cuda.core 1.3.0

Issues

• Add cuda-cccl as a required dependency to cuda-python

  cuda.bindingsP1packagingRFC
  Enhancement

  NVIDIA/cuda-python#691 · Filter by author leofang opened on Jun 7, 2025 · cuda.core 1.3.0
  3

  

• [FEA] cuda.core: memory-pool location routing and new pool attributes (CUDA 13.0/13.2)

  cuda.corefeature
  Enhancement

  NVIDIA/cuda-python#2362 · Filter by author leofang opened on Jul 14, 2026 · cuda.core 1.3.0
  

• Migrate from os.path to pathlib.Path

  cuda.bindingscuda.corecuda.pathfinderenhancement
  Enhancement

  NVIDIA/cuda-python#2410 · Filter by author mdboom opened on Jul 23, 2026 · cuda.core 1.3.0
  7

  

• cuda.core: support multidimensional and array-backed graph memcpy nodes

  cuda.corefeatureP1
  Enhancement

  NVIDIA/cuda-python#2420 · Filter by author Andy-Jost opened on Jul 24, 2026 · cuda.core 1.3.0
  

• cuda.core: support clustered and cooperative kernel graph nodes

  bugcuda.corefeatureP1
  Enhancement

  NVIDIA/cuda-python#2421 · Filter by author Andy-Jost opened on Jul 24, 2026 · cuda.core 1.3.0
  

• EPIC: Typing enhancement

  cuda.coreenhancementEPICP1
  Epic

  NVIDIA/cuda-python#469 · Filter by author leofang opened on Feb 24, 2025 · cuda.core 1.3.0
  3

  

• [FEA] cuda.core: adopt nvFatbin for multi-arch fat binary assembly

  cuda.corefeature
  Enhancement

  NVIDIA/cuda-python#2356 · Filter by author leofang opened on Jul 14, 2026 · cuda.core 1.3.0
  

• [FEA] cuda.core: expose graph and graph-node identity/introspection APIs (CUDA 13.1)

  cuda.corefeature
  Enhancement

  NVIDIA/cuda-python#2360 · Filter by author leofang opened on Jul 14, 2026 · cuda.core 1.3.0
  

• [FEA] cuda.core: support logical endpoints (CUDA 13.3 unicast/multicast memory sharing)

  cuda.corefeature
  Enhancement

  NVIDIA/cuda-python#2358 · Filter by author leofang opened on Jul 14, 2026 · cuda.core 1.3.0
  

• [FEA] cuda.core: support stream batch memory operations (incl. CUDA 13.1 atomic reductions)

  cuda.corefeature
  Enhancement

  NVIDIA/cuda-python#2364 · Filter by author leofang opened on Jul 14, 2026 · cuda.core 1.3.0
  

• [FEA] cuda.core: green context / device-resource follow-ons (CUDA 13.0-13.3)

  cuda.corefeature
  Enhancement

  NVIDIA/cuda-python#2366 · Filter by author leofang opened on Jul 14, 2026 · cuda.core 1.3.0
  

• [MNT] cuda.core: device-attribute catch-up for CUDA 13.1/13.3

  cuda.coreenhancement
  Enhancement

  NVIDIA/cuda-python#2367 · Filter by author leofang opened on Jul 14, 2026 · cuda.core 1.3.0
  

• [FEA] cuda.core: add remaining new NVRTC options to ProgramOptions (CUDA 13.1+)

  cuda.corefeature
  Enhancement

  NVIDIA/cuda-python#2368 · Filter by author leofang opened on Jul 14, 2026 · cuda.core 1.3.0
  

• [FEA] cuda.core: expose device atomic-operation capability queries (CUDA 13.0)

  cuda.corefeature
  Enhancement

  NVIDIA/cuda-python#2361 · Filter by author leofang opened on Jul 14, 2026 · cuda.core 1.3.0
  

• [FEA]: Define new protocol(s) defining the size of an object in GPU memory

  cuda.corefeatureP1
  Enhancement

  NVIDIA/cuda-python#646 · Filter by author vyasr opened on May 19, 2025 · cuda.core 1.3.0
  

• cuda.core: expose GraphDefinition cloning

  cuda.corefeatureP0
  Enhancement

  NVIDIA/cuda-python#2438 · Filter by author Andy-Jost opened on Jul 28, 2026 · cuda.core 1.3.0
  

• [cuda.core] Add support for Multicast Objects

  cuda.corefeatureP1
  Enhancement

  NVIDIA/cuda-python#2057 · Filter by author rparolin opened on May 8, 2026 · cuda.core 1.3.0
  4

  

• build(cuda.core): spike scikit-build-core migration

  CI/CDcuda.bindingscuda.coreexperimentpackaging
  Unread
  NVIDIA/cuda-python#2607·kkraus14 opened Aug 12, 2026 · Updated Aug 20, 2026·Draft
  1

• Pool-backed MemoryResource buffers bypass overridden deallocate() methods

  bugcuda.core
  Bug

  NVIDIA/cuda-python#2615 · Filter by author Andy-Jost opened on Aug 13, 2026 · cuda.core 1.3.0
  3

  

• EPIC: cuda.core C++ integration with RAPIDs & CCCL

  cuda.coreEPICfeatureP1
  Epic

  NVIDIA/cuda-python#1786 · Filter by author rparolin opened on Mar 18, 2026 · cuda.core 1.3.0
  1

  

• RFC: Enable per-thread default stream in free-threading builds

  cuda.bindingsfeatureP0RFC
  Enhancement

  NVIDIA/cuda-python#133 · Filter by author leofang opened on Sep 26, 2024 · cuda.core 1.3.0
  14

  

• Support Python 3.15

  cuda.bindingscuda.corecuda.pathfinderP0packaging
  Enhancement

  NVIDIA/cuda-python#2163 · Filter by author leofang opened on Jun 2, 2026 · cuda.core 1.3.0
  3

  

• Address duplicate import issue found in pypi-installed cuda-core packages

  cuda.coreP2test
  Unread
  NVIDIA/cuda-python#2386·acosmicflamingo opened Jul 17, 2026 · Updated Sep 3, 2026
  20

  

• RFC: Add support for launch_attr in LaunchConfig ctor

  cuda.corefeatureP1
  Enhancement

  NVIDIA/cuda-python#496 · Filter by author realarnavgoel opened on Mar 6, 2025 · cuda.core 1.3.0
  14

  

• Add cuda.core.utils.get_aligned_dtype

  cuda.corefeatureP1
  Enhancement

  NVIDIA/cuda-python#734 · Filter by author leofang opened on Jun 27, 2025 · cuda.core 1.3.0
  4