Kueue

Input—per 1M tokens

Output—per 1M tokens

Context—tokens

WeightsClosed

About

Kueue is ranked #5 of 18 in GPU cluster management software on Inferse. It runs on API, Self-hosted. There is a free plan.

Compared on GPU cluster management software

Free plan: Yeskueue.sigs.k8s.io
Deployment model: self_hostedkueue.sigs.k8s.io
Workload scheduling: batchkueue.sigs.k8s.io
Kubernetes support: Yeskueue.sigs.k8s.io
Quota controls: Yeskueue.sigs.k8s.io
GPU utilization metrics: Yeskueue.sigs.k8s.io
Cloud GPU support: Yeskueue.sigs.k8s.io

Facts

What it does: Kueue manages quotas and job resource consumption, deciding when jobs wait, start, or are preempted.kueue.sigs.k8s.io · 2 Oct 2026
Where it runs: Kueue can be installed on a vanilla Kubernetes cluster and does not replace existing Kubernetes components.kueue.sigs.k8s.io · 2 Oct 2026
Queueing and resource management: Features include priority-based job queueing, resource flavor fungibility, fair sharing, cohorts, and preemption policies.kueue.sigs.k8s.io · 2 Oct 2026
Workload integrations: Built-in integrations include Kubernetes Batch Jobs, Kubeflow training jobs, Ray jobs and clusters, JobSet, AppWrapper, plain Pods, and Pod groups.kueue.sigs.k8s.io · 2 Oct 2026
Multi-cluster: MultiKueue can search for capacity and dispatch jobs across clusters.kueue.sigs.k8s.io · 2 Oct 2026
Topology-aware scheduling: Kueue can schedule with data center topology in mind to optimize pod-to-pod communication throughput.kueue.sigs.k8s.io · 2 Oct 2026
Monitoring: Kueue provides Prometheus metrics and an on-demand visibility endpoint for pending workloads.kueue.sigs.k8s.io · 2 Oct 2026
Installation requirement: The installation guide recommends Kubernetes 1.34 or newer and says only those versions are officially supported and tested.kueue.sigs.k8s.io · 2 Oct 2026
Installation methods: The documentation provides installation instructions using kubectl, Helm, or a source build.kueue.sigs.k8s.io · 2 Oct 2026
Community support: The project homepage describes Kueue as an open, community-driven CNCF project and links to Slack, GitHub, and a mailing list.kueue.sigs.k8s.io · 2 Oct 2026
Purpose: Kueue manages quotas and job resource consumption in Kubernetes, deciding when jobs wait, start, or are preempted.kueue.sigs.k8s.io · 3 Oct 2026
Cluster fit: Kueue installs on a vanilla Kubernetes cluster and does not replace existing Kubernetes components.kueue.sigs.k8s.io · 3 Oct 2026
Quota sharing: Kueue supports tenant quotas and fair sharing, including shared resource pools and quota borrowing between teams.kueue.sigs.k8s.io · 3 Oct 2026
Workload support: Built-in integrations include Kubernetes Jobs, Kubeflow training jobs, Ray jobs and clusters, JobSet, AppWrapper, Pods, Deployments, StatefulSets, and LeaderWorkerSet.kueue.sigs.k8s.io · 3 Oct 2026
Scheduling: Kueue supports priority-based queueing, resource flavor fungibility, preemption, and all-or-nothing scheduling.kueue.sigs.k8s.io · 3 Oct 2026
Topology: Topology-aware scheduling places distributed workloads with data-center topology in mind to improve pod-to-pod communication throughput.kueue.sigs.k8s.io · 3 Oct 2026
Multi-cluster: MultiKueue can search for capacity and dispatch workloads across multiple clusters.kueue.sigs.k8s.io · 3 Oct 2026
Monitoring: Kueue exposes Prometheus metrics for system health and ClusterQueue and LocalQueue status, with Grafana query guidance in its docs.kueue.sigs.k8s.io · 3 Oct 2026
Access control: Kueue installs batch administrator and batch user ClusterRoles and supports composing custom roles from resource-specific editor and viewer roles.kueue.sigs.k8s.io · 3 Oct 2026
Installation requirement: The installation guide recommends Kubernetes 1.34 or newer, stating that only those versions are officially supported and tested.kueue.sigs.k8s.io · 3 Oct 2026
Install methods: The maker documents installation with kubectl or Helm, building from source, and installing a development version.kueue.sigs.k8s.io · 3 Oct 2026
Security operations: Kueue's webhook server uses internal certificate management, and its installation guide also links instructions for using cert-manager.kueue.sigs.k8s.io · 3 Oct 2026
Community support: The project directs users to Kubernetes Slack, GitHub for bugs and contributions, and a mailing list for announcements.kueue.sigs.k8s.io · 3 Oct 2026