Xuesong Ye 叶雪松

Hi, I work on ML infrastructure at LinkedIn, also contribute to SGLang Project.
Currently focusing on post-training / RL infra ↔ inference runtime.

Open Source

SGLang-Omni, High-Performance Multi-Stage Pipeline Framework for Omni Models | Core Maintainer

Talks

SGLang-Omni: Redesigning Inference Framework for Multi-Stage Generative Models | OpenBMB SOAR 2026