@article{mlkvmultilayerkeyvalueheadsformemory, title = {MLKV: Multi-Layer Key-Value Heads for Memory Efficient Transformer Decoding}, author = {Zayd Muhammad Kawakibi Zuhri and Muhammad Farid Adilazuarda and Ayu Purwarianti and Alham Fikri Aji}, year = {2024}, eprint = {2406.09297}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2406.09297v3}, }