Files
FastDeploy/docs/en/build_and_install
yeliang2258 45865c8724 [Other] Change all XPU to KunlunXin (#973)
* [FlyCV] Bump up FlyCV -> official release 1.0.0

* XPU to KunlunXin

* update

* update model link

* update doc

* update device

* update code

* useless code

Co-authored-by: DefTruth <qiustudent_r@163.com>
Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
2022-12-27 10:02:02 +08:00
..

English | 中文

Install FastDeploy - Tutorials

Install Prebuilt FastDeploy

Build FastDeploy and Install

Build options

option description
ENABLE_ORT_BACKEND Default OFF, whether to enable ONNX Runtime backend(CPU/GPU)
ENABLE_PADDLE_BACKEND Default OFFwhether to enable Paddle Inference backend(CPU/GPU)
ENABLE_TRT_BACKEND Default OFFwhether to enable TensorRT backend(GPU)
ENABLE_OPENVINO_BACKEND Default OFFwhether to enable OpenVINO backend(CPU)
ENABLE_VISION Default OFFwhether to enable vision models deployment module
ENABLE_TEXT Default OFFwhether to enable text models deployment module
WITH_GPU Default OFF, if build on GPU, this needs to be ON
WITH_KUNLUNXIN Default OFFif deploy on KunlunXin XPUthis needs to be ON
WITH_TIMVX Default OFFif deploy on RV1126/RV1109/A311Dthis needs to be ON
WITH_ASCEND Default OFFif deploy on Huawei Ascendthis needs to be ON
CUDA_DIRECTORY Default /usr/local/cuda, if build on GPU, this defines the path of CUDA(>=11.2)
TRT_DIRECTORY If build with ENABLE_TRT_BACKEND=ON, this defines the path of TensorRT(>=8.4)
ORT_DIRECTORY [Optional] If build with ENABLE_ORT_BACKEND=ON, this flag defines the path of ONNX Runtime, but if this flag is not set, it will download ONNX Runtime library automatically
OPENCV_DIRECTORY [Optional] If build with ENABLE_VISION=ON, this flag defines the path of OpenCV, but if this flag is not set, it will download OpenCV library automatically
OPENVINO_DIRECTORY [Optional] If build WITH ENABLE_OPENVINO_BACKEND=ON, this flag defines the path of OpenVINO, but if this flag is not set, it will download OpenVINO library automatically