* new general transformer inference support

* Delete inplace strategy in group_norm_fwd

* fix

* first run accumulation node

* support heter reindex

* add unittest, fix bug

* add comment

* delete empty line

* refine example

* fix codestyle

* add disable static

* extend forward fast_ln_kernel to support more column values.

* support CUDAGraph for partial graph

* add ut

* fix ci

* fix ut again because of eager mode

* fix kunlun ci

* fix win ci

* add yaml

* fix infrt compile bugs

* support weight transpose

* add ut

* add template

* fix transpose error

* fix transpose_comment

* add api tests

* add skipif

* add doc

unittest parallel
Co-authored-by: Nzhangbo9674 <zhangbo54@baidu.com>

* Add pinned memory to HostMemoryStats

* Add macro for WrapStatAllocator

* Fix CI errors

* add conv3d yaml

* add conv3d_grad, conv3d_double_grad

* add final_state_conv3d test case

* add conv3d double test case

* add depthwise_conv2d grad yaml

* add depthwise_conv2d double grad test case

* modify the order of args

* add depthwise_conv2d_grad_grad config

* remove attrs from base op

* fix typos

* remove brelu

* undo removing code related to matmul

* remove whitespaces

* undo changes in matmul

* remove empty line

* fix full zero

* fix full zero

* fix full zero

* fix full zero

* refine

* refine

* refine

* fix assign kernel copy impl

* fix test failed

* polish append op using

* fix var error

* fix group norm impl

* fix arg_max and reduce_max

* add arg_max ut

* rrelu逻辑部分

* unregistered op kernel (unresolved)

* commit before merge

* 丰富测试用例

* 修复rrelu-sig的bug

* 修复cpu环境测试

* 修改拼写错误

* 修改code format

* 尝试优化测试用例timeout的问题

* 优化测试用例

* 移除seed, 优化随机函数

* update en doc for rrelu

* fix rrelu en docs, test=document_fix

* add paper link for en docs, test=document_fix

* udpate en doc

* add r,test=document_fix

* change einsum_v2 as default and add new flags: FLAG_einsum_opt=1|0

* make EInsumOP support bf16

* add unittest for BF16

* add condition for test_BF16

* fix bugs

* fix

Co-authored-by: NRyan Jeng <rjeng@nvidia.com>

* support is empty

* fix error

* fix code error

* change to fake empty

* using fake empty first

* using fake empty first

* Support backward prune in fluid

* replace dropout_is_test with is_test.
* improve atol on a100.

* add embedding yaml

* fix infermeta bug

* fix bug of selected_rows infer_meta

* fix selected_rows

* add unittest

OneDNN md-in-tensor refactoring part 5: Memory descriptor enabled for elementwises, reductions and expand_v2 ops (#43036)

* enabled md in elementwises, reductions and expand_v2

* CI fix for invalid numpy copy

* fixed formatting

* CI rerun

* changes after review

* add fused_bias_dropout_residual_ln op and layer.

* update lite compile cmake

* Update delete_fill_constant_op_pass.cc

* Update analysis_config.cc

* support backward inplace in eager fluid mode

* fix

* fix

* optimize format

* little change

* nanmedian op

* 修改cuda kernel的bug

* 修复count_if在其他硬件平台不兼容

* 修复某些cpu硬件不兼容

* 修复某些cpu硬件不兼容

* 修复isnan判断

* 兼容numpy低版本不支持全部nan的情况

* 兼容numpy低版本不支持全部nan的情况

* fix code example

* fix api comment error

* 修改反向传播逻辑以及c++处理逻辑

* 完成修改建议

* typo pre_dim

* update en docs, test=document_fix

* remove numpy in en doc, test=document_fix

* add r,test=document_fix

* 添加api到all

* follow advice from chenwhql