{"id":176069,"date":"2023-11-15T13:23:21","date_gmt":"2023-11-15T19:23:21","guid":{"rendered":"https:\/\/lifeboat.com\/blog\/2023\/11\/running-thousands-of-llms-on-one-gpu-is-now-possible-with-s-lora"},"modified":"2023-11-15T13:23:21","modified_gmt":"2023-11-15T19:23:21","slug":"running-thousands-of-llms-on-one-gpu-is-now-possible-with-s-lora","status":"publish","type":"post","link":"https:\/\/lifeboat.com\/blog\/2023\/11\/running-thousands-of-llms-on-one-gpu-is-now-possible-with-s-lora","title":{"rendered":"Running thousands of LLMs on one GPU is now possible with S-LoRA"},"content":{"rendered":"<p><a class=\"aligncenter blog-photo\" href=\"https:\/\/lifeboat.com\/blog.images\/running-thousands-of-llms-on-one-gpu-is-now-possible-with-s-lora3.jpg\"><\/a><\/p>\n<p><em><strong>VentureBeat presents: AI Unleashed \u2014 An exclusive executive event for enterprise data leaders. Hear from top industry leaders on Nov 15.<\/strong> <\/em><a href=\"https:\/\/venturebeataiunleashed.com\/\"><strong><em>Reserve your free pass<\/em><\/strong><\/a><\/p>\n<p>Fine-tuning large language models (LLM) has become an important tool for businesses seeking to tailor AI capabilities to niche tasks and personalized user experiences. But fine-tuning usually comes with steep computational and financial overhead, keeping its use limited for enterprises with limited resources.<\/p>\n<p>To solve these challenges, researchers have created algorithms and techniques that cut the cost of fine-tuning LLMs and running fine-tuned models. The latest of these techniques is <a href=\"https:\/\/arxiv.org\/abs\/2311.03285\">S-LoRA<\/a>, a collaborative effort between researchers at Stanford University and University of California-Berkeley (UC Berkeley).<\/p>\n","protected":false},"excerpt":{"rendered":"<p>VentureBeat presents: AI Unleashed \u2014 An exclusive executive event for enterprise data leaders. Hear from top industry leaders on Nov 15. Reserve your free pass Fine-tuning large language models (LLM) has become an important tool for businesses seeking to tailor AI capabilities to niche tasks and personalized user experiences. But fine-tuning usually comes with steep [\u2026]<\/p>\n","protected":false},"author":396,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[43,45,41,6],"tags":[],"class_list":["post-176069","post","type-post","status-publish","format-standard","hentry","category-business","category-finance","category-information-science","category-robotics-ai"],"_links":{"self":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/176069","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=176069"}],"version-history":[{"count":0,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/176069\/revisions"}],"wp:attachment":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/media?parent=176069"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/categories?post=176069"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/tags?post=176069"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}