English
Related papers

Related papers: EvoESAP: Non-Uniform Expert Pruning for Sparse MoE

200 papers

The Sparse Mixture of Experts (SMoE) has been widely employed to enhance the efficiency of training and inference for Transformer-based foundational models, yielding promising results.However, the performance of SMoE heavily depends on the…

Machine Learning · Computer Science 2025-03-11 Yongxin Guo , Zhenglin Cheng , Xiaoying Tang , Zhaopeng Tu , Tao Lin

Sparse Mixture of Experts (sMoE) has become a pivotal approach for scaling large vision-language models, offering substantial capacity while maintaining computational efficiency through dynamic, sparse activation of experts. However,…

Machine Learning · Computer Science 2025-10-21 Yongxiang Hua , Haoyu Cao , Zhou Tao , Bocheng Li , Zihao Wu , Chaohu Liu , Linli Xu

We present Marco-MoE, a suite of fully open multilingual sparse Mixture-of-Experts (MoE) models. Marco-MoE features a highly sparse design in which only around 5\% of the total parameters are activated per input token. This extreme…

Computation and Language · Computer Science 2026-04-29 Fan Jiang , Yu Zhao , Chenyang Lyu , Tianqi Shi , Yichao Du , Feihu Jiang , Longyue Wang , Weihua Luo

Large language models typically employ vocabularies of over 100k tokens, which creates a major computational bottleneck at the final linear projection layer when performing speculative decoding. Current methods for vocabulary pruning depend…

Computation and Language · Computer Science 2026-05-27 Zhiyang Chen , Daliang Xu , Yinyuan Zhang , Chenghua Wang , Mengwei Xu , Yun Ma

Neurons in large language models often exhibit \emph{polysemanticity}, simultaneously encoding multiple unrelated concepts and obscuring interpretability. Instead of relying on post-hoc methods, we present \textbf{MoE-X}, a…

Sparse Mixture-of-Experts (MoE) has become a key architecture for scaling large language models (LLMs) efficiently. Recent fine-grained MoE designs introduce hundreds of experts per layer, with multiple experts activated per token, enabling…

Machine Learning · Computer Science 2025-10-01 Yuanteng Chen , Peisong Wang , Yuantian Shao , Nanxin Zeng , Chang Xu , Jian Cheng

Standard LoRA fine-tuning of Mixture-of-Experts (MoE) models applies adapters to every expert, yet our profiling shows that per-layer expert routing is highly skewed: a small subset of experts handles most tokens in each layer, while many…

Machine Learning · Computer Science 2026-03-26 Andrea Manzoni

Unstructured sparsity is now natively accelerated by recent GPU kernels and dataflow hardware, shifting the bottleneck from inference execution to the pruning algorithm. State-of-the-art methods for unstructured LLM pruning are layer-wise…

Machine Learning · Computer Science 2026-05-19 Mohammad Mozaffari , Younes Hourri , Mohammad Rastegari , Mahyar Najibi

Large Language Models (LLMs) have demonstrated remarkable abilities in tackling a wide range of complex tasks. However, their huge computational and memory costs raise significant challenges in deploying these models on resource-constrained…

Sparse Mixture-of-Experts (SMoE) architectures are widely used in large language models (LLMs) due to their computational efficiency. However, though only a few experts are activated for each token, SMoE still requires loading all expert…

Computation and Language · Computer Science 2025-09-15 Yixiao Zhou , Ziyu Zhao , Dongzhou Cheng , zhiliang wu , Jie Gui , Yi Yang , Fei Wu , Yu Cheng , Hehe Fan

The emergence of large-scale Mixture of Experts (MoE) models represents a significant advancement in artificial intelligence, offering enhanced model capacity and computational efficiency through conditional computation. However, deploying…

Machine Learning · Computer Science 2025-01-23 Jiacheng Liu , Peng Tang , Wenfeng Wang , Yuhang Ren , Xiaofeng Hou , Pheng-Ann Heng , Minyi Guo , Chao Li

Modern Mixture-of-Experts (MoE) language models are designed based on total parameters (memory footprint) and active parameters (inference cost). However, we find these two factors alone are insufficient to describe an optimal architecture.…

Computation and Language · Computer Science 2026-01-14 Seng Pei Liew , Kenta Shinzato , Yuyang Dong

Despite MoE models leading many benchmarks, supervised fine-tuning (SFT) for the MoE architectures remains difficult because its router layers are fragile. Methods such as DenseMixer and ESFT mitigate router collapse with dense mixing or…

Machine Learning · Computer Science 2026-04-28 Haoze He , Xingyuan Ding , Xuan Jiang , Xinkai Zou , Alex Cheng , Yibo Zhao , Juncheng Billy Li , Heather Miller

Mixture-of-Experts (MoE) language models increase parameter capacity without proportional per-token compute, but the deployment still requires storing all experts, making expert pruning important for reducing memory and serving overhead.…

Machine Learning · Computer Science 2026-04-14 Zongfang Liu , Shengkun Tang , Yifan Shen , Huan Wang , Xin Yuan

The feedforward (FFW) layers in standard transformer architectures incur a linear increase in computational costs and activation memory as the hidden layer width grows. Sparse mixture-of-experts (MoE) architectures have emerged as a viable…

Machine Learning · Computer Science 2024-07-08 Xu Owen He

Sparse Mixture-of-Experts (SMoE) models represent a significant advancement in large language model (LLM) development through their efficient parameter utilization. These models achieve substantial performance improvements at reduced…

Machine Learning · Computer Science 2025-10-28 I-Chun Chen , Hsu-Shen Liu , Wei-Fang Sun , Chen-Hao Chao , Yen-Chang Hsu , Chun-Yi Lee

In recent years, Mixture-of-Experts (MoE) has emerged as an effective approach for enhancing the capacity of deep neural network (DNN) with sub-linear computational costs. However, storing all experts on GPUs incurs significant memory…

Machine Learning · Computer Science 2025-03-11 Suraiya Tairin , Shohaib Mahmud , Haiying Shen , Anand Iyer

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

Mixture-of-Experts (MoE) has emerged as a promising sparse paradigm for scaling up pre-trained models (PTMs) with remarkable cost-effectiveness. However, the dynamic nature of MoE leads to rapid fluctuations and imbalances in expert loads…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-02-05 Yuhao Qing , Guichao Zhu , Fanxin Li , Lintian Lei , Zekai Sun , Xiuxian Guan , Shixiong Zhao , Xusheng Chen , Dong Huang , Sen Wang , Heming Cui

Multimodal large language models (MLLMs) have achieved impressive performance, but high-resolution visual inputs result in long sequences of visual tokens and substantial inference latency. Reducing redundant visual tokens is critical to…

Computer Vision and Pattern Recognition · Computer Science 2026-03-23 Guoyang Xia , Yifeng Ding , Fengfa Li , Lei Ren , Wei Chen , Fangxiang Feng , Xiaojie Wang