Skip to content
Skills Library
DevOps & cloud · Analysis

aks-gpu-inference

/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).

Repository
skills ↗
Licence
MIT
Last repository change
26.10.2026

Assessment and security

90/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content25 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
5
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 26.10.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

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).

Triggers from the description

Insufficient nvidia.com/gpu
Original author 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).

How it works

  1. Quick Reference
  2. When to Use This Skill
  3. MCP Tools
  4. Host Capability Gate
  5. Workflow
  6. Error Handling
Original SKILL.md headings · 61 lines, 334 words
SKILL.md preview
---
name: aks-gpu-inference
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)."
license: MIT
metadata:
  author: Microsoft
  version: "1.1.1"
---

# 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 |
Files in this package (5)
  • SKILL.md 3 KB
  • references/gpu-cost-and-scaling.md 2 KB
  • references/gpu-observability.md 3 KB
  • references/gpu-scheduling.md 3 KB
  • references/kaito-workspaces.md 2 KB

Versions

The database has no other skills named aks-gpu-inference.

Identical content appears in 3 other GitHub folders. We show one copy with the highest score.

Database snapshot: 13.11.2026 · package version 5c204450d330 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100tune-model-serving-aks
    Tune Model Serving AKS — optimize GPU utilization, quantization level, batch size, spot node pools, auto-scaling rules, cost per inference. Use when: tune, optimize, reduce cost.
  • 90nvidia-ai-operations-day2
    Use this skill when reviewing day-2 operations of NVIDIA GPU fleets — DCGM exporter and DCGM-Diag posture, GPU telemetry into Prometheus/Grafana, MIG partitioning lifecycle, GPU health and Xid error response, fleet upgrade paths, and incident response for GPU-failure modes.…
  • 93vram-radar
    GPU Radar answers which processes currently hold the GPU and VRAM, which model or job that memory belongs to, and whether another model can be started. Use when the user mentions VRAM, GPU usage, VRAM hogs, out-of-memory/OOM, how large a model still fits, freeing VRAM, which…
  • 90aks-troubleshooting
    Debug live Azure Kubernetes Service (AKS) incidents with a read-only, evidence-first investigation. WHEN: pod crashes or Pending, CrashLoopBackOff, OOMKilled, ImagePullBackOff, node NotReady, DNS or ingress failure, connectivity timeout, network policy, SNAT exhaustion,…
  • 100fai-build-kubernetes-manifest
    Generate Kubernetes manifests for AI workloads — GPU scheduling, health/readiness probes, autoscaling, resource limits, and rollout strategy. Use this skill when deploying to AKS/K8s, scheduling GPU pods, or configuring autoscaling — even if the user only says "deploy this to Kubernetes".
  • 100azure-aks-kubernetes-management
    Use this skill when provisioning, securing, and managing enterprise Kubernetes clusters on Azure AKS.

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.