Compal Introduces High-Density NVIDIA HGX™ Rubin NVL8 Integrated Solution at GTC 2026

Compal Electronics showcased its high-density AI server solution based on the NVIDIA HGX Rubin NVL8 at NVIDIA GTC 2026. The company, stock code 2324, aligned the presentation with the NVIDIA Vera Rubin architecture. This architecture is described as Six New Chips One AI Supercomputer. The NVIDIA Vera Rubin architecture integrates the NVIDIA Vera CPU, the NVIDIA Rubin GPU, the NVIDIA NVLink 6 Switch, the NVIDIA BlueField-4 DPU, the NVIDIA Spectrum-X Ethernet and the NVIDIA ConnectX-9 SuperNIC. It forms a comprehensive heterogeneous computing architecture. The NVL72 rack-scale configuration delivers up to 260 TB/s of total bandwidth and enables 3.6 TB/s of all-to-all bandwidth per GPU, supporting MoE models and large-scale training and inference workloads. Compal is introducing the SG231-2-L1 based on the NVIDIA HGX Rubin NVL8. In its booth the company is also featuring an NVIDIA Vera CPU HPM module based on the NVIDIA HGX system. This highlights engineering readiness and manufacturing capabilities aligned with the NVIDIA Vera Rubin platform. Alan Chang, vice president of Compal's Infrastructure Systems Business Group, stated that competition in AI infrastructure has shifted from single-node performance comparisons to overall deployment efficiency and long-term scalability. As the NVIDIA HGX Rubin NVL8 platform advances in both performance and power density, data center architecture must evolve accordingly. The company is strengthening compute capability along with the load-bearing and expansion capacity of the entire infrastructure stack.