Your Location：
Home >
Browse articles >
Minimizing transformer inference overhead using controlling element on Shenwei AI accelerator
Regular Papers | Updated：2025-05-06

    • Minimizing transformer inference overhead using controlling element on Shenwei AI accelerator

    • 使用申威人工智能加速器的控制单元最小化Transformer推理开销
    • “In the field of natural language processing, this study introduces its research progress in optimizing transformer models. Expert xx developed a three-tier scheduling framework and zero-copy memory management technique, which significantly reduces inference overhead and enhances the efficiency of transformer models on AI accelerators.”
    • Frontiers of Information Technology & Electronic Engineering   Vol. 26, Issue 4, Pages: 605-622(2025)

    • DOI：10.1631/FITEE.2400453    

      CLC： TP181

    • Received：28 May 2024，

      Revised：25 August 2024，

      Published：2025-04

    Scan QR Code

  • Yulong ZHAO, Chunzhi WU, Yizhuo WANG, et al. Minimizing transformer inference overhead using controlling element on Shenwei AI accelerator[J]. Frontiers of information technology & electronic engineering, 2025, 26(4): 605-622. DOI： 10.1631/FITEE.2400453.

  •  
  •  

0

Views

13

Downloads

0

CSCD

PlumX

>
Alert me when the article has been cited
Submit
Tools
Download
Export Citation
Share
Add to favorites
Add to my album

Related Articles

No data

Related Author

No data

Related Institution

No data
0