| Name | Modified | Size | Downloads / Week |
|---|---|---|---|
| Parent folder | |||
| CCCL Python Libraries (1.0.0) source code.tar.gz | 2026-05-12 | 10.8 MB | |
| CCCL Python Libraries (1.0.0) source code.zip | 2026-05-12 | 18.1 MB | |
| README.md | 2026-05-12 | 2.5 kB | |
| Totals: 3 Items | 28.9 MB | 0 | |
CCCL Python Libraries (v1.0.0)
Previous release: v0.7.0.
This is the first stable release of the cuda-cccl Python package.
The cuda.compute module is now considered stable, and we will follow semantic versioning for changes to its public API going forward.
The cuda.coop module remains experimental and has been moved to cuda.coop._experimental to reflect that. See breaking changes below.
Installation
Please refer to the install instructions here.
API breaking changes
cuda.coopcooperative primitives moved tocuda.coop._experimental(#8788)
The block, warp, and StatefulFunction entry points previously exported from cuda.coop have been moved to the cuda.coop._experimental submodule, signaling that their API is not yet stable and is expected to change in a future release. Top-level cuda.coop no longer re-exports these.
Before:
python
from cuda.coop import block, warp, StatefulFunction
After:
python
from cuda.coop._experimental import block, warp, StatefulFunction
cuda.cccl.cooperativelegacy namespace removed (#8788)
The deprecated cuda.cccl.cooperative package (previously kept as a transitional alias) has been removed entirely. Migrate any remaining imports to cuda.coop._experimental.
Features
- Python 3.14 support —
cuda-ccclis now built and tested against Python 3.14 in addition to 3.10–3.13 (#8870).
Bug Fixes / Packaging
- Avoid incompatible
numba-cudaversions — The dependency pin onnumba-cudawas tightened to exclude 0.27.x, 0.28.x, 0.29.x, and 0.30.0, which contain regressions that breakcuda-cccl(#8831).
Known issues
cuda.coop._experimentalmay fail withRuntimeError: nvdisasm was not found or could not be executedifnvdisasmis not discoverable. Follow the suggestion in the error message to installnvdisasm. If it is already installed, set theCUDA_PATHenvironment variable (notPATH) to the root of the directory containingbin/nvdisasm:
bash
export CUDA_PATH=/path/to/cuda # such that $CUDA_PATH/bin/nvdisasm exists
Notes
cuda.computeitself has no API changes in this release relative to v0.7.0. The 0.7.0 release contained the API cleanup (keyword-only arguments, parameter reordering,d_in_values/d_out_valuesrename inmerge_sort); 1.0.0 is the formal stabilization of that API.