@article{contextparallelismforscalablemillion, title = {Context Parallelism for Scalable Million-Token Inference}, author = {Amy Yang and Jingyi Yang and Aya Ibrahim and Xinfeng Xie and Bangsheng Tang and Grigory Sizov and Jeremy Reizenstein and Jongsoo Park and Jianyu Huang}, year = {2024}, eprint = {2411.01783}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2411.01783v3}, }