Go to original source<\/a>
\n \t
\n
<\/BR><\/p>\n","protected":false},"excerpt":{"rendered":"Cutting LLM Memory by 84%: A Deep Dive into Fused Kernels Why your final LLM layer is OOMing and how to fix it with a custom Triton kernel. The post Cutting LLM Memory by 84%: A Deep Dive into Fused Kernels appeared first on Towards Data Science. Ryan P\u00e9goud Go to original source<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[62,4626,67,88,4627,71,3903],"tags":[4628,134,731],"class_list":["post-9807","post","type-post","status-publish","format-standard","hentry","category-aimldsaimlds","category-cross-entropy","category-deep-dives","category-deep-learning","category-kernel","category-large-language-models","category-triton","tag-cutting","tag-llm","tag-memory"],"_links":{"self":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/posts\/9807"}],"collection":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/comments?post=9807"}],"version-history":[{"count":0,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/posts\/9807\/revisions"}],"wp:attachment":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/media?parent=9807"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/categories?post=9807"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/tags?post=9807"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}