This is the containerized path. If you’d rather install
geniex directly on the host without Docker, see CLI Install → Linux ARM64 (Native).Prerequisites
- Linux ARM64 host with Docker installed — if you don’t have Docker yet, follow Docker’s Ubuntu install guide.
- Dragonwing IoT chipset — see Supported platforms.
Install host dependencies
The container reaches the NPU through the host’s Qualcomm driver libraries, mounted in via-v /usr/lib:/opt/qcom-lib:ro. Install them on the host before docker run — follow CLI Install → Install host dependencies.
Pull the image
The image is on Docker Hub (public, no login):bash
If
docker pull returns permission denied ... /var/run/docker.sock, see Troubleshooting → Linux for the docker group fix.Baseline ARMv8.0 boards — some NPU-less Dragonwing IoT SoCs cannot run the default ARMv8.2 image; append
-cpu to the tag for those: docker.io/qualcomm/geniex:latest-cpu. That image is CPU-only and needs neither --privileged nor the /usr/lib mount below.Run interactively
Drop into an interactive shell inside the container:bash
Verify
Then run a test command from the container shell:bash
The
--privileged flag is required for NPU access.CLI
For the full CLI Docker install guide, see CLI Install — Linux ARM64 (Docker).Python
For the full Python install guide on native Linux ARM64, see Python Install — Linux ARM64. The Python SDK can be installed inside the Docker container or directly on the Linux ARM64 host. See the Linux ARM64 tab for native install instructions.Was this page helpful?