Skip to content

Conversation

hantao-zhou
Copy link

This version fixed some of the scalar error in the python coding, making the model compatible with torch compile tool, which will provide with a roughly 3x faster inference speed if compiled.

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.

1 participant