[None][chore] reduce the layers of the devel docker image (NVIDIA#9077)

Signed-off-by: Martin Marciniszyn Mehringer <11665257+MartinMarciniszyn@users.noreply.github.com>

Author: MartinMarciniszyn

docker/Dockerfile.multi

@@ -12,9 +12,10 @@ LABEL com.nvidia.eula="https://www.nvidia.com/en-us/agreements/enterprise-softwa
 LABEL com.nvidia.ai-terms="https://www.nvidia.com/en-us/agreements/enterprise-software/product-specific-terms-for-ai-products/"
 
 # https://www.gnu.org/software/bash/manual/html_node/Bash-Startup-Files.html
-# The default values come from `nvcr.io/nvidia/pytorch`
-ENV BASH_ENV=${BASH_ENV:-/etc/bash.bashrc}
-ENV ENV=${ENV:-/etc/shinit_v2}
+ARG SH_ENV="/etc/shinit_v2"
+ENV ENV=${SH_ENV}
+ARG BASH_ENV="/etc/bash.bashrc"
+ENV BASH_ENV=${BASH_ENV}
 
 ARG GITHUB_MIRROR=""
 RUN echo "Using GitHub mirror: $GITHUB_MIRROR"
@@ -43,48 +44,41 @@ COPY docker/common/install.sh \
      docker/common/install_ucx.sh \
      docker/common/install_nixl.sh \
      docker/common/install_etcd.sh \
-     docker/common/install_mooncake.sh \
      ./
 
-RUN GITHUB_MIRROR=${GITHUB_MIRROR} \
-    PYTHON_VERSION=${PYTHON_VERSION} \
-    bash ./install.sh --base && rm install_base.sh
-
-RUN GITHUB_MIRROR=${GITHUB_MIRROR} bash ./install.sh --cmake && rm install_cmake.sh
-
-RUN GITHUB_MIRROR=${GITHUB_MIRROR} bash ./install.sh --ccache && rm install_ccache.sh
-
-RUN bash ./install.sh --cuda_toolkit && rm install_cuda_toolkit.sh
-
 ARG TRT_VER
 ARG CUDA_VER
 ARG CUDNN_VER
 ARG NCCL_VER
 ARG CUBLAS_VER
-RUN TRT_VER=${TRT_VER} \
+ARG TORCH_INSTALL_TYPE="skip"
+RUN GITHUB_MIRROR=${GITHUB_MIRROR} \
+    PYTHON_VERSION=${PYTHON_VERSION} \
+    TRT_VER=${TRT_VER} \
     CUDA_VER=${CUDA_VER} \
     CUDNN_VER=${CUDNN_VER} \
     NCCL_VER=${NCCL_VER} \
     CUBLAS_VER=${CUBLAS_VER} \
-    bash ./install.sh --tensorrt && rm install_tensorrt.sh
-
-RUN GITHUB_MIRROR=${GITHUB_MIRROR} bash ./install.sh --polygraphy && rm install_polygraphy.sh
-
-RUN GITHUB_MIRROR=${GITHUB_MIRROR} bash ./install.sh --mpi4py && rm install_mpi4py.sh
-
-ARG TORCH_INSTALL_TYPE="skip"
-RUN TORCH_INSTALL_TYPE=${TORCH_INSTALL_TYPE} bash ./install.sh --pytorch && rm install_pytorch.sh
-
-RUN bash ./install.sh --opencv && rm install.sh
-
-# Install UCX first
-RUN GITHUB_MIRROR=${GITHUB_MIRROR} bash ./install_ucx.sh && rm install_ucx.sh
-
-# Install NIXL
-RUN GITHUB_MIRROR=${GITHUB_MIRROR} bash ./install_nixl.sh && rm install_nixl.sh
-
-# Install etcd
-RUN bash ./install_etcd.sh && rm install_etcd.sh
+    TORCH_INSTALL_TYPE=${TORCH_INSTALL_TYPE} \
+    bash ./install.sh --base --cmake --ccache --cuda_toolkit --tensorrt --polygraphy --mpi4py --pytorch --opencv && \
+    rm install_base.sh && \
+    rm install_cmake.sh && \
+    rm install_ccache.sh && \
+    rm install_cuda_toolkit.sh && \
+    rm install_tensorrt.sh && \
+    rm install_polygraphy.sh && \
+    rm install_mpi4py.sh && \
+    rm install_pytorch.sh && \
+    rm install.sh
+
+# Install UCX, NIXL, etcd
+# TODO: Combine these into the main install.sh script
+RUN GITHUB_MIRROR=${GITHUB_MIRROR} bash ./install_ucx.sh && \
+    GITHUB_MIRROR=${GITHUB_MIRROR} bash ./install_nixl.sh && \
+    bash ./install_etcd.sh && \
+    rm install_ucx.sh && \
+    rm install_nixl.sh && \
+    rm install_etcd.sh
 
 FROM ${TRITON_IMAGE}:${TRITON_BASE_TAG} AS triton
 
@@ -99,16 +93,18 @@ COPY --from=triton /opt/tritonserver/caches /opt/tritonserver/caches
 
 # Copy all installation scripts at once to reduce layers
 COPY docker/common/install_triton.sh \
+     docker/common/install_mooncake.sh \
      ./
 
-RUN GITHUB_MIRROR=${GITHUB_MIRROR} bash ./install_triton.sh && rm install_triton.sh
-
 # Install Mooncake, after triton handles boost requirement
-RUN if [ -f /etc/redhat-release ]; then \
+RUN GITHUB_MIRROR=${GITHUB_MIRROR} bash ./install_triton.sh && \
+    if [ -f /etc/redhat-release ]; then \
         echo "Rocky8 detected, skipping mooncake installation"; \
     else \
         bash ./install_mooncake.sh; \
-    fi && rm install_mooncake.sh
+    fi && \
+    rm install_triton.sh && \
+    rm install_mooncake.sh
 
 FROM ${DEVEL_IMAGE} AS wheel
 WORKDIR /src/tensorrt_llm

docker/Makefile

@@ -75,8 +75,16 @@ define rewrite_tag
 $(shell echo $(IMAGE_WITH_TAG) | sed "s/\/tensorrt-llm:/\/tensorrt-llm-staging:/g")
 endef
 
+base_pull:
+	@echo "Pulling base image: $(BASE_IMAGE):$(BASE_TAG)"
+	docker pull $(BASE_IMAGE):$(BASE_TAG)
+
 %_build: DEVEL_IMAGE = $(if $(findstring 1,$(JENKINS_DEVEL)),$(shell . ../jenkins/current_image_tags.properties && echo $$LLM_DOCKER_IMAGE))
-%_build:
+%_build: SH_ENV      = $(shell docker inspect --format='{{range .Config.Env}}{{println .}}{{end}}' $(BASE_IMAGE):$(BASE_TAG) \
+				  	   | grep '^ENV=' | sed 's/^[^=]*=//' 2>/dev/null)
+%_build: BASH_ENV    = $(shell docker inspect --format='{{range .Config.Env}}{{println .}}{{end}}' $(BASE_IMAGE):$(BASE_TAG) \
+    				   | grep '^BASH_ENV=' | sed 's/^[^=]*=//' 2>/dev/null)
+%_build: base_pull
 	@echo "Building docker image: $(IMAGE_WITH_TAG)"
 	docker buildx build $(DOCKER_BUILD_OPTS) $(DOCKER_BUILD_ARGS) \
 		--progress $(DOCKER_PROGRESS) \
@@ -97,6 +105,8 @@ endef
 		$(if $(GIT_COMMIT), --build-arg GIT_COMMIT="$(GIT_COMMIT)") \
 		$(if $(GITHUB_MIRROR), --build-arg GITHUB_MIRROR="$(GITHUB_MIRROR)") \
 		$(if $(PYTHON_VERSION), --build-arg PYTHON_VERSION="$(PYTHON_VERSION)") \
+		$(if $(SH_ENV), --build-arg SH_ENV="$(SH_ENV)") \
+		$(if $(BASH_ENV), --build-arg BASH_ENV="$(BASH_ENV)") \
 		$(if $(STAGE), --target $(STAGE)) \
 		--file Dockerfile.multi \
 		--tag $(IMAGE_WITH_TAG) \

docker/common/install.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 set -Eeo pipefail
 shopt -s nullglob
 trap 'echo "[install.sh] Error on line $LINENO" >&2' ERR
@@ -125,7 +125,7 @@ fi
 
 if [ $opencv -eq 1 ]; then
     echo "Installing OpenCV..."
-    pip3 uninstall -y opencv
+    bash -c "pip3 uninstall -y opencv"
     rm -rf /usr/local/lib/python3*/dist-packages/cv2/
-    pip3 install opencv-python-headless --force-reinstall --no-deps --no-cache-dir
+    bash -c "pip3 install opencv-python-headless --force-reinstall --no-deps --no-cache-dir"
 fi

jenkins/current_image_tags.properties

@@ -13,7 +13,7 @@
 #     images are adopted from PostMerge pipelines, the abbreviated commit hash is used instead.
 IMAGE_NAME=urm.nvidia.com/sw-tensorrt-docker/tensorrt-llm
 
-LLM_DOCKER_IMAGE=urm.nvidia.com/sw-tensorrt-docker/tensorrt-llm:pytorch-25.10-py3-x86_64-ubuntu24.04-trt10.13.3.9-skip-tritondevel-202511271125-9294
-LLM_SBSA_DOCKER_IMAGE=urm.nvidia.com/sw-tensorrt-docker/tensorrt-llm:pytorch-25.10-py3-aarch64-ubuntu24.04-trt10.13.3.9-skip-tritondevel-202511271125-9294
-LLM_ROCKYLINUX8_PY310_DOCKER_IMAGE=urm.nvidia.com/sw-tensorrt-docker/tensorrt-llm:cuda-13.0.2-devel-rocky8-x86_64-rocky8-py310-trt10.13.3.9-skip-tritondevel-202511271125-9294
-LLM_ROCKYLINUX8_PY312_DOCKER_IMAGE=urm.nvidia.com/sw-tensorrt-docker/tensorrt-llm:cuda-13.0.2-devel-rocky8-x86_64-rocky8-py312-trt10.13.3.9-skip-tritondevel-202511271125-9294
+LLM_DOCKER_IMAGE=urm.nvidia.com/sw-tensorrt-docker/tensorrt-llm:pytorch-25.10-py3-x86_64-ubuntu24.04-trt10.13.3.9-skip-tritondevel-202511281406-9077
+LLM_SBSA_DOCKER_IMAGE=urm.nvidia.com/sw-tensorrt-docker/tensorrt-llm:pytorch-25.10-py3-aarch64-ubuntu24.04-trt10.13.3.9-skip-tritondevel-202511281406-9077
+LLM_ROCKYLINUX8_PY310_DOCKER_IMAGE=urm.nvidia.com/sw-tensorrt-docker/tensorrt-llm:cuda-13.0.2-devel-rocky8-x86_64-rocky8-py310-trt10.13.3.9-skip-tritondevel-202511281406-9077
+LLM_ROCKYLINUX8_PY312_DOCKER_IMAGE=urm.nvidia.com/sw-tensorrt-docker/tensorrt-llm:cuda-13.0.2-devel-rocky8-x86_64-rocky8-py312-trt10.13.3.9-skip-tritondevel-202511281406-9077