Is this page helpful?

Unified Virtual Memory (UVM)#

Unified Virtual Memory (UVM) gives the guest a single virtual address space visible to both CPU and GPU. Allocations in that space can be touched from host and device code without the application issuing an explicit copy for every transfer, which simplifies some CUDA programs.

For behavior and enablement steps, refer to the Unified Virtual Memory documentation.

Unified Virtual Memory (UVM)

UVM Known Issues and Limitations#

  • Unified Virtual Memory (UVM) is restricted to 1:1 time-sliced and MIG vGPU for Compute profiles that allocate the entire framebuffer of a compatible physical GPU or GPU Instance. Fractional time-sliced vGPUs do not support UVM.

  • UVM is only supported on Linux Guest OS distros. Windows Guest OS is not supported.

  • Enabling UVM disables vGPU migration for the VM, which may reduce operational flexibility in environments reliant on live migration.

  • UVM is disabled by default and must be explicitly enabled for each vGPU that requires it by setting a specific vGPU plugin parameter for the VM.

  • When deploying NVIDIA NIM, if UVM is enabled and an optimized engine is available, the model will run on the TensorRT-LLM (TRT-LLM) backend. Otherwise, it will typically run on the vLLM backend.

Hypervisor Platform Support for UVM#

Unified Virtual Memory (UVM) is disabled by default. If used, you must enable unified memory individually for each vGPU for Compute VM that requires it by setting a vGPU plugin parameter. How to enable UVM for a vGPU VM depends on the hypervisor that you are using.

Table 42 Hypervisor Platform Support for UVM#

Hypervisor Platform

Documentation

Red Hat Enterprise Linux with KVM

Enabling Unified Memory for NVIDIA vGPU for Compute VM on Red Hat Enterprise Linux KVM

Ubuntu with KVM

Enabling Unified Memory for NVIDIA vGPU for Compute VM on Ubuntu KVM

VMware vSphere

Enabling Unified Memory for NVIDIA vGPU for Compute VM on VMware vSphere

vGPU Support for UVM#

UVM is supported on 1:1 MIG-backed and time-sliced vGPUs. These vGPUs have the entire framebuffer of a MIG GPU Instance or physical GPU assigned to a single vGPU.

Table 43 vGPU Support for UVM on the NVIDIA Blackwell GPU Architecture#

Board

vGPU

NVIDIA HGX B300 SXM

  • B300X-279C

  • MIG-backed 1:1 vGPUs

NVIDIA HGX B200 SXM

  • B200X-7-180C

  • MIG-backed 1:1 vGPUs

NVIDIA RTX Pro 6000 Blackwell Server Edition

  • DC-4-96C

  • MIG-backed 1:1 vGPUs

NVIDIA RTX Pro 4500 Blackwell SE

  • DC-2-32C

  • MIG-backed 1:1 vGPUs
Table 44 vGPU Support for UVM on the NVIDIA Hopper GPU Architecture#

Board

vGPU

NVIDIA H800 PCIe 94 GB (H800 NVL)

  • H800L-94C

  • All MIG-backed vGPUs

NVIDIA H800 PCIe 80 GB

  • H800-80C

  • All MIG-backed vGPUs

NVIDIA H800 SXM5 80 GB

  • H800XM-80C

  • All MIG-backed vGPUs

NVIDIA H200 SXM5

  • H200X-141C

  • All MIG-backed vGPUs

NVIDIA H200 NVL

  • H200-141C

  • All MIG-backed vGPUs

NVIDIA H100 PCIe 94 GB (H100 NVL)

  • H100L-94C

  • All MIG-backed vGPUs

NVIDIA H100 SXM5 94 GB

  • H100XL-94C

  • All MIG-backed vGPUs

NVIDIA H100 PCIe 80 GB

  • H100-80C

  • All MIG-backed vGPUs

NVIDIA H100 SXM5 80 GB

  • H100XM-80C

  • All MIG-backed vGPUs

NVIDIA H100 SXM5 64 GB

  • H100XS-64C

  • All MIG-backed vGPUs

NVIDIA H20 SXM5 141 GB

  • H20X-141C

  • All MIG-backed vGPUs

NVIDIA H20 SXM5 96 GB

  • H20-96C

  • All MIG-backed vGPUs
Table 45 vGPU Support for UVM on the NVIDIA Ada Lovelace GPU Architecture#

Board

vGPU

NVIDIA L40

L40-48C

NVIDIA L40S

L40S-48C

  • NVIDIA L20

  • NVIDIA L20 liquid-cooled

L20-48C

NVIDIA L4

L4-24C

NVIDIA L2

L2-24C

NVIDIA RTX 6000 Ada

RTX 6000 Ada-48C

NVIDIA RTX 5880 Ada

RTX 5880 Ada-48C

NVIDIA RTX 5000 Ada

RTX 5000 Ada-32C
Table 46 vGPU Support for UVM on the NVIDIA Ampere GPU Architecture#

Board

vGPU

  • NVIDIA A800 PCIe 80 GB

  • NVIDIA A800 PCIe 80 GB liquid-cooled

  • NVIDIA AX800

  • A800D-80C

  • All MIG-backed vGPUs

NVIDIA A800 PCIe 40 GB active-cooled

  • A800-40C

  • All MIG-backed vGPUs

NVIDIA A800 HGX 80 GB

  • A800DX-80C

  • All MIG-backed vGPUs

  • NVIDIA A100 PCIe 80 GB

  • NVIDIA A100 PCIe 80 GB liquid-cooled

  • NVIDIA A100X

  • A100D-80C

  • All MIG-backed vGPUs

NVIDIA A100 HGX 80 GB

  • A100DX-80C

  • All MIG-backed vGPUs

NVIDIA A100 PCIe 40 GB

  • A100-40C

  • All MIG-backed vGPUs

NVIDIA A100 HGX 40 GB

  • A100X-40C

  • All MIG-backed vGPUs

NVIDIA A40

A40-48C

  • NVIDIA A30

  • NVIDIA A30X

  • NVIDIA A30 liquid-cooled

  • A30-24C

  • All MIG-backed vGPUs

NVIDIA A16

A16-16C

NVIDIA A10

A10-24C

NVIDIA RTX A6000

A6000-48C

NVIDIA RTX A5500

A5500-24C

NVIDIA RTX A5000

A5000-24C