---

The easiest way to build Machine Learning APIs

• Package models trained with any ML frameworks and reproduce them for model serving in production

• Deploy anywhere for online API serving or offline batch serving

• High-Performance API model server with adaptive micro-batching support

• Central hub for managing models and deployment process via Web UI and APIs

• Modular and flexible design making it adaptable to your infrastructure

BentoML is a framework for serving, managing, and deploying machine learning models. It is aiming to bridge the gap between Data Science and DevOps, and enable teams to deliver prediction services in a fast, repeatable, and scalable way.

💻 Get started with BentoML: Quickstart Guide | Quickstart on Google Colab

👩‍💻 Star/Watch/Fork the BentoML Github Repository.

👉 Join the community: Bentoml Slack Channel and the Discussions on Github.

---

• Getting Started
  • Run on Google Colab
  • Run notebook locally
  • Hello World
  • Save prediction service for distribution
  • Model Serving via REST API
  • Launch inference job from CLI
  • Containerize Model API Server
  • Deployment Options
  • Distribute BentoML packaged model as a PyPI library
  • Learning more about BentoML
• Core Concepts
  • Creating BentoService
  • Defining Service Environment
  • Packaging Model Artifacts
  • API Function and Adapters
  • Customize Web UI
  • Saving BentoService
  • Model Serving
  • Model Management
  • Labels
  • Retrieving BentoServices
• Frameworks
  • Scikit-Learn
  • PyTorch
  • Tensorflow 2.0 (Native API)
  • Keras (Tensorflow 2.0 as the backend)
  • Tensorflow 1.0
  • FastAI v1
  • FastAI v2
  • XGBoost
  • LightGBM
  • FastText
  • H2O
  • CoreML
  • ONNX
  • Spacy
  • Transformers
  • Statsmodels
  • Gluon
  • Pytorch Lightning
  • Detectron
• Advanced Guides
  • Configuration
  • Logging
  • Offline Batch Serving
  • Monitoring with Prometheus
  • Understanding BentoML adaptive micro batching
  • 1. The overall architecture of BentoML’s micro-batching server
  • 2. parameter tuning best practices & recommendations
  • 3. How to implement batch mode for custom input adapters
  • 4. Comparison
  • Adding Custom Model Artifact
  • Customizing InputAdapter
  • Deploy yatai server behind NGINX
  • Using Helm to install YataiService
  • 1. Configuration
  • 2. Deploying
• Deployment Guides
  • Deploying to AWS Lambda
  • Deploying to AWS SageMaker
  • Deploying to Azure Functions
  • Deploying to AWS EC2
  • 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
  • Deploying to Kubeflow
  • Deploying to KFServing
  • Deploying to Heroku
  • Deploying to SQL Server Machine Learning Services
• Example Projects
  • FastAI
  • Scikit-Learn
  • PyTorch
  • Tensorflow Keras
  • Tensorflow 2.0
  • XGBoost
  • LightGBM
  • H2O
  • FastText
  • ONNX
  • SQL Server Machine Learning Services
  • Statsmodels
• API Reference
  • BentoService API
  • API InputAdapters
  • API OutputAdapters
  • Adapter Roadmap
  • Frameworks
  • Base Artifact
  • Types
  • Yatai Client
• CLI Reference
  • bentoml
• Frequently Asked Questions
  • Why BentoML?
  • How does BentoML compare to Tensorflow-serving?
  • How does BentoML compare to Clipper?
  • How does BentoML compare to AWS SageMaker?
  • How does BentoML compare to MLFlow?
  • Does BentoML do horizontal scaling?
  • How does BentoML compare with Cortex?
  • How does BentoML compare to Seldon?
  • Is there a plan for R support?