ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2405.03882
36
3

Trio-ViT: Post-Training Quantization and Acceleration for Softmax-Free Efficient Vision Transformer

6 May 2024
Huihong Shi
Haikuo Shao
Wendong Mao
Zhongfeng Wang
    ViT
    MQ
ArXivPDFHTML
Abstract

Motivated by the huge success of Transformers in the field of natural language processing (NLP), Vision Transformers (ViTs) have been rapidly developed and achieved remarkable performance in various computer vision tasks. However, their huge model sizes and intensive computations hinder ViTs' deployment on embedded devices, calling for effective model compression methods, such as quantization. Unfortunately, due to the existence of hardware-unfriendly and quantization-sensitive non-linear operations, particularly {Softmax}, it is non-trivial to completely quantize all operations in ViTs, yielding either significant accuracy drops or non-negligible hardware costs. In response to challenges associated with \textit{standard ViTs}, we focus our attention towards the quantization and acceleration for \textit{efficient ViTs}, which not only eliminate the troublesome Softmax but also integrate linear attention with low computational complexity, and propose \emph{Trio-ViT} accordingly. Specifically, at the algorithm level, we develop a {tailored post-training quantization engine} taking the unique activation distributions of Softmax-free efficient ViTs into full consideration, aiming to boost quantization accuracy. Furthermore, at the hardware level, we build an accelerator dedicated to the specific Convolution-Transformer hybrid architecture of efficient ViTs, thereby enhancing hardware efficiency. Extensive experimental results consistently prove the effectiveness of our Trio-ViT framework. {Particularly, we can gain up to ↑\uparrow↑7.2×\mathbf{7.2}\times7.2× and ↑\uparrow↑14.6×\mathbf{14.6}\times14.6× FPS under comparable accuracy over state-of-the-art ViT accelerators, as well as ↑\uparrow↑5.9×\mathbf{5.9}\times5.9× and ↑\uparrow↑2.0×\mathbf{2.0}\times2.0× DSP efficiency.} Codes will be released publicly upon acceptance.

View on arXiv
Comments on this paper