NVIDIA H100
fast, secure and revolutionary
Multiple GPUs are essential for large data sets, complex simulations and GenAI and HPC workflows: the ninth-generation data center NVIDIA H100 Cloud GPUs are designed to deliver an order-of-magnitude performance leap for large-scale GenAI and HPC workloads over the prior-generation NVIDIA A100 GPUs.
- Faster matrix computations than ever before on an even broader array of GenAI and HPC workloads
- Secure Multi-Instance GPU (MIG) partitions the GPU into isolated, right-size instances to maximize quality of service (QoS) for smaller tasks
- Up to 9X faster AI training and up to 30X faster AI inference compared to the prior GPU generation
Offering sustainable and European Generative AI Infrastructure as a Service, we are certified as an Elite Partner of NVIDIA and an official Cloud Service Provider in NVIDIA’s Partner Network (NPN).
NVIDIA H100 GPU benefits
Hosted in Europe
Achieve sovereignty and compliance standards
Non-blocking network
DE-CIX access and low latency (sub 10Ms)
No overbooking
NVIDIA GPUs as well as CPU and RAM resources
InfiniBand Pods of 512 GPUs
Pods are connected into islands of four pods each (2,048 GPUs) using NVIDIA BlueField DPUs and the NVIDIA Quantum-2 InfiniBand platform. This configuration offers efficient and quick means of training LLMs. It delivers Generative AI solutions in a much shorter timeframe.
PUE performance between 1.15 and 1.09
We leverage best-in-class infrastructure to ensure the environmental footprint of your compute-intensive processes is as light as possible.
