Fix race condition in clearCache causing Metal crash#331
Merged
davidkoski merged 1 commit intoml-explore:mainfrom Jan 10, 2026
Merged
Fix race condition in clearCache causing Metal crash#331davidkoski merged 1 commit intoml-explore:mainfrom
davidkoski merged 1 commit intoml-explore:mainfrom
Conversation
davidkoski
approved these changes
Jan 10, 2026
Collaborator
davidkoski
left a comment
There was a problem hiding this comment.
Nice find, thank you!
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Proposed changes
This PR fixes a crash that occurs when clearCache() is called while an asynchronous evaluation is still encoding commands.
MLX.GPU.clearCache() (which calls Memory.clearCache()) was not synchronized with the evaluation engine. If called during an active generation loop (for example: quitting the app), it would invalidate Metal resources while the command encoder was still using them, leading to an objc_retain crash in CaptureMTLComputeCommandEncoder.
Checklist
Put an
xin the boxes that apply.pre-commit run --all-filesto format my code / installed pre-commit prior to committing changes