Salesforce launches cross-regional inference routing
The story so far
Salesforce deployed cross-regional inference routing in Amazon SageMaker AI, extending model services to over 30 global regions. It routes requests to the currently healthiest endpoint via a router, addressing availability issues caused by fragmented regional capacity. The router dynamically adjusts traffic allocation based on health checks and capacity signals, prioritizing local endpoints, keeping cross-regional traffic below 5%, and automatically falling back in case of failure, without requiring changes to existing application code.
AI-written from the reports · Updated 1 hour ago
Coverage timeline
Follow the coverage to see every side of the story.
- AWS Machine Learning BlogHow Salesforce is advancing global-scale model serving with cross-Region inference routing in Amazon SageMaker AI
Salesforce deployed cross-regional inference routing in Amazon SageMaker AI, extending model services to over 30 global regions. It routes requests to the currently healthiest endpoint via a router, addressing availability issues caused by fragmented regional capacity. The router dynamically adjusts traffic allocation based on health checks and capacity signals, prioritizing local endpoints, keeping cross-regional traffic below 5%, and automatically falling back in case of failure, without requiring changes to existing application code.
Heat over time
Not enough data yet to draw a trend.