vllm-openai (0.28.1nightly-20260908)
Published 2026-09-08 16:54:17 +00:00 by publish
Installation
docker pull packages.speedcloud.co.in/public/vllm-openai:0.28.1nightly-20260908sha256:1ea24ab460278255a2d058667f5f6e67f17bc135180388094dad258543543b0c
Image Layers
| ARG RELEASE |
| ARG LAUNCHPAD_BUILD_ARCH |
| LABEL org.opencontainers.image.ref.name=ubuntu |
| LABEL org.opencontainers.image.version=24.04 |
| ADD file:249778a1782b02a1c2bcf9f292f5778d81442a53c3de1958d712f10baf7e0b60 in / |
| CMD ["/bin/bash"] |
| ENV NVARCH=x86_64 |
| ENV NVIDIA_REQUIRE_CUDA=cuda>=13.0 brand=unknown,driver>=535,driver<536 brand=grid,driver>=535,driver<536 brand=tesla,driver>=535,driver<536 brand=nvidia,driver>=535,driver<536 brand=quadro,driver>=535,driver<536 brand=quadrortx,driver>=535,driver<536 brand=nvidiartx,driver>=535,driver<536 brand=vapps,driver>=535,driver<536 brand=vpc,driver>=535,driver<536 brand=vcs,driver>=535,driver<536 brand=vws,driver>=535,driver<536 brand=cloudgaming,driver>=535,driver<536 brand=unknown,driver>=550,driver<551 brand=grid,driver>=550,driver<551 brand=tesla,driver>=550,driver<551 brand=nvidia,driver>=550,driver<551 brand=quadro,driver>=550,driver<551 brand=quadrortx,driver>=550,driver<551 brand=nvidiartx,driver>=550,driver<551 brand=vapps,driver>=550,driver<551 brand=vpc,driver>=550,driver<551 brand=vcs,driver>=550,driver<551 brand=vws,driver>=550,driver<551 brand=cloudgaming,driver>=550,driver<551 brand=unknown,driver>=565,driver<566 brand=grid,driver>=565,driver<566 brand=tesla,driver>=565,driver<566 brand=nvidia,driver>=565,driver<566 brand=quadro,driver>=565,driver<566 brand=quadrortx,driver>=565,driver<566 brand=nvidiartx,driver>=565,driver<566 brand=vapps,driver>=565,driver<566 brand=vpc,driver>=565,driver<566 brand=vcs,driver>=565,driver<566 brand=vws,driver>=565,driver<566 brand=cloudgaming,driver>=565,driver<566 brand=unknown,driver>=570,driver<571 brand=grid,driver>=570,driver<571 brand=tesla,driver>=570,driver<571 brand=nvidia,driver>=570,driver<571 brand=quadro,driver>=570,driver<571 brand=quadrortx,driver>=570,driver<571 brand=nvidiartx,driver>=570,driver<571 brand=vapps,driver>=570,driver<571 brand=vpc,driver>=570,driver<571 brand=vcs,driver>=570,driver<571 brand=vws,driver>=570,driver<571 brand=cloudgaming,driver>=570,driver<571 brand=unknown,driver>=575,driver<576 brand=grid,driver>=575,driver<576 brand=tesla,driver>=575,driver<576 brand=nvidia,driver>=575,driver<576 brand=quadro,driver>=575,driver<576 brand=quadrortx,driver>=575,driver<576 brand=nvidiartx,driver>=575,driver<576 brand=vapps,driver>=575,driver<576 brand=vpc,driver>=575,driver<576 brand=vcs,driver>=575,driver<576 brand=vws,driver>=575,driver<576 brand=cloudgaming,driver>=575,driver<576 |
| ENV NV_CUDA_CUDART_VERSION=13.0.96-1 |
| ARG TARGETARCH |
| LABEL maintainer=NVIDIA CORPORATION <cudatools@nvidia.com> |
| RUN |1 TARGETARCH=amd64 /bin/sh -c apt-get update && apt-get install -y --no-install-recommends gnupg2 curl ca-certificates && curl -fsSL https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2404/${NVARCH}/3bf863cc.pub | apt-key add - && echo "deb https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2404/${NVARCH} /" > /etc/apt/sources.list.d/cuda.list && apt-get purge --autoremove -y curl && rm -rf /var/lib/apt/lists/* # buildkit |
| ENV CUDA_VERSION=13.0.2 |
| RUN |1 TARGETARCH=amd64 /bin/sh -c apt-get update && apt-get install -y --no-install-recommends cuda-cudart-13-0=${NV_CUDA_CUDART_VERSION} cuda-compat-13-0 && rm -rf /var/lib/apt/lists/* # buildkit |
| RUN |1 TARGETARCH=amd64 /bin/sh -c echo "/usr/local/cuda/lib64" >> /etc/ld.so.conf.d/nvidia.conf # buildkit |
| ENV PATH=/usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin |
| ENV LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/local/cuda/lib64 |
| COPY NGC-DL-CONTAINER-LICENSE / # buildkit |
| ENV NVIDIA_VISIBLE_DEVICES=all |
| ENV NVIDIA_DRIVER_CAPABILITIES=compute,utility |
| ARG INSTALL_RUBIN_PRERELEASE |
| ARG CUDA_VERSION |
| ARG PYTHON_VERSION |
| ARG NCCL_VERSION |
| ARG DEADSNAKES_MIRROR_URL |
| ARG DEADSNAKES_GPGKEY_URL |
| ARG GET_PIP_URL |
| ENV CUDA_VERSION=13.0.2 |
| ENV DEBIAN_FRONTEND=noninteractive |
| WORKDIR /vllm-workspace |
| RUN |7 INSTALL_RUBIN_PRERELEASE=false CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 NCCL_VERSION=2.30.7 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py /bin/sh -c PYTHON_VERSION_STR=$(echo ${PYTHON_VERSION} | sed 's/\.//g') && echo "export PYTHON_VERSION_STR=${PYTHON_VERSION_STR}" >> /etc/environment # buildkit |
| RUN |7 INSTALL_RUBIN_PRERELEASE=false CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 NCCL_VERSION=2.30.7 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 |
| RUN |7 INSTALL_RUBIN_PRERELEASE=false CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 NCCL_VERSION=2.30.7 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-cuobjdump-${CUDA_VERSION_DASH} libcurand-dev-${CUDA_VERSION_DASH} libcublas-dev-${CUDA_VERSION_DASH} libnuma-dev numactl && rm -rf /var/lib/apt/lists/* # buildkit |
| RUN |7 INSTALL_RUBIN_PRERELEASE=false CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 NCCL_VERSION=2.30.7 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py /bin/sh -c if [ "${INSTALL_RUBIN_PRERELEASE}" = "true" ]; then CUDA_MAJOR_MINOR=$(echo "${CUDA_VERSION}" | cut -d. -f1,2) && if [ "${CUDA_MAJOR_MINOR}" = "13.4" ]; then CURAND_LIBRARY=$(find -H /usr/local/cuda -name libcurand.so.10 -print -quit) && test -n "${CURAND_LIBRARY}" && ln -sf "${CURAND_LIBRARY}" /usr/local/cuda/lib64/libcurand.so.11; elif [ "${CUDA_MAJOR_MINOR}" = "13.5" ]; then CURAND_LIBRARY=$(find -H /usr/local/cuda -name libcurand.so.11 -print -quit) && test -n "${CURAND_LIBRARY}" && ! readlink -f "${CURAND_LIBRARY}" | grep -q 'libcurand\.so\.10'; else echo "Unsupported Rubin CUDA version: ${CUDA_MAJOR_MINOR}" >&2; exit 1; fi && NCCL_LIBRARY=$(find /usr/lib -name libnccl.so.2 -print -quit) && test -n "${NCCL_LIBRARY}" && ln -sf "${NCCL_LIBRARY}" /usr/lib/libnccl.so.2 && ln -sf libnccl.so.2 /usr/lib/libnccl.so && ldconfig; fi # buildkit |
| RUN |7 INSTALL_RUBIN_PRERELEASE=false CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 NCCL_VERSION=2.30.7 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 |
| ENV UV_HTTP_TIMEOUT=500 |
| ENV UV_INDEX_STRATEGY=unsafe-best-match |
| ENV UV_LINK_MODE=copy |
| ENV UV_PYTHON_INSTALL_DIR=/opt/uv/python |
| ENV UV_CACHE_DIR=/opt/uv/cache |
| RUN |7 INSTALL_RUBIN_PRERELEASE=false CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 NCCL_VERSION=2.30.7 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 |
| RUN |7 INSTALL_RUBIN_PRERELEASE=false CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 NCCL_VERSION=2.30.7 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 |
| ENV UV_OVERRIDE=/etc/uv-overrides.txt |
| RUN |7 INSTALL_RUBIN_PRERELEASE=false CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 NCCL_VERSION=2.30.7 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 |
| COPY docker/entrypoints/vllm-nonroot-entrypoint.sh /usr/local/bin/vllm-nonroot-entrypoint.sh # buildkit |
| RUN |7 INSTALL_RUBIN_PRERELEASE=false CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 NCCL_VERSION=2.30.7 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 |
| ENV VLLM_ENABLE_CUDA_COMPATIBILITY=0 |
| ARG PYTORCH_CUDA_INDEX_BASE_URL |
| COPY requirements/common.txt /tmp/common.txt # buildkit |
| COPY requirements/cuda.txt /tmp/requirements-cuda.txt # buildkit |
| RUN |8 INSTALL_RUBIN_PRERELEASE=false CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 NCCL_VERSION=2.30.7 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 [ "${INSTALL_RUBIN_PRERELEASE}" = "true" ]; then uv pip install --system -r /tmp/vllm-requirements/rubin-prerelease.txt && sed -Ei '/^[[:space:]]*(torch|torchvision|torchaudio)[[:space:]]*==/Id' /tmp/requirements-cuda.txt && uv pip install --system -r /tmp/requirements-cuda.txt && uv pip install --system -r /tmp/vllm-requirements/rubin-prerelease.txt && printf '%s\n' "/usr/local/lib/python${PYTHON_VERSION}/dist-packages/nvpl/lib" > /etc/ld.so.conf.d/vllm-rubin-python.conf && ldconfig; else uv pip install --system -r /tmp/requirements-cuda.txt --extra-index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.'); fi && rm /tmp/requirements-cuda.txt /tmp/common.txt # buildkit |
| ARG FLASHINFER_VERSION=0.6.18 |
| RUN |9 INSTALL_RUBIN_PRERELEASE=false CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 NCCL_VERSION=2.30.7 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl FLASHINFER_VERSION=0.6.18 /bin/sh -c if [ "${INSTALL_RUBIN_PRERELEASE}" != "true" ]; then uv pip install --system flashinfer-jit-cache==${FLASHINFER_VERSION} --index-url https://flashinfer.ai/whl/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.'); fi # buildkit |
| ARG GDRCOPY_CUDA_VERSION=12.8 |
| ARG GDRCOPY_OS_VERSION=Ubuntu24_04 |
| ARG TARGETPLATFORM |
| COPY tools/install_gdrcopy.sh /tmp/install_gdrcopy.sh # buildkit |
| RUN |12 INSTALL_RUBIN_PRERELEASE=false CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 NCCL_VERSION=2.30.7 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl FLASHINFER_VERSION=0.6.18 GDRCOPY_CUDA_VERSION=12.8 GDRCOPY_OS_VERSION=Ubuntu24_04 TARGETPLATFORM=linux/amd64 /bin/sh -c set -eux; if [ "${INSTALL_RUBIN_PRERELEASE}" = "true" ]; then ldconfig -p | grep -q 'libgdrapi\.so'; else 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}"; fi; rm /tmp/install_gdrcopy.sh # buildkit |
| ARG TIMM_VERSION=>=1.0.17 |
| ARG RUNAI_MODEL_STREAMER_VERSION=>=0.15.7 |
| RUN |14 INSTALL_RUBIN_PRERELEASE=false CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 NCCL_VERSION=2.30.7 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=0.6.18 GDRCOPY_CUDA_VERSION=12.8 GDRCOPY_OS_VERSION=Ubuntu24_04 TARGETPLATFORM=linux/amd64 TIMM_VERSION=>=1.0.17 RUNAI_MODEL_STREAMER_VERSION=>=0.15.7 /bin/sh -c uv pip install --system accelerate 'modelscope<1.38' "timm${TIMM_VERSION}" "runai-model-streamer[s3,gcs,azure]${RUNAI_MODEL_STREAMER_VERSION}" # buildkit |
| ARG PIP_INDEX_URL UV_INDEX_URL |
| ARG PIP_EXTRA_INDEX_URL UV_EXTRA_INDEX_URL |
| ARG PYTORCH_CUDA_INDEX_BASE_URL |
| ARG PIP_KEYRING_PROVIDER UV_KEYRING_PROVIDER |
| ARG PYTORCH_NIGHTLY |
| COPY /workspace/torch_lib_versions.txt torch_lib_versions.txt # buildkit |
| COPY /workspace/dist/wheel.sha256 /tmp/vllm-wheel.sha256 # buildkit |
| RUN |8 PIP_INDEX_URL= UV_INDEX_URL= PIP_EXTRA_INDEX_URL= UV_EXTRA_INDEX_URL= PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl PIP_KEYRING_PROVIDER=disabled UV_KEYRING_PROVIDER=disabled PYTORCH_NIGHTLY= /bin/sh -c if [ "${PYTORCH_NIGHTLY}" = "1" ]; then echo "Installing torch nightly..." && uv pip install --system $(cat torch_lib_versions.txt | xargs) --pre --index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/nightly/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.') && echo "Installing vLLM..." && uv pip install --system dist/*.whl --verbose --extra-index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/nightly/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.'); else echo "Installing vLLM..." && uv pip install --system dist/*.whl --verbose --extra-index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.'); fi # buildkit |
| 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 |
| ENV LD_LIBRARY_PATH=/usr/local/cuda/lib64:/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/local/cuda/lib64 |
| COPY /tmp/ep_kernels_workspace/dist/wheels.sha256 /tmp/ep-kernels-wheels.sha256 # buildkit |
| 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 $CUDA_VERSION | cut -d. -f1,2 | tr -d '.') # buildkit |
| ENV LD_LIBRARY_PATH=/usr/local/nvidia/lib64:/usr/local/cuda/lib64:/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/local/cuda/lib64 |
| COPY examples examples # buildkit |
| COPY benchmarks benchmarks # buildkit |
| COPY ./vllm/collect_env.py . # buildkit |
| ARG TARGETPLATFORM |
| ARG INSTALL_KV_CONNECTORS=false |
| ARG INSTALL_RUBIN_PRERELEASE |
| ARG TRITON_INSTALL_FROM_SOURCE_REPO |
| ARG CUDA_VERSION |
| ARG VLLM_BUILD_COMMIT |
| ARG VLLM_BUILD_PIPELINE |
| ARG VLLM_BUILD_URL |
| ARG VLLM_IMAGE_TAG |
| ARG PIP_INDEX_URL UV_INDEX_URL |
| ARG PIP_EXTRA_INDEX_URL UV_EXTRA_INDEX_URL |
| ENV UV_HTTP_TIMEOUT=500 |
| ARG torch_cuda_arch_list=7.5 8.0 8.6 8.9 9.0 10.0 11.0 12.0 |
| ENV TORCH_CUDA_ARCH_LIST=7.5 8.0 8.6 8.9 9.0 10.0 12.0 |
| RUN |14 TARGETPLATFORM=linux/amd64 INSTALL_KV_CONNECTORS=true INSTALL_RUBIN_PRERELEASE=false TRITON_INSTALL_FROM_SOURCE_REPO= CUDA_VERSION=13.0.2 VLLM_BUILD_COMMIT=44fe2a392b71d52a8d72faf2f8278834379482c9 VLLM_BUILD_PIPELINE=019d130e-464e-4ff7-b84b-492992c0c06b VLLM_BUILD_URL=https://buildkite.com/vllm/release-v2/builds/5825 VLLM_IMAGE_TAG=vllm/vllm-openai:nightly-44fe2a392b71d52a8d72faf2f8278834379482c9 PIP_INDEX_URL= UV_INDEX_URL= PIP_EXTRA_INDEX_URL= UV_EXTRA_INDEX_URL= torch_cuda_arch_list=7.5 8.0 8.6 8.9 9.0 10.0 12.0 /bin/sh -c CUDA_MAJOR="${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 ${BUILD_PKGS} && rm -rf /var/lib/apt/lists/* ); MOONCAKE_VERSION=$(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 "mooncake-transfer-engine-cuda13==${MOONCAKE_VERSION}"; fi; fi # buildkit |
| RUN |14 TARGETPLATFORM=linux/amd64 INSTALL_KV_CONNECTORS=true INSTALL_RUBIN_PRERELEASE=false TRITON_INSTALL_FROM_SOURCE_REPO= CUDA_VERSION=13.0.2 VLLM_BUILD_COMMIT=44fe2a392b71d52a8d72faf2f8278834379482c9 VLLM_BUILD_PIPELINE=019d130e-464e-4ff7-b84b-492992c0c06b VLLM_BUILD_URL=https://buildkite.com/vllm/release-v2/builds/5825 VLLM_IMAGE_TAG=vllm/vllm-openai:nightly-44fe2a392b71d52a8d72faf2f8278834379482c9 PIP_INDEX_URL= UV_INDEX_URL= PIP_EXTRA_INDEX_URL= UV_EXTRA_INDEX_URL= torch_cuda_arch_list=7.5 8.0 8.6 8.9 9.0 10.0 12.0 /bin/sh -c if [ "${INSTALL_RUBIN_PRERELEASE}" = "true" ]; then echo "Installing Rubin prerelease requirements..." && uv pip install --system -r /tmp/vllm-requirements/rubin-prerelease.txt; fi # buildkit |
| COPY /tmp/triton_from_source_workspace/dist/wheel.sha256 /tmp/triton-source-wheel.sha256 # buildkit |
| COPY tools/install_triton_from_source.sh /tmp/install_triton_from_source.sh # buildkit |
| RUN |14 TARGETPLATFORM=linux/amd64 INSTALL_KV_CONNECTORS=true INSTALL_RUBIN_PRERELEASE=false TRITON_INSTALL_FROM_SOURCE_REPO= CUDA_VERSION=13.0.2 VLLM_BUILD_COMMIT=44fe2a392b71d52a8d72faf2f8278834379482c9 VLLM_BUILD_PIPELINE=019d130e-464e-4ff7-b84b-492992c0c06b VLLM_BUILD_URL=https://buildkite.com/vllm/release-v2/builds/5825 VLLM_IMAGE_TAG=vllm/vllm-openai:nightly-44fe2a392b71d52a8d72faf2f8278834379482c9 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 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 |
| ENV VLLM_USAGE_SOURCE=production-docker-image |
| ENV VLLM_BUILD_COMMIT=44fe2a392b71d52a8d72faf2f8278834379482c9 VLLM_BUILD_PIPELINE=019d130e-464e-4ff7-b84b-492992c0c06b VLLM_BUILD_URL=https://buildkite.com/vllm/release-v2/builds/5825 VLLM_IMAGE_TAG=vllm/vllm-openai:nightly-44fe2a392b71d52a8d72faf2f8278834379482c9 |
| LABEL org.opencontainers.image.source=https://github.com/vllm-project/vllm org.opencontainers.image.revision=44fe2a392b71d52a8d72faf2f8278834379482c9 org.opencontainers.image.version=vllm/vllm-openai:nightly-44fe2a392b71d52a8d72faf2f8278834379482c9 org.opencontainers.image.url=https://buildkite.com/vllm/release-v2/builds/5825 ai.vllm.build.commit=44fe2a392b71d52a8d72faf2f8278834379482c9 ai.vllm.build.pipeline=019d130e-464e-4ff7-b84b-492992c0c06b ai.vllm.build.url=https://buildkite.com/vllm/release-v2/builds/5825 ai.vllm.image.tag=vllm/vllm-openai:nightly-44fe2a392b71d52a8d72faf2f8278834379482c9 |
| ENTRYPOINT ["vllm" "serve"] |
Labels
| Key | Value |
|---|---|
| ai.vllm.build.commit | 44fe2a392b71d52a8d72faf2f8278834379482c9 |
| ai.vllm.build.pipeline | 019d130e-464e-4ff7-b84b-492992c0c06b |
| ai.vllm.build.url | https://buildkite.com/vllm/release-v2/builds/5825 |
| ai.vllm.image.tag | vllm/vllm-openai:nightly-44fe2a392b71d52a8d72faf2f8278834379482c9 |
| maintainer | NVIDIA CORPORATION <cudatools@nvidia.com> |
| org.opencontainers.image.ref.name | ubuntu |
| org.opencontainers.image.revision | 44fe2a392b71d52a8d72faf2f8278834379482c9 |
| org.opencontainers.image.source | https://github.com/vllm-project/vllm |
| org.opencontainers.image.url | https://buildkite.com/vllm/release-v2/builds/5825 |
| org.opencontainers.image.version | vllm/vllm-openai:nightly-44fe2a392b71d52a8d72faf2f8278834379482c9 |
Details
2026-09-08 16:54:17 +00:00
Versions (1)
View all
Container
4
OCI / Docker
linux/amd64
8.1 GiB
0.28.1nightly-20260908
2026-09-08