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 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.
View on arXiv@article{ilin2025_2504.05346,
title={ Thanos: A Block-wise Pruning Algorithm for Efficient Large Language Model Compression },
author={ Ivan Ilin and Peter Richtarik },
journal={arXiv preprint arXiv:2504.05346},
year={ 2025 }
}