-
Notifications
You must be signed in to change notification settings - Fork 306
Back to Milestones
cuda.core v0.6.0
Closed Apr 7, 2026
Due by February 17, 2026
•Closed 100% complete
List view
0 of 72 selected 0 issues of 72 selected
Cythonize
_module.pycuda.coreEverything related to the cuda.core moduleEverything related to the cuda.core moduleenhancementAny code-related improvementsAny code-related improvementsP1Medium priority - Should doMedium priority - Should doStatus: Closed (completed).#1081 In NVIDIA/cuda-python;Cythonize
_program.pycuda.coreEverything related to the cuda.core moduleEverything related to the cuda.core moduleenhancementAny code-related improvementsAny code-related improvementsP1Medium priority - Should doMedium priority - Should doStatus: Closed (completed).#1082 In NVIDIA/cuda-python;Cythonize
_context.pyxmorecuda.coreEverything related to the cuda.core moduleEverything related to the cuda.core moduleenhancementAny code-related improvementsAny code-related improvementsP1Medium priority - Should doMedium priority - Should doStatus: Closed (completed).#1075 In NVIDIA/cuda-python;Expand
cuda.core.systemto cover NVML functionalitiesblockedThis task is currently blocked by other tasksThis task is currently blocked by other taskscuda.coreEverything related to the cuda.core moduleEverything related to the cuda.core modulefeatureNew feature or requestNew feature or requestP0High priority - Must do!High priority - Must do!Status: Closed (completed).#1211 In NVIDIA/cuda-python;RFC: Remove
StridedMemoryView(to somewhere else)?breakingBreaking changes are introducedBreaking changes are introducedcuda.coreEverything related to the cuda.core moduleEverything related to the cuda.core moduleP0High priority - Must do!High priority - Must do!RFCPlans and announcementsPlans and announcementsStatus: Closed (completed).#1371 In NVIDIA/cuda-python;[NVVM] Support - Followup enhancements
cuda.coreEverything related to the cuda.core moduleEverything related to the cuda.core moduleenhancementAny code-related improvementsAny code-related improvementsP1Medium priority - Should doMedium priority - Should doStatus: Merged (completed).NVIDIA/cuda-pythonnumber 1218#1218 In NVIDIA/cuda-python;Add CUDA version compatibility check
cuda.coreEverything related to the cuda.core moduleEverything related to the cuda.core modulefeatureNew feature or requestNew feature or requestP0High priority - Must do!High priority - Must do!Status: Merged (completed).__hash__,__eq__, ... should not require a CUDA contextcuda.coreEverything related to the cuda.core moduleEverything related to the cuda.core moduleenhancementAny code-related improvementsAny code-related improvementstriageNeeds the team's attentionNeeds the team's attentionStatus: Closed (completed).#1480 In NVIDIA/cuda-python;[BUG]: Legacy/per-thread default streams should be singletons
bugSomething isn't workingSomething isn't workingcuda.coreEverything related to the cuda.core moduleEverything related to the cuda.core moduleP0High priority - Must do!High priority - Must do!Status: Closed (completed).#1494 In NVIDIA/cuda-python;- Status: Merged (completed).
Remove context dependency from __hash__ and __eq__
cuda.coreEverything related to the cuda.core moduleEverything related to the cuda.core moduleenhancementAny code-related improvementsAny code-related improvementsStatus: Merged (completed).Add multi-GPU CI runners (t4 and h100 with 2 GPUs)
CI/CDCI/CD infrastructureCI/CD infrastructureenhancementAny code-related improvementsAny code-related improvementsP0High priority - Must do!High priority - Must do!Status: Merged (completed).Fix/default stream singletons
cuda.coreEverything related to the cuda.core moduleEverything related to the cuda.core moduleenhancementAny code-related improvementsAny code-related improvementsP0High priority - Must do!High priority - Must do!Status: Merged (completed).NVIDIA/cuda-pythonnumber 1496#1496 In NVIDIA/cuda-python;[FEA]: cuda.core.system: Provide convenience methods to convert between cuda.core.system.Device and cuda.core.Device
cuda.coreEverything related to the cuda.core moduleEverything related to the cuda.core moduleStatus: Closed (completed).#1507 In NVIDIA/cuda-python;[FEA]: cuda.core.system: Be more specific about skipping tests on unsupported hardware
cuda.coreEverything related to the cuda.core moduleEverything related to the cuda.core moduleStatus: Closed (completed).#1497 In NVIDIA/cuda-python;[DOC]: links to subpackages on the landing page of PR links go to existing documentation
P0High priority - Must do!High priority - Must do!Status: Not planned (skipped).#1231 In NVIDIA/cuda-python;Adopt PEP 563 annotations and modern union syntax
cuda.coreEverything related to the cuda.core moduleEverything related to the cuda.core moduleStatus: Merged (completed).Add __weakref__ support to core API classes
cuda.coreEverything related to the cuda.core moduleEverything related to the cuda.core moduleenhancementAny code-related improvementsAny code-related improvementsP1Medium priority - Should doMedium priority - Should doStatus: Merged (completed).Add __eq__ and __hash__ to Buffer, LaunchConfig, Kernel, ObjectCode
cuda.coreEverything related to the cuda.core moduleEverything related to the cuda.core moduleenhancementAny code-related improvementsAny code-related improvementsP1Medium priority - Should doMedium priority - Should doStatus: Merged (completed).Cythonize _program.py
cuda.coreEverything related to the cuda.core moduleEverything related to the cuda.core moduleP0High priority - Must do!High priority - Must do!Status: Merged (completed).- Status: Merged (completed).
[ENH] Add safeguards for unsynchronized stream destruction
cuda.coreEverything related to the cuda.core moduleEverything related to the cuda.core moduleenhancementAny code-related improvementsAny code-related improvementsStatus: Closed (completed).#1539 In NVIDIA/cuda-python;Reduce wheel size by excluding source files
cuda.bindingsEverything related to the cuda.bindings moduleEverything related to the cuda.bindings modulecuda.coreEverything related to the cuda.core moduleEverything related to the cuda.core moduleP0High priority - Must do!High priority - Must do!packagingAnything related to wheels or Conda packagesAnything related to wheels or Conda packagesStatus: Merged (completed).Warn when creating ManagedMemoryResource on platforms without concurrent managed access
cuda.coreEverything related to the cuda.core moduleEverything related to the cuda.core moduleenhancementAny code-related improvementsAny code-related improvementsP0High priority - Must do!High priority - Must do!Status: Closed (completed).#1607 In NVIDIA/cuda-python;Reorganize graph tests and add device-side launch support
cuda.coreEverything related to the cuda.core moduleEverything related to the cuda.core moduleenhancementAny code-related improvementsAny code-related improvementsStatus: Merged (completed).