@article{accllmacceleratinglongcontextllm,
  title = {AccLLM: Accelerating Long-Context LLM Inference Via Algorithm-Hardware Co-Design},
  author = {Yanbiao Liang and Huihong Shi and Haikuo Shao and Zhongfeng Wang},
  year = {2025},
  eprint = {2505.03745},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.03745v1},
}