Skip to content

Fixed LiteLLM multi-hosted_vllm request address mixture. #701

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

Merged
madiator merged 1 commit into from
Jan 5, 2026
Merged

Fixed LiteLLM multi-hosted_vllm request address mixture. #701

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
9 changes: 7 additions & 2 deletions src/bespokelabs/curator/request_processor/online/litellm_online_request_processor.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -45,8 +45,8 @@ class LiteLLMOnlineRequestProcessor(BaseOnlineRequestProcessor):
def __init__(self, config: OnlineRequestProcessorConfig):
"""Initialize the LiteLLMOnlineRequestProcessor."""
super().__init__(config)
if self.config.base_url is not None:
litellm.api_base = self.config.base_url
# NOTE: Removed global litellm.api_base assignment - now passed per-request
# to allow multiple LLM instances with different base_urls
self.client = instructor.from_litellm(litellm.acompletion)
self.header_based_max_requests_per_minute, self.header_based_max_tokens_per_minute = self.get_header_based_rate_limits()

Expand Down Expand Up @@ -185,6 +185,7 @@ def test_call(self):
completion = litellm.completion(
model=self.config.model,
messages=[{"role": "user", "content": "hi"}], # Some models (e.g. Claude) require an non-empty message to get rate limits.
api_base=self.config.base_url, # Pass api_base per-request
**self.config.generation_params,
)
# Try the method of caculating cost
Expand Down Expand Up @@ -252,6 +253,10 @@ def create_api_specific_request_online(self, generic_request: GenericRequest) ->
for key, value in generic_request.generation_params.items():
request[key] = value

# Pass api_base per-request instead of globally
if self.config.base_url is not None:
request["api_base"] = self.config.base_url

# Add safety settings for Gemini models
if "gemini" in generic_request.model.lower():
request["safety_settings"] = [
Expand Down