%0 Conference Paper %1 conf/sc/NarayananSCLPKV21 %A Narayanan, Deepak %A Shoeybi, Mohammad %A Casper, Jared %A LeGresley, Patrick %A Patwary, Mostofa %A Korthikanti, Vijay %A Vainbrand, Dmitri %A Kashinkunti, Prethvi %A Bernauer, Julie %A Catanzaro, Bryan %A Phanishayee, Amar %A Zaharia, Matei %B SC %D 2021 %E de Supinski, Bronis R. %E Hall, Mary W. %E Gamblin, Todd %I ACM %K dblp %P 58 %T Efficient large-scale language model training on GPU clusters using megatron-LM. %U http://dblp.uni-trier.de/db/conf/sc/sc2021.html#NarayananSCLPKV21 %@ 978-1-4503-8442-1

@inproceedings{conf/sc/NarayananSCLPKV21, added-at = {2024-02-05T00:00:00.000+0100}, author = {Narayanan, Deepak and Shoeybi, Mohammad and Casper, Jared and LeGresley, Patrick and Patwary, Mostofa and Korthikanti, Vijay and Vainbrand, Dmitri and Kashinkunti, Prethvi and Bernauer, Julie and Catanzaro, Bryan and Phanishayee, Amar and Zaharia, Matei}, biburl = {https://www.bibsonomy.org/bibtex/2bf6b0f2cba51fbb1d4a92d84e263cac8/dblp}, booktitle = {SC}, crossref = {conf/sc/2021}, editor = {de Supinski, Bronis R. and Hall, Mary W. and Gamblin, Todd}, ee = {https://ieeexplore.ieee.org/document/9910057}, interhash = {9d7bc4d3c7448070431b7f9973f31e6d}, intrahash = {bf6b0f2cba51fbb1d4a92d84e263cac8}, isbn = {978-1-4503-8442-1}, keywords = {dblp}, pages = 58, publisher = {ACM}, timestamp = {2024-04-10T00:30:26.000+0200}, title = {Efficient large-scale language model training on GPU clusters using megatron-LM.}, url = {http://dblp.uni-trier.de/db/conf/sc/sc2021.html#NarayananSCLPKV21}, year = 2021 }