Update Dockerfile

Dockerfile

@@ -1,15 +1,28 @@
+# Base image
 FROM nvidia/cuda:12.2.0-devel-ubuntu22.04
 
 ENV DEBIAN_FRONTEND=noninteractive
 
-# Install dependencies
+# Update and install necessary dependencies
 RUN apt update && \
-    apt install --no-install-recommends -y build-essential python3 python3-pip wget curl git cmake zlib1g-dev libblas-dev && \
-    apt clean && rm -rf /var/lib/apt/lists/*
-
-RUN wget -qO- "https://cmake.org/files/v3.18/cmake-3.18.0-Linux-x86_64.tar.gz" | tar --strip-components=1 -xz -C /usr/local
-
-ENV PATH="/usr/local/cuda/bin:$PATH"
+    apt install --no-install-recommends -y \
+        build-essential \
+        python3 \
+        python3-pip \
+        wget \
+        curl \
+        git \
+        cmake \
+        zlib1g-dev \
+        libblas-dev \
+        cuda-toolkit-12-2 && \
+    apt clean && \
+    rm -rf /var/lib/apt/lists/*
+
+# Setting up CUDA environment variables (this may not be necessary since you're using the official nvidia/cuda image, but it's good to be explicit)
+ENV PATH="/usr/local/cuda/bin:$PATH" \
+    LD_LIBRARY_PATH="/usr/local/cuda/lib64:$LD_LIBRARY_PATH" \
+    CUDA_HOME="/usr/local/cuda"
 
 WORKDIR /app
 
@@ -41,7 +54,5 @@ WORKDIR $HOME/app
 # Expose the port
 EXPOSE 8080
 
-RUN ls -al
-
 # Start the llava-server with models
-CMD ["/app/llava-cpp-server/bin/llava-server", "-m", "ggml-model-q4_k.gguf", "--mmproj", "mmproj-model-f16.gguf", "--host", "0.0.0.0"]
+CMD ["/app/llava-cpp-server/bin/llava-server", "-m", "ggml-model-q4_k.gguf", "--mmproj", "mmproj-model-f16.gguf", "--host", "0.0.0.0"]