Riddhi Raj Ghosh

3 Models Walk Into an NPU: FastSAM, YOLOv8n & NanoDet Pushing the Axon

In our previous YOLO blog post, we walked through the entire journey of getting YOLOv8 and YOLO11 object detection running on the Vicharak Axon; from ONNX export, to post-processing node removal, to RKNN conversion, to finally running inference on the NPU. If you haven't read that one yet,

Running YOLOv8 & YOLO11 Object Detection on the Vicharak Axon: A Complete Guide

If you've ever tried running a state-of-the-art object detection model on an edge device, you know the feeling. You start with excitement, "This will be amazing!", then hit a wall of incompatible frameworks, cryptic errors, and models that just won't cooperate with your hardware.