verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
7 daysStars24.2k24h gain+10Score7.5
Find trending repositories by name or description.
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
⚡️SwanLab - an open-source, modern-design AI training tracking and visualization tool. Supports Cloud / Self-hosted use. Integrated with PyTorch / Transformers / verl / LLaMA Factory / ms-swift / Ultralytics / MMEngine / Keras etc.
A version of verl to support diverse tool use [TMLR 2026]
Uni-Agent is a framework for training long-horizon agents.
Multimodal RL training framework for diffusion & omni models
Run a documented subset of verl-style OPD on one consumer GPU—typed config, Parquet prompts, and PEFT scale-out artifacts.