BibTeX record journals/corr/abs-2402-15627

• > Home > journals/corr/abs-2402-15627

@article{DBLP:journals/corr/abs-2402-15627,
  author       = {Ziheng Jiang and
                  Haibin Lin and
                  Yinmin Zhong and
                  Qi Huang and
                  Yangrui Chen and
                  Zhi Zhang and
                  Yanghua Peng and
                  Xiang Li and
                  Cong Xie and
                  Shibiao Nong and
                  Yulu Jia and
                  Sun He and
                  Hongmin Chen and
                  Zhihao Bai and
                  Qi Hou and
                  Shipeng Yan and
                  Ding Zhou and
                  Yiyao Sheng and
                  Zhuo Jiang and
                  Haohan Xu and
                  Haoran Wei and
                  Zhang Zhang and
                  Pengfei Nie and
                  Leqi Zou and
                  Sida Zhao and
                  Liang Xiang and
                  Zherui Liu and
                  Zhe Li and
                  Xiaoying Jia and
                  Jianxi Ye and
                  Xin Jin and
                  Xin Liu},
  title        = {MegaScale: Scaling Large Language Model Training to More Than 10,
                  000 GPUs},
  journal      = {CoRR},
  volume       = {abs/2402.15627},
  year         = {2024},
  url          = {https://doi.org/10.48550/arXiv.2402.15627},
  doi          = {10.48550/ARXIV.2402.15627},
  eprinttype    = {arXiv},
  eprint       = {2402.15627},
  timestamp    = {Tue, 20 Aug 2024 07:54:43 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2402-15627.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}