IntelGpu-ComfyUI-Collection

202610311439_MossEdit_omnixpu加速_B70_64G_冷启+热启.txt · 2026-10-31 14:39

← 返回执行日志
冷启98.08 s
热启9.35 s
热启 vs 冷启10.49×
每步耗时0.56 s/it
峰值 staged9,295 MB

逐次执行

阶段耗时步数s/itstaged MB其他指标
冷启98.08 s80.569,295fallback ×5CUTE ×3
热启9.35 s80.559,295—
原始日志全文(已脱敏本地路径)
[INFO] got prompt
[INFO] Model storage policy: fast_disk=False paths=['<ComfyUI>/models/vae/flux2-vae.safetensors']
[INFO] Using pytorch attention in VAE
[INFO] Using pytorch attention in VAE
[INFO] VAE load device: xpu:0, offload device: cpu, dtype: torch.float16
# 😺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] Model storage policy: fast_disk=False paths=['<本地路径>/qwen3.5_9b_int8_convrot.safetensors']
[INFO] CLIP/text encoder model load device: xpu:0, offload device: cpu, current: cpu, dtype: torch.float16
[INFO] Requested to load MOSSImageTEModel_
[INFO] Model MOSSImageTEModel_ prepared for dynamic VRAM loading. 9295MB Staged. 0 patches attached. Force pre-loaded 222 weights: 822 KB.
[INFO] [OmniXPU] norm first use: rms_norm_fn shape=torch.Size([1, 10, 4096])
[INFO] [OmniXPU] AIMDO inference budget: devices=0 minimum=2429.6MiB
[INFO] Requested to load AutoencoderKL
[INFO] Model AutoencoderKL prepared for dynamic VRAM loading. 160MB Staged. 0 patches attached. Force pre-loaded 112 weights: 101 KB.
[INFO] [OmniXPU] AIMDO inference budget: devices=0 minimum=2595.3MiB
[INFO] Model AutoencoderKL prepared for dynamic VRAM loading. 160MB Staged. 0 patches attached. Force pre-loaded 112 weights: 101 KB.
[INFO] Model MOSSImageTEModel_ prepared for dynamic VRAM loading. 9295MB Staged. 0 patches attached. Force pre-loaded 222 weights: 822 KB.
[INFO] [OmniXPU] AIMDO inference budget: devices=0 minimum=2429.6MiB
[INFO] Model AutoencoderKL prepared for dynamic VRAM loading. 160MB Staged. 0 patches attached. Force pre-loaded 112 weights: 101 KB.
[INFO] [OmniXPU] AIMDO inference budget: devices=0 minimum=2595.3MiB
[INFO] Model AutoencoderKL prepared for dynamic VRAM loading. 160MB Staged. 0 patches attached. Force pre-loaded 112 weights: 101 KB.
[INFO] Found quantization metadata version 1
[INFO] Detected mixed precision quantization
[INFO] Using mixed precision operations
[INFO] Native ops: int8_tensorwise , emulated ops: asym_w4a8_int8, nvfp4, float8_e5m2, mxfp8, float8_e4m3fn, w6a8_int8, convrot_w4a4
[INFO] model weight dtype torch.bfloat16, manual cast: torch.bfloat16
[INFO] model_type FLOW
[INFO] Model storage policy: fast_disk=False paths=['<本地路径>/moss_image_sft_int8_convrot.safetensors']
[INFO] [OmniXPU] LoRA memory budget cached: source=283.5MiB/504 tensors model_added=283.5MiB model_budget=283.5MiB clip_added=0.0MiB clip_budget=0.0MiB
[INFO] [OmniXPU] LoRA memory budget cached: source=1134.2MiB/756 tensors model_added=1134.0MiB model_budget=1417.5MiB clip_added=0.0MiB clip_budget=0.0MiB
[INFO] [OmniXPU] LoRA model budget applied: cached=1417.5MiB/1008 tensors requested=5045.8->6463.3MiB minimum=2522.9->3940.4MiB xpu_memory=available xpu_allocated=1.5MiB xpu_reserved=4.0MiB xpu_free=20910.3MiB xpu_total=31977.4MiB
[INFO] [OmniXPU] AIMDO inference budget: devices=0 minimum=3940.4MiB
[INFO] Requested to load MOSSImage
[INFO] Model MOSSImage prepared for dynamic VRAM loading. 5162MB Staged. 168 patches attached. Force pre-loaded 177 weights: 559 KB.
[INFO] [OmniXPU] LoRA model load complete: xpu_memory=available xpu_allocated=2.0MiB xpu_reserved=4.0MiB xpu_free=20902.8MiB xpu_total=31977.4MiB
[INFO] [OmniXPU] attention CUTE #1: heads=24 seq=5824 dtype=torch.bfloat16
[INFO] [OmniXPU] attention CUTE #2: heads=24 seq=5824 dtype=torch.bfloat16
[INFO] [OmniXPU] attention CUTE #3: heads=24 seq=5824 dtype=torch.bfloat16
  0%|                                                                | 0/8 [00:00<?, ?it/s,   Model Initializing ...  ][INFO] [OmniXPU] attention fallback: cute_unsupported=dim128,q2858,kv8682 (seq=2858)
[INFO] [OmniXPU] attention fallback: cute_unsupported=dim128,q2858,kv8682 (seq=2858)
[INFO] [OmniXPU] attention fallback: cute_unsupported=dim128,q2858,kv8682 (seq=2858)
[INFO] [OmniXPU] attention fallback: cute_unsupported=dim128,q2858,kv8682 (seq=2858)
[INFO] [OmniXPU] attention fallback: cute_unsupported=dim128,q2858,kv8682 (seq=2858)
100%|████████████████████████████████████████████████████████████████████████████████████| 8/8 [00:04<00:00,  1.80it/s]
[INFO] [OmniXPU] AIMDO inference budget: devices=0 minimum=2994.8MiB
[INFO] Model AutoencoderKL prepared for dynamic VRAM loading. 160MB Staged. 0 patches attached. Force pre-loaded 112 weights: 101 KB.
[INFO] Prompt executed in 98.08 seconds
[INFO] got prompt
# 😺dzNodes: LayerStyle -> ImageScaleByAspectRatio V2 Processed 1 image(s).
[INFO] Model MOSSImageTEModel_ prepared for dynamic VRAM loading. 9295MB Staged. 0 patches attached. Force pre-loaded 222 weights: 822 KB.
[INFO] [OmniXPU] AIMDO inference budget: devices=0 minimum=2429.6MiB
[INFO] Model AutoencoderKL prepared for dynamic VRAM loading. 160MB Staged. 0 patches attached. Force pre-loaded 112 weights: 101 KB.
[INFO] [OmniXPU] AIMDO inference budget: devices=0 minimum=2595.3MiB
[INFO] Model AutoencoderKL prepared for dynamic VRAM loading. 160MB Staged. 0 patches attached. Force pre-loaded 112 weights: 101 KB.
[INFO] Model MOSSImageTEModel_ prepared for dynamic VRAM loading. 9295MB Staged. 0 patches attached. Force pre-loaded 222 weights: 822 KB.
[INFO] [OmniXPU] AIMDO inference budget: devices=0 minimum=2429.6MiB
[INFO] Model AutoencoderKL prepared for dynamic VRAM loading. 160MB Staged. 0 patches attached. Force pre-loaded 112 weights: 101 KB.
[INFO] [OmniXPU] AIMDO inference budget: devices=0 minimum=2595.3MiB
[INFO] Model AutoencoderKL prepared for dynamic VRAM loading. 160MB Staged. 0 patches attached. Force pre-loaded 112 weights: 101 KB.
[INFO] [OmniXPU] LoRA model budget applied: cached=1417.5MiB/1008 tensors requested=5045.8->6463.3MiB minimum=2522.9->3940.4MiB xpu_memory=available xpu_allocated=2.2MiB xpu_reserved=4.0MiB xpu_free=15269.3MiB xpu_total=31977.4MiB
[INFO] [OmniXPU] AIMDO inference budget: devices=0 minimum=3940.4MiB
[INFO] Model MOSSImage prepared for dynamic VRAM loading. 5162MB Staged. 168 patches attached. Force pre-loaded 177 weights: 559 KB.
[INFO] [OmniXPU] LoRA model load complete: xpu_memory=available xpu_allocated=2.2MiB xpu_reserved=4.0MiB xpu_free=15269.3MiB xpu_total=31977.4MiB
100%|████████████████████████████████████████████████████████████████████████████████████| 8/8 [00:04<00:00,  1.81it/s]
[INFO] [OmniXPU] AIMDO inference budget: devices=0 minimum=2994.8MiB
[INFO] Model AutoencoderKL prepared for dynamic VRAM loading. 160MB Staged. 0 patches attached. Force pre-loaded 112 weights: 101 KB.
[INFO] Prompt executed in 9.35 seconds