use nvcr.io/nvidia/tritonserver:24.04-py3-min as base image (#3457)

docker/Dockerfile

-ARG CUDA_VERSION=12.1.1
-FROM nvidia/cuda:${CUDA_VERSION}-devel-ubuntu20.04
+ARG CUDA_VERSION=12.5.1
+
+FROM nvcr.io/nvidia/tritonserver:24.04-py3-min
+
 ARG BUILD_TYPE=all
 ENV DEBIAN_FRONTEND=noninteractive
 
@@ -9,7 +11,7 @@ RUN echo 'tzdata tzdata/Areas select America' | debconf-set-selections \
     && apt install software-properties-common -y \
     && add-apt-repository ppa:deadsnakes/ppa -y && apt update \
     && apt install python3.10 python3.10-dev -y \
-    && update-alternatives --install /usr/bin/python3 python3 /usr/bin/python3.8 1 && update-alternatives --install /usr/bin/python3 python3 /usr/bin/python3.10 2 \
+    && update-alternatives --install /usr/bin/python3 python3 /usr/bin/python3.10 1 \
     && update-alternatives --set python3 /usr/bin/python3.10 && apt install python3.10-distutils -y \
     && apt install curl git sudo libibverbs-dev -y \
     && curl https://bootstrap.pypa.io/get-pip.py -o get-pip.py && python3 get-pip.py \
@@ -67,6 +69,4 @@ RUN python3 -m pip install --upgrade pip setuptools wheel html5lib six \
          fi; \
        fi
 
-RUN python3 -m pip cache purge
-
 ENV DEBIAN_FRONTEND=interactive