Hummingbird

license

MIT(OSI)

source

public

core features withheld

no

The LICENSE file contains the MIT text. The repository is public and the README describes no paid tier, enterprise edition or license-gated build, so the core is ungated.

• https://raw.githubusercontent.com/microsoft/hummingbird/main/LICENSE recorded 2026-09-30

  LICENSE file is the verbatim MIT text, opening with "MIT License" and "Copyright (c) Microsoft Corporation." and "Permission is hereby granted, free of charge, to any person obtaining a copy".

• https://raw.githubusercontent.com/microsoft/hummingbird/main/README.md recorded 2026-09-30

  README says "Hummingbird* is a library for compiling trained traditional ML models into tensor computations" and installs with "python -m pip install hummingbird-ml", with optional dependencies lightgbm and xgboost via "hummingbird-ml[extra]". Searched the body for enterprise, license key, paid, commercial and proprietary: none.

• https://raw.githubusercontent.com/microsoft/hummingbird/main/setup.py recorded 2026-09-30

  setup.py declares license="MIT License" with the classifier "License :: OSI Approved :: MIT License" and install_requires of open packages such as "scikit-learn", "torch>1.7.0" and "onnx<=1.16.1". Searched the body for enterprise, license key, paid, commercial and proprietary: none.

PyPI downloads of `hummingbird-ml` are the adoption signal here.

• https://pypistats.org/api/packages/hummingbird-ml/recent recorded 2026-10-07

  6,571 downloads in the trailing 30 days for hummingbird-ml (pypistats last_month)

Hummingbird translates classical machine-learning models such as decision trees and random forests into PyTorch, TorchScript, ONNX or TVM tensor programs. That is a translation into another runtime's format rather than the optimizing compilation TensorRT performs, and it covers one input class only.

• https://raw.githubusercontent.com/microsoft/hummingbird/main/README.md recorded 2026-09-30

  README says "you can use *Hummingbird* to convert your trained traditional ML models into [PyTorch](https://pytorch.org/), [TorchScript](https://pytorch.org/docs/stable/jit.html), [ONNX](https://onnx.ai/), and [TVM](https://docs.tvm.ai/))" and that supported models include "scikit-learn](https://scikit-learn.org/stable/) Decision Trees and Random Forest, and also [LightGBM]".

• https://raw.githubusercontent.com/microsoft/hummingbird/main/README.md recorded 2026-09-30

  README explains "Hummingbird works by reconfiguring algorithmic operators such that we can perform more regular computations which are amenable to vectorized and GPU execution."