Categories
Featured

This is what Nvidia’s Exaflop supercomputer-in-a-rack looks like — the DGX GB200 NVL72 tower most likely uses 48V, 2.5kA to deliver a staggering 1,440 petaflops, could cost millions

[ad_1]

Nvidia recently unveiled its DGX GB200 NVL72 supercomputer-in-a-rack at Nvidia GTC 2024 and Patrick Kennedy at Serve The Home took a selection of great photos showcasing the impressive beast.

The name of the DGX GB200 NVL72 tells you much of what you need to know. The GB200 signifies the Grace Blackwell GB200 compute structure, while the NVL72 denotes there are 72 Blackwell GPUs connected by NVLink.

The Blackwell platform contains 208 billion transistors across its two GPU dies. These are connected by 10 TB/second chip-to-chip link into a single, unified GPU. Blackwell, set to ship later this year, will reportedly offer up to 20 petaflops of FP4 power and be up to 30x faster than Hopper for AI inference tasks.

Nvidia GTC 2024

TechRadar Pro also snapped our own picture of the DGX GB200 at Nvidia GTC 2024 (Image credit: Future / Mike Moore)

120kW power load

[ad_2]

Source Article Link

Categories
Featured

This popular gaming PC vendor believes it can make AI training much more affordable for small businesses — Maingear partners with Phison to deliver a quad-GPU system using Nvidia’s RTX 6000 Ada

[ad_1]

The surge in demand for large-scale generative AI models has led to a significant increase in hardware requirements, making model training costly and inaccessible for many SMBs and educational establishments.

High-performance custom PC builder Maingear has partnered with storage giant Phison on a new range of Maingear Pro AI workstations that boast powerful Intel Xeon W7-3455 CPUs. 

[ad_2]

Source Article Link

Categories
Featured

Nvidia’s Project GROOT brings the human-robot future a significant step closer

[ad_1]

The age of humanoid robots could be a significant step closer thanks to a new release from Nvidia.

The computing giant has announced the launch of Project GROOT, its new foundational model aimed at helping the development of such robots in industrial use cases.

[ad_2]

Source Article Link

Categories
Featured

‘A single chip to outperform a small GPU data center’: Yet another AI chip firm wants to challenge Nvidia’s GPU-centric world — Taalas wants to have super specialized AI chips

[ad_1]

Toronto-based AI chip startup Taalas has emerged from stealth with $50 million in funding and the lofty aim of revolutionizing the GPU-centric world dominated by Nvidia.

Founded by Ljubisa Bajic, Lejla Bajic, and Drago Ignjatovic, all previously from Tenstorrent (the creator of Grayskull), Taalas is developing an automated flow for quickly turning any AI model – Transformers, SSMs, Diffusers, MoEs, etc. – into custom silicon. The company claims that the resulting Hardcore Models are 1000x more efficient than their software counterparts.

[ad_2]

Source Article Link

Categories
News

NVIDIA’s AI personal assistant demo available for RTX GPU PCs

NVIDIA RTX AI PCs Chat Bot Demo

NVIDIA has recently unveiled a new technology demonstration that is set to enhance the way we interact with artificial intelligence. This new feature, known as “Chat With RTX,” is designed to work seamlessly on Windows RTX PCs, leveraging the power of NVIDIA RTX GPUs to deliver a personalized and efficient chatbot experience. The technology is aimed at providing users with quick, secure, and contextually relevant responses, drawing from their own documents and notes to ensure a private and customized interaction.

At the heart of “Chat With RTX” lies a sophisticated GPT large language model that is capable of tailoring conversations to the user’s specific needs. This is not your average chatbot; it’s an intelligent system that can process a variety of file types, including text documents, PDFs, Word documents, XML files, and even transcriptions from YouTube videos. This versatility allows the chatbot to provide assistance that is highly relevant to the user’s personal content.

NVIDIA RTX AI PCs Chat Bot Demo

One of the key features of NVIDIA’s new tech demo is the use of retrieval-augmented generation (RAG), which significantly enhances the quality of the chatbot’s responses. In addition, the demo incorporates TensorRT-LLM, a tool for optimizing large language models, ensuring that the chatbot operates at peak efficiency. Thanks to RTX acceleration, the chatbot is not only accurate but also incredibly fast, running directly on a user’s Windows RTX PC without the need for cloud processing.

Developers, in particular, may find “Chat With RTX” intriguing as it builds upon the TensorRT-LLM RAG developer reference project available on GitHub. This provides them with a valuable opportunity to explore advanced AI models and potentially integrate similar technologies into their own projects.

 

For those interested in experiencing “Chat With RTX,” there are certain system requirements that must be met. The user’s PC should be equipped with a GeForce RTX 30 Series GPU or a more advanced model, with a minimum of 8GB of VRAM. Additionally, the PC must be running either Windows 10 or 11 and have the latest NVIDIA drivers installed to ensure compatibility with the demo.

NVIDIA has acknowledged a current installation issue with “Chat With RTX” and has promised to resolve it in a forthcoming update. In the meantime, users are advised to install the application in the default directory to avoid any complications.

Furthermore, NVIDIA is encouraging developers to push the boundaries of generative AI by hosting a contest. Participants are invited to create innovative applications using NVIDIA RTX GPUs, with the chance to win prizes. This contest not only stimulates creativity within the developer community but also showcases the potential of NVIDIA’s technology in driving forward AI applications.

The introduction of “Chat With RTX” is a testament to NVIDIA’s ongoing efforts to advance AI and GPU technology. By focusing on high-performance computing and data privacy, NVIDIA is making it possible to integrate sophisticated AI capabilities into everyday tasks. This technology allows users to benefit from a smart, responsive, and personalized AI assistant, all while keeping their data securely processed on their local machine. As NVIDIA continues to innovate and address any initial teething problems, “Chat With RTX” is poised to become an essential tool for those seeking a more intelligent and responsive computing experience.

Filed Under: Technology News, Top News





Latest timeswonderful Deals

Disclosure: Some of our articles include affiliate links. If you buy something through one of these links, timeswonderful may earn an affiliate commission. Learn about our Disclosure Policy.