Fix text generation endpoint #654
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
4 tasks
|
The fix has been also verified by another person here #628 (comment) |
4 tasks
And by me. |
saood06
approved these changes
Jul 27, 2025
|
I've been very intentional in not pushing code into branches that are not mine (including main) without your approval as this is your repo, but I am making an exception in this case as this is a very minor change, that fixes a rather serious bug and you are out on vacation. |
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Outdated suggestions cannot be applied.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.
The recent function call implementation changed streaming responses to always send empty content with diffs, which broke text completion streaming endpoints (like those used by mikupad) that need actual token content in each streaming chunk. This fix differentiates between OpenAI-compatible chat completion (which uses diffs) and text completion endpoints (which need actual content) using the existing slot.oaicompat flag.