Amazon SageMaker AI Keeps Your ML Inference Running Across Regions
Amazon SageMaker AI's cross-Region inference routing solves the headache of capacity shortfalls by automatically routing your inference requests across multiple AWS Regions and accounts through a single endpoint. The router smartly prefers your local Region but seamlessly redirects traffic when local capacity gets tight, keeping your ML workloads running without interruption.
source: [aws/machine-learning-blog]