fix_encoding_bug

Fix bug for pipeline & add docs

add paddle detection and fix dependency

fix some doc and add abtest

fix some doc by HexToString

fix grpc_impl_bug and add readme by HexToString

Fix Bugs for batching predict of pipeline

Update get_model.sh

fix cmake problem and gpu serve

fix_MultiLangServer_bug and encryption doc

Compatible with Python 3 syntax

fix Codestyle

use paddle 2.0.0 fix encryption and some doc

Fit a line - Auto shape

fix encryption get_data.sh bug

fix bert_web_service_gpu and fix doc

Auto shape for Web Service

support cuda10.1 10.2 TensorRT and fix some bug

support multiple devices(cpu/gpu/trt/xpu/arm) in pipeline mode

brpc reduce BTHREAD_MIN_CONCURRENCY from 4 to 2