Lepton AI

Lepton enables developers and enterprises to run AI applications efficiently in minutes, and at a production ready scale. It allows one to:

  • Build models in a python native way without needing to learn containers or Kubernetes,
  • Debug and test models locally, and deploy them to the cloud with a single command,
  • Consume models in any application with a simple, flexible API,
  • Choose heterogeneous hardware that best suits the application,
  • Scale up horizontally to handle large workloads.

If you are new to Lepton, we recommend you start with the Quickstart guide:

More resources you can check out are:

Our SDK codebase lives on GitHub. Whenever you have a question, feel free to file an issue.