airunway-aks-setup
bymicrosoft· 555 skills
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\".
How to install airunway-aks-setup?
microsoft/azure-skills/airunway-aks-setup
$npx -y skills add microsoft/azure-skills --skill airunway-aks-setupInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Run `npx skills use "https://github.com/microsoft/azure-skills" --skill "microsoft/azure-skills/airunway-aks-setup"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/microsoft/azure-skills" that are relevant to the current task. Run `npx skills add "https://github.com/microsoft/azure-skills"` and select the relevant skills, then follow their instructions.
SKILL.md
| 1 | # AI Runway AKS Setup |
| 2 | |
| 3 | 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. |
| 4 | |
| 5 | > **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. |
| 6 | |
| 7 | ## Prerequisites |
| 8 | |
| 9 | 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. |
| 10 | |
| 11 | ## Quick Reference |
| 12 | |
| 13 | | Property | Value | |
| 14 | |----------|-------| |
| 15 | | Best for | End-to-end AI Runway onboarding on AKS | |
| 16 | | CLI tools | `kubectl`, `make`, `curl` | |
| 17 | | MCP tools | None | |
| 18 | | Related skills | `azure-kubernetes` (cluster setup), `azure-diagnostics` (troubleshooting) | |
| 19 | |
| 20 | ## When to Use This Skill |
| 21 | |
| 22 | Use this skill when the user wants to: |
| 23 | - Set up AI Runway on an existing AKS cluster from scratch |
| 24 | - Install the AI Runway controller and CRDs |
| 25 | - Assess GPU hardware compatibility for model deployment |
| 26 | - Choose and install an inference provider (KAITO, Dynamo, KubeRay) |
| 27 | - Deploy their first AI model to AKS via AI Runway |
| 28 | - Resume a partially-complete AI Runway setup from a specific step |
| 29 | |
| 30 | ## MCP Tools |
| 31 | |
| 32 | This skill uses no MCP tools. All cluster operations are performed directly via `kubectl` and `make`. |
| 33 | |
| 34 | ## Rules |
| 35 | |
| 36 | 1. Execute steps in sequence — load the reference for each step as you reach it |
| 37 | 2. Report cluster state at each step: ✓ healthy, ✗ missing/failed |
| 38 | 3. Ask for user confirmation before any install or deployment action |
| 39 | 4. If a step is already complete, report status and skip to the next step |
| 40 | 5. If the user provides `skip-to-step N`, start at step N; assume prior steps are complete |
| 41 | |
| 42 | ## Steps |
| 43 | |
| 44 | | # | Step | Reference | |
| 45 | |---|------|-----------| |
| 46 | | 1 | **Cluster Verification** — context check, node inventory, GPU detection | [step-1-verify.md](references/steps/step-1-verify.md) | |
| 47 | | 2 | **Controller Installation** — CRD + controller deployment | [step-2-controller.md](references/steps/step-2-controller.md) | |
| 48 | | 3 | **GPU Assessment** — detect GPU models, flag dtype/attention constraints | [step-3-gpu.md](references/steps/step-3-gpu.md) | |
| 49 | | 4 | **Provider Setup** — recommend and install inference provider | [step-4-provider.md](references/steps/step-4-provider.md) | |
| 50 | | 5 | **First Deployment** — pick a model, deploy, verify Ready | [step-5-deploy.md](references/steps/step-5-deploy.md) | |
| 51 | | 6 | **Summary** — recap, smoke test, next steps | [step-6-summary.md](references/steps/step-6-summary.md) | |
| 52 | |
| 53 | ## Error Handling |
| 54 | |
| 55 | | Error / Symptom | Likely Cause | Remediation | |
| 56 | |-----------------|--------------|-------------| |
| 57 | | No kubeconfig context | Not connected to a cluster | Run `az aks get-credentials` or equivalent | |
| 58 | | Controller in CrashLoopBackOff | Config or RBAC issue | `kubectl logs -n airunway-system -l control-plane=controller-manager --previous` | |
| 59 | | Provider not ready | Image pull or RBAC issue | `kubectl logs <pod-name> -n <namespace>` for the provider pod | |
| 60 | | ModelDeployment stuck in Pending | GPU scheduling failure or provider not ready | `kubectl describe modeldeployment <name> -n <namespace>` events | |
| 61 | | `bfloat16` errors at inference | T4 or V100 lacks bfloat16 support | Add `--dtype float16` to serving args | |
| 62 | |
| 63 | For full error handling and rollback procedures, see [troubleshooting.md](references/troubleshooting.md). |
Related
6 picksType
- azure-storageAzure Storage Services including Blob Storage, File Shares, Queue Storage, Table Storage, and Data Lake.Jul 2026
- azure-resource-lookupList, find, and show Azure resources across subscriptions or resource groups.Jul 2026
- azure-resource-visualizerAnalyze Azure resource groups and generate detailed Mermaid architecture diagrams showing the relationships between individual resources.Jul 2026
- azure-computeAzure VM/VMSS router. WHEN: create / provision / deploy / spin-up VM, recommend VM size, compare VM pricing, VMSS, scale set, autoscale, burstable, lightweight…Jul 2026
- azure-quotasCheck/manage Azure quotas and usage across providers. For deployment planning, capacity validation, region selection.Jul 2026
- azure-upgradeAssess and upgrade Azure workloads between plans, tiers, or SKUs, or modernize Azure SDK dependencies in source code.Jul 2026