Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
OctoAI: GenAI Inference Stack
Explore practical demos of building and scaling production-ready generative AI using OctoAI’s customizable inference stack, model mixing, and on-premise deployment.
Stop by the community demo pit to check out amazing demos from OctoAI! OctoAI is a cutting-edge AI infrastructure company that empowers developers to build and scale production-ready generative AI applications with ease. Their platform offers a customizable GenAI inference stack, allowing users to mix and match the latest optimized models and fine-tunes. With solutions like OctoStack, developers can deploy AI in their own environments, ensuring data privacy and reducing costs. OctoAI’s innovative approach to AI serving, rooted in technologies like XG Boost and TVM, provides unparalleled flexibility and performance for enterprises seeking AI independence.