sha256:4a28525da6a36518132ff47f15c0e8d0cf64fff0f527412cebad542bc27fa0ae
OS/ARCH
linux/amd64
Compressed size
8.09 GB
Last pushed
9 days by imranpochi
Type
Image
Manifest digest
sha256:0e140784b2d36ff3321b2941927140ca21b9a3f837966ee056125e22ee63abe2
Image Layers
1ARG RELEASE0 B2ARG LAUNCHPAD_BUILD_ARCH0 B3LABEL org.opencontainers.image.ref.name=ubuntu0 B4LABEL org.opencontainers.image.version=24.040 B5ADD file ... in / 29.18 MB6CMD ["/bin/bash"]0 B7ENV NVARCH=x86_640 B8ENV NVIDIA_REQUIRE_CUDA=cuda>=13.0 brand=unknown,driver>=535,driver<536 brand=grid,driver>=535,driver<536 brand=tesla,driver>=535,driver<5360 B9ENV NV_CUDA_CUDART_VERSION=13.0.96-10 B10ARG TARGETARCH0 B12RUN |1 TARGETARCH=amd64 /bin/sh -c4.34 MB13ENV CUDA_VERSION=13.0.20 B14RUN |1 TARGETARCH=amd64 /bin/sh -c100.29 MB15RUN |1 TARGETARCH=amd64 /bin/sh -c182 B16ENV PATH=/usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin0 B17ENV LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/local/cuda/lib640 B18COPY NGC-DL-CONTAINER-LICENSE / # buildkit6.72 KB19ENV NVIDIA_VISIBLE_DEVICES=all0 B20ENV NVIDIA_DRIVER_CAPABILITIES=compute,utility0 B21ARG CUDA_VERSION0 B22ARG PYTHON_VERSION0 B23ARG NCCL_VERSION0 B24ARG DEADSNAKES_MIRROR_URL0 B25ARG DEADSNAKES_GPGKEY_URL0 B26ARG GET_PIP_URL0 B27ENV DEBIAN_FRONTEND=noninteractive0 B28WORKDIR /vllm-workspace104 B29RUN |6 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 NCCL_VERSION=2.30.7230 B30RUN |6 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 NCCL_VERSION=2.30.7222.51 MB31RUN |6 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 NCCL_VERSION=2.30.71.28 GB32RUN |6 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 NCCL_VERSION=2.30.745.64 MB33ENV UV_HTTP_TIMEOUT=5000 B34ENV UV_INDEX_STRATEGY=unsafe-best-match0 B35ENV UV_LINK_MODE=copy0 B36ENV UV_PYTHON_INSTALL_DIR=/opt/uv/python0 B37ENV UV_CACHE_DIR=/opt/uv/cache0 B38RUN |6 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 NCCL_VERSION=2.30.7151 B39RUN |6 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 NCCL_VERSION=2.30.7164 B40ENV UV_OVERRIDE=/etc/uv-overrides.txt0 B41RUN |6 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 NCCL_VERSION=2.30.73.62 KB42COPY docker/entrypoints/vllm-nonroot-entrypoint.sh /usr/local/bin/vllm-nonroot-entrypoint.sh # buildkit2.03 KB43RUN |6 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 NCCL_VERSION=2.30.72.03 KB44ENV VLLM_ENABLE_CUDA_COMPATIBILITY=00 B45ARG PYTORCH_CUDA_INDEX_BASE_URL0 B46COPY requirements/common.txt /tmp/common.txt # buildkit1.63 KB47COPY requirements/cuda.txt /tmp/requirements-cuda.txt # buildkit875 B48RUN |7 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 NCCL_VERSION=2.30.74.32 GB49ARG FLASHINFER_VERSION=0.6.170 B50RUN |8 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 NCCL_VERSION=2.30.71.41 GB51ARG GDRCOPY_CUDA_VERSION=12.80 B52ARG GDRCOPY_OS_VERSION=Ubuntu24_040 B53ARG TARGETPLATFORM0 B54COPY tools/install_gdrcopy.sh /tmp/install_gdrcopy.sh # buildkit896 B55RUN |11 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 NCCL_VERSION=2.30.7523.07 KB56ARG TIMM_VERSION=>=1.0.170 B57ARG RUNAI_MODEL_STREAMER_VERSION=>=0.15.70 B58RUN |13 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 NCCL_VERSION=2.30.758.7 MB59ARG PIP_INDEX_URL UV_INDEX_URL0 B60ARG PIP_EXTRA_INDEX_URL UV_EXTRA_INDEX_URL0 B61ARG PYTORCH_CUDA_INDEX_BASE_URL0 B62ARG PIP_KEYRING_PROVIDER UV_KEYRING_PROVIDER0 B63ARG PYTORCH_NIGHTLY0 B64COPY /workspace/torch_lib_versions.txt torch_lib_versions.txt # buildkit200 B65COPY /workspace/dist/wheel.sha256 /tmp/vllm-wheel.sha256 # buildkit239 B66RUN |8 PIP_INDEX_URL= UV_INDEX_URL= PIP_EXTRA_INDEX_URL=297.27 MB67RUN |8 PIP_INDEX_URL= UV_INDEX_URL= PIP_EXTRA_INDEX_URL=32 B68ENV LD_LIBRARY_PATH=/usr/local/cuda/lib64:/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/local/cuda/lib640 B69COPY /tmp/ep_kernels_workspace/dist/wheels.sha256 /tmp/ep-kernels-wheels.sha256 # buildkit254 B70RUN |8 PIP_INDEX_URL= UV_INDEX_URL= PIP_EXTRA_INDEX_URL=13.81 MB71ENV LD_LIBRARY_PATH=/usr/local/nvidia/lib64:/usr/local/cuda/lib64:/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/local/cuda/lib640 B72COPY examples examples # buildkit269.53 KB73COPY benchmarks benchmarks # buildkit284.1 KB74COPY ./vllm/collect_env.py . # buildkit9.61 KB75ARG TARGETPLATFORM0 B76ARG INSTALL_KV_CONNECTORS=false0 B77ARG CUDA_VERSION0 B78ARG VLLM_BUILD_COMMIT0 B79ARG VLLM_BUILD_PIPELINE0 B80ARG VLLM_BUILD_URL0 B81ARG VLLM_IMAGE_TAG0 B82ARG PIP_INDEX_URL UV_INDEX_URL0 B83ARG PIP_EXTRA_INDEX_URL UV_EXTRA_INDEX_URL0 B84ENV UV_HTTP_TIMEOUT=5000 B85ARG torch_cuda_arch_list=7.5 8.0 8.6 8.90 B86ENV TORCH_CUDA_ARCH_LIST=7.5 8.0 8.6 8.90 B87RUN |12 TARGETPLATFORM=linux/amd64 INSTALL_KV_CONNECTORS=true CUDA_VERSION=13.0.2296.06 MB88ENV VLLM_USAGE_SOURCE=production-docker-image0 B89ENV VLLM_BUILD_COMMIT=a9a17e7095a66ef6c6685a1c7ddd657781a78d3c VLLM_BUILD_PIPELINE=019d130e-464e-4ff7-b84b-492992c0c06b VLLM_BUILD_URL=https://buildkite.com/vllm/release-v2/builds/5600 VLLM_IMAGE_TAG=vllm/vllm-openai:nightly-a9a17e7095a66ef6c6685a1c7ddd657781a78d3c0 B90LABEL org.opencontainers.image.source=https://github.com/vllm-project/vllm org.opencontainers.image.revision=a9a17e7095a66ef6c6685a1c7ddd657781a78d3c org.opencontainers.image.version=vllm/vllm-openai:nightly-a9a17e7095a66ef6c6685a1c7ddd657781a78d3c org.opencontainers.image.url=https://buildkite.com/vllm/release-v2/builds/56000 B91ENTRYPOINT ["vllm" "serve"]0 B92ENV PIP_INDEX_URL=https://packagefeedproxy.microsoft.io/pypi/simple PIP_DISABLE_PIP_VERSION_CHECK=1 VLLM_PLUGINS=modelexpress0 B93RUN /bin/sh -c python3 -m7.05 MB94COPY /src/dynamo/target/release/dynamo-vllm-sidecar /usr/local/bin/ # buildkit17.17 MB95COPY /src/modelexpress/target/release/modelexpress-server /usr/local/bin/ # buildkit13.37 MB96COPY verify-runtime.py /opt/mx-demo/verify-runtime.py # buildkit1.15 KB97RUN /bin/sh -c python3 -B129 B98LABEL org.opencontainers.image.title=ModelExpress upstream refit demo0 B99ENTRYPOINT []0 B100CMD ["/bin/bash"]0 BCommand
ARG RELEASE