NVIDIA AI Enterprise 3.0 or later
NVIDIA AI Enterprise running on RHEL with KVM Virtualization has the following sets of prerequisites:
At least one NVIDIA data center GPU in a single NVIDIA AI Enterprise Compatible NVIDIA-Certified System.
Recommend A100 for training and A30 for inference.
NVIDIA AI Enterprise License
Red Hat Enterprise Linux 9 ISO
NVIDIA AI Enterprise Software:
NVIDIA AI Enterprise Driver
You may leverage the NVIDIA System Management interface (NV-SMI) management and monitoring tool for testing and benchmarking.
The following server configuration details are considered best practices:
Hyperthreading - Enabled
Power Setting or System Profile - High Performance
CPU Performance (if applicable) - Enterprise or High Throughput
Memory Mapped I/O above 4-GB - Enabled (if applicable)
SR-IOV enabled
IOMMU enabled
Secure Boot disabled
For instructions on enabling SR-IOV and IOMMU, please refer here.
Your system meets the following hardware requirements to work as a virtualization host:
The architecture of your host machine supports KVM virtualization.
The following minimum system resources are available:
6 GB free disk space for the host, plus another 6 GB for each intended VM.
2 GB of RAM for the host, plus another 2 GB for each intended VM.
Please refer to the latest NVIDIA vGPU release notes for supplemental information on deploying and managing RHEL with KVM on NVIDIA AI Enterprise.