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.

* Refactor port.h

* Remove some unnecessary code

* Fix CI errors

* fix starganv2

* fix starganv2 stop_gradient end error

* fix edvr_starganv2

* fix mul kernel to fix optional ddx

* fix typo

* Support sequential run for standalone executor

* Add UTs

* Fix test_standalone_multiply_write

* Remove unnecessary UTs

* [MLU]: add elementwise_max mlu kernel

* [MLU]: add int32 support for elementwise maxk MLU kernel

* open inference_ut;test=windows_ci_inference

* inference_ut need onnx;test=windows_ci_inference

* disable trt_split_converter_test; use higher parallel level

* too high parallel will cause ut timeout

* change logic for optimize

* modifty

* optimize the backward speed of EinsumOp

* add cache optimizer for einsum op

* EinsumOp: fix new dygraph mode error

* fix bug

* change Cache->InnerCache

* fix code

* fix

* add nan inf utils for einsum op

* add as_extra

* memory optimizer for einsum

* update code

* cmake-lint

* update

* fix custom op error

* fix code error

* add serialization for new field in event node

* fix a bug

* Enable bert model on CPU

* Style

* fix stride_slice bug

* fix bug

* support set_grad_ivar for eager

* support set_grad_ivar for eager

* support set_grad_ivar for eager

* use GpuMemcpy and GpuMemset

* sparse convert kernel support double dispatch by indices dtype

* cudaMemcpyKind->gpuMemcpyKind

Fix the bug of slice op and optimize the code style of generate_proposals_v2 op for kunlun. *test=kunlun (#43380)

* fix depthwise conv yaml error

* fix depthwise conv double grad error

* change tensor name

* fix unittest bugs