aks-gpu-inference

原文涵盖的主题

• AKS GPU Inference Day-2
• Quick Reference
• When to Use This Skill
• MCP Tools
• Host Capability Gate
• Workflow
• Error Handling

| Property | Value | |---|---| | Best for | AKS GPU/KAITO failures | | Evidence | Bound target, events/status, gpuProfile, DCGM | Use for scheduling, VRAM/OOM, KAITO readiness, and workload scaling. Route exclusions as described above. Use a fitting host-advertised Azure read or the references' read-only queries. 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. 1. Bind subscription, cluster, kube context, pool, and affected resource. 2. Capture exac

这里只展示节选，请以完整原文和当前要求为准。