HW Acceleration with CUDA on NixOS

🚧Setup❓Question🗄️Server☑️Ready

I've been trying to get hardware acceleration working on my machine for a while, and I haven't been able to figure it out. I'm running immich using docker compose on a NixOS system with a GTX 1070.

For a while I thought there was something wrong with my nix config, but all these docker examples work fine on my machine: https://docs.docker.com/desktop/features/gpu/

However, the docker-compose files I am using are exactly the same as the ones provided in the documentation, so I'm unsure of what exactly my issue is.

The immich_machine_learning container has the following logs when I attempt to run an ml job:

[11/14/25 20:03:55] INFO     Starting gunicorn 23.0.0
[11/14/25 20:03:55] INFO     Listening at: http://[::]:3003 (3)
[11/14/25 20:03:55] INFO     Using worker: immich_ml.config.CustomUvicornWorker
[11/14/25 20:03:55] INFO     Booting worker with pid: 4
[11/14/25 20:03:56] INFO     generated new fontManager
[11/14/25 20:03:56] INFO     Started server process [4]
[11/14/25 20:03:56] INFO     Waiting for application startup.
[11/14/25 20:03:56] INFO     Created in-memory cache with unloading after 300s
                             of inactivity.
[11/14/25 20:03:56] INFO     Initialized request thread pool with 16 threads.
[11/14/25 20:03:56] INFO     Application startup complete.
[11/14/25 20:32:13] INFO     Loading visual model 'ViT-B-32__openai' to memory
[11/14/25 20:32:13] INFO     Setting execution providers to
                             ['CUDAExecutionProvider', 'CPUExecutionProvider'],
                             in descending order of preference
[11/14/25 20:32:20] ERROR    Worker (pid:4) was sent code 139!
[11/14/25 20:32:20] INFO     Booting worker with pid: 47
[11/14/25 20:32:21] INFO     Started server process [47]
... more code 139 errors below ...

[11/14/25 20:03:55] INFO     Starting gunicorn 23.0.0
[11/14/25 20:03:55] INFO     Listening at: http://[::]:3003 (3)
[11/14/25 20:03:55] INFO     Using worker: immich_ml.config.CustomUvicornWorker
[11/14/25 20:03:55] INFO     Booting worker with pid: 4
[11/14/25 20:03:56] INFO     generated new fontManager
[11/14/25 20:03:56] INFO     Started server process [4]
[11/14/25 20:03:56] INFO     Waiting for application startup.
[11/14/25 20:03:56] INFO     Created in-memory cache with unloading after 300s
                             of inactivity.
[11/14/25 20:03:56] INFO     Initialized request thread pool with 16 threads.
[11/14/25 20:03:56] INFO     Application startup complete.
[11/14/25 20:32:13] INFO     Loading visual model 'ViT-B-32__openai' to memory
[11/14/25 20:32:13] INFO     Setting execution providers to
                             ['CUDAExecutionProvider', 'CPUExecutionProvider'],
                             in descending order of preference
[11/14/25 20:32:20] ERROR    Worker (pid:4) was sent code 139!
[11/14/25 20:32:20] INFO     Booting worker with pid: 47
[11/14/25 20:32:21] INFO     Started server process [47]
... more code 139 errors below ...

Docker Documentation

GPU support

How to use GPU in Docker Desktop

Immich•3mo ago•

11 replies

124274sashimi

HW Acceleration with CUDA on NixOS

🚧Setup❓Question🗄️Server☑️Ready

[11/14/25 20:03:55] INFO     Starting gunicorn 23.0.0
[11/14/25 20:03:55] INFO     Listening at: http://[::]:3003 (3)
[11/14/25 20:03:55] INFO     Using worker: immich_ml.config.CustomUvicornWorker
[11/14/25 20:03:55] INFO     Booting worker with pid: 4
[11/14/25 20:03:56] INFO     generated new fontManager
[11/14/25 20:03:56] INFO     Started server process [4]
[11/14/25 20:03:56] INFO     Waiting for application startup.
[11/14/25 20:03:56] INFO     Created in-memory cache with unloading after 300s
                             of inactivity.
[11/14/25 20:03:56] INFO     Initialized request thread pool with 16 threads.
[11/14/25 20:03:56] INFO     Application startup complete.
[11/14/25 20:32:13] INFO     Loading visual model 'ViT-B-32__openai' to memory
[11/14/25 20:32:13] INFO     Setting execution providers to
                             ['CUDAExecutionProvider', 'CPUExecutionProvider'],
                             in descending order of preference
[11/14/25 20:32:20] ERROR    Worker (pid:4) was sent code 139!
[11/14/25 20:32:20] INFO     Booting worker with pid: 47
[11/14/25 20:32:21] INFO     Started server process [47]
... more code 139 errors below ...

[11/14/25 20:03:55] INFO     Starting gunicorn 23.0.0
[11/14/25 20:03:55] INFO     Listening at: http://[::]:3003 (3)
[11/14/25 20:03:55] INFO     Using worker: immich_ml.config.CustomUvicornWorker
[11/14/25 20:03:55] INFO     Booting worker with pid: 4
[11/14/25 20:03:56] INFO     generated new fontManager
[11/14/25 20:03:56] INFO     Started server process [4]
[11/14/25 20:03:56] INFO     Waiting for application startup.
[11/14/25 20:03:56] INFO     Created in-memory cache with unloading after 300s
                             of inactivity.
[11/14/25 20:03:56] INFO     Initialized request thread pool with 16 threads.
[11/14/25 20:03:56] INFO     Application startup complete.
[11/14/25 20:32:13] INFO     Loading visual model 'ViT-B-32__openai' to memory
[11/14/25 20:32:13] INFO     Setting execution providers to
                             ['CUDAExecutionProvider', 'CPUExecutionProvider'],
                             in descending order of preference
[11/14/25 20:32:20] ERROR    Worker (pid:4) was sent code 139!
[11/14/25 20:32:20] INFO     Booting worker with pid: 47
[11/14/25 20:32:21] INFO     Started server process [47]
... more code 139 errors below ...

Docker Documentation

GPU support

How to use GPU in Docker Desktop

HW Acceleration with CUDA on NixOS

HW Acceleration with CUDA on NixOS

Similar Threads

Similar Threads

Similar Threads