> For the complete documentation index, see [llms.txt](https://docs.roboflow.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.roboflow.com/deployment/self-hosted.md).

# Self-Hosted

- [Self-Hosted Deployment](https://docs.roboflow.com/deployment/self-hosted/self-hosted.md): Run Roboflow models and Workflows on your own hardware with Inference, the open source computer vision deployment framework.
- [Inference Server](https://docs.roboflow.com/deployment/self-hosted/inference-server.md): What the Inference Server is, how to start it with Docker and the Inference CLI, and how to open its built-in JupyterLab notebook.
- [Install Inference Server](https://docs.roboflow.com/deployment/self-hosted/inference-server/install.md): Install the Roboflow Inference Server with Docker or a native desktop app on Linux, Windows, macOS, NVIDIA Jetson, Raspberry Pi, or your own cloud.
- [Minimum Requirements](https://docs.roboflow.com/deployment/self-hosted/inference-server/install/minimum-requirements.md): Minimum hardware and OS requirements for running Roboflow Inference, plus the devices it is tested and supported on.
- [Install on Linux](https://docs.roboflow.com/deployment/self-hosted/inference-server/install/linux.md): Install and run the Roboflow Inference Server on Linux with the Inference CLI, Docker, or Docker Compose, on CPU, GPU, or TensorRT.
- [Install on Windows](https://docs.roboflow.com/deployment/self-hosted/inference-server/install/windows.md): Install the Roboflow Inference Server on Windows with the native installer or with Docker Desktop, on CPU, GPU, or TensorRT.
- [Install on Mac](https://docs.roboflow.com/deployment/self-hosted/inference-server/install/mac.md): Install the Roboflow Inference Server on macOS with the native Apple Silicon app, with Docker, or outside Docker with MPS acceleration.
- [Install on NVIDIA Jetson](https://docs.roboflow.com/deployment/self-hosted/inference-server/install/jetson.md): Install the Roboflow Inference Server on an NVIDIA Jetson device with JetPack-specific containers, TensorRT acceleration, and Docker Compose.
- [Install on Raspberry Pi](https://docs.roboflow.com/deployment/self-hosted/inference-server/install/raspberry-pi.md): Install the Roboflow Inference Server on a 64-bit Raspberry Pi 4 or 5 with Docker, and what performance to expect.
- [Deploy in Your Own Cloud](https://docs.roboflow.com/deployment/self-hosted/inference-server/install/cloud.md): Run Roboflow Inference on your own AWS, Azure, or GCP infrastructure using the SkyPilot integration in the Inference CLI.
- [Deploy on AWS](https://docs.roboflow.com/deployment/self-hosted/inference-server/install/cloud/aws.md): Deploy a Roboflow Inference server on an AWS EC2 instance with the Inference CLI and SkyPilot.
- [Deploy on Azure](https://docs.roboflow.com/deployment/self-hosted/inference-server/install/cloud/azure.md): Deploy a Roboflow Inference server on an Azure virtual machine with the Inference CLI and SkyPilot.
- [Deploy on Google Cloud Platform](https://docs.roboflow.com/deployment/self-hosted/inference-server/install/cloud/gcp.md): Deploy a Roboflow Inference server on a Google Cloud Platform compute VM with the Inference CLI and SkyPilot.
- [Using Other Devices](https://docs.roboflow.com/deployment/self-hosted/inference-server/install/other.md): Run Roboflow Inference on unsupported hardware, including non-NVIDIA GPUs through alternative ONNX Runtime execution providers, and other edge SDKs.
- [Configuration](https://docs.roboflow.com/deployment/self-hosted/inference-server/configuration.md): Configure, secure, and monitor a self-hosted Roboflow Inference server - container options, environment variables, HTTPS, input formats, and metrics.
- [Docker Configuration Options](https://docs.roboflow.com/deployment/self-hosted/inference-server/configuration/docker-configuration.md): Configure a self-hosted Roboflow Inference container - networking, CORS, NMS defaults, model cache, workers, HTTPS, and the Secure Gateway.
- [Inference Server Environment Variables](https://docs.roboflow.com/deployment/self-hosted/inference-server/configuration/environment-variables.md): Environment variables that control a self-hosted Roboflow Inference server - execution providers, caching, Workflows, Roboflow API retries, telemetry, HTTPS, and security.
- [Securing a Self-Hosted Server](https://docs.roboflow.com/deployment/self-hosted/inference-server/configuration/security.md): Secure a self-hosted Roboflow Inference server with network isolation, authentication, TLS, custom Python restrictions, and SSRF controls on URL image input.
- [Serving Inference over HTTPS](https://docs.roboflow.com/deployment/self-hosted/inference-server/configuration/https.md): Serve a self-hosted Roboflow Inference server over HTTPS with your own TLS certificate, custom cert paths, encrypted keys, and mutual TLS.
- [Accepted Input Formats](https://docs.roboflow.com/deployment/self-hosted/inference-server/configuration/input-formats.md): Input formats accepted by a self-hosted Roboflow Inference server, and how to disable the less secure ones such as pickled numpy payloads and URL image fetching.
- [Inference Server Telemetry](https://docs.roboflow.com/deployment/self-hosted/inference-server/configuration/telemetry.md): Monitor a self-hosted Roboflow Inference server with Prometheus metrics and Docker container statistics.
- [Inference Architecture](https://docs.roboflow.com/deployment/self-hosted/inference-server/architecture.md): How Roboflow Inference is architected - request routing, parallelization, microservice and appliance patterns, capabilities, and why Docker is recommended.
- [Inference Library](https://docs.roboflow.com/deployment/self-hosted/inference-library.md): Run models directly in your own Python process with the inference package, with no server and no HTTP hop.
- [Install Bare Metal Inference GPU on Windows](https://docs.roboflow.com/deployment/self-hosted/inference-library/bare-metal-gpu-windows.md): Install the inference-gpu Python package with NVIDIA CUDA and cuDNN on Windows, without Docker.
- [Other SDKs](https://docs.roboflow.com/deployment/self-hosted/sdks.md): Roboflow SDKs for deploying models to web browsers, mobile, Lens Studio, Luxonis OAK, and OpenMV.
- [iOS SDK](https://docs.roboflow.com/deployment/self-hosted/sdks/ios-sdk.md): Deploy your trained Roboflow model in your iOS app
- [Luxonis OAK](https://docs.roboflow.com/deployment/self-hosted/sdks/luxonis-oak.md): Deploy your Roboflow Train model to your OpenCV AI Kit with Myriad X VPU  acceleration.
- [OpenMV](https://docs.roboflow.com/deployment/self-hosted/sdks/openmv.md): Deploy computer vision models to extremely low power edge cameras.
- [Lens Studio](https://docs.roboflow.com/deployment/self-hosted/sdks/lens-studio.md): Deploy a model to Lens Studio for use in building a Snap Lens.
- [Changelog - Lens Studio](https://docs.roboflow.com/deployment/self-hosted/sdks/lens-studio/changelog-lens-studio.md): A list of public facing changes for the Lens Studio integration
- [Web Browser](https://docs.roboflow.com/deployment/self-hosted/sdks/web-browser.md): Compare the inference-sdk and inferencejs JavaScript packages for running models in web browsers.
- [inferencejs Reference](https://docs.roboflow.com/deployment/self-hosted/sdks/web-browser/inferencejs-reference.md): Reference for \`inferencejs\`, an edge library for deploying computer vision applications built with Roboflow to web/JavaScript environments
- [inferencejs Requirements](https://docs.roboflow.com/deployment/self-hosted/sdks/web-browser/inferencejs-requirements.md): Requirements for running \`inferencejs\`
- [Web inference.js](https://docs.roboflow.com/deployment/self-hosted/sdks/web-browser/inferencejs.md): Run realtime predictions at the edge, on the browser, with inference.js
- [Web inference-sdk](https://docs.roboflow.com/deployment/self-hosted/sdks/web-browser/web-inference-sdk.md): Run realtime video inference from your browser, running on the Roboflow cloud, with inference-sdk
- [Enterprise Deployment](https://docs.roboflow.com/deployment/self-hosted/enterprise.md): Advanced Roboflow Enterprise deployment features like Secure Gateway, offline mode, and Kubernetes.
- [Docker Compose](https://docs.roboflow.com/deployment/self-hosted/enterprise/docker-compose.md): Run the Roboflow inference server alongside other docker containers to build your multi-container application via Docker Compose.
- [Kubernetes](https://docs.roboflow.com/deployment/self-hosted/enterprise/kubernetes.md): Getting started with Roboflow Inference on Kubernetes
- [License Server](https://docs.roboflow.com/deployment/self-hosted/enterprise/license-server.md): You can use the Roboflow License server to proxy the necessary routes for Roboflow Deployment servers into your company's DMZ
- [Offline Mode](https://docs.roboflow.com/deployment/self-hosted/enterprise/offline-mode.md): Roboflow Enterprise customers can deploy models offline.
- [Parallel HTTP API](https://docs.roboflow.com/deployment/self-hosted/enterprise/parallel-http-api.md): Run the Roboflow Inference parallel HTTP server to process inference requests asynchronously for higher throughput and lower latency.
- [Secure Gateway on MicroShift](https://docs.roboflow.com/deployment/self-hosted/enterprise/secure-gateway-microshift.md): Deploy Secure Gateway on Red Hat Device Edge, with the gateway and its encrypted cache running as MicroShift workloads managed by Roboflow Deployment Manager.
- [Secure Gateway on RHEL with Podman](https://docs.roboflow.com/deployment/self-hosted/enterprise/secure-gateway-podman.md): Deploy Secure Gateway on Red Hat Enterprise Linux hosts without Kubernetes, with the gateway and its encrypted cache running as Podman containers managed by Roboflow Deployment Manager.
- [Secure Gateway](https://docs.roboflow.com/deployment/self-hosted/enterprise/secure-gateway.md): Secure Gateway proxies the routes Roboflow Deployment servers need into your company's DMZ, and caches model weights and container images locally.
- [Stream Management API](https://docs.roboflow.com/deployment/self-hosted/enterprise/stream-management-api.md): Remotely manage Roboflow Inference video pipelines with the Stream Management API - run it in Docker, integrate over HTTP, and use the Stream Manager protocol.
- [Deployment Manager](https://docs.roboflow.com/deployment/self-hosted/enterprise/deployment-manager.md): Manage and monitor computer vision models deployed on edge hardware.
- [Setting Up](https://docs.roboflow.com/deployment/self-hosted/enterprise/deployment-manager/setting-up.md): Step-by-step sequence for setting up a device, adding a stream, and configuring alerts in Deployment Manager.
- [Add a Device](https://docs.roboflow.com/deployment/self-hosted/enterprise/deployment-manager/setting-up/add-a-device.md): Set up a device with everything you need to deploy a Workflow using Deployment Manager.
- [Add a Stream](https://docs.roboflow.com/deployment/self-hosted/enterprise/deployment-manager/setting-up/add-a-stream.md): Learn how to configure a stream that you can use to run a Workflow.
- [Hardware Requirements](https://docs.roboflow.com/deployment/self-hosted/enterprise/deployment-manager/setting-up/hardware-requirements.md): Supported hardware, cameras, network, and outbound traffic requirements for Deployment Manager.
- [Set up Device Alerts](https://docs.roboflow.com/deployment/self-hosted/enterprise/deployment-manager/setting-up/set-up-device-alerts.md): Configure email alerts for device connectivity, disk usage, camera FPS, and inference FPS issues.
- [Setup Maintenance Windows](https://docs.roboflow.com/deployment/self-hosted/enterprise/deployment-manager/setting-up/setup-maintenance-windows.md): Schedule maintenance windows so deploy-affecting configuration changes apply only at agreed-upon times.
- [Making Changes](https://docs.roboflow.com/deployment/self-hosted/enterprise/deployment-manager/making-changes.md): Tasks for updating devices and streams already running under Deployment Manager.
- [API Keys for Deployment Manager](https://docs.roboflow.com/deployment/self-hosted/enterprise/deployment-manager/making-changes/api-keys-for-device-manager.md): How device API keys are generated, scoped, viewed, and revoked when you add or remove a device.
- [Configure AI1 Camera Settings](https://docs.roboflow.com/deployment/self-hosted/enterprise/deployment-manager/making-changes/configure-ai1-camera-settings.md): Adjust exposure, gain, focus, white balance, and other camera settings on an AI1 device in real time.
- [Configure Device Network](https://docs.roboflow.com/deployment/self-hosted/enterprise/deployment-manager/making-changes/configure-device-network.md): Set device IP addressing, gateway, DNS, and hostname from the cloud in the Configuration tab.
- [Delete a Device](https://docs.roboflow.com/deployment/self-hosted/enterprise/deployment-manager/making-changes/delete-a-device.md): Permanently remove a device you no longer use from Deployment Manager.
- [Terminate a Stream](https://docs.roboflow.com/deployment/self-hosted/enterprise/deployment-manager/making-changes/delete-a-stream.md): Permanently terminate a stream and remove its configuration from the Deployment Manager dashboard.
- [Redeploy Deployment Manager](https://docs.roboflow.com/deployment/self-hosted/enterprise/deployment-manager/making-changes/redeploy-deployment-manager.md): Redeploy Deployment Manager onto an existing device to recover its Roboflow configuration after a failure.
- [Set a Static IP for a Camera](https://docs.roboflow.com/deployment/self-hosted/enterprise/deployment-manager/making-changes/set-camera-static-ip.md): Assign, edit, or remove a static IP for a GigE Basler or Lucid camera from Deployment Manager.
- [Soft Reset a PoE Port](https://docs.roboflow.com/deployment/self-hosted/enterprise/deployment-manager/making-changes/soft-reset-poe-port.md): Power-cycle a PoE port from the dashboard to recover stuck camera links on supported edge devices.
- [Pause and Resume a Stream](https://docs.roboflow.com/deployment/self-hosted/enterprise/deployment-manager/making-changes/stop-a-stream.md): Pause a running Workflow on a video stream and resume it later from the Deployment Manager dashboard.
- [Trigger a Stream](https://docs.roboflow.com/deployment/self-hosted/enterprise/deployment-manager/making-changes/trigger-a-stream.md): Run a Workflow on demand against the latest frame from a Triggered stream.
- [Update Device Configuration](https://docs.roboflow.com/deployment/self-hosted/enterprise/deployment-manager/making-changes/update-device-configuration.md): Manage device settings, service versions, inference engine, CA certificates, and additional services.
- [Monitoring](https://docs.roboflow.com/deployment/self-hosted/enterprise/deployment-manager/monitoring.md): Ways to observe device health, logs, streams, and Event Store status in Deployment Manager.
- [View a Stream](https://docs.roboflow.com/deployment/self-hosted/enterprise/deployment-manager/monitoring/view-a-stream.md): Learn how to view a Stream configured with Deployment Manager.
- [View Device Logs](https://docs.roboflow.com/deployment/self-hosted/enterprise/deployment-manager/monitoring/view-device-logs.md): View, search, filter, and download logs from Roboflow services running on your edge device.
- [View Event Store Status](https://docs.roboflow.com/deployment/self-hosted/enterprise/deployment-manager/monitoring/view-event-store-status.md): Monitor Event Store status, storage usage, backup progress, and usage history for a device.
- [View the Resource Monitor](https://docs.roboflow.com/deployment/self-hosted/enterprise/deployment-manager/monitoring/view-the-resource-monitor.md): Monitor disk, memory, CPU, and GPU usage, stream FPS, service containers, and network interfaces for a device.
- [Services](https://docs.roboflow.com/deployment/self-hosted/enterprise/deployment-manager/services.md): Optional edge container services a Deployment Manager device can run alongside the inference server.
- [Event Store](https://docs.roboflow.com/deployment/self-hosted/enterprise/deployment-manager/services/event-store.md): Store inference events on the edge device with automatic retention, storage limits, and optional cloud backup.
- [Event Store REST API](https://docs.roboflow.com/deployment/self-hosted/enterprise/deployment-manager/services/event-store/rest-api.md): Endpoint reference for the on-device Event Store v2 API, including event schemas and administration routes.
- [PLC Relay](https://docs.roboflow.com/deployment/self-hosted/enterprise/deployment-manager/services/plc-relay.md): Configure PLC Relay to read and write PLC tags over Allen-Bradley, Modbus TCP, or Siemens S7.
- [OPC UA Server](https://docs.roboflow.com/deployment/self-hosted/enterprise/deployment-manager/services/opc-ua-server.md): Expose device data as OPC UA tags that PLCs, SCADA systems, and other industrial clients can read and write.
- [RTSP Simulator](https://docs.roboflow.com/deployment/self-hosted/enterprise/deployment-manager/services/rtsp-simulator.md): Stream an uploaded video file as a looping RTSP source for testing inference pipelines without a camera.