ncnn
Purpose / CSI Use Case
High-performance on-device neural-network inference for mobile, embedded, browser, and desktop deployments, using pnnx to convert PyTorch/ONNX models and CPU or Vulkan GPU backends for execution.
Source Notes
Verified public GitHub repository Tencent/ncnn, default branch master, not archived. README confirms no third-party runtime dependency, CPU and Vulkan GPU backends, pnnx model conversion, C++ and Python usage, and deployment targets including Android, iOS, macOS, Linux, Windows, Raspberry Pi, Jetson, WebAssembly and other edge platforms. Strong CSI fit for local/private AI and edge inference where a lightweight runtime matters.
Official / Repository URL
https://github.com/Tencent/ncnn
Legacy Metadata
- Added: August 8, 2026
- Category: Model Routing & Inference
- License: BSD 3-Clause; bundled third-party components retain their own licenses
- Priority: VERY HIGH
Migration Notes
Imported deterministically from the canonical CSI Resource Hub Notion export.
No testing, deployment, approval, or production status has been inferred during migration.
Cyber Space Infocom
Making Technology Work for You