NVIDIA/cccl v3.1.2

v3.1.2

Repository: NVIDIA/cccl

Tag: v3.1.2

Published: 2025-11-13T19:14:08Z

Prerelease: no

Release notes:

What's Changed

🔄 Other Changes

• [BACKPORT 3.1] Always include `` when we need operator new for clang-cuda (#6310) by @miscco in https://github.com/NVIDIA/cccl/pull/6445
• [Backport branch/3.1.x] Fix offset_iterator tests by @github-actions[bot] in https://github.com/NVIDIA/cccl/pull/6446
• [BACKPORT 3.1] Add _CCCL_DECLSPEC_EMPTY_BASES to mdspan features (#6444) by @miscco in https://github.com/NVIDIA/cccl/pull/6449
• Bump branch/3.1.x to 3.1.2. by @wmaxey in https://github.com/NVIDIA/cccl/pull/6433
• [Backport 3.1] Fix clang 21 issues (#6404) by @davebayer in https://github.com/NVIDIA/cccl/pull/6447
• [Backport branch/3.1.x] Ensure that detect_wrong_difference is a valid output iterator by @github-actions[bot] in https://github.com/NVIDIA/cccl/pull/6453
• [Backport to 3.1] Fix cub.bench.radix_sort.keys.base regression on H200 (#6452) by @bernhardmgruber in https://github.com/NVIDIA/cccl/pull/6458
• [Backport 3.1] Do not mark deduction guides as hidden (#6350) by @miscco in https://github.com/NVIDIA/cccl/pull/6457

Full Changelog: https://github.com/NVIDIA/cccl/compare/v3.1.1...v3.1.2