--- title: What's new in TensorFlow 2.21 | daily.dev description: TensorFlow 2.21 is released, with the headline change being LiteRT's graduation into full production status. LiteRT is Google's high-performance on-device... canonical: https://daily.dev/posts/what-s-new-in-tensorflow-2-21-i2uzgtrul twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: What's new in TensorFlow 2.21 | daily.dev og:description: TensorFlow 2.21 is released, with the headline change being LiteRT's graduation into full production status. LiteRT is Google's high-performance on-device... og:url: https://daily.dev/posts/what-s-new-in-tensorflow-2-21-i2uzgtrul og:image: https://api.daily.dev/og/posts/I2uzgTRUl.png og:image:alt: What's new in TensorFlow 2.21 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. # What's new in TensorFlow 2.21 **[Google Developers](https://daily.dev/sources/googledevs)** · 2 min read · 0 upvotes · 0 comments ## Summary TensorFlow 2.21 is released, with the headline change being LiteRT's graduation into full production status. LiteRT is Google's high-performance on-device inference runtime, offering up to 1.4x faster GPU performance and enhanced NPU acceleration compared to TFLite, which it replaces. It supports cross-platform deployment for models from PyTorch, JAX, and Keras. The TensorFlow team also commits to faster bug fixes and more timely dependency updates going forward, while recommending Keras 3, JAX, and PyTorch for new generative AI work. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [LiteRT: The Universal Framework for On-Device AI](https://daily.dev/posts/litert-the-universal-framework-for-on-device-ai-dkvzmc8hv) · Google Developers · 0 upvotes · 0 comments - [Google’s LiteRT adds advanced hardware acceleration](https://daily.dev/posts/google-s-litert-adds-advanced-hardware-acceleration-negvjtwmm) · InfoWorld · 0 upvotes · 0 comments - [Google Tensor SDK Beta with LiteRT](https://daily.dev/posts/google-tensor-sdk-beta-with-litert-ot1btuipv) · Google Developers · 0 upvotes · 0 comments - [Google Launches AI Inference “LiteRT.js“](https://daily.dev/posts/google-launches-ai-inference-litert-js--golcrppmb) · C\# Corner · 2 upvotes · 1 comments - [Google's New LiteRT Accelerator Supercharges AI Workloads on Snapdragon-powered Android Devices](https://daily.dev/posts/google-s-new-litert-accelerator-supercharges-ai-workloads-on-snapdragon-powered-android-devices-jfvtx4jvg) · InfoQ · 0 upvotes · 0 comments --- Tags: [#machine-learning](https://daily.dev/tags/machine-learning), [#tensorflow](https://daily.dev/tags/tensorflow), [#local-ai](https://daily.dev/tags/local-ai), [#keras](https://daily.dev/tags/keras) [View this post on daily.dev](https://daily.dev/posts/what-s-new-in-tensorflow-2-21-i2uzgtrul) ```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":"What's new in TensorFlow 2.21","url":"https://daily.dev/posts/what-s-new-in-tensorflow-2-21-i2uzgtrul","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/what-s-new-in-tensorflow-2-21-i2uzgtrul"},"datePublished":"2026-03-06T17:04:58.601Z","dateModified":"2026-08-24T06:52:53.100Z","description":"TensorFlow 2.21 is released, with the headline change being LiteRT's graduation into full production status. LiteRT is Google's high-performance on-device...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/cf53693b357605bc41beacb4264cf2dd?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/cf53693b357605bc41beacb4264cf2dd?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Google Developers","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":"Google Developers","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/ea4bbded4e7f45ccb82e121a3156535f","url":"https://daily.dev/sources/googledevs"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/what-s-new-in-tensorflow-2-21-i2uzgtrul","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"machine-learning,tensorflow,local-ai,keras","timeRequired":"PT2M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Google Developers","item":"https://daily.dev/sources/googledevs"},{"@type":"ListItem","position":3,"name":"What's new in TensorFlow 2.21"}]} ```