Namespace
vllm
Image / Tagvllm-openai:latest-aarch64
Content Digestsha256:e3481489818d3e563cae517b84ab959cc8b69f85a9fbb771c189140131ffc65c
Details
2026-11-01 09:57:17 UTC
10.2 GB
Labels
-
ai.vllm.build.commit4ba787ec9959e566d3b587a796dff07673324da5
-
ai.vllm.build.pipeline019d130e-464e-4ff7-b84b-492992c0c06b
-
ai.vllm.build.urlhttps://buildkite.com/vllm/release-v2/builds/9673
-
ai.vllm.image.tagvllm/vllm-openai:v0.33.0
-
maintainerNVIDIA CORPORATION <cudatools@nvidia.com>
-
org.opencontainers.image.ref.nameubuntu
-
org.opencontainers.image.revision4ba787ec9959e566d3b587a796dff07673324da5
-
org.opencontainers.image.sourcehttps://github.com/vllm-project/vllm
-
org.opencontainers.image.urlhttps://buildkite.com/vllm/release-v2/builds/9673
-
org.opencontainers.image.versionvllm/vllm-openai:v0.33.0
Environment
CRIU_CUDA_PLUGIN_DIR/usr/local/lib/criu
CUDA_HOME/usr/local/cuda
CUDA_VERSION13.0.2
DEBIAN_FRONTENDnoninteractive
LD_LIBRARY_PATH/usr/local/nvidia/lib64:/usr/local/cuda/lib64:/usr/local/cuda/lib64:/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/local/cuda/lib64
NVARCHsbsa
NVIDIA_DRIVER_CAPABILITIEScompute,utility
NVIDIA_REQUIRE_CUDAcuda>=13.0 brand=unknown,driver>=535,driver<536 brand=grid,driver>=535,driver<536 brand=tesla,driver>=535,driver<536 brand=nvidia,driver>=535,driver<536 brand=quadro,driver>=535,driver<536 brand=quadrortx,driver>=535,driver<536 brand=nvidiartx,driver>=535,driver<536 brand=vapps,driver>=535,driver<536 brand=vpc,driver>=535,driver<536 brand=vcs,driver>=535,driver<536 brand=vws,driver>=535,driver<536 brand=cloudgaming,driver>=535,driver<536 brand=unknown,driver>=550,driver<551 brand=grid,driver>=550,driver<551 brand=tesla,driver>=550,driver<551 brand=nvidia,driver>=550,driver<551 brand=quadro,driver>=550,driver<551 brand=quadrortx,driver>=550,driver<551 brand=nvidiartx,driver>=550,driver<551 brand=vapps,driver>=550,driver<551 brand=vpc,driver>=550,driver<551 brand=vcs,driver>=550,driver<551 brand=vws,driver>=550,driver<551 brand=cloudgaming,driver>=550,driver<551 brand=unknown,driver>=565,driver<566 brand=grid,driver>=565,driver<566 brand=tesla,driver>=565,driver<566 brand=nvidia,driver>=565,driver<566 brand=quadro,driver>=565,driver<566 brand=quadrortx,driver>=565,driver<566 brand=nvidiartx,driver>=565,driver<566 brand=vapps,driver>=565,driver<566 brand=vpc,driver>=565,driver<566 brand=vcs,driver>=565,driver<566 brand=vws,driver>=565,driver<566 brand=cloudgaming,driver>=565,driver<566 brand=unknown,driver>=570,driver<571 brand=grid,driver>=570,driver<571 brand=tesla,driver>=570,driver<571 brand=nvidia,driver>=570,driver<571 brand=quadro,driver>=570,driver<571 brand=quadrortx,driver>=570,driver<571 brand=nvidiartx,driver>=570,driver<571 brand=vapps,driver>=570,driver<571 brand=vpc,driver>=570,driver<571 brand=vcs,driver>=570,driver<571 brand=vws,driver>=570,driver<571 brand=cloudgaming,driver>=570,driver<571 brand=unknown,driver>=575,driver<576 brand=grid,driver>=575,driver<576 brand=tesla,driver>=575,driver<576 brand=nvidia,driver>=575,driver<576 brand=quadro,driver>=575,driver<576 brand=quadrortx,driver>=575,driver<576 brand=nvidiartx,driver>=575,driver<576 brand=vapps,driver>=575,driver<576 brand=vpc,driver>=575,driver<576 brand=vcs,driver>=575,driver<576 brand=vws,driver>=575,driver<576 brand=cloudgaming,driver>=575,driver<576
NVIDIA_VISIBLE_DEVICESall
NV_CUDA_CUDART_VERSION13.0.96-1
PATH/usr/local/cuda/bin:/usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin
TORCH_CUDA_ARCH_LIST8.0 8.7 8.9 9.0 10.0 11.0 12.0
UV_CACHE_DIR/opt/uv/cache
UV_COMPILE_BYTECODE1
UV_HTTP_TIMEOUT500
UV_INDEX_STRATEGYunsafe-best-match
UV_LINK_MODEcopy
UV_OVERRIDE/etc/uv-overrides.txt
UV_PYTHON_INSTALL_DIR/opt/uv/python
VLLM_BUILD_COMMIT4ba787ec9959e566d3b587a796dff07673324da5
VLLM_BUILD_PIPELINE019d130e-464e-4ff7-b84b-492992c0c06b
VLLM_BUILD_URLhttps://buildkite.com/vllm/release-v2/builds/9673
VLLM_ENABLE_CUDA_COMPATIBILITY0
VLLM_IMAGE_TAGvllm/vllm-openai:v0.33.0
VLLM_USAGE_SOURCEproduction-docker-image
Layers
[#000] sha256:a91ffad96809552eb41208a0a580e75c014311ef2cb79002fb242da7bc6f8801 - 0.27% (28.6 MB)
[#001] sha256:7be1e3dd81adb79f8fbffa3a472a80e4a024b7dedb4028788e15e05c4a7a3946 - 0.04% (4.32 MB)
[#002] sha256:653ca2e1b0e9f4dda5c4101ba798059d34362dfdd0379f1fb2b80f1e48a703df - 0.91% (95.1 MB)
[#003] sha256:66c8341e87a6fcc90cd8b78f232a7707a96e4fbeaff457268bc6d4fdd8bf509a - 0.0% (186 Bytes)
[#004] sha256:526d5438c009ab7178af1646fed10ff6f47a73f5a1ae7b9f49e63e4ade7e3ae6 - 0.0% (6.72 KB)
[#005] sha256:33cbecde6143af1a74b23a865d22b10284fdf2e2bad905d3516f82a33438e877 - 0.0% (104 Bytes)
[#006] sha256:3aefb5ec78cef5c7e341ec1e8f129c66991db13d088d7da9290355e85d698786 - 0.0% (230 Bytes)
[#007] sha256:5c84bc1308d162452afad5c0d5b9093b4a9315aca091b51ef19038876960f854 - 2.08% (216 MB)
[#008] sha256:e571543f665210f24cd84ab89242c93d25e362c563b85d40ce0b66312bdb45e0 - 14.67% (1.49 GB)
[#009] sha256:56eef2e9879d6c835932a7a446569507677e11e6533fb4ad3c2f96682b05048f - 0.0% (1.62 KB)
[#010] sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1 - 0.0% (32 Bytes)
[#011] sha256:e3cef9eee430c6cfe8d887a2af0da5854fe522ad74044125615b29dd40ecdc8f - 0.31% (32.3 MB)
[#012] sha256:a7994fb15187e268c42fccc9953480d7f8d14cf5b76369681a8458920a558da7 - 0.0% (150 Bytes)
[#013] sha256:8863b106fe98bba33a18ccac265c116c99a3e6866e2cb04707f6106976786765 - 0.0% (164 Bytes)
[#014] sha256:6590738717307581e50b1aec3365105136f4cb287a69f7553644c8446071ec20 - 0.0% (3.62 KB)
[#015] sha256:ba7ec876fa62fccf8ed119e8af03efceebe73f9e458cd6b1296a0edc03217310 - 0.0% (2.03 KB)
[#016] sha256:ba7ec876fa62fccf8ed119e8af03efceebe73f9e458cd6b1296a0edc03217310 - 0.0% (2.03 KB)
[#017] sha256:77b75abd69d2e134b2834097e66187f4d424809dceef1cfd15ed01329c305dc3 - 0.0% (1.7 KB)
[#018] sha256:cb94e1969a33b7a9b94f9edee067e65138149e51535bcd1f61a37b1a3fc5d398 - 0.0% (809 Bytes)
[#019] sha256:647a6a21599169ffcbb75cf04f0705e8f7912f27c76e2616a82afcad7f9d5f40 - 38.59% (3.92 GB)
[#020] sha256:73cefd0dd9f46278880b7977d3feb234647e1acce23efb6a20531d6a80b5b8db - 29.95% (3.04 GB)
[#021] sha256:6212cb9f55978aaa177127122aea1a5216c4640099fe44330d3c3f57c9dbde09 - 0.0% (897 Bytes)
[#022] sha256:ac1c39fe9ab62fc4c97d8a481f137eb7478f4799e19d52b65bab032e93dfd128 - 0.0% (519 KB)
[#023] sha256:7eba65abe6da2f37fdcf04e2473050818ab5384e77485e1e2623c39687fb2b7a - 2.65% (275 MB)
[#024] sha256:f23a72e08e87aa57659b14a96ba0470b38eb583eb7f795c076080e8003ba8898 - 0.0% (198 Bytes)
[#025] sha256:c2bf99e9a72b7737f917f8c369b090156ca14449bf4038b5d9ed62fe775374c5 - 0.0% (226 Bytes)
[#026] sha256:353109e1a1dc30887a28ea18658ed87827a452e89c1fa35935ac2d4348d019f3 - 5.26% (547 MB)
[#027] sha256:a3d2c083c44f76f12b876cf883c2b00a7ee74544ba33d2748bd52cf18ec12f38 - 0.0% (199 Bytes)
[#028] sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1 - 0.0% (32 Bytes)
[#029] sha256:f1ea6f4efa5ee092e5fe767a70a7141c0de05ba32fbb8d728e83390605375d09 - 0.0% (253 Bytes)
[#030] sha256:974610a5405bddb5da6a134e8c484b67fd3469ddfdb4a2ac4c0aa8d357a0303b - 0.15% (15.5 MB)
[#031] sha256:e0dcc5a5f1e188ad7cd697c131159f0df32c186d373cfeb63d9e34d3a1f70917 - 0.0% (315 KB)
[#032] sha256:31d62ce21f524bc3f2e1a5a8c124a1c4fb003cc5eb332b7655c3f0637380adc2 - 0.0% (303 KB)
[#033] sha256:ffa555bd69eaa0d2e20582e848c91a963ab81f79e57a3c3bc922d55b8d733c90 - 0.0% (9.61 KB)
[#034] sha256:c83f2b26dee8c7cc8bee3c1a9c6d709c43f9d12949409b024c091a4ef3ceaa4a - 5.1% (530 MB)
[#035] sha256:2706d73f509cedbbb3ca6065676fb78f619510b0fb9a1df2445f76a7d72c5513 - 0.0% (92 Bytes)
[#036] sha256:1c228a3e25a00bf6e440b0037e1e0b2dcd19f6e9d9455ebf2bada86649f53bdd - 0.0% (212 Bytes)
[#037] sha256:77153f72aebefce79f227783661ba551a224c8a7f5e1bf2469b1487d2f657744 - 0.0% (824 Bytes)
[#038] sha256:47383126f8e27bbeebfb28a98966574cf358bc468c78ccb0067e097ed9f642fe - 0.0% (183 Bytes)
[#039] sha256:9378911e5f472d95ded5be188e7c35a4da16da820582b23402369f63b4b71fb3 - 0.0% (92 Bytes)
History
/bin/sh -c #(nop) ARG RELEASE
2025-10-01 13:01:38 UTC/bin/sh -c #(nop) ARG LAUNCHPAD_BUILD_ARCH
2025-10-01 13:01:38 UTC/bin/sh -c #(nop) LABEL org.opencontainers.image.ref.name=ubuntu
2025-10-01 13:01:38 UTC/bin/sh -c #(nop) LABEL org.opencontainers.image.version=24.04
2025-10-01 13:01:40 UTC/bin/sh -c #(nop) ADD file:d77dea5c49828eb0de89439d2b631bc8ea27cb9ef774412b56a060ba1673487b in /
2025-10-01 13:01:40 UTC/bin/sh -c #(nop) CMD ["/bin/bash"]
2025-10-10 16:55:43 UTC (buildkit.dockerfile.v0)ENV NVARCH=sbsa
2025-10-10 16:55:43 UTC (buildkit.dockerfile.v0)ENV NVIDIA_REQUIRE_CUDA=cuda>=13.0 brand=unknown,driver>=535,driver<536 brand=grid,driver>=535,driver<536 brand=tesla,driver>=535,driver<536 brand=nvidia,driver>=535,driver<536 brand=quadro,driver>=535,driver<536 brand=quadrortx,driver>=535,driver<536 brand=nvidiartx,driver>=535,driver<536 brand=vapps,driver>=535,driver<536 brand=vpc,driver>=535,driver<536 brand=vcs,driver>=535,driver<536 brand=vws,driver>=535,driver<536 brand=cloudgaming,driver>=535,driver<536 brand=unknown,driver>=550,driver<551 brand=grid,driver>=550,driver<551 brand=tesla,driver>=550,driver<551 brand=nvidia,driver>=550,driver<551 brand=quadro,driver>=550,driver<551 brand=quadrortx,driver>=550,driver<551 brand=nvidiartx,driver>=550,driver<551 brand=vapps,driver>=550,driver<551 brand=vpc,driver>=550,driver<551 brand=vcs,driver>=550,driver<551 brand=vws,driver>=550,driver<551 brand=cloudgaming,driver>=550,driver<551 brand=unknown,driver>=565,driver<566 brand=grid,driver>=565,driver<566 brand=tesla,driver>=565,driver<566 brand=nvidia,driver>=565,driver<566 brand=quadro,driver>=565,driver<566 brand=quadrortx,driver>=565,driver<566 brand=nvidiartx,driver>=565,driver<566 brand=vapps,driver>=565,driver<566 brand=vpc,driver>=565,driver<566 brand=vcs,driver>=565,driver<566 brand=vws,driver>=565,driver<566 brand=cloudgaming,driver>=565,driver<566 brand=unknown,driver>=570,driver<571 brand=grid,driver>=570,driver<571 brand=tesla,driver>=570,driver<571 brand=nvidia,driver>=570,driver<571 brand=quadro,driver>=570,driver<571 brand=quadrortx,driver>=570,driver<571 brand=nvidiartx,driver>=570,driver<571 brand=vapps,driver>=570,driver<571 brand=vpc,driver>=570,driver<571 brand=vcs,driver>=570,driver<571 brand=vws,driver>=570,driver<571 brand=cloudgaming,driver>=570,driver<571 brand=unknown,driver>=575,driver<576 brand=grid,driver>=575,driver<576 brand=tesla,driver>=575,driver<576 brand=nvidia,driver>=575,driver<576 brand=quadro,driver>=575,driver<576 brand=quadrortx,driver>=575,driver<576 brand=nvidiartx,driver>=575,driver<576 brand=vapps,driver>=575,driver<576 brand=vpc,driver>=575,driver<576 brand=vcs,driver>=575,driver<576 brand=vws,driver>=575,driver<576 brand=cloudgaming,driver>=575,driver<576
2025-10-10 16:55:43 UTC (buildkit.dockerfile.v0)ENV NV_CUDA_CUDART_VERSION=13.0.96-1
2025-10-10 16:55:43 UTC (buildkit.dockerfile.v0)ARG TARGETARCH
2025-10-10 16:55:43 UTC (buildkit.dockerfile.v0)LABEL maintainer=NVIDIA CORPORATION <cudatools@nvidia.com>
2025-10-10 16:55:43 UTC (buildkit.dockerfile.v0)RUN |1 TARGETARCH=arm64 /bin/sh -c apt-get update && apt-get install -y --no-install-recommends gnupg2 curl ca-certificates && curl -fsSL https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2404/${NVARCH}/3bf863cc.pub | apt-key add - && echo "deb https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2404/${NVARCH} /" > /etc/apt/sources.list.d/cuda.list && apt-get purge --autoremove -y curl && rm -rf /var/lib/apt/lists/* # buildkit
2025-10-10 16:55:43 UTC (buildkit.dockerfile.v0)ENV CUDA_VERSION=13.0.2
2025-10-10 16:59:52 UTC (buildkit.dockerfile.v0)RUN |1 TARGETARCH=arm64 /bin/sh -c apt-get update && apt-get install -y --no-install-recommends cuda-cudart-13-0=${NV_CUDA_CUDART_VERSION} cuda-compat-13-0 && rm -rf /var/lib/apt/lists/* # buildkit
2025-10-10 16:59:52 UTC (buildkit.dockerfile.v0)RUN |1 TARGETARCH=arm64 /bin/sh -c echo "/usr/local/cuda/lib64" >> /etc/ld.so.conf.d/nvidia.conf # buildkit
2025-10-10 16:59:52 UTC (buildkit.dockerfile.v0)ENV PATH=/usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin
2025-10-10 16:59:52 UTC (buildkit.dockerfile.v0)ENV LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/local/cuda/lib64
2025-10-10 16:59:53 UTC (buildkit.dockerfile.v0)COPY NGC-DL-CONTAINER-LICENSE / # buildkit
2025-10-10 16:59:53 UTC (buildkit.dockerfile.v0)ENV NVIDIA_VISIBLE_DEVICES=all
2025-10-10 16:59:53 UTC (buildkit.dockerfile.v0)ENV NVIDIA_DRIVER_CAPABILITIES=compute,utility
2026-11-01 09:25:01 UTC (buildkit.dockerfile.v0)ARG INSTALL_RUBIN_PRERELEASE
2026-11-01 09:25:01 UTC (buildkit.dockerfile.v0)ARG TARGETPLATFORM
2026-11-01 09:25:01 UTC (buildkit.dockerfile.v0)ARG max_jobs=2
2026-11-01 09:25:01 UTC (buildkit.dockerfile.v0)ARG CUDA_VERSION
2026-11-01 09:25:01 UTC (buildkit.dockerfile.v0)ARG PYTHON_VERSION
2026-11-01 09:25:01 UTC (buildkit.dockerfile.v0)ARG NCCL_VERSION
2026-11-01 09:25:01 UTC (buildkit.dockerfile.v0)ARG DEADSNAKES_MIRROR_URL
2026-11-01 09:25:01 UTC (buildkit.dockerfile.v0)ARG DEADSNAKES_GPGKEY_URL
2026-11-01 09:25:01 UTC (buildkit.dockerfile.v0)ARG GET_PIP_URL
2026-11-01 09:25:01 UTC (buildkit.dockerfile.v0)ENV DEBIAN_FRONTEND=noninteractive
2026-11-01 09:25:01 UTC (buildkit.dockerfile.v0)WORKDIR /vllm-workspace
2026-11-01 09:25:02 UTC (buildkit.dockerfile.v0)RUN |9 INSTALL_RUBIN_PRERELEASE=false TARGETPLATFORM=linux/arm64 max_jobs=16 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 NCCL_VERSION=2.31.2 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py /bin/sh -c PYTHON_VERSION_STR=$(echo ${PYTHON_VERSION} | sed 's/\.//g') && echo "export PYTHON_VERSION_STR=${PYTHON_VERSION_STR}" >> /etc/environment # buildkit
2026-11-01 09:25:56 UTC (buildkit.dockerfile.v0)RUN |9 INSTALL_RUBIN_PRERELEASE=false TARGETPLATFORM=linux/arm64 max_jobs=16 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 NCCL_VERSION=2.31.2 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py /bin/sh -c apt-get update -y && apt-get install -y --no-install-recommends ca-certificates software-properties-common curl sudo ffmpeg libsm6 libxext6 libgl1 && if [ ! -z ${DEADSNAKES_MIRROR_URL} ] ; then if [ ! -z "${DEADSNAKES_GPGKEY_URL}" ] ; then mkdir -p -m 0755 /etc/apt/keyrings ; curl -L ${DEADSNAKES_GPGKEY_URL} | gpg --dearmor > /etc/apt/keyrings/deadsnakes.gpg ; sudo chmod 644 /etc/apt/keyrings/deadsnakes.gpg ; echo "deb [signed-by=/etc/apt/keyrings/deadsnakes.gpg] ${DEADSNAKES_MIRROR_URL} $(lsb_release -cs) main" > /etc/apt/sources.list.d/deadsnakes.list ; fi ; else for i in 1 2 3; do add-apt-repository -y ppa:deadsnakes/ppa && break || { echo "Attempt $i failed, retrying in 5s..."; sleep 5; }; done ; fi && apt-get update -y && apt-get install -y --no-install-recommends python${PYTHON_VERSION} python${PYTHON_VERSION}-dev python${PYTHON_VERSION}-venv libibverbs-dev && rm -rf /var/lib/apt/lists/* && update-alternatives --install /usr/bin/python3 python3 /usr/bin/python${PYTHON_VERSION} 1 && update-alternatives --set python3 /usr/bin/python${PYTHON_VERSION} && ln -sf /usr/bin/python${PYTHON_VERSION}-config /usr/bin/python3-config && rm -f /usr/lib/python${PYTHON_VERSION}/EXTERNALLY-MANAGED && curl -sS ${GET_PIP_URL} | python${PYTHON_VERSION} && python3 --version && python3 -m pip --version # buildkit
2026-11-01 09:26:41 UTC (buildkit.dockerfile.v0)RUN |9 INSTALL_RUBIN_PRERELEASE=false TARGETPLATFORM=linux/arm64 max_jobs=16 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 NCCL_VERSION=2.31.2 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py /bin/sh -c CUDA_VERSION_DASH=$(echo $CUDA_VERSION | cut -d. -f1,2 | tr '.' '-') && apt-get update -y && apt-get install -y --no-install-recommends --allow-change-held-packages cuda-nvcc-${CUDA_VERSION_DASH} cuda-cudart-${CUDA_VERSION_DASH} cuda-nvrtc-${CUDA_VERSION_DASH} cuda-nvrtc-dev-${CUDA_VERSION_DASH} cuda-cuobjdump-${CUDA_VERSION_DASH} libcurand-dev-${CUDA_VERSION_DASH} libcublas-dev-${CUDA_VERSION_DASH} libnuma-dev numactl && rm -rf /var/lib/apt/lists/* # buildkit
2026-11-01 09:26:41 UTC (buildkit.dockerfile.v0)ENV CUDA_HOME=/usr/local/cuda
2026-11-01 09:26:41 UTC (buildkit.dockerfile.v0)ENV PATH=/usr/local/cuda/bin:/usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin
2026-11-01 09:26:41 UTC (buildkit.dockerfile.v0)ENV LD_LIBRARY_PATH=/usr/local/cuda/lib64:/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/local/cuda/lib64
2026-11-01 09:26:41 UTC (buildkit.dockerfile.v0)COPY tools/install_snapshot_runtime.sh /usr/local/bin/install_snapshot_runtime.sh # buildkit
2026-11-01 09:26:42 UTC (buildkit.dockerfile.v0)RUN |9 INSTALL_RUBIN_PRERELEASE=false TARGETPLATFORM=linux/arm64 max_jobs=16 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 NCCL_VERSION=2.31.2 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py /bin/sh -c if [ "${TARGETPLATFORM}" = "linux/amd64" ] && [ "${CUDA_VERSION%%.*}" -ge 13 ]; then MAX_JOBS="${max_jobs}" /usr/local/bin/install_snapshot_runtime.sh; else echo "Initialized snapshots are not installed for ${TARGETPLATFORM} with CUDA ${CUDA_VERSION}"; fi # buildkit
2026-11-01 09:26:42 UTC (buildkit.dockerfile.v0)ENV CRIU_CUDA_PLUGIN_DIR=/usr/local/lib/criu
2026-11-01 09:26:44 UTC (buildkit.dockerfile.v0)RUN |9 INSTALL_RUBIN_PRERELEASE=false TARGETPLATFORM=linux/arm64 max_jobs=16 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 NCCL_VERSION=2.31.2 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py /bin/sh -c python3 -m pip install uv # buildkit
2026-11-01 09:26:44 UTC (buildkit.dockerfile.v0)ENV UV_HTTP_TIMEOUT=500
2026-11-01 09:26:44 UTC (buildkit.dockerfile.v0)ENV UV_INDEX_STRATEGY=unsafe-best-match
2026-11-01 09:26:44 UTC (buildkit.dockerfile.v0)ENV UV_LINK_MODE=copy
2026-11-01 09:26:44 UTC (buildkit.dockerfile.v0)ENV UV_PYTHON_INSTALL_DIR=/opt/uv/python
2026-11-01 09:26:44 UTC (buildkit.dockerfile.v0)ENV UV_CACHE_DIR=/opt/uv/cache
2026-11-01 09:26:44 UTC (buildkit.dockerfile.v0)ENV UV_COMPILE_BYTECODE=1
2026-11-01 09:26:44 UTC (buildkit.dockerfile.v0)RUN |9 INSTALL_RUBIN_PRERELEASE=false TARGETPLATFORM=linux/arm64 max_jobs=16 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 NCCL_VERSION=2.31.2 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py /bin/sh -c mkdir -p "${UV_PYTHON_INSTALL_DIR}" "${UV_CACHE_DIR}" && chgrp -R 0 /opt/uv && chmod -R g+rwX,a+rX /opt/uv # buildkit
2026-11-01 09:26:45 UTC (buildkit.dockerfile.v0)RUN |9 INSTALL_RUBIN_PRERELEASE=false TARGETPLATFORM=linux/arm64 max_jobs=16 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 NCCL_VERSION=2.31.2 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py /bin/sh -c CUDA_MAJOR=$(echo $CUDA_VERSION | cut -d. -f1) && if [ -n "$NCCL_VERSION" ]; then echo "nvidia-nccl-cu${CUDA_MAJOR}==${NCCL_VERSION}" > /etc/uv-overrides.txt; else touch /etc/uv-overrides.txt; fi # buildkit
2026-11-01 09:26:45 UTC (buildkit.dockerfile.v0)ENV UV_OVERRIDE=/etc/uv-overrides.txt
2026-11-01 09:26:46 UTC (buildkit.dockerfile.v0)RUN |9 INSTALL_RUBIN_PRERELEASE=false TARGETPLATFORM=linux/arm64 max_jobs=16 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 NCCL_VERSION=2.31.2 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py /bin/sh -c useradd --uid 2000 --gid 0 --create-home --home-dir /home/vllm --shell /bin/bash vllm && mkdir -p /home/vllm/.cache /home/vllm/.config && chown -R 2000:0 /home/vllm && chmod -R g+rwX /home/vllm && chgrp 0 /etc/passwd /etc/group && chmod g=u /etc/passwd /etc/group # buildkit
2026-11-01 09:26:46 UTC (buildkit.dockerfile.v0)COPY docker/entrypoints/vllm-nonroot-entrypoint.sh /usr/local/bin/vllm-nonroot-entrypoint.sh # buildkit
2026-11-01 09:26:47 UTC (buildkit.dockerfile.v0)RUN |9 INSTALL_RUBIN_PRERELEASE=false TARGETPLATFORM=linux/arm64 max_jobs=16 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 NCCL_VERSION=2.31.2 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py /bin/sh -c chmod 0755 /usr/local/bin/vllm-nonroot-entrypoint.sh # buildkit
2026-11-01 09:26:47 UTC (buildkit.dockerfile.v0)ENV VLLM_ENABLE_CUDA_COMPATIBILITY=0
2026-11-01 09:26:47 UTC (buildkit.dockerfile.v0)ARG PYTORCH_CUDA_INDEX_BASE_URL
2026-11-01 09:26:47 UTC (buildkit.dockerfile.v0)COPY requirements/common.txt /tmp/common.txt # buildkit
2026-11-01 09:26:47 UTC (buildkit.dockerfile.v0)COPY requirements/cuda.txt /tmp/requirements-cuda.txt # buildkit
2026-11-01 09:27:14 UTC (buildkit.dockerfile.v0)RUN |10 INSTALL_RUBIN_PRERELEASE=false TARGETPLATFORM=linux/arm64 max_jobs=16 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 NCCL_VERSION=2.31.2 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl /bin/sh -c if [ "${INSTALL_RUBIN_PRERELEASE}" = "true" ] && [ ! -f /tmp/vllm-requirements/rubin-prerelease.txt ]; then echo "INSTALL_RUBIN_PRERELEASE=true requires requirements/rubin-prerelease.txt" >&2; exit 1; fi && if [ "$(echo $CUDA_VERSION | cut -d. -f1)" = "12" ]; then sed -i 's/^nvidia-cutlass-dsl\[cu13\]/nvidia-cutlass-dsl/' /tmp/requirements-cuda.txt; sed -i 's/^humming-kernels\[cu13\]/humming-kernels[cu12]/' /tmp/requirements-cuda.txt; fi && if [ "${INSTALL_RUBIN_PRERELEASE}" = "true" ]; then uv pip install --system --prerelease=allow --index-strategy unsafe-first-match -r /tmp/vllm-requirements/rubin-prerelease.txt && sed -Ei '/^[[:space:]]*(torch|torchvision|torchaudio)[[:space:]]*==/Id' /tmp/requirements-cuda.txt && uv pip install --system -r /tmp/requirements-cuda.txt && uv pip install --system --prerelease=allow --index-strategy unsafe-first-match -r /tmp/vllm-requirements/rubin-prerelease.txt; else uv pip install --system -r /tmp/requirements-cuda.txt --extra-index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.'); fi && rm /tmp/requirements-cuda.txt /tmp/common.txt # buildkit
2026-11-01 09:28:22 UTC (buildkit.dockerfile.v0)RUN |10 INSTALL_RUBIN_PRERELEASE=false TARGETPLATFORM=linux/arm64 max_jobs=16 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 NCCL_VERSION=2.31.2 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl /bin/sh -c PIP_CACHE_DIR=/opt/pip/cache flashinfer download-kernels # buildkit
2026-11-01 09:28:22 UTC (buildkit.dockerfile.v0)ARG GDRCOPY_CUDA_VERSION=12.8
2026-11-01 09:28:22 UTC (buildkit.dockerfile.v0)ARG GDRCOPY_OS_VERSION=Ubuntu24_04
2026-11-01 09:28:22 UTC (buildkit.dockerfile.v0)ARG TARGETPLATFORM
2026-11-01 09:28:23 UTC (buildkit.dockerfile.v0)COPY tools/install_gdrcopy.sh /tmp/install_gdrcopy.sh # buildkit
2026-11-01 09:28:28 UTC (buildkit.dockerfile.v0)RUN |13 INSTALL_RUBIN_PRERELEASE=false TARGETPLATFORM=linux/arm64 max_jobs=16 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 NCCL_VERSION=2.31.2 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl GDRCOPY_CUDA_VERSION=12.8 GDRCOPY_OS_VERSION=Ubuntu24_04 TARGETPLATFORM=linux/arm64 /bin/sh -c set -eux; case "${TARGETPLATFORM}" in linux/arm64) UUARCH="aarch64" ;; linux/amd64) UUARCH="x64" ;; *) echo "Unsupported TARGETPLATFORM: ${TARGETPLATFORM}" >&2; exit 1 ;; esac; /tmp/install_gdrcopy.sh "${GDRCOPY_OS_VERSION}" "${GDRCOPY_CUDA_VERSION}" "${UUARCH}" && rm /tmp/install_gdrcopy.sh # buildkit
2026-11-01 09:28:28 UTC (buildkit.dockerfile.v0)ARG TIMM_VERSION=>=1.0.17
2026-11-01 09:28:28 UTC (buildkit.dockerfile.v0)ARG RUNAI_MODEL_STREAMER_VERSION=>=0.15.7
2026-11-01 09:28:28 UTC (buildkit.dockerfile.v0)ARG GGUF_VERSION=>=0.19.0
2026-11-01 09:28:32 UTC (buildkit.dockerfile.v0)RUN |16 INSTALL_RUBIN_PRERELEASE=false TARGETPLATFORM=linux/arm64 max_jobs=16 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 NCCL_VERSION=2.31.2 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl GDRCOPY_CUDA_VERSION=12.8 GDRCOPY_OS_VERSION=Ubuntu24_04 TARGETPLATFORM=linux/arm64 TIMM_VERSION=>=1.0.17 RUNAI_MODEL_STREAMER_VERSION=>=0.15.7 GGUF_VERSION=>=0.19.0 /bin/sh -c uv pip install --system accelerate 'modelscope<1.38' "timm${TIMM_VERSION}" "runai-model-streamer[s3,gcs,azure]${RUNAI_MODEL_STREAMER_VERSION}" "gguf${GGUF_VERSION}" # buildkit
2026-11-01 09:28:32 UTC (buildkit.dockerfile.v0)ARG PIP_INDEX_URL UV_INDEX_URL
2026-11-01 09:28:32 UTC (buildkit.dockerfile.v0)ARG PIP_EXTRA_INDEX_URL UV_EXTRA_INDEX_URL
2026-11-01 09:28:32 UTC (buildkit.dockerfile.v0)ARG PYTORCH_CUDA_INDEX_BASE_URL
2026-11-01 09:28:32 UTC (buildkit.dockerfile.v0)ARG PIP_KEYRING_PROVIDER UV_KEYRING_PROVIDER
2026-11-01 09:28:32 UTC (buildkit.dockerfile.v0)ARG PYTORCH_NIGHTLY
2026-11-01 09:40:47 UTC (buildkit.dockerfile.v0)COPY /workspace/torch_lib_versions.txt torch_lib_versions.txt # buildkit
2026-11-01 09:57:02 UTC (buildkit.dockerfile.v0)COPY /workspace/dist/wheel.sha256 /tmp/vllm-wheel.sha256 # buildkit
2026-11-01 09:57:06 UTC (buildkit.dockerfile.v0)RUN |8 PIP_INDEX_URL= UV_INDEX_URL= PIP_EXTRA_INDEX_URL= UV_EXTRA_INDEX_URL= PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl PIP_KEYRING_PROVIDER=disabled UV_KEYRING_PROVIDER=disabled PYTORCH_NIGHTLY= /bin/sh -c if [ "${PYTORCH_NIGHTLY}" = "1" ]; then echo "Installing torch nightly..." && uv pip install --system $(cat torch_lib_versions.txt | xargs) --pre --index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/nightly/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.') && echo "Installing vLLM..." && uv pip install --system dist/*.whl --verbose --extra-index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/nightly/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.'); else echo "Installing vLLM..." && uv pip install --system dist/*.whl --verbose --extra-index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.'); fi # buildkit
2026-11-01 09:57:07 UTC (buildkit.dockerfile.v0)RUN |8 PIP_INDEX_URL= UV_INDEX_URL= PIP_EXTRA_INDEX_URL= UV_EXTRA_INDEX_URL= PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl PIP_KEYRING_PROVIDER=disabled UV_KEYRING_PROVIDER=disabled PYTORCH_NIGHTLY= /bin/sh -c ln -s "$(python3 -c 'import sysconfig; print(sysconfig.get_path("platlib"))')/vllm/vllm-rs" /usr/local/bin/vllm-rs && vllm-rs --version # buildkit
2026-11-01 09:57:08 UTC (buildkit.dockerfile.v0)RUN |8 PIP_INDEX_URL= UV_INDEX_URL= PIP_EXTRA_INDEX_URL= UV_EXTRA_INDEX_URL= PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl PIP_KEYRING_PROVIDER=disabled UV_KEYRING_PROVIDER=disabled PYTORCH_NIGHTLY= /bin/sh -c . /etc/environment && uv pip list # buildkit
2026-11-01 09:57:08 UTC (buildkit.dockerfile.v0)ENV LD_LIBRARY_PATH=/usr/local/cuda/lib64:/usr/local/cuda/lib64:/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/local/cuda/lib64
2026-11-01 09:57:08 UTC (buildkit.dockerfile.v0)COPY /tmp/ep_kernels_workspace/dist/wheels.sha256 /tmp/ep-kernels-wheels.sha256 # buildkit
2026-11-01 09:57:09 UTC (buildkit.dockerfile.v0)RUN |8 PIP_INDEX_URL= UV_INDEX_URL= PIP_EXTRA_INDEX_URL= UV_EXTRA_INDEX_URL= PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl PIP_KEYRING_PROVIDER=disabled UV_KEYRING_PROVIDER=disabled PYTORCH_NIGHTLY= /bin/sh -c uv pip install --system ep_kernels/dist/*.whl --verbose --extra-index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.') # buildkit
2026-11-01 09:57:09 UTC (buildkit.dockerfile.v0)ENV LD_LIBRARY_PATH=/usr/local/nvidia/lib64:/usr/local/cuda/lib64:/usr/local/cuda/lib64:/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/local/cuda/lib64
2026-11-01 09:57:09 UTC (buildkit.dockerfile.v0)COPY examples examples # buildkit
2026-11-01 09:57:09 UTC (buildkit.dockerfile.v0)COPY benchmarks benchmarks # buildkit
2026-11-01 09:57:09 UTC (buildkit.dockerfile.v0)COPY ./vllm/collect_env.py . # buildkit
2026-11-01 09:57:09 UTC (buildkit.dockerfile.v0)ARG TARGETPLATFORM
2026-11-01 09:57:09 UTC (buildkit.dockerfile.v0)ARG INSTALL_KV_CONNECTORS=false
2026-11-01 09:57:09 UTC (buildkit.dockerfile.v0)ARG INSTALL_RUBIN_PRERELEASE
2026-11-01 09:57:09 UTC (buildkit.dockerfile.v0)ARG TRITON_INSTALL_FROM_SOURCE_REPO
2026-11-01 09:57:09 UTC (buildkit.dockerfile.v0)ARG CUDA_VERSION
2026-11-01 09:57:09 UTC (buildkit.dockerfile.v0)ARG VLLM_BUILD_COMMIT
2026-11-01 09:57:09 UTC (buildkit.dockerfile.v0)ARG VLLM_BUILD_PIPELINE
2026-11-01 09:57:09 UTC (buildkit.dockerfile.v0)ARG VLLM_BUILD_URL
2026-11-01 09:57:09 UTC (buildkit.dockerfile.v0)ARG VLLM_IMAGE_TAG
2026-11-01 09:57:09 UTC (buildkit.dockerfile.v0)ARG PIP_INDEX_URL UV_INDEX_URL
2026-11-01 09:57:09 UTC (buildkit.dockerfile.v0)ARG PIP_EXTRA_INDEX_URL UV_EXTRA_INDEX_URL
2026-11-01 09:57:09 UTC (buildkit.dockerfile.v0)ENV UV_HTTP_TIMEOUT=500
2026-11-01 09:57:09 UTC (buildkit.dockerfile.v0)ARG torch_cuda_arch_list=7.5 8.0 8.6 8.9 9.0 10.0 11.0 12.0
2026-11-01 09:57:09 UTC (buildkit.dockerfile.v0)ENV TORCH_CUDA_ARCH_LIST=8.0 8.7 8.9 9.0 10.0 11.0 12.0
2026-11-01 09:57:15 UTC (buildkit.dockerfile.v0)RUN |14 TARGETPLATFORM=linux/arm64 INSTALL_KV_CONNECTORS=true INSTALL_RUBIN_PRERELEASE=false TRITON_INSTALL_FROM_SOURCE_REPO= CUDA_VERSION=13.0.2 VLLM_BUILD_COMMIT=4ba787ec9959e566d3b587a796dff07673324da5 VLLM_BUILD_PIPELINE=019d130e-464e-4ff7-b84b-492992c0c06b VLLM_BUILD_URL=https://buildkite.com/vllm/release-v2/builds/9673 VLLM_IMAGE_TAG=vllm/vllm-openai:v0.33.0 PIP_INDEX_URL= UV_INDEX_URL= PIP_EXTRA_INDEX_URL= UV_EXTRA_INDEX_URL= torch_cuda_arch_list=8.0 8.7 8.9 9.0 10.0 11.0 12.0 /bin/sh -c set -eu; CUDA_MAJOR="${CUDA_VERSION%%.*}"; CUDA_VERSION_DASH=$(echo $CUDA_VERSION | cut -d. -f1,2 | tr '.' '-'); CUDA_HOME=/usr/local/cuda; BUILD_PKGS="libcusparse-dev-${CUDA_VERSION_DASH} libcublas-dev-${CUDA_VERSION_DASH} libcusolver-dev-${CUDA_VERSION_DASH}"; if [ "$INSTALL_KV_CONNECTORS" = "true" ]; then KV_REQUIREMENTS=/tmp/vllm-requirements/kv_connectors.txt; if [ "${CUDA_MAJOR}" = "12" ]; then KV_REQUIREMENTS=/tmp/vllm-requirements/kv_connectors_cu12.txt; fi; uv pip freeze --system > /tmp/kv-installed.txt; grep -E '^(torch|torchaudio|torchvision|triton|cuda-bindings|cuda-python|cuda-toolkit)==' /tmp/kv-installed.txt > /tmp/kv-constraints.txt; uv pip install --system -c /tmp/kv-constraints.txt -r "${KV_REQUIREMENTS}" --no-build || ( apt-get update -y && apt-get install -y --no-install-recommends --allow-change-held-packages ${BUILD_PKGS} && uv pip install --system -c /tmp/kv-constraints.txt -r "${KV_REQUIREMENTS}" --no-build-isolation && apt-get purge -y ${BUILD_PKGS} && rm -rf /var/lib/apt/lists/* ); MOONCAKE_VERSION=$(python3 -c "import importlib.metadata as m; print(m.version('mooncake-transfer-engine'))" 2>/dev/null || true) && if [ "${CUDA_MAJOR}" = "13" ] && [ -n "${MOONCAKE_VERSION}" ]; then uv pip uninstall --system mooncake-transfer-engine 2>/dev/null || true; uv pip install --system -c /tmp/kv-constraints.txt "mooncake-transfer-engine-cuda13==${MOONCAKE_VERSION}"; fi; rm -f /tmp/kv-installed.txt /tmp/kv-constraints.txt; fi # buildkit
2026-11-01 09:57:15 UTC (buildkit.dockerfile.v0)RUN |14 TARGETPLATFORM=linux/arm64 INSTALL_KV_CONNECTORS=true INSTALL_RUBIN_PRERELEASE=false TRITON_INSTALL_FROM_SOURCE_REPO= CUDA_VERSION=13.0.2 VLLM_BUILD_COMMIT=4ba787ec9959e566d3b587a796dff07673324da5 VLLM_BUILD_PIPELINE=019d130e-464e-4ff7-b84b-492992c0c06b VLLM_BUILD_URL=https://buildkite.com/vllm/release-v2/builds/9673 VLLM_IMAGE_TAG=vllm/vllm-openai:v0.33.0 PIP_INDEX_URL= UV_INDEX_URL= PIP_EXTRA_INDEX_URL= UV_EXTRA_INDEX_URL= torch_cuda_arch_list=8.0 8.7 8.9 9.0 10.0 11.0 12.0 /bin/sh -c if [ "${INSTALL_RUBIN_PRERELEASE}" = "true" ]; then echo "Installing Rubin prerelease requirements..." && uv pip install --system --prerelease=allow --index-strategy unsafe-first-match -r /tmp/vllm-requirements/rubin-prerelease.txt; fi # buildkit
2026-11-01 09:57:15 UTC (buildkit.dockerfile.v0)COPY /tmp/triton_from_source_workspace/dist/wheel.sha256 /tmp/triton-source-wheel.sha256 # buildkit
2026-11-01 09:57:15 UTC (buildkit.dockerfile.v0)COPY tools/install_triton_from_source.sh /tmp/install_triton_from_source.sh # buildkit
2026-11-01 09:57:16 UTC (buildkit.dockerfile.v0)RUN |14 TARGETPLATFORM=linux/arm64 INSTALL_KV_CONNECTORS=true INSTALL_RUBIN_PRERELEASE=false TRITON_INSTALL_FROM_SOURCE_REPO= CUDA_VERSION=13.0.2 VLLM_BUILD_COMMIT=4ba787ec9959e566d3b587a796dff07673324da5 VLLM_BUILD_PIPELINE=019d130e-464e-4ff7-b84b-492992c0c06b VLLM_BUILD_URL=https://buildkite.com/vllm/release-v2/builds/9673 VLLM_IMAGE_TAG=vllm/vllm-openai:v0.33.0 PIP_INDEX_URL= UV_INDEX_URL= PIP_EXTRA_INDEX_URL= UV_EXTRA_INDEX_URL= torch_cuda_arch_list=8.0 8.7 8.9 9.0 10.0 11.0 12.0 /bin/sh -c if [ -n "${TRITON_INSTALL_FROM_SOURCE_REPO}" ]; then CUDA_MAJOR_MINOR=$(echo "${CUDA_VERSION}" | cut -d. -f1,2); if [ "${INSTALL_RUBIN_PRERELEASE}" = "true" ]; then case "${CUDA_MAJOR_MINOR}" in 13.4|13.5) TRITON_SYSTEM_PTXAS_PATH=/usr/local/cuda/bin/ptxas TRITON_EXPECTED_PTXAS_VERSION="${CUDA_MAJOR_MINOR}" bash /tmp/install_triton_from_source.sh /tmp/triton-source-dist /tmp/triton-source-wheel.sha256 ;; *) echo "Unsupported Rubin CUDA version: ${CUDA_MAJOR_MINOR}" >&2; exit 1 ;; esac; else bash /tmp/install_triton_from_source.sh /tmp/triton-source-dist /tmp/triton-source-wheel.sha256; fi; fi && rm -f /tmp/install_triton_from_source.sh /tmp/triton-source-wheel.sha256 # buildkit
2026-11-01 09:57:16 UTC (buildkit.dockerfile.v0)ARG BUILD_NIXL
2026-11-01 09:57:17 UTC (buildkit.dockerfile.v0)RUN |15 TARGETPLATFORM=linux/arm64 INSTALL_KV_CONNECTORS=true INSTALL_RUBIN_PRERELEASE=false TRITON_INSTALL_FROM_SOURCE_REPO= CUDA_VERSION=13.0.2 VLLM_BUILD_COMMIT=4ba787ec9959e566d3b587a796dff07673324da5 VLLM_BUILD_PIPELINE=019d130e-464e-4ff7-b84b-492992c0c06b VLLM_BUILD_URL=https://buildkite.com/vllm/release-v2/builds/9673 VLLM_IMAGE_TAG=vllm/vllm-openai:v0.33.0 PIP_INDEX_URL= UV_INDEX_URL= PIP_EXTRA_INDEX_URL= UV_EXTRA_INDEX_URL= torch_cuda_arch_list=8.0 8.7 8.9 9.0 10.0 11.0 12.0 BUILD_NIXL=false /bin/sh -c set -eu; if [ "${BUILD_NIXL}" = "true" ]; then ls /tmp/nixl-dist/*.whl; uv pip uninstall --system nixl nixl-cu12 nixl-cu13; uv pip install --system --no-deps /tmp/nixl-dist/*.whl; python3 -c "import glob, importlib.util as u, os, torch; spec = u.find_spec('nixl_ep_cu' + os.environ['CUDA_VERSION'].split('.')[0]); mm = ''.join(torch.__version__.split('.')[:2]); ext = glob.glob(os.path.join(spec.submodule_search_locations[0], 'nixl_ep_cpp_torch' + mm + '.*')) if spec else []; assert ext, 'NIXL EP has no build for torch ' + torch.__version__; print('NIXL EP extension:', ext[0])"; fi # buildkit
2026-11-01 09:57:17 UTC (buildkit.dockerfile.v0)ENV VLLM_USAGE_SOURCE=production-docker-image
2026-11-01 09:57:17 UTC (buildkit.dockerfile.v0)ENV VLLM_BUILD_COMMIT=4ba787ec9959e566d3b587a796dff07673324da5 VLLM_BUILD_PIPELINE=019d130e-464e-4ff7-b84b-492992c0c06b VLLM_BUILD_URL=https://buildkite.com/vllm/release-v2/builds/9673 VLLM_IMAGE_TAG=vllm/vllm-openai:v0.33.0
2026-11-01 09:57:17 UTC (buildkit.dockerfile.v0)LABEL org.opencontainers.image.source=https://github.com/vllm-project/vllm org.opencontainers.image.revision=4ba787ec9959e566d3b587a796dff07673324da5 org.opencontainers.image.version=vllm/vllm-openai:v0.33.0 org.opencontainers.image.url=https://buildkite.com/vllm/release-v2/builds/9673 ai.vllm.build.commit=4ba787ec9959e566d3b587a796dff07673324da5 ai.vllm.build.pipeline=019d130e-464e-4ff7-b84b-492992c0c06b ai.vllm.build.url=https://buildkite.com/vllm/release-v2/builds/9673 ai.vllm.image.tag=vllm/vllm-openai:v0.33.0
2026-11-01 09:57:17 UTC (buildkit.dockerfile.v0)ENTRYPOINT ["vllm" "serve"]
Delete Tag
Please be careful as this will not just delete the reference but also the actual content!
For example when you have latest and v1.2.3 both pointing to the same image
the deletion of latest will also permanently remove v1.2.3.