> ## Documentation Index
> Fetch the complete documentation index at: https://docs.sambanova.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Introduction

[SambaStack](https://sambanova.ai/products/sambastack) is a turnkey AI inference platform delivering industry-leading performance, energy efficiency, and out-of-the-box support for popular open-source models. Available as both cloud (hosted) and on-premises solutions.

With SambaStack, you can:

* **Deploy leading AI models** – Access models from 9+ providers, including Meta, DeepSeek, Mistral AI, and Google, through a unified platform.
* **Reduce latency and inference costs** – Use built-in prompt caching to achieve 90%+ cache hit rates under sustained workloads.
* **Deploy your way** – Run on your infrastructure or use SambaNova's fully managed service.

> **Who this guide is for**
>
> System administrators managing:
>
> * Hardware infrastructure
> * Kubernetes clusters
> * Inference services (models, user groups, access control)

> **Required skills**
>
> * Linux system administration
> * Kubernetes operations (`kubectl`, Helm)
> * Log analysis and troubleshooting
> * System credential management

> [!NOTE]
>
> See the [SambaStack release notes](/docs/en/release-notes/sambastack) for new features, improvements, bug fixes, and version-specific updates. For inference service features and API usage, see the [Developer Guide](/docs/en/get-started/overview).

## Deployment options

> **[SambaStack hosted](/docs/en/v2.2.6/sambastack/getting-started/hosted)**
>
> A fully managed cloud service from SambaNova. Build and operate high-performance inference services without managing the underlying infrastructure – SambaNova provides and maintains the AI hardware and Kubernetes environment, while you configure and manage your AI services (model selection, user groups, and users).
>
> Quickstart guide

> **[SambaStack on-prem](/docs/en/v2.2.6/sambastack/getting-started/on-prem)**
>
> Runs in your own data center, giving you full control over the AI infrastructure, Kubernetes environment, and AI services you deploy. You manage everything end-to-end – model selection, user groups, and users – to support your organization’s needs.
>
> Quickstart guide

## Deployment comparison

| Component | Hosted | On-premises |
| :- | :- | :- |
| **Location** | SambaNova data center | Customer data center |
| **Infrastructure** | SambaNova provides and manages | Customer manages (post-SambaNova installation) |
| **Kubernetes** | SambaNova installs and manages | Customer installs and manages |
| **SambaStack software** | Customer installs and manages | Customer installs and manages |
| **Authentication options** | <ul><li>Existing OIDC compliant solution</li><li>Existing LDAP via Keycloak integration</li><li>Local identity management through Keycloak</li></ul> | <ul><li>Existing OIDC compliant solution</li><li>Existing LDAP via Keycloak integration</li><li>Local identity management through Keycloak</li></ul> |
| **DNS/TLS** | SambaNova provides and manages | Customer provides and manages |
| **Ingress** | SambaNova provides | Customer provides |
| **Software and model repository** | SambaNova provides image/artifact access | SambaNova provides via GCP access (customer retrieves) |

See the [on-prem architecture diagram and connection flows](/docs/en/v2.2.6/sambastack/getting-started/on-prem#sambastack-on-prem-architecture) for a full breakdown of how requests, administration, and supporting infrastructure connect.

## Explore key capabilities

> **[Supported models and bundles](/docs/en/v2.2.6/sambastack/service-administration/model-deployment/supported-models-and-bundles)**
>
> Browse available models, context lengths, and features.

> **[Deploy a model bundle](/docs/en/v2.2.6/sambastack/service-administration/model-deployment/deploying-models-and-bundles/deploy-a-bundle)**
>
> Deploy your first model bundle on SambaStack.

> **[Prompt caching](/docs/en/v2.2.6/sambastack/service-administration/performance/prompt-caching)**
>
> Cut latency and cost by caching repeated context – hit rates reach 90%+ under sustained traffic.

> **[Authentication](/docs/en/v2.2.6/sambastack/service-administration/platform-admin/authentication)**
>
> Set up OIDC or LDAP authentication for your deployment.