@article{papiexploitingdynamicparallelisminlarge, title = {PAPI: Exploiting Dynamic Parallelism in Large Language Model Decoding with a Processing-In-Memory-Enabled Computing System}, author = {Yintao He and Haiyu Mao and Christina Giannoula and Mohammad Sadrosadati and Juan Gómez-Luna and Huawei Li and Xiaowei Li and Ying Wang and Onur Mutlu}, year = {2025}, eprint = {2502.15470}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2502.15470v2}, }