fix: use local token_hop_len in streaming loop to avoid concurrent st…#1849
Open
Caxson wants to merge 1 commit intoFunAudioLLM:mainfrom
Open
fix: use local token_hop_len in streaming loop to avoid concurrent st…#1849Caxson wants to merge 1 commit intoFunAudioLLM:mainfrom
Caxson wants to merge 1 commit intoFunAudioLLM:mainfrom
Conversation
…ate mutation The streaming loop in CosyVoice2Model.tts() mutates self.token_hop_len each iteration (via stream_scale_factor). When multiple requests share the same model instance, this shared state is corrupted across concurrent inferences. Use a local variable token_hop_len initialized from self.token_hop_len and update only the local copy inside the loop, so each streaming session has its own hop length progression. Behavior is unchanged for single-request usage.
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
…ate mutation
The streaming loop in CosyVoice2Model.tts() mutates self.token_hop_len each iteration (via stream_scale_factor). When multiple requests share the same model instance, this shared state is corrupted across concurrent inferences.
Use a local variable token_hop_len initialized from self.token_hop_len and update only the local copy inside the loop, so each streaming session has its own hop length progression. Behavior is unchanged for single-request usage.