microsoft/hummingbird

Hummingbird compiles trained ML models into tensor computation for faster inference.

47
/ 100
Emerging

This tool helps machine learning engineers and data scientists speed up how quickly their trained traditional ML models, like those from scikit-learn or LightGBM, make predictions. It takes your existing trained model and converts it into a format compatible with neural network frameworks, allowing you to leverage powerful hardware like GPUs for faster inference. The output is a functionally identical, but much faster, version of your original model.

3,530 stars. No commits in the last 6 months.

Use this if you need to significantly accelerate the prediction speed of your existing, trained traditional machine learning models without rebuilding them from scratch.

Not ideal if you are working exclusively with deep learning models, or if the inference speed of your current traditional ML models is already sufficient for your needs.

machine-learning-engineering model-inference predictive-analytics data-science performance-optimization
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

3,530

Forks

290

Language

Python

License

MIT

Last pushed

Jul 17, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/microsoft/hummingbird"

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