Immich•3w ago

Issue with nvidia card configuration

Hello everyone !

So, i have an issue

Here my config
Proxmox ( i7 3770 / 32gb ddr3 / K620 2gb )

VM ( immich/jellyfin )
4 Vcpu / 8gb / GPU passtrough

NVIDIA-SMI 535.274.02 Driver Version: 535.274.02 CUDA Version: 12.2
( it work well for transcoding with jellyfin )

(In logs of immich machine learning i got this )
Fail: [ONNXRuntimeError] : 1 : FAIL : Non-zero

status code returned while running Add node.

Name:'Add_10' Status Message: CUDA error

cudaErrorNoKernelImageForDevice:no kernel image is

available for execution on the device

2025-12-10 22:48:02.284896960 [E:onnxruntime:, sequential_executor.cc:516 ExecuteKernel] Non-zero status code returned while running Add node. Name:'Add_10' Status Message: CUDA error cudaErrorNoKernelImageForDevice:no kernel image is available for execution on the device

Thanks you a lot

Immich•12/10/25, 11:16 PM

:wave: Hey @Thethys,

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
```
```
docker compose logs
```
docs
Container Status:
```
docker ps -a
```
```
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

Immich•12/10/25, 11:16 PM

Checklist

I have...

:ballot_box_with_check: verified I'm on the latest release(note that mobile app releases may take some time).
:ballot_box_with_check: read applicable release notes.
:ballot_box_with_check: reviewed the FAQs for known issues.
:ballot_box_with_check: reviewed Github for known issues.
:ballot_box_with_check: tried accessing Immich via local ip (without a custom reverse proxy).
:ballot_box_with_check: uploaded the relevant information (see below).
: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
```
```
fdisk -l
```
and
```
df -h
```
```
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

/close

command, and re-open it later if needed.

ThethysOP•12/10/25, 11:16 PM

name: immich

services:
immich-server:
container_name: immich_server
image: ghcr.io/immich-app/immich-server:v2

environment:

IMMICH_VERSION=v2
NODE_ENV=production
DB_USERNAME=postgres
DB_PASSWORD=28kwBvG5Q2
DB_DATABASE_NAME=immich
DB_HOSTNAME=immich_postgres
REDIS_HOSTNAME=immich_redis
UPLOAD_LOCATION=/usr/src/app/upload
Configuration GPU (K620)
NVIDIA_VISIBLE_DEVICES=all
NVIDIA_DRIVER_CAPABILITIES=compute,video,utilityvolumes:
/data/compose/5/library:/usr/src/app/upload
/etc/localtime:/etc/localtime:ro
ports:
2283:2283
depends_on:
immich-redis
immich-postgres
restart: always
deploy:
resources:
reservations:
devices:
- driver: nvidia
  count: 1
  capabilities: [gpu, video, utility]

ThethysOP•12/10/25, 11:16 PM

immich-machine-learning:
container_name: immich_machine_learning

image: ghcr.io/immich-app/immich-machine-learning:v2-cuda

environment:

IMMICH_VERSION=v2
DB_USERNAME=postgres
DB_PASSWORD=28kwBvG5Q2
DB_DATABASE_NAME=immich
DB_HOSTNAME=immich_postgres
TRANSFORMERS_CACHE=/cache
Configuration GPU
NVIDIA_VISIBLE_DEVICES=all
NVIDIA_DRIVER_CAPABILITIES=compute,utility
volumes:
immich_model-cache:/cacherestart: alwaysdeploy:resources:reservations: devices:
- driver: nvidia
  count: 1
  capabilities: [gpu, compute, utility]
immich-redis:container_name: immich_redisimage: docker.io/valkey/valkey:8restart: alwaysvolumes:
95dd1d62beed79f75c53472683bb2781c716976485e20da616b8067e84236b41:/datahealthcheck:test: ["CMD-SHELL", "valkey-cli ping | grep PONG"]interval: 5stimeout: 5sretries: 5immich-postgres:container_name: immich_postgresimage: ghcr.io/immich-app/postgres:14-vectorchord0.4.3-pgvectors0.2.0environment:
POSTGRES_PASSWORD=28kwBvG5Q2
POSTGRES_USER=postgres
POSTGRES_DB=immich
POSTGRES_INITDB_ARGS=--data-checksums
DB_STORAGE_TYPE=SSDvolumes:
/data/compose/5/postgres:/var/lib/postgresql/datarestart: always

volumes:
immich_model-cache:
external: true
95dd1d62beed79f75c53472683bb2781c716976485e20da616b8067e84236b41:
external: true

networks:
default:
name: immich_default
external: true

ThethysOP•12/10/25, 11:18 PM

Im also here at the advice of Alex
Im also a contributor of immich project

Thanks yall again

bo0tzz•12/10/25, 11:19 PM

That gpu is too old

bo0tzz•12/10/25, 11:19 PM

See the requirements in https://docs.immich.app/features/ml-hardware-acceleration

ThethysOP•12/10/25, 11:27 PM

My bad, my dumb brain think it was more recent then that, i will use my Vcpu until i change my whole setup i think, sorry flr bothering you

Also, thanks a lot for your works guys, y’all are amazing

Issue with nvidia card configuration

References

Checklist

Information

Configuration GPU (K620)

Configuration GPU

Similar Threads

Similar Threads

References

Checklist

Information

Configuration GPU (K620)

Configuration GPU

Similar Threads