Acceleration is all you need (now)

{
  "by": "bcarambio",
  "descendants": 0,
  "id": 40247673,
  "kids": [
    40247674
  ],
  "score": 1,
  "time": 1714744321,
  "title": "Acceleration is all you need (now)",
  "type": "story",
  "url": "https://octo.ai/blog/acceleration-is-all-you-need-techniques-powering-octostacks-10x-performance-boost/"
}

{
  "author": null,
  "date": null,
  "description": "We create the world’s fastest supercomputer and largest gaming platform.",
  "image": "https://www.nvidia.com/content/dam/en-zz/Solutions/homepage/v2/sfg/nvidia-corporate-og-image-1200x630.jpg",
  "logo": "https://logo.clearbit.com/octo.ai",
  "publisher": "OctoML",
  "title": "World Leader in AI Computing",
  "url": "https://www.nvidia.com/en-us/"
}

{
  "url": "https://octo.ai/blog/acceleration-is-all-you-need-techniques-powering-octostacks-10x-performance-boost/",
  "title": "World Leader in Artificial Intelligence Computing",
  "description": "NVIDIA invents the GPU, creates the largest gaming platform, powers the world’s fastest supercomputer, and drives advances in AI, HPC, gaming, creative design, autonomous vehicles, and robotics.",
  "links": [
    "https://www.nvidia.com/en-us/",
    "https://octo.ai/blog/acceleration-is-all-you-need-techniques-powering-octostacks-10x-performance-boost/"
  ],
  "image": "https://www.nvidia.com/content/dam/en-zz/Solutions/homepage/v2/sfg/nvidia-corporate-og-image-1200x630.jpg",
  "content": "<div>\n         <div>\n            <div>\n<div>\n    \t<p>\n\t    \t</p><h2>\n                    Artificial Intelligence\n\t    \t</h2>\n    \t<p></p>\n     </div>\n<div>\n    \t<p>\n\t    \t</p><h2>\n                    OpenAI,  NVIDIA Propel AI Innovation With New Optimized Open Models\n\t    \t</h2>\n    \t<p></p>\n     </div>\n<div>\n\t\t\t\t<p><span>NVIDIA delivers industry-leading gpt-oss-120b performance of 1.5 tokens per second on a single NVIDIA Blackwell GB200 NVL72 system, optimized for the world’s largest AI inference infrastructure.</span></p>\n\t\t\t</div>\n</div>\n<div>\n<div>\n    \t<p>\n\t    \t</p><h2>\n                    Special Address\n\t    \t</h2>\n    \t<p></p>\n     </div>\n<div>\n    \t<p>\n\t    \t</p><h2>\n                    NVIDIA Research Special Address at SIGGRAPH\n\t    \t</h2>\n    \t<p></p>\n     </div>\n<div>\n                \t<p><span><strong>Monday, August 11, 4-5 p.m. PT</strong></span></p> \n<p><span>Join NVIDIA AI research leaders as they chart the next frontier in computer graphics and physical AI.</span></p>\n                </div>\n</div>\n<div>\n<div>\n    \t<p>\n\t    \t</p><h2>\n                    Artificial Intelligence\n\t    \t</h2>\n    \t<p></p>\n     </div>\n<div>\n    \t<p>\n\t    \t</p><h2>\n                    NVIDIA Accelerates OpenAI gpt-oss Models for Industry Leading Inference\n\t    \t</h2>\n    \t<p></p>\n     </div>\n<div>\n\t\t\t\t<p><span>Delivering 1.5 M TPS Inference on NVIDIA GB200 NVL72, NVIDIA accelerates OpenAI gpt-oss models enabling faster, more cost-effective AI inference deployment—from cloud to edge.</span></p>\n\t\t\t</div>\n</div>\n<div>\n<div>\n    \t<p>\n\t    \t</p><h2>\n                    Artificial Intelligence\n\t    \t</h2>\n    \t<p></p>\n     </div>\n<div>\n    \t<p>\n\t    \t</p><h2>\n                    OpenAI’s New Open-Source Models Accelerated on RTX AI PCs\n\t    \t</h2>\n    \t<p></p>\n     </div>\n<div>\n\t\t\t\t<p><span>Groundbreaking open-weight models are now available with local optimizations for NVIDIA GeForce RTX and RTX PRO GPUs.</span></p>\n\t\t\t</div>\n</div>\n<div>\n<div>\n    \t<p>\n\t    \t</p><h2>\n                    Artificial Intelligence\n\t    \t</h2>\n    \t<p></p>\n     </div>\n<div>\n    \t<p>\n\t    \t</p><h2>\n                    NVIDIA Dynamo Delivers Cost-Efficient Inference at Scale With AWS\n\t    \t</h2>\n    \t<p></p>\n     </div>\n<div>\n\t\t\t\t<p><span>Dynamo adds support for popular AWS services, unlocking new levels of performance, scalability, and cost-efficiency for serving large language models.</span></p>\n\t\t\t</div>\n</div>\n<div>\n<div>\n    \t<p>\n\t    \t</p><h2>\n                    Telecoms\n\t    \t</h2>\n    \t<p></p>\n     </div>\n<div>\n    \t<p>\n\t    \t</p><h2>\n                    Indosat to Build AI Center of Excellence With Cisco and NVIDIA\n\t    \t</h2>\n    \t<p></p>\n     </div>\n<div>\n\t\t\t\t<p><span>The new AI infrastructure will include an NVIDIA AI Technology Center to foster local AI research, nurture talent, and drive innovation in Indonesia with NVIDIA Inception startups.</span></p>\n\t\t\t</div>\n</div>\n         </div>\n\t\t    <div>\n\t\t            <div>\n\t\t                <p><label>Artificial Intelligence</label></p><p>OpenAI, NVIDIA Propel AI Innovation With New Optimized Open Models</p>\n\t\t            </div>\n\t\t            <div>\n\t\t                <p><label>Special Address</label></p><p>NVIDIA Research Special Address at SIGGRAPH</p>\n\t\t            </div>\n\t\t            <div>\n\t\t                <p><label>Artificial Intelligence</label></p><p>NVIDIA Accelerates OpenAI gpt-oss Models for Industry Leading Inference</p>\n\t\t            </div>\n\t\t            <div>\n\t\t                <p><label>Artificial Intelligence</label></p><p>OpenAI’s New Open-Source Models Accelerated on RTX AI PCs</p>\n\t\t            </div>\n\t\t            <div>\n\t\t                <p><label>Artificial Intelligence</label></p><p>NVIDIA Dynamo Delivers Cost-Efficient Inference at Scale With AWS</p>\n\t\t            </div>\n\t\t            <div>\n\t\t                <p><label>Telecoms</label></p><p>Indosat to Build AI Center of Excellence With Cisco and NVIDIA</p>\n\t\t            </div>\n\t\t        </div>\n        <ol>\n            <li>Artificial Intelligence</li>\n<li>Special Address</li>\n<li>Artificial Intelligence</li>\n<li>Artificial Intelligence</li>\n<li>Artificial Intelligence</li>\n<li>Telecoms</li>\n        </ol>\n    </div>",
  "author": "@NVIDIA",
  "favicon": "",
  "source": "octo.ai",
  "published": "",
  "ttr": 55,
  "type": "website"
}