English
Related papers

Related papers: Optimal Formats for Weight Quantisation

200 papers

This work studies post-training parameter quantization in large language models (LLMs). We introduce quantization with incoherence processing (QuIP), a new method based on the insight that quantization benefits from $\textit{incoherent}$…

Machine Learning · Computer Science 2024-01-17 Jerry Chee , Yaohui Cai , Volodymyr Kuleshov , Christopher De Sa

Large Language Models (LLMs) have shown an impressive capability in code generation. The LLM effectiveness generally increases with its size: The higher the number of LLM's trainable parameters the better its ability to implement code.…

Software Engineering · Computer Science 2026-01-28 Alessandro Giagnorio , Antonio Mastropaolo , Saima Afrin , Massimiliano Di Penta , Gabriele Bavota

Vector Quantization (VQ) is an appealing model compression method to obtain a tiny model with less accuracy loss. While methods to obtain better codebooks and codes under fixed clustering dimensionality have been extensively studied,…

Computer Vision and Pattern Recognition · Computer Science 2022-11-22 Zezhou Zhu , Yucong Zhou , Zhao Zhong

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…

Machine Learning · Computer Science 2025-06-09 Chao Zhang , Li Wang , Samson Lasaulce , Merouane Debbah

Quantization is a fundamental optimization for many machine-learning use cases, including compressing gradients, model weights and activations, and datasets. The most accurate form of quantization is \emph{adaptive}, where the error is…

Machine Learning · Computer Science 2025-08-01 Ran Ben-Basat , Yaniv Ben-Itzhak , Michael Mitzenmacher , Shay Vargaftik

The realization of scalable fault-tolerant quantum computing is expected to hinge on quantum error-correcting codes. In the quest for more efficient quantum fault tolerance, a critical code parameter is the weight of measurements that…

Quantum Physics · Physics 2025-02-21 Austin Yubo He , Zi-Wen Liu

Neural network quantization is widely used to reduce model inference complexity in real-world deployments. However, traditional integer quantization suffers from accuracy degradation when adapting to various dynamic ranges. Recent research…

Performance · Computer Science 2023-10-30 Zhuoyi Zhang , Yunchen Zhang , Gonglei Shi , Yu Shen , Ruihao Gong , Xiaoxu Xia , Qi Zhang , Lewei Lu , Xianglong Liu

Recent studies introduced effective compression techniques for Large Language Models (LLMs) via post-training quantization or low-bit weight representation. Although quantized weights offer storage efficiency and allow for faster inference,…

Computation and Language · Computer Science 2024-05-02 Irina Proskurina , Luc Brun , Guillaume Metzler , Julien Velcin

As large language models (LLMs) grow in size, efficient compression techniques like quantization and sparsification are critical. While quantization maintains performance with reduced precision, structured sparsity methods, such as N:M…

Machine Learning · Computer Science 2026-04-21 Egor Maximov , Yulia Kuzkina , Azamat Kanametov , Alexander Prutko , Aleksei Goncharov , Maxim Zhelnin , Egor Shvetsov

Large language models (LLMs) have significantly advanced natural language processing, but their massive parameter counts create substantial computational and memory challenges during deployment. Post-training quantization (PTQ) has emerged…

Machine Learning · Computer Science 2025-11-25 Cuong Pham , Hoang Anh Dung , Cuong C. Nguyen , Trung Le , Gustavo Carneiro , Thanh-Toan Do

Multi-bit quantization networks enable flexible deployment of deep neural networks by supporting multiple precision levels within a single model. However, existing approaches suffer from significant training overhead as full-dataset updates…

Computer Vision and Pattern Recognition · Computer Science 2025-10-24 Jinhee Kim , Jae Jun An , Kang Eun Jeon , Jong Hwan Ko

The practical deployment of diffusion models is still hindered by the high memory and computational overhead. Although quantization paves a way for model compression and acceleration, existing methods face challenges in achieving low-bit…

Computer Vision and Pattern Recognition · Computer Science 2025-07-16 Haoxuan Wang , Yuzhang Shang , Zhihang Yuan , Junyi Wu , Junchi Yan , Yan Yan

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

Model quantization has become essential for efficient large language model deployment, yet existing approaches involve clear trade-offs: methods such as GPTQ and AWQ achieve practical compression but are lossy, while lossless techniques…

Machine Learning · Computer Science 2026-05-05 Michael Helcig , Eldar Kurtic , Dan Alistarh

Recent works on compression of large language models (LLM) using quantization considered reparameterizing the architecture such that weights are distributed on the sphere. This demonstratively improves the ability to quantize by increasing…

Machine Learning · Computer Science 2024-12-05 Tycho F. A. van der Ouderaa , Maximilian L. Croci , Agrin Hilmkil , James Hensman

Latent Diffusion Models (LDMs) capture the dynamic evolution of latent variables over time, blending patterns and multimodality in a generative system. Despite the proficiency of LDM in various applications, such as text-to-image…

Computer Vision and Pattern Recognition · Computer Science 2023-12-12 Yuewei Yang , Xiaoliang Dai , Jialiang Wang , Peizhao Zhang , Hongbo Zhang

Deep learning models are the most efficient models in many machine learning tasks. The main disadvantage when using them in IoT, mobile devices, independent autonomous or real-time systems is their complexity and memory size. Therefore,…

Machine Learning · Computer Science 2026-05-08 Marcin Pietroń

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…

Computer Vision and Pattern Recognition · Computer Science 2025-04-15 Wenjin Ke , Zhe Li , Dong Li , Lu Tian , Emad Barsoum

Quantized neural networks with low-bit weights and activations are attractive for developing AI accelerators. However, the quantization functions used in most conventional quantization methods are non-differentiable, which increases the…

Computer Vision and Pattern Recognition · Computer Science 2020-09-21 Zhaohui Yang , Yunhe Wang , Kai Han , Chunjing Xu , Chao Xu , Dacheng Tao , Chang Xu

Large Language Models (LLMs) excel in NLP, but their demands hinder their widespread deployment. While Quantization-Aware Training (QAT) offers a solution, its extensive training costs make Post-Training Quantization (PTQ) a more practical…

Computation and Language · Computer Science 2024-04-09 Jing Liu , Ruihao Gong , Xiuying Wei , Zhiwei Dong , Jianfei Cai , Bohan Zhuang