SaaSHub helps you find the best software and product alternatives Learn more →
Top 20 Shell GPU Projects
-
Project mention: Run GUI applications and desktops in Docker and Podman containers | news.ycombinator.com | 2026-01-23
-
SaaSHub
SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives
-
llm-d is a high-performance distributed inference serving stack optimized for production deployments on Kubernetes. We help you achieve the fastest "time to state-of-the-art (SOTA) performance" for key OSS large language models across most hardware accelerators and infrastructure providers with well-tested guides and real-world benchmarks. - link [code-repo] - ( Added: 2026-03-24 11:31:22 )
-
DreamServer
Turn your PC, Mac, or Linux box into an AI server. LLM inference, chat UI, voice, agents, workflows, RAG, and image generation.
Project mention: Turn your PC, Mac, or Linux box into an AI server | news.ycombinator.com | 2026-05-31 -
-
-
nfancurve
A small and lightweight POSIX script for using a custom fan curve in Linux for those with an Nvidia GPU.
-
vfio
A script for easy pci and usb passthrough along with disks, iso's and other useful flags for quick tinkering with less of a headache. I use it for VM gaming and other PCI/LiveCD/PXE/VM/RawImage testing given the script's accessibility.
-
-
-
Single-GPU-Passthrough-for-Dummies
Non-intimidating guide to create a KVM GPU Passthrough via libvirt/virt-manager on systems with only one GPU.
-
-
pop_OS-win10-KVM-setup
This is a repo that contains directions and the necessary files to create a working pop!_OS -> Windows 10 KVM that has GPU Passthrough, CPU Passthrough with proper pinning, Allocated ram, and PCIe passthrough with QEMU and Virt-Manager.
-
hiveos_gddr6x_temps
Read NVIDIA RTX 3090, 3080, 3080 Ti, 3070 Ti, 3060 Ti, 2080 Ti, 2080, A2000, A4000, A4500, A5000 GDDR6X and GDDR6 temperatures directly on HiveOS GUI
-
-
-
-
Proxmox-VGPU
Script to install vGPU driver on Proxmox. 1. Install NVIDIA GRID vGPU on Proxmox VE 2. Install Intel SR-IOV Graphics on Proxmox VE
I was going off on a bit of a tangent but take a look at this horror, which is still up:
https://github.com/InboraStudio/Proxmox-VGPU
Note the quite professional looking README.md and think about the audience for this thing - kittens hitting the search bong and trying to get something very complicated working.
Read the scripts: they are pretty short and could put your hypervisor in the hands of someone else who may not be too friendly.
Now pip has the same problem except you don't normally go in with a web browser first.
I raised an issue to at least provide a hint to casual browsers and also raised it with the github AI bottie complaint thang which doesn't care about you, me or anything else for that matter.
-
-
nvrun
Application runner for NVIDIA GPUs on a Linux system with a dual-GPU config utilizing NVIDIA On-Demand offloading
-
docker-ollama
Docker image to run an Ollama local LLM server. Secure by default, all API requests require a Bearer token (auto-generated on first start). OpenAI-compatible API. Supports first-start model pre-pull, NVIDIA GPU (CUDA) acceleration, and persistent model storage. Multi-arch: amd64, arm64.
Project mention: Show HN: Secure-by-default Ollama Docker image with built-in auth, only 70MB | news.ycombinator.com | 2026-05-01
Shell GPU discussion
Shell GPU related posts
-
Run GUI applications and desktops in Docker and Podman containers
-
Show HN: Beta9 – Open-source, serverless GPU container runtime
-
Alternative clouds are booming as companies seek cheaper access to GPUs
-
Remote Controlling an HP 1670G Logic Analyzer with a Linux PC X Server
-
I can no longer launch VMs
-
What OSS does companies use to create their own Sandboxed Environments?
-
How to disable nvidia drivers?
-
A note from our sponsor - SaaSHub
www.saashub.com | 13 Jun 2026
Index
What are some of the best open-source GPU projects in Shell? This list will help you:
| # | Project | Stars |
|---|---|---|
| 1 | x11docker | 6,279 |
| 2 | llm-d | 3,346 |
| 3 | DreamServer | 1,896 |
| 4 | Complete-Single-GPU-Passthrough | 1,137 |
| 5 | slurm-docker-cluster | 516 |
| 6 | nfancurve | 322 |
| 7 | vfio | 206 |
| 8 | MobilePassThrough | 177 |
| 9 | LEDs-single-gpu-passthrough | 138 |
| 10 | Single-GPU-Passthrough-for-Dummies | 135 |
| 11 | kubeflow-bootstrap | 73 |
| 12 | pop_OS-win10-KVM-setup | 71 |
| 13 | hiveos_gddr6x_temps | 47 |
| 14 | GPU-accelerated-guppy-basecalling | 18 |
| 15 | DellG5SE-Linux | 11 |
| 16 | passthrough_helper_void | 5 |
| 17 | Proxmox-VGPU | 4 |
| 18 | tmux-plugin-gpu | 3 |
| 19 | nvrun | 3 |
| 20 | docker-ollama | 2 |