Bump CK for a stride fix in CKTile Block-Scale GEMM#2862
Draft
Bump CK for a stride fix in CKTile Block-Scale GEMM#2862
Conversation
Contributor
🏷️ CI GuideRuns automatically on every PR:
Extended tests (opt-in via labels):
|
1 task
nholmber
added a commit
to nholmber/aiter
that referenced
this pull request
Apr 22, 2026
nholmber
added a commit
to nholmber/aiter
that referenced
this pull request
Apr 23, 2026
…eline) The commit IS public in ROCm/composable_kernel. Previous failure was due to shallow clone not having the commit, not it being missing. This is the correct CK version that PR ROCm#2862 intended.
nholmber
added a commit
to nholmber/aiter
that referenced
this pull request
Apr 25, 2026
Tuned 1482 shapes (TP1/TP2/TP4) for Qwen/Qwen3-Next-80B-A3B-Instruct-FP8 on MI355X using CK + CK-TILE backends with splitK support. Depends on: - PR ROCm#2862 (CK bump for stride fix in CK-TILE blockscale) - PR ROCm#2541 (splitK support for CK/CK-TILE blockscale GEMMs) - PR ROCm#2487 (AQLayout tunable for CK-TILE blockscale 8-warp kernels)
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Motivation
This pull request updates the
composable_kernelsubmodule to a newer commit. This will pull in a bugfix for CKTile Block-Scale GEMM (8-wave pipeline for gfx950).Technical Details
See explanation in the commit: ROCm/composable_kernel@cbfb3e2
Test Plan
Running existing tests.
Test Result
Block-Scale GEMM tests are still passing locally.
Submission Checklist