Litcius/Paper detail

TurboTransformers

Jiarui Fang, Yang Yu, Chengduo Zhao, Jie Zhou

2021109 citationsDOIOpen Access PDF

Abstract

The transformer is the most critical algorithm innovation of the Nature Language Processing (NLP) field in recent years. Unlike the Recurrent Neural Network (RNN) models, transformers are able to process on dimensions of sequence lengths in parallel, therefore leads to better accuracy on long sequences. However, efficient deployments of them for online services in data centers equipped with GPUs are not easy. First, more computation introduced by transformer structures makes it more challenging to meet the latency and throughput constraints of serving. Second, NLP tasks take in sentences of variable length. The variability of input dimensions brings a severe problem to efficient memory management and serving optimization.

Topics & Concepts

Computer scienceTransformerComputationRecurrent neural networkLatency (audio)Artificial intelligenceLong short term memoryArtificial neural networkAlgorithmEngineeringElectrical engineeringTelecommunicationsVoltageAdvanced Neural Network ApplicationsNeural Networks and ApplicationsMultimodal Machine Learning Applications