NVIDIA Huang Renxun: Vera Rubin Seven Chips in Full Production, Anticipating $1 Trillion Compute Power Order

According to 1M AI News monitoring, NVIDIA founder and CEO Jensen Huang officially announced at the GTC 2026 conference the full-scale production of the Vera Rubin platform, integrating seven new chips covering five types of rack systems, designed as a supercomputer specifically for AI.

The core Vera Rubin NVL72 rack integrates 72 Rubin GPUs and 36 Vera CPUs interconnected via NVLink 6. Compared to the previous generation Blackwell platform, the number of GPUs required for training large hybrid expert models has been reduced to one-fourth, with peak per-watt inference throughput reaching up to 10 times that of Blackwell and per-token cost reduced to one-tenth.

The five types of rack systems constitute a complete AI factory infrastructure:

- Vera Rubin NVL72 GPU Rack
- Vera CPU Rack (256 Vera CPUs, 2x more efficient than traditional CPUs, 50% speedup)
- Groq 3 LPX Inference Acceleration Rack
- BlueField-4 STX Storage Rack (designed for AI Agent key-value cache, achieving up to 5x higher inference throughput)
- Spectrum-6 SPX Ethernet Rack

In terms of power management, NVIDIA also released the DSX platform: DSX Max-Q can deploy 30% more AI infrastructure within a fixed power limit, and DSX Flex can activate 100 GW of previously unused idle grid capacity.

Cloud service providers such as AWS, Google Cloud, Microsoft Azure, Oracle Cloud, as well as system manufacturers like Cisco, Dell Technologies, Hewlett Packard Enterprise, Lenovo, AMD, have all announced plans to launch Vera Rubin products in the second half of this year. Anthropic, Meta, Mistral AI, and OpenAI have explicitly stated they will use this platform to train larger models.

Jensen Huang stated that he predicts the combined orders for Blackwell and Vera Rubin systems from 2025 to 2027 will reach at least $1 trillion, doubling the $500 billion forecast given at last year's GTC.