microsoft/hummingbird
Hummingbird compiles trained ML models into tensor computation for faster inference.
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.
Stars
3,530
Forks
290
Language
Python
License
MIT
Category
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.
Higher-rated alternatives
NVIDIA/TransformerEngine
A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit...
mlcommons/inference
Reference implementations of MLPerf® inference benchmarks
mlcommons/training
Reference implementations of MLPerf® training benchmarks
datamade/usaddress
:us: a python library for parsing unstructured United States address strings into address components
GRAAL-Research/deepparse
Deepparse is a state-of-the-art library for parsing multinational street addresses using deep learning