Towards Fully 8-bit Integer Inference for the Transformer Model. IJCAI2020.

Release time:2024-01-09

Hits:

First Author:: Ye Lin, Yanyang Li, Tengbo Liu, Tong Xiao, Tongran Liu, Jingbo Zhu

Translation or Not:: no

Pre One:Does Multi-Encoder Help? A Case Study on Context-Aware Neural Machine Translation. ACL2020.
Next One:The NiuTrans System for WNGT 2020 Efficiency Task. ACL2020.