{"slug": "google-tensor-sdk-beta-with-litert", "title": "Google Tensor SDK Beta with LiteRT", "summary": "The Google Tensor ML SDK has moved from an Experimental Access Program to Beta, now integrating with LiteRT to provide a unified API for deploying machine learning models on the Tensor Processing Unit (TPU) of Pixel 10 devices. This update allows developers to access over 100 pre-optimized models, including Gemma 3 1B, enabling on-device AI features like Pro Zoom and Voice Translate with improved performance and privacy. The SDK supports the Pixel 10 family, offering a streamlined workflow for converting, compiling, and running models directly on the device's custom Tensor SoC.", "body_md": "Google Tensor ML SDK empowers you to build on-device machine learning capabilities starting from Google Pixel 10 family of devices1, while leveraging Pixel's custom-designed Google Tensor System-on-Chip (SoC) with its dedicated Tensor Processing Unit (TPU) inference accelerator. Today, the Tensor ML SDK is graduating from its Experimental Access Program (EAP) to Beta, enabling developers to build and deploy their AI experiences seamlessly on Google Tensor’s TPU. Tensor’s TPU unlocks interactive, realtime and private on-device AI experiences such as Pixel’s Pro Zoom2, Add Me, Voice Translate3 and Call Notes4 to name a few.\nLink to Youtube Video (visible only when JS is disabled)\nThe Beta launch unlocks two major advantages for developers:\nLiteRT is Google's on-device framework for high-performance machine learning (ML) deployment on edge platforms. It abstracts away low-level, vendor-specific SDKs including compilers and runtimes and exposes them through a unified, streamlined developer-facing API. Tensor ML SDK is now integrated with LiteRT offering a seamless developer workflow to convert, compile, deploy and run ML and Generative AI models on Google Pixel via Tensor’s TPU.\nFor a full, detailed guide, including colab and sample apps, visit the LiteRT NPU documentation.\nThe Tensor SDK Beta enables deployment of a wide array of models—including computer vision and speech recognition—straight to Pixel devices through a large model garden. The model garden provides over 100+ Classic ML models and Generative AI Models (Gemma 3 1B), alongside a library of precompiled models available to download directly from the LiteRT Hugging Face community.\nHere is a look at what developers can build with the models available:\nHere are a couple of demos for inspiration:\nWe invite the developer community to build a new class of intelligent and responsive AI applications starting with the Pixel 10 family. Explore the Tensor SDK, experiment with running your models on the TPU, and share your feedback with the LiteRT community on Github.\nIf you're joining us at I/O—either in person or virtually—be sure to check out our dedicated codelabs and sample app. You'll get hands-on experience using the Tensor SDK, compiling models, and deploying them to the family of Pixel 10 devices via TPU.\nDevices Supported: Pixel 10, Pixel 10 Pro, Pixel 10 Pro XL, and Pixel 10 Pro Fold.\nWe can’t wait to see what you build on Pixel!\nThis project was made possible through the collaboration of several teams. We thank them for their significant contributions:\nTensor Team: Himangshu Roy, Chirag Gupta, Rishubh Khurana, Rachit Agrawal, Priya Patel, Prakul Sawhney, Abby Chung, Malini P V, Jui Pradhan, Naina Singla, Debapriya Maji, Aditya Srivastava, Abhishek Jatram, Vibhu Agrawal, Rachana Jayaram, Lokesh Vutla, Abhishek Singh, Annie Fu, Chen-Hao Liao, Chanchal Raj, Ty Werbicki, Sriram Kashyap M S, Shubham Saini, Thiru Ramasamy, Jayanthan K, Payal Agarwal, Pranjal Srivastava, Yathish Reddy M, Akhilesh Ravi, Harold Yang, Yi Yo, Priyanka Mittal, Ishaan Agrawal, Vivek Kumar, Minje Park, YoonKyung Kim, Eunji Heo, Mehran Nekuii, John Joseph, Nett Phasukavanich, Jess Tsopanis, Chen-Hao Liao, Jeff Setter, Ganesh Rao, Neena Maldikar.\nLiteRT Team: Lu Wang, Weiyi Wang, Jingjiang Li, Gerardo Carranza, Terry (Woncheol) Heo, Andrew Zhang, Chenchen Tang, Shuangfeng Li, Changming Sun, Somdatta Banerjee, Na Li, Yu-hui Chen, Tenghui Zhu, Alice Zheng, Chintan Parikh, Sachin Kotwani, Cormac Brick, Matthias Grundmann, Salil Tambe.\nhttps://ai.google.dev/edge/litert/next/tensor_ml_terms\n1 - Devices supported are Pixel 10, Pixel 10 Pro, Pixel 10 Pro XL, and Pixel 10 Pro Fold.\n2 - Available in select countries and languages.\n3 - Available in select countries and languages. Results may vary. Check responses for accuracy.\n4 - Available in the US. English Only\nExplore this announcement and all Google I/O 2026 updates on io.google.", "url": "https://wpnews.pro/news/google-tensor-sdk-beta-with-litert", "canonical_source": "https://developers.googleblog.com/google-tensor-sdk-beta-with-litert/", "published_at": "2026-05-20 03:07:11.225006+00:00", "updated_at": "2026-05-20 03:07:15.704372+00:00", "lang": "en", "topics": ["machine-learning", "developer-tools", "artificial-intelligence", "hardware", "products"], "entities": ["Google Tensor", "Tensor ML SDK", "LiteRT", "Pixel", "TPU", "Google", "Pixel 10", "Tensor Processing Unit"], "alternates": {"html": "https://wpnews.pro/news/google-tensor-sdk-beta-with-litert", "markdown": "https://wpnews.pro/news/google-tensor-sdk-beta-with-litert.md", "text": "https://wpnews.pro/news/google-tensor-sdk-beta-with-litert.txt", "jsonld": "https://wpnews.pro/news/google-tensor-sdk-beta-with-litert.jsonld"}}