This paper proposes a lightweight fire detection algorithm, YOLO-LRP, for UAV firefighting scenarios. The algorithm is improved based on YOLOv10, where the MobileOne reparameterized backbone is adopted to reduce computational complexity. The OREPA module is integrated into the neck network to enhance training efficiency and feature fusion. The standard CBS module is replaced with GhostConv to further compress the model size, and the number of detection layers is streamlined to focus on small and medium fire targets. In addition, the SE channel attention mechanism is introduced to strengthen the extraction of key fire features under complex interference. Experimental results show that YOLO-LRP achieves 93.6% mAP50, only 2.26 M parameters, and 434.7 FPS in server-side tests. These improvements make the model more suitable for deployment on resource-constrained UAV platforms.