Bug: CUDA enabled docker container fails to launch

[mblunt]

What happened?

Docker container is missing a shared object, causing failures on launch.

Modify as needed, taken from docs:
docker run -p 8080:8080 -v /path/to/models:/models --gpus all ghcr.io/ggerganov/llama.cpp:server-cuda -m models/7B/ggml-model.gguf -c 512 --host 0.0.0.0 --port 8080 --n-gpu-layers 99

Name and Version

Version unknown, container will not launch.

What operating system are you seeing the problem on?

Ubuntu Server, amd64 architecture.

Relevant log output

/server: error while loading shared libraries: libcuda.so.1: cannot open shared object file: No such file or directory```

[slaren]

libcuda.so is part of the NVIDIA driver, this is likely caused by a configuration issue.

[wilksu]

-e LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/lib/wsl/lib
add the params,then it work

[toanju]

-e LD_LIBRARY_PATH=/usr/local/cuda/compat/ is setting the correct location