Agent Skills › microsoft/azure-skills › aks-gpu-inference

aks-gpu-inference

GitHub

用于诊断 AKS GPU 和 KAITO 故障，涵盖调度、VRAM/OOM、工作区就绪及自动扩缩容。通过只读证据分析，区分容器与设备故障，提供置信度评估及所有者交接建议，严禁未经授权的变更操作。

.github/plugins/aks-skills/skills/aks-gpu-inference/SKILL.md microsoft/azure-skills

触发场景

GPU Pod Pending Insufficient nvidia.com/gpu KAITO Workspace not ready model-load OOM GPU autoscaling issues

安装

npx skills add microsoft/azure-skills --skill aks-gpu-inference -g -y

更多选项

非标准路径

npx skills add https://github.com/microsoft/azure-skills/tree/main/.github/plugins/aks-skills/skills/aks-gpu-inference -g -y

不安装直接使用

npx skills use microsoft/azure-skills@aks-gpu-inference

指定 Agent (Claude Code)

npx skills add microsoft/azure-skills --skill aks-gpu-inference -a claude-code -g -y

安装 repo 全部 skill

npx skills add microsoft/azure-skills --all -g -y

预览 repo 内 skill

npx skills add microsoft/azure-skills --list

SKILL.md

Frontmatter

{
    "name": "aks-gpu-inference",
    "license": "MIT",
    "metadata": {
        "author": "Microsoft",
        "version": "1.1.1"
    },
    "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)."
}

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

Bind subscription, cluster, kube context, pool, and affected resource.
Capture exact events/status and observed gpuProfile; state which reads ran.
Route to scheduling, observability, KAITO, or scaling.
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.
For KAITO not-ready, warn that Workspace deletion leaves its GPU pools; cleanup is separate and needs explicit authorization.
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

版本历史

cf79ce8 当前 2026-10-19 11:53

元信息

文件数: 0
版本: bd001a3
Hash: 0968850f
收录时间: 2026-10-19 11:53

aks-gpu-inference