Features

NVIDIA vGPU (Virtual GPU) for Compute virtualizes NVIDIA GPUs for AI, machine learning, and high-performance computing. The subsections below describe MIG (Multi-Instance GPU) partitioning, provisioning, data paths, migration, multi-GPU guests, interconnects, scheduling, power state, and unified memory.

Table 45 Feature capability summary

Feature	What it covers	Page
MIG-Backed vGPU	Hardware-level GPU partitioning with spatial isolation	MIG-Backed vGPU
Device Groups	Topology-aware detection and provisioning of connected devices	Device Groups
GPUDirect	RDMA and storage paths that reduce CPU overhead	GPUDirect RDMA and GPUDirect Storage
Heterogeneous vGPU	Mixed vGPU profiles on one physical GPU	Heterogeneous vGPU
Live Migration	VM migration with short stun time on supported hypervisors	Live Migration
Multi-vGPU and P2P	Multi-GPU guests, board support, and NVLink P2P (hub)	Multi-vGPU and P2P
NVIDIA NVSwitch	High-bandwidth NVLink fabric between GPUs (includes multicast)	NVIDIA NVSwitch
NVLink Multicast	One-to-many data distribution (requires UVM; see NVSwitch page)	NVLink Multicast
Scheduling Policies	Best Effort, Equal Share, and Fixed Share time-slicing	Scheduling Policies
Suspend-Resume	VM state preservation for resource management	Suspend-Resume
Unified Virtual Memory	Single address space across CPU and GPU (includes board support)	Unified Virtual Memory (UVM)
Inference mode decision	Time-sliced vs MIG-backed vs time-sliced MIG-backed for inference	Choosing a vGPU Mode for Inference

Features on this page

• MIG-Backed vGPU
• Device Groups
• GPUDirect RDMA and GPUDirect Storage
• Heterogeneous vGPU
• Live Migration
• Multi-vGPU and P2P
• NVIDIA NVSwitch
• NVLink Multicast
• Scheduling Policies
• Suspend-Resume
• Unified Virtual Memory (UVM)
• Choosing a vGPU Mode for Inference