v0.7 release
Blog post: verl 0.7 release blog
Highlight
Model Engine
- Integrate Megatron-Bridge and support LoRA/PEFT, see blog post: How We Build Trillion Parameter Reasoning RL with 10% GPUs
- Support experimental fp8 training f...
Unclaimed project
Are you a maintainer of verl? Claim this project to take control of your public changelog and roadmap.
Changelog
verl: Volcano Engine Reinforcement Learning for LLMs
Last updated about 1 month ago
Blog post: verl 0.7 release blog
Model Engine
As noted in https://github.com/volcengine/verl/issues/3624, model engine is a service that provides APIs for manipulation of a parallel and distributed model using single controller. This release provides a prototype for such idea using FSDP + ulysses backend and megatron core backend. The implementation is under https://github.com/volcengine/verl/tree/main/verl/...
verl v0.5 introduces the AgentLoop abstraction that allows easy extension to custom rollout with tool/agent interactions. Server-based asynchronous rollout is adopted to efficiently utilize GPUs. verl provides a few example agent loop implementations including:
PPO fixes and enhancements
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
Stable Diffusion web UI
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.