202610281844_Z-Image-Turbo文生图_omnixpu加速_B70_64G_冷启+热启.txt · 2026-10-28 18:44
| 阶段 | 耗时 | 步数 | s/it | staged MB | 其他指标 |
|---|---|---|---|---|---|
| 冷启 | 46.40 s | 8 | 0.45 | 5,888 | CUTE ×3 |
| 热启 | 20.01 s | 8 | 0.45 | 5,888 | — |
[INFO] got prompt [INFO] Model storage policy: fast_disk=False paths=['<ComfyUI>/models/vae/ae.safetensors'] [INFO] Using pytorch attention in VAE [INFO] Using pytorch attention in VAE [INFO] VAE load device: xpu:0, offload device: cpu, dtype: torch.float32 [INFO] Found quantization metadata version 1 [INFO] Using MixedPrecisionOps for text encoder [INFO] Model storage policy: fast_disk=False paths=['<ComfyUI>/models/text_encoders/qwen_3_4b_int8_convrot.safetensors'] [INFO] CLIP/text encoder model load device: xpu:0, offload device: cpu, current: cpu, dtype: torch.float16 [INFO] Requested to load ZImageTEModel_ [INFO] Model ZImageTEModel_ prepared for dynamic VRAM loading. 4303MB Staged. 0 patches attached. Force pre-loaded 145 weights: 383 KB. [INFO] [OmniXPU] norm first use: rms_norm_fn shape=torch.Size([1, 403, 2560]) [INFO] Found quantization metadata version 1 [INFO] Detected mixed precision quantization [INFO] Using mixed precision operations [INFO] Native ops: int8_tensorwise , emulated ops: convrot_w4a4, mxfp8, asym_w4a8_int8, float8_e4m3fn, float8_e5m2, w6a8_int8, nvfp4 [INFO] model weight dtype torch.bfloat16, manual cast: torch.bfloat16 [INFO] model_type FLOW [INFO] Model storage policy: fast_disk=False paths=['<ComfyUI>/models/diffusion_models/z_image_turbo_int8_convrot.safetensors'] [INFO] [OmniXPU] AIMDO inference budget: devices=0 minimum=903.2MiB [INFO] Requested to load Lumina2 [INFO] Model Lumina2 prepared for dynamic VRAM loading. 5888MB Staged. 0 patches attached. Force pre-loaded 205 weights: 2087 KB. 0%| | 0/8 [00:00<?, ?it/s, Model Initializing ... ] [INFO] [OmniXPU] attention CUTE #1: heads=30 seq=416 dtype=torch.bfloat16 [INFO] [OmniXPU] attention CUTE #2: heads=30 seq=416 dtype=torch.bfloat16 [INFO] [OmniXPU] attention CUTE #3: heads=30 seq=4032 dtype=torch.bfloat16 100%|████████████████████████████████████████████████████████████████████████████████████| 8/8 [00:03<00:00, 2.21it/s] VRAM清理完成 [卸载模型: False, 清空缓存: True] [INFO] [OmniXPU] AIMDO inference budget: devices=0 minimum=544.5MiB [INFO] Requested to load AutoencodingEngine [INFO] Model AutoencodingEngine prepared for dynamic VRAM loading. 319MB Staged. 0 patches attached. Force pre-loaded 108 weights: 182 KB. [INFO] Prompt executed in 46.40 seconds [INFO] Using RAM pressure cache. [INFO] got prompt [INFO] Model storage policy: fast_disk=False paths=['<ComfyUI>/models/vae/ae.safetensors'] [INFO] Using pytorch attention in VAE [INFO] Using pytorch attention in VAE [INFO] VAE load device: xpu:0, offload device: cpu, dtype: torch.float32 [INFO] Found quantization metadata version 1 [INFO] Using MixedPrecisionOps for text encoder [INFO] Model storage policy: fast_disk=False paths=['<ComfyUI>/models/text_encoders/qwen_3_4b_int8_convrot.safetensors'] [INFO] CLIP/text encoder model load device: xpu:0, offload device: cpu, current: cpu, dtype: torch.float16 [INFO] Requested to load ZImageTEModel_ [INFO] Model ZImageTEModel_ prepared for dynamic VRAM loading. 4303MB Staged. 0 patches attached. Force pre-loaded 145 weights: 383 KB. [INFO] Found quantization metadata version 1 [INFO] Detected mixed precision quantization [INFO] Using mixed precision operations [INFO] Native ops: int8_tensorwise , emulated ops: convrot_w4a4, mxfp8, asym_w4a8_int8, float8_e4m3fn, float8_e5m2, w6a8_int8, nvfp4 [INFO] model weight dtype torch.bfloat16, manual cast: torch.bfloat16 [INFO] model_type FLOW [INFO] Model storage policy: fast_disk=False paths=['<ComfyUI>/models/diffusion_models/z_image_turbo_int8_convrot.safetensors'] [INFO] [OmniXPU] AIMDO inference budget: devices=0 minimum=903.2MiB [INFO] Requested to load Lumina2 [INFO] Model Lumina2 prepared for dynamic VRAM loading. 5888MB Staged. 0 patches attached. Force pre-loaded 205 weights: 2087 KB. 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████| 8/8 [00:03<00:00, 2.21it/s] VRAM清理完成 [卸载模型: False, 清空缓存: True] [INFO] [OmniXPU] AIMDO inference budget: devices=0 minimum=544.5MiB [INFO] Requested to load AutoencodingEngine [INFO] Model AutoencodingEngine prepared for dynamic VRAM loading. 319MB Staged. 0 patches attached. Force pre-loaded 108 weights: 182 KB. [INFO] Prompt executed in 20.01 seconds [INFO] Using RAM pressure cache.