* [cherry-pick] not build naive_buffer when build light framework, test=develop (#4251)

* fix opt fatal errors, test=develop (#4293)

* fix cmake dependencies, test=develop

* support build C++ cuda shared lib

* add gpu kernel mul pool relu scale softmax dropout bilinear_interp and can run in tx2

* rm GREATER_EQUAL

* fix conv_transpose error

* fix build error, enable basic test of conv_transpose, test=develop

* fix compiling and fix code style test=develop

* add full_api_static target and fix building errors, test=develop

* fix build errors, test=develop

* fix code style, test=develop

* fix lite/model_parser/pb/var_desc.cc, test=develop

* fix building errors, test=develop

* modify lite/tools/debug/CMakeLists.txt, test=develop

(1)modify tiny publish so to make it excutable
(2)modify the bug of compiling in armlinux
(3)change 3 full publish so into 2

* paddle lite cuda init
can run model with leaky_relu

* add the missing file.
test=develop

* add the load from memory interface.
test=develop

* refine this pr. fix comments
fix ci error
test=develop

* conv impl
fp32:
conv, conv+bais, conv+bias+relu, conv+bias+leaky_relu

int8:
conv, conv+bais+relu(int8 or fp32 output), conv+bias+leaky_relu(int8 or fp32 output)

can run conv+ bias+relu using cxx_api
test=develop

* move the lite/cuda/math to backends/cuda/math
test=develop

* paddle lite cuda init
can run model with leaky_relu

* add the missing file.
test=develop