ecs-genailisted

<!-- Note: ecs-genai intentionally ships no `apex:ecs-genai` steering command (eks-genai has one). This is an omission, not by design — steering-command wiring is deferred repo-wide, so it is left unwired for now to match the rest of the ECS skills. Freshness: instance/spec claims verified against live AWS docs 2026-07-10. --> # GenAI / GPU / ML Workloads on Amazon ECS End-to-end opinionated guidance for running GPU-accelerated, ML-training, and GenAI inference workloads on **Amazon ECS-on-EC2**. This skill is scoped to the compute-and-capacity mechanics that are unique to ECS: the GPU-optimized AMI + NVIDIA container runtime, the **one-homogeneous-ASG-per-GPU-type capacity-provider pattern** — cluster auto scaling *supports* multiple instance types in one ASG, but managed scaling has no instance weighting and bin-packs and protects on the **smallest** instance type, so mixing GPU types (with different GPU counts / VRAM) breaks the scaling math; one homogeneous ASG per GPU type is therefore the best practice, not a hard limit — plus EC2 Capacity Blocks for ML, AWS Neuron (Inferentia/Trainium) on ECS, container inference/serving, distributed ML, and accelerator observability. **The single most important constraint, stated first: AWS Fargate has no GPU support.** GPUs and AWS accelerators (Inferentia/Trainium) are available only on **ECS-on-EC2**, **ECS Managed Instances**, and **ECS Anywhere/External** — never on Fargate. Every GPU/ML answer on ECS begins by ruling Fargate