1 dépôt
Mechanisms for constraining specific workloads to run on designated hardware nodes using selectors and tolerations.
Distinct from Node Stack Deployments: Closest candidates refer to blockchain nodes or general server deployments, not Kubernetes-style node affinity and tolerations.
Explore 1 awesome GitHub repository matching devops & infrastructure · Node Affinity Controls. Refine with filters or upvote what's useful.
SwanLab is an open-source machine learning experiment tracking platform and observability tool. It provides a centralized dashboard for logging training metrics, hyperparameters, and hardware performance to monitor and analyze AI model training runs. The platform is distinguished by its focus on self-hosted infrastructure, allowing users to deploy private instances via Docker or Kubernetes for secure on-premises data control. It also includes specialized utilities for migrating historical experiment logs and synchronizing real-time metrics from external tools like MLflow. The system covers a
Constrains specific services to designated hardware nodes using selectors and tolerations for optimized workload placement.