RadixArk's Ke Bao on SGLang and Miles for Agentic AI
Ke Bao from RadixArk presented on the official PyTorch channel, detailing SGLang and Miles frameworks with a focus on cache reuse, long-context serving, and large-scale RL support for agentic workloads.
ImportanceLocalEvidenceE2 unreplicatedWrite-upQuick
Ke Bao from RadixArk delivered a talk on the official PyTorch channel on September 24, 2026, regarding frontier AI infrastructure, specifically the SGLang and Miles frameworks. The video focuses on the serving and post-training layers that determine real-world model performance, particularly addressing challenges arising when workloads shift towards agentic tasks.
According to the episode description, Ke Bao discussed key features designed for agentic workloads, including Unified Radix Cache, HiCache, and parallelism strategies for long-context serving. The presentation also covered HiSparse and the Miles framework, built on top of SGLang, which aims to support efficient and scalable reinforcement learning (RL) through high-performance rollouts and fully asynchronous training.