Namespace
vllm
Image / Tag
vllm-openai:cu129-nightly-ef8840adc73bfbe3108811cebcd8af7252f9b6f0
Content Digest
sha256:29825183d8d5a9eb18d4036efdfb29bdfb346d62397e4482a8a35b4f57fad955
Details
Created

2026-05-30 06:06:20 UTC

Size

11 GB

Content Digest
Labels
  • ai.vllm.build.commit
    ef8840adc73bfbe3108811cebcd8af7252f9b6f0
  • ai.vllm.build.pipeline
    019d130e-464e-4ff7-b84b-492992c0c06b
  • ai.vllm.build.url
    https://buildkite.com/vllm/release-v2/builds/2144
  • ai.vllm.image.tag
    vllm/vllm-openai:cu129-nightly-ef8840adc73bfbe3108811cebcd8af7252f9b6f0
  • maintainer
    NVIDIA CORPORATION <[email protected]>
  • org.opencontainers.image.ref.name
    ubuntu
  • org.opencontainers.image.revision
    ef8840adc73bfbe3108811cebcd8af7252f9b6f0
  • org.opencontainers.image.source
    https://github.com/vllm-project/vllm
  • org.opencontainers.image.url
    https://buildkite.com/vllm/release-v2/builds/2144
  • org.opencontainers.image.version
    vllm/vllm-openai:cu129-nightly-ef8840adc73bfbe3108811cebcd8af7252f9b6f0

Environment
CUDA_VERSION

12.9.1

DEBIAN_FRONTEND

noninteractive

LD_LIBRARY_PATH

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

NVARCH

x86_64

NVIDIA_DRIVER_CAPABILITIES

compute,utility

NVIDIA_REQUIRE_CUDA

cuda>=12.9 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>=560,driver<561 brand=grid,driver>=560,driver<561 brand=tesla,driver>=560,driver<561 brand=nvidia,driver>=560,driver<561 brand=quadro,driver>=560,driver<561 brand=quadrortx,driver>=560,driver<561 brand=nvidiartx,driver>=560,driver<561 brand=vapps,driver>=560,driver<561 brand=vpc,driver>=560,driver<561 brand=vcs,driver>=560,driver<561 brand=vws,driver>=560,driver<561 brand=cloudgaming,driver>=560,driver<561 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

NVIDIA_VISIBLE_DEVICES

all

NV_CUDA_CUDART_VERSION

12.9.79-1

PATH

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

TORCH_CUDA_ARCH_LIST

7.5 8.0 8.6 8.9 9.0 10.0 12.0

UV_CACHE_DIR

/opt/uv/cache

UV_HTTP_TIMEOUT

500

UV_INDEX_STRATEGY

unsafe-best-match

UV_LINK_MODE

copy

UV_PYTHON_INSTALL_DIR

/opt/uv/python

VLLM_BUILD_COMMIT

ef8840adc73bfbe3108811cebcd8af7252f9b6f0

VLLM_BUILD_PIPELINE

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

VLLM_BUILD_URL

https://buildkite.com/vllm/release-v2/builds/2144

VLLM_ENABLE_CUDA_COMPATIBILITY

0

VLLM_IMAGE_TAG

vllm/vllm-openai:cu129-nightly-ef8840adc73bfbe3108811cebcd8af7252f9b6f0

VLLM_USAGE_SOURCE

production-docker-image


Layers

[#000] sha256:66587c81b81a58d07e40c48d900a1517516bbf58c4378c687d89d645824f5e5f - 0.26% (29 MB)

[#001] sha256:f29b1d4013a93a17a4d4acbb760170b608e6707e85419f0e1a2973233f1c0080 - 0.04% (4.43 MB)

[#002] sha256:340d44d2921c44112afe4f535a1a3bcfdc4eed5093388d098937942f7f883739 - 0.88% (98.7 MB)

[#003] sha256:59a4bcbddda3c45ff4949d35d2321b6eca9eaff7daae2334c99226bb19f60c3a - 0.0% (184 Bytes)

[#004] sha256:6e8af4fd0a071982e528b634ba99dec2474c21147f99748be708f36e10e3f4c2 - 0.0% (6.72 KB)

[#005] sha256:e80879fb16f1e9be7ff4078e4d663904e33428c12522a965d17127ab5c675c86 - 0.0% (104 Bytes)

[#006] sha256:7ca69488860da27f5e7e7831bb268aaf86a807deae4b755c1048fcd10f47c82a - 0.0% (231 Bytes)

[#007] sha256:50eec9451d59f0a29f590ea4a5f8253df0cb2edc39fbcef79de7da25285d86f6 - 1.92% (216 MB)

[#008] sha256:d27fc635c0a49a99b37e7a9c064f82de49803fc413d0af99e6435ecf295cab28 - 19.33% (2.13 GB)

[#009] sha256:bdfc7754a94d863f2544eabce2b17baa864dac78f53d8b63d165d5499c718878 - 0.43% (47.9 MB)

[#010] sha256:7a576bd02391d534dfdae310c58cf9ddee0b9f5dd8cdad6e1f9499b686045196 - 0.0% (149 Bytes)

[#011] sha256:69fa18d02f1093ac90c73bd408d71fb0518aef3c89704a6e6254139f4b400136 - 0.0% (4.81 KB)

[#012] sha256:a397ecdc3d2913b3940ff51d7d8d125301695a331d88e951f6f249b9593fbbdc - 0.0% (2.03 KB)

[#013] sha256:a397ecdc3d2913b3940ff51d7d8d125301695a331d88e951f6f249b9593fbbdc - 0.0% (2.03 KB)

[#014] sha256:0721d3a62e206ab114598ec9511b26d752d29b18919d4fde5d886c11af5c1ea6 - 0.0% (1.59 KB)

[#015] sha256:6ac79759ce98ffe29a6d3232e29bdbd1d565ca995f089b1941fada546ba9c651 - 0.0% (697 Bytes)

[#016] sha256:e2d0a35198cbe5f69ceeeaeb1dc5b4eea98ddb3cd92cbd4070795a3521fa9612 - 45.71% (5.03 GB)

[#017] sha256:6a400803f063863e3811de8e126efe6b52982bb5830eaa4a3afd0d2ec1056d86 - 16.97% (1.87 GB)

[#018] sha256:cb97e09470e8745cad685fd674d48561e792f1a2664cb813c3fc9818df27bd14 - 0.0% (898 Bytes)

[#019] sha256:1090ad55e2adfe45c26002027dcb8790c75836ab74b44b7ba5ac64fd54c56e65 - 0.0% (525 KB)

[#020] sha256:303a65abc651bc8ee5b0d34beb1d0cb570cd380f759063470fd8a462eb34cf7e - 1.03% (116 MB)

[#021] sha256:00ee0cdc2232ee83414e49e3b1cf2f989957a9431218db562bd96ad04e6d475c - 0.0% (199 Bytes)

[#022] sha256:fb2d0c0e9ea6a655ab51ef90a96517713462e10b4475d2a2edcae56610f391e4 - 4.19% (472 MB)

[#023] sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1 - 0.0% (32 Bytes)

[#024] sha256:f03428241bf00cb8ca86a85928f98f8e7a60b79cdc83bdd3072340948d7d2812 - 0.14% (15.4 MB)

[#025] sha256:a8d3b03a04fdee541f7bafa5e9204140a96d0ed26e7274a3466bed45d3beb228 - 3.09% (348 MB)

[#026] sha256:773643e5ea7db4084370bd210149ab003cf068c4802c519c93a7685cce1a149b - 0.0% (254 KB)

[#027] sha256:59504500cc2953abc3bda3bbbdcd19a1f518fb677dfb34e5230b72342a21b7b0 - 0.0% (241 KB)

[#028] sha256:c848010fa4b5a37aa4b25e9a1a61a3993dc8ab76cd5f9d266b740483c7ca23d8 - 0.0% (9.62 KB)

[#029] sha256:c4e2b010cc1e38b77b268d337bf710679f64ee30d13998aef834fdfcc18e5a09 - 1.94% (218 MB)

[#030] sha256:b34344dbdfadc8e0b2eefd014cc61623a2705d34d15273faf2123c032347cf12 - 4.09% (461 MB)


History
2025-07-14 16:33:29 UTC

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

2025-07-14 16:33:29 UTC

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

2025-07-14 16:33:29 UTC

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

2025-07-14 16:33:29 UTC

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

2025-07-14 16:33:31 UTC

/bin/sh -c #(nop) ADD file:415bbc01dfb447d002e2d8173e113ef025d2bbfa20f1205823fa699dc87a2019 in /

2025-07-14 16:33:32 UTC

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

2025-07-18 20:11:02 UTC (buildkit.dockerfile.v0)

ENV NVARCH=x86_64

2025-07-18 20:11:02 UTC (buildkit.dockerfile.v0)

ENV NVIDIA_REQUIRE_CUDA=cuda>=12.9 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>=560,driver<561 brand=grid,driver>=560,driver<561 brand=tesla,driver>=560,driver<561 brand=nvidia,driver>=560,driver<561 brand=quadro,driver>=560,driver<561 brand=quadrortx,driver>=560,driver<561 brand=nvidiartx,driver>=560,driver<561 brand=vapps,driver>=560,driver<561 brand=vpc,driver>=560,driver<561 brand=vcs,driver>=560,driver<561 brand=vws,driver>=560,driver<561 brand=cloudgaming,driver>=560,driver<561 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

2025-07-18 20:11:02 UTC (buildkit.dockerfile.v0)

ENV NV_CUDA_CUDART_VERSION=12.9.79-1

2025-07-18 20:11:02 UTC (buildkit.dockerfile.v0)

ARG TARGETARCH

2025-07-18 20:11:02 UTC (buildkit.dockerfile.v0)

LABEL maintainer=NVIDIA CORPORATION <[email protected]>

2025-07-18 20:11:02 UTC (buildkit.dockerfile.v0)

RUN |1 TARGETARCH=amd64 /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

2025-07-18 20:11:02 UTC (buildkit.dockerfile.v0)

ENV CUDA_VERSION=12.9.1

2025-07-18 20:11:19 UTC (buildkit.dockerfile.v0)

RUN |1 TARGETARCH=amd64 /bin/sh -c apt-get update && apt-get install -y --no-install-recommends cuda-cudart-12-9=${NV_CUDA_CUDART_VERSION} cuda-compat-12-9 && rm -rf /var/lib/apt/lists/* # buildkit

2025-07-18 20:11:19 UTC (buildkit.dockerfile.v0)

RUN |1 TARGETARCH=amd64 /bin/sh -c echo "/usr/local/cuda/lib64" >> /etc/ld.so.conf.d/nvidia.conf # buildkit

2025-07-18 20:11:19 UTC (buildkit.dockerfile.v0)

ENV PATH=/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin

2025-07-18 20:11:19 UTC (buildkit.dockerfile.v0)

ENV LD_LIBRARY_PATH=/usr/local/cuda/lib64

2025-07-18 20:11:19 UTC (buildkit.dockerfile.v0)

COPY NGC-DL-CONTAINER-LICENSE / # buildkit

2025-07-18 20:11:19 UTC (buildkit.dockerfile.v0)

ENV NVIDIA_VISIBLE_DEVICES=all

2025-07-18 20:11:19 UTC (buildkit.dockerfile.v0)

ENV NVIDIA_DRIVER_CAPABILITIES=compute,utility

2026-05-30 05:03:28 UTC (buildkit.dockerfile.v0)

ARG CUDA_VERSION

2026-05-30 05:03:28 UTC (buildkit.dockerfile.v0)

ARG PYTHON_VERSION

2026-05-30 05:03:28 UTC (buildkit.dockerfile.v0)

ARG DEADSNAKES_MIRROR_URL

2026-05-30 05:03:28 UTC (buildkit.dockerfile.v0)

ARG DEADSNAKES_GPGKEY_URL

2026-05-30 05:03:28 UTC (buildkit.dockerfile.v0)

ARG GET_PIP_URL

2026-05-30 05:03:28 UTC (buildkit.dockerfile.v0)

ENV DEBIAN_FRONTEND=noninteractive

2026-05-30 05:03:28 UTC (buildkit.dockerfile.v0)

WORKDIR /vllm-workspace

2026-05-30 05:03:29 UTC (buildkit.dockerfile.v0)

RUN |5 CUDA_VERSION=12.9.1 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

2026-05-30 05:04:35 UTC (buildkit.dockerfile.v0)

RUN |5 CUDA_VERSION=12.9.1 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

2026-05-30 05:06:11 UTC (buildkit.dockerfile.v0)

RUN |5 CUDA_VERSION=12.9.1 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

2026-05-30 05:06:15 UTC (buildkit.dockerfile.v0)

RUN |5 CUDA_VERSION=12.9.1 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

2026-05-30 05:06:15 UTC (buildkit.dockerfile.v0)

ENV UV_HTTP_TIMEOUT=500

2026-05-30 05:06:15 UTC (buildkit.dockerfile.v0)

ENV UV_INDEX_STRATEGY=unsafe-best-match

2026-05-30 05:06:15 UTC (buildkit.dockerfile.v0)

ENV UV_LINK_MODE=copy

2026-05-30 05:06:15 UTC (buildkit.dockerfile.v0)

ENV UV_PYTHON_INSTALL_DIR=/opt/uv/python

2026-05-30 05:06:15 UTC (buildkit.dockerfile.v0)

ENV UV_CACHE_DIR=/opt/uv/cache

2026-05-30 05:06:16 UTC (buildkit.dockerfile.v0)

RUN |5 CUDA_VERSION=12.9.1 PYTHON_VERSION=3.12 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

2026-05-30 05:06:17 UTC (buildkit.dockerfile.v0)

RUN |5 CUDA_VERSION=12.9.1 PYTHON_VERSION=3.12 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

2026-05-30 05:06:17 UTC (buildkit.dockerfile.v0)

COPY docker/entrypoints/vllm-nonroot-entrypoint.sh /usr/local/bin/vllm-nonroot-entrypoint.sh # buildkit

2026-05-30 05:06:18 UTC (buildkit.dockerfile.v0)

RUN |5 CUDA_VERSION=12.9.1 PYTHON_VERSION=3.12 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

2026-05-30 05:06:18 UTC (buildkit.dockerfile.v0)

ENV VLLM_ENABLE_CUDA_COMPATIBILITY=0

2026-05-30 05:06:18 UTC (buildkit.dockerfile.v0)

ARG PYTORCH_CUDA_INDEX_BASE_URL

2026-05-30 05:06:18 UTC (buildkit.dockerfile.v0)

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

2026-05-30 05:06:18 UTC (buildkit.dockerfile.v0)

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

2026-05-30 05:07:31 UTC (buildkit.dockerfile.v0)

RUN |6 CUDA_VERSION=12.9.1 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 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 && 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

2026-05-30 05:07:31 UTC (buildkit.dockerfile.v0)

ARG FLASHINFER_VERSION=0.6.11.post2

2026-05-30 05:08:40 UTC (buildkit.dockerfile.v0)

RUN |7 CUDA_VERSION=12.9.1 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=0.6.11.post2 /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

2026-05-30 05:08:40 UTC (buildkit.dockerfile.v0)

ARG GDRCOPY_CUDA_VERSION=12.8

2026-05-30 05:08:40 UTC (buildkit.dockerfile.v0)

ARG GDRCOPY_OS_VERSION=Ubuntu22_04

2026-05-30 05:08:40 UTC (buildkit.dockerfile.v0)

ARG TARGETPLATFORM

2026-05-30 05:08:40 UTC (buildkit.dockerfile.v0)

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

2026-05-30 05:08:46 UTC (buildkit.dockerfile.v0)

RUN |10 CUDA_VERSION=12.9.1 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=0.6.11.post2 GDRCOPY_CUDA_VERSION=12.8 GDRCOPY_OS_VERSION=Ubuntu22_04 TARGETPLATFORM=linux/amd64 /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

2026-05-30 05:08:46 UTC (buildkit.dockerfile.v0)

ARG BITSANDBYTES_VERSION_X86=0.46.1

2026-05-30 05:08:46 UTC (buildkit.dockerfile.v0)

ARG BITSANDBYTES_VERSION_ARM64=0.42.0

2026-05-30 05:08:46 UTC (buildkit.dockerfile.v0)

ARG TIMM_VERSION=>=1.0.17

2026-05-30 05:08:46 UTC (buildkit.dockerfile.v0)

ARG RUNAI_MODEL_STREAMER_VERSION=>=0.15.7

2026-05-30 05:08:50 UTC (buildkit.dockerfile.v0)

RUN |14 CUDA_VERSION=12.9.1 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=0.6.11.post2 GDRCOPY_CUDA_VERSION=12.8 GDRCOPY_OS_VERSION=Ubuntu22_04 TARGETPLATFORM=linux/amd64 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

2026-05-30 05:08:50 UTC (buildkit.dockerfile.v0)

ARG PIP_INDEX_URL UV_INDEX_URL

2026-05-30 05:08:50 UTC (buildkit.dockerfile.v0)

ARG PIP_EXTRA_INDEX_URL UV_EXTRA_INDEX_URL

2026-05-30 05:08:50 UTC (buildkit.dockerfile.v0)

ARG PYTORCH_CUDA_INDEX_BASE_URL

2026-05-30 05:08:50 UTC (buildkit.dockerfile.v0)

ARG PIP_KEYRING_PROVIDER UV_KEYRING_PROVIDER

2026-05-30 05:08:50 UTC (buildkit.dockerfile.v0)

ARG PYTORCH_NIGHTLY

2026-05-30 05:08:50 UTC (buildkit.dockerfile.v0)

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

2026-05-30 05:57:16 UTC (buildkit.dockerfile.v0)

RUN |22 CUDA_VERSION=12.9.1 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=0.6.11.post2 GDRCOPY_CUDA_VERSION=12.8 GDRCOPY_OS_VERSION=Ubuntu22_04 TARGETPLATFORM=linux/amd64 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

2026-05-30 05:57:16 UTC (buildkit.dockerfile.v0)

RUN |22 CUDA_VERSION=12.9.1 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=0.6.11.post2 GDRCOPY_CUDA_VERSION=12.8 GDRCOPY_OS_VERSION=Ubuntu22_04 TARGETPLATFORM=linux/amd64 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

2026-05-30 05:57:16 UTC (buildkit.dockerfile.v0)

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

2026-05-30 05:57:17 UTC (buildkit.dockerfile.v0)

RUN |22 CUDA_VERSION=12.9.1 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=0.6.11.post2 GDRCOPY_CUDA_VERSION=12.8 GDRCOPY_OS_VERSION=Ubuntu22_04 TARGETPLATFORM=linux/amd64 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

2026-05-30 06:06:06 UTC (buildkit.dockerfile.v0)

RUN |22 CUDA_VERSION=12.9.1 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=0.6.11.post2 GDRCOPY_CUDA_VERSION=12.8 GDRCOPY_OS_VERSION=Ubuntu22_04 TARGETPLATFORM=linux/amd64 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

2026-05-30 06:06:06 UTC (buildkit.dockerfile.v0)

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

2026-05-30 06:06:06 UTC (buildkit.dockerfile.v0)

COPY examples examples # buildkit

2026-05-30 06:06:06 UTC (buildkit.dockerfile.v0)

COPY benchmarks benchmarks # buildkit

2026-05-30 06:06:06 UTC (buildkit.dockerfile.v0)

COPY ./vllm/collect_env.py . # buildkit

2026-05-30 06:06:06 UTC (buildkit.dockerfile.v0)

ARG TARGETPLATFORM

2026-05-30 06:06:06 UTC (buildkit.dockerfile.v0)

ARG INSTALL_KV_CONNECTORS=false

2026-05-30 06:06:06 UTC (buildkit.dockerfile.v0)

ARG CUDA_VERSION

2026-05-30 06:06:06 UTC (buildkit.dockerfile.v0)

ARG VLLM_BUILD_COMMIT

2026-05-30 06:06:06 UTC (buildkit.dockerfile.v0)

ARG VLLM_BUILD_PIPELINE

2026-05-30 06:06:06 UTC (buildkit.dockerfile.v0)

ARG VLLM_BUILD_URL

2026-05-30 06:06:06 UTC (buildkit.dockerfile.v0)

ARG VLLM_IMAGE_TAG

2026-05-30 06:06:06 UTC (buildkit.dockerfile.v0)

ARG PIP_INDEX_URL UV_INDEX_URL

2026-05-30 06:06:06 UTC (buildkit.dockerfile.v0)

ARG PIP_EXTRA_INDEX_URL UV_EXTRA_INDEX_URL

2026-05-30 06:06:06 UTC (buildkit.dockerfile.v0)

ENV UV_HTTP_TIMEOUT=500

2026-05-30 06:06:06 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

2026-05-30 06:06:06 UTC (buildkit.dockerfile.v0)

ENV TORCH_CUDA_ARCH_LIST=7.5 8.0 8.6 8.9 9.0 10.0 12.0

2026-05-30 06:06:12 UTC (buildkit.dockerfile.v0)

RUN |12 TARGETPLATFORM=linux/amd64 INSTALL_KV_CONNECTORS=true CUDA_VERSION=12.9.1 VLLM_BUILD_COMMIT=ef8840adc73bfbe3108811cebcd8af7252f9b6f0 VLLM_BUILD_PIPELINE=019d130e-464e-4ff7-b84b-492992c0c06b VLLM_BUILD_URL=https://buildkite.com/vllm/release-v2/builds/2144 VLLM_IMAGE_TAG=vllm/vllm-openai:cu129-nightly-ef8840adc73bfbe3108811cebcd8af7252f9b6f0 PIP_INDEX_URL= UV_INDEX_URL= PIP_EXTRA_INDEX_URL= UV_EXTRA_INDEX_URL= torch_cuda_arch_list=7.5 8.0 8.6 8.9 9.0 10.0 12.0 /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 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 ${BUILD_PKGS} && rm -rf /var/lib/apt/lists/* ); uv pip install --system --force-reinstall --no-deps nixl-cu${CUDA_MAJOR}; fi # buildkit

2026-05-30 06:06:12 UTC (buildkit.dockerfile.v0)

ARG MOONCAKE_WHEEL_AARCH64

2026-05-30 06:06:12 UTC (buildkit.dockerfile.v0)

ARG MOONCAKE_WHEEL_X86_64

2026-05-30 06:06:20 UTC (buildkit.dockerfile.v0)

RUN |14 TARGETPLATFORM=linux/amd64 INSTALL_KV_CONNECTORS=true CUDA_VERSION=12.9.1 VLLM_BUILD_COMMIT=ef8840adc73bfbe3108811cebcd8af7252f9b6f0 VLLM_BUILD_PIPELINE=019d130e-464e-4ff7-b84b-492992c0c06b VLLM_BUILD_URL=https://buildkite.com/vllm/release-v2/builds/2144 VLLM_IMAGE_TAG=vllm/vllm-openai:cu129-nightly-ef8840adc73bfbe3108811cebcd8af7252f9b6f0 PIP_INDEX_URL= UV_INDEX_URL= PIP_EXTRA_INDEX_URL= UV_EXTRA_INDEX_URL= torch_cuda_arch_list=7.5 8.0 8.6 8.9 9.0 10.0 12.0 MOONCAKE_WHEEL_AARCH64=https://vllm-wheels.s3.amazonaws.com/mooncake/mooncake_transfer_engine-0.3.10.post2-0da9dfea3-cp312-cp312-manylinux_2_35_aarch64.whl MOONCAKE_WHEEL_X86_64=https://vllm-wheels.s3.amazonaws.com/mooncake/mooncake_transfer_engine-0.3.10.post2-0da9dfea3-cp312-cp312-manylinux_2_35_x86_64.whl /bin/sh -c if [ "$INSTALL_KV_CONNECTORS" = "true" ]; then if [ "$TARGETPLATFORM" = "linux/arm64" ]; then WHEEL="${MOONCAKE_WHEEL_AARCH64}"; else WHEEL="${MOONCAKE_WHEEL_X86_64}"; fi && if [ -n "${WHEEL}" ]; then uv pip install --system "${WHEEL}" && CUDA_MAJOR="${CUDA_VERSION%%.*}" && if [ ! -f /usr/local/cuda/lib64/libcudart.so ] && [ -f "/usr/local/cuda/lib64/libcudart.so.${CUDA_MAJOR}" ]; then ln -s "libcudart.so.${CUDA_MAJOR}" /usr/local/cuda/lib64/libcudart.so; fi; fi; fi # buildkit

2026-05-30 06:06:20 UTC (buildkit.dockerfile.v0)

ENV VLLM_USAGE_SOURCE=production-docker-image

2026-05-30 06:06:20 UTC (buildkit.dockerfile.v0)

ENV VLLM_BUILD_COMMIT=ef8840adc73bfbe3108811cebcd8af7252f9b6f0 VLLM_BUILD_PIPELINE=019d130e-464e-4ff7-b84b-492992c0c06b VLLM_BUILD_URL=https://buildkite.com/vllm/release-v2/builds/2144 VLLM_IMAGE_TAG=vllm/vllm-openai:cu129-nightly-ef8840adc73bfbe3108811cebcd8af7252f9b6f0

2026-05-30 06:06:20 UTC (buildkit.dockerfile.v0)

LABEL org.opencontainers.image.source=https://github.com/vllm-project/vllm org.opencontainers.image.revision=ef8840adc73bfbe3108811cebcd8af7252f9b6f0 org.opencontainers.image.version=vllm/vllm-openai:cu129-nightly-ef8840adc73bfbe3108811cebcd8af7252f9b6f0 org.opencontainers.image.url=https://buildkite.com/vllm/release-v2/builds/2144 ai.vllm.build.commit=ef8840adc73bfbe3108811cebcd8af7252f9b6f0 ai.vllm.build.pipeline=019d130e-464e-4ff7-b84b-492992c0c06b ai.vllm.build.url=https://buildkite.com/vllm/release-v2/builds/2144 ai.vllm.image.tag=vllm/vllm-openai:cu129-nightly-ef8840adc73bfbe3108811cebcd8af7252f9b6f0

2026-05-30 06:06:20 UTC (buildkit.dockerfile.v0)

ENTRYPOINT ["vllm" "serve"]

Details
Created

2026-05-30 06:14:16 UTC

Size

11.9 GB

Content Digest
Labels
  • ai.vllm.build.commit
    ef8840adc73bfbe3108811cebcd8af7252f9b6f0
  • ai.vllm.build.pipeline
    019d130e-464e-4ff7-b84b-492992c0c06b
  • ai.vllm.build.url
    https://buildkite.com/vllm/release-v2/builds/2144
  • ai.vllm.image.tag
    vllm/vllm-openai:cu129-nightly-ef8840adc73bfbe3108811cebcd8af7252f9b6f0
  • maintainer
    NVIDIA CORPORATION <[email protected]>
  • org.opencontainers.image.ref.name
    ubuntu
  • org.opencontainers.image.revision
    ef8840adc73bfbe3108811cebcd8af7252f9b6f0
  • org.opencontainers.image.source
    https://github.com/vllm-project/vllm
  • org.opencontainers.image.url
    https://buildkite.com/vllm/release-v2/builds/2144
  • org.opencontainers.image.version
    vllm/vllm-openai:cu129-nightly-ef8840adc73bfbe3108811cebcd8af7252f9b6f0

Environment
CUDA_VERSION

12.9.1

DEBIAN_FRONTEND

noninteractive

LD_LIBRARY_PATH

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

NVARCH

sbsa

NVIDIA_DRIVER_CAPABILITIES

compute,utility

NVIDIA_REQUIRE_CUDA

cuda>=12.9 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>=560,driver<561 brand=grid,driver>=560,driver<561 brand=tesla,driver>=560,driver<561 brand=nvidia,driver>=560,driver<561 brand=quadro,driver>=560,driver<561 brand=quadrortx,driver>=560,driver<561 brand=nvidiartx,driver>=560,driver<561 brand=vapps,driver>=560,driver<561 brand=vpc,driver>=560,driver<561 brand=vcs,driver>=560,driver<561 brand=vws,driver>=560,driver<561 brand=cloudgaming,driver>=560,driver<561 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

NVIDIA_VISIBLE_DEVICES

all

NV_CUDA_CUDART_VERSION

12.9.79-1

PATH

/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 12.0

UV_CACHE_DIR

/opt/uv/cache

UV_HTTP_TIMEOUT

500

UV_INDEX_STRATEGY

unsafe-best-match

UV_LINK_MODE

copy

UV_PYTHON_INSTALL_DIR

/opt/uv/python

VLLM_BUILD_COMMIT

ef8840adc73bfbe3108811cebcd8af7252f9b6f0

VLLM_BUILD_PIPELINE

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

VLLM_BUILD_URL

https://buildkite.com/vllm/release-v2/builds/2144

VLLM_ENABLE_CUDA_COMPATIBILITY

0

VLLM_IMAGE_TAG

vllm/vllm-openai:cu129-nightly-ef8840adc73bfbe3108811cebcd8af7252f9b6f0

VLLM_USAGE_SOURCE

production-docker-image


Layers

[#000] sha256:2ea2730b4ab400d71167ddb8627f741637496aa57128fdfc248d6a9f799d76e9 - 0.22% (27.1 MB)

[#001] sha256:7aa2d0bb5c94f1cf869e71e4db856d2ca0733f5eaab55dd514441da9616abb35 - 0.04% (4.38 MB)

[#002] sha256:5136ae4e75ffd61960e9220c7d7625a3ee213ff63c25fdc24e85bfe229b16ab5 - 0.76% (93.1 MB)

[#003] sha256:6f760a753c5e1fc35281126d63b6ca9bef93e49f89a826a2bc2786e293d88f00 - 0.0% (182 Bytes)

[#004] sha256:6e8af4fd0a071982e528b634ba99dec2474c21147f99748be708f36e10e3f4c2 - 0.0% (6.72 KB)

[#005] sha256:5a045f3132feb6b3e50662049ebb534ec69ebbd88b9580978a10a7c23b0dfc4d - 0.0% (104 Bytes)

[#006] sha256:06897d61d311535f2052846cc26453e57f913fd1b29e4cf795b0bd8198264209 - 0.0% (229 Bytes)

[#007] sha256:d32661240bb679b9c84047c855fe4d592f13fe2792aca1822fcc37193a7289f6 - 1.65% (201 MB)

[#008] sha256:b92ade0ab7ac15c21e6880eff8d5fd82137da9c3ab6272a0def97c68ca71b925 - 17.42% (2.07 GB)

[#009] sha256:3919bdae6be79c4b739f24480b0479787de15a781550bf6642b8cbffab7fc06b - 0.37% (45.6 MB)

[#010] sha256:dc33d4776ce84dfc5caacad709a5254b9894ab499d49c4cfdea77249697e84f1 - 0.0% (150 Bytes)

[#011] sha256:b06062068fff2dc6da85d49756baf3b9e2bb5ea7e060229c9a75e95600287280 - 0.0% (4.8 KB)

[#012] sha256:ad7eba38e4ba4ed8eba24205ee960d95b06e60e89a8eab28434e52c9b993c2c9 - 0.0% (2.03 KB)

[#013] sha256:ad7eba38e4ba4ed8eba24205ee960d95b06e60e89a8eab28434e52c9b993c2c9 - 0.0% (2.03 KB)

[#014] sha256:7312863068936a49ee1b4d6e1fd9913dcaa69639b1c7becad22c3dc9d1680687 - 0.0% (1.59 KB)

[#015] sha256:e9bc6be125bdd422b03505176aec5c7e495d5e10d10ca858ee2153e8bef5f7fc - 0.0% (696 Bytes)

[#016] sha256:81af94e779af3f8772919fc03b6effbe31958a93e78eb7af28db959aa7834179 - 39.09% (4.65 GB)

[#017] sha256:20098a9b83423acc060c0e597f04520eacab859a4261c3352444eb8ac767c4a8 - 15.6% (1.86 GB)

[#018] sha256:1e90ca42b5b564c766ccd005f06ffb74b5e16e615a8ab0363ddb37675e8f40ff - 0.0% (898 Bytes)

[#019] sha256:7bdbfdd71a205d2aff37b5b14efc5857e6574123e5917261bcb4e9fa7f7f7efd - 0.0% (520 KB)

[#020] sha256:c75f6cb8a40230e3f41d8df105cd2b85d64b096b6a27994a2d13318ba8618915 - 2.96% (361 MB)

[#021] sha256:7eb0bf31e599692588f659dc469fbb99d18cdcb3a6d40fbe053ec587b9601371 - 0.0% (200 Bytes)

[#022] sha256:36de025290cd2d7e00cd3950bf94a4e657a80d2a787ef58253fed8fb957e2c7e - 5.86% (713 MB)

[#023] sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1 - 0.0% (32 Bytes)

[#024] sha256:e2b7f43bc0d4c0cd23a52ee041cf52706d29f1753148935f32660cf33750bf18 - 0.12% (15.2 MB)

[#025] sha256:1eb6a322203d34cc880132f32e839a3da04804240428bdcc8a09785e0d8d0664 - 2.86% (348 MB)

[#026] sha256:c8e67624aa6b562c82409bde2b4514026f491c131b31f9811ae0d62aef186f84 - 0.0% (254 KB)

[#027] sha256:139b2592e1ee28fb13d91db23fef9b2657dd94a8e9799291ee3801e3a9fd7ef7 - 0.0% (241 KB)

[#028] sha256:a1061597ab1b7ac358780ddcc10cfb30387c433e57b8c6ef82e2569e10e374ee - 0.0% (9.62 KB)

[#029] sha256:fd9226e1e9b92fe49060f4ef11e6904ec90d37c9827f4674c4ac22a21463c218 - 9.36% (1.11 GB)

[#030] sha256:0e5bfc89b2ccaab3107d643f4d369d6cff543058c155d134978fcc13676bff0f - 3.66% (446 MB)


History
2025-07-14 16:34:14 UTC

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

2025-07-14 16:34:14 UTC

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

2025-07-14 16:34:14 UTC

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

2025-07-14 16:34:14 UTC

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

2025-07-14 16:34:16 UTC

/bin/sh -c #(nop) ADD file:834c1c2a4c7753a37759a9b21f64a990572643eee18669b1faa782fee45355ed in /

2025-07-14 16:34:17 UTC

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

2025-07-18 20:12:35 UTC (buildkit.dockerfile.v0)

ENV NVARCH=sbsa

2025-07-18 20:12:35 UTC (buildkit.dockerfile.v0)

ENV NVIDIA_REQUIRE_CUDA=cuda>=12.9 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>=560,driver<561 brand=grid,driver>=560,driver<561 brand=tesla,driver>=560,driver<561 brand=nvidia,driver>=560,driver<561 brand=quadro,driver>=560,driver<561 brand=quadrortx,driver>=560,driver<561 brand=nvidiartx,driver>=560,driver<561 brand=vapps,driver>=560,driver<561 brand=vpc,driver>=560,driver<561 brand=vcs,driver>=560,driver<561 brand=vws,driver>=560,driver<561 brand=cloudgaming,driver>=560,driver<561 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

2025-07-18 20:12:35 UTC (buildkit.dockerfile.v0)

ENV NV_CUDA_CUDART_VERSION=12.9.79-1

2025-07-18 20:12:35 UTC (buildkit.dockerfile.v0)

ARG TARGETARCH

2025-07-18 20:12:35 UTC (buildkit.dockerfile.v0)

LABEL maintainer=NVIDIA CORPORATION <[email protected]>

2025-07-18 20:12:35 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

2025-07-18 20:12:35 UTC (buildkit.dockerfile.v0)

ENV CUDA_VERSION=12.9.1

2025-07-18 20:13:38 UTC (buildkit.dockerfile.v0)

RUN |1 TARGETARCH=arm64 /bin/sh -c apt-get update && apt-get install -y --no-install-recommends cuda-cudart-12-9=${NV_CUDA_CUDART_VERSION} cuda-compat-12-9 && rm -rf /var/lib/apt/lists/* # buildkit

2025-07-18 20:13:38 UTC (buildkit.dockerfile.v0)

RUN |1 TARGETARCH=arm64 /bin/sh -c echo "/usr/local/cuda/lib64" >> /etc/ld.so.conf.d/nvidia.conf # buildkit

2025-07-18 20:13:38 UTC (buildkit.dockerfile.v0)

ENV PATH=/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin

2025-07-18 20:13:38 UTC (buildkit.dockerfile.v0)

ENV LD_LIBRARY_PATH=/usr/local/cuda/lib64

2025-07-18 20:13:38 UTC (buildkit.dockerfile.v0)

COPY NGC-DL-CONTAINER-LICENSE / # buildkit

2025-07-18 20:13:38 UTC (buildkit.dockerfile.v0)

ENV NVIDIA_VISIBLE_DEVICES=all

2025-07-18 20:13:38 UTC (buildkit.dockerfile.v0)

ENV NVIDIA_DRIVER_CAPABILITIES=compute,utility

2026-05-30 05:02:51 UTC (buildkit.dockerfile.v0)

ARG CUDA_VERSION

2026-05-30 05:02:51 UTC (buildkit.dockerfile.v0)

ARG PYTHON_VERSION

2026-05-30 05:02:51 UTC (buildkit.dockerfile.v0)

ARG DEADSNAKES_MIRROR_URL

2026-05-30 05:02:51 UTC (buildkit.dockerfile.v0)

ARG DEADSNAKES_GPGKEY_URL

2026-05-30 05:02:51 UTC (buildkit.dockerfile.v0)

ARG GET_PIP_URL

2026-05-30 05:02:51 UTC (buildkit.dockerfile.v0)

ENV DEBIAN_FRONTEND=noninteractive

2026-05-30 05:02:51 UTC (buildkit.dockerfile.v0)

WORKDIR /vllm-workspace

2026-05-30 05:02:51 UTC (buildkit.dockerfile.v0)

RUN |5 CUDA_VERSION=12.9.1 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

2026-05-30 05:03:48 UTC (buildkit.dockerfile.v0)

RUN |5 CUDA_VERSION=12.9.1 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

2026-05-30 05:05:17 UTC (buildkit.dockerfile.v0)

RUN |5 CUDA_VERSION=12.9.1 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

2026-05-30 05:05:20 UTC (buildkit.dockerfile.v0)

RUN |5 CUDA_VERSION=12.9.1 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

2026-05-30 05:05:20 UTC (buildkit.dockerfile.v0)

ENV UV_HTTP_TIMEOUT=500

2026-05-30 05:05:20 UTC (buildkit.dockerfile.v0)

ENV UV_INDEX_STRATEGY=unsafe-best-match

2026-05-30 05:05:20 UTC (buildkit.dockerfile.v0)

ENV UV_LINK_MODE=copy

2026-05-30 05:05:20 UTC (buildkit.dockerfile.v0)

ENV UV_PYTHON_INSTALL_DIR=/opt/uv/python

2026-05-30 05:05:20 UTC (buildkit.dockerfile.v0)

ENV UV_CACHE_DIR=/opt/uv/cache

2026-05-30 05:05:21 UTC (buildkit.dockerfile.v0)

RUN |5 CUDA_VERSION=12.9.1 PYTHON_VERSION=3.12 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

2026-05-30 05:05:22 UTC (buildkit.dockerfile.v0)

RUN |5 CUDA_VERSION=12.9.1 PYTHON_VERSION=3.12 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

2026-05-30 05:05:22 UTC (buildkit.dockerfile.v0)

COPY docker/entrypoints/vllm-nonroot-entrypoint.sh /usr/local/bin/vllm-nonroot-entrypoint.sh # buildkit

2026-05-30 05:05:23 UTC (buildkit.dockerfile.v0)

RUN |5 CUDA_VERSION=12.9.1 PYTHON_VERSION=3.12 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

2026-05-30 05:05:23 UTC (buildkit.dockerfile.v0)

ENV VLLM_ENABLE_CUDA_COMPATIBILITY=0

2026-05-30 05:05:23 UTC (buildkit.dockerfile.v0)

ARG PYTORCH_CUDA_INDEX_BASE_URL

2026-05-30 05:05:24 UTC (buildkit.dockerfile.v0)

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

2026-05-30 05:05:24 UTC (buildkit.dockerfile.v0)

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

2026-05-30 05:05:39 UTC (buildkit.dockerfile.v0)

RUN |6 CUDA_VERSION=12.9.1 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 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 && 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

2026-05-30 05:05:39 UTC (buildkit.dockerfile.v0)

ARG FLASHINFER_VERSION=0.6.11.post2

2026-05-30 05:06:31 UTC (buildkit.dockerfile.v0)

RUN |7 CUDA_VERSION=12.9.1 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=0.6.11.post2 /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

2026-05-30 05:06:31 UTC (buildkit.dockerfile.v0)

ARG GDRCOPY_CUDA_VERSION=12.8

2026-05-30 05:06:31 UTC (buildkit.dockerfile.v0)

ARG GDRCOPY_OS_VERSION=Ubuntu22_04

2026-05-30 05:06:31 UTC (buildkit.dockerfile.v0)

ARG TARGETPLATFORM

2026-05-30 05:06:31 UTC (buildkit.dockerfile.v0)

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

2026-05-30 05:06:38 UTC (buildkit.dockerfile.v0)

RUN |10 CUDA_VERSION=12.9.1 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=0.6.11.post2 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

2026-05-30 05:06:38 UTC (buildkit.dockerfile.v0)

ARG BITSANDBYTES_VERSION_X86=0.46.1

2026-05-30 05:06:38 UTC (buildkit.dockerfile.v0)

ARG BITSANDBYTES_VERSION_ARM64=0.42.0

2026-05-30 05:06:38 UTC (buildkit.dockerfile.v0)

ARG TIMM_VERSION=>=1.0.17

2026-05-30 05:06:38 UTC (buildkit.dockerfile.v0)

ARG RUNAI_MODEL_STREAMER_VERSION=>=0.15.7

2026-05-30 05:06:42 UTC (buildkit.dockerfile.v0)

RUN |14 CUDA_VERSION=12.9.1 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=0.6.11.post2 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

2026-05-30 05:06:42 UTC (buildkit.dockerfile.v0)

ARG PIP_INDEX_URL UV_INDEX_URL

2026-05-30 05:06:42 UTC (buildkit.dockerfile.v0)

ARG PIP_EXTRA_INDEX_URL UV_EXTRA_INDEX_URL

2026-05-30 05:06:42 UTC (buildkit.dockerfile.v0)

ARG PYTORCH_CUDA_INDEX_BASE_URL

2026-05-30 05:06:42 UTC (buildkit.dockerfile.v0)

ARG PIP_KEYRING_PROVIDER UV_KEYRING_PROVIDER

2026-05-30 05:06:42 UTC (buildkit.dockerfile.v0)

ARG PYTORCH_NIGHTLY

2026-05-30 05:06:42 UTC (buildkit.dockerfile.v0)

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

2026-05-30 06:00:20 UTC (buildkit.dockerfile.v0)

RUN |22 CUDA_VERSION=12.9.1 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=0.6.11.post2 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

2026-05-30 06:00:21 UTC (buildkit.dockerfile.v0)

RUN |22 CUDA_VERSION=12.9.1 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=0.6.11.post2 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

2026-05-30 06:00:21 UTC (buildkit.dockerfile.v0)

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

2026-05-30 06:00:21 UTC (buildkit.dockerfile.v0)

RUN |22 CUDA_VERSION=12.9.1 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=0.6.11.post2 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

2026-05-30 06:07:24 UTC (buildkit.dockerfile.v0)

RUN |22 CUDA_VERSION=12.9.1 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=0.6.11.post2 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

2026-05-30 06:07:24 UTC (buildkit.dockerfile.v0)

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

2026-05-30 06:07:24 UTC (buildkit.dockerfile.v0)

COPY examples examples # buildkit

2026-05-30 06:07:24 UTC (buildkit.dockerfile.v0)

COPY benchmarks benchmarks # buildkit

2026-05-30 06:07:25 UTC (buildkit.dockerfile.v0)

COPY ./vllm/collect_env.py . # buildkit

2026-05-30 06:07:25 UTC (buildkit.dockerfile.v0)

ARG TARGETPLATFORM

2026-05-30 06:07:25 UTC (buildkit.dockerfile.v0)

ARG INSTALL_KV_CONNECTORS=false

2026-05-30 06:07:25 UTC (buildkit.dockerfile.v0)

ARG CUDA_VERSION

2026-05-30 06:07:25 UTC (buildkit.dockerfile.v0)

ARG VLLM_BUILD_COMMIT

2026-05-30 06:07:25 UTC (buildkit.dockerfile.v0)

ARG VLLM_BUILD_PIPELINE

2026-05-30 06:07:25 UTC (buildkit.dockerfile.v0)

ARG VLLM_BUILD_URL

2026-05-30 06:07:25 UTC (buildkit.dockerfile.v0)

ARG VLLM_IMAGE_TAG

2026-05-30 06:07:25 UTC (buildkit.dockerfile.v0)

ARG PIP_INDEX_URL UV_INDEX_URL

2026-05-30 06:07:25 UTC (buildkit.dockerfile.v0)

ARG PIP_EXTRA_INDEX_URL UV_EXTRA_INDEX_URL

2026-05-30 06:07:25 UTC (buildkit.dockerfile.v0)

ENV UV_HTTP_TIMEOUT=500

2026-05-30 06:07:25 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

2026-05-30 06:07:25 UTC (buildkit.dockerfile.v0)

ENV TORCH_CUDA_ARCH_LIST=8.0 8.7 8.9 9.0 10.0 12.0

2026-05-30 06:14:09 UTC (buildkit.dockerfile.v0)

RUN |12 TARGETPLATFORM=linux/arm64 INSTALL_KV_CONNECTORS=true CUDA_VERSION=12.9.1 VLLM_BUILD_COMMIT=ef8840adc73bfbe3108811cebcd8af7252f9b6f0 VLLM_BUILD_PIPELINE=019d130e-464e-4ff7-b84b-492992c0c06b VLLM_BUILD_URL=https://buildkite.com/vllm/release-v2/builds/2144 VLLM_IMAGE_TAG=vllm/vllm-openai:cu129-nightly-ef8840adc73bfbe3108811cebcd8af7252f9b6f0 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 12.0 /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 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 ${BUILD_PKGS} && rm -rf /var/lib/apt/lists/* ); uv pip install --system --force-reinstall --no-deps nixl-cu${CUDA_MAJOR}; fi # buildkit

2026-05-30 06:14:09 UTC (buildkit.dockerfile.v0)

ARG MOONCAKE_WHEEL_AARCH64

2026-05-30 06:14:09 UTC (buildkit.dockerfile.v0)

ARG MOONCAKE_WHEEL_X86_64

2026-05-30 06:14:16 UTC (buildkit.dockerfile.v0)

RUN |14 TARGETPLATFORM=linux/arm64 INSTALL_KV_CONNECTORS=true CUDA_VERSION=12.9.1 VLLM_BUILD_COMMIT=ef8840adc73bfbe3108811cebcd8af7252f9b6f0 VLLM_BUILD_PIPELINE=019d130e-464e-4ff7-b84b-492992c0c06b VLLM_BUILD_URL=https://buildkite.com/vllm/release-v2/builds/2144 VLLM_IMAGE_TAG=vllm/vllm-openai:cu129-nightly-ef8840adc73bfbe3108811cebcd8af7252f9b6f0 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 12.0 MOONCAKE_WHEEL_AARCH64=https://vllm-wheels.s3.amazonaws.com/mooncake/mooncake_transfer_engine-0.3.10.post2-0da9dfea3-cp312-cp312-manylinux_2_35_aarch64.whl MOONCAKE_WHEEL_X86_64=https://vllm-wheels.s3.amazonaws.com/mooncake/mooncake_transfer_engine-0.3.10.post2-0da9dfea3-cp312-cp312-manylinux_2_35_x86_64.whl /bin/sh -c if [ "$INSTALL_KV_CONNECTORS" = "true" ]; then if [ "$TARGETPLATFORM" = "linux/arm64" ]; then WHEEL="${MOONCAKE_WHEEL_AARCH64}"; else WHEEL="${MOONCAKE_WHEEL_X86_64}"; fi && if [ -n "${WHEEL}" ]; then uv pip install --system "${WHEEL}" && CUDA_MAJOR="${CUDA_VERSION%%.*}" && if [ ! -f /usr/local/cuda/lib64/libcudart.so ] && [ -f "/usr/local/cuda/lib64/libcudart.so.${CUDA_MAJOR}" ]; then ln -s "libcudart.so.${CUDA_MAJOR}" /usr/local/cuda/lib64/libcudart.so; fi; fi; fi # buildkit

2026-05-30 06:14:16 UTC (buildkit.dockerfile.v0)

ENV VLLM_USAGE_SOURCE=production-docker-image

2026-05-30 06:14:16 UTC (buildkit.dockerfile.v0)

ENV VLLM_BUILD_COMMIT=ef8840adc73bfbe3108811cebcd8af7252f9b6f0 VLLM_BUILD_PIPELINE=019d130e-464e-4ff7-b84b-492992c0c06b VLLM_BUILD_URL=https://buildkite.com/vllm/release-v2/builds/2144 VLLM_IMAGE_TAG=vllm/vllm-openai:cu129-nightly-ef8840adc73bfbe3108811cebcd8af7252f9b6f0

2026-05-30 06:14:16 UTC (buildkit.dockerfile.v0)

LABEL org.opencontainers.image.source=https://github.com/vllm-project/vllm org.opencontainers.image.revision=ef8840adc73bfbe3108811cebcd8af7252f9b6f0 org.opencontainers.image.version=vllm/vllm-openai:cu129-nightly-ef8840adc73bfbe3108811cebcd8af7252f9b6f0 org.opencontainers.image.url=https://buildkite.com/vllm/release-v2/builds/2144 ai.vllm.build.commit=ef8840adc73bfbe3108811cebcd8af7252f9b6f0 ai.vllm.build.pipeline=019d130e-464e-4ff7-b84b-492992c0c06b ai.vllm.build.url=https://buildkite.com/vllm/release-v2/builds/2144 ai.vllm.image.tag=vllm/vllm-openai:cu129-nightly-ef8840adc73bfbe3108811cebcd8af7252f9b6f0

2026-05-30 06:14:16 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