Repositories
30
Total stars
21,643
Trending
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.
Created Nov 2025
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.
Created Sep 2026
Google Cloud Karpenter Provider
Created Sep 2024
Add-on for KEDA to scale HTTP workloads
Created Nov 2020
Tensor Fusion is a state-of-the-art GPU virtualization and pooling solution designed to optimize GPU cluster utilization to its fullest potential.
Created Nov 2024
Top
Saves up to 90% of AWS EC2 costs by automating the use of spot instances on existing AutoScaling groups. Installs in minutes using CloudFormation or Terraform. Convenient to deploy at scale using StackSets. Uses tagging to avoid launch configuration changes. Automated spot termination handling. Reliable fallback to on-demand instances.
Created Jul 2016
Add-on for KEDA to scale HTTP workloads
Created Nov 2020
General purpose metrics adapter for Kubernetes HPA metrics
Created Oct 2018
Horizontal Pod Autoscaler built with predictive abilities using statistical models
Created Dec 2019
Google Cloud Karpenter Provider
Created Sep 2024
Custom Pod Autoscaler program and base images, allows creation of Custom Pod Autoscalers
Created Sep 2019
Kubernetes-native scale-to-zero with zero traffic loss, no code changes, and direct integration with kubernetes resources
Created Apr 2024
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.
Created Nov 2025
Custom controller that extends the Horizontal Pod Autoscaler
Created Jul 2019
A Kubernetes controller for automatically optimizing pod requests based on their continuous usage. VPA alternative that can work with HPA.
Created Dec 2022
An open cloud native capacity solution which helps you achieve ultimate resource utilization in an intelligent and risk-free way.
Created Mar 2023
Tensor Fusion is a state-of-the-art GPU virtualization and pooling solution designed to optimize GPU cluster utilization to its fullest potential.
Created Nov 2024
Sherpa is a highly available, fast, and flexible horizontal job scaling for HashiCorp Nomad. It is capable of running in a number of different modes to suit different requirements, and can scale based on Nomad resource metrics or external sources.
Created Apr 2019
Kubernetes autoscaler for the workers. Resource is called WPA. Queues Supported: SQS, Beanstalkd.
Created Jul 2019
Alibaba Cloud Karpenter Provider
Created Jul 2024
KEDA External gRPC Scaler for GPU workloads - native NVML metrics via DaemonSet, no Prometheus required
Created Mar 2026
Tool to build Docker cluster composition for Amazon EC2 Container Service(ECS)
Created May 2015
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.
Created Sep 2026
Kubernetes Operator for Cloud Spanner autoscaling
Created Jun 2020
A Kubernetes controller that modifies the CPU and/or memory resources of containers based on whether they're starting up, according to the startup/post-startup settings you provide.
Created Jan 2024
Dynamically scale kubernetes resources using the length of an AMQP queue (number of messages available for retrieval from the queue) to determine the load
Created Jun 2016
Kubernetes autoscaler for vsphere
Created Dec 2018
DigitalOcean Droplets target plugin for HashiCorp Nomad Autoscaler
Created Apr 2021