arXiv Machine Learning By Runyu Lu, Shiqi He, Wenxuan Tan, Shenggui Li, Ruofan Wu, Jeff J. Ma, Ang Chen, Mosharaf Chowdhury

TetriServe: Efficiently Serving Mixed DiT Workloads

Read the original on arXiv Machine Learning →

arXiv:2510. 01565v4 Announce Type: replace Abstract: Diffusion Transformer (DiT) models excel at generating high-quality images through iterative denoising steps, but serving them under strict Service Level Objectives (SLOs) is challenging due to their high computational cost, particularly at larger resolutions.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv AI
Jul 28

X-Stage: An Overlooked Pipeline Stage for Communication-Computation Overlap in DiT Inference

arXiv:2607. 23264v1 Announce Type: cross Abstract: Fine-grained, device-initiated communication lets persistent GPU kernels in distributed diffusion transformer (DiT) inference issue remote stores and overlap data movement with Tensor Core computation.

By Jianwen Xian, Zhiyuan Xu, Yuchen Li, Ziliang Lai, Kang He, Zhen Huang, Aichen Feng, Jinyan Chen, Yilin Zhang, Qinqin Chen, Chengru Song