phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-03 21:02:38 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix review around /models api call

Browse source
This commit is contained in:
Sumit Jaiswal 2025-05-30 16:14:31 +05:30
parent 6a96b6c264
commit 9c42598aee
No known key found for this signature in database
GPG key ID: A4604B39D64D6AEC
1 changed files with 1 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

6
llama_stack/providers/remote/inference/vllm/vllm.py
View file

@ -312,12 +312,8 @@ class VLLMInferenceAdapter(Inference, ModelsProtocolPrivate):
HealthResponse: A dictionary containing the health status. HealthResponse: A dictionary containing the health status.
""" """
try: try:
headers = {}
client = self._create_client() if self.client is None else self.client client = self._create_client() if self.client is None else self.client
if client.api_key: client.models.list() # Ensure the client is initialized
headers["Authorization"] = f"Bearer {client.api_key}"
models_url = f"{client.base_url}models"
requests.get(models_url, headers=headers, timeout=10)
return HealthResponse( return HealthResponse(
status=HealthStatus.OK status=HealthStatus.OK
) )