fix vllm template (#813)

# What does this PR do?

- Fix vLLM template to resolve
https://github.com/meta-llama/llama-stack/issues/805
- Fix agents test with shields

## Test Plan

```
vllm serve meta-llama/Llama-3.1-8B-Instruct
VLLM_URL="http://localhost:8000/v1" INFERENCE_MODEL="meta-llama/Llama-3.1-8B-Instruct" llama stack run ./llama_stack/templates/remote-vllm/run.yaml
```

```
LLAMA_STACK_BASE_URL=http://localhost:8321 pytest -v ./tests/client-sdk/
```

<img width="1245" alt="image"
src="https://github.com/user-attachments/assets/9af27684-5a9c-4187-b338-cbfc5211bd99"
/>


- custom tool flaky due to model outputs
- /completions API not implemented

**Vision Model**
- 11B-Vision-Instruct
<img width="1240" alt="image"
src="https://github.com/user-attachments/assets/1d3b3b17-fa09-43a7-b56c-3f77263825c5"
/>


## Sources

Please link relevant resources if necessary.


## Before submitting

- [ ] This PR fixes a typo or improves the docs (you can dismiss the
other checks if that's the case).
- [ ] Ran pre-commit to handle lint / formatting issues.
- [ ] Read the [contributor
guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md),
      Pull Request section?
- [ ] Updated relevant documentation.
- [ ] Wrote necessary unit or integration tests.

llama_stack/templates/remote-vllm/vllm.py

@@ -27,6 +27,9 @@ def get_distribution_template() -> DistributionTemplate:
         "memory": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
         "safety": ["inline::llama-guard"],
         "agents": ["inline::meta-reference"],
+        "eval": ["inline::meta-reference"],
+        "datasetio": ["remote::huggingface", "inline::localfs"],
+        "scoring": ["inline::basic", "inline::llm-as-judge", "inline::braintrust"],
         "telemetry": ["inline::meta-reference"],
         "tool_runtime": [
             "remote::brave-search",