docker.io/nvcr.io/nvidia/tritonserver:25.02-trtllm-python-py3 linux/amd64

docker.io/nvcr.io/nvidia/tritonserver:25.02-trtllm-python-py3 - 国内下载镜像源 浏览次数:81

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:25.02-trtllm-python-py3
国内镜像 swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/nvcr.io/nvidia/tritonserver:25.02-trtllm-python-py3
镜像ID sha256:3299eb2f17b07df56cd73fc20ae4319d06153c8b7c3bbf038dce90e23830571a
镜像TAG 25.02-trtllm-python-py3
大小 30.15GB
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 81 次
贡献者 31*******4@qq.com
镜像创建 2025-02-26T01:16:49.301876747Z
同步时间 2025-05-25 02:51
更新时间 2025-06-19 17:33
环境变量
PATH=/opt/tritonserver/bin:/usr/local/mpi/bin:/usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/local/ucx/bin:/opt/amazon/efa/bin CUDA_VERSION=12.8.0.038 CUDA_DRIVER_VERSION=570.86.10 CUDA_CACHE_DISABLE=1 NVIDIA_REQUIRE_JETPACK_HOST_MOUNTS= _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=12.8.3.14 CUFFT_VERSION=11.3.3.41 CURAND_VERSION=10.3.9.55 CUSPARSE_VERSION=12.5.7.53 CUSPARSELT_VERSION=0.6.3.2 CUSOLVER_VERSION=11.7.2.55 CUTENSOR_VERSION=2.1.0.9 NPP_VERSION=12.3.3.65 NVJPEG_VERSION=12.3.5.57 CUFILE_VERSION=1.13.0.11 NVJITLINK_VERSION=12.8.61 CUDNN_VERSION=9.7.1.26 CUDNN_FRONTEND_VERSION=1.10.0 TRT_VERSION=10.8.0.43 TRTOSS_VERSION= NSIGHT_SYSTEMS_VERSION=2025.1.1.65 NSIGHT_COMPUTE_VERSION=2025.1.0.14 DALI_VERSION=1.46.0 DALI_BUILD= DALI_URL_SUFFIX=120 POLYGRAPHY_VERSION=0.49.18 TRANSFORMER_ENGINE_VERSION=2.0 MODEL_OPT_VERSION=0.23.0 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 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 LIBRARY_PATH=/usr/local/cuda/lib64/stubs: CUDA_VER=12.8.0.038 NVRTC_VER=12.8.61-1 PIP_BREAK_SYSTEM_PACKAGES=1 TRT_ROOT=/usr/local/tensorrt TRITON_SERVER_VERSION=2.55.0 NVIDIA_TRITON_SERVER_VERSION=25.02 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=144783146
镜像标签
true: com.amazonaws.sagemaker.capabilities.accept-bind-to-port true: com.amazonaws.sagemaker.capabilities.multi-models 144783146: com.nvidia.build.id f8aa0dfefe498a23d2c7ebf1e2b9254793a59dc3: com.nvidia.build.ref 12.8.3.14: com.nvidia.cublas.version 9.0: com.nvidia.cuda.version 9.7.1.26: com.nvidia.cudnn.version 11.3.3.41: com.nvidia.cufft.version 10.3.9.55: com.nvidia.curand.version 11.7.2.55: com.nvidia.cusolver.version 12.5.7.53: com.nvidia.cusparse.version 0.6.3.2: com.nvidia.cusparselt.version 2.1.0.9: com.nvidia.cutensor.version 2.25.1: com.nvidia.nccl.version 12.3.3.65: com.nvidia.npp.version 2025.1.0.14: com.nvidia.nsightcompute.version 2025.1.1.65: com.nvidia.nsightsystems.version 12.3.5.57: com.nvidia.nvjpeg.version 10.8.0.43: com.nvidia.tensorrt.version : com.nvidia.tensorrtoss.version 2.55.0: 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:25.02-trtllm-python-py3
docker tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/nvcr.io/nvidia/tritonserver:25.02-trtllm-python-py3  docker.io/nvcr.io/nvidia/tritonserver:25.02-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:25.02-trtllm-python-py3
ctr images tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/nvcr.io/nvidia/tritonserver:25.02-trtllm-python-py3  docker.io/nvcr.io/nvidia/tritonserver:25.02-trtllm-python-py3

Shell快速替换命令

sed -i 's#nvcr.io/nvidia/tritonserver:25.02-trtllm-python-py3#swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/nvcr.io/nvidia/tritonserver:25.02-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:25.02-trtllm-python-py3 && docker tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/nvcr.io/nvidia/tritonserver:25.02-trtllm-python-py3  docker.io/nvcr.io/nvidia/tritonserver:25.02-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:25.02-trtllm-python-py3 && ctr images tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/nvcr.io/nvidia/tritonserver:25.02-trtllm-python-py3  docker.io/nvcr.io/nvidia/tritonserver:25.02-trtllm-python-py3'

镜像构建历史


# 2025-02-26 09:16:49  75.93MB 复制新文件或目录到容器中
COPY /opt/hpcx/ompi /opt/hpcx/ompi # buildkit
                        
# 2025-02-26 09:16:49  0.00B 执行命令并创建新的镜像层
RUN |2 TRITON_VERSION=2.55.0 TRITON_CONTAINER_VERSION=25.02 /bin/sh -c rm -fr /opt/hpcx/ompi # buildkit
                        
# 2025-02-26 09:16:48  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
                        
# 2025-02-26 09:16:48  22.27MB 执行命令并创建新的镜像层
RUN |2 TRITON_VERSION=2.55.0 TRITON_CONTAINER_VERSION=25.02 /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
                        
# 2025-02-26 09:16:44  8.37KB 复制新文件或目录到容器中
COPY docker/sagemaker/serve /usr/bin/. # buildkit
                        
# 2025-02-26 09:16:44  0.00B 添加元数据标签
LABEL com.amazonaws.sagemaker.capabilities.multi-models=true
                        
# 2025-02-26 09:16:44  0.00B 添加元数据标签
LABEL com.amazonaws.sagemaker.capabilities.accept-bind-to-port=true
                        
# 2025-02-26 09:16:44  5.94MB 执行命令并创建新的镜像层
RUN |2 TRITON_VERSION=2.55.0 TRITON_CONTAINER_VERSION=25.02 /bin/sh -c pip3 install -r python/openai/requirements.txt # buildkit
                        
# 2025-02-26 09:16:41  313.39MB 执行命令并创建新的镜像层
RUN |2 TRITON_VERSION=2.55.0 TRITON_CONTAINER_VERSION=25.02 /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
                        
# 2025-02-26 09:16:36  3.01MB 复制新文件或目录到容器中
COPY NVIDIA_Deep_Learning_Container_License.pdf . # buildkit
                        
# 2025-02-26 09:16:36  0.00B 设置工作目录为/opt/tritonserver
WORKDIR /opt/tritonserver
                        
# 2025-02-26 09:16:36  543.15MB 复制新文件或目录到容器中
COPY build/install tritonserver # buildkit
                        
# 2025-02-26 09:16:35  0.00B 设置工作目录为/opt
WORKDIR /opt
                        
# 2025-02-26 09:16:35  0.00B 添加元数据标签
LABEL com.nvidia.build.ref=f8aa0dfefe498a23d2c7ebf1e2b9254793a59dc3
                        
# 2025-02-26 09:16:35  0.00B 添加元数据标签
LABEL com.nvidia.build.id=144783146
                        
# 2025-02-26 09:16:35  0.00B 设置环境变量 NVIDIA_BUILD_ID
ENV NVIDIA_BUILD_ID=144783146
                        
# 2025-02-26 09:16:35  733.00B 复制新文件或目录到容器中
COPY docker/entrypoint.d/ /opt/nvidia/entrypoint.d/ # buildkit
                        
# 2025-02-26 09:16:35  0.00B 设置环境变量 NVIDIA_PRODUCT_NAME
ENV NVIDIA_PRODUCT_NAME=Triton Server
                        
# 2025-02-26 09:16:35  0.00B 执行命令并创建新的镜像层
RUN |2 TRITON_VERSION=2.55.0 TRITON_CONTAINER_VERSION=25.02 /bin/sh -c rm -fr /opt/tritonserver/* # buildkit
                        
# 2025-02-26 09:16:35  0.00B 设置工作目录为/opt/tritonserver
WORKDIR /opt/tritonserver
                        
# 2025-02-26 09:16:35  0.00B 执行命令并创建新的镜像层
RUN |2 TRITON_VERSION=2.55.0 TRITON_CONTAINER_VERSION=25.02 /bin/sh -c apt-get update     && apt-get install -y --no-install-recommends         openssh-client     && rm -rf /var/lib/apt/lists/* # buildkit
                        
# 2025-02-26 09:16:31  76.58MB 执行命令并创建新的镜像层
RUN |2 TRITON_VERSION=2.55.0 TRITON_CONTAINER_VERSION=25.02 /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
                        
# 2025-02-26 09:16:24  60.49KB 执行命令并创建新的镜像层
RUN |2 TRITON_VERSION=2.55.0 TRITON_CONTAINER_VERSION=25.02 /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
                        
# 2025-02-26 09:16:24  1.75GB 执行命令并创建新的镜像层
RUN |2 TRITON_VERSION=2.55.0 TRITON_CONTAINER_VERSION=25.02 /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
                        
# 2025-02-26 09:16:00  0.00B 设置环境变量 DCGM_VERSION
ENV DCGM_VERSION=3.3.6
                        
# 2025-02-26 09:16:00  0.00B 设置环境变量 TCMALLOC_RELEASE_RATE
ENV TCMALLOC_RELEASE_RATE=200
                        
# 2025-02-26 09:16:00  347.20MB 执行命令并创建新的镜像层
RUN |2 TRITON_VERSION=2.55.0 TRITON_CONTAINER_VERSION=25.02 /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
                        
# 2025-02-26 09:15:42  0.00B 设置环境变量 DEBIAN_FRONTEND
ENV DEBIAN_FRONTEND=noninteractive
                        
# 2025-02-26 09:15:42  4.49KB 执行命令并创建新的镜像层
RUN |2 TRITON_VERSION=2.55.0 TRITON_CONTAINER_VERSION=25.02 /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
                        
# 2025-02-26 09:15:42  0.00B 设置环境变量 TRITON_SERVER_USER
ENV TRITON_SERVER_USER=triton-server
                        
# 2025-02-26 09:15:42  0.00B 设置环境变量 TRITON_SERVER_GPU_ENABLED
ENV TRITON_SERVER_GPU_ENABLED=1
                        
# 2025-02-26 09:15:42  0.00B 设置环境变量 TF_AUTOTUNE_THRESHOLD
ENV TF_AUTOTUNE_THRESHOLD=2
                        
# 2025-02-26 09:15:42  0.00B 设置环境变量 TF_ENABLE_WINOGRAD_NONFUSED
ENV TF_ENABLE_WINOGRAD_NONFUSED=1
                        
# 2025-02-26 09:15:42  0.00B 设置环境变量 TF_ADJUST_SATURATION_FUSED
ENV TF_ADJUST_SATURATION_FUSED=1
                        
# 2025-02-26 09:15:42  0.00B 设置环境变量 TF_ADJUST_HUE_FUSED
ENV TF_ADJUST_HUE_FUSED=1
                        
# 2025-02-26 09:15:42  0.00B 设置环境变量 UCX_MEM_EVENTS
ENV UCX_MEM_EVENTS=no
                        
# 2025-02-26 09:15:42  0.00B 设置环境变量 PATH
ENV PATH=/opt/tritonserver/bin:/usr/local/mpi/bin:/usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/local/ucx/bin:/opt/amazon/efa/bin
                        
# 2025-02-26 09:15:42  0.00B 添加元数据标签
LABEL com.nvidia.tritonserver.version=2.55.0
                        
# 2025-02-26 09:15:42  0.00B 设置环境变量 NVIDIA_TRITON_SERVER_VERSION
ENV NVIDIA_TRITON_SERVER_VERSION=25.02
                        
# 2025-02-26 09:15:42  0.00B 设置环境变量 TRITON_SERVER_VERSION
ENV TRITON_SERVER_VERSION=2.55.0
                        
# 2025-02-26 09:15:42  0.00B 定义构建参数
ARG TRITON_CONTAINER_VERSION
                        
# 2025-02-26 09:15:42  0.00B 定义构建参数
ARG TRITON_VERSION
                        
# 2025-02-26 09:15:42  0.00B 设置环境变量 PIP_BREAK_SYSTEM_PACKAGES
ENV PIP_BREAK_SYSTEM_PACKAGES=1
                        
# 2025-02-26 08:33:37  6.58MB 复制新文件或目录到容器中
COPY tensorrt_llm/examples examples # buildkit
                        
# 2025-02-26 08:33:37  610.64KB 复制新文件或目录到容器中
COPY tools tools # buildkit
                        
# 2025-02-26 08:33:37  90.98KB 复制新文件或目录到容器中
COPY inflight_batcher_llm/client client # buildkit
                        
# 2025-02-26 08:33:37  386.03KB 复制新文件或目录到容器中
COPY all_models all_models # buildkit
                        
# 2025-02-26 08:33:37  6.82KB 复制新文件或目录到容器中
COPY scripts scripts # buildkit
                        
# 2025-02-26 08:33:37  0.00B 设置工作目录为/app
WORKDIR /app
                        
# 2025-02-26 08:33:37  5.71GB 执行命令并创建新的镜像层
RUN |2 NVRTC_VER=12.8.61-1 TRT_VER=10.8.0.43 /bin/sh -c pip3 install --no-cache-dir tensorrt_llm*.whl &&     rm -f tensorrt_llm*.whl # buildkit
                        
# 2025-02-26 08:32:03  2.86GB 复制新文件或目录到容器中
COPY /workspace/tensorrt_llm/build/tensorrt_llm*whl . # buildkit
                        
# 2025-02-26 07:06:43  0.00B 设置工作目录为/tmp
WORKDIR /tmp
                        
# 2025-02-26 07:06:43  0.00B 设置环境变量 TRT_ROOT
ENV TRT_ROOT=/usr/local/tensorrt
                        
# 2025-02-26 07:06:43  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
                        
# 2025-02-26 07:06:43  0.00B 设置环境变量 TRT_VERSION
ENV TRT_VERSION=10.8.0.43
                        
# 2025-02-26 07:06:43  0.00B 定义构建参数
ARG TRT_VER=10.8.0.43
                        
# 2025-02-26 07:06:43  4.67MB 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
                        
# 2025-02-26 07:06:43  3.03GB 复制新文件或目录到容器中
COPY /usr/local/tensorrt /usr/local/tensorrt # buildkit
                        
# 2025-02-26 07:05:24  261.11MB 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
                        
# 2025-02-26 07:05:16  121.47MB 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
                        
# 2025-02-26 07:05:16  0.00B 设置环境变量 PIP_BREAK_SYSTEM_PACKAGES
ENV PIP_BREAK_SYSTEM_PACKAGES=1
                        
# 2025-02-26 07:05:16  0.00B 设置环境变量 CUDA_VER NVRTC_VER
ENV CUDA_VER=12.8.0.038 NVRTC_VER=12.8.61-1
                        
# 2025-02-26 07:05:16  0.00B 定义构建参数
ARG NVRTC_VER=12.8.61-1
                        
# 2025-02-26 07:04:14  455.86MB 复制新文件或目录到容器中
COPY /usr/local/cuda/lib64/libcusparseLt* /usr/local/cuda/lib64/ # buildkit
                        
# 2025-02-26 07:04:13  17.91KB 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
                        
# 2025-02-26 07:04:13  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
                        
# 2025-02-26 07:04:13  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
                        
# 2025-02-26 07:04:13  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
                        
# 2025-02-26 07:04:13  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
                        
# 2025-02-26 07:04:13  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
                        
# 2025-02-26 07:04:13  8.30KB 复制新文件或目录到容器中
COPY /usr/local/lib/python3.12/dist-packages/jinja2-3.1.4.dist-info /usr/local/lib/python3.12/dist-packages/jinja2-3.1.4.dist-info # buildkit
                        
# 2025-02-26 07:04:13  1.15MB 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
                        
# 2025-02-26 07:04:13  568.01MB 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
                        
# 2025-02-26 07:04:12  39.14KB 复制新文件或目录到容器中
COPY /usr/local/lib/python3.12/dist-packages/pytorch_triton-3.1.0+cf34004b8.internal.dist-info /usr/local/lib/python3.12/dist-packages/pytorch_triton-3.1.0+cf34004b8.internal.dist-info # buildkit
                        
# 2025-02-26 07:04:12  300.14KB 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
                        
# 2025-02-26 07:04:12  53.78KB 复制新文件或目录到容器中
COPY /usr/local/lib/python3.12/dist-packages/setuptools-70.3.0.dist-info /usr/local/lib/python3.12/dist-packages/setuptools-70.3.0.dist-info # buildkit
                        
# 2025-02-26 07:04:12  5.11MB 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
                        
# 2025-02-26 07:04:12  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
                        
# 2025-02-26 07:04:12  48.90KB 复制新文件或目录到容器中
COPY /usr/local/lib/python3.12/dist-packages/torchvision-0.20.0a0.dist-info /usr/local/lib/python3.12/dist-packages/torchvision-0.20.0a0.dist-info # buildkit
                        
# 2025-02-26 07:04:12  14.27MB 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
                        
# 2025-02-26 07:04:12  3.26MB 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
                        
# 2025-02-26 07:04:12  1.85MB 复制新文件或目录到容器中
COPY /usr/local/lib/python3.12/dist-packages/torch-2.6.0a0+ecf3bae40a.nv25.1.dist-info /usr/local/lib/python3.12/dist-packages/torch-2.6.0a0+ecf3bae40a.nv25.1.dist-info # buildkit
                        
# 2025-02-26 07:04:12  2.02GB 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
                        
# 2025-02-26 07:04:08  1.85GB 复制新文件或目录到容器中
COPY /usr/local/lib/lib* /usr/local/lib/ # buildkit
                        
# 2025-02-20 04:36:33  39.98KB 执行命令并创建新的镜像层
RUN |9 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 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
                        
# 2025-02-20 04:36:33  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
                        
# 2025-02-20 04:36:22  0.00B 设置环境变量 LIBRARY_PATH
ENV LIBRARY_PATH=/usr/local/cuda/lib64/stubs:
                        
# 2025-02-20 04:36:22  1.02GB 执行命令并创建新的镜像层
RUN |9 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 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/installCUTENSOR.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
                        
# 2025-02-20 04:33:51  1.49KB 复制新文件或目录到容器中
COPY cuda-*.patch /tmp # buildkit
                        
# 2025-02-20 04:33:51  0.00B 设置环境变量 OMPI_MCA_coll_hcoll_enable
ENV OMPI_MCA_coll_hcoll_enable=0
                        
# 2025-02-20 04:33:51  0.00B 设置环境变量 OPAL_PREFIX PATH
ENV OPAL_PREFIX=/opt/hpcx/ompi PATH=/usr/local/mpi/bin:/usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/local/ucx/bin:/opt/amazon/efa/bin
                        
# 2025-02-20 04:33:51  227.51MB 执行命令并创建新的镜像层
RUN |9 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
                        
# 2025-02-20 04:33:51  0.00B 定义构建参数
ARG TARGETARCH=amd64
                        
# 2025-02-20 04:33:51  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
                        
# 2025-02-20 04:33:51  0.00B 定义构建参数
ARG AWS_OFI_NCCL_VERSION=1.12.1
                        
# 2025-02-20 04:33:51  0.00B 定义构建参数
ARG EFA_VERSION=1.34.0
                        
# 2025-02-20 04:33:51  0.00B 定义构建参数
ARG OPENMPI_VERSION=4.1.7
                        
# 2025-02-20 04:33:51  0.00B 定义构建参数
ARG OPENUCX_VERSION=1.18.0
                        
# 2025-02-20 04:33:51  0.00B 定义构建参数
ARG MOFED_VERSION=5.4-rdmacore50.0
                        
# 2025-02-20 04:33:51  0.00B 定义构建参数
ARG RDMACORE_VERSION=50.0
                        
# 2025-02-20 04:33:51  0.00B 定义构建参数
ARG HPCX_VERSION=2.22.1
                        
# 2025-02-20 04:33:51  0.00B 定义构建参数
ARG GDRCOPY_VERSION=2.4.1
                        
# 2025-02-20 04:33:45  101.51MB 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
                        
# 2025-02-20 04:17:33  148.72KB 复制新文件或目录到容器中
COPY NVIDIA_Deep_Learning_Container_License.pdf /workspace/ # buildkit
                        
# 2025-02-20 04:17:33  0.00B 配置容器启动时运行的命令
ENTRYPOINT ["/opt/nvidia/nvidia_entrypoint.sh"]
                        
# 2025-02-20 04:17:33  0.00B 设置环境变量 NVIDIA_PRODUCT_NAME
ENV NVIDIA_PRODUCT_NAME=CUDA
                        
# 2025-02-20 04:17:33  15.93KB 复制新文件或目录到容器中
COPY entrypoint/ /opt/nvidia/ # buildkit
                        
# 2025-02-20 04:17:33  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/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/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
                        
# 2025-02-20 04:17:33  0.00B 定义构建参数
ARG _LIBPATH_SUFFIX=
                        
# 2025-02-20 04:17:33  46.00B 执行命令并创建新的镜像层
RUN |27 CUDA_VERSION=12.8.0.038 CUDA_DRIVER_VERSION=570.86.10 JETPACK_HOST_MOUNTS= NCCL_VERSION=2.25.1 CUBLAS_VERSION=12.8.3.14 CUFFT_VERSION=11.3.3.41 CURAND_VERSION=10.3.9.55 CUSPARSE_VERSION=12.5.7.53 CUSOLVER_VERSION=11.7.2.55 CUTENSOR_VERSION=2.1.0.9 NPP_VERSION=12.3.3.65 NVJPEG_VERSION=12.3.5.57 CUFILE_VERSION=1.13.0.11 NVJITLINK_VERSION=12.8.61 CUDNN_VERSION=9.7.1.26 CUDNN_FRONTEND_VERSION=1.10.0 TRT_VERSION=10.8.0.43 TRTOSS_VERSION= NSIGHT_SYSTEMS_VERSION=2025.1.1.65 NSIGHT_COMPUTE_VERSION=2025.1.0.14 CUSPARSELT_VERSION=0.6.3.2 DALI_VERSION=1.46.0 DALI_BUILD= DALI_URL_SUFFIX=120 POLYGRAPHY_VERSION=0.49.18 TRANSFORMER_ENGINE_VERSION=2.0 MODEL_OPT_VERSION=0.23.0 /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
                        
# 2025-02-20 04:17:33  13.39KB 复制文件或目录到容器中
ADD docs.tgz / # buildkit
                        
# 2025-02-20 04:17:33  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=1.46.0 DALI_BUILD= DALI_URL_SUFFIX=120 POLYGRAPHY_VERSION=0.49.18 TRANSFORMER_ENGINE_VERSION=2.0 MODEL_OPT_VERSION=0.23.0
                        
# 2025-02-20 04:17:33  0.00B 定义构建参数
ARG MODEL_OPT_VERSION=0.23.0
                        
# 2025-02-20 04:17:33  0.00B 定义构建参数
ARG TRANSFORMER_ENGINE_VERSION=2.0
                        
# 2025-02-20 04:17:33  0.00B 定义构建参数
ARG POLYGRAPHY_VERSION=0.49.18
                        
# 2025-02-20 04:17:33  0.00B 定义构建参数
ARG DALI_URL_SUFFIX=120
                        
# 2025-02-20 04:17:33  0.00B 定义构建参数
ARG DALI_BUILD=
                        
# 2025-02-20 04:17:33  0.00B 定义构建参数
ARG DALI_VERSION=1.46.0
                        
# 2025-02-20 04:17:33  0.00B 添加元数据标签
LABEL com.nvidia.nccl.version=2.25.1 com.nvidia.cublas.version=12.8.3.14 com.nvidia.cufft.version=11.3.3.41 com.nvidia.curand.version=10.3.9.55 com.nvidia.cusparse.version=12.5.7.53 com.nvidia.cusparselt.version=0.6.3.2 com.nvidia.cusolver.version=11.7.2.55 com.nvidia.cutensor.version=2.1.0.9 com.nvidia.npp.version=12.3.3.65 com.nvidia.nvjpeg.version=12.3.5.57 com.nvidia.cudnn.version=9.7.1.26 com.nvidia.tensorrt.version=10.8.0.43 com.nvidia.tensorrtoss.version= com.nvidia.nsightsystems.version=2025.1.1.65 com.nvidia.nsightcompute.version=2025.1.0.14
                        
# 2025-02-20 04:17:33  7.47GB 执行命令并创建新的镜像层
RUN |21 CUDA_VERSION=12.8.0.038 CUDA_DRIVER_VERSION=570.86.10 JETPACK_HOST_MOUNTS= NCCL_VERSION=2.25.1 CUBLAS_VERSION=12.8.3.14 CUFFT_VERSION=11.3.3.41 CURAND_VERSION=10.3.9.55 CUSPARSE_VERSION=12.5.7.53 CUSOLVER_VERSION=11.7.2.55 CUTENSOR_VERSION=2.1.0.9 NPP_VERSION=12.3.3.65 NVJPEG_VERSION=12.3.5.57 CUFILE_VERSION=1.13.0.11 NVJITLINK_VERSION=12.8.61 CUDNN_VERSION=9.7.1.26 CUDNN_FRONTEND_VERSION=1.10.0 TRT_VERSION=10.8.0.43 TRTOSS_VERSION= NSIGHT_SYSTEMS_VERSION=2025.1.1.65 NSIGHT_COMPUTE_VERSION=2025.1.0.14 CUSPARSELT_VERSION=0.6.3.2 /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/installCUTENSOR.sh  && /nvidia/build-scripts/installCUSPARSELT.sh  && if [ -z "${JETPACK_HOST_MOUNTS}" ]; then       /nvidia/build-scripts/installNCCL.sh;     fi; # buildkit
                        
# 2025-02-20 01:56:08  0.00B 设置环境变量 NCCL_VERSION CUBLAS_VERSION CUFFT_VERSION CURAND_VERSION CUSPARSE_VERSION CUSPARSELT_VERSION CUSOLVER_VERSION CUTENSOR_VERSION NPP_VERSION NVJPEG_VERSION CUFILE_VERSION NVJITLINK_VERSION CUDNN_VERSION CUDNN_FRONTEND_VERSION TRT_VERSION TRTOSS_VERSION NSIGHT_SYSTEMS_VERSION NSIGHT_COMPUTE_VERSION
ENV NCCL_VERSION=2.25.1 CUBLAS_VERSION=12.8.3.14 CUFFT_VERSION=11.3.3.41 CURAND_VERSION=10.3.9.55 CUSPARSE_VERSION=12.5.7.53 CUSPARSELT_VERSION=0.6.3.2 CUSOLVER_VERSION=11.7.2.55 CUTENSOR_VERSION=2.1.0.9 NPP_VERSION=12.3.3.65 NVJPEG_VERSION=12.3.5.57 CUFILE_VERSION=1.13.0.11 NVJITLINK_VERSION=12.8.61 CUDNN_VERSION=9.7.1.26 CUDNN_FRONTEND_VERSION=1.10.0 TRT_VERSION=10.8.0.43 TRTOSS_VERSION= NSIGHT_SYSTEMS_VERSION=2025.1.1.65 NSIGHT_COMPUTE_VERSION=2025.1.0.14
                        
# 2025-02-20 01:56:08  0.00B 定义构建参数
ARG CUSPARSELT_VERSION=0.6.3.2
                        
# 2025-02-20 01:56:08  0.00B 定义构建参数
ARG NSIGHT_COMPUTE_VERSION=2025.1.0.14
                        
# 2025-02-20 01:56:08  0.00B 定义构建参数
ARG NSIGHT_SYSTEMS_VERSION=2025.1.1.65
                        
# 2025-02-20 01:56:08  0.00B 定义构建参数
ARG TRTOSS_VERSION=
                        
# 2025-02-20 01:56:08  0.00B 定义构建参数
ARG TRT_VERSION=10.8.0.43
                        
# 2025-02-20 01:56:08  0.00B 定义构建参数
ARG CUDNN_FRONTEND_VERSION=1.10.0
                        
# 2025-02-20 01:56:08  0.00B 定义构建参数
ARG CUDNN_VERSION=9.7.1.26
                        
# 2025-02-20 01:56:08  0.00B 定义构建参数
ARG NVJITLINK_VERSION=12.8.61
                        
# 2025-02-20 01:56:08  0.00B 定义构建参数
ARG CUFILE_VERSION=1.13.0.11
                        
# 2025-02-20 01:56:08  0.00B 定义构建参数
ARG NVJPEG_VERSION=12.3.5.57
                        
# 2025-02-20 01:56:08  0.00B 定义构建参数
ARG NPP_VERSION=12.3.3.65
                        
# 2025-02-20 01:56:08  0.00B 定义构建参数
ARG CUTENSOR_VERSION=2.1.0.9
                        
# 2025-02-20 01:56:08  0.00B 定义构建参数
ARG CUSOLVER_VERSION=11.7.2.55
                        
# 2025-02-20 01:56:08  0.00B 定义构建参数
ARG CUSPARSE_VERSION=12.5.7.53
                        
# 2025-02-20 01:56:08  0.00B 定义构建参数
ARG CURAND_VERSION=10.3.9.55
                        
# 2025-02-20 01:56:08  0.00B 定义构建参数
ARG CUFFT_VERSION=11.3.3.41
                        
# 2025-02-20 01:56:08  0.00B 定义构建参数
ARG CUBLAS_VERSION=12.8.3.14
                        
# 2025-02-20 01:56:08  0.00B 定义构建参数
ARG NCCL_VERSION=2.25.1
                        
# 2025-02-20 01:56:08  0.00B 添加元数据标签
LABEL com.nvidia.volumes.needed=nvidia_driver com.nvidia.cuda.version=9.0
                        
# 2025-02-20 01:56:08  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
                        
# 2025-02-20 01:56:08  59.18KB 执行命令并创建新的镜像层
RUN |3 CUDA_VERSION=12.8.0.038 CUDA_DRIVER_VERSION=570.86.10 JETPACK_HOST_MOUNTS= /bin/sh -c cp -vprd /nvidia/. /  &&  patch -p0 < /etc/startup_scripts.patch  &&  rm -f /etc/startup_scripts.patch # buildkit
                        
# 2025-02-20 01:56:08  767.71MB 执行命令并创建新的镜像层
RUN |3 CUDA_VERSION=12.8.0.038 CUDA_DRIVER_VERSION=570.86.10 JETPACK_HOST_MOUNTS= /bin/sh -c /nvidia/build-scripts/installCUDA.sh # buildkit
                        
# 2025-02-20 01:55:59  0.00B 执行命令并创建新的镜像层
RUN |3 CUDA_VERSION=12.8.0.038 CUDA_DRIVER_VERSION=570.86.10 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
                        
# 2025-02-20 01:55:59  0.00B 设置环境变量 CUDA_VERSION CUDA_DRIVER_VERSION CUDA_CACHE_DISABLE NVIDIA_REQUIRE_JETPACK_HOST_MOUNTS
ENV CUDA_VERSION=12.8.0.038 CUDA_DRIVER_VERSION=570.86.10 CUDA_CACHE_DISABLE=1 NVIDIA_REQUIRE_JETPACK_HOST_MOUNTS=
                        
# 2025-02-20 01:55:59  0.00B 定义构建参数
ARG JETPACK_HOST_MOUNTS=
                        
# 2025-02-20 01:55:59  0.00B 定义构建参数
ARG CUDA_DRIVER_VERSION=570.86.10
                        
# 2025-02-20 01:55:59  0.00B 定义构建参数
ARG CUDA_VERSION=12.8.0.038
                        
# 2025-02-20 01:55:59  334.25MB 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         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
                        
# 2025-01-27 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": "sha256:3299eb2f17b07df56cd73fc20ae4319d06153c8b7c3bbf038dce90e23830571a",
    "RepoTags": [
        "nvcr.io/nvidia/tritonserver:25.02-trtllm-python-py3",
        "swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/nvcr.io/nvidia/tritonserver:25.02-trtllm-python-py3"
    ],
    "RepoDigests": [
        "nvcr.io/nvidia/tritonserver@sha256:2ebda8b5d13390d0aa96fe6ac259447f6e7b008cdd59d6c782521ed64f53688a",
        "swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/nvcr.io/nvidia/tritonserver@sha256:0437cfca149940b509aa35827902bcc2b2e8c9ed333daca36ddadddd516ae5d0"
    ],
    "Parent": "",
    "Comment": "buildkit.dockerfile.v0",
    "Created": "2025-02-26T01:16:49.301876747Z",
    "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/mpi/bin:/usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/local/ucx/bin:/opt/amazon/efa/bin",
            "CUDA_VERSION=12.8.0.038",
            "CUDA_DRIVER_VERSION=570.86.10",
            "CUDA_CACHE_DISABLE=1",
            "NVIDIA_REQUIRE_JETPACK_HOST_MOUNTS=",
            "_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=12.8.3.14",
            "CUFFT_VERSION=11.3.3.41",
            "CURAND_VERSION=10.3.9.55",
            "CUSPARSE_VERSION=12.5.7.53",
            "CUSPARSELT_VERSION=0.6.3.2",
            "CUSOLVER_VERSION=11.7.2.55",
            "CUTENSOR_VERSION=2.1.0.9",
            "NPP_VERSION=12.3.3.65",
            "NVJPEG_VERSION=12.3.5.57",
            "CUFILE_VERSION=1.13.0.11",
            "NVJITLINK_VERSION=12.8.61",
            "CUDNN_VERSION=9.7.1.26",
            "CUDNN_FRONTEND_VERSION=1.10.0",
            "TRT_VERSION=10.8.0.43",
            "TRTOSS_VERSION=",
            "NSIGHT_SYSTEMS_VERSION=2025.1.1.65",
            "NSIGHT_COMPUTE_VERSION=2025.1.0.14",
            "DALI_VERSION=1.46.0",
            "DALI_BUILD=",
            "DALI_URL_SUFFIX=120",
            "POLYGRAPHY_VERSION=0.49.18",
            "TRANSFORMER_ENGINE_VERSION=2.0",
            "MODEL_OPT_VERSION=0.23.0",
            "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",
            "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",
            "LIBRARY_PATH=/usr/local/cuda/lib64/stubs:",
            "CUDA_VER=12.8.0.038",
            "NVRTC_VER=12.8.61-1",
            "PIP_BREAK_SYSTEM_PACKAGES=1",
            "TRT_ROOT=/usr/local/tensorrt",
            "TRITON_SERVER_VERSION=2.55.0",
            "NVIDIA_TRITON_SERVER_VERSION=25.02",
            "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=144783146"
        ],
        "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": "144783146",
            "com.nvidia.build.ref": "f8aa0dfefe498a23d2c7ebf1e2b9254793a59dc3",
            "com.nvidia.cublas.version": "12.8.3.14",
            "com.nvidia.cuda.version": "9.0",
            "com.nvidia.cudnn.version": "9.7.1.26",
            "com.nvidia.cufft.version": "11.3.3.41",
            "com.nvidia.curand.version": "10.3.9.55",
            "com.nvidia.cusolver.version": "11.7.2.55",
            "com.nvidia.cusparse.version": "12.5.7.53",
            "com.nvidia.cusparselt.version": "0.6.3.2",
            "com.nvidia.cutensor.version": "2.1.0.9",
            "com.nvidia.nccl.version": "2.25.1",
            "com.nvidia.npp.version": "12.3.3.65",
            "com.nvidia.nsightcompute.version": "2025.1.0.14",
            "com.nvidia.nsightsystems.version": "2025.1.1.65",
            "com.nvidia.nvjpeg.version": "12.3.5.57",
            "com.nvidia.tensorrt.version": "10.8.0.43",
            "com.nvidia.tensorrtoss.version": "",
            "com.nvidia.tritonserver.version": "2.55.0",
            "com.nvidia.volumes.needed": "nvidia_driver",
            "org.opencontainers.image.ref.name": "ubuntu",
            "org.opencontainers.image.version": "24.04"
        }
    },
    "Architecture": "amd64",
    "Os": "linux",
    "Size": 30147617877,
    "GraphDriver": {
        "Data": {
            "LowerDir": "/var/lib/docker/overlay2/793611a690a1e18d1b25a76c2e18416ae2091c2f0374399374cb1da3c5b45f59/diff:/var/lib/docker/overlay2/70644d6df6f8b3fdc5bbf17905d9223ea5fc4977736c252b76f619f81768c879/diff:/var/lib/docker/overlay2/532186e4f8525a79483d05e1f867f3c58e86cbd0c0a0d998b192ea33e11fbbf1/diff:/var/lib/docker/overlay2/678c316b880334b52ed4317dd50ec3065d93e1378cc33049231763258f78197e/diff:/var/lib/docker/overlay2/10eae57f089ca61a060d9f62b7ec801e22c24617c27006bb3551a95c6225ba1f/diff:/var/lib/docker/overlay2/75c6fdfc1e6bbabf7722844808b90f402515f3e901598fb928f7246b2f53d89b/diff:/var/lib/docker/overlay2/680d28e40d3e109f67992564d7183208f23ea5c0a0f8af9f4344cd98b9a80908/diff:/var/lib/docker/overlay2/22cc1aa0c9ef7a525e4d68572ae15341f91d56811de4acecdc5a37cf054f0a80/diff:/var/lib/docker/overlay2/68233dbd30884b38d354c33872e215e45744dfa5a2673373e2576c6285ba5c46/diff:/var/lib/docker/overlay2/a8551a496fa7507ba50275b3bb369d8cb2a8bac54a72dc499aa98aa9b31d97ee/diff:/var/lib/docker/overlay2/e99ae452a6fb5aac84909bd48468d13061033c8a770d1b66903242ccd8f17aab/diff:/var/lib/docker/overlay2/f8d40b3b989386eec6c9a2bcae7da2848b76f66e6b857d47850814cc40997b48/diff:/var/lib/docker/overlay2/d0b4366a62ca0a7ea9f94d6aa4e999cac5c773290c4b5b4ecb32f3c675fdefd3/diff:/var/lib/docker/overlay2/82b8c93cb092dbef23e2cb19146e993a72f1ff02d194b816b53f3ce82b704410/diff:/var/lib/docker/overlay2/5f6208cfb80499fc3906d110284f1420309d50eb40e899e54ae56b812a5e42cb/diff:/var/lib/docker/overlay2/67b51b5318b175e9b0bec957c4ab2ee660cf2d4ed2a0ba594a69fb9a2abc9ef4/diff:/var/lib/docker/overlay2/0679c29bfa3031c81b0fcfca893cd3857dae616e791d60af92b0309bb1ec1cb1/diff:/var/lib/docker/overlay2/d0f2f26f72abf215f0806a7bb02a826344f2e1c60f57a8009d87d21246c59873/diff:/var/lib/docker/overlay2/af3cf84b31bc7288564690b21e301c40d3a1bc8d1eec242e00f0e76bdebfcc79/diff:/var/lib/docker/overlay2/77195af0855aecc1e39ab029be37fa29d61299c05a10bc86ca8b78cb22eb19f3/diff:/var/lib/docker/overlay2/87d123a902c5afd3c10954e89e8b63df2fd3a201edc649c0d8179e23a83068d9/diff:/var/lib/docker/overlay2/52f58ad019a97f51801d4f6f96afb2be975040d21eb097ca7a2c760dd1a1fea7/diff:/var/lib/docker/overlay2/2eebde398c31e7f8d1e2fc05c057fca6506b3c7c54c1f9bdbecd11e3927f3fa4/diff:/var/lib/docker/overlay2/090d3c42acef19987566974bb623f75991008b21687f1bae66316a7c92cfaa0a/diff:/var/lib/docker/overlay2/b8a5d33ce6bfde82ab422e8b003e4d5e96095db190c158f629bdaaa49739d7f5/diff:/var/lib/docker/overlay2/a94e910c9ffe878aae1a41c603ec62dfef30db90f01b79d39e2737b9305ef436/diff:/var/lib/docker/overlay2/97cc2b7efd901f7d3bef99fe1071206310598c21c5fc8d8e36ac084676663fd8/diff:/var/lib/docker/overlay2/6fffbc39efb6373fe4c611f0a990908627d270470c94fe5f53fefef3a6d4f923/diff:/var/lib/docker/overlay2/f0279030fba2de7169e3b320e5f469af908b0501e6ed2e1782cdb962cdb9d2bd/diff:/var/lib/docker/overlay2/e9a4cd91b484fecdb52a324137af2ba70988267d7e9d3954975e3a71b02af0a6/diff:/var/lib/docker/overlay2/dcdfd48da2749058224c6dc093fcd3abde61aa183c1fda8433d24b6137727682/diff:/var/lib/docker/overlay2/c3e6c983c19e5afef5867ccb217918adca47b6306f08a15900bfe69296a1a028/diff:/var/lib/docker/overlay2/4388cee5c02da5769de12951bdf49b7716db8145e66f0707ac6fba2e83b399eb/diff:/var/lib/docker/overlay2/c8470e1fc16a7b40a7975bf059d05a479d9f03d5e1ab20dd1b1468856dbbeaa8/diff:/var/lib/docker/overlay2/ec474b116995458eb160372cf9a962297bb8cf04b1bb983bdfbec31aa5a274e4/diff:/var/lib/docker/overlay2/3d81afe5c52710edc8eb0683ea742780db225aa29f3c1965e240e58b1b27a77b/diff:/var/lib/docker/overlay2/19f6f3f62f3b31b89a07f6d5041541226b79326f047860aaeebb55eafb0a669e/diff:/var/lib/docker/overlay2/a9122124fd821e93f1b4f8485ad5e2e199120418ac56b1c92f1618403ea5a61a/diff:/var/lib/docker/overlay2/03f1be865cecebdb8345f59e79cccae19772422a8afe90df579a2a8b099702ba/diff:/var/lib/docker/overlay2/f659760f600946a3186e271b5c0fd31f602442d457fa0900dc70bc9805131ef8/diff:/var/lib/docker/overlay2/729a60749ea408602ea7f83ac7121431e7ab9cac6dd1a7cb16fc46f532131bb7/diff:/var/lib/docker/overlay2/32647e7c2d7ab15610e70dbadd051b287cd6db8c7af29b927b8e81b67cae62cc/diff:/var/lib/docker/overlay2/8c216266021849c81364b2391eff9ec0d38ef0c8507fdeecb279f8cc0b769569/diff:/var/lib/docker/overlay2/714eddac467fc54851e8f8a322b294806a64f2ceded1678caf5f418223703bd7/diff:/var/lib/docker/overlay2/50290fba822ad07336d12a30f1743686a48ac0abd031caebd52b8768699be2cc/diff:/var/lib/docker/overlay2/cef897b4965a7b898d12bd2d82a755dc7729aa14aa581d99538960a4570a94e6/diff:/var/lib/docker/overlay2/d9b933ce10e3bc759a5a16236bb02da9b55a82f922da90e83c5bf96a1c15a20c/diff:/var/lib/docker/overlay2/0e7da6d5f627d6f94348b072195182562b8593951e879a63fc43458acef8960d/diff:/var/lib/docker/overlay2/a3139f9b0770ff1ef31c6b606f95d0aa0ef9445bd7ff34005bd355bc16e9bb07/diff:/var/lib/docker/overlay2/c535250f15ffa3c39192970e3b322849f724cadf7bd06854ca280d204db9daf9/diff:/var/lib/docker/overlay2/d71569d0909dbc4efa627cbe03ff8651eba7c2a0d72792250350f9708e492612/diff:/var/lib/docker/overlay2/d753c20b4e9750ca6991766d53c44be19d93668a4d49bb00743e5b1de0803d65/diff:/var/lib/docker/overlay2/3ab398b3eb379bda45b2c000698f5160bb32c482c5de098b12641487468dfe0b/diff:/var/lib/docker/overlay2/00f2f6ba490d3f5f039a63e8352e75dde2a4f6ad3d9a84d187b0ffe35fed7623/diff:/var/lib/docker/overlay2/520e3a2db0dc77dbc18fb4d09189fdee8b2c3704183dd8746dbac95e486ee7f8/diff:/var/lib/docker/overlay2/1a89d780ebf7169180ee038f68733774f11fd9c9d822a5e43c401052d1d7011e/diff:/var/lib/docker/overlay2/1da064c347ee6f7d5ac1e2b2227e35df0f87a044d49ea915509ec72f2e82d9be/diff:/var/lib/docker/overlay2/790c153295dacf830d03db7595e1088655a2a8d815ed3d7444b120e032cc6598/diff:/var/lib/docker/overlay2/c1aecfbc2b8beedf280c9899d0b01d0b4579cf50a32074afa58f81d0860d2060/diff:/var/lib/docker/overlay2/360971a8cd9abffdd828036c8c9f449f91b60d0ede7aed0253063298a137a8b0/diff:/var/lib/docker/overlay2/a7b7393d7b298b706d8a7400e88c54ecd9cc0bda80976f0bc748ef8a7752dc00/diff:/var/lib/docker/overlay2/df89ee393696fe46043f94f605ad1b3c3bf018295c83f2bd79c3d299c975d60d/diff:/var/lib/docker/overlay2/7f0d7ce34b4765bce9934280724e7078d45f0629ee263f97dc6ec89f1c415f91/diff:/var/lib/docker/overlay2/08d68d954ca0cf601aafc8c1aaa0004ef2ebaa0d80732c4751a4f25b4866f402/diff:/var/lib/docker/overlay2/2bf1aad9dc777fe2d6d2e078df6f86b751ecf4425ed56945c28289acd3e187ad/diff:/var/lib/docker/overlay2/9bba01f853003111df877cdf4b776bccbcd82aae7fc7f4fdd262b17f9dd5ad4f/diff:/var/lib/docker/overlay2/d878d8eb8c2a7effc367a5c420b6f660f90f31477f09dce3aecec89c3eec55a1/diff:/var/lib/docker/overlay2/d5ba5778451cb9d6cd53a762324cbf17a65345e17306b42b60d69ba8f9186927/diff",
            "MergedDir": "/var/lib/docker/overlay2/aff657d5d56f7dd348d823162f90f26f6f0d6b9b329ef4edfecf2d4f7021dfac/merged",
            "UpperDir": "/var/lib/docker/overlay2/aff657d5d56f7dd348d823162f90f26f6f0d6b9b329ef4edfecf2d4f7021dfac/diff",
            "WorkDir": "/var/lib/docker/overlay2/aff657d5d56f7dd348d823162f90f26f6f0d6b9b329ef4edfecf2d4f7021dfac/work"
        },
        "Name": "overlay2"
    },
    "RootFS": {
        "Type": "layers",
        "Layers": [
            "sha256:4b7c01ed0534d4f9be9cf97d068da1598c6c20b26cb6134fad066defdb6d541d",
            "sha256:9ccaeaa195d10a507ccd234d4cbab25232cd83022d3cb4d7be30acf1e5b27e94",
            "sha256:5f70bf18a086007016e948b04aed3b82103a36bea41755b6cddfaf10ace3c6ef",
            "sha256:8aad9733b92670dd3c15c8d658e2cea6af3104bc8597ea701512170b64ee5a0c",
            "sha256:8333b229f5e2c120ef465f490bbc04a41c065b6c989acfcfc9415491664111d5",
            "sha256:a8473b0dfd2977276a4a14aa479e9f89707de3129231bec9f0496fd520c54593",
            "sha256:55f1034e38e3771210732073dc0f6e48717102c30f3046b4639c0469ee204b3f",
            "sha256:7a8eb7214cc3a42e5978a0591a1b54315fb1d5502a38b8a35065c08f637aa8ea",
            "sha256:f528343acccbc20cd1e631ec9772397c4ce13bcbd5279bf29ffc419820c58662",
            "sha256:a965ddeb5b2dd3b381dfc71cebecd1226b34f78a10cbbb18e4657649315e4f2b",
            "sha256:4217cb2e1e80307e5832f4b6204e97bf6724f2308bbbd261effceb03b5d5ae21",
            "sha256:9a604ac5d054ce66d7bb6e590be4adc0f90420e24f6397ea001b435d89655c56",
            "sha256:64f09cb4ede663abe333ed396d8e36f9218e5097e650a0ba1c66feff11f70124",
            "sha256:cd9b4f9d640ff2fec1e09844ebc20b869c028a830125e0fa74e28c3ae3eec425",
            "sha256:4c09dc6806172b93cacb674f2f8467d2edb70366c0e05acc464bba9bf9f1fdab",
            "sha256:0752f358904abe869f50f12c7ce5ce21d428c16f39181e74b9f525f99d126a26",
            "sha256:d52250212a13a2f223c1d43b1aa9637e02d245a517dc644850df7c18879d6e68",
            "sha256:e318f028c3fdac45738924ea2090f165f5ae6efd8856394246a34f625590bdc9",
            "sha256:ac41e36f05d801a1ae07e00e13be3035f99627a91022aca205dff37cd41f7116",
            "sha256:e1344b4a1c75a9c28b9e56b13cd27d964a20bc8fc67adfb59340a91d0a691dcf",
            "sha256:89eb5870958304a6dbf464c1613cf591a0e7584b08de49d7ccb0d3baa13059fd",
            "sha256:f04948453247915bf5a37c65fa4aa84eb65f75cce5ecf29dd6fc371363270d89",
            "sha256:796feb1f4817fb4d5de04a88cbb2083b2ba2dd8d1a869e096dbd32f632c6cf9b",
            "sha256:3255d691481ad55cbcbdb9f65ec2d0df53ed63df2882dd092289cf609601e236",
            "sha256:f13a1550e876edc412741adcaac5f946ef1c73c2c3b4666a69e43685b1002a86",
            "sha256:27a74220e96b2268f00c4d8fcf021c1d61e73ae13aa8e82a584a58c4969ce02d",
            "sha256:c36ebfe14204b4ac7b876a75b724496a5d2545e83a284dbd2726382e5d76e4a9",
            "sha256:1a9ad014ab81591b0a9f8b0df1726af2e0f650cb3535812598745375e83ed875",
            "sha256:9897a9dc4b588e9e2877c8192778810aa9990526bb3c40207a21ff08e8063964",
            "sha256:b290b63e1dc10f3287736dcbd2a77d2602f3b35f10296bb674d266b2bf9e60e8",
            "sha256:28a8b2e259d6c4d7b3d457262d2e271cd4207eec211c31b6bf99dc0af194f717",
            "sha256:f8d4f9768dac1ac1d0e69594247048b265fc5173fe1048885f930f392a4600ed",
            "sha256:06487ab9a7d97578f878b9b4e17f290d5f21dc717629deb8c097f499bb4d0591",
            "sha256:d56641438538745bd619d6e634004ae78a9f0733cb891f608673612a47af1695",
            "sha256:d94897bc8211e89b4895aa3c5fd200bf0b843260c8d194669862f6597aea39d3",
            "sha256:a91f9a6c99b15fe276adc771f1327488a6d68e6fd5d62f711fc790d4b452da1e",
            "sha256:8e466876d910962efd68e36f382a2c7930958ff61f7d084cb344b2cdcbd8b192",
            "sha256:afd06c244c36a23f87937ca4cabeb1e22a199d47e4e97e053433b99ef605d0df",
            "sha256:cd5d7400ff27ba14e0ceee49529e72e633314046f08443eafe45a5b64959278b",
            "sha256:4e4fdf7187f0a5f73c73f3075c1875473ed9e8041f161a7481563af77a2f4eb5",
            "sha256:364d39ea3d883a103619582e24fc4353f8763cf74fc0dd7156af443ee19c516e",
            "sha256:5f70bf18a086007016e948b04aed3b82103a36bea41755b6cddfaf10ace3c6ef",
            "sha256:7c01a4d46f1bb923cad2de9ed770fcf4ce580d5242eb7a035556830608b1b0e4",
            "sha256:2c39c5f1f231bdd0ab62dbee229bc4c33ae242cfb76d2514cd200088ac36878f",
            "sha256:a55bc05592517df18a8b188d7a4d90627ee14dc9180e00ad539d186065cac6f7",
            "sha256:cb5661410e9c3406cf26661b491d83fa0a23648676c0196f7d208b8ad351cca5",
            "sha256:2022aacb842607589dd4cd473c554058bc91eede7c3f3d651cc09dccf6747a72",
            "sha256:48e302cfb57de97512d32e38ec654744196a357f7606e5e10594717743de13a6",
            "sha256:7ed401cde3a33e32f6a404379d65a72ee61743dbbc86f52bbc1f6d3c66897bfb",
            "sha256:af8d2666fb3d129d232568df378e3f292afb799e85c12c7d004f106b4f47bc24",
            "sha256:ce09f04e5d39d80be90aff488825fd97f3acdf9b580118927d72a2f273f3bbab",
            "sha256:5628eafd5bc3e02f0c9338e9dc8073a5cfb3b821147b01dfb68db6929f99f684",
            "sha256:0c83802c1deb78075baf9ffb9fdd26896b6628932be54466b91bbd6213e24dda",
            "sha256:22a20a0e9b7fd42901292049707198e98c99b1419d7cbc6d8515e04e63890330",
            "sha256:82df893eb7bf2dd840ef10194efa6800a83b71cdcb4d3b6770a0b97c6842f014",
            "sha256:b95bd5bb3dc84442cbcc1d3c0ffa29644eb7c8bc43c9f254ac9d7e01b362e57e",
            "sha256:354513e771fd64ff9eb9aacd39ae8bb031be15b67e53821006b8b58d452cff5f",
            "sha256:5f70bf18a086007016e948b04aed3b82103a36bea41755b6cddfaf10ace3c6ef",
            "sha256:fbd98e2c1ea60921604ea7ee2376c833f9de8e1407fa353e10c59f96562d2b09",
            "sha256:5f70bf18a086007016e948b04aed3b82103a36bea41755b6cddfaf10ace3c6ef",
            "sha256:cec32f27d5939e65171d27ac7b0ff87b9c8d2a398a0a8b3b3060f0612843d972",
            "sha256:5f70bf18a086007016e948b04aed3b82103a36bea41755b6cddfaf10ace3c6ef",
            "sha256:761d76a60e7f0a2808a11674bffc7ca58c3b140e4f386fc26f2900b39c91c593",
            "sha256:51baf9ae33bb5fc0c428485993891ca2fefcae38f21c436c7106cf9b56001bce",
            "sha256:4c1ad90a18532650a5d139972b508ef2b5cdfdd3aca783baf0740477b376bbc2",
            "sha256:371e121f5f73c39f7ce7205ff57bfb13230aa25e64b8cbd7a44aa6bca9dab07d",
            "sha256:b4ce0a0ccdd564fd5e953b32dfdae821ed1502388d6eaa45d89ffeec63f16d5e",
            "sha256:96c1eaabaabb8e546cab53b3f3284931226e6fc6f5db50ad9278f87bbcc9748f",
            "sha256:b83a8f8872fbdfe67531615fe94cca86c282adb06fde80345885fc69e497e11a"
        ]
    },
    "Metadata": {
        "LastTagTime": "2025-05-25T02:11:59.01565359+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
384

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

linux/amd64 docker.io19.59GB2025-05-22 00:46
220

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

linux/amd64 docker.io30.15GB2025-05-25 02:51
80

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

linux/amd64 docker.io14.00GB2025-06-04 06:32
33

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

linux/amd64 docker.io32.90GB2025-06-09 03:41
92

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

linux/amd64 docker.io23.34GB2025-06-15 02:52
50

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

linux/amd64 docker.io23.93GB2025-06-17 01:33
31