Fix Qwen3-TTS streaming memory leak.#585
Merged
lucasnewman merged 1 commit intoBlaizzy:mainfrom Mar 17, 2026
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
When running the mlx-server and sending stream-able "/v1/audio/speech" requests with the Qwen3-TTS model, memory usage would continue to grow by 3-4GB per request until being culled after about 10GB. Then the cycle would repeat.
The Qwen3-TTS streaming model does a good job keeping memory usage down during the stream, but it fails to do one final
mx.clear_cache()after yielding the last streaming chunk.This PR fixes the leak.