Support models that don't split stream chunks in tokens #8235
+374
−16
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
chenmoneygithub
force-pushed
the
fix-gemini-streaming
branch
from
286aca0 to
069f2a3
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Resolve #8211
Gemini models don't split stream chunks into 1-2 tokens per chunk, but instead have lots of tokens per chunk. We are reworking the listeners' logic to support this use case.
Side note - I do understand the rationale of buffering tokens for safety checks. but why not streaming back the original tokens for consistency with other models? This also creates a burden for app developer who wants to render the stream on UI.