About CuPy

CuPy is a NumPy/SciPy-compatible array library for GPU-accelerated computing with Python. Our goal is to provide Python users with GPU acceleration capabilities without in-depth knowledge of underlying GPU technologies. Specifically, we are focusing on providing:

• A complete NumPy and SciPy API coverage to become a full drop-in replacement, as well as advanced CUDA features to maximize the performance.
• Mature and quality library as a fundamental package for all projects needing acceleration, from a lab environment to a large-scale cluster.

For more information, take a look at the Overview page and the Wikipedia article. You can also explore Projects using CuPy to see various projects that use or support CuPy.

Your Support Matters

CuPy is a non-profit project managed by a small, dedicated team. Your sponsorship helps ensure that we can continue fulfilling our mission. The funds collected support the development team and cover the costs of cloud infrastructure required for continuous integration and building binary packages.

CuPy is a NumFOCUS Sponsored Project. Funds are collected and disbursed via NumFOCUS, a 501(c)(3) public charity in the United States, which acts as the fiscal sponsor for the project.

You can also donate through NumFOUCS if you prefer to use other payment methods, including Apple Pay, Google Pay, or ACH. Your donation is tax-deductible to the extent provided by US law.