@article{precisionwhereitmattersanovelspike,
  title = {Precision Where It Matters: A Novel Spike Aware Mixed-Precision Quantization Strategy for LLaMA-based Language Models},
  author = {Lucas Maisonnave and Cyril Moineau and Olivier Bichler and Fabrice Rastello},
  year = {2025},
  eprint = {2504.21553},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2504.21553v1},
}