NN-512 was monetized by making its author a Senior Architect at the most important company in the machine learning space, a company whose hardware and software you almost certainly use. NN-512 was an EXTREMELY profitable project for its author.

Most competent engineers will be able to dump their network weights to a file as described in the headers. Do you understand your network or not? The weights, etc., are literally a C struct in the header file. Use fread() to load the floats. If that's too complicated, NN-512 is not for you.

As clearly stated on its brief webpage (which you might care to read before commenting) NN-512 does every kind of fusion you can imagine, fusing convolutions, fusing elementwise operations, fusing batch normalization, etc. See https://nn-512.com/example/28 for an example.

If you're using a classical ConvNet (e.g., a DenseNet-121), as many people are, and you want to do inference on AVX-512 CPUs, nothing will outperform NN-512. And your inference code will be completely stand-alone. No dependencies.