%0 Journal Article %1 journals/pvldb/XiaZLZZQL0S23 %A Xia, Haojun %A Zheng, Zhen %A Li, Yuchao %A Zhuang, Donglin %A Zhou, Zhongzhu %A Qiu, Xiafei %A Li, Yong %A Lin, Wei %A Song, Shuaiwen Leon %D 2023 %J Proc. VLDB Endow. %K dblp %N 2 %P 211-224 %T Flash-LLM: Enabling Low-Cost and Highly-Efficient Large Generative Model Inference With Unstructured Sparsity. %U http://dblp.uni-trier.de/db/journals/pvldb/pvldb17.html#XiaZLZZQL0S23 %V 17

@article{journals/pvldb/XiaZLZZQL0S23, added-at = {2023-11-27T00:00:00.000+0100}, author = {Xia, Haojun and Zheng, Zhen and Li, Yuchao and Zhuang, Donglin and Zhou, Zhongzhu and Qiu, Xiafei and Li, Yong and Lin, Wei and Song, Shuaiwen Leon}, biburl = {https://www.bibsonomy.org/bibtex/2c982501568f758774dd5e7b4248b8ef2/dblp}, ee = {https://www.vldb.org/pvldb/vol17/p211-xia.pdf}, interhash = {54925496132e7b5ae1162f9aa7a6537a}, intrahash = {c982501568f758774dd5e7b4248b8ef2}, journal = {Proc. VLDB Endow.}, keywords = {dblp}, number = 2, pages = {211-224}, timestamp = {2024-04-09T01:05:13.000+0200}, title = {Flash-LLM: Enabling Low-Cost and Highly-Efficient Large Generative Model Inference With Unstructured Sparsity.}, url = {http://dblp.uni-trier.de/db/journals/pvldb/pvldb17.html#XiaZLZZQL0S23}, volume = 17, year = 2023 }