From a973c2707bcc10de6886cb70cef1eb85354a44df Mon Sep 17 00:00:00 2001 From: Leo Fang Date: Mon, 11 Aug 2025 13:48:46 +0000 Subject: [PATCH 1/3] make it clear cuda-pathfinder is installed as part of cuda-python --- cuda_python/docs/source/index.rst | 1 + cuda_python/docs/source/release/12.9.1-notes.rst | 1 + cuda_python/docs/source/release/13.0.0-notes.rst | 1 + cuda_python/setup.py | 1 + 4 files changed, 4 insertions(+) diff --git a/cuda_python/docs/source/index.rst b/cuda_python/docs/source/index.rst index 6990df6c4..99197f39f 100644 --- a/cuda_python/docs/source/index.rst +++ b/cuda_python/docs/source/index.rst @@ -9,6 +9,7 @@ multiple components: - `cuda.core`_: Pythonic access to CUDA runtime and other core functionalities - `cuda.bindings`_: Low-level Python bindings to CUDA C APIs +- `cuda.pathfinder`: Utilities for locating CUDA components installed in the user's Python virtual environment - `cuda.cccl.cooperative`_: A Python module providing CCCL's reusable block-wide and warp-wide *device* primitives for use within Numba CUDA kernels - `cuda.cccl.parallel`_: 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`_: Numba's target for CUDA GPU programming by directly compiling a restricted subset of Python code into CUDA kernels and device functions following the CUDA execution model. diff --git a/cuda_python/docs/source/release/12.9.1-notes.rst b/cuda_python/docs/source/release/12.9.1-notes.rst index 282cd56f7..1da1e811f 100644 --- a/cuda_python/docs/source/release/12.9.1-notes.rst +++ b/cuda_python/docs/source/release/12.9.1-notes.rst @@ -11,6 +11,7 @@ Included components ------------------- * `cuda.bindings 12.9.1 `_ +* cuda.pathfinder 1.1.0 Highlights diff --git a/cuda_python/docs/source/release/13.0.0-notes.rst b/cuda_python/docs/source/release/13.0.0-notes.rst index 140c28839..e152093f9 100644 --- a/cuda_python/docs/source/release/13.0.0-notes.rst +++ b/cuda_python/docs/source/release/13.0.0-notes.rst @@ -11,6 +11,7 @@ Included components ------------------- * `cuda.bindings 13.0.0 `_ +* cuda.pathfinder 1.1.0 Highlights diff --git a/cuda_python/setup.py b/cuda_python/setup.py index dd84f5579..f50dad33c 100644 --- a/cuda_python/setup.py +++ b/cuda_python/setup.py @@ -17,6 +17,7 @@ version=version, install_requires=[ f"cuda-bindings~={version}", + "cuda-pathfinder~=1.1", ], extras_require={ "all": [f"cuda-bindings[all]~={version}"], From 9aa38db1bda649e2f9053162753b56f5462acc31 Mon Sep 17 00:00:00 2001 From: Leo Fang Date: Mon, 11 Aug 2025 21:52:34 +0800 Subject: [PATCH 2/3] Update README.md --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index 00e853e29..45ab7f1f7 100644 --- a/README.md +++ b/README.md @@ -4,6 +4,7 @@ CUDA Python is the home for accessing NVIDIA’s CUDA platform from Python. It c * [cuda.core](https://nvidia.github.io/cuda-python/cuda-core/latest): Pythonic access to CUDA Runtime and other core functionalities * [cuda.bindings](https://nvidia.github.io/cuda-python/cuda-bindings/latest): Low-level Python bindings to CUDA C APIs +* cuda.pathfinder: Utilities for locating CUDA components installed in the user's Python virtual environment * [cuda.cccl.cooperative](https://nvidia.github.io/cccl/python/cooperative): A Python module providing CCCL's reusable block-wide and warp-wide *device* primitives for use within Numba CUDA kernels * [cuda.cccl.parallel](https://nvidia.github.io/cccl/python/parallel): 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/): Numba's target for CUDA GPU programming by directly compiling a restricted subset of Python code into CUDA kernels and device functions following the CUDA execution model. From d7b997be22f0f60e7e7285031245d980a6513924 Mon Sep 17 00:00:00 2001 From: Leo Fang Date: Tue, 12 Aug 2025 16:43:50 +0000 Subject: [PATCH 3/3] rewording + add placeholder hyperlinks --- README.md | 2 +- cuda_python/docs/source/index.rst | 4 +++- cuda_python/docs/source/release/12.9.1-notes.rst | 2 +- cuda_python/docs/source/release/13.0.0-notes.rst | 2 +- 4 files changed, 6 insertions(+), 4 deletions(-) diff --git a/README.md b/README.md index 45ab7f1f7..5f8f3a11e 100644 --- a/README.md +++ b/README.md @@ -4,7 +4,7 @@ CUDA Python is the home for accessing NVIDIA’s CUDA platform from Python. It c * [cuda.core](https://nvidia.github.io/cuda-python/cuda-core/latest): Pythonic access to CUDA Runtime and other core functionalities * [cuda.bindings](https://nvidia.github.io/cuda-python/cuda-bindings/latest): Low-level Python bindings to CUDA C APIs -* cuda.pathfinder: Utilities for locating CUDA components installed in the user's Python virtual environment +* [cuda.pathfinder](https://github.com/NVIDIA/cuda-python/blob/main/cuda_pathfinder/cuda/pathfinder/README.md): Utilities for locating CUDA components installed in the user's Python environment * [cuda.cccl.cooperative](https://nvidia.github.io/cccl/python/cooperative): A Python module providing CCCL's reusable block-wide and warp-wide *device* primitives for use within Numba CUDA kernels * [cuda.cccl.parallel](https://nvidia.github.io/cccl/python/parallel): 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/): Numba's target for CUDA GPU programming by directly compiling a restricted subset of Python code into CUDA kernels and device functions following the CUDA execution model. diff --git a/cuda_python/docs/source/index.rst b/cuda_python/docs/source/index.rst index 99197f39f..f0ed6f52d 100644 --- a/cuda_python/docs/source/index.rst +++ b/cuda_python/docs/source/index.rst @@ -9,12 +9,13 @@ multiple components: - `cuda.core`_: Pythonic access to CUDA runtime and other core functionalities - `cuda.bindings`_: Low-level Python bindings to CUDA C APIs -- `cuda.pathfinder`: Utilities for locating CUDA components installed in the user's Python virtual environment +- `cuda.pathfinder_`: Utilities for locating CUDA components installed in the user's Python environment - `cuda.cccl.cooperative`_: A Python module providing CCCL's reusable block-wide and warp-wide *device* primitives for use within Numba CUDA kernels - `cuda.cccl.parallel`_: 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`_: Numba's target for CUDA GPU programming by directly compiling a restricted subset of Python code into CUDA kernels and device functions following the CUDA execution model. * `nvmath-python`_: Pythonic access to NVIDIA CPU & GPU Math Libraries, with both *host* and *device* (through `nvmath.device`_) APIs. It also provides low-level Python bindings to host C APIs (through `nvmath.bindings`_). +.. _cuda.pathfinder: https://github.com/NVIDIA/cuda-python/blob/main/cuda_pathfinder/cuda/pathfinder/README.md .. _nvmath-python: https://docs.nvidia.com/cuda/nvmath-python/latest .. _nvmath.device: https://docs.nvidia.com/cuda/nvmath-python/latest/overview.html#device-apis .. _nvmath.bindings: https://docs.nvidia.com/cuda/nvmath-python/latest/bindings/index.html @@ -34,6 +35,7 @@ be available, please refer to the `cuda.bindings`_ documentation for installatio release.md cuda.core cuda.bindings + cuda.pathfinder cuda.cccl.cooperative cuda.cccl.parallel numba.cuda diff --git a/cuda_python/docs/source/release/12.9.1-notes.rst b/cuda_python/docs/source/release/12.9.1-notes.rst index 1da1e811f..444b7c9ca 100644 --- a/cuda_python/docs/source/release/12.9.1-notes.rst +++ b/cuda_python/docs/source/release/12.9.1-notes.rst @@ -11,7 +11,7 @@ Included components ------------------- * `cuda.bindings 12.9.1 `_ -* cuda.pathfinder 1.1.0 +* `cuda.pathfinder 1.1.0 `_ Highlights diff --git a/cuda_python/docs/source/release/13.0.0-notes.rst b/cuda_python/docs/source/release/13.0.0-notes.rst index e152093f9..e89534bc9 100644 --- a/cuda_python/docs/source/release/13.0.0-notes.rst +++ b/cuda_python/docs/source/release/13.0.0-notes.rst @@ -11,7 +11,7 @@ Included components ------------------- * `cuda.bindings 13.0.0 `_ -* cuda.pathfinder 1.1.0 +* `cuda.pathfinder 1.1.0 `_ Highlights