[AIO] WSL detection for NVIDIA VRAM size is not working

[enricoros]

LocalAI version:

quay.io/go-skynet/local-ai:master-aio-gpu-nvidia-cuda-12

Environment, CPU architecture, OS, and Version:

WSL2, Linux 75be0c1341b1 5.15.146.1-microsoft-standard-WSL2 #1 SMP Thu Jan 11 04:09:03 UTC 2024 x86_64 x86_64 x86_64 GNU/Linux

Describe the bug

The AIO entrypoint says:

Non-NVIDIA GPU detected. GPU memory size detection for non-NVIDIA GPUs is not supported in this script.
despite the GPU being an NVIDIA

To Reproduce

docker run --rm -ti --gpus all quay.io/go-skynet/local-ai:master-aio-gpu-nvidia-cuda-12

Expected behavior

NVIDIA GPU detected. Attempting to find memory size...
Total GPU Memory: 24576 MiB

Additional context

• PR incoming