Conversation
bkorycki
temporarily deployed
to
Scheduled Testing
GitHub Actions
Inactive
|
MLCommons CLA bot All contributors have signed the MLCommons CLA ✍️ ✅ |
wpietri
approved these changes
Mar 11, 2026
Contributor
wpietri
left a comment
wpietri
left a comment
There was a problem hiding this comment.
Ooh, excellent idea, and good job putting your finger on a problem. I love this. Turning the SUT parameters into method arguments is a great way to do it.
superdosh
approved these changes
Mar 11, 2026
Contributor
superdosh
left a comment
superdosh
left a comment
There was a problem hiding this comment.
Thanks for the live overview; makes a lot of sense!
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 subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Goal: We should enforce that SUT UID config parameterizations are actually used.
Right now, if we run
openai/gpt-4o;reas=y;mod=ythe factory will completely ignore the values after;and end up running just the regular openai/gpt-4o sut. This is bad because the UID should be meaningful and accurate.This PR enforces that the values after
;are going to be used/are compatible with the SUT factory.For example, the meta llama SUT factory can update it's method signature to
def make_sut(self, sut_definition: SUTDefinition, moderated: bool=False) -> SUT:and then return either aMetaLlamaSUTor aMetaLlamaModeratedSUTdepending on the kwarg value.We can handle reasoning in the same way.