Faster Dynamically Quantized Inference with XNNPack — The TensorFlow Blog
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…