Library / SDK
Fine-tuning & Training
verl
1Volcano 2Engine's 3library 4for 5RL 6training.
the six Ws · specification
W1
Who
By ByteDance.
W2
What
A flexible, efficient library for reinforcement-learning training of LLMs.
W3
Where
A Python framework on GPU clusters.
W4
When
When training LLMs with reinforcement learning.
W5
Why
A leading open RL-for-LLMs framework.
W6
With
Python, Ray, and a rollout engine.
W7
Watch
Apache-2.0, from ByteDance; runs on your cluster, no credentials.
alternatives
works with
RLTrainingByteDance