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

Remove KV-cache compression disabling flag for compressed models #1141

Merged

Conversation

nikita-savelyevv
Copy link
Collaborator

@nikita-savelyevv nikita-savelyevv commented Feb 5, 2025

What does this PR do?

  • Remove "KV_CACHE_PRECISION": "f16" rt info flag for all weight-compressed models. This way applying weight compression also enables KV cache compression.
  • Add deprecation warning for OVDynamicQuantizationConfig.

Tests:

  • Check that KV_CACHE_PRECISION rt info flag is not present for compressed models.
  • Take list of submodels from image-text-to-text models as list(model.submodels.values()), this is more convenient.

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 marked this pull request as ready for review February 5, 2025 10:28
@AlexKoff88 AlexKoff88 requested a review from eaidova February 5, 2025 10:45
Co-authored-by: Alexander Kozlov <alexander.kozlov@intel.com>
[{"int8": 14, "int4": 16}, {"int8": 9}, {"int8": 1}],
[{"int8": 14, "int4": 16}, {"int8": 1}, {"int8": 9}],
Copy link
Collaborator Author

Choose a reason for hiding this comment

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

Order of some reference values is changed because of the addition of this line: submodels = list(model.submodels.values()). This alters the order of submodels compared to before.

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.

LGTM!

@echarlaix echarlaix merged commit f601b8b into huggingface:main Feb 5, 2025
17 of 22 checks passed
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.

5 participants