Airunway Aks Setup

microsoft/github-copilot-for-azureOfficial

This walks you through setting up AI Runway on an existing AKS cluster in six sequential steps: verify your cluster context and GPU nodes, install the controller and CRDs, assess GPU compatibility for specific model requirements, pick and install an inference provider like KAITO or vLLM, deploy your first model, and confirm it's serving. It's designed for the full zero-to-running-model path rather than troubleshooting individual pieces. The GPU assessment step is genuinely helpful since it flags dtype and attention mechanism constraints before you waste time on an incompatible deployment. Just know this assumes you already have an AKS cluster with GPU nodes provisioned, and those A100 instances rack up $3 to $5 per hour.

GitHub stars: 217
last updated: Jun 11, 2026

View on GitHub

Install

$ npx -y skills add microsoft/github-copilot-for-azure --skill airunway-aks-setup --agent claude-code

Installs into .claude/skills of the current project.

Files

AI Runway AKS Setup

This skill walks users from a bare Kubernetes cluster to a running AI model deployment. Follow each step in sequence unless the user provides skip-to-step N to resume from a specific phase.

Cost awareness: GPU node pools incur significant compute charges (A100-80GB can cost $3–5+/hr). Confirm the user understands cost implications before provisioning GPU resources.

Prerequisites

This skill assumes an AKS cluster already exists. If the user does not have a cluster, hand off to the azure-kubernetes skill first to provision one (with a GPU node pool unless CPU-only inference is acceptable), then return here.

Quick Reference

Property	Value
Best for	End-to-end AI Runway onboarding on AKS
CLI tools	`kubectl`, `make`, `curl`
MCP tools	None
Related skills	`azure-kubernetes` (cluster setup), `azure-diagnostics` (baseline troubleshooting), optional `aks-gpu-inference` (existing GPU/inference Day-2 incidents only)