diff --git a/_data/publications.yml b/_data/publications.yml index b6c1608..5e001a2 100644 --- a/_data/publications.yml +++ b/_data/publications.yml @@ -2,8 +2,8 @@ main: - title: "QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving" authors: Yujun Lin*, Haotian Tang*, Shang Yang*, Zhekai Zhang, Guangxuan Xiao, Chuang Gan, Song Han. - conference_short: arXiv - conference: arXiv, 2024. + conference_short: MLSys + conference: The Eighth Annual Conference on Machine Learning and Systems (MLSys), 2025. paper: https://arxiv.org/abs/2405.04532 code: https://github.com/mit-han-lab/qserve image: ./assets/img/paper_teasers/QServe.png