VainF/Torch-Pruning

[CVPR 2023] DepGraph: Towards Any Structural Pruning; LLMs, Vision Foundation Models, etc.

59
/ 100
Established

This tool helps machine learning engineers and researchers make deep learning models more efficient by reducing their size and computational demands. You input an existing PyTorch deep neural network, and it outputs a smaller, pruned version of the same model. This is especially useful for deploying large models like those used in computer vision and natural language processing to devices with limited resources.

3,267 stars. Used by 1 other package. No commits in the last 6 months. Available on PyPI.

Use this if you need to optimize the size and speed of your large deep learning models, such as LLMs or vision transformers, for deployment or more efficient training.

Not ideal if you are working with very small, simple models where the overhead of pruning might outweigh the benefits, or if you only need to zeroize individual parameters without changing the model's overall structure.

deep-learning-optimization model-compression large-language-models computer-vision neural-network-deployment
Stale 6m
Maintenance 2 / 25
Adoption 11 / 25
Maturity 25 / 25
Community 21 / 25

How are scores calculated?

Stars

3,267

Forks

374

Language

Python

License

MIT

Last pushed

Sep 07, 2025

Commits (30d)

0

Dependencies

2

Reverse dependents

1

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/VainF/Torch-Pruning"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.