Lightning-Fast RL for LLM Reasoning and Agents. Made Simple & Flexible.

Build, evaluate and train General Multi-Agent Assistance with ease

A NCCL extension library, designed to efficiently offload GPU memory allocated by the NCCL communication library.

Ming-UniAudio: Speech LLM for Joint Understanding, Generation and Editing with Unified Representation

An Open-Source Large-Scale Reinforcement Learning Project for Search Agents

Easy and Efficient dLLM Fine-Tuning

dInfer: An Efficient Inference Framework for Diffusion Language Models

Agentic Learning Powered by AWorld

A high-performance RL training-inference weight synchronization framework, designed to enable second-level parameter updates from training to inference in RL workflows

AudioMCQ: A 571k audio multiple-choice question dataset for post-training Large Audio Language Models with dual CoT annotations and audio-contribution filtering. 🏆 1st place in DCASE 2025 Challenge.