NVIDIA GTC Taipei at COMPUTEX: Live Updates on What’s Next in AI

2026-05-21 · Source: NVIDIA Blog · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Robotics & Autonomous Systems, Cloud Computing & IT Infrastructure · Depth: Expert, short

Summary

NVIDIA GTC Taipei at COMPUTEX is underway, featuring NVIDIA founder and CEO Jensen Huang's keynote on Monday, June 1, at 11 a.m. Taipei time. Ahead of the main event, NVIDIA secured multiple COMPUTEX 2026 Best Choice Awards for its innovations. The NVIDIA Vera Rubin NVL72 rack-scale AI supercomputer received a Golden Award and the Sustainable Tech Special Award, offering up to 10x higher inference performance per watt and 10x lower cost per token, and 35x higher throughput with NVIDIA Groq 3 LPX. The NVIDIA Jetson Thor platform for edge AI and robotics also won a Golden Award, delivering 2,070 FP4 teraflops of AI performance. Additionally, the NVIDIA Alpamayo open platform for autonomous vehicle development earned the Vehicle Technology and Smart Cockpit Category Award, addressing complex driving scenarios with 10-billion-parameter models and over 1,700 hours of driving data.

Key takeaway

For AI Architects evaluating next-generation infrastructure, NVIDIA's Vera Rubin NVL72 offers a compelling solution for scaling AI factories, delivering 10x higher inference performance per watt and lower cost per token. You should consider its liquid-cooled, modular design for sustainable, high-throughput deployment of agentic AI and long-context models. Robotics Engineers should explore Jetson Thor for integrating generative AI into autonomous machines, leveraging its 2,070 FP4 teraflops performance.

Key insights

NVIDIA's latest platforms advance AI, robotics, and autonomous vehicles with significant performance and efficiency gains.

Principles

• AI infrastructure prioritizes scalability and sustainability.
• Edge AI requires high performance and energy efficiency.
• AV development benefits from reasoning models for complex scenarios.

Method

The Vera Rubin NVL72 integrates CPUs, GPUs, NVLink, SuperNICs, and DPUs for rack-scale AI, utilizing liquid cooling and modular design.

In practice

• Deploy Vera Rubin NVL72 for agentic AI and long-context workloads.
• Use Jetson Thor for generative AI in robots and industrial systems.
• Apply Alpamayo for autonomous vehicle development in complex edge cases.

Topics

• AI Supercomputing
• Edge AI Platforms
• Autonomous Vehicle Development
• Robotics AI
• NVIDIA Vera Rubin NVL72
• NVIDIA Jetson Thor
• NVIDIA Alpamayo

Best for: CTO, Director of AI/ML, MLOps Engineer, AI Architect, AI Engineer, Robotics Engineer

Related on AIssential

• Nvidia: Star Attraction at CES 2026 — Nvidia's Vera Rubin platform integrates co-designed chips and software to build scalable AI factories.
• NVIDIA GTC Taipei 2026 Moments: Agents, AI PCs, and Physical AI — NVIDIA is driving AI innovation through new hardware, software, and agent development tools.
• Nvidia intros six new AI chips and new open models — Nvidia's new Rubin platform and specialized open models emphasize a full-stack AI factory approach beyond just GPUs.
• How Dell is Scaling Enterprise AI with NVIDIA Vera Servers — Dell and NVIDIA are scaling agentic AI from pilot to production with a unified infrastructure, leveraging Vera CPUs and the Dell AI Factory.
• CES 2026: Nvidia promises five times the AI performance and ten times cheaper inference with Vera Rubin — Nvidia's new Vera Rubin platform and Alpamayo software aim to dominate the AI and autonomous driving value chains.
• The Rubin Era: How NVIDIA’s New Platform Rewrites the Rules for MoE and Agentic AI — NVIDIA's Vera Rubin platform redefines AI hardware by co-designing six chips for unprecedented performance in MoE and agentic AI.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by NVIDIA Blog.