Railway Infrastructure
Guides Railway projects, services, databases, deployments, environment variables, domains, observability, and troubleshooting.
Investigate GPU and KAITO incidents on AKS using read-only evidence, including scheduling failures and memory pressure.
Investigate GPU and KAITO incidents on AKS using read-only evidence, including scheduling failures and memory pressure.
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).
9287b440968850f574d452300a063c8b73f708a1cc54a7ba6adc103ce3c5a601f1a3f3eThis record comes from the publisher's repository. The skill and supporting files have not undergone a security audit. Review the contents and required permissions before installing.
Read the selection policynpx skills add 'https://github.com/microsoft/skills/tree/9287b443662d2433c85621c7325ee72a0ce499b5/.github/plugins/aks-skills/skills/aks-gpu-inference' -a claude-codeRequires Node.js 22.20 or later. The command targets the catalog's pinned revision.
Other agents may require an external tool or adaptation.
The ZIP includes the entire repository and its supporting files.