Fix: Scaled Matmul at rocm 9.0#739
Open
shurale-nkn wants to merge 1 commit intorocm-jaxlib-v0.9.0from
Open
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
PR fixes failing ScaledMatmul and ScaledDot tests on ROCm caused by:
MLIR translation rule for primitive 'scaled_matmul' not found for platform rocmOn ROCm, we now register a dedicated lowering for scaled_matmul that uses a composite approach: it lowers through lax.scaled_dot instead of relying on direct fusion.
The resulting HLO can then be fused later by XLA, which matches the intended backend behavior and avoids the missing primitive translation path on ROCm.
What changed