Installation¶

HyperTorch can be installed from PyPI when you want to use it as a dependency, or from source when you want to contribute or run the latest repository version.

The examples below use uv, which is also the build and development tool used inside the project. If you prefer pip, replace uv pip install with pip install in the installation commands.

Install from PyPI¶

The commands below install the CPU wheels for Python 3.10 through 3.14 on the supported platforms:

• Linux x86_64.
• Linux ARM/aarch64.
• macOS arm64.
• Windows x64.

If you are using CUDA or different hardware, install the matching PyTorch and PyG wheels first, while staying within the dependency ranges declared by HyperTorch. Then, install HyperTorch with the same final command for your platform.

Linux x86_64¶

uv pip install "torch>=2.12.0,<2.13.0" --index-url https://download.pytorch.org/whl/cpu
uv pip install pyg-lib --find-links https://data.pyg.org/whl/torch-2.12.0+cpu.html
uv pip install hypertorch

Linux ARM/aarch64¶

uv pip install "torch>=2.11.0,<2.12.0" --index-url https://download.pytorch.org/whl/cpu
uv pip install torch-cluster --find-links https://data.pyg.org/whl/torch-2.11.0+cpu.html
uv pip install hypertorch

macOS arm64¶

uv pip install "torch>=2.12.0,<2.13.0" --index-url https://download.pytorch.org/whl/cpu
uv pip install pyg-lib --find-links https://data.pyg.org/whl/torch-2.12.0+cpu.html
uv pip install hypertorch

Windows x64¶

uv pip install "torch>=2.12.0,<2.13.0" --index-url https://download.pytorch.org/whl/cpu
uv pip install pyg-lib --find-links https://data.pyg.org/whl/torch-2.12.0+cpu.html
uv pip install hypertorch

Install from source¶

Use the development installation for contributing or if you want to use the latest features that have not been released yet. The Makefile wraps the standard project setup commands:

git clone https://github.com/hypernetwork-research-group/hypertorch.git
cd hypertorch

make setup

See the Development guide for the full development workflow.

Python version support¶

See Python support policy in Policies.

TensorBoard support¶

To include TensorBoard support, also run HyperTorch install command with the TensorBoard extra:

uv pip install "hypertorch[tensorboard]"

When installing from source, run the command:

make setup-tensorboard

Required dependencies¶

HyperTorch declares compatibility ranges for direct dependencies in pyproject.toml.

Optional dependencies¶

Development dependencies¶