paper-with-me

Papers

SlimLLM: Accurate Structured Pruning for Large Language Models

2025-05-28 · Jialong Guo, Xinghao Chen, Yehui Tang, Yunhe Wang

Large language models(LLMs) have garnered significant attention and demonstrated impressive capabilities in a wide range of applications. However, due to their enormous computational costs, the deployment and application of LLMs are often severely limited. To address this issue, structured pruning is an effective solution to compress the parameters of LLMs. Determining the importance of each sub-module in LLMs and minimizing performance loss are critical issues that need to be carefully addressed in structured pruning. In this paper, we propose an effective and fast structured pruning method named SlimLLM for large language models. For channel and attention head pruning, we evaluate the importance based on the entire channel or head, rather than merely aggregating the importance of individual elements within a sub-module. This approach enables a more holistic consideration of the interdependence among elements within the sub-module. In addition, we design a simple linear regression strategy for the output matrix to quickly recover performance. We also propose layer-based importance ratio to determine the pruning ratio for each layer. Based on the LLaMA benchmark results, our SlimLLM outperforms other methods and achieves state-of-the-art performance.

📄 PDF Abstract BibTeX arXiv:2505.22689

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음
Pruning 설명 없음
LLaMA LLaMA is a collection of foundation language models ranging from 7B to 65B parameters. It is based on the transformer architecture with various improvements that were…
Linear Regression Linear Regression is a method for modelling a relationship between a dependent variable and independent variables. These models can be fit with numerous approaches. The most…

Similar Papers 제목 키워드 기반

Accurate Retraining-free Pruning for Pretrained Encoder-based Language Models

2023-08-07 · Seungcheol Park, Hojun Choi, U Kang

Given a pretrained encoder-based language model, how can we accurately compress it without retraining? Retraining-free structured pruning algorithms are crucial in pretrained language model compression due to their signi…

Language ModelingLanguage ModellingModel Compression

The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language Models

2022-03-14 · Eldar Kurtic, Daniel Campos, Tuan Nguyen, Elias Frantar 외

Transformer-based language models have become a key building block for natural language processing. While these models are extremely accurate, they can be too large and computationally intensive to run on standard deploy…

CPUQuantization

FASP: Fast and Accurate Structured Pruning of Large Language Models

2025-01-16 · Hanyu Hu, Pengxiang Zhao, Ping Li, Yi Zheng 외

The rapid increase in the size of large language models (LLMs) has significantly escalated their computational and memory demands, posing challenges for efficient deployment, especially on resource-constrained devices. S…

GPUModel Compression

Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models

2025-01-25 · Zihuai Xu, Yang Xu, Hongli Xu, Yunming Liao 외

Considering the hardware-friendly characteristics and broad applicability, structured pruning has emerged as an efficient solution to reduce the resource demands of large language models (LLMs) on resource-constrained de…

Structured Pruning of Large Language Models via Power Transformation and Sign-Preserving Score Aggregation with Adaptive Feature Retention

2026-07-09 · Ryota Kobayashi, Tsubasa Hirakawa, Takayoshi Yamashita, Hironobu Fujiyoshi 외 arxiv

This paper proposes an improved structured pruning method for large language models (LLMs) that addresses key challenges in adapting Adaptive Feature Retention (AFR), an unstructured pruning technique, to structured prun…