Miles natively supports @sgl_project for fast rollouts, while keeping rollout and training aligned for reliable post-training at scale.
Grateful to the community for the contributions and feedback that continue to shape Miles.
RadixArk's Miles integrates SGLang for fast, aligned post-training rollouts
AISummary
RadixArk says its Miles framework natively supports SGLang for fast rollouts while keeping rollout and training aligned for reliable post-training at scale. The post thanks the community for contributions and feedback shaping Miles. A related post from @adarshxs describes Miles v0.1 running fully async agentic RL on a 744B MoE across 64 GB300 GPUs.
Post on XView on X
@radixark
Huge congrats to the @radixark team on Miles v0.1! 🚀 Fully async agentic RL on a 744B MoE across 64 GB300s, with @sgl_project powering rollouts. Love the focus on getting rollout/training fidelity right alongside throughput. https://huggingface.co/papers/2609.08368View quoted post on X
Source: RadixArk · x.comPublished · added here