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

Update NNCF to 2.10. Enable AWQ algorithm. #673

Merged
merged 12 commits into from
Apr 26, 2024

Conversation

nikita-savelyevv
Copy link
Collaborator

@nikita-savelyevv nikita-savelyevv commented Apr 17, 2024

What does this PR do?

  • Update NNCF to 2.10
  • Enable AWQ weight compression algorithm

Before submitting

  • This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
  • Did you make sure to update the documentation with your changes?
  • Did you write any new necessary tests?

@HuggingFaceDocBuilderDev

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.

@nikita-savelyevv nikita-savelyevv force-pushed the nncf-210-update branch 2 times, most recently from 136eae5 to 420d453 Compare April 23, 2024 14:21
@nikita-savelyevv nikita-savelyevv changed the title Support NNCF 2.10 Update NNCF to 2.10 Apr 23, 2024
@nikita-savelyevv nikita-savelyevv changed the title Update NNCF to 2.10 Update NNCF to 2.10. Enable AWQ algorithm. Apr 23, 2024
@AlexKoff88
Copy link
Collaborator

CI is down due to the required new version of NNCF. I am ok with the changes.
@echarlaix, we will notify you once the release is out.

Copy link
Collaborator

@echarlaix echarlaix left a comment

Choose a reason for hiding this comment

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

Looks good, thanks @nikita-savelyevv

tests/openvino/test_quantization.py Outdated Show resolved Hide resolved
@echarlaix
Copy link
Collaborator

Also would it make sense to have specific configs for different methodologies such as OVAwqConfig like done in transformers what do you think @AlexKoff88 @nikita-savelyevv ?

@AlexKoff88
Copy link
Collaborator

@echarlaix, AWQ is just a part of our weight quantization pipeline, not a separate method. I don't think we need a separate config for it. It is better to have it as an option that can be turned on.

@nikita-savelyevv nikita-savelyevv marked this pull request as ready for review April 25, 2024 14:03
@nikita-savelyevv nikita-savelyevv marked this pull request as draft April 25, 2024 16:06
@nikita-savelyevv nikita-savelyevv marked this pull request as ready for review April 25, 2024 20:09
@AlexKoff88 AlexKoff88 merged commit 920b237 into huggingface:main Apr 26, 2024
11 checks passed
@nikita-savelyevv nikita-savelyevv deleted the nncf-210-update branch April 26, 2024 08:18
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.

4 participants