List view

Python latency testing & benchmarking

cuda.bindingsEverything related to the cuda.bindings moduleEverything related to the cuda.bindings module

cuda.coreEverything related to the cuda.core moduleEverything related to the cuda.core module

P1Medium priority - Should doMedium priority - Should do

Status: Open.

Initiative

#1580 In NVIDIA/cuda-python;

· leofang opened on Feb 5, 2026

Review and standardize all example code before cuda.core 1.0.0 release

cuda.coreEverything related to the cuda.core moduleEverything related to the cuda.core module

Status: Open.

Epic

#1673 In NVIDIA/cuda-python;

· rparolin opened on Feb 20, 2026

CUDA graph phase N - graph updates

cuda.coreEverything related to the cuda.core moduleEverything related to the cuda.core module

featureNew feature or requestNew feature or request

Status: Open.

#1330 In NVIDIA/cuda-python;

· leofang opened on Dec 6, 2025

[FEA]: Expand cuda.core.system to near 100% NVML coverage

cuda.coreEverything related to the cuda.core moduleEverything related to the cuda.core module

Status: Open.

Epic

#1600 In NVIDIA/cuda-python;

· mdboom opened on Feb 11, 2026

Implement compiler caches

cuda.coreEverything related to the cuda.core moduleEverything related to the cuda.core module

featureNew feature or requestNew feature or request

P0High priority - Must do!High priority - Must do!

Status: Open.

#176 In NVIDIA/cuda-python;

· leofang opened on Oct 17, 2024

Add cuda.core.utils.ProgramCacheResource

cuda.coreEverything related to the cuda.core moduleEverything related to the cuda.core module

featureNew feature or requestNew feature or request

P1Medium priority - Should doMedium priority - Should do

Status: Open.

#179 In NVIDIA/cuda-python;

· leofang opened on Oct 17, 2024

Add cuda.core.utils.InMemoryProgramCache

cuda.coreEverything related to the cuda.core moduleEverything related to the cuda.core module

featureNew feature or requestNew feature or request

P1Medium priority - Should doMedium priority - Should do

Status: Open.

#177 In NVIDIA/cuda-python;

· leofang opened on Oct 17, 2024

Add cuda.core.utils.PersistentProgramCache

cuda.coreEverything related to the cuda.core moduleEverything related to the cuda.core module

featureNew feature or requestNew feature or request

P0High priority - Must do!High priority - Must do!

Status: Open.

#178 In NVIDIA/cuda-python;

· leofang opened on Oct 17, 2024

Support batched memory movement

cuda.coreEverything related to the cuda.core moduleEverything related to the cuda.core module

featureNew feature or requestNew feature or request

Status: Open.

#1333 In NVIDIA/cuda-python;

· leofang opened on Dec 6, 2025

Examples: Fix or remove conjugateGradientMultiBlockCG_test.py

cuda.bindingsEverything related to the cuda.bindings moduleEverything related to the cuda.bindings module

documentationImprovements or additions to documentationImprovements or additions to documentation

Status: Open.

#1839 In NVIDIA/cuda-python;

· mdboom opened on Mar 31, 2026

Examples: numba_emm_plugin.py seems to have bit-rotted

bugSomething isn't workingSomething isn't working

Status: Open.

Bug

#1840 In NVIDIA/cuda-python;

· mdboom opened on Mar 31, 2026

Add managed-memory advise, prefetch, and discard-prefetch free functions

Status: Open (in progress).

NVIDIA/cuda-pythonnumber 1775

#1775 In NVIDIA/cuda-python;

· rparolin opened on Mar 17, 2026

[EPIC] Support green contexts

cuda.coreEverything related to the cuda.core moduleEverything related to the cuda.core module

EPICSoul of a releaseSoul of a release

featureNew feature or requestNew feature or request

P0High priority - Must do!High priority - Must do!

Status: Open.

Epic

#112 In NVIDIA/cuda-python;

· leofang opened on Sep 19, 2024

GreenContext: Support allocating SMs

cuda.coreEverything related to the cuda.core moduleEverything related to the cuda.core module

featureNew feature or requestNew feature or request

Status: Open.

#1563 In NVIDIA/cuda-python;

· leofang opened on Feb 2, 2026

Support managed memory advise, prefetch, and discard-prefetch

cuda.coreEverything related to the cuda.core moduleEverything related to the cuda.core module

featureNew feature or requestNew feature or request

P1Medium priority - Should doMedium priority - Should do

Status: Open.

#1332 In NVIDIA/cuda-python;

· leofang opened on Dec 6, 2025

Implement Context.__init__() in cuda.core.experimental._context

blockedThis task is currently blocked by other tasksThis task is currently blocked by other tasks

cuda.coreEverything related to the cuda.core moduleEverything related to the cuda.core module

featureNew feature or requestNew feature or request

P0High priority - Must do!High priority - Must do!

Status: Open.

Enhancement

#189 In NVIDIA/cuda-python;

· keenan-simpson opened on Oct 25, 2024

WIP: Support passing SMV as a kernel argument of type cuda::std::mdspan

cuda.coreEverything related to the cuda.core moduleEverything related to the cuda.core module

featureNew feature or requestNew feature or request

Status: Draft (not ready).

NVIDIA/cuda-pythonnumber 1387

#1387 In NVIDIA/cuda-python;

· leofang opened on Dec 16, 2025

[FEA]: Tests for ltoir, fatbin, object, and library constructors

cuda.coreEverything related to the cuda.core moduleEverything related to the cuda.core module

P1Medium priority - Should doMedium priority - Should do

testImprovements or additions to testsImprovements or additions to tests

Status: Open.

Task

#663 In NVIDIA/cuda-python;

· brandon-b-miller opened on May 29, 2025

refactor(tests): replace exec() with importlib in example runner

Status: Open (in progress).

NVIDIA/cuda-pythonnumber 1628

#1628 In NVIDIA/cuda-python;

· OfficialSerge opened on Feb 14, 2026

test_vmm_allocator_policy_configuration failure: Windows / A6000 / WDDM

bugSomething isn't workingSomething isn't working

cuda.coreEverything related to the cuda.core moduleEverything related to the cuda.core module

P1Medium priority - Should doMedium priority - Should do

Status: Open.

Bug

#1264 In NVIDIA/cuda-python;

· rwgk opened on Nov 18, 2025

WIP: Add cuda.core.utils.make_aligned_dtype

cuda.coreEverything related to the cuda.core moduleEverything related to the cuda.core module

featureNew feature or requestNew feature or request

P0High priority - Must do!High priority - Must do!

Status: Draft (not ready).

NVIDIA/cuda-pythonnumber 1636

#1636 In NVIDIA/cuda-python;

· leofang opened on Feb 18, 2026

[FEA]: private constructor prevents derived classes of cythonized Stream, Event

bugSomething isn't workingSomething isn't working

cuda.coreEverything related to the cuda.core moduleEverything related to the cuda.core module

triageNeeds the team's attentionNeeds the team's attention

Status: Open.

#750 In NVIDIA/cuda-python;

· carterbox opened on Jul 9, 2025

cuda-core build_hooks.py missing compiler/linker flags present in cuda-bindings

cuda.coreEverything related to the cuda.core moduleEverything related to the cuda.core module

P1Medium priority - Should doMedium priority - Should do

packagingAnything related to wheels or Conda packagesAnything related to wheels or Conda packages

Status: Open.

Task

#1882 In NVIDIA/cuda-python;

· leofang opened on Apr 8, 2026

Add torch.Tensor fast path for StridedMemoryView via AOTI tensor bridge

breakingBreaking changes are introducedBreaking changes are introduced

cuda.coreEverything related to the cuda.core moduleEverything related to the cuda.core module

P0High priority - Must do!High priority - Must do!

performance

Status: Draft (not ready).

NVIDIA/cuda-pythonnumber 1894

#1894 In NVIDIA/cuda-python;

· leofang opened on Apr 10, 2026

CI: Check versioned release notes exist before releasing

CI/CDCI/CD infrastructureCI/CD infrastructure

P0High priority - Must do!High priority - Must do!

Status: Open (in progress).

NVIDIA/cuda-pythonnumber 1907

#1907 In NVIDIA/cuda-python;

· cpcloud opened on Apr 14, 2026