Skip to content

Fix Qwen3-TTS streaming memory leak. #585

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.

Sign up for GitHub

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
lucasnewman merged 1 commit into from
Mar 17, 2026
+2 −0
Merged

Fix Qwen3-TTS streaming memory leak. #585

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions mlx_audio/tts/models/qwen3_tts/qwen3_tts.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2072,6 +2072,7 @@ def _generate_icl(
is_final_chunk=True,
)
self.speech_tokenizer.decoder.reset_streaming_state()
mx.clear_cache()
return

if not generated_codes:
Expand Down Expand Up @@ -2386,6 +2387,7 @@ def _generate_with_instruct(
is_final_chunk=True,
)
self.speech_tokenizer.decoder.reset_streaming_state()
mx.clear_cache()
return

if not generated_codes:
Expand Down