Frequently Asked Questions
Administrators of on-premises (on-prem) deployments of Deepgram products sometimes encounter the following issues.
Problems installing the NVIDIA drivers
Sometimes loaded kernel modules can interfere with the installation of the NVIDIA drivers. To correct this issue, try unloading
sudo rmmod nouveau
Failed to find any CUDA devices
Ensure that NVIDIA drivers are installed:
If not, install them before proceeding.
docker run --runtime=nvidia --rm nvidia/cuda:9.0-base nvidia-smi
If not, install it before proceeding.
If you have made changes to NVIDIA drivers, restart Docker:
sudo systemctl restart docker
Deepgram will not start
Running Deepgram on premises requires a valid license. If you think you have an expired license or invalid license ID, contact Support for help.
How can I use Deepgram on-prem offline?
If you have been issued an on-prem license file for offline/air-gapped deployments, please contact your Deepgram Account Representative for additional documentation about maintaining your license.