Install & Compatibility
Where this runs
tested against v? · pip install
Install × environment matrix
Each cell = how many times install + import succeeded across repeated harness runs. Partial = flaky.
glibc = Debian/Ubuntu slim · musl = Alpine Linux
muslpy 3.10–3.910 runs
installs and imports cleanly · install 0.0s · import 0.000s
glibcpy 3.10–3.910 runs
installs and imports cleanly · install 0.0s · import 0.000s
Code
Verified usage
Verified import paths — ran on the pinned version, not inferred.
compute
✓ import cuda.compute
Provides device-level parallel algorithms like reduce, scan, and sort.
coop
✓ import cuda.coop
Provides block and warp-level cooperative primitives for custom CUDA kernels.
This example demonstrates how to perform a parallel reduction sum on a CuPy array using `cuda.compute.reduce`. It showcases a basic use case of the Pythonic interface to GPU-accelerated algorithms.
import cuda.compute
import cupy as cp
def reduce_sum_example():
# Initialize CuPy array on GPU
arr = cp.arange(1000, dtype=cp.int32)
# Perform a reduction sum using cuda.compute
result = cuda.compute.reduce(arr, op='sum')
print(f"Original array sum (CuPy): {arr.sum()}")
print(f"Reduced sum (cuda.compute): {result}")
assert result == arr.sum()
if __name__ == "__main__":
reduce_sum_example()
Debug
Known issues
breakingThe `cuda-cccl` Python package is in 'experimental' status, meaning its API and feature set can change rapidly. Users should anticipate potential breaking changes between minor versions.fixAlways refer to the latest documentation and release notes before upgrading. Pin exact versions in production environments.
affects: All versions of the `cuda-cccl` Python package.
breakingCCCL is not forward compatible with the CUDA Toolkit. An older version of CCCL will not be compatible with a newer CUDA Toolkit. However, a newer CCCL can generally be integrated with an older CUDA Toolkit.fixEnsure that your CCCL version is the same or newer than the version included with your CUDA Toolkit installation. Always use the latest compatible CCCL version for your CUDA Toolkit.
affects: All versions
breakingFor C++ users, CCCL 3.0 (bundled with CUDA Toolkit 13.0) introduced significant breaking changes, including dropping support for C++11/14, CUDA Toolkit versions prior to 12.0, and older host compilers (GCC < 7, Clang < 14, MSVC < 2019). It also removed support for ICC and CUDA Dynamic Parallelism v1.fixUpdate your C++ standard to C++17 or newer, ensure your CUDA Toolkit is 12.0+, and use compatible host compilers. Consult the CCCL 2.x to 3.0 Migration Guide for detailed steps.
affects: CCCL 3.0 and newer (and corresponding CUDA Toolkit 13.0+)
breakingStarting with CUDA Toolkit 13.0 (which includes CCCL 3.0), the on-disk header location for CCCL in the CUDA Toolkit installation moved to `${CTK_ROOT}/include/cccl/`. Also, the `nvidia-cuda-cccl` PyPI package will no longer use `cuXX` suffixes (e.g., `nvidia-cuda-cccl-cu12`) to allow upstream libraries to select the CUDA version.fixUpdate build systems to reflect the new header paths. For Python installations, prefer `pip install cuda-cccl[cuXX]` as specified, or `pip install cuda-cccl` for the general version when CUDA 13.0+ is in use, allowing the upstream to manage the CUDA version selection.
affects: CCCL 3.0 and newer (and corresponding CUDA Toolkit 13.0+)
gotchaWhen compiling CUDA C++ code with `nvcc`, it automatically adds CCCL headers to your include path. However, if compiling with other compilers, you must manually update your build system's include search path to point to the CCCL headers.fixFor non-nvcc compilers, explicitly add the path to CCCL headers (e.g., `/usr/local/cuda/include` or `${CTK_ROOT}/include/cccl/`) to your build system's include paths (`-I`). Avoid `-isystem` and use `-I` to prevent collisions with implicitly included headers. affects: All versions
Upgrade
Version history
13.3.3.4.1latest on PyPI · released Jun 29, 2026
Audit
Dependencies
PythonrequiredRequired runtime environment.
CUDA ToolkitrequiredGPU acceleration requires a compatible CUDA Toolkit installation.
NVIDIA GPUrequiredRequires a GPU with Compute Capability 6.0 or higher.