hosted_vllm endpoint for reranker routing to /v1/rerank instead of /rerank

[skuchipu]

Hi Team,

I'm using v1.79.0-stable image with helm chart "litellm-helm-0.1.804"

and trying to configure hosted_vllm endpoint for a reranker model , however when testing the model endpoint the request is being routed to /v1/rerank , the expected route should be /rerank .

Error:
stack trace: Traceback (most recent call last):
File "/app/litellm/llms/custom_httpx/llm_http_handler.py", line 1005, in arerank
response = await async_httpx_client.post(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
...<4 lines>...
)
^
File "/app/litellm/litellm_core_utils/logging_utils.py", line 190, in async_wrapper
result = await func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/litellm/llms/custom_httpx/http_handler.py", line 360, in post
raise e
File "/app/litellm/llms/custom_httpx/http_handler.py", line 316, in post
response.raise_for_status()
~~~~~~~~~~~~~~~~~~~~~~~~~^^
File "/usr/lib/python3.13/site-packages/httpx/_models.py", line 829, in raise_for_status
raise HTTPStatusError(message, request=request, response=self)
httpx.HTTPStatusError: Client error '404 Not Found' for url 'https://xxxxxxxxxxxxxxx/bge-reranker-v2-m3/v1/rerank'
For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/St