Skip to content

Conversation

@jiqing-feng
Copy link
Collaborator

  1. We need call super post init to get wf_unsqueeze_zero, otherwise we cannot dequant.
  2. IPEXWoqLinear is incompatible with torch.compile, we should disable it until we fix this issue.

@Qubitium Qubitium merged commit a82bdc2 into ModelCloud:main Mar 10, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants