test=developt branch

* add transpose-softmax-transpose fuse pass

test=develop

* enable supported lite-npu ops

test=develop

add x86 math:sequence_scale,sequence_padding,sequence2batch,sequence_pooling. test=develop (#1884)

* [NPU] fix conv2d npu bridge, supports bias from input map
test=develop

* [NPU] support more dimensions for the bias of conv2d NPU bridge
test=develop

2.add flatten2 for gpu.
3.add concat 4 inputs size for gpu.
4.fix pool.
5.fix transpose2
test=develop

* paddle lite cuda init
can run model with leaky_relu

* add the missing file.
test=develop

* [test=develop]1.fix crash when gpu op scale&elementwise_add input dim size equal 2
2.add gpu op mul

* fix code style test=develop

* add npu script and tester

* fix npu armv7 so and refine tests

test=develop

* update fix and refine log

test=develop

* Catch mobile exceptions test=develop

* code style format test=develop

* test=develop add matmul_op

* use lite::arm::math::sgemm func to implement matmul

* test=develop  pre-commit command to run clang-format

* Revert "test=develop  pre-commit command to run clang-format"

This reverts commit 3f56474f.

* test=develop pre-commit command to run clang-format

* enable fast test compilation && push opencl kernels by run.py

* merge cl kernels into so

* restore pre-commit

* fix building ios tiny publish lib error

* support setting cluster and threads in MobileConfig

* fix build error, test=develop

* fix building server publish error, test=develop

test=develop

* [Publish] fix publish compile

* update build.sh to clean build dir

add model_run_test_image
    add range_max_quant op
    add flatten op
    add flatten2 op
fix:
    fix density_prior_box density_size type from float to int
    fix prior_box and density_prior_box some check for get_attr
test=develop

* fix bug: npu permute's input w need unique name

test=develop

* fix bn, eltwise, pool, shuffle_channel, softmax, transpose unique name

test=develop

test=develop

test=develop

move cmake functions to lite.cmake