Administrators of on-premise deployments of Deepgram products sometimes encounter the following issues.
Sometimes loaded kernel modules can interfere with the installation of the
NVIDIA drivers. To correct this issue, try unloading
# rmmod nouveau
Ensure that NVIDIA drivers are installed:
If not, install them before proceeding.
nvidia-docker is installed:
$ docker run --runtime=nvidia --rm nvidia/cuda:9.0-base nvidia-smi
If not, install it before proceeding.
If you are using Docker Swarm, ensure that the default Docker runtime
If you have made changes to NVIDIA drivers, restart Docker:
# systemctl restart docker