TLDR Tech / AI
DAPO (GitHub Repo)
DAPO is a system for large-scale LLM RL. It achieves state-of-the-art large-scale LLM RL performance. DAPO achieved 50 points on AIME 2024 based on the Qwen2.5-32B base model. The system is fully open-sourced, including algorithm details, dataset, and infrastructure.
Read the full story