--- title: Self-Attention in Transformers: Computation Logic and... description: This post explains the computation logic and implementation of self-attention in transformers. It covers the calculation of attention weights, obtaining value... canonical: https://daily.dev/posts/self-attention-in-transformers-computation-logic-and-implementation-qaqwnbvh9 twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Self-Attention in Transformers: Computation Logic and Implementation | daily.dev og:description: This post explains the computation logic and implementation of self-attention in transformers. It covers the calculation of attention weights, obtaining value... og:url: https://daily.dev/posts/self-attention-in-transformers-computation-logic-and-implementation-qaqwnbvh9 og:image: https://api.daily.dev/og/posts/QAQWNbVh9.png og:image:alt: Self-Attention in Transformers: Computation Logic and Implementation og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Self-Attention in Transformers: Computation Logic and Implementation **[Towards AI](https://daily.dev/sources/tai)** · 3 min read · 0 upvotes · 0 comments ## Summary This post explains the computation logic and implementation of self-attention in transformers. It covers the calculation of attention weights, obtaining value vectors and context vectors, and practical optimizations for computational efficiency. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: --- Tags: [#machine-learning](https://daily.dev/tags/machine-learning), [#transformers](https://daily.dev/tags/transformers) [View this post on daily.dev](https://daily.dev/posts/self-attention-in-transformers-computation-logic-and-implementation-qaqwnbvh9) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Self-Attention in Transformers: Computation Logic and Implementation","url":"https://daily.dev/posts/self-attention-in-transformers-computation-logic-and-implementation-qaqwnbvh9","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/self-attention-in-transformers-computation-logic-and-implementation-qaqwnbvh9"},"datePublished":"2024-04-28T05:35:20.204Z","dateModified":"2024-05-09T09:30:38.138Z","description":"This post explains the computation logic and implementation of self-attention in transformers. It covers the calculation of attention weights, obtaining value...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/3c5a222312cfeb4ba4fa6dddf2302d54?_a=AQAEuiZ","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/3c5a222312cfeb4ba4fa6dddf2302d54?_a=AQAEuiZ","isAccessibleForFree":true,"articleSection":"Towards AI","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Towards AI","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/8b7e3e63e47b4d34b4c1e634b902c12f","url":"https://daily.dev/sources/tai"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/self-attention-in-transformers-computation-logic-and-implementation-qaqwnbvh9","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"machine-learning,transformers","timeRequired":"PT3M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Towards AI","item":"https://daily.dev/sources/tai"},{"@type":"ListItem","position":3,"name":"Self-Attention in Transformers: Computation Logic and Implementation"}]} ```