best_of support in output formatter #1992
Merged
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Outdated suggestions cannot be applied.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
For best_of, we wait for the whole generation is finished, because we would not know which of the multiple sequences has the highest cumulative probability until the end of the generation. This is the reason, TGI supports best_of only during non streaming case.
This PR, introduces best_of support in json_output_formatter.
Unit test case:
Added unit test case to validate the output formatter.
Integration tests:
In order to test this in integration test, vllm/lmi-dist handler should support this. Will create a new PR for this, as the changes are a lot. Meanwhile, this PR changes should not fail any integration tests.