* [CustomKernel] add custom kernel c api

* update

* update

* fix unable to export capi
Co-authored-by: Nronny1996 <524019753@qq.com>

* add some kernel(csr*dense->csr, dense*dense->csr) of SparseTensor matmul

* fix CI

* fix CI

* fix comment

* fix comment

Use int64_t in GetGpuLaunchConfig1D and ElementwiseKernel as index type to support large tensor. (#43506)

* Change some data type from int to int64_t in GetGpuLaunchConfig1D to support large tensor.

* Use int64_t in ElementwiseKernel as index type to support large tensor.

* fix stride_slice bug

* fix bug

* 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

* 1st commit

* fix usless change in header transpose_kernel_h file

* add sync

* refactor the optional tensor

* remove optiona<MetaTensor> in InferMeta

* fix bug

* fix optional<vector<Tensor>>

* fix bug

* fix rmsprop

* fix amp of eager_gen

* polish code

* fix deleted code

* fix merge conflict

* polish code

* remove is_nullopt_

* fix merge conflict

* fix merge conflict

* fix maybe-uninitialized warning

* fix compile

* fix xpu compile

* fix npu compile

* fix infer compile

* fix compile

* fix compile

* use fp32 compute type for cublasGemmStridedBatchedEx with fp16 input/output

* add flags to control compute type

* default to false

* add unit test

* default to true

* change the output format of C++ backward api

* fix merge conflict

* fix sparse api code auto-gen

* fix eager_gen bug

* fix bug of output is null

* fix bug of conv2d_grad_impl

* fix optional grad

* fix bug of eager-gen double_grad

* fix bug

* fix multiply_double_grad bug

* fix bug of higher order derivative

* fix bug of FillZeroForEmptyGradInput

* remove redundant vector in grad_node

* fix bug of test_deformable_conv_v1_op

* fix bug of test_deformable_conv_v1_op

* some refacotr

* Create elementwise_heaviside_op.cc

* add ElementwiseHeavisideFunctor

* Create test_elementwise_heaviside_op.py

* 增加heaviside的python接口

* add heaviside in white list

* 增加heaviside的签名

* 增加heaviside的核函数

* 增加heaviside梯度的核函数

* 增加heaviside梯度的注册

* 调整代码格式

* Update elementwise_sig.cc

* add heaviside in __all__

* Update heaviside docs

* Update math.py

* Update math.py

* Update math.py

* set device id of Place() to get GPUContext needed by LimitGridDim in ElemwiseGradBroadcast

* fix code style

* optimize performance of dygraph

* optimize performance of dygraph and elementwise_add

* optimize the trace op

* fix bug

* fix bug

* fix unittest bug

* fix code format

* change sequential logic

* change some quotes

* add some notations

* change wrong note style.

* regist elementwise_xxx

* chnage dispatch to visit

* resolve conflict

* init commit no push

* collect comile errors

* bitwise UT

* fix compile problem

* cancel comments

* restore miss deletion

* fix compilation

* fix UT

* NO stash in multiple branch at the same times

* fix error

* combine .cu from gpu and kps

* replace gpu by kps

* fix by Chen-weihang

* Revert "Fix kps compile error in Junhui logic compare bitwise"

* fix backend test

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

add a inner loop for index_select_grad_init() in index_select op when dealing with large-shape data (#41563)

* replace for with CUDA_KERNEL_LOOP for index_select_grad_init() in index_select op

* use CUDA_KERNEL_LOOP_TYPE

* fix code style

* replace index_select_grad_init with SetConstant