Difference between revisions of "Main Page"

Revision as of 04:22, 12 October 2026

Open-IOV is an open-source virtualization layer for NVIDIA GPUs: it runs stock, unmodified NVIDIA drivers inside virtual machines — Linux and Windows — with CUDA on hardware you own, without proprietary vGPU licenses, without patching the guest driver, the host driver, the hypervisor or the firmware.

Emulate the interface. Pass through the work. Never patch anyone.

The only new component is one host kernel module (vgsp.ko), which implements the interface the guest driver expects to talk to — the GPU System Processor and its resource-manager firmware — and arranges for the guest's work to run on real GPU hardware.

Start here

Project Status — the honest, dated state of the project.
Install and First Run — fresh host to a stock guest driver in about half an hour.
System Overview — how Open-IOV works, in one page.
Documentation — the full index of this wiki.
FAQ — the questions we get asked most.

Project status (2026-10-12)

Area	State
Emulated vGPU device (PCI, BARs, MSI-X, VFIO mdev)	Working
GSP boot emulation and GSP-RM message queues / RPC	Working
Stock guest driver probe, nvidia-smi (TU104)	Working
CUDA userspace init and the driver-API smoke (ALL OK, 64-byte payload round-trips)	Working
Guest CUDA kernel execution on real hardware	In progress — a forwarded launch reaches the engine queue; engine execution is the frontier
OpenGL / Vulkan, Windows guests, multi-tenancy, migration, performance	Not yet

The full story, with evidence and the current wall: Project Status and The Execution Frontier.

Deep dives

System Overview — the architecture before any subsystem
GSP and GSP-RM — the firmware interface we emulate
The vGSP Execution Plane (vEP) — how guest work becomes execution and completion
The Host Module (vgsp.ko) — the module internals
The Guest Stack and CUDASW — what runs unmodified in the guest
CUDA Userspace Driver — the libcuda.so analysis
Introduction to GMMU — GPU address translation from first principles
UVM in the Guest — unified memory as a correctness oracle
Physical GPU Backend and Guest Wiring — how work reaches real hardware
The Execution Frontier — the leading edge, evidence-led
Guest Driver Lifecycle: A Field Guide — boot to CUDA with real IDs and log signatures

Firmware interoperability

GSP 570.144W Firmware Analysis
Address Reference
RPC Message Format · BAR Emulation Specification · WPR Management · Migration Protocol · GSP RPC Emulation (historical, superseded)
risc-v-gsp-rm-debugger — the firmware runtime workbench

Project and ecosystem

Hardware and Software Matrix — supported combinations, honestly labelled
HAAEEP and Collaboration — the agent-edge use case and how to work with us
FAQ · Glossary

Community

Source and issues: git.vgpu.io/open-iov
Chat: Open-IOV Discord

About this wiki

This wiki previously hosted the OpenMdev / LibVF.IO documentation (2021–2023). Those pages are retained for reference under History; current documentation starts at Documentation.

@@ Line 1: / Line 1: @@
-Welcome to the '''Open-IOV Project''' wiki.
+__NOTOC__
+<div style="border:1px solid #c8ccd1; background:#f8f9fa; padding:0.9em 1.2em; margin-bottom:1em;">
+'''Open-IOV''' is an open-source virtualization layer for NVIDIA GPUs: it runs '''stock, unmodified NVIDIA drivers inside virtual machines''' — Linux and Windows — with CUDA on hardware you own, '''without proprietary vGPU licenses''', without patching the guest driver, the host driver, the hypervisor or the firmware.
-== [[Articles]] ==
+'''''Emulate the interface. Pass through the work. Never patch anyone.'''''
-'''Visit the [[Articles|Articles page]] for an overview of this wiki's contents.'''
-New and existing projects related to the following topics are welcome:
+The only new component is one host kernel module (<code>vgsp.ko</code>), which implements the interface the guest driver expects to talk to — the GPU System Processor and its resource-manager firmware — and arranges for the guest's work to run on real GPU hardware.
+</div>
-* '''GPU & IO Virtualization (VFIO / SR-IOV / SIOV / Mdev)'''
+== Start here ==
-* '''GPU & IO Device Drivers'''
+* '''[[Project Status]]''' — the honest, dated state of the project.
-*'''Hypervisor Development'''
+* '''[[Install and First Run]]''' — fresh host to a stock guest driver in about half an hour.
-*'''Virtualization Tools'''
+* '''[[System Overview]]''' — how Open-IOV works, in one page.
-'''Signups are open''' to the public and '''anyone can contribute'''.
+* '''[[Documentation]]''' — the full index of this wiki.
+* '''[[FAQ]]''' — the questions we get asked most.
-== Community ==
+== Project status (2026-10-12) ==
-'''Discord:''' https://discord.gg/Rb9K9DYxKK
+{| class="wikitable"
+! Area !! State
+|-
+| Emulated vGPU device (PCI, BARs, MSI-X, VFIO mdev) || Working
+|-
+| GSP boot emulation and GSP-RM message queues / RPC || Working
+|-
+| Stock guest driver probe, nvidia-smi (TU104) || Working
+|-
+| CUDA userspace init and the driver-API smoke (ALL OK, 64-byte payload round-trips) || Working
+|-
+| Guest CUDA kernel execution on real hardware || In progress — a forwarded launch reaches the engine queue; engine execution is the frontier
+|-
+| OpenGL / Vulkan, Windows guests, multi-tenancy, migration, performance || Not yet
+|}
-'''IRC:''' #gvm & #gvm-devel on oftc.net
+The full story, with evidence and the current wall: [[Project Status]] and [[The Execution Frontier]].
-== Contributing to Open-IOV.org ==
+== Deep dives ==
-Due to spam account creation is temporarily disabled through the Open-IOV website.
+* [[System Overview]] — the architecture before any subsystem
+* [[GSP and GSP-RM]] — the firmware interface we emulate
+* [[The vGSP Execution Plane (vEP)]] — how guest work becomes execution and completion
+* [[The Host Module (vgsp.ko)]] — the module internals
+* [[The Guest Stack and CUDASW]] — what runs unmodified in the guest
+* [[CUDA Userspace Driver]] — the <code>libcuda.so</code> analysis
+* [[Introduction to GMMU]] — GPU address translation from first principles
+* [[UVM in the Guest]] — unified memory as a correctness oracle
+* [[Physical GPU Backend and Guest Wiring]] — how work reaches real hardware
+* [[The Execution Frontier]] — the leading edge, evidence-led
+* [[Guest Driver Lifecycle: A Field Guide]] — boot to CUDA with real IDs and log signatures
-Contact Open-IOV moderators in the community '''#Documentation''' channel to have your account allowlisted until unmoderated signups re-open.
+== Firmware interoperability ==
+* [[GSP 570.144W Firmware Analysis]]
+* [[Address Reference]]
+* [[RPC Message Format]] · [[BAR Emulation Specification]] · [[WPR Management]] · [[Migration Protocol]] · [[GSP RPC Emulation]] (historical, superseded)
+* [[risc-v-gsp-rm-debugger]] — the firmware runtime workbench
-== Creating an Article ==
+== Project and ecosystem ==
-If you'd like to start a new article or contribute to an existing one simply create an account then visit a URL containing the article title you'd like to create or edit and click the "Edit" button.
+* [[Hardware and Software Matrix]] — supported combinations, honestly labelled
+* [[HAAEEP and Collaboration]] — the agent-edge use case and how to work with us
+* [[FAQ]] · [[Glossary]]
-Example:
+== Community ==
+* Source and issues: [https://git.vgpu.io/open-iov git.vgpu.io/open-iov]
-https://open-iov.org/index.php/your-article-title-here
+* Chat: [https://discord.gg/Rb9K9DYxKK Open-IOV Discord]
-New articles should be linked on the [[Articles|Articles page]] so people can find them.
+== About this wiki ==
+This wiki previously hosted the OpenMdev / LibVF.IO documentation (2021–2023). Those pages are retained for reference under [[Documentation|History]]; current documentation starts at [[Documentation]].