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

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

6 May 2024

Zhongfeng Wang

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

5 / 5 papers shown

Title
M $^2$ -ViT: Accelerating Hybrid Vision Transformers with Two-Level Mixed Quantization Yanbiao Liang Huihong Shi Zhongfeng Wang MQ 11 0 0 10 Oct 2024
I-ViT: Integer-only Quantization for Efficient Vision Transformer Inference Zhikai Li Qingyi Gu MQ 41 94 0 04 Jul 2022
MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer Sachin Mehta Mohammad Rastegari ViT 186 1,148 0 05 Oct 2021
I-BERT: Integer-only BERT Quantization Sehoon Kim A. Gholami Z. Yao Michael W. Mahoney Kurt Keutzer MQ 86 332 0 05 Jan 2021
Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT Sheng Shen Zhen Dong Jiayu Ye Linjian Ma Z. Yao A. Gholami Michael W. Mahoney Kurt Keutzer MQ 214 505 0 12 Sep 2019