English
Related papers

Related papers: Janus: Disaggregating Attention and Experts for Sc…

200 papers

Multimodal Mixture-of-Experts (MoE) models offer a promising path toward scalable and efficient large vision-language systems. However, existing approaches rely on rigid routing strategies (typically activating a fixed number of experts per…

Machine Learning · Computer Science 2025-11-25 Yuting Gao , Wang Lan , Hengyuan Zhao , Linjiang Huang , Si Liu , Qingpei Guo

Recent advances in large language models highlighted the excessive quadratic cost of self-attention. Despite the significant research efforts, subquadratic attention methods still suffer from inferior performance in practice. We hypothesize…

Machine Learning · Computer Science 2025-05-02 Piotr Piękos , Róbert Csordás , Jürgen Schmidhuber

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

Sparse Mixture of Expert (MoE) models are popular foundational architectures at large scale, however, under-explored at smaller sizes. Here, we show how to enable Compact Sparse Mixture of Experts (CoSMoEs) for on-device inference.…

Machine Learning · Computer Science 2025-03-04 Patrick Huber , Akshat Shrivastava , Ernie Chang , Chinnadhurai Sankar , Ahmed Aly , Adithya Sagar

In this work, we first explore whether the parameters activated by the MoE layer remain highly sparse at inference. We perform a sparsification study on several representative MoE models. For each expert, we rank parameters by the magnitude…

Computation and Language · Computer Science 2025-10-08 Runxi Cheng , Yuchen Guan , Yucheng Ding , Qingguo Hu , Yongxian Wei , Chun Yuan , Yelong Shen , Weizhu Chen , Yeyun Gong

Human education system trains one student by multiple experts. Mixture-of-experts (MoE) is a powerful sparse architecture including multiple experts. However, sparse MoE model is easy to overfit, hard to deploy, and not hardware-friendly…

Machine Learning · Computer Science 2022-10-26 Fuzhao Xue , Xiaoxin He , Xiaozhe Ren , Yuxuan Lou , Yang You

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

Mixture-of-Experts (MoE) models enable scalable performance by activating large parameter sets sparsely, minimizing computational overhead. To mitigate the prohibitive cost of training MoEs from scratch, recent work employs upcycling,…

Machine Learning · Computer Science 2025-11-13 Qi Wang , Hanyang Peng , Yue Yu

With the widespread adoption of Mixture-of-Experts (MoE) models, there is a growing demand for efficient inference on memory-constrained devices. While offloading expert parameters to CPU memory and loading activated experts on demand has…

Machine Learning · Computer Science 2025-05-13 Yuxin Zhou , Zheng Li , Jun Zhang , Jue Wang , Yiping Wang , Zhongle Xie , Ke Chen , Lidan Shou

Mixture-of-experts (MoEs) have been adopted for reducing inference costs by sparsely activating experts in Large language models (LLMs). Despite this reduction, the massive number of experts in MoEs still makes them expensive to serve. In…

Machine Learning · Computer Science 2025-07-22 Jaeseong Lee , seung-won hwang , Aurick Qiao , Daniel F Campos , Zhewei Yao , Yuxiong He

In multi-GPU Mixture-of-Experts (MoE) network, experts are distributed across different GPUs, which creates load imbalance as each expert processes different number of tokens. Recent works improve MoE inference load balance by dynamically…

Machine Learning · Computer Science 2025-06-10 Haiyue Ma , Zhixu Du , Yiran Chen

Sparse Mixture of Experts (MoE) models offer a scalable and efficient architecture for training large neural networks by activating only a subset of parameters ("experts") for each input. A learned router computes a distribution over these…

Machine Learning · Computer Science 2025-10-14 Nabil Omi , Siddhartha Sen , Ali Farhadi

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

The mixture of experts (MoE) model is a sparse variant of large language models (LLMs), designed to hold a better balance between intelligent capability and computational overhead. Despite its benefits, MoE is still too expensive to deploy…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-04-23 Haodong Wang , Qihua Zhou , Zicong Hong , Song Guo

Mixture-of-Experts (MoE) has successfully scaled up models while maintaining nearly constant computing costs. By employing a gating network to route input tokens, it selectively activates a subset of expert networks to process the…

Machine Learning · Computer Science 2025-04-22 Mohan Zhang , Pingzhi Li , Jie Peng , Mufan Qiu , Tianlong Chen

Mixture-of-Experts (MoE) architectures have become the dominant choice for scaling Large Language Models (LLMs), activating only a subset of parameters per token. While MoE architectures are primarily adopted for computational efficiency,…

Computation and Language · Computer Science 2026-05-19 Jeremy Herbst , Stefan Wermter , Jae Hee Lee

Mixture-of-Experts (MoE) models deliver high quality at low training FLOPs, but this efficiency often vanishes at inference. We identify a double penalty that structurally disadvantages MoE architectures during decoding: first, expert…

Machine Learning · Computer Science 2026-03-11 Vignesh Adhinarayanan , Nuwan Jayasena

Efficient long-context understanding and reasoning are increasingly vital for large language model (LLM) applications such as multi-turn dialogue and program analysis. However, the core self-attention mechanism scales quadratically with…

Computation and Language · Computer Science 2025-12-17 Siran Liu , Zane Cao , Yongchao He

Mixture of Experts (MoE) architectures significantly enhance the capacity of LLMs without proportional increases in computation, but at the cost of a vast parameter size. Offloading MoE expert parameters to host memory and leveraging both…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-02-04 Zeyu Zhu , Gang Li , Peisong Wang , Zitao Mo , Minnan Pei , Zhuoran Song , Xiaoyao Liang , Jian Cheng

The Sparsely-Activated Mixture-of-Experts (MoE) has gained increasing popularity for scaling up large language models (LLMs) without exploding computational costs. Despite its success, the current design faces a challenge where all experts…

Machine Learning · Computer Science 2024-09-20 Manxi Sun , Wei Liu , Jian Luan , Pengzhi Gao , Bin Wang