@misc{wang2024infra, title={1-bit AI Infra: Part 1.1, Fast and Lossless BitNet b1.58 Inference on CPUs}, author={Jinheng Wang and Hansong Zhou and Ting Song and Shaoguang Mao and Shuming Ma and Hongyu Wang and Yan Xia and Furu Wei}, year={2024}, eprint={2410.16144}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2410.16144} }