apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-19 06:54:41 +08:00
Code Issues Actions 3 Packages Projects Releases Wiki Activity

[Backend] Add Huawei Ascend NPU deploy using PaddleLite CANN. (#757)

Browse Source 
* Add Huawei Ascend NPU deploy through PaddleLite CANN

* Add NNAdapter interface for paddlelite

* Modify Huawei Ascend Cmake

* Update way for compiling Huawei Ascend NPU deployment

* remove UseLiteBackend in UseCANN

* Support compile python whlee

* Change names of nnadapter API

* Add nnadapter pybind and remove useless API

* Support Python deployment on Huawei Ascend NPU

* Add models suppor for ascend

* Add PPOCR rec reszie for ascend

* fix conflict for ascend

* Rename CANN to Ascend

* Rename CANN to Ascend

* Improve ascend

* fix ascend bug

* improve ascend docs

* improve ascend docs

* improve ascend docs

* Improve Ascend

* Improve Ascend

* Move ascend python demo

* Imporve ascend

* Improve ascend

* Improve ascend

* Improve ascend

* Improve ascend

* Imporve ascend

* Imporve ascend

* Improve ascend
This commit is contained in:
yunyaoXYY
2022-12-26 10:18:34 +08:00
committed by GitHub
parent 2d3d941372
commit d45382e3cc
42 changed files with 714 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
fastdeploy/backends/lite/lite_backend.cc
View File

@@ -89,6 +89,42 @@ void LiteBackend::BuildOption(const LiteBackendOption& option) {
paddle::lite_api::Place{TARGET(kNNAdapter), PRECISION(kFloat)});
valid_places.push_back(
paddle::lite_api::Place{TARGET(kARM), PRECISION(kInt8)});
}
if(option_.enable_ascend){
if(option_.nnadapter_device_names.empty()){
config_.set_nnadapter_device_names({"huawei_ascend_npu"});
} else {
config_.set_nnadapter_device_names(option_.nnadapter_device_names);
}
if(!option_.nnadapter_context_properties.empty()){
config_.set_nnadapter_context_properties(option_.nnadapter_context_properties);
}
if(!option_.nnadapter_model_cache_dir.empty()){
config_.set_nnadapter_model_cache_dir(option_.nnadapter_model_cache_dir);
}
if(!option_.nnadapter_mixed_precision_quantization_config_path.empty()){
config_.set_nnadapter_mixed_precision_quantization_config_path(
option_.nnadapter_mixed_precision_quantization_config_path
);
}
if(!option_.nnadapter_subgraph_partition_config_path.empty()){
config_.set_nnadapter_subgraph_partition_config_path(
option_.nnadapter_subgraph_partition_config_path
);
}
valid_places.push_back(
paddle::lite_api::Place{TARGET(kNNAdapter), PRECISION(kInt8)});
valid_places.push_back(
paddle::lite_api::Place{TARGET(kNNAdapter), PRECISION(kFloat)});
valid_places.push_back(
paddle::lite_api::Place{TARGET(kARM), PRECISION(kInt8)});
}
if(option_.enable_xpu){

8
fastdeploy/backends/lite/lite_backend.h
View File

@@ -44,7 +44,15 @@ struct LiteBackendOption {
// TODO(qiuyanjun): support more options for lite backend.
// Such as fp16, different device target (kARM/kXPU/kNPU/...)
std::string nnadapter_subgraph_partition_config_path = "";
std::string nnadapter_subgraph_partition_config_buffer = "";
std::string nnadapter_context_properties = "";
std::string nnadapter_model_cache_dir = "";
std::string nnadapter_mixed_precision_quantization_config_path = "";
std::map<std::string, std::vector<std::vector<int64_t>>>
nnadapter_dynamic_shape_info = {{"", {{0}}}};
std::vector<std::string> nnadapter_device_names = {};
bool enable_timvx = false;
bool enable_ascend = false;
bool enable_xpu = false;
int device_id = 0;
int xpu_l3_workspace_size = 0xfffc00;