Miles v0.1: Production-Level Post-Training
RadixArk releases Miles v0.1, an open-source post-training system built on the slime design, covering RL, LoRA RL, on-policy distillation and SFT, with an end-to-end case study running fully asynchronous agentic RL on a 744B-A40B GLM-5.2 model over terminal-use coding tasks.
Ask this paper
Every stage verified, clean and customizable: The stated design principle applies to each component of the RL loop, with accuracy, efficiency, reliability and scalability treated as first-class rather than emergent properties.
Rollout on SGLang, training on two backends: Rollout engines are built on SGLang and the trainer offers a choice of NVIDIA Megatron-LM or PyTorch FSDP, with three weight-synchronization transports covering different deployment topologies.
Beyond full-parameter RL: The same architecture supports LoRA RL, on-policy distillation, supervised fine-tuning, true-on-policy rollout-training alignment, and extends to diffusion models.
A concrete scale number: The case study runs fully asynchronous agentic RL on GLM-5.2 744B-A40B over terminal-use coding tasks on 64 NVIDIA GB300 GPUs, with a median step time of 263 seconds over the first 30 measured steps.
Open source: Code is at github.com/radixark/miles with a project site at miles.radixark.com.
Abstract
We present Miles v0.1, a full-stack, production-ready system for frontier post-training. Building upon the clean design of slime, Miles designs each stage of the reinforcement-learning (RL) training loop around a single principle: components should be verified, clean, and customizable. With accuracy, efficiency, reliability, and scalability as first-class goals, Miles aims to make frontier-scale RL accessible to researchers and enterprises alike. This report walks through the system end to end: rollout engines built on SGLang, a trainer with a choice of two backends (NVIDIA Megatron-LM and PyTorch FSDP), and three weight-synchronization transports for different deployment topologies. Beyond full-parameter RL, Miles also supports LoRA RL, on-policy distillation, supervised fine-tuning, and true-on-policy rollout-training alignment, and extends the same architecture to diffusion models. We close with an end-to-end case study: fully asynchronous agentic RL on a GLM-5.2 744B-A40B model over terminal-use coding tasks, running on 64 NVIDIA GB300 GPUs with a median step time of 263 seconds over the first 30 measured steps. Miles is open-sourced at https://github.com/radixark/miles, with the project website at https://miles.radixark.com.