AMD ROCm Software
AMD ROCm software includes a broad set of libraries, runtimes, compilers, and tools for AI and HPC solution development on AMD GPUs.
Advancing AI with End-to-End Solutions
Only AMD powers the full spectrum of AI, bringing together leadership CPUs, GPUs and other accelerators, networking, and open software to deliver unmatched flexibility and performance.
Accelerated AI Outcomes
- Prepare for AI
- Scale AI Across the Enterprise
- Execute AI Faster
Prepare for AI
Maximize space, power, and OPEX savings when modernizing your existing data centers.
That savings in capital and data center space opens the door to AI expansion.
Scale AI Across the Enterprise
Existing x86 applications can be retained without code re-writes.
Leading CPU and GPU offerings mean optimizing workloads between GPU systems and CPU systems, offering another fast and efficient way to scale.
Execute AI Faster
Choose a partner that sets the high watermark for speed and performance.
AMD technology-based cloud instances boost performance and slash OPEX.
Sustained AI Success
- Minimize Costs
- Prioritize Security
- Stay Flexible
Minimize Costs
Prioritize reducing your operational costs associated with running AI in the long term.
AMD provides leadership data center CPU and GPU performance-per-watt, meaning it can take less space and power utilization and lower licensing costs to achieve the same results.
Prioritize Security
Emphasize security throughout the entire AI environment.
It starts with built-in security features on-chip, focused on shared, open industry security standards in AMD Infinity Guard.1
Then at the software level, avoiding code rewrites helps limit the vulnerabilities that can be introduced.
Stay Flexible
Choose a partner that supports an open ecosystem to avoid proprietary lock-ins.
Industry leaders in compute, networking, storage, and software are all innovating daily.
With our open source approach, AMD customers can take advantage of a variety of AI advancements.
Trusted AI Partner
- Broad AI Portfolio
- Work with a Committed Partner
- Plan with Confidence
Broad AI Portfolio
Access an end-to-end product portfolio.
AMD provides a choice of CPU, GPU, and adaptive computing solutions and is also a leading cluster-level design and product integration partner.
Work with a Committed Partner
Collaborate with AI experts to create unique solutions for your specific needs.
When a new customer works with AMD on a real-world test of their workloads, they overwhelmingly decide that AMD is the right partner for them.
Plan with Confidence
Choose to partner with a stable, decades old technology leader that continually invests in research and development.
AMD has a long history of reliably delivering on product roadmaps and performance projections.
The Latest in AI from AMD
-
Maximizing AI Performance: The Role of AMD EPYC 9575F CPUs in Latency-Constrained Inference Serving
What are the key benefits of running AI inference on a CPU? How can CPUs be utilized for AI? Are GPUs truly required? Join us as we explore CPU infere…
June 12, 2025
-
Introducing the AMD Developer Cloud
The AMD Developer Cloud is an ease-of-use developer platform engineered to democratize access to AMD Instinct™ GPUs, empowering developers, academics,…
June 12, 2025
-
AMD Instinct MI350 Series and Beyond: Accelerating the Future of AI and HPC
AMD introduces its new MI350 Series GPUs for AI and HPC workloads, ROCm 7 software, and previews next-gen Instinct MI400 and “Helios” AI rack
June 12, 2025
-
Enabling the Future of AI: Introducing AMD ROCm 7 and AMD Developer Cloud
AMD introduces its new AMD ROCm7 open-source AI software stack and the AMD Developer Cloud, enabling the AI developer ecosystem.
June 12, 2025
-
AMD Delivering Open Rack Scale AI Infrastructure
AMD delivers open rack-scale AI solution and previews next generation “Helios” AI rack based on Next Generation Instinct, EPYC and Pensando products
June 12, 2025
-
Aligning Mixtral 8x7B with TRL on AMD GPUs — ROCm Blogs
This blog demonstrates how to fine-tune and align Mixtral 8x7B with TRL using DPO and evaluate it on AMD GPUs.
June 11, 2025
-
Introducing Instella-Long: A Fully Open Language Model with Long-Context Capability — ROCm Blogs
Learn about Instella-Long: AMD’s open 3B language model supporting 128K context, trained on MI300X GPUs, outperforming peers on long-context benchmark…
June 10, 2025
-
AI PCs and the Enterprise: Why Now is the Time to Modernize
Aging PCs hold businesses back. PCs are the most important productivity tool and these systems can limit or expand the capabilities of users.
June 10, 2025
For Developers
Find the resources you need to develop your AI applications using AMD products. Access software downloads, documentation portals, training resources, communities, support forums, and more.
The Broadest Portfolio
AMD is the only AI technology partner that provides a choice of CPU, GPU, and adaptive computing solutions, helping ensure workload-optimized architectures with open standards giving you freedom of vendor choice. This end-to-end portfolio enables AI deployments tailored to customer needs.
Develop and Deploy Advanced AI with AMD Silo AI
AMD Silo AI enables businesses to design, build, and deploy cutting-edge AI solutions tailored to their unique needs. With deep expertise in AI model development, optimization, and deployment, Silo AI helps organizations unlock the full potential of artificial intelligence.
From foundation models to custom AI solutions, AMD Silo AI provides the technology and expertise to accelerate AI innovation, optimize performance, and seamlessly integrate AI into real-world applications. Whether you’re scaling AI workloads or developing next-generation AI-driven products, Silo AI delivers the tools to turn your AI ambitions into reality.
Customer Stories
- Advanced Research
- Automotive
- Healthcare
- Industrial
- Public Sector
- Telecommunications
Advanced Research
Discover how AI solutions powered by AMD are helping drive advanced research.
Automotive
Learn how AI solutions powered by AMD are accelerating the development of autonomous vehicles and intelligent transportation systems.
Healthcare
Discover how AI solutions powered by AMD are helping enhance drug formulation, molecular dynamics, cancer research, and more.
Industrial
See how AI solutions powered by AMD are enabling industrial use cases ranging from food inspection, to real-time office space management, to workflow automation with AI-driven robotics.
Public Sector Solutions
Learn how AMD can help governments around the world unlock the promise of AI to drive economic growth, protect national interests, and reveal new scientific frontiers.
Telecommunications
Discover how AI solutions powered by AMD are advancing the telecommunications industry.
Footnotes
- GD-183A: AMD Infinity Guard features vary by EPYC™ Processor generations and/or series. Infinity Guard security features must be enabled by server OEMs and/or Cloud Service Providers to operate. Check with your OEM or provider to confirm support of these features. Learn more about Infinity Guard at http://www.amd.com/en/products/processors/server/epyc/infinity-guard.html.
- PHX-3A As of May 2023, AMD has the first available dedicated AI engine on an x86 Windows processor, where 'dedicated AI engine' is defined as an AI engine that has no function other than to process AI inference models and is part of the x86 processor die. For detailed information, please check: https://www.amd.com/en/technologies/xdna.html.
Footnotes
- GD-183A: AMD Infinity Guard features vary by EPYC™ Processor generations and/or series. Infinity Guard security features must be enabled by server OEMs and/or Cloud Service Providers to operate. Check with your OEM or provider to confirm support of these features. Learn more about Infinity Guard at http://www.amd.com/en/products/processors/server/epyc/infinity-guard.html.
- PHX-3A As of May 2023, AMD has the first available dedicated AI engine on an x86 Windows processor, where 'dedicated AI engine' is defined as an AI engine that has no function other than to process AI inference models and is part of the x86 processor die. For detailed information, please check: https://www.amd.com/en/technologies/xdna.html.