vllm-openai (sha256:eb8b7cf44e53cb8f6cd7deb5539c1150739942f19ea33e28dfc80c74dd327a68)

Published 2026-08-18 21:31:52 +00:00 by thomas.laerm

Pull the image from the command line:

docker pull git.lukko.de/lukko.de/vllm-openai@sha256:eb8b7cf44e53cb8f6cd7deb5539c1150739942f19ea33e28dfc80c74dd327a68

Digest

sha256:eb8b7cf44e53cb8f6cd7deb5539c1150739942f19ea33e28dfc80c74dd327a68

For more information on the Container registry, see the documentation.

ARG RELEASE

ARG LAUNCHPAD_BUILD_ARCH

LABEL org.opencontainers.image.ref.name=ubuntu

LABEL org.opencontainers.image.version=24.04

ADD file:e67907c77897d27192314f6c4fa0112b6f7dce3e127500516535cc50fe736c92 in /

CMD ["/bin/bash"]

ENV NVARCH=x86_64

ENV NVIDIA_REQUIRE_CUDA=cuda>=13.0 brand=unknown,driver>=535,driver<536 brand=grid,driver>=535,driver<536 brand=tesla,driver>=535,driver<536 brand=nvidia,driver>=535,driver<536 brand=quadro,driver>=535,driver<536 brand=quadrortx,driver>=535,driver<536 brand=nvidiartx,driver>=535,driver<536 brand=vapps,driver>=535,driver<536 brand=vpc,driver>=535,driver<536 brand=vcs,driver>=535,driver<536 brand=vws,driver>=535,driver<536 brand=cloudgaming,driver>=535,driver<536 brand=unknown,driver>=550,driver<551 brand=grid,driver>=550,driver<551 brand=tesla,driver>=550,driver<551 brand=nvidia,driver>=550,driver<551 brand=quadro,driver>=550,driver<551 brand=quadrortx,driver>=550,driver<551 brand=nvidiartx,driver>=550,driver<551 brand=vapps,driver>=550,driver<551 brand=vpc,driver>=550,driver<551 brand=vcs,driver>=550,driver<551 brand=vws,driver>=550,driver<551 brand=cloudgaming,driver>=550,driver<551 brand=unknown,driver>=565,driver<566 brand=grid,driver>=565,driver<566 brand=tesla,driver>=565,driver<566 brand=nvidia,driver>=565,driver<566 brand=quadro,driver>=565,driver<566 brand=quadrortx,driver>=565,driver<566 brand=nvidiartx,driver>=565,driver<566 brand=vapps,driver>=565,driver<566 brand=vpc,driver>=565,driver<566 brand=vcs,driver>=565,driver<566 brand=vws,driver>=565,driver<566 brand=cloudgaming,driver>=565,driver<566 brand=unknown,driver>=570,driver<571 brand=grid,driver>=570,driver<571 brand=tesla,driver>=570,driver<571 brand=nvidia,driver>=570,driver<571 brand=quadro,driver>=570,driver<571 brand=quadrortx,driver>=570,driver<571 brand=nvidiartx,driver>=570,driver<571 brand=vapps,driver>=570,driver<571 brand=vpc,driver>=570,driver<571 brand=vcs,driver>=570,driver<571 brand=vws,driver>=570,driver<571 brand=cloudgaming,driver>=570,driver<571 brand=unknown,driver>=575,driver<576 brand=grid,driver>=575,driver<576 brand=tesla,driver>=575,driver<576 brand=nvidia,driver>=575,driver<576 brand=quadro,driver>=575,driver<576 brand=quadrortx,driver>=575,driver<576 brand=nvidiartx,driver>=575,driver<576 brand=vapps,driver>=575,driver<576 brand=vpc,driver>=575,driver<576 brand=vcs,driver>=575,driver<576 brand=vws,driver>=575,driver<576 brand=cloudgaming,driver>=575,driver<576

ENV NV_CUDA_CUDART_VERSION=13.0.88-1

ARG TARGETARCH

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

RUN |1 TARGETARCH=amd64 /bin/sh -c apt-get update && apt-get install -y --no-install-recommends gnupg2 curl ca-certificates && curl -fsSL https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2404/${NVARCH}/3bf863cc.pub | apt-key add - && echo "deb https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2404/${NVARCH} /" > /etc/apt/sources.list.d/cuda.list && apt-get purge --autoremove -y curl && rm -rf /var/lib/apt/lists/* # buildkit

ENV CUDA_VERSION=13.0.1

RUN |1 TARGETARCH=amd64 /bin/sh -c apt-get update && apt-get install -y --no-install-recommends cuda-cudart-13-0=${NV_CUDA_CUDART_VERSION} cuda-compat-13-0 && rm -rf /var/lib/apt/lists/* # buildkit

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

ENV PATH=/usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin

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

COPY NGC-DL-CONTAINER-LICENSE / # buildkit

ENV NVIDIA_VISIBLE_DEVICES=all

ENV NVIDIA_DRIVER_CAPABILITIES=compute,utility

ARG CUDA_VERSION=13.0.1

ARG PYTHON_VERSION=3.12

ARG NCCL_VERSION=2.30.7

ARG DEADSNAKES_MIRROR_URL

ARG DEADSNAKES_GPGKEY_URL

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

ENV DEBIAN_FRONTEND=noninteractive

WORKDIR /vllm-workspace

RUN |6 CUDA_VERSION=13.0.1 PYTHON_VERSION=3.12 NCCL_VERSION=2.30.7 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py /bin/sh -c PYTHON_VERSION_STR=$(echo ${PYTHON_VERSION} | sed 's/\.//g') && echo "export PYTHON_VERSION_STR=${PYTHON_VERSION_STR}" >> /etc/environment # buildkit

RUN |6 CUDA_VERSION=13.0.1 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 patch sudo ffmpeg libsm6 libxext6 libgl1 && if [ ! -z ${DEADSNAKES_MIRROR_URL} ] ; then if [ ! -z "${DEADSNAKES_GPGKEY_URL}" ] ; then mkdir -p -m 0755 /etc/apt/keyrings ; curl -L ${DEADSNAKES_GPGKEY_URL} | gpg --dearmor > /etc/apt/keyrings/deadsnakes.gpg ; sudo chmod 644 /etc/apt/keyrings/deadsnakes.gpg ; echo "deb [signed-by=/etc/apt/keyrings/deadsnakes.gpg] ${DEADSNAKES_MIRROR_URL} $(lsb_release -cs) main" > /etc/apt/sources.list.d/deadsnakes.list ; fi ; else for i in 1 2 3; do add-apt-repository -y ppa:deadsnakes/ppa && break || { echo "Attempt $i failed, retrying in 5s..."; sleep 5; }; done ; fi && apt-get update -y && apt-get install -y --no-install-recommends python${PYTHON_VERSION} python${PYTHON_VERSION}-dev python${PYTHON_VERSION}-venv libibverbs-dev && rm -rf /var/lib/apt/lists/* && update-alternatives --install /usr/bin/python3 python3 /usr/bin/python${PYTHON_VERSION} 1 && update-alternatives --set python3 /usr/bin/python${PYTHON_VERSION} && ln -sf /usr/bin/python${PYTHON_VERSION}-config /usr/bin/python3-config && rm -f /usr/lib/python${PYTHON_VERSION}/EXTERNALLY-MANAGED && curl -sS ${GET_PIP_URL} | python${PYTHON_VERSION} && python3 --version && python3 -m pip --version # buildkit

RUN |6 CUDA_VERSION=13.0.1 PYTHON_VERSION=3.12 NCCL_VERSION=2.30.7 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py /bin/sh -c CUDA_VERSION_DASH=$(echo $CUDA_VERSION | cut -d. -f1,2 | tr '.' '-') && apt-get update -y && apt-get install -y --no-install-recommends --allow-change-held-packages cuda-nvcc-${CUDA_VERSION_DASH} cuda-cudart-${CUDA_VERSION_DASH} cuda-nvrtc-${CUDA_VERSION_DASH} cuda-cuobjdump-${CUDA_VERSION_DASH} libcurand-dev-${CUDA_VERSION_DASH} libcublas-dev-${CUDA_VERSION_DASH} libnuma-dev numactl && rm -rf /var/lib/apt/lists/* # buildkit

ENV UV_HTTP_TIMEOUT=500

ENV UV_INDEX_STRATEGY=unsafe-best-match

ENV UV_LINK_MODE=copy

ENV UV_PYTHON_INSTALL_DIR=/opt/uv/python

ENV UV_CACHE_DIR=/opt/uv/cache

RUN |6 CUDA_VERSION=13.0.1 PYTHON_VERSION=3.12 NCCL_VERSION=2.30.7 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py /bin/sh -c CUDA_MAJOR=$(echo $CUDA_VERSION | cut -d. -f1) && if [ -n "$NCCL_VERSION" ]; then echo "nvidia-nccl-cu${CUDA_MAJOR}==${NCCL_VERSION}" > /etc/uv-overrides.txt; else touch /etc/uv-overrides.txt; fi # buildkit

ENV UV_OVERRIDE=/etc/uv-overrides.txt

RUN |6 CUDA_VERSION=13.0.1 PYTHON_VERSION=3.12 NCCL_VERSION=2.30.7 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py /bin/sh -c useradd --uid 2000 --gid 0 --create-home --home-dir /home/vllm --shell /bin/bash vllm && mkdir -p /home/vllm/.cache /home/vllm/.config && chown -R 2000:0 /home/vllm && chmod -R g+rwX /home/vllm && chgrp 0 /etc/passwd /etc/group && chmod g=u /etc/passwd /etc/group # buildkit

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

ENV VLLM_ENABLE_CUDA_COMPATIBILITY=0

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

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

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

RUN |7 CUDA_VERSION=13.0.1 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 [ "$(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 && 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 '.') && rm /tmp/requirements-cuda.txt /tmp/common.txt # buildkit

ARG FLASHINFER_VERSION=0.6.17

COPY docker/patches/flashinfer-0.6.17-pr-4266.patch docker/patches/flashinfer-0.6.17-pr-4455.patch /tmp/ # buildkit

RUN |8 CUDA_VERSION=13.0.1 PYTHON_VERSION=3.12 NCCL_VERSION=2.30.7 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl FLASHINFER_VERSION=0.6.17 /bin/sh -c set -eux; if [ "${FLASHINFER_VERSION}" = "0.6.17" ]; then FLASHINFER_GEMM_FILE=$(find /usr/local/lib -type f -path '*/flashinfer/gemm/gemm_base.py' -print -quit); test -n "${FLASHINFER_GEMM_FILE}"; FLASHINFER_SITE_PACKAGES=${FLASHINFER_GEMM_FILE%/flashinfer/gemm/gemm_base.py}; for FLASHINFER_PATCH in /tmp/flashinfer-0.6.17-pr-4266.patch /tmp/flashinfer-0.6.17-pr-4455.patch; do patch --batch --forward --fuzz=0 --directory="${FLASHINFER_SITE_PACKAGES}" --strip=1 < "${FLASHINFER_PATCH}"; done; fi; rm /tmp/flashinfer-0.6.17-pr-4266.patch /tmp/flashinfer-0.6.17-pr-4455.patch # buildkit

ARG GDRCOPY_CUDA_VERSION=12.8

ARG GDRCOPY_OS_VERSION=Ubuntu24_04

ARG TARGETPLATFORM=linux/amd64

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

RUN |11 CUDA_VERSION=13.0.1 PYTHON_VERSION=3.12 NCCL_VERSION=2.30.7 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl FLASHINFER_VERSION=0.6.17 GDRCOPY_CUDA_VERSION=12.8 GDRCOPY_OS_VERSION=Ubuntu24_04 TARGETPLATFORM=linux/amd64 /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

ARG TIMM_VERSION=>=1.0.17

ARG RUNAI_MODEL_STREAMER_VERSION=>=0.15.7

RUN |13 CUDA_VERSION=13.0.1 PYTHON_VERSION=3.12 NCCL_VERSION=2.30.7 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl FLASHINFER_VERSION=0.6.17 GDRCOPY_CUDA_VERSION=12.8 GDRCOPY_OS_VERSION=Ubuntu24_04 TARGETPLATFORM=linux/amd64 TIMM_VERSION=>=1.0.17 RUNAI_MODEL_STREAMER_VERSION=>=0.15.7 /bin/sh -c uv pip install --system accelerate 'modelscope<1.38' "timm${TIMM_VERSION}" "runai-model-streamer[s3,gcs,azure]${RUNAI_MODEL_STREAMER_VERSION}" # buildkit

ARG PIP_INDEX_URL UV_INDEX_URL=

ARG PIP_EXTRA_INDEX_URL UV_EXTRA_INDEX_URL=

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

ARG PIP_KEYRING_PROVIDER=disabled UV_KEYRING_PROVIDER=disabled

ARG PYTORCH_NIGHTLY

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

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

RUN |20 CUDA_VERSION=13.0.1 PYTHON_VERSION=3.12 NCCL_VERSION=2.30.7 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl FLASHINFER_VERSION=0.6.17 GDRCOPY_CUDA_VERSION=12.8 GDRCOPY_OS_VERSION=Ubuntu24_04 TARGETPLATFORM=linux/amd64 TIMM_VERSION=>=1.0.17 RUNAI_MODEL_STREAMER_VERSION=>=0.15.7 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

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

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

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

COPY examples examples # buildkit

COPY benchmarks benchmarks # buildkit

COPY ./vllm/collect_env.py . # buildkit

ARG TARGETPLATFORM=linux/amd64

ARG INSTALL_KV_CONNECTORS=true

ARG CUDA_VERSION=13.0.1

ARG VLLM_BUILD_COMMIT=3a0914114705fa38d4c3171d0746c1a6b6f10209

ARG VLLM_BUILD_PIPELINE

ARG VLLM_BUILD_URL

ARG VLLM_IMAGE_TAG=inferactinc/dev:wtn-3a09141-x86_64-cu13.0.1

ARG PIP_INDEX_URL UV_INDEX_URL=

ARG PIP_EXTRA_INDEX_URL UV_EXTRA_INDEX_URL=

ENV UV_HTTP_TIMEOUT=500

ARG torch_cuda_arch_list=7.5 8.0 8.6 8.9 9.0 10.0 11.0 12.0

ENV TORCH_CUDA_ARCH_LIST=7.5 8.0 8.6 8.9 9.0 10.0 11.0 12.0

RUN |26 CUDA_VERSION=13.0.1 PYTHON_VERSION=3.12 NCCL_VERSION=2.30.7 DEADSNAKES_MIRROR_URL= DEADSNAKES_GPGKEY_URL= GET_PIP_URL=https://bootstrap.pypa.io/get-pip.py PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl FLASHINFER_VERSION=0.6.17 GDRCOPY_CUDA_VERSION=12.8 GDRCOPY_OS_VERSION=Ubuntu24_04 TARGETPLATFORM=linux/amd64 TIMM_VERSION=>=1.0.17 RUNAI_MODEL_STREAMER_VERSION=>=0.15.7 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 VLLM_BUILD_COMMIT=3a0914114705fa38d4c3171d0746c1a6b6f10209 VLLM_BUILD_PIPELINE= VLLM_BUILD_URL= VLLM_IMAGE_TAG=inferactinc/dev:wtn-3a09141-x86_64-cu13.0.1 torch_cuda_arch_list=7.5 8.0 8.6 8.9 9.0 10.0 11.0 12.0 /bin/sh -c CUDA_MAJOR="${CUDA_VERSION%%.*}"; CUDA_VERSION_DASH=$(echo $CUDA_VERSION | cut -d. -f1,2 | tr '.' '-'); CUDA_HOME=/usr/local/cuda; BUILD_PKGS="libcusparse-dev-${CUDA_VERSION_DASH} libcublas-dev-${CUDA_VERSION_DASH} libcusolver-dev-${CUDA_VERSION_DASH}"; if [ "$INSTALL_KV_CONNECTORS" = "true" ]; then uv pip install --system -r /tmp/kv_connectors.txt --no-build || ( apt-get update -y && apt-get install -y --no-install-recommends --allow-change-held-packages ${BUILD_PKGS} && uv pip install --system -r /tmp/kv_connectors.txt --no-build-isolation && apt-get purge -y ${BUILD_PKGS} && rm -rf /var/lib/apt/lists/* ); uv pip install --system --force-reinstall --no-deps nixl-cu${CUDA_MAJOR} && MOONCAKE_VERSION=$(python3 -c "import importlib.metadata as m; print(m.version('mooncake-transfer-engine'))" 2>/dev/null || true) && if [ "${CUDA_MAJOR}" = "13" ] && [ -n "${MOONCAKE_VERSION}" ]; then uv pip uninstall --system mooncake-transfer-engine 2>/dev/null || true; uv pip install --system "mooncake-transfer-engine-cuda13==${MOONCAKE_VERSION}"; fi; fi # buildkit

ENV VLLM_USAGE_SOURCE=production-docker-image

ENV VLLM_BUILD_COMMIT=3a0914114705fa38d4c3171d0746c1a6b6f10209 VLLM_BUILD_PIPELINE=local VLLM_BUILD_URL= VLLM_IMAGE_TAG=inferactinc/dev:wtn-3a09141-x86_64-cu13.0.1

LABEL org.opencontainers.image.source=https://github.com/vllm-project/vllm org.opencontainers.image.revision=3a0914114705fa38d4c3171d0746c1a6b6f10209 org.opencontainers.image.version=inferactinc/dev:wtn-3a09141-x86_64-cu13.0.1 org.opencontainers.image.url= ai.vllm.build.commit=3a0914114705fa38d4c3171d0746c1a6b6f10209 ai.vllm.build.pipeline=local ai.vllm.build.url= ai.vllm.image.tag=inferactinc/dev:wtn-3a09141-x86_64-cu13.0.1

ENTRYPOINT ["vllm" "serve"]

LABEL org.lmcache.patch=kv_cache_group_edits: vLLM 0.26.0 fused KV layout (LMCache PR #4253)

COPY lmcache/integration/vllm/kv_cache_group_edits.py /tmp/kv_cache_group_edits.py # buildkit

RUN /bin/sh -c set -eux; py=$(command -v python3 || command -v python); lmcache_dir=$("$py" -c "import lmcache, os; print(os.path.dirname(lmcache.__file__))"); cp /tmp/kv_cache_group_edits.py "$lmcache_dir/integration/vllm/kv_cache_group_edits.py"; find "$lmcache_dir/integration/vllm" -name "kv_cache_group_edits*.pyc" -delete; rm /tmp/kv_cache_group_edits.py; grep -n "_FUSED_KV_NDIM" "$lmcache_dir/integration/vllm/kv_cache_group_edits.py" # buildkit

Key	Value
ai.vllm.build.commit	3a0914114705fa38d4c3171d0746c1a6b6f10209
ai.vllm.build.pipeline	local
ai.vllm.build.url
ai.vllm.image.tag	inferactinc/dev:wtn-3a09141-x86_64-cu13.0.1
maintainer	NVIDIA CORPORATION <cudatools@nvidia.com>
org.lmcache.patch	kv_cache_group_edits: vLLM 0.26.0 fused KV layout (LMCache PR #4253)
org.opencontainers.image.ref.name	ubuntu
org.opencontainers.image.revision	3a0914114705fa38d4c3171d0746c1a6b6f10209
org.opencontainers.image.source	https://github.com/vllm-project/vllm
org.opencontainers.image.url
org.opencontainers.image.version	inferactinc/dev:wtn-3a09141-x86_64-cu13.0.1

Details

Container

2026-08-18 21:31:52 +00:00

OCI / Docker

linux/amd64

Repository website

7.1 GiB

Versions (1) View all

qwen38-lmcache-patch

2026-08-18

vllm-openai (sha256:eb8b7cf44e53cb8f6cd7deb5539c1150739942f19ea33e28dfc80c74dd327a68)

Installation

Image layers

Labels