Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- [34m00:00.09[0m [32mI [0mcmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg)
- [34m00:00.32[0m [32mI [0msrv load_model: loading model 'A:\models\Qwen3.8-27B-NVFP4-MTP-MEDIUM.gguf'
- [34m00:00.84[0m [35mW model has unused tensor blk.64.attn_norm.weight (size = 20480 bytes) -- ignoring
- [0m[34m00:00.84[0m [35mW model has unused tensor blk.64.post_attention_norm.weight (size = 20480 bytes) -- ignoring
- [0m[34m00:00.84[0m [35mW model has unused tensor blk.64.attn_q.weight (size = 33423360 bytes) -- ignoring
- [0m[34m00:00.84[0m [35mW model has unused tensor blk.64.attn_k.weight (size = 2785280 bytes) -- ignoring
- [0m[34m00:00.84[0m [35mW model has unused tensor blk.64.attn_v.weight (size = 2785280 bytes) -- ignoring
- [0m[34m00:00.84[0m [35mW model has unused tensor blk.64.attn_output.weight (size = 16711680 bytes) -- ignoring
- [0m[34m00:00.84[0m [35mW model has unused tensor blk.64.attn_q_norm.weight (size = 1024 bytes) -- ignoring
- [0m[34m00:00.84[0m [35mW model has unused tensor blk.64.attn_k_norm.weight (size = 1024 bytes) -- ignoring
- [0m[34m00:00.84[0m [35mW model has unused tensor blk.64.ffn_gate.weight (size = 47349760 bytes) -- ignoring
- [0m[34m00:00.84[0m [35mW model has unused tensor blk.64.ffn_down.weight (size = 47349760 bytes) -- ignoring
- [0m[34m00:00.84[0m [35mW model has unused tensor blk.64.ffn_up.weight (size = 47349760 bytes) -- ignoring
- [0m[34m00:00.84[0m [35mW model has unused tensor blk.64.nextn.eh_proj.weight (size = 27852800 bytes) -- ignoring
- [0m[34m00:00.84[0m [35mW model has unused tensor blk.64.nextn.enorm.weight (size = 20480 bytes) -- ignoring
- [0m[34m00:00.84[0m [35mW model has unused tensor blk.64.nextn.hnorm.weight (size = 20480 bytes) -- ignoring
- [0m[34m00:00.84[0m [35mW model has unused tensor blk.64.nextn.shared_head_norm.weight (size = 20480 bytes) -- ignoring
- [0m[34m00:05.54[0m [32mI [0mcmn init: llama threadpool init, n_threads = 6
- [34m00:05.67[0m [32mI [0mcommon_speculative_init_result: loading draft model 'A:\models\Qwen3.8-27B-DFlash2-Q4_K_M.gguf'
- [34m00:07.24[0m [32mI [0msrv load_model: loaded multimodal model, 'A:\models\Qwen3.8-27B-mmproj-BF16.gguf'
- [34m00:07.31[0m [32mI [0msrv load_model: initializing, n_slots = 1, n_ctx_slot = 160000, kv_unified = 'true'
- [34m00:07.31[0m [32mI [0mcommon_speculative_impl_draft_dflash: adding speculative implementation 'draft-dflash'
- [34m00:07.31[0m [32mI [0mcommon_speculative_impl_draft_dflash: - n_max=7, n_min=0, p_min=0.00
- [34m00:07.31[0m [32mI [0mcommon_speculative_impl_draft_dflash: - block_size=8, mask_token_id=248070, n_extract=5, sample_from_anchor=true
- [34m00:07.37[0m [32mI [0msrv llama_server: model loaded
- [34m00:07.37[0m [32mI [0msrv llama_server: listening on http://127.0.0.1:8080
- [34m00:07.37[0m [35mW srv llama_server: NOTICE: server default port will be changed to :9931 in a future release
- [0m[34m00:07.37[0m [35mW srv llama_server: ref: https://github.com/ggml-org/llama.cpp/pull/26508
- [0m[34m01:13.31[0m [32mI [0mslot- 0 get_availa | task -1 | selected slot by LRU, t_last = -1
- [34m01:13.31[0m [32mI [0mslot- 0 launch_slo | task 0 | processing task, is_child = 0
- [34m01:17.38[0m [32mI [0mslot- 0 print_timi | task 0 | PP, n_tokens = 8192, progress = 0.09, t = 3.7 s / 2184.9 t/s
- [34m01:18.22[0m [32mI [0mslot- 0 print_timi | task 0 | PP, n_tokens = 10240, progress = 0.12, t = 4.6 s / 2233.6 t/s
- [34m01:19.07[0m [32mI [0mslot- 0 print_timi | task 0 | PP, n_tokens = 12288, progress = 0.14, t = 5.4 s / 2261.0 t/s
- [34m01:19.95[0m [32mI [0mslot- 0 print_timi | task 0 | PP, n_tokens = 14336, progress = 0.16, t = 6.3 s / 2273.1 t/s
- [34m01:20.84[0m [32mI [0mslot- 0 print_timi | task 0 | PP, n_tokens = 16384, progress = 0.18, t = 7.2 s / 2275.6 t/s
- [34m01:21.76[0m [32mI [0mslot- 0 print_timi | task 0 | PP, n_tokens = 18432, progress = 0.21, t = 8.1 s / 2271.2 t/s
- [34m01:22.71[0m [32mI [0mslot- 0 print_timi | task 0 | PP, n_tokens = 20480, progress = 0.23, t = 9.1 s / 2261.8 t/s
- [34m01:23.67[0m [32mI [0mslot- 0 print_timi | task 0 | PP, n_tokens = 22528, progress = 0.25, t = 10.0 s / 2249.1 t/s
- [34m01:24.47[0m [32mI [0mslot- 0 print_timi | task 0 | PP, n_tokens = 24087, progress = 0.27, t = 11.0 s / 2194.2 t/s
- [34m01:25.55[0m [32mI [0mslot- 0 print_timi | task 0 | PP, n_tokens = 26135, progress = 0.29, t = 11.9 s / 2198.5 t/s
- [34m01:26.18[0m [32mI [0mslot- 0 print_timi | task 0 | PP, n_tokens = 27198, progress = 0.31, t = 12.6 s / 2154.0 t/s
- [34m01:27.32[0m [32mI [0mslot- 0 print_timi | task 0 | PP, n_tokens = 29246, progress = 0.33, t = 13.6 s / 2143.2 t/s
- [34m01:28.42[0m [32mI [0mslot- 0 print_timi | task 0 | PP, n_tokens = 31294, progress = 0.35, t = 14.7 s / 2122.8 t/s
- [34m01:29.56[0m [32mI [0mslot- 0 print_timi | task 0 | PP, n_tokens = 33342, progress = 0.37, t = 15.9 s / 2100.7 t/s
- [34m01:30.74[0m [32mI [0mslot- 0 print_timi | task 0 | PP, n_tokens = 35390, progress = 0.40, t = 17.0 s / 2076.3 t/s
- [34m01:31.95[0m [32mI [0mslot- 0 print_timi | task 0 | PP, n_tokens = 37438, progress = 0.42, t = 18.3 s / 2051.0 t/s
- [34m01:33.19[0m [32mI [0mslot- 0 print_timi | task 0 | PP, n_tokens = 39486, progress = 0.44, t = 19.5 s / 2026.1 t/s
- [34m01:33.77[0m [32mI [0mslot- 0 print_timi | task 0 | PP, n_tokens = 40315, progress = 0.45, t = 20.2 s / 1994.1 t/s
- [34m01:34.70[0m [32mI [0mslot- 0 print_timi | task 0 | PP, n_tokens = 41673, progress = 0.47, t = 21.1 s / 1971.1 t/s
- [34m01:36.05[0m [32mI [0mslot- 0 print_timi | task 0 | PP, n_tokens = 43721, progress = 0.49, t = 22.3 s / 1957.3 t/s
- [34m01:36.12[0m [32mI [0mslot- 0 print_timi | task 0 | PP, n_tokens = 43756, progress = 0.49, t = 22.8 s / 1920.9 t/s
- [34m01:37.01[0m [32mI [0mslot- 0 print_timi | task 0 | PP, n_tokens = 44904, progress = 0.50, t = 23.5 s / 1909.0 t/s
- [34m01:37.84[0m [32mI [0mslot- 0 print_timi | task 0 | PP, n_tokens = 45922, progress = 0.52, t = 24.2 s / 1895.7 t/s
- [34m01:39.19[0m [32mI [0mslot- 0 print_timi | task 0 | PP, n_tokens = 47970, progress = 0.54, t = 25.5 s / 1883.3 t/s
- [34m01:40.57[0m [32mI [0mslot- 0 print_timi | task 0 | PP, n_tokens = 50018, progress = 0.56, t = 26.8 s / 1863.6 t/s
- [34m01:41.98[0m [32mI [0mslot- 0 print_timi | task 0 | PP, n_tokens = 52066, progress = 0.58, t = 28.2 s / 1843.1 t/s
- [34m01:42.47[0m [32mI [0mslot- 0 print_timi | task 0 | PP, n_tokens = 52549, progress = 0.59, t = 28.9 s / 1817.7 t/s
- [34m01:44.02[0m [32mI [0mslot- 0 print_timi | task 0 | PP, n_tokens = 54597, progress = 0.61, t = 30.2 s / 1805.1 t/s
- [34m01:45.52[0m [32mI [0mslot- 0 print_timi | task 0 | PP, n_tokens = 56645, progress = 0.64, t = 31.7 s / 1784.3 t/s
- [34m01:46.26[0m [32mI [0mslot- 0 print_timi | task 0 | PP, n_tokens = 57468, progress = 0.65, t = 32.6 s / 1760.2 t/s
- [34m01:47.89[0m [32mI [0mslot- 0 print_timi | task 0 | PP, n_tokens = 59516, progress = 0.67, t = 34.1 s / 1744.9 t/s
- [34m01:49.46[0m [32mI [0mslot- 0 print_timi | task 0 | PP, n_tokens = 61564, progress = 0.69, t = 35.7 s / 1725.6 t/s
- [34m01:50.47[0m [32mI [0mslot- 0 print_timi | task 0 | PP, n_tokens = 62725, progress = 0.70, t = 36.9 s / 1697.9 t/s
- [34m01:52.17[0m [32mI [0mslot- 0 print_timi | task 0 | PP, n_tokens = 64773, progress = 0.73, t = 38.4 s / 1688.1 t/s
- [34m01:53.82[0m [32mI [0mslot- 0 print_timi | task 0 | PP, n_tokens = 66821, progress = 0.75, t = 40.0 s / 1669.9 t/s
- [34m01:53.88[0m [32mI [0mslot- 0 print_timi | task 0 | PP, n_tokens = 66828, progress = 0.75, t = 40.5 s / 1648.2 t/s
- [34m01:55.63[0m [32mI [0mslot- 0 print_timi | task 0 | PP, n_tokens = 68876, progress = 0.77, t = 41.8 s / 1646.7 t/s
- [34m01:57.34[0m [32mI [0mslot- 0 print_timi | task 0 | PP, n_tokens = 70924, progress = 0.80, t = 43.5 s / 1629.4 t/s
- [34m01:58.01[0m [32mI [0mslot- 0 print_timi | task 0 | PP, n_tokens = 71496, progress = 0.80, t = 44.4 s / 1610.5 t/s
- [34m01:59.83[0m [32mI [0mslot- 0 print_timi | task 0 | PP, n_tokens = 73544, progress = 0.83, t = 46.0 s / 1598.6 t/s
- [34m02:00.62[0m [32mI [0mslot- 0 print_timi | task 0 | PP, n_tokens = 74336, progress = 0.84, t = 47.0 s / 1582.5 t/s
- [34m02:02.48[0m [32mI [0mslot- 0 print_timi | task 0 | PP, n_tokens = 76384, progress = 0.86, t = 48.7 s / 1570.0 t/s
- [34m02:04.29[0m [32mI [0mslot- 0 print_timi | task 0 | PP, n_tokens = 78432, progress = 0.88, t = 50.5 s / 1554.2 t/s
- [34m02:06.13[0m [32mI [0mslot- 0 print_timi | task 0 | PP, n_tokens = 80480, progress = 0.90, t = 52.3 s / 1539.1 t/s
- [34m02:08.02[0m [32mI [0mslot- 0 print_timi | task 0 | PP, n_tokens = 82528, progress = 0.93, t = 54.2 s / 1524.0 t/s
- [34m02:09.94[0m [32mI [0mslot- 0 print_timi | task 0 | PP, n_tokens = 84576, progress = 0.95, t = 56.1 s / 1508.3 t/s
- [34m02:11.87[0m [32mI [0mslot- 0 print_timi | task 0 | PP, n_tokens = 86624, progress = 0.97, t = 58.0 s / 1493.3 t/s
- [34m02:12.73[0m [32mI [0mslot- 0 print_timi | task 0 | PP, n_tokens = 87318, progress = 0.98, t = 59.1 s / 1478.5 t/s
- [34m02:14.03[0m [32mI [0mslot- 0 print_timi | task 0 | PP, n_tokens = 88495, progress = 0.99, t = 60.3 s / 1467.4 t/s
- [34m02:14.82[0m [32mI [0mslot- 0 print_timi | task 0 | PP, n_tokens = 89007, progress = 1.00, t = 61.2 s / 1455.5 t/s
- [34m02:18.00[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 157, tg = 51.70 t/s, tg_3s = 52.03 t/s
- [34m02:21.01[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 263, tg = 43.44 t/s, tg_3s = 35.17 t/s
- [34m02:24.05[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 452, tg = 49.70 t/s, tg_3s = 62.11 t/s
- [34m02:27.06[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 619, tg = 51.14 t/s, tg_3s = 55.47 t/s
- [34m02:30.13[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 802, tg = 52.88 t/s, tg_3s = 59.75 t/s
- [34m02:33.15[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 974, tg = 53.53 t/s, tg_3s = 56.81 t/s
- [34m02:36.18[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 1145, tg = 53.97 t/s, tg_3s = 56.56 t/s
- [34m02:39.19[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 1338, tg = 55.23 t/s, tg_3s = 64.10 t/s
- [34m02:42.21[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 1499, tg = 55.02 t/s, tg_3s = 53.36 t/s
- [34m02:45.24[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 1712, tg = 56.55 t/s, tg_3s = 70.33 t/s
- [34m02:48.29[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 1891, tg = 56.74 t/s, tg_3s = 58.61 t/s
- [34m02:51.31[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 2047, tg = 56.32 t/s, tg_3s = 51.66 t/s
- [34m02:54.31[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 2194, tg = 55.76 t/s, tg_3s = 48.98 t/s
- [34m02:57.33[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 2426, tg = 57.27 t/s, tg_3s = 76.93 t/s
- [34m03:00.37[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 2581, tg = 56.84 t/s, tg_3s = 50.96 t/s
- [34m03:03.43[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 2727, tg = 56.26 t/s, tg_3s = 47.61 t/s
- [34m03:06.47[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 2883, tg = 55.97 t/s, tg_3s = 51.33 t/s
- [34m03:09.54[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 3034, tg = 55.60 t/s, tg_3s = 49.31 t/s
- [34m03:12.60[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 3206, tg = 55.62 t/s, tg_3s = 56.10 t/s
- [34m03:15.66[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 3404, tg = 56.08 t/s, tg_3s = 64.74 t/s
- [34m03:18.70[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 3518, tg = 55.19 t/s, tg_3s = 37.46 t/s
- [34m03:21.73[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 3649, tg = 54.65 t/s, tg_3s = 43.31 t/s
- [34m03:24.73[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 3781, tg = 54.19 t/s, tg_3s = 43.95 t/s
- [34m03:27.80[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 3915, tg = 53.75 t/s, tg_3s = 43.70 t/s
- [34m03:30.83[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 4075, tg = 53.71 t/s, tg_3s = 52.70 t/s
- [34m03:33.88[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 4243, tg = 53.77 t/s, tg_3s = 55.17 t/s
- [34m03:37.13[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 4358, tg = 53.04 t/s, tg_3s = 35.37 t/s
- [34m03:40.30[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 4390, tg = 51.44 t/s, tg_3s = 10.09 t/s
- [34m03:43.42[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 4422, tg = 49.99 t/s, tg_3s = 10.25 t/s
- [34m03:46.43[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 4453, tg = 48.68 t/s, tg_3s = 10.30 t/s
- [34m03:49.79[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 4491, tg = 47.36 t/s, tg_3s = 11.33 t/s
- [34m03:53.12[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 4523, tg = 46.08 t/s, tg_3s = 9.60 t/s
- [34m03:56.24[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 4555, tg = 44.97 t/s, tg_3s = 10.24 t/s
- [34m03:59.75[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 4595, tg = 43.85 t/s, tg_3s = 11.41 t/s
- [34m04:02.94[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 4633, tg = 42.91 t/s, tg_3s = 11.92 t/s
- [34m04:06.40[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 4676, tg = 41.96 t/s, tg_3s = 12.41 t/s
- [34m04:09.88[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 4718, tg = 41.05 t/s, tg_3s = 12.07 t/s
- [34m04:13.22[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 4759, tg = 40.24 t/s, tg_3s = 12.29 t/s
- [34m04:16.53[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 4798, tg = 39.46 t/s, tg_3s = 11.78 t/s
- [34m04:19.59[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 4832, tg = 38.77 t/s, tg_3s = 11.13 t/s
- [34m04:22.69[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 4867, tg = 38.10 t/s, tg_3s = 11.26 t/s
- [34m04:25.76[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 4903, tg = 37.48 t/s, tg_3s = 11.75 t/s
- [34m04:29.26[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 4943, tg = 36.80 t/s, tg_3s = 11.41 t/s
- [34m04:32.47[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 4979, tg = 36.21 t/s, tg_3s = 11.23 t/s
- [34m04:35.57[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 5014, tg = 35.66 t/s, tg_3s = 11.28 t/s
- [34m04:38.64[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 5053, tg = 35.17 t/s, tg_3s = 12.71 t/s
- [34m04:42.07[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 5095, tg = 34.63 t/s, tg_3s = 12.24 t/s
- [34m04:45.47[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 5137, tg = 34.13 t/s, tg_3s = 12.35 t/s
- [34m04:48.59[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 5178, tg = 33.70 t/s, tg_3s = 13.16 t/s
- [34m04:51.65[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 5218, tg = 33.30 t/s, tg_3s = 13.06 t/s
- [34m04:54.66[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 5250, tg = 32.87 t/s, tg_3s = 10.62 t/s
- [34m04:57.82[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 5286, tg = 32.46 t/s, tg_3s = 11.41 t/s
- [34m05:01.31[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 5330, tg = 32.04 t/s, tg_3s = 12.60 t/s
- [34m05:04.55[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 5370, tg = 31.66 t/s, tg_3s = 12.35 t/s
- [34m05:07.64[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 5408, tg = 31.32 t/s, tg_3s = 12.28 t/s
- [34m05:10.95[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 5454, tg = 30.99 t/s, tg_3s = 13.92 t/s
- [34m05:14.35[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 5501, tg = 30.66 t/s, tg_3s = 13.81 t/s
- [34m05:17.87[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 5549, tg = 30.34 t/s, tg_3s = 13.64 t/s
- [34m05:21.03[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 5585, tg = 30.01 t/s, tg_3s = 11.38 t/s
- [34m05:24.07[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 5628, tg = 29.76 t/s, tg_3s = 14.13 t/s
- [34m05:27.56[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 5675, tg = 29.46 t/s, tg_3s = 13.47 t/s
- [34m05:31.00[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 5723, tg = 29.19 t/s, tg_3s = 13.98 t/s
- [34m05:34.51[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 5766, tg = 28.89 t/s, tg_3s = 12.22 t/s
- [34m05:37.94[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 5814, tg = 28.64 t/s, tg_3s = 14.00 t/s
- [34m05:41.09[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 5850, tg = 28.38 t/s, tg_3s = 11.45 t/s
- [34m05:44.10[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 5889, tg = 28.16 t/s, tg_3s = 12.94 t/s
- [34m05:47.46[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 5937, tg = 27.94 t/s, tg_3s = 14.28 t/s
- [34m05:50.83[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 5985, tg = 27.72 t/s, tg_3s = 14.26 t/s
- [34m05:54.18[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 6033, tg = 27.52 t/s, tg_3s = 14.34 t/s
- [34m05:57.40[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 6081, tg = 27.34 t/s, tg_3s = 14.87 t/s
- [34m06:00.69[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 6127, tg = 27.14 t/s, tg_3s = 14.01 t/s
- [34m06:03.99[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 6175, tg = 26.96 t/s, tg_3s = 14.52 t/s
- [34m06:07.25[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 6221, tg = 26.78 t/s, tg_3s = 14.13 t/s
- [34m06:10.58[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 6267, tg = 26.60 t/s, tg_3s = 13.81 t/s
- [34m06:14.02[0m [32mI [0mslot- 0 print_timi | task 0 | n_gen = 6314, tg = 26.41 t/s, tg_3s = 13.67 t/s
- [34m06:15.58[0m [32mI [0mslot- 0 print_timi | task 0 | prompt eval time = 61.7 s / 89011 tok ( 0.7 ms/tok, 1443.4 t/s)
- [34m06:15.58[0m [32mI [0mslot- 0 print_timi | task 0 | eval time = 240.6 s / 6338 tok ( 38.0 ms/tok, 26.3 t/s)
- [34m06:15.58[0m [32mI [0mslot- 0 print_timi | task 0 | total time = 302.3 s / 95349 tok
- [34m06:15.58[0m [32mI [0mslot- 0 print_timi | task 0 | graphs reused = 1484
- [34m06:15.58[0m [32mI [0mslot- 0 print_timi | task 0 | draft acceptance = 45.7% (4828 / 10563 accepted), mean len = 4.2
- [34m06:15.58[0m [32mI [0mslot- 0 release | task 0 | stop processing: n_tokens = 95348, truncated = 0
- [34m06:16.22[0m [32mI [0mslot- 0 get_availa | task -1 | selected slot by LCP similarity, f_sim_best = 0.962 (> 0.100 thold), f_keep = 0.971
- [34m06:16.23[0m [32mI [0mslot- 0 launch_slo | task 1564 | processing task, is_child = 0
- [34m06:20.28[0m [32mI [0mslot- 0 print_timi | task 1564 | PP, n_tokens = 4096, progress = 0.97, t = 3.5 s / 1163.3 t/s
- [34m06:22.29[0m [32mI [0mslot- 0 print_timi | task 1564 | PP, n_tokens = 6144, progress = 0.99, t = 5.5 s / 1110.4 t/s
- [34m06:23.09[0m [32mI [0mslot- 0 print_timi | task 1564 | PP, n_tokens = 6700, progress = 0.99, t = 6.5 s / 1027.9 t/s
- [34m06:23.92[0m [32mI [0mslot- 0 print_timi | task 1564 | PP, n_tokens = 7212, progress = 1.00, t = 7.3 s / 985.2 t/s
- [34m06:27.12[0m [32mI [0mslot- 0 print_timi | task 1564 | n_gen = 147, tg = 47.76 t/s, tg_3s = 48.08 t/s
- [34m06:30.17[0m [32mI [0mslot- 0 print_timi | task 1564 | n_gen = 267, tg = 43.58 t/s, tg_3s = 39.40 t/s
- [34m06:33.18[0m [32mI [0mslot- 0 print_timi | task 1564 | n_gen = 411, tg = 44.99 t/s, tg_3s = 47.85 t/s
- [34m06:36.19[0m [32mI [0mslot- 0 print_timi | task 1564 | n_gen = 571, tg = 47.00 t/s, tg_3s = 53.09 t/s
- [34m06:39.25[0m [32mI [0mslot- 0 print_timi | task 1564 | n_gen = 737, tg = 48.46 t/s, tg_3s = 54.24 t/s
- [34m06:42.27[0m [32mI [0mslot- 0 print_timi | task 1564 | n_gen = 916, tg = 50.27 t/s, tg_3s = 59.37 t/s
- [34m06:45.31[0m [32mI [0mslot- 0 print_timi | task 1564 | n_gen = 1057, tg = 49.70 t/s, tg_3s = 46.28 t/s
- [34m06:48.33[0m [32mI [0mslot- 0 print_timi | task 1564 | n_gen = 1183, tg = 48.72 t/s, tg_3s = 41.81 t/s
- [34m06:51.71[0m [32mI [0mslot- 0 print_timi | task 1564 | n_gen = 1219, tg = 44.05 t/s, tg_3s = 10.63 t/s
- [34m06:54.74[0m [32mI [0mslot- 0 print_timi | task 1564 | n_gen = 1251, tg = 40.75 t/s, tg_3s = 10.58 t/s
- [34m06:55.93[0m [32mI [0mslot- 0 print_timi | task 1564 | prompt eval time = 7.8 s / 7216 tok ( 1.1 ms/tok, 920.6 t/s)
- [34m06:55.93[0m [32mI [0mslot- 0 print_timi | task 1564 | eval time = 31.9 s / 1272 tok ( 25.1 ms/tok, 39.9 t/s)
- [34m06:55.93[0m [32mI [0mslot- 0 print_timi | task 1564 | total time = 39.7 s / 8488 tok
- [34m06:55.93[0m [32mI [0mslot- 0 print_timi | task 1564 | graphs reused = 1844
- [34m06:55.93[0m [32mI [0mslot- 0 print_timi | task 1564 | draft acceptance = 35.4% ( 906 / 2562 accepted), mean len = 3.5
- [34m06:55.94[0m [32mI [0mslot- 0 release | task 1564 | stop processing: n_tokens = 97495, truncated = 0
- [34m07:04.25[0m [32mI [0mslot- 0 get_availa | task -1 | selected slot by LCP similarity, f_sim_best = 0.999 (> 0.100 thold), f_keep = 1.000
- [34m07:04.25[0m [32mI [0mslot- 0 launch_slo | task 1937 | processing task, is_child = 0
- [34m07:08.01[0m [32mI [0mslot- 0 print_timi | task 1937 | n_gen = 173, tg = 56.91 t/s, tg_3s = 57.24 t/s
- [34m07:11.01[0m [32mI [0mslot- 0 print_timi | task 1937 | n_gen = 321, tg = 53.09 t/s, tg_3s = 49.26 t/s
- [34m07:13.56[0m [32mI [0mslot- 0 print_timi | task 1937 | prompt eval time = 0.7 s / 92 tok ( 8.0 ms/tok, 124.7 t/s)
- [34m07:13.56[0m [32mI [0mslot- 0 print_timi | task 1937 | eval time = 8.6 s / 438 tok ( 19.6 ms/tok, 51.0 t/s)
- [34m07:13.56[0m [32mI [0mslot- 0 print_timi | task 1937 | total time = 9.3 s / 530 tok
- [34m07:13.56[0m [32mI [0mslot- 0 print_timi | task 1937 | graphs reused = 1964
- [34m07:13.56[0m [32mI [0mslot- 0 print_timi | task 1937 | draft acceptance = 36.9% ( 315 / 854 accepted), mean len = 3.6
- [34m07:13.56[0m [32mI [0mslot- 0 release | task 1937 | stop processing: n_tokens = 98024, truncated = 0
Advertisement
Add Comment
Please, Sign In to add comment