@article{lightningattention2afreelunchfor, title = {Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models}, author = {Zhen Qin and Weigao Sun and Dong Li and Xuyang Shen and Weixuan Sun and Yiran Zhong}, year = {2024}, eprint = {2401.04658}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2401.04658v2}, }