@article{efficientinmemoryaccelerationofsparseblo, title = {Efficient In-Memory Acceleration of Sparse Block Diagonal LLMs}, author = {João Paulo Cardoso de Lima and Marc Dietrich and Jeronimo Castrillon and Asif Ali Khan}, year = {2025}, eprint = {2510.11192}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2510.11192}, }