Understand this story
AWS has launched Amazon SageMaker AI cross-Region inference routing, which can redirect new requests to registered targets in other AWS Regions or accounts when local Region capacity is insufficient or an endpoint experiences an issue, then gradually shift traffic back after recovery. The feature supports real-time and asynchronous inference; each router can contain up to 20 routing targets, and each target can contain up to 10 destinations, but response streaming is not supported. The feature is now generally available in most commercial AWS Regions, with no additional charge for routing itself.
AI-generated from public reports
Latest development · Report
Amazon SageMaker AI Introduces Cross-Region Inference RoutingDevelopments
1 confirmed developments
- Source:AWS Machine Learning
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Nov 20
AWS Machine LearningFirst-party
Amazon SageMaker AI Introduces Cross-Region Inference Routing
Amazon SageMaker AI has introduced cross-region inference routing, which can redirect new requests to registered targets in other AWS Regions or accounts when local Region capacity is insufficient or an endpoint experiences an issue, then gradually fail back after recovery. The feature supports real-time and asynchronous inference. Each router can include up to 20 routing targets, and each target can include up to 10 destinations, but response streaming is not supported. The feature is now generally available in most commercial AWS Regions, with no additional charge for routing itself.
AI Trends