Update CUDA Python project list by leofang · Pull Request #1339 · NVIDIA/cuda-python

leofang · 2025-12-08T03:20:58Z

Description

Make the list of projects under the CUDA Python program up-to-date upon internal requests.

Components Added

cuda.tile - CUDA Tile programming model DSL
nvshmem4py - NVSHMEM PGAS programming interface
NSIGHT Python - Kernel profiling with Nsight Tools
CUPTI Python - CUPTI profiling tool APIs

Components Updated

Renamed cuda.cccl.cooperative → cuda.coop
Renamed cuda.cccl.parallel → cuda.compute
Enhanced nvmath-python description to include distributed APIs
Updated numba.cuda to specify SIMT programming model

URL Corrections

cuda.coop: Updated URL from cccl/python/cooperative to cccl/python/coop
cuda.compute: Updated URL from cccl/python/parallel to cccl/python/compute
Applied corrections to README.md, DESCRIPTION.rst, index.rst, and conf.py

Sphinx Configuration Updates

Updated rst_epilog in cuda_python/docs/source/conf.py to drop mentions of projects that do not use CUDA_PYTHON_DOMAIN
This ensures RST cross-references work correctly across all documentation files

Additional Fixes

Fixed capitalization: "pythonic" → "Pythonic"
Fixed grammar: "interfaces are" → "interfaces is"
Updated wording: "bring up" → "introduce", "is now" → "is being restructured to become"
Added cuda.pathfinder to DESCRIPTION.rst (was missing)

Checklist

New or existing tests cover these changes.
The documentation is up to date with these changes.

Co-authored-by: leofang <5534781+leofang@users.noreply.github.com>

…ted here

Update cuda_python documentation to match README.md component list

copy-pr-bot · 2025-12-08T03:21:02Z

This pull request requires additional validation before any workflows can run on NVIDIA's runners.

Pull request vetters can view their responsibilities here.

Contributors can view more details about this message here.

leofang · 2025-12-08T03:21:23Z

+* [cuda.coop](https://nvidia.github.io/cccl/python/coop): A Python module providing CCCL's reusable block-wide and warp-wide *device* primitives for use within Numba CUDA kernels
+* [cuda.compute](https://nvidia.github.io/cccl/python/compute): A Python module for easy access to CCCL's highly efficient and customizable parallel algorithms, like `sort`, `scan`, `reduce`, `transform`, etc. that are callable on the *host*
+* [numba.cuda](https://nvidia.github.io/numba-cuda/): A Python DSL that exposes CUDA **SIMT** programming model and compiles a restricted subset of Python code into CUDA kernels and device functions
+* [cuda.tile](https://docs.nvidia.com/cuda/cutile-python/): A new Python DSL that exposes CUDA **Tile** programming model and allows users to write NumPy-like code in CUDA kernels


cc @aterrel for vis

leofang · 2025-12-08T03:23:03Z

+* [numba.cuda](https://nvidia.github.io/numba-cuda/): A Python DSL that exposes CUDA **SIMT** programming model and compiles a restricted subset of Python code into CUDA kernels and device functions
+* [cuda.tile](https://docs.nvidia.com/cuda/cutile-python/): A new Python DSL that exposes CUDA **Tile** programming model and allows users to write NumPy-like code in CUDA kernels
+* [nvmath-python](https://docs.nvidia.com/cuda/nvmath-python/latest): Pythonic access to NVIDIA CPU & GPU Math Libraries, with [*host*](https://docs.nvidia.com/cuda/nvmath-python/latest/overview.html#host-apis), [*device*](https://docs.nvidia.com/cuda/nvmath-python/latest/overview.html#device-apis), and distributed [*distributed*](https://docs.nvidia.com/cuda/nvmath-python/latest/distributed-apis/index.html) APIs. It also provides low-level Python bindings to host C APIs ([nvmath.bindings](https://docs.nvidia.com/cuda/nvmath-python/latest/bindings/index.html)).
+* [nvshmem4py](https://docs.nvidia.com/nvshmem/api/api/language_bindings/python/index.html): Pythonic interface to the NVSHMEM library, enabling Python applications to leverage NVSHMEM's high-performance PGAS (Partitioned Global Address Space) programming model for GPU-accelerated computing


cc @benhg for vis

leofang · 2025-12-08T14:27:56Z

/ok to test 2f5339b

github-actions · 2025-12-08T14:37:26Z

Doc Preview CI
🚀 View preview at https://nvidia.github.io/cuda-python/pr-preview/pr-1339/
https://nvidia.github.io/cuda-python/pr-preview/pr-1339/cuda-core/
https://nvidia.github.io/cuda-python/pr-preview/pr-1339/cuda-bindings/
https://nvidia.github.io/cuda-python/pr-preview/pr-1339/cuda-pathfinder/
Preview will be ready when the GitHub Pages deployment is complete.

Co-authored-by: Juan Galvez <jjgalvez@msn.com>

leofang · 2025-12-08T16:09:44Z

/ok to test e6a1cb7

leofang · 2025-12-08T19:28:13Z

This is ready.

rwgk

LGTM

I ran this in Cursor:

Could you please obtain the git diff --merge-base main for this branch? Could you please identify any inconsistencies between the duplicate information between the three changed .rst and .md files?

Conclusion: there are no substantive inconsistencies in the duplicated information across these three changed documentation files; only formatting/markup differences appropriate to Markdown vs reStructuredText.

rwgk · 2025-12-08T20:13:07Z

+- `cuda.coop`_: A Python module providing CCCL's reusable block-wide and warp-wide *device* primitives for use within Numba CUDA kernels
+- `cuda.compute`_: A Python module for easy access to CCCL's highly efficient and customizable parallel algorithms, like ``sort``, ``scan``, ``reduce``, ``transform``, etc. that are callable on the *host*
+- `numba.cuda`_: A Python DSL that exposes CUDA **SIMT** programming model and compiles a restricted subset of Python code into CUDA kernels and device functions
+- `cuda.tile`_: A new Python DSL that exposes CUDA **Tile** programming model and allows users to write NumPy-like code in CUDA kernels


"new" will get stale

Could we write something like: A Python DSL (GA v1.0.0 released with CTK 13.1) that exposes ...?

Stephen Jones doesn't want us to call CUDA a DSL.

Suggest:

The CUDA Tile programming model embeded in Python, it allows users to write NumPy-like code in CUDA kernels

@aterrel would you mind sending a PR to update it? 🙂

leofang · 2025-12-09T00:56:38Z

Thanks to all!

Removed preview folders for the following PRs: - PR #1339

leofang and others added 8 commits December 8, 2025 02:42

update readme

a1e0f91

Initial plan

41698da

Update documentation files following commit a1e0f91

0c5235e

Co-authored-by: leofang <5534781+leofang@users.noreply.github.com>

Update cuda.coop and cuda.compute URLs to correct paths

955f6f2

Co-authored-by: leofang <5534781+leofang@users.noreply.github.com>

Update rst_epilog to use new package names cuda.coop and cuda.compute

f82116c

Co-authored-by: leofang <5534781+leofang@users.noreply.github.com>

only projects maintained in the NVIDIA/cuda-python repo should be lis…

e126704

…ted here

fix numba-cuda hyperlink

107a9b9

Merge pull request #6 from leofang/copilot/update-docs-formatting

2f5339b

Update cuda_python documentation to match README.md component list

leofang added this to the cuda.core beta 10 milestone Dec 8, 2025

leofang requested review from aterrel and kkraus14 December 8, 2025 03:20

leofang self-assigned this Dec 8, 2025

leofang added documentation Improvements or additions to documentation P1 Medium priority - Should do labels Dec 8, 2025

leofang commented Dec 8, 2025

View reviewed changes

leofang requested a review from rparolin December 8, 2025 14:13

juanjgalvez reviewed Dec 8, 2025

View reviewed changes

Comment thread README.md Outdated

Comment thread cuda_python/DESCRIPTION.rst Outdated

Comment thread cuda_python/docs/source/index.rst Outdated

leofang commented Dec 8, 2025

View reviewed changes

Comment thread README.md Outdated

Comment thread cuda_python/DESCRIPTION.rst Outdated

Comment thread cuda_python/docs/source/index.rst Outdated

Comment thread cuda_python/docs/source/index.rst Outdated

Comment thread cuda_python/docs/source/index.rst Outdated

Apply suggestions from code review

e6a1cb7

Co-authored-by: Juan Galvez <jjgalvez@msn.com>

rwgk approved these changes Dec 8, 2025

View reviewed changes

kkraus14 approved these changes Dec 9, 2025

View reviewed changes

leofang commented Dec 9, 2025

View reviewed changes

Apply suggestions from code review

47bf0fe

leofang merged commit 95d5844 into NVIDIA:main Dec 9, 2025
1 check passed

leofang deleted the program_expansion branch December 9, 2025 00:56

github-actions Bot pushed a commit that referenced this pull request Dec 9, 2025

Clean up PR preview folders for 1 closed/merged PRs

b30e8ae

Removed preview folders for the following PRs: - PR #1339

Conversation

leofang commented Dec 8, 2025

Description

Components Added

Components Updated

URL Corrections

Sphinx Configuration Updates

Additional Fixes

Checklist

Uh oh!

copy-pr-bot Bot commented Dec 8, 2025

Uh oh!

leofang Dec 8, 2025

Choose a reason for hiding this comment

Uh oh!

Uh oh!

leofang Dec 8, 2025

Choose a reason for hiding this comment

Uh oh!

Uh oh!

leofang commented Dec 8, 2025

Uh oh!

github-actions Bot commented Dec 8, 2025

Preview will be ready when the GitHub Pages deployment is complete.

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

leofang commented Dec 8, 2025

Uh oh!

leofang commented Dec 8, 2025

Uh oh!

rwgk left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

rwgk Dec 8, 2025

Choose a reason for hiding this comment

Uh oh!

aterrel Feb 6, 2026

Choose a reason for hiding this comment

Uh oh!

leofang Feb 6, 2026

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

leofang commented Dec 9, 2025

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

7 participants