@article{70size100accuracylosslessllmcompression,
  title = {70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float},
  author = {Tianyi Zhang and Yang Sui and Shaochen Zhong and Vipin Chaudhary and Xia Hu and Anshumali Shrivastava},
  year = {2025},
  eprint = {2504.11651},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2504.11651v1},
}