* general optimization no_varlen embedding layernorm

* add onehot trt converter

* add unitest

* fix bug

* opt code

* fix bug

* fix depth_tensor

* fix unitest

* fix bug

* fix unitest

* fix bug

* fix bug

* fix bug

* fix bug

* add reduce max for trt

* pass

* pass

* draft version

* share mem opt

* remove sharemem

* add pattern for the case with circle_shift=0

* add UT

* pass opt

* test_fix

* code-commit

* code-style

* code style

* code-style

* ut-fix

* op teller refine

* resolve conflict

* adjust position op_teller list and pass order for swin

* ut code style update

* adjust paddle pass order

* refine pass order

* refine pass order

* refine pass order

* add_range

* add_range

* fill_any_like_bool

* fill_any_like_bool

* general optimization for no_varlen multihead

* instance norm support dynamic shape
* update unittest

* Support FP16 in generic TensorRT plugin.
* Support FP16 for Pad3D.

* add trt support

* add_gather_nd_

* add_gather_nd_

* add_gather_nd_

* Update communicator.cc

* Update communicator.cc

* remove LoDTensor

* remove LoDTensor and Tensor

* fix loopup_table plugin deserialize size error

* fix

* group norm fp16 support

* optimize token prune

* fix:fix the bug of trt_8.0.3.4

* fix: fix the bug of trt_8.0

* fix: notes

* fix bug of zero_allocator in host

* fix test compile bug

* add unittest

* update test

* remove "gpu_primitives.h" in fluid namespace

* fix PR-CI-GpuPS fail

* fix PR-CI-GpuPS fail

* int scale

* round

* revert commit

* add_cast_bool

* cast

* add_fill_any_like

* add_fill_any_like

* elementwise_op

* add teller

* modify ut

* comments

* modify ut

* return

* modify

* add roformer pass&&plugin（novarlen）

* skip_merge_layernorm

* add UT

* modify comments

* upgrade scale and slice op convert for Paddle-TensorRT

* allow fold fill_constant && allow nms3 into trt in int8 model
* use unordered_map
* fix CI failing

* fix cast bug