* Reorganize the forward codes of flash-attention.

* Fix forward.

* Remove some noused codes.

* Simplify codes and fix backward.

* Change all LOG(INFO) to VLOG and fix the backward.

* add scale for AF2 flash_attn, much thanks to xreki and shaojie for debug these codes

* decrease the effect of debug print on performance

* Unify the initialize of flashattn arguments.

* Rewirte the reshape of temp_mask and temp_bias.

* API support use_flash_attn.

* Fix compiling error on CI.

* Try to crop the flash-attention lib.

* Correct the condition of whether can use flash-attn.

* Remove the softmax_out argument.

* Remove is_causal.

* Polish codes.

* Fix qkv_transpose_out's shape and scaling of Q * K.

* Update commit of flash-attention.

---------
Co-authored-by: NLiu Yiqun <liuyiqun01@baidu.com>

* [tools] add PADDLE_API check file diff approvals

* [tools] fix determine

* [tools] fix determine

* [tools] Change to full character matching
Co-authored-by: N张春乔 <83450930+Liyulingyue@users.noreply.github.com>

* [tools] Update echo_line
Co-authored-by: N张春乔 <83450930+Liyulingyue@users.noreply.github.com>

* [tools] Update check_approval
Co-authored-by: N张春乔 <83450930+Liyulingyue@users.noreply.github.com>

---------
Co-authored-by: N张春乔 <83450930+Liyulingyue@users.noreply.github.com>

* remove user define grad

* fix errors

* remove unused self.x_grad, self.out_grad

* Add large dim test of log_softmax

* fix

* review

* modify opcompat bug

* modify pybind

* delete bf16 of cross entropy

* delete bf16 of cross entropy

* decrease_peak_memory

* add meshgrid,expand_as, prod and grad bf16 kernel

* fix bf16 for optest

* modify code style

* fix amp test

* Revert "[inference][trt]add trt sparse weights switch (#53562)"

This reverts commit 4a69a536.

* remove kSPARSE_WEIGHTS

* remove kFASTER_DYNAMIC_SHAPES_0805 and add 'TrtMajorVersion' function

* fix parameter not passed

* fix repr

* ignore third_party

* modify .gitmodules

* test=document_fix

* test=document_fix

* test=document_fix

* [CINN] Fix TestGelu unittest of CINN

* pass if_enable_cinn

* Fused elementwises kernels and ops

* change fuse pass name

* adjust .pbtxt files

* adjust quantization attributes

* add missing arguments and fix others, review fixed

* simplify fused kernel registration

* fix elementwise unit tests

* reuse one fused elementwise op

* adjust proto

* Add supported datatypes

* Change 'Scale' to 'scale' in tests, change some tests to onednn

* Revert breaking changes

* Fix unit tests

* Delete obsolete test cases

* Delete commented out code

* Fix codestyle

* delete temporary condition

* fix conflicts and delete duplicate fusing

* Fix code after merge

* Move tests to new directory

* fix tests volatility

* Rename test_elementwise_add_onednn_op.py to test_elementwise_add_mkldnn_op.py

* Update CMakeLists.txt add mkldnn op test

---------
Co-authored-by: NSilv3S <slawomir.siwek@intel.com>

* move sequence_mask op InferShape func

* add dtype infer

* fix

* fix