KR6288

6U 8 GPU AI Server with NVIDIA HGX H200 8-GPUs

Massive Performance for Next-Generation AI Workloads

KR6288 is an advanced AI system made for hyperscale data centers, delivering high performance with NVIDIA HGX H200 8-GPUs. This server delivers industry-leading 32 PFlops of AI performance and lightning-fast CPU-to-GPU interconnect bandwidth, with the H200 Transformer Engine supercharging training speeds for GPT large language models. Its optimized power efficiency and modular design with flexible configuration makes it ideal for the most demanding AI tasks in various scenarios like hyperscale data centers, AI model training, and metaverse workloads.

Unprecedented AI Performance

Powered by NVIDIA HGX H200 8-GPU

2x latest Intel® Xeon® or AMD EPYC™ processors

32 PFlops of industry-leading AI performance

H200 Transformer Engine delivers supercharged training speed for GPT large language models


Leading Architecture Design

Lightning-fast CPU-to-GPU interconnect bandwidth

Ultra-high scalable inter-node networking with up to 4.0 Tbps non-blocking bandwidth

Optimized cluster-level architecture with 8:8:2 ratio of GPU to compute network to storage network


Optimized Energy Efficiency

Low air-cooled heat dissipation overhead and high power efficiency

54V, 12V separated power supply with N+N redundancy reducing power conversion loss

Direct liquid cooling design with over 80% cold plate coverage keeps PUE ≤1.15


Flexible Configurations for AI Scenarios

Fully modular design and flexible configurations satisfy both on-premises and cloud deployment

Easily harness large-scale model training, such as GPT-3, MT-NLG, stable diffusion and Alphafold

Diversified SuperPod solutions accelerating the most cutting-edge innovation including AIGC, AI4Science and Metaverse

 


Available Models

KR6288-E2

with AMD EPYC™ 9004 processors

Learn More

KR6288-X2

with 4th Gen Intel® Xeon® Scalable processors

Learn More

KR6288V2 Technical Resources