[lmi] add stricter payload validation on default schema for rolling-b… #2418
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
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Outdated suggestions cannot be applied.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.
…atch use-cases
Description
Adding some light validation on the default schema for requests in the rolling batch case. For rolling batch, we have a published schema, but no real validation in the code.
I noticed that while we have relatively good support for input processing and formatting across the different batching mechanisms and engines, the output_formatter only takes effect on rolling_batch use-cases. We don't have good output_formatting support for dynamic batch use-cases (at least from the default codepath i've tried, we can issue a chat completions request to a model using dynamic batching, but it's not output formatted correctly)
As a follow up here, I'm going to clean up some code and unify these behaviors.