microsoft/hummingbird
Microsoft library that compiles trained scikit-learn, LightGBM, and other traditional ML models into PyTorch, TorchScript, ONNX, and TVM tensor computations for hardware-accelerated inference.
Not currently ranked — collecting fresh signals.
star history
Hummingbird converts trained traditional ML models and featurizers into tensor computations executed via neural network runtimes. It bridges classical ML frameworks like scikit-learn and LightGBM with deep learning infrastructure such as PyTorch and TorchScript, enabling hardware acceleration and optimization passes that neural network frameworks provide. Users can deploy their existing models without re-engineering while gaining the performance benefits of GPU acceleration and framework-level optimizations.
Frequently asked
- What is microsoft/hummingbird?
- Microsoft library that compiles trained scikit-learn, LightGBM, and other traditional ML models into PyTorch, TorchScript, ONNX, and TVM tensor computations for hardware-accelerated inference.
- Is hummingbird open source?
- Yes — microsoft/hummingbird is open source, released under the MIT license.
- What language is hummingbird written in?
- microsoft/hummingbird is primarily written in Python.
- How popular is hummingbird?
- microsoft/hummingbird has 3.5k stars on GitHub.
- Where can I find hummingbird?
- microsoft/hummingbird is on GitHub at https://github.com/microsoft/hummingbird.