Use inference APIs for running llama guard

Test Plan:

First, start a TGI container with `meta-llama/Llama-Guard-3-8B` model
serving on port 5099. See https://github.com/meta-llama/llama-stack/pull/53 and its
description for how.

Then run llama-stack with the following run config:

```
image_name: safety
docker_image: null
conda_env: safety
apis_to_serve:
- models
- inference
- shields
- safety
api_providers:
  inference:
    providers:
    - remote::tgi
  safety:
    providers:
    - meta-reference
  telemetry:
    provider_id: meta-reference
    config: {}
routing_table:
  inference:
  - provider_id: remote::tgi
    config:
      url: http://localhost:5099
      api_token: null
      hf_endpoint_name: null
    routing_key: Llama-Guard-3-8B
  safety:
  - provider_id: meta-reference
    config:
      llama_guard_shield:
        model: Llama-Guard-3-8B
        excluded_categories: []
        disable_input_check: false
        disable_output_check: false
      prompt_guard_shield: null
    routing_key: llama_guard
```

Now simply run `python -m llama_stack.apis.safety.client localhost
<port>` and check that the llama_guard shield calls run correctly. (The
injection_shield calls fail as expected since we have not set up a
router for them.)

llama_stack/distribution/routers/routers.py

@@ -103,8 +103,7 @@ class InferenceRouter(Inference):
         stream: Optional[bool] = False,
         logprobs: Optional[LogProbConfig] = None,
     ) -> AsyncGenerator:
-        # TODO: we need to fix streaming response to align provider implementations with Protocol.
-        async for chunk in self.routing_table.get_provider_impl(model).chat_completion(
+        params = dict(
             model=model,
             messages=messages,
             sampling_params=sampling_params,
@@ -113,6 +112,10 @@ class InferenceRouter(Inference):
             tool_prompt_format=tool_prompt_format,
             stream=stream,
             logprobs=logprobs,
+        )
+        # TODO: we need to fix streaming response to align provider implementations with Protocol.
+        async for chunk in self.routing_table.get_provider_impl(model).chat_completion(
+            **params
         ):
             yield chunk