Hardware-friendly compression and hardware acceleration for transformer: a survey

DOI10.3934/ERA.2022192OpenAlexW4291952092MaRDI QIDQ2700301

Xiangzhan Ping, Enhao Tang, Ruiqi Chen, Shun Li, Shizhen Huang

Publication date: 20 April 2023

Published in: Electronic Research Archive (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.3934/era.2022192

zbMATH Keywords

transformercompressionFPGAhardware acceleratorsself-attention

Mathematics Subject Classification ID

Computer science (68-XX) Information and communication theory, circuits (94-XX)

Uses Software

• CSR5
• Tensor2Tensor
• BERT
• RoBERTa
• AutoFormer

Cites Work

• Data-driven surrogate model with latent data assimilation: application to wildfire forecasting
• Similarity estimation techniques from rounding algorithms
• Unnamed Item
• Unnamed Item

This page was built for publication: Hardware-friendly compression and hardware acceleration for transformer: a survey