[Inference] Make share_external_data supports bf16 and bool; fix while_op cache_inference_while_scope when using fleet_executor. (#56055)

* 1. make share_external_data supports bf16 and bool; 2. don't drop_kids when cache_inference_while_scope

* fix FLAGS_cache_inference_while_scope

* add unitest

* add unitest

* skip unitest when cudnn_version < 8100

* skip test share_external_data_bf16 when CUDA_ARCH < 80

* fix op translator reshape type

* update

* new ir support vector type place transfer

* add test case

* update

* revert code

* add test assert new ir test

* update

* update

* fix shadow output translator

* fix coverage ci

* add vjp autogen v1.0

* resolve type conflict

* trace run when sync bn

* remove execution_config.used_for_control_flow_op

* update

* update

* open static build flag

* close static build flag

* open static build flag

* add searchsorted to analyze dtype list

* recover and add test_searchsorted_op to static build list

* Update CMakeLists.txt

* Update CMakeLists.txt

This reverts commit fd765f61.

* support setting backward prim blacklist

* add test case

* polish prim forward flag

* fix test case

* [paddle-TRT] support mark output

* [fix bug] hook function only call one in different predictor

* add api test

* fix op translator reshape type

* new ir support vector type place transfer

* add test case

* fix new ir bn grad bug

* add lu_unpack data check

* add error input api test

* add error type info

* add flags for cinn test

* rename DescTensor

* remove useless code

* modify code style

* modify code style

* modify code style

* fix op translator reshape type

* new ir support vector type place transfer

* add test case

* [NewIR] support c_broadcast

* add legacyOpList

* refine static op return val

* Fix Mac Timeout Test

* fix test

* fix

* Fix test

* Tesst

* Fix mac test

* fix inset get_parameter op bug

* fix bug: insert  only for parameters

* fix bug: wrong idx in vector

---------
Co-authored-by: Nzhangbo9674 <zhangbo54@baidu.com>

Added a graph data structure in units of ScheduleBlock and some necessary operations, such as finding upstream and downstream nodes, and performing operations in the DFS topological order.

Co-authored-by: Nxiongkun <xiongkun03@baidu.com>

* update

* update

* fix silu backward prim bug

* fix silu double grad prim

* [NewIR]Add CinnJitInstruction for interpreter

* fix windows compile error

runtime compiler api will only build special target if it is bind.

'--include-path' is not supported by hipcc and "-I/include/folder"
is better choice

fix ut:
        * device_code_test
        * test_code_generator
        * test_fusion_group_pass
        * test_fusion_group_op
Signed-off-by: Njiajuku <jiajuku12@163.com>

* [Fluid] Migrate c_embedding to PHI

* fix

* add python_api

* fix ut

* migrate xpu kernel

* fix windows compile error

* add TrilAndTriuOpTranscriber for ir translator

* refine

* fix assert op pd to kernel pass bug

* refine

* refine

* [Approve]Modify inference size approve name list

* [NewIR]Refine shape dialect directory

* modify IR into ir

* fix cmake

* fix typo