# Overview Qualcomm^®^ Linux AI stack allows developers to optimally deploy pre-trained, deep learning models on Qualcomm hardware accelerators, such as Neural Processing Unit (NPU), Graphic Processing Unit (GPU), and Central Processing Unit (CPU). Qualcomm AI software offering contains software development kits (SDKs), APIs, sample applications, development tools, and third-party frameworks support such as GStreamer and TFLite, to ease application development. Page-1 Sheet.1313 Sheet.1218 Hardware Hardware Sheet.1219 AI SDKs AI SDKs Sheet.1220 Qualcomm IMSDK Gstreamer plugins Qualcomm IMSDK Gstreamer plugins Sheet.1221 AI applications AI applications Sheet.1222 Qualcomm® Neural Processing Engine plugin (qtimlsnpe) Qualcomm® Neural Processing Engine plugin (qtimlsnpe) Sheet.1223 Qualcomm Neural Processing Engine Qualcomm Neural Processing Engine Sheet.1224 Qualcomm® AI Engine Direct plugin (qtimlqnn) Qualcomm® AI Engine Direct plugin (qtimlqnn) Sheet.1225 TensorFlow Lite plugin (qtimltflite) TensorFlow Lite plugin (qtimltflite) Sheet.1226 NPU (DSP/HMX/HTP) NPU (DSP/HMX/HTP) Sheet.1227 GPU GPU Sheet.1228 CPU CPU Sheet.1229 Sheet.1230 Sheet.1231 Sheet.1233 Qualcomm AI Engine Direct Qualcomm AI Engine Direct Sheet.1234 Sheet.1235 Sheet.1240 TFLite Delegate TFLite Delegate Sheet.1244 Sheet.1310 Sheet.1311 Sheet.1312 Sheet.1314 Qualcomm Qualcomm Sheet.1315 Hardware Hardware Sheet.1316 Third-party Third-party **Top-level AI hardware and software blocks of the Qualcomm Linux AI stack** The key components of the Qualcomm Linux AI stack are: - **AI applications** - Sample applications based on Gstreamer that can be used or customized as needed. - **GStreamer plugins** - Qualcomm Linux software offers GStreamer-based, machine learning plugins for accelerating AI inference using TFLite, Qualcomm^®^ Neural Processing Engine SDK, etc., along with GStreamer plugins for pre- and postprocessing. - **Qualcomm AI Stack** consists of two SDKs to accelerate AI workloads. The **Qualcomm Neural Processing Engine SDK** and **Qualcomm AI Engine Direct** provide tools, libraries, etc., to optimally accelerate AI models on multiple hardware accelerators. - Qualcomm SoCs offer three **hardware cores** for AI loads. - **Neural Processing Unit (NPU)** - Also referred to as Qualcomm® Hexagon™ Tensor Processor (HTP) or DSP/HMX, is suitable for executing AI workloads with low-power and high-performance. To get optimized performance, pre-trained models need be quantized to one of the supported precisions. - **Graphics Processing Unit (GPU)** - Qualcomm® Adreno™ GPU is suitable for executing AI workloads with medium-power, and medium-performance. AI workloads are accelerated with OpenCL kernels. The GPU can also be used to accelerate model pre/post processing. - **Central Processing Unit (CPU)** - AI inferencing on the CPU can be used to benchmark model accuracy/performance against other hardware accelerators. The CPU can also be used to run model pre/post processing. ## Architecture The Qualcomm AI offering consists of hardware accelerators and AI SDKs to harness the power of hardware. Page-1 Sheet.61 Sheet.38 Sheet.1 Backend libraries Backend libraries Sheet.4 Sheet.5 Qualcomm AI Engine Direct API Qualcomm AIEngine Direct API Sheet.6 Kernels Kernels Sheet.7 OpenCL OpenCL Sheet.9 Sheet.10 Qualcomm AI Engine Direct API Qualcomm AIEngine Direct API Sheet.11 QML QML Sheet.12 Neon Neon Sheet.14 Sheet.15 Qualcomm AI Engine Direct API Qualcomm AIEngine Direct API Sheet.16 HTP core HTP core Sheet.17 HMX/HVX HMX/HVX Sheet.18 Hardware IP cores Hardware IP cores Sheet.19 NPU (DSP/HMX/HTP) NPU (DSP/HMX/HTP) Sheet.20 GPU GPU Sheet.21 CPU CPU Sheet.35 Sheet.27 TensorFlow TensorFlow Sheet.28 LiteRT LiteRT Sheet.29 ONNX ONNX Sheet.30 PyTorch PyTorch Sheet.31 .pb .pb Sheet.32 .tflite .tflite Sheet.33 .onnx .onnx Sheet.34 .ts .ts Sheet.36 Sheet.37 Sheet.39 Sheet.40 Sheet.22 ML runtime frameworks, applications ML runtime frameworks, applications Sheet.52 Qualcomm Neural Processing SDK Qualcomm Neural Processing SDK Sheet.53 LiteRT LiteRT Sheet.54 ONNX RT ONNX RT Sheet.55 Other ML frameworks OtherMLframeworks Sheet.59 Sheet.62 Sheet.63 Sheet.64 Sheet.65 Qualcomm Qualcomm Sheet.66 Hardware Hardware Sheet.67 Third-party Third-party Sheet.68 Sheet.69 Open source Open source ### AI hardware accelerators AI workloads can be accelerated on multiple hardware cores: - Qualcomm^®^ Hexagon™ Tensor Processor (HTP) - Also known as NPU/DSP/HMX, suitable to execute AI workloads with low-power and high-performance. For optimized performance, pre-trained models need be quantized to one of the supported precisions. - Qualcomm^®^ Adreno™ GPU - Suitable to execute AI workloads with medium-power, and medium-performance. AI workloads are accelerated with OpenCL kernels. The GPU can also be used to accelerate model pre/post-processing. - Qualcomm^®^ Kryo™ CPU - AI inferencing on CPU can be used to benchmark model accuracy/performance against other hardware accelerators. The CPU can also be used to run model pre/post processing. ### AI software stack AI stack contains SDKs to harness the power of AI hardware accelerators. Developers can use the stack of their choice to deploy AI workloads. Pre-trained models (with the exception of TFLite models) need to be converted to an executable format with the selected AI Stack SDK before running them. Note that TFLite Delegate allows developers to directly run TFLite models. - [Qualcomm Neural Processing Engine (SNPE)](https://docs.qualcomm.com/bundle/publicresource/topics/80-63442-2) An all-in-one SDK that provides C, C++, and Java APIs to support heterogenous computing, system-level configurations, and direct AI workloads to all accelerator cores. Provides developers with flexibility, including inter-core collaboration support and other advanced features. - [Qualcomm AI Engine Direct (QNN)](https://docs.qualcomm.com/bundle/publicresource/topics/80-63442-50) Lower-level, highly customizable unified APIs that speed up AI models on all AI accelerator cores with individual libraries. Can be used directly to target a specific accelerator core or delegate workloads from popular runtimes including Qualcomm Neural Processing Engine SDK, TensorFlow Lite, and ONNX runtime. Low-level SDK provides more functionality and debugging abilities. - [AI Model Efficiency Toolkit (AIMET)](https://quic.github.io/aimet-pages/releases/latest/index.html) Open-source library to optimize (compressing and quantizing) trained neural network models. This is a complex SDK designed to generate optimized quantized models. It is intended only for advanced developers. References | Title | Number | | --- | --- | | [AI Hub](https://aihub.qualcomm.com/get-started) | — | | [Qualcomm AI Model Efficiency Toolkit](https://quic.github.io/aimet-pages/releases/latest/index.html) | — | | [Qualcomm Neural Processing Engine](https://docs.qualcomm.com/bundle/publicresource/topics/80-63442-2/) | 80-63442-2 | | [Qualcomm AI Engine Direct](https://docs.qualcomm.com/bundle/publicresource/topics/80-63442-50/) | 80-63442-50 | | [AI Engine Direct: TFLite Delegate](https://docs.qualcomm.com/bundle/publicresource/topics/80-63442-50/tflite_delegate.html) | 80-63442-50 | | [Qualcomm Intelligent Multimedia SDK](https://docs.qualcomm.com/bundle/publicresource/topics/80-70020-50/example-applications.html) | 80-70020-50 | Last Published: Jul 07, 2025 [Previous Topic AI/ML documentation](https://docs.qualcomm.com/bundle/publicresource/80-70020-15/topics/home.md) [Next Topic APIs](https://docs.qualcomm.com/bundle/publicresource/80-70020-15/topics/interfaces.md)