* python inference enable_memory_optim(#18817)

python inference API support enable_memory_optim

* Python infer api update and add unit test (#19353)

* python inference api supports numpy and add unit test, fix unit test fail in test_slim_int8_googlenet and test_slim_int8_mobilenet

* change api approve

* update

* test=develop

* test=develop

* Support memory eager deletion on recurrent OP (#17710)

Test PaddingRNN on V100 GPU device.

Test configuration: large model, padding mode (which is the mode using recurrentOp), one GPU.
                   
GPU memory (MiB):   6414 (this PR)     vs   6837 (without this PR)
Speed (steps/s):         10.28 (this PR)    vs    9.89 (without this PR)

* Fix random test_recurrent_op failure (#18718)

The change includes 3 things:

1. Set CPU_NUM to 1 in the tests because the ParallelExecutor will print warning that CPU_NUM is not set and use default 1.

2. Old tests compare two RNNs, hand written simple RNN and same RNN built by Paddle, but initialized RNN weights in numpy random and Paddle random separately. Fixed it by setting weights and bias values.

3. Also set numpy random seed in the tests. Now the two RNNs diff can be smaller (rtol from 0.1, 0.2 to. 0.01) in the tests.

* update executor feed

This PR cherry-picked the fix of multiple Layers parameter missing error in dygraph mode，the original one is #18968

* fix bug in Class MultiSlotDataGenerator's function _gen_str, test=develop (#18222)
* fix some bug when merge sparse embedding parameters, test=develop (#18223)
* fix communicator with pyreader (#18350)
* delete AllocatorFacade destructor  (#18606)
* fix distribute transpiler GRPC error code 4, RPC Deadline (#18984)
* merge pr #18441

test=release/1.5

* fix depthwise conv gpu kernel bug, test=develop
* add more depthwise conv test, test=develop

* make_roi_perspective_transform_op_return_mask_and_matrix

* make_roi_perspective_transform_op_return_mask_and_matrix

* CHERRY_PICK 18941, 18860: TRT fp16 support.

test=release/1.5

* CHERRY_PICK 19213: Fix BUG: Mask RCNN inference diff When using AnalysisPredictor.
    1. fix affine channel fuse pass.
    2. fix condition block op.
    3. fix merge lod tensor op bug.
    4. fix memory optim cause by reset lod op.

    test=release/1.5

* add fusion_seqpool_cvm_concat test=develop

* simplify pass, test=develop

* fix code style, test=develop

* Add call stack info during runtime and compile time
test=develop

* add warning info for CPU_NUM
test=develop

* update dygraph parallel.py
test=develop

* prune the feed op in compiler
test=release/1.5

* remove compile from PE
test=develop

* test CUDAPinnedPlace in reader
test=release/1.5

* add PADDLE_ENFORCE_CUDA_SUCCESS, test=develop (#19211)

* test=develop,Modify PADDLE_ENFORCE to PADDLE_ENFORCE_CUDA_SUCCESS

* fix REGISTER_OP_WITHOUT_GRADIENT
test=develop

* add function:error code,test=develop

* add function:fix inference lib bug,test=develop

* fix the bug that PYTHON_EXECUTABLE not exists

* merge from develop: add tensorrt support for win test=develop

* fix warpctc dynamic library not found issue on mac and windows platform

* fix gather op bug
test=release/1.5

* fix backward bug

[cherry pick]fix roi_align_op cpu backward's bug

* rewrite the conv_op using cudnn_conv_helper

* add workspace limit for v7 test=develop

* fix test=develop

* add half float test=develop

* fix test=develop

* fix test=develop

* revise code style test=develop

* fix test=develop

fix mask rcnn
add interface for setting optim_cache_dir(eg: when in trt int8 mode, and load model from memory, there should be a interface for setting the trt calibration table data dir)

test=release/1.5

Add path to handle 1D vector

test=release/1.5

test=release/1.5

* test=develop

* test=develop

* fix mac build error

* test=develop

* fix

* add pm approval api.spec

* fix mac ci random fail
* use platform instead

test=release/1.5