Namespace
vllm
Image / Tag
vllm-openai:nightly-aarch64
Content Digest
sha256:aa0e81342ffe09122ea38360876e0cf4a58d06a5e6405e678fc3681b7f65a261
Details
Created

2026-05-11 06:49:49 UTC

Size

9.21 GB

Content Digest
Labels
  • ai.vllm.build.commit
    5536fc0c019db9b1f42afcc18fc38f4666b65e23
  • ai.vllm.build.pipeline
    019d130e-464e-4ff7-b84b-492992c0c06b
  • ai.vllm.build.url
    https://buildkite.com/vllm/release-v2/builds/1468
  • ai.vllm.image.tag
    vllm/vllm-openai:nightly-5536fc0c019db9b1f42afcc18fc38f4666b65e23
  • maintainer
    NVIDIA CORPORATION <cudatools@nvidia.com>
  • org.opencontainers.image.ref.name
    ubuntu
  • org.opencontainers.image.revision
    5536fc0c019db9b1f42afcc18fc38f4666b65e23
  • org.opencontainers.image.source
    https://github.com/vllm-project/vllm
  • org.opencontainers.image.url
    https://buildkite.com/vllm/release-v2/builds/1468
  • org.opencontainers.image.version
    vllm/vllm-openai:nightly-5536fc0c019db9b1f42afcc18fc38f4666b65e23

Environment
CUDA_VERSION

13.0.2

DEBIAN_FRONTEND

noninteractive

LD_LIBRARY_PATH

/usr/local/nvidia/lib64:/usr/local/cuda/lib64:/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/local/cuda/lib64

NVARCH

sbsa

NVIDIA_DRIVER_CAPABILITIES

compute,utility

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

NVIDIA_VISIBLE_DEVICES

all

NV_CUDA_CUDART_VERSION

13.0.96-1

PATH

/usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin

TORCH_CUDA_ARCH_LIST

8.0 8.7 8.9 9.0 10.0 11.0 12.0+PTX

UV_HTTP_TIMEOUT

500

UV_INDEX_STRATEGY

unsafe-best-match

UV_LINK_MODE

copy

VLLM_BUILD_COMMIT

5536fc0c019db9b1f42afcc18fc38f4666b65e23

VLLM_BUILD_PIPELINE

019d130e-464e-4ff7-b84b-492992c0c06b

VLLM_BUILD_URL

https://buildkite.com/vllm/release-v2/builds/1468

VLLM_ENABLE_CUDA_COMPATIBILITY

0

VLLM_IMAGE_TAG

vllm/vllm-openai:nightly-5536fc0c019db9b1f42afcc18fc38f4666b65e23

VLLM_USAGE_SOURCE

production-docker-image


Layers

[#000] sha256:12403f88a1054ff59ff86fb6c6623e916416a7d213639ca666b53d4400c5cc9a - 0.29% (27.1 MB)

[#001] sha256:c327bf13a03a6e91b0e93c9c86f548fd414d3bab9e53a09ab840a78827a3bde5 - 0.05% (4.38 MB)

[#002] sha256:5c04029b1239fd11e9779003e6bd46610f115cc00779d78227f6d4dd1a6fb2fd - 1.01% (95.1 MB)

[#003] sha256:cadec1e9319420ae0d1db1e735e489edb0f6b33dea6b03cd95ea82e5d9c1f112 - 0.0% (186 Bytes)

[#004] sha256:526d5438c009ab7178af1646fed10ff6f47a73f5a1ae7b9f49e63e4ade7e3ae6 - 0.0% (6.72 KB)

[#005] sha256:a7b134a27ca37851923acb784c3764033d9aed3b4afde925ac5c0ae222875785 - 0.0% (104 Bytes)

[#006] sha256:620fea8278ac129ecf892f30dd0e73b74a19623aee315773162db1bfdc232eec - 0.0% (229 Bytes)

[#007] sha256:7b4221cc83467493d3dc56afe7d0873e1688500001651bc079f9e77cfab16daf - 2.11% (199 MB)

[#008] sha256:4b1d55ad7d791964f80485fe4cb5d00fe034a59a1bdd9e7b1e24048227cc13b0 - 19.37% (1.78 GB)

[#009] sha256:f37a8c88a212a153f74098d1462e8d2d09a76e35350b45e176c6fa27198ed909 - 0.48% (45.3 MB)

[#010] sha256:eb7ab9677aace6e1b07d3f80dcbcc98bd41639fc8bbcf2323666a89d22e3a826 - 0.0% (1.52 KB)

[#011] sha256:46014fe06fe8248e514e27efed3802f9a669421f27dd8ae74140dac9bbe94961 - 0.0% (626 Bytes)

[#012] sha256:40a621193b2752db5feb00a1c7b18b244ae3256b2e9ea6be23fae9450c373fb1 - 35.75% (3.29 GB)

[#013] sha256:e4e1af5f846b319a8d7ec95091196f257b16575e3691232d22ae31246865eab6 - 20.87% (1.92 GB)

[#014] sha256:69704777712920d431903066cc28399cb975249f0ddcfeca095d99da4c3aeaaf - 0.0% (896 Bytes)

[#015] sha256:d1b32fbec204e763851d517ed409318de5491f446b90d753dedabe2ef10e8ea0 - 0.01% (521 KB)

[#016] sha256:83f02e63c742798e2f3c7787ff5d2fb5b66b6e45e2c965ec1104fbea7bbf5fd0 - 3.18% (300 MB)

[#017] sha256:d91e3ffe4fe74738faa64a1dcf74e90ff4237981d656ff667d64a695cec8e2ac - 0.0% (198 Bytes)

[#018] sha256:ac903531f0d1a250564a3a6fe61fb51e55d68a9ebad2637464ce648dc2d4468f - 4.59% (433 MB)

[#019] sha256:3a5acc23b64f61ebc8ad82a76ebe1f4138e7501a9c7a2730b21965326186dddd - 0.0% (123 Bytes)

[#020] sha256:0fa114a78aab1e527ff8699273be3ede02ac7ee130adf23ff0fde74019b7b9b2 - 0.12% (10.9 MB)

[#021] sha256:0f1db09a37bd0b6ab3b3bb18378b08e10a90026fdfa92a88a4d7e166aa2bfe51 - 3.04% (286 MB)

[#022] sha256:616d9c7aa388fa692b36fb9dfa7c567233b031898ed6df1b0780805f85ec3d90 - 0.0% (249 KB)

[#023] sha256:43226cc455061bb9444371e2c654ce46ab155b3fc25edb47bce32361a59055cf - 0.0% (226 KB)

[#024] sha256:ad95c4ccd415f33af7e40ce48520f9316b141b893a70767220cb42fd4222edf1 - 0.0% (9.62 KB)

[#025] sha256:a5f129e74653fafe555a2e5004cc8c870576247e39901436640ce13c498f6ded - 9.14% (862 MB)


History
2025-10-01 07:16:10 UTC

/bin/sh -c #(nop) ARG RELEASE

2025-10-01 07:16:10 UTC

/bin/sh -c #(nop) ARG LAUNCHPAD_BUILD_ARCH

2025-10-01 07:16:10 UTC

/bin/sh -c #(nop) LABEL org.opencontainers.image.ref.name=ubuntu

2025-10-01 07:16:10 UTC

/bin/sh -c #(nop) LABEL org.opencontainers.image.version=22.04

2025-10-01 07:16:12 UTC

/bin/sh -c #(nop) ADD file:7a71c1d52054f8e04c815eaec639d14adaaa62346860f4003201834430b7ff18 in /

2025-10-01 07:16:12 UTC

/bin/sh -c #(nop) CMD ["/bin/bash"]

2025-10-10 16:50:55 UTC (buildkit.dockerfile.v0)

ENV NVARCH=sbsa

2025-10-10 16:50:55 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 16:50:55 UTC (buildkit.dockerfile.v0)

ENV NV_CUDA_CUDART_VERSION=13.0.96-1

2025-10-10 16:50:55 UTC (buildkit.dockerfile.v0)

ARG TARGETARCH

2025-10-10 16:50:55 UTC (buildkit.dockerfile.v0)

LABEL maintainer=NVIDIA CORPORATION <cudatools@nvidia.com>

2025-10-10 16:50:55 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 -fsSLO https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/${NVARCH}/cuda-keyring_1.1-1_all.deb && dpkg -i cuda-keyring_1.1-1_all.deb && apt-get purge --autoremove -y curl && rm -rf /var/lib/apt/lists/* # buildkit

2025-10-10 16:50:55 UTC (buildkit.dockerfile.v0)

ENV CUDA_VERSION=13.0.2

2025-10-10 16:51:55 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 16:51:55 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 16:51:55 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 16:51:55 UTC (buildkit.dockerfile.v0)

ENV LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/local/cuda/lib64

2025-10-10 16:51:55 UTC (buildkit.dockerfile.v0)

COPY NGC-DL-CONTAINER-LICENSE / # buildkit

2025-10-10 16:51:55 UTC (buildkit.dockerfile.v0)

ENV NVIDIA_VISIBLE_DEVICES=all

2025-10-10 16:51:55 UTC (buildkit.dockerfile.v0)

ENV NVIDIA_DRIVER_CAPABILITIES=compute,utility

2026-05-11 05:02:58 UTC (buildkit.dockerfile.v0)

ARG CUDA_VERSION

2026-05-11 05:02:58 UTC (buildkit.dockerfile.v0)

ARG PYTHON_VERSION

2026-05-11 05:02:58 UTC (buildkit.dockerfile.v0)

ARG DEADSNAKES_MIRROR_URL

2026-05-11 05:02:58 UTC (buildkit.dockerfile.v0)

ARG DEADSNAKES_GPGKEY_URL

2026-05-11 05:02:58 UTC (buildkit.dockerfile.v0)

ARG GET_PIP_URL

2026-05-11 05:02:58 UTC (buildkit.dockerfile.v0)

ENV DEBIAN_FRONTEND=noninteractive

2026-05-11 05:02:58 UTC (buildkit.dockerfile.v0)

WORKDIR /vllm-workspace

2026-05-11 05:02:58 UTC (buildkit.dockerfile.v0)

RUN |5 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 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

2026-05-11 05:03:55 UTC (buildkit.dockerfile.v0)

RUN |5 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 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 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

2026-05-11 05:05:01 UTC (buildkit.dockerfile.v0)

RUN |5 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py /bin/sh -c CUDA_VERSION_DASH=$(echo $CUDA_VERSION | cut -d. -f1,2 | tr '.' '-') && CUDA_VERSION_SHORT=$(echo $CUDA_VERSION | cut -d. -f1,2) && apt-get update -y && apt-get install -y --no-install-recommends --allow-change-held-packages cuda-nvcc-${CUDA_VERSION_DASH} cuda-cudart-${CUDA_VERSION_DASH} cuda-nvrtc-${CUDA_VERSION_DASH} cuda-cuobjdump-${CUDA_VERSION_DASH} libcurand-dev-${CUDA_VERSION_DASH} libcublas-dev-${CUDA_VERSION_DASH} libnuma-dev numactl && NCCL_VER=$(apt-cache madison libnccl-dev | grep "+cuda${CUDA_VERSION_SHORT}" | head -1 | awk -F'|' '{gsub(/^ +| +$/, "", $2); print $2}') && apt-get install -y --no-install-recommends --allow-change-held-packages libnccl-dev=${NCCL_VER} libnccl2=${NCCL_VER} && rm -rf /var/lib/apt/lists/* # buildkit

2026-05-11 05:05:03 UTC (buildkit.dockerfile.v0)

RUN |5 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 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

2026-05-11 05:05:03 UTC (buildkit.dockerfile.v0)

ENV UV_HTTP_TIMEOUT=500

2026-05-11 05:05:03 UTC (buildkit.dockerfile.v0)

ENV UV_INDEX_STRATEGY=unsafe-best-match

2026-05-11 05:05:03 UTC (buildkit.dockerfile.v0)

ENV UV_LINK_MODE=copy

2026-05-11 05:05:03 UTC (buildkit.dockerfile.v0)

ENV VLLM_ENABLE_CUDA_COMPATIBILITY=0

2026-05-11 05:05:03 UTC (buildkit.dockerfile.v0)

ARG PYTORCH_CUDA_INDEX_BASE_URL

2026-05-11 05:05:03 UTC (buildkit.dockerfile.v0)

COPY requirements/common.txt /tmp/common.txt # buildkit

2026-05-11 05:05:03 UTC (buildkit.dockerfile.v0)

COPY requirements/cuda.txt /tmp/requirements-cuda.txt # buildkit

2026-05-11 05:05:13 UTC (buildkit.dockerfile.v0)

RUN |6 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 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 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 '.') && rm /tmp/requirements-cuda.txt /tmp/common.txt # buildkit

2026-05-11 05:05:13 UTC (buildkit.dockerfile.v0)

ARG FLASHINFER_VERSION=0.6.8.post1

2026-05-11 05:06:09 UTC (buildkit.dockerfile.v0)

RUN |7 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 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 FLASHINFER_VERSION=0.6.8.post1 /bin/sh -c uv pip install --system flashinfer-jit-cache==${FLASHINFER_VERSION} --extra-index-url https://flashinfer.ai/whl/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.') # buildkit

2026-05-11 05:06:09 UTC (buildkit.dockerfile.v0)

ARG GDRCOPY_CUDA_VERSION=12.8

2026-05-11 05:06:09 UTC (buildkit.dockerfile.v0)

ARG GDRCOPY_OS_VERSION=Ubuntu22_04

2026-05-11 05:06:09 UTC (buildkit.dockerfile.v0)

ARG TARGETPLATFORM

2026-05-11 05:06:09 UTC (buildkit.dockerfile.v0)

COPY tools/install_gdrcopy.sh /tmp/install_gdrcopy.sh # buildkit

2026-05-11 05:06:17 UTC (buildkit.dockerfile.v0)

RUN |10 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 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 FLASHINFER_VERSION=0.6.8.post1 GDRCOPY_CUDA_VERSION=12.8 GDRCOPY_OS_VERSION=Ubuntu22_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

2026-05-11 05:06:17 UTC (buildkit.dockerfile.v0)

ARG BITSANDBYTES_VERSION_X86=0.46.1

2026-05-11 05:06:17 UTC (buildkit.dockerfile.v0)

ARG BITSANDBYTES_VERSION_ARM64=0.42.0

2026-05-11 05:06:17 UTC (buildkit.dockerfile.v0)

ARG TIMM_VERSION=>=1.0.17

2026-05-11 05:06:17 UTC (buildkit.dockerfile.v0)

ARG RUNAI_MODEL_STREAMER_VERSION=>=0.15.7

2026-05-11 05:06:20 UTC (buildkit.dockerfile.v0)

RUN |14 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 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 FLASHINFER_VERSION=0.6.8.post1 GDRCOPY_CUDA_VERSION=12.8 GDRCOPY_OS_VERSION=Ubuntu22_04 TARGETPLATFORM=linux/arm64 BITSANDBYTES_VERSION_X86=0.46.1 BITSANDBYTES_VERSION_ARM64=0.42.0 TIMM_VERSION=>=1.0.17 RUNAI_MODEL_STREAMER_VERSION=>=0.15.7 /bin/sh -c if [ "$TARGETPLATFORM" = "linux/arm64" ]; then BITSANDBYTES_VERSION="${BITSANDBYTES_VERSION_ARM64}"; else BITSANDBYTES_VERSION="${BITSANDBYTES_VERSION_X86}"; fi; uv pip install --system accelerate modelscope "bitsandbytes>=${BITSANDBYTES_VERSION}" "timm${TIMM_VERSION}" "runai-model-streamer[s3,gcs,azure]${RUNAI_MODEL_STREAMER_VERSION}" # buildkit

2026-05-11 05:06:20 UTC (buildkit.dockerfile.v0)

ARG PIP_INDEX_URL UV_INDEX_URL

2026-05-11 05:06:20 UTC (buildkit.dockerfile.v0)

ARG PIP_EXTRA_INDEX_URL UV_EXTRA_INDEX_URL

2026-05-11 05:06:20 UTC (buildkit.dockerfile.v0)

ARG PYTORCH_CUDA_INDEX_BASE_URL

2026-05-11 05:06:20 UTC (buildkit.dockerfile.v0)

ARG PIP_KEYRING_PROVIDER UV_KEYRING_PROVIDER

2026-05-11 05:06:20 UTC (buildkit.dockerfile.v0)

ARG PYTORCH_NIGHTLY

2026-05-11 05:06:20 UTC (buildkit.dockerfile.v0)

COPY /workspace/torch_lib_versions.txt torch_lib_versions.txt # buildkit

2026-05-11 06:41:15 UTC (buildkit.dockerfile.v0)

RUN |22 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 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 FLASHINFER_VERSION=0.6.8.post1 GDRCOPY_CUDA_VERSION=12.8 GDRCOPY_OS_VERSION=Ubuntu22_04 TARGETPLATFORM=linux/arm64 BITSANDBYTES_VERSION_X86=0.46.1 BITSANDBYTES_VERSION_ARM64=0.42.0 TIMM_VERSION=>=1.0.17 RUNAI_MODEL_STREAMER_VERSION=>=0.15.7 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

2026-05-11 06:41:15 UTC (buildkit.dockerfile.v0)

RUN |22 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 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 FLASHINFER_VERSION=0.6.8.post1 GDRCOPY_CUDA_VERSION=12.8 GDRCOPY_OS_VERSION=Ubuntu22_04 TARGETPLATFORM=linux/arm64 BITSANDBYTES_VERSION_X86=0.46.1 BITSANDBYTES_VERSION_ARM64=0.42.0 TIMM_VERSION=>=1.0.17 RUNAI_MODEL_STREAMER_VERSION=>=0.15.7 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

2026-05-11 06:41:15 UTC (buildkit.dockerfile.v0)

ENV LD_LIBRARY_PATH=/usr/local/cuda/lib64:/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/local/cuda/lib64

2026-05-11 06:41:16 UTC (buildkit.dockerfile.v0)

RUN |22 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 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 FLASHINFER_VERSION=0.6.8.post1 GDRCOPY_CUDA_VERSION=12.8 GDRCOPY_OS_VERSION=Ubuntu22_04 TARGETPLATFORM=linux/arm64 BITSANDBYTES_VERSION_X86=0.46.1 BITSANDBYTES_VERSION_ARM64=0.42.0 TIMM_VERSION=>=1.0.17 RUNAI_MODEL_STREAMER_VERSION=>=0.15.7 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

2026-05-11 06:46:18 UTC (buildkit.dockerfile.v0)

RUN |22 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 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 FLASHINFER_VERSION=0.6.8.post1 GDRCOPY_CUDA_VERSION=12.8 GDRCOPY_OS_VERSION=Ubuntu22_04 TARGETPLATFORM=linux/arm64 BITSANDBYTES_VERSION_X86=0.46.1 BITSANDBYTES_VERSION_ARM64=0.42.0 TIMM_VERSION=>=1.0.17 RUNAI_MODEL_STREAMER_VERSION=>=0.15.7 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 flashinfer show-config && flashinfer download-cubin # buildkit

2026-05-11 06:46:18 UTC (buildkit.dockerfile.v0)

ENV LD_LIBRARY_PATH=/usr/local/nvidia/lib64:/usr/local/cuda/lib64:/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/local/cuda/lib64

2026-05-11 06:46:19 UTC (buildkit.dockerfile.v0)

COPY examples examples # buildkit

2026-05-11 06:46:19 UTC (buildkit.dockerfile.v0)

COPY benchmarks benchmarks # buildkit

2026-05-11 06:46:19 UTC (buildkit.dockerfile.v0)

COPY ./vllm/collect_env.py . # buildkit

2026-05-11 06:46:19 UTC (buildkit.dockerfile.v0)

ARG TARGETPLATFORM

2026-05-11 06:46:19 UTC (buildkit.dockerfile.v0)

ARG INSTALL_KV_CONNECTORS=false

2026-05-11 06:46:19 UTC (buildkit.dockerfile.v0)

ARG CUDA_VERSION

2026-05-11 06:46:19 UTC (buildkit.dockerfile.v0)

ARG VLLM_BUILD_COMMIT

2026-05-11 06:46:19 UTC (buildkit.dockerfile.v0)

ARG VLLM_BUILD_PIPELINE

2026-05-11 06:46:19 UTC (buildkit.dockerfile.v0)

ARG VLLM_BUILD_URL

2026-05-11 06:46:19 UTC (buildkit.dockerfile.v0)

ARG VLLM_IMAGE_TAG

2026-05-11 06:46:19 UTC (buildkit.dockerfile.v0)

ARG PIP_INDEX_URL UV_INDEX_URL

2026-05-11 06:46:19 UTC (buildkit.dockerfile.v0)

ARG PIP_EXTRA_INDEX_URL UV_EXTRA_INDEX_URL

2026-05-11 06:46:19 UTC (buildkit.dockerfile.v0)

ENV UV_HTTP_TIMEOUT=500

2026-05-11 06:46:19 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+PTX

2026-05-11 06:46:19 UTC (buildkit.dockerfile.v0)

ENV TORCH_CUDA_ARCH_LIST=8.0 8.7 8.9 9.0 10.0 11.0 12.0+PTX

2026-05-11 06:49:49 UTC (buildkit.dockerfile.v0)

RUN |12 TARGETPLATFORM=linux/arm64 INSTALL_KV_CONNECTORS=true CUDA_VERSION=13.0.2 VLLM_BUILD_COMMIT=5536fc0c019db9b1f42afcc18fc38f4666b65e23 VLLM_BUILD_PIPELINE=019d130e-464e-4ff7-b84b-492992c0c06b VLLM_BUILD_URL=https://buildkite.com/vllm/release-v2/builds/1468 VLLM_IMAGE_TAG=vllm/vllm-openai:nightly-5536fc0c019db9b1f42afcc18fc38f4666b65e23 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+PTX /bin/sh -c 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 [ "$INSTALL_KV_CONNECTORS" = "true" ]; then if [ "$CUDA_MAJOR" -ge 13 ]; then uv pip install --system nixl-cu13; fi; uv pip install --system -r /tmp/kv_connectors.txt --no-build || ( apt-get update -y && apt-get install -y --no-install-recommends --allow-change-held-packages ${BUILD_PKGS} && uv pip install --system -r /tmp/kv_connectors.txt --no-build-isolation && apt-get purge -y ${BUILD_PKGS} && rm -rf /var/lib/apt/lists/* ); fi # buildkit

2026-05-11 06:49:49 UTC (buildkit.dockerfile.v0)

ENV VLLM_USAGE_SOURCE=production-docker-image

2026-05-11 06:49:49 UTC (buildkit.dockerfile.v0)

ENV VLLM_BUILD_COMMIT=5536fc0c019db9b1f42afcc18fc38f4666b65e23 VLLM_BUILD_PIPELINE=019d130e-464e-4ff7-b84b-492992c0c06b VLLM_BUILD_URL=https://buildkite.com/vllm/release-v2/builds/1468 VLLM_IMAGE_TAG=vllm/vllm-openai:nightly-5536fc0c019db9b1f42afcc18fc38f4666b65e23

2026-05-11 06:49:49 UTC (buildkit.dockerfile.v0)

LABEL org.opencontainers.image.source=https://github.com/vllm-project/vllm org.opencontainers.image.revision=5536fc0c019db9b1f42afcc18fc38f4666b65e23 org.opencontainers.image.version=vllm/vllm-openai:nightly-5536fc0c019db9b1f42afcc18fc38f4666b65e23 org.opencontainers.image.url=https://buildkite.com/vllm/release-v2/builds/1468 ai.vllm.build.commit=5536fc0c019db9b1f42afcc18fc38f4666b65e23 ai.vllm.build.pipeline=019d130e-464e-4ff7-b84b-492992c0c06b ai.vllm.build.url=https://buildkite.com/vllm/release-v2/builds/1468 ai.vllm.image.tag=vllm/vllm-openai:nightly-5536fc0c019db9b1f42afcc18fc38f4666b65e23

2026-05-11 06:49:49 UTC (buildkit.dockerfile.v0)

ENTRYPOINT ["vllm" "serve"]

Danger Zone
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.

Delete