Anyone having issues with ROCM or VULKAN?

[NexGen-3D-Printing]

Not sure if this is a known issue but I can seem to get anything to hit the GPU, I have 7900 GRE and ROCM is installed properly but no matter how small the model, they will always load into system ram.

I tried the following:

docker run -ti --name local-ai -p 8080:8080 --device=/dev/kfd --device=/dev/dri --group-add=video localai/localai:latest-gpu-hipblas
docker run -ti --name local-ai -p 8080:8080 localai/localai:latest-gpu-vulkan

Both of these fail to even detect a GPU, they only detect the CPU

and this one:

docker run -ti --name local-ai -p 8080:8080 --device=/dev/kfd --device=/dev/dri --group-add=video localai/localai:latest-aio-gpu-hipblas

It does detect the GPU and is detected as AMD, but it doesnt know what type.

under rocminfo in the cli everything is correct, I have gfx1100 and gxf1036

Trying to run anything under the AIO will always result in: localai failed to load model with internal loader: could not load model: rpc error: code = Unavailable desc = error reading from server: EOF

Running LocalAI works perfectly fine under CPU only, but I cant seem to get it to hit the GPU at all, not sure if I'm doing somthing wrong here, or if I'm missing something.