Merge branch 'main' of github.com:abetlen/llama_cpp_python into main

Author: abetlen

Dockerfile.cuda

@@ -1,4 +1,5 @@
-FROM nvidia/cuda:12.1.1-devel-ubuntu20.04
+ARG CUDA_VERSION=12.1.1
+FROM nvidia/cuda:${CUDA_VERSION}-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 +13,4 @@ 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