ncnn

ncnn is a high-performance neural network inference framework optimized for the mobile platform

View on GitHub↗Upstream Tencent/ncnn↗

Builder

Tencent

Tencent • individual

Stars

23,046

Using upstream star count

Forks

4,415

Using upstream fork count

Open Issues

Activity Score

0/100

0 commits in 30d

Created

Jun 30, 2017

Project creation date

README Summary

ncnn is a high-performance neural network inference framework specifically optimized for mobile platforms, developed by Tencent. It provides efficient deep learning model deployment with minimal dependencies and supports various mobile architectures including ARM, x86, and GPU acceleration.

AI Dev Skills

Unmapped

Tags

Neural Network OptimizationMobile Deep Learning DeploymentModel QuantizationEdge AI InferenceCross-platform Neural Network ImplementationMemory-efficient Neural NetworksARM/Mobile GPU OptimizationVulkan Compute ShadersOpenGL Compute IntegrationReal-time Object Detection on MobileOCR on Embedded SystemsAudioStyle Transfer on Mobile AppsAugmented RealityOn-device AIEmbedded SystemsComputer Vision ApplicationsSpeech Recognition on Edge HardwareModel CompressionMobile AIAutomotiveIoT DevicesFace Recognition on Edge DevicesCross-platform Mobile AppsConsumer ElectronicsVideoEfficient Neural NetworksEdge ComputingRoboticsPose Estimation on IoT DevicesImage Classification on SmartphonesIoTImageMobile ApplicationsEdge/MobileC++

Recent Activity

Updated 26 days ago

7 Days

30 Days

90 Days

Quality

production

Quality: high
Maturity: production

PM Skills

Developer Platform

Languages

C++100.0%

Timeline

Project created: Jun 30, 2017
Forked: Mar 22, 2026
Your last push: 26 days ago
Upstream last push: 7 days ago
Tracked since: Mar 18, 2026

Similar Repos

pgvector cosine similarity · $0

Loading…