Related papers: Genetic Quantization-Aware Approximation for Non-L…

Quantization is a powerful tool for accelerating large language model (LLM) inference, but the accuracy-performance trade-offs across different formats remain unclear. In this paper, we conduct the most comprehensive empirical study to…

Post-Training Quantization (PTQ) and Quantization-Aware Training (QAT) represent two mainstream model quantization approaches. However, PTQ often leads to unacceptable performance degradation in quantized models, while QAT imposes…

Vision Transformers (ViTs) are essential in computer vision but are computationally intensive, too. Model quantization, particularly to low bit-widths like 4-bit, aims to alleviate this difficulty, yet existing Post-Training Quantization…

Generative Artificial Intelligence (GenAI) features such as image editing, object removal, and prompt-guided image transformation are increasingly integrated into mobile applications. However, deploying Large Vision Models (LVMs) for such…

The deployment of Vision Transformers (ViTs) on hardware platforms, specially Field-Programmable Gate Arrays (FPGAs), presents many challenges, which are mainly due to the substantial computational and power requirements of their non-linear…

Transformer-based models have revolutionized computer vision (CV) and natural language processing (NLP) by achieving state-of-the-art performance across a range of benchmarks. However, nonlinear operations in models significantly contribute…

Although deep neural networks are highly effective, their high computational and memory costs severely challenge their applications on portable devices. As a consequence, low-bit quantization, which converts a full-precision neural network…

Efficient inference is critical for deploying deep learning models on edge AI devices. Low-bit quantization (e.g., 3- and 4-bit) with fixed-point arithmetic improves efficiency, while low-power memory technologies like analog nonvolatile…

Quantized neural networks typically require smaller memory footprints and lower computation complexity, which is crucial for efficient deployment. However, quantization inevitably leads to a distribution divergence from the original…

Quantization is an essential and popular technique for improving the accessibility of large language models (LLMs) by reducing memory usage and computational costs while maintaining performance. In this study, we apply 4-bit Group Scaling…

Large Language Models (LLMs) demonstrate exceptional performance but entail significant memory and computational costs, restricting their practical deployment. While existing INT4/INT8 quantization reduces these costs, they often degrade…

Generative Pre-trained Transformer models, known as GPT or OPT, set themselves apart through breakthrough performance across complex language modelling tasks, but also by their extremely high computational and storage costs. Specifically,…

Quantization is essential for reducing the computational cost and memory usage of deep neural networks, enabling efficient inference on low-precision hardware. Despite the growing adoption of uniform and floating-point quantization schemes,…

We introduce a novel framework for Generalized Tensor Transforms (GTTs), constructed through an $n$-fold tensor product of an arbitrary $b \times b$ unitary matrix $W$. This construction generalizes many established transforms, by providing…

Improving the efficiency of inference in Large Language Models (LLMs) is a critical area of research. Post-training Quantization (PTQ) is a popular technique, but it often faces challenges at low-bit levels, particularly in downstream…

Research has shown that deep neural networks contain significant redundancy, and thus that high classification accuracy can be achieved even when weights and activations are quantized down to binary values. Network binarization on FPGAs…

Most pattern recognition models are developed on pre-proce\-ssed data. In computer vision, for instance, RGB images processed through image signal processing (ISP) pipelines designed to cater to human perception are the most frequent input…

Operating deep neural networks (DNNs) on devices with limited resources requires the reduction of their memory as well as computational footprint. Popular reduction methods are network quantization or pruning, which either reduce the word…

In Large Language Models (LLMs), the number of parameters has grown exponentially in the past few years, e.g., from 1.5 billion parameters in GPT-2 to 175 billion in GPT-3 to possibly more than trillion in higher versions. This raises a…

Methods based on weight compensation, which iteratively apply quantization and weight compensation to minimize the output error, have recently demonstrated remarkable success in quantizing Large Language Models (LLMs). The representative…