From a673bdc05279197a578aedc23ee7cb7f8ce6a378 Mon Sep 17 00:00:00 2001 From: "copilot-swe-agent[bot]" <198982749+Copilot@users.noreply.github.com> Date: Mon, 25 Aug 2025 21:07:36 +0000 Subject: [PATCH 1/3] Initial plan From cf64e78ace5c4f12bd3441905578b95b8358c474 Mon Sep 17 00:00:00 2001 From: "copilot-swe-agent[bot]" <198982749+Copilot@users.noreply.github.com> Date: Mon, 25 Aug 2025 21:12:56 +0000 Subject: [PATCH 2/3] Update installation guides and support policies to cover CUDA 12/13 instead of 11/12 Co-authored-by: leofang <5534781+leofang@users.noreply.github.com> --- cuda_bindings/docs/source/support.rst | 2 +- cuda_core/docs/source/install.rst | 18 +++++++++--------- 2 files changed, 10 insertions(+), 10 deletions(-) diff --git a/cuda_bindings/docs/source/support.rst b/cuda_bindings/docs/source/support.rst index 2aa5896985e..f0283611733 100644 --- a/cuda_bindings/docs/source/support.rst +++ b/cuda_bindings/docs/source/support.rst @@ -10,7 +10,7 @@ The ``cuda.bindings`` module has the following support policy: third number in the version string), however, is reserved to reflect Python-only changes and is out of sync with the Toolkit patch version. 2. The module is actively maintained to support the latest CUDA major version and its prior major - version. For example, as of writing the bindings for CUDA 11 & 12 are maintained. Any fix in the + version. For example, as of writing the bindings for CUDA 12 & 13 are maintained. Any fix in the latest bindings would be backported to the prior major version. 3. The module supports `CUDA minor version compatibility`_, meaning that ``cuda.bindings`` 12.x supports any Toolkit 12.y. (Whether or not a binding API would actually correctly function diff --git a/cuda_core/docs/source/install.rst b/cuda_core/docs/source/install.rst index 8bc1faa0e14..0a2e197e1d0 100644 --- a/cuda_core/docs/source/install.rst +++ b/cuda_core/docs/source/install.rst @@ -14,14 +14,14 @@ dependencies are as follows: :header-rows: 1 * - - - CUDA 11 - CUDA 12 + - CUDA 13 * - CUDA Toolkit\ [#f1]_ - - 11.2 - 11.8 - 12.x + - 13.x * - Driver - - 450.80.02+ (Linux), 452.39+ (Windows) - 525.60.13+ (Linux), 527.41+ (Windows) + - 555.00+ (Linux), 556.12+ (Windows) .. [#f1] Including ``cuda-python``. @@ -31,27 +31,27 @@ dependencies are as follows: Installing from PyPI -------------------- -``cuda.core`` works with ``cuda.bindings`` (part of ``cuda-python``) 11 or 12. Test dependencies now use the ``cuda-toolkit`` metapackage for improved dependency resolution. For example with CUDA 12: +``cuda.core`` works with ``cuda.bindings`` (part of ``cuda-python``) 12 or 13. Test dependencies now use the ``cuda-toolkit`` metapackage for improved dependency resolution. For example with CUDA 12: .. code-block:: console $ pip install cuda-core[cu12] -and likewise use ``[cu11]`` for CUDA 11, or ``[cu13]`` for CUDA 13. +and likewise use ``[cu13]`` for CUDA 13. Note that using ``cuda.core`` with NVRTC installed from PyPI via ``pip install`` requires -``cuda.bindings`` 12.8.0+ or 11.8.6+. Likewise, with nvJitLink it requires 12.8.0+. +``cuda.bindings`` 12.8.0+. Likewise, with nvJitLink it requires 12.8.0+. Installing from Conda (conda-forge) ----------------------------------- -Same as above, ``cuda.core`` can be installed in a CUDA 11 or 12 environment. For example with CUDA 12: +Same as above, ``cuda.core`` can be installed in a CUDA 12 or 13 environment. For example with CUDA 12: .. code-block:: console $ conda install -c conda-forge cuda-core cuda-version=12 -and likewise use ``cuda-version=11`` for CUDA 11. +and likewise use ``cuda-version=13`` for CUDA 13. Note that to use ``cuda.core`` with nvJitLink installed from conda-forge requires ``cuda.bindings`` 12.8.0+. @@ -64,4 +64,4 @@ Installing from Source $ cd cuda-python/cuda_core $ pip install . -``cuda-bindings`` 11.x or 12.x is a required dependency. +``cuda-bindings`` 12.x or 13.x is a required dependency. From 08ac62f50ddcf38a08bf31245d211a9532d09751 Mon Sep 17 00:00:00 2001 From: "copilot-swe-agent[bot]" <198982749+Copilot@users.noreply.github.com> Date: Mon, 25 Aug 2025 21:25:14 +0000 Subject: [PATCH 3/3] Update CUDA 13 driver requirements and add CUDA 11 deprecation note Co-authored-by: leofang <5534781+leofang@users.noreply.github.com> --- cuda_core/docs/source/install.rst | 2 +- cuda_core/docs/source/release/0.X.Y-notes.rst | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/cuda_core/docs/source/install.rst b/cuda_core/docs/source/install.rst index 0a2e197e1d0..32028a63bdf 100644 --- a/cuda_core/docs/source/install.rst +++ b/cuda_core/docs/source/install.rst @@ -21,7 +21,7 @@ dependencies are as follows: - 13.x * - Driver - 525.60.13+ (Linux), 527.41+ (Windows) - - 555.00+ (Linux), 556.12+ (Windows) + - 580.65+ (Linux), 580.88+ (Windows) .. [#f1] Including ``cuda-python``. diff --git a/cuda_core/docs/source/release/0.X.Y-notes.rst b/cuda_core/docs/source/release/0.X.Y-notes.rst index 40fece768e6..8024a14f622 100644 --- a/cuda_core/docs/source/release/0.X.Y-notes.rst +++ b/cuda_core/docs/source/release/0.X.Y-notes.rst @@ -18,6 +18,7 @@ Highlights Breaking Changes ---------------- +- **CUDA 11 support dropped**: CUDA 11 support is no longer tested and it may or may not work with cuda.bindings and CTK 11.x. Users are encouraged to migrate to CUDA 12.x or 13.x. - **LaunchConfig grid parameter interpretation**: When :attr:`LaunchConfig.cluster` is specified, the :attr:`LaunchConfig.grid` parameter now correctly represents the number of clusters instead of blocks. Previously, the grid parameter was incorrectly interpreted as blocks, causing a mismatch with the expected C++ behavior. This change ensures that ``LaunchConfig(grid=4, cluster=2, block=32)`` correctly produces 4 clusters × 2 blocks/cluster = 8 total blocks, matching the C++ equivalent ``cudax::make_hierarchy(cudax::grid_dims(4), cudax::cluster_dims(2), cudax::block_dims(32))``. - When :class:`Buffer` is closed, :attr:`Buffer.handle` is now set to ``None``. It was previously set to ``0`` by accident.