Open sourceActive

BentoML

Unified Inference Platform for deploying and scaling AI models with production-grade reliability.

Field note

What it does

BentoML is a Unified Inference Platform for deploying and scaling AI models with production-grade reliability. It enables developers to build AI systems faster, scale efficiently, and maintain control over security.

Capabilities

Available capabilities

BentoML SDK Bento Build Options Bento Import Model Serving Client API Bento Export Bento Management BentoML CLI Framework APIs Deployment Bento and Model APIs Model Management Autoscaling

BentoML

What it does

Available capabilities

Tags

Ways to use it

Product features

Bento and model APIs ¶

Load models ¶

Manage Bentos ¶

Manage models ¶

Work with BentoCloud ¶