Enable streaming for Qwen3-TTS when ICL mode is enabled. #466
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
Contributor
Author
|
The test failure appears to be in Dia and seems unrelated to this PR. I don't know how to re-run the test to see if it is a sporadic one. |
lucasnewman
approved these changes
Feb 1, 2026
Collaborator
lucasnewman
left a comment
lucasnewman
left a comment
There was a problem hiding this comment.
Thanks, looks good!The tests were pulling network data unauthenticated to HF which was triggering timeouts -- it should be more reliable now.
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Outdated suggestions cannot be applied.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.
#461 increased memory usage because streaming is not supported when running in ICL mode.
This PR enables streaming for ICL mode, drastically reducing memory usage again. Some quick eyeballing shows a decrease in peak memory usage from ~10GB to ~6GB.
This code was adapted from the streaming code in
generate().