Haojun Xia, Zhen Zheng, Yuchao Li, Donglin Zhuang, Zhongzhu Zhou, Xiafei Qiu, Yong Li, Wei Lin 0016, Shuaiwen Leon Song. Flash-LLM: Enabling Low-Cost and Highly-Efficient Large Generative Model Inference With Unstructured Sparsity. PVLDB, 17(2):211-224, 2023. [doi]
@article{XiaZLZZQL0S23,
title = {Flash-LLM: Enabling Low-Cost and Highly-Efficient Large Generative Model Inference With Unstructured Sparsity},
author = {Haojun Xia and Zhen Zheng and Yuchao Li and Donglin Zhuang and Zhongzhu Zhou and Xiafei Qiu and Yong Li and Wei Lin 0016 and Shuaiwen Leon Song},
year = {2023},
url = {https://www.vldb.org/pvldb/vol17/p211-xia.pdf},
researchr = {https://researchr.org/publication/XiaZLZZQL0S23},
cites = {0},
citedby = {0},
journal = {PVLDB},
volume = {17},
number = {2},
pages = {211-224},
}