Looking for help implementing ONNXRuntime backend

[isty2e]

I am currently trying to implement an ONNXRuntime backend. Main motivations are:

• Being available to use .onnx file as the network file, which enables us to experiment with different network architectures or details without implementing everything in CUDA/OpenCL backend.
• Graph optimization shipped in ONNXRuntime, which might be helpful for performance.
• Easier access to some platform-specific backends such as TensorRT, DirectML, and MIGraphX.

I have done some work in my branch, but it is of course not functional yet. My main concerns are:

• I have little to no experience with C++, so I'm pretty sure that I messed up somewhere and everything is broken here and there.
• I have totally no idea how to configure CMakeList.txt, especially considering that find_package(onnxruntime) does not work. This comment is probably helpful for this purpose, but I'm not getting how to use this in a proper way.

For those who might be interested in, b20 and b40 weight files converted into .onnx format are available here.

[lightvector]

This is cool. Presumably it will be a lot easier to get C++ part tested once cmake is configured, so that you can actually compile it reliably. :)

So it looks like based on the comment you linked that onnx has not implemented cmake integration, so they require you to manually include/link things. My impression is that at least for testing for the moment, the commented hacky solution A is most straightforward - have you run into issues when trying to apply it?