|
Hi, trying to get ML using hardware acceleration working with OpenVino and ARC A380, but I get I can get hardware transcoding working in Immich and Full compose file here. immich-machine-learning:
container_name: immich_machine_learning
image: ghcr.io/immich-app/immich-machine-learning:release-openvino
restart: unless-stopped
user: root
# https://docs.immich.app/features/ml-hardware-acceleration
# https://github.com/immich-app/immich/releases/latest/download/hwaccel.ml.yml
device_cgroup_rules: # Why
- "c 189:* rmw"
# cat /etc/group | grep -e render -e video
# stat -c \"%g\" /dev/dri/render*
group_add: # Running as root, should not be needed, but saw this being added in troubleshooting steps
- 44
- 104
devices:
- /dev/dri:/dev/dri
environment:
- TZ=${TZ}
- IMMICH_LOG_LEVEL=debug
networks:
stack_network:
volumes:
- model-cache:/cache
- /dev/bus/usb:/dev/bus/usb # Why?
healthcheck:
disable: falseOS is Proxmox 8 running Docker 29 directly on host OS. $ ls -l /dev/dri
total 0
drwxr-xr-x 2 root root 100 Nov 2 07:38 by-path
crw-rw---- 1 root video 226, 0 Nov 2 07:38 card0
crw-rw---- 1 root video 226, 1 Nov 2 07:38 card1
crw-rw---- 1 root render 226, 128 Nov 2 07:38 renderD128$ uname -r
6.8.12-16-pve$ docker --version
Docker version 29.0.3, build 511dad6$ lspci -nn | grep -Ei "3d|display|vga"
43:00.0 VGA compatible controller [0300]: Intel Corporation DG2 [Arc A380] [8086:56a5] (rev 05)
c6:00.0 VGA compatible controller [0300]: ASPEED Technology, Inc. ASPEED Graphics Family [1a03:2000] (rev 52)Any help troubleshooting appreciated. |
Answered by
ptr727
Dec 2, 2025
Replies: 1 comment 1 reply
|
I tried the latest OpenVINO docker toolkit directly and it also does not detect the GPU. |
1 reply
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
I updated from kernel 6.8 to 6.17 and now it is working.
Available OpenVINO devices: ['CPU', 'GPU']There must be some minimum kernel version required for this to work?