Add TetriServe Arxiv

source/_data/SymbioticLab.bib

@@ -2124,5 +2124,20 @@ @PhDThesis{amberljc:dissertation
   }
 }
 
-
+@Article{tetriserve:arxiv25,
+author          = {Runyu Lu and Shiqi He and Wenxuan Tan and Shenggui Li and Ruofan Wu and Jeff J. Ma and Ang Chen and Mosharaf Chowdhury},
+title           = {{TetriServe}: Efficient {DiT} Serving for Heterogeneous Image Generation},
+year            = {2025},
+month           = {Oct},
+volume          = {abs/2510.01565},
+archivePrefix   = {arXiv},
+eprint          = {2510.01565},
+url             = {https://arxiv.org/abs/2510.01565},
+publist_confkey = {arXiv:2510.01565},
+publist_link    = {paper || https://arxiv.org/abs/2510.01565},
+publist_topic   = {Systems + AI},
+publist_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 large resolutions. Existing serving systems use fixed degree sequence parallelism, which is inefficient for heterogeneous workloads with mixed resolutions and deadlines, leading to poor GPU utilization and low SLO attainment. In this paper, we propose step-level sequence parallelism to dynamically adjust the parallel degree of individual requests according to their deadlines. We present TetriServe, a DiT serving system that implements this strategy for highly efficient image generation. Specifically, TetriServe introduces a novel round-based scheduling mechanism that improves SLO attainment: (1) discretizing time into fixed rounds to make deadline-aware scheduling tractable, (2) adapting parallelism at the step level and minimize GPU hour consumption, and (3) jointly packing requests to minimize late completions. Extensive evaluation on state-of-the-art DiT models shows that TetriServe achieves up to 32% higher SLO attainment compared to existing solutions without degrading image quality.
+}
+}