* 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

* new general transformer inference support

* fix maybe-uninitialized warning

* fix compile

* fix xpu compile

* fix npu compile

* fix infer compile

* fix compile

* fix compile

* support yolov5s static/int8

* fix eltwise_sub and div weight compute

* fix delete_fill_constant_pass

* swish refactor

* bug fix

* trt7 non-linear bug fix

* fix FlattenContiguousRangeOpConverter out dim error

* update code