HPE Updates NVIDIA-Powered AI Factory and Supercomputers
HPE unveiled updates to its NVIDIA AI Computing by HPE portfolio, combining compute, GPUs, networking, liquid cooling, software, and services for exascale and sovereign AI deployments. The release introduces the GX240 blade with up to 16 NVIDIA Vera CPUs, the Vera Rubin NVL72 rack for frontier models exceeding one trillion parameters, Quantum-X800 InfiniBand support, and availability timelines from Spring 2026 to early 2027.
Key Points
- 1Introduces GX240 blade with up to 16 NVIDIA Vera CPUs, 640 CPUs and 56,320 Arm cores per rack
- 2Expands exascale and AI convergence by integrating Rubin GPUs, NVLink, Quantum-X800, and liquid cooling
- 3Enables providers and sovereigns to deploy multi-tenant, high-density AI factories with accelerated networking and management
Scoring Rationale
Significant hardware-software integration across exascale and AI stacks; limited novelty relative to prior NVIDIA-HPE collaborations constrains breakthrough potential.
Sources
Public references used for this report.
Practice interview problems based on real data
1,625 SQL & Python problems across 15 industry datasets — the exact type of data you work with.
Try 250 free problems
