-
Notifications
You must be signed in to change notification settings - Fork 296
Closed
Labels
documentationImprovements or additions to documentationImprovements or additions to documentationenhancementNew feature or requestNew feature or request
Description
Description
Create a new installation guide for deploying vLLM Semantic Router with Gateway API Inference Extension on Kubernetes.
Requirements
-
Create new documentation file:
- Path:
website/docs/installation/k8s/gateway-api-inference-extension.md - Follow the same structure and format as
ai-gateway.md
- Path:
-
Content Requirements:
- Architecture overview section
- Prerequisites (kind, kubectl, Helm)
- Step-by-step installation using Helm
- Use GHCR OCI registry for semantic router:
oci://ghcr.io/vllm-project/charts/semantic-router - All resource paths must use remote GitHub URLs:
https://raw.githubusercontent.com/vllm-project/semantic-router/refs/heads/main/... - Testing section with example curl commands
- Troubleshooting section
- Cleanup section using helm uninstall commands
-
Integration with Gateway API Inference Extension:
- Document how to install Gateway API CRDs
- Document how to install Inference Extension
- Show how to configure semantic router to work with the extension
- Include example Gateway API resources
Reference Documentation
- Follow the same structure as:
website/docs/installation/k8s/ai-gateway.md - Gateway API Inference Extension docs: https://gateway-api-inference-extension.sigs.k8s.io/guides/
- Existing Istio guide mentions the extension:
website/docs/installation/k8s/istio.md(line 87)
Files to Create
website/docs/installation/k8s/gateway-api-inference-extension.md
Acceptance Criteria
- New documentation file created with complete installation guide
- Uses Helm-based installation for semantic router
- All resource references use remote GitHub URLs
- Includes architecture overview and benefits
- Includes testing and troubleshooting sections
- Cleanup section uses helm uninstall commands
- Documentation follows the same pattern as ai-gateway.md
- All commands are tested and working
Metadata
Metadata
Assignees
Labels
documentationImprovements or additions to documentationImprovements or additions to documentationenhancementNew feature or requestNew feature or request