CuPy – NumPy & SciPy for GPU

• Overview
  • Project Goal
• Installation
  • Requirements
  • Installing CuPy
  • Uninstalling CuPy
  • Upgrading CuPy
  • Reinstalling CuPy
  • Using CuPy inside Docker
  • FAQ
• Using CuPy on AMD GPU (experimental)
  • Requirements
  • Environment Variables
  • Docker
  • Installing Binary Packages
  • Building CuPy for ROCm From Source
  • Limitations
• User Guide
  • Basics of CuPy
  • User-Defined Kernels
  • Accessing CUDA Functionalities
  • Fast Fourier Transform with CuPy
  • Memory Management
  • Performance Best Practices
  • Interoperability
  • Differences between CuPy and NumPy
  • API Compatibility Policy
• API Reference
  • The N-dimensional array (ndarray)
  • Universal functions (cupy.ufunc)
  • Routines (NumPy)
  • Routines (SciPy)
  • CuPy-specific functions
  • Low-level CUDA support
  • Custom kernels
  • Distributed
  • Environment variables
  • Comparison Table
  • Python Array API Support

Development

• Contribution Guide
  • Classification of Contributions
  • Development Cycle
  • Issues and Pull Requests
  • Coding Guidelines
  • Unit Testing
  • Documentation
  • Tips for Developers

Misc Notes

• Upgrade Guide
  • CuPy v10
  • CuPy v9
  • CuPy v8
  • CuPy v7
  • CuPy v6
  • CuPy v5
  • CuPy v4
  • CuPy v2
  • Compatibility Matrix
• License
  • NumPy
  • SciPy

Overview