Update and simplify CodeGen tutorials

[alexsin368]

• Remove steps to build images: just use docker compose to pull images instead
• Add steps for running with vLLM and TGI
• Update steps to validate microservices, including newly added dataprep
• Remove extra UI options, only need to show the default one for Gradio
• Update steps for port forwarding and changing BACKEND_SERVICE_IP for UI to work
• Fix grammar and improve wording

[Copilot]

Pull Request Overview

This PR simplifies and updates the CodeGen tutorial deployment guides by removing redundant steps and improving the clarity of instructions. Key changes include updated port forwarding examples, revised deployment commands for both vLLM and TGI services, and improved language and grammar throughout the tutorials.

Reviewed Changes

Copilot reviewed 2 out of 3 changed files in this pull request and generated 2 comments.

File	Description
tutorial/CodeGen/deploy/xeon.md	Revised instructions, fixed grammar issues, and updated commands for deploying on Xeon.
tutorial/CodeGen/deploy/gaudi.md	Updated deployment steps and commands for Gaudi deployments, with updated model details.

Files not reviewed (1)

• tutorial/CodeGen/CodeGen_Guide.rst: Language not supported

[mkbhanda]

Please do a quick check for consistency/recommendation on model (7B versus 32B) for Xeon versus Gaudi. Also add a recommendation on instance size so user will be successful in running the application.

[alexsin368]

addressed all comments

[alexsin368]

addressed comments

[mkbhanda]

LGTM