@article{swiftfusionscalablesequenceparallelismfo, title = {SwiftFusion: Scalable Sequence Parallelism for Distributed Inference of Diffusion Transformers on GPUs}, author = {Jiacheng Yang and Jun Wu and Yaoyao Ding and Zhiying Xu and Yida Wang and Gennady Pekhimenko}, year = {2026}, eprint = {2601.20273}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2601.20273}, }