TetriServe: Efficiently Serving Mixed DiT Workloads

Runyu Lu, Shiqi He, Wenxuan Tan, Shenggui Li, Ruofan Wu, Jeff J. Ma, Ang Chen 0001, Mosharaf Chowdhury. TetriServe: Efficiently Serving Mixed DiT Workloads. In Benjamin C. Lee, Harry Xu 0001, Mark Silberstein, Bingyao Li, editors, Proceedings of the 31st ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2, ASPLOS 2026, Pittsburgh, PA, USA, March 22-26, 2026. pages 1982-1997, ACM, 2026. [doi]

Abstract

Abstract is missing.