Data and AI releases

2,002 this month · 180 companies

Amazon SageMaker AI now detects rising response times, idle GPUs, and missed optimizations on your generative AI inference endpoints

UpdateNot yet verified

Amazon SageMaker AI introduced default monitoring on generative AI inference endpoints to automatically detect latency spikes, idle GPUs, and configuration optimization opportunities.

ObservabilityPerformance

Read on aws.amazon.com

Also shipped Nov 19, 2026AWS in November 2026 →

More from Amazon SageMakerEvery Amazon SageMaker release →