diff --git a/README.md b/README.md index 066f4bb..43172ea 100644 --- a/README.md +++ b/README.md @@ -1,51 +1,55 @@ # AI Engine Direct Helper +## We used a new name 'QAI AppBuilder' instead of 'qnnhelper' + ## Introduction +#### QNN SDK Qualcomm® AI Engine Direct is designed to provide unified, low-level APIs for AI development. Qualcomm® AI Engine Direct is also referred to as *QNN* in the source and documentation. The QNN SDK can be downloaded from Qualcomm software center:
-https://softwarecenter.qualcomm.com/#/catalog/item/a0844287-db23-11ed-a260-063166a9270b
+https://softwarecenter.qualcomm.com/#/catalog/item/a0844287-db23-11ed-a260-063166a9270b?type=Tool
Or from QPM [this option expected to be deprecated soon]
https://qpm.qualcomm.com/#/main/tools/details/qualcomm_ai_engine_direct -AI Engine Direct Helper(this repository) is also referred to as *QNNHelper* in the source and documentation. QNNHelper is extension for QNN SDK. We need some libraries in QNN SDK for using QNNHelper.
-QNNHelper is designed for developer to using QNN SDK to execute model on Windows on Snapdragon(WoS) platforms more easily. We encapsulated QNN SDK APIs to several simple APIs into QNNHelper for loading the models to CPU or HTP, running inference and releasing the resource. +#### QAI AppBuilder +AI Engine Direct Helper(this repository) is also referred to as *QAI AppBuilder* in the source and documentation. QAI AppBuilder is extension for QNN SDK. We need some libraries in QNN SDK for using QAI AppBuilder.
+QAI AppBuilder is designed for developer to using QNN SDK to execute model on Windows on Snapdragon(WoS) platforms easily. We encapsulated QNN SDK APIs to several simple APIs for loading the models to CPU or HTP and executing inference. ## Advantage -Developers can use these helper libraries for C++ & Python to call functions within the SDK.
+Developers can use QAI AppBuilder in both C++ and Python projects
• Support both C++ & Python
• Support multiple models.
• Support multiple inputs & outputs.
-• Support multiple processes.
• Easier for developing apps.
• Faster for testing models.
Using the Python extensions with ARM64 Python will make it easier for developers to build GUI app for Windows on Snapdragon(WoS) platforms. Python 3.11.5 ARM64 version has support for following modules: PyQt6, OpenCV, Numpy, PyTorch*, Torchvision*, ONNX*. Developers can design apps that benefit from rich Python ecosystem.
**PyTorch, Torchvision, ONNX, ONNX Runtime: need to compile from source code.* +**Also support x64 Python.* ## Components -There're two ways to use QNNHelper: -### 1. Using the QNNHelper C++ libraries to develop C++ based AI application. -Download prebuild binary package *QNNHelper-win_arm64-{QNN SDK version}-Release.zip* to get these files: https://github.com/quic/ai-engine-direct-helper/releases +There're two ways to use QAI AppBuilder: +### 1. Using the QAI AppBuilder C++ libraries to develop C++ based AI application. +Download prebuild binary package *QAI_AppBuilder-win_arm64-{QNN SDK version}-Release.zip* to get these files: https://github.com/quic/ai-engine-direct-helper/releases -**libqnnhelper.dll {libqnnhelper.lib, LibQNNHelper.hpp}** –– C++ projects can use this lib to run models in HTP. -**SvcQNNHelper.exe** –– Due to HTP limitations, we can only load models smaller than 4GB in one process. This app is used to help us load the models in new processes(Multiple processes can be created) and inference to avoid HTP restrictions. +**libappbuilder.dll {libappbuilder.lib, LibAppBuilder.hpp}** –– C++ projects can use this lib to run models in HTP. +**QAIAppSvc.exe** –– Due to HTP limitations, we can only load models smaller than 4GB in one process. This app is used to help us load the models in new processes(Multiple processes can be created) and inference to avoid HTP restrictions. -### 2. Using the QNNHelper Python binding extension to develop Python based AI application. -Download Python extension *qnnhelper-{version}-cp311-cp311-win_arm64.whl* and install it with the command below: +### 2. Using the QAI AppBuilder Python binding extension to develop Python based AI application. +Download Python extension *qai_appbuilder-{version}-cp311-cp311-win_arm64.whl* and install it with the command below: https://github.com/quic/ai-engine-direct-helper/releases ``` -pip install qnnhelper-2.23.0-cp311-cp311-win_arm64.whl +pip install qai_appbuilder-2.24.0-cp311-cp311-win_arm64.whl ``` ## User Guide -Please refere to [User Guide](Docs/User_Guide.md) on how to use QNNHelper in your project. +Please refere to [User Guide](docs/user_guide.md) on how to use QAI AppBuilder in your project. ## Build Build project with Visual Studio 2022 on WoS device:
-- Set environment 'QNN_SDK_ROOT' to the QNN SDK path which you're using. E.g.: QNN_SDK_ROOT = "C:\\Qualcomm\\AIStack\\QAIRT\\2.23.0.240531\\" +- Set environment 'QNN_SDK_ROOT' to the QNN SDK path which you're using. E.g.: Set QNN_SDK_ROOT = "C:\\Qualcomm\\AIStack\\QAIRT\\2.24.0.240626\\" - Install Visual Studio 2022: - https://docs.qualcomm.com/bundle/publicresource/topics/80-62010-1/Install-Visual-Studio-2022.html?product=Windows%20on%20Snapdragon - Install Python-3.11.5 ARM64: @@ -54,7 +58,7 @@ Build project with Visual Studio 2022 on WoS device:
``` pip install wheel setuptools pybind11 ``` -- Download pybind11 repository to 'ai-engine-direct-helper\PyQNNHelper\pybind11': +- Download pybind11 repository to 'ai-engine-direct-helper\pybind\pybind11': - https://github.com/pybind/pybind11.git - Use the commands below to build and install Python extension(*.whl): ``` @@ -62,8 +66,8 @@ cd C:\Source\ai-engine-direct-helper python setup.py bdist_wheel # Install the extension: -pip install dist\qnnhelper-2.23.0-cp311-cp311-win_arm64.whl +pip install dist\qai_appbuilder-2.24.0-cp311-cp311-win_arm64.whl ``` ## License -QNNHelper is licensed under the BSD 3-clause "New" or "Revised" License. Check out the [LICENSE](LICENSE) for more details. +QAI AppBuilder is licensed under the BSD 3-clause "New" or "Revised" License. Check out the [LICENSE](LICENSE) for more details.