CoreWeave Leads AI Infrastructure with NVIDIA H200 Tensor Core GPUs

CoreWeave, the AI Hyperscaler™, has announced its pioneering move to become the first cloud provider to introduce NVIDIA H200 Tensor Core GPUs to the market, according to PRNewswire. This development marks a significant milestone in the evolution of AI infrastructure, promising enhanced performance and efficiency for generative AI applications.

Advancements in AI Infrastructure

The NVIDIA H200 Tensor Core GPU is engineered to push the boundaries of AI capabilities, boasting 4.8 TB/s memory bandwidth and 141 GB GPU memory capacity. These specifications enable up to 1.9 times higher inference performance compared to the previous H100 GPUs. CoreWeave has leveraged these advancements by integrating H200 GPUs with Intel’s fifth-generation Xeon CPUs (Emerald Rapids) and 3200Gbps of NVIDIA Quantum-2 InfiniBand networking. This combination is deployed in clusters with up to 42,000 GPUs and accelerated storage solutions, significantly reducing the time and cost required to train generative AI models.

CoreWeave’s Mission Control Platform

CoreWeave’s Mission Control platform plays a pivotal role in managing AI infrastructure. It offers high reliability and resilience through software automation, which streamlines the complexities of AI deployment and maintenance. The platform features advanced system validation processes, proactive fleet health-checking, and extensive monitoring capabilities, ensuring customers experience minimal downtime and reduced total cost of ownership.

Michael Intrator, CEO and co-founder of CoreWeave, stated, “CoreWeave is dedicated to pushing the boundaries of AI development. Our collaboration with NVIDIA allows us to offer high-performance, scalable, and resilient infrastructure with NVIDIA H200 GPUs, empowering customers to tackle complex AI models with unprecedented efficiency.”

Scaling Data Center Operations

To meet the growing demand for its advanced infrastructure services, CoreWeave is rapidly expanding its data center operations. Since the beginning of 2024, the company has completed nine new data center builds, with 11 more in progress. By the end of the year, CoreWeave expects to have 28 data centers globally, with plans to add another 10 in 2025.

Industry Impact

CoreWeave’s rapid deployment of NVIDIA technology ensures that customers have access to the latest advancements for training and running large language models for generative AI. Ian Buck, vice president of Hyperscale and HPC at NVIDIA, highlighted the importance of this partnership, stating, “With NVLink and NVSwitch, as well as its increased memory capabilities, the H200 is designed to accelerate the most demanding AI tasks. When paired with the CoreWeave platform powered by Mission Control, the H200 provides customers with advanced AI infrastructure that will be the backbone of innovation across the industry.”

About CoreWeave

CoreWeave, the AI Hyperscaler™, offers a cloud platform of cutting-edge software powering the next wave of AI. Since 2017, CoreWeave has operated a growing footprint of data centers across the US and Europe. The company was recognized as one of the TIME100 most influential companies and featured on the Forbes Cloud 100 ranking in 2024. For more information, visit www.coreweave.com.

Image source: Shutterstock