We wanted to use ONNX runtime for a "model driver" for MD simulations, where any ML model can be used for molecular dynamics simulations. Problem was it was way too immature. Like ceiling function will only work with single precision in ONNX. But the biggest issue was that we could not take derivatives in ONNX runtime, so any complicated model that uses derivatives inside was a nogo, is that limitation still exist? Do you know if it can take derivatives in training mode now?

Eventually we went with pytorch only support for the time being, with still exploring OpenXLA in place of ONNX, as a universal adapter: https://github.com/ipcamit/colabfit-model-driver

Tinygrad is python only right? Can it provide gradients during C++ runtime as well? ONNX runtime have multiple language backends for inference.

One option to your case is OpenVino. It's written in C++ and has Python Bindings. Also, it can be used to train new nets. You can use ONNX files with OpenVino too.

There is [torch-md](https://github.com/torchmd/torchmd)