---

BentoML Documenation

BentoML is an open-source platform for machine learning model serving.

What does BentoML do?

• Turn your ML model into production API endpoint with just a few lines of code

• Support all major machine learning training frameworks

• High performance API serving system with adaptive micro-batching support

• DevOps best practices baked in, simplify the transition from model development to production

• Model management for teams, providing CLI and Web UI dashboard

• Flexible model deployment orchestration with support for AWS Lambda, SageMaker, EC2, Docker, Kubernetes, KNative and more

👉 Join BentoML Slack community to hear about the latest development updates.

---

• Getting Started
  • Installing BentoML
  • Hello World
  • From Model Training To Serving
  • Model Serving via REST API
  • Batch Serving via CLI
  • Containerize Model API Server
  • Deploy API server to the cloud
  • Distribute BentoService as a PyPI package
• Core Concepts
  • Creating BentoService
  • Defining Service Environment
  • Packaging Model Artifacts
  • API Function and Handlers
  • Saving BentoService
  • Model Management
• Advanced Guides
  • Offline Batch Serving
  • Monitoring with Prometheus
  • Request Logging
  • Adaptive Micro Batching
  • Adding Custom Model Artifact
  • Customizing BentoHandler
  • Model Management for Teams
• Deployment Guides
  • Deploying to AWS Lambda
  • Deploying to AWS SageMaker
  • Deploying to Clipper Cluster
  • Deploying to AWS ECS(Elastic Container Service)
  • Deploying to Google Cloud Run
  • Deploying to Azure Container Instance
  • Deploying to Kubernetes Cluster
  • Deploying to Knative
• API Reference
  • BentoService API
  • Model Artifacts
  • API Handlers
• CLI Reference
  • bentoml