add gpu support

Remove paddle.v2

* host_memo_profile

* Update host_memory_profiling_en.md

* Review

test=develop

* upload write_docs_en.md

* Textual Review

* fix link ref

* upload op_notesen

* Review

* review2

* upload new_op_en.md

* Review

* Review2

* mobile_build_en

* Review

* mobile_readme_en

* Update mobile_readme_en.md

* Review

* Review

* remove v2

* remove mobile

* fix_02

* windows_cpp_inference_en

* Update windows_cpp_inference_en.md

* Review

* paddle_gpu_benchmark_en

* Update paddle_gpu_benchmark_en.md

* Review

* review2

* paddle_tensorrt_infer_en

* Update paddle_tensorrt_infer_en.md

* Review

* native_infer_en

* Update native_infer_en.md

* Review

* review2

* build_and_install_lib_en

* Update build_and_install_lib_en.rst

* Review

Fix reader.md doc

update inference doc (analysis predictor and  trt int8) for 1.3

* upload fluid_design_ideaen.md

* review

* remove redundant files

- delete the Models index in root index
- update models/index_en.rst

* py_reader_en

* Textual Check

* test_while_training

* Textual Review

Textual Fix

* single_node

* Textual Fix

* review on webpage

* simple_model

* Contextual Review

* review on webpage

* numpt_array_en

* Textual Content Check

* fix wrong file location and name

* review on webpage

* lod_tensor_en

* Textual Content Check

* Review and fix on webpage

* upload metricsen

* First round review

* minor fix to round 1 review

* Update metricsen.rst

* Change file name and re-review

* upload indexen

* Textual Review

* upload train_on_baidu_cloud_en

* First round review check

* review on webpage, fix minors

* upload save_load_variables_en

* Textual Review

* upload enhowto

* upload cluster quick start en

* review commit

* recover original multi_node.rst index

* fix index of cluster_howto

* fix index

* fix bugs

add rcnn doc