Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[LLAMA] update pattern to consider initializers #1716

Merged
merged 6 commits into from
Sep 13, 2023
Merged

Conversation

dsikka
Copy link
Contributor

@dsikka dsikka commented Sep 7, 2023

For the quantized models, the Slice nodes that need to be updated have input values stored as initializers, while for the dense models, they're stored as constants. This PR updates to check for both.

@dsikka dsikka marked this pull request as ready for review September 11, 2023 13:55
Copy link
Contributor Author

@dsikka dsikka left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

address comments

bfineran
bfineran previously approved these changes Sep 12, 2023
Co-authored-by: Benjamin Fineran <bfineran@users.noreply.github.com>
@bfineran bfineran merged commit c610973 into main Sep 13, 2023
9 of 11 checks passed
@bfineran bfineran deleted the update_llama_pattern branch September 13, 2023 19:57
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.

3 participants