Releases: NVIDIA/cuda-python
Releases · NVIDIA/cuda-python
cuda-pathfinder v1.2.3
cuda-pathfinder v1.2.2
cuda-pathfinder v1.2.1
cuda-pathfinder v1.2.0
CUDA Python 13.0.1
CUDA Python 12.9.2
CUDA Python 13.0.0
cuda.core v0.3.2
cuda.core
v0.3.2 release announcement
Release note
All functionalities are currently hosted under the cuda.core.experimental
namespace. Once the features become stable they will be moved out of experimental
.
Documentation
Sample codes
What's Changed
- Fix CI build-time parallelism + support the same env var in
cuda.core
by @leofang in #743 - [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci[bot] in #746
SPDX-FileCopyrightText
cleanup by @rwgk in #753- Construct instance of appropriate class in Event._init and Stream._init by @shwina in #752
- Fix typos and grammar in documentation by @cluster2600 in #774
- Update
cuda.bindings
to 13.0.0 by @leofang in #792 - getting started example is complete by @richardhboyd in #797
- Make
Device.set_current()
faster by @leofang in #781 - Bump cuda.core to 0.3.2 by @leofang in #817
New Contributors
- @cluster2600 made their first contribution in #774
- @richardhboyd made their first contribution in #797
Full Changelog: cuda-core-v0.3.1...cuda-core-v0.3.2
CUDA Python 12.9.1
cuda-pathfinder v1.1.0
- CTK 13.0.0 compatibility
- Bug fix: load
libnvJitLink.so.12
from conda, not/usr/local/cuda
PR #767