Fix bool attention mask bias conversion#4354
Open
fallintoplace wants to merge 1 commit into
Open
Conversation
Collaborator
|
@fallintoplace Thanks for the contribution. Torchscript is being removed soon (like pytorch 2.14). Please use Dynamo instead. |
zewenli98
reviewed
Jun 30, 2026
zewenli98
left a comment
Collaborator
There was a problem hiding this comment.
@fallintoplace Thanks for the contribution. Torchscript is being removed soon (like pytorch 2.14). Please use Dynamo instead.
@fallintoplace Pytorch decided not to remove Torchscript support in 2.14. This PR looks good to me. Can you rebase the PR to the main?
Author
|
@zewenli98 Sure, let me push in a few minutes. |
b4a67e8 to
19e2a2b
Compare
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
ISelectLayerinstead of arithmetic involving-inf.0.0for valid mask entries and-inffor masked entries.Testing
git diff --checkTORCH_PATH="$PWD/.venv/lib/python3.12/site-packages/torch" bazelisk test //tests/core/conversion/converters:test_scaled_dot_product_attention --test_filter=ATenScaledDotProductAttnMaskBoolDoesNotProduceNaNwas attempted locally. Bazel stayed in analysis without reaching compilation or test execution after about 96 seconds, so the run was interrupted.