paper-with-me

Papers

Thanos: A Block-wise Pruning Algorithm for Efficient Large Language Model Compression

2025-04-06 · Ivan Ilin, Peter Richtarik

This paper presents Thanos, a novel weight-pruning algorithm designed to reduce the memory footprint and enhance the computational efficiency of large language models (LLMs) by removing redundant weights while maintaining accuracy. Thanos introduces a block-wise pruning strategy with adaptive masks that dynamically adjust to weight importance, enabling flexible sparsity patterns and structured formats, such as $n:m$ sparsity, optimized for hardware acceleration. Experimental evaluations demonstrate that Thanos achieves state-of-the-art performance in structured pruning and outperforms existing methods in unstructured pruning. By providing an efficient and adaptable approach to model compression, Thanos offers a practical solution for deploying large models in resource-constrained environments.

📄 PDF Abstract BibTeX arXiv:2504.05346

Code (1)

vectozavr/thanos 공식 구현 pytorch

Tasks

Computational EfficiencyLanguage ModelingLanguage ModellingLarge Language ModelModel Compression

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

Ethanos: Lightweight Bootstrapping for Ethereum

2019-11-14 · Jae-Yun Kim, Jun-Mo Lee, Yeon-Jae Koo, Sang-Hyeon Park 외

As ethereum blockchain has become popular, the number of users and transactions has skyrocketed, causing an explosive increase of its data size. As a result, ordinary clients using PCs or smartphones cannot easily bootst…

ABCP: Automatic Block-wise and Channel-wise Network Pruning via Joint Search

2021-10-08 · Jiaqi Li, Haoran Li, Yaran Chen, Zixiang Ding 외

Currently, an increasing number of model pruning methods are proposed to resolve the contradictions between the computer powers required by the deep learning models and the resource-constrained devices. However, most of …

Deep Reinforcement LearningNetwork Pruning

Realizing Unaligned Block-wise Pruning for DNN Acceleration on Mobile Devices

2024-07-29 · Hayun Lee, Dongkun Shin

With the recent proliferation of on-device AI, there is an increasing need to run computationally intensive DNNs directly on mobile devices. However, the limited computing and memory resources of these devices necessitat…

BESA: Pruning Large Language Models with Blockwise Parameter-Efficient Sparsity Allocation

2024-02-18 · Peng Xu, Wenqi Shao, Mengzhao Chen, Shitao Tang 외

Large language models (LLMs) have demonstrated outstanding performance in various tasks, such as text summarization, text question-answering, and etc. While their performance is impressive, the computational footprint du…

GPUQuestion AnsweringText Summarization

Scalable iterative pruning of large language and vision models using block coordinate descent

2024-11-26 · Gili Rosenberg, J. Kyle Brubaker, Martin J. A. Schuetz, Elton Yechao Zhu 외

Pruning neural networks, which involves removing a fraction of their weights, can often maintain high accuracy while significantly reducing model complexity, at least up to a certain limit. We present a neural network pr…

Combinatorial OptimizationNetwork Pruning