From 4b7f8514287ead84338beb0a624d22efe8a26bf4 Mon Sep 17 00:00:00 2001 From: Joren Guillaume Date: Fri, 17 Oct 2025 15:05:07 +0200 Subject: [PATCH] docs: Expand on OpenVINO WSL HW accel (#21054) * add group/render section to openvino-wsl hwaccel * Fix indentation for YAML * Remove obsolete enter * chore: formatting --------- Co-authored-by: Jason Rasmussen --- docs/docs/features/ml-hardware-acceleration.md | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/docs/docs/features/ml-hardware-acceleration.md b/docs/docs/features/ml-hardware-acceleration.md index 7f92c25449..685f23932c 100644 --- a/docs/docs/features/ml-hardware-acceleration.md +++ b/docs/docs/features/ml-hardware-acceleration.md @@ -57,6 +57,22 @@ You do not need to redo any machine learning jobs after enabling hardware accele - Ensure the server's kernel version is new enough to use the device for hardware acceleration. - Expect higher RAM usage when using OpenVINO compared to CPU processing. +#### OpenVINO-WSL + +- Ensure your container can access the /dev/dri directory, you can verify this by doing `docker exec -t immich_machine_learning ls -la /dev/dri`. If this is not the case execute `getent group render` and `getent group video` on the WSL host, then add those groups to hwaccel.ml.yaml + ```yaml + openvino-wsl: + devices: + - /dev/dri:/dev/dri + - /dev/dxg:/dev/dxg + volumes: + - /dev/bus/usb:/dev/bus/usb + - /usr/lib/wsl:/usr/lib/wsl + group_add: + - 44 # Replace this number with the number you found with getent group video + - 992 # Replace this number with the number you found with getent group render + ``` + #### RKNN - You must have a supported Rockchip SoC: only RK3566, RK3568, RK3576 and RK3588 are supported at this moment.