apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-06 00:57:33 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[Hackthon_4th 244] Added Paddle Lite GPU Backend (#1907)

Browse Source 
* [improved] enum; ConfigureGpu();

* [improved] init()

* [improved] valid place; model dir; is valid;

* [added] WITH_OPENCL in cmake

* [improved] set model; valid place; cmake url; cmake option;

* Update runtime_option.cc

---------

Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
This commit is contained in:
unseenme
2023-05-12 20:44:27 +09:00
committed by GitHub
parent 15c29f7e49
commit 3fd21c935e
10 changed files with 70 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
fastdeploy/runtime/enum_variables.h
View File

@@ -35,7 +35,7 @@ enum Backend {
PDINFER, ///< Paddle Inference, support Paddle format model, CPU / Nvidia GPU
POROS, ///< Poros, support TorchScript format model, CPU / Nvidia GPU
OPENVINO, ///< Intel OpenVINO, support Paddle/ONNX format, CPU only
LITE, ///< Paddle Lite, support Paddle format model, ARM CPU only
LITE, ///< Paddle Lite, support Paddle format model, ARM CPU / ARM GPU
RKNPU2, ///< RKNPU2, support RKNN format model, Rockchip NPU only
SOPHGOTPU, ///< SOPHGOTPU, support SOPHGO format model, Sophgo TPU only
HORIZONNPU, ///< HORIZONNPU, support Horizon format model, Horizon NPU
@@ -93,7 +93,8 @@ static std::map<Device, std::vector<Backend>>
s_default_backends_by_device = {
{Device::CPU, {Backend::LITE, Backend::PDINFER, Backend::ORT,
Backend::OPENVINO, Backend::POROS}},
{Device::GPU, {Backend::PDINFER, Backend::ORT, Backend::TRT, Backend::POROS}},
{Device::GPU, {Backend::LITE, Backend::PDINFER, Backend::ORT,
Backend::TRT, Backend::POROS}},
{Device::RKNPU, {Backend::RKNPU2}},
{Device::SUNRISENPU, {Backend::HORIZONNPU}},
{Device::IPU, {Backend::PDINFER}},