p

Signed-off-by: khluu <khluu000@gmail.com>

.buildkite/release-pipeline.yaml

@@ -121,25 +121,7 @@ steps:
           queue: cpu_queue_release
         commands:
           - "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
-          - "aws ecr get-login-password --region us-east-1 | docker login --username AWS --password-stdin 936637512419.dkr.ecr.us-east-1.amazonaws.com || true"
+          - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --build-arg GIT_REPO_CHECK=1 --build-arg CUDA_VERSION=13.0.2 --build-arg torch_cuda_arch_list=\"${CUDA_ARCH_X86}\" --build-arg INSTALL_KV_CONNECTORS=true --build-arg BUILD_BASE_IMAGE=nvidia/cuda:13.0.2-devel-ubuntu22.04 --tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m) --target vllm-openai --progress plain -f docker/Dockerfile ."
-          - "docker buildx create --name release-builder --driver docker-container --use 2>/dev/null || docker buildx use release-builder"
-          - |
-            DOCKER_BUILDKIT=1 docker buildx build \
-              --build-arg max_jobs=16 \
-              --build-arg USE_SCCACHE=1 \
-              --build-arg GIT_REPO_CHECK=1 \
-              --build-arg CUDA_VERSION=13.0.2 \
-              --build-arg torch_cuda_arch_list="${CUDA_ARCH_X86}" \
-              --build-arg INSTALL_KV_CONNECTORS=true \
-              --build-arg BUILD_BASE_IMAGE=nvidia/cuda:13.0.2-devel-ubuntu22.04 \
-              --cache-from type=registry,ref=936637512419.dkr.ecr.us-east-1.amazonaws.com/vllm-ci-postmerge-cache:latest,mode=max \
-              --cache-from type=registry,ref=936637512419.dkr.ecr.us-east-1.amazonaws.com/vllm-ci-test-cache:release-$BUILDKITE_COMMIT,mode=max \
-              --cache-to type=registry,ref=936637512419.dkr.ecr.us-east-1.amazonaws.com/vllm-ci-test-cache:release-$BUILDKITE_COMMIT,mode=max,compression=zstd \
-              --tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m) \
-              --target vllm-openai \
-              --progress plain \
-              --load \
-              -f docker/Dockerfile .
           - "docker push public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)"
           # re-tag to default image tag and push, just in case arm64 build fails
           - "docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m) public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT"
@@ -152,25 +134,7 @@ steps:
           queue: arm64_cpu_queue_release
         commands:
           - "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
-          - "aws ecr get-login-password --region us-east-1 | docker login --username AWS --password-stdin 936637512419.dkr.ecr.us-east-1.amazonaws.com || true"
+          - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --build-arg GIT_REPO_CHECK=1 --build-arg CUDA_VERSION=13.0.2 --build-arg torch_cuda_arch_list=\"${CUDA_ARCH_AARCH64}\" --build-arg INSTALL_KV_CONNECTORS=true --build-arg BUILD_BASE_IMAGE=nvidia/cuda:13.0.2-devel-ubuntu22.04 --tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m) --target vllm-openai --progress plain -f docker/Dockerfile ."
-          - "docker buildx create --name release-builder --driver docker-container --use 2>/dev/null || docker buildx use release-builder"
-          - |
-            DOCKER_BUILDKIT=1 docker buildx build \
-              --build-arg max_jobs=16 \
-              --build-arg USE_SCCACHE=1 \
-              --build-arg GIT_REPO_CHECK=1 \
-              --build-arg CUDA_VERSION=13.0.2 \
-              --build-arg torch_cuda_arch_list="${CUDA_ARCH_AARCH64}" \
-              --build-arg INSTALL_KV_CONNECTORS=true \
-              --build-arg BUILD_BASE_IMAGE=nvidia/cuda:13.0.2-devel-ubuntu22.04 \
-              --cache-from type=registry,ref=936637512419.dkr.ecr.us-east-1.amazonaws.com/vllm-ci-postmerge-cache:latest,mode=max \
-              --cache-from type=registry,ref=936637512419.dkr.ecr.us-east-1.amazonaws.com/vllm-ci-test-cache:release-$BUILDKITE_COMMIT,mode=max \
-              --cache-to type=registry,ref=936637512419.dkr.ecr.us-east-1.amazonaws.com/vllm-ci-test-cache:release-$BUILDKITE_COMMIT,mode=max,compression=zstd \
-              --tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m) \
-              --target vllm-openai \
-              --progress plain \
-              --load \
-              -f docker/Dockerfile .
           - "docker push public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)"
 
       - label: "Build release image - x86_64 - CUDA 12.9"
@@ -180,24 +144,7 @@ steps:
           queue: cpu_queue_release
         commands:
           - "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
-          - "aws ecr get-login-password --region us-east-1 | docker login --username AWS --password-stdin 936637512419.dkr.ecr.us-east-1.amazonaws.com || true"
+          - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --build-arg GIT_REPO_CHECK=1 --build-arg CUDA_VERSION=12.9.1 --build-arg torch_cuda_arch_list=\"${CUDA_ARCH_X86_CU129}\" --build-arg INSTALL_KV_CONNECTORS=true --tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)-cu129 --target vllm-openai --progress plain -f docker/Dockerfile ."
-          - "docker buildx create --name release-builder --driver docker-container --use 2>/dev/null || docker buildx use release-builder"
-          - |
-            DOCKER_BUILDKIT=1 docker buildx build \
-              --build-arg max_jobs=16 \
-              --build-arg USE_SCCACHE=1 \
-              --build-arg GIT_REPO_CHECK=1 \
-              --build-arg CUDA_VERSION=12.9.1 \
-              --build-arg torch_cuda_arch_list="${CUDA_ARCH_X86_CU129}" \
-              --build-arg INSTALL_KV_CONNECTORS=true \
-              --cache-from type=registry,ref=936637512419.dkr.ecr.us-east-1.amazonaws.com/vllm-ci-postmerge-cache:latest,mode=max \
-              --cache-from type=registry,ref=936637512419.dkr.ecr.us-east-1.amazonaws.com/vllm-ci-test-cache:release-$BUILDKITE_COMMIT,mode=max \
-              --cache-to type=registry,ref=936637512419.dkr.ecr.us-east-1.amazonaws.com/vllm-ci-test-cache:release-$BUILDKITE_COMMIT,mode=max,compression=zstd \
-              --tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)-cu129 \
-              --target vllm-openai \
-              --progress plain \
-              --load \
-              -f docker/Dockerfile .
           - "docker push public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)-cu129"
           # re-tag to default image tag and push, just in case arm64 build fails
           - "docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)-cu129 public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-cu129"
@@ -210,24 +157,7 @@ steps:
           queue: arm64_cpu_queue_release
         commands:
           - "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
-          - "aws ecr get-login-password --region us-east-1 | docker login --username AWS --password-stdin 936637512419.dkr.ecr.us-east-1.amazonaws.com || true"
+          - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --build-arg GIT_REPO_CHECK=1 --build-arg CUDA_VERSION=12.9.1 --build-arg torch_cuda_arch_list=\"${CUDA_ARCH_AARCH64_CU129}\" --build-arg INSTALL_KV_CONNECTORS=true --tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)-cu129 --target vllm-openai --progress plain -f docker/Dockerfile ."
-          - "docker buildx create --name release-builder --driver docker-container --use 2>/dev/null || docker buildx use release-builder"
-          - |
-            DOCKER_BUILDKIT=1 docker buildx build \
-              --build-arg max_jobs=16 \
-              --build-arg USE_SCCACHE=1 \
-              --build-arg GIT_REPO_CHECK=1 \
-              --build-arg CUDA_VERSION=12.9.1 \
-              --build-arg torch_cuda_arch_list="${CUDA_ARCH_AARCH64_CU129}" \
-              --build-arg INSTALL_KV_CONNECTORS=true \
-              --cache-from type=registry,ref=936637512419.dkr.ecr.us-east-1.amazonaws.com/vllm-ci-postmerge-cache:latest,mode=max \
-              --cache-from type=registry,ref=936637512419.dkr.ecr.us-east-1.amazonaws.com/vllm-ci-test-cache:release-$BUILDKITE_COMMIT,mode=max \
-              --cache-to type=registry,ref=936637512419.dkr.ecr.us-east-1.amazonaws.com/vllm-ci-test-cache:release-$BUILDKITE_COMMIT,mode=max,compression=zstd \
-              --tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)-cu129 \
-              --target vllm-openai \
-              --progress plain \
-              --load \
-              -f docker/Dockerfile .
           - "docker push public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)-cu129"
 
       - label: "Build release image - x86_64 - CUDA 13.0 - Ubuntu 24.04"
@@ -237,27 +167,7 @@ steps:
           queue: cpu_queue_release
         commands:
           - "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
-          - "aws ecr get-login-password --region us-east-1 | docker login --username AWS --password-stdin 936637512419.dkr.ecr.us-east-1.amazonaws.com || true"
+          - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --build-arg GIT_REPO_CHECK=1 --build-arg CUDA_VERSION=13.0.2 --build-arg UBUNTU_VERSION=24.04 --build-arg GDRCOPY_OS_VERSION=Ubuntu24_04 --build-arg torch_cuda_arch_list=\"${CUDA_ARCH_X86}\" --build-arg INSTALL_KV_CONNECTORS=true --build-arg BUILD_BASE_IMAGE=nvidia/cuda:13.0.2-devel-ubuntu24.04 --tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)-ubuntu2404 --target vllm-openai --progress plain -f docker/Dockerfile ."
-          - "docker buildx create --name release-builder --driver docker-container --use 2>/dev/null || docker buildx use release-builder"
-          - |
-            DOCKER_BUILDKIT=1 docker buildx build \
-              --build-arg max_jobs=16 \
-              --build-arg USE_SCCACHE=1 \
-              --build-arg GIT_REPO_CHECK=1 \
-              --build-arg CUDA_VERSION=13.0.2 \
-              --build-arg UBUNTU_VERSION=24.04 \
-              --build-arg GDRCOPY_OS_VERSION=Ubuntu24_04 \
-              --build-arg torch_cuda_arch_list="${CUDA_ARCH_X86}" \
-              --build-arg INSTALL_KV_CONNECTORS=true \
-              --build-arg BUILD_BASE_IMAGE=nvidia/cuda:13.0.2-devel-ubuntu24.04 \
-              --cache-from type=registry,ref=936637512419.dkr.ecr.us-east-1.amazonaws.com/vllm-ci-postmerge-cache:latest,mode=max \
-              --cache-from type=registry,ref=936637512419.dkr.ecr.us-east-1.amazonaws.com/vllm-ci-test-cache:release-$BUILDKITE_COMMIT,mode=max \
-              --cache-to type=registry,ref=936637512419.dkr.ecr.us-east-1.amazonaws.com/vllm-ci-test-cache:release-$BUILDKITE_COMMIT,mode=max,compression=zstd \
-              --tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)-ubuntu2404 \
-              --target vllm-openai \
-              --progress plain \
-              --load \
-              -f docker/Dockerfile .
           - "docker push public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)-ubuntu2404"
           - "docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)-ubuntu2404 public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-ubuntu2404"
           - "docker push public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-ubuntu2404"
@@ -269,27 +179,7 @@ steps:
           queue: arm64_cpu_queue_release
         commands:
           - "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
-          - "aws ecr get-login-password --region us-east-1 | docker login --username AWS --password-stdin 936637512419.dkr.ecr.us-east-1.amazonaws.com || true"
+          - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --build-arg GIT_REPO_CHECK=1 --build-arg CUDA_VERSION=13.0.2 --build-arg UBUNTU_VERSION=24.04 --build-arg GDRCOPY_OS_VERSION=Ubuntu24_04 --build-arg torch_cuda_arch_list=\"${CUDA_ARCH_AARCH64}\" --build-arg INSTALL_KV_CONNECTORS=true --build-arg BUILD_BASE_IMAGE=nvidia/cuda:13.0.2-devel-ubuntu24.04 --tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)-ubuntu2404 --target vllm-openai --progress plain -f docker/Dockerfile ."
-          - "docker buildx create --name release-builder --driver docker-container --use 2>/dev/null || docker buildx use release-builder"
-          - |
-            DOCKER_BUILDKIT=1 docker buildx build \
-              --build-arg max_jobs=16 \
-              --build-arg USE_SCCACHE=1 \
-              --build-arg GIT_REPO_CHECK=1 \
-              --build-arg CUDA_VERSION=13.0.2 \
-              --build-arg UBUNTU_VERSION=24.04 \
-              --build-arg GDRCOPY_OS_VERSION=Ubuntu24_04 \
-              --build-arg torch_cuda_arch_list="${CUDA_ARCH_AARCH64}" \
-              --build-arg INSTALL_KV_CONNECTORS=true \
-              --build-arg BUILD_BASE_IMAGE=nvidia/cuda:13.0.2-devel-ubuntu24.04 \
-              --cache-from type=registry,ref=936637512419.dkr.ecr.us-east-1.amazonaws.com/vllm-ci-postmerge-cache:latest,mode=max \
-              --cache-from type=registry,ref=936637512419.dkr.ecr.us-east-1.amazonaws.com/vllm-ci-test-cache:release-$BUILDKITE_COMMIT,mode=max \
-              --cache-to type=registry,ref=936637512419.dkr.ecr.us-east-1.amazonaws.com/vllm-ci-test-cache:release-$BUILDKITE_COMMIT,mode=max,compression=zstd \
-              --tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)-ubuntu2404 \
-              --target vllm-openai \
-              --progress plain \
-              --load \
-              -f docker/Dockerfile .
           - "docker push public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)-ubuntu2404"
 
       - label: "Build release image - x86_64 - CUDA 12.9 - Ubuntu 24.04"
@@ -299,26 +189,7 @@ steps:
           queue: cpu_queue_release
         commands:
           - "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
-          - "aws ecr get-login-password --region us-east-1 | docker login --username AWS --password-stdin 936637512419.dkr.ecr.us-east-1.amazonaws.com || true"
+          - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --build-arg GIT_REPO_CHECK=1 --build-arg CUDA_VERSION=12.9.1 --build-arg UBUNTU_VERSION=24.04 --build-arg GDRCOPY_OS_VERSION=Ubuntu24_04 --build-arg torch_cuda_arch_list=\"${CUDA_ARCH_X86_CU129}\" --build-arg INSTALL_KV_CONNECTORS=true --tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)-cu129-ubuntu2404 --target vllm-openai --progress plain -f docker/Dockerfile ."
-          - "docker buildx create --name release-builder --driver docker-container --use 2>/dev/null || docker buildx use release-builder"
-          - |
-            DOCKER_BUILDKIT=1 docker buildx build \
-              --build-arg max_jobs=16 \
-              --build-arg USE_SCCACHE=1 \
-              --build-arg GIT_REPO_CHECK=1 \
-              --build-arg CUDA_VERSION=12.9.1 \
-              --build-arg UBUNTU_VERSION=24.04 \
-              --build-arg GDRCOPY_OS_VERSION=Ubuntu24_04 \
-              --build-arg torch_cuda_arch_list="${CUDA_ARCH_X86_CU129}" \
-              --build-arg INSTALL_KV_CONNECTORS=true \
-              --cache-from type=registry,ref=936637512419.dkr.ecr.us-east-1.amazonaws.com/vllm-ci-postmerge-cache:latest,mode=max \
-              --cache-from type=registry,ref=936637512419.dkr.ecr.us-east-1.amazonaws.com/vllm-ci-test-cache:release-$BUILDKITE_COMMIT,mode=max \
-              --cache-to type=registry,ref=936637512419.dkr.ecr.us-east-1.amazonaws.com/vllm-ci-test-cache:release-$BUILDKITE_COMMIT,mode=max,compression=zstd \
-              --tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)-cu129-ubuntu2404 \
-              --target vllm-openai \
-              --progress plain \
-              --load \
-              -f docker/Dockerfile .
           - "docker push public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)-cu129-ubuntu2404"
           - "docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)-cu129-ubuntu2404 public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-cu129-ubuntu2404"
           - "docker push public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-cu129-ubuntu2404"
@@ -330,26 +201,7 @@ steps:
           queue: arm64_cpu_queue_release
         commands:
           - "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
-          - "aws ecr get-login-password --region us-east-1 | docker login --username AWS --password-stdin 936637512419.dkr.ecr.us-east-1.amazonaws.com || true"
+          - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --build-arg GIT_REPO_CHECK=1 --build-arg CUDA_VERSION=12.9.1 --build-arg UBUNTU_VERSION=24.04 --build-arg GDRCOPY_OS_VERSION=Ubuntu24_04 --build-arg torch_cuda_arch_list=\"${CUDA_ARCH_AARCH64_CU129}\" --build-arg INSTALL_KV_CONNECTORS=true --tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)-cu129-ubuntu2404 --target vllm-openai --progress plain -f docker/Dockerfile ."
-          - "docker buildx create --name release-builder --driver docker-container --use 2>/dev/null || docker buildx use release-builder"
-          - |
-            DOCKER_BUILDKIT=1 docker buildx build \
-              --build-arg max_jobs=16 \
-              --build-arg USE_SCCACHE=1 \
-              --build-arg GIT_REPO_CHECK=1 \
-              --build-arg CUDA_VERSION=12.9.1 \
-              --build-arg UBUNTU_VERSION=24.04 \
-              --build-arg GDRCOPY_OS_VERSION=Ubuntu24_04 \
-              --build-arg torch_cuda_arch_list="${CUDA_ARCH_AARCH64_CU129}" \
-              --build-arg INSTALL_KV_CONNECTORS=true \
-              --cache-from type=registry,ref=936637512419.dkr.ecr.us-east-1.amazonaws.com/vllm-ci-postmerge-cache:latest,mode=max \
-              --cache-from type=registry,ref=936637512419.dkr.ecr.us-east-1.amazonaws.com/vllm-ci-test-cache:release-$BUILDKITE_COMMIT,mode=max \
-              --cache-to type=registry,ref=936637512419.dkr.ecr.us-east-1.amazonaws.com/vllm-ci-test-cache:release-$BUILDKITE_COMMIT,mode=max,compression=zstd \
-              --tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)-cu129-ubuntu2404 \
-              --target vllm-openai \
-              --progress plain \
-              --load \
-              -f docker/Dockerfile .
           - "docker push public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)-cu129-ubuntu2404"
 
       - block: "Build release image for x86_64 CPU"

docker/Dockerfile

@@ -478,9 +478,6 @@ FROM ${FINAL_BASE_IMAGE} AS vllm-base
 
 ARG CUDA_VERSION
 ARG PYTHON_VERSION
-ARG DEADSNAKES_MIRROR_URL
-ARG DEADSNAKES_GPGKEY_URL
-ARG GET_PIP_URL
 
 ENV DEBIAN_FRONTEND=noninteractive
 WORKDIR /vllm-workspace
@@ -490,7 +487,12 @@ WORKDIR /vllm-workspace
 RUN PYTHON_VERSION_STR=$(echo ${PYTHON_VERSION} | sed 's/\.//g') && \
     echo "export PYTHON_VERSION_STR=${PYTHON_VERSION_STR}" >> /etc/environment
 
-# Install Python from source and system dependencies
+# Install Python (via uv / python-build-standalone) and system dependencies.
+# This replaces the deadsnakes PPA, removing the build-time dependency on
+# Launchpad and matching how the build-stage (`base`) installs Python.
+# python-build-standalone bundles dev headers, the venv module, and
+# python3-config, so the python3.X-dev / python3.X-venv apt packages
+# are not needed.
 RUN apt-get update -y \
     && apt-get install -y --no-install-recommends \
         curl \
@@ -500,38 +502,20 @@ RUN apt-get update -y \
         libxext6 \
         libgl1 \
         libibverbs-dev \
-        build-essential \
-        libssl-dev \
-        libffi-dev \
-        zlib1g-dev \
-        libbz2-dev \
-        libreadline-dev \
-        libsqlite3-dev \
-        libncurses-dev \
-        liblzma-dev \
-        libgdbm-dev \
-        uuid-dev \
-        tk-dev \
-    && PYTHON_MAJOR_MINOR=${PYTHON_VERSION} \
-    && PYTHON_FULL_VERSION=$(curl -s https://www.python.org/ftp/python/ \
-        | grep -oE "${PYTHON_MAJOR_MINOR}\.[0-9]+" \
-        | sort -t. -k3 -n | uniq \
-        | tail -1) \
-    && echo "Building Python ${PYTHON_FULL_VERSION} from source..." \
-    && curl -fSL https://www.python.org/ftp/python/${PYTHON_FULL_VERSION}/Python-${PYTHON_FULL_VERSION}.tgz -o /tmp/python.tgz \
-    && tar -xzf /tmp/python.tgz -C /tmp \
-    && cd /tmp/Python-${PYTHON_FULL_VERSION} \
-    && ./configure --enable-optimizations --with-ensurepip=install --prefix=/usr/local \
-    && make -j$(nproc) \
-    && make install \
-    && cd / \
-    && rm -rf /tmp/python.tgz /tmp/Python-${PYTHON_FULL_VERSION} \
-    && ln -sf /usr/local/bin/python${PYTHON_MAJOR_MINOR} /usr/bin/python3 \
-    && ln -sf /usr/local/bin/python${PYTHON_MAJOR_MINOR}-config /usr/bin/python3-config \
-    && ln -sf /usr/local/bin/pip${PYTHON_MAJOR_MINOR} /usr/bin/pip \
     && rm -rf /var/lib/apt/lists/* \
+    && curl -LsSf https://astral.sh/uv/install.sh | sh \
+    && $HOME/.local/bin/uv venv /opt/venv --python ${PYTHON_VERSION} \
+    && rm -f /usr/bin/python3 /usr/bin/python3-config /usr/bin/pip \
+    && ln -s /opt/venv/bin/python3 /usr/bin/python3 \
+    && ln -s /opt/venv/bin/python${PYTHON_VERSION} /usr/bin/python${PYTHON_VERSION} \
+    && ln -s /opt/venv/bin/python3-config /usr/bin/python3-config \
+    && ln -s /opt/venv/bin/pip /usr/bin/pip \
     && python3 --version && python3 -m pip --version
 
+# Activate virtual environment and add uv to PATH
+ENV PATH="/opt/venv/bin:/root/.local/bin:$PATH"
+ENV VIRTUAL_ENV="/opt/venv"
+
 # Install CUDA development tools for runtime JIT compilation
 # (FlashInfer, DeepGEMM, EP kernels all require compilation at runtime)
 RUN CUDA_VERSION_DASH=$(echo $CUDA_VERSION | cut -d. -f1,2 | tr '.' '-') && \
@@ -556,9 +540,6 @@ RUN CUDA_VERSION_DASH=$(echo $CUDA_VERSION | cut -d. -f1,2 | tr '.' '-') && \
     apt-get install -y --no-install-recommends --allow-change-held-packages libnccl-dev=${NCCL_VER} libnccl2=${NCCL_VER} && \
     rm -rf /var/lib/apt/lists/*
 
-# Install uv for faster pip installs
-RUN python3 -m pip install uv
-
 # Environment for uv
 ENV UV_HTTP_TIMEOUT=500
 ENV UV_INDEX_STRATEGY="unsafe-best-match"
@@ -748,7 +729,7 @@ ENV HF_XET_HIGH_PERFORMANCE 1
 ENV HF_HUB_DOWNLOAD_TIMEOUT 60
 
 # Copy in the v1 package for testing (it isn't distributed yet)
-COPY vllm/v1 /usr/local/lib/python${PYTHON_VERSION}/dist-packages/vllm/v1
+COPY vllm/v1 /opt/venv/lib/python${PYTHON_VERSION}/site-packages/vllm/v1
 
 # Source code is used in the `python_only_compile.sh` test
 # We hide it inside `src/` so that this source code