Fix llava next text#532
Merged
gkumbhat merged 1 commit intoJun 10, 2026
Merged
Conversation
Signed-off-by: Gaurav-Kumbhat <Gaurav.Kumbhat@ibm.com>
544c2b3 to
ed4ebe8
Compare
joerunde
approved these changes
Jun 10, 2026
joerunde
left a comment
Contributor
There was a problem hiding this comment.
we verified this fixes the crash in vllm by not changing the input shapes for text-only prompts
flaviabeo
approved these changes
Jun 10, 2026
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Changes
llava_next model was incorrectly passing on input_ids instead of embeddings in case of text only inputs. This PR fixes that by invoking embedding resolution for text only calls