I was exploring the code for the mobile optimizer. The Home | PyTorch ; mentions that PyTorch mobile optimizer supports build level optimization and selective compilation depending on the operators needed for user applications.
On exploring the code I could find the code for Operator Fusion and Folding of prepacked ops; however, I could not understand how the build level optimization and selective compilation is happening. It would be great if someone can help me understand this part.
Thanking in Advance