phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 04:04:14 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Fix rerank model endpoint issue

Browse source
This commit is contained in:
Jiayi 2025-09-28 17:45:54 -07:00
parent f85743dcca
commit 2fb8756fe2
2 changed files with 24 additions and 8 deletions
Download patch file Download diff file Expand all files Collapse all files

5
llama_stack/providers/remote/inference/nvidia/nvidia.py
View file

@ -138,10 +138,9 @@ class NVIDIAInferenceAdapter(OpenAIMixin, Inference):
provider_model_id = await self._get_provider_model_id(model)
ranking_url = self.get_base_url()
model_obj = await self.model_store.get_model(model)
if _is_nvidia_hosted(self._config) and "endpoint" in model_obj.metadata:
ranking_url = model_obj.metadata["endpoint"]
if _is_nvidia_hosted(self._config) and provider_model_id in self._rerank_model_endpoints:
ranking_url = self._rerank_model_endpoints[provider_model_id]
logger.debug(f"Using rerank endpoint: {ranking_url} for model: {provider_model_id}")