OctoML Unveils Self-Optimizing Compute Service for Generative AI Innovation

OctoML launches OctoAI, a self-optimizing compute service for AI that helps businesses build ML-based applications and put them into production without having to worry about the underlying infrastructure. Users simply decide what they want to prioritize and OctoAI will automatically choose the right hardware for them, optimizing models and deciding whether it’s best to run them on Nvidia GPUs or AWS’s Inferentia machines. The service offers accelerated versions of popular foundation models and is focused on generative AI.