https://docs.opennebula.io/7.4/platform_services/oneks/catalog/Recent content in OneKS Application Catalog onHugoenThu, 01 Oct 2026 00:00:00 +0000https://docs.opennebula.io/7.4/platform_services/oneks/catalog/kserve_llmisvc_platform/Thu, 01 Oct 2026 00:00:00 +0000https://docs.opennebula.io/7.4/platform_services/oneks/catalog/kserve_llmisvc_platform/<h2 id="description-and-purpose"> Description and Purpose <a class="anchor-link" href="#description-and-purpose" aria-label="Link to this section"> <i class="fas fa-link fa-xs"></i> </a> </h2><p>The <a href="https://kserve.github.io/website/docs/model-serving/generative-inference/llmisvc/llmisvc-overview"><strong>KServe LLMInferenceService Platform</strong></a> installs the KServe runtime configuration for generative-inference workloads. It provides Gateway API routing through Envoy AI Gateway, the LeaderWorkerSet operator for multi-node inference workloads, and node-local model caching.</p> <table> <thead> <tr> <th><strong>Attribute</strong></th> <th><strong>Value</strong></th> </tr> </thead> <tbody> <tr> <td>Application ID</td> <td><code>8323494d-06ad-48e1-8ebe-779a2a91f17d</code></td> </tr> <tr> <td>Helm chart</td> <td><code>oci://ghcr.io/kserve/charts/kserve-runtime-configs</code></td> </tr> <tr> <td>Version</td> <td><code>v0.20.0</code></td> </tr> </tbody> </table> <p>The application requires the <code>cert-manager</code> installation provided by Cluster API. OneKS also installs the following managed components before the root chart:</p>https://docs.opennebula.io/7.4/platform_services/oneks/catalog/nvidia_gpu_operator/Thu, 01 Oct 2026 00:00:00 +0000https://docs.opennebula.io/7.4/platform_services/oneks/catalog/nvidia_gpu_operator/<h2 id="description-and-purpose"> Description and Purpose <a class="anchor-link" href="#description-and-purpose" aria-label="Link to this section"> <i class="fas fa-link fa-xs"></i> </a> </h2><p>The <a href="https://docs.nvidia.com/datacenter/cloud-native/gpu-operator/latest/"><strong>NVIDIA GPU Operator</strong></a> deploys the NVIDIA GPU software stack required to expose and manage NVIDIA GPUs in Kubernetes. Use it on K8s Clusters with NVIDIA GPU worker nodes so workloads can request GPU resources through Kubernetes.</p> <table> <thead> <tr> <th><strong>Attribute</strong></th> <th><strong>Value</strong></th> </tr> </thead> <tbody> <tr> <td>Application ID</td> <td><code>8cb0d29e-4521-4bcb-a977-786df097d162</code></td> </tr> <tr> <td>Helm repository</td> <td><code>https://helm.ngc.nvidia.com/nvidia</code></td> </tr> <tr> <td>Helm chart</td> <td><code>gpu-operator</code></td> </tr> <tr> <td>Version</td> <td><code>v26.3.1</code></td> </tr> </tbody> </table> <h2 id="parameters"> Parameters <a class="anchor-link" href="#parameters" aria-label="Link to this section"> <i class="fas fa-link fa-xs"></i> </a> </h2><p>This application has no application-specific user inputs. During installation, provide the standard release name, target namespace, and namespace-creation option.</p>https://docs.opennebula.io/7.4/platform_services/oneks/catalog/prometheus/Thu, 01 Oct 2026 00:00:00 +0000https://docs.opennebula.io/7.4/platform_services/oneks/catalog/prometheus/<h2 id="description-and-purpose"> Description and Purpose <a class="anchor-link" href="#description-and-purpose" aria-label="Link to this section"> <i class="fas fa-link fa-xs"></i> </a> </h2><p>The <a href="https://prometheus.io/docs/introduction/overview/"><strong>Prometheus</strong></a> application installs the <code>kube-prometheus-stack</code> chart to collect Kubernetes metrics and store them as time-series data. Use it to monitor K8s Cluster components and workloads and to provide a metrics source for observability integrations.</p> <table> <thead> <tr> <th><strong>Attribute</strong></th> <th><strong>Value</strong></th> </tr> </thead> <tbody> <tr> <td>Application ID</td> <td><code>d511b694-d868-4e40-8224-fdf6a0ca3383</code></td> </tr> <tr> <td>Helm repository</td> <td><code>https://prometheus-community.github.io/helm-charts</code></td> </tr> <tr> <td>Helm chart</td> <td><code>kube-prometheus-stack</code></td> </tr> <tr> <td>Version</td> <td><code>v87.12.2</code></td> </tr> </tbody> </table> <h2 id="parameters"> Parameters <a class="anchor-link" href="#parameters" aria-label="Link to this section"> <i class="fas fa-link fa-xs"></i> </a> </h2><p>This application has no application-specific user inputs. During installation, provide the standard release name, target namespace, and namespace-creation option.</p>https://docs.opennebula.io/7.4/platform_services/oneks/catalog/nvidia_runai_platform/Thu, 01 Oct 2026 00:00:00 +0000https://docs.opennebula.io/7.4/platform_services/oneks/catalog/nvidia_runai_platform/<h2 id="description-and-purpose"> Description and Purpose <a class="anchor-link" href="#description-and-purpose" aria-label="Link to this section"> <i class="fas fa-link fa-xs"></i> </a> </h2><p>The <a href="https://docs.nvidia.com/run-ai/self-hosted/index.html"><strong>NVIDIA Run:ai Platform</strong></a> installs the Run:ai control plane with managed ingress, GPU, monitoring, storage, certificate, and CA-distribution components. Use it to provide centralized Run:ai scheduling and administration services for AI workloads.</p> <table> <thead> <tr> <th><strong>Attribute</strong></th> <th><strong>Value</strong></th> </tr> </thead> <tbody> <tr> <td>Application ID</td> <td><code>905abc6e-7cea-4a0a-bc84-ad215a3fc1fe</code></td> </tr> <tr> <td>Helm repository</td> <td><code>https://helm.ngc.nvidia.com/nvidia/runai</code></td> </tr> <tr> <td>Helm chart</td> <td><code>control-plane</code></td> </tr> <tr> <td>Version</td> <td><code>v2.25</code></td> </tr> </tbody> </table> <p>As internal dependencies, OneKS also installs and fully manages the following components. They are not exposed as standalone applications, but appear inside the Kubernetes cluster among the resources created by this application:</p>