* disable_skip_layernorm_fp16

* update trt workspace size param

* update

* update

* update

* use int64_t

* use int64_t

* upate

* update

* add rnn

* remove cudaDeviceContext

* remove more template

* fix rocm compile

* remove alias name CUDADeviceContext

* fix compile

* fix tests

* revert changes

* add varlen_token_prune plugin, pass, convert

* update

* empty commit

* update

* update

* update

* fix_fill_constant

* fix_fill_constant

* fix_ernie

* Rename BOOST_GET macros

* Fix conflicts

* shape sum

* add shape, sum trt layer

* remove useless code in fc

* reshape fill_constant

* commit

* commit

* add fused token prune op and plugin

* fix convtranspose and elementwise

* 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

* support inpus is weight

* fix init()

* delete test_device_context

* replace CPUDeviceContext with CPUContext

* fix test_scalar

* remove dot_op.cc

* fix compile

* add relu6 kernel and yaml

* format files

* format code and fix bug

* fix build failed

* add comparisons trt converter

* rewrite elementwise

* add cast trt converter

* fix arg_max converter

* add fc, multihead_mul, shape tensor infer, slice

* shuffle_channel

* shuffle

* shuffle

* shuffle

* add bilinear_interp_v2 converter

* add activation layer

* add squeeze2

* add squeeze

* add squeeze2,unsqueeze2

* merge develop

* fix format

* add conditions for squeeze2 and unsqueeze in op_teller

* merge develop

* add squeeze unsqueeze

* add squeeze unsqueeze

* add squeeze unsqueeze

* remove unsqueeze2_eltwise_fuse_pass

* add squeeze/unsqueeze

* add unary