Upstream software project

xnnpack

High-efficiency floating-point neural network inference operators

About xnnpack

High-efficiency floating-point neural network inference operators

This project links 8 native package records across 4 recorded operating-system releases. Compare the retained versions and architectures below, then open the package for your own release.

These are catalog observations, not a guarantee of installation, compatibility, or upstream support.

Project pictures and package coverage

xnnpack repository preview from GitHub
Project repository preview, supplied by GitHub. Open source repository
Debian 12 (Bookworm): 2 package records; Debian 13 (Trixie): 2 package records; Fedora 43: 2 package records; Fedora 44: 2 package records. Catalog coverage diagram, not an application screenshot.xnnpack: recorded package coverageDebian 12 (Bookworm)2 recordsDebian 13 (Trixie)2 recordsFedora 432 recordsFedora 442 records
OpenFactory diagram of linked package records. It is not an application screenshot.

Project identity

Project
xnnpack
Publisher
Not authoritatively mapped
Native package records
8
Operating systems
debian-12, debian-13, fedora-43, fedora-44
License expression
BSD-3-Clause
Source repository
Open source repository

Source-reported description

The fullest retained description is shown with its source. Distribution packaging descriptions may include downstream details.

XNNPACK is a highly optimized solution for neural network inference on ARM, x86, WebAssembly, and RISC-V platforms. XNNPACK is not intended for direct use by deep learning practitioners and researchers; instead it provides low-level performance primitives for accelerating high-level machine learning frameworks, such as TensorFlow Lite, TensorFlow.js, PyTorch, ONNX Runtime, and MediaPipe.

Description source

Packages by operating system

Compare recorded versions, then open a package for dependency, file, checksum, and repository evidence. Version strings are distribution-specific, not a ranking of newer software.

Debian 12 (Bookworm)

  1. Package libxnnpack0

    bookworm (Debian 12 (Bookworm)) (math): High-efficiency floating-point neural network inference operators (libs)

    0.0~git20220216.ae108ef-2: amd64 arm64

    Source: xnnpack

  2. Package libxnnpack-dev

    bookworm (Debian 12 (Bookworm)) (math): High-efficiency floating-point neural network inference operators (dev)

    0.0~git20220216.ae108ef-2: amd64 arm64

    Source: xnnpack

Debian 13 (Trixie)

  1. Package libxnnpack0.20241108

    trixie (Debian 13 (Trixie)) (libs): High-efficiency floating-point neural network inference operators (libs)

    0.0~git20241108.4ea82e5-2: amd64 arm64

    Source: xnnpack

  2. Package libxnnpack-dev

    trixie (Debian 13 (Trixie)) (math): High-efficiency floating-point neural network inference operators (dev)

    0.0~git20241108.4ea82e5-2: amd64 arm64

    Source: xnnpack

Fedora 43

  1. Package xnnpack

    43 (Fedora 43) (Unspecified): High-efficiency floating-point neural network inference operators

    0.0^git20240814.312eb7e-4.fc43: aarch64 x86_64

    Source: xnnpack

  2. Package xnnpack-devel

    43 (Fedora 43) (Unspecified): Headers and libraries for xnnpack

    0.0^git20240814.312eb7e-4.fc43: aarch64 x86_64

    Source: xnnpack

Fedora 44

  1. Package xnnpack

    44 (Fedora 44) (Unspecified): High-efficiency floating-point neural network inference operators

    0.0^git20240814.312eb7e-5.fc44: aarch64 x86_64

    Source: xnnpack

  2. Package xnnpack-devel

    44 (Fedora 44) (Unspecified): Headers and libraries for xnnpack

    0.0^git20240814.312eb7e-5.fc44: aarch64 x86_64

    Source: xnnpack

Project resources and further reading

Mapping provenance

Only source-backed identity signals create public cross-OS links. A reviewer can later approve or dispute an inferred relationship without rewriting native package history.

No field-level source record is published yet.