MLX CUDA backend passes all tests, enabling NVIDIA GPU support

Developer teased upcoming release of Dflash with continuous batch inference for draft models

Open-source project DFlash launched, implementing speculative decoding for Apple Silicon using MLX framework

Release of Apple's MLX framework for efficient on-device machine learning on Apple Silicon

Apple's MLX framework was highlighted at the AI Engineer Summit for enabling local grounded reasoning for satellite, security, and robotics AI.