[CPU][Zen] Add DA8W4 (W4A8) int4 support for dense and MoE layers - #54024
Open
ganeshr10 wants to merge 1 commit into
Open
[CPU][Zen] Add DA8W4 (W4A8) int4 support for dense and MoE layers#54024ganeshr10 wants to merge 1 commit into
ganeshr10 wants to merge 1 commit into
Conversation
Symmetric int4 checkpoints can now run with dynamically int8-quantized activations on Zen CPUs: the dense path extends ZentorchWNA16LinearKernel, and a new ZEN_CPU WNA16 MoE backend repacks stacked experts to s4 for zentorch_fused_moe. Signed-off-by: R <Ganesh.R@amd.com> Co-authored-by: Cursor <cursoragent@cursor.com> Change-Id: Ie38eb795815f0a18a0796d4bc772099a94dfa8cb
ganeshr10
requested review from
AndreasKaratzas,
WoosukKwon,
mgoin,
pavanimajety,
tlrmchlsmth,
yewentao256 and
zyongye
as code owners
August 27, 2026 08:36
![claude[bot]](https://avatars.githubusercontent.com/in/1236702?s=60&v=4){kind=small}
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Purpose
Symmetric int4 checkpoints can now run with dynamically int8-quantized activations on Zen CPUs: the dense path extends ZentorchWNA16LinearKernel, and a new ZEN_CPU WNA16 MoE backend repacks stacked experts to s4 for zentorch_fused_moe.
Test Plan
Test Result
Essential Elements of an Effective PR Description Checklist
supported_models.mdandexamplesfor a new model.