Fix device mismatch in AttentionSharingUnit for SD 1.5 (Grok @ xAI) #128
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
added 2 commits
May 6, 2025 00:02
Resolved RuntimeError: Expected all tensors to be on the same device in AttentionSharingUnit and AttentionSharingPatcher by ensuring consistent CUDA/CPU device placement. Added explicit device synchronization for LoRA layers, temporal layers, and LayerNorm weights/biases in forward and initialization. Ensures compatibility with CUDA-enabled systems while maintaining CPU fallback. Fixes crashes during diffusion model sampling in ComfyUI workflows.
Replaced torch.median with torch.mean in estimate_augmented to avoid empty tensor (shape=[0]) errors on DirectML. Added NaN/inf checks and debug logs for robustness. Preserved original 8 augmentations.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Resolved RuntimeError: Expected all tensors to be on the same device in AttentionSharingUnit and AttentionSharingPatcher by ensuring consistent CUDA/CPU device placement. Added explicit device synchronization for LoRA layers, temporal layers, and LayerNorm weights/biases in forward and initialization. Ensures compatibility with CUDA-enabled systems while maintaining CPU fallback. Fixes crashes during diffusion model sampling in ComfyUI workflows.