RadixArk Open-Sources RL Post-Training Framework Miles v0.1

RadixArk released Miles v0.1, an open-source production-grade RL and post-training framework for LLMs and multimodal models. Built over 9 months with 72 contributors and 1,326 commits, it addresses the difficulty of debugging RL training and supports multiple backends, LoRA, and diffusion models.

2026-09-09 ~ 2026-09-10 · 2 related posts

• Miles v0.1: Open-Source Production-Grade RL Post-Training System with LoRA and Diffusion Support — RadixArk · 2026-09-09
• Miles v0.1 launches: open-source RL framework battle-tested on frontier models — ChengleiSi · 2026-09-10