NVIDIA cuPyNumeric

Important

cuPyNumeric has reached end of life and is no longer maintained or supported. The final release is v26.06.01. No further releases, fixes, or support are planned. Existing packages and documentation remain available for historical reference, but we do not recommend starting new projects with cuPyNumeric.

Consider one of the following alternatives for multi-GPU/multi-node array computing:

• nvmath-python, in particular the nvmath.distributed module

• CuPy combined with mpi4py or Dask Array & Dask-CUDA

• JAX, in particular the multi-controller module

• PyTorch, in particular the torch.distributed module

cuPyNumeric implements the NumPy API on top of the Legate framework, providing transparent accelerated computing that scales from a single CPU to a single GPU, and up to multi-node, multi-GPU systems.

For example, you can run the final example of the Python CFD course completely unmodified on 2048 A100 GPUs in a DGX SuperPOD and achieve good weak scaling.

Contents:

• Installation
• User guide
• Examples
• API Reference
• Frequently Asked Questions
• Developer guide
• Acknowledgments
• Third-party notices

Indices and tables

• Index

• Search Page