-
-
Notifications
You must be signed in to change notification settings - Fork 4.3k
Open
Description
I have searched the existing issues, both open and closed, to make sure this is not a duplicate report.
- Yes
The bug
I updated my Nvidia drivers today and now my Immich ML console log is filled with the following error:
2025-10-12 17:48:07.182877091 [E:onnxruntime:Default, cuda_call.cc:118 CudaCall] CUDA failure 35: CUDA driver version is insufficient for CUDA runtime version ; GPU=-1 ; hostname=309636a2e4d3 ; file=/onnxruntime_src/onnxruntime/core/providers/cuda/cuda_execution_provider_info.cc ; line=66 ; expr=cudaGetDeviceCount(&num_devices);
The OS that Immich Server is running on
Ubuntu 25.04 (ML is on Windows 11)
Version of Immich Server
2.0.1
Version of Immich Mobile App
2.0.1
Platform with the issue
- Server
- Web
- Mobile
Device make and model
No response
Your docker-compose.yml content
name: immich_remote_ml
services:
immich-machine-learning:
container_name: immich_machine_learning
# Note the `-cuda` at the end
image: ghcr.io/immich-app/immich-machine-learning:${IMMICH_VERSION:-release}-cuda
# Note the lack of an `extends` section
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: 1
capabilities:
- gpu
volumes:
#- "C:\Code\Immich-ML\cache:/cache"
# ...
- type: bind
source: ./cache
target: /cache
restart: always
ports:
- 3003:3003
Your .env content
n/a
Reproduction steps
- Upload images to Immich
- See error in ML console
Relevant log output
2025-10-12 17:48:07.182877091 [E:onnxruntime:Default, cuda_call.cc:118 CudaCall] CUDA failure 35: CUDA driver version is insufficient for CUDA runtime version ; GPU=-1 ; hostname=309636a2e4d3 ; file=/onnxruntime_src/onnxruntime/core/providers/cuda/cuda_execution_provider_info.cc ; line=66 ; expr=cudaGetDeviceCount(&num_devices);
Additional information
No response
Metadata
Metadata
Assignees
Labels
No labels
Type
Projects
Status
To triage