* support onnx format quantized model

* update code

* add test

* add test

* fix

* fix test

* fix cmake

* update code

* change scale file path to calibration file path

* update code

* update code

* fix build bug

* fix build bugs

* fix

* fix

* fix doc of max_pool_2d

* dbg

* fix format

* fix bug in PostTrainingProgram for certain cases

* fix scale bug

* [CustomDevice] unittests tracking the fixed version plugin

* update

* [Eager] fix pool2d interface under eager mode

* add use_gpudnn for pool2d

* fix pool2d yaml conflicts

* fix pool2d yaml

* migrate memcpy to phi

* fix typo error

* fix typo error

* fix  bug and testcase

* fix typo, uniform_random_kernel.cc header

* fix Alloc pinned bug

* change GPUContext::GetPinnedPlace

* add GetPinnedPlace function

* add GetPinnedPlace function

* restore default throw error

* fix Unimplemented error

* skip StandaloneExecutor testcase

* delete memcpy_sig

* [Eager, Performance optimization] fix pool3d under eager mode

* polish code

* dist_matmul trans

* update unittest

* update cmakelist

* [Eager] Cast,uniform_random,assign_value use final state

* fix mistake

* fix mistake

* fix CI errors

* add dygraph test for unform

* add fp16 test case for bilinear_initializer

* [OpAttr]ksize of pool2d support Tensor type

* fix unittest

* add unittest

* [ONXX]Remove cond_var from Input(X) in while_loop op

* fix unittest

* vit_384_opt

* just support trt8

* padding + unpadding

* fix:unit test

* refactor:padding

* fix: change the position of round_up

* refactor: delete workspace

* 1. make list transformer into jit form.
2. fix some bugs in tensor_array, such as append.
3. enhance the function analysis visitor to recognize push/pop.
4. add setter/getter helper to deal with 2+ name sets.

* fix ci errors:
1. add to_tensor_array logic in convert_cond
2. fix IfExpr error.
3. fix erros while return_names or push_pop_names is None
4. fix slice error in a[i]=1 where a is tensor_array
5. add pop interface in Variable

* [Eager] fix spectral_norm interface under eager mode

* fix spectral_norm yaml config

* [Eager] fix max_pool3d_with_index interface under different mode

* fix mistake

* Add tests under legacy and supplement comments

* bugfix (#45332)

* customize wait_comm

* [NPU] add conv3d_transpose, instance_norm, instance_norm_grad

* add ut

* remove instance_norm_grad

* add erf_p primitive operators

* add gelu orig2prim rule

test=kunlun

* add fetch and prune for build cinn pass

* add prune flag