English
Related papers

Related papers: BrownoutServe: SLO-Aware Inference Serving under B…

200 papers

While multi-agent systems have been shown to significantly enhance the performance of Large Language Models (LLMs) across various tasks and applications, the dense interaction between scaling agents potentially hampers their efficiency and…

Artificial Intelligence · Computer Science 2024-11-06 Dawei Li , Zhen Tan , Peijia Qian , Yifan Li , Kumar Satvik Chaudhary , Lijie Hu , Jiayi Shen

Mixture-of-Experts (MoE) architectures offer the promise of larger model capacity without the prohibitive costs of fully dense designs. However, in real-world inference serving, load skew across experts often leads to suboptimal device…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-05-30 Shaoyu Wang , Guangrong He , Geon-Woo Kim , Yanqi Zhou , Seo Jin Park

The Mixture of Experts (MoE) architecture is a cornerstone of modern state-of-the-art (SOTA) large language models (LLMs). MoE models facilitate scalability by enabling sparse parameter activation. However, traditional MoE architecture uses…

Computation and Language · Computer Science 2025-08-12 Haoyuan Wu , Haoxing Chen , Xiaodong Chen , Zhanchao Zhou , Tieyuan Chen , Yihong Zhuang , Guoshan Lu , Zenan Huang , Junbo Zhao , Lin Liu , Zhenzhong Lan , Bei Yu , Jianguo Li

The scaling of large language models (LLMs) has revolutionized their capabilities in various tasks, yet this growth must be matched with efficient computational strategies. The Mixture-of-Experts (MoE) architecture stands out for its…

Computation and Language · Computer Science 2025-03-20 Zihan Qiu , Zeyu Huang , Shuang Cheng , Yizhi Zhou , Zili Wang , Ivan Titov , Jie Fu

An increasing number of LLMs employ Mixture-of-Experts (MoE) architectures where the feed-forward layer is replaced by a pool of experts and each token only activates a small subset of them. During autoregressive generation, these models…

Machine Learning · Computer Science 2025-11-05 Costin-Andrei Oncescu , Qingyang Wu , Wai Tong Chung , Robert Wu , Bryan Gopal , Junxiong Wang , Tri Dao , Ben Athiwaratkun

Mixture-of-Experts (MoE) Large Language Models (LLMs) efficiently scale-up the model while keeping relatively low inference cost. As MoE models only activate part of the experts, related work has proposed expert prediction and caching…

Computation and Language · Computer Science 2025-11-17 Shien Zhu , Samuel Bohl , Robin Oester , Gustavo Alonso

Apple Neural Engine (ANE) is a dedicated neural processing unit (NPU) present in every Apple Silicon chip. Mixture-of-Experts (MoE) LLMs improve inference efficiency via sparse activation but are challenging for NPUs in three ways: expert…

Machine Learning · Computer Science 2026-04-22 Afsara Benazir , Felix Xiaozhu Lin

The rapid growth of generative AI and its integration into everyday workflows have significantly increased the demand for large language model (LLM) inference services. While proprietary models remain popular, recent advancements in…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-01-28 Linyu Wu , Xiaoyuan Liu , Tianneng Shi , Zhe Ye , Dawn Song

Mixture-of-Experts (MoE) models scale efficiently by activating only a subset of experts per token, offering a computationally sparse alternative to dense architectures. While prior post-training optimizations, such as inter- and…

Machine Learning · Computer Science 2025-09-04 Krishna Teja Chitty-Venkata , Sandeep Madireddy , Murali Emani , Venkatram Vishwanath

Efficient deployment of a pre-trained LLM to a cluster with multiple servers is a critical step for providing fast responses to users' queries. The recent success of Mixture-of-Experts (MoE) LLMs raises the question of how to deploy them…

Networking and Internet Architecture · Computer Science 2025-08-14 Danil Sivtsov , Aleksandr Katrutsa , Ivan Oseledets

Recent advances demonstrate that scaling Large Vision-Language Models (LVLMs) effectively improves downstream task performances. However, existing scaling methods enable all model parameters to be active for each token in the calculation,…

Computer Vision and Pattern Recognition · Computer Science 2024-12-24 Bin Lin , Zhenyu Tang , Yang Ye , Jinfa Huang , Junwu Zhang , Yatian Pang , Peng Jin , Munan Ning , Jiebo Luo , Li Yuan

Mixture-of-Experts (MoE) has emerged as an effective approach to reduce the computational overhead of Transformer architectures by sparsely activating a subset of parameters for each token while preserving high model capacity. This paradigm…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Dohwan Ko , Jinyoung Park , Seoung Choi , Sanghyeok Lee , Seohyun Lee , Hyunwoo J. Kim

The performance of the reward model (RM) is a critical factor in improving the effectiveness of the large language model (LLM) during alignment fine-tuning. There remain two challenges in RM training: 1) training the same RM using various…

Computation and Language · Computer Science 2024-04-30 Shanghaoran Quan

Multimodal large language models (MLLMs) have demonstrated impressive capabilities across various vision-language tasks. However, a generalist MLLM typically underperforms compared with a specialist MLLM on most VL tasks, which can be…

Computer Vision and Pattern Recognition · Computer Science 2024-07-18 Leyang Shen , Gongwei Chen , Rui Shao , Weili Guan , Liqiang Nie

This paper presents a comprehensive review of the Mixture-of-Experts (MoE) architecture in large language models, highlighting its ability to significantly enhance model performance while maintaining minimal computational overhead. Through…

Machine Learning · Computer Science 2025-12-24 Danyang Zhang , Junhao Song , Ziqian Bi , Xinyuan Song , Yingfang Yuan , Tianyang Wang , Joe Yeong , Junfeng Hao

The context window of large language models (LLMs) is rapidly increasing, leading to a huge variance in resource usage between different requests as well as between different phases of the same request. Restricted by static parallelism…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-10-30 Bingyang Wu , Shengyu Liu , Yinmin Zhong , Peng Sun , Xuanzhe Liu , Xin Jin

Mixture-of-Experts (MoE) models enable scalable neural networks through conditional computation, offering enhanced effectiveness and efficiency for next-generation wireless communications. However, deploying MoE with federated learning (FL)…

Machine Learning · Computer Science 2026-05-19 Boyang Zhang , Xiaobing Chen , Songyang Zhang , Shuai Zhang , Xiangwei Zhou , Jian Zhang , Mingxuan Sun

The interpretability of Mixture-of-Experts (MoE) models, especially those with heterogeneous designs, remains underexplored. Existing attribution methods for dense models fail to capture dynamic routing-expert interactions in sparse MoE…

Computation and Language · Computer Science 2025-06-12 Junzhuo Li , Bo Wang , Xiuze Zhou , Peijie Jiang , Jia Liu , Xuming Hu

Large Language Models (LLMs) have shown great promise in multilingual machine translation (MT), even with limited bilingual supervision. However, fine-tuning LLMs with parallel corpora presents major challenges, namely parameter…

Computation and Language · Computer Science 2026-05-26 Bo Li , Tianyu Dong , Shaolin Zhu , Deyi Xiong

The Mixture-of-Experts (MoE) architecture has enabled the creation of massive yet efficient Large Language Models (LLMs). However, the standard deterministic routing mechanism presents a significant limitation: its inherent brittleness is a…

Machine Learning · Computer Science 2025-09-30 Albus Yizhuo Li