A high-performance deep-learning inference engine for efficient AI inferencing

PPLNN

PPLNN, which is short for "PPLNN is a Primitive Library for Neural Network", is a high-performance deep-learning inference engine for efficient AI inferencing. It can run various ONNX models and has better support for OpenMMLab.

Documents

• Supported Ops and Platforms
• Building from Source
• Generating ONNX models from OpenMMLab
• Getting Started in C++
• C++ API References
• Develop Guide
  • Add New Engines and Ops
  • X86
    • Add Ops（中文版）
    • Benchmark（中文版）
  • CUDA
    • Add Ops（中文版）
    • Benchmark（中文版）

GitHub

https://github.com/openppl-public/ppl.nn