Skip to content

adds concurrent_requests parameter for litellm backend #953

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 3 commits into
base: main
Choose a base branch
from
Open

adds concurrent_requests parameter for litellm backend #953

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
75e8b39
adding concurency feature for litellm
anupam-dewan Sep 10, 2025
8060c92
adding concurrent_requests as acceptable feild
anupam-dewan Sep 10, 2025
054991b
Merge branch 'main' into concurency-litellm-feature
NathanHB Sep 15, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions examples/model_configs/litellm_model.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,7 @@ model_parameters:
model_name: "openai/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B"
provider: "openai"
base_url: "https://router.huggingface.co/hf-inference/v1"
concurrent_requests: 10 # Configure the number of concurrent API requests
generation_parameters:
temperature: 0.5
max_new_tokens: 256
Expand Down
6 changes: 6 additions & 0 deletions src/lighteval/models/abstract_model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -54,6 +54,10 @@ class ModelConfig(BaseModel, extra="forbid"):
behavior and context for the model during evaluation.
cache_dir (str):
Directory to cache the model. Defaults to "~/.cache/huggingface/lighteval".
concurrent_requests (int):
Maximum number of concurrent API requests to execute in parallel.
Higher values can improve throughput for batch processing but may hit rate limits
or exhaust API quotas faster. Default is 10.

Methods:
from_path(path: str):
Expand Down Expand Up @@ -83,6 +87,8 @@ class ModelConfig(BaseModel, extra="forbid"):
generation_parameters: GenerationParameters = GenerationParameters()
system_prompt: str | None = None
cache_dir: str = "~/.cache/huggingface/lighteval"
concurrent_requests: int = 10
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

can you put it in the litellm model config instead of the abstract model ? this is really specific to litellm



@classmethod
def from_path(cls, path: str):
Expand Down
Loading