RMalkiv/torch-audit

The Linter for PyTorch: Detects silent training bugs

37
/ 100
Emerging

This tool helps machine learning engineers and researchers building PyTorch models catch hidden issues during training. It acts like a "check engine light" for your model's training loop, inspecting real data, gradients, and model behavior as it runs. You provide your PyTorch model and optimizer, and it flags potential problems like incorrect data formats, unstable gradients, or misconfigured optimizers that might silently degrade performance or waste computing resources.

Available on PyPI.

Use this if you are training PyTorch models and want to automatically detect silent bugs and inefficiencies that don't cause crashes but lead to poor model performance or wasted compute.

Not ideal if you are looking for a static code linter for general Python code or if you are not using PyTorch for your deep learning projects.

deep-learning model-training pytorch-development ml-debugging gpu-optimization
Maintenance 10 / 25
Adoption 5 / 25
Maturity 22 / 25
Community 0 / 25

How are scores calculated?

Stars

12

Forks

Language

Python

License

MIT

Last pushed

Jan 24, 2026

Commits (30d)

0

Dependencies

3

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/RMalkiv/torch-audit"

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