diff --git a/install/mindspore_ascend_install_conda.md b/install/mindspore_ascend_install_conda.md index ef405fd2e5c496ef3e1304316e784b86606e2a54..f16b0e067c9d88322a115a4060e28026f880fd25 100644 --- a/install/mindspore_ascend_install_conda.md +++ b/install/mindspore_ascend_install_conda.md @@ -36,7 +36,7 @@ ### 安装昇腾AI处理器配套软件包 -昇腾软件包社区版下载链接待发布，以及在[固件与驱动](https://www.hiascend.com/hardware/firmware-drivers/community)链接中获取对应的固件和驱动安装包，安装包的选择与安装方式请参照[安装指引文档（待发布）]。 +昇腾软件包社区版下载链接请前往[CANN社区版](https://www.hiascend.com/developer/download/community/result?module=cann)，推荐优先选择`8.3.RC1`版本，以及在[固件与驱动](https://www.hiascend.com/hardware/firmware-drivers/community)链接中获取对应的固件和驱动安装包，安装包的选择与安装方式请参照[安装指引文档](https://www.hiascend.com/document/detail/zh/CANNCommunityEdition/83RC1/softwareinst/instg/instg_quick.html)。 安装包默认安装路径为`/usr/local/Ascend`。安装后确认当前用户有权限访问昇腾AI处理器配套软件包的安装路径，若无权限，需要root用户将当前用户添加到`/usr/local/Ascend`所在的用户组。 diff --git a/install/mindspore_ascend_install_conda_en.md b/install/mindspore_ascend_install_conda_en.md index 60df15cdc4e5622802561a6f9ef2930d39e24e82..ea62730c4d615c3db176421b8cc6768d32031796 100644 --- a/install/mindspore_ascend_install_conda_en.md +++ b/install/mindspore_ascend_install_conda_en.md @@ -36,7 +36,7 @@ The following describes how to install the third-party dependencies. ### Installing Ascend AI processor software package -To install Ascend software package community edition, the recommended version is TBD, then choose relevant driver and firmware packages in [firmware and driver](https://www.hiascend.com/hardware/firmware-drivers/community). Please refer to [Installation guide](https://www.hiascend.com/document/detail/zh/CANNCommunityEdition/83RC1/softwareinst/instg/instg_quick.html) to choose which packages are to be installed and how to install them. +To install Ascend software package community edition, the recommended version is `8.3.RC1` in [CANN community edition](https://www.hiascend.com/developer/download/community/result?module=cann), then choose relevant driver and firmware packages in [firmware and driver](https://www.hiascend.com/hardware/firmware-drivers/community). Please refer to [Installation guide](https://www.hiascend.com/document/detail/zh/CANNCommunityEdition/83RC1/softwareinst/instg/instg_quick.html) to choose which packages are to be installed and how to install them. The default installation path of the installation package is `/usr/local/Ascend`. Ensure that the current user has the right to access the installation path `/usr/local/Ascend` of Ascend AI processor software package. If not, the root user needs to add the current user to the user group where `/usr/local/Ascend` is located. diff --git a/install/mindspore_ascend_install_docker.md b/install/mindspore_ascend_install_docker.md new file mode 100644 index 0000000000000000000000000000000000000000..49be9f811788df4ac56a24bceedb7ba71fd4bd12 --- /dev/null +++ b/install/mindspore_ascend_install_docker.md @@ -0,0 +1,194 @@ +# Docker方式安装MindSpore Ascend版本 + + + +- [Docker方式安装MindSpore Ascend版本](#docker方式安装mindspore-ascend版本) + - [确认系统环境信息](#确认系统环境信息) + - [安装昇腾AI处理器配套软件包](#安装昇腾ai处理器配套软件包) + - [获取MindSpore镜像](#获取mindspore镜像) + - [运行MindSpore镜像](#运行mindspore镜像) + - [验证是否安装成功](#验证是否安装成功) + - [升级MindSpore版本](#升级mindspore版本) + - [注意事项](#注意事项) + + + +[![查看源文件](https://mindspore-website.obs.cn-north-4.myhuaweicloud.com/website-images/master/resource/_static/logo_source.svg)](https://gitee.com/mindspore/docs/blob/r2.7.1/install/mindspore_ascend_install_docker.md) + +[Docker](https://docs.docker.com/get-docker/)是一个开源的应用容器引擎，支持将开发者的应用和依赖包打包到一个轻量级、可移植的容器中。通过使用Docker，可以实现MindSpore的快速部署，并与系统环境隔离。 + +本文档介绍如何在Ascend环境的Linux系统上，使用Docker方式快速安装MindSpore。 + +MindSpore的Docker镜像托管在[Huawei SWR](https://support.huaweicloud.com/swr/index.html)上。 + +目前容器化构建选项支持情况如下： + +| 硬件平台 | Docker命名空间 | Docker镜像名称 | 标签 | 说明 | +| :--------- | :------------------------ | :------------------------ | :----------------------- | :--------------------------------------- | +| Atlas 训练系列 | `mindspore` | `mindspore-ascend-a1` | `x.y.z` | 已经预安装Ascend Data Center Solution 与对应的MindSpore Ascend x.y.z版本的生产环境。 | +| Atlas A2 训练系列 | `mindspore` | `mindspore-ascend-a2` | `x.y.z` | 已经预安装Ascend Data Center Solution 与对应的MindSpore Ascend x.y.z版本的生产环境。 | + +> `x.y.z`对应MindSpore版本号，例如安装2.7.1版本MindSpore时，`x.y.z`应写为2.7.1。 + +## 确认系统环境信息 + +下表列出了使用Docker方式快速安装MindSpore所需的系统环境。 + +|软件名称|版本|作用| +|-|-|-| +|Debian系列操作系统 / openEuler系列操作系统|Debian系列：Debian、Ubuntu、veLinux / openEuler系列：openEuler、CentOS、Kylin、BCLinux、UOS V20、AntOS、CTyunOS、CULinux、Tlinux、MTOS|运行MindSporer容器的操作系统| +|[昇腾AI处理器配套软件包](#安装昇腾ai处理器配套软件包)|CANN 8.3.RC1、CANN 8.2.RC1、CANN 8.1.RC1|MindSpore使用的Ascend平台AI计算库| +|Docker | Docker 18.03或更高版本 |提供轻量级容器化环境，实现MindSpore及其依赖的隔离部署与跨平台运行| + +## 安装昇腾AI处理器配套软件包 + +昇腾软件包社区版下载链接请前往[CANN社区版](https://www.hiascend.com/developer/download/community/result?module=cann)，推荐优先选择`8.3.RC1`版本，以及在[固件与驱动](https://www.hiascend.com/hardware/firmware-drivers/community)链接中获取对应的固件和驱动安装包，安装包的选择与安装方式请参照[安装指引文档](https://www.hiascend.com/document/detail/zh/CANNCommunityEdition/83RC1/softwareinst/instg/instg_quick.html)。 + +安装包默认安装路径为`/usr/local/Ascend`。安装后确认当前用户有权限访问昇腾AI处理器配套软件包的安装路径，若无权限，需要root用户将当前用户添加到`/usr/local/Ascend`所在的用户组。 + +## 获取MindSpore镜像 + +对于不同架构的Ascend硬件平台后端，可以直接使用以下命令获取最新的稳定镜像： + +```bash +docker pull swr.cn-south-1.myhuaweicloud.com/mindspore/{image_name}:{tag} +``` + +其中： + +- `{image_name}` 对应上述表格中的docker镜像名称，使用 Atlas 训练系列产品请下载 `mindspore-ascend-a1` 镜像；Atlas A2 训练系列产品请下载 `mindspore-ascend-a2` 镜像。 +- `{tag}`对应上述表格中的标签,如2.7.1。 + +如果需要使用MindSpore 2.7.1版本，Atlas训练系列硬件的镜像，使用以下命令： + +```bash +docker pull swr.cn-south-1.myhuaweicloud.com/mindspore/mindspore-ascend-a1:2.7.1 +``` + +如果需要使用MindSpore 2.7.1版本，Atlas A2训练系列硬件的镜像，使用以下命令： + +```bash +docker pull swr.cn-south-1.myhuaweicloud.com/mindspore/mindspore-ascend-a2:2.7.1 +``` + +## 运行MindSpore镜像 + +执行以下命令，启动Docker容器实例： + +```bash +docker run -it --ipc=host \ + --device=/dev/davinci0 \ + --device=/dev/davinci1 \ + --device=/dev/davinci2 \ + --device=/dev/davinci3 \ + --device=/dev/davinci4 \ + --device=/dev/davinci5 \ + --device=/dev/davinci6 \ + --device=/dev/davinci7 \ + --device=/dev/davinci_manager \ + --device=/dev/devmm_svm \ + --device=/dev/hisi_hdc \ + -v /usr/local/bin/npu-smi:/usr/local/bin/npu-smi \ + -v /usr/local/Ascend/driver:/usr/local/Ascend/driver \ + -v /etc/ascend_install.info:/etc/ascend_install.info \ + -v /var/log/npu/:/usr/slog \ + -v /usr/bin/hccn_tool:/usr/bin/hccn_tool \ + -v /etc/hccn.conf:/etc/hccn.conf \ + swr.cn-south-1.myhuaweicloud.com/mindspore/{image_name}:{tag} \ + /bin/bash +``` + +其中： + +- `{image_name}` 对应上述表格中的docker镜像名称，Atlas 训练系列产品对应 `mindspore-ascend-a1` 镜像；Atlas A2 训练系列产品对应 `mindspore-ascend-a2` 镜像。 +- `{tag}`对应上述表格中的标签，如2.7.1。 +- 详细参数说明请见下表： + +|参数|参数说明| +|-|-| +|--device|表示映射的设备，可以挂载一个或多个设备。
/dev/davinciX：NPU设备，X代表设备id，如：davinci0。
/dev/davinci_manager：NPU相关管理设备。
/dev/hisi_hdc：HDC相关管理设备。
/dev/devmm_svm：内存管理设备。| +|-v /usr/local/bin/npu-smi:/usr/local/bin/npu-smi|将设备状态查询工具`npu-smi`挂载到容器。| +|-v /usr/local/Ascend/driver:/usr/local/Ascend/driver|将宿主机目录“/usr/local/Ascend/driver”挂载到容器。| +|-v /etc/ascend_install.info:/etc/ascend_install.info|将宿主机上CANN软件包安装记录文件挂载到容器。| +|-v /var/log/npu/:/usr/slog|将宿主机上的NPU日志目录挂载到容器。| +|-v /usr/bin/hccn_tool:/usr/bin/hccn_tool|将NPU通信配置工具`hccn_tool`挂载到容器。| +|-v /etc/hccn.conf:/etc/hccn.conf|将NPU通信配置文件挂载到容器。| + +## 验证是否安装成功 + +按照上述步骤进入MindSpore容器后，测试Docker容器是否正常工作，请执行下面的Python代码并检查输出： + +**方法一：** + +执行以下命令： + +```bash +python -c "import mindspore;mindspore.set_device('Ascend');mindspore.run_check()" +``` + +如果输出： + +```text +MindSpore version: 版本号 +The result of multiplication calculation is correct, MindSpore has been installed on platform [Ascend] successfully! +``` + +至此，你已经成功通过Docker方式安装了MindSpore Ascend版本。 + +**方法二：** + +执行以下代码： + +```python +import numpy as np +import mindspore as ms +import mindspore.ops as ops + +ms.set_device("Ascend") +x = ms.Tensor(np.ones([1,3,3,4]).astype(np.float32)) +y = ms.Tensor(np.ones([1,3,3,4]).astype(np.float32)) +print(ops.add(x, y)) +``` + +代码成功执行时会输出： + +```text +[[[[2. 2. 2. 2.] + [2. 2. 2. 2.] + [2. 2. 2. 2.]] + + [[2. 2. 2. 2.] + [2. 2. 2. 2.] + [2. 2. 2. 2.]] + + [[2. 2. 2. 2.] + [2. 2. 2. 2.] + [2. 2. 2. 2.]]]] +``` + +至此，你已经成功通过Docker方式安装了MindSpore Ascend版本。 + +## 升级MindSpore版本 + +当需要升级MindSpore版本时： + +- 根据需要升级的MindSpore版本以及Ascend硬件平台，升级对应的Ascend AI处理器配套软件包。 +- 直接使用以下命令获取最新的稳定镜像： + + ```bash + docker pull swr.cn-south-1.myhuaweicloud.com/mindspore/{image_name}:{tag} + ``` + + 其中： + + - `{tag}`对应上述表格中的标签。 + - `{image_name}` 对应上述表格中的docker镜像名称，使用 Atlas 训练系列产品请下载 `mindspore-ascend-a1` 镜像；Atlas A2 训练系列产品请下载 `mindspore-ascend-a2` 镜像。 + +## 注意事项 + +- 在非root用户模式下创建容器时，必须确保目标NPU设备未被其他非root容器占用。启动后可以执行 `npu-smi info` 命令验证设备状态，若目标NPU设备已被其他非root容器占用，则会出现以下报错，可以在创建容器时加上 `-u root --privileged`。 + +```text + DrvMngGetConsoleLogLevel failed. (g_conLogLevel=3) + dcmi model initialized failed, because the device is used. ret is -802 +``` \ No newline at end of file diff --git a/install/mindspore_ascend_install_docker_en.md b/install/mindspore_ascend_install_docker_en.md new file mode 100644 index 0000000000000000000000000000000000000000..94877052cd208ca64bc5bea6ffd4df1c671c2dd6 --- /dev/null +++ b/install/mindspore_ascend_install_docker_en.md @@ -0,0 +1,193 @@ +# Installing MindSpore in Ascend by Docker + + + +- [Installing MindSpore in Ascend by Docker](#installing-mindspore-in-ascend-by-docker) + - [System Environment Information Confirmation](#system-environment-information-confirmation) + - [Installing Ascend AI processor software package](#installing-ascend-ai-processor-software-package) + - [Obtaining MindSpore Image](#obtaining-mindspore-image) + - [Running MindSpore Image](#running-mindspore-image) + - [Installation Verification](#installation-verification) + - [Version Update](#version-update) + - [Notes](#notes) + + + +[![View Source On Gitee](https://mindspore-website.obs.cn-north-4.myhuaweicloud.com/website-images/master/resource/_static/logo_source_en.svg)](https://gitee.com/mindspore/docs/blob/r2.7.1/install/mindspore_ascend_install_docker_en.md) + +[Docker](https://docs.docker.com/get-docker/) is an open source application container engine, and supports packaging developers' applications and dependency packages into a lightweight, portable container. By using Docker, MindSpore can be rapidly deployed and separated from the system environment. + +This document describes how to install MindSpore by Docker on Linux in an Ascend environment. + +The Docker image of MindSpore is hosted on [Huawei SWR](https://support.huaweicloud.com/swr/index.html). + +The current support for containerized build options is as follows: + +| Hardware | Docker Namespace | Image Name | Label | Note | +| :--------- | :------------------------ | :------------------------ | :----------------------- | :--------------------------------------- | +| Atlas Training Series‌| `mindspore` | `mindspore-ascend-a1` | `x.y.z` | The production environment of MindSpore Ascend x.y.z together with the corresponding version of Ascend Data Center Solution. | +| Atlas A2 Training Series‌| `mindspore` | `mindspore-ascend-a2` | `x.y.z` | The production environment of MindSpore Ascend x.y.z together with the corresponding version of Ascend Data Center Solution. | + +> `x.y.z` corresponds to the MindSpore version number. For example, when MindSpore version 2.7.1 is installed, `x.y.z` should be written as 2.7.1. + +## System Environment Information Confirmation + +The following table outlines the system requirements for deploying MindSpore using Docker. + +|Software Name|Version|Function| +|-|-|-| +|Debian series OS / openEuler series OS|Debianseries: Debian, Ubuntu, veLinux / openEuler serires: openEuler, CentOS, Kylin, BCLinux, UOS V20, AntOS, CTyunOS, CULinux, Tlinux, MTOS|‌Recommended OS for MindSpore Container Deployment| +|[Ascend AI processor software package](#installing-ascend-ai-processor-software-package)|CANN 8.3.RC1, CANN 8.2.RC1, CANN 8.1.RC1|Ascend platform AI computing library used by MindSpore| +|Docker | Docker 18.03+ |Provides lightweight containerization environment for isolated deployment and cross-platform execution of MindSpore and its dependencies| + +## Installing Ascend AI processor software package + +To install Ascend software package community edition, the recommended version is `8.3.RC1` in [CANN community edition](https://www.hiascend.com/developer/download/community/result?module=cann), then choose relevant driver and firmware packages in [firmware and driver](https://www.hiascend.com/hardware/firmware-drivers/community). Please refer to [Installation guide](https://www.hiascend.com/document/detail/zh/CANNCommunityEdition/83RC1/softwareinst/instg/instg_quick.html) to choose which packages are to be installed and how to install them. + +The default installation path of the installation package is `/usr/local/Ascend`. Ensure that the current user has the right to access the installation path `/usr/local/Ascend` of Ascend AI processor software package. If not, the root user needs to add the current user to the user group where `/usr/local/Ascend` is located. + +## Obtaining MindSpore Image + +For the `Ascend` backend, you can directly use the following command to obtain the latest stable image: + +```bash +docker pull swr.cn-south-1.myhuaweicloud.com/mindspore/{image_name}:{tag} +``` + +of which, + +- `{image_name}` corresponds to the image name in the above table. For Atlas Training Series A1 products, download the `mindspore-ascend-a1` image; for Atlas A2 Training Series products, download the `mindspore-ascend-a2` image. +- `{tag}` corresponds to the label in the above table. + +To install MindSpore 2.7.1 on Atlas Training Platform, use the following command: + +```bash +docker pull swr.cn-south-1.myhuaweicloud.com/mindspore/mindspore-ascend-a1:2.7.1 +``` + +To install MindSpore 2.7.1 on Atlas A2 Training Platform, use the following command: + +```bash +docker pull swr.cn-south-1.myhuaweicloud.com/mindspore/mindspore-ascend-a2:2.7.1 +``` + +## Running MindSpore Image + +Execute the following command to start the Docker container instance: + +```bash +docker run -it --ipc=host \ + --device=/dev/davinci0 \ + --device=/dev/davinci1 \ + --device=/dev/davinci2 \ + --device=/dev/davinci3 \ + --device=/dev/davinci4 \ + --device=/dev/davinci5 \ + --device=/dev/davinci6 \ + --device=/dev/davinci7 \ + --device=/dev/davinci_manager \ + --device=/dev/devmm_svm \ + --device=/dev/hisi_hdc \ + -v /usr/local/bin/npu-smi:/usr/local/bin/npu-smi \ + -v /usr/local/Ascend/driver:/usr/local/Ascend/driver \ + -v /etc/ascend_install.info:/etc/ascend_install.info \ + -v /var/log/npu/:/usr/slog \ + -v /usr/bin/hccn_tool:/usr/bin/hccn_tool \ + -v /etc/hccn.conf:/etc/hccn.conf \ + swr.cn-south-1.myhuaweicloud.com/mindspore/{image_name}:{tag} \ + /bin/bash +``` + +of which, + +- `{image_name}` corresponds to the image name in the above table. For Atlas Training Series A1 products, use `mindspore-ascend-a1` image; for Atlas A2 Training Series products, use `mindspore-ascend-a2` image. +- `{tag}` corresponds to the label in the above table. +- Description for parameters are listed below: + +|Parameter|Description| +|-|-| +|--device|Mapping devices to the container.
/dev/davinciX: NPU device, X represents device ID, e.g. davinci0.
/dev/davinci_manager: Management device for NPU.
/dev/hisi_hdc: Management device for HDC.
/dev/devmm_svm: Management device for device memory.| +|-v /usr/local/bin/npu-smi:/usr/local/bin/npu-smi|Mapping NPU management interface `npu-smi` to the container.| +|-v /usr/local/Ascend/driver:/usr/local/Ascend/driver|Mapping host directory "/usr/local/Ascend/driver" to the container.| +|-v /etc/ascend_install.info:/etc/ascend_install.info|Mapping installation log for CANN software packages to the container.| +|-v /var/log/npu/:/usr/slog|Mapping NPU log to the container.| +|-v /usr/bin/hccn_tool:/usr/bin/hccn_tool|Mapping NPU communication configuration tool `hccn_tool` to the container.| +|-v /etc/hccn.conf:/etc/hccn.conf|Mapping hccn configuration file to the container.| + +## Installation Verification + +After entering the MindSpore container according to the above steps, to test whether the Docker container is working properly, please execute the following Python code and check the output: + +**Method 1:** + +Execute the following command: + +```bash +python -c "import mindspore;mindspore.set_device('Ascend');mindspore.run_check()" +``` + +The outputs should be the same as: + +```text +MindSpore version: __version__ +The result of multiplication calculation is correct, MindSpore has been installed on platform [Ascend] successfully! +``` + +So far, it means MindSpore Ascend has been installed by Docker successfully. + +**Method 2:** + +Execute the following command: + +```python +import numpy as np +import mindspore as ms +import mindspore.ops as ops + +ms.set_device("Ascend") +x = ms.Tensor(np.ones([1,3,3,4]).astype(np.float32)) +y = ms.Tensor(np.ones([1,3,3,4]).astype(np.float32)) +print(ops.add(x, y)) +``` + +The outputs should be the same as: + +```text +[[[[2. 2. 2. 2.] + [2. 2. 2. 2.] + [2. 2. 2. 2.]] + + [[2. 2. 2. 2.] + [2. 2. 2. 2.] + [2. 2. 2. 2.]] + + [[2. 2. 2. 2.] + [2. 2. 2. 2.] + [2. 2. 2. 2.]]]] +``` + +So far, it means MindSpore Ascend has been installed by Docker successfully. + +## Version Update + +When you need to update the MindSpore version: + +- update corresponding Ascend AI processor software package according to MindSpore package version of which you wish to update. +- directly use the following command to obtain the latest stable image: + + ```bash + docker pull swr.cn-south-1.myhuaweicloud.com/mindspore/{image_name}:{tag} + ``` + + of which, + + - `{tag}` corresponds to the label in the above table. + +## Notes + +- When deploying containers in non-root user mode, it is essential to verify that the target NPU device is not occupied by other unprivileged containers. After startup, execute the `npu-smi` info command to check device status. If the target NPU device is already allocated to another non-root container, the following error will occur, You can add `-u root --privileged` when creating the container. + +```text + DrvMngGetConsoleLogLevel failed. (g_conLogLevel=3) + dcmi model initialized failed, because the device is used. ret is -802 +``` \ No newline at end of file diff --git a/install/mindspore_ascend_install_pip.md b/install/mindspore_ascend_install_pip.md index 54f0be70267efe11c22d48db0a893916d1dcc19d..1b0a84ea521e564a743a8c54e80f5b0bf954abc3 100644 --- a/install/mindspore_ascend_install_pip.md +++ b/install/mindspore_ascend_install_pip.md @@ -69,7 +69,7 @@ python -m pip install -U pip ### 安装昇腾AI处理器配套软件包 -昇腾软件包社区版下载链接待发布，以及在[固件与驱动](https://www.hiascend.com/hardware/firmware-drivers/community)链接中获取对应的固件和驱动安装包，安装包的选择与安装方式请参照[安装指引文档（待发布）]。 +昇腾软件包社区版下载链接请前往[CANN社区版](https://www.hiascend.com/developer/download/community/result?module=cann)，推荐优先选择`8.3.RC1`版本，以及在[固件与驱动](https://www.hiascend.com/hardware/firmware-drivers/community)链接中获取对应的固件和驱动安装包，安装包的选择与安装方式请参照[安装指引文档](https://www.hiascend.com/document/detail/zh/CANNCommunityEdition/83RC1/softwareinst/instg/instg_quick.html)。 安装包默认安装路径为`/usr/local/Ascend`。安装后确认当前用户有权限访问昇腾AI处理器配套软件包的安装路径，若无权限，需要root用户将当前用户添加到`/usr/local/Ascend`所在的用户组。 diff --git a/install/mindspore_ascend_install_pip_en.md b/install/mindspore_ascend_install_pip_en.md index 4b37351c6b658d31c6f60f710783995d6f5a44dc..26c5e9cdd9d78f52c51955602ad437bfcd87da36 100644 --- a/install/mindspore_ascend_install_pip_en.md +++ b/install/mindspore_ascend_install_pip_en.md @@ -69,7 +69,7 @@ python -m pip install -U pip ### Installing Ascend AI processor software package -To install Ascend software package community edition, the recommended version is TBD, then choose relevant driver and firmware packages in [firmware and driver](https://www.hiascend.com/hardware/firmware-drivers/community). Please refer to [Installation guide(TBD)] to choose which packages are to be installed and how to install them. +To install Ascend software package community edition, the recommended version is `8.3.RC1` in [CANN community edition](https://www.hiascend.com/developer/download/community/result?module=cann), then choose relevant driver and firmware packages in [firmware and driver](https://www.hiascend.com/hardware/firmware-drivers/community). Please refer to [Installation guide](https://www.hiascend.com/document/detail/zh/CANNCommunityEdition/83RC1/softwareinst/instg/instg_quick.html) to choose which packages are to be installed and how to install them. The default installation path of the installation package is `/usr/local/Ascend`. Ensure that the current user has the right to access the installation path of Ascend AI processor software package. If not, the root user needs to add the current user to the user group where `/usr/local/Ascend` is located. diff --git a/install/mindspore_ascend_install_source.md b/install/mindspore_ascend_install_source.md index 8e09d2e6a48761ca0af846190b86e94d2a33d816..1baf66f0bd2dc72c54ed541a633419e5ffeb25c2 100644 --- a/install/mindspore_ascend_install_source.md +++ b/install/mindspore_ascend_install_source.md @@ -80,7 +80,7 @@ python --version ### 安装昇腾AI处理器配套软件包 -昇腾软件包社区版下载链接待发布，以及在[固件与驱动](https://www.hiascend.com/hardware/firmware-drivers/community)链接中获取对应的固件和驱动安装包，安装包的选择与安装方式请参照[安装指引文档（待发布）]。 +昇腾软件包社区版下载链接请前往[CANN社区版](https://www.hiascend.com/developer/download/community/result?module=cann)，推荐优先选择`8.3.RC1`版本，以及在[固件与驱动](https://www.hiascend.com/hardware/firmware-drivers/community)链接中获取对应的固件和驱动安装包，安装包的选择与安装方式请参照[安装指引文档](https://www.hiascend.com/document/detail/zh/CANNCommunityEdition/83RC1/softwareinst/instg/instg_quick.html)。 安装包默认安装路径为`/usr/local/Ascend`。安装后确认当前用户有权限访问昇腾AI处理器配套软件包的安装路径，若无权限，需要root用户将当前用户添加到`/usr/local/Ascend`所在的用户组。 diff --git a/install/mindspore_ascend_install_source_en.md b/install/mindspore_ascend_install_source_en.md index 2d72bc7ed38d40831008645aed5602f1ff7a2d88..4041d31107d46e905ee87ae4252344fcaf78a768 100644 --- a/install/mindspore_ascend_install_source_en.md +++ b/install/mindspore_ascend_install_source_en.md @@ -80,7 +80,7 @@ python --version ### Installing Ascend AI processor software package -To install Ascend software package community edition, the recommended version is TBD, then choose relevant driver and firmware packages in [firmware and driver](https://www.hiascend.com/hardware/firmware-drivers/community). Please refer to [Installation guide(TBD)] to choose which packages are to be installed and how to install them. +To install Ascend software package community edition, the recommended version is `8.3.RC1` in [CANN community edition](https://www.hiascend.com/developer/download/community/result?module=cann), then choose relevant driver and firmware packages in [firmware and driver](https://www.hiascend.com/hardware/firmware-drivers/community). Please refer to [Installation guide](https://www.hiascend.com/document/detail/zh/CANNCommunityEdition/83RC1/softwareinst/instg/instg_quick.html) to choose which packages are to be installed and how to install them. The default installation path of the installation package is `/usr/local/Ascend`. Ensure that the current user has the right to access the installation path `/usr/local/Ascend` of Ascend AI processor software package. If not, the root user needs to add the current user to the user group where `/usr/local/Ascend` is located. diff --git a/resource/release/release_list_en.md b/resource/release/release_list_en.md index 4073570dc08f62b79dc381ed9bcc63cb0c8334a1..bb43db571821a41108f067fb92593bf596e2d2da 100644 --- a/resource/release/release_list_en.md +++ b/resource/release/release_list_en.md @@ -87,7 +87,7 @@ | Installation guide | Community edition download link | |--------|------------------| -| [Installation guide(TBD)] | CANN TBD
[firmware and driver](https://www.hiascend.com/hardware/firmware-drivers/community) | +| [Installation guide](https://www.hiascend.com/document/detail/zh/CANNCommunityEdition/83RC1/softwareinst/instg/instg_quick.html) | [CANN 8.3.RC1](https://www.hiascend.com/developer/download/community/result?module=cann)
[firmware and driver](https://www.hiascend.com/hardware/firmware-drivers/community) | ## 2.7.0 diff --git a/resource/release/release_list_zh_cn.md b/resource/release/release_list_zh_cn.md index 839a8ed396f3261e9e4bdd214ada9146664518e0..80a2f158e2f8e39a820ee7d8f3af2ae16115718e 100644 --- a/resource/release/release_list_zh_cn.md +++ b/resource/release/release_list_zh_cn.md @@ -87,7 +87,7 @@ | 安装指引 | 社区版下载地址 | |--------|------------------| -| [安装指引文档（待发布）] | CANN版本待发布
[固件与驱动](https://www.hiascend.com/hardware/firmware-drivers/community) | +| [安装指引文档](https://www.hiascend.com/document/detail/zh/CANNCommunityEdition/83RC1/softwareinst/instg/instg_quick.html) | [CANN 8.3.RC1](https://www.hiascend.com/developer/download/community/result?module=cann)
[固件与驱动](https://www.hiascend.com/hardware/firmware-drivers/community) | ## 2.7.0