Decrement CUDA version and bump Ubuntu

Signed-off-by: Marcel Coetzee <marcel@mooncoon.com>

Author: Marcel Coetzee

Dockerfile.cuda

@@ -1,4 +1,4 @@
-FROM nvidia/cuda:12.1.1-devel-ubuntu20.04
+FROM nvidia/cuda:12.0.1-devel-ubuntu22.04
 
 # We need to set the host to 0.0.0.0 to allow outside access
 ENV HOST 0.0.0.0
@@ -12,4 +12,4 @@ RUN python3 -m pip install --upgrade pip pytest cmake scikit-build setuptools fa
 RUN LLAMA_CUBLAS=1 python3 setup.py develop
 
 # Run the server
-CMD python3 -m llama_cpp.server
+CMD python3 -m llama_cpp.server