Heterogeneous vGPU#
Heterogeneous vGPU allows a single physical GPU to host multiple vGPU profiles with different framebuffer sizes at the same time. Use it when VMs need different GPU memory footprints on one physical GPU so guests can take smaller profiles instead of all sharing one large profile.
When a GPU is configured for heterogeneous vGPU, its behavior during events like a host reboot, NVIDIA Virtual GPU Manager reload, or GPU reset varies by hypervisor.
Note
Heterogeneous vGPU configuration only supports the Best Effort and Equal Share schedulers.
Heterogeneous vGPU is supported on Turing and later GPUs. For additional information and operational instructions across different hypervisors, refer to the Heterogeneous vGPU documentation.
Platform Support for Heterogeneous vGPUs#
NVIDIA AI Enterprise Infra Releases:
NVIDIA AI Enterprise Infra 8.x
NVIDIA AI Enterprise Infra 7.x
Refer to Configuring a GPU for Heterogeneous vGPU on RHEL KVM.
NVIDIA AI Enterprise Infra Releases:
NVIDIA AI Enterprise Infra 8.x
NVIDIA AI Enterprise Infra 7.x
Refer to Configuring a GPU for Heterogeneous vGPU on Linux KVM.
NVIDIA AI Enterprise Infra Releases:
NVIDIA AI Enterprise Infra 8.x
NVIDIA AI Enterprise Infra 7.x
Refer to Configuring a GPU for Heterogeneous vGPU on VMware vSphere.