English
Related papers

Related papers: STUN: Structured-Then-Unstructured Pruning for Sca…

200 papers

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

Large Language Models (LLMs) now exhibit remarkable reasoning capabilities through test-time compute scaling (TTS), with impressive performance across math and coding benchmarks. In parallel, research in model compression has developed…

Artificial Intelligence · Computer Science 2026-05-29 Ocean Monjur , Shahriar Kabir Nahin , Anshuman Chhabra

Vision-language models (VLMs) increasingly rely on chain-of-thought (CoT) reasoning to solve complex multimodal tasks, but their large parameter sizes make deployment expensive. Structured pruning offers a natural solution; however,…

Artificial Intelligence · Computer Science 2026-05-26 Aritra Dutta , Somak Aditya

Mixture-of-Experts large language models (MoE-LLMs) marks a significant step forward of language models, however, they encounter two critical challenges in practice: 1) expert parameters lead to considerable memory consumption and loading…

Machine Learning · Computer Science 2025-02-25 Wei Huang , Yue Liao , Jianhui Liu , Ruifei He , Haoru Tan , Shiming Zhang , Hongsheng Li , Si Liu , Xiaojuan Qi

N:M structured pruning is essential for large language models (LLMs) because it can remove less important network weights and reduce the memory and computation requirements. Existing pruning methods mainly focus on designing metrics to…

Computation and Language · Computer Science 2025-03-17 Chi Xu , Gefei Zhang , Yantong Zhu , Luca Benini , Guosheng Hu , Yawei Li , Zhihong Zhang

Mixture of Experts (MoE) models with conditional execution of sparsely activated layers have enabled training models with a much larger number of parameters. As a result, these models have achieved significantly better quality on various…

Computation and Language · Computer Science 2022-11-21 Young Jin Kim , Rawn Henry , Raffy Fahim , Hany Hassan Awadalla

Mixture-of-Experts (MoE) is a promising way to scale up the learning capacity of large language models. It increases the number of parameters while keeping FLOPs nearly constant during inference through sparse activation. Yet, it still…

Machine Learning · Computer Science 2025-02-26 Pingzhi Li , Xiaolong Jin , Zhen Tan , Yu Cheng , Tianlong Chen

The considerable size of Large Language Models (LLMs) presents notable deployment challenges, particularly on resource-constrained hardware. Structured pruning, offers an effective means to compress LLMs, thereby reducing storage costs and…

Computation and Language · Computer Science 2024-06-28 Shengrui Li , Junzhe Chen , Xueting Han , Jing Bai

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

Feed-forward networks (FFNs) dominate the parameter count and computation of modern language models, yet existing pruning methods often struggle to convert sparsity into hardware-friendly inference efficiency gains. We introduce…

Computation and Language · Computer Science 2026-05-28 Zhexuan Gu , Zixun Fu , Yancheng Yuan

Sparse mixture of expert architectures (MoEs) scale model capacity without significant increases in training or inference costs. Despite their success, MoEs suffer from a number of issues: training instability, token dropping, inability to…

Machine Learning · Computer Science 2024-05-28 Joan Puigcerver , Carlos Riquelme , Basil Mustafa , Neil Houlsby

Mixture of Experts (MoE) architectures have emerged as pivotal for scaling Large Language Models (LLMs) efficiently. Fine-grained MoE approaches - utilizing more numerous, smaller experts - have demonstrated potential in improving model…

Machine Learning · Computer Science 2025-06-04 Jakub Krajewski , Marcin Chochowski , Daniel Korzekwa

Structured pruning is a widely used technique for reducing the size of pre-trained language models (PLMs), but current methods often overlook the potential of compressing the hidden dimension (d) in PLMs, a dimension critical to model size…

Computation and Language · Computer Science 2024-08-20 Yuxuan Hu , Jing Zhang , Zhe Zhao , Chen Zhao , Xiaodong Chen , Cuiping Li , Hong Chen

As large language models continue to scale, computational costs and resource consumption have emerged as significant challenges. While existing sparsification methods like pruning reduce computational overhead, they risk losing model…

Computation and Language · Computer Science 2025-09-16 Minxuan Lv , Zhenpeng Su , Leiyu Pan , Yizhe Xiong , Zijia Lin , Hui Chen , Wei Zhou , Jungong Han , Guiguang Ding , Cheng Luo , Di Zhang , Kun Gai , Songlin Hu

Speculative decoding accelerates Large Language Model (LLM) inference by verifying multiple drafted tokens in parallel. However, for Mixture-of-Experts (MoE) models, this parallelism introduces a severe bottleneck: large draft trees…

Machine Learning · Computer Science 2026-02-19 Bradley McDanel , Steven Li , Sruthikesh Surineni , Harshit Khaitan

With the increasing size of large language models, layer pruning has gained increased attention as a hardware-friendly approach for model compression. However, existing layer pruning methods struggle to simultaneously address key practical…

Computation and Language · Computer Science 2025-11-24 Tao Yuan , Haoli Bai , Yinfei Pan , Xuyang Cao , Tianyu Zhang , Lu Hou , Ting Hu , Xianzhi Yu

Mixture of Experts layers (MoEs) enable efficient scaling of language models through conditional computation. This paper presents a detailed empirical study of how autoregressive MoE language models scale in comparison with dense models in…

Pruning methods have shown to be effective at reducing the size of deep neural networks while keeping accuracy almost intact. Among the most effective methods are those that prune a network while training it with a sparsity prior loss and…

Neural and Evolutionary Computing · Computer Science 2019-12-20 Carl Lemaire , Andrew Achkar , Pierre-Marc Jodoin

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

Sparse Mixture-of-Experts (MoE) models offer a powerful way to scale model size without increasing compute, as per-token FLOPs depend only on k active experts rather than the total pool of E experts. Yet, this asymmetry creates an MoE…

Machine Learning · Computer Science 2026-05-15 Linghao Jin , Chufan Shi , Huijuan Wang , Nuan Wen , Zhengzhong Liu , Eric Xing , Xuezhe Ma