GPU Virtualization Without the Complexity — VergeOS × NVIDIA
click anywhere to advance →
Live · April 2, 2026 · 1:00 PM ET
VergeIO × NVIDIA  ·  Webinar
GPU Virtualization
Without the Complexity
How VergeOS Delivers Enterprise vGPU Through
Unified Infrastructure Management
Aaron Richman
Host · VergeIO
Jimmy Rotella
Co-Host · NVIDIA
Paul Hodges
Demo · VergeIO Field CTO
George Crump
Commentator · VergeIO CMO
VergeIO
45 min + Live Q&A
Today’s Session
Presented byNVIDIA
VergeIO
45 Minutes That Change How You
Think About GPU Management
01 — The Problem   The GPU management barrier stopping IT teams today
02 — NVIDIA vGPU 20   What’s new, what it means for the enterprise — Jimmy Rotella, NVIDIA
03 — VergeOS Architecture   Three modes, one interface, zero specialists required
04 — Live Demo   Paul Hodges, VergeIO Field CTO — live in the VergeOS interface, no recordings
05 — Scenarios & Q&A   Deployment use cases and your questions live
Our Ask of You
Let’s Make This Interactive
1
Keep it interactive. Use the chat — tell us where you are, ask questions. We have team members monitoring the chat to give you quick answers.
2
Be on the lookout for our meeting links. Schedule a deep dive on VergeOS — GPUs for VDI, Private AI, or your specific use case.
3
Watch for polling questions. We have polls timed throughout the session — your answers help us tailor the conversation in real time.
Poll · Launching Now in Zoom
Tell Us About Your Environment
Question 1
What hypervisor are you currently running?
VMware vSphere
Microsoft Hyper-V
Nutanix AHV
KVM / Proxmox
Other
Evaluating
Question 2
Are you currently using GPUs in your data center?
Yes — in production
Yes — testing / pilot
No — evaluating
No — not yet planned
Question 3
What is your primary GPU use case?
VDI / Virtual Desktops
AI Inference
Data Science / Dev
Visualization / Rendering
Not using GPUs yet
Answers are anonymous — use the Zoom polling panel on your screen.
01
Section 01
The GPU
Management Problem
Why every IT team is stuck — and what it’s costing them
The Problem
Every IT Team Is Being Asked to Support GPU Workloads
Driver management: NVIDIA driver versions must match hypervisor, guest OS, and vGPU software — version mismatches break everything
MIG CLI complexity: Multi-Instance GPU configuration requires nvidia-smi expertise most sysadmins have never touched
Fragmented tooling: GPU resources managed separately from compute, storage, and networking — no unified view, no standard workflow
The result: Organizations hire specialists, engage expensive consultants, or defer GPU projects entirely
The Reality
The GPU Expertise Gap Is Real
0%
Lack in-house GPU expertise
Organizations without a dedicated GPU operations role — the gap is structural, not solvable by hiring alone
0 mo
Average time-to-production
Without a unified management platform, GPU deployment timelines stretch to 6+ months
$200K+
Annual GPU specialist cost
Salary, benefits, and recruiting — for expertise that should be built into the platform itself
⧡ Poll · Launching in Zoom Now
What is the biggest barrier to GPU adoption in your environment?
Lack of in-house expertise
Cost of hardware
Licensing complexity
Management / operational complexity
02
Section 02
NVIDIA vGPU 20
What’s new — and why the VergeOS partnership matters
NVIDIA vGPU 20 · March 2026 GTC
The Enterprise GPU Virtualization
Standard — Updated
NVIDIA RTX PRO 6000 Blackwell Server Edition — first Blackwell GPU with full MIG + vGPU support
MIG vGPU on KVM — hardware-level isolation plus time-slicing for maximum workload density
vGPU 20 driver validated across: A100, A30, A40, L40 series and the new RTX PRO 6000 Blackwell Server Edition
NVIDIA introduced VergeOS as a supported vGPU platform — joint support paths established with VergeIO engineering
Drivers deployed bit-for-bit identical to NVIDIA’s release — no modification, no redistribution
Platform Details
RTX PRO 6000 Blackwell Server Edition + The VergeOS Partnership
NVIDIA RTX PRO 6000 Blackwell Server Edition
Blackwell architecture — first server GPU with MIG vGPU support
Up to 4 MIG instances with hardware-level isolation enforced in silicon
Dual-slot PCIe — fits existing server infrastructure
vGPU software license required — available through NVIDIA-authorized partners
● Validated in VergeOS 26.1.3
What the VergeOS Partnership Means
Joint support paths: Both NVIDIA and VergeIO engineering collaborate on GPU issue resolution — one call gets both vendors engaged
Validated configurations: VergeOS 26.1.3 + vGPU 20 tested and confirmed by NVIDIA’s technical teams
Production ready today: Not roadmap — deployed and supported now, not a preview
● Introduced by NVIDIA
03
Section 03
VergeOS
GPU Architecture
Three modes. One interface. Zero specialists required.
GPU Modes in VergeOS
Three Modes. One Interface. No CLI.
Mode 01 — Passthrough
GPU Passthrough
1 VM = 1 Physical GPU
Entire GPU dedicated to a single VM. Maximum raw performance. No sharing. Ideal for rendering, simulation, and training workloads that need full GPU horsepower — no contention with other users.
Max Performance
Mode 02 — vGPU
NVIDIA vGPU
N VMs sharing 1 Physical GPU
Multiple VMs share one GPU through NVIDIA’s virtualization driver. Each VM gets dedicated GPU memory. Compute is fairly scheduled. Ideal for VDI, development environments, and inference hosting at scale.
Shared · Efficient
Mode 03 — MIG
Multi-Instance GPU
Hardware partitions — enforced in silicon
GPU divided into isolated instances at the hardware level. Each instance has dedicated compute engines, memory, and bandwidth — enforced in silicon, not software. Guaranteed performance per tenant, no interference.
Isolated · Guaranteed
Driver Management
One Upload. Automatic Deployment
to Every GPU-Enabled VM.
1
Obtain Driver
from NVIDIA
Download from nvidia.com. Bit-for-bit identical.
2
Upload Once
to VergeOS
Single upload via the VergeOS UI. No CLI.
3
VergeOS
Builds ISO
Platform bundles driver into deployment ISO.
4
ISO Attaches
on Assignment
When VM is assigned GPU, ISO attaches automatically.
5
VM Boots with
Correct Driver
No manual steps. No version mismatches.
nvidia-smi not required at any point.  MIG configuration is point-and-click. Entire workflow managed through the VergeOS interface.
GPU as Infrastructure
GPUs Are First-Class Resources
in VergeOS
Automatic inventory: Add a supported NVIDIA GPU to a cluster node — VergeOS detects and inventories it automatically, no manual registration required
Snapshot & replication: GPU-enabled VMs snapshot and replicate the same way as any other VM — DR workflows unchanged, no special handling
Unified monitoring: GPU utilization tracked alongside CPU and memory in the same dashboard — one pane, all resources, real-time visibility
Single management plane: No separate GPU orchestration layer, no plug-in, no third-party tool — the same interface IT already uses for everything else
05
Section 05
Deployment
Scenarios
Four use cases your team can deploy today — no specialists required
Deployment Scenarios
Four Ways to Start Today
VDI with GPU Acceleration
Engineering, design, and scientific visualization from centralized infrastructure. Users connect from standard endpoints. Inuvika OVD Enterprise confirmed.
⚡ Fastest time-to-value
Private AI Inference with MIG Isolation
Inference on isolated MIG instances — guaranteed compute, no noisy neighbors. Data stays on-premises. Compliance maintained.
⚡ Priority for regulated industries
Multi-Tenant Developer Environments
Split one high-end GPU across multiple data science teams via MIG. Each team gets isolated resources. No contention, no dedicated hardware per group.
Cost-efficient · Enterprise scale
Edge AI Deployments
Process data locally — manufacturing QC, retail analytics, healthcare imaging. On-premises, GPU-accelerated, full data sovereignty.
Low latency · Data sovereignty
Production Ready Today
VergeOS 26.1.3 + vGPU 20 — Validated & Shipping
0
Validated GPU Models
A100 · A30 · A40 · L40 series — plus RTX PRO 6000 Blackwell Server Edition for MIG vGPU
Zero
CLI Commands Required
Zero nvidia-smi. Zero command-line steps. Entire workflow in the VergeOS UI
0
Driver Upload per Version
Upload once. VergeOS automatically bundles and deploys to every GPU-enabled VM from that point forward
0
Vendors Behind Your Deployment
VergeIO + NVIDIA — joint support path established. Both engineering teams engaged on GPU issues. No finger-pointing.
“
This is the piece that surprises IT directors every time — they expect a command line. When they see MIG configuration done entirely through a point-and-click interface, the conversation shifts from ‘can we afford to do this’ to ‘when do we start.’
Jason Yaeger · SVP of Engineering, VergeIO
From customer conversations across enterprise GPU deployments
04
Section 04
Live Demo
Paul Hodges, Field CTO · VergeIO — Live in the VergeOS interface
Demo Sequence · 12 Minutes
12 Minutes. Five Steps. No Command Line.
1
GPU Inventory
View
1 min · Detected hardware in VergeOS UI
2
Driver
Upload
2 min · Upload once, deploy everywhere
3
MIG
Configuration
4 min · Point-and-click, no nvidia-smi
4
VM + vGPU
Assignment
3 min · Profile selection, VM launch
5
Monitoring
Dashboard
2 min · GPU + CPU + memory unified
Click the numbered circles to open related resources in a new tab
Presenter Notes
Press N to open notes.
00:00