Where to download the correct Neuropilot SDK for IoT Platforms?

NeuroPilot NeuroPilot - Analytical AI
1

I downloaded the NeuroPilot SDK from

In the extracted folders, I see several directories (such as host, mt6878, mt6897, mt6899, mt6989, and mt6991), each containing both neuronrt and ncc-tflite files.
How do I choose the correct versions for deploying a model on Genio-720?

2

Thank you for this question.

The MediaTek Genio-720 /Genio-520 correspond to the mt8189 code name in the NeuroPilot ecosystem.
mt8189 belongs to the Genio IoT series and uses MDLA5.3 (MediaTek Deep Learning Accelerator version 5.3) with NeuroPilot 8 (NP8) support.

Important:
As of now, the official NeuroPilot SDK All-In-One Bundle does not include binaries for mt8189, which are required for Genio-720/Genio-520 deployments.

Recommended Download for Genio-720

Please download the dedicated mt8189 package from:

Version Table: Mapping SoC Code Names to IoT Series and MDLA Versions

Directory Name IoT Code Name IoT Product Series NeuroPilot Version MDLA Version
mt6878 8873 IoT-Modem NP7 MDLA3.5
mt6897 8883 IoT-Modem NP7 MDLA5.0
mt6989 8893 IoT-Modem NP7 MDLA5.1
mt6991 8894 IoT-Modem NP8 MDLA5.5
mt8189 8391 IoT-Genio NP8 MDLA5.3

Tool Selection: neuronrt and ncc-tflite Usage Guide

  • neuronrt

    • In the host folder: Early developer validation tool, intended for PC environments with compatible MediaTek NPU. Not used for on-device deployment.
    • In device-specific folders (e.g., mt8189): Validation and inference tool for on-device usage—select the version matching your device’s SoC code name.

  • ncc-tflite

    • Host tool for converting TFLite models into DLA binaries targeting a specific hardware generation (e.g., MDLA3, MDLA5).
    • Use the version that corresponds to your deployment target (e.g., for Genio-720 use the one from the mt8189 package).

Deployment Steps for Genio-720 / Genio-520

  1. Download the mt8189-specific package from the NeuroPilot download page (not the All-In-One Bundle).
  2. Use the ncc-tflite tool from the mt8189 package to convert TFLite models to DLA binaries targeting MDLA5.3.
  3. Use the neuronrt tool from the mt8189 package on your Genio-720 device for model validation or on-device inference.

MediaTek Recommendation: Prefer Host Tool for Model Conversion

MediaTek strongly recommends using the host version of ncc-tflite (located in the host folder) for model conversion tasks. The host-side ncc-tflite tool provides:

  • More comprehensive operator (op) support than device-specific versions

  • Improved memory management during model conversion

  • Better overall reliability, reducing the chance of memory allocation failures that can sometimes arise with device-side tools

Always perform model conversion on your development host PC with the host ncc-tflite, then transfer the generated DLA binaries for deployment on the target device.

Summary

  • Do not use the neuronrt or ncc-tflite tools from other SoC folders (e.g., mt6878, mt6991) for Genio-720.
  • Always match the tool version to your target device’s code name (mt8189 for Genio-720/Genio-520).
  • For complete documentation and updates, refer to the official MediaTek NeuroPilot download page.
4

It seems command, like 20250423_Neuron_SDK_v1.2517.03_neuron-8.0-release_release/mt8189/bin/neuronrt, can not be run on GENIO 720 with Ubuntu 24.04 ? there are some shared library issues ?

5

Hi @Sting_Cheng,

The AI-related function on Genio 720 with Ubuntu is still under development, and it’s expected to be completed in 2H26.

Here’s the OS supporting information based on different platforms.
You could choose G510/G700/G1200 for AI funtion development :slight_smile: :hugs:

6

Hi @joying.kuo

For Genio 1200, The libneuro*.so are only available in Yocto image but NOT Ubuntu, can you please tell me how I can find the required neuron libraries for Ubuntu 22.04 or 24.04 ?

~Sting

image
image1264×211 30.8 KB

7

Hi Sting_Cheng,

For Ubuntu, the Neuron libraries are installed via a separate NeuroPilot package. Once installed, you’ll get libneuron*.so ready to use.

Setup guide: NeuroPilot on Ubuntu

Best,
Jun

8

你好joying.kuo，我也遇到了同样的问题，在开发中我期望获取可以用于C++编程的针对yocto系统的SDK，根据你的回复我找到AI Development Resources — IoT AI Hub documentation
下面的20250423_Neuron_SDK_v1.2517.03_neuron-8.0-release.tar.gz: Link
但是根据描述这个似乎只是针对android的并且下载的压缩包中也没有G720对应的MT8391。

所以我想确定是我找错文件/位置了吗还是目前确实还没有用于C++编程的针对yocto系统的SDK呢

9

Dear @huang_hui ,

Yocto中的neuron runtime libs/SDK是built-in的, 可以直接使用, 所以沒有額外提供下載的壓縮包.

image
image1725×462 54.5 KB

10

@joying.kuo 非常感谢您的回复，然而：
首先， 我现在使用的OS 是yocto，而这个截图中对应的行的supported os是Android；
其次，yocto板端的确有neuronrt，但它只是一个二进制可执行程序，可用于验证但不适用于代码开发。我需要"头文件+库"，在板端并没有发现可用的头文件，同时板端并没有C++开发所需要的基础库和编译器（g++, cmake, make etc.）。当然，如我开始请求有一个可供检查编译的环境（包括交叉编译器 + yocto系统SDK for 视频操作 + 推理库SDK for 模型推理 + SDK使用示例）就更好了。

11

Hi Huang_Hui,

關於 Yocto SDK 詳細的產生、安裝與使用步驟，可以參考這份文件：
Application SDK

內容涵蓋：

  • 交叉編譯器安裝
  • 環境設定腳本
  • Make / CMake / Meson 範本
  • 第三方軟體交叉編譯範例

另外，Neuron API .h 的說明文件可以參考：
Neuron API Reference

Best,
Jun