macOS
Homebrewverifiziert · 100%
brew install ncnnlocal Homebrew formula metadata
brew
ncnn mit Homebrew, dnf, Nix, pacman, zypper installieren
Prüfe Installationswege, Executables, Metadaten und Sicherheitshinweise für ncnn in AI-Agent-Workflows.
Installation
Weitere Installationsbefehle
Linux
Fedora dnfverifiziert · 92%
sudo dnf install ncnnFedora Rawhide package metadata · ncnn · Quelle: dl.fedoraproject.org
Nixverifiziert · 92%
nix profile install nixpkgs#ncnnnixpkgs package indexes · pkgs/by-name/nc/ncnn/package.nix · Quelle: api.github.com
Arch Linux pacmanverifiziert · 92%
sudo pacman -S ncnnArch Linux sync databases · ncnn · Quelle: geo.mirror.pkgbuild.com
openSUSE zypperverifiziert · 92%
sudo zypper install ncnnopenSUSE Tumbleweed package metadata · ncnn · Quelle: download.opensuse.org
Überblick
Paketzusammenfassung
High-performance neural network inference framework
Projektlinks
Befehle und Aliase
- caffe2ncnn
- darknet2ncnn
- mxnet2ncnn
- ncnn2int8
- ncnn2mem
- ncnn2table
- ncnnmerge
- ncnnoptimize
Verlauf
Projektgeschichte und Nutzung
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.
Projektgeschichte
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.
Adoptionsgeschichte
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.
Wie es verwendet wird
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.
Warum Paket-Nerds sich dafür interessieren
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.
Zeitleiste
- 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
Quellen
Sicherheitslage
Risikostufe: blue
broad file, network, media, or database tool signal.
Risikoklassifikator
blue Risiko · mittel Konfidenz · tool
Warum
- broad file, network, media, or database tool signal
Signale
- text:network
Installationsverhalten
- In den Formelmetadaten ist kein Homebrew-Post-install-Hook erfasst.
- Homebrew-Bottle-Metadaten sind für 6 Plattformziele verfügbar.
- Installiert mit 6 Laufzeitabhängigkeiten.
- Build-Metadaten listen 1 Build-Abhängigkeiten.
Empfohlene Prüfung
Prüfe vor unbeaufsichtigter Agent-Nutzung, ob das Tool Klartext-Credentials liest, Remote-Zustand schreibt, Artefakte veröffentlicht oder Plugins ausführt.
Executables
Installierte Executables
| Befehl | Art | Sichtbarkeit | Hinweis |
|---|---|---|---|
caffe2ncnn | cli | globales Executable | |
darknet2ncnn | cli | globales Executable | |
mxnet2ncnn | cli | globales Executable | |
ncnn2int8 | cli | globales Executable | |
ncnn2mem | cli | globales Executable | |
ncnn2table | cli | globales Executable | |
ncnnmerge | cli | globales Executable | |
ncnnoptimize | cli | globales Executable |
Aktualität
Version und Aktualität
Diese Signale trennen das Alter der Seitengenerierung, Aktivität des Paketmanagers und Upstream-Release-Vergleich. Versionsrückstand wird nur gemeldet, wenn eine Evidenz-URL und vergleichbare Versionen vorhanden sind.
Seite generiert2026-07-25
Manager-Version20260526
Manager aktualisiert2026-06-25
lokale DatenOK
Upstreamnot checked
neueste erkannte Versionnicht erkannt
https://github.com/Tencent/ncnn
- InfoNo cached GitHub release or tag data was available.https://github.com/Tencent/ncnnnone Konfidenz
Installationsmetadaten
Paketmetadaten
| Paketschlüssel | brew:ncnn |
|---|---|
| Version | 20260526 |
| Paketmanager | Homebrew |
| Paketmanager-Seite | https://formulae.brew.sh/formula/ncnn |
| Homepage | https://github.com/Tencent/ncnn |
| Repository | https://github.com/Tencent/ncnn |
| Upstream-Dokumentation | https://github.com/Tencent/ncnn |
| Lizenz | BSD-3-Clause |
| Quellarchiv | https://github.com/Tencent/ncnn/archive/refs/tags/20260526.tar.gz |
| Zuletzt aktualisiert | 2026-06-25T13:37:56+02:00 |
| Pulse | updated |
| Abhängigkeiten | abseil, glslang, libomp, molten-vk, protobuf, spirv-tools |
| Build-Abhängigkeiten | cmake |
| Bottle | verfügbar (auf arm64_linux, arm64_sequoia, arm64_sonoma, arm64_tahoe, sonoma, x86_64_linux) |
| Homebrew post-install | nicht definiert |
| Dienst | keiner deklariert |
Registry-Fakten
Details aus der Quelldatenbank
| Source Database | Homebrew formula API |
|---|---|
| Tap | homebrew/core |
| Full Name | ncnn |
| Version Scheme | 0 |
| Revision | 1 |
| Head Version | HEAD |
| Bottle Stable Root URL | https://ghcr.io/v2/homebrew/core |
| Deprecated | no |
| Disabled | no |
| Keg Only | no |
| URL Keys |
|
Source-Datenbank-Treffer
Andere Paketmanager-Einträge
Treffer stammen aus externen Paketmanager-Indizes und bleiben von lokalen Automic-Vault-Paketlinks getrennt.
Nix95%
ncnn
nix profile install nixpkgs#ncnn- normalized package name match
- Abgeglichen nach: Ncnn
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 Abhängigkeiten
- 2 stellt bereit
- normalized package name match
- Abgeglichen nach: Ncnn
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 Abhängigkeiten
- 3 stellt bereit
- normalized package name match
- Abgeglichen nach: Ncnn
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 Abhängigkeiten
- 1 optionale Abhängigkeiten
- normalized package name match
- Abgeglichen nach: Ncnn
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 Abhängigkeiten
- 2 stellt bereit
- normalized package name match
- Abgeglichen nach: Ncnn
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 Abhängigkeiten
- 1 stellt bereit
- normalized package name match
- Abgeglichen nach: Ncnn
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 Abhängigkeiten
- 3 stellt bereit
- normalized package name match
- Abgeglichen nach: Ncnn
Quellspur
Aus Repository-Daten generiert
Diese Seite wird von av-web aus dem privaten Paket-SQLite-Artefakt bereitgestellt, das scripts/generate-pkg-sqlite.py erstellt.
Combined YAML source
View the package source record on GitHub.
Verwendete Quellen
- 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