English
Related papers

Related papers: CodeQuant: Unified Clustering and Quantization for…

200 papers

Microscaling floating-point (MXFP) formats have emerged as a promising standard for deploying Multi-modal Large Language Models (MLLMs) and Large Language Models (LLMs) on modern accelerator architectures. However, existing Post-Training…

Computation and Language · Computer Science 2026-03-18 Ji-Fu Li , Manyi Zhang , Xiaobo Xia , Han Bao , Haoli Bai , Zhenhua Dong , Xianzhi Yu

Sparse Mixture-of-Experts (MoE) allows scaling of language and vision models efficiently by activating only a small subset of experts per input. While this reduces computation, the large number of parameters still incurs substantial memory…

Large language models (LLMs) with hundreds of billions of parameters require powerful server-grade GPUs for inference, limiting their practical deployment. To address this challenge, we introduce the outlier-aware weight quantization (OWQ)…

Computation and Language · Computer Science 2024-01-25 Changhun Lee , Jungyu Jin , Taesu Kim , Hyungjun Kim , Eunhyeok Park

Mixture of Experts (MoE) models have achieved great success by significantly improving performance while maintaining computational efficiency through sparse expert activation. However, their enormous parameter sizes and memory demands pose…

Machine Learning · Computer Science 2026-02-25 Zukang Xu , Zhixiong Zhao , Xing Hu , Zhixuan Chen , Dawei Yang

While 4-bit quantization is essential for high-throughput deployment of Large Language Models, activation outliers often lead to significant accuracy degradation due to the restricted dynamic range of low-bit formats. In this paper, we…

Machine Learning · Computer Science 2026-04-15 Zhiyuan Zhang , Yanzhao Li , Zhiqiang Zou , Bai Du , Yupeng Sun , Hui Dong , Hui Wang

Quantization for deep neural networks (DNNs) is the process of mapping the parameter values of DNNs from original data types to other data types of lower precision to reduce model sizes and make inference faster. Quantization often maps…

Machine Learning · Computer Science 2025-02-07 Jaewoo Song , Fangzhen Lin

Post-training quantization (PTQ) compresses the weights and activations of large language models (LLMs) into low-precision representations to reduce memory footprint and accelerate inference. However, the presence of outliers in weights and…

Computation and Language · Computer Science 2026-02-17 Yesheng Liang , Haisheng Chen , Zihan Zhang , Song Han , Zhijian Liu

The Mixture of Experts (MoE) architecture is an important method for scaling Large Language Models (LLMs). It increases model capacity while keeping computation cost low. However, the ultra-large MoE models still have hundreds of billions…

Artificial Intelligence · Computer Science 2025-10-01 Yixiao Chen , Yanyue Xie , Ruining Yang , Wei Jiang , Wei Wang , Yong He , Yue Chen , Pu Zhao , Yanzhi Wang

Existing weight-activation quantization methods for Large Language Models (LLMs) primarily address channel-wise outliers but often neglect token-wise outliers, which limits the accuracy of quantized models. In this work, we propose…

Machine Learning · Computer Science 2025-01-28 Mengzhao Chen , Yi Liu , Jiahao Wang , Yi Bin , Wenqi Shao , Ping Luo

The Mixture of Experts (MoE) has emerged as a highly successful technique in deep learning, based on the principle of divide-and-conquer to maximize model capacity without significant additional computational cost. Even in the era of…

Computation and Language · Computer Science 2024-09-02 Boan Liu , Liang Ding , Li Shen , Keqin Peng , Yu Cao , Dazhao Cheng , Dacheng Tao

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

Mixture-of-Experts (MoE) models enable efficient scaling of large language models (LLMs) by activating only a subset of experts per input. However, we observe that the commonly used auxiliary load balancing loss often leads to expert…

Computation and Language · Computer Science 2026-01-27 Hongcan Guo , Haolang Lu , Guoshun Nan , Bolun Chu , Jialin Zhuang , Yuan Yang , Wenhao Che , Xinye Cao , Sicong Leng , Qimei Cui , Xudong Jiang

With the breakthrough progress of large language models (LLMs) in natural language processing and multimodal tasks, efficiently deploying them on resource-constrained edge devices has become a critical challenge. The Mixture of Experts…

Machine Learning · Computer Science 2025-08-12 Tuo Zhang , Ning Li , Xin Yuan , Wenchao Xu , Quan Chen , Song Guo , Haijun Zhang

Mixture-of-Experts (MoE) Large Language Models (LLMs) face a trilemma of load imbalance, parameter redundancy, and communication overhead. We introduce a unified framework based on dynamic expert clustering and structured compression to…

Computation and Language · Computer Science 2026-02-06 Peijun Zhu , Ning Yang , Baoliang Tian , Jiayu Wei , Weihao Zhang , Haijun Zhang , Pin Lv

Rotations have become essential to state-of-the-art quantization pipelines for large language models (LLMs) by effectively smoothing outliers in weights and activations. However, further optimizing the rotation parameters offers only…

Machine Learning · Computer Science 2025-09-01 Liulu He , Shenli Zheng , Karwei Sun , Yijiang Liu , Yufei Zhao , Chongkang Tan , Huanrui Yang , Yuan Du , Li Du

Mixture-of-experts (MoE) has been extensively employed to scale large language models to trillion-plus parameters while maintaining a fixed computational cost. The development of large MoE models in the distributed scenario encounters the…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-03-05 Shulai Zhang , Ningxin Zheng , Haibin Lin , Ziheng Jiang , Wenlei Bao , Chengquan Jiang , Qi Hou , Weihao Cui , Size Zheng , Li-Wen Chang , Quan Chen , Xin Liu

Mixture-of-Experts (MoE) effectively scales large language models (LLMs) and vision-language models (VLMs) by increasing capacity through sparse activation. However, preloading all experts into memory and activating multiple experts per…

Machine Learning · Computer Science 2025-10-14 Wei Huang , Yue Liao , Yukang Chen , Jianhui Liu , Haoru Tan , Si Liu , Shiming Zhang , Shuicheng Yan , Xiaojuan Qi

Extreme activation outliers in Large Language Models (LLMs) critically degrade quantization performance, hindering efficient on-device deployment. While channel-wise operations and adaptive gradient scaling are recognized causes, practical…

Machine Learning · Computer Science 2025-06-25 Jungwoo Park , Taewhoo Lee , Chanwoong Yoon , Hyeon Hwang , Jaewoo Kang

Post-Training Quantization (PTQ) enhances the efficiency of Large Language Models (LLMs) by enabling faster operation and compatibility with more accessible hardware through reduced memory usage, at the cost of small performance drops. We…

Machine Learning · Computer Science 2024-06-06 Davide Paglieri , Saurabh Dash , Tim Rocktäschel , Jack Parker-Holder

Scaling large language models has driven remarkable advancements across various domains, yet the continual increase in model size presents significant challenges for real-world deployment. The Mixture of Experts (MoE) architecture offers a…

Machine Learning · Computer Science 2025-03-18 Shwai He , Daize Dong , Liang Ding , Ang Li