* initial commit for cutlass_teller

* second commit for cutlass_teller

* add conv2d_depthwise python template

* add conv2d_depthwise cutlass template

* /zhoukangkang/paddle_cutlass/Paddle/paddle/fluid/framework/ir/cutlass_teller.h

* refine code in Conv2dFusionCanSupport

* add macro in cutlass_teller.h

* add 3x3 5x5 teller

* add groups not 1 or conv2d_depthwise teller

* 只生成ic是8的倍数的conv2d_depthwise 的kernel

* add EXPLICIT in cutlass_teller.h

* final commit

* add split_k_slices in conv2d_depthwise

* make stages == 2

* 重构部分代码

* add CutlassFusionType

* solve illegal memory

* make stride_h=stride_w && make dilation==1

* must check HasAttr(use_cutlass) before GetAttrIfExists

* add CONV2D_DEPTHWISE_BIAS_SILU to OpType2String

* modify decl.h and util.cu

* add register info for eigh and eig_gard

* add sync_batch_norm_op.cu register info

* add lamb output register info

* add unique register info

* change type name

* change type name

* add output register info for check_finite_and_unscale

* update cmake and config file

* add register info for adagrad

* fix build error

* add sync to run_unittests.sh

* add register info for unique_consecutive

* fix build error

* add eigh to STATIC_BUILD_TESTS

* update eig_kernel.cc

* update eig_kernel.cc

* fix infer mate error

* fix unique register error

* fix lamb register info error

* fix lamb register info

* update lamb register info

* fix lamb

* remove one Output Register

* update static build file

* add eigh op to disable_wingpu_test

* update run_unittests

* delete SupportNPU(), SupportMLU()

* delete npu branch

1. modify set_value op, use Scalars to represent attr `values`, instead of a bunch of attributs of various types; (#52408)

2. add program converter and set_value op as an example, which provides the functionality to convert `paddle::framework::ProgramDesc` between old and new formats(the differences are mainly some operators with incompatible updates in the definition);
3. program version and operator version map now are always saved when serializing `paddle::framework::ProgramDesc` to identify the version;
3. provide an option `legacy_format=false` in  serialization of `paddle::framework::ProgramDesc`, it decided whether to convert ProgramDesc back to a legacy format, which is compatible for paddle 2.4.2 or earlier versions to load and execute;
4. deserialization of `paddle::framework::ProgramDesc` is now automatically detecting whether the bytes it receives is in legacy format(contains any of the operators that has been incompatibly updated and have any attribute of type `Scalar`) and convert it to new format. But if you want a faithful deserialization without the automatic conversion, you can use protobuf's deserialization instead. Though it is not recommended, it can be used for the purpose of testing.

* Paddle-Trt: Replace fc mul matmul matmul_v2 with matrix_multiply

* [enforce.h Decouple logging.h] Delete glog/logging.h from enforce.h

* Add logging.h for profiler.cc

* Add logging.h for gloo_utils.h

* Add logging.h for addmm_kernel_impl.h

* Add logging.h for addmm_grad_kernel_impl.h

* Add logging.h for p_send_kernel.cu

* Add logging.h for determinant_grad_kernel_impl.h

* Add logging.h for p_recv_kernel.cu

* Add logging.h for elementwise_grad_base.h

* Add logging.h for transfer_layout_kernel.cc

* Add logging.h for eigvals_kernel.cc and index_select_impl.h

* Add logging.h for all files in kernel directory

* Add logging.h for xpu_info.cc

* Add logging.h for xpu

* add bfp16 test for isfinite

* fixed for ci

* deal with comments

* fixed test

* skip test in cpu

* deal with comments

* fixed for ci

* fixed testcase

* fixed for ci

* fixed for testcase

* Support two inputs of multihead attention named qk_multihead

* [Opt Performance] Optimize custom operator performance, reconstruct python API auto-gen, add cache and use const inference

* opt AutoGradMeta implementation

* remove profiler codes

* fix unit test

* change year, 2021->2023

* fix int64_t parse bug

* add strategy force_sequential_run

* remove flag

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* add strategy force_sequential_run

* fix

* fix

* fix

* fix

* fix

* fix_build_ci_error

* fix_build_ci_error

* fix_build_ci_error

* Verify SequentialRun Model of StandaloneExecutor

* fix

* fix

* fix

* remove redundant code

* fix CI

* fix CI

* recover multi-step dependency

* update

* fix compile bug

* fix bug

* fix bug

* revert crop_op

* fix xpu compile

* fix cinn compile

* fix bug

* fix bug

* fix bug

* fix bug

* update

* update

* update

* replace matmul with matmul_v2 in fuse passes

* Remove fusion logic from matmul

* removing fusion methods

* add proper name

* adjust namespaces

* clean attrs in python tests

* delete checkpoint and restore matmul version

* remove unused code

* matmul and reshape/transpose fuses migrated

* split MatmulOneDNN headers

* fuse activation and eltwise_add

* add fuse_activation

* matmul_transpose_reshape/reshape_transpose_matmul

* matmul + elementwise_add (fused)

* activation temporary modifciation

* restore matmul(v1) version 0

* merge newest develop

* remove depedency from other PR

* revert pbtxt

* remove placeholders from matmul_v2

* add description in OPMaker

* remove matmul_v2_op.h and all depedencies

* remove dims changing in base op

* add possibility to fuse already fused_matmul

* restart broken CI

* Empty-Commit

* revert matmul_utils.h

* codestyle

* adjust imports

* add pbtxt file

* 100% matmul unit tests coverage

* trigger CI with minimal changes to develop

* adjust changes to develop

* add fused_matmul op

* inherit base ops

* add "v2"

* move OPMaker

* Gradually add fused_matmul files

* second batch of fused_matmul changes

* split infershapes of matmul_v2 and fused_matmul

* merge code from other PR

* 2023

* inherit fused_matmul from matmul_v2

* Update paddle/phi/backends/onednn/onednn_reuse.h
Co-authored-by: NTomasz Socha <tomasz.socha@intel.com>

* Update paddle/phi/kernels/fusion/onednn/fused_matmul_kernel.cc
Co-authored-by: NTomasz Socha <tomasz.socha@intel.com>

* resolve conflicts

* codestyle

* simplify isgemmlinear

* 2023

* remove import

* reuse methods

* matmul_v2_mkldnn cleanup

* simplify ExecuteMatMulV1Grad

* matmul refactored

* fc

* SetOutMemDescWithLogicalLayoutFusesSupport

* matmul_v2

* alpha support

* group repetetive funcs

* matmul utils

* execute matmul methods

* restore registered kernel names

* split header and impl files

* remove double negatives

* reduce numer of modified files

* adjust ExecuteMatmul

* add scales for ut

* dates

* limit number of modified files

* fluid imports

* remove alpha

* codestyle

---------
Co-authored-by: NTomasz Socha <tomasz.socha@intel.com>

* delete [-Wno-error=terminate], test=develop

* remove GPUps[-Wterminate],test=develop

* autogen embedding

* deal

* fix bug in CompatMetaTensor::share_lod

* Improve new executor static build

* Skip GC for static build

* Skip infershape for static build

* Handle read_op

* Add fused_attention to OpsWithFluidKernelNeedMoveToPhi

* Fix argsort typos

* Add sequence_pool to OpsWithFluidKernelNeedMoveToPhi

* Fix skip share lod errors

* Fix errors for adam

* Fix errors for eigvals, memcpy and fake_quantize

* Add static_build.cc

* Add black list

* Fix CI errors

* Fix CI errors

* Fix CI errors

* Fix TensorArray

* Fix TensorArray

* Add update_loss_scaling to OpsNeedSetOutputDtypeWhenRegisterPhiKernel

* Fix copy

* Fix errors

* Fix momentum

* Skip mkldnn

* Fix CI errors

* Fix c_sync_calc_stream_op

* Fix CINN

* Fix while op

* All CI pass, disable FLAGS to merge code, enable it after more tests in future

* Add UTs

* Fix typos

* Fix typos

* Add mkldnn UT

* Remove mkldnn test

* Fix typos

* Fix dist test

* Fix typos

* Fix CI errors

* Fix CI errors

* Add UTs

* Fix typos

* Fix typos

* Add sparse tests

* ToComplexType -> ToComplex

* Add test_matmul_op_static_build to disable_win_inference_test

* change skip-layernorm to adapt a new method

* fix review problem and add vlog

* fix review problem

* [CustomOP Optional Inplace] Custom operator supports inplace optional vector Tensor input

* uncomment unittest codes