Add logs (prints :/) to dump out what URL vllm / tgi is connecting to

llama_stack/providers/remote/inference/tgi/tgi.py

@@ -264,6 +264,7 @@ class _HfAdapter(Inference, ModelsProtocolPrivate):
 
 class TGIAdapter(_HfAdapter):
     async def initialize(self, config: TGIImplConfig) -> None:
+        print(f"Initializing TGI client with url={config.url}")
         self.client = AsyncInferenceClient(model=config.url, token=config.api_token)
         endpoint_info = await self.client.get_endpoint_info()
         self.max_tokens = endpoint_info["max_total_tokens"]

llama_stack/providers/remote/inference/vllm/vllm.py

@@ -53,6 +53,7 @@ class VLLMInferenceAdapter(Inference, ModelsProtocolPrivate):
         self.client = None
 
     async def initialize(self) -> None:
+        print(f"Initializing VLLM client with base_url={self.config.url}")
         self.client = OpenAI(base_url=self.config.url, api_key=self.config.api_token)
 
     async def shutdown(self) -> None: