apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-05 16:48:03 +08:00
Code Issues Actions 2 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

52
fastdeploy/runtime.h
View File

@@ -116,6 +116,9 @@ struct FASTDEPLOY_DECL RuntimeOption {
/// Use TimVX to inference
void UseTimVX();
/// Use Huawei Ascend to inference
void UseAscend();
///
/// \brief Turn on XPU.
///
@@ -235,11 +238,48 @@ struct FASTDEPLOY_DECL RuntimeOption {
void SetLiteOptimizedModelDir(const std::string& optimized_model_dir);
/**
* @brief Set nnadapter subgraph partition path for Paddle Lite backend.
* @brief Set subgraph partition path for Paddle Lite backend.
*/
void SetLiteSubgraphPartitionPath(
const std::string& nnadapter_subgraph_partition_config_path);
/**
* @brief Set subgraph partition path for Paddle Lite backend.
*/
void SetLiteSubgraphPartitionConfigBuffer(
const std::string& nnadapter_subgraph_partition_config_buffer);
/**
* @brief Set device name for Paddle Lite backend.
*/
void SetLiteDeviceNames(
const std::vector<std::string>& nnadapter_device_names);
/**
* @brief Set context properties for Paddle Lite backend.
*/
void SetLiteContextProperties(
const std::string& nnadapter_context_properties);
/**
* @brief Set model cache dir for Paddle Lite backend.
*/
void SetLiteModelCacheDir(
const std::string& nnadapter_model_cache_dir);
/**
* @brief Set dynamic shape info for Paddle Lite backend.
*/
void SetLiteDynamicShapeInfo(
const std::map<std::string, std::vector<std::vector<int64_t>>>&
nnadapter_dynamic_shape_info);
/**
* @brief Set mixed precision quantization config path for Paddle Lite backend.
*/
void SetLiteMixedPrecisionQuantizationConfigPath(
const std::string& nnadapter_mixed_precision_quantization_config_path);
/**
* @brief enable half precision while use paddle lite backend
*/
@@ -398,7 +438,17 @@ struct FASTDEPLOY_DECL RuntimeOption {
// optimized model dir for CxxConfig
std::string lite_optimized_model_dir = "";
std::string lite_nnadapter_subgraph_partition_config_path = "";
// and other nnadapter settings for CxxConfig
std::string lite_nnadapter_subgraph_partition_config_buffer = "";
std::string lite_nnadapter_context_properties = "";
std::string lite_nnadapter_model_cache_dir = "";
std::string lite_nnadapter_mixed_precision_quantization_config_path = "";
std::map<std::string, std::vector<std::vector<int64_t>>>
lite_nnadapter_dynamic_shape_info = {{"", {{0}}}};
std::vector<std::string> lite_nnadapter_device_names = {};
bool enable_timvx = false;
bool enable_ascend = false;
bool enable_xpu = false;
// ======Only for Trt Backend=======