Table of Contents
2.5.1rc2

Home

  • Lightning in 15 minutes
  • Install
  • 2.0 Upgrade Guide

Level Up

  • Basic skills
  • Intermediate skills
  • Advanced skills
  • Expert skills

Core API

  • LightningModule
  • Trainer

Optional API

  • accelerators
  • callbacks
  • cli
  • core
  • loggers
  • profiler
  • trainer
  • strategies
  • tuner
  • utilities

More

  • Community
  • Examples
  • Glossary
  • How-to Guides
  • Overview
  • Team management
  • Production
  • Security
  • Open source
    • Overview
    • PyTorch Lightning
    • Fabric
    • Lit-GPT
    • Torchmetrics
    • Litdata
    • Lit LLaMA
    • Litserve
  • Examples
  • Glossary
  • FAQ
  • Docs >
  • How-to Guides >
  • Deploy models into production
Shortcuts

Deploy models into production¶

Basics¶

Basic

Learn the basics of predicting with Lightning

basic

Intermediate

Learn to remove the Lightning dependencies and use pure PyTorch for prediction.

intermediate


Advanced¶

Deploy with ONNX

Optimize models for enterprise-scale production environments with ONNX.

advanced

Deploy with torchscript

Optimize models for enterprise-scale production environments with torchscript.

advanced

Compress models for fast inference

Compress models for fast inference for deployment with Quantization and Pruning.

advanced

  • Deploy models into production
    • Basics
    • Advanced

To analyze traffic and optimize your experience, we serve cookies on this site. By clicking or navigating, you agree to allow our usage of cookies. Read PyTorch Lightning's Privacy Policy.