@article{sun2024shadowkv, title={ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference}, author={Sun, Hanshi and Chang, Li-Wen and Bao, Wenlei and Zheng, Size and Zheng, Ningxin and Liu, Xin and Dong, Harry and Chi, Yuejie and Chen, Beidi}, journal={arXiv preprint arXiv:2410.21465}, year={2024} }