April 09, 2024 — Posted by Alan Kelly, Software EngineerWe are excited to announce that XNNPack’s Fully Connected and Convolution 2D operators now support dynamic range quantization. XNNPack is TensorFlow Lite’s CPU backend and CPUs deliver the widest reach for ML inference and remain the default target for TensorFlow Lite. Consequently, improving CPU inference performance is a top priority. We quadrupled inferen…
February 06, 2024 — Posted by Dustin Zelle – Software Engineer, Research and Arno Eigenwillig – Software Engineer, CoreML
November 29, 2023 — Posted by Marat Dukhan and Frank Barchard, Software Engineers