Repository navigation
Conversation
tandede
force-pushed
the
fix/expand-matmul-of-sum-broadcast
branch
from
October 15, 2026 02:06
51912a1 to
1b7a4ee
Compare
This branch has not been deployed
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fixes #20697.
ExpandMatmulOfSumcurrently distributesmatmul(x, A + B)even whenAandBare broadcast to form the sum. In that case, the independently computed matmuls can have different shapes, and adding them may produce a different result shape from the original expression.Skip the rewrite unless both addends have the same inferred tensor type as the sum. This preserves the existing optimization for non-broadcast additions while avoiding the invalid transformation.
A regression test covers addends with shapes
[1]and[1, 1, 1].Tests:
tests/python/relax/test_transform_expand_matmul_of_sum.py