SpiditsOpen Live Timeline
Product Launch
Amazon SageMaker AI Async Inference now supports inline request payloads
Summary
Today, we're announcing inline payload support for Amazon SageMaker AI Async Inference. Customers can now send inference payloads directly in the request body o
Why It Matters
Broadens access to advanced AI capabilities for developers and end-users.
Referenced Coverage & Sources
Amazon SageMaker AI Async Inference now supports inline request payloads
AWS ML Blog•Jun 17, 2026
Building Supercharger: How Rocket Close optimized title operations with agentic AI
AWS ML Blog•Jun 12, 2026
Introducing container caching in Amazon SageMaker AI for faster model scaling
AWS ML Blog•Jun 16, 2026
Extract Data with On-demand and Batch Pipelines Dynamically
AWS ML Blog•Jun 11, 2026
From PDFs to insights: Architecting an intelligent document processing pipeline with AWS generative AI services
AWS ML Blog•Jun 12, 2026
Parallelize speculative decoding with P-EAGLE on Amazon SageMaker AI
AWS ML Blog•Jun 16, 2026
Track AI Developments
See model releases, funding rounds, and technical news on the live interactive timeline.