[Model] Explicit interface for vLLM models and support OOT embedding models #9108
+342
−37
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Outdated suggestions cannot be applied.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.
This PR adds
interface_base.py
which specifies the required methods for vLLM models, something that wasn't clear before. Hope that this can clear up some confusion during model development and refactoring efforts.I have updated model registry tests to ensure that our existing models satisfy those interfaces.
Based on this change, we now automatically detect embedding models without relying on the internal
_EMBEDDING_MODELS
global, making them available for OOT - I've added tests for this as well.