microsoft/hummingbird
Hummingbird compiles trained ML models into tensor computation for faster inference.
Converts traditional ML models (scikit-learn, XGBoost, LightGBM) to PyTorch, TorchScript, ONNX, or TVM by reconfiguring operators into tensor-based computations—enabling GPU acceleration and hardware optimizations without model re-engineering. Uses strategies like GEMM (matrix multiplication) to translate tree traversal into vectorized operations. Maintains scikit-learn-compatible inference API for seamless model swapping and supports serving via TorchServe.
3,530 stars. No commits in the last 6 months.
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
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
mlcommons/training
Reference implementations of MLPerf® training benchmarks