paper-with-me

Papers

Resource-aware Mixed-precision Quantization for Enhancing Deployability of Transformers for Time-series Forecasting on Embedded FPGAs

2024-10-04 · Tianheng Ling, Chao Qian, Gregor Schiele

This study addresses the deployment challenges of integer-only quantized Transformers on resource-constrained embedded FPGAs (Xilinx Spartan-7 XC7S15). We enhanced the flexibility of our VHDL template by introducing a selectable resource type for storing intermediate results across model layers, thereby breaking the deployment bottleneck by utilizing BRAM efficiently. Moreover, we developed a resource-aware mixed-precision quantization approach that enables researchers to explore hardware-level quantization strategies without requiring extensive expertise in Neural Architecture Search. This method provides accurate resource utilization estimates with a precision discrepancy as low as 3%, compared to actual deployment metrics. Compared to previous work, our approach has successfully facilitated the deployment of model configurations utilizing mixed-precision quantization, thus overcoming the limitations inherent in five previously non-deployable configurations with uniform quantization bitwidths. Consequently, this research enhances the applicability of Transformers in embedded systems, facilitating a broader range of Transformer-powered applications on edge devices.

📄 PDF Abstract BibTeX arXiv:2410.03294

Code (0)

등록된 구현이 없습니다.

Tasks

Neural Architecture SearchQuantizationTime SeriesTime Series Forecasting

Similar Papers 제목 키워드 기반

Adaptive quantization with mixed-precision based on low-cost proxy

2024-02-27 · Junzhe Chen, Qiao Yang, Senmao Tian, Shunli Zhang

It is critical to deploy complicated neural network models on hardware with limited resources. This paper proposes a novel model quantization method, named the Low-Cost Proxy-Based Adaptive Mixed-Precision Model Quantiza…

Neural Architecture SearchQuantization

FracBits: Mixed Precision Quantization via Fractional Bit-Widths

2020-07-04 · Linjie Yang, Qing Jin

Model quantization helps to reduce model size and latency of deep neural networks. Mixed precision quantization is favorable with customized hardwares supporting arithmetic operations at multiple bit-widths to achieve ma…

Quantization

Modular Quantization-Aware Training for 6D Object Pose Estimation

2023-03-12 · Saqib Javed, Chengkun Li, Andrew Price, Yinlin Hu 외

Edge applications, such as collaborative robotics and spacecraft rendezvous, demand efficient 6D object pose estimation on resource-constrained embedded platforms. Existing 6D pose estimation networks are often too large…

6D Pose Estimation6D Pose Estimation using RGBPose EstimationQuantization

WINDQuant: Weight-Informed Neural Decision-Making for Global Mixed-Precision LLM Quantization

2026-05-26 · Phong Nam Huu Nguyen, Khoi M. Le, Cong-Duy T Nguyen, Anh Tuan Luu 외 arxiv

Quantization is an effective approach to reduce the memory footprint and inference cost of large language models (LLMs), yet maintaining performance in the ultra-low-bit regime remains challenging. Existing post-training…

Reinforcement Learning

MetaMix: Meta-state Precision Searcher for Mixed-precision Activation Quantization

2023-11-12 · Han-Byul Kim, Joo Hyung Lee, Sungjoo Yoo, Hong-Seok Kim

Mixed-precision quantization of efficient networks often suffer from activation instability encountered in the exploration of bit selections. To address this problem, we propose a novel method called MetaMix which consis…

Quantization