Huang’s Law ?? ????

NVIDIA has sounded the death knell for Moore’s Law with the release of Blackwell, an AI superchip with 208 billion transistors (up from 80 billion in Hopper) across its two GPU dies, connected by 10 TB/second chip-to-chip link into a single, unified GPU.?

This advanced computing platform, designed for real-time generative AI and large language model processing, offers significantly reduced cost and energy consumption, giving rise to a new era of ‘Huang’s Law’, as you may call it.?

Reflecting on the rapid advancement in computing power, Huang said that in just eight years, NVIDIA has increased computational capacity by a thousandfold, a rate of progress that far exceeds the benchmarks set during the heyday of Moore's Law. He, however, suggested that even this remarkable growth is not meeting the industry's accelerating demands.?

“In the last eight years, we've gone 1000 times, and we have two more years to go. And so that puts it in perspective the rate at which we're advancing computing is insane. And it's still not fast enough,” said Huang.?

Huang said that the future is generative, which is why we call it ‘generative AI’, marking the start of a brand new industry. “We’ve created a processor specifically for the generative era. A critical component of this is what we call ‘content token generation’, which we format as FP4,” he added, saying that their approach to computing is quite different from their competitors.?

Further, he said that this involves a significant amount of computation – 5x the token generation and 5x the inference capability of Hopper. That might seem sufficient, but we asked ourselves, why stop there?” pondered Huang, and said that the answer is that it is not enough.?

Enjoy the full story here.?

Accelerating Humanoid Robots??

NVIDIA, a powerhouse in accelerated computing, now aims to redefine humanoid robotics with its innovative Project GR00T. With some unexpected showmanship at the highly-anticipated NVIDIA GTC event, chief Jensen Huang announced GR00T, a general-purpose foundation model for humanoid robot learning.?

The model will enable a robot to understand multimodal instructions, including language, video, and demonstration, and perform a variety of useful tasks. “We are collaborating with many leading humanoid companies around the world, so that GR00T may transfer across embodiments and help the ecosystem thrive,” said Jim Fan, who is currently leading this project.?

Learn more about Project GR00T here.?

Unleashing GenAI for Healthcare?

Healthcare has always been one of NVIDIA’s biggest bets. And now, precisely on the one-year anniversary of BioNeMo cloud, the company has introduced a set of over 25 new generative AI-powered microservices to empower healthcare organisations globally across various domains, such as drug discovery, MedTech, and digital health, at the much-awaited NVIDIA GTC 2024. Read more here.?

An AI Marketplace for India

Formerly known as Videsh Sanchar Nigam Limited (VSNL), a government-owned entity, Tata Communications has undergone significant evolution. It has expanded its services from managed cloud services, microservices, and connected solutions to content delivery networks and analytics. It also partnered with NVIDIA to build a large-scale AI cloud infrastructure for its customers in the private and public sectors.

Positioning itself at the forefront of technological advancements, it now aims to lead the AI revolution in India. Read the full story here.?