홈 › Papers

Quasar-ViT: Hardware-Oriented Quantization-Aware Architecture Search for Vision Transformers

2024-07-25 · Zhengang Li, Alec Lu, Yanyue Xie, Zhenglun Kong, Mengshu Sun, Hao Tang, Zhong Jia Xue, Peiyan Dong, Caiwen Ding, Yanzhi Wang, Xue Lin, Zhenman Fang

Vision transformers (ViTs) have demonstrated their superior accuracy for computer vision tasks compared to convolutional neural networks (CNNs). However, ViT models are often computation-intensive for efficient deployment on resource-limited edge devices. This work proposes Quasar-ViT, a hardware-oriented quantization-aware architecture search framework for ViTs, to design efficient ViT models for hardware implementation while preserving the accuracy. First, Quasar-ViT trains a supernet using our row-wise flexible mixed-precision quantization scheme, mixed-precision weight entanglement, and supernet layer scaling techniques. Then, it applies an efficient hardware-oriented search algorithm, integrated with hardware latency and resource modeling, to determine a series of optimal subnets from supernet under different inference latency targets. Finally, we propose a series of model-adaptive designs on the FPGA platform to support the architecture search and mitigate the gap between the theoretical computation reduction and the practical inference speedup. Our searched models achieve 101.5, 159.6, and 251.6 frames-per-second (FPS) inference speed on the AMD/Xilinx ZCU102 FPGA with 80.4%, 78.6%, and 74.9% top-1 accuracy, respectively, for the ImageNet dataset, consistently outperforming prior works.

📄 PDF Abstract BibTeX arXiv:2407.18175

Code (0)

등록된 구현이 없습니다.

Tasks

Quantization

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

QUASAR: Lowering the Loss Floor of Quantization-Aware Training with Loss-Aware Reconstruction

2026-08-14 · Vincent Counathe, Ben Athiwaratkun, Christopher De Sa, Tianyi Zhang arxiv

As large language model inference shifts toward lower precision, post-training quantization (PTQ) becomes increasingly brittle, making quantization-aware training (QAT) essential for preserving model quality. However, QA…

Phoenix: A Low-Precision Floating-Point Quantization Oriented Architecture for Convolutional Neural Networks

2020-02-29

Convolutional neural networks (CNNs) achieve state-of-the-art performance at the cost of becoming deeper and larger. Although quantization (both fixed-point and floating-point) has proven effective for reducing storage a…

Quantization

HAQ: Hardware-Aware Automated Quantization with Mixed Precision

2018-11-21 · CVPR 2019 6 · Kuan Wang, Zhijian Liu, Yujun Lin, Ji Lin 외

Model quantization is a widely used technique to compress and accelerate deep neural network (DNN) inference. Emergent DNN hardware accelerators begin to support mixed precision (1-8 bits) to further improve the computat…

Quantization Reinforcement Learning

NAS-Driven Hardware Accelerator Exploration for Edge AI and Quantization Effects on the Pareto Space

2026-08-13 · Eleftherios Mylonas, Angelos Kouprizas, Michael Birbas, Alexios Birbas arxiv

Edge AI deployment demands neural architectures that are simultaneously accurate, computationally efficient, and hardware-deployable - a challenge addressed by hardware-aware Neural Architecture Search (NAS). While recen…

Neural Architecture Search

Hardware-Centric AutoML for Mixed-Precision Quantization

2020-08-11 · Kuan Wang, Zhijian Liu, Yujun Lin, Ji Lin 외

AutoML Quantization