Limitations#

This page collects platform-specific product limitations and known issues for NVIDIA® vGPU™ for Compute. For an introduction to vGPU concepts and architecture, refer to Overview.

GPU Monitoring and Profiling on Hypervisor Hosts#

DCGM monitoring caveat for vGPU environments

NVIDIA Data Center GPU Manager (DCGM) is not supported in vGPU environments. This applies in two cases:

  • Hypervisor hosts: Not supported on hosts running the NVIDIA AI Enterprise vGPU Manager (host driver), including Linux KVM with SR-IOV passthrough and MIG-backed vGPU.

  • vGPU guest VMs: Not supported inside guests for MIG-backed or time-sliced vGPU.

Expect missing or zero metrics. Expect profiling errors and loss of visibility. Tools such as NVIDIA Nsight™ Compute may fail to read performance counters in these setups.

Hypervisor Limitations and Known Issues#

Refer to the Red Hat Enterprise Linux with KVM product limitations.

Refer to the Ubuntu KVM product limitations.

Refer to the VMware vSphere product limitations.

Large-Memory VMs (64 GB+ MMIO)

Some GPUs require 64 GB or more of MMIO space. A vGPU on such a GPU can be assigned to a VM with 32 GB or more of memory on ESXi. In that case, raise the VM’s MMIO space to the GPU’s requirement.

Details: Requirements for Using vGPU on GPUs Requiring 64 GB or More of MMIO Space with Large-Memory VMs.

MMIO space lookup - GPUs requiring 64 GB or more
Table 20 GPUs Requiring 64 GB or More of MMIO Space with Large-Memory VMs#

GPU

MMIO Space Required

NVIDIA B300 HGX™

768 GB

NVIDIA B200 HGX

768 GB

NVIDIA H200 (all variants)

512 GB

NVIDIA H100 (all variants)

256 GB

NVIDIA H800 (all variants)

256 GB

NVIDIA H20 141 GB

512 GB

NVIDIA H20 96 GB

256 GB

NVIDIA L40

128 GB

NVIDIA L20

128 GB

NVIDIA L4

64 GB

NVIDIA L2

64 GB

NVIDIA RTX™ 6000 Ada

128 GB

NVIDIA RTX 5000 Ada

64 GB

NVIDIA A40

128 GB

NVIDIA A30

64 GB

NVIDIA A10

64 GB

NVIDIA A100 80 GB (all variants)

256 GB

NVIDIA A100 40 GB (all variants)

128 GB

NVIDIA RTX A6000

128 GB

NVIDIA RTX A5500

64 GB

NVIDIA RTX A5000

64 GB

Microsoft Windows Server Limitations and Known Issues#

Refer to the Microsoft Windows Server product limitations.

Starting with NVIDIA AI Enterprise Infra 9.0, the Microsoft Compute Driver Model (MCDM) is supported for Windows guest drivers on NVIDIA Ampere, Ada Lovelace, Hopper™, and Blackwell GPUs, and the Tesla Compute Cluster (TCC) driver model is deprecated in favor of MCDM. MCDM applies to Windows guests only. Refer to MCDM (Microsoft Compute Driver Model).

Warning

MIG-backed vGPU VMs are not supported for Windows guests on NVIDIA A30, A100, A800, H100, H200, B200, and B300 GPUs. Only time-sliced vGPU is supported on those GPUs; assigning a MIG-backed profile to a Windows VM will fail at guest driver install. Windows guest VMs with MIG-backed vGPU are supported on NVIDIA RTX PRO 6000 Blackwell Server Edition and NVIDIA RTX PRO 4500 Blackwell Server Edition.

Windows guest VMs only support running native applications - no containers. NVIDIA AI Enterprise features that require containerization are not supported on Windows guest operating systems. Windows Subsystem for Linux 2 is covered separately in the next paragraph.

Windows Subsystem for Linux 2 (WSL 2). Starting with NVIDIA AI Enterprise Infra 9.0, WSL 2 is supported in Windows 11 guest VMs on Red Hat Enterprise Linux with KVM and on Ubuntu with KVM. For the guest OS versions, refer to the Support Matrix.

On generic Linux under KVM, guest OS support for Windows follows the hypervisor vendor’s matrix.

For the Non-containerized Applications on Hypervisors and Guest Operating Systems Supported with vGPU table, refer to the Support Matrix.