NVIDIA Corporation (NASDAQ: NVDA) announced the Vera Rubin platform, featuring seven new chips in full production designed for artificial intelligence applications. The platform was unveiled at the company's GTC conference.

The Vera Rubin system integrates multiple components including the NVIDIA Vera CPU, NVIDIA Rubin GPU, NVIDIA NVLink 6 Switch, NVIDIA ConnectX-9 SuperNIC, NVIDIA BlueField-4 DPU, NVIDIA Spectrum-6 Ethernet switch, and the NVIDIA Groq 3 LPU. The platform operates across five rack configurations: Vera Rubin NVL72 GPU racks, Vera CPU racks, NVIDIA Groq 3 LPX inference accelerator racks, NVIDIA BlueField-4 STX storage racks, and NVIDIA Spectrum-6 SPX Ethernet racks.

"Vera Rubin is a generational leap — seven breakthrough chips, five racks, one giant supercomputer — built to power every phase of AI," said Jensen Huang, founder and CEO of NVIDIA.

The Vera Rubin NVL72 rack integrates 72 Rubin GPUs and 36 Vera CPUs connected by NVLink 6. According to the company, this configuration trains large mixture-of-experts models with one-fourth the number of GPUs compared with the NVIDIA Blackwell platform.

The NVIDIA Groq 3 LPX rack contains 256 LPU processors with 128GB of on-chip SRAM and 640 TB/s of scale-up bandwidth. The system is designed for low-latency inference applications and trillion-parameter models.

Cloud providers including Amazon Web Services, Google Cloud, Microsoft Azure, and Oracle Cloud Infrastructure plan to offer Vera Rubin-based products. System manufacturers such as Cisco, Dell Technologies, HPE, Lenovo, and Supermicro are expected to deliver servers based on the platform.

Products based on the Vera Rubin platform will be available from partners starting in the second half of this year, according to the company's press release.