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

Develop

fix python bug and add java example

[WIP]support arm and xpu

Update channel_acc_size

fix compile doc for trt

fix param name

2.0 develop first commit

Update pip version

Update  pip install paddle-serving-app==0.2.0

brpc reduce BTHREAD_MIN_CONCURRENCY from 4 to 2

原命令：pip install paddle-serving-server-gpu==0.4.0.trt # GPU with CUDA10.1+TensorRT

新命令：pip install paddle-serving-server-gpu==0.4.0.100 # GPU with CUDA10.1+TensorRT