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
| Vendor | Models | Supported Modalities |
|---|---|---|
| NVIDIA Jetson | Jetson platforms with CUDA/TensorRT, Jetpack 6.x | Face, Iris, Palm |
| Ambarella CV Flow | CV28, CV25, CV22, CV2 | Face, Face Liveness |
| Rockchip RKNPU | RV1126 | Face, Face Liveness |
| Rockchip RKNPU2 | RK3566/RK3568, RK3576 | Face, Face Liveness, Iris, Palm, Palm Liveness |
| NXP | i.MX 8M Plus | Face, Face Liveness |
| Android GPUs/NPUs | Qualcomm, MediaTek, ARM Mali | Face, Face Liveness |
Available in
- SFE Toolkit — see Solvers & Platforms for the per-engine solver variants.
Related pages
- Identification (1:N) (performance & matching guidance)
- High Level Overview