@inproceedings{zeng-etal-2025-gqsa,
    title = "{GQSA}: Group Quantization and Sparsity for Accelerating Large Language Model Inference",
    author = "Zeng, Chao  and
      Liu, Songwei  and
      Yang, Shu  and
      Chen, Fangmin  and
      Mei, Xing  and
      Fu, Lean",
    editor = "Inui, Kentaro  and
      Sakti, Sakriani  and
      Wang, Haofen  and
      Wong, Derek F.  and
      Bhattacharyya, Pushpak  and
      Banerjee, Biplab  and
      Ekbal, Asif  and
      Chakraborty, Tanmoy  and
      Singh, Dhirendra Pratap",
    booktitle = "Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics",
    month = dec,
    year = "2025",
    address = "Mumbai, India",
    publisher = "The Asian Federation of Natural Language Processing and The Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-ijcnlp-aacl/2025.ijcnlp-long.10/",
    pages = "149--165",
    ISBN = "979-8-89176-298-5"
}