Lin, Ji, Tang, Jiaming, Tang, Haotian, Yang, Shang, Chen, Wei-Ming, Wang, Wei-Chen, Xiao, Guangxuan, Dang, Xingyu, Gan, Chuang, and Han, Song. AWQ: ACTIVATION-AWARE WEIGHT QUANTIZATION FOR ON-DEVICE LLM COMPRESSION AND ACCELERATION. Retrieved from https://par.nsf.gov/biblio/10553833.

Lin, Ji, Tang, Jiaming, Tang, Haotian, Yang, Shang, Chen, Wei-Ming, Wang, Wei-Chen, Xiao, Guangxuan, Dang, Xingyu, Gan, Chuang, & Han, Song. AWQ: ACTIVATION-AWARE WEIGHT QUANTIZATION FOR ON-DEVICE LLM COMPRESSION AND ACCELERATION. Retrieved from https://par.nsf.gov/biblio/10553833.

Lin, Ji, Tang, Jiaming, Tang, Haotian, Yang, Shang, Chen, Wei-Ming, Wang, Wei-Chen, Xiao, Guangxuan, Dang, Xingyu, Gan, Chuang, and Han, Song. "AWQ: ACTIVATION-AWARE WEIGHT QUANTIZATION FOR ON-DEVICE LLM COMPRESSION AND ACCELERATION". Country unknown/Code not available: The Seventh Annual Conference on Machine Learning and Systems (MLSys). https://par.nsf.gov/biblio/10553833.

@article{osti_10553833,
place = {Country unknown/Code not available}, title = {AWQ: ACTIVATION-AWARE WEIGHT QUANTIZATION FOR ON-DEVICE LLM COMPRESSION AND ACCELERATION}, url = {https://par.nsf.gov/biblio/10553833}, abstractNote = {}, journal = {}, publisher = {The Seventh Annual Conference on Machine Learning and Systems (MLSys)}, author = {Lin, Ji and Tang, Jiaming and Tang, Haotian and Yang, Shang and Chen, Wei-Ming and Wang, Wei-Chen and Xiao, Guangxuan and Dang, Xingyu and Gan, Chuang and Han, Song}, }