English
Related papers

Related papers: Efficient MoE Serving in the Memory-Bound Regime: …

200 papers

Sparse Mixture of Experts (MoE) models are popular for training large language models due to their computational efficiency. However, the commonly used top-$k$ routing mechanism suffers from redundancy computation and memory costs due to…

Machine Learning · Computer Science 2024-02-22 Zhiyuan Zeng , Qipeng Guo , Zhaoye Fei , Zhangyue Yin , Yunhua Zhou , Linyang Li , Tianxiang Sun , Hang Yan , Dahua Lin , Xipeng Qiu

Mixture-of-Experts (MoE) architectures employ sparse activation to deliver faster training and inference with higher accuracy than dense LLMs. However, in production serving, MoE models require batch inference to optimize hardware…

Machine Learning · Computer Science 2026-02-10 Juntong Wu , Jialiang Cheng , Fuyu Lv , Ou Dan , Li Yuan

We present MegaBlocks, a system for efficient Mixture-of-Experts (MoE) training on GPUs. Our system is motivated by the limitations of current frameworks, which restrict the dynamic routing in MoE layers to satisfy the constraints of…

Machine Learning · Computer Science 2022-11-30 Trevor Gale , Deepak Narayanan , Cliff Young , Matei Zaharia

The generation quality of large language models (LLMs) is often improved by utilizing inference-time sequence-level scaling methods (e.g., Chain-of-Thought). We introduce hyper-parallel scaling, a complementary framework that improves…

Artificial Intelligence · Computer Science 2025-10-15 Soheil Zibakhsh , Mohammad Samragh , Kumari Nishu , Lauren Hannah , Arnav Kundu , Minsik Cho

Mixture-of-Experts models have become a dominant architecture for scaling Large Language Models by activating only a sparse subset of experts per token. However, latency-critical MoE inference faces a fundamental tension: while expert…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-02-04 Qianchao Zhu , Xucheng Ye , Yuliang Liu , Haodong Ouyang , Chengru Song

This paper introduces a theoretical framework for a Transformer-augmented, sectional Mixture-of-Experts (MoE) architecture that aims to enhance computational efficiency while preserving model scalability. Unlike conventional MoE models,…

Machine Learning · Computer Science 2025-03-27 Soham Sane

The deployment of large-scale Mixture-of-Experts (MoE) models on edge devices presents significant challenges due to memory constraints. While MoE architectures enable efficient utilization of computational resources by activating only a…

Machine Learning · Computer Science 2025-08-26 Nishant Gavhane , Arush Mehrotra , Rohit Chawla , Peter Proenca

Recent advancements in Mixture of Experts (MoE) models have significantly increased their parameter scale as well as model performance. Extensive offloading techniques have been proposed to address the GPU memory limitations of MoE…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-11-03 Zhibin Wang , Zhonghui Zhang , Yuhang Zhou , Zibo Wang , Mo Zhou , Peng Jiang , Weilin Cai , Chengying Huan , Rong Gu , Sheng Zhong , Chen Tian

Mixture of Experts (MoE) models based on Transformer architecture are pushing the boundaries of language and vision tasks. The allure of these models lies in their ability to substantially increase the parameter count without a…

The Mixture-of-Experts (MoE) architecture has emerged as a promising approach to mitigate the rising computational costs of large language models (LLMs) by selectively activating parameters. However, its high memory requirements and…

Artificial Intelligence · Computer Science 2026-04-14 Jehyeon Bang , Eunyeong Cho , Ranggi Hwang , Jinha Chung , Minsoo Rhu

Mixture-of-Experts (MoE) has become a dominant architecture for scaling large language models (LLMs). However, the execution characteristics of MoE inference are changing rapidly and increasingly mismatch the assumptions underlying existing…

Hardware Architecture · Computer Science 2026-05-13 Jungwoo Kim , Rubens Lacouture , Genghan Zhang , Gina Sohn , Qizheng Zhang , Swapnil Gandhi , Christos Kozyrakis , Kunle Olukotun

Mixture-of-Experts (MoE) architectures have emerged as a key strategy for scaling large language models (LLMs) efficiently. However, current MoE systems suffer from severe load imbalance, where only a small subset of experts is consistently…

Machine Learning · Computer Science 2025-06-27 Jiajie Yang

Sparsely activated Mixture-of-Experts (MoE) models are widely adopted to scale up model capacity without increasing the computation budget. However, vanilla TopK routers are trained in a discontinuous, non-differentiable way, limiting their…

Machine Learning · Computer Science 2025-02-28 Ziteng Wang , Jun Zhu , Jianfei Chen

The Mixture-of-Experts (MoE) paradigm has emerged as a promising solution to scale up model capacity while maintaining inference efficiency. However, deploying MoE models across heterogeneous end-cloud environments poses new challenges in…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-08-11 Zheming Yang , Yunqing Hu , Sheng Sun , Wen Ji

As giant dense models advance quality but require large amounts of GPU budgets for training, the sparsely gated Mixture-of-Experts (MoE), a kind of conditional computation architecture, is proposed to scale models while keeping their…

Distributed, Parallel, and Cluster Computing · Computer Science 2022-11-18 Xiaonan Nie , Pinxue Zhao , Xupeng Miao , Tong Zhao , Bin Cui

Mixture-of-Experts (MoE), while offering significant advantages as a Large Language Model (LLM) architecture, faces substantial challenges when deployed on low-cost edge devices with tight memory constraints. Expert offloading mitigates…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-12-04 Liujianfu Wang , Yuyang Du , Yuchen Pan , Soung Chang Liew , Jiacheng Liu , Kexin Chen

The Mixture of Experts (MoE) models are emerging as the latest paradigm for Large Language Models (LLMs). However, due to memory constraints, MoE models with billions or even trillions of parameters can only be deployed in multi-GPU or even…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-01-14 Bowen Zhou , Jinrui Jia , Wenhao He , Yong Zhang , Fang Dong

Mixture-of-Experts (MoE) architectures have emerged as a powerful paradigm for scaling neural networks while maintaining computational efficiency. However, standard MoE implementations rely on two rigid design assumptions: (1) fixed Top-K…

Machine Learning · Computer Science 2026-03-03 Gökdeniz Gülmez

The sparse Mixture-of-Experts (MoE) model is powerful for large-scale pre-training and has achieved promising results due to its model capacity. However, with trillions of parameters, MoE is hard to be deployed on cloud or mobile…

Machine Learning · Computer Science 2022-06-03 Tianyu Chen , Shaohan Huang , Yuan Xie , Binxing Jiao , Daxin Jiang , Haoyi Zhou , Jianxin Li , Furu Wei

Sparse Mixtures of Experts (SMoE) scales model capacity without significant increases in training and inference costs, but exhibits the following two issues: (1) Low expert activation, where only a small subset of experts are activated for…

Computation and Language · Computer Science 2024-04-24 Xun Wu , Shaohan Huang , Wenhui Wang , Furu Wei