Fix torch.load() for PyTorch 2.6+ compatibility#414
Open
SeanL009 wants to merge 1 commit into
Open
Conversation
Always use map_location=self.device in torch.load() to ensure compatibility with PyTorch 2.6+. The previous code omitted map_location when CUDA was available, which can cause deserialization errors with zip-serialized checkpoints in newer PyTorch versions. Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
PyTorch 2.6+ changed the default of
torch.load()toweights_only=True, and also introduced stricter zip archive handling. The previous code omittedmap_locationwhen CUDA was available, which can cause deserialization errors with zip-serialized checkpoints.This PR always passes
map_location=self.devicetotorch.load()for consistent behavior across PyTorch versions.Changes
musetalk/models/unet.py: Always usemap_location=self.deviceintorch.load()instead of conditionally omitting it when CUDA is available