Avoid inferred expand_shape in unflatten lowering#4565
Open
KyleHerndon wants to merge 1 commit into
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This fixes a use-after-free in ConvertAtenUnflattenIntOp by avoiding the tensor.expand_shape builder overload that infers the output shape from the source tensor. During dialect conversion, that inference can create/fold arithmetic using stale IR when the framework has already replaced/erased related operations.
Instead, the lowering now computes the mixed output shape explicitly from the converted input, result type, and unflatten sizes, and passes it to tensor.expand_shape.
Verification: