2026-05-09 05:42:58 UTC
11.2 GB
12.9.1
DEBIAN_FRONTENDnoninteractive
LD_LIBRARY_PATH/usr/local/nvidia/lib64:/usr/local/cuda/lib64:/usr/local/cuda/lib64
NVARCHsbsa
NVIDIA_DRIVER_CAPABILITIEScompute,utility
NVIDIA_REQUIRE_CUDAcuda>=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_DEVICESall
NV_CUDA_CUDART_VERSION12.9.79-1
PATH/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 12.0
UV_HTTP_TIMEOUT500
UV_INDEX_STRATEGYunsafe-best-match
UV_LINK_MODEcopy
VLLM_BUILD_COMMITf6490a28413526adefae8dd7af32906d060e0436
VLLM_BUILD_PIPELINE019d130e-464e-4ff7-b84b-492992c0c06b
VLLM_BUILD_URLhttps://buildkite.com/vllm/release-v2/builds/1423
VLLM_ENABLE_CUDA_COMPATIBILITY0
VLLM_IMAGE_TAGvllm/vllm-openai:cu129-nightly-f6490a28413526adefae8dd7af32906d060e0436
VLLM_USAGE_SOURCEproduction-docker-image
[#000] sha256:2ea2730b4ab400d71167ddb8627f741637496aa57128fdfc248d6a9f799d76e9 - 0.24% (27.1 MB)
[#001] sha256:7aa2d0bb5c94f1cf869e71e4db856d2ca0733f5eaab55dd514441da9616abb35 - 0.04% (4.38 MB)
[#002] sha256:5136ae4e75ffd61960e9220c7d7625a3ee213ff63c25fdc24e85bfe229b16ab5 - 0.81% (93.1 MB)
[#003] sha256:6f760a753c5e1fc35281126d63b6ca9bef93e49f89a826a2bc2786e293d88f00 - 0.0% (182 Bytes)
[#004] sha256:6e8af4fd0a071982e528b634ba99dec2474c21147f99748be708f36e10e3f4c2 - 0.0% (6.72 KB)
[#005] sha256:22e49b96b24fbc0bfeed84fa7d1563e8f1fb1924b369f1fe288959c1e0aa0892 - 0.0% (104 Bytes)
[#006] sha256:5e919c3138db1dafcf2e83e54af6eb704578d37bc3231e892b97df2687f57b39 - 0.0% (230 Bytes)
[#007] sha256:1b5e7bb2c3c4bdc3e9fed07c69eb50de783003f98dad74caa80a0a92ca260531 - 1.76% (201 MB)
[#008] sha256:121c68dff15a9f55b85e415fc885fa121f723338f09fdd8b705804d8a9928f76 - 18.53% (2.07 GB)
[#009] sha256:ec721b07c7d88f0f6dedcb7b09efff15fc938ecb03c2d5f93da84f8eea66c430 - 0.4% (45.3 MB)
[#010] sha256:b17df201ed7863d727cad944780da48a2bf3df309e5300d8dd8e0b3145e9d8d7 - 0.0% (1.52 KB)
[#011] sha256:64ba202fc5e8c9c9a554d93931382af708a95c2c57ad15fd73d2509bddc6e84d - 0.0% (628 Bytes)
[#012] sha256:a2140964285ae653b7308d94a8357f1784cd6f9ca327c36124f18c5f052810f4 - 39.97% (4.47 GB)
[#013] sha256:1d88b20f26503500f0f58c28dc3f8cbf0ab96c2a501357867d261ba10ad4d908 - 15.86% (1.77 GB)
[#014] sha256:4cb91f294a0d966a8fa245e67e91a1fae9e5d5d26ad1afed6c8b406ac4ff7fb4 - 0.0% (895 Bytes)
[#015] sha256:3f34c601e414402313c76302b50b1348404afe9d488e2ab943ea2592dc01df64 - 0.0% (520 KB)
[#016] sha256:d4d151a0a13fcefae97e3467d8a111e589308e8c749b8bf403ec98e8aacc0798 - 3.15% (360 MB)
[#017] sha256:b5f9dc8a6fd433c2edeedca0b5b7e7b16705cd55f6f052824a0cf562b7a509c2 - 0.0% (200 Bytes)
[#018] sha256:5ee552546cef0b643b047d4ce484257dc37d8f6c2caed0409aca7de142b4fdfb - 5.88% (672 MB)
[#019] sha256:1c2630a4d2fc235d2042e6f66699a0472b846c13321cc14ad401cd11174f94e6 - 0.0% (123 Bytes)
[#020] sha256:b03d858ae0324568f763a084d75a71f8ccd18282a60c658c8d1ac786b3533590 - 0.13% (15.2 MB)
[#021] sha256:8c239bebf1847ba9a9e20baef82249793e0b8b1c269ccb1b6dbc62383a650233 - 2.49% (285 MB)
[#022] sha256:84d051758bf53d037834e03e004b4815966fe4998e4f9bc83bab6b9f66d71525 - 0.0% (249 KB)
[#023] sha256:1f355d96a3f2c09a3ab27d4e37e9cf27070934056fa8e4b1d8397fa6b323aa48 - 0.0% (226 KB)
[#024] sha256:13062601dbe0e2649f536add224fe62df1bcaa078de66adfd614d40623bb555e - 0.0% (9.62 KB)
[#025] sha256:f0201c11f8c2739f1d899703b262b3fb28038c210fde0c94bd599aeccdf61c80 - 10.75% (1.2 GB)
/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 <cudatools@nvidia.com>
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
2026-05-09 05:03:00 UTC (buildkit.dockerfile.v0)ARG CUDA_VERSION
2026-05-09 05:03:00 UTC (buildkit.dockerfile.v0)ARG PYTHON_VERSION
2026-05-09 05:03:00 UTC (buildkit.dockerfile.v0)ARG DEADSNAKES_MIRROR_URL
2026-05-09 05:03:00 UTC (buildkit.dockerfile.v0)ARG DEADSNAKES_GPGKEY_URL
2026-05-09 05:03:00 UTC (buildkit.dockerfile.v0)ARG GET_PIP_URL
2026-05-09 05:03:00 UTC (buildkit.dockerfile.v0)ENV DEBIAN_FRONTEND=noninteractive
2026-05-09 05:03:00 UTC (buildkit.dockerfile.v0)WORKDIR /vllm-workspace
2026-05-09 05:03:01 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
2026-05-09 05:04:32 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
2026-05-09 05:06:13 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
2026-05-09 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
2026-05-09 05:06:15 UTC (buildkit.dockerfile.v0)ENV UV_HTTP_TIMEOUT=500
2026-05-09 05:06:15 UTC (buildkit.dockerfile.v0)ENV UV_INDEX_STRATEGY=unsafe-best-match
2026-05-09 05:06:15 UTC (buildkit.dockerfile.v0)ENV UV_LINK_MODE=copy
2026-05-09 05:06:15 UTC (buildkit.dockerfile.v0)ENV VLLM_ENABLE_CUDA_COMPATIBILITY=0
2026-05-09 05:06:15 UTC (buildkit.dockerfile.v0)ARG PYTORCH_CUDA_INDEX_BASE_URL
2026-05-09 05:06:15 UTC (buildkit.dockerfile.v0)COPY requirements/common.txt /tmp/common.txt # buildkit
2026-05-09 05:06:15 UTC (buildkit.dockerfile.v0)COPY requirements/cuda.txt /tmp/requirements-cuda.txt # buildkit
2026-05-09 05:06:28 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 uv pip install --system -r /tmp/requirements-cuda.txt --extra-index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.') && rm /tmp/requirements-cuda.txt /tmp/common.txt # buildkit
2026-05-09 05:06:28 UTC (buildkit.dockerfile.v0)ARG FLASHINFER_VERSION=0.6.8.post1
2026-05-09 05:07:19 UTC (buildkit.dockerfile.v0)RUN |7 CUDA_VERSION=12.9.1 PYTHON_VERSION=3.12 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl FLASHINFER_VERSION=0.6.8.post1 /bin/sh -c uv pip install --system flashinfer-jit-cache==${FLASHINFER_VERSION} --extra-index-url https://flashinfer.ai/whl/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.') # buildkit
2026-05-09 05:07:19 UTC (buildkit.dockerfile.v0)ARG GDRCOPY_CUDA_VERSION=12.8
2026-05-09 05:07:19 UTC (buildkit.dockerfile.v0)ARG GDRCOPY_OS_VERSION=Ubuntu22_04
2026-05-09 05:07:19 UTC (buildkit.dockerfile.v0)ARG TARGETPLATFORM
2026-05-09 05:07:19 UTC (buildkit.dockerfile.v0)COPY tools/install_gdrcopy.sh /tmp/install_gdrcopy.sh # buildkit
2026-05-09 05:07:33 UTC (buildkit.dockerfile.v0)RUN |10 CUDA_VERSION=12.9.1 PYTHON_VERSION=3.12 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl FLASHINFER_VERSION=0.6.8.post1 GDRCOPY_CUDA_VERSION=12.8 GDRCOPY_OS_VERSION=Ubuntu22_04 TARGETPLATFORM=linux/arm64 /bin/sh -c set -eux; case "${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
2026-05-09 05:07:33 UTC (buildkit.dockerfile.v0)ARG BITSANDBYTES_VERSION_X86=0.46.1
2026-05-09 05:07:33 UTC (buildkit.dockerfile.v0)ARG BITSANDBYTES_VERSION_ARM64=0.42.0
2026-05-09 05:07:33 UTC (buildkit.dockerfile.v0)ARG TIMM_VERSION=>=1.0.17
2026-05-09 05:07:33 UTC (buildkit.dockerfile.v0)ARG RUNAI_MODEL_STREAMER_VERSION=>=0.15.7
2026-05-09 05:07:36 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=0.6.8.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
2026-05-09 05:07:36 UTC (buildkit.dockerfile.v0)ARG PIP_INDEX_URL UV_INDEX_URL
2026-05-09 05:07:36 UTC (buildkit.dockerfile.v0)ARG PIP_EXTRA_INDEX_URL UV_EXTRA_INDEX_URL
2026-05-09 05:07:36 UTC (buildkit.dockerfile.v0)ARG PYTORCH_CUDA_INDEX_BASE_URL
2026-05-09 05:07:36 UTC (buildkit.dockerfile.v0)ARG PIP_KEYRING_PROVIDER UV_KEYRING_PROVIDER
2026-05-09 05:07:36 UTC (buildkit.dockerfile.v0)ARG PYTORCH_NIGHTLY
2026-05-09 05:07:36 UTC (buildkit.dockerfile.v0)COPY /workspace/torch_lib_versions.txt torch_lib_versions.txt # buildkit
2026-05-09 05:21:25 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=0.6.8.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
2026-05-09 05:21:25 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=0.6.8.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
2026-05-09 05:21:25 UTC (buildkit.dockerfile.v0)ENV LD_LIBRARY_PATH=/usr/local/cuda/lib64:/usr/local/cuda/lib64
2026-05-09 05:21:26 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=0.6.8.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
2026-05-09 05:36:10 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=0.6.8.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
2026-05-09 05:36:10 UTC (buildkit.dockerfile.v0)ENV LD_LIBRARY_PATH=/usr/local/nvidia/lib64:/usr/local/cuda/lib64:/usr/local/cuda/lib64
2026-05-09 05:36:10 UTC (buildkit.dockerfile.v0)COPY examples examples # buildkit
2026-05-09 05:36:10 UTC (buildkit.dockerfile.v0)COPY benchmarks benchmarks # buildkit
2026-05-09 05:36:10 UTC (buildkit.dockerfile.v0)COPY ./vllm/collect_env.py . # buildkit
2026-05-09 05:36:10 UTC (buildkit.dockerfile.v0)ARG TARGETPLATFORM
2026-05-09 05:36:10 UTC (buildkit.dockerfile.v0)ARG INSTALL_KV_CONNECTORS=false
2026-05-09 05:36:10 UTC (buildkit.dockerfile.v0)ARG CUDA_VERSION
2026-05-09 05:36:10 UTC (buildkit.dockerfile.v0)ARG VLLM_BUILD_COMMIT
2026-05-09 05:36:10 UTC (buildkit.dockerfile.v0)ARG VLLM_BUILD_PIPELINE
2026-05-09 05:36:10 UTC (buildkit.dockerfile.v0)ARG VLLM_BUILD_URL
2026-05-09 05:36:10 UTC (buildkit.dockerfile.v0)ARG VLLM_IMAGE_TAG
2026-05-09 05:36:10 UTC (buildkit.dockerfile.v0)ARG PIP_INDEX_URL UV_INDEX_URL
2026-05-09 05:36:10 UTC (buildkit.dockerfile.v0)ARG PIP_EXTRA_INDEX_URL UV_EXTRA_INDEX_URL
2026-05-09 05:36:10 UTC (buildkit.dockerfile.v0)ENV UV_HTTP_TIMEOUT=500
2026-05-09 05:36:10 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
2026-05-09 05:36:10 UTC (buildkit.dockerfile.v0)ENV TORCH_CUDA_ARCH_LIST=8.0 8.7 8.9 9.0 10.0 12.0
2026-05-09 05:42:58 UTC (buildkit.dockerfile.v0)RUN |12 TARGETPLATFORM=linux/arm64 INSTALL_KV_CONNECTORS=true CUDA_VERSION=12.9.1 VLLM_BUILD_COMMIT=f6490a28413526adefae8dd7af32906d060e0436 VLLM_BUILD_PIPELINE=019d130e-464e-4ff7-b84b-492992c0c06b VLLM_BUILD_URL=https://buildkite.com/vllm/release-v2/builds/1423 VLLM_IMAGE_TAG=vllm/vllm-openai:cu129-nightly-f6490a28413526adefae8dd7af32906d060e0436 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 [ "$INSTALL_KV_CONNECTORS" = "true" ]; then if [ "$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
2026-05-09 05:42:58 UTC (buildkit.dockerfile.v0)ENV VLLM_USAGE_SOURCE=production-docker-image
2026-05-09 05:42:58 UTC (buildkit.dockerfile.v0)ENV VLLM_BUILD_COMMIT=f6490a28413526adefae8dd7af32906d060e0436 VLLM_BUILD_PIPELINE=019d130e-464e-4ff7-b84b-492992c0c06b VLLM_BUILD_URL=https://buildkite.com/vllm/release-v2/builds/1423 VLLM_IMAGE_TAG=vllm/vllm-openai:cu129-nightly-f6490a28413526adefae8dd7af32906d060e0436
2026-05-09 05:42:58 UTC (buildkit.dockerfile.v0)LABEL org.opencontainers.image.source=https://github.com/vllm-project/vllm org.opencontainers.image.revision=f6490a28413526adefae8dd7af32906d060e0436 org.opencontainers.image.version=vllm/vllm-openai:cu129-nightly-f6490a28413526adefae8dd7af32906d060e0436 org.opencontainers.image.url=https://buildkite.com/vllm/release-v2/builds/1423 ai.vllm.build.commit=f6490a28413526adefae8dd7af32906d060e0436 ai.vllm.build.pipeline=019d130e-464e-4ff7-b84b-492992c0c06b ai.vllm.build.url=https://buildkite.com/vllm/release-v2/builds/1423 ai.vllm.image.tag=vllm/vllm-openai:cu129-nightly-f6490a28413526adefae8dd7af32906d060e0436
2026-05-09 05:42:58 UTC (buildkit.dockerfile.v0)ENTRYPOINT ["vllm" "serve"]
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.