SkyRL

SkyRL Documentation

Welcome to SkyRL's Documentation!

SkyRL is a full-stack reinforcement learning library for training LLMs, designed for modularity and extensibility.

New: Tinker Integration — Run any Tinker API training script on your own hardware with zero code changes. Get started →

Getting Started

Tinker Integration

  • Overview - Run Tinker API scripts on SkyRL with zero code changes
  • Quickstart - Start a Tinker server and run your first training script
  • Architecture - How SkyRL implements the Tinker API
  • Cookbook Scripts - Validated tinker-cookbook recipes

Tutorials

Examples

Reference

On this page