apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-18 14:40:44 +08:00
Code Issues Actions 6 Packages Projects Releases Wiki Activity

[Backend] Support Intel GPU with heterogeneous mode (#701)

Browse Source 
* Add some comments for python api

* support openvino gpu

* Add cpu operators

* add interface to specify hetero operators

* remove useless dir

* format code

* remove debug code

* Support GPU for ONNX
This commit is contained in:
Jason
2022-11-25 19:40:56 +08:00
committed by GitHub
parent ad5c9c08b2
commit 5b3fd9dd88
7 changed files with 156 additions and 44 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
fastdeploy/pybind/runtime.cc
View File

@@ -34,6 +34,8 @@ void BindRuntime(pybind11::module& m) {
.def("use_lite_backend", &RuntimeOption::UseLiteBackend)
.def("set_paddle_mkldnn", &RuntimeOption::SetPaddleMKLDNN)
.def("set_openvino_device", &RuntimeOption::SetOpenVINODevice)
.def("set_openvino_shape_info", &RuntimeOption::SetOpenVINOShapeInfo)
.def("set_openvino_cpu_operators", &RuntimeOption::SetOpenVINOCpuOperators)
.def("enable_paddle_log_info", &RuntimeOption::EnablePaddleLogInfo)
.def("disable_paddle_log_info", &RuntimeOption::DisablePaddleLogInfo)
.def("set_paddle_mkldnn_cache_size",