Skip to content

Conversation

@kylesayrs
Copy link
Collaborator

Purpose

  • Support wrapping modules after wrap_module_forward_quantized has been called (ie using torch offloader)

Changes

  • Instead of passing the original module as "self", use the self which is input to the wrapper function
    • If self is changed (via wrapping, ect), those changes will now be reflected in the wrapper function

Testing

  • Tested e2e with torch offloader

Signed-off-by: Kyle Sayers <kylesayrs@gmail.com>
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