Cannot install any backend: operation not supported

[JPVenson]

LocalAI version:
LocalAI v4.7.1 (b224c96)

Environment, CPU architecture, OS, and Version:
docker install CUDA 12 version
localai/localai:latest-gpu-nvidia-cuda-12

services:
  local-ai:
    container_name: local-ai
    hostname: local-ai
    restart: unless-stopped
    image: localai/localai:latest-gpu-nvidia-cuda-12
    user: 1000:1000
    networks:
      - ReverseProxyNetwork
    environment:
      - MODELS_PATH=/models
    volumes:
      - localai-models:/models:cached
      - localai-backends:/backends:Z
      - ../../data/localAi/images/:/tmp/generated/images/
    deploy:
      resources:
        limits:
          memory: 12GB
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [gpu] 
networks:
  ReverseProxyNetwork:
    external: true
    name: "ReverseProxyNetwork"

volumes:
  localai-models:
    driver: local
    driver_opts:
      type: cifs
      device: //xxx/sharedExtern/StableDiffusion/localAi/models/
      o: "username=${},password=${},uid=1000,gid=1000,iocharset=utf8,vers=3.1.1,file_mode=0755,dir_mode=0755"
  localai-backends:
    driver: local
    driver_opts:
      type: cifs
      device: //xxx/sharedExtern/StableDiffusion/localAi/backends/
      o: "username=${},password=${},uid=1000,gid=1000,iocharset=utf8,vers=3.1.1,file_mode=0755,dir_mode=0755"

Describe the bug
Whenever i try to install any backend, be it directly though the store or indirectly though the store with a model i get the same error. The models get downloaded just fine, just the backend install seems to fail. The backeend folder is empty after the error.

To Reproduce

Expected behavior

Logs

local-ai  | Jul 17 16:47:48 INFO  Fallback URI failed fallback="quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-llama-cpp" error=failed to extract image tar: symlink libcublas.so.12.8.5.5 /backends/cuda12-llama-cpp.install-tmp/lib/libcublas.so: operation not supported 
local-ai  | Jul 17 16:47:48 INFO  Trying development fallback URI fallback="quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-llama-cpp-development" 
local-ai  | Jul 17 16:47:48 INFO  Development fallback URI failed fallback="quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-llama-cpp-development" error=failed to get image "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-llama-cpp-development": GET https://quay.io/v2/go-skynet/local-ai-backends/manifests/master-gpu-nvidia-cuda-12-llama-cpp-development: MANIFEST_UNKNOWN: manifest unknown; map[] 
local-ai  | Jul 17 16:47:48 ERROR Failed to download backend uri="quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-llama-cpp" backendPath="/backends/cuda12-llama-cpp.install-tmp" error=failed to extract image tar: symlink libcublas.so.12.8.5.5 /backends/cuda12-llama-cpp.install-tmp/lib/libcublas.so: operation not supported 

Additional context