Allow extra request inputs #552
Merged
Conversation
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
![github-advanced-security[bot]](https://avatars.githubusercontent.com/in/57789?s=60&v=4){kind=small}
debermudez
reviewed
Mar 27, 2024
nv-braf
reviewed
Mar 27, 2024
nv-hwoo
reviewed
Apr 3, 2024
Co-authored-by: Hyunjae Woo <[email protected]>
debermudez
pushed a commit
that referenced
this pull request
Apr 4, 2024
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Outdated suggestions cannot be applied.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.
This will allow users to pass in additional inputs beyond those in the model. This is useful for adding support to different backends/endpoints that have different arguments they support without hardcoding each one into GenAi-Perf.
This has been tested for Triton+TRT-LLM, Triton+vLLM, vLLM+OpenAI (both endpoints). If we wanted to drop support for
--streaming, we could so since that would now be supported via--extra-inputs(e.g.--extra-inputs stream:True).When a non-existent input name is given, no error is raised and GenAi-Perf works as if it was not provided. I created a follow-up ticket (TMA-1799) to investigate if PA is not raising an error when input data for non-existent inputs is provided in an input data JSON. That ticket aims to make sure an error is raised in PA and GenAi-Perf for those cases.
Unit testing passes:
