English
Related papers

Related papers: Efficient 8-Bit Quantization of Transformer Neural…

200 papers

Attentional sequence-to-sequence models have become the new standard for machine translation, but one challenge of such models is a significant increase in training and decoding cost compared to phrase-based systems. Here, we focus on…

Computation and Language · Computer Science 2017-05-08 Jacob Devlin

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 and memory access,…

Signal Processing · Electrical Eng. & Systems 2020-03-06 Chen Wu , Mingyu Wang , Xiayu Li , Jicheng Lu , Kun Wang , Lei He

Quantization for deep neural networks (DNN) have enabled developers to deploy models with less memory and more efficient low-power inference. However, not all DNN designs are friendly to quantization. For example, the popular Mobilenet…

Computer Vision and Pattern Recognition · Computer Science 2020-11-17 Thu Dinh , Andrey Melnikov , Vasilios Daskalopoulos , Sek Chai

Recent advancements in machine learning achieved by Deep Neural Networks (DNNs) have been significant. While demonstrating high accuracy, DNNs are associated with a huge number of parameters and computations, which leads to high memory…

Machine Learning · Computer Science 2023-12-20 Babak Rokh , Ali Azarpeyvand , Alireza Khanteymoori

We explore options to use Transformer networks in neural transducer for end-to-end speech recognition. Transformer networks use self-attention for sequence modeling and comes with advantages in parallel computation and capturing contexts.…

Audio and Speech Processing · Electrical Eng. & Systems 2019-10-30 Ching-Feng Yeh , Jay Mahadeokar , Kaustubh Kalgaonkar , Yongqiang Wang , Duc Le , Mahaveer Jain , Kjell Schubert , Christian Fuegen , Michael L. Seltzer

We introduce a quantization-aware training algorithm that guarantees avoiding numerical overflow when reducing the precision of accumulators during inference. We leverage weight normalization as a means of constraining parameters during…

Machine Learning · Computer Science 2023-02-01 Ian Colbert , Alessandro Pappalardo , Jakoba Petri-Koenig

As large language models become increasingly prevalent, memory bandwidth constraints significantly limit inference throughput, motivating post-training quantization (PTQ). In this paper, we propose FireQ, a co-designed PTQ framework and an…

Machine Learning · Computer Science 2025-07-21 Daehyeon Baek , Jieun Choi , Jimyoung Son , Kyungmin Bin , Seungbeom Choi , Kihyo Moon , Minsung Jang , Hyojung Lee

Vision Transformer (ViT)-based models have shown state-of-the-art performance (e.g., accuracy) in vision-based AI tasks. However, realizing their capability in resource-constrained embedded AI systems is challenging due to their inherent…

Neural and Evolutionary Computing · Computer Science 2026-01-06 Rachmad Vidya Wicaksana Putra , Saad Iftikhar , Muhammad Shafique

Quantization for deep neural networks have afforded models for edge devices that use less on-board memory and enable efficient low-power inference. In this paper, we present a comparison of model-parameter driven quantization approaches…

Computer Vision and Pattern Recognition · Computer Science 2019-10-14 Prateeth Nayak , David Zhang , Sek Chai

We investigate the effects of post-training quantization and quantization-aware training on the generalization of Transformer language models. We present a new method called self-distilled quantization (SDQ) that minimizes accumulative…

Computation and Language · Computer Science 2023-07-13 James O' Neill , Sourav Dutta

Pre-trained language models like Ernie or Bert are currently used in many applications. These models come with a set of pre-trained weights typically obtained in unsupervised/self-supervised modality on a huge amount of data. After that,…

Machine Learning · Statistics 2021-06-29 Andrea Zanetti

Using medical imaging as case-study, we demonstrate how Intel-optimized TensorFlow on an x86-based server equipped with 2nd Generation Intel Xeon Scalable Processors with large system memory allows for the training of memory-intensive…

Machine Learning · Computer Science 2020-03-20 David Ojika , Bhavesh Patel , G. Anthony Reina , Trent Boyer , Chad Martin , Prashant Shah

Modern deployment often requires trading accuracy for efficiency under tight CPU and memory constraints, yet common compression proxies such as parameter count or FLOPs do not reliably predict wall-clock inference time. In particular,…

Machine Learning · Computer Science 2026-04-10 Longsheng Zhou , Yu Shen

Deep neural network (DNN)-based policy models like vision-language-action (VLA) models are transformative in automating complex decision-making across applications by interpreting multi-modal data. However, scaling these models greatly…

Robotics · Computer Science 2024-12-03 Seongmin Park , Hyungmin Kim , Wonseok Jeon , Juyoung Yang , Byeongwook Jeon , Yoonseon Oh , Jungwook Choi

Adjusting the latency, power, and accuracy of natural language understanding models is a desirable objective of an efficient architecture. This paper proposes an efficient Transformer architecture that adjusts the inference computational…

Computation and Language · Computer Science 2024-09-20 Sajjad Kachuee , Mohammad Sharifkhani

Quantization is a practical technique for making large language models easier to deploy by reducing the precision used to store and operate on model weights. This can lower memory use and improve runtime feasibility on constrained hardware,…

Machine Learning · Computer Science 2026-01-22 Uygar Kurt

Deploying Large Language Models (LLMs) efficiently on edge devices is often constrained by limited memory capacity and high power consumption. Low-bit quantization methods, particularly ternary quantization, have demonstrated significant…

Hardware Architecture · Computer Science 2025-05-02 Chenyang Yin , Zhenyu Bai , Pranav Venkatram , Shivam Aggarwal , Zhaoying Li , Tulika Mitra

Integer AI inference significantly reduces computational complexity in embedded systems. Quantization-aware training (QAT) helps mitigate accuracy degradation associated with post-training quantization but still overlooks the impact of…

Machine Learning · Computer Science 2025-10-14 Lion Mueller , Alberto Garcia-Ortiz , Ardalan Najafi , Adam Fuks , Lennart Bamberg

We introduce a data-free quantization method for deep neural networks that does not require fine-tuning or hyperparameter selection. It achieves near-original model performance on common computer vision architectures and tasks. 8-bit…

Machine Learning · Computer Science 2019-11-26 Markus Nagel , Mart van Baalen , Tijmen Blankevoort , Max Welling

Large Language Models (LLMs) have showcased remarkable impacts across a wide spectrum of natural language processing tasks. Fine-tuning these pretrained models on downstream datasets provides further significant performance gains; however,…

Computation and Language · Computer Science 2026-03-19 Zhikai Li , Xiaoxuan Liu , Banghua Zhu , Zhen Dong , Qingyi Gu , Kurt Keutzer