@article{enhancingperformanceandscalabilityof, title = {Enhancing Performance and Scalability of Large-Scale Recommendation Systems with Jagged Flash Attention}, author = {Rengan Xu and Junjie Yang and Yifan Xu and Hong Li and Xing Liu and Devashish Shankar and Haoci Zhang and Meng Liu and Boyang Li and Yuxi Hu and Mingwei Tang and Zehua Zhang and Tunhou Zhang and Dai Li and Sijia Chen and Gian-Paolo Musumeci and Jiaqi Zhai and Bill Zhu and Hong Yan and Srihari Reddy}, year = {2024}, eprint = {2409.15373}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2409.15373v1}, }