SwiftFusion: Scalable Sequence Parallelism for Distributed Inference of Diffusion Transformers on GPUs 文章

ArXiv CS.CV2026-05-26NEWSen作者: Jiacheng Yang, Jun Wu, Yaoyao Ding, Zhiying Xu, Yida Wang, Gennady Pekhimenko
大语言模型
查看原文 →
关系图谱

SwiftFusion: Scalable Sequence Parallelism for Distributed Inference of Diffusion Transformers on GPUs · 相关人物

暂无数据