feat: Deploy Gradio UI App as a k8s deployment and service for stable diffusion inference

[ratnopamc]

What does this PR do?

• Containerizes the Gradio UI App
• Model endpoint and Service endpoint are passed an envs
• Deploys the app as a deployment and exposes it as a service on EKS
• Restructures the rayserve blueprints under inference

🛑 Please open an issue first to discuss any significant work and flesh out details/direction - we would hate for your time to be wasted.
Consult the CONTRIBUTING guide for submitting pull-requests.

Motivation

With this, users no longer need to have access to a local python environment and no longer needs to install python dependencies locally.

More

• Yes, I have tested the PR using my local account setup (Provide any test evidence report under Additional Notes)
• Mandatory for new blueprints. Yes, I have added a example to support my blueprint PR
• Mandatory for new blueprints. Yes, I have updated the website/docs or website/blog section for this feature
• Yes, I ran pre-commit run -a with this PR. Link for installing pre-commit locally

For Moderators

• E2E Test successfully complete before merge?

Additional Notes

[vara-bonthu]

Thank you for the update on the Gradio UI deployment. I've noted a few small points for consideration. Additionally, I noticed that the folder path for Llama2 inference has been altered. Could you please ensure the Llama2 documentation is updated to reflect this change? The specific document can be found here:

data-on-eks/website/docs/gen-ai/inference/Llama2.md

Line 157 in a38b7ba

cd ai-ml/trainium-inferentia/examples/ray-serve/llama2-inf2

.