%0 Journal Article %1 journals/corr/abs-2201-11990 %A Smith, Shaden %A Patwary, Mostofa %A Norick, Brandon %A LeGresley, Patrick %A Rajbhandari, Samyam %A Casper, Jared %A Liu, Zhun %A Prabhumoye, Shrimai %A Zerveas, George %A Korthikanti, Vijay %A Zheng, Elton %A Child, Rewon %A Aminabadi, Reza Yazdani %A Bernauer, Julie %A Song, Xia %A Shoeybi, Mohammad %A He, Yuxiong %A Houston, Michael %A Tiwary, Saurabh %A Catanzaro, Bryan %D 2022 %J CoRR %K dblp %T Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model. %U http://dblp.uni-trier.de/db/journals/corr/corr2201.html#abs-2201-11990 %V abs/2201.11990

@article{journals/corr/abs-2201-11990, added-at = {2022-02-02T00:00:00.000+0100}, author = {Smith, Shaden and Patwary, Mostofa and Norick, Brandon and LeGresley, Patrick and Rajbhandari, Samyam and Casper, Jared and Liu, Zhun and Prabhumoye, Shrimai and Zerveas, George and Korthikanti, Vijay and Zheng, Elton and Child, Rewon and Aminabadi, Reza Yazdani and Bernauer, Julie and Song, Xia and Shoeybi, Mohammad and He, Yuxiong and Houston, Michael and Tiwary, Saurabh and Catanzaro, Bryan}, biburl = {https://www.bibsonomy.org/bibtex/2e5d987e1f3a485df4e4cb1e3b80e05d2/dblp}, ee = {https://arxiv.org/abs/2201.11990}, interhash = {7561f804bea983608a9294a2799c3ca7}, intrahash = {e5d987e1f3a485df4e4cb1e3b80e05d2}, journal = {CoRR}, keywords = {dblp}, timestamp = {2024-04-08T22:49:42.000+0200}, title = {Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model.}, url = {http://dblp.uni-trier.de/db/journals/corr/corr2201.html#abs-2201-11990}, volume = {abs/2201.11990}, year = 2022 }