autoscaling

Open repos and models their makers tagged autoscaling, most starred first. The same for everyone.

AI on my own machineRepo

LLMKube

Kubernetes operator for self-hosted LLM inference across a heterogeneous GPU fleet: NVIDIA CUDA, AMD Vulkan, and Apple Silicon Metal. Runtimes: llama.cpp, vLLM, TGI, mlx-server. Multi-GPU sharding, model caching, OpenAI-compatible endpoints. Apache-2.0, run across homelab and on-prem fleets, actively developed.

  • 267
  • Go
  • Apache-2.0
  • 2 d ago
defilantechTake it
Run my own servicesRepo

zoomies

Zoomies is a lightweight, self-hosted GitHub Actions runner fleet controller. Ephemeral runners by default, GitHub App auth, webhook-driven autoscaling, multi-host agents, a polished live web UI, and a one-line interactive installer. Single Go binary, SQLite, no Kubernetes.

  • 95
  • Go
  • AGPL-3.0
  • 2 h ago
eyupioTake it
GitHubRepo

generic-socket-rooms

Generic, scalable websocket server that should support most use-cases. We are using Elixir / Phoenix to use the language specific features and mitigate the use for Redis adapters (KISS) for scaling across multiple instances.

  • 4
  • TypeScript
  • 3 y ago
RheosophTake it
Images and videoRepo

comfyui-on-openshift

Stock ComfyUI for a whole team on one scale-to-zero GPU pool — cluster SSO, fair queueing, VRAM-tier routing, per-user showback with FOCUS chargeback, and GPU workers unreachable rather than defended. Demo on a laptop with make demo-local; deploy on ROSA or any OpenShift 4.x.

  • 1
  • Python
  • Apache-2.0
  • 2 mo ago
redhat-etTake it
Search GitHub and Hugging Face for autoscaling

Get , open it once and sign in. Then come back here and press the button again.

autoscaling: open source repos and models on Take My Repo