[Hands-on Lab] SGLang Diffusion: High-Performance Image and Video Generation — Run an Open Diffusion Model Live

Diffusion models have become the backbone of modern image and video generation, but serving them efficiently remains challenging. In this talk, we introduce SGLang-Diffusion, a high-performance inference framework designed for scalable diffusion generation. We present its system architecture and key optimizations—including advanced parallelism, distributed VAE, kernel fusion, and serving improvements—that enable efficient and production-ready deployment of diffusion models. We also demonstrate how SGLang-Diffusion accelerates popular open-source models and supports large-scale multimodal generation workloads.