Amazon Bedrock's Project Mantle represents a fundamental reimagining of how we serve generative AI inference at scale. Join AWS engineers as we unveil Mantle's architecture and take you behind the scenes, exploring how we've raised the bar on security, performance, and developer experience. We'll start with the why"-the technical and security challenges that drove us to build a next-generation inference engine operating at massive scale and global reach from the ground up-and how Mantle's design and architectural considerations are overcoming those challenges. Next we'll explore what Mantle means for you as a builder. You'll learn about OpenAI-compatible APIs for easy migration asynchronous inference for long-running tasks and practical considerations like inference tiers quota management and expanded regional availability. Finally we'll hear from a customer about real-world experience with open-weight models on Mantle including their value proposition and production use cases. Whether...