stable-diffusion-webui-forge icon indicating copy to clipboard operation
stable-diffusion-webui-forge copied to clipboard

Published 20 hours ago • verified publisher icon lllyasviel

[Bug] Intermittent Hang After Starting: Using pytorch attention for VAE

Open lunar-studio opened this issue 5 months ago • 0 comments

Using Stability Matrix to start. Intermittent hang in console after:

Using cudaMallocAsync backend.
Total VRAM 24576 MB, total RAM 65437 MB
pytorch version: 2.3.1+cu121
Set vram state to: NORMAL_VRAM
Always pin shared GPU memory
Device: cuda:0 NVIDIA GeForce RTX 3090 : cudaMallocAsync
VAE dtype preferences: [torch.bfloat16, torch.float32] -> torch.bfloat16
CUDA Using Stream: True
Using pytorch cross attention
Using pytorch attention for VAE

lunar-studio avatar Aug 26 '24 12:08 lunar-studio