English
Related papers

Related papers: TurboBoA: Faster and Exact Attention-aware Quantiz…

200 papers

Large language models (LLMs) require substantial compute, and thus energy, at inference time. While quantizing weights and activations is effective at improving efficiency, naive quantization of LLMs can significantly degrade performance…

Machine Learning · Computer Science 2025-06-06 Boris van Breugel , Yelysei Bondarenko , Paul Whatmough , Markus Nagel

Large language models have significantly advanced natural language processing, yet their heavy resource demands pose severe challenges regarding hardware accessibility and energy consumption. This paper presents a focused and high-level…

Artificial Intelligence · Computer Science 2025-05-14 Tollef Emil Jørgensen

Quantization is critical for efficiently deploying large language models (LLMs). Yet conventional methods remain hardware-agnostic, limited to bit-width constraints, and do not account for intrinsic circuit characteristics such as the…

Hardware Architecture · Computer Science 2025-11-18 Rohan Juneja , Shivam Aggarwal , Safeen Huda , Tulika Mitra , Li-Shiuan Peh

In this paper, we address post-training quantization (PTQ) for large language models (LLMs) from an overlooked perspective: given a pre-trained high-precision LLM, the predominant sequential quantization framework treats different layers…

Artificial Intelligence · Computer Science 2026-03-27 Shigeng Wang , Chao Li , Yangyuxuan Kang , Jiawei Fan , Zhonghong Ou , Anbang Yao

Post-training quantization (PTQ) is essential for deploying large diffusion transformers on resource-constrained hardware, but aggressive 4-bit quantization significantly degrades generative performance. Low-rank approximation methods have…

Machine Learning · Computer Science 2026-04-21 Yann Bouquet , Alireza Khodamoradi , Sophie Yáng Shen , Kristof Denolf , Mathieu Salzmann

Post-training quantization is a key technique for reducing the memory and inference latency of large language models by quantizing weights and activations without requiring retraining. However, existing methods either (1) fail to account…

Machine Learning · Computer Science 2025-09-23 Jinuk Kim , Marwa El Halabi , Wonpyo Park , Clemens JS Schaefer , Deokjae Lee , Yeonhong Park , Jae W. Lee , Hyun Oh Song

Memory-efficient finetuning of large language models (LLMs) has recently attracted huge attention with the increasing size of LLMs, primarily due to the constraints posed by GPU memory limitations and the effectiveness of these methods…

Machine Learning · Computer Science 2024-06-24 Baohao Liao , Christian Herold , Shahram Khadivi , Christof Monz

Tiny machine learning (tinyML) has emerged during the past few years aiming to deploy machine learning models to embedded AI processors with highly constrained memory and computation capacity. Low precision quantization is an important…

Large language models (LLMs) deliver impressive results for a variety of tasks, but state-of-the-art systems require fast GPUs with large amounts of memory. To reduce both the memory and latency of these systems, practitioners quantize…

Computer Vision and Pattern Recognition · Computer Science 2026-01-22 Gautom Das , Vincent La , Ethan Lau , Abhinav Shrivastava , Matthew Gwilliam

Quantization-aware training (QAT) schemes have been shown to achieve near-full precision accuracy. They accomplish this by training a quantized model for multiple epochs. This is computationally expensive, mainly because of the full…

Machine Learning · Computer Science 2024-11-19 Saleh Ashkboos , Bram Verhoef , Torsten Hoefler , Evangelos Eleftheriou , Martino Dazzi

Post-training quantization (PTQ) is the go-to compression technique for large generative models, such as stable diffusion or large language models. PTQ methods commonly keep the softmax activation in higher precision as it has been shown to…

Machine Learning · Computer Science 2023-09-06 Nilesh Prasad Pandey , Marios Fournarakis , Chirag Patel , Markus Nagel

AutoRegressive Visual Generation (ARVG) models retain an architecture compatible with language models, while achieving performance comparable to diffusion-based models. Quantization is commonly employed in neural networks to reduce model…

Computer Vision and Pattern Recognition · Computer Science 2026-01-30 Xuewen Liu , Zhikai Li , Jing Zhang , Mengjuan Chen , Qingyi Gu

The increasing adoption of large language models (LLMs) on heterogeneous computing platforms poses significant challenges to achieving high inference efficiency. To address these efficiency bottlenecks across diverse platforms, this paper…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-02-06 Yaozheng Zhang , Wei Wang , Jie Kong , Jiehan Zhou , Xianwei Zhang , Huanqing Cui , Han Bao , Yuhai Liu

Denoising diffusion models have emerged as state-of-the-art in generative tasks across image, audio, and video domains, producing high-quality, diverse, and contextually relevant data. However, their broader adoption is limited by high…

Sound · Computer Science 2024-09-24 Jayneel Vora , Aditya Krishnan , Nader Bouacida , Prabhu RV Shankar , Prasant Mohapatra

As large language models (LLMs) become more prevalent, there is a growing need for new and improved quantization methods that can meet the computationalast layer demands of these modern architectures while maintaining the accuracy. In this…

Computation and Language · Computer Science 2023-10-18 Wenhua Cheng , Yiyang Cai , Kaokao Lv , Haihao Shen

When quantizing weights and activations to increasingly narrower representations, the cost of additions begins to dominate that of multiplications in multiply-accumulate (MAC) units. Recent studies show that reducing addition costs via…

Machine Learning · Computer Science 2025-08-01 Ian Colbert , Giuseppe Franco , Fabian Grob , Jinjie Zhang , Rayan Saab

Quantization is essential for deploying large language models (LLMs) on resource-constrained hardware, but its implications for multilingual tasks remain underexplored. We conduct the first large-scale evaluation of post-training…

Computation and Language · Computer Science 2025-08-29 Benjamin Marie , Atsushi Fujita

We study the challenging task of neural network quantization without end-to-end retraining, called Post-training Quantization (PTQ). PTQ usually requires a small subset of training data but produces less powerful quantized models than…

Machine Learning · Computer Science 2021-07-27 Yuhang Li , Ruihao Gong , Xu Tan , Yang Yang , Peng Hu , Qi Zhang , Fengwei Yu , Wei Wang , Shi Gu

Diffusion models have recently dominated image synthesis tasks. However, the iterative denoising process is expensive in computations at inference time, making diffusion models less practical for low-latency and scalable real-world…

Computer Vision and Pattern Recognition · Computer Science 2023-11-02 Yefei He , Luping Liu , Jing Liu , Weijia Wu , Hong Zhou , Bohan Zhuang

One of the challenges of quantizing a large language model (LLM) is the presence of outliers. Outliers often make uniform quantization schemes less effective, particularly in extreme cases such as 4-bit quantization. We introduce KurTail, a…

Machine Learning · Computer Science 2025-03-04 Mohammad Sadegh Akhondzadeh , Aleksandar Bojchevski , Evangelos Eleftheriou , Martino Dazzi