{"id":1450,"date":"2023-11-04T17:59:22","date_gmt":"2023-11-04T17:59:22","guid":{"rendered":"https:\/\/blog.thomarite.uk\/?p=1450"},"modified":"2023-11-04T17:59:22","modified_gmt":"2023-11-04T17:59:22","slug":"fp8-lm","status":"publish","type":"post","link":"https:\/\/blog.thomarite.uk\/index.php\/2023\/11\/04\/fp8-lm\/","title":{"rendered":"FP8-LM"},"content":{"rendered":"\n<p>From the AlphaSignal email list, that most of the times go over my lame knowledge, I found this piece of info, quite interesting:<\/p>\n\n\n\n<h4 class=\"wp-block-heading\">FP8-LM: Training FP8 Large Language Models<\/h4>\n\n\n\n<p>Goal: Optimize LLM training with FP8 low-bit data formats.<br>Issue: High cost of LLM computational resources.<br>Solution: FP8 automatic mixed-precision framework for LLMs.<br>Results: Reduced memory by 42%, increased speed by 64%.<br>Insight: FP8 maintains accuracy, optimizes training efficiency.<\/p>\n\n\n\n<p><a href=\"https:\/\/github.com\/Azure\/MS-AMP\">Repo<\/a>. <a href=\"https:\/\/arxiv.org\/pdf\/2310.18313.pdf\">Paper<\/a><\/p>\n\n\n\n<p>This is something I want to really understand at one point. FP (Floating-Point) instructions can be from several sizes (8, 16, 32, 64). So the bigger, the better precision. I guess for some scientific tasks that is important. But looks like for AI, with FP8 could be good enough. <\/p>\n","protected":false},"excerpt":{"rendered":"<p>From the AlphaSignal email list, that most of the times go over my lame knowledge, I found this piece of info, quite interesting: FP8-LM: Training FP8 Large Language Models Goal: Optimize LLM training with FP8 low-bit data formats.Issue: High cost of LLM computational resources.Solution: FP8 automatic mixed-precision framework for LLMs.Results: Reduced memory by 42%, increased &hellip; <a href=\"https:\/\/blog.thomarite.uk\/index.php\/2023\/11\/04\/fp8-lm\/\" class=\"more-link\">Continue reading<span class=\"screen-reader-text\"> &#8220;FP8-LM&#8221;<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[32],"tags":[],"class_list":["post-1450","post","type-post","status-publish","format-standard","hentry","category-cpu"],"_links":{"self":[{"href":"https:\/\/blog.thomarite.uk\/index.php\/wp-json\/wp\/v2\/posts\/1450","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/blog.thomarite.uk\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/blog.thomarite.uk\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/blog.thomarite.uk\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/blog.thomarite.uk\/index.php\/wp-json\/wp\/v2\/comments?post=1450"}],"version-history":[{"count":1,"href":"https:\/\/blog.thomarite.uk\/index.php\/wp-json\/wp\/v2\/posts\/1450\/revisions"}],"predecessor-version":[{"id":1451,"href":"https:\/\/blog.thomarite.uk\/index.php\/wp-json\/wp\/v2\/posts\/1450\/revisions\/1451"}],"wp:attachment":[{"href":"https:\/\/blog.thomarite.uk\/index.php\/wp-json\/wp\/v2\/media?parent=1450"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/blog.thomarite.uk\/index.php\/wp-json\/wp\/v2\/categories?post=1450"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/blog.thomarite.uk\/index.php\/wp-json\/wp\/v2\/tags?post=1450"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}