* multihead matmul add fp16

* fix windows error

* fix rocm error

* fix rocm error

* remove cudaDeviceContext

* remove more template

* fix rocm compile

* remove alias name CUDADeviceContext

* fix compile

* fix tests

* revert changes

* infer context fix place error.

* update

* update

* add varlen_token_prune plugin, pass, convert

* skip cast trt convert when input dtype is bool

* fused_fc_elementwise_layernorm support fp16

* fused_fc_elementwise_layernorm support double

* multi stream support handle lazy init.

* support eigen lazy init

* update

* fix ci problem

* update

* empty commit

* update

* update

* update

* fc support fp16

* add a ‘,’ on paddle_pass_builder.cc

* fc support fp16 on non-cuda.

* fix_fill_constant

* fix_fill_constant

* fix_ernie

* fix some error found in tipc.

* update

* convfusionfp16

* convfusionfp16

* convfusionfp16

* Rename BOOST_GET macros

* Fix conflicts

* add labels for infer ut

* add RUN_TYPE=INFER for cpp ut

* fix formaterror

* update

* shape sum

* add shape, sum trt layer

* test

* update

* fix_cast

* fix_cast

* commit

* remove useless code in fc

* reshape fill_constant

* commit

* commit

* add fused token prune op and plugin

* fix convtranspose and elementwise

* add method for post ops

* format code

* gpd

* format style

* add matmul+act test

* implement matmul+activation

* whitespaces

* code style

* python code format

* Increase UT timeout

* code format

* update style

* generalize activation fuse passes

* change order

* Unify activation GPD

* Revert changes with op_act

* remove softmax mkldnn attrs

* set common name for act attributes

* whitespace

* append postops by helper function

* ut style

* revert changes related to quantization

* Reduce redundancy

* reduce number of parameters

* trigger CI

* validate attribute

* trim unit test

* Quantize shape operator

* Add shape op to propagate scales pass

make linux link both paddle_inference_shared and paddle_inference_c to aoivid size increase (#44180)

* add ort clone interface

* paddle2onnx update to 1.0.0rc

* ort input_tensor use mutable data of scope

* fix_pool

* fix pool_op_plugin

* copy onnxruntime.dll to c++ test folder in windows

* remove ut that failed due to onnxrumtime.dll

* test_api_impl failed of diff

* use TARGET to make sure if the test exist; use POST_BUILD to add copy command