* disable scale op in amp pass

* Do not insert redundant cast op

* fix fused_fc_elementwise_layernorm kernel diff

* fix fc kerenl diff

* cherry-pick 45860

* [BUG FIX]Fix MetaTensor's bug when run infermeta (#46265)

* fix sum bug

* fix ci bugs

* fix ci bugs

* update code according comment

* [Release2.4] Revert python link prs (#48573)

* Revert "Fix mac link python (#48017)"

This reverts commit 3fa7a736.

* Revert "[Cherry-pick] Fix python link error (#47811)"

This reverts commit ff642c68.

* Update config.go

* fix mixed precision inference
Co-authored-by: NChen Weihang <chenweihang@baidu.com>

* [Release2.4] Revert python link prs (#48573)

* Revert "Fix mac link python (#48017)"

This reverts commit 3fa7a736.

* Revert "[Cherry-pick] Fix python link error (#47811)"

This reverts commit ff642c68.

* Update config.go

* [Paddle Inference] Add float_to_half_pass to support  inference with mixed precision (#47993)

* [Inference] optimize some code and fix some bug (#48780)

* clean ir_pass_manager and fix map_depthwise_conv_to_conv_pass

* fix unitest timeout

* [Paddle Inference] clean unused code  (#48392)

* fix

* update

* update
Co-authored-by: NChen Weihang <chenweihang@baidu.com>

[cherry-pick] updating mul and matmul with set_mem_desc and fix squeeze_transpose for MKLDNN (#47951)

* Fix slice bugs in MKLDNN when input dims are zeros (#46671)

* fix slice bugs

* fix

* update code

* fix

* update code

* updating mul and matmul with set_mem_desc (#45624)

* - mul & matmul changes

- fix

- bs16 correction of strides

* - cosmetic fixes

* - lint

* - fix

* - fix

* - format -> mem_desc

* - fix

* - fix

* - fix

* - fix

* - fix

* fix squueze_transpose (#47911)
Co-authored-by: NJacek Czaja <jacek.czaja@intel.com>

* Reduce squeeze2_matmul_fuse_pass, flattent tests time (#47098)

* Add missing fp32 config and reduce the testing combination

* Reduce trt matmul pass test max examples

* Loose TRT fp16 tests tolerance (#47100)

* Loose TRT half test tolerance to 1e-3 (#47101)

* Loose TRT half test tolerance to 1e-3 (#47106)

* Update distributed_strategy.proto (#46531)

* Close popen pipe after used (#47053)

* Add launch_bounds (#47285)

* Fix TRT UT failures (#47488)

* Format cherry-picked commits

* CudnnNormConvolution is no longer supported on NVIDIA Hopper GPUs (#48203)

* Skip tests that use fused_ops on H100

* Add error message to FusedOps on H100
Co-authored-by: NShijie <505749828@qq.com>
Co-authored-by: NLeo Chen <39020268+leo0519@users.noreply.github.com>
Co-authored-by: NTian Zheng <tizheng@nvidia.com>

* add fuse_multi_transformer_layer_pass

* suqeeze2 + transpose2 fuse onednn cherrypick 2.4

* format

* fix merge

* fc cherrypick

* another files added

* added transpose cherrypick

* reverter somebodys fc changes

* minor fix

* minor fix

* cherry-pick of fc+act changes

* minor fix

* fix

* add constant_folding_pass pass for mkldnn int8

* update UpdateScaleOpInOutScales

* fix memory copy in prepare_data. test=develop

* add cache_kv fp16 support. test=develop

* fit for simplify_with_basic_ops_pass. test=develop

* support generating code of opmaker for backward op invoke forward op (#46912)

* [code-gen] Support code-gen for opmaker of sparse op (#46993)

* support generating code of opmaker for backward op invoke forward op

* gsupport code-gen of opmaker for sparse op

* refind logic of choose phi kernrel

* fix complie budg

* fix code_gen bug

* fix bug

* fix kernel signature code-gen

* fix complie bug of VarType

* fix complie bug of VarType

* fix test_sparse_conv_op

* fix test_sparse_norm_op

* [Phi] Refactor logic of judging whether having a phi kernrel (#46920)

* refind logic of choose phi kernrel

* fix complie budg

* update cmake

* add fused_attention_pass. test=develop

* support fp16. test=develop

* fix format. test=develop

* Fix quantize model deploy bugs when using MKLDNN (#45920)

* fix immutable op quantize bugs

* fix

* fix build bug

* fix test

* notest,test=inference

* fix ppyoloe acc drop bugs

* fix test

* fix test

* add test

* fix

* fix

* fix test

* fix refined name bug

* fix test

* bias fix

* fix matmul weight dequant bug

* re-ci

* fix tester

* fix test

* fix tester

* update weight dequantize func

* update code

* update test for converage

* update test

* update cmake

* update cmakelist

* update code

* rerun ci

* remove useless code

* re-ci

* update code

* update code

* fix header

* update code for log

* Enhance the layernorm shift partation fuse op when shift size > 0 (roll shifting)
* fix cherry-pick test

* Add unsigned int8 propagation

* Add or modify unit tests

* Correct concat scale checking

* Apply review suggestions

* Corrections
Co-authored-by: Njoanna.wozna.intel <joanna.wozna@intel.com>

* Fix bug of reduce_sum op. When input.numel() > INT32_MAX, its result
is wrong.

* Support allow_partial switch, which can be configure in
pipeline_configs. If sent tensor are not the same from
different hosts, they shouldn't been sent partially and
then concated as a whole tensor.

* Change name allow_partial to enable_partial_send_recv.

* Add global variable _enable_partial_send_recv

[CherryPick][Dy2St]Fix recurrent op eager deletion pass error in dy2st

cherry-pick : #46322, #46245
Sparse API 支持静态图

* paddle-inference support custom-ops
Co-authored-by: NZhixin Yao <zhixiny@graphcore.ai>

* fix tolower
Co-authored-by: NZhixin Yao <zhixiny@graphcore.ai>
Co-authored-by: NZhixin Yao <zhixiny@graphcore.ai>

* [PHI] Migrate gelu kernels (#45596)

* gaussian random

* mkldnn to onednn renaming

* fix merge conflicts

* remove fluid code

* onednn renaming

* gelu fwd

* sort activations

* gelu gradient

* remove unused macros

* merge conflicts

* fix merge conflicts

* remove extra contraint from gelu op

* [PHI] relu6_grad kernel (#46501)

* Relu6

* remove fluid handler

* add individual kernel signature

* coding style

* replace bounded_relu with clip

* whitespace

* code style

* Clear extra attrs of elementwise op in OpMaker (#45845)

* clear extra attrs of elementwise op in opmaker

* fix op_debug_string_test

* fix bug of grad_add

* fix sort of runtime attrs

* Clear extra attrs of scale in OpMaker (#45984)

* clear extra attr of scale in opmaker

* fix sum bug

* fix merge conflict

* fix minus

* Clear extra attributes of some Op in OpMaker (Part4) (#46060)

* clear extra attr of some ops in opmaker

* revert clear use_cudnn for pool

* fix test_operator_desc

* fix Attr interface of OperatorBase

* fix code stype

* polish code comments

* polish data_device_transform.cc

* add config

* add config

* follow comments

* fix serial run

* fix preln_residual_bias_fuse_pass bug in TNT_small model

* add scope cache & reuse

* add gc scope for end of each train step

* del scope reuse for jit

* refine code

* test

* fix wrong eigen header include

* fix complie bug

* fix nan_inf_utils_detail

* fix resource_manager

* fix conv_miopen_helper

* normalize yaml file name (#45894)

* Clear extra attributes of activation op in OpMaker (#45772)

* clear extra attr of activation op in opmaker

* fix syntax bug

* fix mkldnn kernel

* fix merge conflict

* fix bug

* [PHI] Normalize yaml op label (#45976)

* normalize yaml op label

* revert op_compat yaml change

* fix prelu and rnn compat problem

* replace api by op

* support assign op backward refuse forward (#45879)

* normize yaml backward op label (#46028)
Co-authored-by: Nzyfncg <zhangyunfei07@baidu.com>
Co-authored-by: NCharles-hit <56987902+Charles-hit@users.noreply.github.com>

Support 0 shapes input Tensor for MKL slice kernel

* delete eigen header in data_type.h

* fix complie bug

* refactor

* Allow manaully set py_reader name in standalone executor

* Fix CI errors