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

Make handling of FP8 scales more consisent #2666

Merged
merged 1 commit into from
Oct 19, 2024

Conversation

danieldk
Copy link
Member

What does this PR do?

Change fp8_quantize so that we can pass around reciprocals everywhere, so scales are always passed around in the checkpoint format.

I also noticed that we ignore any input scales that we might have when fbgemm is available. Skip this path if we already have a scale.

Before submitting

  • This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
  • Did you read the contributor guideline,
    Pull Request section?
  • Was this discussed/approved via a Github issue or the forum? Please add a link
    to it if that's the case.
  • Did you make sure to update the documentation with your changes? Here are the
    documentation guidelines, and
    here are tips on formatting docstrings.
  • Did you write any new necessary tests?

Who can review?

Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.

mht-sharma
mht-sharma previously approved these changes Oct 18, 2024
Copy link
Collaborator

@mht-sharma mht-sharma left a comment

Choose a reason for hiding this comment

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

Thanks @danieldk, LGTM This make things clearer

server/text_generation_server/layers/fp8.py Outdated Show resolved Hide resolved
Change `fp8_quantize` so that we can pass around reciprocals everywhere,
so scales are always passed around in the checkpoint format.

I also noticed that we ignore any input scales that we might have when
fbgemm is available. Skip this path if we already have a scale.
@danieldk danieldk force-pushed the maintenance/reciprocal-handling branch from c1f34c7 to f5b0946 Compare October 18, 2024 15:40
@danieldk danieldk merged commit 5e0fb46 into main Oct 19, 2024
11 of 12 checks passed
@danieldk danieldk deleted the maintenance/reciprocal-handling branch October 19, 2024 07:05
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