# Aks Gpu Inference

Diagnose Day-2 AKS GPU and KAITO incidents using profile-aware, read-only evidence.

- Repository: https://github.com/microsoft/skills (3164 stars)
- Category: DevOps
- License: MIT
- Last updated: 2026-11-01
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add microsoft/skills --skill aks-gpu-inference -g -a claude-code -y`
Codex: `npx skills add microsoft/skills --skill aks-gpu-inference -g -a codex -y`
Cursor: `npx skills add microsoft/skills --skill aks-gpu-inference -g -a cursor -y`
Gemini CLI: `npx skills add microsoft/skills --skill aks-gpu-inference -g -a gemini-cli -y`
Claude Code plugin marketplace: `/plugin marketplace add microsoft/skills`

## Description

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).

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# 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

The rest: https://github.com/microsoft/skills/blob/HEAD/.github/plugins/aks-skills/skills/aks-gpu-inference/SKILL.md