Embedded Files
Our IP inference accelerators boost AI performance, enabling faster, more efficient processing for tasks like object detection, NLP, and image recognition.
VisionNet
Configurable CNN accelerator for fast and efficient inference on VGG16, AlexNet, ResNet, EfficientNet-Lite, YOLOv6-Nano, and custom models with up to 8-bit precision.
GenCore
Configurable transformer accelerator for fast, efficient inference on LLaMA and custom models, supporting INT8, INT4, FP8, FP16, BF16
Page updated
Report abuse