NVIDIA/numba-cuda-mlir v0.3.0

v0.3.0

Repository: NVIDIA/numba-cuda-mlir

Tag: v0.3.0

Published: 2026-05-12T22:43:51Z

Prerelease: no

Release notes:

What's Changed

• Clean up pyproject.toml dependencies and align CI with cuda-python/numba-cuda by @leofang in https://github.com/NVIDIA/numba-cuda-mlir/pull/12
• Fix sporadic bitcode signature nvJitLink error in LTO path by @VijayKandiah in https://github.com/NVIDIA/numba-cuda-mlir/pull/14
• [Cleanups] Remove license info for removed benchmark + update contributors by @atmnp in https://github.com/NVIDIA/numba-cuda-mlir/pull/15
• Add array debug info by @jiel-nv in https://github.com/NVIDIA/numba-cuda-mlir/pull/8
• Fix recreate_with_lto to use cuda.core.ObjectCode public API by @VijayKandiah in https://github.com/NVIDIA/numba-cuda-mlir/pull/17
• Fix typo in CONTRIBUTORS.md by @atmnp in https://github.com/NVIDIA/numba-cuda-mlir/pull/20
• Update README, CONTRIBUTING, and INSTALL by @gmarkall in https://github.com/NVIDIA/numba-cuda-mlir/pull/18
• Add User guide by @gmarkall in https://github.com/NVIDIA/numba-cuda-mlir/pull/13
• Fix ExternFunction capture in overloads and linker cuda.core compat by @atmnp in https://github.com/NVIDIA/numba-cuda-mlir/pull/21
• [CI] Enable Python 3.11 by @atmnp in https://github.com/NVIDIA/numba-cuda-mlir/pull/16
• Add discriminated-union debug info for polymorphic scalar variables by @jiel-nv in https://github.com/NVIDIA/numba-cuda-mlir/pull/22
• Add mypy/pyright support by @ZzEeKkAa in https://github.com/NVIDIA/numba-cuda-mlir/pull/26
• Move experimental features into cuda.experimental submodule by @VijayKandiah in https://github.com/NVIDIA/numba-cuda-mlir/pull/25
• Update docs to use dependency groups (PEP 735) for dev/test install by @VijayKandiah in https://github.com/NVIDIA/numba-cuda-mlir/pull/30
• [Compile-Time] Re-design the extending API + dispatcher changes by @atmnp in https://github.com/NVIDIA/numba-cuda-mlir/pull/27
• Add docs build by @gmarkall in https://github.com/NVIDIA/numba-cuda-mlir/pull/28
• Add float16 vector support by @ZzEeKkAa in https://github.com/NVIDIA/numba-cuda-mlir/pull/32
• Fix array.view dtype resolution, typing, and lowering by @VijayKandiah in https://github.com/NVIDIA/numba-cuda-mlir/pull/34
• Expose variables_used linker option by @isVoid in https://github.com/NVIDIA/numba-cuda-mlir/pull/10
• MNT: Fix sccache summary to count CUDA sub-tool cache hits by @leofang in https://github.com/NVIDIA/numba-cuda-mlir/pull/29
• Support cuda-core 1.0 compatibility by @isVoid in https://github.com/NVIDIA/numba-cuda-mlir/pull/23
• Try to fix publish workflow by @leofang in https://github.com/NVIDIA/numba-cuda-mlir/pull/41
• Bump version to 0.3.0 by @leofang in https://github.com/NVIDIA/numba-cuda-mlir/pull/42

New Contributors

• @VijayKandiah made their first contribution in https://github.com/NVIDIA/numba-cuda-mlir/pull/14
• @jiel-nv made their first contribution in https://github.com/NVIDIA/numba-cuda-mlir/pull/8
• @gmarkall made their first contribution in https://github.com/NVIDIA/numba-cuda-mlir/pull/18
• @ZzEeKkAa made their first contribution in https://github.com/NVIDIA/numba-cuda-mlir/pull/26
• @isVoid made their first contribution in https://github.com/NVIDIA/numba-cuda-mlir/pull/10

Full Changelog: https://github.com/NVIDIA/numba-cuda-mlir/commits/v0.3.0