Add Triton + TensorRT-LLM inference example

[ajaykrishnan23]

This example demonstrates how to deploy a high-performance LLM inference server using NVIDIA Triton Inference Server with TensorRT-LLM for optimized GPU inference.

Features:

• Triton Inference Server with Python backend
• TensorRT-LLM with PyTorch backend for Llama 3.2 3B Instruct
• Model Download to Persistent Storage to avoid redundant downloads
• Configurable sampling parameters (temperature, top_p, max_tokens)

The deployment uses an A10 GPU and exposes Triton's standard HTTP API on port 8000.