* Try to increase the repeat of autotune and fix the setting of allow_tf32_cublas.

* Change the repeat of cublaslt to 10.

* Use FLAGS_cublaslt_exhaustive_search_times as repeats.

* Fix compiling error on CI.

* Polish the key and simplify codes.

[XPU][PHI Kernels] bind bitwise_add kernel & add int32/int64 support to scatter_nd_add kernel for xpu (#54066)

* bind new kernels to xpu

* refine code

* fix bugs in unittest

* 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>

* test,test=develop

* test,test=develop

* test,test=develop

* test,test=develop

* test,test=develop

* test,test=develop

* [CustomDevice] add inference MP support, PART0

* update

* add pad op for xpu

* add pad op for xpu

* add pad op for xpu

* add_depthwise_conv2d_transpose

* Update test_depthwise_conv2d_transpose_op_xpu.py

删除print语句

* fix as review, add fp16 conv2d_transpose

* fix unittest of bn and reduce_mean

* fix bn unittest

* fix ci

* fix ci

* test,test=develop

* test,test=develop

* test,test=develop

* test,test=develop

* bind sparse_coo_tensor, reduce_max/max_int32, range/arange_int32, equal_bool, scatter_grad_float32, nearest_interp_int64 kernels

* add more unit tests; modify compilation logic of xpu sparse kernels

* test,test=develop

* test,test=develop

* clang format

* add cumsum_grad op to xpu2_op_list

* Optimize prompt information

* add_information

* add_information

* add flags for phi

* fix compile bugs

* fix ci bugs

* fix inference bugs

* fix cinn' bugs

* fix cinn bugs

* perfect code according comment

* fix ci bugs

* fix ci bugs

* test,test=develop

* test,test=develop

* test,test=develop

* test,test=develop

* test,test=develop

* test,test=develop

* test,test=develop

* test ,test=develop

* [XPU] add numel op

* [XPU] update numel/size op registration

* remove ASCEND* keyword

* update docstring

* bug fixed

* bug fixed

[Zero-Dim] support 0-D tensor for reduce/reshape/stack/prelu/expand_v2/gaussion onednn kernels (#52185)

* support 0-D tensor for reduce/reshape/stack/prelu/expand_v2/gaussion ops

* fix gaussian random mkldnn op ut

* delete WITH_ASCEND_CL

* delete NPU/ and WITH_MLU

* [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