AWS to Offer NVIDIA Blackwell GPU Platform

<p><strong>SAN JOSE<&sol;strong> <b>—<&sol;b>Amazon Web Services &lpar;AWS&rpar;&comma; an Amazon&period;com company&comma; and NVIDIA announced that the new NVIDIA Blackwell GPU platform is coming to AWS&period;<&sol;p>&NewLine;<p>AWS will offer the NVIDIA GB200 Grace Blackwell Superchip and B100 Tensor Core GPUs&comma; extending the companies’ longstanding strategic collaboration to deliver the most secure and advanced infrastructure&comma; software&comma; and services to help customers unlock new generative artificial intelligence &lpar;AI&rpar; capabilities&period;<&sol;p>&NewLine;<p>NVIDIA and AWS continue to bring together the best of their technologies&comma; including NVIDIA’s newest multi-node systems featuring the next-generation NVIDIA Blackwell platform and AI software&comma; AWS’s Nitro System and AWS Key Management Service &lpar;AWS KMS&rpar; advanced security&comma; Elastic Fabric Adapter &lpar;EFA&rpar; petabit scale networking&comma; and Amazon Elastic Compute Cloud &lpar;Amazon EC2&rpar; UltraCluster hyper-scale clustering&period; Together&comma; they deliver the infrastructure and tools that enable customers to build and run real-time inference on multi-trillion parameter large language models &lpar;LLMs&rpar; faster&comma; at massive scale&comma; and at a lower cost than previous-generation NVIDIA GPUs on Amazon EC2&period;<&sol;p>&NewLine;<p>&OpenCurlyDoubleQuote;The deep collaboration between our two organizations goes back more than 13 years&comma; when together we launched the world’s first GPU cloud instance on AWS&comma; and today we offer the widest range of NVIDIA GPU solutions for customers&comma;” said Adam Selipsky&comma; CEO at AWS&period; &OpenCurlyDoubleQuote;NVIDIA’s next-generation Grace Blackwell processor marks a significant step forward in generative AI and GPU computing&period; When combined with AWS’s powerful Elastic Fabric Adapter Networking&comma; Amazon EC2 UltraClusters’ hyper-scale clustering&comma; and our unique Nitro system’s advanced virtualization and security capabilities&comma; we make it possible for customers to build and run multi-trillion parameter large language models faster&comma; at massive scale&comma; and more securely than anywhere else&period; Together&comma; we continue to innovate to make AWS the best place to run NVIDIA GPUs in the cloud&period;”<&sol;p>&NewLine;<p>&&num;8220&semi;AI is driving breakthroughs at an unprecedented pace&comma; leading to new applications&comma; business models&comma; and innovation across industries&comma;” said Jensen Huang&comma; founder and CEO of NVIDIA&period; &OpenCurlyDoubleQuote;Our collaboration with AWS is accelerating new generative AI capabilities and providing customers with unprecedented computing power to push the boundaries of what&&num;8217&semi;s possible&period;&&num;8221&semi;<&sol;p>&NewLine;<p><b>Latest innovations from AWS and NVIDIA accelerate training of cutting-edge LLMs that can reach beyond 1 trillion parameters<&sol;b><&sol;p>&NewLine;<p>AWS will offer the NVIDIA Blackwell platform&comma; featuring GB200 NVL72&comma; with 72 Blackwell GPUs and 36 Grace CPUs interconnected by fifth-generation NVIDIA NVLink™&period; When connected with Amazon’s powerful networking &lpar;<span class&equals;"Enhancement-inline"><span class&equals;"Enhancement-item"><a class&equals;"Link" href&equals;"https&colon;&sol;&sol;cts&period;businesswire&period;com&sol;ct&sol;CT&quest;id&equals;smartlink&amp&semi;url&equals;https&percnt;3A&percnt;2F&percnt;2Faws&period;amazon&period;com&percnt;2Fhpc&percnt;2Fefa&percnt;2F&amp&semi;esheet&equals;53911679&amp&semi;newsitemid&equals;20240318794112&amp&semi;lan&equals;en-US&amp&semi;anchor&equals;EFA&amp&semi;index&equals;2&amp&semi;md5&equals;d3b15a92c63818a68669645013f74c81" target&equals;"&lowbar;blank" rel&equals;"noopener" data-cms-ai&equals;"0">EFA<&sol;a><&sol;span><&sol;span>&rpar;&comma; and supported by advanced virtualization &lpar;<span class&equals;"Enhancement-inline"><span class&equals;"Enhancement-item"><a class&equals;"Link" href&equals;"https&colon;&sol;&sol;cts&period;businesswire&period;com&sol;ct&sol;CT&quest;id&equals;smartlink&amp&semi;url&equals;https&percnt;3A&percnt;2F&percnt;2Faws&period;amazon&period;com&percnt;2Fec2&percnt;2Fnitro&percnt;2F&amp&semi;esheet&equals;53911679&amp&semi;newsitemid&equals;20240318794112&amp&semi;lan&equals;en-US&amp&semi;anchor&equals;AWS&plus;Nitro&plus;System&amp&semi;index&equals;3&amp&semi;md5&equals;62cd1c54964f92d20318392854bd9d80" target&equals;"&lowbar;blank" rel&equals;"noopener" data-cms-ai&equals;"0">AWS Nitro System<&sol;a><&sol;span><&sol;span>&rpar; and hyper-scale clustering &lpar;<span class&equals;"Enhancement-inline"><span class&equals;"Enhancement-item"><a class&equals;"Link" href&equals;"https&colon;&sol;&sol;cts&period;businesswire&period;com&sol;ct&sol;CT&quest;id&equals;smartlink&amp&semi;url&equals;https&percnt;3A&percnt;2F&percnt;2Faws&period;amazon&period;com&percnt;2Fec2&percnt;2Fultraclusters&percnt;2F&amp&semi;esheet&equals;53911679&amp&semi;newsitemid&equals;20240318794112&amp&semi;lan&equals;en-US&amp&semi;anchor&equals;Amazon&plus;EC2&plus;UltraClusters&amp&semi;index&equals;4&amp&semi;md5&equals;6eabc9e5235aeecff065048929a4a0a6" target&equals;"&lowbar;blank" rel&equals;"noopener" data-cms-ai&equals;"0">Amazon EC2 UltraClusters<&sol;a><&sol;span><&sol;span>&rpar;&comma; customers can scale to thousands of GB200 Superchips&period; NVIDIA Blackwell on AWS delivers a massive leap forward in speeding up inference workloads for resource-intensive&comma; multi-trillion parameter language models&period;<&sol;p>&NewLine;<p>Based on the success of the NVIDIA H100-powered EC2 P5 instances&comma; which are available to customers for short durations through <span class&equals;"Enhancement-inline"><span class&equals;"Enhancement-item"><a class&equals;"Link" href&equals;"https&colon;&sol;&sol;cts&period;businesswire&period;com&sol;ct&sol;CT&quest;id&equals;smartlink&amp&semi;url&equals;https&percnt;3A&percnt;2F&percnt;2Faws&period;amazon&period;com&percnt;2Fec2&percnt;2Fcapacityblocks&percnt;2F&amp&semi;esheet&equals;53911679&amp&semi;newsitemid&equals;20240318794112&amp&semi;lan&equals;en-US&amp&semi;anchor&equals;Amazon&plus;EC2&plus;Capacity&plus;Blocks&plus;for&plus;ML&amp&semi;index&equals;5&amp&semi;md5&equals;67a435a7bb309c42210a95b779659f32" target&equals;"&lowbar;blank" rel&equals;"noopener" data-cms-ai&equals;"0">Amazon EC2 Capacity Blocks for ML<&sol;a><&sol;span><&sol;span>&comma; AWS plans to offer EC2 instances featuring the new B100 GPUs deployed in EC2 UltraClusters for accelerating generative AI training and inference at massive scale&period; GB200s will also be available on <span class&equals;"Enhancement-inline"><span class&equals;"Enhancement-item"><a class&equals;"Link" href&equals;"https&colon;&sol;&sol;cts&period;businesswire&period;com&sol;ct&sol;CT&quest;id&equals;smartlink&amp&semi;url&equals;https&percnt;3A&percnt;2F&percnt;2Fwww&period;nvidia&period;com&percnt;2Fen-us&percnt;2Fdata-center&percnt;2Fdgx-cloud&percnt;2F&amp&semi;esheet&equals;53911679&amp&semi;newsitemid&equals;20240318794112&amp&semi;lan&equals;en-US&amp&semi;anchor&equals;NVIDIA&plus;DGX&percnt;26&percnt;238482&percnt;3B&plus;Cloud&amp&semi;index&equals;6&amp&semi;md5&equals;b4d764163d2ed6c90c2bb14fbe8ef09a" target&equals;"&lowbar;blank" rel&equals;"noopener" data-cms-ai&equals;"0">NVIDIA DGX™ Cloud<&sol;a><&sol;span><&sol;span>&comma; an AI platform co-engineered on AWS&comma; that gives enterprise developers dedicated access to the infrastructure and software needed to build and deploy advanced generative AI models&period; The Blackwell-powered DGX Cloud instances on AWS will accelerate development of cutting-edge generative AI and LLMs that can reach beyond 1 trillion parameters&period;<&sol;p>&NewLine;

Editor

Wispr Scores $25 Million Series A Extension

SAN FRANCISCO -- Wispr, the voice-to-text AI that turns speech into clear, polished writing in every…

1 day

Numeric Dials Up $51 Million Series B

SAN FRANCISCO -- Numeric, an AI accounting automation platform, has raised a $51 million Series…

1 day

Apple Names 45 Finalists for App Store of the Year Awards

Apple has announced 45 finalists for this year’s App Store Awards, recognizing the best apps…

2 days

UC Reaches Agreement With Nurses, Strike Canceled

The University of California (UC) and the California Nurses Association (CNA) have reached a tentative…

4 days

HouseRX Rakes In $55 Million Series B

SAN FRANCISCO -- House Rx, a health tech company focused on making specialty medications more accessible and…

4 days

King Charles Honors NVIDIA’s Jensen Huang

Britain's King has given an award to the King of NVIDIA! NVIDIA founder and CEO…

4 days