All news

Google open-sourced ML Drift under Apache 2.0, a cross-platform GPU compute engine for on-device inference over OpenGL ES, OpenCL, Metal and WebGPU.

A user found Samsung TVs run an INT8 TensorFlow Lite model on 960x540 screenshots every few seconds to detect what game is being played.

DWI speeds up on-device LLM decoding by picking the width of a nested model per step.