BentoML

Open-source platform for building AI inference APIs

Code & DevelopmentFreemium

BentoML is an open-source platform for packaging and deploying machine learning models as production-ready inference APIs. It supports all major ML frameworks and provides a unified interface for serving models locally, on Kubernetes, or via BentoCloud. ML engineers use BentoML to standardize model serving and reduce deployment complexity.

Key Features

• ✓ML model serving framework
• ✓Multi-framework support
• ✓Docker and Kubernetes deployment
• ✓BentoCloud managed service
• ✓Adaptive batching