verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
Unclaimed
Are you the maintainer?
Claim this page →Verl
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
A 83/100 GitHub score ? This grade is derived from GitHub signals, not user votes. Open for the full
breakdown.
Discussion 01 / Summary
About Verl.
02 / Discussion CREDIBILITY-GATED
Discussion
Reading is open to everyone. Posting and voting need a verified identity or a GitHub grade of B or higher.
- No discussions yet.
03 / Related
More around Verl.
Similar tools
PrimeRL
Asynchronous, decentralized reinforcement-learning framework for post-training.
Surogate
Toolkit for training and serving LLMs on NVIDIA GPUs with native C++ and CUDA engines
Miles
Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.
RLinf
RLinf: Reinforcement Learning Infrastructure for Embodied and Agentic AI
04 / Build
Build with Verl.
Browse the catalog for frameworks, tools, and harnesses, each scored on real GitHub credibility.
Get Verl →