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
- Installation - Set up SkyRL with Docker or from source
- Quick Start - Run your first GRPO training on GSM8K
- System Overview - Understand SkyRL's architecture
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
- Creating a New Environment - Build custom environments and tasks
- Async Training - Implement asynchronous training pipelines
- Using Tools - Add tool-use capabilities to your agents
Examples
- Megatron Backend - 5D parallelism for large-scale training
- Multi-Turn Text2SQL - Train agents for database queries
- Search with SkyRL - Multi-turn RL for search tasks
Reference
- Configuration - Training configuration options
- Algorithms - DAPO and custom algorithm implementation
- Recipes - End-to-end training recipes