%0 Conference Paper %1 conf/wcnc/Zhang0XHX024 %A Zhang, Xinyuan %A Liu, Jiang %A Xiong, Zehui %A Huang, Yudong %A Xie, Gaochang %A Zhang, Ran %B WCNC %D 2024 %I IEEE %K dblp %P 1-6 %T Edge Intelligence Optimization for Large Language Model Inference with Batching and Quantization. %U http://dblp.uni-trier.de/db/conf/wcnc/wcnc2024.html#Zhang0XHX024 %@ 979-8-3503-0358-2

@inproceedings{conf/wcnc/Zhang0XHX024, added-at = {2024-07-16T00:00:00.000+0200}, author = {Zhang, Xinyuan and Liu, Jiang and Xiong, Zehui and Huang, Yudong and Xie, Gaochang and Zhang, Ran}, biburl = {https://www.bibsonomy.org/bibtex/2a312943a7b044b35640933c22bbf177c/dblp}, booktitle = {WCNC}, crossref = {conf/wcnc/2024}, ee = {https://doi.org/10.1109/WCNC57260.2024.10571127}, interhash = {6badf390ec05a231733415153cab0474}, intrahash = {a312943a7b044b35640933c22bbf177c}, isbn = {979-8-3503-0358-2}, keywords = {dblp}, pages = {1-6}, publisher = {IEEE}, timestamp = {2024-07-22T07:17:35.000+0200}, title = {Edge Intelligence Optimization for Large Language Model Inference with Batching and Quantization.}, url = {http://dblp.uni-trier.de/db/conf/wcnc/wcnc2024.html#Zhang0XHX024}, year = 2024 }