LiteRT.js

LiteRT.js is a high-performance web AI runtime that enables developers to run machine learning models directly in the browser. By leveraging WebAssembly and hardware acceleration like WebGPU and WebNN, it allows for low-latency, private, and serverless AI inference using .tflite models.

LiteRT.js is a high-performance web AI runtime that enables developers to run machine learning models directly in the browser. By leveraging WebAssembly and hardware acceleration like WebGPU and WebNN, it allows for low-latency, private, and serverless AI inference using .tflite models.

• 01Native hardware acceleration via XNNPACK (CPU), WebGPU (GPU), and WebNN (NPU)
• 02Seamless deployment of existing .tflite models in web applications
• 03Tailored quantization support via AI Edge Quantizer for optimized performance and model size
• 04Unified cross-platform runtime shared with LiteRT for Android, iOS, and desktop
• 05Integrated PyTorch conversion support through LiteRT Torch