gpu-virtualization

Heterogeneous GPU Sharing on Kubernetes

KVM Backend for VirtualBox

A transparent, in-container GPU resource controller that enforces memory and compute limits by intercepting CUDA calls without application or driver changes.

Here are my personal paper reading notes (including machine learning systems, AI infrastructure, and other interesting stuffs).

Tensor Fusion is a state-of-the-art GPU virtualization and pooling solution designed to optimize GPU cluster utilization to its fullest potential.

Paravirtual NVIDIA GPU for KVM guests — run unmodified CUDA, PyTorch and Vulkan inside a VM at host parity, on a GPU the host keeps using. No passthrough, no vGPU licence. Experimental.

Research: vGPU unlock on consumer NVIDIA RTX 5090 (Blackwell/GB202). 19 binary patches, full CPU-side pipeline working, GSP firmware blocked by fused-off VF PRIV registers.

A GPU Virtualisation benchmarking tool - For LLM like workloads, overhead evaluations and on resource isolation metrics

TensorFusion landing page and product docs

Archived - WSL2-style NVIDIA GPU ioctl forwarding for KVM/QEMU guests on Linux hosts - superseded by nvkvm-pv

Sovereign private GPU cloud platform. Slices physical GPUs into 4–8 isolated, 60 FPS in-browser AI workstations streaming full graphical Linux desktops directly to any web browser with persistent storage.

Transparent library for CUDA/NVML that virtualizes GPU access, enforces memory limits, and enables container-friendly sharing with minimal performance overhead.

NVIDIA vGPU on a consumer GeForce RTX 3090 (GA102) via legacy mdev. Working config, the exact kernel requirement, ~80 measured dead ends, and a tool to port the fix to other driver builds. Fixes the runlist-disable leak behind 'Immediate pteblit timed out' and silent no-render guests.

Bitfusion Io — independent third-party profile of a public API surface, by API Evangelist. Bitfusion (bitfusion.io) was an Austin, Texas startup, backed by DCVC, that built "elastic AI" infrastructure software. Its FlexDirect platform was a transparent GPU/CPU virtualization layer that pooled network-attached accelerators (GPUs, FPGAs, ASICs) acros

🎮 Enable GPU passthrough for KVM on full AMD systems, simplifying setup for Arch Linux and Windows 11 virtual machines.

Bitfusion — independent third-party profile of a public API surface, by API Evangelist. Bitfusion (Bitfusion.io) was a GPU virtualization startup whose FlexDirect software pooled and disaggregated GPUs across a network so machine learning and AI workloads could share accelerator hardware on demand.

HAMI — independent third-party profile of a public API surface, by API Evangelist. HAMI (Heterogeneous AI Computing Virtualization Middleware) is an open-source project that enables GPU virtualization and sharing for Kubernetes workloads, allowing multiple AI containers to share GPU resources efficiently.