English
Related papers

Related papers: LSQ+: Improving low-bit quantization through learn…

200 papers

The exponentially large discrete search space in mixed-precision quantization (MPQ) makes it hard to determine the optimal bit-width for each layer. Previous works usually resort to iterative search methods on the training set, which…

Machine Learning · Computer Science 2023-03-07 Chen Tang , Kai Ouyang , Zhi Wang , Yifei Zhu , Yaowei Wang , Wen Ji , Wenwu Zhu

Quantization of the weights and activations is one of the main methods to reduce the computational footprint of Deep Neural Networks (DNNs) training. Current methods enable 4-bit quantization of the forward phase. However, this constitutes…

Machine Learning · Computer Science 2024-06-11 Brian Chmiel , Ron Banner , Elad Hoffer , Hilla Ben Yaacov , Daniel Soudry

In the era of large language models (LLMs), weight-activation quantization helps fit models on edge device by reducing memory and compute bit-widths. However, three challenges persist for energy constrained hardware: (1) even after…

Machine Learning · Computer Science 2025-10-23 Chenyu Wang , Zhanglu Yan , Zhi Zhou , Xu Chen , Weng-Fai Wong

Quantization-aware training (QAT) is an effective method to drastically reduce the memory footprint of LLMs while keeping performance degradation at an acceptable level. However, the optimal choice of quantization format and bit-width…

Machine Learning · Computer Science 2026-02-18 Sohir Maskey , Constantin Eichenberg , Johannes Messner , Douglas Orr

Large Language Models (LLMs) deliver strong performance across a wide range of NLP tasks, but their massive sizes hinder deployment on resource-constrained devices. To reduce their computational and memory burden, various compression…

Machine Learning · Computer Science 2026-05-18 Dung Anh Hoang , Cuong Pham , Cuong Nguyen , Trung le , Jianfei Cai , Thanh-Toan Do

For on-device automatic speech recognition (ASR), quantization aware training (QAT) is ubiquitous to achieve the trade-off between model predictive performance and efficiency. Among existing QAT methods, one major drawback is that the…

The use of low-bit quantization has emerged as an indispensable technique for enabling the efficient training of large-scale models. Despite its widespread empirical success, a rigorous theoretical understanding of its impact on learning…

Machine Learning · Statistics 2026-02-17 Dechen Zhang , Junwei Su , Difan Zou

Designing a deep neural network (DNN) with good generalization capability is a complex process especially when the weights are severely quantized. Model averaging is a promising approach for achieving the good generalization capability of…

Machine Learning · Computer Science 2020-02-04 Sungho Shin , Yoonho Boo , Wonyong Sung

Post-training quantization (PTQ) is a widely used approach for reducing the memory and compute costs of large language models (LLMs). Recent studies have shown that applying invertible transformations to activations can significantly…

Machine Learning · Computer Science 2026-04-27 Ofir Gordon , Lior Dikstein , Arnon Netzer , Idan Achituve , Hai Victor Habi

Shift neural networks reduce computation complexity by removing expensive multiplication operations and quantizing continuous weights into low-bit discrete values, which are fast and energy efficient compared to conventional neural…

Computer Vision and Pattern Recognition · Computer Science 2021-12-08 Xinlin Li , Bang Liu , Yaoliang Yu , Wulong Liu , Chunjing Xu , Vahid Partovi Nia

Quantization of neural networks provides benefits of inference in less compute and memory requirements. Previous work in quantization lack two important aspects which this work provides. First almost all previous work in quantization used a…

Computer Vision and Pattern Recognition · Computer Science 2025-12-12 Zia Badar

Large language models (LLMs) achieve impressive performance across domains but face significant challenges when deployed on consumer-grade GPUs or personal devices such as laptops, due to high memory consumption and inference costs.…

Machine Learning · Computer Science 2026-02-02 Li Lin , Xinyu Hu , Xiaojun Wan

4-bit and lower precision mobile models are required due to the ever-increasing demand for better energy efficiency in mobile devices. In this work, we report that the activation instability induced by weight quantization (AIWQ) is the key…

Computer Vision and Pattern Recognition · Computer Science 2020-08-12 Eunhyeok Park , Sungjoo Yoo

Quantization techniques commonly reduce the inference costs of neural networks by restricting the precision of weights and activations. Recent studies show that also reducing the precision of the accumulator can further improve hardware…

Machine Learning · Computer Science 2024-01-22 Ian Colbert , Alessandro Pappalardo , Jakoba Petri-Koenig , Yaman Umuroglu

Large Language Models (LLMs) stand out for their impressive performance in intricate language modeling tasks. However, their demanding computational and memory needs pose obstacles for broad use on edge devices. Quantization is then…

Machine Learning · Computer Science 2025-04-22 Xuan Shen , Peiyan Dong , Lei Lu , Zhenglun Kong , Zhengang Li , Ming Lin , Chao Wu , Yanzhi Wang

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…

Computer Vision and Pattern Recognition · Computer Science 2019-12-02 Jiwei Yang , Xu Shen , Jun Xing , Xinmei Tian , Houqiang Li , Bing Deng , Jianqiang Huang , Xiansheng Hua

Despite the outstanding performance of transformers in both language and vision tasks, the expanding computation and model size have increased the demand for efficient deployment. To address the heavy computation and parameter drawbacks,…

Machine Learning · Computer Science 2024-10-15 Xijie Huang , Zhiqiang Shen , Pingcheng Dong , Kwang-Ting Cheng

Post-training quantization (PTQ) techniques applied to weights, activations, and the KV cache greatly reduce memory usage, latency, and power consumption of Large Language Models (LLMs), but may lead to large quantization errors when…

Large language models can be quantized to reduce inference time latency, model size, and energy consumption, thereby delivering a better user experience at lower cost. A challenge exists to deliver quantized models with minimal loss of…

Machine Learning · Computer Science 2025-07-24 Steven K. Esser , Jeffrey L. McKinstry , Deepika Bablani , Rathinakumar Appuswamy , Dharmendra S. Modha

Weight quantization effectively reduces memory consumption and enable the deployment of Large Language Models on edge devices, yet existing hardware-friendly methods often rely on uniform quantization, which suffers from poor…

Machine Learning · Computer Science 2026-02-03 Xin Nie , Liang Dong , Haicheng Zhang , Jiawang Xiao , G. Sun