202610271807_h3_FL2VA_1mp10s_omnixpu加速_B70_64G_冷启+热启.txt · 2026-10-27 18:07
| 阶段 | 耗时 | 步数 | s/it | staged MB | 其他指标 |
|---|---|---|---|---|---|
| 冷启 | 541.03 s | 4 | 103.80 | 25,882 | CUTE_BHLD_D128 ×3CUTE_H3_VAE_D64 ×3 |
| 热启 | 475.70 s | 4 | 103.75 | 19,995 | — |
[INFO] got prompt [INFO] Model storage policy: fast_disk=False paths=['<本地路径>/minimax_h3_audio_vae_fp32.safetensors'] [INFO] VAE load device: xpu:0, offload device: cpu, dtype: torch.float32 [INFO] Model storage policy: fast_disk=False paths=['<本地路径>/minimax_h3_video_vae_fp16.safetensors'] [INFO] VAE load device: xpu:0, offload device: cpu, dtype: torch.float16 [INFO] Found quantization metadata version 1 [INFO] Using MixedPrecisionOps for text encoder [INFO] Model storage policy: fast_disk=False paths=['<本地路径>/qwen3vl_32b_minimax_h3_int8_convrot.safetensors'] [INFO] CLIP/text encoder model load device: xpu:0, offload device: cpu, current: cpu, dtype: torch.float16 [INFO] Requested to load MiniMaxH3TEModel_ [INFO] Model MiniMaxH3TEModel_ prepared for dynamic VRAM loading. 25882MB Staged. 0 patches attached. Force pre-loaded 310 weights: 1272 KB. [INFO] [OmniXPU] norm first use: LayerNorm shape=torch.Size([4128, 1152]) [INFO] [OmniXPU] AIMDO inference budget: devices=0 minimum=230.6MiB [INFO] Requested to load MiniMaxH3VideoVAE [INFO] Model MiniMaxH3VideoVAE prepared for dynamic VRAM loading. 4965MB Staged. 0 patches attached. Force pre-loaded 128 weights: 352 KB. [INFO] Found quantization metadata version 1 [INFO] Detected mixed precision quantization [INFO] Using mixed precision operations [INFO] Native ops: int8_tensorwise , emulated ops: float8_e4m3fn, float8_e5m2, mxfp8, convrot_w4a4, asym_w4a8_int8, w6a8_int8, nvfp4 [INFO] model weight dtype torch.bfloat16, manual cast: torch.bfloat16 [INFO] model_type FLOW_AV [INFO] Model storage policy: fast_disk=False paths=['<本地路径>/minimax_h3_fl2va_pruned_int8_convrot.safetensors'] [INFO] [OmniXPU] LoRA memory budget cached: source=1865.5MiB/416 tensors model_added=1865.5MiB model_budget=1865.5MiB clip_added=0.0MiB clip_budget=0.0MiB [INFO] [OmniXPU] LoRA model budget applied: cached=1865.5MiB/416 tensors requested=32645.5->34511.0MiB minimum=16322.8->18188.3MiB xpu_allocated=1.9MiB xpu_reserved=2.0MiB xpu_free=26330.8MiB [INFO] [OmniXPU] AIMDO inference budget: devices=0 minimum=18188.3MiB [INFO] Requested to load MiniMaxH3 [INFO] Model MiniMaxH3 prepared for dynamic VRAM loading. 19995MB Staged. 208 patches attached. Force pre-loaded 210 weights: 1175 KB. [INFO] [OmniXPU] LoRA model load complete: xpu_allocated=3.1MiB xpu_reserved=4.0MiB xpu_free=26330.8MiB [WARNING] [OmniXPU] experimental capability-driven BMG D128 CUTE route enabled; set OMNI_ATTN_BACKEND=torch to disable it if this workflow shows an issue [INFO] [OmniXPU] attention CUTE_BHLD_D128 #1: heads=56 q=1054 kv=1054 dtype=torch.bfloat16 [INFO] [OmniXPU] attention CUTE_BHLD_D128 #2: heads=56 q=1054 kv=1054 dtype=torch.bfloat16 0%| | 0/4 [00:00<?, ?it/s, Model Initializing ... ][INFO] [OmniXPU] attention CUTE_BHLD_D128 #3: heads=56 q=77200 kv=77200 dtype=torch.bfloat16 100%|██████████| 4/4 [06:55<00:00, 103.80s/it] [INFO] [OmniXPU] AIMDO inference budget: devices=0 minimum=358.7MiB [INFO] Requested to load MiniMaxH3AudioVAE [INFO] Model MiniMaxH3AudioVAE prepared for dynamic VRAM loading. 576MB Staged. 0 patches attached. Force pre-loaded 401 weights: 539 KB. [INFO] [OmniXPU] AIMDO inference budget: devices=0 minimum=1122.1MiB [INFO] Model MiniMaxH3VideoVAE prepared for dynamic VRAM loading. 4965MB Staged. 0 patches attached. Force pre-loaded 128 weights: 348 KB. [INFO] [OmniXPU] attention CUTE_H3_VAE_D64 #1: heads=32 seq=1797 dtype=torch.float16 [INFO] [OmniXPU] attention CUTE_H3_VAE_D64 #2: heads=32 seq=1797 dtype=torch.float16 [INFO] [OmniXPU] attention CUTE_H3_VAE_D64 #3: heads=32 seq=1797 dtype=torch.float16 [INFO] Prompt executed in 541.03 seconds [INFO] got prompt [INFO] [OmniXPU] LoRA model budget applied: cached=1865.5MiB/416 tensors requested=32645.5->34511.0MiB minimum=16322.8->18188.3MiB xpu_memory=available xpu_allocated=4.2MiB xpu_reserved=6.0MiB xpu_free=20266.2MiB xpu_total=31977.4MiB [INFO] [OmniXPU] AIMDO inference budget: devices=0 minimum=18188.3MiB [INFO] Model MiniMaxH3 prepared for dynamic VRAM loading. 19995MB Staged. 208 patches attached. Force pre-loaded 210 weights: 1175 KB. [INFO] [OmniXPU] LoRA model load complete: xpu_memory=available xpu_allocated=4.2MiB xpu_reserved=6.0MiB xpu_free=20266.2MiB xpu_total=31977.4MiB 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 4/4 [06:54<00:00, 103.75s/it] [INFO] [OmniXPU] AIMDO inference budget: devices=0 minimum=358.7MiB [INFO] Model MiniMaxH3AudioVAE prepared for dynamic VRAM loading. 576MB Staged. 0 patches attached. Force pre-loaded 401 weights: 539 KB. [INFO] [OmniXPU] AIMDO inference budget: devices=0 minimum=1122.1MiB [INFO] Model MiniMaxH3VideoVAE prepared for dynamic VRAM loading. 4965MB Staged. 0 patches attached. Force pre-loaded 128 weights: 352 KB. [INFO] Prompt executed in 475.70 seconds