@article{chessoptimizingllminferenceviachannel,
  title = {CHESS: Optimizing LLM Inference via Channel-Wise Thresholding and Selective Sparsification},
  author = {Junhui He and Shangyu Wu and Weidong Wen and Chun Jason Xue and Qingan Li},
  year = {2024},
  eprint = {2409.01366},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2409.01366v2},
}