Chains is a new framework and SDK designed for high-performance workflows using multiple models and components. In practice, we've seen processin

Introducing Baseten Chains

submited by

Style Pass

2024-06-27 18:00:14

Chains is a new framework and SDK designed for high-performance workflows using multiple models and components. In practice, we've seen processing times halved and GPU utilization improved 6x for use cases like text-to-speech applications. Sign up and try it today or register for the webinar to learn more!

Today, we're excited to announce the beta release of Chains, a framework and SDK designed to simplify the creation and deployment of compound AI systems featuring multiple models and components. We’re committed to continuously evolving our platform to deliver the best performance, reliability, and efficiency for the sophisticated AI products our customers build. The release of Chains represents a giant leap forward in that commitment to enhancing the performance and efficiency of AI infrastructure.

When we first built the Truss framework, we wanted to simplify deploying and scaling models for real production use cases. Truss allowed AI engineers, data scientists, and MLOps teams to consistently serve different types of models using different frameworks in a reliable, performant, and secure manner. However, with the rise of compound AI systems and multimodal products, we knew we needed to evolve the framework to better facilitate workflows leveraging multiple models. Enter Chains.