docs: redirect kubernetes installation page to ai-gateway guide (#603)

- Remove website/docs/installation/kubernetes.md
- Add redirect from /docs/installation/kubernetes to /docs/installation/k8s/ai-gateway
- Update all references to the old URL in documentation
- Install @docusaurus/plugin-client-redirects for handling redirects

Signed-off-by: bitliu <bitliu@tencent.com>

Author: Xunzhuo

README.md

@@ -23,7 +23,7 @@
 - [2025/10/15] We announced the [vLLM Semantic Router Dashboard](https://www.youtube.com/watch?v=E2IirN8PsFw) 🚀.
 - [2025/10/12] **Our paper** [When to Reason: Semantic Router for vLLM](https://arxiv.org/abs/2510.08731) accepted by NeurIPS 2025 MLForSys 🧠.
 - [2025/10/08] We announced the integration with [vLLM Production Stack](https://github.com/vllm-project/production-stack) Team 👋.
-- [2025/10/01] We supported to deploy on [Kubernetes](https://vllm-semantic-router.com/docs/installation/kubernetes/) 🌊.
+- [2025/10/01] We supported to deploy on [Kubernetes](https://vllm-semantic-router.com/docs/installation/k8s/ai-gateway) 🌊.
 - [2025/09/15] We reached 1000 stars on GitHub! 🔥
 - [2025/09/01] We released the project officially: [vLLM Semantic Router: Next Phase in LLM inference](https://blog.vllm.ai/2025/09/11/semantic-router.html) 🚀.
 

website/docs/installation/k8s/production-stack.md

@@ -93,7 +93,7 @@ kubectl get svc vllm-router-service
 
 ## Step 2: Deploy vLLM Semantic Router and point it at your vLLM router Service
 
-Follow the official guide from the official website with **the updated config file as the following**: [Install in Kubernetes](https://vllm-semantic-router.com/docs/installation/kubernetes).
+Follow the official guide from the official website with **the updated config file as the following**: [Install in Kubernetes](https://vllm-semantic-router.com/docs/installation/k8s/ai-gateway).
 
 Minimal sequence (same as the guide):
 

website/docs/installation/kubernetes.md

@@ -1502,7 +1502,7 @@ prompt_guard:
 
 - [Semantic Router Overview](https://vllm-semantic-router.com/docs/overview/semantic-router-overview/)
 - [System Architecture](https://vllm-semantic-router.com/docs/overview/architecture/system-architecture/)
-- [Kubernetes Deployment](https://vllm-semantic-router.com/docs/installation/kubernetes/)
+- [Kubernetes Deployment](https://vllm-semantic-router.com/docs/installation/k8s/ai-gateway)
 - [Distributed Tracing Support (PR #322)](https://github.com/vllm-project/semantic-router/pull/322)
 - [Milvus-based Semantic Caching](https://vllm-semantic-router.com/docs/features/semantic-caching/)
 

website/docs/proposals/nvidia-dynamo-integration.md

@@ -102,7 +102,7 @@ kubectl get svc vllm-router-service
 
 ## Step 2: Deploy vLLM Semantic Router and point it at your vLLM router Service
 
-Follow the official guide from the official website with **the updated config file as the following**: [Install in Kubernetes](https://vllm-semantic-router.com/docs/installation/kubernetes).
+Follow the official guide from the official website with **the updated config file as the following**: [Install in Kubernetes](https://vllm-semantic-router.com/docs/installation/k8s/ai-gateway).
 
 Remember to update the semantic router config to include your vLLM router service as an endpoint. Edit `deploy/kubernetes/config.yaml` and set `vllm_endpoints` like this (replace the IP/port with your router Service ClusterIP/port from step 1):
 

website/docs/tutorials/integration/production-stack-integration.md

@@ -67,6 +67,20 @@ const config: Config = {
     ],
   ],
 
+  plugins: [
+    [
+      '@docusaurus/plugin-client-redirects',
+      {
+        redirects: [
+          {
+            from: '/docs/installation/kubernetes',
+            to: '/docs/installation/k8s/ai-gateway',
+          },
+        ],
+      },
+    ],
+  ],
+
   themeConfig: {
     // Replace with your project's social card
     image: 'img/docusaurus-social-card.jpg',

website/docusaurus.config.ts

@@ -28,6 +28,7 @@
   ],
   "dependencies": {
     "@docusaurus/core": "^3.8.1",
+    "@docusaurus/plugin-client-redirects": "^3.8.1",
     "@docusaurus/preset-classic": "^3.8.1",
     "@docusaurus/theme-mermaid": "^3.8.1",
     "@mdx-js/react": "^3.1.0",