Unparalleled AI performance: A powerhouse that contains 72 NVIDIA Blackwell GPUs and 36 Grace CPUs for exceptional AI inference and training.
Superior efficiency: The full-rack solution is a symphony of GPUs, CPUs and switches harmonizing in lightning-fast, direct communication, turbocharging trillion-parameter LLM training and real-time inference.
High-speed interconnect: Features fifth-generation NVIDIA NVLink technology, 14.4TB/s switching capacity for high-bandwidth, low-latency GPU connections within a single rack, enabling seamless communication and superior throughput.
Advanced cooling portfolio: Supports both liquid-to-air and liquid-to-liquid cooling solutions, unleashing optimal AI computing performance while ensuring effective heat dissipation.