Nscale’s Post

Lowest hanging fruit for #AI #inference performance optimization on MI300X - all with open-source tools!

#DellTechWorld Omdia 2 formats to support AI a 70KW with 64 GPUs, a 100KW with 72 Blackwell GPUs liquid cooled,

Come by and see how the easy-button works for safe GenAI and ML in content creation workflows! Promise....the hair is not as big as advertised. See you soon. #genai, #ML #contentcreation, #contentauthenticity

"Let's shift focus from NVIDIA GPUs to something less discussed but equally crucial: Active Copper Cables or ACC's by Spectra7 Microsystems. In the hyperscalers arena, the future lies in seamlessly connecting AI network's vital arteries. Enter 400G/800G Active Copper Cables (ACCs) – the powerhouse behind millions of connections, silently yet efficiently driving the next wave of AI innovation. #AI #Hyperscalers #800G"

Talking of a 'killer app' for #quantumcomputing ... it is at the intersection of the two most powerful technologies of our time - #ai #quantumcomputing Quantum computing might provide the ability to train AI models. Gibbs sampling coupled with other techniques such as quantum classification will be a game changer for AI, especially if training of new models on 'private' data is required, which is what companies will demand of technology.

Heading to RSA? Excited to explore the power of Confidential AI with Anjuna Security and NVIDIA? Discover how Confidential AI accelerated AI innovation by increasing security and data pricacy Visit booth #2360 and let's chat!

Portable AI supercomputer comes as a carry-on suitcase with wheels — four GPUs, 246TB of storage, and a 2,500W integrated power supply By Jeff Butts All passengers, please ensure your carry-on baggage has enough storage for your anticipated data needs. GigaIO and SourceCode have teamed up to bring the world an ultraportable but still supercomputer-class device for AI needs. The Gryf weighs 55 pounds or less and is packed into a TSA-friendly carry-on suitcase. Despite the small form factor, Gryf can accommodate data collection and processing on a scale that would otherwise require sending the data offsite. This revolutionary development for use cases requires quick processing and analysis turnaround. Register to watch this online video session for more details about this latest portable AI supercomputer. https://lnkd.in/gkySG4vP

Portable AI supercomputer comes as a carry-on suitcase with wheels — four GPUs, 246TB of storage, and a 2,500W integrated power supply By Jeff Butts All passengers, please ensure your carry-on baggage has enough storage for your anticipated data needs. GigaIO and SourceCode have teamed up to bring the world an ultraportable but still supercomputer-class device for AI needs. The Gryf weighs 55 pounds or less and is packed into a TSA-friendly carry-on suitcase. Despite the small form factor, Gryf can accommodate data collection and processing on a scale that would otherwise require sending the data offsite. This revolutionary development for use cases requires quick processing and analysis turnaround. Register to watch this online video session for more details about this latest portable AI supercomputer. https://lnkd.in/gkySG4vP

Portable AI supercomputer comes as a carry-on suitcase with wheels — four GPUs, 246TB of storage, and a 2,500W integrated power supply By Jeff Butts All passengers, please ensure your carry-on baggage has enough storage for your anticipated data needs. GigaIO and SourceCode have teamed up to bring the world an ultraportable but still supercomputer-class device for AI needs. The Gryf weighs 55 pounds or less and is packed into a TSA-friendly carry-on suitcase. Despite the small form factor, Gryf can accommodate data collection and processing on a scale that would otherwise require sending the data offsite. This revolutionary development for use cases requires quick processing and analysis turnaround. Register to watch this online video session for more details about this latest portable AI supercomputer. https://lnkd.in/gVae2JW5

Introducing the 2nd generation Versal Adaptive SoCs.