feat: remote ramalama provider implementation

Implement remote ramalama provider using AsyncOpenAI as the client since ramalama doesn't have its own Async library.
Ramalama is similar to ollama, as it is a lightweight local inference server. However, it runs by default in a containerized mode.

RAMALAMA_URL is http://localhost:8080 by default

Signed-off-by: Charlie Doern <cdoern@redhat.com>

llama_stack/distribution/resolver.py

@@ -306,6 +306,7 @@ async def instantiate_provider(
     additional_protocols = additional_protocols_map()
 
     provider_spec = provider.spec
+
     if not hasattr(provider_spec, "module"):
         raise AttributeError(f"ProviderSpec of type {type(provider_spec)} does not have a 'module' attribute")