@article{autochunkautomatedactivationchunkfor, title = {AutoChunk: Automated Activation Chunk for Memory-Efficient Long Sequence Inference}, author = {Xuanlei Zhao and Shenggan Cheng and Guangyang Lu and Jiarui Fang and Haotian Zhou and Bin Jia and Ziming Liu and Yang You}, year = {2024}, eprint = {2401.10652}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2401.10652v3}, }