Keep up with the ever-evolving AI landscape
Unlock exclusive AI content by subscribing to our newsletter!!
IBM Partners With AMD; Expands AI Accelerator Offerings
Companies launching AMD Instinct MI300X accelerators as a service in 2025
2 Min Read
AMD
IBM and AMD have announced a collaboration to improve the performance and power efficiency of generative AI models and high-performance computing applications.
The companies plan to make AMD Instinct MI300X accelerators available as a service to enterprise clients on IBM Cloud in the first half of 2025 for generative AI inferencing workloads.
The accelerators will integrate with IBM's watsonx AI and data platform to provide additional AI infrastructure resources for scaling AI workloads across hybrid cloud environments.
It will also enable Red Hat Enterprise Linux AI and Red Hat OpenShift AI platforms to run Granite family large language models (LLMs) with alignment tooling using InstructLab on MI300X accelerators.
“As enterprises continue adopting larger AI models and datasets, it is critical that the accelerators within the system can process compute-intensive workloads with high performance and flexibility to scale,” said Philip Guido, AMD executive vice president and chief commercial officer.
“AMD Instinct accelerators combined with AMD ROCm software offer wide support including IBM watsonx AI, Red Hat Enterprise Linux AI and Red Hat OpenShift AI platforms to build leading frameworks using these powerful open ecosystem tools. Our collaboration with IBM Cloud will aim to allow customers to execute and scale generative AI inferencing without hindering cost, performance or efficiency.”
The partners intend to use IBM Cloud’s security and compliance capabilities to support highly regulated industries.
“AMD and IBM Cloud share the same vision around bringing AI to enterprises. We’re committed to bringing the power of AI to enterprise clients, helping them prioritize their outcomes and ensuring they have the power of choice when it comes to their AI deployments,” said Alan Peacock, IBM Cloud general manager.
“Leveraging AMD’s accelerators on IBM Cloud will give our enterprise clients another option to scale to meet their enterprise AI needs, while also aiming to help them optimize cost and performance.”
AMD Instinct MI300X accelerators have 192GB of high-bandwidth memory to support large model inferencing and fine-tuning. A larger memory capacity means larger models can run on fewer GPUs, which could bring down costs.
The proposed architecture would offer access to AMD Instinct MI300X accelerators as a service on IBM Cloud Virtual Servers for VPC and through container support with IBM Cloud Kubernetes Service and IBM Red Hat OpenShift on IBM Cloud. According to the companies, this could help optimize performance and security for enterprises running AI applications.
About the Author
You May Also Like
