Open Source

verl

verl: Volcano Engine Reinforcement Learning for LLMs.

Source: GitHub Pricing: Open Source
💻 View Code

About This Project

verl is a flexible, efficient and production-ready RL training library for large language models (LLMs). It enables easy extension of diverse RL algorithms, seamless integration of existing LLM infra with modular APIs, flexible device mapping, and state-of-the-art throughput.

Tags

LLM reinforcement-learning rlhf

Reviews & Ratings

Share your experience

User Reviews (0)

No reviews yet. Be the first to share your experience!