Source: xnnpack
Section: math
Homepage: https://github.com/google/XNNPACK
Priority: optional
Standards-Version: 4.5.0
Vcs-Git: https://salsa.debian.org/deeplearning-team/xnnpack.git
Vcs-Browser: https://salsa.debian.org/deeplearning-team/xnnpack
Maintainer: Debian Science Team <debian-science-maintainers@lists.alioth.debian.org>
Uploaders: Mo Zhou <lumin@debian.org>
Rules-Requires-Root: no
Build-Depends: cmake,
               debhelper-compat (= 13),
               googletest,
# for libclog.a and clog.h
               libcpuinfo-dev (>= 0.0~git20200422.a1e0b95-2~),
               libfp16-dev,
               libfxdiv-dev,
               libpsimd-dev,
               libpthreadpool-dev,
               ninja-build

Package: libxnnpack-dev
Architecture: any
Depends: libxnnpack0 (= ${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
Architecture: any
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.
