20261023_Krea2Edit_omnixpu加速_B70_64G_冷启+热启.txt · 2026-10-23 02:52
| 阶段 | 耗时 | 步数 | s/it | staged MB | 其他指标 |
|---|---|---|---|---|---|
| 冷启 | 71.83 s | 8 | 2.14 | 12,864 | 3.5 MB freedfallback ×5CUTE ×3 |
| 热启 | 37.02 s | 8 | 1.88 | 12,864 | 3.5 MB freed |
[INFO] got prompt [INFO] Using pytorch attention in VAE [INFO] Using pytorch attention in VAE [INFO] VAE load device: xpu:0, offload device: cpu, dtype: torch.float32 # 😺dzNodes: LayerStyle -> ImageScaleByAspectRatio V2 Processed 1 image(s). # 😺dzNodes: LayerStyle -> ImageScaleByAspectRatio V2 Processed 1 image(s). [INFO] Found quantization metadata version 1 [INFO] Using MixedPrecisionOps for text encoder [INFO] CLIP/text encoder model load device: xpu:0, offload device: cpu, current: cpu, dtype: torch.float16 [INFO] Requested to load Krea2TEModel_ [INFO] Model Krea2TEModel_ prepared for dynamic VRAM loading. 4999MB Staged. 0 patches attached. Force pre-loaded 249 weights: 627 KB. [INFO] [OmniXPU] norm first use: LayerNorm shape=torch.Size([1728, 1024]) [INFO] Model Krea2TEModel_ prepared for dynamic VRAM loading. 4999MB Staged. 0 patches attached. Force pre-loaded 249 weights: 627 KB. [INFO] [OmniXPU] AIMDO inference budget: devices=0 minimum=4406.2MiB [INFO] Requested to load WanVAE [INFO] Model WanVAE prepared for dynamic VRAM loading. 483MB Staged. 0 patches attached. Force pre-loaded 60 weights: 89 KB. [INFO] [OmniXPU] AIMDO inference budget: devices=0 minimum=4500.0MiB [INFO] Model WanVAE prepared for dynamic VRAM loading. 483MB Staged. 0 patches attached. Force pre-loaded 60 weights: 89 KB. [INFO] Found quantization metadata version 1 [INFO] Detected mixed precision quantization [INFO] Using mixed precision operations [INFO] Native ops: int8_tensorwise, convrot_w4a4, asym_w4a8_int8 , emulated ops: float8_e4m3fn, float8_e5m2, nvfp4, mxfp8 [INFO] model weight dtype torch.bfloat16, manual cast: torch.bfloat16 [INFO] model_type FLUX [INFO] [OmniXPU] LoRA memory budget cached: source=1743.5MiB/512 tensors model_added=1743.5MiB model_budget=1743.5MiB clip_added=0.0MiB clip_budget=0.0MiB [krea2edit] pre-encoding sources at target 1024x768px (before sampling, fit_mode=fit) [krea2edit] _fit_encode_image: mode=fit in=(1, 1024, 768, 3) target_latent=128x96 [INFO] [OmniXPU] AIMDO inference budget: devices=0 minimum=4500.0MiB [INFO] Model WanVAE prepared for dynamic VRAM loading. 483MB Staged. 0 patches attached. Force pre-loaded 60 weights: 89 KB. [krea2edit] _fit_encode_image: mode=fit in=(1, 752, 1024, 3) target_latent=128x96 [INFO] [OmniXPU] AIMDO inference budget: devices=0 minimum=2460.9MiB [INFO] Model WanVAE prepared for dynamic VRAM loading. 483MB Staged. 0 patches attached. Force pre-loaded 60 weights: 89 KB. [INFO] [OmniXPU] LoRA model budget applied: cached=1743.5MiB/512 tensors requested=1081.3->2824.8MiB minimum=540.7->2284.2MiB xpu_allocated=0.7MiB xpu_reserved=2.0MiB xpu_free=20028.0MiB [INFO] [OmniXPU] AIMDO inference budget: devices=0 minimum=2284.2MiB [INFO] Requested to load Krea2 [INFO] Model Krea2 prepared for dynamic VRAM loading. 12864MB Staged. 256 patches attached. Force pre-loaded 160 weights: 2824 KB. [INFO] [OmniXPU] LoRA model load complete: xpu_allocated=3.5MiB xpu_reserved=4.0MiB xpu_free=20028.0MiB 0%| | 0/8 [00:00<?, ?it/s, Model Initializing ... ][krea2edit] pixel path ACTIVE (fit_mode=fit) [INFO] [OmniXPU] attention fallback: batch=891 (seq=12) [INFO] [OmniXPU] attention fallback: batch=891 (seq=12) [INFO] [OmniXPU] attention CUTE #1: heads=20 seq=891 dtype=torch.bfloat16 [INFO] [OmniXPU] attention CUTE #2: heads=20 seq=891 dtype=torch.bfloat16 [krea2edit] STRIDE1-POS fit: ref grids [(64, 48), (35, 48)] centered in (64,48) [INFO] [OmniXPU] attention CUTE #3: heads=48 seq=8715 dtype=torch.bfloat16 12%|█▎ | 1/8 [00:22<02:37, 22.45s/it, Model Initialization complete! ][INFO] [OmniXPU] attention fallback: batch=891 (seq=12) [INFO] [OmniXPU] attention fallback: batch=891 (seq=12) [krea2edit] STRIDE1-POS fit: ref grids [(64, 48), (35, 48)] centered in (64,48) 25%|██▌ | 2/8 [00:04<00:12, 2.13s/it][INFO] [OmniXPU] attention fallback: batch=891 (seq=12) [krea2edit] STRIDE1-POS fit: ref grids [(64, 48), (35, 48)] centered in (64,48) 38%|███▊ | 3/8 [00:06<00:10, 2.13s/it][krea2edit] STRIDE1-POS fit: ref grids [(64, 48), (35, 48)] centered in (64,48) 50%|█████ | 4/8 [00:08<00:08, 2.13s/it][krea2edit] STRIDE1-POS fit: ref grids [(64, 48), (35, 48)] centered in (64,48) 62%|██████▎ | 5/8 [00:10<00:06, 2.14s/it][krea2edit] STRIDE1-POS fit: ref grids [(64, 48), (35, 48)] centered in (64,48) 75%|███████▌ | 6/8 [00:12<00:04, 2.13s/it][krea2edit] STRIDE1-POS fit: ref grids [(64, 48), (35, 48)] centered in (64,48) 88%|████████▊ | 7/8 [00:14<00:02, 2.17s/it][krea2edit] STRIDE1-POS fit: ref grids [(64, 48), (35, 48)] centered in (64,48) 100%|██████████| 8/8 [00:17<00:00, 2.14s/it]VRAM清理完成 [卸载模型: False, 清空缓存: False] [INFO] [OmniXPU] AIMDO inference budget: devices=0 minimum=550.0MiB [INFO] Model WanVAE prepared for dynamic VRAM loading. 483MB Staged. 0 patches attached. Force pre-loaded 60 weights: 89 KB. [INFO] VRAMdebug: free memory before: 33,526,931,456 [INFO] VRAMdebug: free memory after: 33,530,599,936 [INFO] VRAMdebug: freed memory: 3,668,480 [INFO] Prompt executed in 71.83 seconds [INFO] got prompt # 😺dzNodes: LayerStyle -> ImageScaleByAspectRatio V2 Processed 1 image(s). [INFO] Requested to load Krea2TEModel_ [INFO] Model Krea2TEModel_ prepared for dynamic VRAM loading. 4999MB Staged. 0 patches attached. Force pre-loaded 249 weights: 627 KB. [INFO] Model Krea2TEModel_ prepared for dynamic VRAM loading. 4999MB Staged. 0 patches attached. Force pre-loaded 249 weights: 627 KB. [INFO] [OmniXPU] AIMDO inference budget: devices=0 minimum=4125.0MiB [INFO] Requested to load WanVAE [INFO] Model WanVAE prepared for dynamic VRAM loading. 483MB Staged. 0 patches attached. Force pre-loaded 60 weights: 89 KB. [krea2edit] pre-encoding sources at target 1024x704px (before sampling, fit_mode=fit) [krea2edit] _fit_encode_image: mode=fit in=(1, 1024, 704, 3) target_latent=128x88 [INFO] [OmniXPU] AIMDO inference budget: devices=0 minimum=4125.0MiB [INFO] Model WanVAE prepared for dynamic VRAM loading. 483MB Staged. 0 patches attached. Force pre-loaded 60 weights: 89 KB. [krea2edit] _fit_encode_image: mode=fit in=(1, 752, 1024, 3) target_latent=128x88 [INFO] [OmniXPU] AIMDO inference budget: devices=0 minimum=2062.5MiB [INFO] Model WanVAE prepared for dynamic VRAM loading. 483MB Staged. 0 patches attached. Force pre-loaded 60 weights: 89 KB. [INFO] [OmniXPU] LoRA model budget applied: cached=1743.5MiB/512 tensors requested=991.2->2734.7MiB minimum=495.6->2239.1MiB xpu_allocated=0.9MiB xpu_reserved=4.0MiB xpu_free=19884.3MiB [INFO] [OmniXPU] AIMDO inference budget: devices=0 minimum=2239.1MiB [INFO] Requested to load Krea2 [INFO] Model Krea2 prepared for dynamic VRAM loading. 12864MB Staged. 256 patches attached. Force pre-loaded 160 weights: 2824 KB. [INFO] [OmniXPU] LoRA model load complete: xpu_allocated=3.6MiB xpu_reserved=4.0MiB xpu_free=19884.3MiB 0%| | 0/8 [00:00<?, ?it/s, Model Initializing ... ][krea2edit] pixel path ACTIVE (fit_mode=fit) [krea2edit] STRIDE1-POS fit: ref grids [(64, 44), (32, 44)] centered in (64,44) 12%|█▎ | 1/8 [00:10<01:12, 10.33s/it, Model Initialization complete! ][krea2edit] STRIDE1-POS fit: ref grids [(64, 44), (32, 44)] centered in (64,44) 25%|██▌ | 2/8 [00:03<00:11, 1.88s/it][krea2edit] STRIDE1-POS fit: ref grids [(64, 44), (32, 44)] centered in (64,44) 38%|███▊ | 3/8 [00:05<00:09, 1.87s/it][krea2edit] STRIDE1-POS fit: ref grids [(64, 44), (32, 44)] centered in (64,44) 50%|█████ | 4/8 [00:07<00:07, 1.86s/it][krea2edit] STRIDE1-POS fit: ref grids [(64, 44), (32, 44)] centered in (64,44) 62%|██████▎ | 5/8 [00:09<00:05, 1.87s/it][krea2edit] STRIDE1-POS fit: ref grids [(64, 44), (32, 44)] centered in (64,44) 75%|███████▌ | 6/8 [00:11<00:03, 1.87s/it][krea2edit] STRIDE1-POS fit: ref grids [(64, 44), (32, 44)] centered in (64,44) 88%|████████▊ | 7/8 [00:13<00:01, 1.88s/it][krea2edit] STRIDE1-POS fit: ref grids [(64, 44), (32, 44)] centered in (64,44) 100%|██████████| 8/8 [00:15<00:00, 1.88s/it]VRAM清理完成 [卸载模型: False, 清空缓存: False] [INFO] [OmniXPU] AIMDO inference budget: devices=0 minimum=550.0MiB [INFO] Model WanVAE prepared for dynamic VRAM loading. 483MB Staged. 0 patches attached. Force pre-loaded 60 weights: 89 KB. [INFO] VRAMdebug: free memory before: 33,526,931,456 [INFO] VRAMdebug: free memory after: 33,530,599,936 [INFO] VRAMdebug: freed memory: 3,668,480 [INFO] Prompt executed in 37.02 seconds