update tensor-rt llm in enum

[ian-scale]

Pull Request Summary

What is this PR changing? Why is this change being made? Any caveats you'd like to highlight? Link any relevant documents, links, or screenshots here if applicable.
adds tensorrt-llm to enum for valid inference frameworks. currently Model.list() is broken due to the addition of endpoints that use tensorrt-llm as an inference framework when this framework isn't an option in the client.

Ex:

ValidationError: 1 validation error for ListLLMEndpointsResponse
model_endpoints -> 13 -> inference_framework
  value is not a valid enumeration member; permitted: 'deepspeed', 'text_generation_inference', 'vllm', 'lightllm' (type=type_error.enum; enum_values=[<LLMInferenceFramework.DEEPSPEED: 'deepspeed'>, <LLMInferenceFramework.TEXT_GENERATION_INFERENCE: 'text_generation_inference'>, <LLMInferenceFramework.VLLM: 'vllm'>, <LLMInferenceFramework.LIGHTLLM: 'lightllm'>])

Test Plan and Usage Guide

How did you validate that your PR works correctly? How do you run or demo the code? Provide enough detail so a reviewer can reasonably reproduce the testing procedure. Paste example command line invocations if applicable.

[yixu34]

Any tests to update?

[ian-scale]

Any tests to update?
no tests to update, but we may want to create something that tests this issue since we've seen it before.