English
Related papers

Related papers: CoServe: Efficient Collaboration-of-Experts (CoE) …

200 papers

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

The advancement of deep learning has led to the emergence of Mixture-of-Experts (MoEs) models, known for their dynamic allocation of computational resources based on input. Despite their promise, MoEs face challenges, particularly in terms…

Computation and Language · Computer Science 2024-04-09 Alexandre Muzio , Alex Sun , Churan He

Mixture-of-Experts (MoE) models have become a dominant paradigm for scaling large language models, but their rapidly growing parameter sizes introduce a fundamental inefficiency during inference: most expert weights remain idle in GPU…

Machine Learning · Computer Science 2026-05-01 Qingxiu Liu , Cyril Y. He , Hanser Jiang , Zion Wang , Alan Zhao , Patrick P. C. Lee

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

Prevailing LLM serving engines employ expert parallelism (EP) to implement multi-device inference of massive MoE models. However, the efficiency of expert parallel inference is largely bounded by inter-device communication, as EP embraces…

Machine Learning · Computer Science 2026-03-02 Yan Li , Zhenyu Zhang , Zhengang Wang , Pengfei Chen , Pengfei Zheng

Mixture of experts has emerged as the primary mechanism for making Large Language Models (LLMs) computationally efficient. However, in distributed settings, communicating token embeddings between experts is a significant bottleneck. We…

Machine Learning · Computer Science 2026-05-08 Muhammad Shahir Abdurrahman , Chun Deng , Azalia Mirhoseini , Philip Levis

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

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

Recent advances in artificial intelligence have driven increasing intelligent applications at the network edge, such as smart home, smart factory, and smart city. To deploy computationally intensive Deep Neural Networks (DNNs) on…

Networking and Internet Architecture · Computer Science 2020-12-08 Liekang Zeng , Xu Chen , Zhi Zhou , Lei Yang , Junshan Zhang

The promising applications of large language models are often limited by the constrained GPU memory capacity available on edge devices. Mixture-of-Experts (MoE) models help address this issue by activating only a subset of the model's…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-09-03 Xiaoniu Song , Zihang Zhong , Rong Chen , Haibo Chen

Mixture-of-Experts (MoE) activates only a subset of experts during inference, allowing the model to maintain low inference FLOPs and latency even as the parameter count scales up. However, since MoE dynamically selects the experts, all the…

Machine Learning · Computer Science 2025-05-27 Shibo Jie , Yehui Tang , Kai Han , Yitong Li , Duyu Tang , Zhi-Hong Deng , Yunhe Wang

The mixture-of-experts (MoE) architecture scales model size with sublinear computational increase but suffers from memory-intensive inference due to KV caches and sparse expert activation. Recent disaggregated expert parallelism (DEP)…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-12-29 Xinglin Pan , Shaohuai Shi , Wenxiang Lin , Yuxin Wang , Zhenheng Tang , Wei Wang , Xiaowen Chu

Mixture-of-Experts (MoE) models facilitate edge deployment by decoupling model capacity from active computation, yet their large memory footprint drives the need for GPU systems with near-data processing (NDP) capabilities that offload…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-01-08 Qi Wu , Chao Fang , Jiayuan Chen , Ye Lin , Yueqi Zhang , Yichuan Bai , Yuan Du , Li Du

Mixture-of-Experts (MoE) models typically fix the number of activated experts $k$ at both training and inference. However, real-world deployments often face heterogeneous hardware, fluctuating workloads, and diverse quality-latency…

Computation and Language · Computer Science 2026-05-12 Naibin Gu , Zhenyu Zhang , Yuchen Feng , Yilong Chen , Peng Fu , Zheng Lin , Shuohuan Wang , Yu Sun , Hua Wu , Weiping Wang , Haifeng Wang

Mixture of experts (MoE) is a popular technique to improve capacity of Large Language Models (LLMs) with conditionally-activated parallel experts. However, serving MoE models on memory-constrained devices is challenging due to the large…

Artificial Intelligence · Computer Science 2024-05-30 Rui Kong , Yuanchun Li , Qingtian Feng , Weijun Wang , Xiaozhou Ye , Ye Ouyang , Linghe Kong , Yunxin Liu

In parameter-efficient fine-tuning, mixture-of-experts (MoE), which involves specializing functionalities into different experts and sparsely activating them appropriately, has been widely adopted as a promising approach to trade-off…

Machine Learning · Computer Science 2025-08-29 Jinyuan Feng , Chaopeng Wei , Tenghai Qiu , Tianyi Hu , Zhiqiang Pu

Mixture of Experts (MoE) has become a mainstream architecture for building Large Language Models (LLMs) by reducing per-token computation while enabling model scaling. It can be viewed as partitioning a large Feed-Forward Network (FFN) at…

Machine Learning · Computer Science 2025-08-27 Weilin Cai , Le Qin , Shwai He , Junwei Cui , Ang Li , Jiayi Huang

Large language model (LLM) serving demands low latency and high throughput, but high load variability makes it challenging to achieve high GPU utilization. In this paper, we identify a synergetic but overlooked opportunity to co-serve…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-09-05 Yifan Qiao , Shu Anzai , Shan Yu , Haoran Ma , Shuo Yang , Yang Wang , Miryung Kim , Yongji Wu , Yang Zhou , Jiarong Xing , Joseph E. Gonzalez , Ion Stoica , Harry Xu

This paper presents MoE-Infinity, an efficient MoE inference system designed for personal machines with limited GPU memory capacity. The key idea for MoE-Infinity is that on personal machines, which are often single-user environments,…

Machine Learning · Computer Science 2025-03-14 Leyang Xue , Yao Fu , Zhan Lu , Luo Mai , Mahesh Marina

Mixture-of-Experts (MoE) has become a dominant architecture in large language models (LLMs) due to its ability to scale model capacity via sparse expert activation. Meanwhile, serverless computing, with its elasticity and pay-per-use…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-12-23 Wentao Liu , Yuhao Hu , Ruiting Zhou , Baochun Li , Ne Wang