paper-with-me

홈 › Papers

Shedding the Bits: Pushing the Boundaries of Quantization with Minifloats on FPGAs

2023-11-21 · Shivam Aggarwal, Hans Jakob Damsgaard, Alessandro Pappalardo, Giuseppe Franco, Thomas B. Preußer, Michaela Blott, Tulika Mitra

Post-training quantization (PTQ) is a powerful technique for model compression, reducing the numerical precision in neural networks without additional training overhead. Recent works have investigated adopting 8-bit floating-point formats(FP8) in the context of PTQ for model inference. However, floating-point formats smaller than 8 bits and their relative comparison in terms of accuracy-hardware cost with integers remains unexplored on FPGAs. In this work, we present minifloats, which are reduced-precision floating-point formats capable of further reducing the memory footprint, latency, and energy cost of a model while approaching full-precision model accuracy. We implement a custom FPGA-based multiply-accumulate operator library and explore the vast design space, comparing minifloat and integer representations across 3 to 8 bits for both weights and activations. We also examine the applicability of various integerbased quantization techniques to minifloats. Our experiments show that minifloats offer a promising alternative for emerging workloads such as vision transformers.

📄 PDF Abstract BibTeX arXiv:2311.12359

Code (0)

등록된 구현이 없습니다.

Tasks

Model CompressionQuantization

Methods 이 논문이 사용한 방법론

Library 설명 없음

Similar Papers 제목 키워드 기반

Achieving binary weight and activation for LLMs using Post-Training Quantization

2025-04-07 · Siqing Song, Chuang Wang, Ruiqi Wang, Yi Yang 외

Quantizing large language models (LLMs) to 1-bit precision significantly reduces computational costs, but existing quantization techniques suffer from noticeable performance degradation when using weight and activation p…

Quantization

Don't Waste Your Bits! Squeeze Activations and Gradients for Deep Neural Networks via TinyScript

2020-01-01 · ICML 2020 1 · Fangcheng Fu, Yuzheng Hu, Yihan He, Jiawei Jiang 외

Recent years have witnessed intensive research interests on training deep neural networks (DNNs) more efficiently by quantization-based compression methods, which facilitate DNNs training in two ways: (1) activations are…

Quantization

ScaleBITS: Scalable Bitwidth Search for Hardware-Aligned Mixed-Precision LLMs

2026-02-06 · Xinlin Li, Timothy Chou, Josh Fromm, Zichang Liu 외 arxiv

Post-training weight quantization is crucial for reducing the memory and inference cost of large language models (LLMs), yet pushing the average precision below 4 bits remains challenging due to highly non-uniform weight…

Bi-VLM: Pushing Ultra-Low Precision Post-Training Quantization Boundaries in Vision-Language Models

2025-09-23 · Xijun Wang, Junyun Huang, Rayyan Abdalla, Chengyuan Zhang 외 arxiv

We address the critical gap between the computational demands of vision-language models and the possible ultra-low-bit weight precision (bitwidth $\leq2$ bits) we can use for higher efficiency. Our work is motivated by t…

Visual Question Answering

RobuQ: Pushing DiTs to W1.58A2 via Robust Activation Quantization

2025-09-28 · Kaicheng Yang, Xun Zhang, Haotong Qin, Yucheng Lin 외 arxiv

Diffusion Transformers (DiTs) have recently emerged as a powerful backbone for image generation, demonstrating superior scalability and performance over U-Net architectures. However, their practical deployment is hindere…

Conditional Image Generation