paper-with-me

홈 › Papers

ZipNN: Lossless Compression for AI Models

2024-11-07 · Moshik Hershcovitch, Andrew Wood, Leshem Choshen, Guy Girmonsky, Roy Leibovitz, Ilias Ennmouri, Michal Malka, Peter Chin, Swaminathan Sundararaman, Danny Harnik

With the growth of model sizes and the scale of their deployment, their sheer size burdens the infrastructure requiring more network and more storage to accommodate these. While there is a vast model compression literature deleting parts of the model weights for faster inference, we investigate a more traditional type of compression - one that represents the model in a compact form and is coupled with a decompression algorithm that returns it to its original form and size - namely lossless compression. We present ZipNN a lossless compression tailored to neural networks. Somewhat surprisingly, we show that specific lossless compression can gain significant network and storage reduction on popular models, often saving 33% and at times reducing over 50% of the model size. We investigate the source of model compressibility and introduce specialized compression variants tailored for models that further increase the effectiveness of compression. On popular models (e.g. Llama 3) ZipNN shows space savings that are over 17% better than vanilla compression while also improving compression and decompression speeds by 62%. We estimate that these methods could save over an ExaByte per month of network traffic downloaded from a large model hub like Hugging Face.

📄 PDF Abstract BibTeX arXiv:2411.05239

Code (1)

zipnn/zipnn 공식 구현 pytorch

Tasks

Model Compression

Methods 이 논문이 사용한 방법론

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…

Similar Papers 제목 키워드 기반

Lossless Compression of Neural Network Components: Weights, Checkpoints, and K/V Caches in Low-Precision Formats

2025-08-20 · Anat Heilper, Doron Singer arxiv

As deep learning models grow and deployment becomes more widespread, reducing the storage and transmission costs of neural network weights has become increasingly important. While prior work such as ZipNN has shown that …

Lossless Tensor Compression as Program Synthesis

2026-08-03 · Jieke Shi, Junda He, Wenjia Jiang, Weifeng Sun 외 hf

Model checkpoints are growing in both number and size, which makes archival, transfer, and deployment increasingly costly. General-purpose compressors can reduce storage requirements but ignore tensor structure, whereas …

Program SynthesisImage Generation

Deep Lossy Plus Residual Coding for Lossless and Near-lossless Image Compression

2022-09-11 · Yuanchao Bai, Xianming Liu, Kai Wang, Xiangyang Ji 외

Lossless and near-lossless image compression is of paramount importance to professional users in many technical fields, such as medicine, remote sensing, precision engineering and scientific research. But despite rapidly…

Image Compression

Learned Lossless Image Compression With Combined Autoregressive Models And Attention Modules

2022-08-30 · Ran Wang, Jinming Liu, Heming Sun, Jiro Katto

Lossless image compression is an essential research field in image compression. Recently, learning-based image compression methods achieved impressive performance compared with traditional lossless methods, such as WebP,…

Image Compression

End-to-end lossless compression of high precision depth maps guided by pseudo-residual

2022-01-10 · Yuyang Wu, Wei Gao

As a fundamental data format representing spatial information, depth map is widely used in signal processing and computer vision fields. Massive amount of high precision depth maps are produced with the rapid development…