{"id":108219,"date":"2020-06-05T13:44:31","date_gmt":"2020-06-05T20:44:31","guid":{"rendered":"https:\/\/lifeboat.com\/blog\/2020\/06\/serving-gpt-2-at-scale"},"modified":"2020-06-05T13:44:31","modified_gmt":"2020-06-05T20:44:31","slug":"serving-gpt-2-at-scale","status":"publish","type":"post","link":"https:\/\/lifeboat.com\/blog\/2020\/06\/serving-gpt-2-at-scale","title":{"rendered":"Serving GPT-2 at scale"},"content":{"rendered":"<p><a class=\"aligncenter blog-photo\" href=\"https:\/\/lifeboat.com\/blog.images\/serving-gpt-2-at-scale.jpg\"><\/a><\/p>\n<p>Over the last few years, the size of deep learning models has increased at an exponential pace (famously among language models):<\/p>\n<p>And in fact, this chart is out of date. As of this month, OpenAI has announced GPT-3, which is a 175 billion parameter model\u2014or roughly ten times the height of this chart.<\/p>\n<p>As models grow larger, they introduce new infrastructure challenges. For my colleagues and I building <a href=\"https:\/\/github.com\/cortexlabs\/cortex\" class=\"\" target=\"_blank\" rel=\"noopener nofollow\">Cortex<\/a> (open source model serving infrastructure), these challenges are front and center, especially as the number of users deploying large models to production increases.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Over the last few years, the size of deep learning models has increased at an exponential pace (famously among language models): And in fact, this chart is out of date. As of this month, OpenAI has announced GPT-3, which is a 175 billion parameter model\u2014or roughly ten times the height of this chart. As models [\u2026]<\/p>\n","protected":false},"author":396,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[6],"tags":[],"class_list":["post-108219","post","type-post","status-publish","format-standard","hentry","category-robotics-ai"],"_links":{"self":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/108219","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/users\/396"}],"replies":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/comments?post=108219"}],"version-history":[{"count":0,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/108219\/revisions"}],"wp:attachment":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/media?parent=108219"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/categories?post=108219"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/tags?post=108219"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}