solve false negtive gap for multiple output operators#16729
Merged
meta-codesync[bot] merged 1 commit intopytorch:mainfrom Jan 21, 2026
Merged
solve false negtive gap for multiple output operators#16729meta-codesync[bot] merged 1 commit intopytorch:mainfrom
meta-codesync[bot] merged 1 commit intopytorch:mainfrom
Conversation
Summary: When comparing AOT intermediate outputs with runtime, we believed that AOT and runtime should have same output for same operator. But if there're multiple intermediate outputs from a single operator / single operator blob, the statement may not correct. Like drop out, which only record output tensor during AOT, but in runtime we record both mask and output tensor. To support that, for 1 to many scenerio, instead of only take the last element for comparsion, we compare the runtime output sharing the same size and dtype with the aot one to have the best comparsion. Reviewed By: GregoryComer Differential Revision: D90790256
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/16729
Note: Links to docs will display an error until the docs builds have been completed. ❌ 5 New Failures, 1 Cancelled JobAs of commit 9e6ebe4 with merge base c92f03f ( NEW FAILURES - The following jobs have failed:
CANCELLED JOB - The following job was cancelled. Please retry:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
Bot
added
the
CLA Signed
Contributor
|
@Gasoonjia has exported this pull request. If you are a Meta employee, you can view the originating Diff in D90790256. |
This PR needs a
|
GregoryComer
approved these changes
Jan 21, 2026
Contributor
Author
|
@pytorchbot cherry-pick --onto release/1.1 -c fixnewfeature |
Collaborator
Cherry picking #16729The cherry pick PR is at #16736 and it is recommended to link a fixnewfeature cherry pick PR with an issue. Details for Dev Infra teamRaised by workflow job |
Gasoonjia
added a commit
to Gasoonjia/executorch-1
that referenced
this pull request
Jan 22, 2026
Summary: When comparing AOT intermediate outputs with runtime, we believed that AOT and runtime should have same output for same operator. But if there're multiple intermediate outputs from a single operator / single operator blob, the statement may not correct. Like drop out, which only record output tensor during AOT, but in runtime we record both mask and output tensor. To support that, for 1 to many scenerio, instead of only take the last element for comparsion, we compare the runtime output sharing the same size and dtype with the aot one to have the best comparsion. Differential Revision: D91201882
meta-codesync Bot
pushed a commit
that referenced
this pull request
Jan 23, 2026
Differential Revision: D91201882 Pull Request resolved: #16763
pytorchbot
pushed a commit
that referenced
this pull request
Jan 23, 2026
rascani
pushed a commit
that referenced
this pull request
Jan 23, 2026
Summary: When comparing AOT intermediate outputs with runtime, we believed that AOT and runtime should have same output for same operator. But if there're multiple intermediate outputs from a single operator / single operator blob, the statement may not correct. Like drop out, which only record output tensor during AOT, but in runtime we record both mask and output tensor. To support that, for 1 to many scenerio, instead of only take the last element for comparsion, we compare the runtime output sharing the same size and dtype with the aot one to have the best comparsion. Differential Revision: D91201882 Co-authored-by: Gasoonjia <gasoonjia@meta.com>
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:
When comparing AOT intermediate outputs with runtime, we believed that AOT and runtime should have same output for same operator. But if there're multiple intermediate outputs from a single operator / single operator blob, the statement may not correct. Like drop out, which only record output tensor during AOT, but in runtime we record both mask and output tensor.
To support that, for 1 to many scenerio, instead of only take the last element for comparsion, we compare the runtime output sharing the same size and dtype with the aot one to have the best comparsion.
Reviewed By: GregoryComer
Differential Revision: D90790256