verl-project/verl
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
- Stars
- 24k
- Forks
- 4.8k
- Open issues
- 633
- Last push
- today
About verl
verl is a free, open-source machine learning tool by verl-project, written mainly in Python. verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework. It has 24k GitHub stars and 4.8k forks, and was last updated today. It's released under the Apache-2.0 license, a standard open-source license.
- License
- Apache-2.0
- Language
- Python
- Stars
- 23,979
- Last update
- today
- Runs on Mac
- Not stated
- GPU
- Not stated
- Paid API key
- Not required
- Self-hostable
- Not stated
Similar free tools
verl-omni1.3k stars · Multimodal RL training framework for diffusion & omni models
pytorch-image-models37k stars · The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT)
Music-Source-Separation-Training1.6k stars · Repository for training models for music source separation.
uni2ts1.6k stars · Unified Training of Universal Time Series Forecasting Transformers
ai-trains-ai243 stars · RL-training an AI agent to RL-train AI agents.
mini-verl307 stars · verl for a single consumer GPU. PPO, GRPO and on-policy distillation on NVIDIA GPUs.
verl FAQ
Is verl free?
Yes. verl is open source and free to use. It's released under the Apache-2.0 license, a standard open-source license.
Does verl run on a Mac?
The project doesn't say. Check its installation guide before you start.
Does verl need a GPU?
The project doesn't state hardware needs. AI models generally run much faster with a GPU.
Is verl still maintained?
Yes. It was last updated today and has 633 open issues on GitHub.
What are alternatives to verl?
Similar free, open-source tools include verl-omni, pytorch-image-models, Music-Source-Separation-Training, uni2ts.