LLM-FP4: 4-Bit Floating-Point Quantized Transformers

Shih-Yang Liu, Zechun Liu, Xijie Huang, Pingcheng Dong, Kwang-Ting Cheng. LLM-FP4: 4-Bit Floating-Point Quantized Transformers. In Houda Bouamor, Juan Pino 0001, Kalika Bali, editors, Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023, Singapore, December 6-10, 2023. pages 592-605, Association for Computational Linguistics, 2023. [doi]

Authors

Shih-Yang Liu

This author has not been identified. Look up 'Shih-Yang Liu' in Google

Zechun Liu

This author has not been identified. Look up 'Zechun Liu' in Google

Xijie Huang

This author has not been identified. Look up 'Xijie Huang' in Google

Pingcheng Dong

This author has not been identified. Look up 'Pingcheng Dong' in Google

Kwang-Ting Cheng

This author has not been identified. Look up 'Kwang-Ting Cheng' in Google