aks-gpu-inference

github:microsoft/azure-skills · first seen 2026-10-30 · source · badge

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 option

Works with

airunway-aks-setup
Shares gpu, kaito, airunway, aks
0.33
aks-troubleshooting
Shares aks, incidents, gpu, pod
0.24
aks-cost-optimization
Shares aks, incidents, cost, scaling
0.24

Used with

airunway-aks-setup
Shares gpu, kaito, airunway, aks
0.33
aks-cost-optimization
Shares aks, incidents, cost, scaling
0.24
aks-troubleshooting
Shares aks, incidents, gpu, pod
0.24
aks-network-capture
Shares aks, evidence, troubleshooting, host
0.22
aks-known-issues
Shares aks, insufficient, quota, troubleshooting
0.15

Skill Health 90 (freshness and quality) estimated by backskills

Listed, not yet scored. This skill has no public model test yet. It is in the scoring queue; submitted skills go first, then the most-installed.

Freshness 100 · Quality 80 · Efficacy not yet tested

Version history

2026-10-30T20:36:17 · sha256 0968850f574d