* add dynamic support

* add more test

* fix bug

* change test

* change test

* fix multihead

* fix multihead

* move layer_norm_kernel.cu.h to phi

* fix bugs

* fix namespace

* fix bugs

* fix CI-Windwos

* replace mutable_data

* fix bugs

* fix bugs

* eleadd_trans first version

log fix

* refine code for linear format, add pass check

* linear format refine and ut fix

* fix ut

* windows ut

* windows ut 2

* move tensorMeta and alloc to configure

* add fmha_flashattention oss plugin

* add fmhca

* add oss fmhca

* code reconstruct and add ut

* code style refine

* fix ut and enforce check

* refine trt version check

refine compile

fix compile

* fix cross ut

* code refine

* use runtime trt version check

* bug fix and code refine

* compile fix

* merge develop

* add GN QDQ kernel

* support GN int8 fake kernel

* add with_int8

* add GN int8 fake kernel

* add GN int8 fake kernel

* add GN int8 fake kernel

* add GN int8 fake kernel

* add GN int8 fake kernel

* add GN int8 fake kernel

* add GN int8 fake kernel

* add GN int8  UT

* add verison > 8000  in GN int8  UT

* add some check in .cu

* add stdlib.h in UT

* little change  in .cu

* remove rand_r use rand

* remove use rand

* setAxis(1)

* when int8 is on allow fall back to fp16

---------
Co-authored-by: Nwwbitejotunn <wang_bojun@outlook.com>

* trans_layernorm

* gn_silu

* add ut

* set TIMEOUT

* correct comments

* comments

* disable windows ut

* rename parameter

* compile fix

* fix compile

* compile fix

* add more preln

* compile fix

* fix compile

* compile fix

* gn bug fix

* bug fix

* gn bug fix

* skip_groupnorm

* init

* preln

* add ut

* more assert

* set timeout

* fix windows ci issue

* add ouutput(CLSInds) for fused_token_prune

* optimize token prune for no varlen

* gn nhwc8

* remove error

* General optimization for no_varlen embedding layernorm

* fix some transformer unitest

* general optimization no_varlen embedding layernorm

* 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

* 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

* fix loopup_table plugin deserialize size error

* fix

* group norm fp16 support

* optimize token prune

* remove "gpu_primitives.h" in fluid namespace

* fix PR-CI-GpuPS fail

* fix PR-CI-GpuPS fail

* add roformer pass&&plugin（novarlen）

* skip_merge_layernorm

* add UT

* modify comments

* upgrade scale and slice op convert for Paddle-TensorRT

* optimize: vit 384

* fix:bug

* fix:bug

* fix:supoort rocm complie

* refactor:name

* fix:support rocm

* fix:__HIP_NO_HALF_CONVERSIONS__

* optimize: delete scalar

* fix:rocm can't support

* fix:ernie error

* prelnlayernorm_shift

* add ut

* remove paddle_enforce

* remove useless

* add UT

* remove UT

* add UT

* set timeout