Getting Started

Here, you can find a comprehensive list of pages to get you started with your product, from installing it to maximizing its performance with advanced functions.

Overview to Using Mobilint’s NPU

Mobilint has two flagship NPU chips: ARIES (AI Accelerator) and REGULUS (System-on-Chip). Depending on the core NPU and the form factor, the installation process may vary.

Click the name of your product to check its environmental prerequisites and get the instructions on how to install it in your system.

Hardware Introduction

• ARIES MLA100 PCIe Card: ARIES NPU on a PCIe card for servers and workstations.

• ARIES MLA100 MXM Module: ARIES NPU as an MXM module for embedded systems.

• ARIES MLX-A1 Edge AI PC: Turnkey edge AI PC powered by ARIES.

• REGULUS System-on-Module (SoM): Ultra-low-power REGULUS SoM, documentation in progress.

Software SDK Introduction

Important

• The installation steps below apply to ARIES-based devices only.

• REGULUS devices ship with the essential SDK stack (driver, runtime library) and utilities pre-installed. Proceed directly to the Tutorials section below.

Install the SDK software required to use an ARIES NPU by following these documents in order.

1. Installing Driver: The kernel driver that exposes the NPU to your operating system.

2. Installing Runtime Library: The C++ and Python runtime for loading models and running inference.

3. Checking Compatibility: Verify that driver, firmware, and library versions match.

Note

You need a Download Center account to access and download some files and modules. Please contact contact@mobilint.com for more information.

Optional Setup

These steps are not required for a standard setup — perform them only when needed.

• Update Firmware: Needed only when the compatibility check reports a device firmware older than the version the SDK requires.

Note

Compiling deep learning models into MXQ with qb Compiler is covered in separate documentation and is not part of this manual. To run models right away, use the pre-compiled models in the Model Zoo.

Tutorials

After installing all essential SDK components required for NPU operation, refer to the following tutorials to learn how to successfully run AI inference on a Mobilint NPU.

• Running Pre-Compiled ResNet50: Run your first inference with a ready-made model.

• NPU Programming Guide: The core runtime API and the inference workflow.

Utilities

Explore the utility tools provided by Mobilint. These help you monitor the NPU’s status or run tests. If you want to use an open-source pre-trained model off the shelf, visit our Model Zoo to check the availability of a pre-compiled model.

• Installing Utility: Install Mobilint’s command-line tools.

• Utility Usage: Monitor NPU status and run diagnostics.

• Model Zoo: 400+ pre-compiled open-source models.

Advanced

Once you get the hang of the system, follow the Advanced Usage sections to further optimize your NPU usage or refer to the advanced tutorials.

• Advanced Usage: Optimize throughput, batching, and memory.

• Utilizing Multi-Core Modes: Distribute inference across NPU cores.

Deployment

To deploy NPU workloads on a Kubernetes cluster, install the device plugin so that Pods can request NPUs as a schedulable resource.

• Mobilint Device Plugin: Schedule NPUs as resources on a Kubernetes cluster.