@article{understandandacceleratememoryprocessingp,
  title = {Understand and Accelerate Memory Processing Pipeline for Large Language Model Inference},
  author = {Zifan He and Rui Ma and Yizhou Sun and Jason Cong},
  year = {2026},
  eprint = {2603.29002},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2603.29002},
}