aks-gpu-inference

aks-gpu-inference is a skill for Claude Code from Azure/AKS-Skills. It costs 206 tokens per session (1,335 once invoked), scanned A, original, MIT.

An operations guide for diagnosing GPU and machine-learning model workloads on Azure Kubernetes Service after they have been deployed.

In plain words
What is it for?
Use it to investigate pending GPU pods, missing GPU resources, CUDA or driver mismatches, model memory failures, quota errors, KAITO workspaces that are not ready, and GPU cost or scaling issues.
Why use it?
It helps trace why GPU workloads cannot start, from resource quotas and capacity through scheduling, drivers, and model memory problems.

Skill for Claude Code ✓ vendor

Written for Claude Code: shipped in a Claude Code plugin.

Part of the aks plugin — 8 skills, 1 MCP server shipped together

Good fit Use it to investigate pending GPU pods, missing GPU resources, CUDA or driver mismatches, model memory failures, quota errors, KAITO workspaces that are not ready, and GPU cost or scaling issues.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/azure/aks-skills/aks-gpu-inference
About the project

Azure/AKS-Skills is a collection of agent skills for operating Azure Kubernetes Service clusters after they are provisioned. It helps compatible coding agents investigate incidents, control costs, assess AKS Automatic readiness, run GPU and inference workloads, capture packet-level evidence, and design clusters. The catalogue entries provide the skills, MCP integration, and plugin configuration for these AKS operations.

Azure/AKS-Skills · 4 stars · on GitHub

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Azure/AKS-Skills --skill aks-gpu-inference
Clone the repo
git clone --depth 1 https://github.com/Azure/AKS-Skills

Made for: Claude Code.

Or install aks, the plugin that ships this one along with the rest of its 8 skills, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for aks-gpu-inference

README.md
[![agentmods](https://agentmods.dev/badge/skills/azure/aks-skills/aks-gpu-inference/github.svg)](https://agentmods.dev/skills/azure/aks-skills/aks-gpu-inference)
Your own site
<a href="https://agentmods.dev/skills/azure/aks-skills/aks-gpu-inference"><img src="https://agentmods.dev/badge/skills/azure/aks-skills/aks-gpu-inference/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for aks-gpu-inference

Your own site · 80×15
<a href="https://agentmods.dev/skills/azure/aks-skills/aks-gpu-inference"><img src="https://agentmods.dev/badge/skills/azure/aks-skills/aks-gpu-inference.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 206 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,335 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00206 $0.01335
Opus 5 $0.00103 $0.00668
Sonnet 5 $0.00041 $0.00267
Haiku 4.5 $0.00021 $0.00134

Measured 9d ago against content hash cdfb9caaf115, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

aks-gpu-inference scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **DCGM metrics port differs by install model.** AKS-**managed** GPU pools expose the DCGM exporter on **port 19400**; NVIDIA upstream / GPU-Operator use **9400**. A `curl localhost:9400/metrics` against a managed pool
skills/aks-gpu-inference/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AKS GPU & Inference (Day-2)

Operate and troubleshoot GPU and model-serving workloads on AKS after they exist. This is the failure → check → fix loop, not a setup guide — for enabling GPUs, KAITO, or a model runway, use azure-skills airunway-aks-setup.

Operating rules

  • Read-only by default. Diagnose and propose; do not scale, cordon, delete node pools, or delete KAITO Workspaces unless the user explicitly asks — deleting a Workspace has a cost trap (below).
  • Evidence before conclusion. GPU symptoms have layered causes (quota → capacity → scheduling → driver). Quote the event, node capacity, or condition that supports the root cause.

The four walls (check in this order)

Most "my GPU workload won't run" incidents are one of these, and they stack — clearing one exposes the next:

  1. GPU quota is 0 by default. Every N-series VM family starts at 0 vCPUs in every region, and quota is measured in vCPUs, not GPUs. Check: az vm list-usage --location <region> -o table and look for the family row (e.g. Standard NC Family vCPUs, Standard NCADSA100v4 Family vCPUs). Error signature: "Insufficient vCPU quota for Standard NCASv3_T4 Family…".
  2. Quota ≠ capacity ≠ SKU-eligibility. Even with quota, a region/zone can lack physical GPU capacity, and AKS gates some GPU SKUs behind a separate eligibility ticket. Check what's actually creatable: az vm list-skus --location <region> --resource-type virtualMachines -o table.
  3. The taint/toleration/nodeSelector triad. GPU pools use the convention taint sku=gpu:NoSchedule. A GPU pod must carry the matching toleration (key=sku, value=gpu, effect=NoSchedule), request nvidia.com/gpu: 1, and (by convention) select accelerator: nvidia. A missing toleration is the most common Pending cause after quota.
  4. No nvidia.com/gpu advertised on the node → a driver / device-plugin model mismatch. See the driver decision matrix in references/gpu-scheduling.md.

Read the full file on GitHub · 65 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 65 lines · 206 tokens per session scan A cdfb9caaf115

Subscribe to this mod's changes

aks-gpu-inference is a skill published in the GitHub repository Azure/AKS-Skills (4 stars, last pushed yesterday), licensed MIT. It adds 206 tokens to every session and 1,335 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

azure-storage-file-datalake-py

Azure Data Lake Storage Gen2 SDK for Python. Use for hierarchical file systems, big data analytics, and file/directory operations. Triggers: "data lake", "DataLakeServiceClient", "FileSystemClient", "ADLS Gen2", "hierarchical namespace".

microsoft/skills · 63 tokens

airunway-aks-setup

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…

microsoft/skills · 121 tokens

deploy-model

Unified Azure OpenAI model deployment skill with intelligent intent-based routing. Handles quick preset deployments, fully customized deployments (version/SKU/capacity/RAI policy), and capacity discovery across regions and projects. USE FOR: deploy model, deploy gpt, create deployment, model deployment, deploy openai…

jonathan-vella/apex-accelerator · 129 tokens

databricks-lakehouse-engineering-at-azure

Review and guide Databricks Lakehouse engineering on Azure: medallion architecture (bronze/silver/gold), Delta Lake pipelines, ADLS Gen2 access via Unity Catalog external locations and storage credentials, Access Connector managed identity, cluster access mode enforcement, AKV-backed secret scopes, VNet injection and…

VincentChuWaiChow/vanguard-frontier-agentic · 0 tokens

azure-cli

Operational skill for agents to manage Microsoft Azure via az CLI - subscriptions, resource groups, AKS, App Service, Key Vault, and RBAC hygiene.

alivirgo/Major-AI-Skills · 34 tokens

azure-cli

A command-line tool for managing Microsoft Azure, Microsoft's cloud platform, from a terminal. It covers account sign-in, subscriptions, resource groups, virtual machines, and other cloud resources.

chaterm/terminal-skills · 7 tokens