alibaba/ROLL

About

🚀 An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models 🚀

ROLL is an efficient and user-friendly RL library designed for Large Language Models (LLMs) utilizing Large Scale GPU resources. It significantly enhances LLM performance in key areas such as human preference alignment, complex reasoning, and multi-turn agentic interaction scenarios.

Leveraging a multi-role distributed architecture with Ray for flexible resource allocation and heterogeneous task scheduling, ROLL integrates cutting-edge technologies like Megatron-Core, SGLang and vLLM to accelerate model training and inference.

| [16/06/2026] 🎉 Our OSDI’26 RollArt paper is now…

Excerpted from github.com/alibaba/ROLL