AI Potluck
Infrastructure / Compilers & Model Optimization

oneMath

UXL Foundation

oneMath is the UXL Foundation's open implementation of the oneMath specification, a cross-vendor math library exposing one interface for BLAS, LAPACK, FFT, RNG and sparse routines and dispatching to a vendor backend - oneMKL, NVIDIA cuBLAS, AMD rocBLAS and others - per target device. It began as oneMKL Interfaces before the UXL Foundation renamed the project.

Verified 2026-09-02 via the GitHub API and the LICENSE body.

Openness

5 high confidence
5.0
license
Apache-2.0(OSI)
source
public
core-gated
ungated

Apache-2.0 license body confirmed. The repository is public and unarchived and builds the whole product, and the README describes no paid tier, enterprise edition or license-gated build beside it, so source is public and the core ungated.

Adoption

1 low confidence
1.0

773 GitHub stars, which lands in the <1K stars band of the stars scale, level 1. oneMath ships as a source build and inside the oneAPI toolkit installers, neither of which publishes a download count, so the stars scale applies.

Capability

3 medium confidence
3.0

Banded on the category feature matrix as performance-critical kernel and operator library, the same shape as onednn and arm-compute-library. Placed two bands below the apache-tvm anchor, on a matrix that bands on how much of the model-to-hardware transformation pipeline a product performs, over how many inputs and targets.

  • https://github.com/uxlfoundation/oneMath/blob/develop/README.md recorded 2026-09-02

    README describes oneMath as the UXL Foundation's open-source implementation of the oneMath specification, dispatching to third-party backend libraries per hardware target, with no paid tier, enterprise edition or license-gated build beside it.

Verified 2026-09-02