Immich•5mo ago

No GPU usage on remote ML with Windows 10 and Docker Desktop

Hello, I have set up a remote ML container on my Win10-desktop, because it is more powerful. The jobs run on my PC and they run faster than on the immich-host, but taks manager shows CPU usage, but no GPU usage. How can I fix that? docker-compose

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}-cuda
    extends:
      file: hwaccel.ml.yml
      service: cuda # set to one of [armnn, cuda, openvino, openvino-wsl] for accelerated inference - use the `-wsl` version for WSL2 where applicable
    volumes:
      - model-cache:/cache
    restart: always
    ports:
      - 3003:3003

volumes:
  model-cache:

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}-cuda
    extends:
      file: hwaccel.ml.yml
      service: cuda # set to one of [armnn, cuda, openvino, openvino-wsl] for accelerated inference - use the `-wsl` version for WSL2 where applicable
    volumes:
      - model-cache:/cache
    restart: always
    ports:
      - 3003:3003

volumes:
  model-cache:

3 Replies

Immich•5mo ago

:wave: Hey @GrafBunsenbrenner, Thanks for reaching out to us. Please carefully read this message and follow the recommended actions. This will help us be more effective in our support effort and leave more time for building Immich :immich:. References - Container Logs: docker compose logs docs - Container Status: docker ps -a docs - Reverse Proxy: https://immich.app/docs/administration/reverse-proxy - Code Formatting https://support.discord.com/hc/en-us/articles/210298617-Markdown-Text-101-Chat-Formatting-Bold-Italic-Underline#h_01GY0DAKGXDEHE263BCAYEGFJA Checklist I have... 1. :ballot_box_with_check: verified I'm on the latest release(note that mobile app releases may take some time). 2. :ballot_box_with_check: read applicable release notes. 3. :ballot_box_with_check: reviewed the FAQs for known issues. 4. :ballot_box_with_check: reviewed Github for known issues. 5. :ballot_box_with_check: tried accessing Immich via local ip (without a custom reverse proxy). 6. :ballot_box_with_check: uploaded the relevant information (see below). 7. :ballot_box_with_check: tried an incognito window, disabled extensions, cleared mobile app cache, logged out and back in, different browsers, etc. as applicable (an item can be marked as "complete" by reacting with the appropriate number) Information In order to be able to effectively help you, we need you to provide clear information to show what the problem is. The exact details needed vary per case, but here is a list of things to consider: - Your docker-compose.yml and .env files. - Logs from all the containers and their status (see above). - All the troubleshooting steps you've tried so far. - Any recent changes you've made to Immich or your system. - Details about your system (both software/OS and hardware). - Details about your storage (filesystems, type of disks, output of commands like fdisk -l and df -h). - The version of the Immich server, mobile app, and other relevant pieces. - Any other information that you think might be relevant. Please paste files and logs with proper code formatting, and especially avoid blurry screenshots. Without the right information we can't work out what the problem is. Help us help you ;) If this ticket can be closed you can use the /close command, and re-open it later if needed.

GrafBunsenbrennerOP•5mo ago

hwaccel.ml

# Configurations for hardware-accelerated machine learning

# If using Unraid or another platform that doesn't allow multiple Compose files,
# you can inline the config for a backend by copying its contents
# into the immich-machine-learning service in the docker-compose.yml file.

# See https://immich.app/docs/features/ml-hardware-acceleration for info on usage.

services:
  armnn:
    devices:
      - /dev/mali0:/dev/mali0
    volumes:
      - /lib/firmware/mali_csffw.bin:/lib/firmware/mali_csffw.bin:ro # Mali firmware for your chipset (not always required depending on the driver)
      - /usr/lib/libmali.so:/usr/lib/libmali.so:ro # Mali driver for your chipset (always required)

  cpu: {}

  cuda:
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities:
                - gpu

  openvino:
    device_cgroup_rules:
      - 'c 189:* rmw'
    devices:
      - /dev/dri:/dev/dri
    volumes:
      - /dev/bus/usb:/dev/bus/usb

  openvino-wsl:
    devices:
      - /dev/dri:/dev/dri
      - /dev/dxg:/dev/dxg
    volumes:
      - /dev/bus/usb:/dev/bus/usb
      - /usr/lib/wsl:/usr/lib/wsl

# Configurations for hardware-accelerated machine learning

# If using Unraid or another platform that doesn't allow multiple Compose files,
# you can inline the config for a backend by copying its contents
# into the immich-machine-learning service in the docker-compose.yml file.

# See https://immich.app/docs/features/ml-hardware-acceleration for info on usage.

services:
  armnn:
    devices:
      - /dev/mali0:/dev/mali0
    volumes:
      - /lib/firmware/mali_csffw.bin:/lib/firmware/mali_csffw.bin:ro # Mali firmware for your chipset (not always required depending on the driver)
      - /usr/lib/libmali.so:/usr/lib/libmali.so:ro # Mali driver for your chipset (always required)

  cpu: {}

  cuda:
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities:
                - gpu

  openvino:
    device_cgroup_rules:
      - 'c 189:* rmw'
    devices:
      - /dev/dri:/dev/dri
    volumes:
      - /dev/bus/usb:/dev/bus/usb

  openvino-wsl:
    devices:
      - /dev/dri:/dev/dri
      - /dev/dxg:/dev/dxg
    volumes:
      - /dev/bus/usb:/dev/bus/usb
      - /usr/lib/wsl:/usr/lib/wsl

But if I use docker run -it --gpus=all --rm nvcr.io/nvidia/k8s/cuda-sample:nbody nbody -benchmark I get

docker run -it --gpus=all --rm nvcr.io/nvidia/k8s/cuda-sample:nbody nbody -benchmark
Run "nbody -benchmark [-numbodies=<numBodies>]" to measure performance.
        -fullscreen       (run n-body simulation in fullscreen mode)
        -fp64             (use double precision floating point values for simulation)
        -hostmem          (stores simulation data in host memory)
        -benchmark        (run benchmark to measure performance)
        -numbodies=<N>    (number of bodies (>= 1) to run in simulation)
        -device=<d>       (where d=0,1,2.... for the CUDA device to use)
        -numdevices=<i>   (where i=(number of CUDA devices > 0) to use for simulation)
        -compare          (compares simulation results running once on the default GPU and once on the CPU)
        -cpu              (run n-body simulation on the CPU)
        -tipsy=<file.bin> (load a tipsy model file for simulation)

NOTE: The CUDA Samples are not meant for performance measurements. Results may vary when GPU Boost is enabled.

> Windowed mode
> Simulation data stored in video memory
> Single precision floating point simulation
> 1 Devices used for simulation
GPU Device 0: "Turing" with compute capability 7.5

> Compute 7.5 CUDA device: [NVIDIA GeForce GTX 1660]
22528 bodies, total time for 10 iterations: 32.610 ms
= 155.629 billion interactions per second
= 3112.589 single-precision GFLOP/s at 20 flops per interaction

docker run -it --gpus=all --rm nvcr.io/nvidia/k8s/cuda-sample:nbody nbody -benchmark
Run "nbody -benchmark [-numbodies=<numBodies>]" to measure performance.
        -fullscreen       (run n-body simulation in fullscreen mode)
        -fp64             (use double precision floating point values for simulation)
        -hostmem          (stores simulation data in host memory)
        -benchmark        (run benchmark to measure performance)
        -numbodies=<N>    (number of bodies (>= 1) to run in simulation)
        -device=<d>       (where d=0,1,2.... for the CUDA device to use)
        -numdevices=<i>   (where i=(number of CUDA devices > 0) to use for simulation)
        -compare          (compares simulation results running once on the default GPU and once on the CPU)
        -cpu              (run n-body simulation on the CPU)
        -tipsy=<file.bin> (load a tipsy model file for simulation)

NOTE: The CUDA Samples are not meant for performance measurements. Results may vary when GPU Boost is enabled.

> Windowed mode
> Simulation data stored in video memory
> Single precision floating point simulation
> 1 Devices used for simulation
GPU Device 0: "Turing" with compute capability 7.5

> Compute 7.5 CUDA device: [NVIDIA GeForce GTX 1660]
22528 bodies, total time for 10 iterations: 32.610 ms
= 155.629 billion interactions per second
= 3112.589 single-precision GFLOP/s at 20 flops per interaction

wich seems to suggest the GPU-passthrough does work for other containers, just not for immich remote ML.

Immich•5mo ago

Successfully submitted, a tag has been added to inform contributors. :white_check_mark:

Gaming

Programming

No GPU usage on remote ML with Windows 10 and Docker Desktop

Did you find this page helpful?