Amaryllo Group

With generative AI and large language models (LLMs) advancing rapidly, building a GPU cluster is no longer just about “having GPUs.” When a cluster reaches dozens or even hundreds of nodes, the real differentiator is not raw hardware but how well the cluster is designed, administered, and optimized for real-world AI workloads.

Amaryllo is thrilled to announce a strategic partnership between its Global Supercomputing Network (GSN) and G-TECH Corp. 株式会社 in Japan. This collaboration aims to promote and expand access to hyperscale supercomputing services powered by NVIDIA's cutting-edge Blackwell Ultra architecture, including the high-performance B300 GPUs and GB300 NVL72 systems.

As artificial intelligence continues to grow, it is important to measure how efficiently hardware and software can handle real-world AI workloads. The MLPerf Inference 5.1 benchmark provides a standardized way to do this. In recent tests, the Cisco C845A rack server, equipped with eight NVIDIA H200 NVL PCIe GPUs, was used to evaluate the performance of Meta’s Llama2-70B, a large language model with 70 billion parameters.