Skip to main content

Hardware acceleration

Run biometric inference on neural-network accelerators (Ambarella CVFlow, Rockchip RKNPU, NVIDIA CUDA/TensorRT, NXP) for higher throughput and lower power on the edge.

Supported hardware accelerators — on-device SDKs

VendorModelsSupported Modalities
NVIDIA JetsonJetson platforms with CUDA/TensorRT, Jetpack 6.xFace, Iris, Palm
Ambarella CV FlowCV28, CV25, CV22, CV2Face, Face Liveness
Rockchip RKNPURV1126Face, Face Liveness
Rockchip RKNPU2RK3566/RK3568, RK3576Face, Face Liveness, Iris, Palm, Palm Liveness
NXPi.MX 8M PlusFace, Face Liveness
Android GPUs/NPUsQualcomm, MediaTek, ARM MaliFace, Face Liveness

Available in