%0 Journal Article %1 journals/tcss/JiangWCGZMZ24 %A Jiang, Peiwen %A Wang, Haoxin %A Cai, Zinuo %A Gao, Lintao %A Zhang, Weishan %A Ma, Ruhui %A Zhou, Xiaokang %D 2024 %J IEEE Trans. Comput. Soc. Syst. %K dblp %N 6 %P 7941-7951 %T SLoB: Suboptimal Load Balancing Scheduling in Local Heterogeneous GPU Clusters for Large Language Model Inference. %U http://dblp.uni-trier.de/db/journals/tcss/tcss11.html#JiangWCGZMZ24 %V 11

@article{journals/tcss/JiangWCGZMZ24, added-at = {2025-01-08T00:00:00.000+0100}, author = {Jiang, Peiwen and Wang, Haoxin and Cai, Zinuo and Gao, Lintao and Zhang, Weishan and Ma, Ruhui and Zhou, Xiaokang}, biburl = {https://www.bibsonomy.org/bibtex/2e4e0e449ded0ed6bc073bbced91f635a/dblp}, ee = {https://doi.org/10.1109/TCSS.2024.3423749}, interhash = {8982997356d351031e5443251c088911}, intrahash = {e4e0e449ded0ed6bc073bbced91f635a}, journal = {IEEE Trans. Comput. Soc. Syst.}, keywords = {dblp}, month = {December}, number = 6, pages = {7941-7951}, timestamp = {2025-01-13T07:09:38.000+0100}, title = {SLoB: Suboptimal Load Balancing Scheduling in Local Heterogeneous GPU Clusters for Large Language Model Inference.}, url = {http://dblp.uni-trier.de/db/journals/tcss/tcss11.html#JiangWCGZMZ24}, volume = 11, year = 2024 }