- 
                Notifications
    You must be signed in to change notification settings 
- Fork 706
Metal backend: eliminate memory leak #15343
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
          
     Merged
      
      
    
                
     Merged
            
            
          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
    
  
  
    
    | Stack from ghstack (oldest at bottom): | 
| 🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/15343
 Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New Failure, 1 Cancelled Job, 2 Pending, 2 Unrelated FailuresAs of commit ee043e3 with merge base 5d71c9b ( NEW FAILURE - The following job has failed:
 
 BROKEN TRUNK - The following jobs failed but were present on the merge base:👉 Rebase onto the `viable/strict` branch to avoid these failures 
 This comment was automatically generated by Dr. CI and updates every 15 minutes. | 
  This was referenced Oct 22, 2025 
      
              
                    larryliu0820
  
              
              approved these changes
              
                  
                    Oct 22, 2025 
                  
              
              
            
            
  
    Sign up for free
    to join this conversation on GitHub.
    Already have an account?
    Sign in to comment
  
      Labels
      
    CLA Signed
  This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. 
  
    release notes: none
  Do not include this in the release notes 
  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 pull request refactors the Metal backend's stream commit logic and improves memory management for MPSGraph operations. The most significant changes are the rewrite of the "commit" SyncType to always release the command buffer after commit, and the addition of explicit resource releases to prevent memory leaks after MPSGraph execution.
Stream commit logic changes:
ETMetalStream::commitmethod now always commits and releases the command buffer directly, removing support for the "commit and continue" optimization and adding error logging if no command buffer is present.SyncType::COMMITinstead ofSyncType::COMMIT_AND_CONTINUE.Memory management improvements:
mm_out,convolution, andscaled_dot_product_attention_math_for_mps), the code now explicitly releases the MPSGraph and all associatedMPSGraphTensorDataobjects to prevent memory leaks.Code simplification and clarity:
scaledDotProductAttentionWithQueryTensorwas removed, streamlining the attention math implementation.biasData,maskData) are now declared outside conditional blocks for proper release and scope management.