* Load models and run PE

* Stash all code

* Fix C++ UT and refine code

* Fix string length error

* skip windows ci because windows do not have wget

* Just print out in layer_test because bce param file changed

* Refine code

* Fix pdiparam download error for layer_test

* Polish FunctionSchema and rename some arg

* New Exector only once

* Add value type for ivalue

* Read params from one pdiparam file

* Replace ivalue using Variable

* Remove ivalue file

* Fix inner_exe new

* Using DeserializeFromStream to load tensor

* Split .cc files

* Polish cmakelist

* [CustomKernel] add custom kernel c api

* update

* update

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

* add squeeze2

* add squeeze

* add squeeze2,unsqueeze2

* merge develop

* fix format

* add conditions for squeeze2 and unsqueeze in op_teller

* merge develop

* add squeeze unsqueeze

* add squeeze unsqueeze

* add squeeze unsqueeze

* remove unsqueeze2_eltwise_fuse_pass

* add squeeze/unsqueeze

* add unary

* Support disable GC for some vars in standalone executor

* Setting skip_gc_vars in interprecore construction

* fix xpu kp compilation

* add depends

* lazy creating work queue

* fix dry_run

* Optimize prod's python implementation for dygraph.

* Change key_dim to head_dim.

* Add comment in unittest.

* Disable TF32 in unittest.

* rename yaml file

* fix merge conflict

* fix infrt

* 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.

* 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