[Bench] Specialize OpenAI endpoint for backends not supporting debug config #2962
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Outdated suggestions cannot be applied.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 specializes the OpenAI endpoint with the option of "not attaching
debug_config
". Prior to this PR, when--ignore-eos
is enabled, adebug_config
field is included in the payload for MLC to recognize. However, some backend servers (e.g., vLLM) do not support thisdebug_config
field. So we need to manually specify not attaching this field when benchmarking these backends.