`make install` does not remake whl package if only change .cc or .h

Fix a bug in save_inference_model and prune when the program is initailized by load_inference_model (#10011)

* Fix bug in save_inference_model and prune when the program is initialized by load_inference_program.

* Save the transpiled program instead.

Add neural transformer leanring rate decay function

* Add topk Python API.

* Add unit test.

* Remove the repeated API.

- EPS added to softmax mkldnn primitive outcome is limited to training
phase

Fixes after review

clang format fixes

clang format fixes