English
Related papers

Related papers: Delta Decompression for MoE-based LLMs Compression

200 papers

Large language models (LLMs) with the Mixture-of-Experts (MoE) architecture achieve high cost-efficiency by selectively activating a subset of the parameters. Despite the inference efficiency of MoE LLMs, the training of extensive experts…

Computation and Language · Computer Science 2025-06-12 Yuchen Feng , Bowen Shen , Naibin Gu , Jiaxuan Zhao , Peng Fu , Zheng Lin , Weiping Wang

Mixture-of-Experts (MoE) models have become a key approach for scaling large language models efficiently by activating only a subset of experts during training and inference. Typically, the number of activated experts presents a trade-off:…

Machine Learning · Computer Science 2025-09-04 Yifei He , Yang Liu , Chen Liang , Hany Hassan Awadalla

Mixture-of-Experts (MoE) language models can reduce computational costs by 2-4$\times$ compared to dense models without sacrificing performance, making them more efficient in computation-bounded scenarios. However, MoE models generally…

Machine Learning · Computer Science 2024-04-09 Bowen Pan , Yikang Shen , Haokun Liu , Mayank Mishra , Gaoyuan Zhang , Aude Oliva , Colin Raffel , Rameswar Panda

Large language models (LLMs) such as GPTs and Mixtral-8x7B have revolutionized machine intelligence due to their exceptional abilities in generic ML tasks. Transiting LLMs from datacenters to edge devices brings benefits like better privacy…

Machine Learning · Computer Science 2025-03-10 Rongjie Yi , Liwei Guo , Shiyun Wei , Ao Zhou , Shangguang Wang , Mengwei Xu

Mixture-of-Experts (MoE) architectures are increasingly adopted in large language models (LLMs) for their scalability and efficiency. However, their modular structure introduces a unique vulnerability: adversaries can attempt to compress or…

Machine Learning · Computer Science 2025-11-26 Pinaki Prasad Guha Neogi , Ahmad Mohammadshirazi , Dheeraj Kulshrestha , Rajiv Ramnath

Large language models achieve exceptional performance on various downstream tasks through supervised fine-tuning. However, the diversity of downstream tasks and practical requirements makes deploying multiple full-parameter fine-tuned…

Machine Learning · Computer Science 2024-10-14 Yanfeng Jiang , Zelan Yang , Bohua Chen , Shen Li , Yong Li , Tao Li

Large Language Models (LLMs) have achieved significant success in various natural language processing tasks, but the role of wireless networks in supporting LLMs has not been thoroughly explored. In this paper, we propose a wireless…

Machine Learning · Computer Science 2024-11-12 Nan Xue , Yaping Sun , Zhiyong Chen , Meixia Tao , Xiaodong Xu , Liang Qian , Shuguang Cui , Wenjun Zhang , Ping Zhang

While large language models (LLMs) excel on generation tasks, their decoder-only architecture often limits their potential as embedding models if no further representation finetuning is applied. Does this contradict their claim of…

Computation and Language · Computer Science 2024-10-17 Ziyue Li , Tianyi Zhou

Large language models (LLMs) have demonstrated remarkable capabilities across a wide range of natural language processing tasks. Exploiting the heterogeneous capabilities of edge LLMs is crucial for diverse emerging applications, as it…

Networking and Internet Architecture · Computer Science 2025-01-17 Lyudong Jin , Yanning Zhang , Yanhan Li , Shurong Wang , Howard H. Yang , Jian Wu , Meng Zhang

Mixture-of-Experts (MoE) language models reduce per-token computation but still require storing and serving all experts, making deployment memory-intensive. Existing post-training compression methods mainly shrink this cost by pruning…

Artificial Intelligence · Computer Science 2026-05-29 Yilun Yao , Jiaming Pan , Elsie Dai , Peizhuang Cong , Yaoming Li , Tong Yang

Expanding Large Language Models~(LLMs) to new languages is a costly endeavor, demanding extensive Continued Pre-Training~(CPT) and data-intensive alignment. While recent data-free merging techniques attempt to bypass alignment by fusing a…

Computation and Language · Computer Science 2026-05-19 Hao Zhou , Tianhao Li , Zhijun Wang , Shuaijie She , Linjuan Wu , Hao-Ran Wei , Baosong Yang , Jiajun Chen , Shujian Huang

Despite the significant breakthrough of Mixture-of-Experts (MoE), the increasing scale of these MoE models presents huge memory and storage challenges. Existing MoE pruning methods, which involve reducing parameter size with a uniform…

Computation and Language · Computer Science 2025-09-22 Sikai Bai , Haoxi Li , Jie Zhang , Zicong Hong , Song Guo

The proliferation of large language models (LLMs) has led to the adoption of Mixture-of-Experts (MoE) architectures that dynamically leverage specialized subnetworks for improved efficiency and performance. Despite their benefits, MoE…

Computation and Language · Computer Science 2024-10-28 Ruisi Cai , Yeonju Ro , Geon-Woo Kim , Peihao Wang , Babak Ehteshami Bejnordi , Aditya Akella , Zhangyang Wang

Conventional large language models (LLMs) are equipped with dozens of GB to TB of model parameters, making inference highly energy-intensive and costly as all the weights need to be loaded to onboard processing elements during computation.…

Hardware Architecture · Computer Science 2025-07-28 Wei-Hsing Huang , Janak Sharda , Cheng-Jhih Shih , Yuyao Kong , Faaiq Waqar , Pin-Jun Chen , Yingyan , Lin , Shimeng Yu

Large Language Models (LLMs) have demonstrated remarkable abilities in tackling a wide range of complex tasks. However, their huge computational and memory costs raise significant challenges in deploying these models on resource-constrained…

Mixture-of-Experts (MoE) based large language models (LLMs) offer strong performance but suffer from high memory and computation costs. Weight binarization provides extreme efficiency, yet existing binary methods designed for dense LLMs…

Machine Learning · Computer Science 2026-04-22 Zhixiong Zhao , Zukang Xu , Zhixuan Chen , Dawei Yang

Despite LLMs' excellent code creation capabilities, multilingual code generation remains extremely challenging. To address this, we intent to improve the multi-programming-lingual (MultiPL) performance of the base LLMs while retaining the…

Computation and Language · Computer Science 2025-09-09 Qing Wang , Xue Han , Jiahui Wang , Lehao Xing , Qian Hu , Lianlian Zhang , Chao Deng , Junlan Feng

Mixture-of-experts (MoE) architectures used in large language models (LLMs) achieve state-of-the-art performance across diverse tasks yet face practical challenges such as deployment complexity and low activation efficiency. Expert pruning…

Machine Learning · Computer Science 2025-12-23 Xican Yang , Yuanhe Tian , Yan Song

The Mixture of Experts (MoE) paradigm provides a powerful way to decompose dense layers into smaller, modular computations often more amenable to human interpretation, debugging, and editability. However, a major challenge lies in the…

Computer Vision and Pattern Recognition · Computer Science 2024-10-18 James Oldfield , Markos Georgopoulos , Grigorios G. Chrysos , Christos Tzelepis , Yannis Panagakis , Mihalis A. Nicolaou , Jiankang Deng , Ioannis Patras

Upcycled Mixture-of-Experts (MoE) models have shown great potential in various tasks by converting the original Feed-Forward Network (FFN) layers in pre-trained dense models into MoE layers. However, these models still suffer from…

Machine Learning · Computer Science 2025-03-04 Yongqi Huang , Peng Ye , Chenyu Huang , Jianjian Cao , Lin Zhang , Baopu Li , Gang Yu , Tao Chen