Obtaining Software Packages

Software packages can be obtained by using either of the following methods. However, the MindSpore and MindStudio packages can be obtained only using method 1.

The ascend-deployer tool cannot distinguish Atlas 200 (EP) from the Atlas 300 inference card. Therefore, note the following restrictions when using this tool:

The online software package download function of the ascend-deployer tool does not include the driver and firmware packages of the Atlas 200 (EP). For the Atlas 200 (EP) environment, you need to prepare the driver and firmware packages of the Atlas 200 (EP).
The Atlas 200 (EP) and Atlas 300 inference cards cannot be deployed in batches at the same time. When deploying the Atlas 200 (EP) environment, do not store the driver and firmware packages of Atlas 300 inference cards in the ascend-deployer/resources directory. When deploying the Atlas 300 inference card environment, do not store the driver and firmware packages of the Atlas 200 (EP) in the ascend-deployer/resources directory.

Method 1: Use ascend-deployer to download the software packages (such as the CANN software package) listed in Table 1, MindSpore software package, and MindStudio software package. For details, see Downloading Packages.

Method 2: Obtain the software package in other ways.

Determine the software packages to be installed according to the site requirements. Obtain the required software packages and their digital signature files by visiting the links in Table 1.

**Table 1** Software packages
Name	Software Package	Description	How to Obtain
Driver and firmware package	Axxx --npu_- {arch}.zip, Axxx--driver_-{arch}.run, or Axxx--firmware_-{arch}.run	NPU firmware and driver are included. Software packages in *Ascend-hdk--npu_-* **{arch}.zip format support the installation of firmware and drivers for multiple products, and are recommended. For products such as Atlas 300I Pro, Atlas 300V, Atlas 300I Duo, and Atlas 300V Pro, you can use the Ascend-hdk-310p-npu_-* **{arch}.zip** package to install the firmware and driver.	Link
Development kit	Ascend-cann-toolkit _{version} _linux-{arch}.zip or Ascend-cann-toolkit _{version} _linux-{arch}.run	It is used for application development, operator customization, and model conversion. The development kit contains the library files required for developing applications and auxiliary development tools such as the ATC for model conversion. If the operating environment is AArch64 and the development environment is x86_64, you need to obtain the development kits of both architectures.	Link
Offline inference engine package	Ascend-cann-nnrt_{version}_linux-{arch}.zip or Ascend-cann-nnrt_ {version} _linux-{arch}.run	It is used for model inference of applications. This package includes AscendCL libraries and building dependencies (excluding the libraries in the driver package). It supports offline inference only. This software package is installed in the Atlas Intelligent Edge Solution scenario.
Deep learning engine package	Ascend-cann-nnae_{version}_linux-{arch}.zip or Ascend-cann-nnae_ {version} _linux-{arch}.run	It contains the Fwklib and OPP. It supports offline and online inference. This software package is installed in the Ascend Data Center Solution scenario.
Framework plugin package	Ascend-cann -tfplugin_ {version} _linux-{arch}.zip or Ascend-cann -tfplugin_ {version} _linux-{arch}.run	(Optional) Plugin package, an adaptation plugin used to connect to the upper-layer framework TensorFlow. If the deep learning framework TensorFlow is used for online inference or training, you need to obtain the software package.	Link
Binary OPP	Ascend-cann-kernels-{chip_type}_{version}_linux.zip or Ascend-cann-kernels-{chip_type}_{version}_linux.run	(Optional) The CANN binary OPP can be used during operator compilation. Before installing the package, install NNAE or Toolkit first.	Link
Toolbox	Ascend-mindx-toolbox_ {version} _linux-{arch}.zip or Ascend-mindx-toolbox_ {version} _linux-{arch}.run	The Ascend-DMI tool is included. The toolbox of a version earlier than MindX DL 3.0.0 mainly includes the container engine plugin Ascend Docker Runtime and the Ascend-DMI tool.	Link

{version} indicates the software version, and {arch} indicates the CPU architecture.
Verifying the digital signatures of software packages

To prevent a software package from being maliciously tampered with during transmission or storage, download the corresponding digital signature file for integrity verification when downloading the software package.

After the software package is downloaded from the Huawei Support website, verify its PGP digital signature. See OpenPGP Signature Verification Guide. If the verification fails, do not use the software package, and contact Huawei technical support engineers.

Before a software package is used in installation or update, its digital signature also needs to be verified according to OpenPGP Signature Verification Guide to ensure that the software package is not tampered with.

For carriers: http://support.huawei.com/carrier/digitalSignatureAction.

For enterprise users: https://support.huawei.com/enterprise/en/tool/pgp-verify-TL1000000054.

Store the software packages to be installed in the ascend-deployer/resources directory. The following is an example (the information in bold is the software packages to be installed).
Each software package in the resources directory must have only one version. Otherwise, the versions may not match.
```
ascend-deployer
|- ...
|- install.sh
|- inventory_file
|- ...
|- playbooks
|- README.md
|- resources
   |- A300-3010-npu_*.zip
   |- ...
   |- Ascend-cann-toolkit_*.zip
   |- ...
   |- CentOS_7.6_aarch64
   |- CentOS_7.6_x86_64
   |- ...
```

The ascend-deployer tool cannot automatically download the PyTorch or TensorFlow (AArch64 architecture) installation package. If you want to install PyTorch (torch-1.5.0+*.whl and apex-0.1+*.whl) or TensorFlow for the AArch64 architecture (tensorflow-1.15.0-*.whl and tensorflow-2.6.5-*.whl), place the compiled *.whl package in the ascend-deployer/resources/pylibs directory. Strictly comply with the official compilation specifications when compiling TensorFlow for the AArch64 architecture.
- For details about how to compile the TensorFlow installation package (AArch64), see section "Installing the Deep Learning Framework" in the CANN Software Installation Guide.
- For details about how to compile the PyTorch installation package, see the Section "Installing PyTorch" in CANN Software Installation Guide.
To deploy an image, obtain the required image from Ascend Hub, save it as an image file in the specified format (*_x86_64.tar or *_aarch64.tar), and save it to the ascend-deployer/resources/docker_images directory (you need to create this directory).
If the device to be deployed is A500 Pro-3000, A500-3000, or A500-3010 and the IEF agent needs to be installed, the following conditions must be met for IEF to register and manage edge nodes:
- The IEF server is running properly, and the network between edge nodes and IEF is accessible. For details about other restrictions, such as requirements on device specifications, see IEF User Guide.
- Obtain the node certificate, EdgeCore Register, and EdgeCore Installer. For details, see "Creating a Batch Node Registration Job" in Batch Node Registration. Place the obtained node certificate, EdgeCore Register, and EdgeCore Installer in the resources directory.
- Ensure that AtlasEdge on the edge node works properly. The A500-3000 and A500-3010 have built-in AtlasEdge. You need to install AtlasEdge on the A500 Pro-3000.
- For A500-3000 and A500-3010, the EdgeCore Register and EdgeCore Installer have been preset. Therefore, you only need to obtain the node certificate.
- EulerOS on the A500-3000 and A500-3010 does not support ascend-deployer. Therefore, only remote installation is supported by these two types of devices.
- Ensure the validity and integrity of the node certificate. If the certificate has been modified, damaged, or expired, the IEF agent will fail to be installed.

Parent topic: Installation Process