Skip to content

[CPU] Fix AWQ on CPU after refactoring #2688

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
Closed
wants to merge 1 commit into from
Closed

[CPU] Fix AWQ on CPU after refactoring #2688

wants to merge 1 commit into from
+154 −60

Conversation

Xia-Weiwen
Copy link
Collaborator

Fix the CPU path of AWQ after the refactoring of AWQ implementation by #2400

@pytorch-bot PyTorch Bot
Copy link

pytorch-bot bot commented Aug 5, 2025 •
edited
Loading

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/2688

Note: Links to docs will display an error until the docs builds have been completed.

❌ 2 New Failures

As of commit 8e94408 with merge base 7dbc816 (image):

NEW FAILURES - The following jobs have failed:

This comment was automatically generated by Dr. CI and updates every 15 minutes.

@meta-cla meta-cla bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label Aug 5, 2025
@Xia-Weiwen
Copy link
Collaborator Author

@pytorchbot label "not user facing"

@pytorch-bot PyTorch Bot
Copy link

pytorch-bot bot commented Aug 5, 2025

Didn't find following labels among repository labels: not user facing

@Xia-Weiwen
Copy link
Collaborator Author

@pytorchbot label "topic: not user facing"

@pytorch-bot pytorch-bot bot added the topic: not user facing Use this tag if you don't want this PR to show up in release notes label Aug 5, 2025
@Xia-Weiwen Xia-Weiwen marked this pull request as ready for review August 5, 2025 06:36
@Xia-Weiwen
Copy link
Collaborator Author

Hi @jerryzh168 Could you please review this PR? Thanks.

@Xia-Weiwen Xia-Weiwen mentioned this pull request Aug 5, 2025
Merged
@Xia-Weiwen Xia-Weiwen requested a review from jerryzh168 August 7, 2025 03:00
@jerryzh168
Copy link
Contributor

jerryzh168 commented Aug 7, 2025 •
edited
Loading

we have some planned changes for AWQ actually, which might require refactoring the CPU path, I'll put up soon

@jerryzh168
Copy link
Contributor

jerryzh168 commented Aug 7, 2025 •
edited
Loading

@Xia-Weiwen can you work on splitting out Int4CPUAQTTensorImpl from AffineQuantizedTensor and have a separate Int4SomePackingFormatTensor following the implementation in #2687

or you can wait a bit for a dev guide that we'll have as well, hopefully will come out in 2 weeks

@Xia-Weiwen
Copy link
Collaborator Author

@jerryzh168 Thanks for the info. Sure, I can wait until your new design is ready.

@Xia-Weiwen
Copy link
Collaborator Author

Close this as we are going to use the new Int4OpaqueTensor (#2798) to implement AWQ.

@Xia-Weiwen Xia-Weiwen closed this Sep 1, 2025
@Xia-Weiwen Xia-Weiwen deleted the fix_awq_cpu branch September 1, 2025 02:38
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@jerryzh168 jerryzh168 Awaiting requested review from jerryzh168

Assignees
No one assigned
Labels
CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. topic: not user facing Use this tag if you don't want this PR to show up in release notes
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@Xia-Weiwen @jerryzh168