← Discover
Discover · GitHub · Cupy↑ +174 today

GPU-powered numerical computing library

CuPy combines the numerical computing library NumPy and SciPy interfaces with graphics processing unit (GPU) acceleration. This Python-based library accelerates complex mathematical operations using CUDA cores.

Updates

  • August 20, 2026: Stars 12,227 → 12,259, latest release v14.2.0 (August 20, 2026).
  • August 2, 2026: Stars 11,639 → 12,227, latest release v14.1.1 (June 1, 2026).

What you get

  • Compatible with NumPy and SciPy
  • NVIDIA CUDA and AMD ROCm support
  • Access to low-level CUDA features

Running it

Running with Docker
docker run --gpus all -it cupy/cupy

If you don't write code

🤖 Paste this into your AI agent (Claude Code · Codex · Antigravity)

I want to take advantage of GPU acceleration in my Python code instead of NumPy or SciPy. How can I run my existing NumPy codes on the GPU using CuPy and integrate low-level CUDA features like RawKernels into my project?

Related dictionary terms

GPUArtificial Intelligence
Who it is forIt's for data scientists and engineers who need GPU acceleration for their Python-based numerical calculations.
LicenseMIT

Links

TreScout did not build this tool · we found it in GitHub trends and wrote it up. This page describes the repository as of 2026-06-29: The star count and our text belong to that day, the repository may have changed since. Check the repository link for the current state. This page was machine-translated from the Turkish original · the Turkish version prevails.