MNN
/All repositories
Overview
HEALTH SCORE
Excellent
92out of 100
Strong development cadence and maintainer coverage. Security posture is the only remaining gap.
LIFECYCLE
Active
Consistent commits, responsive maintainers, regular releases, and healthy issue triage.
Health breakdown
Excellent(92/100)
Maintainer availability, known risks and supply chain posture, and whether the project is actively developed or appropriately stable.
Maintainer responsiveness
Median response time is 2 days.
Bus factor
8 active maintainers currently have merge rights.
Organization Diversity
Contributors span 274 organizations.
Project Achievements
Leaderboards
About
MNN is a high-performance deep learning inference engine that enables efficient deployment of AI models across multiple platforms and hardware. It supports model compression, hardware acceleration, and cross-platform deployment on mobile devices, IoT, and cloud.
First commit
Software value
$118M
Tags
arm
convolution
deep-learning
embedded-devices
llm
machine-learning
ml
mnn
transformer
vulkan
winograd-algorithm
License(s)
Apache-2.0
Links
Data sources
Git
GitHub