Automic VaultAutomic Vault

brew

使用 Homebrew, dnf, Nix, pacman, zypper 安装 ncnn

查看 ncnn 的安装路径、可执行文件、元数据以及面向 AI 代理工作流的安全说明。

安装命令安全说明

安装

其他安装命令

macOS

Homebrew已验证 · 100%
brew install ncnn

local Homebrew formula metadata

Linux

Fedora dnf已验证 · 92%
sudo dnf install ncnn

Fedora Rawhide package metadata · ncnn · 来源: dl.fedoraproject.org

Nix已验证 · 92%
nix profile install nixpkgs#ncnn

nixpkgs package indexes · pkgs/by-name/nc/ncnn/package.nix · 来源: api.github.com

Arch Linux pacman已验证 · 92%
sudo pacman -S ncnn

Arch Linux sync databases · ncnn · 来源: geo.mirror.pkgbuild.com

openSUSE zypper已验证 · 92%
sudo zypper install ncnn

openSUSE Tumbleweed package metadata · ncnn · 来源: download.opensuse.org

概览

软件包摘要

High-performance neural network inference framework

命令和别名

  • caffe2ncnn
  • darknet2ncnn
  • mxnet2ncnn
  • ncnn2int8
  • ncnn2mem
  • ncnn2table
  • ncnnmerge
  • ncnnoptimize

历史

项目历史与用法

ncnn is Tencent's open-source neural-network inference runtime for mobile, embedded, desktop, browser, and edge deployment. Its niche is small, dependency-light inference: the upstream README emphasizes no third-party runtime dependencies, CPU and Vulkan GPU backends, explicit low-memory allocator design, and conversion tools such as pnnx for PyTorch and ONNX workflows.

项目历史

Tencent presentations describe the ncnn project as dating from 2017, with open collaboration and Vulkan acceleration as central design points. That timing put it in the wave of mobile inference runtimes that appeared after deep-learning deployment moved from server GPUs into phones and edge devices.

采用历史

Upstream states that ncnn is used in Tencent applications including QQ, Qzone, WeChat, and Pitu. Outside Tencent, its adoption pattern is typical for low-level ML infrastructure: package-manager availability, examples for object detection and vision models, and use by developers who want a C++ runtime without TensorFlow Lite or ONNX Runtime-sized baggage.

使用方式

Package users usually install ncnn for the converter and optimizer executables as much as for the library. A common flow is export from PyTorch through pnnx, produce .param and .bin model files, run optimization or int8 tooling, and embed the resulting model in a C++ or mobile application using ncnn::Net.

为什么软件包爱好者会关心

For package maintainers, ncnn is interesting because it is a fast-moving C++/Vulkan project that exposes both libraries and many small CLI tools. It is also a useful example of a Homebrew formula where the command-line surface is mostly build/deployment tooling around a library rather than one end-user command.

时间线

  • 2017: Tencent presentation material describes ncnn as active since 2017.
  • 2020s: README documents pnnx-based PyTorch/ONNX conversion and CPU/Vulkan deployment across mobile, desktop, browser, and edge targets.

Related projects

  • PyTorch, ONNX, pnnx, Vulkan, TensorFlow, Caffe, MXNet, Darknet

安全态势

风险级别：blue

broad file, network, media, or database tool signal.

风险分类器

blue 风险 · 中 置信度 · tool

原因

  • broad file, network, media, or database tool signal

信号

  • text:network

安装行为

  • formula 元数据中未记录 Homebrew post-install 钩子。
  • Homebrew bottle 元数据适用于 6 个平台目标。
  • 安装时包含 6 个运行时依赖。
  • 构建元数据列出 1 个构建依赖。

建议审查

在无人值守的代理使用前，请检查该工具是否读取明文凭据、写入远程状态、发布制品或调用插件。

可执行文件

已安装的可执行文件

命令类型暴露范围备注
caffe2ncnncli全局可执行文件
darknet2ncnncli全局可执行文件
mxnet2ncnncli全局可执行文件
ncnn2int8cli全局可执行文件
ncnn2memcli全局可执行文件
ncnn2tablecli全局可执行文件
ncnnmergecli全局可执行文件
ncnnoptimizecli全局可执行文件

新鲜度

版本和新鲜度

这些信号区分页生成时间、软件包管理器活动和上游发布比较。只有存在证据 URL 和可比较版本时，才会提示版本落后。

页面生成时间2026-07-25
管理器版本20260526
管理器更新时间2026-06-25
本地数据OK
上游not checked
检测到的最新版本未检测到

https://github.com/Tencent/ncnn

安装元数据

软件包元数据

软件包键brew:ncnn
版本20260526
软件包管理器Homebrew
软件包管理器页面https://formulae.brew.sh/formula/ncnn
主页https://github.com/Tencent/ncnn
仓库https://github.com/Tencent/ncnn
上游文档https://github.com/Tencent/ncnn
许可证BSD-3-Clause
源码归档https://github.com/Tencent/ncnn/archive/refs/tags/20260526.tar.gz
最后更新2026-06-25T13:37:56+02:00
Pulseupdated
依赖abseil, glslang, libomp, molten-vk, protobuf, spirv-tools
构建依赖cmake
Bottle可用 (于 arm64_linux, arm64_sequoia, arm64_sonoma, arm64_tahoe, sonoma, x86_64_linux)
Homebrew post-install未定义
服务未声明

注册表事实

源数据库详情

Source DatabaseHomebrew formula API
Taphomebrew/core
Full Namencnn
Version Scheme0
Revision1
Head VersionHEAD
Bottle Stable Root URLhttps://ghcr.io/v2/homebrew/core
Deprecatedno
Disabledno
Keg Onlyno
URL Keys
  • head
  • stable

源数据库匹配

其他软件包管理器记录

匹配项来自外部软件包管理器索引，并与本地 Automic Vault 软件包链接分开显示。

Nix95%

ncnn

nix profile install nixpkgs#ncnn
  • normalized package name match
  • 匹配方式：Ncnn
nixpkgs package indexes · api.github.com · nixpkgs package indexes: pkgs/by-name/nc/ncnn/package.nix from https://api.github.com/repos/NixOS/nixpkgs/git/trees/master?recursive=1
dnf95%

ncnn 20250916-3.fc45

A high-performance neural network inference framework

https://github.com/Tencent/ncnn

sudo dnf install ncnn
  • License: BSD-3-Clause AND BSD-2-Clause AND Zlib
  • Category: Unspecified
  • Architecture: i686
  • Source Package: ncnn
  • 9 依赖
  • 2 提供
  • normalized package name match
  • 匹配方式：Ncnn
Fedora Rawhide package metadata · dl.fedoraproject.org · Fedora Rawhide package metadata: ncnn from https://dl.fedoraproject.org/pub/fedora/linux/development/rawhide/Everything/x86_64/os/repodata/e5ca8ce900cd68f5419e1c39ae517343100b306336cbaeb70a3c153121d95094-primary.xml.zst
dnf95%

ncnn-devel 20250916-3.fc45

Development files for ncnn

https://github.com/Tencent/ncnn

sudo dnf install ncnn-devel
  • License: BSD-3-Clause AND BSD-2-Clause AND Zlib
  • Category: Unspecified
  • Architecture: i686
  • Source Package: ncnn
  • 13 依赖
  • 3 提供
  • normalized package name match
  • 匹配方式：Ncnn
Fedora Rawhide package metadata · dl.fedoraproject.org · Fedora Rawhide package metadata: ncnn-devel from https://dl.fedoraproject.org/pub/fedora/linux/development/rawhide/Everything/x86_64/os/repodata/e5ca8ce900cd68f5419e1c39ae517343100b306336cbaeb70a3c153121d95094-primary.xml.zst
pacman95%

ncnn 20260113-6

High-performance neural network inference framework optimized for the mobile platform

https://github.com/Tencent/ncnn

sudo pacman -S ncnn
  • License: BSD-3-Clause
  • Architecture: x86_64
  • 6 依赖
  • 1 可选依赖
  • normalized package name match
  • 匹配方式：Ncnn
Arch Linux sync databases · geo.mirror.pkgbuild.com · Arch Linux sync databases: ncnn from https://geo.mirror.pkgbuild.com/extra/os/x86_64/extra.db.tar.gz
zypper95%

libncnn1 20250916-1.8

NCNN library

https://github.com/Tencent/ncnn

sudo zypper install libncnn1
  • License: BSD-2-Clause AND BSD-3-Clause AND Zlib
  • Category: System/Libraries
  • Architecture: x86_64
  • Source Package: ncnn
  • 7 依赖
  • 2 提供
  • normalized package name match
  • 匹配方式：Ncnn
openSUSE Tumbleweed package metadata · download.opensuse.org · openSUSE Tumbleweed package metadata: libncnn1 from https://download.opensuse.org/tumbleweed/repo/oss/repodata/be8d3611d25469107f32075a1697e69ec57a2b850b42348a658cc671ad5ec2b50760d02c3e59524d50da9a11d5be799bdaffba2e166e8ca8858512e3c0bd665d-primary.xml.zst
zypper95%

ncnn 20250916-1.8

A high-performance neural network inference framework

https://github.com/Tencent/ncnn

sudo zypper install ncnn
  • License: BSD-2-Clause AND BSD-3-Clause AND Zlib
  • Category: Development/Tools/Other
  • Architecture: x86_64
  • Source Package: ncnn
  • 7 依赖
  • 1 提供
  • normalized package name match
  • 匹配方式：Ncnn
openSUSE Tumbleweed package metadata · download.opensuse.org · openSUSE Tumbleweed package metadata: ncnn from https://download.opensuse.org/tumbleweed/repo/oss/repodata/be8d3611d25469107f32075a1697e69ec57a2b850b42348a658cc671ad5ec2b50760d02c3e59524d50da9a11d5be799bdaffba2e166e8ca8858512e3c0bd665d-primary.xml.zst
zypper95%

ncnn-devel 20250916-1.8

Development tools for ncnn

https://github.com/Tencent/ncnn

sudo zypper install ncnn-devel
  • License: BSD-2-Clause AND BSD-3-Clause AND Zlib
  • Category: Development/Libraries/C and C++
  • Architecture: x86_64
  • Source Package: ncnn
  • 2 依赖
  • 3 提供
  • normalized package name match
  • 匹配方式：Ncnn
openSUSE Tumbleweed package metadata · download.opensuse.org · openSUSE Tumbleweed package metadata: ncnn-devel from https://download.opensuse.org/tumbleweed/repo/oss/repodata/be8d3611d25469107f32075a1697e69ec57a2b850b42348a658cc671ad5ec2b50760d02c3e59524d50da9a11d5be799bdaffba2e166e8ca8858512e3c0bd665d-primary.xml.zst

软件包图谱

链接来自本地软件包关系图、补充数据、依赖边、生态匹配和软件包 hub 归属。

相关工具

  • glslangRuntime dependency declared by Homebrew.
  • molten-vkRuntime dependency declared by Homebrew.
  • protobufRuntime dependency declared by Homebrew.
  • spirv-toolsRuntime dependency declared by Homebrew.
  • cmakeBuild dependency declared by Homebrew.

相同工作流

  • djl-servingShares av.db curated category or tags: ai, cli, inference, machine-learning, ml-tools.
  • opencvShares av.db curated category or tags: ai, cli, computer-vision, machine-learning, ml-tools.
  • text-embeddings-inferenceShares av.db curated category or tags: ai, cli, inference, machine-learning, ml-tools.
  • apache-opennlpShares av.db curated category or tags: ai, cli, machine-learning, ml-tools.
  • hfShares av.db curated category or tags: ai, cli, machine-learning, ml-tools.
  • libsvmShares av.db curated category or tags: ai, cli, machine-learning, ml-tools.

来源线索

由仓库数据生成

此页面由 av-web 从 scripts/generate-pkg-sqlite.py 生成的私有软件包 SQLite 工件提供。

使用的来源

  • Geiger risk classifier
  • Nucleus package database
  • av.db category and tag curation
  • cross-ecosystem install command graph
  • curated package history
  • external package-manager database matches
  • package relationship graph
  • package version freshness
  • package-page enrichment