docker.io/roboflow/roboflow-inference-server-gpu:latest - 镜像下载

ℹ️

注意：这是一个 latest 标签镜像

latest 并不代表最新版本，本站同步时间存在延迟，无法保证此镜像与上游最新版本一致。
生产环境建议使用明确的版本号（如 v1.2.3），避免因版本不一致导致问题。了解更多 →

docker.io/roboflow/roboflow-inference-server-gpu:latest

linux/amd64 docker.io

该Docker镜像是Roboflow提供的推理服务器GPU版本，用于在GPU加速环境下运行计算机视觉模型的推理任务，支持高效处理图像或视频输入并输出模型预测结果。

362

浏览次数

15.06GB

镜像大小

源镜像

docker.io/roboflow/roboflow-inference-server-gpu:latest

国内镜像

swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/roboflow/roboflow-inference-server-gpu:latest

镜像ID

sha256:4ee373e920ef591f32057d7fca5e8f121189734acdaf87c4269dae0ff5891096

镜像 TAG

latest

镜像大小

15.06GB

平台架构

linux/amd64

镜像源

docker.io

项目信息

Hub 主页所有 TAG

CMD

启动入口

/bin/sh -c uvicorn gpu_http:app --workers $NUM_WORKERS --host $HOST --port $PORT

工作目录

/app/

OS/平台

linux/amd64

镜像创建

2026-01-09T16:57:56.233329141Z

同步时间

2026-01-12 02:59

浏览量

362 次

贡献者

⚙️ 环境变量 40

Key	Value
`PATH=/usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin`	`0`
`NVARCH=x86_64`	`1`
NVIDIA_REQUIRE_CUDA=cuda>=12.4 brand=tesla,driver>=470,driver<471 brand=unknown,driver>=470,driver<471 brand=nvidia,driver>=470,driver<471 brand=nvidiartx,driver>=470,driver<471 brand=geforce,driver>=470,driver<471 brand=geforcertx,driver>=470,driver<471 brand=quadro,driver>=470,driver<471 brand=quadrortx,driver>=470,driver<471 brand=titan,driver>=470,driver<471 brand=titanrtx,driver>=470,driver<471 brand=tesla,driver>=525,driver<526 brand=unknown,driver>=525,driver<526 brand=nvidia,driver>=525,driver<526 brand=nvidiartx,driver>=525,driver<526 brand=geforce,driver>=525,driver<526 brand=geforcertx,driver>=525,driver<526 brand=quadro,driver>=525,driver<526 brand=quadrortx,driver>=525,driver<526 brand=titan,driver>=525,driver<526 brand=titanrtx,driver>=525,driver<526 brand=tesla,driver>=535,driver<536 brand=unknown,driver>=535,driver<536 brand=nvidia,driver>=535,driver<536 brand=nvidiartx,driver>=535,driver<536 brand=geforce,driver>=535,driver<536 brand=geforcertx,driver>=535,driver<536 brand=quadro,driver>=535,driver<536 brand=quadrortx,driver>=535,driver<536 brand=titan,driver>=535,driver<536 brand=titanrtx,driver>=535,driver<536	`2`
`NV_CUDA_CUDART_VERSION=12.4.127-1`	`3`
`NV_CUDA_COMPAT_PACKAGE=cuda-compat-12-4`	`4`
`CUDA_VERSION=12.4.1`	`5`
`LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64`	`6`
`NVIDIA_VISIBLE_DEVICES=all`	`7`
`NVIDIA_DRIVER_CAPABILITIES=compute,utility`	`8`
`NV_CUDA_LIB_VERSION=12.4.1-1`	`9`
`NV_NVTX_VERSION=12.4.127-1`	`10`
`NV_LIBNPP_VERSION=12.2.5.30-1`	`11`
`NV_LIBNPP_PACKAGE=libnpp-12-4=12.2.5.30-1`	`12`
`NV_LIBCUSPARSE_VERSION=12.3.1.170-1`	`13`
`NV_LIBCUBLAS_PACKAGE_NAME=libcublas-12-4`	`14`
`NV_LIBCUBLAS_VERSION=12.4.5.8-1`	`15`
`NV_LIBCUBLAS_PACKAGE=libcublas-12-4=12.4.5.8-1`	`16`
`NV_LIBNCCL_PACKAGE_NAME=libnccl2`	`17`
`NV_LIBNCCL_PACKAGE_VERSION=2.21.5-1`	`18`
`NCCL_VERSION=2.21.5-1`	`19`
`NV_LIBNCCL_PACKAGE=libnccl2=2.21.5-1+cuda12.4`	`20`
`NVIDIA_PRODUCT_NAME=CUDA`	`21`
`NV_CUDNN_VERSION=9.1.0.70-1`	`22`
`NV_CUDNN_PACKAGE_NAME=libcudnn9-cuda-12`	`23`
`NV_CUDNN_PACKAGE=libcudnn9-cuda-12=9.1.0.70-1`	`24`
`VERSION_CHECK_MODE=continuous`	`25`
`PROJECT=roboflow-platform`	`26`
`NUM_WORKERS=1`	`27`
`HOST=0.0.0.0`	`28`
`PORT=9001`	`29`
`WORKFLOWS_STEP_EXECUTION_MODE=local`	`30`
`WORKFLOWS_MAX_CONCURRENT_STEPS=4`	`31`
`API_LOGGING_ENABLED=True`	`32`
`LMM_ENABLED=True`	`33`
`CORE_MODEL_SAM2_ENABLED=True`	`34`
`CORE_MODEL_SAM3_ENABLED=True`	`35`
`CORE_MODEL_OWLV2_ENABLED=True`	`36`
`ENABLE_STREAM_API=True`	`37`
`ENABLE_PROMETHEUS=True`	`38`
`STREAM_API_PRELOADED_PROCESSES=2`	`39`

🏷️ 镜像标签 4

Key	Value
`9.1.0.70-1`	`com.nvidia.cudnn.version`
`NVIDIA CORPORATION <cudatools@nvidia.com>`	`maintainer`
`ubuntu`	`org.opencontainers.image.ref.name`
`22.04`	`org.opencontainers.image.version`

Chatgpt|Claude一站式支持平台提供先进的AI镜像服务，助你在国内优雅的使用Chatgpt和Claude等AI服务

无权限下载？点我修复生成 Docker Run 命令生成 Kubernetes YAML

Docker拉取命令

docker pull swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/roboflow/roboflow-inference-server-gpu:latest
docker tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/roboflow/roboflow-inference-server-gpu:latest  docker.io/roboflow/roboflow-inference-server-gpu:latest

Containerd拉取命令

ctr images pull swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/roboflow/roboflow-inference-server-gpu:latest
ctr images tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/roboflow/roboflow-inference-server-gpu:latest  docker.io/roboflow/roboflow-inference-server-gpu:latest

Shell快速替换命令

sed -i 's#roboflow/roboflow-inference-server-gpu:latest#swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/roboflow/roboflow-inference-server-gpu:latest#' deployment.yaml

Ansible快速分发-Docker

#ansible k8s -m shell -a 'docker pull swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/roboflow/roboflow-inference-server-gpu:latest && docker tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/roboflow/roboflow-inference-server-gpu:latest  docker.io/roboflow/roboflow-inference-server-gpu:latest'

Ansible快速分发-Containerd

#ansible k8s -m shell -a 'ctr images pull swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/roboflow/roboflow-inference-server-gpu:latest && ctr images tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/roboflow/roboflow-inference-server-gpu:latest  docker.io/roboflow/roboflow-inference-server-gpu:latest'

镜像构建历史


# 2026-01-10 00:57:56  0.00B 配置容器启动时运行的命令
ENTRYPOINT ["/bin/sh" "-c" "uvicorn gpu_http:app --workers $NUM_WORKERS --host $HOST --port $PORT"]
                        
# 2026-01-10 00:57:56  0.00B 设置环境变量 STREAM_API_PRELOADED_PROCESSES
ENV STREAM_API_PRELOADED_PROCESSES=2
                        
# 2026-01-10 00:57:56  0.00B 设置环境变量 ENABLE_PROMETHEUS
ENV ENABLE_PROMETHEUS=True
                        
# 2026-01-10 00:57:56  0.00B 设置环境变量 ENABLE_STREAM_API
ENV ENABLE_STREAM_API=True
                        
# 2026-01-10 00:57:56  0.00B 设置环境变量 CORE_MODEL_OWLV2_ENABLED
ENV CORE_MODEL_OWLV2_ENABLED=True
                        
# 2026-01-10 00:57:56  0.00B 设置环境变量 CORE_MODEL_SAM3_ENABLED
ENV CORE_MODEL_SAM3_ENABLED=True
                        
# 2026-01-10 00:57:56  0.00B 设置环境变量 CORE_MODEL_SAM2_ENABLED
ENV CORE_MODEL_SAM2_ENABLED=True
                        
# 2026-01-10 00:57:56  0.00B 设置环境变量 LMM_ENABLED
ENV LMM_ENABLED=True
                        
# 2026-01-10 00:57:56  0.00B 设置环境变量 API_LOGGING_ENABLED
ENV API_LOGGING_ENABLED=True
                        
# 2026-01-10 00:57:56  0.00B 设置环境变量 WORKFLOWS_MAX_CONCURRENT_STEPS
ENV WORKFLOWS_MAX_CONCURRENT_STEPS=4
                        
# 2026-01-10 00:57:56  0.00B 设置环境变量 WORKFLOWS_STEP_EXECUTION_MODE
ENV WORKFLOWS_STEP_EXECUTION_MODE=local
                        
# 2026-01-10 00:57:56  0.00B 设置环境变量 PORT
ENV PORT=9001
                        
# 2026-01-10 00:57:56  0.00B 设置环境变量 HOST
ENV HOST=0.0.0.0
                        
# 2026-01-10 00:57:56  0.00B 设置环境变量 NUM_WORKERS
ENV NUM_WORKERS=1
                        
# 2026-01-10 00:57:56  0.00B 设置环境变量 PROJECT
ENV PROJECT=roboflow-platform
                        
# 2026-01-10 00:57:56  0.00B 设置环境变量 VERSION_CHECK_MODE
ENV VERSION_CHECK_MODE=continuous
                        
# 2026-01-10 00:57:56  1.68KB 复制新文件或目录到容器中
COPY docker/config/gpu_http.py gpu_http.py # buildkit
                        
# 2026-01-10 00:57:56  10.49MB 复制新文件或目录到容器中
COPY inference inference # buildkit
                        
# 2026-01-10 00:57:55  0.00B 设置工作目录为/app/
WORKDIR /app/
                        
# 2026-01-10 00:57:55  12.03MB 复制新文件或目录到容器中
COPY examples/notebooks . # buildkit
                        
# 2026-01-10 00:57:55  0.00B 设置工作目录为/notebooks
WORKDIR /notebooks
                        
# 2026-01-10 00:57:55  20.58MB 执行命令并创建新的镜像层
RUN /bin/sh -c pip3 install --no-cache-dir dist/inference_cli*.whl dist/inference_core*.whl dist/inference_gpu*.whl dist/inference_sdk*.whl "setuptools<=75.5.0" # buildkit
                        
# 2026-01-10 00:57:49  31.18MB 执行命令并创建新的镜像层
RUN /bin/sh -c /bin/make create_wheels_for_gpu_notebook # buildkit
                        
# 2026-01-10 00:57:38  16.00B 执行命令并创建新的镜像层
RUN /bin/sh -c ln -s /usr/bin/python3 /usr/bin/python # buildkit
                        
# 2026-01-10 00:57:38  139.27MB 复制新文件或目录到容器中
COPY . . # buildkit
                        
# 2026-01-06 23:07:55  0.00B 设置工作目录为/build
WORKDIR /build
                        
# 2026-01-06 23:07:54  2.46GB 执行命令并创建新的镜像层
RUN /bin/sh -c set -eux;     rm -rf /var/lib/apt/lists/*; apt-get clean;     dpkg -i /tmp/cuda-keyring.deb || true;     rm -f /tmp/cuda-keyring.deb;     apt-get update -y;     DEBIAN_FRONTEND=noninteractive apt-get install -y         libxext6         libopencv-dev         uvicorn         python3-pip         git         libgdal-dev         libvips-dev         wget         rustc         cargo;     rm -rf /var/lib/apt/lists/* # buildkit
                        
# 2026-01-06 23:05:30  4.33KB 复制文件或目录到容器中
ADD https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/x86_64/cuda-keyring_1.1-1_all.deb /tmp/cuda-keyring.deb # buildkit
                        
# 2026-01-06 23:05:30  56.13MB 复制新文件或目录到容器中
COPY /usr/local/bin /usr/local/bin # buildkit
                        
# 2026-01-06 23:05:29  9.00GB 复制新文件或目录到容器中
COPY /usr/local/lib/python3.10 /usr/local/lib/python3.10 # buildkit
                        
# 2025-12-11 02:03:58  0.00B 设置工作目录为/app
WORKDIR /app
                        
# 2024-04-23 08:07:03  1.02GB 执行命令并创建新的镜像层
RUN |1 TARGETARCH=amd64 /bin/sh -c apt-get update && apt-get install -y --no-install-recommends     ${NV_CUDNN_PACKAGE}     && apt-mark hold ${NV_CUDNN_PACKAGE_NAME}     && rm -rf /var/lib/apt/lists/* # buildkit
                        
# 2024-04-23 08:07:03  0.00B 添加元数据标签
LABEL com.nvidia.cudnn.version=9.1.0.70-1
                        
# 2024-04-23 08:07:03  0.00B 添加元数据标签
LABEL maintainer=NVIDIA CORPORATION <cudatools@nvidia.com>
                        
# 2024-04-23 08:07:03  0.00B 定义构建参数
ARG TARGETARCH
                        
# 2024-04-23 08:07:03  0.00B 设置环境变量 NV_CUDNN_PACKAGE
ENV NV_CUDNN_PACKAGE=libcudnn9-cuda-12=9.1.0.70-1
                        
# 2024-04-23 08:07:03  0.00B 设置环境变量 NV_CUDNN_PACKAGE_NAME
ENV NV_CUDNN_PACKAGE_NAME=libcudnn9-cuda-12
                        
# 2024-04-23 08:07:03  0.00B 设置环境变量 NV_CUDNN_VERSION
ENV NV_CUDNN_VERSION=9.1.0.70-1
                        
# 2024-04-23 07:46:26  0.00B 配置容器启动时运行的命令
ENTRYPOINT ["/opt/nvidia/nvidia_entrypoint.sh"]
                        
# 2024-04-23 07:46:26  0.00B 设置环境变量 NVIDIA_PRODUCT_NAME
ENV NVIDIA_PRODUCT_NAME=CUDA
                        
# 2024-04-23 07:46:26  2.53KB 复制新文件或目录到容器中
COPY nvidia_entrypoint.sh /opt/nvidia/ # buildkit
                        
# 2024-04-23 07:46:26  3.06KB 复制新文件或目录到容器中
COPY entrypoint.d/ /opt/nvidia/entrypoint.d/ # buildkit
                        
# 2024-04-23 07:46:26  263.02KB 执行命令并创建新的镜像层
RUN |1 TARGETARCH=amd64 /bin/sh -c apt-mark hold ${NV_LIBCUBLAS_PACKAGE_NAME} ${NV_LIBNCCL_PACKAGE_NAME} # buildkit
                        
# 2024-04-23 07:46:26  2.05GB 执行命令并创建新的镜像层
RUN |1 TARGETARCH=amd64 /bin/sh -c apt-get update && apt-get install -y --no-install-recommends     cuda-libraries-12-4=${NV_CUDA_LIB_VERSION}     ${NV_LIBNPP_PACKAGE}     cuda-nvtx-12-4=${NV_NVTX_VERSION}     libcusparse-12-4=${NV_LIBCUSPARSE_VERSION}     ${NV_LIBCUBLAS_PACKAGE}     ${NV_LIBNCCL_PACKAGE}     && rm -rf /var/lib/apt/lists/* # buildkit
                        
# 2024-04-23 07:46:26  0.00B 添加元数据标签
LABEL maintainer=NVIDIA CORPORATION <cudatools@nvidia.com>
                        
# 2024-04-23 07:46:26  0.00B 定义构建参数
ARG TARGETARCH
                        
# 2024-04-23 07:46:26  0.00B 设置环境变量 NV_LIBNCCL_PACKAGE
ENV NV_LIBNCCL_PACKAGE=libnccl2=2.21.5-1+cuda12.4
                        
# 2024-04-23 07:46:26  0.00B 设置环境变量 NCCL_VERSION
ENV NCCL_VERSION=2.21.5-1
                        
# 2024-04-23 07:46:26  0.00B 设置环境变量 NV_LIBNCCL_PACKAGE_VERSION
ENV NV_LIBNCCL_PACKAGE_VERSION=2.21.5-1
                        
# 2024-04-23 07:46:26  0.00B 设置环境变量 NV_LIBNCCL_PACKAGE_NAME
ENV NV_LIBNCCL_PACKAGE_NAME=libnccl2
                        
# 2024-04-23 07:46:26  0.00B 设置环境变量 NV_LIBCUBLAS_PACKAGE
ENV NV_LIBCUBLAS_PACKAGE=libcublas-12-4=12.4.5.8-1
                        
# 2024-04-23 07:46:26  0.00B 设置环境变量 NV_LIBCUBLAS_VERSION
ENV NV_LIBCUBLAS_VERSION=12.4.5.8-1
                        
# 2024-04-23 07:46:26  0.00B 设置环境变量 NV_LIBCUBLAS_PACKAGE_NAME
ENV NV_LIBCUBLAS_PACKAGE_NAME=libcublas-12-4
                        
# 2024-04-23 07:46:26  0.00B 设置环境变量 NV_LIBCUSPARSE_VERSION
ENV NV_LIBCUSPARSE_VERSION=12.3.1.170-1
                        
# 2024-04-23 07:46:26  0.00B 设置环境变量 NV_LIBNPP_PACKAGE
ENV NV_LIBNPP_PACKAGE=libnpp-12-4=12.2.5.30-1
                        
# 2024-04-23 07:46:26  0.00B 设置环境变量 NV_LIBNPP_VERSION
ENV NV_LIBNPP_VERSION=12.2.5.30-1
                        
# 2024-04-23 07:46:26  0.00B 设置环境变量 NV_NVTX_VERSION
ENV NV_NVTX_VERSION=12.4.127-1
                        
# 2024-04-23 07:46:26  0.00B 设置环境变量 NV_CUDA_LIB_VERSION
ENV NV_CUDA_LIB_VERSION=12.4.1-1
                        
# 2024-04-23 07:42:28  0.00B 设置环境变量 NVIDIA_DRIVER_CAPABILITIES
ENV NVIDIA_DRIVER_CAPABILITIES=compute,utility
                        
# 2024-04-23 07:42:28  0.00B 设置环境变量 NVIDIA_VISIBLE_DEVICES
ENV NVIDIA_VISIBLE_DEVICES=all
                        
# 2024-04-23 07:42:28  17.29KB 复制新文件或目录到容器中
COPY NGC-DL-CONTAINER-LICENSE / # buildkit
                        
# 2024-04-23 07:42:28  0.00B 设置环境变量 LD_LIBRARY_PATH
ENV LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64
                        
# 2024-04-23 07:42:28  0.00B 设置环境变量 PATH
ENV PATH=/usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin
                        
# 2024-04-23 07:42:28  46.00B 执行命令并创建新的镜像层
RUN |1 TARGETARCH=amd64 /bin/sh -c echo "/usr/local/nvidia/lib" >> /etc/ld.so.conf.d/nvidia.conf     && echo "/usr/local/nvidia/lib64" >> /etc/ld.so.conf.d/nvidia.conf # buildkit
                        
# 2024-04-23 07:42:28  155.93MB 执行命令并创建新的镜像层
RUN |1 TARGETARCH=amd64 /bin/sh -c apt-get update && apt-get install -y --no-install-recommends     cuda-cudart-12-4=${NV_CUDA_CUDART_VERSION}     ${NV_CUDA_COMPAT_PACKAGE}     && rm -rf /var/lib/apt/lists/* # buildkit
                        
# 2024-04-23 07:42:16  0.00B 设置环境变量 CUDA_VERSION
ENV CUDA_VERSION=12.4.1
                        
# 2024-04-23 07:42:16  10.57MB 执行命令并创建新的镜像层
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/ubuntu2204/${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
                        
# 2024-04-23 07:42:16  0.00B 添加元数据标签
LABEL maintainer=NVIDIA CORPORATION <cudatools@nvidia.com>
                        
# 2024-04-23 07:42:16  0.00B 定义构建参数
ARG TARGETARCH
                        
# 2024-04-23 07:42:16  0.00B 设置环境变量 NV_CUDA_COMPAT_PACKAGE
ENV NV_CUDA_COMPAT_PACKAGE=cuda-compat-12-4
                        
# 2024-04-23 07:42:16  0.00B 设置环境变量 NV_CUDA_CUDART_VERSION
ENV NV_CUDA_CUDART_VERSION=12.4.127-1
                        
# 2024-04-23 07:42:16  0.00B 设置环境变量 NVIDIA_REQUIRE_CUDA brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand brand
ENV NVIDIA_REQUIRE_CUDA=cuda>=12.4 brand=tesla,driver>=470,driver<471 brand=unknown,driver>=470,driver<471 brand=nvidia,driver>=470,driver<471 brand=nvidiartx,driver>=470,driver<471 brand=geforce,driver>=470,driver<471 brand=geforcertx,driver>=470,driver<471 brand=quadro,driver>=470,driver<471 brand=quadrortx,driver>=470,driver<471 brand=titan,driver>=470,driver<471 brand=titanrtx,driver>=470,driver<471 brand=tesla,driver>=525,driver<526 brand=unknown,driver>=525,driver<526 brand=nvidia,driver>=525,driver<526 brand=nvidiartx,driver>=525,driver<526 brand=geforce,driver>=525,driver<526 brand=geforcertx,driver>=525,driver<526 brand=quadro,driver>=525,driver<526 brand=quadrortx,driver>=525,driver<526 brand=titan,driver>=525,driver<526 brand=titanrtx,driver>=525,driver<526 brand=tesla,driver>=535,driver<536 brand=unknown,driver>=535,driver<536 brand=nvidia,driver>=535,driver<536 brand=nvidiartx,driver>=535,driver<536 brand=geforce,driver>=535,driver<536 brand=geforcertx,driver>=535,driver<536 brand=quadro,driver>=535,driver<536 brand=quadrortx,driver>=535,driver<536 brand=titan,driver>=535,driver<536 brand=titanrtx,driver>=535,driver<536
                        
# 2024-04-23 07:42:16  0.00B 设置环境变量 NVARCH
ENV NVARCH=x86_64
                        
# 2024-04-11 02:52:04  0.00B 
/bin/sh -c #(nop)  CMD ["/bin/bash"]
                        
# 2024-04-11 02:52:04  77.86MB 
/bin/sh -c #(nop) ADD file:3bd10da0673e2e72cb06a1f64a9df49a36341df39b0f762e3d1b38ee4de296fa in / 
                        
# 2024-04-11 02:52:02  0.00B 
/bin/sh -c #(nop)  LABEL org.opencontainers.image.version=22.04
                        
# 2024-04-11 02:52:02  0.00B 
/bin/sh -c #(nop)  LABEL org.opencontainers.image.ref.name=ubuntu
                        
# 2024-04-11 02:52:02  0.00B 
/bin/sh -c #(nop)  ARG LAUNCHPAD_BUILD_ARCH
                        
# 2024-04-11 02:52:02  0.00B 
/bin/sh -c #(nop)  ARG RELEASE

镜像信息

{
    "Id": "sha256:4ee373e920ef591f32057d7fca5e8f121189734acdaf87c4269dae0ff5891096",
    "RepoTags": [
        "roboflow/roboflow-inference-server-gpu:latest",
        "swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/roboflow/roboflow-inference-server-gpu:latest"
    ],
    "RepoDigests": [
        "roboflow/roboflow-inference-server-gpu@sha256:32f0b6f80b5d4ece86574405171dd77cc9f982dfdb23cb08a1d7ed5da1fe6181",
        "swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/roboflow/roboflow-inference-server-gpu@sha256:ca0f8daaf15c1ec330af977cdfe2627c192965e91bc98fa43336bc431e62f812"
    ],
    "Parent": "",
    "Comment": "buildkit.dockerfile.v0",
    "Created": "2026-01-09T16:57:56.233329141Z",
    "Container": "",
    "ContainerConfig": null,
    "DockerVersion": "",
    "Author": "",
    "Config": {
        "Hostname": "",
        "Domainname": "",
        "User": "",
        "AttachStdin": false,
        "AttachStdout": false,
        "AttachStderr": false,
        "Tty": false,
        "OpenStdin": false,
        "StdinOnce": false,
        "Env": [
            "PATH=/usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin",
            "NVARCH=x86_64",
            "NVIDIA_REQUIRE_CUDA=cuda\u003e=12.4 brand=tesla,driver\u003e=470,driver\u003c471 brand=unknown,driver\u003e=470,driver\u003c471 brand=nvidia,driver\u003e=470,driver\u003c471 brand=nvidiartx,driver\u003e=470,driver\u003c471 brand=geforce,driver\u003e=470,driver\u003c471 brand=geforcertx,driver\u003e=470,driver\u003c471 brand=quadro,driver\u003e=470,driver\u003c471 brand=quadrortx,driver\u003e=470,driver\u003c471 brand=titan,driver\u003e=470,driver\u003c471 brand=titanrtx,driver\u003e=470,driver\u003c471 brand=tesla,driver\u003e=525,driver\u003c526 brand=unknown,driver\u003e=525,driver\u003c526 brand=nvidia,driver\u003e=525,driver\u003c526 brand=nvidiartx,driver\u003e=525,driver\u003c526 brand=geforce,driver\u003e=525,driver\u003c526 brand=geforcertx,driver\u003e=525,driver\u003c526 brand=quadro,driver\u003e=525,driver\u003c526 brand=quadrortx,driver\u003e=525,driver\u003c526 brand=titan,driver\u003e=525,driver\u003c526 brand=titanrtx,driver\u003e=525,driver\u003c526 brand=tesla,driver\u003e=535,driver\u003c536 brand=unknown,driver\u003e=535,driver\u003c536 brand=nvidia,driver\u003e=535,driver\u003c536 brand=nvidiartx,driver\u003e=535,driver\u003c536 brand=geforce,driver\u003e=535,driver\u003c536 brand=geforcertx,driver\u003e=535,driver\u003c536 brand=quadro,driver\u003e=535,driver\u003c536 brand=quadrortx,driver\u003e=535,driver\u003c536 brand=titan,driver\u003e=535,driver\u003c536 brand=titanrtx,driver\u003e=535,driver\u003c536",
            "NV_CUDA_CUDART_VERSION=12.4.127-1",
            "NV_CUDA_COMPAT_PACKAGE=cuda-compat-12-4",
            "CUDA_VERSION=12.4.1",
            "LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64",
            "NVIDIA_VISIBLE_DEVICES=all",
            "NVIDIA_DRIVER_CAPABILITIES=compute,utility",
            "NV_CUDA_LIB_VERSION=12.4.1-1",
            "NV_NVTX_VERSION=12.4.127-1",
            "NV_LIBNPP_VERSION=12.2.5.30-1",
            "NV_LIBNPP_PACKAGE=libnpp-12-4=12.2.5.30-1",
            "NV_LIBCUSPARSE_VERSION=12.3.1.170-1",
            "NV_LIBCUBLAS_PACKAGE_NAME=libcublas-12-4",
            "NV_LIBCUBLAS_VERSION=12.4.5.8-1",
            "NV_LIBCUBLAS_PACKAGE=libcublas-12-4=12.4.5.8-1",
            "NV_LIBNCCL_PACKAGE_NAME=libnccl2",
            "NV_LIBNCCL_PACKAGE_VERSION=2.21.5-1",
            "NCCL_VERSION=2.21.5-1",
            "NV_LIBNCCL_PACKAGE=libnccl2=2.21.5-1+cuda12.4",
            "NVIDIA_PRODUCT_NAME=CUDA",
            "NV_CUDNN_VERSION=9.1.0.70-1",
            "NV_CUDNN_PACKAGE_NAME=libcudnn9-cuda-12",
            "NV_CUDNN_PACKAGE=libcudnn9-cuda-12=9.1.0.70-1",
            "VERSION_CHECK_MODE=continuous",
            "PROJECT=roboflow-platform",
            "NUM_WORKERS=1",
            "HOST=0.0.0.0",
            "PORT=9001",
            "WORKFLOWS_STEP_EXECUTION_MODE=local",
            "WORKFLOWS_MAX_CONCURRENT_STEPS=4",
            "API_LOGGING_ENABLED=True",
            "LMM_ENABLED=True",
            "CORE_MODEL_SAM2_ENABLED=True",
            "CORE_MODEL_SAM3_ENABLED=True",
            "CORE_MODEL_OWLV2_ENABLED=True",
            "ENABLE_STREAM_API=True",
            "ENABLE_PROMETHEUS=True",
            "STREAM_API_PRELOADED_PROCESSES=2"
        ],
        "Cmd": null,
        "Image": "",
        "Volumes": null,
        "WorkingDir": "/app/",
        "Entrypoint": [
            "/bin/sh",
            "-c",
            "uvicorn gpu_http:app --workers $NUM_WORKERS --host $HOST --port $PORT"
        ],
        "OnBuild": null,
        "Labels": {
            "com.nvidia.cudnn.version": "9.1.0.70-1",
            "maintainer": "NVIDIA CORPORATION \u003ccudatools@nvidia.com\u003e",
            "org.opencontainers.image.ref.name": "ubuntu",
            "org.opencontainers.image.version": "22.04"
        }
    },
    "Architecture": "amd64",
    "Os": "linux",
    "Size": 15056584347,
    "GraphDriver": {
        "Data": {
            "LowerDir": "/var/lib/docker/overlay2/871fc78d9d3bba2358ded3c8b409efc546c5cc9899ae253a1dde41af3e21557f/diff:/var/lib/docker/overlay2/6cb51cd4f7da2adaa379628fb5a8bc3e3fcc7c964e7f078413019131585fd1cc/diff:/var/lib/docker/overlay2/f16397fccb2b44b3ffc03bf85a81a8352fa2b27b81653d8ffe16d864b15ab574/diff:/var/lib/docker/overlay2/6114c5a4ecbb7ee609080448104231ced038ebba8a464a4e57509d73476cfcdb/diff:/var/lib/docker/overlay2/2d900ffb0db7888f97ce53f9caa47fee05a0c039b591d4d8c1105ec2cae5982e/diff:/var/lib/docker/overlay2/195098dbf3e1dbe1cfb0961889f86668e40b83f5da62e6bf1a199f1373e7ef62/diff:/var/lib/docker/overlay2/6f2f6c923ae778dc54bc2e7b2e1edcc836ee617303d3db1f241f1a2e2b868da8/diff:/var/lib/docker/overlay2/a8a212e1eb3b91a070db079a29b8bbb3f9ec8425043ebe152988922f5671b32b/diff:/var/lib/docker/overlay2/1e150cad9d8c8cf4fa3d67f1ed671ba6e10bc95ddf163659a84c32d956e9e392/diff:/var/lib/docker/overlay2/71aa1895d0f93ad311af4516cd2e0e7e15059e3af2f5fd9bf6a22e9bee8b96a7/diff:/var/lib/docker/overlay2/23094717f57e6953be96f3c70c3e013a2cf85a4c0293d72d2c38df55afb756fc/diff:/var/lib/docker/overlay2/de9de4d0758ceaa1902a4c3e725b5d158f5c7e9bf220f925ce25c8a8d01c6e0e/diff:/var/lib/docker/overlay2/0d94043baa6c47fb8bebe294a1fee77515203270616ddfec1bb56b8dbdf3db78/diff:/var/lib/docker/overlay2/4aaa77e45250356e7a00ae7aa5e42645c6cedbd24112959b4e9add220f2980d5/diff:/var/lib/docker/overlay2/7cdb51144e7dea7fd4c8b3e5a4d993bfb3bff9b2f79dc9f5e672e1f771d15878/diff:/var/lib/docker/overlay2/6521c75f7fcc620515b8122d67e169f23c7c342ecccaeec56f29716b3a28e90c/diff:/var/lib/docker/overlay2/01911b97d376b344414ad2264de854b6b9d3f72df03b091e39d1c53cc6f7910c/diff:/var/lib/docker/overlay2/8d43a7dae639f1936a7fc97bb102088aba1e70ed36e86201d844c2be8f583d4a/diff:/var/lib/docker/overlay2/67fcac1bd48536ef1a4bd9ef0b4b5a6eba810dcd5c25e1e5a9883db651f98cfa/diff:/var/lib/docker/overlay2/64313f0d8fd6e303f5baf36f07045d973ea54e808a3c40998f62be9124f28c0d/diff:/var/lib/docker/overlay2/b9d832cff62d67f39ce1294df9803e6decb3cf59b8af13d58407a31c63848006/diff:/var/lib/docker/overlay2/03e046b59e6db3280e9622b070766d2e01dde7ff98e819c8f7519ea4aac55d57/diff:/var/lib/docker/overlay2/98fa49191811acfe03329604bd65eb7d7de243b0f40704043821ae789eda2822/diff:/var/lib/docker/overlay2/518175769d21bd73a7a0eefee7bafc6624b91f0161dddcc4a0fc9a991535701e/diff",
            "MergedDir": "/var/lib/docker/overlay2/4531a5c75db3b0e129802936db1eab5c7750975ea36e093e62306f475c22fd65/merged",
            "UpperDir": "/var/lib/docker/overlay2/4531a5c75db3b0e129802936db1eab5c7750975ea36e093e62306f475c22fd65/diff",
            "WorkDir": "/var/lib/docker/overlay2/4531a5c75db3b0e129802936db1eab5c7750975ea36e093e62306f475c22fd65/work"
        },
        "Name": "overlay2"
    },
    "RootFS": {
        "Type": "layers",
        "Layers": [
            "sha256:e0a9f5911802534ba097660206feabeb0247a81e409029167b30e2e1f2803b57",
            "sha256:47654eeadbc543f1dd44ebb41c6ca0954b9f1813efabdcd46b0e7f17ac4e9fd1",
            "sha256:efe2b79b53de08e199a2ce107d83adc0cbdff94f605e03f5ef51f3df3ae31cfd",
            "sha256:46d54736d31f4bfeb749544e22e8611dba11128bdb2cebb820a3b452b50e7d52",
            "sha256:809d3bb9c80fb3d31d4c061ba0b38ba4e83b6329e33c2cb2bbf27251a8e527c6",
            "sha256:1ffbbe19418f9726ebb365371ef96637c68f9d25af3f76a4f01f760e87fb31be",
            "sha256:1b30dd39de2709bc00beebf392ea1f931d5f037d08e0f675a50855385cddad93",
            "sha256:89fd878224a017aead1d4c83d5c62749307aa6f1a9e22087144ef339c3df8c1e",
            "sha256:2b4acda8678c6f7ae0075eabb2c0c21078b80671800996ad2cf730f15fa0ef26",
            "sha256:cf2dd37126ba1f3e6adbba8f6b7452f367fe0b0fc3a468c7988f9de68e2ecaa7",
            "sha256:ec55e95d6b7be7f8242488aafd07ea708bcd6c8ba3ba827724fb462ff8d4d714",
            "sha256:f7a8bc931301bfac17dfba6818b14a1badb87e0ebcd8c1167c01078ff606345f",
            "sha256:61d3aa8b5234aee3772696e0e7bed48fff1bac661ca820dc5c00108bf0458083",
            "sha256:bc62645fbe5eeda3ab9b4485477c201b62c5853444db9f3ec4c16e1be6952c3b",
            "sha256:8dd5dc691867f31a156b2b2cf45f952c51aab8f7c6544db029390af03265931a",
            "sha256:7c5ee690bf7814a3f9ad42ebb9c877d5a4ee62422f756335edcbfa7fb67d3af0",
            "sha256:124aed346a4a0b0e3f15a8b66d5205ef000b6c260391f09b0771d35bdb21141e",
            "sha256:d2712f7d4464803706b386a8b99633a6650b1452aa3dd3443b8dd12e91eee46a",
            "sha256:d71b247e666ed391ff7e499f278614cba0d7ad3b0d58d48f229e57e3929e3de1",
            "sha256:768d91f7944585b36a6e5a414c792c6d2d912a8983729ebc0742501861b8e8b4",
            "sha256:7828760d920c4844f66af7b4d42ca8f36efd872ccb932eb44cffce14d48850fb",
            "sha256:6c77f61319d838f0d8700909cee144bb2bc4ab0760074212ab89b66fc51b1110",
            "sha256:5f70bf18a086007016e948b04aed3b82103a36bea41755b6cddfaf10ace3c6ef",
            "sha256:0b3b21c76031fee084aacedf7b2fc2f071a75c349dd6e5235cda815a94da88da",
            "sha256:ec86fd8f978239f1953818b3725821631a735aa852df4045cd17ca56885f153f"
        ]
    },
    "Metadata": {
        "LastTagTime": "2026-01-12T02:44:54.788714095+08:00"
    }
}

更多版本

docker.io/roboflow/roboflow-inference-server-gpu:0.62.4

linux/amd64 docker.io15.00GB2025-12-11 00:40

236

docker.io/roboflow/roboflow-inference-server-gpu:latest

linux/amd64 docker.io15.06GB2026-01-12 02:59

361

0 点赞

0 收藏镜像 Run 生成 Docker Run 命令 K8s 生成 Kubernetes YAML 回到顶部