Source: xnnpack
Section: math
Homepage: https://github.com/google/XNNPACK
Priority: optional
Standards-Version: 4.7.0
Uploaders: Mo Zhou <lumin@debian.org>, Shengqi Chen <harry@debian.org>
Rules-Requires-Root: no
Build-Depends: cmake,
               debhelper-compat (= 13),
               googletest,
               libcpuinfo-dev (>= 0.0~git20231104.d6860c4~),
               libfp16-dev,
               libfxdiv-dev,
               libpsimd-dev,
               libpthreadpool-dev (>= 0.0~git20240616.560c60d~),
               ninja-build,
               python3
Vcs-Git: https://invent.kde.org/neon/backports-noble/xnnpack-noble.git
Vcs-Browser: https://invent.kde.org/neon/backports-noble/xnnpack-noble
Maintainer: Neon CI <neon@kde.org>

Package: libxnnpack-dev
Section: libdevel
Architecture: amd64 i386 x32 armhf arm64 riscv64
Depends: libxnnpack0.20241108 (= ${binary:Version}), ${misc:Depends}
Description: High-efficiency floating-point neural network inference operators (dev)
 XNNPACK is a highly optimized library of floating-point neural network
 inference operators for ARM, WebAssembly, and x86 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,
 and MediaPipe.
 .
 This package contains the development files.

Package: libxnnpack0.20241108
Section: libs
Architecture: amd64 i386 x32 armhf arm64 riscv64
Multi-Arch: same
Depends: ${misc:Depends}, ${shlibs:Depends}
Description: High-efficiency floating-point neural network inference operators (libs)
 XNNPACK is a highly optimized library of floating-point neural network
 inference operators for ARM, WebAssembly, and x86 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,
 and MediaPipe.
 .
 This package contains the shared object.
