Halo is not limited to supervised fine-tuning. It supports async RL and training with external environments.
We are excited to partner with the @sgl_project team to make it the primary engine for rollouts.
Introducing Halo, the best framework for post-training of open-source models.
Halo delivers up to 2.8x the throughput of stock TRL with less peak memory, while models stay in their native HuggingFace format.
Star us on GitHub: