Namespace
vllm
Image / Tag
vllm-openai:nightly-dev-amd64-cu130-69d383751
Content Digest
sha256:414e72ee4e29cbaf8af4a7515f38d0b4d76be0da51000dd17b9dcc877b743122
Details
Created

2026-09-27 01:53:48 UTC

Size

8.34 GB

Content Digest
Labels
  • ai.vllm.build.commit
    69d383751226559cf215040b2ee95a13a7b79288
  • ai.vllm.build.pipeline
    image-build
  • ai.vllm.build.url
    https://buildkite.com/inferact/image-build/builds/2646
  • ai.vllm.image.tag
    inferactinc/dev:vllm-dsv41-decoder-replay-pr58132-69d383751226-cu130-amd64
  • maintainer
    NVIDIA CORPORATION <cudatools@nvidia.com>
  • org.opencontainers.image.revision
    69d383751226559cf215040b2ee95a13a7b79288
  • org.opencontainers.image.source
    https://github.com/vllm-project/vllm
  • org.opencontainers.image.url
    https://buildkite.com/inferact/image-build/builds/2646
  • org.opencontainers.image.version
    inferactinc/dev:vllm-dsv41-decoder-replay-pr58132-69d383751226-cu130-amd64

Environment
CRIU_CUDA_PLUGIN_DIR

/usr/local/lib/criu

CUDA_HOME

/usr/local/cuda

CUDA_VERSION

13.0.3

DEBIAN_FRONTEND

noninteractive

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

NVARCH

x86_64

NVIDIA_DRIVER_CAPABILITIES

compute,utility

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

NVIDIA_VISIBLE_DEVICES

all

NV_CUDA_CUDART_VERSION

13.0.96-1

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_LIST

7.5 8.0 8.6 8.9 9.0 10.0 11.0 12.0

UV_CACHE_DIR

/opt/uv/cache

UV_HTTP_TIMEOUT

500

UV_INDEX_STRATEGY

unsafe-best-match

UV_LINK_MODE

copy

UV_OVERRIDE

/etc/uv-overrides.txt

UV_PYTHON_INSTALL_DIR

/opt/uv/python

VLLM_BUILD_COMMIT

69d383751226559cf215040b2ee95a13a7b79288

VLLM_BUILD_PIPELINE

image-build

VLLM_BUILD_URL

https://buildkite.com/inferact/image-build/builds/2646

VLLM_ENABLE_CUDA_COMPATIBILITY

0

VLLM_IMAGE_TAG

inferactinc/dev:vllm-dsv41-decoder-replay-pr58132-69d383751226-cu130-amd64

VLLM_USAGE_SOURCE

production-docker-image


Layers

[#000] sha256:8c4a2c659b41a7ee5d843a17b83f99781568398a44d2f600ff333f820ea50927 - 0.34% (29.2 MB)

[#001] sha256:95e35692d3cc347d712fd236fd2af3b1c697783518182b1ae716722f694ed616 - 0.08% (6.64 MB)

[#002] sha256:5e25946ba40dcbc2410bf1852d135a46cb31cc7f89c05b9ef1ab12a6ef988aeb - 0.0% (354 KB)

[#003] sha256:f0af354daeda18f18684b23520969ef6bb3de82bb267936f867b12769be9125d - 1.17% (100 MB)

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

[#005] sha256:ccf9c70a85fc6158d617c85f3f719f669efb00c28fd45fa292575d351435bd2f - 0.0% (186 Bytes)

[#006] sha256:730c8029606bf4b4533d7a7159458cf5e3f348ea956ccfb10ce5da3e20adac8f - 0.0% (6.72 KB)

[#007] sha256:e97b1f5cf8804c4600e5fe809c32c1f12c7649bfcd6371b978c1170ae204fd49 - 0.0% (104 Bytes)

[#008] sha256:9e8a8ddb5cf78749fb5d0cc6a840548d16c765b98fa445322a8f55f7c3cbe331 - 0.0% (230 Bytes)

[#009] sha256:4ac8c9cf2e54483053b94ce30194f692503273e086e60dfbcd9097bb7bc028a9 - 2.59% (222 MB)

[#010] sha256:caeb9acbfbf45692de06e3d096838e8bd55823de87d1195b4d0f6a12f1c44cd1 - 16.23% (1.35 GB)

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

[#012] sha256:28c85e0734b34f6c7dcbc96854e4bdf585f2654fde8937681629dacc405dc773 - 0.0% (1.62 KB)

[#013] sha256:41ec51e6ac86d0499a887475a8c0d5524b3a64704d5e1f9cd91ad5b5ac3215eb - 0.1% (8.85 MB)

[#014] sha256:127a20a46c3e0ebc77ab74f44a6f7b6e3eb18c4a1f5a59f66d4239f39abdbf2e - 0.46% (39.6 MB)

[#015] sha256:923a65bc5fa57f7e21d671e27aae0effe22b37eadaf8b2c1a8e68c711473c5d3 - 0.0% (150 Bytes)

[#016] sha256:0c2b0b30a243d589e76e6d6f18a4d57a04ffffe19ea9c4aeb30ba4d8c87e79c1 - 0.0% (164 Bytes)

[#017] sha256:eaf20081d933a04595a406ac95771b87fb427ebb0a44fb73cdff7e466d84b262 - 0.0% (3.42 KB)

[#018] sha256:1eaef27e1726d1d70273b9fddfb9e2494caf19aee6ed5a53d2f561eee1f87a0c - 0.0% (2.03 KB)

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

[#020] sha256:93052406374629b4051f773a9e0e5e7b90ceaaad7927521ada73365973f769c4 - 0.0% (1.65 KB)

[#021] sha256:a4ecbab8979dc1f0656d2b2a69fbf53a8849971faf187cc5c2b5cf9aa452ca88 - 0.0% (866 Bytes)

[#022] sha256:b7ba0bccd13332595337a4881dcf08bc83b8d068df00bed05285fcab5f4c3dee - 57.55% (4.8 GB)

[#023] sha256:2524522b00ab6425c83726732c3cb74de9ac77fccc864426ad22f2d9466f16fc - 13.16% (1.1 GB)

[#024] sha256:5fca9b0e9eee854f2d0706eba2a5e7e7d86db20c8e0370d0bf86d8430b13b400 - 0.0% (897 Bytes)

[#025] sha256:602b833cb6ce68c6c9de4d7f6dad66d20301b9140690bffca372f76ff3054e5e - 0.0% (336 KB)

[#026] sha256:80e1b8ccc97cb28a3cbfe2e5dbe94e1b316ed1c40719ee06b6d9fae2fdd08171 - 0.69% (59 MB)

[#027] sha256:b8ea23d2afd25bce146eb97b58ff25dcb067e2648e56f736ba84e9e63cd0f700 - 0.0% (202 Bytes)

[#028] sha256:b68c529ed3820c088bdc0222da738da4169cffc6c6a3960a1b9fc5dd27796cca - 0.0% (236 Bytes)

[#029] sha256:f8cb9b7b135108e53b736ef52f5b76d19980ebd1d06c96abe9b3947a360330de - 3.58% (306 MB)

[#030] sha256:d5132f89909f41bcdfadc9c7f29bab98ab9fed132d9a3ff67ee5f1a783ee7a25 - 0.0% (5.22 KB)

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

[#032] sha256:b0d8b8e280221f4336982b092698ccc3674c049e03d9196db38a31941d57693d - 0.0% (255 Bytes)

[#033] sha256:62f55a1258e072bb42e354b653d0d22565c03e525c2e464146d0d6c261c22eb3 - 0.16% (13.8 MB)

[#034] sha256:a2e590cc497abc0c8214b3e2319e521edaeffd446c1846310e837f7301097077 - 0.0% (298 KB)

[#035] sha256:867f3c9144a1bed49d997320ff43388a5fb5032f4b0e72c0001db80cb86b4c4b - 0.0% (297 KB)

[#036] sha256:1f63ad674f0e507c15a57a8e42ac7926efafcb14441607d43826ef9d62670242 - 0.0% (9.61 KB)

[#037] sha256:67ac5fc5f50856e9c37fa6602650a02e4016986fa500d58983a5365ee229fba3 - 3.86% (330 MB)

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

[#039] sha256:458593cd659175bb8f0e3a636df642dab26353cd67c7017ddab5edac07365df6 - 0.0% (212 Bytes)

[#040] sha256:c89e3573b2bb20c8edfb37c5b53c882127ad4614097abec0d32cd98891b5af2e - 0.0% (822 Bytes)

[#041] sha256:93ab5d3331c63d1492ba64bfebf8727c53aa7c472694d8b0060ef3909bc96b24 - 0.0% (175 Bytes)


History
2026-04-03 15:16:40 UTC

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

2026-04-03 15:16:40 UTC

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

2026-04-03 15:16:40 UTC

/bin/sh -c #(nop) LABEL org.opencontainers.image.version=24.04

2026-04-03 15:16:42 UTC

/bin/sh -c #(nop) ADD file:0f6466425c4f1800aae9224ddc3437b90c829cea58fb8edd5dde2f1eb0ee28da in /

2026-04-03 15:16:43 UTC

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

2026-04-14 16:30:51 UTC (buildkit.dockerfile.v0)

ENV NVARCH=x86_64

2026-04-14 16:30:51 UTC (buildkit.dockerfile.v0)

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

2026-04-14 16:30:51 UTC (buildkit.dockerfile.v0)

ENV NV_CUDA_CUDART_VERSION=13.0.96-1

2026-04-14 16:30:51 UTC (buildkit.dockerfile.v0)

ARG TARGETARCH

2026-04-14 16:30:51 UTC (buildkit.dockerfile.v0)

LABEL maintainer=NVIDIA CORPORATION <cudatools@nvidia.com>

2026-04-14 16:30:51 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/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

2026-04-14 16:30:51 UTC (buildkit.dockerfile.v0)

ENV CUDA_VERSION=13.0.3

2026-04-14 16:31:02 UTC (buildkit.dockerfile.v0)

RUN |1 TARGETARCH=amd64 /bin/sh -c apt-get update && apt-get install -y --no-install-recommends cuda-cudart-13-0=${NV_CUDA_CUDART_VERSION} cuda-toolkit-13-0-config-common=${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

2026-04-14 16:31:18 UTC (buildkit.dockerfile.v0)

RUN |1 TARGETARCH=amd64 /bin/sh -c apt-get update && if apt-cache policy cuda-compat-13-0 2>/dev/null | grep -q "Candidate:"; then apt-get install -y --no-install-recommends cuda-compat-13-0; fi && rm -rf /var/lib/apt/lists/* # buildkit

2026-04-14 16:31:25 UTC (buildkit.dockerfile.v0)

RUN |1 TARGETARCH=amd64 /bin/sh -c apt-get update && if apt-cache policy cuda-compat-orin-13-0 2>/dev/null | grep -q "Candidate:"; then apt-get install -y --no-install-recommends cuda-compat-orin-13-0; fi && rm -rf /var/lib/apt/lists/* # buildkit

2026-04-14 16:31:25 UTC (buildkit.dockerfile.v0)

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

2026-04-14 16:31:25 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

2026-04-14 16:31:25 UTC (buildkit.dockerfile.v0)

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

2026-04-14 16:31:25 UTC (buildkit.dockerfile.v0)

COPY NGC-DL-CONTAINER-LICENSE / # buildkit

2026-04-14 16:31:25 UTC (buildkit.dockerfile.v0)

ENV NVIDIA_VISIBLE_DEVICES=all

2026-04-14 16:31:25 UTC (buildkit.dockerfile.v0)

ENV NVIDIA_DRIVER_CAPABILITIES=compute,utility

2026-09-26 23:33:44 UTC (buildkit.dockerfile.v0)

ARG INSTALL_RUBIN_PRERELEASE=false

2026-09-26 23:33:44 UTC (buildkit.dockerfile.v0)

ARG TARGETPLATFORM=linux/amd64

2026-09-26 23:33:44 UTC (buildkit.dockerfile.v0)

ARG max_jobs=64

2026-09-26 23:33:44 UTC (buildkit.dockerfile.v0)

ARG CUDA_VERSION=13.0.3

2026-09-26 23:33:44 UTC (buildkit.dockerfile.v0)

ARG PYTHON_VERSION=3.12

2026-09-26 23:33:44 UTC (buildkit.dockerfile.v0)

ARG NCCL_VERSION=2.30.7

2026-09-26 23:33:44 UTC (buildkit.dockerfile.v0)

ARG DEADSNAKES_MIRROR_URL

2026-09-26 23:33:44 UTC (buildkit.dockerfile.v0)

ARG DEADSNAKES_GPGKEY_URL

2026-09-26 23:33:44 UTC (buildkit.dockerfile.v0)

ARG GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py

2026-09-26 23:33:44 UTC (buildkit.dockerfile.v0)

ENV CUDA_VERSION=13.0.3

2026-09-26 23:33:44 UTC (buildkit.dockerfile.v0)

ENV DEBIAN_FRONTEND=noninteractive

2026-09-26 23:33:44 UTC (buildkit.dockerfile.v0)

WORKDIR /vllm-workspace

2026-09-26 23:34:02 UTC (buildkit.dockerfile.v0)

RUN |9 INSTALL_RUBIN_PRERELEASE=false TARGETPLATFORM=linux/amd64 max_jobs=64 CUDA_VERSION=13.0.3 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

2026-09-26 23:39:39 UTC (buildkit.dockerfile.v0)

RUN |9 INSTALL_RUBIN_PRERELEASE=false TARGETPLATFORM=linux/amd64 max_jobs=64 CUDA_VERSION=13.0.3 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

2026-09-26 23:41:07 UTC (buildkit.dockerfile.v0)

RUN |9 INSTALL_RUBIN_PRERELEASE=false TARGETPLATFORM=linux/amd64 max_jobs=64 CUDA_VERSION=13.0.3 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-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

2026-09-26 23:41:07 UTC (buildkit.dockerfile.v0)

ENV CUDA_HOME=/usr/local/cuda

2026-09-26 23:41:07 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

2026-09-26 23:41:07 UTC (buildkit.dockerfile.v0)

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

2026-09-27 01:21:31 UTC (buildkit.dockerfile.v0)

RUN |9 INSTALL_RUBIN_PRERELEASE=false TARGETPLATFORM=linux/amd64 max_jobs=64 CUDA_VERSION=13.0.3 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: ${CUDA_MAJOR_MINOR}" >&2; exit 1; fi && if NCCL_LIBRARY=$(find /usr/lib -name libnccl.so.2 -print -quit) && [ -n "${NCCL_LIBRARY}" ]; then if [ "${NCCL_LIBRARY}" != "/usr/lib/libnccl.so.2" ]; then ln -sf "${NCCL_LIBRARY}" /usr/lib/libnccl.so.2; fi && ln -sf libnccl.so.2 /usr/lib/libnccl.so; fi && ldconfig; fi # buildkit

2026-09-26 23:41:08 UTC (buildkit.dockerfile.v0)

COPY tools/install_snapshot_runtime.sh /usr/local/bin/install_snapshot_runtime.sh # buildkit

2026-09-26 23:41:57 UTC (buildkit.dockerfile.v0)

RUN |9 INSTALL_RUBIN_PRERELEASE=false TARGETPLATFORM=linux/amd64 max_jobs=64 CUDA_VERSION=13.0.3 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 [ "${TARGETPLATFORM}" = "linux/amd64" ]; then MAX_JOBS="${max_jobs}" /usr/local/bin/install_snapshot_runtime.sh; else echo "Initialized snapshots are not installed for ${TARGETPLATFORM}"; fi # buildkit

2026-09-26 23:41:57 UTC (buildkit.dockerfile.v0)

ENV CRIU_CUDA_PLUGIN_DIR=/usr/local/lib/criu

2026-09-26 23:42:02 UTC (buildkit.dockerfile.v0)

RUN |9 INSTALL_RUBIN_PRERELEASE=false TARGETPLATFORM=linux/amd64 max_jobs=64 CUDA_VERSION=13.0.3 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

2026-09-26 23:42:02 UTC (buildkit.dockerfile.v0)

ENV UV_HTTP_TIMEOUT=500

2026-09-26 23:42:02 UTC (buildkit.dockerfile.v0)

ENV UV_INDEX_STRATEGY=unsafe-best-match

2026-09-26 23:42:02 UTC (buildkit.dockerfile.v0)

ENV UV_LINK_MODE=copy

2026-09-26 23:42:02 UTC (buildkit.dockerfile.v0)

ENV UV_PYTHON_INSTALL_DIR=/opt/uv/python

2026-09-26 23:42:02 UTC (buildkit.dockerfile.v0)

ENV UV_CACHE_DIR=/opt/uv/cache

2026-09-26 23:42:04 UTC (buildkit.dockerfile.v0)

RUN |9 INSTALL_RUBIN_PRERELEASE=false TARGETPLATFORM=linux/amd64 max_jobs=64 CUDA_VERSION=13.0.3 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

2026-09-26 23:42:04 UTC (buildkit.dockerfile.v0)

RUN |9 INSTALL_RUBIN_PRERELEASE=false TARGETPLATFORM=linux/amd64 max_jobs=64 CUDA_VERSION=13.0.3 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

2026-09-26 23:42:04 UTC (buildkit.dockerfile.v0)

ENV UV_OVERRIDE=/etc/uv-overrides.txt

2026-09-26 23:42:05 UTC (buildkit.dockerfile.v0)

RUN |9 INSTALL_RUBIN_PRERELEASE=false TARGETPLATFORM=linux/amd64 max_jobs=64 CUDA_VERSION=13.0.3 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

2026-09-26 23:42:05 UTC (buildkit.dockerfile.v0)

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

2026-09-27 01:21:31 UTC (buildkit.dockerfile.v0)

RUN |9 INSTALL_RUBIN_PRERELEASE=false TARGETPLATFORM=linux/amd64 max_jobs=64 CUDA_VERSION=13.0.3 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

2026-09-27 01:21:31 UTC (buildkit.dockerfile.v0)

ENV VLLM_ENABLE_CUDA_COMPATIBILITY=0

2026-09-27 01:21:31 UTC (buildkit.dockerfile.v0)

ARG PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl

2026-09-26 23:42:06 UTC (buildkit.dockerfile.v0)

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

2026-09-26 23:42:06 UTC (buildkit.dockerfile.v0)

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

2026-09-26 23:44:56 UTC (buildkit.dockerfile.v0)

RUN |10 INSTALL_RUBIN_PRERELEASE=false TARGETPLATFORM=linux/amd64 max_jobs=64 CUDA_VERSION=13.0.3 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 [ "${INSTALL_RUBIN_PRERELEASE}" = "true" ]; then uv pip install --system --prerelease=allow --index-strategy unsafe-first-match -r /tmp/vllm-requirements/rubin-prerelease.txt && sed -Ei '/^[[:space:]]*(torch|torchvision|torchaudio)[[:space:]]*==/Id' /tmp/requirements-cuda.txt && uv pip install --system -r /tmp/requirements-cuda.txt && uv pip install --system --prerelease=allow --index-strategy unsafe-first-match -r /tmp/vllm-requirements/rubin-prerelease.txt && printf '%s\n' "/usr/local/lib/python${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

2026-09-26 23:44:56 UTC (buildkit.dockerfile.v0)

ARG FLASHINFER_VERSION=0.7.0

2026-09-26 23:45:43 UTC (buildkit.dockerfile.v0)

RUN |11 INSTALL_RUBIN_PRERELEASE=false TARGETPLATFORM=linux/amd64 max_jobs=64 CUDA_VERSION=13.0.3 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=0.7.0 /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

2026-09-26 23:45:43 UTC (buildkit.dockerfile.v0)

ARG GDRCOPY_CUDA_VERSION=12.8

2026-09-26 23:45:43 UTC (buildkit.dockerfile.v0)

ARG GDRCOPY_OS_VERSION=Ubuntu24_04

2026-09-26 23:45:43 UTC (buildkit.dockerfile.v0)

ARG TARGETPLATFORM=linux/amd64

2026-09-26 23:45:45 UTC (buildkit.dockerfile.v0)

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

2026-09-26 23:45:51 UTC (buildkit.dockerfile.v0)

RUN |13 INSTALL_RUBIN_PRERELEASE=false TARGETPLATFORM=linux/amd64 max_jobs=64 CUDA_VERSION=13.0.3 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=0.7.0 GDRCOPY_CUDA_VERSION=12.8 GDRCOPY_OS_VERSION=Ubuntu24_04 /bin/sh -c set -eux; if [ "${INSTALL_RUBIN_PRERELEASE}" = "true" ] && ldconfig -p | grep -q 'libgdrapi\.so'; then true; else case "${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

2026-09-26 23:45:51 UTC (buildkit.dockerfile.v0)

ARG TIMM_VERSION=>=1.0.17

2026-09-26 23:45:51 UTC (buildkit.dockerfile.v0)

ARG RUNAI_MODEL_STREAMER_VERSION=>=0.15.7

2026-09-26 23:45:57 UTC (buildkit.dockerfile.v0)

RUN |15 INSTALL_RUBIN_PRERELEASE=false TARGETPLATFORM=linux/amd64 max_jobs=64 CUDA_VERSION=13.0.3 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=0.7.0 GDRCOPY_CUDA_VERSION=12.8 GDRCOPY_OS_VERSION=Ubuntu24_04 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

2026-09-26 23:45:57 UTC (buildkit.dockerfile.v0)

ARG PIP_INDEX_URL UV_INDEX_URL=

2026-09-26 23:45:57 UTC (buildkit.dockerfile.v0)

ARG PIP_EXTRA_INDEX_URL UV_EXTRA_INDEX_URL=

2026-09-26 23:45:57 UTC (buildkit.dockerfile.v0)

ARG PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl

2026-09-26 23:45:57 UTC (buildkit.dockerfile.v0)

ARG PIP_KEYRING_PROVIDER=disabled UV_KEYRING_PROVIDER=disabled

2026-09-26 23:45:57 UTC (buildkit.dockerfile.v0)

ARG PYTORCH_NIGHTLY

2026-09-26 23:45:58 UTC (buildkit.dockerfile.v0)

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

2026-09-27 01:53:09 UTC (buildkit.dockerfile.v0)

COPY /workspace/dist/wheel.sha256 /tmp/vllm-wheel.sha256 # buildkit

2026-09-27 01:53:24 UTC (buildkit.dockerfile.v0)

RUN |22 INSTALL_RUBIN_PRERELEASE=false TARGETPLATFORM=linux/amd64 max_jobs=64 CUDA_VERSION=13.0.3 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=0.7.0 GDRCOPY_CUDA_VERSION=12.8 GDRCOPY_OS_VERSION=Ubuntu24_04 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= 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

2026-09-27 01:53:24 UTC (buildkit.dockerfile.v0)

RUN |22 INSTALL_RUBIN_PRERELEASE=false TARGETPLATFORM=linux/amd64 max_jobs=64 CUDA_VERSION=13.0.3 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=0.7.0 GDRCOPY_CUDA_VERSION=12.8 GDRCOPY_OS_VERSION=Ubuntu24_04 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= 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

2026-09-27 01:53:25 UTC (buildkit.dockerfile.v0)

RUN |22 INSTALL_RUBIN_PRERELEASE=false TARGETPLATFORM=linux/amd64 max_jobs=64 CUDA_VERSION=13.0.3 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=0.7.0 GDRCOPY_CUDA_VERSION=12.8 GDRCOPY_OS_VERSION=Ubuntu24_04 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= PIP_KEYRING_PROVIDER=disabled UV_KEYRING_PROVIDER=disabled PYTORCH_NIGHTLY= /bin/sh -c . /etc/environment && uv pip list # buildkit

2026-09-27 01:53:25 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

2026-09-27 01:53:25 UTC (buildkit.dockerfile.v0)

COPY /tmp/ep_kernels_workspace/dist/wheels.sha256 /tmp/ep-kernels-wheels.sha256 # buildkit

2026-09-27 01:53:25 UTC (buildkit.dockerfile.v0)

RUN |22 INSTALL_RUBIN_PRERELEASE=false TARGETPLATFORM=linux/amd64 max_jobs=64 CUDA_VERSION=13.0.3 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=0.7.0 GDRCOPY_CUDA_VERSION=12.8 GDRCOPY_OS_VERSION=Ubuntu24_04 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= 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

2026-09-27 01:53:25 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

2026-09-27 01:53:25 UTC (buildkit.dockerfile.v0)

COPY examples examples # buildkit

2026-09-27 01:53:25 UTC (buildkit.dockerfile.v0)

COPY benchmarks benchmarks # buildkit

2026-09-27 01:53:25 UTC (buildkit.dockerfile.v0)

COPY ./vllm/collect_env.py . # buildkit

2026-09-27 01:53:25 UTC (buildkit.dockerfile.v0)

ARG TARGETPLATFORM=linux/amd64

2026-09-27 01:53:25 UTC (buildkit.dockerfile.v0)

ARG INSTALL_KV_CONNECTORS=true

2026-09-27 01:53:25 UTC (buildkit.dockerfile.v0)

ARG INSTALL_RUBIN_PRERELEASE=false

2026-09-27 01:53:25 UTC (buildkit.dockerfile.v0)

ARG TRITON_INSTALL_FROM_SOURCE_REPO=

2026-09-27 01:53:25 UTC (buildkit.dockerfile.v0)

ARG CUDA_VERSION=13.0.3

2026-09-27 01:53:25 UTC (buildkit.dockerfile.v0)

ARG VLLM_BUILD_COMMIT=69d383751226559cf215040b2ee95a13a7b79288

2026-09-27 01:53:25 UTC (buildkit.dockerfile.v0)

ARG VLLM_BUILD_PIPELINE=image-build

2026-09-27 01:53:25 UTC (buildkit.dockerfile.v0)

ARG VLLM_BUILD_URL=https://buildkite.com/inferact/image-build/builds/2646

2026-09-27 01:53:25 UTC (buildkit.dockerfile.v0)

ARG VLLM_IMAGE_TAG=inferactinc/dev:vllm-dsv41-decoder-replay-pr58132-69d383751226-cu130-amd64

2026-09-27 01:53:25 UTC (buildkit.dockerfile.v0)

ARG PIP_INDEX_URL UV_INDEX_URL=

2026-09-27 01:53:25 UTC (buildkit.dockerfile.v0)

ARG PIP_EXTRA_INDEX_URL UV_EXTRA_INDEX_URL=

2026-09-27 01:53:25 UTC (buildkit.dockerfile.v0)

ENV UV_HTTP_TIMEOUT=500

2026-09-27 01:53:25 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

2026-09-27 01:53:25 UTC (buildkit.dockerfile.v0)

ENV TORCH_CUDA_ARCH_LIST=7.5 8.0 8.6 8.9 9.0 10.0 11.0 12.0

2026-09-27 01:53:48 UTC (buildkit.dockerfile.v0)

RUN |29 INSTALL_RUBIN_PRERELEASE=false TARGETPLATFORM=linux/amd64 max_jobs=64 CUDA_VERSION=13.0.3 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=0.7.0 GDRCOPY_CUDA_VERSION=12.8 GDRCOPY_OS_VERSION=Ubuntu24_04 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= PIP_KEYRING_PROVIDER=disabled UV_KEYRING_PROVIDER=disabled PYTORCH_NIGHTLY= INSTALL_KV_CONNECTORS=true TRITON_INSTALL_FROM_SOURCE_REPO= VLLM_BUILD_COMMIT=69d383751226559cf215040b2ee95a13a7b79288 VLLM_BUILD_PIPELINE=image-build VLLM_BUILD_URL=https://buildkite.com/inferact/image-build/builds/2646 VLLM_IMAGE_TAG=inferactinc/dev:vllm-dsv41-decoder-replay-pr58132-69d383751226-cu130-amd64 torch_cuda_arch_list=7.5 8.0 8.6 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

2026-09-27 01:53:48 UTC (buildkit.dockerfile.v0)

RUN |29 INSTALL_RUBIN_PRERELEASE=false TARGETPLATFORM=linux/amd64 max_jobs=64 CUDA_VERSION=13.0.3 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=0.7.0 GDRCOPY_CUDA_VERSION=12.8 GDRCOPY_OS_VERSION=Ubuntu24_04 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= PIP_KEYRING_PROVIDER=disabled UV_KEYRING_PROVIDER=disabled PYTORCH_NIGHTLY= INSTALL_KV_CONNECTORS=true TRITON_INSTALL_FROM_SOURCE_REPO= VLLM_BUILD_COMMIT=69d383751226559cf215040b2ee95a13a7b79288 VLLM_BUILD_PIPELINE=image-build VLLM_BUILD_URL=https://buildkite.com/inferact/image-build/builds/2646 VLLM_IMAGE_TAG=inferactinc/dev:vllm-dsv41-decoder-replay-pr58132-69d383751226-cu130-amd64 torch_cuda_arch_list=7.5 8.0 8.6 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

2026-09-27 01:53:48 UTC (buildkit.dockerfile.v0)

COPY /tmp/triton_from_source_workspace/dist/wheel.sha256 /tmp/triton-source-wheel.sha256 # buildkit

2026-09-27 01:53:48 UTC (buildkit.dockerfile.v0)

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

2026-09-27 01:53:48 UTC (buildkit.dockerfile.v0)

RUN |29 INSTALL_RUBIN_PRERELEASE=false TARGETPLATFORM=linux/amd64 max_jobs=64 CUDA_VERSION=13.0.3 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=0.7.0 GDRCOPY_CUDA_VERSION=12.8 GDRCOPY_OS_VERSION=Ubuntu24_04 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= PIP_KEYRING_PROVIDER=disabled UV_KEYRING_PROVIDER=disabled PYTORCH_NIGHTLY= INSTALL_KV_CONNECTORS=true TRITON_INSTALL_FROM_SOURCE_REPO= VLLM_BUILD_COMMIT=69d383751226559cf215040b2ee95a13a7b79288 VLLM_BUILD_PIPELINE=image-build VLLM_BUILD_URL=https://buildkite.com/inferact/image-build/builds/2646 VLLM_IMAGE_TAG=inferactinc/dev:vllm-dsv41-decoder-replay-pr58132-69d383751226-cu130-amd64 torch_cuda_arch_list=7.5 8.0 8.6 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

2026-09-27 01:53:48 UTC (buildkit.dockerfile.v0)

ENV VLLM_USAGE_SOURCE=production-docker-image

2026-09-27 01:53:48 UTC (buildkit.dockerfile.v0)

ENV VLLM_BUILD_COMMIT=69d383751226559cf215040b2ee95a13a7b79288 VLLM_BUILD_PIPELINE=image-build VLLM_BUILD_URL=https://buildkite.com/inferact/image-build/builds/2646 VLLM_IMAGE_TAG=inferactinc/dev:vllm-dsv41-decoder-replay-pr58132-69d383751226-cu130-amd64

2026-09-27 01:53:48 UTC (buildkit.dockerfile.v0)

LABEL org.opencontainers.image.source=https://github.com/vllm-project/vllm org.opencontainers.image.revision=69d383751226559cf215040b2ee95a13a7b79288 org.opencontainers.image.version=inferactinc/dev:vllm-dsv41-decoder-replay-pr58132-69d383751226-cu130-amd64 org.opencontainers.image.url=https://buildkite.com/inferact/image-build/builds/2646 ai.vllm.build.commit=69d383751226559cf215040b2ee95a13a7b79288 ai.vllm.build.pipeline=image-build ai.vllm.build.url=https://buildkite.com/inferact/image-build/builds/2646 ai.vllm.image.tag=inferactinc/dev:vllm-dsv41-decoder-replay-pr58132-69d383751226-cu130-amd64

2026-09-27 01:53:48 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