server: multimodal - fix misreported prompt and num prompt tokens #392
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
jart
approved these changes
May 7, 2024
Collaborator
jart
left a comment
jart
left a comment
There was a problem hiding this comment.
Thank you! I was wondering about that.
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Outdated suggestions cannot be applied.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.
Ported the code from llama.cpp PR 5896
Should address llama.cpp 5852 and llama.cpp 5863
To fix, we set the number of tokens processed to it's correct value in ingest_images where the prompt is tokenized for multimodal.
Additionally a fix for the prompt being set to the empty string for multimodal responses. Basically we iteratively rebuild the initial prompt since it was cleared.