I know TVM can easily invoke a compiled kernel from Python. I want to export the .o file and integrate it to a C/C++ binary. Is there any existing SDK to do that? If not I am willing to contribute one.
Maybe let me make my question clearer?
I am working on some cross-compilation work and the kernel is gonna be integrated to a C/C++ project.
An ideal interface that generates the kernel for me should be a pair of (.o, .h).
Even more aggressively, I want a pair of (.ll, .h) since I want to run some customized passes on the generated LLVM IR.
@were bundle_deploy will do what you want, and you can modify build_model.py to generate .ll with Module#save.