Zihao Wang, Bin Cui, Shaoduo Gan. SqueezeAttention: 2D Management of KV-Cache in LLM Inference via Layer-wise Optimal Budget. In The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025. OpenReview.net, 2025. [doi]
@inproceedings{WangCG25-0,
title = {SqueezeAttention: 2D Management of KV-Cache in LLM Inference via Layer-wise Optimal Budget},
author = {Zihao Wang and Bin Cui and Shaoduo Gan},
year = {2025},
url = {https://openreview.net/forum?id=9HK2rHNAhd},
researchr = {https://researchr.org/publication/WangCG25-0},
cites = {0},
citedby = {0},
booktitle = {The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025},
publisher = {OpenReview.net},
}