skill
Aks Gpu Inference
Diagnose Day-2 AKS GPU and KAITO incidents using profile-aware, read-only evidence. WHEN: 'Insufficient nvidia.com/gpu', GPU pod Pending, model-load OOM, DCGM/VRAM, KAITO Workspace not ready, or GPU autoscaling. DO NOT USE FOR: setup (airunway-aks-setup), non-GPU incidents (aks-troubleshooting), standalone VM quota (azure-quotas), or generic cost (cost-analysis or cost-optimization from the optional azure-cost plugin).
About
# AKS GPU Inference Day-2
## Quick Reference
| Property | Value | |---|---| | Best for | AKS GPU/KAITO failures | | Evidence | Bound target, events/status, `gpuProfile`, DCGM |
## When to Use This Skill
Use for scheduling, VRAM/OOM, KAITO readiness, and workload scaling. Route exclusions as described above.
## MCP Tools
Use a fitting host-advertised Azure read or the references' read-only queries.
## Host Capability Gate
Before executing any referenced pipeline, verify that the host authorizes the required shell and `kubectl`/`az` commands against the bound target. File-backed collection also requires approved artifact storage and access to any bundled files it uses. A governed Azure CLI tool alone does not establish these capabilities. Equivalent host reads may replace commands only where their advertised schemas provide the required evidence.
If execution is unavailable or prohibited, say so and analyze supplied or redacted events, status, logs, and metrics, or give the operator a scoped collection plan. State which reads did not run and leave conclusions requiring missing evidence unconfirmed. Never route `kubectl` through Azure MCP or bypass host policy. The authorization requirements below still apply.
## Workflow
1. Bind subscription, cluster, kube context, pool, and affected resource. 2. Capture exact events/status and observed `gpuProfile`; state which reads ran. 3. Route to [scheduling](references/gpu-scheduling.md), [observability](references/gpu-observability.md), [KAITO](references/kaito-workspaces.md), or [scaling](references/gpu-cost-and-scaling.md). 4. Separate container/host OOM from device-allocation failures. For `OOMKilled`, correlate container memory limits/usage and node conditions. For Managed+Install device-memory evidence, use the exporter on port 19400 and incident-window `FB_USED`/`FB_FREE`; sizing tables do not establish a cause. 5. For KAITO not-ready, warn that Workspace deletion leaves its GPU pools; cleanup is separate and needs explicit authorization. 6. Report evidence, confidence, missing evidence, and owner handoff.
Require explicit authorization before scaling, cordon/drain, deletion, add-on enablement, or monitoring mutation.
## Error Handling
| Condition | Response | |---|---| | Missing/contradictory evidence | Mark unconfirmed; request the owner/read | | Unknown profile | Preserve evidence; do not prescribe stack repair | | Mutation required | Propose separately and wait for authorization |
Install
Run this command
git clone https://github.com/microsoft/azure-skills && cp -r azure-skills/.github/plugins/aks-skills/skills/aks-gpu-inference ~/.claude/skills/Works with
Manual steps
Clone the repository and copy the `.github/plugins/aks-skills/skills/aks-gpu-inference` folder into your Claude skills directory. Compatible with Claude Code, Cursor, Codex, and any Agent Skills-compatible agent.
Frequently asked questions
What is the Aks Gpu Inference skill?
Diagnose Day-2 AKS GPU and KAITO incidents using profile-aware, read-only evidence. WHEN: 'Insufficient nvidia.com/gpu', GPU pod Pending, model-load OOM, DCGM/VRAM, KAITO Workspace not ready, or GPU autoscaling. DO NOT USE FOR: setup (airunway-aks-setup), non-GPU incidents (aks-troubleshooting), standalone VM quota (azure-quotas), or generic cost (cost-analysis or cost-optimization from the optional azure-cost plugi…
How do I install Aks Gpu Inference?
Run this in your terminal:
git clone https://github.com/microsoft/azure-skills && cp -r azure-skills/.github/plugins/aks-skills/skills/aks-gpu-inference ~/.claude/skills/Which AI tools does Aks Gpu Inference work with?
It works with claude_app, claude_code, claude_api, cursor, codex, windsurf, cline, zed.
Who made Aks Gpu Inference?
Microsoft, released under the MIT license.
Is Aks Gpu Inference free?
Yes, it is free to use under the MIT license.
npx skills add microsoft/azure-skills
npx skills add prime-skills/runcomfy-agent-skills
npx skills add genmedia-labs/skills
npx skills add genmedia-labs/skills
npx skills add anthropics/skills
git clone https://github.com/microsoft/azure-skills && cp -r azure-skills/.github/plugins/aks-skills/skills/aks-troubleshooting ~/.claude/skills/
Audit before you install
Run any source through our checks - AI visibility, security, performance, and stack detection.
AI Agent / MCP Server Tester
ai testing
Automated Web Security Scan
security
AI Content Quality Test
arabic content
Site Stack Detector
migration
PageSpeed Analyzer
performance
AI SEO / AEO / GEO Audit
ai visibility
llms.txt Generator
ai visibility
Schema / JSON-LD Builder
ai visibility
Readability Score
arabic content
AI Cost Calculator
ai testing
Headline Analyzer
arabic content