Self-Hosting on EKS, AKS, GKE

Running your own serving stack on managed Kubernetes: the GPU node reality, the engine deployment, and the day-2 work nobody budgets.

Content last verified 2026-09.

Lessons

1. Why Kubernetes at All
2. The Serving Stack
3. Scheduling GPUs
4. Day 2: The Work That Never Ends

Sources

• Kubernetes documentation — Schedule GPUs
• NVIDIA GPU Operator documentation
• AWS EC2 accelerated computing instance specifications
• Azure GPU-accelerated VM sizes (Microsoft Learn)
• Google Cloud GPU machine types