From 9c42598aee14481f4954ad71cce3a57888487a4e Mon Sep 17 00:00:00 2001 From: Sumit Jaiswal Date: Fri, 30 May 2025 16:14:31 +0530 Subject: [PATCH] fix review around /models api call --- llama_stack/providers/remote/inference/vllm/vllm.py | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/llama_stack/providers/remote/inference/vllm/vllm.py b/llama_stack/providers/remote/inference/vllm/vllm.py index 49a0b96bc..21e4c0e1d 100644 --- a/llama_stack/providers/remote/inference/vllm/vllm.py +++ b/llama_stack/providers/remote/inference/vllm/vllm.py @@ -312,12 +312,8 @@ class VLLMInferenceAdapter(Inference, ModelsProtocolPrivate): HealthResponse: A dictionary containing the health status. """ try: - headers = {} client = self._create_client() if self.client is None else self.client - if client.api_key: - headers["Authorization"] = f"Bearer {client.api_key}" - models_url = f"{client.base_url}models" - requests.get(models_url, headers=headers, timeout=10) + client.models.list() # Ensure the client is initialized return HealthResponse( status=HealthStatus.OK )