QNN LPAI Predict

R2026b

Predict responses of QNN context binary for LPAI backend

Since R2025b

• 

QNN LPAI Predict block

To add a block to a model, double-click the canvas and start typing the block name. Then, select the block from the list.

Libraries:
Embedded Coder Support Package for Qualcomm Hexagon Processors / QNN

Description

The QNN LPAI Predict block predicts responses of a deep learning network represented as a QNN context binary for the LPAI backend of Qualcomm^® AI Direct Engine based on the given input data.

You use the QNN LPAI Predict block to select a QNN context binary file (.bin) that is optimized to run on LPAI backend for both x86-based host simulations and target executions.

You can deploy the code generated using this block to one of these boards that are available under the Hardware board parameter in Configuration Parameters:

• Qualcomm Android Board

• Qualcomm Hexagon Android Board

The block also provides the option to dequantize outputs to single-precision, if required.

Examples

Deploy Deep Neural Networks to Qualcomm Targets Using Qualcomm AI Engine Direct (QNN)

Learn the workflow for using the Simulink blocks under the QNN Simulink library.

• Open Live Script

Ports

Input

Port_1 — Input signal to predict response

n–D array

The input tensor to use for inference with the selected QNN model, represented as an n-D array, in accordance with the Input layer size parameter of the QNN model.

The QNN LPAI Predict block supports a multiple-input multiple-output tensor with a maximum of four dimensions, but the batch size must always be 1. For example, if the input layer of the original deep learning network is 128-by-128-by-3, the input dimension should be either 128-by-128-by-3 or 1-by-128-by-128-by-3.

If the leading dimensions are 1 (singleton dimensions), these dimensions can often be removed without affecting compatibility. For example, if the input layer of an AI model expects an input size of 1-by-1-by-128-by-3, the input can be provided as 1-by-1-by-128-by-3 or simply 128-by-3. This is because dimensions of size 1 can be broadcast to match the expected shape.

The QNN LPAI Predict block accepts either a floating-point input or a fixed-point input. The input data type must match the data type of the QNN network's input layer. Additionally, the input can be floating-point even for quantized QNN network.

Data Types: single | half | int8 | int16 | int32 | uint8 | uint16 | uint32

Output

Port_2 — Output signal after inference

n–D array

The output tensor to use for inference with the selected QNN model, represented as an n-D array, in accordance with the QNN output layer. The output data types match the data types of the QNN network's output layers. If you select Dequantize Ouptut, the output is always single.

Data Types: single | half | int8 | int16 | int32 | uint8 | uint16 | uint32

Parameters

LPAI version — Version of LPAI backend

v5 (default) | v6

Since R2026a

Select one of these LPAI backend version to perform inference:

• v5

• v6

Context binary file — QNN context binary file on LPAI backend

"<filename>.bin"

Click Browse and select the QNN context binary file (.bin) on the target to perform inference on the host. For details on creating an binary file to run on device processors like LPAI, refer to Qualcomm AI Engine Direct SDK documentation.

Backend configuration file — Backend configuration filename

"<filename>.json"

Since R2026a

Click Browse and select the backend configuration file. Use this parameter to browse and select a Qualcomm QNN-compliant json file that defines GPU backend-specific execution settings for the model. These settings include memory allocation, precision mode, thread count, and performance profile.

Dequantize output — Option to use output dequantization to predict response

off (default) | on

Select the checkbox to dequantize the block's output. Enabling this option results in output data type always being single, irrespective of the deep learning neural network's output layer data type.

Programmatic Use: Add Block

To add the block programmatically, use the add_block function with one of these library block paths as the source.

"mwqnnlib/QNN LPAI Predict"

Example: add_block("mwqnnlib/QNN LPAI Predict","myModel/myBlock",MakeNameUnique="on")

Extended Capabilities

C/C++ Code Generation
Generate C and C++ code using Simulink® Coder™.

Version History

Introduced in R2025b

R2026b: QNN Host Model parameter has been removed

The QNN Host Model parameter of the QNN LPAI Predict block has been removed.

R2026a: Specify LPAI version for QNN LPAI Predict block

In R2026a, the QNN LPAI Predict adds the LPAI Version parameter to select the version of the LPAI backend.