AMD will ship its Helios rack-scale AI platform in H2 2026, delivering 1.4 exaFLOPS per rack with Microsoft Azure, Meta, and Oracle as early deployers.

AMD is taking aim at Nvidia with Helios, its first AI rack system, and has landed Microsoft as a new customer, joining Meta, OpenAI and Oracle.

But it’s not clear just how much AMD AI compute Microsoft is buying

AMD will ship its Helios rack-scale AI platform in H2 2026, delivering 1.4 exaFLOPS per rack with Microsoft Azure, Meta, and Oracle as early deployers.

Microsoft will deploy AMD's next-gen Instinct MI455X GPUs and EPYC Venice processors in Azure, intensifying competition with NVIDIA in AI compute.

AMD Helios packs 72 MI455X GPUs, 31TB of HBM4, and 2.9 exaflops of inference compute into a single rack. Engineering samples ship H2 2026. Mass production in Q2 2027.

AMD e Microsoft rafforzano la collaborazione strategica portando la piattaforma rack-scale Helios nei data center Azure. La soluzione integra GPU Instinct MI455X, CPU EPYC Venice,…

Alongside its existing NVIDIA systems and proprietary Maia silicon, Microsoft is positioning Azure as a highly flexible AI cloud environment with the new expanded partnership with…

Microsoft amplia l’intesa con AMD: Helios su Azure, nuove vm Venice e più networking Pensando per i servizi AI cloud

AMD zieht einen Deal in der Azure-Cloud an Land. Microsoft kauft Epyc-Venice-Prozessoren und hochpreisige KI-Beschleuniger.

Microsoft will use AMD's Helios AI system in Azure data centers, boosting AMD's challenge to Nvidia as competition in the AI chip market intensifies.

Microsoft will use AMD’s AI-optimized Helios racks in Azure - SiliconANGLE