@article{pimbaaprocessinginmemoryaccelerationforp, title = {Pimba: A Processing-in-Memory Acceleration for Post-Transformer Large Language Model Serving}, author = {Wonung Kim and Yubin Lee and Yoonsung Kim and Jinwoo Hwang and Seongryong Oh and Jiyong Jung and Aziz Huseynov and Woong Gyu Park and Chang Hyun Park and Divya Mahajan and Jongse Park}, year = {2025}, eprint = {2507.10178}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2507.10178}, }