[NewIR]Add NOT_FOR_INFER to prune Inference Library Size and Split VJP CodeGen into pd_op_vjp.cc (#56352)

* [NewIR]Prune Inference Library Size and Remove IR Dialect

* remove options

* add NOT_FOR_INFER

* fix pd_vjp.cc

* polish deps

* fix code style

* fix unittest

* fix cmake

* fix inference CI

* fix inplace with set_parameter

* fix bug

* fix bug

* fix bug

* fix bug

* fix bug

* refine code

* refine code

* support ir fill constant

* Integrate quantize/dequantize linear and add config for explicit quantization

* Fix the build error

* Add macro for TRT version < 8.0

* Remove qdq UT from windows

* Fix UT failure

* Check TRT version in qdq UT

* Test tensorrt_explicit_enabled API

* Disable QDQ UT if TRT version < 8.5

* Add quantization postfix into public APIs

* Apply code formatter

* Fix the UT failure for explicit quantization

* Apply code formatter on modified files

* Correct the year in copyright

* fix coverage compile error

* test

* modify tensorrt ci timeout

* activation ci bug fix

* Update CMakeLists.txt

* Update CMakeLists.txt

* comment out  int8 mode test_trt_dynamic_shape_groupnorm

* fix test_sync_batch_norm_op Segmentation fault

* fix timeout

* Update CMakeLists.txt

* add inverse kernel for xpu

* add more kernels

* add index_put kernel for xpu

* add index_put kernel for xpu

* remove unused headers

* refine test

* wait to avoid memory bugs for xpu

* refine inverse

* polish dist teensor design

* adjust constructor

* polish details

* polish details design

* fix compile error

* refactor init tensor impl

* fix reshard test

* polish details

* add unittest for coverage

* Modify kernels to support quantized_matmul

---------
Co-authored-by: Nsuperxf <1208713646@qq.com>

* [NewIR]Split PaddleDialect and KernelDialect and Implement Layered Compailation

* remove ir_core DEPS

* fix header files

* fix conflict

* ignore test_assert UT

* fix code style

* fix UT

* change prim forward in New IR

* polish code

* polish code

* test case

* add cpu quantize pass unit test

graph_compiler_util.h/cc：
整合GraphCompiler与ParallelCompiler共同持有的数据结构CompilationStage、CompilationStatus、CompilationContext、CompilationResult
Parallel Compiler：
整合数据结构至CompilationContext
支持分阶段编译，通过指定CompilationContext::Stage
添加编译状态信息，包括状态CompilationResult::Status和信息CompilationResult::message
一个Task对应一个fusion_group，每一阶段编译完成后，将编译结果放入CompilationResult数组的对应下标中，删去原Task中内部的局部变量，省去了MergeResult
Graph Compiler：
丰富CompilationResult，提供编译各阶段的中间结果
整合数据结构至CompilationContext
添加编译状态信息，包括状态CompilationResult::Status和信息CompilationResult::message
启用单测
其他：相关单测、前端接口、paddle2cinn适配CompilationContext

* add complex numel

* change test && add doc

* support ir api form prim

* convert vector of int to intarray

* support ir api for prim

* Add more gen api

* concat python api to concat_grad

* fix gen conflict

* support vjp prim mode in new ir

* remove useless code

* add vjp autogen v1.0

* add test for prim

* resolve type conflict

* modify utils

* remove useless code

* add split op and modify some bug of vectorType

* fix conflict

* add concat python test

---------
Co-authored-by: Ncyber-pioneer <chenzhuo@tju.edu.cn>
Co-authored-by: NCharles-hit <wanghao107@baidu.com>
Co-authored-by: N0x45f <wangzhen45@baidu.com>
Co-authored-by: Nchenzhiyang <1792266893@qq.com>
Co-authored-by: NChen Zhiyang <chenzhiyang99@126.com>

* support ir api form prim

* convert vector of int to intarray

* support ir api for prim

* support vjp prim mode in new ir

* remove useless code

* add test for prim

* modify utils

* remove useless code

---------
Co-authored-by: Ncyber-pioneer <chenzhuo@tju.edu.cn>

[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

【New IR】 backward gradients accumulate test and pulish append_backward_ops func for op_pattern  (#56265)

* [prim][newir] add basic framework for primitive

* support desctensor in new ir

* add vjp interface

* support vjp in new ir

* support vjp in new ir

* polish vjp interface

* fix stop_gradients set

* fix vjp dispatch

* add comment

* add vjp test for new ir

* add test for tanh vjp

* [prim][newir] add basic framework for primitive

* support desctensor in new ir

* support vjp in new ir

* support vjp in new ir

* polish vjp interface

* fix stop_gradients set

* fix vjp dispatch

* add comment

* add vjp test for new ir

* add test for tanh vjp

* add eager and static backend for warp lower level api

* support call_vjp pybind

* polish code and add test for vjp

* remove useless code

* polish code

* remove useless code

* support mean vjp

* backward origin code

* add test for mean vjp and support has_vjp function

* fix call_vjp

* polish code

* add attrs and dtype interface

* add primitive ops set for backend

* fix compile bugs

* fix some bugs

* fix windows bugs

* add vjp test for tanh_

* fix inference CI

* fix inference ci

* modify fluid cmake

* origin test of tanh and mean passed

* fix conflict

* modify stop_gradient

* remove useless deps

* add cmake

* modify block.ops

* modify test

* fix conflict

* reply review comments

* reply review comments

* pulish code

* fix comment

* fix test

* polish code

* modify backward stop_gradients

* modify static_backend.cc

* refactor grad_op

* support add and add_inplace vjp

* remove useless code

* remove useless code

* remove cout

* modify add_n

* modify add_n with add_vjp test

* modify add_n with add_vjp test

* fix conflict and concat call_vjp

* modify backward test

* Add more gen api

---------
Co-authored-by: Ncxxly <chenxx_id@163.com>
Co-authored-by: NCharles-hit <wanghao107@baidu.com>
Co-authored-by: Nzhangbo9674 <zhangbo54@baidu.com>
Co-authored-by: NYuanRisheng <yuanrisheng@baidu.com>
Co-authored-by: N0x45f <wangzhen45@baidu.com>

* update

* fix codestyle

* update

* update

* 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

* Fix and add unittest

* don't introduce assign when already in global block.

* fix more

* fix bugs

* fix bugs

* fix ci

* fix bfgs

* make function local

* 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

* add lu_unpack data check

* add error input api test

* add error type info

* fix op translator reshape type

* new ir support vector type place transfer

* add test case

* refine static op return val

* 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>

* [NewIR]Add CinnJitInstruction for interpreter

* fix windows compile error