angelolamonaca/PyTorch-Precision-Converter

A flexible utility for converting tensor precision in PyTorch models and safetensors files, enabling efficient deployment across various platforms.

21
/ 100
Experimental

This tool helps machine learning engineers and researchers optimize their deep learning models for deployment. It takes existing PyTorch model checkpoints or safetensors files and converts their internal data precision (e.g., from full precision to half-precision). The output is a more memory-efficient and faster-running model, suitable for environments with limited resources like mobile devices or specialized hardware.

No commits in the last 6 months.

Use this if you need to reduce the memory footprint or improve the inference speed of your PyTorch models for deployment, especially on resource-constrained platforms.

Not ideal if you are solely focused on model training and do not require precision optimization for deployment.

deep-learning-deployment model-optimization machine-learning-engineering resource-constrained-ai edge-ai
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

11

Forks

Language

Python

License

MIT

Last pushed

Aug 24, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/angelolamonaca/PyTorch-Precision-Converter"

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