Skip to content
<open-source>
Oeiuwq Faith Blog OpenSource Porfolio

ROCm/ROCm

AMD ROCm™ Software - GitHub Home
Source code at GitHub https://rocm.docs.amd.com
ROCm/ROCm.json
{
  "createdAt": "2016-03-18T00:24:29Z",
  "defaultBranch": "develop",
  "description": "AMD ROCm™ Software - GitHub Home",
  "fullName": "ROCm/ROCm",
  "homepage": "https://rocm.docs.amd.com",
  "language": "Shell",
  "name": "ROCm",
  "pushedAt": "2026-07-10T13:19:18Z",
  "stargazersCount": 6679,
  "topics": [
    "documentation"
  ],
  "updatedAt": "2026-07-12T20:00:46Z",
  "url": "https://github.com/ROCm/ROCm"
}
ROCm logo

Open-source stack designed for GPU computation

Docs • Blogs • Tutorials • Deep learning frameworks • ROCm for AI

AMD ROCm™ software

Section titled “AMD ROCm™ software”

ROCm is an open-source stack, composed primarily of open-source software, designed for graphics processing unit (GPU) computation. ROCm consists of a collection of drivers, development tools, and APIs that enable GPU programming from low-level kernel to end-user applications.

You can customize the ROCm software to meet your specific needs. You can develop, collaborate, test, and deploy your applications in a free, open-source, integrated, and secure software ecosystem. ROCm is particularly well-suited to GPU-accelerated high-performance computing (HPC), artificial intelligence (AI), scientific computing, and computer-aided design (CAD).

ROCm is powered by HIP, a C++ runtime API and kernel language for AMD GPUs. HIP allows developers to create portable applications by providing a programming interface that is similar to NVIDIA CUDA™.

ROCm supports programming models, such as OpenMP and OpenCL, and includes all necessary open-source software compilers, debuggers, and libraries. ROCm is fully integrated into machine learning (ML) frameworks, such as PyTorch and TensorFlow.

[!IMPORTANT] A new open-source build platform for ROCm is under development at https://github.com/ROCm/TheRock, featuring a unified CMake build with bundled dependencies, Microsoft Windows support, and more.

Table of contents

Section titled “Table of contents”
  • [Supported hardware and operating systems]!(#supported-hardware-and-operating-systems)
  • [Quick start]!(#quick-start)
    • [Get started with ROCm]!(#get-started-with-rocm)
    • [Get started with PyTorch on ROCm]!(#get-started-with-pytorch-on-rocm)
  • [Core components]!(#core-components)
    • [Math libraries]!(#math-libraries)
    • [ML and computer vision]!(#ml-and-computer-vision)
    • [Collective communication and primitives]!(#collective-communication-and-primitives)
    • [System management tools]!(#system-management-tools)
    • [Profiling tools]!(#profiling-tools)
    • [Development tools]!(#development-tools)
    • [Runtimes and compilers]!(#runtimes-and-compilers)
  • [Release notes]!(#release-notes)
  • [Licenses]!(#licenses)
  • [ROCm release history]!(#rocm-release-history)
  • [Contribute]!(#contribute)

Supported hardware and operating systems

Section titled “Supported hardware and operating systems”

Use the Compatibility matrix for official support across ROCm versions, operating system kernels, and GPU architectures (CDNA/Instinct™, RDNA/Radeon™, and Radeon Pro). Recent releases cover Ubuntu, RHEL, SLES, Oracle Linux, Debian, Rocky Linux, and more. GPU targets include CDNA4, CDNA3, CDNA2, RDNA4, and RDNA3.

If you’re using AMD Radeon GPUs or Ryzen APUs in a workstation setting with a display connected, see the ROCm on Radeon and Ryzen documentation for operating system/framework support and step-by-step installation instructions.

Quick start

Section titled “Quick start”

Follow these instructions to start using ROCm.

Get started with ROCm

Section titled “Get started with ROCm”

Follow the ROCm installation guide to install ROCm on your system.

Get started with PyTorch on ROCm

Section titled “Get started with PyTorch on ROCm”

Follow the PyTorch on ROCm installation guide to install PyTorch with ROCm support in a Docker environment.

Core components

Section titled “Core components”

The core ROCm stack consists of the following components:

Math libraries

Section titled “Math libraries”

ML and computer vision

Section titled “ML and computer vision”

Collective communication and primitives

Section titled “Collective communication and primitives”

System management tools

Section titled “System management tools”

Profiling tools

Section titled “Profiling tools”

Development tools

Section titled “Development tools”

Runtimes and compilers

Section titled “Runtimes and compilers”

For a complete list of ROCm components and version information, see the ROCm components.

Release notes

Section titled “Release notes”

Licenses

Section titled “Licenses”

ROCm release history

Section titled “ROCm release history”

For information on older ROCm releases, see the ROCm release history.

Contribute

Section titled “Contribute”

AMD welcomes ROCm contributions using GitHub PRs or issues. See the links below for contribution guidelines.