@article{zeng2023vcc, title={Vcc: Scaling Transformers to 128K Tokens or More by Prioritizing Important Tokens}, author={Zeng, Zhanpeng and Hawkins, Cole and Hong, Mingyi and Zhang, Aston and Pappas, Nikolaos and Singh, Vikas and Zheng, Shuai}, journal={arXiv preprint arXiv:2305.04241}, year={2023} }