apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-12-24 13:28:13 +08:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

[Serving]Update images version to 0.6.0 (#594)

Browse Source 
* serving images update to 0.6

* serving images update to 0.6

* serving images update to 0.6
This commit is contained in:
heliqi
2022-11-16 10:11:43 +08:00
committed by GitHub
parent 7084a94bdc
commit 2f73857b2b
10 changed files with 42 additions and 24 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
examples/vision/classification/paddleclas/serving/README.md
View File

@@ -21,12 +21,12 @@ mv ResNet50_vd_infer/inference.pdiparams models/runtime/1/model.pdiparams
# 拉取fastdeploy镜像
# GPU镜像
docker pull paddlepaddle/fastdeploy:0.3.0-gpu-cuda11.4-trt8.4-21.10
docker pull paddlepaddle/fastdeploy:0.6.0-gpu-cuda11.4-trt8.4-21.10
# CPU镜像
docker pull paddlepaddle/fastdeploy:0.3.0-cpu-only-21.10
docker pull paddlepaddle/fastdeploy:0.6.0-cpu-only-21.10
# 运行容器.容器名字为 fd_serving, 并挂载当前目录为容器的 /serving 目录
nvidia-docker run -it --net=host --name fd_serving -v `pwd`/:/serving paddlepaddle/fastdeploy:0.3.0-gpu-cuda11.4-trt8.4-21.10 bash
nvidia-docker run -it --net=host --name fd_serving -v `pwd`/:/serving paddlepaddle/fastdeploy:0.6.0-gpu-cuda11.4-trt8.4-21.10 bash
# 启动服务(不设置CUDA_VISIBLE_DEVICES环境变量，会拥有所有GPU卡的调度权限)
CUDA_VISIBLE_DEVICES=0 fastdeployserver --model-repository=/serving/models --backend-config=python,shm-default-byte-size=10485760

6
examples/vision/detection/yolov5/serving/README.md
View File

@@ -14,13 +14,13 @@ wget https://bj.bcebos.com/paddlehub/fastdeploy/yolov5s.onnx
mv yolov5s.onnx models/runtime/1/model.onnx
# 拉取fastdeploy镜像
docker pull paddlepaddle/fastdeploy:0.3.0-gpu-cuda11.4-trt8.4-21.10
docker pull paddlepaddle/fastdeploy:0.6.0-gpu-cuda11.4-trt8.4-21.10
# 运行容器.容器名字为 fd_serving, 并挂载当前目录为容器的 /yolov5_serving 目录
nvidia-docker run -it --net=host --name fd_serving -v `pwd`/:/yolov5_serving paddlepaddle/fastdeploy:0.3.0-gpu-cuda11.4-trt8.4-21.10 bash
nvidia-docker run -it --net=host --name fd_serving -v `pwd`/:/yolov5_serving paddlepaddle/fastdeploy:0.6.0-gpu-cuda11.4-trt8.4-21.10 bash
# 启动服务(不设置CUDA_VISIBLE_DEVICES环境变量，会拥有所有GPU卡的调度权限)
CUDA_VISIBLE_DEVICES=0 fastdeployserver --model-repository=models --backend-config=python,shm-default-byte-size=10485760
CUDA_VISIBLE_DEVICES=0 fastdeployserver --model-repository=/yolov5_serving/models --backend-config=python,shm-default-byte-size=10485760
```
>> **注意**: 当出现"Address already in use", 请使用`--grpc-port`指定端口号来启动服务，同时更改yolov5_grpc_client.py中的请求端口号

4
examples/vision/detection/yolov5/serving/README_EN.md
View File

@@ -10,10 +10,10 @@ wget https://bj.bcebos.com/paddlehub/fastdeploy/yolov5s.onnx
mv yolov5s.onnx models/infer/1/
# Pull fastdeploy image
docker pull paddlepaddle/fastdeploy:0.3.0-gpu-cuda11.4-trt8.4-21.10
docker pull paddlepaddle/fastdeploy:0.6.0-gpu-cuda11.4-trt8.4-21.10
# Run the docker. The docker name is fd_serving, and the current directory is mounted as the docker's /yolov5_serving directory
nvidia-docker run -it --net=host --name fd_serving -v `pwd`/:/yolov5_serving paddlepaddle/fastdeploy:0.3.0-gpu-cuda11.4-trt8.4-21.10 bash
nvidia-docker run -it --net=host --name fd_serving -v `pwd`/:/yolov5_serving paddlepaddle/fastdeploy:0.6.0-gpu-cuda11.4-trt8.4-21.10 bash
# Start the service (Without setting the CUDA_VISIBLE_DEVICES environment variable, it will have scheduling privileges for all GPU cards)
CUDA_VISIBLE_DEVICES=0 fastdeployserver --model-repository=models --backend-config=python,shm-default-byte-size=10485760

2
serving/Dockerfile
View File

@@ -33,7 +33,7 @@ RUN apt-get update \
&& apt-get update && apt-get install -y --no-install-recommends datacenter-gpu-manager=1:2.2.9
RUN apt-get update \
&& apt-get install -y --no-install-recommends libre2-5 libb64-0d python3 python3-pip libarchive-dev \
&& apt-get install -y --no-install-recommends libre2-5 libb64-0d python3 python3-pip libarchive-dev ffmpeg libsm6 libxext6 \
&& python3 -m pip install -U pip \
&& python3 -m pip install paddlepaddle-gpu paddlenlp faster_tokenizer

2
serving/Dockerfile_cpu
View File

@@ -17,7 +17,7 @@ FROM paddlepaddle/fastdeploy:22.09-cpu-only-min
ENV TZ=Asia/Shanghai \
DEBIAN_FRONTEND=noninteractive
RUN apt-get update && apt-get install -y --no-install-recommends apt-utils libgomp1 \
RUN apt-get update && apt-get install -y --no-install-recommends apt-utils libgomp1 ffmpeg libsm6 libxext6 \
&& python3 -m pip install -U pip \
&& python3 -m pip install paddlepaddle paddlenlp faster_tokenizer

14
serving/README_CN.md
View File

@@ -17,13 +17,13 @@ FastDeploy基于[Triton Inference Server](https://github.com/triton-inference-se
#### CPU镜像
CPU镜像仅支持Paddle/ONNX模型在CPU上进行服务化部署，支持的推理后端包括OpenVINO、Paddle Inference和ONNX Runtime
``` shell
docker pull paddlepaddle/fastdeploy:0.3.0-cpu-only-21.10
docker pull paddlepaddle/fastdeploy:0.6.0-cpu-only-21.10
```
#### GPU镜像
GPU镜像支持Paddle/ONNX模型在GPU/CPU上进行服务化部署，支持的推理后端包括OpenVINO、TensorRT、Paddle Inference和ONNX Runtime
```
docker pull paddlepaddle/fastdeploy:0.3.0-gpu-cuda11.4-trt8.4-21.10
docker pull paddlepaddle/fastdeploy:0.6.0-gpu-cuda11.4-trt8.4-21.10
```
用户也可根据自身需求，参考如下文档自行编译镜像
@@ -33,4 +33,12 @@ docker pull paddlepaddle/fastdeploy:0.3.0-gpu-cuda11.4-trt8.4-21.10
- [服务化模型目录说明](docs/zh_CN/model_repository.md) (说明如何准备模型目录)
- [服务化部署配置说明](docs/zh_CN/model_configuration.md) (说明runtime的配置选项)
- [服务化部署示例](docs/zh_CN/demo.md)
- [YOLOV5 检测任务](../examples/vision/detection/yolov5/serving/README.md)
### 模型示例列表
| 任务场景 | 模型 |
|---|---|
| Classification | [PaddleClas](../examples/vision/classification/paddleclas/serving/README.md) |
| Detection | [ultralytics/YOLOv5](../examples/vision/detection/yolov5/serving/README.md) |
| NLP | [PaddleNLP/ERNIE-3.0](../examples/text/ernie-3.0/serving/README.md)|
| Speech | [PaddleSpeech/PP-TTS](../examples/audio/pp-tts/serving/README.md)|

13
serving/README_EN.md
View File

@@ -20,7 +20,7 @@ FastDeploy builds an end-to-end serving deployment based on [Triton Inference Se
CPU images only support Paddle/ONNX models for serving deployment on CPUs, and supported inference backends include OpenVINO, Paddle Inference, and ONNX Runtime
```shell
docker pull paddlepaddle/fastdeploy:0.3.0-cpu-only-21.10
docker pull paddlepaddle/fastdeploy:0.6.0-cpu-only-21.10
```
#### GPU Image
@@ -28,7 +28,7 @@ docker pull paddlepaddle/fastdeploy:0.3.0-cpu-only-21.10
GPU images support Paddle/ONNX models for serving deployment on GPU and CPU, and supported inference backends including OpenVINO, TensorRT, Paddle Inference, and ONNX Runtime
```
docker pull paddlepaddle/fastdeploy:0.3.0-gpu-cuda11.4-trt8.4-21.10
docker pull paddlepaddle/fastdeploy:0.6.0-gpu-cuda11.4-trt8.4-21.10
```
Users can also compile the image by themselves according to their own needs, referring to the following documents:
@@ -41,3 +41,12 @@ Users can also compile the image by themselves according to their own needs, ref
- [Serving Deployment Configuration for Runtime](docs/zh_CN/model_configuration.md)
- [Serving Deployment Demo](docs/zh_CN/demo.md)
- [YOLOV5 - Detection Task](../examples/vision/detection/yolov5/serving/README.md)
### Model List
| Task | Model |
|---|---|
| Classification | [PaddleClas](../examples/vision/classification/paddleclas/serving/README.md) |
| Detection | [ultralytics/YOLOv5](../examples/vision/detection/yolov5/serving/README.md) |
| NLP | [PaddleNLP/ERNIE-3.0](../examples/text/ernie-3.0/serving/README.md)|
| Speech | [PaddleSpeech/PP-TTS](../examples/audio/pp-tts/serving/README.md)|

6
serving/docs/EN/compile-en.md
View File

@@ -13,7 +13,7 @@ bash scripts/build.sh
# Exit to the FastDeploy home directory and create the image
cd ../
docker build -t paddlepaddle/fastdeploy:0.3.0-gpu-cuda11.4-trt8.4-21.10 -f serving/Dockerfile .
docker build -t paddlepaddle/fastdeploy:0.6.0-gpu-cuda11.4-trt8.4-21.10 -f serving/Dockerfile .
```
## CPU Image
@@ -26,7 +26,7 @@ bash scripts/build.sh OFF
# Exit to the FastDeploy home directory and create the image
cd ../
docker build -t paddlepaddle/fastdeploy:0.3.0-cpu-only-21.10 -f serving/Dockerfile_cpu .
docker build -t paddlepaddle/fastdeploy:0.6.0-cpu-only-21.10 -f serving/Dockerfile_cpu .
```
## IPU Image
@@ -38,5 +38,5 @@ bash scripts/build_fd_ipu.sh
# Exit to the FastDeploy home directory and create the image
cd ../
docker build -t paddlepaddle/fastdeploy:0.3.0-ipu-only-21.10 -f serving/Dockerfile_ipu .
docker build -t paddlepaddle/fastdeploy:0.6.0-ipu-only-21.10 -f serving/Dockerfile_ipu .
```

6
serving/docs/zh_CN/compile.md
View File

@@ -13,7 +13,7 @@ bash scripts/build.sh
# 退出到FastDeploy主目录，制作镜像
cd ../
docker build -t paddlepaddle/fastdeploy:0.3.0-gpu-cuda11.4-trt8.4-21.10 -f serving/Dockerfile .
docker build -t paddlepaddle/fastdeploy:0.6.0-gpu-cuda11.4-trt8.4-21.10 -f serving/Dockerfile .
```
## 制作CPU镜像
@@ -25,7 +25,7 @@ bash scripts/build.sh OFF
# 退出到FastDeploy主目录，制作镜像
cd ../
docker build -t paddlepaddle/fastdeploy:0.3.0-cpu-only-21.10 -f serving/Dockerfile_cpu .
docker build -t paddlepaddle/fastdeploy:0.6.0-cpu-only-21.10 -f serving/Dockerfile_cpu .
```
## 制作IPU镜像
@@ -37,5 +37,5 @@ bash scripts/build_fd_ipu.sh
# 退出到FastDeploy主目录，制作镜像
cd ../
docker build -t paddlepaddle/fastdeploy:0.3.0-ipu-only-21.10 -f serving/Dockerfile_ipu .
docker build -t paddlepaddle/fastdeploy:0.6.0-ipu-only-21.10 -f serving/Dockerfile_ipu .
```

7
serving/scripts/build.sh
View File

@@ -30,7 +30,7 @@ if [ ! -d "./TensorRT-8.4.1.5/" ]; then
rm -rf TensorRT-8.4.1.5.Linux.x86_64-gnu.cuda-11.6.cudnn8.4.tar.gz
fi
nvidia-docker run -it --rm --name build_fd_vison \
nvidia-docker run -it --rm --name build_fd \
-v`pwd`/..:/workspace/fastdeploy \
nvcr.io/nvidia/tritonserver:21.10-py3-min \
bash -c \
@@ -50,7 +50,8 @@ nvidia-docker run -it --rm --name build_fd_vison \
export ENABLE_TEXT=ON;
python setup.py build;
python setup.py bdist_wheel;
cd ../;rm -rf build; mkdir -p build;cd build;
cd /workspace/fastdeploy;
rm -rf build; mkdir -p build;cd build;
cmake .. -DENABLE_TRT_BACKEND=ON -DCMAKE_INSTALL_PREFIX=${PWD}/fastdeploy_install -DWITH_GPU=ON -DTRT_DIRECTORY=/workspace/fastdeploy/serving/TensorRT-8.4.1.5/ -DENABLE_PADDLE_BACKEND=ON -DENABLE_ORT_BACKEND=ON -DENABLE_OPENVINO_BACKEND=ON -DENABLE_VISION=OFF -DBUILD_FASTDEPLOY_PYTHON=OFF -DENABLE_PADDLE_FRONTEND=ON -DENABLE_TEXT=OFF -DLIBRARY_NAME=fastdeploy_runtime;
make -j`nproc`;
make install;
@@ -65,7 +66,7 @@ else
echo "start build FD CPU library"
docker run -it --rm --name build_fd_vison \
docker run -it --rm --name build_fd \
-v`pwd`/..:/workspace/fastdeploy \
paddlepaddle/fastdeploy:21.10-cpu-only-buildbase \
bash -c \