Skip to main content

CUDA target for Numba

Project description

Numba CUDA Target

An out-of-tree CUDA target for Numba.

This contains an entire copy of Numba's CUDA target (the numba.cuda module), and a mechanism to ensure the code from this module (numba_cuda.numba.cuda) is used as the numba.cuda module instead of the code from the numba package.

This is presently in an early state and is published for testing and feedback.

Building / testing

Install as an editable install:

pip install -e .

Running tests:

python -m numba.runtests numba.cuda.tests

This should discover thenumba.cuda module from the numba_cuda package. You can check where numba.cuda files are being located by running

python -c "from numba import cuda; print(cuda.__file__)"

which will show a path like:

<path to numba-cuda repo>/numba_cuda/numba/cuda/__init__.py

Branching strategy

Presently the main branch is being used to target the exact behavior of the built-in CUDA target. New feature development and bug fixes should be applied to develop. Once the main branch is widely tested and confirmed to work well as a drop-in replacement for the built-in numba.cuda, the develop branch will be merged in and new feature development will proceed on main.

Current PR targets

  • PRs related to replacing the built-in CUDA target's features should target main.
  • PRs adding new features and bug fixes should target develop.

Future PR targets

  • In future, all PRs should target the main branch.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distribution

numba_cuda-0.0.14-py3-none-any.whl (424.3 kB view details)

Uploaded Python 3

File details

Details for the file numba_cuda-0.0.14-py3-none-any.whl.

File metadata

  • Download URL: numba_cuda-0.0.14-py3-none-any.whl
  • Upload date:
  • Size: 424.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.0 CPython/3.12.5

File hashes

Hashes for numba_cuda-0.0.14-py3-none-any.whl
Algorithm Hash digest
SHA256 7b78106048f3b43035270dabeb9b28810317111c357c8654631e44fc7977a1e5
MD5 84ebaf28a7e434fbe218b0681ba7a704
BLAKE2b-256 05464d6871d58e7666b26a9bf4d0b7b4a90ff8d02a3f564c68afc19d8e6574c0

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page