@article{pushingthelimitsofllminferencevia2bit, title = {MiniKV: Pushing the Limits of LLM Inference via 2-Bit Layer-Discriminative KV Cache}, author = {Akshat Sharma and Hangliang Ding and Jianping Li and Neel Dani and Minjia Zhang}, year = {2024}, eprint = {2411.18077}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2411.18077v2}, }