Introduction to the inference server project using the ONNX Runtime

[kibae]

Hi, all 🤗

Thank you for creating and maintaining the ONNX Runtime.

I would like to introduce my personal project using ONNX Runtime C++ API.

https://github.com/kibae/onnxruntime-server
The onnxruntime-server can easily provide an inference API for ONNX files. It provides TCP, HTTP/HTTPS REST API backend and has built-in swagger API documentation. It also supports hardware acceleration using CUDA.

Just copy the ONNX files to the model directory of onnxruntime-server and it provides onnx session management and execution without any code.

I hope you're interested and if you have any questions, feel free to let me know!

---