{"id":120462,"date":"2025-04-29T15:27:01","date_gmt":"2025-04-29T13:27:01","guid":{"rendered":"https:\/\/aixia.se\/nvidia-dynamo\/"},"modified":"2026-03-09T13:47:10","modified_gmt":"2026-03-09T12:47:10","slug":"nvidia-dynamo","status":"publish","type":"post","link":"https:\/\/aixia.se\/en\/nvidia-dynamo\/","title":{"rendered":"NVIDIA Dynamo &#8211; new framework for AI inference"},"content":{"rendered":"\t\t<div data-elementor-type=\"wp-post\" data-elementor-id=\"120462\" class=\"elementor elementor-120462 elementor-118483\" data-elementor-post-type=\"post\">\n\t\t\t\t<div class=\"elementor-element elementor-element-4450781 e-flex e-con-boxed e-con e-parent\" data-id=\"4450781\" data-element_type=\"container\" data-e-type=\"container\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t<div class=\"elementor-element elementor-element-fe0c848 e-con-full e-flex e-con e-child\" data-id=\"fe0c848\" data-element_type=\"container\" data-e-type=\"container\">\n\t\t\t\t<div class=\"elementor-element elementor-element-4c959ef elementor-widget elementor-widget-text-editor\" data-id=\"4c959ef\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<h2 data-start=\"40\" data-end=\"185\"><strong data-start=\"40\" data-end=\"141\">NVIDIA Dynamo: Next-generation AI infrastructure solution for more efficient and scalable inference<\/strong><\/h2><h5 data-start=\"187\" data-end=\"572\">NVIDIA has recently launched <em data-start=\"215\" data-end=\"223\">Dynamo<\/em>, an open source AI inference solution designed to manage and optimize large language models (LLMs) in distributed environments. This software represents a significant step forward for organizations looking to maximize the performance and cost efficiency of their GPU-based AI infrastructures. <\/h5>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-44f3f5f e-con-full e-flex e-con e-child\" data-id=\"44f3f5f\" data-element_type=\"container\" data-e-type=\"container\">\n\t\t\t\t<div class=\"elementor-element elementor-element-0b2bd73 elementor-widget elementor-widget-image\" data-id=\"0b2bd73\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"image.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<img fetchpriority=\"high\" decoding=\"async\" width=\"800\" height=\"800\" src=\"https:\/\/aixia.se\/wp-content\/uploads\/2025\/04\/ChatGPT-Image-29-apr.-2025-15_23_12.png\" class=\"attachment-large size-large wp-image-118488\" alt=\"\" srcset=\"https:\/\/aixia.se\/wp-content\/uploads\/2025\/04\/ChatGPT-Image-29-apr.-2025-15_23_12.png 1024w, https:\/\/aixia.se\/wp-content\/uploads\/2025\/04\/ChatGPT-Image-29-apr.-2025-15_23_12-300x300.png 300w, https:\/\/aixia.se\/wp-content\/uploads\/2025\/04\/ChatGPT-Image-29-apr.-2025-15_23_12-150x150.png 150w, https:\/\/aixia.se\/wp-content\/uploads\/2025\/04\/ChatGPT-Image-29-apr.-2025-15_23_12-768x768.png 768w\" sizes=\"(max-width: 800px) 100vw, 800px\" \/>\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-cf98926 e-flex e-con-boxed e-con e-parent\" data-id=\"cf98926\" data-element_type=\"container\" data-e-type=\"container\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t\t\t<div class=\"elementor-element elementor-element-5464de2 elementor-widget elementor-widget-text-editor\" data-id=\"5464de2\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<h3 data-start=\"579\" data-end=\"607\"> <\/h3><h3 class=\"\" data-start=\"579\" data-end=\"607\">What is NVIDIA Dynamo?<\/h3><p class=\"\" data-start=\"609\" data-end=\"728\"><span class=\"relative -mx-px my-[-0.2rem] rounded px-px py-[0.2rem] transition-colors duration-100 ease-in-out\">Dynamo is a modular and low-latency inference platform that enables efficient management of generative AI models across large GPU clusters.<\/span> <span class=\"relative -mx-px my-[-0.2rem] rounded px-px py-[0.2rem] transition-colors duration-100 ease-in-out\">It is designed to scale seamlessly from single GPUs to thousands, making it ideal for companies running large-scale AI applications.<\/span><\/p><h3 class=\"\" data-start=\"735\" data-end=\"787\">Technical benefits for IT and AI specialists<\/h3><ul data-start=\"789\" data-end=\"1244\"><li class=\"\" data-start=\"789\" data-end=\"899\"><p class=\"\" data-start=\"791\" data-end=\"899\"><strong data-start=\"791\" data-end=\"816\">Disaggregated Serving<\/strong>: <span class=\"relative -mx-px my-[-0.2rem] rounded px-px py-[0.2rem] transition-colors duration-100 ease-in-out\">Separate preprocessing and generation of LLMs across different GPUs to optimize resource usage and increase throughput.<\/span><\/p><\/li><li class=\"\" data-start=\"901\" data-end=\"1002\"><p class=\"\" data-start=\"903\" data-end=\"1002\"><strong data-start=\"903\" data-end=\"919\">Smart Router<\/strong>: <span class=\"relative -mx-px my-[-0.2rem] rounded px-px py-[0.2rem] transition-colors duration-100 ease-in-out\">Intelligent traffic routing that minimizes redundant computations and balances load efficiently across GPU fleets.<\/span><\/p><\/li><li class=\"\" data-start=\"1004\" data-end=\"1119\"><p class=\"\" data-start=\"1006\" data-end=\"1119\"><strong data-start=\"1006\" data-end=\"1032\">Dynamic GPU scheduling<\/strong>: <span class=\"relative -mx-px my-[-0.2rem] rounded px-px py-[0.2rem] transition-colors duration-100 ease-in-out\">Automatically allocate GPU resources based on real-time demand, eliminating bottlenecks and improving performance.<\/span><\/p><\/li><li class=\"\" data-start=\"1121\" data-end=\"1244\"><p class=\"\" data-start=\"1123\" data-end=\"1244\"><strong data-start=\"1123\" data-end=\"1157\">Support for multiple inference engines<\/strong>: <span class=\"relative -mx-px my-[-0.2rem] rounded px-px py-[0.2rem] transition-colors duration-100 ease-in-out\">Compatible with TensorRT-LLM, vLLM, SGLang, PyTorch and others, providing flexibility in backend selection.<\/span><\/p><\/li><\/ul><h3 class=\"\" data-start=\"1251\" data-end=\"1291\">Business benefits for decision-makers<\/h3><ul data-start=\"1293\" data-end=\"1631\"><li class=\"\" data-start=\"1293\" data-end=\"1406\"><p class=\"\" data-start=\"1295\" data-end=\"1406\"><strong data-start=\"1295\" data-end=\"1319\">Cost efficiency<\/strong>: <span class=\"relative -mx-px my-[-0.2rem] rounded px-px py-[0.2rem] transition-colors duration-100 ease-in-out\">By increasing the number of inference requests per GPU, Dynamo reduces the overall operational costs of AI applications.<\/span><\/p><\/li><li class=\"\" data-start=\"1408\" data-end=\"1511\"><p class=\"\" data-start=\"1410\" data-end=\"1511\"><strong data-start=\"1410\" data-end=\"1424\">Scalability<\/strong>: <span class=\"relative -mx-px my-[-0.2rem] rounded px-px py-[0.2rem] transition-colors duration-100 ease-in-out\">Ability to quickly adapt to changing business needs through dynamic scaling of GPU resources.<\/span><\/p><\/li><li class=\"\" data-start=\"1513\" data-end=\"1631\"><p class=\"\" data-start=\"1515\" data-end=\"1631\"><strong data-start=\"1515\" data-end=\"1544\">Future-proof investment<\/strong>: <span class=\"relative -mx-px my-[-0.2rem] rounded px-px py-[0.2rem] transition-colors duration-100 ease-in-out\">Dynamo is an open and modular platform that easily integrates with existing AI stacks, protecting past investments and simplifying future upgrades.<\/span><\/p><\/li><\/ul><h3 class=\"\" data-start=\"1638\" data-end=\"1666\">Performance in practice<\/h3><p class=\"\" data-start=\"1668\" data-end=\"1833\"><span class=\"relative -mx-px my-[-0.2rem] rounded px-px py-[0.2rem] transition-colors duration-100 ease-in-out\">When tested with the DeepSeek-R1 671B open model on the NVIDIA GB200 NVL72, Dynamo increased throughput by up to 30x per GPU.<\/span> <span class=\"relative -mx-px my-[-0.2rem] rounded px-px py-[0.2rem] transition-colors duration-100 ease-in-out\">When the Llama 70B model was run on the NVIDIA Hopper platform, throughput doubled.<\/span> <span class=\"relative -mx-px my-[-0.2rem] rounded px-px py-[0.2rem] transition-colors duration-100 ease-in-out\">These improvements mean businesses can deliver AI services faster and at lower cost.<\/span><\/p><h3 class=\"\" data-start=\"1840\" data-end=\"1892\">How Aixia can support your transition to Dynamo<\/h3><p class=\"\" data-start=\"1894\" data-end=\"2019\"><span class=\"relative -mx-px my-[-0.2rem] rounded px-px py-[0.2rem] transition-colors duration-100 ease-in-out\">At Aixia, we offer expertise in implementing and optimizing AI infrastructures.<\/span> <span class=\"relative -mx-px my-[-0.2rem] rounded px-px py-[0.2rem] transition-colors duration-100 ease-in-out\">We can help your company to.<\/span><\/p><ul data-start=\"2021\" data-end=\"2363\"><li class=\"\" data-start=\"2021\" data-end=\"2138\"><p class=\"\" data-start=\"2023\" data-end=\"2138\"><strong data-start=\"2023\" data-end=\"2051\">Evaluate compatibility<\/strong>: <span class=\"relative -mx-px my-[-0.2rem] rounded px-px py-[0.2rem] transition-colors duration-100 ease-in-out\">Analyze your current GPU infrastructure to ensure it is ready for Dynamo.<\/span><\/p><\/li><li class=\"\" data-start=\"2140\" data-end=\"2252\"><p class=\"\" data-start=\"2142\" data-end=\"2252\"><strong data-start=\"2142\" data-end=\"2165\">Implement Dynamo<\/strong>: <span class=\"relative -mx-px my-[-0.2rem] rounded px-px py-[0.2rem] transition-colors duration-100 ease-in-out\">Support the installation and configuration of Dynamo to maximize performance and efficiency.<\/span><\/p><\/li><li class=\"\" data-start=\"2254\" data-end=\"2363\"><p class=\"\" data-start=\"2256\" data-end=\"2363\"><strong data-start=\"2256\" data-end=\"2276\">Train staff<\/strong>: <span class=\"relative -mx-px my-[-0.2rem] rounded px-px py-[0.2rem] transition-colors duration-100 ease-in-out\">Provide training for your team in the use and maintenance of the new platform.<\/span><\/p><\/li><\/ul><p class=\"\" data-start=\"2365\" data-end=\"2450\"><span class=\"relative -mx-px my-[-0.2rem] rounded px-px py-[0.2rem] transition-colors duration-100 ease-in-out\">Contact us to discuss how we can help your business benefit from NVIDIA Dynamo and take your AI infrastructure to the next level.<\/span><\/p><p class=\"\" data-start=\"2457\" data-end=\"2571\"><em data-start=\"2457\" data-end=\"2571\">For more information about NVIDIA Dynamo, visit <a class=\"\" href=\"https:\/\/www.nvidia.com\/en-us\/ai\/dynamo\/\" target=\"_new\" rel=\"noopener noreferrer nofollow\" data-start=\"2502\" data-end=\"2569\" target=\"_blank\">the official NVIDIA website<\/a>.<\/em><\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t","protected":false},"excerpt":{"rendered":"<p>Read about NVIDIA Dynamo. 13\u219244 characters. <\/p>\n","protected":false},"author":4,"featured_media":118490,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"om_disable_all_campaigns":false,"inline_featured_image":false,"_monsterinsights_skip_tracking":false,"_monsterinsights_sitenote_active":false,"_monsterinsights_sitenote_note":"","_monsterinsights_sitenote_category":0,"footnotes":""},"categories":[46,77],"tags":[],"class_list":["post-120462","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news","category-techblog"],"acf":[],"aioseo_notices":[],"aioseo_head":"\n\t\t<!-- All in One SEO 5.0.0.1 - aioseo.com -->\n\t<meta name=\"description\" content=\"Read about NVIDIA Dynamo. 13\u219244 characters.\" \/>\n\t<meta name=\"robots\" content=\"max-image-preview:large\" \/>\n\t<meta name=\"author\" content=\"Petter\"\/>\n\t<link rel=\"canonical\" href=\"https:\/\/aixia.se\/en\/nvidia-dynamo\/\" \/>\n\t<meta name=\"generator\" content=\"All in One SEO (AIOSEO) 5.0.0.1\" \/>\n\t\t<meta property=\"og:locale\" content=\"en_US\" \/>\n\t\t<meta property=\"og:site_name\" content=\"Aixia -\" \/>\n\t\t<meta property=\"og:type\" content=\"article\" \/>\n\t\t<meta property=\"og:title\" content=\"NVIDIA Dynamo \u2013 new framework for AI inference - Aixia\" \/>\n\t\t<meta property=\"og:description\" content=\"Read about NVIDIA Dynamo. 13\u219244 characters.\" \/>\n\t\t<meta property=\"og:url\" content=\"https:\/\/aixia.se\/en\/nvidia-dynamo\/\" \/>\n\t\t<meta property=\"article:published_time\" content=\"2025-04-29T13:27:01+00:00\" \/>\n\t\t<meta property=\"article:modified_time\" content=\"2026-03-09T12:47:10+00:00\" \/>\n\t\t<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/aixiasverige\" \/>\n\t\t<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n\t\t<meta name=\"twitter:site\" content=\"@aixiasverige\" \/>\n\t\t<meta name=\"twitter:title\" content=\"NVIDIA Dynamo \u2013 new framework for AI inference - Aixia\" \/>\n\t\t<meta name=\"twitter:description\" content=\"Read about NVIDIA Dynamo. 13\u219244 characters.\" \/>\n\t\t<meta name=\"twitter:creator\" content=\"@aixiasverige\" \/>\n\t\t<script type=\"application\/ld+json\" class=\"aioseo-schema\">\n\t\t\t{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"BlogPosting\",\"@id\":\"https:\\\/\\\/aixia.se\\\/en\\\/nvidia-dynamo\\\/#blogposting\",\"name\":\"NVIDIA Dynamo \\u2013 new framework for AI inference - Aixia\",\"headline\":\"NVIDIA Dynamo &#8211; new framework for AI inference\",\"author\":{\"@id\":\"https:\\\/\\\/aixia.se\\\/en\\\/author\\\/petter\\\/#author\"},\"publisher\":{\"@id\":\"https:\\\/\\\/aixia.se\\\/en\\\/#organization\"},\"image\":{\"@type\":\"ImageObject\",\"url\":\"https:\\\/\\\/aixia.se\\\/wp-content\\\/uploads\\\/2025\\\/04\\\/Nvidia-Dynamo-Aixia.png?wsr\",\"width\":1306,\"height\":871},\"datePublished\":\"2025-04-29T15:27:01+02:00\",\"dateModified\":\"2026-03-09T13:47:10+01:00\",\"inLanguage\":\"en-US\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/aixia.se\\\/en\\\/nvidia-dynamo\\\/#webpage\"},\"isPartOf\":{\"@id\":\"https:\\\/\\\/aixia.se\\\/en\\\/nvidia-dynamo\\\/#webpage\"},\"articleSection\":\"News, Techblog, Optional\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/aixia.se\\\/en\\\/nvidia-dynamo\\\/#breadcrumblist\",\"itemListElement\":[{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/aixia.se\\\/en\\\/#listItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/aixia.se\\\/en\\\/\",\"nextItem\":{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/aixia.se\\\/en\\\/category\\\/news\\\/#listItem\",\"name\":\"News\"}},{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/aixia.se\\\/en\\\/category\\\/news\\\/#listItem\",\"position\":2,\"name\":\"News\",\"item\":\"https:\\\/\\\/aixia.se\\\/en\\\/category\\\/news\\\/\",\"nextItem\":{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/aixia.se\\\/en\\\/nvidia-dynamo\\\/#listItem\",\"name\":\"NVIDIA Dynamo &#8211; new framework for AI inference\"},\"previousItem\":{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/aixia.se\\\/en\\\/#listItem\",\"name\":\"Home\"}},{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/aixia.se\\\/en\\\/nvidia-dynamo\\\/#listItem\",\"position\":3,\"name\":\"NVIDIA Dynamo &#8211; new framework for AI inference\",\"previousItem\":{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/aixia.se\\\/en\\\/category\\\/news\\\/#listItem\",\"name\":\"News\"}}]},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/aixia.se\\\/en\\\/#organization\",\"name\":\"Aixia Group AB\",\"description\":\"Aixia levererar AI-infrastruktur, GPU-kluster, MLOps och IT-drift till nordiska f\\u00f6retag. Exklusiv NVIDIA DGX SuperPOD-partner med egen AI-plattform AiQu.\",\"url\":\"https:\\\/\\\/aixia.se\\\/en\\\/\",\"email\":\"info@aixia.se\",\"telephone\":\"+46317620240\",\"foundingDate\":\"2007-01-01\",\"numberOfEmployees\":{\"@type\":\"QuantitativeValue\",\"value\":60},\"logo\":{\"@type\":\"ImageObject\",\"url\":\"https:\\\/\\\/aixia.se\\\/wp-content\\\/uploads\\\/2026\\\/06\\\/aixia-scaled.png?wsr\",\"@id\":\"https:\\\/\\\/aixia.se\\\/en\\\/nvidia-dynamo\\\/#organizationLogo\",\"width\":2560,\"height\":648},\"image\":{\"@id\":\"https:\\\/\\\/aixia.se\\\/en\\\/nvidia-dynamo\\\/#organizationLogo\"},\"sameAs\":[\"https:\\\/\\\/www.facebook.com\\\/aixiasverige\",\"https:\\\/\\\/twitter.com\\\/aixiasverige\",\"https:\\\/\\\/www.instagram.com\\\/aixiasverige\\\/\",\"https:\\\/\\\/www.linkedin.com\\\/company\\\/aixia-ab\",\"https:\\\/\\\/sv.wikipedia.org\\\/wiki\\\/Aixia_Group_AB\",\"https:\\\/\\\/www.wikidata.org\\\/entity\\\/Q140274897\",\"https:\\\/\\\/www.nasdaqomxnordic.com\\\/shares\\\/microsite?Instrument=SE0015192065\",\"https:\\\/\\\/aiqu.ai\"]},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/aixia.se\\\/en\\\/author\\\/petter\\\/#author\",\"url\":\"https:\\\/\\\/aixia.se\\\/en\\\/author\\\/petter\\\/\",\"name\":\"Petter\",\"image\":{\"@type\":\"ImageObject\",\"@id\":\"https:\\\/\\\/aixia.se\\\/en\\\/nvidia-dynamo\\\/#authorImage\",\"url\":\"https:\\\/\\\/aixia.se\\\/wp-content\\\/litespeed\\\/avatar\\\/562b0bb786aac147ec6b7caf25d3572a.jpg?ver=1787190032\",\"width\":96,\"height\":96,\"caption\":\"Petter\"}},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/aixia.se\\\/en\\\/nvidia-dynamo\\\/#webpage\",\"url\":\"https:\\\/\\\/aixia.se\\\/en\\\/nvidia-dynamo\\\/\",\"name\":\"NVIDIA Dynamo \\u2013 new framework for AI inference - Aixia\",\"description\":\"Read about NVIDIA Dynamo. 13\\u219244 characters.\",\"inLanguage\":\"en-US\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/aixia.se\\\/en\\\/#website\"},\"breadcrumb\":{\"@id\":\"https:\\\/\\\/aixia.se\\\/en\\\/nvidia-dynamo\\\/#breadcrumblist\"},\"author\":{\"@id\":\"https:\\\/\\\/aixia.se\\\/en\\\/author\\\/petter\\\/#author\"},\"creator\":{\"@id\":\"https:\\\/\\\/aixia.se\\\/en\\\/author\\\/petter\\\/#author\"},\"image\":{\"@type\":\"ImageObject\",\"url\":\"https:\\\/\\\/aixia.se\\\/wp-content\\\/uploads\\\/2025\\\/04\\\/Nvidia-Dynamo-Aixia.png?wsr\",\"@id\":\"https:\\\/\\\/aixia.se\\\/en\\\/nvidia-dynamo\\\/#mainImage\",\"width\":1306,\"height\":871},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/aixia.se\\\/en\\\/nvidia-dynamo\\\/#mainImage\"},\"datePublished\":\"2025-04-29T15:27:01+02:00\",\"dateModified\":\"2026-03-09T13:47:10+01:00\"},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/aixia.se\\\/en\\\/#website\",\"url\":\"https:\\\/\\\/aixia.se\\\/en\\\/\",\"name\":\"AI-infrastruktur, MLOps &amp; IT-l\\u00f6sningar Norden | Aixia\",\"inLanguage\":\"en-US\",\"publisher\":{\"@id\":\"https:\\\/\\\/aixia.se\\\/en\\\/#organization\"}}]}\n\t\t<\/script>\n\t\t<!-- All in One SEO -->\n\n","aioseo_head_json":{"title":"NVIDIA Dynamo \u2013 new framework for AI inference - Aixia","description":"Read about NVIDIA Dynamo. 13\u219244 characters.","canonical_url":"https:\/\/aixia.se\/en\/nvidia-dynamo\/","robots":"max-image-preview:large","keywords":"","webmasterTools":{"miscellaneous":""},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"BlogPosting","@id":"https:\/\/aixia.se\/en\/nvidia-dynamo\/#blogposting","name":"NVIDIA Dynamo \u2013 new framework for AI inference - Aixia","headline":"NVIDIA Dynamo &#8211; new framework for AI inference","author":{"@id":"https:\/\/aixia.se\/en\/author\/petter\/#author"},"publisher":{"@id":"https:\/\/aixia.se\/en\/#organization"},"image":{"@type":"ImageObject","url":"https:\/\/aixia.se\/wp-content\/uploads\/2025\/04\/Nvidia-Dynamo-Aixia.png?wsr","width":1306,"height":871},"datePublished":"2025-04-29T15:27:01+02:00","dateModified":"2026-03-09T13:47:10+01:00","inLanguage":"en-US","mainEntityOfPage":{"@id":"https:\/\/aixia.se\/en\/nvidia-dynamo\/#webpage"},"isPartOf":{"@id":"https:\/\/aixia.se\/en\/nvidia-dynamo\/#webpage"},"articleSection":"News, Techblog, Optional"},{"@type":"BreadcrumbList","@id":"https:\/\/aixia.se\/en\/nvidia-dynamo\/#breadcrumblist","itemListElement":[{"@type":"ListItem","@id":"https:\/\/aixia.se\/en\/#listItem","position":1,"name":"Home","item":"https:\/\/aixia.se\/en\/","nextItem":{"@type":"ListItem","@id":"https:\/\/aixia.se\/en\/category\/news\/#listItem","name":"News"}},{"@type":"ListItem","@id":"https:\/\/aixia.se\/en\/category\/news\/#listItem","position":2,"name":"News","item":"https:\/\/aixia.se\/en\/category\/news\/","nextItem":{"@type":"ListItem","@id":"https:\/\/aixia.se\/en\/nvidia-dynamo\/#listItem","name":"NVIDIA Dynamo &#8211; new framework for AI inference"},"previousItem":{"@type":"ListItem","@id":"https:\/\/aixia.se\/en\/#listItem","name":"Home"}},{"@type":"ListItem","@id":"https:\/\/aixia.se\/en\/nvidia-dynamo\/#listItem","position":3,"name":"NVIDIA Dynamo &#8211; new framework for AI inference","previousItem":{"@type":"ListItem","@id":"https:\/\/aixia.se\/en\/category\/news\/#listItem","name":"News"}}]},{"@type":"Organization","@id":"https:\/\/aixia.se\/en\/#organization","name":"Aixia Group AB","description":"Aixia levererar AI-infrastruktur, GPU-kluster, MLOps och IT-drift till nordiska f\u00f6retag. Exklusiv NVIDIA DGX SuperPOD-partner med egen AI-plattform AiQu.","url":"https:\/\/aixia.se\/en\/","email":"info@aixia.se","telephone":"+46317620240","foundingDate":"2007-01-01","numberOfEmployees":{"@type":"QuantitativeValue","value":60},"logo":{"@type":"ImageObject","url":"https:\/\/aixia.se\/wp-content\/uploads\/2026\/06\/aixia-scaled.png?wsr","@id":"https:\/\/aixia.se\/en\/nvidia-dynamo\/#organizationLogo","width":2560,"height":648},"image":{"@id":"https:\/\/aixia.se\/en\/nvidia-dynamo\/#organizationLogo"},"sameAs":["https:\/\/www.facebook.com\/aixiasverige","https:\/\/twitter.com\/aixiasverige","https:\/\/www.instagram.com\/aixiasverige\/","https:\/\/www.linkedin.com\/company\/aixia-ab","https:\/\/sv.wikipedia.org\/wiki\/Aixia_Group_AB","https:\/\/www.wikidata.org\/entity\/Q140274897","https:\/\/www.nasdaqomxnordic.com\/shares\/microsite?Instrument=SE0015192065","https:\/\/aiqu.ai"]},{"@type":"Person","@id":"https:\/\/aixia.se\/en\/author\/petter\/#author","url":"https:\/\/aixia.se\/en\/author\/petter\/","name":"Petter","image":{"@type":"ImageObject","@id":"https:\/\/aixia.se\/en\/nvidia-dynamo\/#authorImage","url":"https:\/\/aixia.se\/wp-content\/litespeed\/avatar\/562b0bb786aac147ec6b7caf25d3572a.jpg?ver=1787190032","width":96,"height":96,"caption":"Petter"}},{"@type":"WebPage","@id":"https:\/\/aixia.se\/en\/nvidia-dynamo\/#webpage","url":"https:\/\/aixia.se\/en\/nvidia-dynamo\/","name":"NVIDIA Dynamo \u2013 new framework for AI inference - Aixia","description":"Read about NVIDIA Dynamo. 13\u219244 characters.","inLanguage":"en-US","isPartOf":{"@id":"https:\/\/aixia.se\/en\/#website"},"breadcrumb":{"@id":"https:\/\/aixia.se\/en\/nvidia-dynamo\/#breadcrumblist"},"author":{"@id":"https:\/\/aixia.se\/en\/author\/petter\/#author"},"creator":{"@id":"https:\/\/aixia.se\/en\/author\/petter\/#author"},"image":{"@type":"ImageObject","url":"https:\/\/aixia.se\/wp-content\/uploads\/2025\/04\/Nvidia-Dynamo-Aixia.png?wsr","@id":"https:\/\/aixia.se\/en\/nvidia-dynamo\/#mainImage","width":1306,"height":871},"primaryImageOfPage":{"@id":"https:\/\/aixia.se\/en\/nvidia-dynamo\/#mainImage"},"datePublished":"2025-04-29T15:27:01+02:00","dateModified":"2026-03-09T13:47:10+01:00"},{"@type":"WebSite","@id":"https:\/\/aixia.se\/en\/#website","url":"https:\/\/aixia.se\/en\/","name":"AI-infrastruktur, MLOps &amp; IT-l\u00f6sningar Norden | Aixia","inLanguage":"en-US","publisher":{"@id":"https:\/\/aixia.se\/en\/#organization"}}]},"og:locale":"en_US","og:site_name":"Aixia -","og:type":"article","og:title":"NVIDIA Dynamo \u2013 new framework for AI inference - Aixia","og:description":"Read about NVIDIA Dynamo. 13\u219244 characters.","og:url":"https:\/\/aixia.se\/en\/nvidia-dynamo\/","article:published_time":"2025-04-29T13:27:01+00:00","article:modified_time":"2026-03-09T12:47:10+00:00","article:publisher":"https:\/\/www.facebook.com\/aixiasverige","twitter:card":"summary_large_image","twitter:site":"@aixiasverige","twitter:title":"NVIDIA Dynamo \u2013 new framework for AI inference - Aixia","twitter:description":"Read about NVIDIA Dynamo. 13\u219244 characters.","twitter:creator":"@aixiasverige"},"aioseo_meta_data":{"post_id":"120462","title":null,"description":null,"keywords":null,"keyphrases":{"focus":{"keyphrase":"","score":0,"analysis":{"keyphraseInTitle":{"score":0,"maxScore":9,"error":1}}},"additional":[]},"primary_term":null,"canonical_url":null,"og_title":null,"og_description":null,"og_object_type":"default","og_image_type":"default","og_image_url":null,"og_image_width":null,"og_image_height":null,"og_image_custom_url":null,"og_image_custom_fields":null,"og_video":"","og_custom_url":null,"og_article_section":null,"og_article_tags":null,"twitter_use_og":false,"twitter_card":"default","twitter_image_type":"default","twitter_image_url":null,"twitter_image_custom_url":null,"twitter_image_custom_fields":null,"twitter_title":null,"twitter_description":null,"schema":{"blockGraphs":[],"customGraphs":[],"default":{"data":{"Article":[],"Course":[],"Dataset":[],"FAQPage":[],"Movie":[],"Person":[],"Product":[],"ProductReview":[],"Car":[],"Recipe":[],"Service":[],"SoftwareApplication":[],"WebPage":[]},"graphName":"BlogPosting","isEnabled":true},"graphs":[]},"schema_type":"default","schema_type_options":null,"pillar_content":false,"robots_default":true,"robots_noindex":false,"robots_noarchive":false,"robots_nosnippet":false,"robots_nofollow":false,"robots_noimageindex":false,"robots_noodp":false,"robots_notranslate":false,"robots_max_snippet":"-1","robots_max_videopreview":"-1","robots_max_imagepreview":"large","priority":null,"frequency":"default","local_seo":null,"breadcrumb_settings":null,"limit_modified_date":false,"ai":null,"created":"2025-11-11 23:10:18","updated":"2026-03-09 13:02:57","focus_keyword":null,"additional_keywords":null,"truseo_locale":null,"seo_analyzer_scan_date":null},"aioseo_breadcrumb":"<div class=\"aioseo-breadcrumbs\"><span class=\"aioseo-breadcrumb\">\n\t\t\t<a href=\"https:\/\/aixia.se\/en\/\" title=\"Home\">Home<\/a>\n\t\t<\/span><span class=\"aioseo-breadcrumb-separator\">&raquo;<\/span><span class=\"aioseo-breadcrumb\">\n\t\t\t<a href=\"https:\/\/aixia.se\/en\/category\/news\/\" title=\"News\">News<\/a>\n\t\t<\/span><span class=\"aioseo-breadcrumb-separator\">&raquo;<\/span><span class=\"aioseo-breadcrumb\">\n\t\t\tNVIDIA Dynamo \u2013 new framework for AI inference\n\t\t<\/span><\/div>","aioseo_breadcrumb_json":[{"label":"Home","link":"https:\/\/aixia.se\/en\/"},{"label":"News","link":"https:\/\/aixia.se\/en\/category\/news\/"},{"label":"NVIDIA Dynamo &#8211; new framework for AI inference","link":"https:\/\/aixia.se\/en\/nvidia-dynamo\/"}],"_links":{"self":[{"href":"https:\/\/aixia.se\/en\/wp-json\/wp\/v2\/posts\/120462","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/aixia.se\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/aixia.se\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/aixia.se\/en\/wp-json\/wp\/v2\/users\/4"}],"replies":[{"embeddable":true,"href":"https:\/\/aixia.se\/en\/wp-json\/wp\/v2\/comments?post=120462"}],"version-history":[{"count":2,"href":"https:\/\/aixia.se\/en\/wp-json\/wp\/v2\/posts\/120462\/revisions"}],"predecessor-version":[{"id":121240,"href":"https:\/\/aixia.se\/en\/wp-json\/wp\/v2\/posts\/120462\/revisions\/121240"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/aixia.se\/en\/wp-json\/wp\/v2\/media\/118490"}],"wp:attachment":[{"href":"https:\/\/aixia.se\/en\/wp-json\/wp\/v2\/media?parent=120462"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/aixia.se\/en\/wp-json\/wp\/v2\/categories?post=120462"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/aixia.se\/en\/wp-json\/wp\/v2\/tags?post=120462"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}