English
Related papers

Related papers: MPQ-DM: Mixed Precision Quantization for Extremely…

200 papers

Today, large language models have demonstrated their strengths in various tasks ranging from reasoning, code generation, and complex problem solving. However, this advancement comes with a high computational cost and memory requirements,…

Machine Learning · Computer Science 2026-03-26 Meriem Bouzouad , Yuan-Hao Chang , Jalil Boukhobza

Quantization is wildly taken as a model compression technique, which obtains efficient models by converting floating-point weights and activations in the neural network into lower-bit integers. Quantization has been proven to work well on…

Computer Vision and Pattern Recognition · Computer Science 2022-09-15 Lingran Zhao , Zhen Dong , Kurt Keutzer

Quantized neural networks are well known for reducing the latency, power consumption, and model size without significant harm to the performance. This makes them highly appropriate for systems with limited resources and low power capacity.…

Machine Learning · Computer Science 2024-06-11 Moshe Kimhi , Tal Rozen , Avi Mendelson , Chaim Baskin

Deploying Vision-Language Models (VLMs) on edge devices (e.g., smartphones and robots) is crucial for enabling low-latency and privacy-preserving intelligent applications. Given the resource constraints of these devices, quantization offers…

Computer Vision and Pattern Recognition · Computer Science 2025-11-13 Tianyu Guo , Shanwei Zhao , Shiai Zhu , Chenguang Ma

Inference time, model size, and accuracy are three key factors in deep model compression. Most of the existing work addresses these three key factors separately as it is difficult to optimize them all at the same time. For example, low-bit…

Computer Vision and Pattern Recognition · Computer Science 2023-07-18 Dan Liu , Xi Chen , Jie Fu , Chen Ma , Xue Liu

Diffusion-based large language models (DLLMs) have shown promise for non-autoregressive text generation, but their deployment is constrained by large model sizes and heavy computational costs. Post-training quantization (PTQ), a widely used…

Computation and Language · Computer Science 2025-08-27 Chen Xu , Dawei Yang

Diffusion Transformers (DiTs) enable high-quality audio synthesis but are often computationally intensive and require substantial storage, which limits their practical deployment. In this paper, we present a comprehensive evaluation of…

Audio and Speech Processing · Electrical Eng. & Systems 2025-10-02 Tanmay Khandelwal , Magdalena Fuentes

Diffusion models have transformed image synthesis by establishing unprecedented quality and creativity benchmarks. Nevertheless, their large-scale deployment faces challenges due to computationally intensive iterative denoising processes.…

Computer Vision and Pattern Recognition · Computer Science 2026-04-02 Songwei Liu , Chao Zeng , Chenqian Yan , Xurui Peng , Xing Wang , Fangmin Chen , Xing Mei

Large Mixture of Experts (MoE) models could achieve state-of-the-art quality on various language tasks, including machine translation task, thanks to the efficient model scaling capability with expert parallelism. However, it has brought a…

Machine Learning · Computer Science 2023-10-05 Young Jin Kim , Raffy Fahim , Hany Hassan Awadalla

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

Video diffusion models (DMs) have enabled high-quality video synthesis. Yet, their substantial computational and memory demands pose serious challenges to real-world deployment, even on high-end GPUs. As a commonly adopted solution,…

Computer Vision and Pattern Recognition · Computer Science 2026-01-29 Yushi Huang , Ruihao Gong , Jing Liu , Yifu Ding , Chengtao Lv , Haotong Qin , Jun Zhang

Neural networks commonly execute on hardware accelerators such as NPUs and GPUs for their size and computation overhead. These accelerators are costly and it is hard to scale their resources to handle real-time workload fluctuations. We…

Machine Learning · Computer Science 2025-10-06 Jaemin Kim , Hongjun Um , Sungkyun Kim , Yongjun Park , Jiwon Seo

Mixed-precision quantization can potentially achieve the optimal tradeoff between performance and compression rate of deep neural networks, and thus, have been widely investigated. However, it lacks a systematic method to determine the…

Machine Learning · Computer Science 2021-02-23 Huanrui Yang , Lin Duan , Yiran Chen , Hai Li

Data-free quantization (DFQ) is a technique that creates a lightweight network from its full-precision counterpart without the original training data, often through a synthetic dataset. Although several DFQ methods have been proposed for…

Machine Learning · Computer Science 2025-04-15 Kanghyun Choi , Hye Yoon Lee , Dain Kwon , SunJong Park , Kyuyeun Kim , Noseong Park , Jonghyun Choi , Jinho Lee

Quantization is an effective technique to reduce memory footprint, inference latency, and power consumption of deep learning models. However, existing quantization methods suffer from accuracy degradation compared to full-precision (FP)…

Machine Learning · Computer Science 2022-10-14 Zheng Wang , Juncheng B Li , Shuhui Qu , Florian Metze , Emma Strubell

We investigate the effects of post-training quantization and quantization-aware training on the generalization of Transformer language models. We present a new method called self-distilled quantization (SDQ) that minimizes accumulative…

Computation and Language · Computer Science 2023-07-13 James O' Neill , Sourav Dutta

The Muon optimizer has emerged as a compelling alternative to Adam for training large language models, achieving remarkable computational savings through gradient orthogonalization. However, Muon's optimizer state is more sensitive to…

Machine Learning · Computer Science 2026-05-13 Yupeng Su , Ruijie Zhang , Ziyue Liu , Yequan Zhao , Zheng Zhang

Quantization-Aware Training (QAT) is a critical technique for deploying deep neural networks on resource-constrained devices. However, existing methods often face two major challenges: the highly non-uniform distribution of activations and…

Computer Vision and Pattern Recognition · Computer Science 2025-10-23 Shaohang Jia , Zhiyong Huang , Zhi Yu , Mingyang Hou , Shuai Miao , Han Yang

Large language models (LLMs) demand extensive memory capacity during both fine-tuning and inference. To enable memory-efficient fine-tuning, existing methods apply block-wise quantization techniques, such as NF4 and AF4, to the network…

Machine Learning · Computer Science 2025-05-13 Patrick Blumenberg , Thomas Graave , Tim Fingscheidt

Upon compressing perceptually relevant signals, conventional quantization generally results in unnatural outcomes at low rates. We propose distribution preserving quantization (DPQ) to solve this problem. DPQ is a new quantization concept…

Information Theory · Computer Science 2011-08-19 Minyue Li , Janusz Klejsa , W. Bastiaan Kleijn