@article{tenderacceleratinglargelanguagemodelsvia, title = {Tender: Accelerating Large Language Models via Tensor Decomposition and Runtime Requantization}, author = {Jungi Lee and Wonbeom Lee and Jaewoong Sim}, year = {2024}, eprint = {2406.12930}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2406.12930v1}, }