LiteRT
A unified on-device AI runtime introduced by Google that provides an inference execution engine for mobile and embedded devices across frameworks including PyTorch, JAX, and TensorFlow.
Core Facts
Timeline (last 90 days)
LiteRT-LM is Google's language model runtime built on LiteRT, responsible for model loading, KV cache management, sampling decoding and streaming output orchestration.
LiteRT is the unified on-device AI runtime Google launched in 2024, replacing components such as TensorFlow Lite and the TensorFlow Lite GPU Delegate, with the goal of providing mobile and embedded devices with a cross-framework (including PyTorch, JAX, TensorFlow) inference execution engine.
All Facts (3)
Google developed lightweight inference frameworks such as TensorFlow Lite and LiteRT for on-device AI inference on mobile devices.
65%UnverifiedLiteRT-LM is Google's language model runtime built on LiteRT, responsible for model loading, KV cache management, sampling decoding and streaming output orchestration.
50%UnverifiedLiteRT is the unified on-device AI runtime Google launched in 2024, replacing components such as TensorFlow Lite and the TensorFlow Lite GPU Delegate, with the goal of providing mobile and embedded devices with a cross-framework (including PyTorch, JAX, TensorFlow) inference execution engine.
50%