task, is_child = 0 5.10.725.022 I slot print_timing: id 4 | task 8965 | prompt eval time = 1770.02 ms / 1034 tokens ( 1.71 ms per token, 584.17 tokens per second) 5.10.725.026 I slot print_timing: id 4 | task 8965 | eval time = 7067.93 ms / 256 tokens ( 27.72 ms per token, 36.08 tokens per second) 5.10.725.027 I slot print_timing: id 4 | task 8965 | total time = 8837.95 ms / 1290 tokens 5.10.725.028 I slot print_timing: id 4 | task 8965 | graphs reused = 8895 5.10.725.067 I slot release: id 4 | task 8965 | stop processing: n_tokens = 1331, truncated = 0 5.10.725.292 I slot print_timing: id 5 | task 8966 | prompt eval time = 1716.09 ms / 939 tokens ( 1.83 ms per token, 547.17 tokens per second) 5.10.725.293 I slot print_timing: id 5 | task 8966 | eval time = 7067.96 ms / 256 tokens ( 27.72 ms per token, 36.08 tokens per second) 5.10.725.294 I slot print_timing: id 5 | task 8966 | total time = 8784.05 ms / 1195 tokens 5.10.725.294 I slot print_timing: id 5 | task 8966 | graphs reused = 8895 5.10.725.323 I slot release: id 5 | task 8966 | stop processing: n_tokens = 1236, truncated = 0 5.10.725.574 I slot print_timing: id 6 | task 8967 | prompt eval time = 1658.17 ms / 1034 tokens ( 1.60 ms per token, 623.58 tokens per second) 5.10.725.576 I slot print_timing: id 6 | task 8967 | eval time = 7068.00 ms / 256 tokens ( 27.72 ms per token, 36.08 tokens per second) 5.10.725.576 I slot print_timing: id 6 | task 8967 | total time = 8726.17 ms / 1290 tokens 5.10.725.576 I slot print_timing: id 6 | task 8967 | graphs reused = 8895 5.10.725.606 I slot release: id 6 | task 8967 | stop processing: n_tokens = 1331, truncated = 0 5.10.725.832 I slot print_timing: id 7 | task 8968 | n_gen = 255, tg = 36.34 t/s, tg_3s = 29.21 t/s 5.11.418.217 I slot print_timing: id 7 | task 8968 | prompt eval time = 1678.51 ms / 1034 tokens ( 1.62 ms per token, 616.02 tokens per second) 5.11.418.220 I slot print_timing: id 7 | task 8968 | eval time = 7682.19 ms / 256 tokens ( 30.13 ms per token, 33.19 tokens per second) 5.11.418.220 I slot print_timing: id 7 | task 8968 | total time = 9360.69 ms / 1290 tokens 5.11.418.221 I slot print_timing: id 7 | task 8968 | graphs reused = 8896 5.11.418.261 I slot release: id 7 | task 8968 | stop processing: n_tokens = 1331, truncated = 0 5.11.418.275 I slot get_availabl: id 4 | task -1 | selected slot by LRU, t_last = 679905480366 5.11.418.346 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 676.221 MiB) 5.11.576.000 I slot launch_slot_: id 4 | task 9232 | processing task, is_child = 0 5.11.576.058 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 5.11.733.847 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 827.097 MiB) 5.11.899.539 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.785 MiB) 5.12.084.503 I slot get_availabl: id 5 | task -1 | selected slot by LRU, t_last = 679905480623 5.12.084.641 I slot launch_slot_: id 5 | task 9233 | processing task, is_child = 0 5.12.084.737 I slot get_availabl: id 6 | task -1 | selected slot by LRU, t_last = 679905480906 5.12.084.810 I slot launch_slot_: id 6 | task 9234 | processing task, is_child = 0 5.12.084.861 I slot get_availabl: id 7 | task -1 | selected slot by LRU, t_last = 679906173561 5.12.084.929 I slot launch_slot_: id 7 | task 9235 | processing task, is_child = 0 5.16.205.438 I slot print_timing: id 0 | task 9226 | n_gen = 100, tg = 31.44 t/s, tg_3s = 31.76 t/s 5.16.205.617 I slot print_timing: id 1 | task 9227 | n_gen = 100, tg = 31.44 t/s, tg_3s = 31.76 t/s 5.16.205.803 I slot print_timing: id 2 | task 9228 | n_gen = 100, tg = 31.44 t/s, tg_3s = 31.76 t/s 5.16.838.101 I slot print_timing: id 3 | task 9229 | n_gen = 128, tg = 42.08 t/s, tg_3s = 42.41 t/s 5.17.034.446 I slot print_timing: id 4 | task 9232 | n_gen = 136, tg = 44.92 t/s, tg_3s = 45.25 t/s 5.17.034.627 I slot print_timing: id 5 | task 9233 | n_gen = 136, tg = 44.92 t/s, tg_3s = 45.25 t/s 5.17.034.811 I slot print_timing: id 6 | task 9234 | n_gen = 136, tg = 44.92 t/s, tg_3s = 45.25 t/s 5.17.122.187 I slot print_timing: id 7 | task 9235 | n_gen = 139, tg = 45.79 t/s, tg_3s = 46.12 t/s 5.19.221.345 I slot print_timing: id 0 | task 9226 | n_gen = 238, tg = 38.44 t/s, tg_3s = 45.76 t/s 5.19.221.523 I slot print_timing: id 1 | task 9227 | n_gen = 238, tg = 38.45 t/s, tg_3s = 45.76 t/s 5.19.221.706 I slot print_timing: id 2 | task 9228 | n_gen = 238, tg = 38.45 t/s, tg_3s = 45.76 t/s 5.19.615.360 I slot print_timing: id 0 | task 9226 | prompt eval time = 3093.52 ms / 883 tokens ( 3.50 ms per token, 285.44 tokens per second) 5.19.615.362 I slot print_timing: id 0 | task 9226 | eval time = 6558.70 ms / 256 tokens ( 25.72 ms per token, 38.88 tokens per second) 5.19.615.362 I slot print_timing: id 0 | task 9226 | total time = 9652.22 ms / 1139 tokens 5.19.615.363 I slot print_timing: id 0 | task 9226 | graphs reused = 9148 5.19.615.401 I slot release: id 0 | task 9226 | stop processing: n_tokens = 1180, truncated = 0 5.19.615.577 I slot print_timing: id 1 | task 9227 | prompt eval time = 3040.24 ms / 1035 tokens ( 2.94 ms per token, 340.43 tokens per second) 5.19.615.578 I slot print_timing: id 1 | task 9227 | eval time = 6558.63 ms / 256 tokens ( 25.72 ms per token, 38.88 tokens per second) 5.19.615.579 I slot print_timing: id 1 | task 9227 | total time = 9598.86 ms / 1291 tokens 5.19.615.579 I slot print_timing: id 1 | task 9227 | graphs reused = 9148 5.19.615.611 I slot release: id 1 | task 9227 | stop processing: n_tokens = 1332, truncated = 0 5.19.615.798 I slot print_timing: id 2 | task 9228 | prompt eval time = 2985.65 ms / 1034 tokens ( 2.89 ms per token, 346.32 tokens per second) 5.19.615.799 I slot print_timing: id 2 | task 9228 | eval time = 6558.58 ms / 256 tokens ( 25.72 ms per token, 38.88 tokens per second) 5.19.615.799 I slot print_timing: id 2 | task 9228 | total time = 9544.23 ms / 1290 tokens 5.19.615.800 I slot print_timing: id 2 | task 9228 | graphs reused = 9148 5.19.615.829 I slot release: id 2 | task 9228 | stop processing: n_tokens = 1331, truncated = 0 5.19.643.991 I slot print_timing: id 3 | task 9229 | prompt eval time = 3691.38 ms / 1031 tokens ( 3.58 ms per token, 279.30 tokens per second) 5.19.643.993 I slot print_timing: id 3 | task 9229 | eval time = 5824.20 ms / 256 tokens ( 22.84 ms per token, 43.78 tokens per second) 5.19.643.994 I slot print_timing: id 3 | task 9229 | total time = 9515.58 ms / 1287 tokens 5.19.643.994 I slot print_timing: id 3 | task 9229 | graphs reused = 9148 5.19.644.029 I slot release: id 3 | task 9229 | stop processing: n_tokens = 1328, truncated = 0 5.19.644.858 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 679914370701 5.19.644.923 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 676.408 MiB) 5.19.795.638 I slot launch_slot_: id 0 | task 9493 | processing task, is_child = 0 5.19.795.705 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 5.19.951.551 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 831.412 MiB) 5.20.114.126 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 677.534 MiB) 5.20.300.890 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 679914370911 5.20.301.029 I slot launch_slot_: id 1 | task 9494 | processing task, is_child = 0 5.20.301.123 I slot get_availabl: id 2 | task -1 | selected slot by LRU, t_last = 679914371129 5.20.301.199 I slot launch_slot_: id 2 | task 9495 | processing task, is_child = 0 5.20.301.250 I slot get_availabl: id 3 | task -1 | selected slot by LRU, t_last = 679914399328 5.20.301.320 I slot launch_slot_: id 3 | task 9496 | processing task, is_child = 0 5.21.060.595 I slot print_timing: id 4 | task 9232 | prompt eval time = 1798.72 ms / 1019 tokens ( 1.77 ms per token, 566.51 tokens per second) 5.21.060.598 I slot print_timing: id 4 | task 9232 | eval time = 7031.56 ms / 256 tokens ( 27.57 ms per token, 36.27 tokens per second) 5.21.060.598 I slot print_timing: id 4 | task 9232 | total time = 8830.28 ms / 1275 tokens 5.21.060.599 I slot print_timing: id 4 | task 9232 | graphs reused = 9149 5.21.060.636 I slot release: id 4 | task 9232 | stop processing: n_tokens = 1316, truncated = 0 5.21.060.870 I slot print_timing: id 5 | task 9233 | prompt eval time = 1744.77 ms / 968 tokens ( 1.80 ms per token, 554.80 tokens per second) 5.21.060.871 I slot print_timing: id 5 | task 9233 | eval time = 7031.60 ms / 256 tokens ( 27.57 ms per token, 36.26 tokens per second) 5.21.060.871 I slot print_timing: id 5 | task 9233 | total time = 8776.37 ms / 1224 tokens 5.21.060.872 I slot print_timing: id 5 | task 9233 | graphs reused = 9149 5.21.060.897 I slot release: id 5 | task 9233 | stop processing: n_tokens = 1265, truncated = 0 5.21.061.113 I slot print_timing: id 6 | task 9234 | prompt eval time = 1686.76 ms / 1034 tokens ( 1.63 ms per token, 613.01 tokens per second) 5.21.061.114 I slot print_timing: id 6 | task 9234 | eval time = 7031.59 ms / 256 tokens ( 27.57 ms per token, 36.26 tokens per second) 5.21.061.114 I slot print_timing: id 6 | task 9234 | total time = 8718.35 ms / 1290 tokens 5.21.061.114 I slot print_timing: id 6 | task 9234 | graphs reused = 9149 5.21.061.137 I slot release: id 6 | task 9234 | stop processing: n_tokens = 1331, truncated = 0 5.21.061.357 I slot print_timing: id 7 | task 9235 | n_gen = 255, tg = 36.53 t/s, tg_3s = 29.45 t/s 5.21.755.069 I slot print_timing: id 7 | task 9235 | prompt eval time = 1707.37 ms / 1036 tokens ( 1.65 ms per token, 606.78 tokens per second) 5.21.755.071 I slot print_timing: id 7 | task 9235 | eval time = 7646.93 ms / 256 tokens ( 29.99 ms per token, 33.35 tokens per second) 5.21.755.072 I slot print_timing: id 7 | task 9235 | total time = 9354.29 ms / 1292 tokens 5.21.755.073 I slot print_timing: id 7 | task 9235 | graphs reused = 9150 5.21.755.111 I slot release: id 7 | task 9235 | stop processing: n_tokens = 1333, truncated = 0 5.21.755.124 I slot get_availabl: id 4 | task -1 | selected slot by LRU, t_last = 679915815936 5.21.755.191 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 5.21.911.866 I slot launch_slot_: id 4 | task 9499 | processing task, is_child = 0 5.21.911.930 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 5.22.070.153 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 825.409 MiB) 5.22.236.855 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 5.22.421.033 I slot get_availabl: id 5 | task -1 | selected slot by LRU, t_last = 679915816197 5.22.421.173 I slot launch_slot_: id 5 | task 9500 | processing task, is_child = 0 5.22.421.277 I slot get_availabl: id 6 | task -1 | selected slot by LRU, t_last = 679915816436 5.22.421.351 I slot launch_slot_: id 6 | task 9501 | processing task, is_child = 0 5.22.421.402 I slot get_availabl: id 7 | task -1 | selected slot by LRU, t_last = 679916510411 5.22.421.476 I slot launch_slot_: id 7 | task 9502 | processing task, is_child = 0 5.26.519.752 I slot print_timing: id 0 | task 9493 | n_gen = 100, tg = 31.46 t/s, tg_3s = 31.77 t/s 5.26.519.928 I slot print_timing: id 1 | task 9494 | n_gen = 100, tg = 31.46 t/s, tg_3s = 31.77 t/s 5.26.520.111 I slot print_timing: id 2 | task 9495 | n_gen = 100, tg = 31.46 t/s, tg_3s = 31.78 t/s 5.27.152.806 I slot print_timing: id 3 | task 9496 | n_gen = 128, tg = 42.09 t/s, tg_3s = 42.42 t/s 5.27.349.093 I slot print_timing: id 4 | task 9499 | n_gen = 136, tg = 44.92 t/s, tg_3s = 45.25 t/s 5.27.349.284 I slot print_timing: id 5 | task 9500 | n_gen = 136, tg = 44.92 t/s, tg_3s = 45.25 t/s 5.27.349.468 I slot print_timing: id 6 | task 9501 | n_gen = 136, tg = 44.92 t/s, tg_3s = 45.25 t/s 5.27.436.806 I slot print_timing: id 7 | task 9502 | n_gen = 139, tg = 45.78 t/s, tg_3s = 46.11 t/s 5.29.538.203 I slot print_timing: id 0 | task 9493 | n_gen = 238, tg = 38.44 t/s, tg_3s = 45.72 t/s 5.29.538.382 I slot print_timing: id 1 | task 9494 | n_gen = 238, tg = 38.44 t/s, tg_3s = 45.72 t/s 5.29.538.565 I slot print_timing: id 2 | task 9495 | n_gen = 238, tg = 38.44 t/s, tg_3s = 45.72 t/s 5.29.932.382 I slot print_timing: id 0 | task 9493 | prompt eval time = 3071.14 ms / 1034 tokens ( 2.97 ms per token, 336.68 tokens per second) 5.29.932.385 I slot print_timing: id 0 | task 9493 | eval time = 6559.90 ms / 256 tokens ( 25.73 ms per token, 38.87 tokens per second) 5.29.932.386 I slot print_timing: id 0 | task 9493 | total time = 9631.04 ms / 1290 tokens 5.29.932.387 I slot print_timing: id 0 | task 9493 | graphs reused = 9402 5.29.932.418 I slot release: id 0 | task 9493 | stop processing: n_tokens = 1331, truncated = 0 5.29.932.607 I slot print_timing: id 1 | task 9494 | prompt eval time = 3018.18 ms / 1034 tokens ( 2.92 ms per token, 342.59 tokens per second) 5.29.932.609 I slot print_timing: id 1 | task 9494 | eval time = 6559.82 ms / 256 tokens ( 25.72 ms per token, 38.87 tokens per second) 5.29.932.610 I slot print_timing: id 1 | task 9494 | total time = 9578.01 ms / 1290 tokens 5.29.932.610 I slot print_timing: id 1 | task 9494 | graphs reused = 9402 5.29.932.647 I slot release: id 1 | task 9494 | stop processing: n_tokens = 1331, truncated = 0 5.29.932.841 I slot print_timing: id 2 | task 9495 | prompt eval time = 2962.93 ms / 933 tokens ( 3.18 ms per token, 314.89 tokens per second) 5.29.932.844 I slot print_timing: id 2 | task 9495 | eval time = 6559.77 ms / 256 tokens ( 25.72 ms per token, 38.87 tokens per second) 5.29.932.844 I slot print_timing: id 2 | task 9495 | total time = 9522.69 ms / 1189 tokens 5.29.932.845 I slot print_timing: id 2 | task 9495 | graphs reused = 9402 5.29.932.877 I slot release: id 2 | task 9495 | stop processing: n_tokens = 1230, truncated = 0 5.29.960.991 I slot print_timing: id 3 | task 9496 | prompt eval time = 3666.98 ms / 932 tokens ( 3.93 ms per token, 254.16 tokens per second) 5.29.960.993 I slot print_timing: id 3 | task 9496 | eval time = 5825.88 ms / 256 tokens ( 22.85 ms per token, 43.77 tokens per second) 5.29.960.994 I slot print_timing: id 3 | task 9496 | total time = 9492.86 ms / 1188 tokens 5.29.960.994 I slot print_timing: id 3 | task 9496 | graphs reused = 9402 5.29.961.028 I slot release: id 3 | task 9496 | stop processing: n_tokens = 1229, truncated = 0 5.29.961.771 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 679924687718 5.29.961.838 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 675.783 MiB) 5.30.131.608 I slot launch_slot_: id 0 | task 9760 | processing task, is_child = 0 5.30.131.670 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 681.723 MiB) 5.30.292.721 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 831.349 MiB) 5.30.454.198 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 672.282 MiB) 5.30.632.500 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 679924687947 5.30.632.634 I slot launch_slot_: id 1 | task 9761 | processing task, is_child = 0 5.30.632.735 I slot get_availabl: id 2 | task -1 | selected slot by LRU, t_last = 679924688177 5.30.632.807 I slot launch_slot_: id 2 | task 9762 | processing task, is_child = 0 5.30.632.856 I slot get_availabl: id 3 | task -1 | selected slot by LRU, t_last = 679924716327 5.30.632.924 I slot launch_slot_: id 3 | task 9763 | processing task, is_child = 0 5.31.417.556 I slot print_timing: id 4 | task 9499 | prompt eval time = 1777.30 ms / 1035 tokens ( 1.72 ms per token, 582.34 tokens per second) 5.31.417.560 I slot print_timing: id 4 | task 9499 | eval time = 7073.98 ms / 256 tokens ( 27.74 ms per token, 36.05 tokens per second) 5.31.417.560 I slot print_timing: id 4 | task 9499 | total time = 8851.29 ms / 1291 tokens 5.31.417.561 I slot print_timing: id 4 | task 9499 | graphs reused = 9403 5.31.417.604 I slot release: id 4 | task 9499 | stop processing: n_tokens = 1332, truncated = 0 5.31.417.844 I slot print_timing: id 5 | task 9500 | prompt eval time = 1723.43 ms / 1034 tokens ( 1.67 ms per token, 599.96 tokens per second) 5.31.417.847 I slot print_timing: id 5 | task 9500 | eval time = 7074.01 ms / 256 tokens ( 27.74 ms per token, 36.05 tokens per second) 5.31.417.847 I slot print_timing: id 5 | task 9500 | total time = 8797.44 ms / 1290 tokens 5.31.417.847 I slot print_timing: id 5 | task 9500 | graphs reused = 9403 5.31.417.891 I slot release: id 5 | task 9500 | stop processing: n_tokens = 1331, truncated = 0 5.31.418.151 I slot print_timing: id 6 | task 9501 | prompt eval time = 1665.19 ms / 966 tokens ( 1.72 ms per token, 580.12 tokens per second) 5.31.418.153 I slot print_timing: id 6 | task 9501 | eval time = 7074.06 ms / 256 tokens ( 27.74 ms per token, 36.05 tokens per second) 5.31.418.153 I slot print_timing: id 6 | task 9501 | total time = 8739.25 ms / 1222 tokens 5.31.418.154 I slot print_timing: id 6 | task 9501 | graphs reused = 9403 5.31.418.183 I slot release: id 6 | task 9501 | stop processing: n_tokens = 1263, truncated = 0 5.31.418.428 I slot print_timing: id 7 | task 9502 | n_gen = 255, tg = 36.31 t/s, tg_3s = 29.13 t/s 5.32.111.383 I slot print_timing: id 7 | task 9502 | prompt eval time = 1684.93 ms / 934 tokens ( 1.80 ms per token, 554.33 tokens per second) 5.32.111.386 I slot print_timing: id 7 | task 9502 | eval time = 7688.90 ms / 256 tokens ( 30.15 ms per token, 33.16 tokens per second) 5.32.111.386 I slot print_timing: id 7 | task 9502 | total time = 9373.83 ms / 1190 tokens 5.32.111.387 I slot print_timing: id 7 | task 9502 | graphs reused = 9404 5.32.111.422 I slot release: id 7 | task 9502 | stop processing: n_tokens = 1231, truncated = 0 5.35.320.683 I slot print_timing: id 0 | task 9760 | n_gen = 133, tg = 43.73 t/s, tg_3s = 44.06 t/s 5.35.320.841 I slot print_timing: id 1 | task 9761 | n_gen = 133, tg = 43.73 t/s, tg_3s = 44.06 t/s 5.35.320.996 I slot print_timing: id 2 | task 9762 | n_gen = 133, tg = 43.73 t/s, tg_3s = 44.06 t/s 5.35.388.359 I slot print_timing: id 3 | task 9763 | n_gen = 135, tg = 44.57 t/s, tg_3s = 44.90 t/s 5.38.084.187 I slot print_timing: id 0 | task 9760 | prompt eval time = 1669.25 ms / 1034 tokens ( 1.61 ms per token, 619.44 tokens per second) 5.38.084.190 I slot print_timing: id 0 | task 9760 | eval time = 5781.99 ms / 256 tokens ( 22.67 ms per token, 44.10 tokens per second) 5.38.084.191 I slot print_timing: id 0 | task 9760 | total time = 7451.24 ms / 1290 tokens 5.38.084.192 I slot print_timing: id 0 | task 9760 | graphs reused = 9656 5.38.084.232 I slot release: id 0 | task 9760 | stop processing: n_tokens = 1331, truncated = 0 5.38.084.393 I slot print_timing: id 1 | task 9761 | prompt eval time = 1615.52 ms / 1034 tokens ( 1.56 ms per token, 640.04 tokens per second) 5.38.084.394 I slot print_timing: id 1 | task 9761 | eval time = 5781.93 ms / 256 tokens ( 22.67 ms per token, 44.10 tokens per second) 5.38.084.395 I slot print_timing: id 1 | task 9761 | total time = 7397.45 ms / 1290 tokens 5.38.084.395 I slot print_timing: id 1 | task 9761 | graphs reused = 9656 5.38.084.424 I slot release: id 1 | task 9761 | stop processing: n_tokens = 1331, truncated = 0 5.38.084.582 I slot print_timing: id 2 | task 9762 | prompt eval time = 1559.83 ms / 1033 tokens ( 1.51 ms per token, 662.25 tokens per second) 5.38.084.583 I slot print_timing: id 2 | task 9762 | eval time = 5781.88 ms / 256 tokens ( 22.67 ms per token, 44.10 tokens per second) 5.38.084.583 I slot print_timing: id 2 | task 9762 | total time = 7341.71 ms / 1289 tokens 5.38.084.583 I slot print_timing: id 2 | task 9762 | graphs reused = 9656 5.38.084.610 I slot release: id 2 | task 9762 | stop processing: n_tokens = 1330, truncated = 0 5.38.101.281 I slot print_timing: id 3 | task 9763 | prompt eval time = 1581.07 ms / 941 tokens ( 1.68 ms per token, 595.17 tokens per second) 5.38.101.283 I slot print_timing: id 3 | task 9763 | eval time = 5719.49 ms / 256 tokens ( 22.43 ms per token, 44.58 tokens per second) 5.38.101.283 I slot print_timing: id 3 | task 9763 | total time = 7300.56 ms / 1197 tokens 5.38.101.284 I slot print_timing: id 3 | task 9763 | graphs reused = 9656 5.38.101.313 I slot release: id 3 | task 9763 | stop processing: n_tokens = 1238, truncated = 0 6.41.580.211 I srv operator(): operator(): cleaning up before exit...