feat: use cuda_graph by default for vllm

[parthchadha]

What does this PR do ?

Enables cuda graph by default for vllm generation.
For llama-8b I am seeing 10-15% better generation speed compared to eager mode.

Issues

Closes #115.

Usage

• You can potentially add a usage example below

# Add a code snippet demonstrating how to use this 

Before your PR is "Ready for review"

Pre checks:

• Make sure you read and followed Contributor guidelines
• Did you write any new necessary tests?
• Did you run the unit tests and functional tests locally? Visit our Testing Guide for how to run tests
• Did you add or update any necessary documentation? Visit our Document Development Guide for how to write, build and test the docs.

Additional Information

• ...