{"id":1017939,"date":"2024-03-22T17:14:57","date_gmt":"2024-03-23T00:14:57","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-project&#038;p=1017939"},"modified":"2024-09-06T14:53:30","modified_gmt":"2024-09-06T21:53:30","slug":"efficient-ai","status":"publish","type":"msr-project","link":"https:\/\/www.microsoft.com\/en-us\/research\/project\/efficient-ai\/","title":{"rendered":"Efficient AI"},"content":{"rendered":"<section class=\"mb-3 moray-highlight\">\n\t<div class=\"card-img-overlay mx-lg-0\">\n\t\t<div class=\"card-background  has-background- card-background--full-bleed\">\n\t\t\t<img loading=\"lazy\" decoding=\"async\" width=\"1920\" height=\"720\" src=\"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2023\/11\/RoboticsWorkshop_WebBanner_1920x720_Dark-Spectrum.jpg\" class=\"attachment-full size-full\" alt=\"robotics workshop header - server hallway with a color gradient overlay\" style=\"\" srcset=\"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2023\/11\/RoboticsWorkshop_WebBanner_1920x720_Dark-Spectrum.jpg 1920w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2023\/11\/RoboticsWorkshop_WebBanner_1920x720_Dark-Spectrum-300x113.jpg 300w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2023\/11\/RoboticsWorkshop_WebBanner_1920x720_Dark-Spectrum-1024x384.jpg 1024w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2023\/11\/RoboticsWorkshop_WebBanner_1920x720_Dark-Spectrum-768x288.jpg 768w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2023\/11\/RoboticsWorkshop_WebBanner_1920x720_Dark-Spectrum-1536x576.jpg 1536w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2023\/11\/RoboticsWorkshop_WebBanner_1920x720_Dark-Spectrum-1600x600.jpg 1600w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2023\/11\/RoboticsWorkshop_WebBanner_1920x720_Dark-Spectrum-240x90.jpg 240w\" sizes=\"(max-width: 1920px) 100vw, 1920px\" \/>\t\t<\/div>\n\t\t<!-- Foreground -->\n\t\t<div class=\"card-foreground d-flex mt-md-n5 my-lg-5 px-g px-lg-0\">\n\t\t\t<!-- Container -->\n\t\t\t<div class=\"container d-flex mt-md-n5 my-lg-5 \">\n\t\t\t\t<!-- Card wrapper -->\n\t\t\t\t<div class=\"w-100 w-lg-col-5\">\n\t\t\t\t\t<!-- Card -->\n\t\t\t\t\t<div class=\"card material-md-card py-5 px-md-5\">\n\t\t\t\t\t\t<div class=\"card-body \">\n\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t\n\n<h1 class=\"wp-block-heading\" id=\"efficient-ai\">Efficient AI<\/h1>\n\n\n\n<p>Making Azure&#8217;s big bet possible<\/p>\n\n\t\t\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t<\/div>\n\t\t<\/div>\n\t<\/div>\n<\/section>\n\n\n\n\n\n<p>Recent innovations in generative large language models (LLMs) have made their applications and use-cases ubiquitous. This has led to large-scale deployments of these models, using complex, expensive, and power-hungry AI accelerators, most commonly GPUs. These developments make LLM training and inference efficiency an important challenge.<\/p>\n\n\n\n<p>In the <a class=\"msr-external-link glyph-append glyph-append-open-in-new-tab glyph-append-xsmall\" href=\"https:\/\/aka.ms\/azrs\">Azure Research &#8211; Systems<span class=\"sr-only\"> (opens in new tab)<\/span><\/a> group we are working on improving the Azure infrastructure including hardware, power, and serving.<\/p>\n\n\n\n<p>Check the publications tab for our work so far!<\/p>\n\n\n\n<div style=\"height:25px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n","protected":false},"excerpt":{"rendered":"<p>Making Azure&#8217;s big bet possible Recent innovations in generative large language models (LLMs) have made their applications and use-cases ubiquitous. This has led to large-scale deployments of these models, using complex, expensive, and power-hungry AI accelerators, most commonly GPUs. These developments make LLM training and inference efficiency an important challenge. In the Azure Research &#8211; [&hellip;]<\/p>\n","protected":false},"featured_media":981582,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","footnotes":""},"research-area":[13547],"msr-locale":[268875],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-1017939","msr-project","type-msr-project","status-publish","has-post-thumbnail","hentry","msr-research-area-systems-and-networking","msr-locale-en_us","msr-archive-status-active"],"msr_project_start":"","related-publications":[1083432,1083438,1088772,990234,990468,999297,1016907,1083420,1083426],"related-downloads":[],"related-videos":[],"related-groups":[],"related-events":[],"related-opportunities":[],"related-posts":[],"related-articles":[],"tab-content":[],"slides":[],"related-researchers":[{"type":"user_nicename","display_name":"Esha Choukse","user_id":40417,"people_section":"Related people","alias":"eschouks"},{"type":"user_nicename","display_name":"Chaojie Zhang","user_id":42705,"people_section":"Related people","alias":"chaojiezhang"},{"type":"user_nicename","display_name":"&Iacute;&ntilde;igo Goiri","user_id":32102,"people_section":"Related people","alias":"inigog"},{"type":"user_nicename","display_name":"Rodrigo Fonseca","user_id":40429,"people_section":"Related people","alias":"rofons"},{"type":"user_nicename","display_name":"Ricardo Bianchini","user_id":33393,"people_section":"Related people","alias":"ricardob"}],"msr_research_lab":[],"msr_impact_theme":[],"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/1017939"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-project"}],"version-history":[{"count":8,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/1017939\/revisions"}],"predecessor-version":[{"id":1083444,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/1017939\/revisions\/1083444"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media\/981582"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=1017939"}],"wp:term":[{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=1017939"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=1017939"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=1017939"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=1017939"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}