@misc{hooper2025fgmp,
  title={FGMP: Fine-Grained Mixed-Precision Weight and Activation Quantization for Hardware-Accelerated LLM Inference},
  author={Coleman Hooper and Charbel Sakr and Ben Keller and Rangharajan Venkatesan and Kurt Keutzer and Sophia Shao and Brucek Khailany},
  year={2025},
  eprint={2504.14152},
  archivePrefix={arXiv},
  primaryClass={cs.AR},
  url={https://arxiv.org/abs/2504.14152}
}