Skip to content

[Attention] Support FP4 attention quantization #491

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.

Sign up for GitHub

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

Jump to bottom
Open
wants to merge 3 commits into
base: main
Choose a base branch
from
Open

[Attention] Support FP4 attention quantization #491

wants to merge 3 commits into from

Conversation

@kylesayrs
Copy link
Collaborator

Purpose

  • Support FP4 attention quantization

Postrequisites

Changes

  • Update observer mocking to better mirror LLM Compressor implementation
  • Update expected_shape of tensor_group to only use the second-to-last dimension, which does not change behavior but avoids division error.

Testing

@kylesayrs
attention quant
9ead292 
Signed-off-by: Kyle Sayers <[email protected]>
@kylesayrs
reduce diff
dc43b64 
Signed-off-by: Kyle Sayers <[email protected]>
@kylesayrs
add fp4
864df00 
Signed-off-by: Kyle Sayers <[email protected]>
Base automatically changed from kylesayrs/r3-only to main October 23, 2025 14:35
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

1 participant

@kylesayrs