NVIDIA® cuOpt™ is a GPU-accelerated optimization engine that excels in mixed integer linear programming (MILP), linear programming (LP), and vehicle routing problems (VRP). It enables near real-time solutions for large-scale challenges with millions of variables and constraints, offering easy integration into existing solvers and seamless deployment across hybrid and multi-cloud environments.
The core engine is written in C++ and wrapped with a C API, Python API and Server API.
For the latest stable version ensure you are on the main branch.
cuOpt supports the following APIs:
- C API support
- Linear Programming (LP)
- Mixed Integer Linear Programming (MILP)
- C++ API support
- cuOpt is written in C++ and includes a native C++ API. However, we do not provide documentation for the C++ API at this time. We anticipate that the C++ API will change significantly in the future. Use it at your own risk.
- Python support
- Routing (TSP, VRP, and PDP)
- Linear Programming (LP) and Mixed Integer Linear Programming (MILP)
- cuOpt includes a Python API that is used as the backend of the cuOpt server. However, we do not provide documentation for the Python API at this time. We suggest using cuOpt server to access cuOpt via Python. We anticipate that the Python API will change significantly in the future. Use it at your own risk.
- Server support
- Linear Programming (LP)
- Mixed Integer Linear Programming (MILP)
- Routing (TSP, VRP, and PDP)
- CUDA 12.0+
- NVIDIA driver >= 525.60.13 (Linux) and >= 527.41 (Windows)
- Volta architecture or better (Compute Capability >=7.0)
- Python >=3.10.x, <= 3.12.x
- Only Linux is supported and Windows via WSL2
- x86_64 (64-bit)
- aarch64 (64-bit)
Note: WSL2 is tested to run cuOpt, but not for building.
More details on system requirements can be found here
Pip wheels are easy to install and easy to configure. Users with existing workflows who uses pip as base to build their workflows can use pip to install cuOpt.
cuOpt can be installed via pip from the NVIDIA Python Package Index.
Be sure to select the appropriate cuOpt package depending
on the major version of CUDA available in your environment:
For CUDA 12.x:
pip install --extra-index-url=https://pypi.nvidia.com cuopt-server-cu12==25.5.* cuopt-sh-client==25.5.* nvidia-cuda-runtime-cu12==12.8.*Development wheels are available as nightlies, please update --extra-index-url to https://pypi.anaconda.org/rapidsai-wheels-nightly/simple/ to install latest nightly packages.
cuOpt can be installed with conda (via miniforge) from the nvidia channel:
All other dependencies are installed automatically when cuopt-server and cuopt-sh-client are installed.
Users who are used to conda env based workflows would benefit with conda packages readily available for cuOpt.
For CUDA 12.x:
conda install -c rapidsai -c conda-forge -c nvidia \
cuopt-server=25.05.* cuopt-sh-client=25.05.* python=3.12 cuda-version=12.8We also provide nightly Conda packages built from the HEAD
of our latest development branch. Just replace -c rapidsai with -c rapidsai-nightly.
Users can pull the cuOpt container from the NVIDIA container registry.
docker pull nvidia/cuopt:latest-cuda12.8-py312 Note: The latest tag is the latest stable release of cuOpt. If you want to use a specific version, you can use the <version>-cuda12.8-py312 tag. For example, to use cuOpt 25.5.0, you can use the 25.5.0-cuda12.8-py312 tag. Please refer to cuOpt dockerhub page <https://hub.docker.com/r/nvidia/cuopt>_ for the list of available tags.
More information about the cuOpt container can be found here.
Users who are using cuOpt for quick testing or research can use the cuOpt container. Alternatively, users who are planning to plug cuOpt as a service in their workflow can quickly start with the cuOpt container. But users are required to build security layers around the service to safeguard the service from untrusted users.
Please see our guide for building cuOpt from source. This will be helpful if users want to add new features or fix bugs for cuOpt. This would also be very helpful in case users want to customize cuOpt for their own use cases which require changes to the cuOpt source code.
Review the CONTRIBUTING.md file for information on how to contribute code and issues to the project.
- libcuopt (C) documentation
- cuopt (Python) documentation
- cuopt (Server) documentation
- Examples and Notebooks
- Test cuopt with NVIDIA Launchable: Examples notebooks are pulled and hosted on NVIDIA Launchable.
- Test cuopt on Google Colab: Examples notebooks can be opened in Google Colab. Please note that you need to choose a
RuntimeasGPUin order to run the notebooks.