Optimize Quantization for Large Language Models via Progressive Training.

@inproceedings{du-2025-optimize, author = {Jiangcun Du and Renren Jin and Wuwei Huang and Wei Liu and Jian Luan and Deyi Xiong}, editor = {Guodong Long and Michale Blumestein and Yi Chang and Liane Lewin-Eytan and Zi Huang and Elad Yom-Tov}, title = {{Optimize Quantization for Large Language Models via Progressive Training}}, booktitle = {{Companion Proceedings of the ACM on Web Conference 2025, WWW 2025, Sydney, NSW, Australia, 28 April 2025 - 2 May 2025}}, pages = {2474--2483}, publisher = {ACM}, year = {2025}, url = {https://doi.org/10.1145/3701716.3717578}, doi = {https://doi.org/10.1145/3701716.3717578} }