Install on Windows

Install the Roboflow Inference Server on Windows with the native installer or with Docker Desktop, on CPU, GPU, or TensorRT.

Windows installer (x86)

You can run the Roboflow Inference Server on your Windows machine with the native desktop app. Download the latest Windows installer from the latest GitHub release: View the latest release and download installers on GitHub.

1. Download the latest installer and run it to install Roboflow Inference.

2. When the install finishes, it offers to launch the Inference Server.

3. To stop the server, close the terminal window it opens.

4. To start it again later, find Roboflow Inference in your Start Menu.

inference-models backend. When used with the inference-models backend, the Inference Server must run with elevated admin rights because of cache management with symlinks. The alternative is to enable Developer Mode.

The inference-models backend is opt-in via an environment flag: $env:USE_INFERENCE_MODELS = "True".

Using Docker

First, install Docker Desktop. Then use the CLI to start the container.

CPU

pip install inference-cli
inference server start

GPU

To access the GPU, make sure you have installed up-to-date NVIDIA drivers and the latest version of WSL 2, and that the WSL 2 backend is configured in Docker. Follow the setup instructions from Docker.

Then use the CLI to start the container:

pip install inference-cli
inference server start

If the pip install command fails, you may need to install Python first. Once you have Python 3.12, 3.11, or 3.10 on your machine, retry the command.

Manually starting the container

If you want more control over the container settings, start it yourself.

CPU

The core CPU Docker image includes support for OpenVINO acceleration on x64 CPUs via onnxruntime. Heavy models like SAM2 may run too slowly (dozens of seconds per image) to be practical; if you need them, use a CUDA-capable GPU.

The primary use cases for CPU inference are processing still images (for example NSFW classification of uploads or document verification) or infrequent sampling of frames from a video (for example occupancy tracking of a parking lot).

To get started with CPU inference, use the roboflow/roboflow-inference-server-cpu:latest container.

docker run -d ^
    --name inference-server ^
    --read-only ^
    -p 9001:9001 ^
    --volume "%USERPROFILE%\.inference\cache:/tmp:rw" ^
    --security-opt="no-new-privileges" ^
    --cap-drop="ALL" ^
    --cap-add="NET_BIND_SERVICE" ^
    roboflow/roboflow-inference-server-cpu:latest

GPU

The GPU container adds hardware acceleration on cards that support CUDA via NVIDIA-Docker. Make sure you have set up Docker to access the GPU, then add --gpus all to the docker run command:

docker run -d ^
    --name inference-server ^
    --gpus all ^
    --read-only ^
    -p 9001:9001 ^
    --volume "%USERPROFILE%\.inference\cache:/tmp:rw" ^
    --security-opt="no-new-privileges" ^
    --cap-drop="ALL" ^
    --cap-add="NET_BIND_SERVICE" ^
    roboflow/roboflow-inference-server-gpu:latest

TensorRT

With the GPU container you can optionally enable TensorRT, NVIDIA's model optimization runtime. It greatly increases your models' speed at the expense of a heavy compilation and optimization step (sometimes 15+ minutes) the first time you load each model.

Enable TensorRT by adding TensorrtExecutionProvider to the ONNXRUNTIME_EXECUTION_PROVIDERS environment variable.

docker run -d ^
    --name inference-server ^
    --gpus all ^
    --read-only ^
    -p 9001:9001 ^
    --volume "%USERPROFILE%\.inference\cache:/tmp:rw" ^
    --security-opt="no-new-privileges" ^
    --cap-drop="ALL" ^
    --cap-add="NET_BIND_SERVICE" ^
    -e ONNXRUNTIME_EXECUTION_PROVIDERS="[TensorrtExecutionProvider,CUDAExecutionProvider,OpenVINOExecutionProvider,CPUExecutionProvider]" ^
    roboflow/roboflow-inference-server-gpu:latest

Docker Compose

If you use Docker Compose for your application, the equivalent YAML is:

CPU

version: "3.9"

services:
  inference-server:
    container_name: inference-server
    image: roboflow/roboflow-inference-server-cpu:latest

    read_only: true
    ports:
      - "9001:9001"

    volumes:
      - "${USERPROFILE}/.inference/cache:/tmp:rw"

    security_opt:
      - no-new-privileges
    cap_drop:
      - ALL
    cap_add:
      - NET_BIND_SERVICE

GPU

version: "3.9"

services:
  inference-server:
    container_name: inference-server
    image: roboflow/roboflow-inference-server-gpu:latest

    read_only: true
    ports:
      - "9001:9001"

    volumes:
      - "${USERPROFILE}/.inference/cache:/tmp:rw"

    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]

    security_opt:
      - no-new-privileges
    cap_drop:
      - ALL
    cap_add:
      - NET_BIND_SERVICE

TensorRT

version: "3.9"

services:
  inference-server:
    container_name: inference-server
    image: roboflow/roboflow-inference-server-gpu:latest

    read_only: true
    ports:
      - "9001:9001"

    volumes:
      - "${USERPROFILE}/.inference/cache:/tmp:rw"

    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]

    environment:
      ONNXRUNTIME_EXECUTION_PROVIDERS: "[TensorrtExecutionProvider,CUDAExecutionProvider,OpenVINOExecutionProvider,CPUExecutionProvider]"

    security_opt:
      - no-new-privileges
    cap_drop:
      - ALL
    cap_add:
      - NET_BIND_SERVICE

Roboflow Enterprise plans add a Helm chart for Kubernetes deployments, networking solutions for OT networks, and customized support and installation packages. Contact the sales team to learn more.

Next steps

• Run a model against your new server.

• Install inference-gpu bare metal on Windows if you cannot use Docker.

• Securing a self-hosted server before you expose it beyond localhost.