paper-with-me

Papers

Samoyeds: Accelerating MoE Models with Structured Sparsity Leveraging Sparse Tensor Cores

2025-03-13 · Chenpeng Wu, Qiqi Gu, Heng Shi, Jianguo Yao, Haibing Guan

The escalating size of Mixture-of-Experts (MoE) based Large Language Models (LLMs) presents significant computational and memory challenges, necessitating innovative solutions to enhance efficiency without compromising model accuracy. Structured sparsity emerges as a compelling strategy to address these challenges by leveraging the emerging sparse computing hardware. Prior works mainly focus on the sparsity in model parameters, neglecting the inherent sparse patterns in activations. This oversight can lead to additional computational costs associated with activations, potentially resulting in suboptimal performance. This paper presents Samoyeds, an innovative acceleration system for MoE LLMs utilizing Sparse Tensor Cores (SpTCs). Samoyeds is the first to apply sparsity simultaneously to both activations and model parameters. It introduces a bespoke sparse data format tailored for MoE computation and develops a specialized sparse-sparse matrix multiplication kernel. Furthermore, Samoyeds incorporates systematic optimizations specifically designed for the execution of dual-side structured sparse MoE LLMs on SpTCs, further enhancing system performance. Evaluations show that Samoyeds outperforms SOTA works by up to 1.99$\times$ at the kernel level and 1.58$\times$ at the model level. Moreover, it enhances memory efficiency, increasing maximum supported batch sizes by 4.41$\times$ on average. Additionally, Samoyeds surpasses existing SOTA structured sparse solutions in both model accuracy and hardware portability.

📄 PDF Abstract BibTeX arXiv:2503.10725

Code (1)

guqiqi/Samoyeds 공식 구현 pytorch

Tasks

Mixture-of-Experts

Methods 이 논문이 사용한 방법론

MoE 설명 없음
Focus 설명 없음

Similar Papers 제목 키워드 기반

SparseRT: Accelerating Unstructured Sparsity on GPUs for Deep Learning Inference

2020-08-26 · Ziheng Wang

In recent years, there has been a flurry of research in deep neural network pruning and compression. Early approaches prune weights individually. However, it is difficult to take advantage of the resulting unstructured s…

Deep LearningNetwork Pruning

Hardware/Software Co-Design of RISC-V Extensions for Accelerating Sparse DNNs on FPGAs

2025-04-28 · Muhammad Sabih, Abrarul Karim, Jakob Wittmann, Frank Hannig 외

The customizability of RISC-V makes it an attractive choice for accelerating deep neural networks (DNNs). It can be achieved through instruction set extensions and corresponding custom functional units. Yet, efficiently …

Human Detectionimage-classificationImage ClassificationKeyword Spotting

GQSA: Group Quantization and Sparsity for Accelerating Large Language Model Inference

2024-12-23 · Chao Zeng, Songwei Liu, Shu Yang, Fangmin Chen 외

With the rapid growth in the scale and complexity of large language models (LLMs), the costs of training and inference have risen substantially. Model compression has emerged as a mainstream solution to reduce memory usa…

GPULanguage ModelingLanguage ModellingLarge Language Model+2

Enabling Unstructured Sparse Acceleration on Structured Sparse Accelerators

2024-03-12 · Geonhwa Jeong, Po-An Tsai, Abhimanyu R. Bambhaniya, Stephen W. Keckler 외

Exploiting sparsity in deep neural networks (DNNs) has been a promising area for meeting the growing computation requirements. To minimize the overhead of sparse acceleration, hardware designers have proposed structured …

Tensor Decomposition

S2TA: Exploiting Structured Sparsity for Energy-Efficient Mobile CNN Acceleration

2021-07-16 · Zhi-Gang Liu, Paul N. Whatmough, Yuhao Zhu, Matthew Mattina

Exploiting sparsity is a key technique in accelerating quantized convolutional neural network (CNN) inference on mobile devices. Prior sparse CNN accelerators largely exploit un-structured sparsity and achieve significan…