[[["易于理解","easyToUnderstand","thumb-up"],["解决了我的问题","solvedMyProblem","thumb-up"],["其他","otherUp","thumb-up"]],[["没有我需要的信息","missingTheInformationINeed","thumb-down"],["太复杂/步骤太多","tooComplicatedTooManySteps","thumb-down"],["内容需要更新","outOfDate","thumb-down"],["翻译问题","translationIssue","thumb-down"],["示例/代码问题","samplesCodeIssue","thumb-down"],["其他","otherDown","thumb-down"]],["最后更新时间 (UTC):2025-06-17。"],[],[],null,["# Google AI Edge Portal\n\n| **Note:** Google AI Edge Portal is in Private Preview and supports .litert models on GPU \\& CPU at this time. Complete our [sign-up form](https://docs.google.com/forms/d/e/1FAIpQLSfTcGPycQve8TLAsfH46pBlXBZe9FrgJAClwbF7DeL1LgVn4Q/viewform?usp=header) to request access.\n\n**AI Edge's Google Cloud solution for testing and benchmarking on-device machine learning (ML) at scale.**\n\n[Sign Up](https://docs.google.com/forms/d/e/1FAIpQLSfTcGPycQve8TLAsfH46pBlXBZe9FrgJAClwbF7DeL1LgVn4Q/viewform?usp=header)\n\nOptimizing ML model performance across diverse mobile devices can be challenging.\nManual testing is slow, costly, and often inaccessible to most developers,\nleading to uncertainties in real-world model performance. Google AI Edge\nPortal solves this by **enabling LiteRT model benchmarking across a wide-range\nof mobile devices**, helping developers find the best configurations for\nlarge-scale ML model deployment.\n\nOptimizing mobile ML deployment\n-------------------------------\n\n- **Simplify \\& accelerate testing cycles across the diverse hardware landscape**:\n Effortlessly assess model performance across hundreds of\n representative mobile devices in minutes.\n\n- **Proactively assure model quality \\& identify issues early**: Pinpoint\n hardware-specific performance variations or regressions (like on particular\n chipsets or memory-constrained devices) before deployment.\n\n- **Lower device testing cost \\& access latest hardware**: Test on diverse and\n continually growing fleet of physical devices (currently 100+ device models\n from various Android OEMs) without the expense and complexity of maintaining\n your own lab.\n\n- **Unlock powerful, data-driven decisions \\& business intelligence**: Google AI\n Edge Portal delivers rich performance data and comparisons, providing the\n crucial business intelligence needed to confidently guide model optimization\n and validate deployment readiness.\n\nExample benchmark:\n\n\u003cbr /\u003e\n\nHow Google AI Edge Portal helps you benchmark your LiteRT models\n----------------------------------------------------------------\n\n1. **Upload \\& configure**: Upload your model file via the UI or point to it in your\n Google Cloud Storage bucket.\n\n2. **Select accelerators**: Specify testing against CPU or GPU (with automatic CPU\n fallback). NPU support is planned for future releases.\n\n3. **Select devices**: Choose target devices from our diverse pool using filters\n (device tier, brand, chipset, RAM) or select curated lists with convenient\n shortcuts.\n\n\u003cbr /\u003e\n\n\n*Create a New Benchmark Job on 100+ Devices. (Note: GIF is accelerated and edited for brevity)*\n\nFrom there, submit your job and await completion. Once ready, explore the\nresults in the Interactive Dashboard:\n\n- **Compare configurations**: Quickly visualize how performance metrics (e.g.,\n average latency, peak memory) differ when using different accelerators across\n all tested devices.\n\n- **Analyze device impact**: See how a specific model configuration performs across\n the range of selected devices. Use histograms and scatter plots to quickly\n identify performance variations tied to device characteristics.\n\n- **Detailed metrics**: Access a detailed, sortable table showing specific metrics\n (initialization time, inference latency, memory usage) for each individual\n device, alongside its hardware specifications.\n\n\u003cbr /\u003e\n\n\n*View Benchmark Results on the interactive Dashboard. (Note: GIF is accelerated and edited for brevity)*\n\nJoin the Google AI Edge Portal private preview\n----------------------------------------------\n\nGoogle AI Edge Portal is available in private preview for allowlisted Google\nCloud customers. During this private preview period, access is provided at no\ncharge, subject to the preview terms.\n\nThis preview is ideal for developers and teams building mobile ML applications\nwith LiteRT who need reliable benchmarking data across diverse Android hardware\nand are willing to provide feedback to help shape the product's future. To\nrequest access, complete our [sign-up form here](https://docs.google.com/forms/d/e/1FAIpQLSfTcGPycQve8TLAsfH46pBlXBZe9FrgJAClwbF7DeL1LgVn4Q/viewform?usp=header)\nto express interest. Access is granted via allowlisting."]]