Fix race condition during the tracing phase of automatic differentiation (vjp, value_and_grad)#338
Merged
davidkoski merged 2 commits intoml-explore:mainfrom Jan 21, 2026
Merged
Conversation
…ion (vjp, value_and_grad) While the execution of the graph is thread-safe and lazy, the construction of that graph is not.
Collaborator
|
Nice find! I just fixed some others here in #339 -- we should use this same |
Contributor
Author
Updated. Thanks. |
davidkoski
approved these changes
Jan 21, 2026
Collaborator
davidkoski
left a comment
There was a problem hiding this comment.
Thank you for finding this and fixing!
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This PR introduces thread safety to the graph construction phase of the function transformations (vjp, jvp, and valueAndGrad).When multiple threads attempt to compute gradients or vector-Jacobian products simultaneously, data races occur within the C++ layer, leading to std::bad_access crashes and heap corruption.
Proposed changes
The lock is only held during the graph tracing/construction phase. It does not block the actual evaluation or computation of the arrays (which remains lazy).
Checklist
Put an
xin the boxes that apply.pre-commit run --all-filesto format my code / installed pre-commit prior to committing changes