OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Infrastructure & Serving

Hummingbird

Hummingbird is a Python library that compiles trained traditional machine-learning models into tensor computations for inference through frameworks such as PyTorch.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Hummingbird — OpenViST project profile in AI Infrastructure & Serving.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when you want to convert a supported traditional ML model into a tensor-oriented representation for inference, rather than re-engineering the model for a neural-network framework.

Who it is for

  • Developers working with trained traditional machine-learning models.
  • Teams seeking to use tensor-oriented frameworks or inference tooling with supported scikit-learn, LightGBM or XGBoost models.

Documented uses

  • Convert supported trained models into PyTorch, TorchScript, ONNX or TVM representations.
  • Use a scikit-learn-style inference API with Hummingbird-generated models.
  • Prepare converted PyTorch or TorchScript models for serving through TorchServe.
Before you choose

Requirements & limits

The project is an open-source public GitHub repository under the MIT license. The README provides pip installation instructions.

  • PyTorch 1.6.0 or later is required.
  • The README lists Python 3.9, 3.10 and 3.11; its TVM note limits that path to Python 3.10.
  • LightGBM and XGBoost are listed as optional dependencies installable with the extra package option.
  • The README names supported model families and conversion targets; support should be considered at that documented scope.
  • The README says converted PyTorch and TorchScript models can be served using TorchServe.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install Hummingbird for a Python environment

Install the library after preparing a compatible Python environment and PyTorch.

Before you start

  • Python 3.9, 3.10 or 3.11; the README recommends using a virtual environment.
  • PyTorch 1.6.0 or later.

Steps

  1. Install PyTorch using the instructions appropriate to the platform and hardware.

  2. Install Hummingbird with the command below.

    Documented command
    python -m pip install hummingbird-ml

  3. For optional LightGBM and XGBoost dependencies, install the command below.

    Documented command
    python -m pip install hummingbird-ml[extra]

Expected outcome

Hummingbird and, if requested, its optional LightGBM and XGBoost dependencies are installed in the environment.

Guide limitations

  • TVM works through Python 3.10 only, according to the README.
  • Installation instructions do not establish that a particular model or hardware configuration is compatible.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Model inference and serving

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
HummingbirdConvert supported trained models into PyTorch, TorchScript, ONNX or TVM representations.CLIThe project is an open-source public GitHub repository under the MIT license. The README provides pip installation instructions.
Cloud AI SDKAdapt and run documented model recipes for computer-vision and NLP inference.Cloud, ServerThe GitHub repository is public. Its public visibility does not establish license terms.
TurboquantReplace a model’s existing inference cache with a compressed cache.Cloud, Linux, macOS, Self-hostedThe project describes itself as open source. The README documents installation through pip or from a source checkout.
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
10 October 2026
Original website title
microsoft/hummingbird · Official homepage title · retained in its source language
How we review sourcesSuggest a correction