New GPU engine in the on-device AI framework delivers comprehensive GPU and NPU support across Android, iOS, macOS, Windows, Linux, and web platforms.

InfoWorld is a source of news, analysis, and commentary on technology trends, IT strategies, and business innovation. With a focus on enterprise technology and digital transformation, InfoWorld offers insights and guidance for IT decision-makers, software developers, and technology professionals. From  articles on cloud computing and cybersecurity to product reviews and industry trends, InfoWorld helps readers navigate the complexities of modern IT environments and make informed decisions to drive business success.

InfoWorld

LiteRT, Google's on-device AI inference framework evolved from TensorFlow Lite, has introduced advanced hardware acceleration through its ML Drift GPU engine. The framework now delivers 1.4x faster GPU performance, provides unified GPU and NPU acceleration across Android, iOS, macOS, Windows, Linux, and web platforms, and supports OpenCL, OpenGL, Metal, and WebGPU. LiteRT offers improved cross-platform deployment for generative AI models and first-class PyTorch/JAX support through seamless model conversion, while abstracting away vendor-specific SDKs for simplified NPU deployment.

Google’s LiteRT adds advanced hardware acceleration