add hpa docs

Author: LuyuZhang00

site/content/en/docs/examples/_index.md

@@ -5,3 +5,18 @@ weight: 6
 description: >
   This section contains examples of using LWS with or without specific inference runtime.
 ---
+
+This section provides practical examples of using LeaderWorkerSet (LWS) in various scenarios:
+
+## Infrastructure Examples
+
+- **[Horizontal Pod Autoscaler (HPA)](hpa/)** - Configure automatic scaling based on resource utilization
+
+## Inference Runtime Examples
+
+- **[vLLM](vllm/)** - Deploy distributed inference with vLLM on GPUs/TPUs
+- **[TensorRT-LLM](tensorrt-llm/)** - High-performance inference with TensorRT-LLM
+- **[SGLang](sglang/)** - Structured generation language inference
+- **[LlamaCPP](llamacpp/)** - CPU-based inference with LlamaCPP
+
+Each example includes detailed configuration files, deployment instructions, and best practices for production use.