updated the inference file

Merge branch 'main' of https://github.com/Mohith202/Transformer_hackathon

FEAT: " Added for BOth GPU and CPU utilization with thermal control and best allocation."

updated inference py file

added uv.lock file

restructed the application file

Updated README.md

added yaml and toml file for HF

added validation script and reduced the step due to MAX API limit

feat: implement cloud resource management environment and LLM-based inference pipeline

Initial commit