VMware vSphere

Virtual GPU Software R580 for VMware vSphere Release Notes

Release information for all users of NVIDIA virtual GPU software and hardware on VMware vSphere.

These Release Notes summarize current status, information on validated platforms, and known issues with NVIDIA vGPU software and associated hardware on VMware vSphere.

1.1. NVIDIA vGPU Software Driver Versions

Each release in this release family of NVIDIA vGPU software includes a specific version of the NVIDIA Virtual GPU Manager, NVIDIA Windows driver, and NVIDIA Linux driver.

For details of which VMware vSphere releases are supported, see Hypervisor Software Releases.

1.2. Compatibility Requirements for the NVIDIA vGPU Manager and Guest VM Driver

The releases of the NVIDIA vGPU Manager and guest VM drivers that you install must be compatible. If you install an incompatible guest VM driver release for the release of the vGPU Manager that you are using, the NVIDIA vGPU fails to load.

See VM running an incompatible NVIDIA vGPU guest driver fails to initialize vGPU when booted.

Compatible NVIDIA vGPU Manager and Guest VM Driver Releases

The following combinations of NVIDIA vGPU Manager and guest VM driver releases are compatible with each other.

• NVIDIA vGPU Manager with guest VM drivers from the same release
• NVIDIA vGPU Manager from a later major release branch with guest VM drivers from the previous branch
• NVIDIA vGPU Manager from a later long-term support branch with guest VM drivers from the previous long-term support branch

The following table lists the specific software releases that are compatible with the components in the NVIDIA vGPU software 19 major release branch.

Incompatible NVIDIA vGPU Manager and Guest VM Driver Releases

The following combinations of NVIDIA vGPU Manager and guest VM driver releases are incompatible with each other.

• NVIDIA vGPU Manager from a later major release branch with guest VM drivers from a production branch two or more major releases before the release of the vGPU Manager
• NVIDIA vGPU Manager from an earlier major release branch with guest VM drivers from a later branch

The following table lists the specific software releases that are incompatible with the components in the NVIDIA vGPU software 19 major release branch.

1.3. Updates in Release 19.0

New Features in Release 19.0

• Support for Multi-Instance GPU (MIG)-backed vGPUs for graphics on GPUs that support MIG
• New B-series vGPU profiles with 3 GB of frame buffer on supported GPUs based on the NVIDIA Ada Lovelace and NVIDIA Blackwell GPU architectures
• Miscellaneous bug fixes

Newly Supported Hardware and Software in Release 19.0

• Newly supported graphics cards:
  • NVIDIA RTX PRO 6000 Blackwell Server Edition

Features Deprecated in Release 19.0

NVIDIA vGPU software 19 is the last release branch to support the following graphics cards:

• Tesla M10
• Tesla V100 SXM2
• Tesla V100 SXM2 32GB
• Tesla V100 PCIe
• Tesla V100 PCIe 32GB
• Tesla V100S PCIe 32GB
• Tesla V100 FHHL
• Quadro RTX 6000
• Quadro RTX 6000 passive
• Quadro RTX 8000
• Quadro RTX 8000 passive

Disabling strict round robin policy is deprecated and NVIDIA vGPU software 19 is the last release branch to support it. Support for this feature is planned to be removed in the next major release of NVIDIA vGPU software.

This release family of NVIDIA vGPU software provides support for several NVIDIA GPUs on validated server hardware platforms, VMware vSphere hypervisor software versions, and guest operating systems. It also supports the version of NVIDIA CUDA Toolkit that is compatible with R580 drivers.

2.1. Supported NVIDIA GPUs and Validated Server Platforms

This release of NVIDIA vGPU software on VMware vSphere provides support for several NVIDIA GPUs running on validated server hardware platforms.

For a list of validated server platforms, refer to NVIDIA GRID Certified Servers.

The supported products for each type of NVIDIA vGPU software deployment depend on the GPU.

GPUs Based on the NVIDIA Blackwell Architecture

GPUs Based on the NVIDIA Ada Lovelace Architecture

GPUs Based on the NVIDIA Ampere Architecture

GPUs Based on the NVIDIA Turing Architecture

GPUs Based on the NVIDIA Volta Architecture

GPUs Based on the NVIDIA Maxwell Graphic Architecture

2.1.1. Support for a Mixture of Time-Sliced vGPU Types on the Same GPU

VMware vSphere Hypervisor (ESXi) support for a mixture of time-sliced vGPU types on the same GPU depends on the VMware vSphere Hypervisor (ESXi) release.

2.1.2. Switching the Mode of a GPU that Supports Multiple Display Modes

Some GPUs support display-off and display-enabled modes but must be used in NVIDIA vGPU software deployments in display-off mode.

The GPUs listed in the following table support multiple display modes. As shown in the table, some GPUs are supplied from the factory in display-off mode, but other GPUs are supplied in a display-enabled mode.

A GPU that is supplied from the factory in display-off mode, such as the NVIDIA A40 GPU, might be in a display-enabled mode if its mode has previously been changed.

To change the mode of a GPU that supports multiple display modes, use the displaymodeselector tool, which you can request from the NVIDIA Display Mode Selector Tool page on the NVIDIA Developer website.

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

Some GPUs require 64 GB or more of MMIO space. When a vGPU on a GPU that requires 64 GB or more of MMIO space is assigned to a VM with 32 GB or more of memory on ESXi , the VM’s MMIO space must be increased to the amount of MMIO space that the GPU requires.

For more information, refer to VMware Knowledge Base Article: VMware vSphere VMDirectPath I/O: Requirements for Platforms and Devices (2142307).

No extra configuration is needed.

The following table lists the GPUs that require 64 GB or more of MMIO space and the amount of MMIO space that each GPU requires.

2.1.4. Requirements for Using GPUs Requiring Large MMIO Space in Pass-Through Mode

• The following GPUs require 32 GB of MMIO space in pass-through mode:
  • Tesla V100 (all 16GB variants)
• The following GPUs require 64 GB of MMIO space in pass-through mode.
  • Quadro RTX 8000 passive
  • Quadro RTX 6000 passive
  • Tesla V100 (all 32GB variants)

  If a GPU that requires more than 32 GB of MMIO space is assigned to a VM, the VM's MMIO space must be increased as explained in VMware Knowledge Base Article: VMware vSphere VMDirectPath I/O: Requirements for Platforms and Devices (2142307).

• Pass through of GPUs with large BAR memory settings has some restrictions on VMware ESXi:
  • The guest OS must be a 64-bit OS.
  • 64-bit MMIO must be enabled for the VM.
  • If the total BAR1 memory exceeds 256 Mbytes, EFI boot must be enabled for the VM.
    Note:

    To determine the total BAR1 memory, run nvidia-smi -q on the host.

  • The guest OS must be able to be installed in EFI boot mode.

2.1.5. Requirements for Assigning Multiple GPUs in Pass-Through Mode to a Single VM

If you are assigning multiple GPUs in pass-through mode to a single VM, ensure that you allocate enough MMIO space to the VM for all the GPUs.

1. Calculate the amount of MMIO space that is required for all the GPUs that you want to assign in pass-through mode to the VM.
   1. On the hypervisor host, get the total BAR1 memory usage for each GPU.
      Copy

      Copied!

                  
      
                  
      nvidia-smi -q
      ==============NVSMI LOG==============
      
      Timestamp                                 : Mon Jun 16 18:36:45 2025
      Driver Version                            : 580.65.05 
      CUDA Version                              :  13.0
      
      Attached GPUs                             : 4
      GPU 00000000:01:00.0
      ...
         BAR1 Memory Usage Total : 128 GiB
      ...
              

      In this example, the total BAR1 memory usage for each GPU is 128 GiB.

   2. Multiply the total BAR1 memory usage for each GPU by the number of GPUs that you are assigning in pass-through mode to the VM. For example, if you are assigning four GPUs to a VM, the amount of MMIO space that is required for all the GPUs is 4⨯128 GiB, which equals 512 GiB.
2. Under the VM settings, choose VM Options > Advanced and set pciPassthru.use64bitMMIO="TRUE".
3. Allocate the required amount of MMIO space to the VM.
   Copy

   Copied!

               
   
               
   pciPassthru.64bitMMIOSizeGB = "mmio-space-in-gb"
           

   mmio-space-in-gb

   The required amount of MMIO space in GiB that you calculated previously. For example, if you are assigning four GPUs to a VM that each use a total of 128 GiB of BAR1 memory, the amount of MMIO space that is required for all the GPUs is 512 GiB.

   Copy

   Copied!

               
   
               
   pciPassthru.64bitMMIOSizeGB = "512"
           

2.1.6. Linux Only: Error Messages for Misconfigured GPUs Requiring Large MMIO Space

In a Linux VM, if the requirements for using C-Series vCS vGPUs or GPUs requiring large MMIO space in pass-through mode are not met, the following error messages are written to the VM's dmesg log during installation of the NVIDIA vGPU software graphics driver:

            

            
NVRM: BAR1 is 0M @ 0x0 (PCI:0000:02:02.0)
[  90.823015] NVRM: The system BIOS may have misconfigured your GPU.
[  90.823019] nvidia: probe of 0000:02:02.0 failed with error -1
[  90.823031] NVRM: The NVIDIA probe routine failed for 1 device(s).
        

2.2. Hypervisor Software Releases

Supported VMware vSphere Hypervisor (ESXi) Releases

This release is supported on the VMware vSphere Hypervisor (ESXi) releases listed in the table.

Supported Management Software and Virtual Desktop Software Releases

This release supports the management software and virtual desktop software releases listed in the table.

2.3. Guest OS Support

NVIDIA vGPU software supports several Windows releases and Linux distributions as a guest OS. The supported guest operating systems depend on the hypervisor software version.

2.3.1. Windows Guest OS Support

NVIDIA vGPU software supports only the 64-bit Windows releases listed as a guest OS on VMware vSphere. The releases of VMware vSphere for which a Windows release is supported depend on whether NVIDIA vGPU or pass-through GPU is used.

2.3.1.1. Windows Guest OS Support in Release 19.0

• Windows Server 2025
• Windows Server 2022
• Windows 11 24H2 and all Windows 11 releases supported by Microsoft up to and including this release
• Windows 10 2022 Update (22H2) and all Windows 10 releases supported by Microsoft up to and including this release
  Note:

  The hardware-accelerated GPU scheduling feature introduced in Windows 10 May 2020 Update (2004) is not supported on GPUs based on the Maxwell architecture and is supported only in pass-through mode on GPUs based on later architectures.

2.3.2. Linux Guest OS Support

NVIDIA vGPU software supports only the Linux distributions listed as a guest OS on VMware vSphere. The releases of VMware vSphere for which a Linux release is supported depend on whether NVIDIA vGPU or pass-through GPU is used.

2.3.2.1. Linux Guest OS Support in Release 19.0

• Deprecated: CentOS Linux 8 (2105)
• Debian 12
• Red Hat CoreOS 4.11
• Red Hat Enterprise Linux 9.6
• Red Hat Enterprise Linux 9.4
• Red Hat Enterprise Linux 8.10
• SUSE Linux Enterprise Server 15 SP2
• Ubuntu 24.04 LTS
• Ubuntu 22.04 LTS
• Ubuntu 20.04 LTS

2.4. NVIDIA CUDA Toolkit Version Support

The releases in this release family of NVIDIA vGPU software support NVIDIA CUDA Toolkit 13.0.

To build a CUDA application, the system must have the NVIDIA CUDA Toolkit and the libraries required for linking. For details of the components of NVIDIA CUDA Toolkit, refer to NVIDIA CUDA Toolkit 12.8 Release Notes.

To run a CUDA application, the system must have a CUDA-enabled GPU and an NVIDIA display driver that is compatible with the NVIDIA CUDA Toolkit release that was used to build the application. If the application relies on dynamic linking for libraries, the system must also have the correct version of these libraries.

For more information about NVIDIA CUDA Toolkit, refer to CUDA Toolkit Documentation 13.0.

2.5. vGPU Migration Support

vGPU Migration, which includes vMotion and suspend-resume, is supported on all supported GPUs, but only on a subset of supported VMware vSphere Hypervisor (ESXi) releases and guest operating systems.

Limitations with vGPU Migration Support

vGPU migration is disabled for a VM for which any of the following NVIDIA CUDA Toolkit features is enabled:

• Unified memory
• Debuggers
• Profilers

Supported Hypervisor Software Releases

All supported releases of VMware vSphere

Supported Guest OS Releases

Windows and Linux.

Known Issues with vGPU Migration Support

2.6. Fast Suspend-Resume Support

NVIDIA vGPU software supports VMware Fast Suspend-Resume with the NVIDIA Virtual GPU Manager. Fast Suspend-Resume enables changes to a VM, such as adding a network adapter, with minimal disruption to the VM. Fast Suspend-Resume is supported on all supported guest operating systems, but on only a subset of supported GPUs and VMware vSphere Hypervisor (ESXi) releases.

Supported GPUs

Fast Suspend-Resume is supported on all supported GPUs, except the Tesla M10 GPU.

Supported Hypervisor Software Releases

Since VMware vSphere 9.0

Supported Guest OS Releases

Windows and Linux.

Limitations with Fast Suspend-Resume Support

Unified memory is not supported. If unified memory is enabled for a vGPU, VMware vSphere Hypervisor (ESXi) operations that involve Fast Suspend-Resume fail, reporting a hot plug operation failure.

2.7. Multiple vGPU Support

To support applications and workloads that are compute or graphics intensive, multiple vGPUs can be added to a single VM. The assignment of more than one vGPU to a VM is supported only on a subset of vGPUs and hypervisor software releases.

2.7.1. vGPUs that Support Multiple vGPUs Assigned to a VM

The supported vGPUs depend on the architecture of the GPU on which the vGPUs reside:

• For GPUs based on the NVIDIA Volta architecture and later GPU architectures, all Q-series vGPUs are supported. On GPUs that support the Multi-Instance GPU (MIG) feature, both time-sliced and MIG-backed vGPUs are supported.
• For GPUs based on the NVIDIA NVIDIA Maxwell™ graphic architecture, only Q-series vGPUs that are allocated all of the physical GPU's frame buffer are supported.

You can assign multiple vGPUs with differing amounts of frame buffer to a single VM, provided the board type and the series of all the vGPUs is the same. For example, you can assign an A40-48Q vGPU and an A40-16Q vGPU to the same VM. However, you cannot assign an A30-8Q vGPU and an A16-8Q vGPU to the same VM.

Multiple vGPU Support on the NVIDIA Blackwell Architecture

Multiple vGPU Support on the NVIDIA Ada Lovelace Architecture

Multiple vGPU Support on the NVIDIA Ampere GPU Architecture

Multiple vGPU Support on the NVIDIA Turing GPU Architecture

Multiple vGPU Support on the NVIDIA Maxwell GPU Architecture

2.7.2. Maximum Number of vGPUs Supported per VM

For VMware vSphere, the maximum number of vGPUs per VM supported depends on the hypervisor release:

2.7.3. Hypervisor Releases that Support Multiple vGPUs Assigned to a VM

All hypervisor releases that support NVIDIA vGPU software are supported.

2.8. Peer-to-Peer CUDA Transfers over NVLink Support

Peer-to-peer CUDA transfers enable device memory between vGPUs on different GPUs that are assigned to the same VM to be accessed from within the CUDA kernels. NVLink is a high-bandwidth interconnect that enables fast communication between such vGPUs. Peer-to-Peer CUDA transfers over NVLink are supported only on a subset of vGPUs, VMware vSphere Hypervisor (ESXi) releases, and guest OS releases.

2.8.1. vGPUs that Support Peer-to-Peer CUDA Transfers

Only Q-series time-sliced vGPUs that are allocated all of the physical GPU's frame buffer on physical GPUs that support NVLink are supported.

Peer-to-Peer CUDA Transfer Support on the NVIDIA Ampere GPU Architecture

Peer-to-Peer CUDA Transfer Support on the NVIDIA Turing GPU Architecture

Peer-to-Peer CUDA Transfer Support on the NVIDIA Volta GPU Architecture

2.8.2. Hypervisor Releases that Support Peer-to-Peer CUDA Transfers

Peer-to-Peer CUDA transfers over NVLink are supported on all hypervisor releases that support the assignment of more than one vGPU to a VM. For details, see Multiple vGPU Support.

2.8.3. Guest OS Releases that Support Peer-to-Peer CUDA Transfers

Linux only. Peer-to-Peer CUDA transfers over NVLink are not supported on Windows.

2.8.4. Limitations on Support for Peer-to-Peer CUDA Transfers

• NVSwitch is not supported. Only direct connections are supported.
• Only time-sliced vGPUs are supported. MIG-backed vGPUs are not supported.
• PCIe is not supported.
• SLI is not supported.

2.9. Unified Memory Support

Unified memory is a single memory address space that is accessible from any CPU or GPU in a system. It creates a pool of managed memory that is shared between the CPU and GPU to provide a simple way to allocate and access data that can be used by code running on any CPU or GPU in the system. Unified memory is supported only on a subset of vGPUs and guest OS releases.

2.9.1. vGPUs that Support Unified Memory

On GPUs that support the MIG feature and on which this feature is enabled, only Q-series MIG-backed vGPUs that occupy an entire GPU instance are supported. All other MIG-backed vGPUs are not supported.

On single-instance GPUs, only Q-series vGPUs that are allocated all of the physical GPU's frame buffer on physical GPUs that support unified memory are supported.

Unified Memory Support on the NVIDIA Blackwell GPU Architecture

Unified Memory Support on the NVIDIA Ada Lovelace GPU Architecture

Unified Memory Support on the NVIDIA Ampere GPU Architecture

2.9.2. Guest OS Releases that Support Unified Memory

Linux only. Unified memory is not supported on Windows.

2.9.3. Limitations on Support for Unified Memory

• Only time-sliced Q-series and C-series vGPUs that are allocated all of the physical GPU's frame buffer on physical GPUs that support unified memory are supported. Fractional time-sliced vGPUs are not supported.
• When unified memory is enabled for a VM, vGPU migration is disabled for the VM.

2.10. NVIDIA GPU Operator Support

NVIDIA GPU Operator simplifies the deployment of NVIDIA vGPU software with software container platforms on immutable operating systems. An immutable operating system does not allow the installation of the NVIDIA vGPU software graphics driver directly on the operating system. NVIDIA GPU Operator is supported only on specific combinations of hypervisor software release, container platform, and guest OS release.

For more information, refer to Using NVIDIA vGPU in the NVIDIA GPU Operator documentation.

2.11. NVIDIA Deep Learning Super Sampling (DLSS) Support

NVIDIA vGPU software supports NVIDIA DLSS on NVIDIA RTX Virtual Workstation.

Supported DLSS versions: 2.0. Version 1.0 is not supported.

Supported GPUs:

• NVIDIA L40
• NVIDIA L40S
• NVIDIA L20
• NVIDIA L20 liquid cooled
• NVIDIA L4
• NVIDIA L2
• NVIDIA RTX 6000 Ada
• NVIDIA RTX 5880 Ada
• NVIDIA RTX 5000 Ada
• NVIDIA A40
• NVIDIA A16
• NVIDIA A2
• NVIDIA A10
• NVIDIA RTX A6000
• NVIDIA RTX A5500
• NVIDIA RTX A5000
• NVIDIA RTX PRO 6000 Blackwell Server Edition
• Tesla T4
• Quadro RTX 8000
• Quadro RTX 8000 passive
• Quadro RTX 6000
• Quadro RTX 6000 passive

Supported applications: only applications that use nvngx_dlss.dll version 2.0.18 or newer

2.12. vSphere Lifecycle Management (vLCM) Support

NVIDIA vGPU software supports updating the Virtual GPU Manager for VMware vSphere Hypervisor (ESXi) by using vLCM.

Supported VMware vSphere Hypervisor (ESXi) releases: All releases supported by NVIDIA vGPU software

Supported VMware vCenter Server releases: All releases supported by NVIDIA vGPU software

            

            
Host not compatible with the image. The bootbank partition on the host has a capacity of <size>, the image requires <size>. Remove unnecessary components from the image.
        

Known product limitations for this release of NVIDIA vGPU software are described in the following sections.

3.1. vGPUs of different sizes on the same GPU are not supported

VMware vSphere Hypervisor (ESXi) supports a mixture of time-sliced vGPUs with the same amount of frame buffer from different virtual GPU series on the same physical GPU. A-series, B-series, and Q-series vGPUs with the same amount of frame buffer, for example, A40-2B and A40-2Q, can reside on the same physical GPU simultaneously. However, vGPUs with different amounts of frame buffer are not supported on the same GPU.

VMware vSphere Hypervisor (ESXi) 8 Update 3 and, unless explicitly stated otherwise, later update releases supports a mixture of different types of time-sliced vGPUs on the same physical GPU. Any combination of A-series, B-series, and Q-series vGPUs with any amount of frame buffer can reside on the same physical GPU simultaneously. The total amount of frame buffer allocated to the vGPUs on a physical GPU must not exceed the amount of frame buffer that the physical GPU has.

3.2. NVENC does not support resolutions greater than 4096×4096

Description

The NVIDIA hardware-based H.264 video encoder (NVENC) does not support resolutions greater than 4096×4096. This restriction applies to all NVIDIA GPU architectures and is imposed by the GPU encoder hardware itself, not by NVIDIA vGPU software. The maximum supported resolution for each encoding scheme is listed in the documentation for NVIDIA Video Codec SDK. This limitation affects any remoting tool where H.264 encoding is used with a resolution greater than 4096×4096. Most supported remoting tools fall back to software encoding in such scenarios.

Workaround

If your GPU is based on a GPU architecture later than the NVIDIA Maxwell^® architecture, use H.265 encoding. H.265 is more efficient than H.264 encoding and has a maximum resolution of 8192×8192. On GPUs based on the NVIDIA Maxwell architecture, H.265 has the same maximum resolution as H.264, namely 4096×4096.

Because the client-side Workspace App on Windows is a 32-bit application, resolutions greater than 4096×4096 are not supported for Windows clients of Citrix Virtual Apps and Desktops. Therefore, if you are using a Windows client with Citrix Virtual Apps and Desktops, ensure that you are using H.264 hardware encoding with the default Use video codec for compression Citrix graphics policy setting, namely Actively Changing Regions. This policy setting encodes only actively changing regions of the screen (for example, a window in which a video is playing). Provided that the number of pixels along any edge of the actively changing region does not exceed 4096, H.264 encoding is offloaded to the NVENC hardware encoder.

3.3. vCS is not supported on VMware vSphere

NVIDIA Virtual Compute Server (vCS) is not supported on VMware vSphere. C-series vGPU types are not available.

Instead, vCS is supported with NVIDIA AI Enterprise. For more information, see NVIDIA AI Enterprise Documentation.

3.4. Nested Virtualization Is Not Supported by NVIDIA vGPU

In general, NVIDIA vGPU deployments do not support nested virtualization, that is, running a hypervisor in a guest VM. For example, enabling the Hyper-V role in a guest VM running the Windows Server OS is not supported because it entails enabling nested virtualization. Similarly, enabling Windows Hypervisor Platform is not supported because it requires the Hyper-V role to be enabled.

3.5. Issues occur when the channels allocated to a vGPU are exhausted

Description

Issues occur when the channels allocated to a vGPU are exhausted and the guest VM to which the vGPU is assigned fails to allocate a channel to the vGPU. A physical GPU has a fixed number of channels and the number of channels allocated to each vGPU is inversely proportional to the maximum number of vGPUs allowed on the physical GPU.

When the channels allocated to a vGPU are exhausted and the guest VM fails to allocate a channel, the following errors are reported on the hypervisor host or in an NVIDIA bug report:

            

            
Jun 26 08:01:25 srvxen06f vgpu-3[14276]: error: vmiop_log: (0x0): Guest attempted to allocate channel above its max channel limit 0xfb
Jun 26 08:01:25 srvxen06f vgpu-3[14276]: error: vmiop_log: (0x0): VGPU message 6 failed, result code: 0x1a
Jun 26 08:01:25 srvxen06f vgpu-3[14276]: error: vmiop_log: (0x0):         0xc1d004a1, 0xff0e0000, 0xff0400fb, 0xc36f,
Jun 26 08:01:25 srvxen06f vgpu-3[14276]: error: vmiop_log: (0x0):         0x1, 0xff1fe314, 0xff1fe038, 0x100b6f000, 0x1000,
Jun 26 08:01:25 srvxen06f vgpu-3[14276]: error: vmiop_log: (0x0):         0x80000000, 0xff0e0200, 0x0, 0x0, (Not logged),
Jun 26 08:01:25 srvxen06f vgpu-3[14276]: error: vmiop_log: (0x0):         0x1, 0x0
Jun 26 08:01:25 srvxen06f vgpu-3[14276]: error: vmiop_log: (0x0): , 0x0
        

Workaround

Use a vGPU type with more frame buffer, thereby reducing the maximum number of vGPUs allowed on the physical GPU. As a result, the number of channels allocated to each vGPU is increased.

3.6. Total frame buffer for vGPUs is less than the total frame buffer on the physical GPU

Some of the physical GPU's frame buffer is used by the hypervisor on behalf of the VM for allocations that the guest OS would otherwise have made in its own frame buffer. The frame buffer used by the hypervisor is not available for vGPUs on the physical GPU. In NVIDIA vGPU deployments, frame buffer for the guest OS is reserved in advance, whereas in bare-metal deployments, frame buffer for the guest OS is reserved on the basis of the runtime needs of applications.

If error-correcting code (ECC) memory is enabled on a physical GPU that does not have HBM2 memory, the amount of frame buffer that is usable by vGPUs is further reduced. All types of vGPU are affected, not just vGPUs that support ECC memory.

On all GPUs that support ECC memory and, therefore, dynamic page retirement, additional frame buffer is allocated for dynamic page retirement. The amount that is allocated is inversely proportional to the maximum number of vGPUs per physical GPU. All GPUs that support ECC memory are affected, even GPUs that have HBM2 memory or for which ECC memory is disabled.

The approximate amount of frame buffer that NVIDIA vGPU software reserves can be calculated from the following formula:

max-reserved-fb = vgpu-profile-size-in-mb÷16 + 16 + ecc-adjustments + page-retirement-allocation + compression-adjustment

max-reserved-fb

The maximum total amount of reserved frame buffer in Mbytes that is not available for vGPUs.

vgpu-profile-size-in-mb

The amount of frame buffer in Mbytes allocated to a single vGPU. This amount depends on the vGPU type. For example, for the T4-16Q vGPU type, vgpu-profile-size-in-mb is 16384.

ecc-adjustments

The amount of frame buffer in Mbytes that is not usable by vGPUs when ECC is enabled on a physical GPU that does not have HBM2 memory.

• If ECC is enabled on a physical GPU that does not have HBM2 memory ecc-adjustments is fb-without-ecc/16, which is equivalent to 64 Mbytes for every Gbyte of frame buffer assigned to the vGPU. fb-without-ecc is total amount of frame buffer with ECC disabled.
• If ECC is disabled or the GPU has HBM2 memory, ecc-adjustments is 0.

page-retirement-allocation

The amount of frame buffer in Mbytes that is reserved for dynamic page retirement.

• On GPUs based on the NVIDIA Maxwell GPU architecture, page-retirement-allocation = 4÷max-vgpus-per-gpu.
• On GPUs based on NVIDIA GPU architectures after the Maxwell architecture, page-retirement-allocation = 128÷max-vgpus-per-gpu

max-vgpus-per-gpu

The maximum number of vGPUs that can be created simultaneously on a physical GPU. This number varies according to the vGPU type. For example, for the T4-16Q vGPU type, max-vgpus-per-gpu is 1.

compression-adjustment

The amount of frame buffer in Mbytes that is reserved for the higher compression overhead in vGPU types with 12 Gbytes or more of frame buffer on GPUs based on the Turing architecture.

compression-adjustment depends on the vGPU type as shown in the following table.

vGPU Type	Compression Adjustment (MB)
T4-16Q T4-16C T4-16A	28
RTX6000-12Q RTX6000-12C RTX6000-12A	32
RTX6000-24Q RTX6000-24C RTX6000-24A	104
RTX6000P-12Q RTX6000P-12C RTX6000P-12A	32
RTX6000P-24Q RTX6000P-24C RTX6000P-24A	104
RTX8000-12Q RTX8000-12C RTX8000-12A	32
RTX8000-16Q RTX8000-16C RTX8000-16A	64
RTX8000-24Q RTX8000-24C RTX8000-24A	96
RTX8000-48Q RTX8000-48C RTX8000-48A	238
RTX8000P-12Q RTX8000P-12C RTX8000P-12A	32
RTX8000P-16Q RTX8000P-16C RTX8000P-16A	64
RTX8000P-24Q RTX8000P-24C RTX8000P-24A	96
RTX8000P-48Q RTX8000P-48C RTX8000P-48A	238

For all other vGPU types, compression-adjustment is 0.

3.7. Issues may occur with graphics-intensive OpenCL applications on vGPU types with limited frame buffer

Description

Issues may occur when graphics-intensive OpenCL applications are used with vGPU types that have limited frame buffer. These issues occur when the applications demand more frame buffer than is allocated to the vGPU.

For example, these issues may occur with the Adobe Photoshop and LuxMark OpenCL Benchmark applications:

• When the image resolution and size are changed in Adobe Photoshop, a program error may occur or Photoshop may display a message about a problem with the graphics hardware and a suggestion to disable OpenCL.
• When the LuxMark OpenCL Benchmark application is run, XID error 31 may occur.

Workaround

For graphics-intensive OpenCL applications, use a vGPU type with more frame buffer.

3.8. In pass through mode, all GPUs connected to each other through NVLink must be assigned to the same VM

Description

In pass through mode, all GPUs connected to each other through NVLink must be assigned to the same VM. If a subset of GPUs connected to each other through NVLink is passed through to a VM, unrecoverable error XID 74 occurs when the VM is booted. This error corrupts the NVLink state on the physical GPUs and, as a result, the NVLink bridge between the GPUs is unusable.

Workaround

Restore the NVLink state on the physical GPUs by resetting the GPUs or rebooting the hypervisor host.

3.9. vGPU profiles with 512 Mbytes or less of frame buffer support only 1 virtual display head on Windows 10

Description

To reduce the possibility of memory exhaustion, vGPU profiles with 512 Mbytes or less of frame buffer support only 1 virtual display head on a Windows 10 guest OS.

The following vGPU profiles have 512 Mbytes or less of frame buffer:

• Tesla M10-0B
• Tesla M10-0Q

Workaround

Use a profile that supports more than 1 virtual display head and has at least 1 Gbyte of frame buffer.

3.10. NVENC requires at least 1 Gbyte of frame buffer

Description

Using the frame buffer for the NVIDIA hardware-based H.264/HEVC video encoder (NVENC) may cause memory exhaustion with vGPU profiles that have 512 Mbytes or less of frame buffer. To reduce the possibility of memory exhaustion, NVENC is disabled on profiles that have 512 Mbytes or less of frame buffer. Application GPU acceleration remains fully supported and available for all profiles, including profiles with 512 MBytes or less of frame buffer. NVENC support from both Citrix and VMware is a recent feature and, if you are using an older version, you should experience no change in functionality.

The following vGPU profiles have 512 Mbytes or less of frame buffer:

• Tesla M10-0B
• Tesla M10-0Q

Workaround

If you require NVENC to be enabled, use a profile that has at least 1 Gbyte of frame buffer.

3.11. VM failures or crashes on servers with 1 TiB or more of system memory

Description

Support for vGPU is limited to servers with less than 1 TiB of system memory. On servers with 1 TiB or more of system memory, VM failures or crashes may occur. For example, when Citrix Virtual Apps and Desktops is used with a Windows 7 guest OS, a blue screen crash may occur. However, support for vDGA is not affected by this limitation.

Depending on the version of NVIDIA vGPU software that you are using, the log file on the VMware vSphere host might also report the following errors:

            

            
2016-10-27T04:36:21.128Z cpu74:70210)DMA: 1935: Unable to perform element mapping: DMA mapping could not be completed
2016-10-27T04:36:21.128Z cpu74:70210)Failed to DMA map address 0x118d296c000 (0x4000): Can't meet address mask of the device..
2016-10-27T04:36:21.128Z cpu74:70210)NVRM: VM: nv_alloc_contig_pages: failed to allocate memory
        

This limitation applies only to systems with supported GPUs based on the Maxwell architecture, namely, Tesla M10.

Resolution

Limit the amount of system memory on the server to 1 TiB minus 16 GiB.

1. Set memmapMaxRAMMB to 1032192, which is equal to 1048576 minus 16384.

   For detailed instructions, see Set Advanced Host Attributes in the VMware vSphere documentation.

2. Reboot the server.

If the problem persists, contact your server vendor for the recommended system memory configuration with NVIDIA GPUs.

3.12. VM running an incompatible NVIDIA vGPU guest driver fails to initialize vGPU when booted

Description

A VM running a version of the NVIDIA guest VM driver that is incompatible with the current release of Virtual GPU Manager will fail to initialize vGPU when booted on a VMware vSphere platform running that release of Virtual GPU Manager.

A guest VM driver is incompatible with the current release of Virtual GPU Manager in either of the following situations:

• The guest driver is from a release in a branch two or more major releases before the current release, for example release 9.4.

  In this situation, the VMware vSphere VM’s log file reports the following error:

  Copy

  Copied!

              
  
              
  vmiop_log: (0x0): Incompatible Guest/Host drivers: Guest VGX version is older than the minimum version supported by the Host. Disabling vGPU.
          

• The guest driver is from a later release than the Virtual GPU Manager.

  In this situation, the VMware vSphere VM’s log file reports the following error:

  Copy

  Copied!

              
  
              
  vmiop_log: (0x0): Incompatible Guest/Host drivers: Guest VGX version is newer than the maximum version supported by the Host. Disabling vGPU.
          

In either situation, the VM boots in standard VGA mode with reduced resolution and color depth. The NVIDIA virtual GPU is present in Windows Device Manager but displays a warning sign, and the following device status:

            

            
Windows has stopped this device because it has reported problems. (Code 43)
        

Resolution

Install a release of the NVIDIA guest VM driver that is compatible with current release of Virtual GPU Manager.

3.13. Single vGPU benchmark scores are lower than pass-through GPU

Description

A single vGPU configured on a physical GPU produces lower benchmark scores than the physical GPU run in pass-through mode.

Aside from performance differences that may be attributed to a vGPU’s smaller frame buffer size, vGPU incorporates a performance balancing feature known as Frame Rate Limiter (FRL). On vGPUs that use the best-effort scheduler, FRL is enabled. On vGPUs that use the fixed share or equal share scheduler, FRL is disabled.

FRL is used to ensure balanced performance across multiple vGPUs that are resident on the same physical GPU. The FRL setting is designed to give good interactive remote graphics experience but may reduce scores in benchmarks that depend on measuring frame rendering rates, as compared to the same benchmarks running on a pass-through GPU.

Resolution

FRL is controlled by an internal vGPU setting. On vGPUs that use the best-effort scheduler, NVIDIA does not validate vGPU with FRL disabled, but for validation of benchmark performance, FRL can be temporarily disabled by adding the configuration parameter pciPassthru0.cfg.frame_rate_limiter in the VM’s advanced configuration options.

1. Select Edit Settings.
2. In Edit Settings window, select the VM Options tab.
3. From the Advanced drop-down list, select Edit Configuration.
4. In the Configuration Parameters dialog box, click Add Row.
5. In the Name field, type the parameter name pciPassthru0.cfg.frame_rate_limiter, in the Value field type 0, and click OK.

   

With this setting in place, the VM’s vGPU will run without any frame rate limit. The FRL can be reverted back to its default setting by setting pciPassthru0.cfg.frame_rate_limiter to 1 or by removing the parameter from the advanced settings.

3.14. VMs configured with large memory fail to initialize vGPU when booted

Description

When starting multiple VMs configured with large amounts of RAM (typically more than 32GB per VM), a VM may fail to initialize vGPU. In this scenario, the VM boots in VMware SVGA mode and doesn’t load the NVIDIA driver. The NVIDIA vGPU software GPU is present in Windows Device Manager but displays a warning sign, and the following device status:

            

            
Windows has stopped this device because it has reported problems. (Code 43)
        

When this error occurs, VGPU message failed messages and XID error messages are written to the VMware vSphere VM’s log file.

Resolution

vGPU reserves a portion of the VM’s framebuffer for use in GPU mapping of VM system memory. The reservation is sufficient to support up to 32GB of system memory, and may be increased to accommodate up to 64GB by adding the configuration parameter pciPassthru0.cfg.enable_large_sys_mem in the VM’s advanced configuration options

1. Select Edit Settings.
2. In Edit Settings window, select the VM Options tab.
3. From the Advanced drop-down list, select Edit Configuration.
4. In the Configuration Parameters dialog box, click Add Row.
5. In the Name field, type the parameter name pciPassthru0.cfg.enable_large_sys_mem, in the Value field type 1, and click OK.

With this setting in place, less GPU framebuffer is available to applications running in the VM. To accommodate system memory larger than 64GB, the reservation can be further increased by adding pciPassthru0.cfg.extra_fb_reservation in the VM’s advanced configuration options, and setting its value to the desired reservation size in megabytes. The default value of 64M is sufficient to support 64 GB of RAM. We recommend adding 2 M of reservation for each additional 1 GB of system memory. For example, to support 96 GB of RAM, set pciPassthru0.cfg.extra_fb_reservation to 128.

The reservation can be reverted back to its default setting by setting pciPassthru0.cfg.enable_large_sys_mem to 0, or by removing the parameter from the advanced settings.

Only resolved issues that have been previously noted as known issues or had a noticeable user impact are listed. The summary and description for each resolved issue indicate the effect of the issue on NVIDIA vGPU software before the issue was resolved.

4.1. Issues Resolved in Release 19.0

No resolved issues are reported in this release for VMware vSphere.

1. Linux graphics driver installation from a .run file fails
2. GPU device is unavailable on Windows 11 VMs with more than 1 TB of memory
3. Default client configuration token folder missing on Windows client VMs
4. Omnissa IDD, not the NVIDIA vGPU software graphics driver is driving the display in Windows 11 24H2 VMs
5. vGPU VM fails to boot with error vmiop-display unable to reserve vgpu
6. NVIDIA Control Panel is not available in multiuser environments
7. NVIDIA Control Panel crashes if a user session is disconnected and reconnected
8. VM assigned multiple fractional vGPUs from the same GPU hangs
9. CUDA profilers cannot gather hardware metrics on NVIDIA vGPU
10. NVIDIA vGPU software graphics driver for Windows sends a remote call to ngx.download.nvidia.com
11. Multiple RDP session reconnections on Windows Server 2022 can consume all frame buffer
12. VM with multiple legacy fractional vGPUs on the same GPU fails to boot
13. NLS client fails to acquire a license with the error The allowed time to process response has expired
14. With multiple active sessions, NVIDIA Control Panel incorrectly shows that the system is unlicensed
15. VP9 and AV1 decoding with web browsers are not supported on Microsoft Windows Server 2019
16. nvidia-smi ignores the second NVIDIA vGPU device added to a Microsoft Windows Server 2016 VM
17. After an upgrade of the Linux graphics driver from an RPM package in a licensed VM, licensing fails
18. After an upgrade of the Linux graphics driver from a Debian package, the driver is not loaded into the VM
19. Desktop session freezes when a VM is migrated to or from a host running an NVIDIA vGPU software 14 release
20. Application or vGPU VM crashes when multiple application instances are launched
21. The reported NVENC frame rate is double the actual frame rate
22. VM fails after a second vGPU is assigned to it
23. NVENC does not work with Teradici Cloud Access Software on Windows
24. When a licensed client deployed by using VMware instant clone technology is destroyed, it does not return the license
25. A licensed client might fail to acquire a license if a proxy is set
26. Session connection fails with four 4K displays and NVENC enabled on a 2Q, 3Q, or 4Q vGPU
27. Disconnected sessions cannot be reconnected or might be reconnected very slowly with NVWMI installed
28. Windows VM crashes during Custom (Advanced) driver upgrade
29. VMs with vGPUs on GPUs based on the NVIDIA Ampere architecture fail to power on
30. Linux VM hangs after vGPU migration to a host running a newer vGPU manager version
31. Idle Teradici Cloud Access Software session disconnects from Linux VM
32. GPU Operator doesn't support vGPU on GPUs based on architectures before NVIDIA Turing
33. Idle NVIDIA A100, NVIDIA A40, and NVIDIA A10 GPUs show 100% GPU utilization
34. Driver upgrade in a Linux guest VM with multiple vGPUs might fail
35. NVIDIA Control Panel fails to start if launched too soon from a VM without licensing information
36. Citrix Virtual Apps and Desktops session corruption occurs in the form of residual window borders
37. Omnissa Horizon clients cannot connect to a Windows 10 2004 VM with multiple displays
38. Suspend and resume between hosts running different versions of the vGPU manager fails
39. On Linux, a VMware Horizon 7.12 session freezes after a switch to full screen
40. On Linux, a VMware Horizon 7.12 session with two 4K displays freezes
41. On Linux, the frame rate might drop to 1 after several minutes
42. Frame buffer consumption grows with Omnissa Horizon over Blast Extreme
43. DWM crashes randomly occur in Windows VMs
44. Remote desktop session freezes with assertion failure and XID error 43 after migration
45. Citrix Virtual Apps and Desktops session freezes when the desktop is unlocked
46. NVIDIA vGPU software graphics driver fails after Linux kernel upgrade with DKMS enabled
47. Red Hat Enterprise Linux and CentOS 6 VMs hang during driver installation
48. Tesla T4 is enumerated as 32 separate GPUs by VMware vSphere ESXi
49. Users' sessions may freeze during vMotion migration of VMs configured with vGPU
50. Migration of VMs configured with vGPU stops before the migration is complete
51. ECC memory settings for a vGPU cannot be changed by using NVIDIA X Server Settings
52. Changes to ECC memory settings for a Linux vGPU VM by nvidia-smi might be ignored
53. Host core CPU utilization is higher than expected for moderate workloads
54. H.264 encoder falls back to software encoding on 1Q vGPUs with a 4K display
55. H.264 encoder falls back to software encoding on 2Q vGPUs with 3 or more 4K displays
56. Frame capture while the interactive logon message is displayed returns blank screen
57. RDS sessions do not use the GPU with Microsoft Windows Server as guest OS
58. VMware vMotion fails gracefully under heavy load
59. View session freezes intermittently after a Linux VM acquires a license
60. When the scheduling policy is fixed share, GPU utilization is reported as higher than expected
61. nvidia-smi reports that vGPU migration is supported on all hypervisors
62. GPU resources not available error during VMware instant clone provisioning
63. Module load failed during VIB downgrade from R390 to R384
64. On Linux, 3D applications run slowly when windows are dragged
65. A segmentation fault in DBus code causes nvidia-gridd to exit on Red Hat Enterprise Linux and CentOS
66. No Manage License option available in NVIDIA X Server Settings by default
67. Licenses remain checked out when VMs are forcibly powered off
68. Memory exhaustion can occur with vGPU profiles that have 512 Mbytes or less of frame buffer
69. vGPU VM fails to boot in ESXi if the graphics type is Shared
70. GNOME Display Manager (GDM) fails to start on Red Hat Enterprise Linux 7.2 and CentOS 7.0
71. NVIDIA Control Panel fails to start and reports that “you are not currently using a display that is attached to an Nvidia GPU”
72. VM configured with more than one vGPU fails to initialize vGPU when booted
73. A VM configured with both a vGPU and a passthrough GPU fails to start the passthrough GPU
74. vGPU allocation policy fails when multiple VMs are started simultaneously
75. Before Horizon agent is installed inside a VM, the Start menu’s sleep option is available
76. vGPU-enabled VMs fail to start, nvidia-smi fails when VMs are configured with too high a proportion of the server’s memory.
77. On reset or restart VMs fail to start with the error VMIOP: no graphics device is available for vGPU…
78. nvidia-smi shows high GPU utilization for vGPU VMs with active Horizon sessions

Notice

This document is provided for information purposes only and shall not be regarded as a warranty of a certain functionality, condition, or quality of a product. NVIDIA Corporation (“NVIDIA”) makes no representations or warranties, expressed or implied, as to the accuracy or completeness of the information contained in this document and assumes no responsibility for any errors contained herein. NVIDIA shall have no liability for the consequences or use of such information or for any infringement of patents or other rights of third parties that may result from its use. This document is not a commitment to develop, release, or deliver any Material (defined below), code, or functionality.

NVIDIA reserves the right to make corrections, modifications, enhancements, improvements, and any other changes to this document, at any time without notice.

Customer should obtain the latest relevant information before placing orders and should verify that such information is current and complete.

NVIDIA products are sold subject to the NVIDIA standard terms and conditions of sale supplied at the time of order acknowledgement, unless otherwise agreed in an individual sales agreement signed by authorized representatives of NVIDIA and customer (“Terms of Sale”). NVIDIA hereby expressly objects to applying any customer general terms and conditions with regards to the purchase of the NVIDIA product referenced in this document. No contractual obligations are formed either directly or indirectly by this document.

NVIDIA products are not designed, authorized, or warranted to be suitable for use in medical, military, aircraft, space, or life support equipment, nor in applications where failure or malfunction of the NVIDIA product can reasonably be expected to result in personal injury, death, or property or environmental damage. NVIDIA accepts no liability for inclusion and/or use of NVIDIA products in such equipment or applications and therefore such inclusion and/or use is at customer’s own risk.

NVIDIA makes no representation or warranty that products based on this document will be suitable for any specified use. Testing of all parameters of each product is not necessarily performed by NVIDIA. It is customer’s sole responsibility to evaluate and determine the applicability of any information contained in this document, ensure the product is suitable and fit for the application planned by customer, and perform the necessary testing for the application in order to avoid a default of the application or the product. Weaknesses in customer’s product designs may affect the quality and reliability of the NVIDIA product and may result in additional or different conditions and/or requirements beyond those contained in this document. NVIDIA accepts no liability related to any default, damage, costs, or problem which may be based on or attributable to: (i) the use of the NVIDIA product in any manner that is contrary to this document or (ii) customer product designs.

No license, either expressed or implied, is granted under any NVIDIA patent right, copyright, or other NVIDIA intellectual property right under this document. Information published by NVIDIA regarding third-party products or services does not constitute a license from NVIDIA to use such products or services or a warranty or endorsement thereof. Use of such information may require a license from a third party under the patents or other intellectual property rights of the third party, or a license from NVIDIA under the patents or other intellectual property rights of NVIDIA.

Reproduction of information in this document is permissible only if approved in advance by NVIDIA in writing, reproduced without alteration and in full compliance with all applicable export laws and regulations, and accompanied by all associated conditions, limitations, and notices.

THIS DOCUMENT AND ALL NVIDIA DESIGN SPECIFICATIONS, REFERENCE BOARDS, FILES, DRAWINGS, DIAGNOSTICS, LISTS, AND OTHER DOCUMENTS (TOGETHER AND SEPARATELY, “MATERIALS”) ARE BEING PROVIDED “AS IS.” NVIDIA MAKES NO WARRANTIES, EXPRESSED, IMPLIED, STATUTORY, OR OTHERWISE WITH RESPECT TO THE MATERIALS, AND EXPRESSLY DISCLAIMS ALL IMPLIED WARRANTIES OF NONINFRINGEMENT, MERCHANTABILITY, AND FITNESS FOR A PARTICULAR PURPOSE. TO THE EXTENT NOT PROHIBITED BY LAW, IN NO EVENT WILL NVIDIA BE LIABLE FOR ANY DAMAGES, INCLUDING WITHOUT LIMITATION ANY DIRECT, INDIRECT, SPECIAL, INCIDENTAL, PUNITIVE, OR CONSEQUENTIAL DAMAGES, HOWEVER CAUSED AND REGARDLESS OF THE THEORY OF LIABILITY, ARISING OUT OF ANY USE OF THIS DOCUMENT, EVEN IF NVIDIA HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGES. Notwithstanding any damages that customer might incur for any reason whatsoever, NVIDIA’s aggregate and cumulative liability towards customer for the products described herein shall be limited in accordance with the Terms of Sale for the product.

VESA DisplayPort

DisplayPort and DisplayPort Compliance Logo, DisplayPort Compliance Logo for Dual-mode Sources, and DisplayPort Compliance Logo for Active Cables are trademarks owned by the Video Electronics Standards Association in the United States and other countries.

HDMI

HDMI, the HDMI logo, and High-Definition Multimedia Interface are trademarks or registered trademarks of HDMI Licensing LLC.

OpenCL

OpenCL is a trademark of Apple Inc. used under license to the Khronos Group Inc.

Trademarks

NVIDIA, the NVIDIA logo, NVIDIA GRID, NVIDIA GRID vGPU, NVIDIA Maxwell, NVIDIA Pascal, NVIDIA Turing, NVIDIA Volta, GPUDirect, Quadro, and Tesla are trademarks or registered trademarks of NVIDIA Corporation in the U.S. and other countries. Other company and product names may be trademarks of the respective companies with which they are associated.