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.
npx -y skills add microsoft/github-copilot-for-azure --skill airunway-aks-setup --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
sickn33/antigravity-awesome-skills
kubesphere/kubesphere
supercent-io/skills-template