--- title: Google Launches AI Inference “LiteRT.js“ | daily.dev description: Google has launched LiteRT.js, a high-performance JavaScript runtime that enables machine learning and generative AI inference directly in web browsers using... canonical: https://daily.dev/posts/google-launches-ai-inference-litert-js--golcrppmb twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Google Launches AI Inference “LiteRT.js“ | daily.dev og:description: Google has launched LiteRT.js, a high-performance JavaScript runtime that enables machine learning and generative AI inference directly in web browsers using... og:url: https://daily.dev/posts/google-launches-ai-inference-litert-js--golcrppmb og:image: https://api.daily.dev/og/posts/GOLCrpPMB.png og:image:alt: Google Launches AI Inference “LiteRT.js“ 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. # Google Launches AI Inference “LiteRT.js“ **[C\# Corner](https://daily.dev/sources/csharpcorner)** · 2 min read · 2 upvotes · 1 comments ## Summary Google has launched LiteRT.js, a high-performance JavaScript runtime that enables machine learning and generative AI inference directly in web browsers using local hardware acceleration via WebGPU. It is part of the LiteRT ecosystem (successor to TensorFlow Lite) and extends browser AI with fully local execution, zero inference costs after model download, offline support, and a simplified model conversion pipeline from PyTorch, TensorFlow, and JAX. LiteRT.js is designed to complement rather than replace TensorFlow.js, allowing developers to swap only the model execution layer for improved performance while keeping existing preprocessing logic intact. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What is LiteRT.js and how does it run AI models in the browser? LiteRT.js is a JavaScript runtime from Google that runs machine learning and generative AI models directly inside web browsers using local hardware acceleration, primarily WebGPU with future WebNN support. It is part of the LiteRT ecosystem, the successor to TensorFlow Lite, and executes models fully on-device for lower latency, offline use, and no per-inference cloud costs after the model is downloaded. _Developers weighing on-device versus cloud inference can track runtime releases like this on daily.dev._ ### Can I use LiteRT.js together with TensorFlow.js in the same web app? Yes, LiteRT.js is designed as a complementary runtime rather than a TensorFlow.js replacement. Developers can keep using TensorFlow.js for preprocessing and postprocessing while swapping only the model execution layer to LiteRT.js, so migration typically means replacing model loading code while leaving most application logic unchanged. _Teams planning a TensorFlow.js migration path can follow runtime updates like this via daily.dev._ ### How do I convert a PyTorch model to run with LiteRT.js in the browser? LiteRT.js supports converting models directly from PyTorch, TensorFlow, or JAX into the .tflite format without the complex conversion chains typically required for TensorFlow.js workflows. This simplified pipeline is one of the key improvements over earlier browser-based inference approaches, making it easier to bring existing models to web-native AI experiences. _Developers migrating models across frameworks can follow tooling changes like this on daily.dev._ ## Community discussion Top comments from developers on daily.dev. **@aleksei\_aleinikov** · 0 upvotes > A useful step for browser-based AI. Local inference with WebGPU can reduce latency, improve privacy, and remove ongoing inference costs. ## Similar posts on daily.dev - [LiteRT.js, Google's high performance Web AI Inference](https://daily.dev/posts/litert-js-google-s-high-performance-web-ai-inference-trneihldh) · Google Developers · 3 upvotes · 0 comments - [How Google Is Shifting AI From the Cloud to Your Browser](https://daily.dev/posts/how-google-is-shifting-ai-from-the-cloud-to-your-browser-gdtsilce3) · The New Stack · 1 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 - [WebGPU Browser AI: Client-Side Inference in JavaScript](https://daily.dev/posts/webgpu-browser-ai-client-side-inference-in-javascript-qmvpskeqv) · SitePoint · 0 upvotes · 0 comments - [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 --- Tags: [#machine-learning](https://daily.dev/tags/machine-learning), [#tensorflow](https://daily.dev/tags/tensorflow), [#webgpu](https://daily.dev/tags/webgpu) [View this post on daily.dev](https://daily.dev/posts/google-launches-ai-inference-litert-js--golcrppmb) ```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":"Google Launches AI Inference “LiteRT.js“","url":"https://daily.dev/posts/google-launches-ai-inference-litert-js--golcrppmb","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/google-launches-ai-inference-litert-js--golcrppmb"},"datePublished":"2026-07-10T05:26:38.641Z","dateModified":"2026-09-14T08:14:01.510Z","description":"Google has launched LiteRT.js, a high-performance JavaScript runtime that enables machine learning and generative AI inference directly in web browsers using...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/81f698b062e81502c45df6b257ae3843?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/81f698b062e81502c45df6b257ae3843?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"C# Corner","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":"C# Corner","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/ada2d584df6241748fc4e71878dc70a3","url":"https://daily.dev/sources/csharpcorner"},"commentCount":1,"discussionUrl":"https://daily.dev/posts/google-launches-ai-inference-litert-js--golcrppmb","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":2},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":1}],"keywords":"machine-learning,tensorflow,webgpu","timeRequired":"PT2M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"C# Corner","item":"https://daily.dev/sources/csharpcorner"},{"@type":"ListItem","position":3,"name":"Google Launches AI Inference “LiteRT.js“"}]} {"@context":"https://schema.org","@type":"WebPage","@id":"https://daily.dev/posts/google-launches-ai-inference-litert-js--golcrppmb","comment":[{"@type":"Comment","text":"A useful step for browser-based AI. Local inference with WebGPU can reduce latency, improve privacy, and remove ongoing inference costs.","datePublished":"2026-07-11T17:30:29.925Z","url":"https://daily.dev/posts/GOLCrpPMB#c-HhbR0IWnO","author":{"@type":"Person","name":"Aleksei Aleinikov","url":"https://daily.dev/aleksei_aleinikov","image":"https://lh3.googleusercontent.com/a/ACg8ocJ_l1qn_U-_YIOWNm3o7ajQpJM5DHFhA-FW4lS7TeUPB4h8uIM=s96-c"}}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/google-launches-ai-inference-litert-js--golcrppmb#faq","mainEntity":[{"@type":"Question","name":"What is LiteRT.js and how does it run AI models in the browser?","acceptedAnswer":{"@type":"Answer","text":"LiteRT.js is a JavaScript runtime from Google that runs machine learning and generative AI models directly inside web browsers using local hardware acceleration, primarily WebGPU with future WebNN support. It is part of the LiteRT ecosystem, the successor to TensorFlow Lite, and executes models fully on-device for lower latency, offline use, and no per-inference cloud costs after the model is downloaded. Developers weighing on-device versus cloud inference can track runtime releases like this on daily.dev."}},{"@type":"Question","name":"Can I use LiteRT.js together with TensorFlow.js in the same web app?","acceptedAnswer":{"@type":"Answer","text":"Yes, LiteRT.js is designed as a complementary runtime rather than a TensorFlow.js replacement. Developers can keep using TensorFlow.js for preprocessing and postprocessing while swapping only the model execution layer to LiteRT.js, so migration typically means replacing model loading code while leaving most application logic unchanged. Teams planning a TensorFlow.js migration path can follow runtime updates like this via daily.dev."}},{"@type":"Question","name":"How do I convert a PyTorch model to run with LiteRT.js in the browser?","acceptedAnswer":{"@type":"Answer","text":"LiteRT.js supports converting models directly from PyTorch, TensorFlow, or JAX into the .tflite format without the complex conversion chains typically required for TensorFlow.js workflows. This simplified pipeline is one of the key improvements over earlier browser-based inference approaches, making it easier to bring existing models to web-native AI experiences. Developers migrating models across frameworks can follow tooling changes like this on daily.dev."}}]} ```