docker.io/nvcr.io/nvidia/tritonserver:25.05-trtllm-python-py3 linux/amd64

docker.io/nvcr.io/nvidia/tritonserver:25.05-trtllm-python-py3 - 国内下载镜像源 浏览次数:10

这是一个 NVIDIA Triton Inference Server 的 Docker 镜像。Triton Inference Server 是一个高性能的推理服务器,用于部署各种深度学习模型,支持多种框架(例如 TensorFlow, PyTorch, TensorRT 等),并提供模型版本管理、模型部署、以及高效的推理服务。

源镜像 docker.io/nvcr.io/nvidia/tritonserver:25.05-trtllm-python-py3
国内镜像 swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/nvcr.io/nvidia/tritonserver:25.05-trtllm-python-py3
镜像ID sha256:83fb714b5c3ca2166ff6797c97e4bd61c32571304448888e40190448fa73ff7a
镜像TAG 25.05-trtllm-python-py3
大小 32.90GB
镜像源 docker.io
项目信息 Docker-Hub主页 🚀项目TAG 🚀
CMD
启动入口 /opt/nvidia/nvidia_entrypoint.sh
工作目录 /opt/tritonserver
OS/平台 linux/amd64
浏览量 10 次
贡献者 yo*********0@163.com
镜像创建 2025-05-22T00:44:10.156167537Z
同步时间 2025-06-09 03:41
更新时间 2025-06-09 16:20
环境变量
PATH=/opt/tritonserver/bin:/usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/local/mpi/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/local/ucx/bin:/opt/amazon/efa/bin NVIDIA_REQUIRE_JETPACK_HOST_MOUNTS= GDRCOPY_VERSION=2.4.1 HPCX_VERSION=2.22.1 MOFED_VERSION=5.4-rdmacore50.0 OPENUCX_VERSION=1.18.0 OPENMPI_VERSION=4.1.7 RDMACORE_VERSION=50.0 EFA_VERSION=1.34.0 AWS_OFI_NCCL_VERSION=1.12.1 OPAL_PREFIX=/opt/hpcx/ompi OMPI_MCA_coll_hcoll_enable=0 CUDA_VERSION=12.8.1.012 CUDA_DRIVER_VERSION=570.124.06 CUDA_CACHE_DISABLE=1 _CUDA_COMPAT_PATH=/usr/local/cuda/compat ENV=/etc/shinit_v2 BASH_ENV=/etc/bash.bashrc SHELL=/bin/bash NVIDIA_REQUIRE_CUDA=cuda>=9.0 NCCL_VERSION=2.25.1 CUBLAS_VERSION=12.8.4.1 CUFFT_VERSION=11.3.3.83 CURAND_VERSION=10.3.9.90 CUSPARSE_VERSION=12.5.8.93 CUSPARSELT_VERSION=0.7.1.0 CUSOLVER_VERSION=11.7.3.90 NPP_VERSION=12.3.3.100 NVJPEG_VERSION=12.3.5.92 CUFILE_VERSION=1.13.1.3 NVJITLINK_VERSION=12.8.93 CUBLASMP_VERSION=0.4.0.789 CAL_VERSION=0.4.4.50 NVSHMEM_VERSION=3.2.5 CUDNN_VERSION=9.8.0.87 CUDNN_FRONTEND_VERSION=1.10.0 TRT_VERSION=10.9.0.34 TRTOSS_VERSION= NSIGHT_SYSTEMS_VERSION=2025.1.1.110 NSIGHT_COMPUTE_VERSION=2025.1.1.2 DALI_VERSION=1.47.0 DALI_BUILD= DALI_URL_SUFFIX=120 POLYGRAPHY_VERSION=0.49.18 TRANSFORMER_ENGINE_VERSION=2.1 MODEL_OPT_VERSION=0.25.0 LD_LIBRARY_PATH=/usr/local/tensorrt/lib/:/opt/tritonserver/backends/tensorrtllm:/usr/local/tensorrt/lib:/usr/local/cuda/compat/lib:/usr/local/nvidia/lib:/usr/local/nvidia/lib64 NVIDIA_VISIBLE_DEVICES=all NVIDIA_DRIVER_CAPABILITIES=compute,utility,video NVIDIA_PRODUCT_NAME=Triton Server LIBRARY_PATH=/usr/local/cuda/lib64/stubs: CUDA_VER=12.8.1.012 NVRTC_VER=12.8.61-1 PIP_BREAK_SYSTEM_PACKAGES=1 TRT_ROOT=/usr/local/tensorrt TRITON_SERVER_VERSION=2.58.0 NVIDIA_TRITON_SERVER_VERSION=25.05 UCX_MEM_EVENTS=no TF_ADJUST_HUE_FUSED=1 TF_ADJUST_SATURATION_FUSED=1 TF_ENABLE_WINOGRAD_NONFUSED=1 TF_AUTOTUNE_THRESHOLD=2 TRITON_SERVER_GPU_ENABLED=1 TRITON_SERVER_USER=triton-server DEBIAN_FRONTEND=noninteractive TCMALLOC_RELEASE_RATE=200 DCGM_VERSION=3.3.6 NVIDIA_BUILD_ID=170551418
镜像标签
true: com.amazonaws.sagemaker.capabilities.accept-bind-to-port true: com.amazonaws.sagemaker.capabilities.multi-models 170551418: com.nvidia.build.id 30bc978a595bdf75d7117144c250a3b6c98f2f98: com.nvidia.build.ref 0.4.4.50: com.nvidia.cal.version 12.8.4.1: com.nvidia.cublas.version 0.4.0.789: com.nvidia.cublasmp.version 9.0: com.nvidia.cuda.version 9.8.0.87: com.nvidia.cudnn.version 11.3.3.83: com.nvidia.cufft.version 10.3.9.90: com.nvidia.curand.version 11.7.3.90: com.nvidia.cusolver.version 12.5.8.93: com.nvidia.cusparse.version 0.7.1.0: com.nvidia.cusparselt.version 2.25.1: com.nvidia.nccl.version 12.3.3.100: com.nvidia.npp.version 2025.1.1.2: com.nvidia.nsightcompute.version 2025.1.1.110: com.nvidia.nsightsystems.version 12.3.5.92: com.nvidia.nvjpeg.version 10.9.0.34: com.nvidia.tensorrt.version : com.nvidia.tensorrtoss.version 2.58.0: com.nvidia.tritonserver.version nvidia_driver: com.nvidia.volumes.needed ubuntu: org.opencontainers.image.ref.name 24.04: org.opencontainers.image.version

Docker拉取命令

docker pull swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/nvcr.io/nvidia/tritonserver:25.05-trtllm-python-py3
docker tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/nvcr.io/nvidia/tritonserver:25.05-trtllm-python-py3  docker.io/nvcr.io/nvidia/tritonserver:25.05-trtllm-python-py3

Containerd拉取命令

ctr images pull swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/nvcr.io/nvidia/tritonserver:25.05-trtllm-python-py3
ctr images tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/nvcr.io/nvidia/tritonserver:25.05-trtllm-python-py3  docker.io/nvcr.io/nvidia/tritonserver:25.05-trtllm-python-py3

Shell快速替换命令

sed -i 's#nvcr.io/nvidia/tritonserver:25.05-trtllm-python-py3#swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/nvcr.io/nvidia/tritonserver:25.05-trtllm-python-py3#' 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/nvcr.io/nvidia/tritonserver:25.05-trtllm-python-py3 && docker tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/nvcr.io/nvidia/tritonserver:25.05-trtllm-python-py3  docker.io/nvcr.io/nvidia/tritonserver:25.05-trtllm-python-py3'

Ansible快速分发-Containerd

#ansible k8s -m shell -a 'ctr images pull swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/nvcr.io/nvidia/tritonserver:25.05-trtllm-python-py3 && ctr images tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/nvcr.io/nvidia/tritonserver:25.05-trtllm-python-py3  docker.io/nvcr.io/nvidia/tritonserver:25.05-trtllm-python-py3'

镜像构建历史


# 2025-05-22 08:44:10  75.93MB 复制新文件或目录到容器中
COPY /opt/hpcx/ompi /opt/hpcx/ompi # buildkit
                        
# 2025-05-22 08:44:09  0.00B 执行命令并创建新的镜像层
RUN |2 TRITON_VERSION=2.58.0 TRITON_CONTAINER_VERSION=25.05 /bin/sh -c rm -fr /opt/hpcx/ompi # buildkit
                        
# 2025-05-22 08:44:09  0.00B 设置环境变量 LD_LIBRARY_PATH
ENV LD_LIBRARY_PATH=/usr/local/tensorrt/lib/:/opt/tritonserver/backends/tensorrtllm:/usr/local/tensorrt/lib:/usr/local/cuda/compat/lib:/usr/local/nvidia/lib:/usr/local/nvidia/lib64
                        
# 2025-05-22 08:44:09  24.53MB 执行命令并创建新的镜像层
RUN |2 TRITON_VERSION=2.58.0 TRITON_CONTAINER_VERSION=25.05 /bin/sh -c ldconfig &&     ARCH="$(uname -i)" &&     rm -fr ${TRT_ROOT}/bin ${TRT_ROOT}/targets/${ARCH}-linux-gnu/bin ${TRT_ROOT}/data &&     rm -fr ${TRT_ROOT}/doc ${TRT_ROOT}/onnx_graphsurgeon ${TRT_ROOT}/python &&     rm -fr ${TRT_ROOT}/samples ${TRT_ROOT}/targets/${ARCH}-linux-gnu/samples &&     pip3 install --no-cache-dir transformers &&     find /usr -name libtensorrt_llm.so -exec dirname {} \; > /etc/ld.so.conf.d/tensorrt-llm.conf &&     find /opt/tritonserver -name libtritonserver.so -exec dirname {} \; > /etc/ld.so.conf.d/triton-tensorrtllm-worker.conf &&     pip3 install --no-cache-dir  grpcio-tools==1.64.0 &&     pip3 uninstall -y setuptools # buildkit
                        
# 2025-05-22 08:44:01  8.85KB 复制新文件或目录到容器中
COPY --chown=1000:1000 docker/sagemaker/serve /usr/bin/. # buildkit
                        
# 2025-05-22 08:44:01  0.00B 添加元数据标签
LABEL com.amazonaws.sagemaker.capabilities.multi-models=true
                        
# 2025-05-22 08:44:01  0.00B 添加元数据标签
LABEL com.amazonaws.sagemaker.capabilities.accept-bind-to-port=true
                        
# 2025-05-22 08:44:01  6.03MB 执行命令并创建新的镜像层
RUN |2 TRITON_VERSION=2.58.0 TRITON_CONTAINER_VERSION=25.05 /bin/sh -c pip3 install -r python/openai/requirements.txt # buildkit
                        
# 2025-05-22 08:43:58  365.87MB 执行命令并创建新的镜像层
RUN |2 TRITON_VERSION=2.58.0 TRITON_CONTAINER_VERSION=25.05 /bin/sh -c find /opt/tritonserver/python -maxdepth 1 -type f -name     "tritonserver-*.whl" | xargs -I {} pip install --upgrade {}[all] &&     find /opt/tritonserver/python -maxdepth 1 -type f -name     "tritonfrontend-*.whl" | xargs -I {} pip install --upgrade {}[all] # buildkit
                        
# 2025-05-22 08:43:49  3.01MB 复制新文件或目录到容器中
COPY --chown=1000:1000 NVIDIA_Deep_Learning_Container_License.pdf . # buildkit
                        
# 2025-05-22 08:43:49  0.00B 设置工作目录为/opt/tritonserver
WORKDIR /opt/tritonserver
                        
# 2025-05-22 08:43:49  543.76MB 复制新文件或目录到容器中
COPY --chown=1000:1000 build/install tritonserver # buildkit
                        
# 2025-05-22 08:43:48  0.00B 设置工作目录为/opt
WORKDIR /opt
                        
# 2025-05-22 08:43:48  0.00B 添加元数据标签
LABEL com.nvidia.build.ref=30bc978a595bdf75d7117144c250a3b6c98f2f98
                        
# 2025-05-22 08:43:48  0.00B 添加元数据标签
LABEL com.nvidia.build.id=170551418
                        
# 2025-05-22 08:43:48  0.00B 设置环境变量 NVIDIA_BUILD_ID
ENV NVIDIA_BUILD_ID=170551418
                        
# 2025-05-22 08:43:48  733.00B 复制新文件或目录到容器中
COPY docker/entrypoint.d/ /opt/nvidia/entrypoint.d/ # buildkit
                        
# 2025-05-22 08:43:48  0.00B 设置环境变量 NVIDIA_PRODUCT_NAME
ENV NVIDIA_PRODUCT_NAME=Triton Server
                        
# 2025-05-22 08:43:48  0.00B 执行命令并创建新的镜像层
RUN |2 TRITON_VERSION=2.58.0 TRITON_CONTAINER_VERSION=25.05 /bin/sh -c rm -fr /opt/tritonserver/* # buildkit
                        
# 2025-05-22 08:43:48  0.00B 设置工作目录为/opt/tritonserver
WORKDIR /opt/tritonserver
                        
# 2025-05-22 08:43:48  5.57MB 执行命令并创建新的镜像层
RUN |2 TRITON_VERSION=2.58.0 TRITON_CONTAINER_VERSION=25.05 /bin/sh -c apt-get update     && apt-get install -y --no-install-recommends         openssh-client     && rm -rf /var/lib/apt/lists/* # buildkit
                        
# 2025-05-22 08:43:40  80.18MB 执行命令并创建新的镜像层
RUN |2 TRITON_VERSION=2.58.0 TRITON_CONTAINER_VERSION=25.05 /bin/sh -c apt-get update       && apt-get install -y --no-install-recommends             python3             libarchive-dev             python3-pip             python3-wheel             python3-setuptools             libpython3-dev       && pip3 install --upgrade             "numpy<2"             virtualenv       && rm -rf /var/lib/apt/lists/* # buildkit
                        
# 2025-05-22 08:43:31  60.11KB 执行命令并创建新的镜像层
RUN |2 TRITON_VERSION=2.58.0 TRITON_CONTAINER_VERSION=25.05 /bin/sh -c ln -sf ${_CUDA_COMPAT_PATH}/lib.real ${_CUDA_COMPAT_PATH}/lib     && echo ${_CUDA_COMPAT_PATH}/lib > /etc/ld.so.conf.d/00-cuda-compat.conf     && ldconfig     && rm -f ${_CUDA_COMPAT_PATH}/lib # buildkit
                        
# 2025-05-22 08:43:30  1.75GB 执行命令并创建新的镜像层
RUN |2 TRITON_VERSION=2.58.0 TRITON_CONTAINER_VERSION=25.05 /bin/sh -c curl -o /tmp/cuda-keyring.deb           https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2404/x86_64/cuda-keyring_1.1-1_all.deb       && apt install /tmp/cuda-keyring.deb       && rm /tmp/cuda-keyring.deb       && apt-get update       && apt-get install -y datacenter-gpu-manager=1:3.3.6 # buildkit
                        
# 2025-05-22 08:42:08  0.00B 设置环境变量 DCGM_VERSION
ENV DCGM_VERSION=3.3.6
                        
# 2025-05-22 08:42:08  0.00B 设置环境变量 TCMALLOC_RELEASE_RATE
ENV TCMALLOC_RELEASE_RATE=200
                        
# 2025-05-22 08:42:08  351.84MB 执行命令并创建新的镜像层
RUN |2 TRITON_VERSION=2.58.0 TRITON_CONTAINER_VERSION=25.05 /bin/sh -c apt-get update       && apt-get install -y --no-install-recommends               clang               curl               dirmngr               git               gperf               libb64-0d               libcurl4-openssl-dev               libgoogle-perftools-dev               libjemalloc-dev               libnuma-dev               software-properties-common               wget                              python3-pip       && rm -rf /var/lib/apt/lists/* # buildkit
                        
# 2025-05-22 08:41:43  0.00B 设置环境变量 DEBIAN_FRONTEND
ENV DEBIAN_FRONTEND=noninteractive
                        
# 2025-05-22 08:41:43  4.49KB 执行命令并创建新的镜像层
RUN |2 TRITON_VERSION=2.58.0 TRITON_CONTAINER_VERSION=25.05 /bin/sh -c userdel tensorrt-server > /dev/null 2>&1 || true       && userdel ubuntu > /dev/null 2>&1 || true       && if ! id -u $TRITON_SERVER_USER > /dev/null 2>&1 ; then           useradd $TRITON_SERVER_USER;         fi       && [ `id -u $TRITON_SERVER_USER` -eq 1000 ]       && [ `id -g $TRITON_SERVER_USER` -eq 1000 ] # buildkit
                        
# 2025-05-22 08:41:43  0.00B 设置环境变量 TRITON_SERVER_USER
ENV TRITON_SERVER_USER=triton-server
                        
# 2025-05-22 08:41:43  0.00B 设置环境变量 TRITON_SERVER_GPU_ENABLED
ENV TRITON_SERVER_GPU_ENABLED=1
                        
# 2025-05-22 08:41:43  0.00B 设置环境变量 TF_AUTOTUNE_THRESHOLD
ENV TF_AUTOTUNE_THRESHOLD=2
                        
# 2025-05-22 08:41:43  0.00B 设置环境变量 TF_ENABLE_WINOGRAD_NONFUSED
ENV TF_ENABLE_WINOGRAD_NONFUSED=1
                        
# 2025-05-22 08:41:43  0.00B 设置环境变量 TF_ADJUST_SATURATION_FUSED
ENV TF_ADJUST_SATURATION_FUSED=1
                        
# 2025-05-22 08:41:43  0.00B 设置环境变量 TF_ADJUST_HUE_FUSED
ENV TF_ADJUST_HUE_FUSED=1
                        
# 2025-05-22 08:41:43  0.00B 设置环境变量 UCX_MEM_EVENTS
ENV UCX_MEM_EVENTS=no
                        
# 2025-05-22 08:41:43  0.00B 设置环境变量 PATH
ENV PATH=/opt/tritonserver/bin:/usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/local/mpi/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/local/ucx/bin:/opt/amazon/efa/bin
                        
# 2025-05-22 08:41:43  0.00B 添加元数据标签
LABEL com.nvidia.tritonserver.version=2.58.0
                        
# 2025-05-22 08:41:43  0.00B 设置环境变量 NVIDIA_TRITON_SERVER_VERSION
ENV NVIDIA_TRITON_SERVER_VERSION=25.05
                        
# 2025-05-22 08:41:43  0.00B 设置环境变量 TRITON_SERVER_VERSION
ENV TRITON_SERVER_VERSION=2.58.0
                        
# 2025-05-22 08:41:43  0.00B 定义构建参数
ARG TRITON_CONTAINER_VERSION=25.05
                        
# 2025-05-22 08:41:43  0.00B 定义构建参数
ARG TRITON_VERSION=2.58.0
                        
# 2025-05-22 08:41:43  0.00B 设置环境变量 PIP_BREAK_SYSTEM_PACKAGES
ENV PIP_BREAK_SYSTEM_PACKAGES=1
                        
# 2025-05-22 08:21:43  9.20MB 复制新文件或目录到容器中
COPY tensorrt_llm/examples examples # buildkit
                        
# 2025-05-22 08:21:43  622.01KB 复制新文件或目录到容器中
COPY tools tools # buildkit
                        
# 2025-05-22 08:21:43  98.31KB 复制新文件或目录到容器中
COPY inflight_batcher_llm/client client # buildkit
                        
# 2025-05-22 08:21:43  503.34KB 复制新文件或目录到容器中
COPY all_models all_models # buildkit
                        
# 2025-05-22 08:21:43  8.06KB 复制新文件或目录到容器中
COPY scripts scripts # buildkit
                        
# 2025-05-22 08:21:43  0.00B 设置工作目录为/app
WORKDIR /app
                        
# 2025-05-22 08:21:43  6.52GB 执行命令并创建新的镜像层
RUN |2 NVRTC_VER=12.8.61-1 TRT_VER=10.9.0.34 /bin/sh -c pip3 install --no-cache-dir tensorrt_llm*.whl &&     rm -f tensorrt_llm*.whl # buildkit
                        
# 2025-05-22 08:20:33  3.05GB 复制新文件或目录到容器中
COPY /workspace/tensorrt_llm/build/tensorrt_llm*whl . # buildkit
                        
# 2025-05-22 05:36:15  0.00B 设置工作目录为/tmp
WORKDIR /tmp
                        
# 2025-05-22 05:36:15  0.00B 设置环境变量 TRT_ROOT
ENV TRT_ROOT=/usr/local/tensorrt
                        
# 2025-05-22 05:36:15  0.00B 设置环境变量 LD_LIBRARY_PATH
ENV LD_LIBRARY_PATH=/usr/local/tensorrt/lib:/usr/local/cuda/compat/lib:/usr/local/nvidia/lib:/usr/local/nvidia/lib64
                        
# 2025-05-22 05:36:15  0.00B 设置环境变量 TRT_VERSION
ENV TRT_VERSION=10.9.0.34
                        
# 2025-05-22 05:36:15  0.00B 定义构建参数
ARG TRT_VER=10.9.0.34
                        
# 2025-05-22 05:36:15  4.87MB 执行命令并创建新的镜像层
RUN |1 NVRTC_VER=12.8.61-1 /bin/sh -c pip3 install /usr/local/tensorrt/python/tensorrt-*-cp$( python3 -c "import sys; print(str(sys.version_info.major) + str(sys.version_info.minor))" )* # buildkit
                        
# 2025-05-22 05:36:15  3.04GB 复制新文件或目录到容器中
COPY /usr/local/tensorrt /usr/local/tensorrt # buildkit
                        
# 2025-05-22 05:34:41  261.23MB 执行命令并创建新的镜像层
RUN |1 NVRTC_VER=12.8.61-1 /bin/sh -c [ "$(uname -m)" != "x86_64" ] && arch="sbsa" || arch="x86_64" &&     curl -o /tmp/cuda-keyring.deb https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/$arch/cuda-keyring_1.0-1_all.deb &&     apt install /tmp/cuda-keyring.deb &&     rm /tmp/cuda-keyring.deb &&     apt-get remove --purge -y --allow-change-held-packages cuda-nvrtc-dev* &&     CUDA_VER_SHORT=${CUDA_VER: 0:4} &&     NVRTC_CUDA_VERSION=${CUDA_VER_SHORT/./-} &&     apt-get update -qq &&     apt-get install -y --no-install-recommends cuda-nvrtc-dev-${NVRTC_CUDA_VERSION}=${NVRTC_VER} &&     rm -rf /var/lib/apt/lists/* # buildkit
                        
# 2025-05-22 05:34:33  97.10MB 执行命令并创建新的镜像层
RUN |1 NVRTC_VER=12.8.61-1 /bin/sh -c apt-get update -q=2 &&     apt-get install -y --no-install-recommends         python3-dev         python3-pip         python-is-python3         git-lfs &&     apt-get remove -y tensorrt* libnvinfer* &&     rm -rf /var/lib/apt/lists/* &&     pip3 uninstall -y tensorrt &&     pip3 install --no-cache-dir polygraphy==0.49.9 mpi4py==3.1.5 # buildkit
                        
# 2025-05-22 05:34:33  0.00B 设置环境变量 PIP_BREAK_SYSTEM_PACKAGES
ENV PIP_BREAK_SYSTEM_PACKAGES=1
                        
# 2025-05-22 05:34:33  0.00B 设置环境变量 CUDA_VER NVRTC_VER
ENV CUDA_VER=12.8.1.012 NVRTC_VER=12.8.61-1
                        
# 2025-05-22 05:34:33  0.00B 定义构建参数
ARG NVRTC_VER=12.8.61-1
                        
# 2025-05-22 05:33:43  849.88MB 复制新文件或目录到容器中
COPY /usr/local/cuda/lib64/libcusparseLt* /usr/local/cuda/lib64/ # buildkit
                        
# 2025-05-22 05:33:43  1.44GB 复制新文件或目录到容器中
COPY /usr/local/lib/python3.12/dist-packages/flash_attn_2_cuda.cpython-312-*-linux-gnu.so /usr/local/lib/python3.12/dist-packages/ # buildkit
                        
# 2025-05-22 05:33:41  36.07KB 复制新文件或目录到容器中
COPY /usr/local/lib/python3.12/dist-packages/flash_attn-2.7.3.dist-info /usr/local/lib/python3.12/dist-packages/flash_attn-2.7.3.dist-info # buildkit
                        
# 2025-05-22 05:33:41  1.59MB 复制新文件或目录到容器中
COPY /usr/local/lib/python3.12/dist-packages/flash_attn /usr/local/lib/python3.12/dist-packages/flash_attn # buildkit
                        
# 2025-05-22 05:33:41  17.48KB 复制新文件或目录到容器中
COPY /usr/local/lib/python3.12/dist-packages/packaging-23.2.dist-info /usr/local/lib/python3.12/dist-packages/packaging-23.2.dist-info # buildkit
                        
# 2025-05-22 05:33:41  329.74KB 复制新文件或目录到容器中
COPY /usr/local/lib/python3.12/dist-packages/packaging /usr/local/lib/python3.12/dist-packages/packaging # buildkit
                        
# 2025-05-22 05:33:41  316.70KB 复制新文件或目录到容器中
COPY /usr/local/lib/python3.12/dist-packages/sympy-1.13.1.dist-info /usr/local/lib/python3.12/dist-packages/sympy-1.13.1.dist-info # buildkit
                        
# 2025-05-22 05:33:41  67.79MB 复制新文件或目录到容器中
COPY /usr/local/lib/python3.12/dist-packages/sympy /usr/local/lib/python3.12/dist-packages/sympy # buildkit
                        
# 2025-05-22 05:33:41  107.58KB 复制新文件或目录到容器中
COPY /usr/local/lib/python3.12/dist-packages/networkx-3.4.2.dist-info /usr/local/lib/python3.12/dist-packages/networkx-3.4.2.dist-info # buildkit
                        
# 2025-05-22 05:33:41  14.49MB 复制新文件或目录到容器中
COPY /usr/local/lib/python3.12/dist-packages/networkx /usr/local/lib/python3.12/dist-packages/networkx # buildkit
                        
# 2025-05-22 05:33:41  8.11KB 复制新文件或目录到容器中
COPY /usr/local/lib/python3.12/dist-packages/jinja2-3.1.6.dist-info /usr/local/lib/python3.12/dist-packages/jinja2-3.1.6.dist-info # buildkit
                        
# 2025-05-22 05:33:41  1.16MB 复制新文件或目录到容器中
COPY /usr/local/lib/python3.12/dist-packages/jinja2 /usr/local/lib/python3.12/dist-packages/jinja2 # buildkit
                        
# 2025-05-22 05:33:41  701.55MB 复制新文件或目录到容器中
COPY /usr/local/lib/python3.12/dist-packages/triton /usr/local/lib/python3.12/dist-packages/triton # buildkit
                        
# 2025-05-22 05:33:40  39.62KB 复制新文件或目录到容器中
COPY /usr/local/lib/python3.12/dist-packages/pytorch_triton-3.2.0+gitb2684bf3b.nvinternal.dist-info /usr/local/lib/python3.12/dist-packages/pytorch_triton-3.2.0+gitb2684bf3b.nvinternal.dist-info # buildkit
                        
# 2025-05-22 05:33:40  299.69KB 复制新文件或目录到容器中
COPY /usr/local/lib/python3.12/dist-packages/functorch /usr/local/lib/python3.12/dist-packages/functorch # buildkit
                        
# 2025-05-22 05:33:40  84.29KB 复制新文件或目录到容器中
COPY /usr/local/lib/python3.12/dist-packages/setuptools-75.8.2.dist-info /usr/local/lib/python3.12/dist-packages/setuptools-75.8.2.dist-info # buildkit
                        
# 2025-05-22 05:33:40  8.25MB 复制新文件或目录到容器中
COPY /usr/local/lib/python3.12/dist-packages/setuptools /usr/local/lib/python3.12/dist-packages/setuptools # buildkit
                        
# 2025-05-22 05:33:40  674.92KB 复制新文件或目录到容器中
COPY /usr/local/lib/python3.12/dist-packages/torchvision.libs /usr/local/lib/python3.12/dist-packages/torchvision.libs # buildkit
                        
# 2025-05-22 05:33:40  49.11KB 复制新文件或目录到容器中
COPY /usr/local/lib/python3.12/dist-packages/torchvision-0.22.0a0.dist-info /usr/local/lib/python3.12/dist-packages/torchvision-0.22.0a0.dist-info # buildkit
                        
# 2025-05-22 05:33:40  19.99MB 复制新文件或目录到容器中
COPY /usr/local/lib/python3.12/dist-packages/torchvision /usr/local/lib/python3.12/dist-packages/torchvision # buildkit
                        
# 2025-05-22 05:33:40  3.28MB 复制新文件或目录到容器中
COPY /usr/local/lib/python3.12/dist-packages/torchgen /usr/local/lib/python3.12/dist-packages/torchgen # buildkit
                        
# 2025-05-22 05:33:40  1.87MB 复制新文件或目录到容器中
COPY /usr/local/lib/python3.12/dist-packages/torch-2.7.0a0+7c8ec84dab.nv25.3.dist-info /usr/local/lib/python3.12/dist-packages/torch-2.7.0a0+7c8ec84dab.nv25.3.dist-info # buildkit
                        
# 2025-05-22 05:33:40  2.04GB 复制新文件或目录到容器中
COPY /usr/local/lib/python3.12/dist-packages/torch /usr/local/lib/python3.12/dist-packages/torch # buildkit
                        
# 2025-05-22 05:33:38  1.85GB 复制新文件或目录到容器中
COPY /usr/local/lib/lib* /usr/local/lib/ # buildkit
                        
# 2025-03-11 05:06:29  39.60KB 执行命令并创建新的镜像层
RUN /bin/sh -c if [ ! -f /etc/ld.so.conf.d/nvidia-tegra.conf ]; then            echo "/opt/amazon/aws-ofi-nccl/lib" > /etc/ld.so.conf.d/aws-ofi-nccl.conf       && ldconfig;                                                 fi # buildkit
                        
# 2025-03-11 05:06:29  934.89KB 复制新文件或目录到容器中
COPY /opt/amazon/aws-ofi-nccl /opt/amazon/aws-ofi-nccl # buildkit
                        
# 2025-03-11 05:06:29  0.00B 设置环境变量 LIBRARY_PATH
ENV LIBRARY_PATH=/usr/local/cuda/lib64/stubs:
                        
# 2025-03-11 05:06:18  983.47MB 执行命令并创建新的镜像层
RUN /bin/sh -c export DEVEL=1 BASE=0  && /nvidia/build-scripts/installNCU.sh  && /nvidia/build-scripts/installCUDA.sh  && /nvidia/build-scripts/installLIBS.sh  && if [ ! -f /etc/ld.so.conf.d/nvidia-tegra.conf ]; then /nvidia/build-scripts/installNCCL.sh; fi  && /nvidia/build-scripts/installCUDNN.sh  && /nvidia/build-scripts/installTRT.sh  && /nvidia/build-scripts/installNSYS.sh  && /nvidia/build-scripts/installCUSPARSELT.sh  && if [ -f "/tmp/cuda-${_CUDA_VERSION_MAJMIN}.patch" ]; then patch -p0 < /tmp/cuda-${_CUDA_VERSION_MAJMIN}.patch; fi  && rm -f /tmp/cuda-*.patch # buildkit
                        
# 2025-03-11 05:03:45  1.49KB 复制新文件或目录到容器中
COPY cuda-*.patch /tmp # buildkit
                        
# 2025-03-11 05:03:45  99.01MB 执行命令并创建新的镜像层
RUN /bin/sh -c export DEBIAN_FRONTEND=noninteractive  && apt-get update  && apt-get install -y --no-install-recommends         build-essential         git         libglib2.0-0         less         libhwloc15         libnl-route-3-200         libnl-3-dev         libnl-route-3-dev         libnuma-dev         libnuma1         libpmi2-0-dev         nano         numactl         openssh-client         vim         wget  && rm -rf /var/lib/apt/lists/* # buildkit
                        
# 2025-03-11 04:54:05  467.00B 执行命令并创建新的镜像层
RUN |39 JETPACK_HOST_MOUNTS= GDRCOPY_VERSION=2.4.1 HPCX_VERSION=2.22.1 RDMACORE_VERSION=50.0 MOFED_VERSION=5.4-rdmacore50.0 OPENUCX_VERSION=1.18.0 OPENMPI_VERSION=4.1.7 EFA_VERSION=1.34.0 AWS_OFI_NCCL_VERSION=1.12.1 TARGETARCH=amd64 CUDA_VERSION=12.8.1.012 CUDA_DRIVER_VERSION=570.124.06 NCCL_VERSION=2.25.1 CUBLAS_VERSION=12.8.4.1 CUFFT_VERSION=11.3.3.83 CURAND_VERSION=10.3.9.90 CUSPARSE_VERSION=12.5.8.93 CUSOLVER_VERSION=11.7.3.90 NPP_VERSION=12.3.3.100 NVJPEG_VERSION=12.3.5.92 CUFILE_VERSION=1.13.1.3 NVJITLINK_VERSION=12.8.93 CUBLASMP_VERSION=0.4.0.789 CAL_VERSION=0.4.4.50 NVSHMEM_VERSION=3.2.5 CUDNN_VERSION=9.8.0.87 CUDNN_FRONTEND_VERSION=1.10.0 TRT_VERSION=10.9.0.34 TRTOSS_VERSION= NSIGHT_SYSTEMS_VERSION=2025.1.1.110 NSIGHT_COMPUTE_VERSION=2025.1.1.2 CUSPARSELT_VERSION=0.7.1.0 DALI_VERSION=1.47.0 DALI_BUILD= DALI_URL_SUFFIX=120 POLYGRAPHY_VERSION=0.49.18 TRANSFORMER_ENGINE_VERSION=2.1 MODEL_OPT_VERSION=0.25.0 _LIBPATH_SUFFIX= /bin/sh -c mkdir -p /workspace && cp -f -p /opt/nvidia/entrypoint.d/30-container-license.txt /workspace/license.txt # buildkit
                        
# 2025-03-11 04:54:05  0.00B 配置容器启动时运行的命令
ENTRYPOINT ["/opt/nvidia/nvidia_entrypoint.sh"]
                        
# 2025-03-11 04:54:05  0.00B 设置环境变量 NVIDIA_PRODUCT_NAME
ENV NVIDIA_PRODUCT_NAME=CUDA
                        
# 2025-03-11 04:54:05  16.04KB 复制新文件或目录到容器中
COPY entrypoint/ /opt/nvidia/ # buildkit
                        
# 2025-03-11 04:54:05  0.00B 设置环境变量 PATH LD_LIBRARY_PATH NVIDIA_VISIBLE_DEVICES NVIDIA_DRIVER_CAPABILITIES
ENV PATH=/usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/local/mpi/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/local/ucx/bin:/opt/amazon/efa/bin LD_LIBRARY_PATH=/usr/local/cuda/compat/lib:/usr/local/nvidia/lib:/usr/local/nvidia/lib64 NVIDIA_VISIBLE_DEVICES=all NVIDIA_DRIVER_CAPABILITIES=compute,utility,video
                        
# 2025-03-11 04:54:05  0.00B 定义构建参数
ARG _LIBPATH_SUFFIX=
                        
# 2025-03-11 04:54:05  46.00B 执行命令并创建新的镜像层
RUN |38 JETPACK_HOST_MOUNTS= GDRCOPY_VERSION=2.4.1 HPCX_VERSION=2.22.1 RDMACORE_VERSION=50.0 MOFED_VERSION=5.4-rdmacore50.0 OPENUCX_VERSION=1.18.0 OPENMPI_VERSION=4.1.7 EFA_VERSION=1.34.0 AWS_OFI_NCCL_VERSION=1.12.1 TARGETARCH=amd64 CUDA_VERSION=12.8.1.012 CUDA_DRIVER_VERSION=570.124.06 NCCL_VERSION=2.25.1 CUBLAS_VERSION=12.8.4.1 CUFFT_VERSION=11.3.3.83 CURAND_VERSION=10.3.9.90 CUSPARSE_VERSION=12.5.8.93 CUSOLVER_VERSION=11.7.3.90 NPP_VERSION=12.3.3.100 NVJPEG_VERSION=12.3.5.92 CUFILE_VERSION=1.13.1.3 NVJITLINK_VERSION=12.8.93 CUBLASMP_VERSION=0.4.0.789 CAL_VERSION=0.4.4.50 NVSHMEM_VERSION=3.2.5 CUDNN_VERSION=9.8.0.87 CUDNN_FRONTEND_VERSION=1.10.0 TRT_VERSION=10.9.0.34 TRTOSS_VERSION= NSIGHT_SYSTEMS_VERSION=2025.1.1.110 NSIGHT_COMPUTE_VERSION=2025.1.1.2 CUSPARSELT_VERSION=0.7.1.0 DALI_VERSION=1.47.0 DALI_BUILD= DALI_URL_SUFFIX=120 POLYGRAPHY_VERSION=0.49.18 TRANSFORMER_ENGINE_VERSION=2.1 MODEL_OPT_VERSION=0.25.0 /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
                        
# 2025-03-11 04:54:05  13.39KB 复制文件或目录到容器中
ADD docs.tgz / # buildkit
                        
# 2025-03-11 04:54:04  0.00B 设置环境变量 DALI_VERSION DALI_BUILD DALI_URL_SUFFIX POLYGRAPHY_VERSION TRANSFORMER_ENGINE_VERSION MODEL_OPT_VERSION
ENV DALI_VERSION=1.47.0 DALI_BUILD= DALI_URL_SUFFIX=120 POLYGRAPHY_VERSION=0.49.18 TRANSFORMER_ENGINE_VERSION=2.1 MODEL_OPT_VERSION=0.25.0
                        
# 2025-03-11 04:54:04  0.00B 定义构建参数
ARG MODEL_OPT_VERSION=0.25.0
                        
# 2025-03-11 04:54:04  0.00B 定义构建参数
ARG TRANSFORMER_ENGINE_VERSION=2.1
                        
# 2025-03-11 04:54:04  0.00B 定义构建参数
ARG POLYGRAPHY_VERSION=0.49.18
                        
# 2025-03-11 04:54:04  0.00B 定义构建参数
ARG DALI_URL_SUFFIX=120
                        
# 2025-03-11 04:54:04  0.00B 定义构建参数
ARG DALI_BUILD=
                        
# 2025-03-11 04:54:04  0.00B 定义构建参数
ARG DALI_VERSION=1.47.0
                        
# 2025-03-11 04:54:04  0.00B 添加元数据标签
LABEL com.nvidia.nccl.version=2.25.1 com.nvidia.cublas.version=12.8.4.1 com.nvidia.cufft.version=11.3.3.83 com.nvidia.curand.version=10.3.9.90 com.nvidia.cusparse.version=12.5.8.93 com.nvidia.cusparselt.version=0.7.1.0 com.nvidia.cusolver.version=11.7.3.90 com.nvidia.npp.version=12.3.3.100 com.nvidia.nvjpeg.version=12.3.5.92 com.nvidia.cublasmp.version=0.4.0.789 com.nvidia.cal.version=0.4.4.50 com.nvidia.cudnn.version=9.8.0.87 com.nvidia.tensorrt.version=10.9.0.34 com.nvidia.tensorrtoss.version= com.nvidia.nsightsystems.version=2025.1.1.110 com.nvidia.nsightcompute.version=2025.1.1.2
                        
# 2025-03-11 04:54:04  7.17GB 执行命令并创建新的镜像层
RUN |32 JETPACK_HOST_MOUNTS= GDRCOPY_VERSION=2.4.1 HPCX_VERSION=2.22.1 RDMACORE_VERSION=50.0 MOFED_VERSION=5.4-rdmacore50.0 OPENUCX_VERSION=1.18.0 OPENMPI_VERSION=4.1.7 EFA_VERSION=1.34.0 AWS_OFI_NCCL_VERSION=1.12.1 TARGETARCH=amd64 CUDA_VERSION=12.8.1.012 CUDA_DRIVER_VERSION=570.124.06 NCCL_VERSION=2.25.1 CUBLAS_VERSION=12.8.4.1 CUFFT_VERSION=11.3.3.83 CURAND_VERSION=10.3.9.90 CUSPARSE_VERSION=12.5.8.93 CUSOLVER_VERSION=11.7.3.90 NPP_VERSION=12.3.3.100 NVJPEG_VERSION=12.3.5.92 CUFILE_VERSION=1.13.1.3 NVJITLINK_VERSION=12.8.93 CUBLASMP_VERSION=0.4.0.789 CAL_VERSION=0.4.4.50 NVSHMEM_VERSION=3.2.5 CUDNN_VERSION=9.8.0.87 CUDNN_FRONTEND_VERSION=1.10.0 TRT_VERSION=10.9.0.34 TRTOSS_VERSION= NSIGHT_SYSTEMS_VERSION=2025.1.1.110 NSIGHT_COMPUTE_VERSION=2025.1.1.2 CUSPARSELT_VERSION=0.7.1.0 /bin/sh -c /nvidia/build-scripts/installLIBS.sh  && /nvidia/build-scripts/installCUDNN.sh  && /nvidia/build-scripts/installTRT.sh  && /nvidia/build-scripts/installNSYS.sh  && /nvidia/build-scripts/installNCU.sh  && /nvidia/build-scripts/installCUSPARSELT.sh  && if [ -z "${JETPACK_HOST_MOUNTS}" ]; then       /nvidia/build-scripts/installNCCL.sh;     fi; # buildkit
                        
# 2025-03-11 04:53:07  0.00B 设置环境变量 NCCL_VERSION CUBLAS_VERSION CUFFT_VERSION CURAND_VERSION CUSPARSE_VERSION CUSPARSELT_VERSION CUSOLVER_VERSION NPP_VERSION NVJPEG_VERSION CUFILE_VERSION NVJITLINK_VERSION CUBLASMP_VERSION CAL_VERSION NVSHMEM_VERSION CUDNN_VERSION CUDNN_FRONTEND_VERSION TRT_VERSION TRTOSS_VERSION NSIGHT_SYSTEMS_VERSION NSIGHT_COMPUTE_VERSION
ENV NCCL_VERSION=2.25.1 CUBLAS_VERSION=12.8.4.1 CUFFT_VERSION=11.3.3.83 CURAND_VERSION=10.3.9.90 CUSPARSE_VERSION=12.5.8.93 CUSPARSELT_VERSION=0.7.1.0 CUSOLVER_VERSION=11.7.3.90 NPP_VERSION=12.3.3.100 NVJPEG_VERSION=12.3.5.92 CUFILE_VERSION=1.13.1.3 NVJITLINK_VERSION=12.8.93 CUBLASMP_VERSION=0.4.0.789 CAL_VERSION=0.4.4.50 NVSHMEM_VERSION=3.2.5 CUDNN_VERSION=9.8.0.87 CUDNN_FRONTEND_VERSION=1.10.0 TRT_VERSION=10.9.0.34 TRTOSS_VERSION= NSIGHT_SYSTEMS_VERSION=2025.1.1.110 NSIGHT_COMPUTE_VERSION=2025.1.1.2
                        
# 2025-03-11 04:53:07  0.00B 定义构建参数
ARG CUSPARSELT_VERSION=0.7.1.0
                        
# 2025-03-11 04:53:07  0.00B 定义构建参数
ARG NSIGHT_COMPUTE_VERSION=2025.1.1.2
                        
# 2025-03-11 04:53:07  0.00B 定义构建参数
ARG NSIGHT_SYSTEMS_VERSION=2025.1.1.110
                        
# 2025-03-11 04:53:07  0.00B 定义构建参数
ARG TRTOSS_VERSION=
                        
# 2025-03-11 04:53:07  0.00B 定义构建参数
ARG TRT_VERSION=10.9.0.34
                        
# 2025-03-11 04:53:07  0.00B 定义构建参数
ARG CUDNN_FRONTEND_VERSION=1.10.0
                        
# 2025-03-11 04:53:07  0.00B 定义构建参数
ARG CUDNN_VERSION=9.8.0.87
                        
# 2025-03-11 04:53:07  0.00B 定义构建参数
ARG NVSHMEM_VERSION=3.2.5
                        
# 2025-03-11 04:53:07  0.00B 定义构建参数
ARG CAL_VERSION=0.4.4.50
                        
# 2025-03-11 04:53:07  0.00B 定义构建参数
ARG CUBLASMP_VERSION=0.4.0.789
                        
# 2025-03-11 04:53:07  0.00B 定义构建参数
ARG NVJITLINK_VERSION=12.8.93
                        
# 2025-03-11 04:53:07  0.00B 定义构建参数
ARG CUFILE_VERSION=1.13.1.3
                        
# 2025-03-11 04:53:07  0.00B 定义构建参数
ARG NVJPEG_VERSION=12.3.5.92
                        
# 2025-03-11 04:53:07  0.00B 定义构建参数
ARG NPP_VERSION=12.3.3.100
                        
# 2025-03-11 04:53:07  0.00B 定义构建参数
ARG CUSOLVER_VERSION=11.7.3.90
                        
# 2025-03-11 04:53:07  0.00B 定义构建参数
ARG CUSPARSE_VERSION=12.5.8.93
                        
# 2025-03-11 04:53:07  0.00B 定义构建参数
ARG CURAND_VERSION=10.3.9.90
                        
# 2025-03-11 04:53:07  0.00B 定义构建参数
ARG CUFFT_VERSION=11.3.3.83
                        
# 2025-03-11 04:53:07  0.00B 定义构建参数
ARG CUBLAS_VERSION=12.8.4.1
                        
# 2025-03-11 04:53:07  0.00B 定义构建参数
ARG NCCL_VERSION=2.25.1
                        
# 2025-03-11 04:53:07  0.00B 添加元数据标签
LABEL com.nvidia.volumes.needed=nvidia_driver com.nvidia.cuda.version=9.0
                        
# 2025-03-11 04:53:07  0.00B 设置环境变量 _CUDA_COMPAT_PATH ENV BASH_ENV SHELL NVIDIA_REQUIRE_CUDA
ENV _CUDA_COMPAT_PATH=/usr/local/cuda/compat ENV=/etc/shinit_v2 BASH_ENV=/etc/bash.bashrc SHELL=/bin/bash NVIDIA_REQUIRE_CUDA=cuda>=9.0
                        
# 2025-03-11 04:53:07  59.18KB 执行命令并创建新的镜像层
RUN |12 JETPACK_HOST_MOUNTS= GDRCOPY_VERSION=2.4.1 HPCX_VERSION=2.22.1 RDMACORE_VERSION=50.0 MOFED_VERSION=5.4-rdmacore50.0 OPENUCX_VERSION=1.18.0 OPENMPI_VERSION=4.1.7 EFA_VERSION=1.34.0 AWS_OFI_NCCL_VERSION=1.12.1 TARGETARCH=amd64 CUDA_VERSION=12.8.1.012 CUDA_DRIVER_VERSION=570.124.06 /bin/sh -c cp -vprd /nvidia/. /  &&  patch -p0 < /etc/startup_scripts.patch  &&  rm -f /etc/startup_scripts.patch # buildkit
                        
# 2025-03-11 04:53:07  809.53MB 执行命令并创建新的镜像层
RUN |12 JETPACK_HOST_MOUNTS= GDRCOPY_VERSION=2.4.1 HPCX_VERSION=2.22.1 RDMACORE_VERSION=50.0 MOFED_VERSION=5.4-rdmacore50.0 OPENUCX_VERSION=1.18.0 OPENMPI_VERSION=4.1.7 EFA_VERSION=1.34.0 AWS_OFI_NCCL_VERSION=1.12.1 TARGETARCH=amd64 CUDA_VERSION=12.8.1.012 CUDA_DRIVER_VERSION=570.124.06 /bin/sh -c /nvidia/build-scripts/installCUDA.sh # buildkit
                        
# 2025-03-08 03:56:30  0.00B 设置环境变量 CUDA_VERSION CUDA_DRIVER_VERSION CUDA_CACHE_DISABLE
ENV CUDA_VERSION=12.8.1.012 CUDA_DRIVER_VERSION=570.124.06 CUDA_CACHE_DISABLE=1
                        
# 2025-03-08 03:56:30  0.00B 定义构建参数
ARG CUDA_DRIVER_VERSION=570.124.06
                        
# 2025-03-08 03:56:30  0.00B 定义构建参数
ARG CUDA_VERSION=12.8.1.012
                        
# 2025-03-08 03:56:30  0.00B 设置环境变量 OMPI_MCA_coll_hcoll_enable
ENV OMPI_MCA_coll_hcoll_enable=0
                        
# 2025-03-08 03:56:30  0.00B 设置环境变量 OPAL_PREFIX PATH
ENV OPAL_PREFIX=/opt/hpcx/ompi PATH=/usr/local/mpi/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/local/ucx/bin:/opt/amazon/efa/bin
                        
# 2025-03-08 03:56:30  229.92MB 执行命令并创建新的镜像层
RUN |10 JETPACK_HOST_MOUNTS= GDRCOPY_VERSION=2.4.1 HPCX_VERSION=2.22.1 RDMACORE_VERSION=50.0 MOFED_VERSION=5.4-rdmacore50.0 OPENUCX_VERSION=1.18.0 OPENMPI_VERSION=4.1.7 EFA_VERSION=1.34.0 AWS_OFI_NCCL_VERSION=1.12.1 TARGETARCH=amd64 /bin/sh -c cd /nvidia  && ( export DEBIAN_FRONTEND=noninteractive        && apt-get update                            && apt-get install -y --no-install-recommends              libibverbs1                                  libibverbs-dev                               librdmacm1                                   librdmacm-dev                                libibumad3                                   libibumad-dev                                ibverbs-utils                                ibverbs-providers                     && rm -rf /var/lib/apt/lists/*               && rm $(dpkg-query -L                                    libibverbs-dev                               librdmacm-dev                                libibumad-dev                            | grep "\(\.so\|\.a\)$")          )                                            && ( cd opt/gdrcopy/                              && dpkg -i libgdrapi_*.deb                   )                                         && ( cp -r opt/hpcx /opt/                                         && cp etc/ld.so.conf.d/hpcx.conf /etc/ld.so.conf.d/          && ln -sf /opt/hpcx/ompi /usr/local/mpi                      && ln -sf /opt/hpcx/ucx  /usr/local/ucx                      && sed -i 's/^\(hwloc_base_binding_policy\) = core$/\1 = none/' /opt/hpcx/ompi/etc/openmpi-mca-params.conf         && sed -i 's/^\(btl = self\)$/#\1/'                             /opt/hpcx/ompi/etc/openmpi-mca-params.conf       )                                                         && ( if [ ! -f /etc/ld.so.conf.d/nvidia-tegra.conf ]; then           cd opt/amazon/efa/                                           && dpkg -i libfabric*.deb                                    && rm /opt/amazon/efa/lib/libfabric.a                        && echo "/opt/amazon/efa/lib" > /etc/ld.so.conf.d/efa.conf;         fi                                                         )                                                         && ldconfig # buildkit
                        
# 2025-03-08 03:56:22  0.00B 定义构建参数
ARG TARGETARCH=amd64
                        
# 2025-03-08 03:56:22  0.00B 设置环境变量 GDRCOPY_VERSION HPCX_VERSION MOFED_VERSION OPENUCX_VERSION OPENMPI_VERSION RDMACORE_VERSION EFA_VERSION AWS_OFI_NCCL_VERSION
ENV GDRCOPY_VERSION=2.4.1 HPCX_VERSION=2.22.1 MOFED_VERSION=5.4-rdmacore50.0 OPENUCX_VERSION=1.18.0 OPENMPI_VERSION=4.1.7 RDMACORE_VERSION=50.0 EFA_VERSION=1.34.0 AWS_OFI_NCCL_VERSION=1.12.1
                        
# 2025-03-08 03:56:22  0.00B 定义构建参数
ARG AWS_OFI_NCCL_VERSION=1.12.1
                        
# 2025-03-08 03:56:22  0.00B 定义构建参数
ARG EFA_VERSION=1.34.0
                        
# 2025-03-08 03:56:22  0.00B 定义构建参数
ARG OPENMPI_VERSION=4.1.7
                        
# 2025-03-08 03:56:22  0.00B 定义构建参数
ARG OPENUCX_VERSION=1.18.0
                        
# 2025-03-08 03:56:22  0.00B 定义构建参数
ARG MOFED_VERSION=5.4-rdmacore50.0
                        
# 2025-03-08 03:56:22  0.00B 定义构建参数
ARG RDMACORE_VERSION=50.0
                        
# 2025-03-08 03:56:22  0.00B 定义构建参数
ARG HPCX_VERSION=2.22.1
                        
# 2025-03-08 03:56:22  0.00B 定义构建参数
ARG GDRCOPY_VERSION=2.4.1
                        
# 2025-03-08 03:56:22  340.75MB 执行命令并创建新的镜像层
RUN |1 JETPACK_HOST_MOUNTS= /bin/sh -c export DEBIAN_FRONTEND=noninteractive  && apt-get update  && apt-get install -y --no-install-recommends         apt-utils         build-essential         ca-certificates         curl         libncurses6         libncursesw6         patch         wget         unzip         jq         gnupg         libtcmalloc-minimal4  && rm -rf /var/lib/apt/lists/*  && echo "hsts=0" > /root/.wgetrc # buildkit
                        
# 2025-03-08 03:56:02  0.00B 执行命令并创建新的镜像层
RUN |1 JETPACK_HOST_MOUNTS= /bin/sh -c if [ -n "${JETPACK_HOST_MOUNTS}" ]; then        echo "/usr/lib/aarch64-linux-gnu/tegra" > /etc/ld.so.conf.d/nvidia-tegra.conf     && echo "/usr/lib/aarch64-linux-gnu/tegra-egl" >> /etc/ld.so.conf.d/nvidia-tegra.conf;     fi # buildkit
                        
# 2025-03-08 03:56:02  0.00B 设置环境变量 NVIDIA_REQUIRE_JETPACK_HOST_MOUNTS
ENV NVIDIA_REQUIRE_JETPACK_HOST_MOUNTS=
                        
# 2025-03-08 03:56:02  0.00B 定义构建参数
ARG JETPACK_HOST_MOUNTS=
                        
# 2025-01-27 12:14:03  0.00B 
/bin/sh -c #(nop)  CMD ["/bin/bash"]
                        
# 2025-01-27 12:14:03  78.13MB 
/bin/sh -c #(nop) ADD file:6df775300d76441aa33f31b22c1afce8dfe35c8ffbc14ef27c27009235b12a95 in / 
                        
# 2025-01-27 12:14:00  0.00B 
/bin/sh -c #(nop)  LABEL org.opencontainers.image.version=24.04
                        
# 2025-01-27 12:14:00  0.00B 
/bin/sh -c #(nop)  LABEL org.opencontainers.image.ref.name=ubuntu
                        
# 2025-01-27 12:14:00  0.00B 
/bin/sh -c #(nop)  ARG LAUNCHPAD_BUILD_ARCH
                        
# 2025-01-27 12:14:00  0.00B 
/bin/sh -c #(nop)  ARG RELEASE
                        
                    

镜像信息

{
    "Id": "sha256:83fb714b5c3ca2166ff6797c97e4bd61c32571304448888e40190448fa73ff7a",
    "RepoTags": [
        "nvcr.io/nvidia/tritonserver:25.05-trtllm-python-py3",
        "swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/nvcr.io/nvidia/tritonserver:25.05-trtllm-python-py3"
    ],
    "RepoDigests": [
        "nvcr.io/nvidia/tritonserver@sha256:68a74a08d0839f033befda55b0d9b88da06d943aa3d2bafdb759213bf4427358",
        "swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/nvcr.io/nvidia/tritonserver@sha256:a89bfbd386b5b7f1480f7d025772909d9efc93c8ca7bece28a377d5d0b86ccad"
    ],
    "Parent": "",
    "Comment": "buildkit.dockerfile.v0",
    "Created": "2025-05-22T00:44:10.156167537Z",
    "Container": "",
    "ContainerConfig": null,
    "DockerVersion": "",
    "Author": "",
    "Config": {
        "Hostname": "",
        "Domainname": "",
        "User": "",
        "AttachStdin": false,
        "AttachStdout": false,
        "AttachStderr": false,
        "Tty": false,
        "OpenStdin": false,
        "StdinOnce": false,
        "Env": [
            "PATH=/opt/tritonserver/bin:/usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/local/mpi/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/local/ucx/bin:/opt/amazon/efa/bin",
            "NVIDIA_REQUIRE_JETPACK_HOST_MOUNTS=",
            "GDRCOPY_VERSION=2.4.1",
            "HPCX_VERSION=2.22.1",
            "MOFED_VERSION=5.4-rdmacore50.0",
            "OPENUCX_VERSION=1.18.0",
            "OPENMPI_VERSION=4.1.7",
            "RDMACORE_VERSION=50.0",
            "EFA_VERSION=1.34.0",
            "AWS_OFI_NCCL_VERSION=1.12.1",
            "OPAL_PREFIX=/opt/hpcx/ompi",
            "OMPI_MCA_coll_hcoll_enable=0",
            "CUDA_VERSION=12.8.1.012",
            "CUDA_DRIVER_VERSION=570.124.06",
            "CUDA_CACHE_DISABLE=1",
            "_CUDA_COMPAT_PATH=/usr/local/cuda/compat",
            "ENV=/etc/shinit_v2",
            "BASH_ENV=/etc/bash.bashrc",
            "SHELL=/bin/bash",
            "NVIDIA_REQUIRE_CUDA=cuda\u003e=9.0",
            "NCCL_VERSION=2.25.1",
            "CUBLAS_VERSION=12.8.4.1",
            "CUFFT_VERSION=11.3.3.83",
            "CURAND_VERSION=10.3.9.90",
            "CUSPARSE_VERSION=12.5.8.93",
            "CUSPARSELT_VERSION=0.7.1.0",
            "CUSOLVER_VERSION=11.7.3.90",
            "NPP_VERSION=12.3.3.100",
            "NVJPEG_VERSION=12.3.5.92",
            "CUFILE_VERSION=1.13.1.3",
            "NVJITLINK_VERSION=12.8.93",
            "CUBLASMP_VERSION=0.4.0.789",
            "CAL_VERSION=0.4.4.50",
            "NVSHMEM_VERSION=3.2.5",
            "CUDNN_VERSION=9.8.0.87",
            "CUDNN_FRONTEND_VERSION=1.10.0",
            "TRT_VERSION=10.9.0.34",
            "TRTOSS_VERSION=",
            "NSIGHT_SYSTEMS_VERSION=2025.1.1.110",
            "NSIGHT_COMPUTE_VERSION=2025.1.1.2",
            "DALI_VERSION=1.47.0",
            "DALI_BUILD=",
            "DALI_URL_SUFFIX=120",
            "POLYGRAPHY_VERSION=0.49.18",
            "TRANSFORMER_ENGINE_VERSION=2.1",
            "MODEL_OPT_VERSION=0.25.0",
            "LD_LIBRARY_PATH=/usr/local/tensorrt/lib/:/opt/tritonserver/backends/tensorrtllm:/usr/local/tensorrt/lib:/usr/local/cuda/compat/lib:/usr/local/nvidia/lib:/usr/local/nvidia/lib64",
            "NVIDIA_VISIBLE_DEVICES=all",
            "NVIDIA_DRIVER_CAPABILITIES=compute,utility,video",
            "NVIDIA_PRODUCT_NAME=Triton Server",
            "LIBRARY_PATH=/usr/local/cuda/lib64/stubs:",
            "CUDA_VER=12.8.1.012",
            "NVRTC_VER=12.8.61-1",
            "PIP_BREAK_SYSTEM_PACKAGES=1",
            "TRT_ROOT=/usr/local/tensorrt",
            "TRITON_SERVER_VERSION=2.58.0",
            "NVIDIA_TRITON_SERVER_VERSION=25.05",
            "UCX_MEM_EVENTS=no",
            "TF_ADJUST_HUE_FUSED=1",
            "TF_ADJUST_SATURATION_FUSED=1",
            "TF_ENABLE_WINOGRAD_NONFUSED=1",
            "TF_AUTOTUNE_THRESHOLD=2",
            "TRITON_SERVER_GPU_ENABLED=1",
            "TRITON_SERVER_USER=triton-server",
            "DEBIAN_FRONTEND=noninteractive",
            "TCMALLOC_RELEASE_RATE=200",
            "DCGM_VERSION=3.3.6",
            "NVIDIA_BUILD_ID=170551418"
        ],
        "Cmd": null,
        "Image": "",
        "Volumes": null,
        "WorkingDir": "/opt/tritonserver",
        "Entrypoint": [
            "/opt/nvidia/nvidia_entrypoint.sh"
        ],
        "OnBuild": null,
        "Labels": {
            "com.amazonaws.sagemaker.capabilities.accept-bind-to-port": "true",
            "com.amazonaws.sagemaker.capabilities.multi-models": "true",
            "com.nvidia.build.id": "170551418",
            "com.nvidia.build.ref": "30bc978a595bdf75d7117144c250a3b6c98f2f98",
            "com.nvidia.cal.version": "0.4.4.50",
            "com.nvidia.cublas.version": "12.8.4.1",
            "com.nvidia.cublasmp.version": "0.4.0.789",
            "com.nvidia.cuda.version": "9.0",
            "com.nvidia.cudnn.version": "9.8.0.87",
            "com.nvidia.cufft.version": "11.3.3.83",
            "com.nvidia.curand.version": "10.3.9.90",
            "com.nvidia.cusolver.version": "11.7.3.90",
            "com.nvidia.cusparse.version": "12.5.8.93",
            "com.nvidia.cusparselt.version": "0.7.1.0",
            "com.nvidia.nccl.version": "2.25.1",
            "com.nvidia.npp.version": "12.3.3.100",
            "com.nvidia.nsightcompute.version": "2025.1.1.2",
            "com.nvidia.nsightsystems.version": "2025.1.1.110",
            "com.nvidia.nvjpeg.version": "12.3.5.92",
            "com.nvidia.tensorrt.version": "10.9.0.34",
            "com.nvidia.tensorrtoss.version": "",
            "com.nvidia.tritonserver.version": "2.58.0",
            "com.nvidia.volumes.needed": "nvidia_driver",
            "org.opencontainers.image.ref.name": "ubuntu",
            "org.opencontainers.image.version": "24.04"
        }
    },
    "Architecture": "amd64",
    "Os": "linux",
    "Size": 32902403783,
    "GraphDriver": {
        "Data": {
            "LowerDir": "/var/lib/docker/overlay2/4c657014f4f6e926faa53f9bea92cf5d80290ac5f913139e0b5c6b6e0308ec69/diff:/var/lib/docker/overlay2/6cf2e83fb7cdc80e156143f21702429e9c4251388a65e2bdd8507ba10827b1ab/diff:/var/lib/docker/overlay2/d68ce052455b6d362ec2e5471f58799d181b64acb02f9861f486f09021ef5a21/diff:/var/lib/docker/overlay2/584d9884528d013f5a4f35f727aca42545eb567a891fe55de0df211c9585c9a2/diff:/var/lib/docker/overlay2/eaa8923dce554874d2f27e65fc8ac599f73d353d7551edc1f287e9f78c4473aa/diff:/var/lib/docker/overlay2/da95be3fd063e250264a12b65ec8030984fed7621559baded4eb351ff37b41a2/diff:/var/lib/docker/overlay2/65902f7ce37e7757a0edda070d6850159286a55dab3c4b99f2f1a905587a9c54/diff:/var/lib/docker/overlay2/fe752916bae302f3df0b3d5aff4ab8dcd7b2c831c3ccb10b735f17d78d0c6116/diff:/var/lib/docker/overlay2/572882bdeb193206be00e65dca7d1dfd03fd80dedbccc0a726146be791dfccd9/diff:/var/lib/docker/overlay2/ccda4b4ec81b5fc874b03263826427a79d066706d5e6d688367d1fd1b4fa299f/diff:/var/lib/docker/overlay2/26ca1f27cde8d0b0d7f81834650ca20ae77f235787da57ec9c7d62a4a36578a1/diff:/var/lib/docker/overlay2/2a8d273a10292843946a53e088948e658e1f47b63c2b5ac34edcba3e54f5ff1f/diff:/var/lib/docker/overlay2/adc7802007df4d8ca02174ca1b6cf8299eff4679a8a9e3db8631d5b11cde3ba2/diff:/var/lib/docker/overlay2/584a20ab8121c2082cba360c83928c79a1caefd4fe1014113f28ff65c09c8b34/diff:/var/lib/docker/overlay2/32123b1215623c439ad169e5e4070b9facb5a71002508e27769727672196af9f/diff:/var/lib/docker/overlay2/de93551187a23195a6bb75446facd8984cb909e68e0cd8e6ab1f01752f8033d7/diff:/var/lib/docker/overlay2/6d5e92a63de03cb7c3e35e272dcfcde20fae6c66ae64ce6b148af62a92967f63/diff:/var/lib/docker/overlay2/cffbd19d4243c65f9a004749e70ceda1c513c0a60b10802fa72f91fccef8de94/diff:/var/lib/docker/overlay2/4e46a9c684b9b67da76614ddfebc0665382873238fa68415b1b72337669edc0d/diff:/var/lib/docker/overlay2/65d00dc44c421aa13f431cdcbcc801cde18627706f0d6ba7c21f546282cbad6c/diff:/var/lib/docker/overlay2/4cd88444c7c3d7ba2339a308f0e8c1a4fbabec9076409f32fe1c01d3724db359/diff:/var/lib/docker/overlay2/a0d270b25702e4431082fab900e65b613b879327ee5d326ac11e19bf0ec77198/diff:/var/lib/docker/overlay2/3860cee260258c490242a197ab976ac5e28011ce24c0ba48186d97c5db678f26/diff:/var/lib/docker/overlay2/c7c0e6d60ed2493253ae91a8e4b620731307108f3511d37ef29f418bea81f488/diff:/var/lib/docker/overlay2/37900611da1d3329b0dfab7ef49ca870b5ecd44eb3993b319a44dbae356b8288/diff:/var/lib/docker/overlay2/3e26d8c5bf6c9f0558e416163c2849a60ab6ef0ea85a27b16b86ae5d626e7916/diff:/var/lib/docker/overlay2/416822a99eccca369dfca7b1e83e2d46f927aeb02e5183f1a5af03015daccf64/diff:/var/lib/docker/overlay2/642ed73db266e50ed4bb3659fcebaf983f3cec72cffe3d2a84000409982ebbbc/diff:/var/lib/docker/overlay2/bc6919c08d1345305d3f1fd25bb25f1d8050a5c64efd199f5fb4fed58529214e/diff:/var/lib/docker/overlay2/4717d63befa37dbf342244a45298b973c501cee1d90d4cbd7fe95ef1e9179992/diff:/var/lib/docker/overlay2/d3c47890c6ca80f7f840cbe7ab29a725d8ccadf2134b5b3cef5ad8cc15556006/diff:/var/lib/docker/overlay2/00e0d22d592fe3e138b1deb158f34663083a88fac3361d980d661a373ddadbf7/diff:/var/lib/docker/overlay2/2efc44afc92b96aa0b18c25224ef93ee2ee9937ca3e5cd4f9661c74803631e87/diff:/var/lib/docker/overlay2/ffe6b9e21605ba5caab6a0c979c6f71366c036b6e9cff71cd2cf38d01ec5521c/diff:/var/lib/docker/overlay2/20c4589ffb0b7df64c9ae90ef96dbb19f0e8680a20b479e2096e2994e87ebbb5/diff:/var/lib/docker/overlay2/870becfed3e101231b9eab0a50b4f3e53def2d415d18e910cf798eb6d837381f/diff:/var/lib/docker/overlay2/55c4889864cd51b903d8891be83b7f07dccf8ecc952ffc381724a46f1683e05b/diff:/var/lib/docker/overlay2/68af1e541089f9669b723262ac24e542f47658791557854b25ba08fadd19f6b2/diff:/var/lib/docker/overlay2/c8b92949bfd616ee8dcf4e60b7067d7a90684687554c9ddc09e34466ee018f4d/diff:/var/lib/docker/overlay2/5ac980978d5d60b53bedc5e6870b969664c447a3ba252ccccc31eb5933c4eb37/diff:/var/lib/docker/overlay2/18170125d9dd119ed9be91fb8dafa81c4b1cd3d247be1d6956052863ceb56174/diff:/var/lib/docker/overlay2/981a62bdd6ddbec257a3e6b1c09d367f5a02c02658a501bbf26ddca08d9bd4b4/diff:/var/lib/docker/overlay2/f446e2519276e874fc984dcb394a7db4cab94b39657185070a9d950137d310a1/diff:/var/lib/docker/overlay2/7ec686b285aaae17ef6825e7004fdf24e6c39f47463ff0e9e5df659f0da29860/diff:/var/lib/docker/overlay2/0a47f2f919a8288e4fbc1f32bc95bcb87aeb29b5532bbf1277b1f0c3daa2c029/diff:/var/lib/docker/overlay2/0adb37cb6981613240d073240009c752dcbbfbdbfb573bea1b006c13eccd539e/diff:/var/lib/docker/overlay2/e200716d274f9122e254be1f25993514009b8b35cc66473996f8b27112713ede/diff:/var/lib/docker/overlay2/de0dfea2c2f9c5a2c90d18ff8251223d34af2c679d2cd1466e4f1636a9ecf72f/diff:/var/lib/docker/overlay2/f78ca0565c166d981e13c61263ba70b7c2084dc0c05acf36d29724112b0e900e/diff:/var/lib/docker/overlay2/52ad7adc414afb8c86b664d6a8c45c4d481169babdb4489fda1bd23371f584a7/diff:/var/lib/docker/overlay2/ec89ef6efc9a1061af615a5b9a71e8c3a2071dd3e1ecb3fca396edba5674a826/diff:/var/lib/docker/overlay2/093f74e7479ed1fe28c49dadb14f88e8b04f7913216e7c1e43e2447f2387a337/diff:/var/lib/docker/overlay2/7e994cd1ac2f9730fcfcd2c0643f4ebb9d7a84ed4cfe81aff6acc8ae72954aa3/diff:/var/lib/docker/overlay2/e534e977ec17d468cde6fafc202353328c8aa02fe7d702ab9b65c45c37cb7067/diff:/var/lib/docker/overlay2/f0de65ecb97877b12e28379e5a81e4c2610ccefe3116ea6476ddb4007bb96197/diff:/var/lib/docker/overlay2/8b5c5e910228a5cb4989a35bab0dcd77bda150e7b2693b1b82d73cbed7b1c0a4/diff:/var/lib/docker/overlay2/1e1f92fdbd248665376a1f7b78745154512d19c26f91d0289315acc80ab2721e/diff:/var/lib/docker/overlay2/15c2f6f722f275a7d22acba059726c0c754906d10a35f4b9c29e971caf451e7b/diff:/var/lib/docker/overlay2/8f60fbd6d88c037177f769354ef0eb91d065a4e70a054f95af148e1fa1e7bac7/diff:/var/lib/docker/overlay2/3016eb16d28f77170a4977d37f519f764b796abf679060fdb0a082fa893bf28d/diff:/var/lib/docker/overlay2/bf63e20a7b183e0de49c61e95bcbef3949f1c8e0f7783927a1f2b0bcac856ff0/diff:/var/lib/docker/overlay2/d56277dd47323df8d9e273514ea437c09bc3b458e89d6df20afbe0c625e002f2/diff:/var/lib/docker/overlay2/23a6ccb4ba25196b347a16a6b841b11eef39d888f116700b1b1a9c6bc65609eb/diff:/var/lib/docker/overlay2/e5dd29627cee9ddb5e2dcab805019e3aea1e165a45582f23383dadc1e9e822bb/diff:/var/lib/docker/overlay2/4bc3dc85d713d7538903f978b197d26e98294a3c37c2d4467f570cbe6f50a4f9/diff:/var/lib/docker/overlay2/b7261bc1d5252720c93339d7fe92751bbc95810d71207eb1f2b65c34656bf4f7/diff:/var/lib/docker/overlay2/0d979fad1c265cae2728af520b2ef2677bd4beab8db71b99c1ec6304d450971a/diff:/var/lib/docker/overlay2/c972e59361142ffda58107946324c66bf489068732994bf3332d3498ea422c5a/diff:/var/lib/docker/overlay2/4d8d67956abbaa485c80711c4e7a3a1268dffc222305d30f3e845b97fadf6c96/diff:/var/lib/docker/overlay2/e9c25caab7b2b1e14111b2cb3a882f95d9f99b9ef7111320ebc6c8060d27bdc6/diff:/var/lib/docker/overlay2/d5ba5778451cb9d6cd53a762324cbf17a65345e17306b42b60d69ba8f9186927/diff",
            "MergedDir": "/var/lib/docker/overlay2/c4d5886388413f78cfe40fa3ca5e75104f25a6034b04eb53e500e57fc6262d9f/merged",
            "UpperDir": "/var/lib/docker/overlay2/c4d5886388413f78cfe40fa3ca5e75104f25a6034b04eb53e500e57fc6262d9f/diff",
            "WorkDir": "/var/lib/docker/overlay2/c4d5886388413f78cfe40fa3ca5e75104f25a6034b04eb53e500e57fc6262d9f/work"
        },
        "Name": "overlay2"
    },
    "RootFS": {
        "Type": "layers",
        "Layers": [
            "sha256:4b7c01ed0534d4f9be9cf97d068da1598c6c20b26cb6134fad066defdb6d541d",
            "sha256:5f70bf18a086007016e948b04aed3b82103a36bea41755b6cddfaf10ace3c6ef",
            "sha256:dd2fc1287b9cd04d69da44c57427669c4726406fd3e47d17732ba14ef98abc23",
            "sha256:41998022a4884015955a975f9e8475f1009be0373cd97da6cdaf8ea9679fed52",
            "sha256:776daa5430ec801fdb2ef2bb532d79768c4a4fb07ef2966f0f62cf374fb99659",
            "sha256:4c20946579b2a2ff121feddf8f99883bcc076decffaf8bce0b5f2a2cfe19004e",
            "sha256:9a9ae6b40127f64ee9673a11c9dcae785580c36ee6336836139b0e58b7bb89ec",
            "sha256:e13ff1e0c3d4696452ce57efb82e8084481bc71ec5fabb31570c3b34279c7173",
            "sha256:0531efbe7556461beda18906536cb1693b29fb8dcaf8bbce30ecfa2830711d82",
            "sha256:602a257195dc2e75336cca070cb6da706d7a700213c54452c2f7c3b2f194d662",
            "sha256:85cd99cc984a1e9ce1c4dd9ff478fc229ff78f501315fc840d46b215dc8dac9c",
            "sha256:cb8dab9e0d6a439e6b64da3aee7f1a0e461923cecf39a90459f1fa5907888e83",
            "sha256:2f553261fe6a36c9ecbebb82b4be68b804e86da2d72c6e82da41fd247a764bbd",
            "sha256:019700a2270e1d1bd6a8550db4736a5618edd98f4cb44abf9dcd4780761a276f",
            "sha256:475b06c642329c182a459127aa6b9c345aa380f586a211ca4887801e133f9fab",
            "sha256:598f76036e24d9da4e30361843691b120b0addf15ffac18655c0caff380daca4",
            "sha256:77ce75d929b3e1394011c450e9231ddbaf0c68ce1c1739194b25103e259568d2",
            "sha256:c5130bcff6b25170d91d75e44fac5d7994192df1287b2a9cf5c3a09adb15c3c6",
            "sha256:3410f7060b9633897dfbb006c7b57252d6c74a1a87330b126fe40b9c4c4251e5",
            "sha256:9128af80bb0bc4504a4448d15df2108bb8ec57e2cf8d4a59f35eaf30ff56787b",
            "sha256:459c708dfc571479cba89e0a74f81be5a4963f320a283e8f8d08c5683fd6af87",
            "sha256:c3c0c03b526401bb9593fc84f3befaabfa46635abcee8451107deb6ff9b4c587",
            "sha256:1c88f748045431644e6326e2f866e78b2850bcbd37ecbed391f6f9acc267b698",
            "sha256:eae9af8036fe38f22f408e349da8ef96187c548948ac085e188d0cf7014108fd",
            "sha256:5c9f063c32a7ddebbe8e7b38d9201330c48f9a85160d7a19d08a9e47e5fe54c5",
            "sha256:392f8fddde2cd9ac415b1e9230c7f9e251f159554c1c4a35987e5130abcd7dbe",
            "sha256:800eb10c160d6c10c62664582b6f197f3cca0bcecae3baf479a231e44438ead2",
            "sha256:05b6326d22f3c230b5bec59d5f44ff8924030acd56590ab4428a1737d77ae0e1",
            "sha256:481c5ccb970328cb1997a16a6c9743f280850663d14d7c4fcb96e0665885ae27",
            "sha256:2b9dcc0324be7f52f50cc304d51a1ebfb8945c9013631c00f31df44034bf1890",
            "sha256:fbb49643d7f408bd9f70e08036b63cfd2e381a56684334ec9ba15dbe51c46183",
            "sha256:6940733d84421a1b397bc3d8dc751dc2a6478285cc0c1ec57538f505956ef6e4",
            "sha256:4e8f367fef68140b608fb6c5e56bfd00bd2222faaf75986f81c2b918dfef0038",
            "sha256:ce2fafb810f77349848e6c66c3b8600d04d12f60bcff340d94afc092a68d4579",
            "sha256:b8876c9cef7724af2ae0609bdb6e140dc4e9817ee9997a8bc452eab831b715f9",
            "sha256:e88cfaedabaebb66b10ec6bb4b4541bd7a9c6a83f0c9197b064a14c2131a6f7d",
            "sha256:86bf043a6b740c9774e6fe13ce154bf9df3227370635f24f40f446e431e45fd1",
            "sha256:9a4bd4cf234b2aed9059f0d11fc5906c751c43ce61727eb142c55c58ea45bb4f",
            "sha256:7fbabddab8c1de9a193ccbd514e5261d5e412882460ad46c6087fb67487639a0",
            "sha256:9719c5bba4f7634e4cfe64be7d152dd4df7f37f4e7627af1724fd773687281ba",
            "sha256:f0f89e82017be5db86f3b40a74d48c00e33e7c9c667d624f959ff25c9788f2c4",
            "sha256:9085e096baf2b609c2ee47e083717c359a08f6449b8d5d0d2270e7e07262b25a",
            "sha256:273d15ab573182451ce02abda8aa8579cbaebb41b1059fd4e9f03bd54f5ee642",
            "sha256:fd9892ab0286831216a2a9ae221f6f9ef3ae0afba42754b45574e75ab1e63e51",
            "sha256:5f70bf18a086007016e948b04aed3b82103a36bea41755b6cddfaf10ace3c6ef",
            "sha256:fb21bf85670137f77d9e0e4009ce5191deb51e99a569ce432137308d11619635",
            "sha256:ea350f634417085898be0a0b12edaef5f11cc5934ac30944acfbdde2b04e75cc",
            "sha256:33053e6fed10d703ec974d0736c7dbc667f3b4b99b4aecf3cea5e391c2c6e66f",
            "sha256:5027b92a8e595539bd68fb061171a1b8d76ff3988a844a03c409316510e991fb",
            "sha256:09ff919b659d89d1f86344987b969c14f3b5be9f053cd3d42273e7cc4d12d538",
            "sha256:8a9ab181431628698d118b5c7792ee69b75b4e06173447173a682f1b77d3a3d6",
            "sha256:7f03999f1dcaa09f703bd2d74fe84916dac202d30772a26d656cacabd105c690",
            "sha256:5c925fd31d1efebaf7ec29b9f064ee2738f544843ae03d7490d5501105745a25",
            "sha256:59e50cbfc5a47c285af6fbbbeb11293411748264738ba409a7bb5d52737687ab",
            "sha256:c3278d36d10f0b31e87bce16504946069f7a78427d121651da91f3bd1031a3b1",
            "sha256:d4be87946f889eaa47d9235307cfc1eaebfac4be0719d10d5624163fd2d14991",
            "sha256:7b191c32c787c78bea5b833e07748501a29298975c8d2846e81446b57ad9cee7",
            "sha256:7cf6f6571548d44d44319270cb0ada65d2c35b7fa2ba6e36d5a7a975b6afc1f3",
            "sha256:4f34e8e93b41c057f380fa49de3d1c38d6a76607d691395237e5cf349be4995d",
            "sha256:548df57a2c74ce7a3acc0f208e74af9594e38cb70766b68a5d98ffc9a40ff870",
            "sha256:5f70bf18a086007016e948b04aed3b82103a36bea41755b6cddfaf10ace3c6ef",
            "sha256:0c7b409f4165b20489340b0f1e22d6a4aa78e30a4fb01f0efd1d725abe4094c7",
            "sha256:5f70bf18a086007016e948b04aed3b82103a36bea41755b6cddfaf10ace3c6ef",
            "sha256:76bf1d67feb1b9f20a55941f1d141f0d4cf3b5616214045ac0cc59c7c7d85df3",
            "sha256:5f70bf18a086007016e948b04aed3b82103a36bea41755b6cddfaf10ace3c6ef",
            "sha256:b2bcab6b7975fe4992ecaa304df14ed6c1f8b70cf7cb268746bd18bfafe304e4",
            "sha256:06037b9685c4d4fd37500f8bf35f03601fb6b6eea929804a29daa5e189463fac",
            "sha256:80a4f70a41d6cface4d9416d77529ec9ca6e0c82a9860d4f9f725d8e26fe4ec2",
            "sha256:155cec503db13f6d6642031d7e3656b9b6335edc3bf43595cb41c6c2875f74b3",
            "sha256:787f103939a19c5cc4ebc052fc98af24d49500a8d707750b0b0f938ab854df79",
            "sha256:2817b92159062f5516cc3200711e400e739c722c3fa869763f4029935a5cf650",
            "sha256:40ba69f0c90a4eb27c6a54864476a6c8f5ef81fdf9afad56d934daf18d21a84b"
        ]
    },
    "Metadata": {
        "LastTagTime": "2025-06-09T03:41:08.780769657+08:00"
    }
}

更多版本

docker.io/nvcr.io/nvidia/tritonserver:24.11-trtllm-python-py3

linux/amd64 docker.io24.86GB2025-02-26 02:25
361

docker.io/nvcr.io/nvidia/tritonserver:25.04-py3

linux/amd64 docker.io19.59GB2025-05-22 00:46
162

docker.io/nvcr.io/nvidia/tritonserver:25.02-trtllm-python-py3

linux/amd64 docker.io30.15GB2025-05-25 02:51
58

docker.io/nvcr.io/nvidia/tritonserver:22.12-py3

linux/amd64 docker.io14.00GB2025-06-04 06:32
26

docker.io/nvcr.io/nvidia/tritonserver:25.05-trtllm-python-py3

linux/amd64 docker.io32.90GB2025-06-09 03:41
9