← Latest products

CUDA/graphics in QEMU-KVM VMs without passing the Nvidia card to them

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. I built this because I wanted a VM with a real GeForce GPU without losing the card on my desktop.

Open source

83 stars · GitHubexternal site

Visit github.comexternal site

Reactions (1)

Similar products

by description similarity

  1. LLMKube

    github.com

    Kubernetes for Local LLMs with GPU Acceleration

    Hacker News5 pts

  2. Rgpu

    github.com

    a PyTorch device whose tensors live on a remote GPU

    Hacker News57 pts

  3. HipScript

    hipscript.lights0123.com

    Run CUDA in the browser with WebAssembly and WebGPU

    Hacker News309 pts

  4. Continuous Nvidia CUDA PC Sampling Profiler

    polarsignals.com

    Blog post about how we extended our open source profiler to include support for continuous production PC sampling.

    Hacker News14 pts

  5. VMetal

    vmetal.ai

    run a GPU cloud on bare metal without OpenStack

    Hacker News12 pts