Nvidia Jumps on Super Micro Saying Blackwell-Based System Ready

Nvidia, the world's leading graphics and compute solutions provider, has announced a significant partnership with Super Micro, a global leader in architecting and deploying comprehensive rack-scale solutions tailored for AI and HPC. The collaboration brings forth the new SuperCluster solutions, which are designed to accelerate the deployment of generative AI and meet the most demanding customer requirements for optimal performance, scalability, and efficiency. The partnership is a key enabler for the rapid evolution of generative AI and large language models (LLMs) in the AI and HPC market landscape.



The new SuperCluster solutions feature the NVIDIA HGX H100/H200 8-GPU systems, which double the density of the 8U air-cooled system by using liquid cooling. This reduces energy consumption and lowers data center TCO. The systems are designed to support the next-generation NVIDIA Blackwell architecture-based GPUs, which are ideal for training generative AI. The high-speed interconnected GPUs through NVIDIA® NVLink®, high GPU memory bandwidth, and capacity are key for running LLM models cost-effectively.

The partnership between Nvidia and Super Micro enables the delivery of complete generative AI clusters to customers faster than ever before, with expanded global manufacturing capacity of 5,000 racks/month. This collaboration allows for the deployment of powerful LLM training performance, as well as large batch size and high-volume LLM inference. The interconnected GPUs, CPUs, memory, storage, and networking, when deployed across multiple nodes in racks, construct the foundation of today's AI. Super Micro's SuperCluster solutions combined with Nvidia AI Enterprise software are ideal for enterprise and cloud infrastructures to train today's LLMs with up to trillions of parameters.



The partnership between Nvidia and Super Micro is a significant factor in the AI and HPC market landscape. The new SuperCluster solutions provide foundational building blocks for the present and the future of large language model (LLM) infrastructure. These solutions are designed to meet the most demanding customer requirements to ensure optimal performance, scalability, and efficiency. Nvidia's Networking Platforms serve as the nervous system for compute infrastructure. Both Nvidia Spectrum-X and Quantum-2 InfiniBand are available today to meet the demands of AI and HPC workloads. The partnership between Nvidia and Super Micro enables the delivery of complete generative AI clusters to customers faster than ever before, with expanded global manufacturing capacity of 5,000 racks/month. This collaboration allows for the deployment of powerful LLM training performance, as well as large batch size and high-volume LLM inference. The interconnected GPUs, CPUs, memory, storage, and networking, when deployed across multiple nodes in racks, construct the foundation of today's AI. Super Micro's SuperCluster solutions combined with Nvidia AI Enterprise software are ideal for enterprise and cloud infrastructures to train today's LLMs with up to trillions of parameters.