Installation Description

This document describes how to efficiently install the Ascend NPU driver and firmware and the Compute Architecture for Neural Networks (CANN) software on Ascend inference devices. Table 1 describes the software.

**Table 1** Ascend software
Software Type	Description
Ascend NPU Firmware	The firmware contains the OS, power component, and power consumption management control software of an Ascend AI Processor. It is used for model calculation, processor startup control, and power consumption control that are loaded to the Ascend AI Processor.
Ascend NPU Driver	The driver is deployed on an Ascend server and functions similar to the NVIDIA driver. It manages and queries the Ascend AI Processor and provides processor control and resource allocation interfaces for the upper-layer CANN software.
CANN	CANN is deployed on an Ascend server and functions similar to the NVIDIA CUDA. It includes the Runtime, operator package (OPP), graph engine, and media data processing components. It uses Ascend Computing Language (AscendCL) to provide APIs for external systems to enable functions such as device management, context management, stream management, memory management, model loading and execution, operator loading and execution, and media data processing. This helps developers develop and run AI services on Ascend software and hardware platforms. The CANN software packages include the Toolkit (development kit), NNAE (deep learning engine), and NNRT (offline inference engine). The functions of each software package are as follows: Toolkit: supports training and inference services, model conversion, and operator/application/model development and build. NNAE: supports training and inference services, and model conversion. NNRT: supports only inference services.

Installation Scenario

You need to install the hardware, OS, Ascend NPU driver and firmware, and CANN software. Because model conversion is required before inference, the CANN software uses the Toolkit (development kit).

Figure 1 Installation scenario

Hardware Requirements

Table 2 lists the Ascend inference devices that can be used as the inference environments of Modelzoo models. A server can be used for inference only after inference cards are inserted into it.

**Table 2** Hardware requirements
Hardware Type	Hardware Model
Server	Atlas 800 inference server (model 3000) Atlas 800 inference server (model 3010) Atlas 500 Pro AI edge server (model 3000)
Inference Card	Atlas 300I Pro inference card Atlas 300V Pro video analysis card Atlas 300I Duo inference card Atlas 300I inference card (model 3000) Atlas 300I inference card (model 3010)