Namespace
vllm
Image / Tagvllm-openai:muse-spark-open
Content Digestsha256:c91025b5be1039a93ca975d1d44f352b0e770bb6c8b142b5056cf92204ca137c
Details
2026-10-14 15:27:29 UTC
13.5 GB
Labels
-
ai.vllm.build.commitunknown
-
ai.vllm.build.pipelinelocal
-
ai.vllm.build.url
-
ai.vllm.image.taglocal/vllm-openai:dev
-
io.inferact.deepgemm.commit1704143a9f75375d31ba644691645fdf316d4866
-
io.inferact.flashinfer.commit6b49d21cf3b56ea3048ee42b15ed050ee7e7f6a6
-
maintainerNVIDIA CORPORATION <cudatools@nvidia.com>
-
org.opencontainers.image.revisiona34ca64c138ad0360c472ada748b750435b607ae
-
org.opencontainers.image.sourcehttps://github.com/vllm-project/vllm
-
org.opencontainers.image.url
-
org.opencontainers.image.versionlocal/vllm-openai:dev
Environment
CRIU_CUDA_PLUGIN_DIR/usr/local/lib/criu
CUDA_HOME/usr/local/cuda
CUDA_VERSION13.0.3
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
NVARCHx86_64
NVIDIA_DRIVER_CAPABILITIEScompute,utility
NVIDIA_REQUIRE_CUDAcuda>=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_DEVICESall
NV_CUDA_CUDART_VERSION13.0.96-1
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_LIST9.0 10.0 10.3 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_COMMITunknown
VLLM_BUILD_PIPELINElocal
VLLM_BUILD_URL VLLM_ENABLE_CUDA_COMPATIBILITY0
VLLM_IMAGE_TAGlocal/vllm-openai:dev
VLLM_USAGE_SOURCEproduction-docker-image
Layers
[#000] sha256:689b91d88a0f4086057ec826027b128902ecf2b516be510371c115bc55da19a6 - 0.21% (28.4 MB)
[#001] sha256:95e35692d3cc347d712fd236fd2af3b1c697783518182b1ae716722f694ed616 - 0.05% (6.64 MB)
[#002] sha256:5e25946ba40dcbc2410bf1852d135a46cb31cc7f89c05b9ef1ab12a6ef988aeb - 0.0% (354 KB)
[#003] sha256:f0af354daeda18f18684b23520969ef6bb3de82bb267936f867b12769be9125d - 0.73% (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] sha256:56e0903e063507f1c423e09418d1ae1697edd6f4204bf9b987db5797e9ed0f2d - 0.0% (104 Bytes)
[#008] sha256:282a6078a0dac97bf277558bde02ce2c07d19b01e1c4c3700f60c950843b5892 - 0.0% (231 Bytes)
[#009] sha256:ad0cf3fdf120603265d744ee8029486add17438d2e5f0025d463f8775153d241 - 1.61% (222 MB)
[#010] sha256:ca7914a1288c7eda6e2b9507e5caa7c0db838a20ca2de489b643a19876fde6e1 - 10.05% (1.35 GB)
[#011] sha256:6f64cd0694f3061f1d813c77ac9c925d409e827bafc868e9994936cd2b2c36fc - 0.0% (1.62 KB)
[#012] sha256:07a83d9d029faa8bc25414acb68c53dbe7ccb13785d2f1b7b981772c861a3c7f - 0.06% (8.85 MB)
[#013] sha256:fc7e3f33a01a8427e91f8e48611caefaaa1d6badba25f232b0a4f0c2a3e645df - 0.24% (33.6 MB)
[#014] sha256:93d8bc837c03acb71094fa43f599d3c41ef838d4fac6dcd146b12f194a34fcf6 - 0.0% (150 Bytes)
[#015] sha256:57edb58f87a5f58fc8723a5817b2d3e5f4a9913a948edabb802b9cabbcde8338 - 0.0% (164 Bytes)
[#016] sha256:df204ed7d2eb6ea02f88989b4dcad46cde5ece6337d716404a0708b4b16d5b80 - 0.0% (3.42 KB)
[#017] sha256:c3665411096f45bdbffb1c417a0412953c0aa6b8063f1184fe14cdedba1d29b6 - 0.0% (2.03 KB)
[#018] sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1 - 0.0% (32 Bytes)
[#019] sha256:535fb06532cf5353e2ba32f9e863b45da31d06dd5833586dd00336cbda13efcb - 0.0% (1.67 KB)
[#020] sha256:82128b3f56bc090f1826587b0d4fc45dd3ec397f82940d6d5835d00ae3d5c8cb - 0.0% (723 Bytes)
[#021] sha256:3651445e0e492e7aee539a97ce778bbf1fc029943dd9982b73c043f8d530205f - 25.99% (3.5 GB)
[#022] sha256:60f32a7f5c16dc270990d706076a4b063973d6b92648f798abcf6fb9edfe54c4 - 19.34% (2.6 GB)
[#023] sha256:a6540a77083ad038f1664a8a5df65b51fd7c0e92fc845edef1f07e3b88305c4b - 0.0% (897 Bytes)
[#024] sha256:3012ed2b73b2670046486144d35ee07731e43a6622940a3a06fe4a47707b221e - 0.0% (336 KB)
[#025] sha256:bdf959f15655bf978d1d7b63d48cffe778b3c6d4fc878a392ad1156c698561d6 - 0.46% (62.8 MB)
[#026] sha256:5d910e92b09c6cb17dc85ce8c4cc07b7d9044a1f861fb90f88afaa21843e72ce - 0.0% (201 Bytes)
[#027] sha256:218c7a59fd21ca72b566cbcca668f3f3929d5cd38d7eb2c3b1d12dc30a6c192f - 0.0% (235 Bytes)
[#028] sha256:c86c06b209fdfa8e50128393e7b3553cf75cc451396a0fab718a5fe40151f61a - 2.16% (297 MB)
[#029] sha256:7667b333c744a733cb2129c461ac5c856130321151d7c2e9450c133e19ea71e1 - 0.0% (197 Bytes)
[#030] sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1 - 0.0% (32 Bytes)
[#031] sha256:3eb30c8dc70ff347a9c4cd2ea2fc6555897099bded76acd138af7b7215e6ac71 - 0.0% (253 Bytes)
[#032] sha256:6438d1f4867eb186012b0a5f3a2a2963f3b4f576e19936add090883ce6b27df7 - 0.1% (13.9 MB)
[#033] sha256:4e24810749df513075c7de0f422f9a4bdce0af01a977e470489230c9c93e6bee - 0.0% (309 KB)
[#034] sha256:3bf5cab2a20e4012ec0d2b2526409ed4a0977657a64de264df2be81697c8c81c - 0.0% (298 KB)
[#035] sha256:8511de7556c7dcf8deba0ad34994be5e76f0442f471445df8e89089105928be5 - 0.0% (9.61 KB)
[#036] sha256:0e74d26ab2fbf30255d5568de937e1f2beba2a9d2e5fa4e7940251af2ae77c99 - 2.42% (334 MB)
[#037] sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1 - 0.0% (32 Bytes)
[#038] sha256:6ca38d821f9c0816542d6574d5d29104f3b1b961404f9107b42310580634af74 - 0.0% (211 Bytes)
[#039] sha256:968156616f36cb8bfd10abb04dbee7e6872c5fd9fe7302d08beb4432f5c6d2b9 - 0.0% (824 Bytes)
[#040] sha256:999810f2c2d9575feccce78c97e107cf379ecf17f0b99ea5d2edee11615c1424 - 0.0% (174 Bytes)
[#041] sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1 - 0.0% (32 Bytes)
[#042] sha256:aa9231cd3a7cdb92ea4af6171f69e208bddce2739115803d282c3f992217c04f - 17.85% (2.4 GB)
[#043] sha256:7dae7830712ef6c0c9f0a7b2329a6371402bba396f0b6d344e6b9d2bdf2bd64f - 0.69% (95 MB)
[#044] sha256:18e43dd76047e1756d957f94e16e79760d730fe89624421e793bcf6827f06b04 - 18.05% (2.43 GB)
[#045] sha256:eee19088c382b442d6876fabbf23f0be477b311d63025f8eaa555dac9367a1dd - 0.0% (1.22 KB)
[#046] sha256:7d4af0166fa5509c77d86ff4c0f401bafa9bdcaee9d9209f4b6e3fd2f0599d30 - 0.0% (174 Bytes)
History
/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
2026-10-14 14:23:18 UTC (buildkit.dockerfile.v0)ARG INSTALL_RUBIN_PRERELEASE=false
2026-10-14 14:23:18 UTC (buildkit.dockerfile.v0)ARG TARGETPLATFORM=linux/amd64
2026-10-14 14:23:18 UTC (buildkit.dockerfile.v0)ARG max_jobs=64
2026-10-14 14:23:18 UTC (buildkit.dockerfile.v0)ARG CUDA_VERSION=13.0.3
2026-10-14 14:23:18 UTC (buildkit.dockerfile.v0)ARG PYTHON_VERSION=3.12
2026-10-14 14:23:18 UTC (buildkit.dockerfile.v0)ARG NCCL_VERSION=2.30.7
2026-10-14 14:23:18 UTC (buildkit.dockerfile.v0)ARG DEADSNAKES_MIRROR_URL
2026-10-14 14:23:18 UTC (buildkit.dockerfile.v0)ARG DEADSNAKES_GPGKEY_URL
2026-10-14 14:23:18 UTC (buildkit.dockerfile.v0)ARG GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py
2026-10-14 14:23:18 UTC (buildkit.dockerfile.v0)ENV DEBIAN_FRONTEND=noninteractive
2026-10-14 14:23:18 UTC (buildkit.dockerfile.v0)WORKDIR /vllm-workspace
2026-10-14 14:23:42 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
2026-10-14 14:25:56 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
2026-10-14 15:02:54 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
2026-10-14 15:02:54 UTC (buildkit.dockerfile.v0)ENV CUDA_HOME=/usr/local/cuda
2026-10-14 15:02:54 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
2026-10-14 15:02:54 UTC (buildkit.dockerfile.v0)ENV LD_LIBRARY_PATH=/usr/local/cuda/lib64:/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/local/cuda/lib64
2026-10-14 15:03:49 UTC (buildkit.dockerfile.v0)COPY tools/install_snapshot_runtime.sh /usr/local/bin/install_snapshot_runtime.sh # buildkit
2026-10-14 15:04:14 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 [ "${TARGETPLATFORM}" = "linux/amd64" ] && [ "${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 ${CUDA_VERSION}"; fi # buildkit
2026-10-14 15:04:14 UTC (buildkit.dockerfile.v0)ENV CRIU_CUDA_PLUGIN_DIR=/usr/local/lib/criu
2026-10-14 15:04:16 UTC (buildkit.dockerfile.v0)RUN |9 INSTALL_RUBIN_PRERELEASE=false TARGETPLATFORM=linux/amd64 max_jobs=64 CUDA_VERSION=13.0.3 PYTHON_VERSION=3.12 NCCL_VERSION=2.30.7 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py /bin/sh -c python3 -m pip install uv # buildkit
2026-10-14 15:04:16 UTC (buildkit.dockerfile.v0)ENV UV_HTTP_TIMEOUT=500
2026-10-14 15:04:16 UTC (buildkit.dockerfile.v0)ENV UV_INDEX_STRATEGY=unsafe-best-match
2026-10-14 15:04:16 UTC (buildkit.dockerfile.v0)ENV UV_LINK_MODE=copy
2026-10-14 15:04:16 UTC (buildkit.dockerfile.v0)ENV UV_PYTHON_INSTALL_DIR=/opt/uv/python
2026-10-14 15:04:16 UTC (buildkit.dockerfile.v0)ENV UV_CACHE_DIR=/opt/uv/cache
2026-10-14 15:04:16 UTC (buildkit.dockerfile.v0)ENV UV_COMPILE_BYTECODE=1
2026-10-14 15:05:02 UTC (buildkit.dockerfile.v0)RUN |9 INSTALL_RUBIN_PRERELEASE=false TARGETPLATFORM=linux/amd64 max_jobs=64 CUDA_VERSION=13.0.3 PYTHON_VERSION=3.12 NCCL_VERSION=2.30.7 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py /bin/sh -c mkdir -p "${UV_PYTHON_INSTALL_DIR}" "${UV_CACHE_DIR}" && chgrp -R 0 /opt/uv && chmod -R g+rwX,a+rX /opt/uv # buildkit
2026-10-14 15:05:03 UTC (buildkit.dockerfile.v0)RUN |9 INSTALL_RUBIN_PRERELEASE=false TARGETPLATFORM=linux/amd64 max_jobs=64 CUDA_VERSION=13.0.3 PYTHON_VERSION=3.12 NCCL_VERSION=2.30.7 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py /bin/sh -c CUDA_MAJOR=$(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
2026-10-14 15:05:03 UTC (buildkit.dockerfile.v0)ENV UV_OVERRIDE=/etc/uv-overrides.txt
2026-10-14 15:05:05 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
2026-10-14 15:05:06 UTC (buildkit.dockerfile.v0)COPY docker/entrypoints/vllm-nonroot-entrypoint.sh /usr/local/bin/vllm-nonroot-entrypoint.sh # buildkit
2026-10-14 15:05:08 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
2026-10-14 15:05:08 UTC (buildkit.dockerfile.v0)ENV VLLM_ENABLE_CUDA_COMPATIBILITY=0
2026-10-14 15:05:08 UTC (buildkit.dockerfile.v0)ARG PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl
2026-10-14 15:05:09 UTC (buildkit.dockerfile.v0)COPY requirements/common.txt /tmp/common.txt # buildkit
2026-10-14 15:05:10 UTC (buildkit.dockerfile.v0)COPY requirements/cuda.txt /tmp/requirements-cuda.txt # buildkit
2026-10-14 15:06:35 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; else uv pip install --system -r /tmp/requirements-cuda.txt --extra-index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.'); fi && rm /tmp/requirements-cuda.txt /tmp/common.txt # buildkit
2026-10-14 15:10:10 UTC (buildkit.dockerfile.v0)RUN |10 INSTALL_RUBIN_PRERELEASE=false TARGETPLATFORM=linux/amd64 max_jobs=64 CUDA_VERSION=13.0.3 PYTHON_VERSION=3.12 NCCL_VERSION=2.30.7 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl /bin/sh -c PIP_CACHE_DIR=/opt/pip/cache flashinfer download-kernels # buildkit
2026-10-14 15:10:10 UTC (buildkit.dockerfile.v0)ARG GDRCOPY_CUDA_VERSION=12.8
2026-10-14 15:10:10 UTC (buildkit.dockerfile.v0)ARG GDRCOPY_OS_VERSION=Ubuntu24_04
2026-10-14 15:10:10 UTC (buildkit.dockerfile.v0)ARG TARGETPLATFORM=linux/amd64
2026-10-14 15:10:16 UTC (buildkit.dockerfile.v0)COPY tools/install_gdrcopy.sh /tmp/install_gdrcopy.sh # buildkit
2026-10-14 15:10:22 UTC (buildkit.dockerfile.v0)RUN |12 INSTALL_RUBIN_PRERELEASE=false TARGETPLATFORM=linux/amd64 max_jobs=64 CUDA_VERSION=13.0.3 PYTHON_VERSION=3.12 NCCL_VERSION=2.30.7 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl GDRCOPY_CUDA_VERSION=12.8 GDRCOPY_OS_VERSION=Ubuntu24_04 /bin/sh -c set -eux; case "${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
2026-10-14 15:10:22 UTC (buildkit.dockerfile.v0)ARG TIMM_VERSION=>=1.0.17
2026-10-14 15:10:22 UTC (buildkit.dockerfile.v0)ARG RUNAI_MODEL_STREAMER_VERSION=>=0.15.7
2026-10-14 15:10:25 UTC (buildkit.dockerfile.v0)RUN |14 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 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
2026-10-14 15:10:25 UTC (buildkit.dockerfile.v0)ARG PIP_INDEX_URL UV_INDEX_URL=
2026-10-14 15:10:25 UTC (buildkit.dockerfile.v0)ARG PIP_EXTRA_INDEX_URL UV_EXTRA_INDEX_URL=
2026-10-14 15:10:25 UTC (buildkit.dockerfile.v0)ARG PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl
2026-10-14 15:10:25 UTC (buildkit.dockerfile.v0)ARG PIP_KEYRING_PROVIDER=disabled UV_KEYRING_PROVIDER=disabled
2026-10-14 15:10:25 UTC (buildkit.dockerfile.v0)ARG PYTORCH_NIGHTLY
2026-10-14 15:10:26 UTC (buildkit.dockerfile.v0)COPY /workspace/torch_lib_versions.txt torch_lib_versions.txt # buildkit
2026-10-14 15:14:53 UTC (buildkit.dockerfile.v0)COPY /workspace/dist/wheel.sha256 /tmp/vllm-wheel.sha256 # buildkit
2026-10-14 15:15:07 UTC (buildkit.dockerfile.v0)RUN |21 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 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 $CUDA_VERSION | cut -d. -f1,2 | tr -d '.'); fi # buildkit
2026-10-14 15:15:07 UTC (buildkit.dockerfile.v0)RUN |21 INSTALL_RUBIN_PRERELEASE=false TARGETPLATFORM=linux/amd64 max_jobs=64 CUDA_VERSION=13.0.3 PYTHON_VERSION=3.12 NCCL_VERSION=2.30.7 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl GDRCOPY_CUDA_VERSION=12.8 GDRCOPY_OS_VERSION=Ubuntu24_04 TIMM_VERSION=>=1.0.17 RUNAI_MODEL_STREAMER_VERSION=>=0.15.7 PIP_INDEX_URL= UV_INDEX_URL= PIP_EXTRA_INDEX_URL= UV_EXTRA_INDEX_URL= PIP_KEYRING_PROVIDER=disabled UV_KEYRING_PROVIDER=disabled PYTORCH_NIGHTLY= /bin/sh -c ln -s "$(python3 -c 'import sysconfig; print(sysconfig.get_path("platlib"))')/vllm/vllm-rs" /usr/local/bin/vllm-rs && vllm-rs --version # buildkit
2026-10-14 15:15:07 UTC (buildkit.dockerfile.v0)RUN |21 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 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
2026-10-14 15:15:07 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
2026-10-14 15:15:07 UTC (buildkit.dockerfile.v0)COPY /tmp/ep_kernels_workspace/dist/wheels.sha256 /tmp/ep-kernels-wheels.sha256 # buildkit
2026-10-14 15:15:08 UTC (buildkit.dockerfile.v0)RUN |21 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 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
2026-10-14 15:15:08 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
2026-10-14 15:15:08 UTC (buildkit.dockerfile.v0)COPY examples examples # buildkit
2026-10-14 15:15:08 UTC (buildkit.dockerfile.v0)COPY benchmarks benchmarks # buildkit
2026-10-14 15:15:08 UTC (buildkit.dockerfile.v0)COPY ./vllm/collect_env.py . # buildkit
2026-10-14 15:15:08 UTC (buildkit.dockerfile.v0)ARG TARGETPLATFORM=linux/amd64
2026-10-14 15:15:08 UTC (buildkit.dockerfile.v0)ARG INSTALL_KV_CONNECTORS=true
2026-10-14 15:15:08 UTC (buildkit.dockerfile.v0)ARG INSTALL_RUBIN_PRERELEASE=false
2026-10-14 15:15:08 UTC (buildkit.dockerfile.v0)ARG TRITON_INSTALL_FROM_SOURCE_REPO=
2026-10-14 15:15:08 UTC (buildkit.dockerfile.v0)ARG CUDA_VERSION=13.0.3
2026-10-14 15:15:08 UTC (buildkit.dockerfile.v0)ARG VLLM_BUILD_COMMIT
2026-10-14 15:15:08 UTC (buildkit.dockerfile.v0)ARG VLLM_BUILD_PIPELINE
2026-10-14 15:15:08 UTC (buildkit.dockerfile.v0)ARG VLLM_BUILD_URL
2026-10-14 15:15:08 UTC (buildkit.dockerfile.v0)ARG VLLM_IMAGE_TAG
2026-10-14 15:15:08 UTC (buildkit.dockerfile.v0)ARG PIP_INDEX_URL UV_INDEX_URL=
2026-10-14 15:15:08 UTC (buildkit.dockerfile.v0)ARG PIP_EXTRA_INDEX_URL UV_EXTRA_INDEX_URL=
2026-10-14 15:15:08 UTC (buildkit.dockerfile.v0)ENV UV_HTTP_TIMEOUT=500
2026-10-14 15:15:08 UTC (buildkit.dockerfile.v0)ARG torch_cuda_arch_list=9.0 10.0 10.3 12.0
2026-10-14 15:15:08 UTC (buildkit.dockerfile.v0)ENV TORCH_CUDA_ARCH_LIST=9.0 10.0 10.3 12.0
2026-10-14 15:15:20 UTC (buildkit.dockerfile.v0)RUN |28 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 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= VLLM_BUILD_PIPELINE= VLLM_BUILD_URL= VLLM_IMAGE_TAG= torch_cuda_arch_list=9.0 10.0 10.3 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==${MOONCAKE_VERSION}"; fi; rm -f /tmp/kv-installed.txt /tmp/kv-constraints.txt; fi # buildkit
2026-10-14 15:15:20 UTC (buildkit.dockerfile.v0)RUN |28 INSTALL_RUBIN_PRERELEASE=false TARGETPLATFORM=linux/amd64 max_jobs=64 CUDA_VERSION=13.0.3 PYTHON_VERSION=3.12 NCCL_VERSION=2.30.7 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl GDRCOPY_CUDA_VERSION=12.8 GDRCOPY_OS_VERSION=Ubuntu24_04 TIMM_VERSION=>=1.0.17 RUNAI_MODEL_STREAMER_VERSION=>=0.15.7 PIP_INDEX_URL= UV_INDEX_URL= PIP_EXTRA_INDEX_URL= UV_EXTRA_INDEX_URL= PIP_KEYRING_PROVIDER=disabled UV_KEYRING_PROVIDER=disabled PYTORCH_NIGHTLY= INSTALL_KV_CONNECTORS=true TRITON_INSTALL_FROM_SOURCE_REPO= VLLM_BUILD_COMMIT= VLLM_BUILD_PIPELINE= VLLM_BUILD_URL= VLLM_IMAGE_TAG= torch_cuda_arch_list=9.0 10.0 10.3 12.0 /bin/sh -c if [ "${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
2026-10-14 15:15:20 UTC (buildkit.dockerfile.v0)COPY /tmp/triton_from_source_workspace/dist/wheel.sha256 /tmp/triton-source-wheel.sha256 # buildkit
2026-10-14 15:15:21 UTC (buildkit.dockerfile.v0)COPY tools/install_triton_from_source.sh /tmp/install_triton_from_source.sh # buildkit
2026-10-14 15:15:21 UTC (buildkit.dockerfile.v0)RUN |28 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 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= VLLM_BUILD_PIPELINE= VLLM_BUILD_URL= VLLM_IMAGE_TAG= torch_cuda_arch_list=9.0 10.0 10.3 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: ${CUDA_MAJOR_MINOR}" >&2; exit 1 ;; esac; else bash /tmp/install_triton_from_source.sh /tmp/triton-source-dist /tmp/triton-source-wheel.sha256; fi; fi && rm -f /tmp/install_triton_from_source.sh /tmp/triton-source-wheel.sha256 # buildkit
2026-10-14 15:15:21 UTC (buildkit.dockerfile.v0)ARG BUILD_NIXL=false
2026-10-14 15:15:21 UTC (buildkit.dockerfile.v0)RUN |29 INSTALL_RUBIN_PRERELEASE=false TARGETPLATFORM=linux/amd64 max_jobs=64 CUDA_VERSION=13.0.3 PYTHON_VERSION=3.12 NCCL_VERSION=2.30.7 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl GDRCOPY_CUDA_VERSION=12.8 GDRCOPY_OS_VERSION=Ubuntu24_04 TIMM_VERSION=>=1.0.17 RUNAI_MODEL_STREAMER_VERSION=>=0.15.7 PIP_INDEX_URL= UV_INDEX_URL= PIP_EXTRA_INDEX_URL= UV_EXTRA_INDEX_URL= PIP_KEYRING_PROVIDER=disabled UV_KEYRING_PROVIDER=disabled PYTORCH_NIGHTLY= INSTALL_KV_CONNECTORS=true TRITON_INSTALL_FROM_SOURCE_REPO= VLLM_BUILD_COMMIT= VLLM_BUILD_PIPELINE= VLLM_BUILD_URL= VLLM_IMAGE_TAG= torch_cuda_arch_list=9.0 10.0 10.3 12.0 BUILD_NIXL=false /bin/sh -c set -eu; if [ "${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
2026-10-14 15:15:21 UTC (buildkit.dockerfile.v0)ENV VLLM_USAGE_SOURCE=production-docker-image
2026-10-14 15:15:21 UTC (buildkit.dockerfile.v0)ENV VLLM_BUILD_COMMIT=unknown VLLM_BUILD_PIPELINE=local VLLM_BUILD_URL= VLLM_IMAGE_TAG=local/vllm-openai:dev
2026-10-14 15:15:21 UTC (buildkit.dockerfile.v0)LABEL org.opencontainers.image.source=https://github.com/vllm-project/vllm org.opencontainers.image.revision=unknown org.opencontainers.image.version=local/vllm-openai:dev org.opencontainers.image.url= ai.vllm.build.commit=unknown ai.vllm.build.pipeline=local ai.vllm.build.url= ai.vllm.image.tag=local/vllm-openai:dev
2026-10-14 15:15:21 UTC (buildkit.dockerfile.v0)ENTRYPOINT ["vllm" "serve"]
2026-10-14 15:24:44 UTC (buildkit.dockerfile.v0)LABEL org.opencontainers.image.revision=a34ca64c138ad0360c472ada748b750435b607ae io.inferact.deepgemm.commit=1704143a9f75375d31ba644691645fdf316d4866 io.inferact.flashinfer.commit=6b49d21cf3b56ea3048ee42b15ed050ee7e7f6a6
2026-10-14 15:24:44 UTC (buildkit.dockerfile.v0)COPY wheels /tmp/flashinfer-mpk-wheels # buildkit
2026-10-14 15:24:47 UTC (buildkit.dockerfile.v0)RUN /bin/sh -c uv pip install --system --no-cache av scipy librosa soundfile soxr audioread 'mistral_common[audio]' # buildkit
2026-10-14 15:27:22 UTC (buildkit.dockerfile.v0)RUN /bin/sh -c uv pip install --system --no-cache --reinstall --no-deps /tmp/flashinfer-mpk-wheels/flashinfer_jit_cache*.whl /tmp/flashinfer-mpk-wheels/flashinfer_cubin-*.whl /tmp/flashinfer-mpk-wheels/flashinfer_python-*.whl && rm -rf /tmp/flashinfer-mpk-wheels # buildkit
2026-10-14 15:27:23 UTC (buildkit.dockerfile.v0)COPY verify_runtime.py /tmp/verify_runtime.py # buildkit
2026-10-14 15:27:29 UTC (buildkit.dockerfile.v0)RUN /bin/sh -c python3 /tmp/verify_runtime.py && rm /tmp/verify_runtime.py # buildkit
Details
2026-10-14 16:00:50 UTC
14.4 GB
Labels
-
ai.vllm.build.commitunknown
-
ai.vllm.build.pipelinelocal
-
ai.vllm.build.url
-
ai.vllm.image.taglocal/vllm-openai:dev
-
io.inferact.deepgemm.commit1704143a9f75375d31ba644691645fdf316d4866
-
io.inferact.flashinfer.commit6b49d21cf3b56ea3048ee42b15ed050ee7e7f6a6
-
maintainerNVIDIA CORPORATION <cudatools@nvidia.com>
-
org.opencontainers.image.revisiona34ca64c138ad0360c472ada748b750435b607ae
-
org.opencontainers.image.sourcehttps://github.com/vllm-project/vllm
-
org.opencontainers.image.url
-
org.opencontainers.image.versionlocal/vllm-openai:dev
Environment
CRIU_CUDA_PLUGIN_DIR/usr/local/lib/criu
CUDA_HOME/usr/local/cuda
CUDA_VERSION13.0.3
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>=13.0 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_DEVICESall
NV_CUDA_CUDART_VERSION13.0.96-1
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_LIST9.0 10.0 10.3 12.0 12.1
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_COMMITunknown
VLLM_BUILD_PIPELINElocal
VLLM_BUILD_URL VLLM_ENABLE_CUDA_COMPATIBILITY0
VLLM_IMAGE_TAGlocal/vllm-openai:dev
VLLM_USAGE_SOURCEproduction-docker-image
Layers
[#000] sha256:76fd055477b6edf8004a5a962edad02a820d4c8b2f02682410edfbe376b418c5 - 0.19% (27.5 MB)
[#001] sha256:2ed23d91404d4701b704d1bde211c59a2a564a31c315f05871a6e9403bc19945 - 0.04% (6.44 MB)
[#002] sha256:b69841cb303ccedcf38d7b88ef5624621de9afac92f991bd9493046493af0459 - 0.0% (368 KB)
[#003] sha256:f96e895ae7545ec872855c3f2adf4d95fa731dd2e8545b054f7aa1afc3d979f9 - 0.64% (94.8 MB)
[#004] sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1 - 0.0% (32 Bytes)
[#005] sha256:4efc2d488f5acb1bcdef886876870bffe7f6435015718596101285c66bfd9fea - 0.0% (187 Bytes)
[#006] sha256:730c8029606bf4b4533d7a7159458cf5e3f348ea956ccfb10ce5da3e20adac8f - 0.0% (6.72 KB)
[#007] sha256:d7a29537f73980ec12bf15befac142a82c6602fdb7d5156e23704337f164771d - 0.0% (104 Bytes)
[#008] sha256:196099b77d21ffaf1b5913c792e3a723cbf15ccbc083af1cb0bd0b22152fb54c - 0.0% (229 Bytes)
[#009] sha256:e42dba27159ef6c94e4985f6ed03cce76e4c418df2def81c567f6e2d0d916fe3 - 1.46% (215 MB)
[#010] sha256:6937dbd7e7c0a2ee7e49cfffc38111e3e90ba74b3c1e5625075550b7a07b92b4 - 10.33% (1.49 GB)
[#011] sha256:0868f058b05ffcb7eb0bb536aad97e2700c83f00bd84ca80597ac490f41ca676 - 0.0% (1.62 KB)
[#012] sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1 - 0.0% (32 Bytes)
[#013] sha256:21a60419ced8a5e410a78c12b5505d8e4372bda02f7cf04158bf90dd30d3a807 - 0.22% (32.4 MB)
[#014] sha256:df2a912da3ddca0bb7d31d17e513b0733cf5e1f23467184394a5c81695ff56b8 - 0.0% (150 Bytes)
[#015] sha256:8f5593a80eeed06079a72e25afeab4a3b4169d19fd677d164c1ec351844eb045 - 0.0% (163 Bytes)
[#016] sha256:bd7f99dcb088934ff3f0c0673f9e09e3ebc7b8ae6d9080e6d1da0721eaac4da6 - 0.0% (3.62 KB)
[#017] sha256:5ee39c76a985002acd819f51b248b981d3306db912f7177f6687b6ed021e5488 - 0.0% (2.03 KB)
[#018] sha256:5ee39c76a985002acd819f51b248b981d3306db912f7177f6687b6ed021e5488 - 0.0% (2.03 KB)
[#019] sha256:92c05c9e12c451d23c823a35e2c9fbcf9d08c1c8fc6097bce48f7ce82126cab0 - 0.0% (1.67 KB)
[#020] sha256:80b9728678a76a06dab0edfd49283be7ab7356022b6e5b50dbd43a5aa3a46fdf - 0.0% (722 Bytes)
[#021] sha256:22f75d14f8bef1d1f2ee800a82d0e93eca96fea5247a5e04f0b25cb2eafb9b5c - 24.78% (3.57 GB)
[#022] sha256:f98a575393eba5c9d1caa20415ef3e2ccb590d257d7d8d746841d47fb8b7bc3a - 19.75% (2.85 GB)
[#023] sha256:a4b54fe5b7fb268b0dc458c0330f29dbfafbfa0800bd3b1863ca190d3681844c - 0.0% (897 Bytes)
[#024] sha256:182931d3a48b9ff35ab9f6864c1fed8acf2f1c2421518bb12664566dc3777f32 - 0.0% (519 KB)
[#025] sha256:34ef9a953046f06d39af9f52e8e7f87f61c3c06d55a2bb7510cab8a8bd1b75f3 - 1.86% (275 MB)
[#026] sha256:7db8f5b92b97d7188085643962a03b6b8d6418eda2d3a3c4c4b5009d5a547dc7 - 0.0% (200 Bytes)
[#027] sha256:709d5b636e0c5fb1786a5aea43c7a25fd25eeefe21de1ab92eeba2eeb18e6805 - 0.0% (236 Bytes)
[#028] sha256:daef7afccea6295ac3b7e720b26c654de90b61d35521ff4f7ccfa05e2b428c1f - 3.44% (507 MB)
[#029] sha256:246b8f17581b4d54de85e01ea1cd44263b0e3286a387ad4a64eb6609f13cd72c - 0.0% (200 Bytes)
[#030] sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1 - 0.0% (32 Bytes)
[#031] sha256:2d9d1c00e98982488d7a25ed3c37d581e41c216b7439300409a6e3f8ea7a3f37 - 0.0% (253 Bytes)
[#032] sha256:0d52581437159612d740cc54b752c4ee5aa7ba78d2f4144bd8b8685853558b3e - 0.09% (13.7 MB)
[#033] sha256:5cac8a5677e8944a53cfa4bde17175c3f19670638ed08785e0b5f9c2725c9603 - 0.0% (309 KB)
[#034] sha256:d862fc8be10e229a80691b51d37bee20bfd6ae2f273de52ce8002f127d138845 - 0.0% (298 KB)
[#035] sha256:e424b3e5d80ef37ff732c1b98c1d355fb57a3984e1cb25e2a821021c62c39158 - 0.0% (9.61 KB)
[#036] sha256:a6cb9aed7edecb84b7fb576f6696b4a3da0930db43907bcece8639ce0c4f07fd - 3.53% (521 MB)
[#037] sha256:38e858597394cbd5b163fdf665d46a64d6bdafabc2dae63316a23497190e9a12 - 0.0% (92 Bytes)
[#038] sha256:25bcc59515f2ecab69ef5165e61eeb7cf35d42a07e09046feb273d2d52b35962 - 0.0% (212 Bytes)
[#039] sha256:605d1332a2586a2207fd1cd813ef4c922a92045d5a943ddf3fdfa3f0ba0ba4f7 - 0.0% (822 Bytes)
[#040] sha256:341c7ad385c2466806d91cf6b8a31e22862eeff13b820c555278f7e5745f4261 - 0.0% (181 Bytes)
[#041] sha256:564c03a87e5a0f40e345ad7468c258712391e0eea5b86701d4f38ae3de3025be - 0.0% (92 Bytes)
[#042] sha256:048172b79f7a73612a42bef7722945a74ca4fe8cc6edea2a0fe0ceb0655aa66e - 16.41% (2.36 GB)
[#043] sha256:ca2cb7c815d7acf0befc300e4a0e41759d31c44541359c799b0f43deb09fb647 - 0.63% (92.5 MB)
[#044] sha256:014e0fef99acaec0ae040b738a4b7053b825f61867b64576688d85578aac1d0b - 16.62% (2.4 GB)
[#045] sha256:4bed48e873f3ebd35cb41a8a8f84a4fb08a930712d4c3721e4b0b30df64ff67b - 0.0% (1.22 KB)
[#046] sha256:c65a3ba3228f3bf8b9ffd64d4c88ff7f8af61be2c32152bd2fbac7a427bf9ca9 - 0.0% (288 Bytes)
History
/bin/sh -c #(nop) ARG RELEASE
2026-04-03 15:15:14 UTC/bin/sh -c #(nop) ARG LAUNCHPAD_BUILD_ARCH
2026-04-03 15:15:14 UTC/bin/sh -c #(nop) LABEL org.opencontainers.image.version=24.04
2026-04-03 15:15:17 UTC/bin/sh -c #(nop) ADD file:9bab986009eae65b5534b3547eb3a7d0a1564404426de350dfd183cf3a4ffa9f in /
2026-04-03 15:15:17 UTC/bin/sh -c #(nop) CMD ["/bin/bash"]
2026-04-14 16:37:51 UTC (buildkit.dockerfile.v0)ENV NVARCH=sbsa
2026-04-14 16:37:51 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 16:37:51 UTC (buildkit.dockerfile.v0)ENV NV_CUDA_CUDART_VERSION=13.0.96-1
2026-04-14 16:37:51 UTC (buildkit.dockerfile.v0)ARG TARGETARCH
2026-04-14 16:37:51 UTC (buildkit.dockerfile.v0)LABEL maintainer=NVIDIA CORPORATION <cudatools@nvidia.com>
2026-04-14 16:37:51 UTC (buildkit.dockerfile.v0)RUN |1 TARGETARCH=arm64 /bin/sh -c apt-get update && apt-get install -y --no-install-recommends gnupg2 curl ca-certificates && curl -fsSLO https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2404/${NVARCH}/cuda-keyring_1.1-1_all.deb && dpkg -i cuda-keyring_1.1-1_all.deb && apt-get purge --autoremove -y curl && rm -rf /var/lib/apt/lists/* # buildkit
2026-04-14 16:37:51 UTC (buildkit.dockerfile.v0)ENV CUDA_VERSION=13.0.3
2026-04-14 16:41:16 UTC (buildkit.dockerfile.v0)RUN |1 TARGETARCH=arm64 /bin/sh -c apt-get update && apt-get install -y --no-install-recommends cuda-cudart-13-0=${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 16:46:19 UTC (buildkit.dockerfile.v0)RUN |1 TARGETARCH=arm64 /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 16:49:06 UTC (buildkit.dockerfile.v0)RUN |1 TARGETARCH=arm64 /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 16:49:06 UTC (buildkit.dockerfile.v0)RUN |1 TARGETARCH=arm64 /bin/sh -c echo "/usr/local/cuda/lib64" >> /etc/ld.so.conf.d/nvidia.conf # buildkit
2026-04-14 16:49:06 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 16:49:06 UTC (buildkit.dockerfile.v0)ENV LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/local/cuda/lib64
2026-04-14 16:49:06 UTC (buildkit.dockerfile.v0)COPY NGC-DL-CONTAINER-LICENSE / # buildkit
2026-04-14 16:49:06 UTC (buildkit.dockerfile.v0)ENV NVIDIA_VISIBLE_DEVICES=all
2026-04-14 16:49:06 UTC (buildkit.dockerfile.v0)ENV NVIDIA_DRIVER_CAPABILITIES=compute,utility
2026-10-14 15:33:07 UTC (buildkit.dockerfile.v0)ARG INSTALL_RUBIN_PRERELEASE
2026-10-14 15:33:07 UTC (buildkit.dockerfile.v0)ARG TARGETPLATFORM
2026-10-14 15:33:07 UTC (buildkit.dockerfile.v0)ARG max_jobs=2
2026-10-14 15:33:07 UTC (buildkit.dockerfile.v0)ARG CUDA_VERSION
2026-10-14 15:33:07 UTC (buildkit.dockerfile.v0)ARG PYTHON_VERSION
2026-10-14 15:33:07 UTC (buildkit.dockerfile.v0)ARG NCCL_VERSION
2026-10-14 15:33:07 UTC (buildkit.dockerfile.v0)ARG DEADSNAKES_MIRROR_URL
2026-10-14 15:33:07 UTC (buildkit.dockerfile.v0)ARG DEADSNAKES_GPGKEY_URL
2026-10-14 15:33:07 UTC (buildkit.dockerfile.v0)ARG GET_PIP_URL
2026-10-14 15:33:07 UTC (buildkit.dockerfile.v0)ENV DEBIAN_FRONTEND=noninteractive
2026-10-14 15:33:07 UTC (buildkit.dockerfile.v0)WORKDIR /vllm-workspace
2026-10-14 15:33:23 UTC (buildkit.dockerfile.v0)RUN |9 INSTALL_RUBIN_PRERELEASE=false TARGETPLATFORM=linux/arm64 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
2026-10-14 15:36:42 UTC (buildkit.dockerfile.v0)RUN |9 INSTALL_RUBIN_PRERELEASE=false TARGETPLATFORM=linux/arm64 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
2026-10-14 15:38:13 UTC (buildkit.dockerfile.v0)RUN |9 INSTALL_RUBIN_PRERELEASE=false TARGETPLATFORM=linux/arm64 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
2026-10-14 15:38:13 UTC (buildkit.dockerfile.v0)ENV CUDA_HOME=/usr/local/cuda
2026-10-14 15:38:13 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
2026-10-14 15:38:13 UTC (buildkit.dockerfile.v0)ENV LD_LIBRARY_PATH=/usr/local/cuda/lib64:/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/local/cuda/lib64
2026-10-14 15:38:13 UTC (buildkit.dockerfile.v0)COPY tools/install_snapshot_runtime.sh /usr/local/bin/install_snapshot_runtime.sh # buildkit
2026-10-14 15:38:13 UTC (buildkit.dockerfile.v0)RUN |9 INSTALL_RUBIN_PRERELEASE=false TARGETPLATFORM=linux/arm64 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 [ "${TARGETPLATFORM}" = "linux/amd64" ] && [ "${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 ${CUDA_VERSION}"; fi # buildkit
2026-10-14 15:38:13 UTC (buildkit.dockerfile.v0)ENV CRIU_CUDA_PLUGIN_DIR=/usr/local/lib/criu
2026-10-14 15:38:16 UTC (buildkit.dockerfile.v0)RUN |9 INSTALL_RUBIN_PRERELEASE=false TARGETPLATFORM=linux/arm64 max_jobs=64 CUDA_VERSION=13.0.3 PYTHON_VERSION=3.12 NCCL_VERSION=2.30.7 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py /bin/sh -c python3 -m pip install uv # buildkit
2026-10-14 15:38:16 UTC (buildkit.dockerfile.v0)ENV UV_HTTP_TIMEOUT=500
2026-10-14 15:38:16 UTC (buildkit.dockerfile.v0)ENV UV_INDEX_STRATEGY=unsafe-best-match
2026-10-14 15:38:16 UTC (buildkit.dockerfile.v0)ENV UV_LINK_MODE=copy
2026-10-14 15:38:16 UTC (buildkit.dockerfile.v0)ENV UV_PYTHON_INSTALL_DIR=/opt/uv/python
2026-10-14 15:38:16 UTC (buildkit.dockerfile.v0)ENV UV_CACHE_DIR=/opt/uv/cache
2026-10-14 15:38:16 UTC (buildkit.dockerfile.v0)ENV UV_COMPILE_BYTECODE=1
2026-10-14 15:38:17 UTC (buildkit.dockerfile.v0)RUN |9 INSTALL_RUBIN_PRERELEASE=false TARGETPLATFORM=linux/arm64 max_jobs=64 CUDA_VERSION=13.0.3 PYTHON_VERSION=3.12 NCCL_VERSION=2.30.7 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py /bin/sh -c mkdir -p "${UV_PYTHON_INSTALL_DIR}" "${UV_CACHE_DIR}" && chgrp -R 0 /opt/uv && chmod -R g+rwX,a+rX /opt/uv # buildkit
2026-10-14 15:38:18 UTC (buildkit.dockerfile.v0)RUN |9 INSTALL_RUBIN_PRERELEASE=false TARGETPLATFORM=linux/arm64 max_jobs=64 CUDA_VERSION=13.0.3 PYTHON_VERSION=3.12 NCCL_VERSION=2.30.7 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py /bin/sh -c CUDA_MAJOR=$(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
2026-10-14 15:38:18 UTC (buildkit.dockerfile.v0)ENV UV_OVERRIDE=/etc/uv-overrides.txt
2026-10-14 15:38:19 UTC (buildkit.dockerfile.v0)RUN |9 INSTALL_RUBIN_PRERELEASE=false TARGETPLATFORM=linux/arm64 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
2026-10-14 15:38:19 UTC (buildkit.dockerfile.v0)COPY docker/entrypoints/vllm-nonroot-entrypoint.sh /usr/local/bin/vllm-nonroot-entrypoint.sh # buildkit
2026-10-14 15:38:20 UTC (buildkit.dockerfile.v0)RUN |9 INSTALL_RUBIN_PRERELEASE=false TARGETPLATFORM=linux/arm64 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
2026-10-14 15:38:20 UTC (buildkit.dockerfile.v0)ENV VLLM_ENABLE_CUDA_COMPATIBILITY=0
2026-10-14 15:38:20 UTC (buildkit.dockerfile.v0)ARG PYTORCH_CUDA_INDEX_BASE_URL
2026-10-14 15:38:20 UTC (buildkit.dockerfile.v0)COPY requirements/common.txt /tmp/common.txt # buildkit
2026-10-14 15:38:20 UTC (buildkit.dockerfile.v0)COPY requirements/cuda.txt /tmp/requirements-cuda.txt # buildkit
2026-10-14 15:39:43 UTC (buildkit.dockerfile.v0)RUN |10 INSTALL_RUBIN_PRERELEASE=false TARGETPLATFORM=linux/arm64 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; else uv pip install --system -r /tmp/requirements-cuda.txt --extra-index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.'); fi && rm /tmp/requirements-cuda.txt /tmp/common.txt # buildkit
2026-10-14 15:42:11 UTC (buildkit.dockerfile.v0)RUN |10 INSTALL_RUBIN_PRERELEASE=false TARGETPLATFORM=linux/arm64 max_jobs=64 CUDA_VERSION=13.0.3 PYTHON_VERSION=3.12 NCCL_VERSION=2.30.7 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl /bin/sh -c PIP_CACHE_DIR=/opt/pip/cache flashinfer download-kernels # buildkit
2026-10-14 15:42:11 UTC (buildkit.dockerfile.v0)ARG GDRCOPY_CUDA_VERSION=12.8
2026-10-14 15:42:11 UTC (buildkit.dockerfile.v0)ARG GDRCOPY_OS_VERSION=Ubuntu24_04
2026-10-14 15:42:11 UTC (buildkit.dockerfile.v0)ARG TARGETPLATFORM
2026-10-14 15:42:11 UTC (buildkit.dockerfile.v0)COPY tools/install_gdrcopy.sh /tmp/install_gdrcopy.sh # buildkit
2026-10-14 15:42:19 UTC (buildkit.dockerfile.v0)RUN |13 INSTALL_RUBIN_PRERELEASE=false TARGETPLATFORM=linux/arm64 max_jobs=64 CUDA_VERSION=13.0.3 PYTHON_VERSION=3.12 NCCL_VERSION=2.30.7 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl GDRCOPY_CUDA_VERSION=12.8 GDRCOPY_OS_VERSION=Ubuntu24_04 TARGETPLATFORM=linux/arm64 /bin/sh -c set -eux; case "${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
2026-10-14 15:42:19 UTC (buildkit.dockerfile.v0)ARG TIMM_VERSION=>=1.0.17
2026-10-14 15:42:19 UTC (buildkit.dockerfile.v0)ARG RUNAI_MODEL_STREAMER_VERSION=>=0.15.7
2026-10-14 15:42:30 UTC (buildkit.dockerfile.v0)RUN |15 INSTALL_RUBIN_PRERELEASE=false TARGETPLATFORM=linux/arm64 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 GDRCOPY_CUDA_VERSION=12.8 GDRCOPY_OS_VERSION=Ubuntu24_04 TARGETPLATFORM=linux/arm64 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
2026-10-14 15:42:30 UTC (buildkit.dockerfile.v0)ARG PIP_INDEX_URL UV_INDEX_URL
2026-10-14 15:42:30 UTC (buildkit.dockerfile.v0)ARG PIP_EXTRA_INDEX_URL UV_EXTRA_INDEX_URL
2026-10-14 15:42:30 UTC (buildkit.dockerfile.v0)ARG PYTORCH_CUDA_INDEX_BASE_URL
2026-10-14 15:42:30 UTC (buildkit.dockerfile.v0)ARG PIP_KEYRING_PROVIDER UV_KEYRING_PROVIDER
2026-10-14 15:42:30 UTC (buildkit.dockerfile.v0)ARG PYTORCH_NIGHTLY
2026-10-14 15:49:18 UTC (buildkit.dockerfile.v0)COPY /workspace/torch_lib_versions.txt torch_lib_versions.txt # buildkit
2026-10-14 15:57:20 UTC (buildkit.dockerfile.v0)COPY /workspace/dist/wheel.sha256 /tmp/vllm-wheel.sha256 # buildkit
2026-10-14 15:57:39 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 --extra-index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.'); fi # buildkit
2026-10-14 15:57:39 UTC (buildkit.dockerfile.v0)RUN |8 PIP_INDEX_URL= UV_INDEX_URL= PIP_EXTRA_INDEX_URL= UV_EXTRA_INDEX_URL= PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl PIP_KEYRING_PROVIDER=disabled UV_KEYRING_PROVIDER=disabled PYTORCH_NIGHTLY= /bin/sh -c ln -s "$(python3 -c 'import sysconfig; print(sysconfig.get_path("platlib"))')/vllm/vllm-rs" /usr/local/bin/vllm-rs && vllm-rs --version # buildkit
2026-10-14 15:57:40 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
2026-10-14 15:57:40 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
2026-10-14 15:57:40 UTC (buildkit.dockerfile.v0)COPY /tmp/ep_kernels_workspace/dist/wheels.sha256 /tmp/ep-kernels-wheels.sha256 # buildkit
2026-10-14 15:57:41 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
2026-10-14 15:57:41 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
2026-10-14 15:57:41 UTC (buildkit.dockerfile.v0)COPY examples examples # buildkit
2026-10-14 15:57:41 UTC (buildkit.dockerfile.v0)COPY benchmarks benchmarks # buildkit
2026-10-14 15:57:41 UTC (buildkit.dockerfile.v0)COPY ./vllm/collect_env.py . # buildkit
2026-10-14 15:57:41 UTC (buildkit.dockerfile.v0)ARG TARGETPLATFORM
2026-10-14 15:57:41 UTC (buildkit.dockerfile.v0)ARG INSTALL_KV_CONNECTORS=false
2026-10-14 15:57:41 UTC (buildkit.dockerfile.v0)ARG INSTALL_RUBIN_PRERELEASE
2026-10-14 15:57:41 UTC (buildkit.dockerfile.v0)ARG TRITON_INSTALL_FROM_SOURCE_REPO
2026-10-14 15:57:41 UTC (buildkit.dockerfile.v0)ARG CUDA_VERSION
2026-10-14 15:57:41 UTC (buildkit.dockerfile.v0)ARG VLLM_BUILD_COMMIT
2026-10-14 15:57:41 UTC (buildkit.dockerfile.v0)ARG VLLM_BUILD_PIPELINE
2026-10-14 15:57:41 UTC (buildkit.dockerfile.v0)ARG VLLM_BUILD_URL
2026-10-14 15:57:41 UTC (buildkit.dockerfile.v0)ARG VLLM_IMAGE_TAG
2026-10-14 15:57:41 UTC (buildkit.dockerfile.v0)ARG PIP_INDEX_URL UV_INDEX_URL
2026-10-14 15:57:41 UTC (buildkit.dockerfile.v0)ARG PIP_EXTRA_INDEX_URL UV_EXTRA_INDEX_URL
2026-10-14 15:57:41 UTC (buildkit.dockerfile.v0)ENV UV_HTTP_TIMEOUT=500
2026-10-14 15:57:41 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
2026-10-14 15:57:41 UTC (buildkit.dockerfile.v0)ENV TORCH_CUDA_ARCH_LIST=9.0 10.0 10.3 12.0 12.1
2026-10-14 15:58:07 UTC (buildkit.dockerfile.v0)RUN |14 TARGETPLATFORM=linux/arm64 INSTALL_KV_CONNECTORS=true INSTALL_RUBIN_PRERELEASE=false TRITON_INSTALL_FROM_SOURCE_REPO= CUDA_VERSION=13.0.3 VLLM_BUILD_COMMIT= VLLM_BUILD_PIPELINE= VLLM_BUILD_URL= VLLM_IMAGE_TAG= PIP_INDEX_URL= UV_INDEX_URL= PIP_EXTRA_INDEX_URL= UV_EXTRA_INDEX_URL= torch_cuda_arch_list=9.0 10.0 10.3 12.0 12.1 /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==${MOONCAKE_VERSION}"; fi; rm -f /tmp/kv-installed.txt /tmp/kv-constraints.txt; fi # buildkit
2026-10-14 15:58:07 UTC (buildkit.dockerfile.v0)RUN |14 TARGETPLATFORM=linux/arm64 INSTALL_KV_CONNECTORS=true INSTALL_RUBIN_PRERELEASE=false TRITON_INSTALL_FROM_SOURCE_REPO= CUDA_VERSION=13.0.3 VLLM_BUILD_COMMIT= VLLM_BUILD_PIPELINE= VLLM_BUILD_URL= VLLM_IMAGE_TAG= PIP_INDEX_URL= UV_INDEX_URL= PIP_EXTRA_INDEX_URL= UV_EXTRA_INDEX_URL= torch_cuda_arch_list=9.0 10.0 10.3 12.0 12.1 /bin/sh -c if [ "${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
2026-10-14 15:58:07 UTC (buildkit.dockerfile.v0)COPY /tmp/triton_from_source_workspace/dist/wheel.sha256 /tmp/triton-source-wheel.sha256 # buildkit
2026-10-14 15:58:07 UTC (buildkit.dockerfile.v0)COPY tools/install_triton_from_source.sh /tmp/install_triton_from_source.sh # buildkit
2026-10-14 15:58:08 UTC (buildkit.dockerfile.v0)RUN |14 TARGETPLATFORM=linux/arm64 INSTALL_KV_CONNECTORS=true INSTALL_RUBIN_PRERELEASE=false TRITON_INSTALL_FROM_SOURCE_REPO= CUDA_VERSION=13.0.3 VLLM_BUILD_COMMIT= VLLM_BUILD_PIPELINE= VLLM_BUILD_URL= VLLM_IMAGE_TAG= PIP_INDEX_URL= UV_INDEX_URL= PIP_EXTRA_INDEX_URL= UV_EXTRA_INDEX_URL= torch_cuda_arch_list=9.0 10.0 10.3 12.0 12.1 /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: ${CUDA_MAJOR_MINOR}" >&2; exit 1 ;; esac; else bash /tmp/install_triton_from_source.sh /tmp/triton-source-dist /tmp/triton-source-wheel.sha256; fi; fi && rm -f /tmp/install_triton_from_source.sh /tmp/triton-source-wheel.sha256 # buildkit
2026-10-14 15:58:08 UTC (buildkit.dockerfile.v0)ARG BUILD_NIXL
2026-10-14 15:58:09 UTC (buildkit.dockerfile.v0)RUN |15 TARGETPLATFORM=linux/arm64 INSTALL_KV_CONNECTORS=true INSTALL_RUBIN_PRERELEASE=false TRITON_INSTALL_FROM_SOURCE_REPO= CUDA_VERSION=13.0.3 VLLM_BUILD_COMMIT= VLLM_BUILD_PIPELINE= VLLM_BUILD_URL= VLLM_IMAGE_TAG= PIP_INDEX_URL= UV_INDEX_URL= PIP_EXTRA_INDEX_URL= UV_EXTRA_INDEX_URL= torch_cuda_arch_list=9.0 10.0 10.3 12.0 12.1 BUILD_NIXL=false /bin/sh -c set -eu; if [ "${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
2026-10-14 15:58:09 UTC (buildkit.dockerfile.v0)ENV VLLM_USAGE_SOURCE=production-docker-image
2026-10-14 15:58:09 UTC (buildkit.dockerfile.v0)ENV VLLM_BUILD_COMMIT=unknown VLLM_BUILD_PIPELINE=local VLLM_BUILD_URL= VLLM_IMAGE_TAG=local/vllm-openai:dev
2026-10-14 15:58:09 UTC (buildkit.dockerfile.v0)LABEL org.opencontainers.image.source=https://github.com/vllm-project/vllm org.opencontainers.image.revision=unknown org.opencontainers.image.version=local/vllm-openai:dev org.opencontainers.image.url= ai.vllm.build.commit=unknown ai.vllm.build.pipeline=local ai.vllm.build.url= ai.vllm.image.tag=local/vllm-openai:dev
2026-10-14 15:58:09 UTC (buildkit.dockerfile.v0)ENTRYPOINT ["vllm" "serve"]
2026-10-14 15:59:15 UTC (buildkit.dockerfile.v0)LABEL org.opencontainers.image.revision=a34ca64c138ad0360c472ada748b750435b607ae io.inferact.deepgemm.commit=1704143a9f75375d31ba644691645fdf316d4866 io.inferact.flashinfer.commit=6b49d21cf3b56ea3048ee42b15ed050ee7e7f6a6
2026-10-14 15:59:15 UTC (buildkit.dockerfile.v0)COPY wheels /tmp/flashinfer-mpk-wheels # buildkit
2026-10-14 15:59:18 UTC (buildkit.dockerfile.v0)RUN /bin/sh -c uv pip install --system --no-cache av scipy librosa soundfile soxr audioread 'mistral_common[audio]' # buildkit
2026-10-14 16:00:43 UTC (buildkit.dockerfile.v0)RUN /bin/sh -c uv pip install --system --no-cache --reinstall --no-deps /tmp/flashinfer-mpk-wheels/flashinfer_jit_cache*.whl /tmp/flashinfer-mpk-wheels/flashinfer_cubin-*.whl /tmp/flashinfer-mpk-wheels/flashinfer_python-*.whl && rm -rf /tmp/flashinfer-mpk-wheels # buildkit
2026-10-14 16:00:43 UTC (buildkit.dockerfile.v0)COPY verify_runtime.py /tmp/verify_runtime.py # buildkit
2026-10-14 16:00:50 UTC (buildkit.dockerfile.v0)RUN /bin/sh -c python3 /tmp/verify_runtime.py && rm /tmp/verify_runtime.py # buildkit
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.