Fix duplicate gradient addition in backward pass #200
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
Fix duplicate gradient creation in _backward_idempotent function causing memory waste and potential gradient aggregation issues. - Remove redundant gradient addition at lines 365-366 - Preserve existing gradient addition with proper metadata handling - Ensure single gradient per variable in idempotent operations
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Outdated suggestions cannot be applied.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.
Summary
Fixes a bug in the function where the same gradient was being added twice to each variable's gradient set.
Problem
Lines 365-366 contained a duplicate gradient addition after the proper gradient addition with metadata handling. This caused memory waste and potential gradient aggregation issues.
Solution
Remove the redundant gradient addition while preserving correct metadata propagation.