[CI/Build] Replace COPY scripts with bind mounts to reduce layers

Signed-off-by: Morteza Mirzaei <[email protected]>

Author: mirzaim

docker/Dockerfile

@@ -225,12 +225,12 @@ RUN --mount=type=cache,target=/root/.cache/ccache \
     fi
 
 # Check the size of the wheel if RUN_WHEEL_CHECK is true
-COPY .buildkite/check-wheel-size.py check-wheel-size.py
 # sync the default value with .buildkite/check-wheel-size.py
 ARG VLLM_MAX_SIZE_MB=500
 ENV VLLM_MAX_SIZE_MB=$VLLM_MAX_SIZE_MB
 ARG RUN_WHEEL_CHECK=true
-RUN if [ "$RUN_WHEEL_CHECK" = "true" ]; then \
+RUN --mount=type=bind,source=.buildkite/check-wheel-size.py,target=check-wheel-size.py \
+    if [ "$RUN_WHEEL_CHECK" = "true" ]; then \
         python3 check-wheel-size.py dist; \
     else \
         echo "Skipping wheel size check."; \
@@ -367,24 +367,23 @@ RUN --mount=type=cache,target=/root/.cache/uv \
 
 # Install DeepGEMM from source
 ARG DEEPGEMM_GIT_REF
-COPY tools/install_deepgemm.sh /tmp/install_deepgemm.sh
-RUN --mount=type=cache,target=/root/.cache/uv \
+RUN --mount=type=bind,source=tools/install_deepgemm.sh,target=/tmp/install_deepgemm.sh \
+    --mount=type=cache,target=/root/.cache/uv \
     VLLM_DOCKER_BUILD_CONTEXT=1 TORCH_CUDA_ARCH_LIST="9.0a 10.0a" /tmp/install_deepgemm.sh --cuda-version "${CUDA_VERSION}" ${DEEPGEMM_GIT_REF:+--ref "$DEEPGEMM_GIT_REF"}
 
-COPY tools/install_gdrcopy.sh install_gdrcopy.sh
-RUN set -eux; \
+RUN --mount=type=bind,source=tools/install_gdrcopy.sh,target=install_gdrcopy.sh \
+    set -eux; \
     case "${TARGETPLATFORM}" in \
       linux/arm64) UUARCH="aarch64" ;; \
       linux/amd64) UUARCH="x64" ;; \
       *) echo "Unsupported TARGETPLATFORM: ${TARGETPLATFORM}" >&2; exit 1 ;; \
     esac; \
-    ./install_gdrcopy.sh "${GDRCOPY_OS_VERSION}" "${GDRCOPY_CUDA_VERSION}" "${UUARCH}"; \
-    rm ./install_gdrcopy.sh
+    ./install_gdrcopy.sh "${GDRCOPY_OS_VERSION}" "${GDRCOPY_CUDA_VERSION}" "${UUARCH}";
 
 # Install EP kernels(pplx-kernels and DeepEP)
-COPY tools/ep_kernels/install_python_libraries.sh install_python_libraries.sh
 ENV CUDA_HOME=/usr/local/cuda
-RUN export TORCH_CUDA_ARCH_LIST="${TORCH_CUDA_ARCH_LIST:-9.0a 10.0a+PTX}" \
+RUN --mount=type=bind,source=tools/ep_kernels/install_python_libraries.sh,target=install_python_libraries.sh \
+    export TORCH_CUDA_ARCH_LIST="${TORCH_CUDA_ARCH_LIST:-9.0a 10.0a+PTX}" \
     && bash install_python_libraries.sh
 
 # CUDA image changed from /usr/local/nvidia to /usr/local/cuda in 12.8 but will