Replies: 2 comments 15 replies
-
|
I'm also facing the same issue, it seems like docker with It seems to be a docker issue. Simple Reproduction of not working services:
test:
image: nvidia/cuda:12.3.1-base-ubuntu20.04
command: nvidia-smi
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: 1
capabilities: [compute, video, gpu]$ docker compose up
[+] Running 1/1
✔ Container gpu-test-test-1 Recreated 0.1s
Attaching to test-1
Error response from daemon: failed to create task for container: failed to create shim task: OCI runtime create failed: runc create failed: unable to start container process: exec: "nvidia-smi": executable file not found in $PATH: unknownAnd a working services:
test:
image: nvidia/cuda:12.3.1-base-ubuntu20.04
command: nvidia-smi
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: 1
capabilities: [gpu]$ docker compose up
[+] Running 1/1
✔ Container gpu-test-test-1 Recreated 0.1s
Attaching to test-1
test-1 | Wed Feb 21 16:47:11 2024
test-1 | +---------------------------------------------------------------------------------------+
test-1 | | NVIDIA-SMI 545.29.06 Driver Version: 545.29.06 CUDA Version: 12.3 |
test-1 | |-----------------------------------------+----------------------+----------------------+
test-1 | | GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
test-1 | | Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
test-1 | | | | MIG M. |
test-1 | |=========================================+======================+======================|
test-1 | | 0 NVIDIA GeForce GTX 950M Off | 00000000:01:00.0 Off | N/A |
test-1 | | N/A 55C P8 N/A / 200W | 76MiB / 4096MiB | 0% Default |
test-1 | | | | N/A |
test-1 | +-----------------------------------------+----------------------+----------------------+
test-1 |
test-1 | +---------------------------------------------------------------------------------------+
test-1 | | Processes: |
test-1 | | GPU GI CI PID Type Process name GPU Memory |
test-1 | | ID ID Usage |
test-1 | |=======================================================================================|
test-1 | +---------------------------------------------------------------------------------------+
test-1 exited with code 0 |
Beta Was this translation helpful? Give feedback.
5 replies
-
|
Sorry, on further inspection, it seems like regardless, |
Beta Was this translation helpful? Give feedback.
-
|
For me running Host CUDA version: 12.4 |
Beta Was this translation helpful? Give feedback.
-
|
I'm experiencing the same issue, also on a docker setup. I pass my nvidia GPU to many other containers without an issue. Also have no issue with HW transcoding on the microservers container using the same EDIT: Fixed it (mostly) It wasn't clear from documentation but the machine learning image needs to use a vendor specific tag, unlike the other images, and this is what I was missing. Changing
resolved Available Providers missing my gpu as a provider. I haven't verified the |
Beta Was this translation helpful? Give feedback.
-
|
Can confirm @tastelessjolt statement. immich-server:
container_name: immich_server
image: ghcr.io/immich-app/immich-server:${IMMICH_VERSION:-release}
restart: unless-stopped
networks:
- immich
- proxy
ports:
- 2283:3001
command: ['start.sh', 'immich']
volumes:
- ${UPLOAD_LOCATION}:/usr/src/app/upload
- /etc/localtime:/etc/localtime:ro
- $PICTURES:/mnt/media/:ro
env_file:
- .env
depends_on:
- immich_redis
- immich_postgres
labels:
traefik.enable: true
traefik.http.routers.immich.rule: Host(`immich.$DOMAINNAME`)
traefik.http.services.immich.loadbalancer.server.port: 3001
traefik.http.routers.immich.entryPoints: https
immich-microservices:
container_name: immich_microservices
image: ghcr.io/immich-app/immich-server:${IMMICH_VERSION:-release}
restart: unless-stopped
networks:
- immich
command: ['start.sh', 'microservices']
volumes:
- ${UPLOAD_LOCATION}:/usr/src/app/upload
- /etc/localtime:/etc/localtime:ro
- $PICTURES:/mnt/media/:ro
env_file:
- .env
environment:
- NVIDIA_VISIBLE_DEVICES=all
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: 1
capabilities:
- gpu
#- compute
#- video
depends_on:
- immich_redis
- immich_postgres
immich-machine-learning:
container_name: immich_machine_learning
image: ghcr.io/immich-app/immich-machine-learning:${IMMICH_VERSION:-release}-cuda
restart: unless-stopped
networks:
- immich
volumes:
- model-cache:/cache
env_file:
- .env
environment:
- NVIDIA_VISIBLE_DEVICES=all
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: 1
capabilities:
- gpu
#- compute
#- video
immich_redis:
container_name: immich_redis
image: registry.hub.docker.com/library/redis:alpine
networks:
- immich
restart: unless-stopped
immich_postgres:
container_name: immich_postgres
image: registry.hub.docker.com/tensorchord/pgvecto-rs:pg14-v0.2.0
networks:
- immich
environment:
POSTGRES_PASSWORD: ${DB_PASSWORD}
POSTGRES_USER: ${DB_USERNAME}
POSTGRES_DB: ${DB_DATABASE_NAME}
volumes:
- $DOCKERDIR/immich/pgdata:/var/lib/postgresql/data
restart: unless-stoppedResult of python commandroot@Galax:~# docker exec -it immich_machine_learning python -c "import onnxruntime as ort;print(ort.get_device())"
GPU
root@Galax:~#
|
Beta Was this translation helpful? Give feedback.
-
|
Can confirm here as well. My GTX 1080 was recognized in the container after removing The test with the |
Beta Was this translation helpful? Give feedback.
-
name: immich
services:
immich-server:
container_name: immich_server
image: ghcr.io/immich-app/immich-server:${IMMICH_VERSION:-release}
command: [ "start.sh", "immich" ]
volumes:
- ${UPLOAD_LOCATION}:/usr/src/app/upload
- ${EXTERNAL_LOCATION}:/mnt/catImages:ro
- /etc/localtime:/etc/localtime:ro
env_file:
- .env
ports:
- 2283:3001
depends_on:
- redis
- database
restart: always
labels:
- "com.centurylinklabs.watchtower.enable=false"
immich-microservices:
container_name: immich_microservices
image: ghcr.io/immich-app/immich-server:${IMMICH_VERSION:-release}
# extends: # uncomment this section for hardware acceleration - see https://immich.app/docs/features/hardware-transcoding
# file: hwaccel.transcoding.yml
# service: cpu # set to one of [nvenc, quicksync, rkmpp, vaapi, vaapi-wsl] for accelerated transcoding
command: [ "start.sh", "microservices" ]
volumes:
- ${UPLOAD_LOCATION}:/usr/src/app/upload
- ${EXTERNAL_LOCATION}:/mnt/catImages:ro
- /etc/localtime:/etc/localtime:ro
env_file:
- .env
runtime: nvidia
# devices:
# - /dev/dri:/dev/dri
depends_on:
- redis
- database
restart: always
environment:
- NVIDIA_VISIBLE_DEVICES=all
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: 1
capabilities:
- gpu
- compute
- video
labels:
- "com.centurylinklabs.watchtower.enable=false"
immich-machine-learning:
container_name: immich_machine_learning
# For hardware acceleration, add one of -[armnn, cuda, openvino] to the image tag.
# Example tag: ${IMMICH_VERSION:-release}-cuda
image: ghcr.io/immich-app/immich-machine-learning:${IMMICH_VERSION:-release}-cuda
# extends: # uncomment this section for hardware acceleration - see https://immich.app/docs/features/ml-hardware-acceleration
# file: hwaccel.ml.yml
# service: cuda # set to one of [armnn, cuda, openvino, openvino-wsl] for accelerated inference - use the `-wsl` version for WSL2 where applicable
volumes:
- model-cache:/cache
env_file:
- .env
restart: always
labels:
- "com.centurylinklabs.watchtower.enable=false"
environment:
- NVIDIA_VISIBLE_DEVICES=all
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: 1
capabilities:
- gpu
- compute
- video
redis:
container_name: immich_redis
image: redis:6.2-alpine@sha256:afb290a0a0d0b2bd7537b62ebff1eb84d045c757c1c31ca2ca48c79536c0de82
restart: always
labels:
- "com.centurylinklabs.watchtower.enable=false"
volumes:
- redis-data:/data
database:
container_name: immich_postgres
image: tensorchord/pgvecto-rs:pg14-v0.2.0@sha256:90724186f0a3517cf6914295b5ab410db9ce23190a2d9d0b9dd6463e3fa298f0
env_file:
- .env
environment:
POSTGRES_PASSWORD: ${DB_PASSWORD}
POSTGRES_USER: ${DB_USERNAME}
POSTGRES_DB: ${DB_DATABASE_NAME}
volumes:
- pgdata:/var/lib/postgresql/data
restart: always
labels:
- "com.centurylinklabs.watchtower.enable=false"
volumes:
pgdata:
model-cache:
redis-data:Any suggestion? Thanks! |
Beta Was this translation helpful? Give feedback.
10 replies
-
|
im facing the same issue, which version did you rollback to? |
Beta Was this translation helpful? Give feedback.
-
|
@Quenom 552.44 WHQL |
Beta Was this translation helpful? Give feedback.
-
|
I have the same issue, thanks for the information... maybe the massive upgrade from 552.xx to 555.xx made it a bug for developers. |
Beta Was this translation helpful? Give feedback.
-
Are you suggesting to use a non-stable driver? |
Beta Was this translation helpful? Give feedback.
-
|
In windows I suggest to use only WHQL version (Windows Hardware Quality Labs testing) on linux, i don't know. Only i know, that the version it's a key for probleb . |
Beta Was this translation helpful? Give feedback.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
The bug
Immich cannot work with a video card. I completed all the requirements according to the instructions but still ran into a problem.
NVIDIA-SMI 535.154.05
Driver Version: 535.154.05
CUDA Version: 12.2
nvcc --version
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2021 NVIDIA Corporation
Built on Thu_Nov_18_09:45:30_PST_2021
Cuda compilation tools, release 11.5, V11.5.119
Build cuda_11.5.r11.5/compiler.30672275_0
nvidia-container-toolkit --version
NVIDIA Container Runtime Hook version 1.14.5
commit: 9ea336070134e612145d342e495f2fc616aab063
ML container logs.txt
microservices logs.txt
server logs.txt
The OS that Immich Server is running on
Ubuntu 22.04.4 LTS (GNU/Linux 5.15.0-94-generic x86_64)
Version of Immich Server
1.94.1
Version of Immich Mobile App
1.94.1
Platform with the issue
Your docker-compose.yml content
Your .env content
Reproduction steps
Additional information
No response
Beta Was this translation helpful? Give feedback.
All reactions