Namespace
vllm
Image / Tagvllm-openai:cu134-nightly-aarch64
Content Digestsha256:9d1f28a1d81edb39f86c2fc35c24bdd422b07df8435f2fe3f186f98c6d9a1b28
Details
2026-11-02 06:40:26 UTC
11.7 GB
Labels
-
ai.vllm.build.commit76c6f3f2a95f6049657db1e513133b824a5c8175
-
ai.vllm.build.pipeline019d130e-464e-4ff7-b84b-492992c0c06b
-
ai.vllm.build.urlhttps://buildkite.com/vllm/release-v2/builds/9707
-
ai.vllm.image.tagvllm/vllm-openai:cu134-nightly-76c6f3f2a95f6049657db1e513133b824a5c8175
-
maintainerNVIDIA CORPORATION <cudatools@nvidia.com>
-
org.opencontainers.image.revision76c6f3f2a95f6049657db1e513133b824a5c8175
-
org.opencontainers.image.sourcehttps://github.com/vllm-project/vllm
-
org.opencontainers.image.urlhttps://buildkite.com/vllm/release-v2/builds/9707
-
org.opencontainers.image.versionvllm/vllm-openai:cu134-nightly-76c6f3f2a95f6049657db1e513133b824a5c8175
Environment
CRIU_CUDA_PLUGIN_DIR/usr/local/lib/criu
CUDA_HOME/usr/local/cuda
CUDA_VERSION13.4.1
DEBIAN_FRONTENDnoninteractive
LD_LIBRARY_PATH/usr/local/nvidia/lib64:/usr/local/cuda/lib64:/usr/local/cuda/lib64:/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/local/cuda/lib64
NVARCHsbsa
NVIDIA_DRIVER_CAPABILITIEScompute,utility
NVIDIA_REQUIRE_CUDAcuda>=13.4 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>=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>=580,driver<581 brand=grid,driver>=580,driver<581 brand=tesla,driver>=580,driver<581 brand=nvidia,driver>=580,driver<581 brand=quadro,driver>=580,driver<581 brand=quadrortx,driver>=580,driver<581 brand=nvidiartx,driver>=580,driver<581 brand=vapps,driver>=580,driver<581 brand=vpc,driver>=580,driver<581 brand=vcs,driver>=580,driver<581 brand=vws,driver>=580,driver<581 brand=cloudgaming,driver>=580,driver<581 brand=unknown,driver>=590,driver<591 brand=grid,driver>=590,driver<591 brand=tesla,driver>=590,driver<591 brand=nvidia,driver>=590,driver<591 brand=quadro,driver>=590,driver<591 brand=quadrortx,driver>=590,driver<591 brand=nvidiartx,driver>=590,driver<591 brand=vapps,driver>=590,driver<591 brand=vpc,driver>=590,driver<591 brand=vcs,driver>=590,driver<591 brand=vws,driver>=590,driver<591 brand=cloudgaming,driver>=590,driver<591 brand=unknown,driver>=595,driver<596 brand=grid,driver>=595,driver<596 brand=tesla,driver>=595,driver<596 brand=nvidia,driver>=595,driver<596 brand=quadro,driver>=595,driver<596 brand=quadrortx,driver>=595,driver<596 brand=nvidiartx,driver>=595,driver<596 brand=vapps,driver>=595,driver<596 brand=vpc,driver>=595,driver<596 brand=vcs,driver>=595,driver<596 brand=vws,driver>=595,driver<596 brand=cloudgaming,driver>=595,driver<596 brand=unknown,driver>=610,driver<611 brand=grid,driver>=610,driver<611 brand=tesla,driver>=610,driver<611 brand=nvidia,driver>=610,driver<611 brand=quadro,driver>=610,driver<611 brand=quadrortx,driver>=610,driver<611 brand=nvidiartx,driver>=610,driver<611 brand=vapps,driver>=610,driver<611 brand=vpc,driver>=610,driver<611 brand=vcs,driver>=610,driver<611 brand=vws,driver>=610,driver<611 brand=cloudgaming,driver>=610,driver<611
NVIDIA_VISIBLE_DEVICESall
NV_CUDA_CUDART_VERSION13.4.49-1
PATH/usr/local/cuda/bin:/usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin
TORCH_CUDA_ARCH_LIST8.0 8.7 8.9 9.0 10.0 11.0 12.0
UV_CACHE_DIR/opt/uv/cache
UV_COMPILE_BYTECODE1
UV_HTTP_TIMEOUT500
UV_INDEX_STRATEGYunsafe-best-match
UV_LINK_MODEcopy
UV_OVERRIDE/etc/uv-overrides.txt
UV_PYTHON_INSTALL_DIR/opt/uv/python
VLLM_BUILD_COMMIT76c6f3f2a95f6049657db1e513133b824a5c8175
VLLM_BUILD_PIPELINE019d130e-464e-4ff7-b84b-492992c0c06b
VLLM_BUILD_URLhttps://buildkite.com/vllm/release-v2/builds/9707
VLLM_ENABLE_CUDA_COMPATIBILITY0
VLLM_IMAGE_TAGvllm/vllm-openai:cu134-nightly-76c6f3f2a95f6049657db1e513133b824a5c8175
VLLM_USAGE_SOURCEproduction-docker-image
Layers
[#000] sha256:cbe7d19e9352b766d4ee4478b2ad88f0ce56cd739a2e9435751f24ffb9bbcbd8 - 0.24% (28.6 MB)
[#001] sha256:41539e8f3ab4d59d1cfbaf7d1a7b8980174025fddbb4d4d024bde423fcf2d8bd - 0.08% (9.9 MB)
[#002] sha256:2b65f41e87808cf0182588cd6c34f19e0b6a26ffe72c37f66c5ebc9b5d12f886 - 0.0% (398 KB)
[#003] sha256:e9565537a4394232947398643dee33cfa46093d9c4d449c6d4ecc6d89efcfcc3 - 1.28% (153 MB)
[#004] sha256:cf2558de4d5cf175a4e3006dd6ca332bd29780d432770bb5fc2a0fd09b83b5c2 - 1.28% (153 MB)
[#005] sha256:d7bed4e05d98a671f84a9e0df60967420a7764e777680a6446a07dd8e107d33e - 0.0% (187 Bytes)
[#006] sha256:541a3eb87cd3c57a7b35621cc132a2096274503bffe4806c14db97943b681042 - 0.0% (6.72 KB)
[#007] sha256:028f85386b7a27889fa72a2c85bbe4743dbe07b2f7a6dc2951042daff6b199f1 - 0.0% (104 Bytes)
[#008] sha256:c5d5698f8ce560856735357544289cf455e82d13cac1c35b86ca1845e5cdea5f - 0.0% (229 Bytes)
[#009] sha256:8c8460430194de59c912d4d6aad0ca1efcf5d2eab483814a71985357807018b6 - 1.74% (208 MB)
[#010] sha256:06cbc325332f6b0ad4c73d644f8c16e92e74bde3c9ad21023b160fbf085339de - 13.2% (1.55 GB)
[#011] sha256:798666330478e31a1b0bd78b6237d33d89ed77543f15ae8bc59e46e49e4ee540 - 0.0% (1.62 KB)
[#012] sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1 - 0.0% (32 Bytes)
[#013] sha256:221b314b67ac22c4c764059e3a00819a5a48c34488985cc35fea01ce770f2343 - 0.27% (32.3 MB)
[#014] sha256:e957059c1c5f09fd8f55942add6f357a0d7b77c667ab8df9d4636ecf99ff6d90 - 0.0% (149 Bytes)
[#015] sha256:f3484a0a83e23e2ad43681997a2c5139793e84fd0067c8b24fa34cc34973628f - 0.0% (161 Bytes)
[#016] sha256:3b45701198ef14e131eebed5f455485ceeb54535aa62f1f68271cf139be29512 - 0.0% (3.62 KB)
[#017] sha256:145c114d88bb8fe0680c10c76eb24105d0040fe46bbec067b602bf73f302f8bc - 0.0% (2.03 KB)
[#018] sha256:145c114d88bb8fe0680c10c76eb24105d0040fe46bbec067b602bf73f302f8bc - 0.0% (2.03 KB)
[#019] sha256:70b5fcb6b4382a14bda9cedf60c42fdb88d1c86749f6fa994c3ab1e93d1a248d - 0.0% (1.69 KB)
[#020] sha256:75fc77a9cdfce5d9bdcb87d95377410a3171b9482740354f2c448a4d84d23c04 - 0.0% (810 Bytes)
[#021] sha256:7477c1a14e5d4a4963c6167ddc7e5e23dec067cd50ec462117a804a6b1afe47c - 36.54% (4.28 GB)
[#022] sha256:281d4faa180343d6f4386034e9c107aaec7a2e42b0ed3f0285de15301a747fb6 - 27.44% (3.21 GB)
[#023] sha256:81c89e51c0094b2662bf67aa3bd92417c943abf4f93fda6768bdf572b10f3502 - 0.0% (894 Bytes)
[#024] sha256:46e38c033e0f1987e91e3f7db7f52521c3d60548a1973de345d6aeefa6541a8f - 0.0% (519 KB)
[#025] sha256:e19d7103a3109c89369596bbdd8885f70061b4022121ef6bd27289a511595224 - 2.3% (275 MB)
[#026] sha256:e69fb01d829a53f213ceec923589468c815c3565f8d31845a9658c10abae969e - 0.0% (204 Bytes)
[#027] sha256:95258acd879110f03f7de944a20a51501a010bf33a5ac98711894485b4e63d4a - 0.0% (249 Bytes)
[#028] sha256:99d1a344160165fd47dcb3370c5246669f6be2801dfbb46180a75aaeff970702 - 4.67% (559 MB)
[#029] sha256:d06b8be7728243828bfc91d1c2eda4490ebfb0ed6c0dc261ad5da30fe21bee53 - 0.0% (195 Bytes)
[#030] sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1 - 0.0% (32 Bytes)
[#031] sha256:2e457d2756ab547da5a886b23d6c1f6f8b4028d6ef077e23758bf08c19bae9e0 - 0.0% (253 Bytes)
[#032] sha256:6374d9929c0b9ef0f547261b221b8054b0dce0c7ea803af54f2b9c73609a1883 - 0.14% (17 MB)
[#033] sha256:4d2e591cd36ef72f28fe27aab8582dc8496e8b99af488a78db00d8699f00b4f8 - 0.0% (317 KB)
[#034] sha256:fc14eadf7ac81624e18ef829c9fee0fee57762399a73ffa437215bdec7040eaf - 0.0% (309 KB)
[#035] sha256:64da5e5f879eca029cebeb9bf805b18b68f0917a153f4721557a25c12c84f24b - 0.0% (9.61 KB)
[#036] sha256:589d6ec532dcdbb5253dece5e769b84a19045bd491617761687aeba16e044114 - 4.57% (547 MB)
[#037] sha256:b707e66a60ebd1b6591cbb7be7205ecad22c3f9e463c5679429490a6dc13ee9b - 2.83% (339 MB)
[#038] sha256:88c5d61053fff75bff9afaf20ee569c07447f1fb711dba93c93a40267a74b26e - 0.0% (237 Bytes)
[#039] sha256:a5282992d4ec749dc4bf9e57ed7b895d895e37ccd94bb7c396b99d1c0511a1d6 - 0.0% (825 Bytes)
[#040] sha256:3b31bce76e26cfcb0407423e862d57e7619f113f368e588343c7ac480eb243e3 - 3.21% (385 MB)
[#041] sha256:8c59bfc3ec065797a1b31dbfbbba8e40afd4b5b618fd568e7fa2727b5f194845 - 0.23% (27.1 MB)
History
/bin/sh -c #(nop) ARG RELEASE
2026-09-07 06:57:57 UTC/bin/sh -c #(nop) ARG LAUNCHPAD_BUILD_ARCH
2026-09-07 06:57:57 UTC/bin/sh -c #(nop) LABEL org.opencontainers.image.version=24.04
2026-09-07 06:58:01 UTC/bin/sh -c #(nop) ADD file:06e064cbfe0750594affea730437107320bdf1e36232c304b900eaa55f88a633 in /
2026-09-07 06:58:01 UTC/bin/sh -c #(nop) CMD ["/bin/bash"]
2026-09-14 19:22:48 UTC (buildkit.dockerfile.v0)ENV NVARCH=sbsa
2026-09-14 19:22:48 UTC (buildkit.dockerfile.v0)ENV NVIDIA_REQUIRE_CUDA=cuda>=13.4 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>=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>=580,driver<581 brand=grid,driver>=580,driver<581 brand=tesla,driver>=580,driver<581 brand=nvidia,driver>=580,driver<581 brand=quadro,driver>=580,driver<581 brand=quadrortx,driver>=580,driver<581 brand=nvidiartx,driver>=580,driver<581 brand=vapps,driver>=580,driver<581 brand=vpc,driver>=580,driver<581 brand=vcs,driver>=580,driver<581 brand=vws,driver>=580,driver<581 brand=cloudgaming,driver>=580,driver<581 brand=unknown,driver>=590,driver<591 brand=grid,driver>=590,driver<591 brand=tesla,driver>=590,driver<591 brand=nvidia,driver>=590,driver<591 brand=quadro,driver>=590,driver<591 brand=quadrortx,driver>=590,driver<591 brand=nvidiartx,driver>=590,driver<591 brand=vapps,driver>=590,driver<591 brand=vpc,driver>=590,driver<591 brand=vcs,driver>=590,driver<591 brand=vws,driver>=590,driver<591 brand=cloudgaming,driver>=590,driver<591 brand=unknown,driver>=595,driver<596 brand=grid,driver>=595,driver<596 brand=tesla,driver>=595,driver<596 brand=nvidia,driver>=595,driver<596 brand=quadro,driver>=595,driver<596 brand=quadrortx,driver>=595,driver<596 brand=nvidiartx,driver>=595,driver<596 brand=vapps,driver>=595,driver<596 brand=vpc,driver>=595,driver<596 brand=vcs,driver>=595,driver<596 brand=vws,driver>=595,driver<596 brand=cloudgaming,driver>=595,driver<596 brand=unknown,driver>=610,driver<611 brand=grid,driver>=610,driver<611 brand=tesla,driver>=610,driver<611 brand=nvidia,driver>=610,driver<611 brand=quadro,driver>=610,driver<611 brand=quadrortx,driver>=610,driver<611 brand=nvidiartx,driver>=610,driver<611 brand=vapps,driver>=610,driver<611 brand=vpc,driver>=610,driver<611 brand=vcs,driver>=610,driver<611 brand=vws,driver>=610,driver<611 brand=cloudgaming,driver>=610,driver<611
2026-09-14 19:22:48 UTC (buildkit.dockerfile.v0)ENV NV_CUDA_CUDART_VERSION=13.4.49-1
2026-09-14 19:22:48 UTC (buildkit.dockerfile.v0)ARG TARGETARCH
2026-09-14 19:22:48 UTC (buildkit.dockerfile.v0)LABEL maintainer=NVIDIA CORPORATION <cudatools@nvidia.com>
2026-09-14 19:22:48 UTC (buildkit.dockerfile.v0)ARG IMAGE_UPGRADE_ID=0
2026-09-14 19:22:48 UTC (buildkit.dockerfile.v0)RUN |2 TARGETARCH=arm64 IMAGE_UPGRADE_ID=20260914 /bin/sh -c echo "IMAGE_UPGRADE_ID=${IMAGE_UPGRADE_ID}" && apt-get update && apt-get upgrade -y && apt-get install -y --no-install-recommends gnupg2 curl ca-certificates && curl -fsSLO https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2404/${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
2026-09-14 19:22:48 UTC (buildkit.dockerfile.v0)ENV CUDA_VERSION=13.4.1
2026-09-14 19:24:45 UTC (buildkit.dockerfile.v0)RUN |2 TARGETARCH=arm64 IMAGE_UPGRADE_ID=20260914 /bin/sh -c apt-get update && apt-get install -y --no-install-recommends cuda-cudart-13-4=${NV_CUDA_CUDART_VERSION} cuda-toolkit-13-4-config-common=${NV_CUDA_CUDART_VERSION} cuda-toolkit-13-config-common=${NV_CUDA_CUDART_VERSION} cuda-toolkit-config-common=${NV_CUDA_CUDART_VERSION} && rm -rf /var/lib/apt/lists/* # buildkit
2026-09-14 19:28:14 UTC (buildkit.dockerfile.v0)RUN |2 TARGETARCH=arm64 IMAGE_UPGRADE_ID=20260914 /bin/sh -c apt-get update && if apt-cache policy cuda-compat-13-4 2>/dev/null | grep -q "Candidate:"; then apt-get install -y --no-install-recommends cuda-compat-13-4; fi && rm -rf /var/lib/apt/lists/* # buildkit
2026-09-14 19:31:49 UTC (buildkit.dockerfile.v0)RUN |2 TARGETARCH=arm64 IMAGE_UPGRADE_ID=20260914 /bin/sh -c apt-get update && if apt-cache policy cuda-compat-orin-13-4 2>/dev/null | grep -q "Candidate:"; then apt-get install -y --no-install-recommends cuda-compat-orin-13-4; fi && rm -rf /var/lib/apt/lists/* # buildkit
2026-09-14 19:31:50 UTC (buildkit.dockerfile.v0)RUN |2 TARGETARCH=arm64 IMAGE_UPGRADE_ID=20260914 /bin/sh -c echo "/usr/local/cuda/lib64" >> /etc/ld.so.conf.d/nvidia.conf # buildkit
2026-09-14 19:31:50 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
2026-09-14 19:31:50 UTC (buildkit.dockerfile.v0)ENV LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/local/cuda/lib64
2026-09-14 19:31:50 UTC (buildkit.dockerfile.v0)COPY NGC-DL-CONTAINER-LICENSE / # buildkit
2026-09-14 19:31:50 UTC (buildkit.dockerfile.v0)ENV NVIDIA_VISIBLE_DEVICES=all
2026-09-14 19:31:50 UTC (buildkit.dockerfile.v0)ENV NVIDIA_DRIVER_CAPABILITIES=compute,utility
2026-11-02 06:03:04 UTC (buildkit.dockerfile.v0)ARG INSTALL_RUBIN_PRERELEASE
2026-11-02 06:03:04 UTC (buildkit.dockerfile.v0)ARG TARGETPLATFORM
2026-11-02 06:03:04 UTC (buildkit.dockerfile.v0)ARG max_jobs=2
2026-11-02 06:03:04 UTC (buildkit.dockerfile.v0)ARG CUDA_VERSION
2026-11-02 06:03:04 UTC (buildkit.dockerfile.v0)ARG PYTHON_VERSION
2026-11-02 06:03:04 UTC (buildkit.dockerfile.v0)ARG NCCL_VERSION
2026-11-02 06:03:04 UTC (buildkit.dockerfile.v0)ARG DEADSNAKES_MIRROR_URL
2026-11-02 06:03:04 UTC (buildkit.dockerfile.v0)ARG DEADSNAKES_GPGKEY_URL
2026-11-02 06:03:04 UTC (buildkit.dockerfile.v0)ARG GET_PIP_URL
2026-11-02 06:03:04 UTC (buildkit.dockerfile.v0)ENV DEBIAN_FRONTEND=noninteractive
2026-11-02 06:03:04 UTC (buildkit.dockerfile.v0)WORKDIR /vllm-workspace
2026-11-02 06:03:05 UTC (buildkit.dockerfile.v0)RUN |9 INSTALL_RUBIN_PRERELEASE=true TARGETPLATFORM=linux/arm64 max_jobs=16 CUDA_VERSION=13.4 PYTHON_VERSION=3.12 NCCL_VERSION=2.32.3 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py /bin/sh -c PYTHON_VERSION_STR=$(echo ${PYTHON_VERSION} | sed 's/\.//g') && echo "export PYTHON_VERSION_STR=${PYTHON_VERSION_STR}" >> /etc/environment # buildkit
2026-11-02 06:04:05 UTC (buildkit.dockerfile.v0)RUN |9 INSTALL_RUBIN_PRERELEASE=true TARGETPLATFORM=linux/arm64 max_jobs=16 CUDA_VERSION=13.4 PYTHON_VERSION=3.12 NCCL_VERSION=2.32.3 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py /bin/sh -c apt-get update -y && apt-get install -y --no-install-recommends ca-certificates software-properties-common curl sudo ffmpeg libsm6 libxext6 libgl1 && if [ ! -z ${DEADSNAKES_MIRROR_URL} ] ; then if [ ! -z "${DEADSNAKES_GPGKEY_URL}" ] ; then mkdir -p -m 0755 /etc/apt/keyrings ; curl -L ${DEADSNAKES_GPGKEY_URL} | gpg --dearmor > /etc/apt/keyrings/deadsnakes.gpg ; sudo chmod 644 /etc/apt/keyrings/deadsnakes.gpg ; echo "deb [signed-by=/etc/apt/keyrings/deadsnakes.gpg] ${DEADSNAKES_MIRROR_URL} $(lsb_release -cs) main" > /etc/apt/sources.list.d/deadsnakes.list ; fi ; else for i in 1 2 3; do add-apt-repository -y ppa:deadsnakes/ppa && break || { echo "Attempt $i failed, retrying in 5s..."; sleep 5; }; done ; fi && apt-get update -y && apt-get install -y --no-install-recommends python${PYTHON_VERSION} python${PYTHON_VERSION}-dev python${PYTHON_VERSION}-venv libibverbs-dev && rm -rf /var/lib/apt/lists/* && update-alternatives --install /usr/bin/python3 python3 /usr/bin/python${PYTHON_VERSION} 1 && update-alternatives --set python3 /usr/bin/python${PYTHON_VERSION} && ln -sf /usr/bin/python${PYTHON_VERSION}-config /usr/bin/python3-config && rm -f /usr/lib/python${PYTHON_VERSION}/EXTERNALLY-MANAGED && curl -sS ${GET_PIP_URL} | python${PYTHON_VERSION} && python3 --version && python3 -m pip --version # buildkit
2026-11-02 06:04:58 UTC (buildkit.dockerfile.v0)RUN |9 INSTALL_RUBIN_PRERELEASE=true TARGETPLATFORM=linux/arm64 max_jobs=16 CUDA_VERSION=13.4 PYTHON_VERSION=3.12 NCCL_VERSION=2.32.3 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py /bin/sh -c CUDA_VERSION_DASH=$(echo $CUDA_VERSION | cut -d. -f1,2 | tr '.' '-') && apt-get update -y && apt-get install -y --no-install-recommends --allow-change-held-packages cuda-nvcc-${CUDA_VERSION_DASH} cuda-cudart-${CUDA_VERSION_DASH} cuda-nvrtc-${CUDA_VERSION_DASH} cuda-nvrtc-dev-${CUDA_VERSION_DASH} cuda-cuobjdump-${CUDA_VERSION_DASH} libcurand-dev-${CUDA_VERSION_DASH} libcublas-dev-${CUDA_VERSION_DASH} libnuma-dev numactl && rm -rf /var/lib/apt/lists/* # buildkit
2026-11-02 06:04:58 UTC (buildkit.dockerfile.v0)ENV CUDA_HOME=/usr/local/cuda
2026-11-02 06:04:58 UTC (buildkit.dockerfile.v0)ENV PATH=/usr/local/cuda/bin:/usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin
2026-11-02 06:04:58 UTC (buildkit.dockerfile.v0)ENV LD_LIBRARY_PATH=/usr/local/cuda/lib64:/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/local/cuda/lib64
2026-11-02 06:04:58 UTC (buildkit.dockerfile.v0)COPY tools/install_snapshot_runtime.sh /usr/local/bin/install_snapshot_runtime.sh # buildkit
2026-11-02 06:04:59 UTC (buildkit.dockerfile.v0)RUN |9 INSTALL_RUBIN_PRERELEASE=true TARGETPLATFORM=linux/arm64 max_jobs=16 CUDA_VERSION=13.4 PYTHON_VERSION=3.12 NCCL_VERSION=2.32.3 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py /bin/sh -c if [ "${TARGETPLATFORM}" = "linux/amd64" ] && [ "${CUDA_VERSION%%.*}" -ge 13 ]; then MAX_JOBS="${max_jobs}" /usr/local/bin/install_snapshot_runtime.sh; else echo "Initialized snapshots are not installed for ${TARGETPLATFORM} with CUDA ${CUDA_VERSION}"; fi # buildkit
2026-11-02 06:04:59 UTC (buildkit.dockerfile.v0)ENV CRIU_CUDA_PLUGIN_DIR=/usr/local/lib/criu
2026-11-02 06:05:01 UTC (buildkit.dockerfile.v0)RUN |9 INSTALL_RUBIN_PRERELEASE=true TARGETPLATFORM=linux/arm64 max_jobs=16 CUDA_VERSION=13.4 PYTHON_VERSION=3.12 NCCL_VERSION=2.32.3 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py /bin/sh -c python3 -m pip install uv # buildkit
2026-11-02 06:05:01 UTC (buildkit.dockerfile.v0)ENV UV_HTTP_TIMEOUT=500
2026-11-02 06:05:01 UTC (buildkit.dockerfile.v0)ENV UV_INDEX_STRATEGY=unsafe-best-match
2026-11-02 06:05:01 UTC (buildkit.dockerfile.v0)ENV UV_LINK_MODE=copy
2026-11-02 06:05:01 UTC (buildkit.dockerfile.v0)ENV UV_PYTHON_INSTALL_DIR=/opt/uv/python
2026-11-02 06:05:01 UTC (buildkit.dockerfile.v0)ENV UV_CACHE_DIR=/opt/uv/cache
2026-11-02 06:05:01 UTC (buildkit.dockerfile.v0)ENV UV_COMPILE_BYTECODE=1
2026-11-02 06:05:02 UTC (buildkit.dockerfile.v0)RUN |9 INSTALL_RUBIN_PRERELEASE=true TARGETPLATFORM=linux/arm64 max_jobs=16 CUDA_VERSION=13.4 PYTHON_VERSION=3.12 NCCL_VERSION=2.32.3 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py /bin/sh -c mkdir -p "${UV_PYTHON_INSTALL_DIR}" "${UV_CACHE_DIR}" && chgrp -R 0 /opt/uv && chmod -R g+rwX,a+rX /opt/uv # buildkit
2026-11-02 06:05:03 UTC (buildkit.dockerfile.v0)RUN |9 INSTALL_RUBIN_PRERELEASE=true TARGETPLATFORM=linux/arm64 max_jobs=16 CUDA_VERSION=13.4 PYTHON_VERSION=3.12 NCCL_VERSION=2.32.3 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py /bin/sh -c CUDA_MAJOR=$(echo $CUDA_VERSION | cut -d. -f1) && if [ -n "$NCCL_VERSION" ]; then echo "nvidia-nccl-cu${CUDA_MAJOR}==${NCCL_VERSION}" > /etc/uv-overrides.txt; else touch /etc/uv-overrides.txt; fi # buildkit
2026-11-02 06:05:03 UTC (buildkit.dockerfile.v0)ENV UV_OVERRIDE=/etc/uv-overrides.txt
2026-11-02 06:05:04 UTC (buildkit.dockerfile.v0)RUN |9 INSTALL_RUBIN_PRERELEASE=true TARGETPLATFORM=linux/arm64 max_jobs=16 CUDA_VERSION=13.4 PYTHON_VERSION=3.12 NCCL_VERSION=2.32.3 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py /bin/sh -c useradd --uid 2000 --gid 0 --create-home --home-dir /home/vllm --shell /bin/bash vllm && mkdir -p /home/vllm/.cache /home/vllm/.config && chown -R 2000:0 /home/vllm && chmod -R g+rwX /home/vllm && chgrp 0 /etc/passwd /etc/group && chmod g=u /etc/passwd /etc/group # buildkit
2026-11-02 06:05:04 UTC (buildkit.dockerfile.v0)COPY docker/entrypoints/vllm-nonroot-entrypoint.sh /usr/local/bin/vllm-nonroot-entrypoint.sh # buildkit
2026-11-02 06:05:06 UTC (buildkit.dockerfile.v0)RUN |9 INSTALL_RUBIN_PRERELEASE=true TARGETPLATFORM=linux/arm64 max_jobs=16 CUDA_VERSION=13.4 PYTHON_VERSION=3.12 NCCL_VERSION=2.32.3 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py /bin/sh -c chmod 0755 /usr/local/bin/vllm-nonroot-entrypoint.sh # buildkit
2026-11-02 06:05:06 UTC (buildkit.dockerfile.v0)ENV VLLM_ENABLE_CUDA_COMPATIBILITY=0
2026-11-02 06:05:06 UTC (buildkit.dockerfile.v0)ARG PYTORCH_CUDA_INDEX_BASE_URL
2026-11-02 06:05:06 UTC (buildkit.dockerfile.v0)COPY requirements/common.txt /tmp/common.txt # buildkit
2026-11-02 06:05:06 UTC (buildkit.dockerfile.v0)COPY requirements/cuda.txt /tmp/requirements-cuda.txt # buildkit
2026-11-02 06:05:43 UTC (buildkit.dockerfile.v0)RUN |10 INSTALL_RUBIN_PRERELEASE=true TARGETPLATFORM=linux/arm64 max_jobs=16 CUDA_VERSION=13.4 PYTHON_VERSION=3.12 NCCL_VERSION=2.32.3 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl /bin/sh -c if [ "${INSTALL_RUBIN_PRERELEASE}" = "true" ] && [ ! -f /tmp/vllm-requirements/rubin-prerelease.txt ]; then echo "INSTALL_RUBIN_PRERELEASE=true requires requirements/rubin-prerelease.txt" >&2; exit 1; fi && if [ "$(echo $CUDA_VERSION | cut -d. -f1)" = "12" ]; then sed -i 's/^nvidia-cutlass-dsl\[cu13\]/nvidia-cutlass-dsl/' /tmp/requirements-cuda.txt; sed -i 's/^humming-kernels\[cu13\]/humming-kernels[cu12]/' /tmp/requirements-cuda.txt; fi && if [ "${INSTALL_RUBIN_PRERELEASE}" = "true" ]; then uv pip install --system --prerelease=allow --index-strategy unsafe-first-match -r /tmp/vllm-requirements/rubin-prerelease.txt && sed -Ei '/^[[:space:]]*(torch|torchvision|torchaudio)[[:space:]]*==/Id' /tmp/requirements-cuda.txt && uv pip install --system -r /tmp/requirements-cuda.txt && uv pip install --system --prerelease=allow --index-strategy unsafe-first-match -r /tmp/vllm-requirements/rubin-prerelease.txt; else uv pip install --system -r /tmp/requirements-cuda.txt --index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.') --extra-index-url https://pypi.org/simple --index-strategy unsafe-first-match; fi && rm /tmp/requirements-cuda.txt /tmp/common.txt # buildkit
2026-11-02 06:06:57 UTC (buildkit.dockerfile.v0)RUN |10 INSTALL_RUBIN_PRERELEASE=true TARGETPLATFORM=linux/arm64 max_jobs=16 CUDA_VERSION=13.4 PYTHON_VERSION=3.12 NCCL_VERSION=2.32.3 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl /bin/sh -c PIP_CACHE_DIR=/opt/pip/cache flashinfer download-kernels # buildkit
2026-11-02 06:06:57 UTC (buildkit.dockerfile.v0)ARG GDRCOPY_CUDA_VERSION=12.8
2026-11-02 06:06:57 UTC (buildkit.dockerfile.v0)ARG GDRCOPY_OS_VERSION=Ubuntu24_04
2026-11-02 06:06:57 UTC (buildkit.dockerfile.v0)ARG TARGETPLATFORM
2026-11-02 06:06:57 UTC (buildkit.dockerfile.v0)COPY tools/install_gdrcopy.sh /tmp/install_gdrcopy.sh # buildkit
2026-11-02 06:07:02 UTC (buildkit.dockerfile.v0)RUN |13 INSTALL_RUBIN_PRERELEASE=true TARGETPLATFORM=linux/arm64 max_jobs=16 CUDA_VERSION=13.4 PYTHON_VERSION=3.12 NCCL_VERSION=2.32.3 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl GDRCOPY_CUDA_VERSION=12.8 GDRCOPY_OS_VERSION=Ubuntu24_04 TARGETPLATFORM=linux/arm64 /bin/sh -c set -eux; case "${TARGETPLATFORM}" in linux/arm64) UUARCH="aarch64" ;; linux/amd64) UUARCH="x64" ;; *) echo "Unsupported TARGETPLATFORM: ${TARGETPLATFORM}" >&2; exit 1 ;; esac; /tmp/install_gdrcopy.sh "${GDRCOPY_OS_VERSION}" "${GDRCOPY_CUDA_VERSION}" "${UUARCH}" && rm /tmp/install_gdrcopy.sh # buildkit
2026-11-02 06:07:02 UTC (buildkit.dockerfile.v0)ARG TIMM_VERSION=>=1.0.17
2026-11-02 06:07:02 UTC (buildkit.dockerfile.v0)ARG RUNAI_MODEL_STREAMER_VERSION=>=0.17.1
2026-11-02 06:07:02 UTC (buildkit.dockerfile.v0)ARG GGUF_VERSION=>=0.19.0
2026-11-02 06:07:05 UTC (buildkit.dockerfile.v0)RUN |16 INSTALL_RUBIN_PRERELEASE=true TARGETPLATFORM=linux/arm64 max_jobs=16 CUDA_VERSION=13.4 PYTHON_VERSION=3.12 NCCL_VERSION=2.32.3 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl GDRCOPY_CUDA_VERSION=12.8 GDRCOPY_OS_VERSION=Ubuntu24_04 TARGETPLATFORM=linux/arm64 TIMM_VERSION=>=1.0.17 RUNAI_MODEL_STREAMER_VERSION=>=0.17.1 GGUF_VERSION=>=0.19.0 /bin/sh -c uv pip install --system accelerate 'modelscope<1.38' "timm${TIMM_VERSION}" "runai-model-streamer[s3,gcs,azure]${RUNAI_MODEL_STREAMER_VERSION}" "gguf${GGUF_VERSION}" # buildkit
2026-11-02 06:07:05 UTC (buildkit.dockerfile.v0)ARG PIP_INDEX_URL UV_INDEX_URL
2026-11-02 06:07:05 UTC (buildkit.dockerfile.v0)ARG PIP_EXTRA_INDEX_URL UV_EXTRA_INDEX_URL
2026-11-02 06:07:05 UTC (buildkit.dockerfile.v0)ARG PYTORCH_CUDA_INDEX_BASE_URL
2026-11-02 06:07:05 UTC (buildkit.dockerfile.v0)ARG PIP_KEYRING_PROVIDER UV_KEYRING_PROVIDER
2026-11-02 06:07:05 UTC (buildkit.dockerfile.v0)ARG PYTORCH_NIGHTLY
2026-11-02 06:18:52 UTC (buildkit.dockerfile.v0)COPY /workspace/torch_lib_versions.txt torch_lib_versions.txt # buildkit
2026-11-02 06:40:04 UTC (buildkit.dockerfile.v0)COPY /workspace/dist/wheel.sha256 /tmp/vllm-wheel.sha256 # buildkit
2026-11-02 06:40:08 UTC (buildkit.dockerfile.v0)RUN |8 PIP_INDEX_URL= UV_INDEX_URL= PIP_EXTRA_INDEX_URL= UV_EXTRA_INDEX_URL= PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl PIP_KEYRING_PROVIDER=disabled UV_KEYRING_PROVIDER=disabled PYTORCH_NIGHTLY= /bin/sh -c if [ "${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 --index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.') --extra-index-url https://pypi.org/simple --index-strategy unsafe-first-match; fi # buildkit
2026-11-02 06:40:09 UTC (buildkit.dockerfile.v0)RUN |8 PIP_INDEX_URL= UV_INDEX_URL= PIP_EXTRA_INDEX_URL= UV_EXTRA_INDEX_URL= PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl PIP_KEYRING_PROVIDER=disabled UV_KEYRING_PROVIDER=disabled PYTORCH_NIGHTLY= /bin/sh -c ln -s "$(python3 -c 'import sysconfig; print(sysconfig.get_path("platlib"))')/vllm/vllm-rs" /usr/local/bin/vllm-rs && vllm-rs --version # buildkit
2026-11-02 06:40:10 UTC (buildkit.dockerfile.v0)RUN |8 PIP_INDEX_URL= UV_INDEX_URL= PIP_EXTRA_INDEX_URL= UV_EXTRA_INDEX_URL= PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl PIP_KEYRING_PROVIDER=disabled UV_KEYRING_PROVIDER=disabled PYTORCH_NIGHTLY= /bin/sh -c . /etc/environment && uv pip list # buildkit
2026-11-02 06:40:10 UTC (buildkit.dockerfile.v0)ENV LD_LIBRARY_PATH=/usr/local/cuda/lib64:/usr/local/cuda/lib64:/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/local/cuda/lib64
2026-11-02 06:40:10 UTC (buildkit.dockerfile.v0)COPY /tmp/ep_kernels_workspace/dist/wheels.sha256 /tmp/ep-kernels-wheels.sha256 # buildkit
2026-11-02 06:40:11 UTC (buildkit.dockerfile.v0)RUN |8 PIP_INDEX_URL= UV_INDEX_URL= PIP_EXTRA_INDEX_URL= UV_EXTRA_INDEX_URL= PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl PIP_KEYRING_PROVIDER=disabled UV_KEYRING_PROVIDER=disabled PYTORCH_NIGHTLY= /bin/sh -c uv pip install --system ep_kernels/dist/*.whl --verbose --extra-index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.') # buildkit
2026-11-02 06:40:11 UTC (buildkit.dockerfile.v0)ENV LD_LIBRARY_PATH=/usr/local/nvidia/lib64:/usr/local/cuda/lib64:/usr/local/cuda/lib64:/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/local/cuda/lib64
2026-11-02 06:40:11 UTC (buildkit.dockerfile.v0)COPY examples examples # buildkit
2026-11-02 06:40:11 UTC (buildkit.dockerfile.v0)COPY benchmarks benchmarks # buildkit
2026-11-02 06:40:11 UTC (buildkit.dockerfile.v0)COPY ./vllm/collect_env.py . # buildkit
2026-11-02 06:40:11 UTC (buildkit.dockerfile.v0)ARG TARGETPLATFORM
2026-11-02 06:40:11 UTC (buildkit.dockerfile.v0)ARG INSTALL_KV_CONNECTORS=false
2026-11-02 06:40:11 UTC (buildkit.dockerfile.v0)ARG INSTALL_RUBIN_PRERELEASE
2026-11-02 06:40:11 UTC (buildkit.dockerfile.v0)ARG TRITON_INSTALL_FROM_SOURCE_REPO
2026-11-02 06:40:11 UTC (buildkit.dockerfile.v0)ARG CUDA_VERSION
2026-11-02 06:40:11 UTC (buildkit.dockerfile.v0)ARG VLLM_BUILD_COMMIT
2026-11-02 06:40:11 UTC (buildkit.dockerfile.v0)ARG VLLM_BUILD_PIPELINE
2026-11-02 06:40:11 UTC (buildkit.dockerfile.v0)ARG VLLM_BUILD_URL
2026-11-02 06:40:11 UTC (buildkit.dockerfile.v0)ARG VLLM_IMAGE_TAG
2026-11-02 06:40:11 UTC (buildkit.dockerfile.v0)ARG PIP_INDEX_URL UV_INDEX_URL
2026-11-02 06:40:11 UTC (buildkit.dockerfile.v0)ARG PIP_EXTRA_INDEX_URL UV_EXTRA_INDEX_URL
2026-11-02 06:40:11 UTC (buildkit.dockerfile.v0)ENV UV_HTTP_TIMEOUT=500
2026-11-02 06:40:11 UTC (buildkit.dockerfile.v0)ARG torch_cuda_arch_list=7.5 8.0 8.6 8.9 9.0 10.0 11.0 12.0
2026-11-02 06:40:11 UTC (buildkit.dockerfile.v0)ENV TORCH_CUDA_ARCH_LIST=8.0 8.7 8.9 9.0 10.0 11.0 12.0
2026-11-02 06:40:17 UTC (buildkit.dockerfile.v0)RUN |14 TARGETPLATFORM=linux/arm64 INSTALL_KV_CONNECTORS=true INSTALL_RUBIN_PRERELEASE=true TRITON_INSTALL_FROM_SOURCE_REPO=https://github.com/triton-lang/triton.git CUDA_VERSION=13.4 VLLM_BUILD_COMMIT=76c6f3f2a95f6049657db1e513133b824a5c8175 VLLM_BUILD_PIPELINE=019d130e-464e-4ff7-b84b-492992c0c06b VLLM_BUILD_URL=https://buildkite.com/vllm/release-v2/builds/9707 VLLM_IMAGE_TAG=vllm/vllm-openai:cu134-nightly-76c6f3f2a95f6049657db1e513133b824a5c8175 PIP_INDEX_URL= UV_INDEX_URL= PIP_EXTRA_INDEX_URL= UV_EXTRA_INDEX_URL= torch_cuda_arch_list=8.0 8.7 8.9 9.0 10.0 11.0 12.0 /bin/sh -c set -eu; CUDA_MAJOR="${CUDA_VERSION%%.*}"; CUDA_VERSION_DASH=$(echo $CUDA_VERSION | cut -d. -f1,2 | tr '.' '-'); CUDA_HOME=/usr/local/cuda; BUILD_PKGS="libcusparse-dev-${CUDA_VERSION_DASH} libcublas-dev-${CUDA_VERSION_DASH} libcusolver-dev-${CUDA_VERSION_DASH}"; if [ "$INSTALL_KV_CONNECTORS" = "true" ]; then KV_REQUIREMENTS=/tmp/vllm-requirements/kv_connectors.txt; if [ "${CUDA_MAJOR}" = "12" ]; then KV_REQUIREMENTS=/tmp/vllm-requirements/kv_connectors_cu12.txt; fi; uv pip freeze --system > /tmp/kv-installed.txt; grep -E '^(torch|torchaudio|torchvision|triton|cuda-bindings|cuda-python|cuda-toolkit)==' /tmp/kv-installed.txt > /tmp/kv-constraints.txt; uv pip install --system -c /tmp/kv-constraints.txt -r "${KV_REQUIREMENTS}" --no-build || ( apt-get update -y && apt-get install -y --no-install-recommends --allow-change-held-packages ${BUILD_PKGS} && uv pip install --system -c /tmp/kv-constraints.txt -r "${KV_REQUIREMENTS}" --no-build-isolation && apt-get purge -y ${BUILD_PKGS} && rm -rf /var/lib/apt/lists/* ); MOONCAKE_VERSION=$(python3 -c "import importlib.metadata as m; print(m.version('mooncake-transfer-engine'))" 2>/dev/null || true) && if [ "${CUDA_MAJOR}" = "13" ] && [ -n "${MOONCAKE_VERSION}" ]; then uv pip uninstall --system mooncake-transfer-engine 2>/dev/null || true; uv pip install --system -c /tmp/kv-constraints.txt "mooncake-transfer-engine-cuda13==${MOONCAKE_VERSION}"; fi; rm -f /tmp/kv-installed.txt /tmp/kv-constraints.txt; fi # buildkit
2026-11-02 06:40:18 UTC (buildkit.dockerfile.v0)RUN |14 TARGETPLATFORM=linux/arm64 INSTALL_KV_CONNECTORS=true INSTALL_RUBIN_PRERELEASE=true TRITON_INSTALL_FROM_SOURCE_REPO=https://github.com/triton-lang/triton.git CUDA_VERSION=13.4 VLLM_BUILD_COMMIT=76c6f3f2a95f6049657db1e513133b824a5c8175 VLLM_BUILD_PIPELINE=019d130e-464e-4ff7-b84b-492992c0c06b VLLM_BUILD_URL=https://buildkite.com/vllm/release-v2/builds/9707 VLLM_IMAGE_TAG=vllm/vllm-openai:cu134-nightly-76c6f3f2a95f6049657db1e513133b824a5c8175 PIP_INDEX_URL= UV_INDEX_URL= PIP_EXTRA_INDEX_URL= UV_EXTRA_INDEX_URL= torch_cuda_arch_list=8.0 8.7 8.9 9.0 10.0 11.0 12.0 /bin/sh -c if [ "${INSTALL_RUBIN_PRERELEASE}" = "true" ]; then echo "Installing Rubin prerelease requirements..." && uv pip install --system --prerelease=allow --index-strategy unsafe-first-match -r /tmp/vllm-requirements/rubin-prerelease.txt; fi # buildkit
2026-11-02 06:40:18 UTC (buildkit.dockerfile.v0)COPY /tmp/triton_from_source_workspace/dist/wheel.sha256 /tmp/triton-source-wheel.sha256 # buildkit
2026-11-02 06:40:18 UTC (buildkit.dockerfile.v0)COPY tools/install_triton_from_source.sh /tmp/install_triton_from_source.sh # buildkit
2026-11-02 06:40:24 UTC (buildkit.dockerfile.v0)RUN |14 TARGETPLATFORM=linux/arm64 INSTALL_KV_CONNECTORS=true INSTALL_RUBIN_PRERELEASE=true TRITON_INSTALL_FROM_SOURCE_REPO=https://github.com/triton-lang/triton.git CUDA_VERSION=13.4 VLLM_BUILD_COMMIT=76c6f3f2a95f6049657db1e513133b824a5c8175 VLLM_BUILD_PIPELINE=019d130e-464e-4ff7-b84b-492992c0c06b VLLM_BUILD_URL=https://buildkite.com/vllm/release-v2/builds/9707 VLLM_IMAGE_TAG=vllm/vllm-openai:cu134-nightly-76c6f3f2a95f6049657db1e513133b824a5c8175 PIP_INDEX_URL= UV_INDEX_URL= PIP_EXTRA_INDEX_URL= UV_EXTRA_INDEX_URL= torch_cuda_arch_list=8.0 8.7 8.9 9.0 10.0 11.0 12.0 /bin/sh -c if [ -n "${TRITON_INSTALL_FROM_SOURCE_REPO}" ]; then CUDA_MAJOR_MINOR=$(echo "${CUDA_VERSION}" | cut -d. -f1,2); if [ "${INSTALL_RUBIN_PRERELEASE}" = "true" ]; then case "${CUDA_MAJOR_MINOR}" in 13.4|13.5) TRITON_SYSTEM_PTXAS_PATH=/usr/local/cuda/bin/ptxas TRITON_EXPECTED_PTXAS_VERSION="${CUDA_MAJOR_MINOR}" bash /tmp/install_triton_from_source.sh /tmp/triton-source-dist /tmp/triton-source-wheel.sha256 ;; *) echo "Unsupported Rubin CUDA version: ${CUDA_MAJOR_MINOR}" >&2; exit 1 ;; esac; else bash /tmp/install_triton_from_source.sh /tmp/triton-source-dist /tmp/triton-source-wheel.sha256; fi; fi && rm -f /tmp/install_triton_from_source.sh /tmp/triton-source-wheel.sha256 # buildkit
2026-11-02 06:40:24 UTC (buildkit.dockerfile.v0)ARG BUILD_NIXL
2026-11-02 06:40:26 UTC (buildkit.dockerfile.v0)RUN |15 TARGETPLATFORM=linux/arm64 INSTALL_KV_CONNECTORS=true INSTALL_RUBIN_PRERELEASE=true TRITON_INSTALL_FROM_SOURCE_REPO=https://github.com/triton-lang/triton.git CUDA_VERSION=13.4 VLLM_BUILD_COMMIT=76c6f3f2a95f6049657db1e513133b824a5c8175 VLLM_BUILD_PIPELINE=019d130e-464e-4ff7-b84b-492992c0c06b VLLM_BUILD_URL=https://buildkite.com/vllm/release-v2/builds/9707 VLLM_IMAGE_TAG=vllm/vllm-openai:cu134-nightly-76c6f3f2a95f6049657db1e513133b824a5c8175 PIP_INDEX_URL= UV_INDEX_URL= PIP_EXTRA_INDEX_URL= UV_EXTRA_INDEX_URL= torch_cuda_arch_list=8.0 8.7 8.9 9.0 10.0 11.0 12.0 BUILD_NIXL=true /bin/sh -c set -eu; if [ "${BUILD_NIXL}" = "true" ]; then ls /tmp/nixl-dist/*.whl; uv pip uninstall --system nixl nixl-cu12 nixl-cu13; uv pip install --system --no-deps /tmp/nixl-dist/*.whl; python3 -c "import glob, importlib.util as u, os, torch; spec = u.find_spec('nixl_ep_cu' + os.environ['CUDA_VERSION'].split('.')[0]); mm = ''.join(torch.__version__.split('.')[:2]); ext = glob.glob(os.path.join(spec.submodule_search_locations[0], 'nixl_ep_cpp_torch' + mm + '.*')) if spec else []; assert ext, 'NIXL EP has no build for torch ' + torch.__version__; print('NIXL EP extension:', ext[0])"; fi # buildkit
2026-11-02 06:40:26 UTC (buildkit.dockerfile.v0)ENV VLLM_USAGE_SOURCE=production-docker-image
2026-11-02 06:40:26 UTC (buildkit.dockerfile.v0)ENV VLLM_BUILD_COMMIT=76c6f3f2a95f6049657db1e513133b824a5c8175 VLLM_BUILD_PIPELINE=019d130e-464e-4ff7-b84b-492992c0c06b VLLM_BUILD_URL=https://buildkite.com/vllm/release-v2/builds/9707 VLLM_IMAGE_TAG=vllm/vllm-openai:cu134-nightly-76c6f3f2a95f6049657db1e513133b824a5c8175
2026-11-02 06:40:26 UTC (buildkit.dockerfile.v0)LABEL org.opencontainers.image.source=https://github.com/vllm-project/vllm org.opencontainers.image.revision=76c6f3f2a95f6049657db1e513133b824a5c8175 org.opencontainers.image.version=vllm/vllm-openai:cu134-nightly-76c6f3f2a95f6049657db1e513133b824a5c8175 org.opencontainers.image.url=https://buildkite.com/vllm/release-v2/builds/9707 ai.vllm.build.commit=76c6f3f2a95f6049657db1e513133b824a5c8175 ai.vllm.build.pipeline=019d130e-464e-4ff7-b84b-492992c0c06b ai.vllm.build.url=https://buildkite.com/vllm/release-v2/builds/9707 ai.vllm.image.tag=vllm/vllm-openai:cu134-nightly-76c6f3f2a95f6049657db1e513133b824a5c8175
2026-11-02 06:40:26 UTC (buildkit.dockerfile.v0)ENTRYPOINT ["vllm" "serve"]
Delete Tag
Please be careful as this will not just delete the reference but also the actual content!
For example when you have latest and v1.2.3 both pointing to the same image
the deletion of latest will also permanently remove v1.2.3.