AI Runway AKS Setup
Skill AktivSet up AI Runway on AKS — from bare cluster to running model. Covers cluster verification, controller install, GPU assessment, provider setup, and first deployment. WHEN: "setup AI Runway", "onboard AKS cluster", "install AI Runway", "airunway setup", "deploy model to AKS", "GPU inference on AKS", "KAITO setup on AKS", "run LLM on AKS", "vLLM on AKS", "set up model serving on AKS", "AI Runway controller".
To provide a guided, step-by-step process for users to deploy and run AI models using AI Runway on AKS, from a bare cluster to a fully operational inference environment.
Funktionen
- Cluster verification and node inventory
- AI Runway controller and CRD installation
- GPU hardware assessment and compatibility checks
- Inference provider recommendation and installation (KAITO, Dynamo, KubeRay)
- Model deployment with gated and non-gated model support
- Interactive prompt for sensitive credentials (HuggingFace token)
Anwendungsfälle
- Setting up a new AI Runway environment on AKS from scratch.
- Onboarding an existing AKS cluster for AI model serving.
- Deploying the first AI model to AKS using AI Runway.
- Troubleshooting and resuming a partially complete AI Runway setup.
Nicht-Ziele
- Provisioning the AKS cluster itself (delegates to `azure-kubernetes` skill).
- Managing Kubernetes cluster networking or ingress beyond basic setup.
- Advanced AI Runway configuration or custom provider development.
- Managing AI models beyond the initial deployment and verification.
Voraussetzungen
- Existing AKS cluster
- kubectl installed and configured
- make installed
- curl installed
Trust
- warning:Issues Attention19 issues opened and 11 closed in the last 90 days indicates a closure rate of approximately 37%, suggesting maintainers are responsive but could improve closure speed.
Installation
Zuerst Marketplace hinzufügen
/plugin marketplace add microsoft/skills/plugin install azure-skills@skillsQualitätspunktzahl
Vertrauenssignale
Ähnliche Erweiterungen
Render Deploy
99Deploy applications to Render by analyzing codebases, generating render.yaml Blueprints, and providing Dashboard deeplinks. Use when the user wants to deploy, host, publish, or set up their application on Render's cloud platform.
Cloudflare Deploy
99Deploy applications and infrastructure to Cloudflare using Workers, Pages, and related platform services. Use when the user asks to deploy, host, publish, or set up a project on Cloudflare.
Azure Kubernetes
98Plan, create, and configure production-ready Azure Kubernetes Service (AKS) clusters. Covers Day-0 checklist, SKU selection (Automatic vs Standard), networking options (private API server, Azure CNI Overlay, egress configuration), security, and operations (autoscaling, upgrade strategy, cost analysis). WHEN: create AKS environment, provision AKS environment, enable AKS observability, design AKS networking, choose AKS SKU, secure AKS, optimize AKS, rightsize AKS pod, AKS spot nodes, AKS cluster-autoscaler.
Hybrid Cloud Networking
100Configure secure, high-performance connectivity between on-premises infrastructure and cloud platforms using VPN and dedicated connections. Use when building hybrid cloud architectures, connecting data centers to cloud, or implementing secure cross-premises networking.
Cloud Architect
100Designs cloud architectures, creates migration plans, generates cost optimization recommendations, and produces disaster recovery strategies across AWS, Azure, and GCP. Use when designing cloud architectures, planning migrations, or optimizing multi-cloud deployments. Invoke for Well-Architected Framework, cost optimization, disaster recovery, landing zones, security architecture, serverless design.
Firebase Firestore
100Sets up, manages, and executes queries against Cloud Firestore database instances. You MUST unconditionally activate this skill if you plan to use Firestore in any way. Use when listing or creating Firestore databases, configuring security rules, designing data models, writing client SDK queries, or checking indexes.