nvidia/cuda

英伟达在GitLab仓库（gitlab.com/nvidia/cuda）提供的CUDA（并行计算平台）和cuDNN（深度神经网络加速库）镜像，为开发者提供了预配置的开发环境，支持高效进行并行计算应用开发、深度学习模型训练及推理任务，确保了环境的一致性和部署的便捷性，是构建基于英伟达GPU加速应用的重要资源。

2.0千次收藏下载次数: 0状态：社区镜像维护者：NVIDIA 官方容器镜像仓库类型：镜像最近更新：10 天前

让 AI 帮你使用轩辕镜像？ · 展开查看说明

如果你使用 DeepSeek、元宝 AI、Copilot、ChatGPT 等 AI 工具，协助配置轩辕镜像、编写 docker pull 命令、修改 Docker Compose 镜像地址、配置镜像加速、排查镜像拉取失败、分析报错日志等问题，请先让 AI 阅读并遵守轩辕镜像的规则文档。

只需在 AI 对话中先发送下面这段话即可：

请先阅读并遵守：https://xuanyuan.cloud/agents.md

未读文档前不要生成 pull 命令或排错方案。

查看 agents.md 用法指南与完整示范。国内用户首推元宝 AI、DeepSeek 的深度思考模式，不推荐豆包 AI；Cursor 等编辑器可在对话 @ 该链接，或加入 User Rules。若 AI 无法访问外链，可打开说明文档复制全文粘贴。文档会随站点更新，复制内容可能过期，建议定期检查。

DockerHub 官方简介

轩辕镜像中文简介

下载命令

镜像标签列表与下载命令

轩辕镜像，加速的不只是镜像。

点击查看

NVIDIA CUDA

https://developer.nvidia.com/cuda-zone is a parallel computing platform and programming model developed by NVIDIA for general computing on graphical processing units (GPUs). With CUDA, developers can dramatically speed up computing applications by harnessing the power of GPUs.

The CUDA Toolkit from NVIDIA provides everything you need to develop GPU-accelerated applications. The CUDA Toolkit includes GPU-accelerated libraries, a compiler, development tools and the CUDA runtime.

The CUDA container images provide an easy-to-use distribution for CUDA supported platforms and architectures.

End User License Agreements

The images are governed by the following NVIDIA End User License Agreements. By pulling and using the CUDA images, you accept the terms and conditions of these licenses. Since the images may include components licensed under open-source licenses such as GPL, the sources for these components are archived https://developer.download.nvidia.com/compute/cuda/opensource/image.

NVIDIA Deep learning Container License

To view the NVIDIA Deep Learning Container license, click https://developer.nvidia.com/ngc/nvidia-deep-learning-container-license

Documentation

For more information on CUDA, including the release notes, programming model, APIs and developer tools, visit the https://docs.nvidia.com/cuda.

Announcement

CUDA Container Support Policy

CUDA image container tags have a lifetime. The tags will be deleted Six Months after the last supported "Tesla Recommended Driver" has gone end-of-life OR a newer update release has been made for the same CUDA version.

Please see https://gitlab.com/nvidia/container-images/cuda/-/blob/master/doc/support-policy.md for more information.

Breaking changes are announced on https://gitlab.com/nvidia/container-images/cuda/-/work_items/209.

Cuda Repo Signing Key has Changed!

This may present itself as the following errors.

debian:

Reading package lists... Done
W: GPG error: http://developer.download.nvidia.com/compute/cuda/repos/ubuntu1604/x86_64  InRelease: The following signatures couldn't be verified because the public key is not available: NO_PUBKEY A4B469963BF863CC
W: The repository 'http://developer.download.nvidia.com/compute/cuda/repos/ubuntu1604/x86_64  InRelease' is not signed.
N: Data from such a repository can't be authenticated and is therefore potentially dangerous to use.
N: See apt-secure(8) manpage for repository creation and user configuration details.

RPM:

warning: /var/cache/dnf/cuda-fedora32-x86_64-d60aafcddb176bf5/packages/libnvjpeg-11-1-11.3.0.105-1.x86_64.rpm: Header V4 RSA/SHA512 Signature, key ID d42d0685: NOKEY
cuda-fedora32-x86_64                                                                                  23 kB/s | 1.6 kB     00:00
Importing GPG key 0x7FA2AF80:
 Userid     : "cudatools <cudatools@nvidia.com>"
 Fingerprint: AE09 FE4B BD22 3A84 B2CC FCE3 F60F 4B3D 7FA2 AF80
 From       : https://developer.download.nvidia.com/compute/cuda/repos/fedora32/x86_64/7fa2af80.pub
Is this ok [y/N]: y
Key imported successfully
Import of key(s) didn't help, wrong key(s)?
Public key for libnvjpeg-11-1-11.3.0.105-1.x86_64.rpm is not installed. Failing package is: libnvjpeg-11-1-11.3.0.105-1.x86_64
 GPG Keys are configured as: https://developer.download.nvidia.com/compute/cuda/repos/fedora32/x86_64/7fa2af80.pub
The downloaded packages were saved in cache until the next successful transaction.
You can remove cached packages by executing 'dnf clean packages'.
Error: GPG check FAILED

Updated images will be pushed out over the next few days containing the new repo key. Please follow progress using the links below:

https://gitlab.com/nvidia/container-images/cuda/-/work_items/158

Multi-arch image manifests are now LIVE for all supported CUDA container image versions

It is now possible to build CUDA container images for all supported architectures using Docker Buildkit in one step. See the example script below.

The deprecated image names nvidia/cuda-arm64 and nvidia/cuda-ppc64le will remain available, but no longer supported.

The following product pages still exist but will no longer be supported:

https://hub.docker.com/r/nvidia/cuda-ppc64le
https://hub.docker.com/r/nvidia/cuda-arm64

The following gitlab repositories will be archived:

https://gitlab.com/nvidia/container-images/cuda-ppc64le

Deprecated: "latest" tag

The "latest" tag for CUDA, CUDAGL, and OPENGL images has been deprecated on NGC and Docker Hub.

With the removal of the latest tag, the following use case will result in the "manifest unknown" error:

$ docker pull nvidia/cuda
Error response from daemon: manifest for nvidia/cuda:latest not found: manifest unknown: manifest
unknown

This is not a bug.

Overview of Images

Three flavors of images are provided:

base: Includes the CUDA runtime (cudart)
runtime: Builds on the base and includes the https://developer.nvidia.com/gpu-accelerated-libraries, and https://developer.nvidia.com/nccl. A runtime image that also includes https://developer.nvidia.com/cudnn is available. Some images may also include https://developer.nvidia.com/tensorrt.
devel: Builds on the runtime and includes headers, development tools for building CUDA images. These images are particularly useful for multi-stage builds.

The Dockerfiles for the images are open-source and licensed under 3-clause BSD. For more information see the Supported Tags section below.

NVIDIA Container Toolkit

The https://github.com/NVIDIA/nvidia-container-toolkit for Docker is required to run CUDA images.

For CUDA 10.0, nvidia-docker2 (v2.1.0) or greater is recommended. It is also recommended to use Docker 19.03.

How to report a problem

Read https://github.com/NVIDIA/nvidia-container-toolkit/issues to see if the problem has been encountered before.

After it has been determined the problem is not with the NVIDIA runtime, report an issue at the https://gitlab.com/nvidia/container-images/cuda/-/work_items.

Supported tags

Supported tags are updated to the latest CUDA, cuDNN, and TensorRT versions. These tags are also periodically updated to fix CVE vulnerabilities.

For a full list of supported tags, click https://gitlab.com/nvidia/container-images/cuda/blob/master/doc/supported-tags.md.

LATEST CUDA 13.4.2

Visit https://developer.download.nvidia.com/compute/cuda/opensource/image/ for the GPL sources of the packages contained in the CUDA base image layers.

ubuntu26.04 [arm64, x86_64]

https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/ubuntu2604/runtime/tensorrt/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/ubuntu2604/runtime/cudnn/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/ubuntu2604/runtime/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/ubuntu2604/devel/tensorrt/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/ubuntu2604/devel/cudnn/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/ubuntu2604/devel/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/ubuntu2604/base/Dockerfile

ubuntu24.04 [arm64, x86_64]

https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/ubuntu2404/runtime/tensorrt/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/ubuntu2404/runtime/cudnn/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/ubuntu2404/runtime/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/ubuntu2404/devel/tensorrt/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/ubuntu2404/devel/cudnn/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/ubuntu2404/devel/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/ubuntu2404/base/Dockerfile

ubuntu22.04 [arm64, x86_64]

https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/ubuntu2204/runtime/cudnn/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/ubuntu2204/runtime/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/ubuntu2204/devel/cudnn/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/ubuntu2204/devel/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/ubuntu2204/base/Dockerfile

ubi9 [arm64, x86_64]

https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/ubi9/runtime/cudnn/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/ubi9/runtime/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/ubi9/devel/cudnn/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/ubi9/devel/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/ubi9/base/Dockerfile

ubi8 [arm64, x86_64]

https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/ubi8/runtime/cudnn/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/ubi8/runtime/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/ubi8/devel/cudnn/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/ubi8/devel/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/ubi8/base/Dockerfile

ubi10 [arm64, x86_64]

https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/ubi10/runtime/cudnn/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/ubi10/runtime/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/ubi10/devel/cudnn/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/ubi10/devel/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/ubi10/base/Dockerfile

suse16 [arm64, x86_64]

https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/suse16/runtime/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/suse16/devel/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/suse16/base/Dockerfile

rockylinux9 [arm64, x86_64]

https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/rockylinux9/runtime/cudnn/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/rockylinux9/runtime/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/rockylinux9/devel/cudnn/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/rockylinux9/devel/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/rockylinux9/base/Dockerfile

rockylinux8 [arm64, x86_64]

https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/rockylinux8/runtime/cudnn/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/rockylinux8/runtime/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/rockylinux8/devel/cudnn/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/rockylinux8/devel/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/rockylinux8/base/Dockerfile

rockylinux10 [arm64, x86_64]

https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/rockylinux10/runtime/cudnn/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/rockylinux10/runtime/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/rockylinux10/devel/cudnn/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/rockylinux10/devel/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/rockylinux10/base/Dockerfile

oraclelinux9 [arm64, x86_64]

https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/oraclelinux9/runtime/cudnn/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/oraclelinux9/runtime/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/oraclelinux9/devel/cudnn/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/oraclelinux9/devel/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/oraclelinux9/base/Dockerfile

oraclelinux8 [arm64, x86_64]

https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/oraclelinux8/runtime/cudnn/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/oraclelinux8/runtime/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/oraclelinux8/devel/cudnn/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/oraclelinux8/devel/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/oraclelinux8/base/Dockerfile

oraclelinux10 [arm64, x86_64]

https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/oraclelinux10/runtime/cudnn/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/oraclelinux10/runtime/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/oraclelinux10/devel/cudnn/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/oraclelinux10/devel/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/oraclelinux10/base/Dockerfile

opensuse15 [x86_64]

https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/opensuse15/runtime/cudnn/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/opensuse15/runtime/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/opensuse15/devel/cudnn/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/opensuse15/devel/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/opensuse15/base/Dockerfile

azl3 [arm64, x86_64]

https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/azl3/runtime/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/azl3/devel/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/azl3/base/Dockerfile

amzn2023 [arm64, x86_64]

https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/amzn2023/runtime/cudnn/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/amzn2023/runtime/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/amzn2023/devel/cudnn/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/amzn2023/devel/Dockerfile
https://gitlab.com/nvidia/container-images/cuda/blob/master/dist/13.4.2/amzn2023/base/Dockerfile

Unsupported tags

A list of tags that are no longer supported can be found https://gitlab.com/nvidia/container-images/cuda/blob/master/doc/unsupported-tags.md

Source of this description

This https://gitlab.com/nvidia/container-images/cuda/blob/master/doc/README.md is located in the doc directory of the CUDA Container Image source repository. (https://gitlab.com/nvidia/container-images/cuda/commits/master/doc/README.md)

Help

If you run into any issues, please file an issue at https://gitlab.com/nvidia/container-images/cuda/-/work_items.

Deployment & Usage Documentation

NVIDIA CUDA 镜像 Docker 容器化部署全流程

CPU 像“全能但慢的多面手”，适合处理逻辑复杂但数据量小的任务；GPU 像“成千上万的小工人”，擅长同时处理大量重复、简单的计算。CUDA 就是连接开发者与 GPU 能力的“桥梁”，让 GPU 能脱离显卡驱动，直接为科学计算、AI 训练、数据处理等任务服务。

镜像拉取方式

您可以使用以下命令拉取该镜像。请将 <标签> 替换为具体的标签版本。如需查看所有可用标签版本，请访问标签列表页面。

轩辕镜像加速拉取命令点我查看更多 cuda 镜像标签

docker pull docker.xuanyuan.run/nvidia/cuda:<标签>

使用方法：

DockerHub 原生拉取命令

docker pull nvidia/cuda:<标签>

轩辕镜像配置手册

按平台快速找到配置文档

一键安装

一键安装 Docker

Linux Docker 一键安装

AI

用 AI 使用轩辕镜像

agents.md · AI 对话 · 提示词

Docker

登录仓库拉取

登录认证 · 私有仓库

专属域名拉取

免登录 · 高速拉取

Linux

Docker 镜像配置

Windows / Mac

Docker Desktop 配置

MacOS OrbStack

OrbStack 容器

Apple Container

macOS 原生容器

Docker Compose

Compose 项目配置

NAS

群晖

Synology 配置

飞牛

fnOS 镜像配置

绿联

绿联 NAS

威联通

QNAP 配置

极空间

极空间 NAS

Unraid

Unraid NAS

企业仓库

其他仓库

ghcr · Quay · nvcr

Harbor 镜像源

Proxy Repository 对接

Portainer 镜像源

Registries 配置

Nexus 镜像源

Docker Proxy 缓存

开发工具

Dev Containers

VS Code 开发容器

Podman

Podman 配置指南

Singularity / Apptainer

HPC 科学计算容器

Kubernetes

K8s Containerd

Kubernetes · Containerd

K3s

轻量级集群

面板 / 网络

爱快路由

爱快 4.0 · iKuai 镜像加速

宝塔面板

一键配置镜像源

需要其他帮助？请查看我们的常见问题Docker 镜像访问常见问题解答或提交工单

镜像拉取常见问题

功能

版本功能对比

功能对比 · 版本选择

支持的镜像仓库

Docker Hub · GCR · GHCR

专属域名用法

专属域名 · 开启停用 · 多仓库

新手拉取配置

docker search 限制

专属域名 · Hub 搜索

不支持 push

仅支持 pull · 不支持

拉取速度原因

带宽 · 缓存 · 冷热镜像

错误码

402 与流量用尽

402 · 流量包 · 充值

401 认证失败

401 · docker login

manifest unknown

标签错误 · 镜像不存在

410 Gone 排查

410 · Docker 升级

429 限流

免费版 · 专业版 · 企业版 · 请求频率

其他报错

DNS 超时

DNS 解析 · 网络超时

TLS 证书失败

no matching manifest（架构）

docker.sock / daemon

账号

失败是否计费

manifest · blob · 计费

申请开票（企业 / 个人）

开票 · 发票 · 工单

修改登录密码

网站 · 仓库 · 重置

注销账户

工单 · 数据 · 注销

原理

mirrors 不生效

daemon.json · 重启

去掉域名前缀

docker tag · 重命名

指定架构拉取

ARM64 · AMD64 · 多架构

latest 与「最新」

digest · 版本号 · 标签

查看全部问题→

用户好评

来自真实用户的反馈，见证轩辕镜像的优质服务

oldzhang

运维工程师

Linux服务器

"Docker访问体验非常流畅，大镜像也能快速完成下载。"