Papers
Communities
Events
Blog
Pricing
Search
Open menu
Home
Papers
2104.05343
Cited By
An Efficient 2D Method for Training Super-Large Deep Learning Models
12 April 2021
Qifan Xu
Shenggui Li
Chaoyu Gong
Yang You
Re-assign community
ArXiv
PDF
HTML
Papers citing
"An Efficient 2D Method for Training Super-Large Deep Learning Models"
2 / 2 papers shown
Title
ZeRO-Offload: Democratizing Billion-Scale Model Training
Jie Ren
Samyam Rajbhandari
Reza Yazdani Aminabadi
Olatunji Ruwase
Shuangyang Yang
Minjia Zhang
Dong Li
Yuxiong He
MoE
177
417
0
18 Jan 2021
Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism
M. Shoeybi
M. Patwary
Raul Puri
P. LeGresley
Jared Casper
Bryan Catanzaro
MoE
245
1,833
0
17 Sep 2019
1