Related papers: Extremely Low Bit Transformer Quantization for On-…

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 maximum efficiency. We…

We investigate the compression of deep neural networks by quantizing their weights and activations into multiple binary bases, known as multi-bit networks (MBNs), which accelerate the inference and reduce the storage for the deployment on…

Post-training model quantization is a widely adopted technique for reducing the memory and computational costs of large language models (LLMs). However, most existing methods rely on uniform or heuristic bitwidth assignments, failing to…

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…

Low-bit quantization is widely used to compress super-resolution (SR) models and reduce storage and computation costs for deployment on resource-limited devices. However, when SR models are pushed to ultra-low precision (2-4 bits),…

Morphological modeling in neural machine translation (NMT) is a promising approach to achieving open-vocabulary machine translation for morphologically-rich languages. However, existing methods such as sub-word tokenization and…

The deployment of Quantized Neural Networks (QNNs) on resource-constrained edge devices, such as microcontrollers (MCUs), introduces fundamental challenges in balancing model performance, computational complexity, and memory constraints.…

Quantization is a popular technique that $transforms$ the parameter representation of a neural network from floating-point numbers into lower-precision ones ($e.g.$, 8-bit integers). It reduces the memory footprint and the computational…

Quantized Neural Networks (QNNs), which use low bitwidth numbers for representing parameters and performing computations, have been proposed to reduce the computation complexity, storage size and memory usage. In QNNs, parameters and…

Recently, there is a high demand for deploying DeepSeek-R1 and V3 locally, possibly because the official service often suffers from being busy and some organizations have data privacy concerns. While single-machine deployment offers…

We study weight-only post-training quantization (PTQ), which quantizes the weights of a large language model (LLM) without retraining, using little or no calibration data. Weight-only PTQ is crucial for reducing the memory footprint and…

Transformer architectures based on the attention mechanism have revolutionized natural language processing (NLP), driving major breakthroughs across virtually every NLP task. However, their substantial memory and computational requirements…

We report on aggressive quantization strategies that greatly accelerate inference of Recurrent Neural Network Transducers (RNN-T). We use a 4 bit integer representation for both weights and activations and apply Quantization Aware Training…

This paper explores the adaptation of Transformerbased models for edge devices through the quantisation and hardware acceleration of the ARM Keyword Transformer (KWT) model on a RISC-V platform. The model was targeted to run on 64kB RAM in…

Deep neural networks (DNN) have achieved impressive success in multiple domains. Over the years, the accuracy of these models has increased with the proliferation of deeper and more complex architectures. Thus, state-of-the-art solutions…

Quantization methods reduce the number of bits required to represent each parameter in a model, trading accuracy for smaller memory footprints and inference latencies. However, the final model size depends on both the number of parameters…

Embedding Artificial Intelligence onto low-power devices is a challenging task that has been partly overcome with recent advances in machine learning and hardware design. Presently, deep neural networks can be deployed on embedded targets…

Extreme compression, particularly ultra-low bit precision (binary/ternary) quantization, has been proposed to fit large NLP models on resource-constraint devices. However, to preserve the accuracy for such aggressive compression schemes,…

Neural network quantization is frequently used to optimize model size, latency and power consumption for on-device deployment of neural networks. In many cases, a target bit-width is set for an entire network, meaning every layer get…

In this paper we present a simple and computationally efficient quantization scheme that enables us to reduce the resolution of the parameters of a neural network from 32-bit floating point values to 8-bit integer values. The proposed…