Nvidia container cli error

[MBoutray]

Nvidia container cli error

[kropochev]

I have a similar problem:
docker compose --profile auto up --build
[+] Building 6.2s (26/26) FINISHED docker:desktop-linux
=> [auto internal] load build definition from Dockerfile 0.0s
=> => transferring dockerfile: 2.70kB 0.0s
=> [auto internal] load .dockerignore 0.0s
=> => transferring context: 2B 0.0s
=> [auto internal] load metadata for docker.io/pytorch/pytorch:2.1.0-cuda12.1-cudnn8-runtime 5.9s
=> [auto internal] load metadata for docker.io/alpine/git:2.36.2 5.8s
=> [auto auth] pytorch/pytorch:pull token for registry-1.docker.io 0.0s
=> [auto auth] alpine/git:pull token for registry-1.docker.io 0.0s
=> [auto internal] load build context 0.0s
=> => transferring context: 122B 0.0s
=> [auto stage-1 1/11] FROM docker.io/pytorch/pytorch:2.1.0-cuda12.1-cudnn8-runtime@sha256:e4aaefef0c9631875916 0.0s
=> [auto download 1/8] FROM docker.io/alpine/git:2.36.2@sha256:ec491c893597b68c92b88023827faa771772cfd5e106b76c7 0.0s
=> CACHED [auto stage-1 2/11] RUN --mount=type=cache,target=/var/cache/apt apt-get update && apt-get instal 0.0s
=> CACHED [auto stage-1 3/11] RUN --mount=type=cache,target=/root/.cache/pip git clone https://github.com/AUT 0.0s
=> CACHED [auto download 2/8] COPY clone.sh /clone.sh 0.0s
=> CACHED [auto download 3/8] RUN . /clone.sh stable-diffusion-stability-ai https://github.com/Stability-AI/stab 0.0s
=> CACHED [auto download 4/8] RUN . /clone.sh CodeFormer https://github.com/sczhou/CodeFormer.git c5b4593074ba62 0.0s
=> CACHED [auto download 5/8] RUN . /clone.sh BLIP https://github.com/salesforce/BLIP.git 48211a1594f1321b00f14c 0.0s
=> CACHED [auto download 6/8] RUN . /clone.sh k-diffusion https://github.com/crowsonkb/k-diffusion.git ab527a9a6 0.0s
=> CACHED [auto download 7/8] RUN . /clone.sh clip-interrogator https://github.com/pharmapsychotic/clip-interrog 0.0s
=> CACHED [auto download 8/8] RUN . /clone.sh generative-models https://github.com/Stability-AI/generative-model 0.0s
=> CACHED [auto stage-1 4/11] COPY --from=download /repositories/ /stable-diffusion-webui/repositories/ 0.0s
=> CACHED [auto stage-1 5/11] RUN mkdir /stable-diffusion-webui/interrogate && cp /stable-diffusion-webui/repos 0.0s
=> CACHED [auto stage-1 6/11] RUN --mount=type=cache,target=/root/.cache/pip pip install -r /stable-diffusion 0.0s
=> CACHED [auto stage-1 7/11] RUN --mount=type=cache,target=/root/.cache/pip pip install pyngrok xformers g 0.0s
=> CACHED [auto stage-1 8/11] COPY . /docker 0.0s
=> CACHED [auto stage-1 9/11] RUN sed -i 's/in_app_dir = .*/in_app_dir = True/g' /opt/conda/lib/python3.10/si 0.0s
=> CACHED [auto stage-1 10/11] WORKDIR /stable-diffusion-webui 0.0s
=> [auto] exporting to image 0.0s
=> => exporting layers 0.0s
=> => writing image sha256:538d71b70724f204623d7c4061cdb14ca3749a73ddf9e14b9ffd3153b48ea970 0.0s
=> => naming to docker.io/library/sd-auto:68 0.0s
Attaching to webui-docker-auto-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: error during container init: error running hook #0: error running hook: exit status 1, stdout: , stderr: Auto-detected mode as 'legacy'
nvidia-container-cli: initialization error: load library failed: libnvidia-ml.so.1: cannot open shared object file: no such file or directory: unknown

Which UI
auto and invoke

Hardware / Software

• OS: Linux 6.5.0-13-generic Ubuntu 23.10
• Docker version 24.0.7, build afdd53b
• Docker Compose version v2.23.0-desktop.1
• Repo version: 3e67f55
• RAM: 64Gb
• GPU/VRAM: RTX 4080 16Gb

Steps to Reproduce
execute commands docker compose --profile auto up --build or docker compose --profile invoke up --build

[kropochev]

If commented deploy section in docker-compose.yml file

version: '3.9'

x-base_service: &base_service
    ports:
      - "${WEBUI_PORT:-7860}:7860"
    volumes:
      - &v1 ./data:/data
      - &v2 ./output:/output
    stop_signal: SIGKILL
    tty: true
  #  deploy:
  #    resources:
  #      reservations:
  #        devices:
  #            - driver: nvidia
  #              device_ids: ['0']
  #              capabilities: [compute, utility]

and execute docker compose --profile auto-cpu up --build then worked.