Fix tgi adapter (#796)

# What does this PR do?

- Fix TGI adapter

## Test Plan

<img width="851" alt="image"
src="https://github.com/user-attachments/assets/0084cbc6-6713-4079-b87b-0befd9aca0b0"
/>

- most inference working
- agent test failure due to model outputs

## 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/providers/remote/inference/tgi/config.py

@@ -15,10 +15,6 @@ class TGIImplConfig(BaseModel):
     url: str = Field(
         description="The URL for the TGI serving endpoint",
     )
-    api_token: Optional[SecretStr] = Field(
-        default=None,
-        description="A bearer token if your TGI endpoint is protected.",
-    )
 
     @classmethod
     def sample_run_config(cls, url: str = "${env.TGI_URL}", **kwargs):