AutoGineer
Generated banner for Airunway Aks Setup
Generated logo for Airunway Aks Setup

Airunway Aks Setup

MicrosoftOfficialCreated by Microsoft

  • Skill
  • Workflow
  • Cloud and DevOps
  • MIT
  • No issues found
Download ZIP

From the author

Set 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".
— the description by Microsoft

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

The AI Runway AKS Setup skill provides a structured, step-by-step process to onboard AI Runway onto an existing AKS cluster. It guides users from initial cluster verification and GPU hardware assessment through controller installation, inference provider selection, and the deployment of their first AI model. The skill includes built-in compatibility checks for GPU types and model sizing recommendations to ensure successful inference deployments.

What it does

  • Verifies existing AKS cluster health and GPU node inventory.
  • Installs the AI Runway controller and necessary CRDs.
  • Assesses GPU hardware compatibility and constraints.
  • Configures and installs inference providers like KAITO, Dynamo, or KubeRay.
  • Deploys and verifies the initial AI model serving instance.
  • Provides troubleshooting guidance for common deployment and scheduling errors.

When to use it

  • When you need to set up AI Runway on an existing AKS cluster from scratch.
  • When you need to assess if your current GPU hardware supports specific model requirements.
  • When you want to deploy a model using an inference provider on AKS.
  • When you need to resume a partially completed AI Runway installation.

Advantages

  • Ensures a logical, sequential setup process for complex AI infrastructure.
  • Includes hardware-specific compatibility warnings for GPU types like T4 and V100.
  • Provides clear model sizing and VRAM estimation guidance.
  • Offers built-in error handling and troubleshooting steps for common AKS issues.
  • Supports flexible resumption of setup via skip-to-step functionality.

Usage examples

“I need to set up AI Runway on my AKS cluster.”
The agent initiates the step-by-step onboarding process, starting with cluster verification.
“Can you help me deploy a model to AKS using AI Runway?”
The agent guides you through the controller installation, provider setup, and final model deployment steps.
“Skip to step 4 for AI Runway setup.”
The agent skips the initial verification and installation steps and begins directly with the inference provider setup.

Install

  1. Download the skill as a ZIP:

    https://autogineer.com/agent-skills/microsoft/airunway-aks-setup/download

  2. Unzip it into the cross-client skills folder of your project:

    mkdir -p .agents/skills && unzip airunway-aks-setup.zip -d .agents/skills

Documentation by Microsoft

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

PropertyValue
Best forEnd-to-end AI Runway onboarding on AKS
CLI toolskubectl, make, curl
MCP toolsNone
Related skillsazure-kubernetes (cluster setup), azure-diagnostics (baseline troubleshooting), optional aks-gpu-inference (existing GPU/inference Day-2 incidents only)

When to Use This Skill

Use this skill when the user wants to:

  • Set up AI Runway on an existing AKS cluster from scratch

  • Install the AI Runway controller and CRDs

  • Assess GPU hardware compatibility for model deployment

  • Choose and install an inference provider (KAITO, Dynamo, KubeRay)

  • Deploy their first AI model to AKS via AI Runway

  • Resume a partially-complete AI Runway setup from a specific step

GPU setup versus Day-2 incidents

Keep initial GPU node-pool, provider, controller, and model setup in this skill. For an incident affecting an existing GPU or inference deployment, load optional-gpu-day2.md before deciding whether to offer the focused optional add-on.

MCP Tools

This skill uses no MCP tools. All cluster operations are performed directly via kubectl and make.

Rules

  1. Execute steps in sequence — load the reference for each step as you reach it

  2. Report cluster state at each step: ✓ healthy, ✗ missing/failed

  3. Ask for user confirmation before any install or deployment action

  4. If a step is already complete, report status and skip to the next step

  5. If the user provides skip-to-step N, start at step N; assume prior steps are complete

Steps

#StepReference
1Cluster Verification — context check, node inventory, GPU detectionstep-1-verify.md
2Controller Installation — CRD + controller deploymentstep-2-controller.md
3GPU Assessment — detect GPU models, flag dtype/attention constraintsstep-3-gpu.md
4Provider Setup — recommend and install inference providerstep-4-provider.md
5First Deployment — pick a model, deploy, verify Readystep-5-deploy.md
6Summary — recap, smoke test, next stepsstep-6-summary.md

Error Handling

Error / SymptomLikely CauseRemediation
No kubeconfig contextNot connected to a clusterRun az aks get-credentials or equivalent
Controller in CrashLoopBackOffConfig or RBAC issuekubectl logs -n airunway-system -l control-plane=controller-manager --previous
Provider not readyImage pull or RBAC issuekubectl logs <pod-name> -n <namespace> for the provider pod
ModelDeployment stuck in PendingGPU scheduling failure or provider not readykubectl describe modeldeployment <name> -n <namespace> events
bfloat16 errors at inferenceT4 or V100 lacks bfloat16 supportAdd --dtype float16 to serving args

For full error handling and rollback procedures, see troubleshooting.md.

Files

references/model-sizing.md

Model Sizing & Starter Recommendations

VRAM Sizing Guide

Estimate how much VRAM a model requires. Values are weights only — add 20–30% overhead for KV cache and activations during inference.

Parametersfloat16 / bfloat16int8int4 / GGUF Q4
1B~2 GB~1 GB~0.5 GB
3B~6 GB~3 GB~1.5 GB
7–8B~14–16 GB~7–8 GB~3.5–4 GB
13B~26 GB~13 GB~6.5 GB
34B~68 GB~34 GB~17 GB
70B~140 GB~70 GB~35 GB

Example: 4× A100 80 GB = 320 GB total. Llama-3.1-70B at bfloat16 ≈ 168 GB with overhead — fits across 4 GPUs with tensor parallelism.

Starter Model Recommendations

Cluster CapacityModelProviderNotes
CPU-onlygoogle/gemma-3-1b-it-qat-q8_0-ggufKAITO (llama.cpp)GGUF Q8; runs on CPU
1× T4 (16 GB)microsoft/Phi-3-mini-4k-instructKAITO (vLLM)~8 GB float16; fits with headroom
1× A10G/L4 (24 GB)meta-llama/Llama-3.1-8B-InstructKAITO (vLLM)~16 GB bfloat16; gated — needs HF token
1× A100 40 GBmicrosoft/Phi-3-medium-128k-instructKAITO (vLLM)~28 GB float16; non-gated; MIT license
1× A100 80 GB / H100meta-llama/Llama-3.1-8B-InstructKAITO (vLLM)Oversized; upgrade to 70B if more GPUs available
4× A100 80 GBmeta-llama/Llama-3.1-70B-InstructKAITO (vLLM, TP)~168 GB; tensor parallelism; gated
Gated Models

These models are gated on HuggingFace and require an access token:

  • meta-llama/Llama-3.1-8B-Instruct

  • meta-llama/Llama-3.1-70B-Instruct

Non-gated alternatives (no token required):

  • microsoft/Phi-3-mini-4k-instruct (MIT license)

  • microsoft/Phi-3-medium-128k-instruct (MIT license)

  • google/gemma-3-1b-it-qat-q8_0-gguf (Gemma license)

Requirements and compatibility

Written for: Claude Code

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Needs: Claude Code frontmatter, Needs Node.js

Security

No issues found by our static scan· No issues found

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Attribution and licence

Created by
Microsoft
Publisher
Microsoft (Official)
Source
microsoft/skills · .github/plugins/azure-skills/skills/airunway-aks-setup · commit 0696600
Licence
MIT License (redistribution allowed)
  • LICENSE (added by AutoGineer from .github/plugins/azure-skills/LICENSE)
  • ATTRIBUTION.md (written by AutoGineer)
Synced
Also distributed in
microsoft/azure-skills

AutoGineer is not affiliated with or endorsed by Microsoft or Microsoft.

Download ZIP

The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download airunway-aks-setup.zip