Repository files navigation

Website|Install|Tutorial|Examples|Documentation|API Reference|Forum

CuPy is a NumPy/SciPy-compatible array library for GPU-accelerated computing with Python.CuPy acts as adrop-in replacement to run existing NumPy/SciPy code on NVIDIA CUDA or AMD ROCm platforms.

>>>importcupyascp>>>x=cp.arange(6).reshape(2,3).astype('f')>>>xarray([[0.,1.,2.],       [3.,4.,5.]],dtype=float32)>>>x.sum(axis=1)array([3.,12.],dtype=float32)

CuPy also provides access to low-level CUDA features.You can passndarray to existing CUDA C/C++ programs viaRawKernels, useStreams for performance, or even callCUDA Runtime APIs directly.

Binary packages (wheels) are available for Linux and Windows onPyPI.Choose the right package for your platform.

Binary packages are also available for Linux and Windows onConda-Forge.

If you need a slim installation (without also getting CUDA dependencies installed), you can doconda install -c conda-forge cupy-core.

If you need to use a particular CUDA version (say 12.0), you can use thecuda-version metapackage to select the version, e.g.conda install -c conda-forge cupy cuda-version=12.0.

UseNVIDIA Container Toolkit to runCuPy container images.

$ docker run --gpus all -it cupy/cupy

• Installation Guide - instructions on building from source
• Release Notes
• Projects using CuPy
• Contribution Guide
• GPU Acceleration in Python using CuPy and Numba (GTC November 2021 Technical Session)
• GPU-Acceleration of Signal Processing Workflows using CuPy and cuSignal1 (ICASSP'21 Tutorial)

MIT License (seeLICENSE file).

CuPy is designed based on NumPy's API and SciPy's API (seedocs/source/license.rst file).

CuPy is being developed and maintained byPreferred Networks andcommunity contributors.

Ryosuke Okuta, Yuya Unno, Daisuke Nishino, Shohei Hido and Crissman Loomis.CuPy: A NumPy-Compatible Library for NVIDIA GPU Calculations.Proceedings of Workshop on Machine Learning Systems (LearningSys) in The Thirty-first Annual Conference on Neural Information Processing Systems (NIPS), (2017).[PDF]

@inproceedings{cupy_learningsys2017,author       ="Okuta, Ryosuke and Unno, Yuya and Nishino, Daisuke and Hido, Shohei and Loomis, Crissman",title        ="CuPy: A NumPy-Compatible Library for NVIDIA GPU Calculations",booktitle    ="Proceedings of Workshop on Machine Learning Systems (LearningSys) in The Thirty-first Annual Conference on Neural Information Processing Systems (NIPS)",year         ="2017",url          ="http://learningsys.org/nips17/assets/papers/paper_16.pdf"}