English
Related papers

Related papers: MoE-SpeQ: Speculative Quantized Decoding with Proa…

200 papers

The surgence of Mixture of Experts (MoE) in Large Language Models promises a small price of execution cost for a much larger model parameter count and learning capacity, because only a small fraction of parameters are activated for each…

The Mixture-of-Experts (MoE) architecture has become a predominant paradigm for scaling large language models (LLMs). Despite offering strong performance and computational efficiency, large MoE-based LLMs like DeepSeek-V3-0324 and…

Machine Learning · Computer Science 2025-08-08 Xiaodong Chen , Mingming Ha , Zhenzhong Lan , Jing Zhang , Jianguo Li

One of the primary challenges in optimizing large language models (LLMs) for long-context inference lies in the high memory consumption of the Key-Value (KV) cache. Existing approaches, such as quantization, have demonstrated promising…

Computer Vision and Pattern Recognition · Computer Science 2025-06-10 Wei Tao , Haocheng Lu , Xiaoyang Qu , Bin Zhang , Kai Lu , Jiguang Wan , Jianzong Wang

The Mixture of Experts (MoE) model becomes an important choice of large language models nowadays because of its scalability with sublinear computational complexity for training and inference. However, existing MoE models suffer from two…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-04-25 Xin Chen , Hengheng Zhang , Xiaotao Gu , Kaifeng Bi , Lingxi Xie , Qi Tian

Mixture-of-Experts models, now popular for scaling capacity at fixed inference speed, switch experts at nearly every token. Once a model outgrows available GPU memory, this churn can render optimizations like offloading and pre-fetching…

Machine Learning · Computer Science 2026-04-23 Zeyu Shen , Peter Henderson

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

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

Mixture-of-Experts (MoE) architectures offer a general solution to the high inference costs of large language models (LLMs) via sparse routing, bringing faster and more accurate models, at the cost of massive parameter counts. For example,…

Machine Learning · Computer Science 2023-10-26 Elias Frantar , Dan Alistarh

Large Language Models (LLMs) are increasingly deployed as Internet/Web services (LLM-as-a-Service) with strict latency Service-Level Objectives (SLOs) under tight GPU memory budgets. Mixture-of-Experts (MoE) models improve quality and…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-04-10 Yuning Zhang , Grant Pinkert , Nan Yang , Yanli Li , Dong Yuan

Expert Parallelism (EP) permits Mixture of Experts (MoE) models to scale beyond a single GPU. To address load imbalance across GPUs in EP, existing approaches aim to balance the number of tokens each GPU processes. Surprisingly, we find…

Recently, Mixture-of-Experts (MoE) has become one of the most popular techniques to scale pre-trained models to extraordinarily large sizes. Dynamic activation of experts allows for conditional computation, increasing the number of…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-06-30 Zheng Zhang , Donglin Yang , Yaqi Xia , Liang Ding , Dacheng Tao , Xiaobo Zhou , Dazhao Cheng

Mixture-of-Experts (MoE) models can achieve promising results with outrageous large amount of parameters but constant computation cost, and thus it has become a trend in model scaling. Still it is a mystery how MoE layers bring quality…

Machine Learning · Computer Science 2021-08-10 An Yang , Junyang Lin , Rui Men , Chang Zhou , Le Jiang , Xianyan Jia , Ang Wang , Jie Zhang , Jiamang Wang , Yong Li , Di Zhang , Wei Lin , Lin Qu , Jingren Zhou , Hongxia Yang

Large Language and Vision Models using a Mixture-of-Experts (MoE) architecture pose significant challenges for deployment due to their computational and memory demands. Mixed Precision Quantization assigns different precisions to different…

Machine Learning · Computer Science 2025-09-03 Krishna Teja Chitty-Venkata , Jie Ye , Murali Emani

Recently, Mixture of Experts (MoE) based Transformer has shown promising results in many domains. This is largely due to the following advantages of this architecture: firstly, MoE based Transformer can increase model capacity without…

Sound · Computer Science 2021-05-10 Zhao You , Shulin Feng , Dan Su , Dong Yu

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

Large language models are typically deployed as monolithic systems, requiring the full model even when applications need only a narrow subset of capabilities, e.g., code, math, or domain-specific knowledge. Mixture-of-Experts (MoEs)…

Computation and Language · Computer Science 2026-05-12 Ryan Wang , Akshita Bhagia , Sewon Min

Expert parallelism has emerged as a key strategy for distributing the computational workload of sparsely-gated mixture-of-experts (MoE) models across multiple devices, enabling the processing of increasingly large-scale models. However, the…

Machine Learning · Computer Science 2025-05-30 Weilin Cai , Juyong Jiang , Le Qin , Junwei Cui , Sunghun Kim , Jiayi Huang

Mixture-of-Experts (MoE) architectures leverage sparse activation to enhance the scalability of large language models (LLMs), making them suitable for deployment in resource-constrained edge networks. However, the sheer number of experts…

Information Theory · Computer Science 2026-03-26 Qian Chen , Xianhao Chen , Kaibin Huang

Emerging expert-specialized Mixture-of-Experts (MoE) architectures, such as DeepSeek-MoE, deliver strong model quality through fine-grained expert segmentation and large top-k routing. However, their scalability is limited by substantial…

Machine Learning · Computer Science 2025-08-20 Yueming Yuan , Ahan Gupta , Jianping Li , Sajal Dash , Feiyi Wang , Minjia Zhang

Mixture-of-Experts (MoE) showcases tremendous potential to scale large language models (LLMs) with enhanced performance and reduced computational complexity. However, its sparsely activated architecture shifts feed-forward networks (FFNs)…