Remote machine learning on Windows with GPU

I have remote ML working on Windows via Docker Desktop, but it does not use the GPU.

docker-compose.yml:
name: immich_remote_ml

services:
  immich-machine-learning:
    container_name: immich_machine_learning
    # For hardware acceleration, add one of -[armnn, cuda, openvino] to the image tag.
    # Example tag: ${IMMICH_VERSION:-release}-cuda
    image: ghcr.io/immich-app/immich-machine-learning:${IMMICH_VERSION:-release}
    extends:
      file: hwaccel.ml.yml
      service: cuda
    volumes:
      - model-cache:/cache
    restart: always
    ports:
      - 3003:3003

volumes:
  model-cache: 


hwaccel.ml.yml is the standard one from the documentation
Was this page helpful?