Fix bug in le broadcast for single element broadcast#11922
Merged
kimishpatel merged 1 commit intomainfrom Jun 25, 2025
Merged
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/11922
Note: Links to docs will display an error until the docs builds have been completed. ✅ You can merge normally! (3 Unrelated Failures)As of commit 35caf87 with merge base 44ab83a ( FLAKY - The following jobs failed but were likely due to flakiness present on trunk:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
This PR needs a
|
Contributor
Author
|
This also fixes the garbage output issue in optimum-executorch models |
guangy10
approved these changes
Jun 24, 2025
Contributor
guangy10
left a comment
guangy10
left a comment
There was a problem hiding this comment.
LGTM. Accepted to unblock the work in optimum-executorch.
Summary: Really comparison ops cannot be handled in the same way as other binary ops for broadcasting because output tensor dtype is different than input tensor dtype. As a result we just have to fall back to portable. Even the current vectorized impl for le, ge etc. assumes that the output type of compare is same as input type. That might actually be a bug. A potential way to handle this maybe via vectorized compare natively supporting binary output vector Test Plan: Tests added which fail before and passes after Reviewers: Subscribers: Tasks: Tags:
kimishpatel
force-pushed
the
fix_le_broadcast
branch
from
22e81d9 to
35caf87
Compare
Contributor
Author
|
failures are not related |
This was referenced Jun 25, 2025
hinriksnaer
pushed a commit
to hinriksnaer/executorch
that referenced
this pull request
Jun 26, 2025
Summary: Really comparison ops cannot be handled in the same way as other binary ops for broadcasting because output tensor dtype is different than input tensor dtype. As a result we just have to fall back to portable. Even the current vectorized impl for le, ge etc. assumes that the output type of compare is same as input type. That might actually be a bug. A potential way to handle this maybe via vectorized compare natively supporting binary output vector Test Plan: Tests added which fail before and passes after Reviewers: Subscribers: Tasks: Tags: ### Summary [PLEASE REMOVE] See [CONTRIBUTING.md's Pull Requests](https://github.com/pytorch/executorch/blob/main/CONTRIBUTING.md#pull-requests) for ExecuTorch PR guidelines. [PLEASE REMOVE] If this PR closes an issue, please add a `Fixes #<issue-id>` line. [PLEASE REMOVE] If this PR introduces a fix or feature that should be the upcoming release notes, please add a "Release notes: <area>" label. For a list of available release notes labels, check out [CONTRIBUTING.md's Pull Requests](https://github.com/pytorch/executorch/blob/main/CONTRIBUTING.md#pull-requests). ### Test plan [PLEASE REMOVE] How did you test this PR? Please write down any manual commands you used and note down tests that you have written if applicable.
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
3 participants
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:
Really comparison ops cannot be handled in the same way as other binary ops for broadcasting because output tensor dtype is different than input tensor dtype.
As a result we just have to fall back to portable.
Even the current vectorized impl for le, ge etc. assumes that the output type of compare is same as input type. That might actually be a bug.
A potential way to handle this maybe via vectorized compare natively supporting binary output vector
Test Plan:
Tests added which fail before and passes after
Reviewers:
Subscribers:
Tasks:
Tags:
Summary
[PLEASE REMOVE] See CONTRIBUTING.md's Pull Requests for ExecuTorch PR guidelines.
[PLEASE REMOVE] If this PR closes an issue, please add a
Fixes #<issue-id>line.[PLEASE REMOVE] If this PR introduces a fix or feature that should be the upcoming release notes, please add a "Release notes: " label. For a list of available release notes labels, check out CONTRIBUTING.md's Pull Requests.
Test plan
[PLEASE REMOVE] How did you test this PR? Please write down any manual commands you used and note down tests that you have written if applicable.