-
Notifications
You must be signed in to change notification settings - Fork 270
Pull requests: NVIDIA/cuda-python
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
Sync CI: switch to rapidsai sccache fork and bump CUDA to 13.2.1
CI/CD
CI/CD infrastructure
cuda.bindings
Everything related to the cuda.bindings module
Add PersistentProgramCache (sqlite + filestream backends)
cuda.core
Everything related to the cuda.core module
feature
New feature or request
P0
High priority - Must do!
Rework Linker dispatching for cross-major nvJitLink/driver skew
breaking
Breaking changes are introduced
cuda.core
Everything related to the cuda.core module
enhancement
Any code-related improvements
P0
High priority - Must do!
Make Linker.backend a classmethod
breaking
Breaking changes are introduced
cuda.core
Everything related to the cuda.core module
enhancement
Any code-related improvements
P0
High priority - Must do!
CI: Test sdist builds for all user-facing packages
CI/CD
CI/CD infrastructure
P0
High priority - Must do!
CI: Detect changed paths and gate cuda.bindings tests
CI/CD
CI/CD infrastructure
enhancement
Any code-related improvements
P0
High priority - Must do!
CI: Check versioned release notes exist before releasing
CI/CD
CI/CD infrastructure
P0
High priority - Must do!
[no-ci] CI: drive restricted paths guard from user-in-org-check-bot
CI/CD
CI/CD infrastructure
P0
High priority - Must do!
[DRAFT] Replace nvrtc Tempita templates with pre-generated Cython files
cuda.bindings
Everything related to the cuda.bindings module
enhancement
Any code-related improvements
[no-ci] CI: add dedicated merge gate for restricted-paths review
CI/CD
CI/CD infrastructure
cuda.bindings
Everything related to the cuda.bindings module
P0
High priority - Must do!
[no-ci] DUMMY CHANGE: cuda_bindings/pyproject.toml
Needs-Restricted-Paths-Review
PR touches cuda_bindings or cuda_python; only NVIDIA employees may modify these paths; see LICENSEs
#1895
opened Apr 12, 2026 by
rwgkunplugged
Loading…
Add torch.Tensor fast path for StridedMemoryView via AOTI tensor bridge
cuda.core
Everything related to the cuda.core module
P0
High priority - Must do!
performance
[NVVM] Expose nvvm version detection in cuda.bindings.utils.
cuda.bindings
Everything related to the cuda.bindings module
enhancement
Any code-related improvements
P1
Medium priority - Should do
[no-ci] coverage: fix Linux git ownership and add Windows stack wrapper
bug
Something isn't working
CI/CD
CI/CD infrastructure
P1
Medium priority - Should do
Fix bug 5811173: update cufile tests and configuration
bug
Something isn't working
cuda.bindings
Everything related to the cuda.bindings module
test
Improvements or additions to tests
[WIP] Guard host managed-memory access on concurrentManagedAccess=0
bug
Something isn't working
cuda.core
Everything related to the cuda.core module
P0
High priority - Must do!
test
Improvements or additions to tests
WIP: Add Everything related to the cuda.core module
feature
New feature or request
P0
High priority - Must do!
cuda.core.utils.make_aligned_dtype
cuda.core
Switch CI to uv and use build[uv] frontend for cibuildwheel
to-be-backported
Trigger the bot to raise a backport PR upon merge
#1615
opened Feb 12, 2026 by
kkraus14
Collaborator
Loading…
4 tasks
Previous Next
ProTip!
What’s not been updated in a month: updated:<2026-03-15.