ncnn-20250916-1.1 RPM for x86_64

From OpenSuSE Tumbleweed for x86_64

ncnn is a high-performance neural network inference computing framework
optimized for mobile platforms. ncnn is deeply considerate about deployment and
uses on mobile phones from the beginning of design. ncnn does not have third
party dependencies. It is cross-platform, and runs faster than all known open
source frameworks on mobile phone cpu. Developers can easily deploy deep
learning algorithm models to the mobile platform by using efficient ncnn
implementation, create intelligent APPs, and bring the artificial intelligence
to your fingertips. ncnn is currently being used in many Tencent applications,
such as QQ, Qzone, WeChat, Pitu and so on.

Provides

• ncnn
• ncnn(x86-64)

Requires

• libc.so.6()(64bit)
• libc.so.6(GLIBC_2.14)(64bit)
• libc.so.6(GLIBC_2.2.5)(64bit)
• libc.so.6(GLIBC_2.3.4)(64bit)
• libc.so.6(GLIBC_2.34)(64bit)
• libc.so.6(GLIBC_2.38)(64bit)
• libc.so.6(GLIBC_2.4)(64bit)
• libc.so.6(GLIBC_2.7)(64bit)
• libgcc_s.so.1()(64bit)
• libgcc_s.so.1(GCC_3.0)(64bit)
• libgcc_s.so.1(GCC_3.3.1)(64bit)
• libgcc_s.so.1(GCC_3.4)(64bit)
• libgomp.so.1()(64bit)
• libgomp.so.1(GOMP_1.0)(64bit)
• libgomp.so.1(GOMP_4.0)(64bit)
• libgomp.so.1(OMP_1.0)(64bit)
• libm.so.6()(64bit)
• libm.so.6(GLIBC_2.2.5)(64bit)
• libm.so.6(GLIBC_2.27)(64bit)
• libm.so.6(GLIBC_2.29)(64bit)
• libncnn.so.1()(64bit)
• libprotobuf.so.32.1.0()(64bit)
• libstdc++.so.6()(64bit)
• libstdc++.so.6(CXXABI_1.3)(64bit)
• libstdc++.so.6(CXXABI_1.3.5)(64bit)
• libstdc++.so.6(CXXABI_1.3.9)(64bit)
• libstdc++.so.6(GLIBCXX_3.4)(64bit)
• libstdc++.so.6(GLIBCXX_3.4.11)(64bit)
• libstdc++.so.6(GLIBCXX_3.4.18)(64bit)
• libstdc++.so.6(GLIBCXX_3.4.20)(64bit)
• libstdc++.so.6(GLIBCXX_3.4.21)(64bit)
• libstdc++.so.6(GLIBCXX_3.4.29)(64bit)
• libstdc++.so.6(GLIBCXX_3.4.32)(64bit)
• rpmlib(CompressedFileNames) <= 3.0.4-1
• rpmlib(FileDigests) <= 4.6.0-1
• rpmlib(PayloadFilesHavePrefix) <= 4.0-1
• rpmlib(PayloadIsZstd) <= 5.4.18-1

License

BSD-2-Clause AND BSD-3-Clause AND Zlib

Changelog

* Thu Oct 02 2025 Hillwood Yang <hillwood@opensuse.org>
  - Update version to 20250916
    * x86 (SSE2/AVX/AVX512): Loop tail optimization for clip, tanh, unaryop, sigmoid,
      instancenorm, and groupnorm.
    * ARM (Neon): Optimization for groupnorm.
    * Loongarch (LSX/LASX): Optimization for sigmoid and some mathematical functions.
    * RISC-V (RVV/ZFH/ZVFh/XTheadvector): Optimization for shufflechannel and layernorm.
    * General: Improved support for extra-large tensors by using the size_t type.
    * Updated ruapu to detect and dynamically dispatch for RISC-V ZFH ZVFH XTheadvector.
    * Increased maximum supported GPU count to 32.
    * Added support for nvidia headless vulkan.
    * Detected new Vulkan extensions including VK_KHR_shader_integer_dot_product,
      VK_EXT_robustness2, etc.
    * Supported querying arbitrary cooperative matrix MNK size.
    * Added support for Vulkan Int8 packing/quantize/dequantize/requantize.
    * Removed vkimagemat type input/output forward implementation from all layers.
    * Removed layer support_image_storage and option use_image_storage fields.
    * Removed all layer pack8 shader implementations.
    * Supported Vulkan drivers without a graphics queue.
    * Unified elempack shaders for vulkan convolution (1x1s1d1/gemm/winograd), deconvolution
      gemm, gemm, absval, sigmoid, activation functions, and unaryop
* Tue Aug 05 2025 Hillwood Yang <hillwood@opensuse.org>
  - Update version to 20250503
    * Fix blacklist for amd radv coopmat
    * workaround for qcom adreno turnip
    * Read more detail at https://github.com/Tencent/ncnn/compare/20240820...20250503
* Fri Sep 13 2024 Hillwood Yang <hillwood@opensuse.org>
  - Update version to 20240820
    * See the changelog at https://github.com/Tencent/ncnn/releases/tag/20240820
* Thu Jun 13 2024 Hillwood Yang <hillwood@opensuse.org>
  - Update version to 20240410
    * See the changelog at https://github.com/Tencent/ncnn/releases/tag/20240410
* Tue Feb 27 2024 Hillwood Yang <hillwood@opensuse.org>
  - Update version to 20240102
    * See the changelog at https://github.com/Tencent/ncnn/releases/tag/20240102
* Sun Dec 31 2023 Hillwood Yang <hillwood@opensuse.org>
  - Set SPIRV-Tools-opt as BuildRequires
* Thu Nov 02 2023 Hillwood Yang <hillwood@opensuse.org>
  - Update version to 20231027
    * See changelog at https://github.com/Tencent/ncnn/releases/tag/20231027
  - Drop gcc-13.patch
* Tue May 02 2023 Hillwood Yang <hillwood@opensuse.org>
  - Initial package for version 20230223
  - Add gcc-13.patch

Files

/usr/bin/caffe2ncnn
/usr/bin/darknet2ncnn
/usr/bin/mxnet2ncnn
/usr/bin/ncnn2int8
/usr/bin/ncnn2mem
/usr/bin/ncnn2table
/usr/bin/ncnnmerge
/usr/bin/ncnnoptimize
/usr/bin/onnx2ncnn
/usr/share/doc/packages/ncnn
/usr/share/doc/packages/ncnn/CONTRIBUTING.md
/usr/share/doc/packages/ncnn/README.md
/usr/share/licenses/ncnn
/usr/share/licenses/ncnn/LICENSE.txt

Generated by rpm2html 1.8.1

Fabrice Bellet, Sat Nov 1 22:38:26 2025