fix(judge): honor concurrent_requests for the OpenAI/TGI judge backend - #1371
Open
mohansree14 wants to merge 1 commit into
Open
fix(judge): honor concurrent_requests for the OpenAI/TGI judge backend#1371mohansree14 wants to merge 1 commit into
mohansree14 wants to merge 1 commit into
Conversation
The litellm judge backend already reads backend_options.concurrent_requests (LitellmBackendOptions, default 10), but __call_api_parallel -- the path used for the openai and tgi backends -- hard-coded ThreadPoolExecutor(10) and never looked at backend_options at all. Read the same key there, defaulting to 10, so concurrency is configurable for every backend, not just litellm. Fixes huggingface#567
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 join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The litellm judge backend already reads
backend_options.concurrent_requests(viaLitellmBackendOptions, default 10), but__call_api_parallel— the path used for theopenaiandtgibackends — hard-codedThreadPoolExecutor(10)and never looked atbackend_optionsat all.This reads the same
concurrent_requestskey there (defaulting to 10 when not set), so concurrency is configurable for every judge backend, not just litellm — closing the remaining gap from #567.Fixes #567