Skip to main content

NVIDIA vGPU Software 17

NVIDIA have released virtual GPU (vGPU) software 17. This is a production release and EOL Feb 2025.

Customers can now use vGPU with different amounts of frame buffer on same physical GPU.
Example if you have a NVIDIA A40 you can use 2Q, 4Q, 8Q profiles on the same physical GPU.

NOTE:
If you are customer using Microsoft Windows Server 2019 and have extended support from Microsoft and you can’t upgrade to Windows Server 2022, I advice you stay on NVIDIA 16.x release as this is supported until July 2026. After that you are forced to upgrade your operating system as NVIDIA will no longer support Windows Server 2019 with NVIDIA vGPU 16.x after July 2026. If you would like to use NVIDIA vGPU 17 with Windows Server 2019, this is not supported.

Driver versions with NVIDIA vGPU Software 17

vGPU SoftwareLinux vGPU ManagerWindows vGPU ManagerLinux DriverWindows DriverRelease Date
17.0550.54.10551.60550.54.14551.61February 2024

New Features in Release 17.0

  • Distribution of a release of the Virtual GPU Manager and the NVIDIA vGPU software graphics driver for Linux that is based on NVIDIA Linux open GPU kernel modules
  • Support for vGPUs with different amounts of frame buffer on the same physical GPU
  • Support in the NVML API and the nvidia-smi command for getting information about vGPUs with different amounts of frame buffer on the same physical GPU
  • An option to configure guest VMs or physical hosts to acquire NVIDIA vGPU software licenses when a user logs in instead of at boot time
  • Support for GPU-P on GPUs that are based on the NVIDIA Ada Lovelace GPU architecture on Microsoft Azure Stack HCI

What’s new in vGPU software 17

  • Newly supported graphics cards:
    • NVIDIA RTX 5880 Ada
  • Newly supported hypervisor software:
    • Red Hat Enterprise Linux with KVM 9.3
  • Newly supported guest OSes:
    • Microsoft Windows 11 23H2
    • Microsoft Windows Server 2022 on Ubuntu
    • Red Hat Enterprise Linux 9.0-9.2 on Microsoft Azure Stack HCI
    • Red Hat Enterprise Linux 9.3
    • Ubuntu 22.04 on Microsoft Azure Stack HCI
  • Newly supported remoting solutions:
    • VMware Horizon 2312 (8.12)

Feature Support Withdrawn in Release 17.0

  • Graphics cards no longer supported:
    • Tesla M6
    • Tesla M60
    • Tesla P4
    • Tesla P6
    • Tesla P40
    • Tesla P100 PCIe 12 GB
    • Tesla P100 PCIe 16 GB
    • Tesla P100 SXM2 16 GB
  • Hypervisor software no longer supported:
    • Red Hat Virtualization (RHV)
    • Windows Server 2019
  • Guest OSes no longer supported:
    • Windows Server 2019

Supported NVIDIA GPUs with NVIDIA vGPU Software 17

  • L2
  • L4
  • L20
  • L40
  • L40S
  • RTX 5000 Ada
  • RTX 5880 Ada
  • RTX 6000 Ada
  • A2
  • A10
  • A16
  • A40
  • M10
  • T4
  • V100
  • RTX A5000
  • RTX A5500
  • RTX A6000
  • RTX 6000, RTX 6000 passive, RTX 8000, RTX 8000 passive

API Support on NVIDIA vGPU 17 

NVIDIA vGPU includes support for the following APIs:

  • Open Computing Language (OpenCL™ software) 3.0
  • OpenGL® 4.6
  • Vulkan® 1.3
  • DirectX 11
  • DirectX 12 (Windows 10)
  • Direct2D
  • DirectX Video Acceleration (DXVA)
  • NVIDIA® CUDA® 12.3
  • NVIDIA vGPU software SDK (remote graphics acceleration)
  • NVIDIA RTX (on GPUs based on the NVIDIA Volta graphic architecture and later architectures)

Note: These APIs are backwards compatible. Older versions of the API are also supported.

NVIDIA CUDA Toolkit and OpenCL Support on NVIDIA vGPU Software

NVIDIA CUDA Toolkit and OpenCL are supported with NVIDIA vGPU only on a subset of vGPU types and supported GPUs.

For more information about NVIDIA CUDA Toolkit, see CUDA Toolkit 12.3 Documentation.

Note:

If you are using NVIDIA vGPU software with CUDA on Linux, avoid conflicting installation methods by installing CUDA from a distribution-independent runfile package. Do not install CUDA from a distribution-specific RPM or Deb package.

To ensure that the NVIDIA vGPU software graphics driver is not overwritten when CUDA is installed, deselect the CUDA driver when selecting the CUDA components to install.

For more information, see NVIDIA CUDA Installation Guide for Linux.

OpenCL and CUDA Application Support

OpenCL and CUDA applications are supported on the following NVIDIA vGPU types:

  • The 8Q vGPU type on the Tesla M10 GPU
  • All Q-series vGPU types on the following GPUs:
    • NVIDIA L2
    • NVIDIA L4
    • NVIDIA L20
    • NVIDIA L40
    • NVIDIA L40S
    • NVIDIA RTX 5000 Ada
    • NVIDIA RTX 6000 Ada
    • NVIDIA A2
    • NVIDIA A10
    • NVIDIA A16
    • NVIDIA A40
    • NVIDIA RTX A5000
    • NVIDIA RTX A5500
    • NVIDIA RTX A6000
    • Tesla V100 SXM2
    • Tesla V100 SXM2 32GB
    • Tesla V100 PCIe
    • Tesla V100 PCIe 32GB
    • Tesla V100S PCIe 32GB
    • Tesla V100 FHHL
    • Tesla T4
    • Quadro RTX 6000
    • Quadro RTX 6000 passive
    • Quadro RTX 8000
    • Quadro RTX 8000 passive

NVIDIA CUDA Toolkit Development Tool Support

NVIDIA vGPU supports the following NVIDIA CUDA Toolkit development tools on some GPUs:

  • Debuggers:
    • CUDA-GDB
    • Compute Sanitizer
  • Profilers:
    • The Activity, Callback, and Profiling APIs of the CUDA Profiling Tools Interface (CUPTI)Other CUPTI APIs, such as the Event and Metric APIs, are not supported.
    • NVIDIA Nsight™ Compute
    • NVIDIA Nsight Systems
    • NVIDIA Nsight plugin
    • NVIDIA Nsight Visual Studio plugin
    Other CUDA profilers, such as nvprof and NVIDIA Visual Profiler, are not supported.

These tools are supported only in Linux guest VMs.

NVIDIA CUDA Toolkit profilers are supported and can be enabled on a VM for which unified memory is enabled.

Note:By default, NVIDIA CUDA Toolkit development tools are disabled on NVIDIA vGPU. If used, you must enable NVIDIA CUDA Toolkit development tools individually for each VM that requires them by setting vGPU plugin parameters. For instructions, see Enabling NVIDIA CUDA Toolkit Development Tools for NVIDIA vGPU.

The following table lists the GPUs on which NVIDIA vGPU supports these debuggers and profilers.

GPUvGPU ModeDebuggersProfilers
NVIDIA L2Time-sliced
NVIDIA L4Time-sliced
NVIDIA L20Time-sliced
NVIDIA L40Time-sliced
NVIDIA L40STime-sliced
NVIDIA RTX 5000 AdaTime-sliced
NVIDIA RTX 6000 AdaTime-sliced
NVIDIA A2Time-sliced
NVIDIA A10Time-sliced
NVIDIA A16Time-sliced
NVIDIA A40Time-sliced
NVIDIA RTX A5000Time-sliced
NVIDIA RTX A5500Time-sliced
NVIDIA RTX A6000Time-sliced
Tesla T4Time-sliced
Quadro RTX 6000Time-sliced
Quadro RTX 6000 passiveTime-sliced
Quadro RTX 8000Time-sliced
Quadro RTX 8000 passiveTime-sliced
Tesla V100 SXM2Time-sliced
Tesla V100 SXM2 32GBTime-sliced
Tesla V100 PCIeTime-sliced
Tesla V100 PCIe 32GBTime-sliced
Tesla V100S PCIe 32GBTime-sliced
Tesla V100 FHHLTime-sliced

✓ Feature is supported

– Feature is not supported

Supported Hypervisors with NVIDIA vGPU 17

  • Citrix XenServer 8.0
  • Citrix Hypervisor 8.2  
  • VMware vSphere 7.0 U2 or newer, 8.0 or newer
  • Microsoft Azure Stack HCI 22H2
  • Microsoft Server 2022 with Hyper-V role
  • Red Hat Enterprise Linux with KVM 7.9, 8.6, 8.9, 9.0,9.2,9.3
  • Red Hat Virtualization (RHV) 4.2, 4.3, 4.4
  • Ubuntu 20.04 LTS, 22.04 LTS
  • Linux for KVM (H3C CAS, Huawei FusionSphere, Inspur InCloud Sphere, Nutanix AHV, Red Hat OpenStack Platform, Sangfor aDesk, SUSE Linux Enterprise Server)

Supported Cloud Services for vGPU 17

NVIDIA virtual GPU software is supported on several cloud services with bring your own license (BYOL) licensing and licensing provided by the cloud service. Read more here: 

  • Alibaba Cloud
  • Amazon Web Services Elastic Compute Cloud (AWS EC2)
  • Google Cloud Platform (GCP)
  • Microsoft Azure

Alibaba Cloud

NVIDIA vGPU and GPU pass through are supported on Alibaba Cloud.

NVIDIA vGPU Support
GPU Supported Alibaba Cloud ECS Instances Supported Guest Operating Systems NVIDIA Licensing
Tesla P4

ecs.vgn5i-m1.large

ecs.vgn5i-m2.xlarge

ecs.vgn5i-m4.2xlarge

ecs.vgn5i-m8.4xlarge

Microsoft Windows Server 2019

Microsoft Windows Server 2016 1607, 1709

Microsoft Windows Server 2012 R2

Microsoft Windows Server 2008 R2

CentOS 7.x (64-bit)

Red Hat Enterprise Linux 7.5 (64-bit)

SUSE Linux Enterprise Server 11 SP4/12 SP2 (64-bit)

Ubuntu 16.04 LTS (64-bit)

BYOL
Tesla T4

ecs.vgn6i-m4.xlarge

ecs.vgn6i-m8.2xlarge

GPU Pass Through Support
GPU Supported Alibaba Cloud ECS Instances Supported Guest Operating Systems NVIDIA Licensing
Tesla P4

ecs.gn5i-c2g1.large

ecs.gn5i-c4g1.xlarge

ecs.gn5i-c8g1.2xlarge

ecs.gn5i-c16g1.4xlarge

ecs.gn5i-c16g1.8xlarge

ecs.gn5i-c28g1.14xlarge

Windows Server 2019

Windows Server 2016 1607, 1709

Windows Server 2012 R2

Windows Server 2008 R2

CentOS 7.x (64-bit)

Red Hat Enterprise Linux 7.4/7.5 (64-bit)

SUSE Linux Enterprise Server 11 SP4/12 SP2 (64-bit)

Ubuntu 16.04 LTS (64-bit)

BYOL
Tesla P100

ecs.gn5-c4g1.xlarge

ecs.gn5-c8g1.2xlarge

ecs.gn5-c4g1.2xlarge

ecs.gn5-c8g1.4xlarge

ecs.gn5-c28g1.7xlarge

ecs.gn5-c8g1.8xlarge

ecs.gn5-c28g1.14xlarge

ecs.gn5-c8g1.14xlarge

Tesla T4

ecs.gn6i-c4g1.xlarge

ecs.gn6i-c8g1.2xlarge

ecs.gn6i-c16g1.4xlarge

ecs.gn6i-c24g1.6xlarge

ecs.gn6i-c24g1.12xlarge

ecs.gn6i-c24g1.24xlarge

ecs.gn6i-c32g1.8xlarge

ecs.gn6i-c48g1.12xlarge

ecs.gn6i-c72g1.18xlarge

Tesla V100

ecs.gn6v-c8g1.2xlarge

ecs.gn6v-c8g1.8xlarge

ecs.gn6v-c8g1.16xlarge

Related Alibaba Cloud Documentation

Create a compute optimized instance with GPU
vgn5i, light-weight compute optimized type family with GPU
Install the GPU driver
Install a GRID driver in a GPU-equipped ECS instance (Linux)

Amazon Web Services Elastic Compute Cloud (AWS EC2)

Only GPU pass through is supported on AWS EC2.

GPU Pass Through Support
GPU Supported AWS EC2 Instances Supported Guest Operating Systems NVIDIA Licensing
NVIDIA A10

g5.xlarge

g5.2xlarge

g5.4xlarge

g5.8xlarge

g5.16xlarge

g5.12xlarge

g5.24xlarge

g5.48xlarge

Windows Server 2022

Windows Server 2019

Windows Server 2016 1607, 1709

CentOS 8

Red Hat Enterprise Linux 7.9

Red Hat Enterprise Linux 8.2, 8.4, 8.5

SUSE Linux Enterprise Server 15 SP2

SUSE Linux Enterprise Server 12 SP3+

Ubuntu 20.04 LTS

Ubuntu 18.04 LTS

Ubuntu 16.04 LTS

Ubuntu 14.04 LTS

Provided by AWS
Tesla M60

g3.4xlarge

g3.8xlarge

g3.16xlarge

g3s.xlarge

Windows Server 2022

Windows Server 2019

Windows Server 2016 1607, 1709

CentOS 8

Red Hat Enterprise Linux 7.9

Red Hat Enterprise Linux 8.2, 8.4, 8.5

SUSE Linux Enterprise Server 15 SP2

SUSE Linux Enterprise Server 12 SP3+

Ubuntu 20.04 LTS

Ubuntu 18.04 LTS

Ubuntu 16.04 LTS

Ubuntu 14.04 LTS

Provided by AWS
Tesla T4

g4dn.xlarge

g4dn.2xlarge

g4dn.4xlarge

g4dn.8xlarge

g4dn.12xlarge

g4dn.16xlarge

Windows Server 2022

Windows Server 2019

Windows Server 2016 1607, 1709

CentOS 8

Red Hat Enterprise Linux 7.9

Red Hat Enterprise Linux 8.2, 8.4, 8.5

SUSE Linux Enterprise Server 15 SP2

SUSE Linux Enterprise Server 12 SP3+

Ubuntu 20.04 LTS

Ubuntu 18.04 LTS

Ubuntu 16.04 LTS

Ubuntu 14.04 LTS

Tesla M60

g3.4xlarge

g3.8xlarge

g3.16xlarge

g3s.xlarge

Windows Server 2022

Windows Server 2019

Microsoft Windows Server 2016 1607, 1709

CentOS 8

Red Hat Enterprise Linux 7.9

Red Hat Enterprise Linux 8.2, 8.4, 8.5

SUSE Linux Enterprise Server 15 SP2

SUSE Linux Enterprise Server 12 SP3+

Ubuntu 20.04 LTS

Ubuntu 18.04 LTS

Ubuntu 16.04 LTS

Ubuntu 14.04 LTS

BYOL
Tesla T4

g4dn.xlarge

g4dn.2xlarge

g4dn.4xlarge

g4dn.8xlarge

g4dn.12xlarge

g4dn.16xlarge

Windows Server 2022

Windows Server 2019

Microsoft Windows Server 2016 1607, 1709

CentOS 8

Red Hat Enterprise Linux 7.9

Red Hat Enterprise Linux 8.2, 8.4, 8.5

SUSE Linux Enterprise Server 15 SP2

SUSE Linux Enterprise Server 12 SP3+

Ubuntu 20.04 LTS

Ubuntu 18.04 LTS

Ubuntu 16.04 LTS

Ubuntu 14.04 LTS

Tesla V100

P3.2xlarge

P3.8xlarge

P3.16xlarge

Windows Server 2022

Windows Server 2019

Microsoft Windows Server 2016 1607, 1709

CentOS 8

Red Hat Enterprise Linux 7.9

Red Hat Enterprise Linux 8.2, 8.4, 8.5

SUSE Linux Enterprise Server 15 SP2

SUSE Linux Enterprise Server 12 SP3+

Ubuntu 20.04 LTS

Ubuntu 18.04 LTS

Ubuntu 16.04 LTS

Ubuntu 14.04 LTS

Related AWS EC2 Documentation

Linux Accelerated Computing Instances
Windows Accelerated Computing Instances
Amazon EC2 G5 Instances

Related NVIDIA Knowledge Base Articles

Known issue: NVIDIA vGPU software graphics driver installation fails on some Amazon Linux2 instances


Google Cloud Platform (GCP)

Only GPU pass through is supported on GCP.

GPU Pass Through Support
GPU Supported GCP Instances Supported Guest Operating Systems NVIDIA Licensing

Tesla P4

Any predefined machine type

Any custom machine type that can be created in a zone

Microsoft Windows Server 2019

Microsoft Windows Server 2016 1607, 1709

Microsoft Windows Server 2012 R2

Microsoft Windows Server 2008 R2

Red Hat Enterprise Linux 7.x (64-bit)

Ubuntu 16.04 LTS/18.04 LTS (64-bit)

Provided by GCP

Tesla P100

Tesla T4

Tesla P4

Any predefined machine type

Any custom machine type that can be created in a zone

Microsoft Windows Server 2019

Microsoft Windows Server 2016 1607, 1709

Microsoft Windows Server 2012 R2

Microsoft Windows Server 2008 R2

Red Hat Enterprise Linux 7.x (64-bit)

Ubuntu 16.04 LTS/18.04 LTS (64-bit)

BYOL

Tesla P100

Tesla T4

Tesla V100

Related GCP Documentation

NVIDIA and Google Cloud Platform
GPUs on Compute Engine


Microsoft Azure

GPU-P and GPU pass through are supported on Microsoft Azure.

GPU-P Support
GPU Supported Microsoft Azure VM Sizes Supported Guest Operating Systems NVIDIA Licensing
NVIDIA A10

Standard_NV6ads_A10_v5

Standard_NV12ads_A10_v5

Standard_NV18ads_A10_v5

Standard_NV36ads_A10_v5

Standard_NV36adms_A10_v5

Standard_NV72ads_A10_v5

Microsoft Windows Server 2022

Microsoft Windows Server 2019

Microsoft Windows Server 2016 1607, 1709

Microsoft Windows 11

Microsoft Windows 10

Red Hat Enterprise Linux 7.x (64-bit)

SUSE Linux Enterprise Server 15 SP2

SUSE Linux Enterprise Server 12 SP2

Ubuntu 20.04 LTS (64-bit)

Ubuntu 18.04 LTS (64-bit)

Ubuntu 16.04 LTS (64-bit)

Provided by Microsoft Azure
GPU Pass Through Support
GPU Supported Microsoft Azure VM Sizes Supported Guest Operating Systems NVIDIA Licensing
Tesla M60

NV6

NV12

NV24

NV12s_v3

NV24s_v3

NV48s_v3

Microsoft Windows Server 2022

Microsoft Windows Server 2019

Microsoft Windows Server 2016 1607, 1709

Microsoft Windows 11

Microsoft Windows 10

Red Hat Enterprise Linux 7.x (64-bit)

SUSE Linux Enterprise Server 15 SP2

SUSE Linux Enterprise Server 12 SP2

Ubuntu 20.04 LTS (64-bit)

Ubuntu 18.04 LTS (64-bit)

Ubuntu 16.04 LTS (64-bit)

Provided by Microsoft Azure
Tesla T4

NC4as_T4_v3

NC8as_T4_v3

NC16as_T4_v3

NC64as_T4_v3

Tesla M60

NV6

NV12

NV24

NV12s_v3

NV24s_v3

NV48s_v3

Microsoft Windows Server 2022

Microsoft Windows Server 2019

Microsoft Windows Server 2016 1607, 1709

Microsoft Windows 11

Microsoft Windows 10

Red Hat Enterprise Linux 7.x (64-bit)

SUSE Linux Enterprise Server 15 SP2

SUSE Linux Enterprise Server 12 SP2

Ubuntu 20.04 LTS (64-bit)

Ubuntu 18.04 LTS (64-bit)

Ubuntu 16.04 LTS (64-bit)

BYOL

Whats new in NVIDIA Virtual GPU Manager 550.54.01

Included in this release are available for following hypervisors.

  • NVIDIA Virtual GPU Manager versions 550.54.01 for Citrix XenServer 8.0
  • NVIDIA Virtual GPU Manager versions 550.54.01 for Citrix XenServer 8.2
  • NVIDIA Virtual GPU Manager version 550.54.01 for VMware vSphere 7.0 Hypervisor (ESXi)
  • NVIDIA Virtual GPU Manager version 550.54.01 for VMware vSphere 6.7 Hypervisor (ESXi)
  • NVIDIA Virtual GPU Manager version 550.54.01 for VMware vSphere 6.5 Hypervisor (ESXi)
  • NVIDIA Virtual GPU Manager version 550.54.01 for Red Hat Enterprise Linux with KVM 7.7, 7.8, 7.9, 8.1, 8.2, 8.3, 8.4
  • NVIDIA Virtual GPU Manager version 550.54.01 for Red Hat Virtualization RHV 4.2, 4.3, 4.4

Windows Guest OS support in NVIDIA vGPU 17.0 – 551.61

NVIDIA vGPU 551.61 supports following Windows release as a guest OS

  • Windows Server 2022
  • Windows 11 23H2 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

Linux Guest OS support in NVIDIA vGPU 17.0 – 550.54.14

NVIDIA vGPU 535.54.14 supports following Linux distributions as a guest OS

  • Red Hat CoreOS 4.11
  • Red Hat Enterprise Linux 9.0, 9.2, 9.3
  • Red Hat Enterprise Linux 8.6, 8.8, 8.9
  • Red Hat Enterprise Linux 7.9
  • Debian 10
  • Red Hat CoreOS 4.11
  • SUSE Linux Enterprise Server 15 SP2
  • SUSE Linux Enterprise Server 12 SP5
  • SUSE Linux Enterprise Server 12 SP3+
  • SUSE Linux Enterprise Server 12 SP2+
  • Ubuntu 22.04 LTS
  • Ubuntu 20.04 LTS
  • Ubuntu 20.04 LTSSUSE Linux Enterprise Server 15 SP2

Source

https://docs.nvidia.com/grid/17.0/whats-new-vgpu/index.html

Leave a Reply

Your email address will not be published. Required fields are marked *

Turn on pictures to see the captcha *