Fast, lightweight, portable, rust-powered, and OpenAI compatible. We work with cloud providers, especially edge cloud/CDN compute providers, to support microservices for web apps. Use cases include AI inference, database access, CRM, ecommerce, workflow management, and server-side rendering. We work with streaming frameworks and databases to support embedded serverless functions for data filtering and analytics. The serverless functions could be database UDFs. They could also be embedded in data ingest or query result streams. Take full advantage of the GPUs, write once, and run anywhere. Get started with the Llama 2 series of models on your own device in 5 minutes. Retrieval-argumented generation (RAG) is a very popular approach to building AI agents with external knowledge bases. Create an HTTP microservice for image classification. It runs YOLO and Mediapipe models at native GPU speed.