Salesforce has implemented cross-Region inference routing in Amazon SageMaker AI to improve global-scale model serving and reliability. This feature allows Salesforce to add capacity securely while adhering to data residency commitments.
What happened
Salesforce has introduced cross-Region inference routing in Amazon SageMaker AI to address capacity and reliability issues in global-scale model serving. The new routing feature enables Salesforce to distribute traffic across multiple Regions, ensuring that capacity shortfalls do not turn into availability problems. This solution allows Salesforce to add capacity securely while maintaining data residency commitments. The cross-Region inference routing is generally available starting November 18, 2026, in all commercial Regions where inference is supported for real-time endpoints.
Source: Amazon Web Services
