English
Related papers

Related papers: Adaptive Block-Scaled Data Types

200 papers

Improving the deployment efficiency of transformer-based language models has been challenging given their high computation and memory cost. While INT8 quantization has recently been shown to be effective in reducing both the memory cost and…

Computation and Language · Computer Science 2023-06-01 Xiaoxia Wu , Cheng Li , Reza Yazdani Aminabadi , Zhewei Yao , Yuxiong He

In the complex domain of large language models (LLMs), striking a balance between computational efficiency and maintaining model quality is a formidable challenge. Navigating the inherent limitations of uniform quantization, particularly…

Machine Learning · Computer Science 2023-07-24 Xiaoxia Wu , Zhewei Yao , Yuxiong He

Recent advances in deep learning methods such as LLMs and Diffusion models have created a need for improved quantization methods that can meet the computational demands of these modern architectures while maintaining accuracy. Towards this…

Machine Learning · Computer Science 2024-04-02 Haihao Shen , Naveen Mellempudi , Xin He , Qun Gao , Chang Wang , Mengni Wang

Large language models (LLMs) show great performance in various tasks, but face deployment challenges from limited memory capacity and bandwidth. Low-bit weight quantization can save memory and accelerate inference. Although floating-point…

Computation and Language · Computer Science 2023-11-06 Yijia Zhang , Sicheng Zhang , Shijie Cao , Dayou Du , Jianyu Wei , Ting Cao , Ningyi Xu

Diffusion models have been achieving remarkable performance in face restoration. However, the heavy computations hamper the widespread adoption of these models. In this work, we propose QuantFace, a novel low-bit quantization framework for…

Computer Vision and Pattern Recognition · Computer Science 2025-11-24 Jiatong Li , Libo Zhu , Haotong Qin , Jingkai Wang , Linghe Kong , Guihai Chen , Yulun Zhang , Xiaokang Yang

The increasing computational demands of foundation models have spurred research into low-precision training, with 4-bit floating-point (\texttt{FP4}) formats emerging as a frontier for maximizing hardware throughput. While numerous…

Machine Learning · Computer Science 2025-09-23 Robert Hu , Carlo Luschi , Paul Balanca

Large Language Models (LLMs) training is prohibitively expensive, driving interest in low-precision fully-quantized training (FQT). While novel 4-bit formats like NVFP4 offer substantial efficiency gains, achieving near-lossless training at…

Machine Learning · Computer Science 2026-05-12 Yuxiang Chen , Yifan Liu , Xiaoming Xu , Pengle Zhang , Michael Beyer , Martin Rapp , Jun Zhu , Jianfei Chen

Large language models (LLMs) demand substantial computational and memory resources, creating deployment challenges. Quantization-aware training (QAT) addresses these challenges by reducing model precision while maintaining performance.…

Machine Learning · Computer Science 2025-05-21 Mengzhao Chen , Chaoyi Zhang , Jing Liu , Yutao Zeng , Zeyue Xue , Zhiheng Liu , Yunshui Li , Jin Ma , Jie Huang , Xun Zhou , Ping Luo

The inference of Large language models (LLMs) requires immense computation and memory resources. To curtail these costs, quantisation has merged as a promising solution, but existing LLM quantisation mainly focuses on 8-bit. In this work,…

Machine Learning · Computer Science 2024-03-15 Cheng Zhang , Jianyi Cheng , Ilia Shumailov , George A. Constantinides , Yiren Zhao

Large language models (LLMs), with their billions of parameters, pose substantial challenges for deployment on edge devices, straining both memory capacity and computational resources. Block Floating Point (BFP) quantisation reduces memory…

Hardware Architecture · Computer Science 2025-04-23 Xiaomeng Han , Yuan Cheng , Jing Wang , Junyang Lu , Hui Wang , X. x. Zhang , Ning Xu , Dawei Yang , Zhe Jiang

Modern deep neural network (DNN) models generally require a huge amount of weight and activation values to achieve good inference outcomes. Those data inevitably demand a massive off-chip memory capacity/bandwidth, and the situation gets…

Machine Learning · Computer Science 2021-04-27 Cheng-Wei Huang , Tim-Wei Chen , Juinn-Dar Huang

The transformer architectures with attention mechanisms have obtained success in Nature Language Processing (NLP), and Vision Transformers (ViTs) have recently extended the application domains to various vision tasks. While achieving high…

Machine Learning · Computer Science 2022-02-21 Mengshu Sun , Haoyu Ma , Guoliang Kang , Yifan Jiang , Tianlong Chen , Xiaolong Ma , Zhangyang Wang , Yanzhi Wang

The IEEE 754 floating-point standard is the bedrock of modern computing, but its structural requirements -- a hidden leading bit, Base-2 bit-level normalization, and Sign-Magnitude encoding -- impose significant silicon area and power…

Hardware Architecture · Computer Science 2026-03-11 Keita Morisaki

Deep neural networks (DNNs) are powerful for cognitive tasks such as image classification, object detection, and scene segmentation. One drawback however is the significant high computational complexity and memory consumption, which makes…

Computer Vision and Pattern Recognition · Computer Science 2024-09-26 Yongqi Xu , Yujian Lee , Gao Yi , Bosheng Liu , Yucong Chen , Peng Liu , Jigang Wu , Xiaoming Chen , Yinhe Han

Diffusion models are emerging models that generate images by iteratively denoising random Gaussian noise using deep neural networks. These models typically exhibit high computational and memory demands, necessitating effective post-training…

Computer Vision and Pattern Recognition · Computer Science 2024-08-14 Cheng Chen , Christina Giannoula , Andreas Moshovos

Microscaling Floating-Point (MXFP) has emerged as a promising low-precision format for large language models (LLMs). Despite various post-training quantization (PTQ) algorithms being proposed, they mostly focus on integer quantization,…

Computation and Language · Computer Science 2026-01-15 Manyi Zhang , Ji-Fu Li , Zhongao Sun , Haoli Bai , Hui-Ling Zhen , Zhenhua Dong , Xianzhi Yu

The MXFP4 microscaling format, which partitions tensors into blocks of 32 elements sharing an E8M0 scaling factor, has emerged as a promising substrate for efficient LLM inference, backed by native hardware support on NVIDIA Blackwell…

Computer Vision and Pattern Recognition · Computer Science 2026-04-22 Haokun Lin , Xinle Jia , Haobo Xu , Bingchen Yao , Xianglong Guo , Yichen Wu , Zhichao Lu , Ying Wei , Qingfu Zhang , Zhenan Sun

Quantization enables efficient acceleration of deep neural networks by reducing model memory footprint and exploiting low-cost integer math hardware units. Quantization maps floating-point weights and activations in a trained model to…

Machine Learning · Computer Science 2021-02-11 Steve Dai , Rangharajan Venkatesan , Haoxing Ren , Brian Zimmer , William J. Dally , Brucek Khailany

Quantized low-precision neural networks are very popular because they require less computational resources for inference and can provide high performance, which is vital for real-time and embedded recognition systems. However, their…

Computer Vision and Pattern Recognition · Computer Science 2020-10-21 Anton Trusov , Elena Limonova , Dmitry Slugin , Dmitry Nikolaev , Vladimir V. Arlazarov

Quantization is a proven effective method for compressing large language models. Although popular techniques like W8A8 and W4A16 effectively maintain model performance, they often fail to concurrently speed up the prefill and decoding…

Machine Learning · Computer Science 2024-08-01 Ying Zhang , Peng Zhang , Mincong Huang , Jingyang Xiang , Yujie Wang , Chao Wang , Yineng Zhang , Lei Yu , Chuan Liu , Wei Lin