Optimize the stack operator

* Initialize the elementwise plugin.

* Implement the basic CUDA kernel of elementwise plugin.
test=develop

jitcode act support all size

Introducing MKL to softmax for inference

* refine GraphCheck
test=develop

* fix ci fail
test=develop

This reverts commit be506703.

add api example of brelu, leaky_relu and soft_relu

* Modify some infer-shape in compile-time.

[WIP] Correcting and extending MKLDNN residual connection fuse pass

test=develop

* Optimize layer_norm operator with AVX intrinsic functions

* Revert the wrong modifications

* Implement the jit kernel for layer_norm operator

* Add math headfile to fix the compile issue (test=develop)

* Add math headfile to fix the compile issue (test=develop)

* Fixed the intrinsic headfile issue (test=develop)

* Fix the conflicts (test=develop)

* Revert for CUDA compiler (test=develop)

* Fixed the cuda depency (test=develop)

* Fix the marco issues (test=develop)

Fix tensorrt plugin cmake dependency, test=develop

Rewrite allocation

* Convolution fusion operator.
* Clean code
test=develop

test=develop

test=develop

test=develop

* fix dist deps test=develop

* update test=develop

* update test=develop

* update test=develop

* update test=develop

test=develop

test=develop

optimize distribute checkport

test=develop

test=develop

test=develop

test=develop

test=develop

fix build error on noavx

test=develop

* wip simplify operator framework

* wip

* wip

* done test=develop

* clean test=develop

* fix test=develop

* fix deps test=develop

* fix cpu build test=develop

* fix tensorrt build test=develop

* fix tests test=develop

* fix test=develop

* fix cpu build test=develop

test=develop

jitcode act relu, exp, sigmoid, tanh

* fix space_to_depth_op unicode problem

* test=develop