SUSE AI 1.0
- WHAT?
SUSE AI is a multi-layered enterprise AI solution that consists of several software components and dependencies.
- WHY?
Use this guide to deploy and install SUSE AI and its dependencies in a consistent and supported manner.
- EFFORT
It takes less than one hour of reading time and requires advanced knowledge of Linux deployment.
- GOAL
By the end of this guide, you will have SUSE AI and all required dependencies installed and ready for use.
Publication Date: 2026-04-02
- 1 Installation overview
- 2 Installing the Linux and Kubernetes distribution
- 3 Preparing the cluster for AI Library
- 4 Installing applications from AI Library
- 4.1 What is SUSE Application Collection?
- 4.2 What is SUSE Registry?
- 4.3 Installation procedure
- 4.4 Installing cert-manager
- 4.5 Installing OpenSearch
- 4.6 Installing Milvus
- 4.7 Installing Ollama
- 4.8 Installing Open WebUI
- 4.9 Installing vLLM
- 4.10 Installing mcpo
- 4.11 Installing PyTorch
- 4.12 Installing Qdrant
- 4.13 Installing LiteLLM
- 4.14 Installing MLflow
- 4.15 Verifying SUSE AI Library applications
- 5 Alternative deployments
- Glossary
- A Copyright
- B GNU Free Documentation License
- B1 0. PREAMBLE
- B2 1. APPLICABILITY AND DEFINITIONS
- B3 2. VERBATIM COPYING
- B4 3. COPYING IN QUANTITY
- B5 4. MODIFICATIONS
- B6 5. COMBINING DOCUMENTS
- B7 6. COLLECTIONS OF DOCUMENTS
- B8 7. AGGREGATION WITH INDEPENDENT WORKS
- B9 8. TRANSLATION
- B10 9. TERMINATION
- B11 1. FUTURE REVISIONS OF THIS LICENSE
- B12 ADDENDUM: How to use this License for your documents
List of Figures
- 1.1 SUSE AI installation process
- 2.1 Language, keyboard and product selection
- 2.2 License agreement
- 2.3 Network settings
- 2.4 Registration
- 2.5 Extension and module selection
- 2.6 Add-on product
- 2.7 System role
- 2.8 Suggested partitioning
- 2.9 Clock and time zone
- 2.10 Local user creation
- 2.11 Password for the system administrator
root - 2.12 Installation settings
- 2.13 Confirm installation
- 2.14 Performing the installation
- 3.1 Rancher extensions
- 3.2 Enable extensions
- 3.3 Install UI extension
- 3.4 Reload extension
- 3.5 Install SUSE Security application
- 3.6 SUSE Security dasboard
- 3.7 Uninstalling extension
- 3.8 Rancher chart
- 3.9 Neuvector values
- 3.10 Neuvector deployed
- 3.11 Neuvector console access
- 3.12 Neuvector administrator users
- 3.13 Local admin
- 3.14 Rancher SSO
- 3.15 High-level overview of the SUSE Observability setup
- 3.16 Separate clusters for SUSE AI and SUSE Observability
- 3.17 New GenAI Observability menu item
- 4.1 Milvus page in the SUSE Application Collection
- 4.2 Adding a vLLM connection to Open WebUI
- 4.3 MLflow Web UI
List of Tables
List of Examples
- 3.1 Click to Expand
- 4.1 Ollama Helm chart version 0.x.x
- 4.2 Ollama Helm chart version 1.x.x
- 4.3 Basic override file with GPU and two models pulled at startup
- 4.4 Basic override file with Ingress and no GPU
- 4.5 Open WebUI override file with Ollama included
- 4.6 Open WebUI override file with Ollama installed separately
- 4.7 Open WebUI override file with pipelines enabled
- 4.8 Open WebUI override file with a connection to vLLM
- 4.9 Minimal configuration
- 4.10 Basic configuration
- 4.11 Loading prefetched models from persistent storage
- 4.12 Configuration with multiple models
- 4.13 CPU offloading
- 4.14 Shared remote KV cache storage with LMCache
- 4.15 Basic override file with GPU enabled
- 4.16 ConfigMap-based upload
- 4.17 Host-folder with files baked into the chart
- 4.18 Git repository clone: public with no authentication
- 4.19 Git repository clone: private with authentication
- 4.20 Basic override file when the cluster has no default storage class set.
- 4.21 An example where Qdrant uses GPU capabilities.
- 4.22 Basic override file with PostgreSQL deployment and master key automatically generated.
- 4.23 Verifying containers and Helm charts hosted on the SUSE Application Collection
- 4.24 Verifying containers and Helm charts hosted on the SUSE Registry
- 4.25 Discovering attached attestations (optional)
- 4.26 Extracting the CycloneDX SBOM
- 4.27 Scanning the SBOM for Vulnerabilities
- 5.1 You already have an OS provisioned on the servers and you want to deploy an RKE2 cluster with a Rancher management server.
- 5.2 You already have an OS provisioned on the servers and you want to deploy an RKE2 cluster to serve as the execution environment for SUSE AI workloads.