Since we are pushing for HF repos, we should accept them in inference configs (#497)

# What does this PR do?

As the title says. 

## Test Plan

This needs
8752149f58
to also land. So the next package (0.0.54) will make this work properly.

The test is:

```bash
pytest -v -s -m "llama_3b and meta_reference" test_model_registration.py
```

llama_stack/providers/utils/inference/prompt_adapter.py

@@ -178,7 +178,9 @@ def chat_completion_request_to_messages(
         cprint(f"Could not resolve model {llama_model}", color="red")
         return request.messages
 
-    if model.descriptor() not in supported_inference_models():
+    allowed_models = supported_inference_models()
+    descriptors = [m.descriptor() for m in allowed_models]
+    if model.descriptor() not in descriptors:
         cprint(f"Unsupported inference model? {model.descriptor()}", color="red")
         return request.messages