A cross-platform AI inference framework supporting multiple backends like TensorRT, OpenVINO, and CoreML. It provides a unified C++ API to simplify model deployment across cloud, edge, and mobile devices.
Tech Stack
C++AI, ML & Data
Why nndeploy?
• Unified abstraction for multiple inference engines
• High-performance C++ core
• Extensive hardware support
Limitations
• Steep learning curve for C++ API
• Complex build environment setup
• Limited documentation for advanced backends
3/4/2026
Last Update
212
Forks
21
Issues
Apache-2.0
License
Financial Leak Detected
Stop the "SaaS Tax"
Your team could be burning cash. Switching to nndeploy instantly boosts your runway.
Competitor Cost
-$1,440
/ year (est. based on NVIDIA Triton Inference Server)
