feat: stream tokens usage #4415
Merged
Conversation
This file contains 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
…to get the proper usage data in reply streaming mode at the last [DONE] frame
Seems like that empty message marker trick was unnecessary
✅ Deploy Preview for localai ready!
To edit notification comments on pull requests, go to your Netlify site configuration. |
|
Just did tested this and seems to work, thanks! |
mudler
approved these changes
Dec 18, 2024
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Outdated suggestions cannot be applied.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.
Description
This PR fixes #4334
Notes for Reviewers
Got some time to take a look at log of issue with hanging webui response - found that llama sends the empty message from the start for some reason
There was an unnecessary usage of such case to break the channel loop, which was overlooked
Still can't reproduce that by myself, since i can't really run more advanced models, than phi2 on my 8/256 machine
Yet, tokens count still works like before and code from http/openai/chat remains untouched
@mudler can you confirm that everything is working now?