aks-gpu-inference SKILL.md skillA
aks-gpu-inference from azure/aks-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add azure/aks-skills/aks-gpu-inference@v1.0.0Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- azure/aks-skills
- Path
skills/aks-gpu-inference/SKILL.md- Versions recorded
- 2
- Latest version
- v1.0.0, committed Aug 24, 2026
- First version recorded
- Jul 30, 2026
- Size
- 5,190 bytes
- Repository stars
- 6
- License
- MIT
Day-2 operations for GPU and model-inference workloads on Azure Kubernetes Service (AKS): diagnose GPU pods stuck Pending, missing nvidia.com/gpu, CUDA/driver mismatches, model OOM on weight load, GPU vCPU-quota failures, KAITO (AI toolchain operator) Workspaces stuck not-ready, and GPU cost / scale-to-zero / spot eviction. WHEN: GPU pod Pending 'Insufficient nvidia.com/gpu', no nvidia.com/gpu on node, CUDA driver version insufficient, model OOMKilled loading weights, GPU node pool quota…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# 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…"*. …
Read the whole file at its exact version.
How to install
mdr add azure/aks-skills/aks-gpu-inference@sha256:cdfb9caaf115cd7bThe line at the top of this page pins the label v1.0.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_3nqs3bnesfp4pk26)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Jul 30, 2026 and Aug 24, 2026, about one every 24 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.0.0 latest | 2026-08-24 | e076860 | 5,190 B | A | view · diff |
| v1.0.0 | 2026-07-30 | 98380bb | 5,283 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (5190 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
azure/aks-skills · 6 stars · license MIT · pushed 2026-09-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_3nqs3bnesfp4pk26 GET https://markdownregistry.com/api/v1/resolve?ref=azure/aks-skills/aks-gpu-inference GET https://markdownregistry.com/api/v1/blob/cdfb9caaf115cd7be7795362a296f6e0444487fee222f7d3b87dbd1d22e746b5
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from azure/aks-skills
Every file in azure/aks-skills