• search
    search
  • reviewers
    reviewers
  • feeds
    feeds
  • assignments
    assignments
  • settings
  • logout

DeepSpeed- Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale.

Reza Yazdani AminabadiSamyam RajbhandariAmmar Ahmad AwanCheng LiDu LiElton ZhengOlatunji RuwaseShaden SmithMinjia ZhangJeff RasleyYuxiong He
Published in: SC (2022)
Keyphrases