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

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。

1268
浏览次数
23.93GB
镜像大小
源镜像
docker.io/nvcr.io/nvidia/tritonserver:25.05-vllm-python-py3
国内镜像
swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/nvcr.io/nvidia/tritonserver:25.05-vllm-python-py3
镜像ID
sha256:4a686c2e51fa05a5faee7a34333bcb84e29aebae1b9f48a40befe2aba4e4dc7c
镜像 TAG
25.05-vllm-python-py3
镜像大小
23.93GB
平台架构
linux/amd64
镜像源
docker.io
CMD
启动入口
/opt/nvidia/nvidia_entrypoint.sh
工作目录
/opt/tritonserver
OS/平台
linux/amd64
镜像创建
2025-05-29T17:25:56.025988625Z
同步时间
2025-06-17 01:33
浏览量
1268 次
贡献者
⚙️ 环境变量 65
KeyValue
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 0
NVIDIA_REQUIRE_JETPACK_HOST_MOUNTS= 1
GDRCOPY_VERSION=2.4.4 2
HPCX_VERSION=2.23 3
MOFED_VERSION=5.4-rdmacore50.0 4
OPENUCX_VERSION=1.19.0 5
OPENMPI_VERSION=4.1.7 6
RDMACORE_VERSION=50.0 7
EFA_VERSION=1.38.1 8
AWS_OFI_NCCL_VERSION=1.14.0 9
OPAL_PREFIX=/opt/hpcx/ompi 10
OMPI_MCA_coll_hcoll_enable=0 11
CUDA_VERSION=12.9.0.043 12
CUDA_DRIVER_VERSION=575.51.03 13
_CUDA_COMPAT_PATH=/usr/local/cuda/compat 14
ENV=/etc/shinit_v2 15
BASH_ENV=/etc/bash.bashrc 16
SHELL=/bin/bash 17
NVIDIA_REQUIRE_CUDA=cuda>=9.0 18
NCCL_VERSION=2.26.5 19
CUBLAS_VERSION=12.9.0.13 20
CUFFT_VERSION=11.4.0.6 21
CURAND_VERSION=10.3.10.19 22
CUSPARSE_VERSION=12.5.9.5 23
CUSPARSELT_VERSION=0.7.1.0 24
CUSOLVER_VERSION=11.7.4.40 25
NPP_VERSION=12.4.0.27 26
NVJPEG_VERSION=12.4.0.16 27
CUFILE_VERSION=1.14.0.30 28
NVJITLINK_VERSION=12.9.41 29
CUBLASMP_VERSION=0.4.0.789 30
CAL_VERSION=0.4.4.50 31
NVSHMEM_VERSION=3.2.5 32
CUDNN_VERSION=9.10.1.4 33
CUDNN_FRONTEND_VERSION=1.11.0 34
TRT_VERSION=10.10.0.31 35
TRTOSS_VERSION= 36
NSIGHT_SYSTEMS_VERSION=2025.3.1.90 37
NSIGHT_COMPUTE_VERSION=2025.2.0.11 38
DALI_VERSION=1.49.0 39
DALI_BUILD= 40
DALI_URL_SUFFIX=120 41
POLYGRAPHY_VERSION=0.49.20 42
TRANSFORMER_ENGINE_VERSION=2.3 43
MODEL_OPT_VERSION=0.27.1 44
CUDA_ARCH_LIST=7.5 8.0 8.6 9.0 10.0 12.0 45
LD_LIBRARY_PATH=/usr/local/lib:/usr/local/lib/python3.12/dist-packages/torch/lib:/usr/local/cuda/compat/lib:/usr/local/nvidia/lib:/usr/local/nvidia/lib64 46
NVIDIA_VISIBLE_DEVICES=all 47
NVIDIA_DRIVER_CAPABILITIES=compute,utility,video 48
NVIDIA_PRODUCT_NAME=Triton Server 49
LIBRARY_PATH=/usr/local/cuda/lib64/stubs: 50
PIP_BREAK_SYSTEM_PACKAGES=1 51
TRITON_SERVER_VERSION=2.58.0 52
NVIDIA_TRITON_SERVER_VERSION=25.05 53
UCX_MEM_EVENTS=no 54
TF_ADJUST_HUE_FUSED=1 55
TF_ADJUST_SATURATION_FUSED=1 56
TF_ENABLE_WINOGRAD_NONFUSED=1 57
TF_AUTOTUNE_THRESHOLD=2 58
TRITON_SERVER_GPU_ENABLED=1 59
TRITON_SERVER_USER=triton-server 60
DEBIAN_FRONTEND=noninteractive 61
TCMALLOC_RELEASE_RATE=200 62
DCGM_VERSION=3.3.6 63
NVIDIA_BUILD_ID=172940304 64
🏷️ 镜像标签 25
KeyValue
true com.amazonaws.sagemaker.capabilities.accept-bind-to-port
true com.amazonaws.sagemaker.capabilities.multi-models
172940304 com.nvidia.build.id
313ba108edee8e3c37fb123e32bbf760acf67069 com.nvidia.build.ref
0.4.4.50 com.nvidia.cal.version
12.9.0.13 com.nvidia.cublas.version
0.4.0.789 com.nvidia.cublasmp.version
9.0 com.nvidia.cuda.version
9.10.1.4 com.nvidia.cudnn.version
11.4.0.6 com.nvidia.cufft.version
10.3.10.19 com.nvidia.curand.version
11.7.4.40 com.nvidia.cusolver.version
12.5.9.5 com.nvidia.cusparse.version
0.7.1.0 com.nvidia.cusparselt.version
2.26.5 com.nvidia.nccl.version
12.4.0.27 com.nvidia.npp.version
2025.2.0.11 com.nvidia.nsightcompute.version
2025.3.1.90 com.nvidia.nsightsystems.version
12.4.0.16 com.nvidia.nvjpeg.version
10.10.0.31 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-vllm-python-py3
docker tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/nvcr.io/nvidia/tritonserver:25.05-vllm-python-py3  docker.io/nvcr.io/nvidia/tritonserver:25.05-vllm-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-vllm-python-py3
ctr images tag  swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/nvcr.io/nvidia/tritonserver:25.05-vllm-python-py3  docker.io/nvcr.io/nvidia/tritonserver:25.05-vllm-python-py3

Shell快速替换命令

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

镜像构建历史


# 2025-05-30 01:25:56  8.85KB 复制新文件或目录到容器中
COPY --chown=1000:1000 docker/sagemaker/serve /usr/bin/. # buildkit
                        
# 2025-05-30 01:25:55  0.00B 添加元数据标签
LABEL com.amazonaws.sagemaker.capabilities.multi-models=true
                        
# 2025-05-30 01:25:55  0.00B 添加元数据标签
LABEL com.amazonaws.sagemaker.capabilities.accept-bind-to-port=true
                        
# 2025-05-30 01:25:55  6.68MB 执行命令并创建新的镜像层
RUN |7 TRITON_VERSION=2.58.0 TRITON_CONTAINER_VERSION=25.05 BUILD_PUBLIC_VLLM=false VLLM_INDEX_URL=https://gitlab-ci-token:glcbt-64_uKwA96frgZzefrzydQWW@gitlab-master.nvidia.com/api/v4/projects/100660/packages/pypi/simple PYTORCH_TRITON_URL=https://gitlab-master.nvidia.com/api/v4/projects/105799/packages/generic/pytorch_triton/wheel/pytorch_triton-3.1.0+cf34004b8.internal-cp312-cp312-linux_x86_64.whl NVPL_SLIM_URL=None PYVER=3.12 /bin/sh -c pip3 install -r python/openai/requirements.txt # buildkit
                        
# 2025-05-30 01:25:49  365.86MB 执行命令并创建新的镜像层
RUN |7 TRITON_VERSION=2.58.0 TRITON_CONTAINER_VERSION=25.05 BUILD_PUBLIC_VLLM=false VLLM_INDEX_URL=https://gitlab-ci-token:glcbt-64_uKwA96frgZzefrzydQWW@gitlab-master.nvidia.com/api/v4/projects/100660/packages/pypi/simple PYTORCH_TRITON_URL=https://gitlab-master.nvidia.com/api/v4/projects/105799/packages/generic/pytorch_triton/wheel/pytorch_triton-3.1.0+cf34004b8.internal-cp312-cp312-linux_x86_64.whl NVPL_SLIM_URL=None PYVER=3.12 /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
                        
# 2025-05-30 01:25:33  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
                        
# 2025-05-30 01:25:33  0.00B 设置工作目录为/opt/tritonserver
WORKDIR /opt/tritonserver
                        
# 2025-05-30 01:25:32  535.36MB 复制新文件或目录到容器中
COPY --chown=1000:1000 build/install tritonserver # buildkit
                        
# 2025-05-30 01:25:29  0.00B 设置工作目录为/opt
WORKDIR /opt
                        
# 2025-05-30 01:25:28  0.00B 添加元数据标签
LABEL com.nvidia.build.ref=313ba108edee8e3c37fb123e32bbf760acf67069
                        
# 2025-05-30 01:25:28  0.00B 添加元数据标签
LABEL com.nvidia.build.id=172940304
                        
# 2025-05-30 01:25:28  0.00B 设置环境变量 NVIDIA_BUILD_ID
ENV NVIDIA_BUILD_ID=172940304
                        
# 2025-05-30 01:25:28  733.00B 复制新文件或目录到容器中
COPY docker/entrypoint.d/ /opt/nvidia/entrypoint.d/ # buildkit
                        
# 2025-05-30 01:25:28  0.00B 设置环境变量 NVIDIA_PRODUCT_NAME
ENV NVIDIA_PRODUCT_NAME=Triton Server
                        
# 2025-05-30 01:25:28  0.00B 执行命令并创建新的镜像层
RUN |7 TRITON_VERSION=2.58.0 TRITON_CONTAINER_VERSION=25.05 BUILD_PUBLIC_VLLM=false VLLM_INDEX_URL=https://gitlab-ci-token:glcbt-64_uKwA96frgZzefrzydQWW@gitlab-master.nvidia.com/api/v4/projects/100660/packages/pypi/simple PYTORCH_TRITON_URL=https://gitlab-master.nvidia.com/api/v4/projects/105799/packages/generic/pytorch_triton/wheel/pytorch_triton-3.1.0+cf34004b8.internal-cp312-cp312-linux_x86_64.whl NVPL_SLIM_URL=None PYVER=3.12 /bin/sh -c rm -fr /opt/tritonserver/* # buildkit
                        
# 2025-05-30 01:25:28  0.00B 设置工作目录为/opt/tritonserver
WORKDIR /opt/tritonserver
                        
# 2025-05-30 01:25:27  0.00B 设置环境变量 LD_LIBRARY_PATH
ENV LD_LIBRARY_PATH=/usr/local/lib:/usr/local/lib/python3.12/dist-packages/torch/lib:/usr/local/cuda/compat/lib:/usr/local/nvidia/lib:/usr/local/nvidia/lib64
                        
# 2025-05-30 01:25:27  0.00B 定义构建参数
ARG PYVER=3.12
                        
# 2025-05-30 01:25:27  10.23GB 执行命令并创建新的镜像层
RUN |6 TRITON_VERSION=2.58.0 TRITON_CONTAINER_VERSION=25.05 BUILD_PUBLIC_VLLM=false VLLM_INDEX_URL=https://gitlab-ci-token:glcbt-64_uKwA96frgZzefrzydQWW@gitlab-master.nvidia.com/api/v4/projects/100660/packages/pypi/simple PYTORCH_TRITON_URL=https://gitlab-master.nvidia.com/api/v4/projects/105799/packages/generic/pytorch_triton/wheel/pytorch_triton-3.1.0+cf34004b8.internal-cp312-cp312-linux_x86_64.whl NVPL_SLIM_URL=None /bin/sh -c if [ "$BUILD_PUBLIC_VLLM" = "false" ]; then         if [ "$(uname -m)" = "x86_64" ]; then             pip3 install --no-cache-dir                 mkl==2021.1.1                 mkl-include==2021.1.1                 mkl-devel==2021.1.1;         elif [ "$(uname -m)" = "aarch64" ]; then             echo "Downloading NVPL from: $NVPL_SLIM_URL" &&             cd /tmp &&             wget -O nvpl_slim_24.04.tar $NVPL_SLIM_URL &&             tar -xf nvpl_slim_24.04.tar &&             cp -r nvpl_slim_24.04/lib/* /usr/local/lib &&             cp -r nvpl_slim_24.04/include/* /usr/local/include &&             rm -rf nvpl_slim_24.04.tar nvpl_slim_24.04;         fi         && pip3 install --no-cache-dir --progress-bar on --index-url $VLLM_INDEX_URL -r /run/secrets/requirements         && cd /tmp         && wget $PYTORCH_TRITON_URL         && pip install --no-cache-dir /tmp/pytorch_triton-*.whl         && rm /tmp/pytorch_triton-*.whl;     else         pip3 install vllm==0.8.4;     fi # buildkit
                        
# 2025-05-30 01:21:16  0.00B 定义构建参数
ARG NVPL_SLIM_URL=None
                        
# 2025-05-30 01:21:16  0.00B 定义构建参数
ARG PYTORCH_TRITON_URL=https://gitlab-master.nvidia.com/api/v4/projects/105799/packages/generic/pytorch_triton/wheel/pytorch_triton-3.1.0+cf34004b8.internal-cp312-cp312-linux_x86_64.whl
                        
# 2025-05-30 01:21:16  0.00B 定义构建参数
ARG VLLM_INDEX_URL=https://gitlab-ci-token:glcbt-64_uKwA96frgZzefrzydQWW@gitlab-master.nvidia.com/api/v4/projects/100660/packages/pypi/simple
                        
# 2025-05-30 01:21:16  0.00B 定义构建参数
ARG BUILD_PUBLIC_VLLM=false
                        
# 2025-05-30 01:21:16  203.09MB 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
                        
# 2025-05-30 01:19:19  50.59KB 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
                        
# 2025-05-30 01:19:18  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
                        
# 2025-05-30 01:18:22  0.00B 设置环境变量 DCGM_VERSION
ENV DCGM_VERSION=3.3.6
                        
# 2025-05-30 01:18:22  0.00B 设置环境变量 TCMALLOC_RELEASE_RATE
ENV TCMALLOC_RELEASE_RATE=200
                        
# 2025-05-30 01:18:22  388.44MB 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
                        
# 2025-05-30 01:13:23  0.00B 设置环境变量 DEBIAN_FRONTEND
ENV DEBIAN_FRONTEND=noninteractive
                        
# 2025-05-30 01:13:23  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
                        
# 2025-05-30 01:13:23  0.00B 设置环境变量 TRITON_SERVER_USER
ENV TRITON_SERVER_USER=triton-server
                        
# 2025-05-30 01:13:23  0.00B 设置环境变量 TRITON_SERVER_GPU_ENABLED
ENV TRITON_SERVER_GPU_ENABLED=1
                        
# 2025-05-30 01:13:23  0.00B 设置环境变量 TF_AUTOTUNE_THRESHOLD
ENV TF_AUTOTUNE_THRESHOLD=2
                        
# 2025-05-30 01:13:23  0.00B 设置环境变量 TF_ENABLE_WINOGRAD_NONFUSED
ENV TF_ENABLE_WINOGRAD_NONFUSED=1
                        
# 2025-05-30 01:13:23  0.00B 设置环境变量 TF_ADJUST_SATURATION_FUSED
ENV TF_ADJUST_SATURATION_FUSED=1
                        
# 2025-05-30 01:13:23  0.00B 设置环境变量 TF_ADJUST_HUE_FUSED
ENV TF_ADJUST_HUE_FUSED=1
                        
# 2025-05-30 01:13:23  0.00B 设置环境变量 UCX_MEM_EVENTS
ENV UCX_MEM_EVENTS=no
                        
# 2025-05-30 01:13:23  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
                        
# 2025-05-30 01:13:23  0.00B 添加元数据标签
LABEL com.nvidia.tritonserver.version=2.58.0
                        
# 2025-05-30 01:13:23  0.00B 设置环境变量 NVIDIA_TRITON_SERVER_VERSION
ENV NVIDIA_TRITON_SERVER_VERSION=25.05
                        
# 2025-05-30 01:13:23  0.00B 设置环境变量 TRITON_SERVER_VERSION
ENV TRITON_SERVER_VERSION=2.58.0
                        
# 2025-05-30 01:13:23  0.00B 定义构建参数
ARG TRITON_CONTAINER_VERSION=25.05
                        
# 2025-05-30 01:13:23  0.00B 定义构建参数
ARG TRITON_VERSION=2.58.0
                        
# 2025-05-30 01:13:23  0.00B 设置环境变量 PIP_BREAK_SYSTEM_PACKAGES
ENV PIP_BREAK_SYSTEM_PACKAGES=1
                        
# 2025-05-15 09:01:15  0.00B 设置环境变量 LIBRARY_PATH
ENV LIBRARY_PATH=/usr/local/cuda/lib64/stubs:
                        
# 2025-05-15 09:01:15  1.02GB 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
                        
# 2025-05-15 08:58:46  1.49KB 复制新文件或目录到容器中
COPY cuda-*.patch /tmp # buildkit
                        
# 2025-05-15 08:58:46  99.02MB 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
                        
# 2025-05-15 08:37:55  0.00B 添加元数据标签
LABEL com.nvidia.nccl.version=2.26.5 com.nvidia.cublas.version=12.9.0.13 com.nvidia.cufft.version=11.4.0.6 com.nvidia.curand.version=10.3.10.19 com.nvidia.cusparse.version=12.5.9.5 com.nvidia.cusparselt.version=0.7.1.0 com.nvidia.cusolver.version=11.7.4.40 com.nvidia.npp.version=12.4.0.27 com.nvidia.nvjpeg.version=12.4.0.16 com.nvidia.cublasmp.version=0.4.0.789 com.nvidia.cal.version=0.4.4.50 com.nvidia.cudnn.version=9.10.1.4 com.nvidia.tensorrt.version=10.10.0.31 com.nvidia.tensorrtoss.version= com.nvidia.nsightsystems.version=2025.3.1.90 com.nvidia.nsightcompute.version=2025.2.0.11
                        
# 2025-05-15 08:37:55  7.84GB 执行命令并创建新的镜像层
RUN /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
                        
# 2025-05-15 08:36:58  584.70MB 执行命令并创建新的镜像层
RUN /bin/sh -c /nvidia/build-scripts/installCUDA.sh # buildkit
                        
# 2025-05-15 08:36:49  302.31MB 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         libncurses6         libncursesw6         unzip         jq         gnupg         libtcmalloc-minimal4  && rm -rf /var/lib/apt/lists/* # buildkit
                        
# 2025-05-15 08:23:05  467.00B 执行命令并创建新的镜像层
RUN |40 JETPACK_HOST_MOUNTS= GDRCOPY_VERSION=2.4.4 HPCX_VERSION=2.23 RDMACORE_VERSION=50.0 MOFED_VERSION=5.4-rdmacore50.0 OPENUCX_VERSION=1.19.0 OPENMPI_VERSION=4.1.7 EFA_VERSION=1.38.1 AWS_OFI_NCCL_VERSION=1.14.0 TARGETARCH=amd64 CUDA_VERSION=12.9.0.043 CUDA_DRIVER_VERSION=575.51.03 NCCL_VERSION=2.26.5 CUBLAS_VERSION=12.9.0.13 CUFFT_VERSION=11.4.0.6 CURAND_VERSION=10.3.10.19 CUSPARSE_VERSION=12.5.9.5 CUSOLVER_VERSION=11.7.4.40 NPP_VERSION=12.4.0.27 NVJPEG_VERSION=12.4.0.16 CUFILE_VERSION=1.14.0.30 NVJITLINK_VERSION=12.9.41 CUBLASMP_VERSION=0.4.0.789 CAL_VERSION=0.4.4.50 NVSHMEM_VERSION=3.2.5 CUDNN_VERSION=9.10.1.4 CUDNN_FRONTEND_VERSION=1.11.0 TRT_VERSION=10.10.0.31 TRTOSS_VERSION= NSIGHT_SYSTEMS_VERSION=2025.3.1.90 NSIGHT_COMPUTE_VERSION=2025.2.0.11 CUSPARSELT_VERSION=0.7.1.0 DALI_VERSION=1.49.0 DALI_BUILD= DALI_URL_SUFFIX=120 POLYGRAPHY_VERSION=0.49.20 TRANSFORMER_ENGINE_VERSION=2.3 MODEL_OPT_VERSION=0.27.1 CUDA_ARCH_LIST=7.5 8.0 8.6 9.0 10.0 12.0 _LIBPATH_SUFFIX= /bin/sh -c mkdir -p /workspace && cp -f -p /opt/nvidia/entrypoint.d/30-container-license.txt /workspace/license.txt # buildkit
                        
# 2025-05-15 08:23:05  0.00B 配置容器启动时运行的命令
ENTRYPOINT ["/opt/nvidia/nvidia_entrypoint.sh"]
                        
# 2025-05-15 08:23:05  0.00B 设置环境变量 NVIDIA_PRODUCT_NAME
ENV NVIDIA_PRODUCT_NAME=CUDA
                        
# 2025-05-15 08:23:05  16.23KB 复制新文件或目录到容器中
COPY entrypoint/ /opt/nvidia/ # buildkit
                        
# 2025-05-15 08:23:05  21.81KB 执行命令并创建新的镜像层
RUN |40 JETPACK_HOST_MOUNTS= GDRCOPY_VERSION=2.4.4 HPCX_VERSION=2.23 RDMACORE_VERSION=50.0 MOFED_VERSION=5.4-rdmacore50.0 OPENUCX_VERSION=1.19.0 OPENMPI_VERSION=4.1.7 EFA_VERSION=1.38.1 AWS_OFI_NCCL_VERSION=1.14.0 TARGETARCH=amd64 CUDA_VERSION=12.9.0.043 CUDA_DRIVER_VERSION=575.51.03 NCCL_VERSION=2.26.5 CUBLAS_VERSION=12.9.0.13 CUFFT_VERSION=11.4.0.6 CURAND_VERSION=10.3.10.19 CUSPARSE_VERSION=12.5.9.5 CUSOLVER_VERSION=11.7.4.40 NPP_VERSION=12.4.0.27 NVJPEG_VERSION=12.4.0.16 CUFILE_VERSION=1.14.0.30 NVJITLINK_VERSION=12.9.41 CUBLASMP_VERSION=0.4.0.789 CAL_VERSION=0.4.4.50 NVSHMEM_VERSION=3.2.5 CUDNN_VERSION=9.10.1.4 CUDNN_FRONTEND_VERSION=1.11.0 TRT_VERSION=10.10.0.31 TRTOSS_VERSION= NSIGHT_SYSTEMS_VERSION=2025.3.1.90 NSIGHT_COMPUTE_VERSION=2025.2.0.11 CUSPARSELT_VERSION=0.7.1.0 DALI_VERSION=1.49.0 DALI_BUILD= DALI_URL_SUFFIX=120 POLYGRAPHY_VERSION=0.49.20 TRANSFORMER_ENGINE_VERSION=2.3 MODEL_OPT_VERSION=0.27.1 CUDA_ARCH_LIST=7.5 8.0 8.6 9.0 10.0 12.0 _LIBPATH_SUFFIX= /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
                        
# 2025-05-15 08:23:05  5.13MB 复制新文件或目录到容器中
COPY /opt/amazon/aws-ofi-nccl /opt/amazon/aws-ofi-nccl # buildkit
                        
# 2025-05-15 08:22:44  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
                        
# 2025-05-15 08:22:44  0.00B 定义构建参数
ARG _LIBPATH_SUFFIX=
                        
# 2025-05-15 08:22:44  46.00B 执行命令并创建新的镜像层
RUN |39 JETPACK_HOST_MOUNTS= GDRCOPY_VERSION=2.4.4 HPCX_VERSION=2.23 RDMACORE_VERSION=50.0 MOFED_VERSION=5.4-rdmacore50.0 OPENUCX_VERSION=1.19.0 OPENMPI_VERSION=4.1.7 EFA_VERSION=1.38.1 AWS_OFI_NCCL_VERSION=1.14.0 TARGETARCH=amd64 CUDA_VERSION=12.9.0.043 CUDA_DRIVER_VERSION=575.51.03 NCCL_VERSION=2.26.5 CUBLAS_VERSION=12.9.0.13 CUFFT_VERSION=11.4.0.6 CURAND_VERSION=10.3.10.19 CUSPARSE_VERSION=12.5.9.5 CUSOLVER_VERSION=11.7.4.40 NPP_VERSION=12.4.0.27 NVJPEG_VERSION=12.4.0.16 CUFILE_VERSION=1.14.0.30 NVJITLINK_VERSION=12.9.41 CUBLASMP_VERSION=0.4.0.789 CAL_VERSION=0.4.4.50 NVSHMEM_VERSION=3.2.5 CUDNN_VERSION=9.10.1.4 CUDNN_FRONTEND_VERSION=1.11.0 TRT_VERSION=10.10.0.31 TRTOSS_VERSION= NSIGHT_SYSTEMS_VERSION=2025.3.1.90 NSIGHT_COMPUTE_VERSION=2025.2.0.11 CUSPARSELT_VERSION=0.7.1.0 DALI_VERSION=1.49.0 DALI_BUILD= DALI_URL_SUFFIX=120 POLYGRAPHY_VERSION=0.49.20 TRANSFORMER_ENGINE_VERSION=2.3 MODEL_OPT_VERSION=0.27.1 CUDA_ARCH_LIST=7.5 8.0 8.6 9.0 10.0 12.0 /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
                        
# 2025-05-15 08:22:44  13.39KB 复制文件或目录到容器中
ADD docs.tgz / # buildkit
                        
# 2025-05-15 08:22:44  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 DALI_VERSION DALI_BUILD DALI_URL_SUFFIX POLYGRAPHY_VERSION TRANSFORMER_ENGINE_VERSION MODEL_OPT_VERSION CUDA_ARCH_LIST
ENV NCCL_VERSION=2.26.5 CUBLAS_VERSION=12.9.0.13 CUFFT_VERSION=11.4.0.6 CURAND_VERSION=10.3.10.19 CUSPARSE_VERSION=12.5.9.5 CUSPARSELT_VERSION=0.7.1.0 CUSOLVER_VERSION=11.7.4.40 NPP_VERSION=12.4.0.27 NVJPEG_VERSION=12.4.0.16 CUFILE_VERSION=1.14.0.30 NVJITLINK_VERSION=12.9.41 CUBLASMP_VERSION=0.4.0.789 CAL_VERSION=0.4.4.50 NVSHMEM_VERSION=3.2.5 CUDNN_VERSION=9.10.1.4 CUDNN_FRONTEND_VERSION=1.11.0 TRT_VERSION=10.10.0.31 TRTOSS_VERSION= NSIGHT_SYSTEMS_VERSION=2025.3.1.90 NSIGHT_COMPUTE_VERSION=2025.2.0.11 DALI_VERSION=1.49.0 DALI_BUILD= DALI_URL_SUFFIX=120 POLYGRAPHY_VERSION=0.49.20 TRANSFORMER_ENGINE_VERSION=2.3 MODEL_OPT_VERSION=0.27.1 CUDA_ARCH_LIST=7.5 8.0 8.6 9.0 10.0 12.0
                        
# 2025-05-15 08:22:44  0.00B 定义构建参数
ARG NCCL_VERSION=2.26.5 CUBLAS_VERSION=12.9.0.13 CUFFT_VERSION=11.4.0.6 CURAND_VERSION=10.3.10.19 CUSPARSE_VERSION=12.5.9.5 CUSOLVER_VERSION=11.7.4.40 NPP_VERSION=12.4.0.27 NVJPEG_VERSION=12.4.0.16 CUFILE_VERSION=1.14.0.30 NVJITLINK_VERSION=12.9.41 CUBLASMP_VERSION=0.4.0.789 CAL_VERSION=0.4.4.50 NVSHMEM_VERSION=3.2.5 CUDNN_VERSION=9.10.1.4 CUDNN_FRONTEND_VERSION=1.11.0 TRT_VERSION=10.10.0.31 TRTOSS_VERSION= NSIGHT_SYSTEMS_VERSION=2025.3.1.90 NSIGHT_COMPUTE_VERSION=2025.2.0.11 CUSPARSELT_VERSION=0.7.1.0 DALI_VERSION=1.49.0 DALI_BUILD= DALI_URL_SUFFIX=120 POLYGRAPHY_VERSION=0.49.20 TRANSFORMER_ENGINE_VERSION=2.3 MODEL_OPT_VERSION=0.27.1 CUDA_ARCH_LIST=7.5 8.0 8.6 9.0 10.0 12.0
                        
# 2025-05-15 08:22:44  0.00B 添加元数据标签
LABEL com.nvidia.volumes.needed=nvidia_driver com.nvidia.cuda.version=9.0
                        
# 2025-05-15 08:22:44  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
                        
# 2025-05-15 08:22:44  68.28KB 执行命令并创建新的镜像层
RUN |12 JETPACK_HOST_MOUNTS= GDRCOPY_VERSION=2.4.4 HPCX_VERSION=2.23 RDMACORE_VERSION=50.0 MOFED_VERSION=5.4-rdmacore50.0 OPENUCX_VERSION=1.19.0 OPENMPI_VERSION=4.1.7 EFA_VERSION=1.38.1 AWS_OFI_NCCL_VERSION=1.14.0 TARGETARCH=amd64 CUDA_VERSION=12.9.0.043 CUDA_DRIVER_VERSION=575.51.03 /bin/sh -c cp -vprd /nvidia/. /  &&  patch -p0 < /etc/startup_scripts.patch  &&  rm -f /etc/startup_scripts.patch # buildkit
                        
# 2025-05-15 08:22:44  290.43MB 执行命令并创建新的镜像层
RUN |12 JETPACK_HOST_MOUNTS= GDRCOPY_VERSION=2.4.4 HPCX_VERSION=2.23 RDMACORE_VERSION=50.0 MOFED_VERSION=5.4-rdmacore50.0 OPENUCX_VERSION=1.19.0 OPENMPI_VERSION=4.1.7 EFA_VERSION=1.38.1 AWS_OFI_NCCL_VERSION=1.14.0 TARGETARCH=amd64 CUDA_VERSION=12.9.0.043 CUDA_DRIVER_VERSION=575.51.03 /bin/sh -c BASE=min /nvidia/build-scripts/installCUDA.sh # buildkit
                        
# 2025-05-15 07:04:54  0.00B 设置环境变量 CUDA_VERSION CUDA_DRIVER_VERSION
ENV CUDA_VERSION=12.9.0.043 CUDA_DRIVER_VERSION=575.51.03
                        
# 2025-05-15 07:04:54  0.00B 定义构建参数
ARG CUDA_DRIVER_VERSION=575.51.03
                        
# 2025-05-15 07:04:54  0.00B 定义构建参数
ARG CUDA_VERSION=12.9.0.043
                        
# 2025-05-15 07:04:54  0.00B 设置环境变量 OMPI_MCA_coll_hcoll_enable
ENV OMPI_MCA_coll_hcoll_enable=0
                        
# 2025-05-15 07:04:54  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
                        
# 2025-05-15 07:04:54  230.97MB 执行命令并创建新的镜像层
RUN |10 JETPACK_HOST_MOUNTS= GDRCOPY_VERSION=2.4.4 HPCX_VERSION=2.23 RDMACORE_VERSION=50.0 MOFED_VERSION=5.4-rdmacore50.0 OPENUCX_VERSION=1.19.0 OPENMPI_VERSION=4.1.7 EFA_VERSION=1.38.1 AWS_OFI_NCCL_VERSION=1.14.0 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
                        
# 2025-05-15 07:04:54  0.00B 定义构建参数
ARG TARGETARCH=amd64
                        
# 2025-05-15 07:04:54  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=2.4.4 HPCX_VERSION=2.23 MOFED_VERSION=5.4-rdmacore50.0 OPENUCX_VERSION=1.19.0 OPENMPI_VERSION=4.1.7 RDMACORE_VERSION=50.0 EFA_VERSION=1.38.1 AWS_OFI_NCCL_VERSION=1.14.0
                        
# 2025-05-15 07:04:54  0.00B 定义构建参数
ARG AWS_OFI_NCCL_VERSION=1.14.0
                        
# 2025-05-15 07:04:54  0.00B 定义构建参数
ARG EFA_VERSION=1.38.1
                        
# 2025-05-15 07:04:54  0.00B 定义构建参数
ARG OPENMPI_VERSION=4.1.7
                        
# 2025-05-15 07:04:54  0.00B 定义构建参数
ARG OPENUCX_VERSION=1.19.0
                        
# 2025-05-15 07:04:54  0.00B 定义构建参数
ARG MOFED_VERSION=5.4-rdmacore50.0
                        
# 2025-05-15 07:04:54  0.00B 定义构建参数
ARG RDMACORE_VERSION=50.0
                        
# 2025-05-15 07:04:54  0.00B 定义构建参数
ARG HPCX_VERSION=2.23
                        
# 2025-05-15 07:04:54  0.00B 定义构建参数
ARG GDRCOPY_VERSION=2.4.4
                        
# 2025-05-15 07:04:54  9.25MB 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         ca-certificates         curl         patch         wget  && rm -rf /var/lib/apt/lists/*  && echo "hsts=0" > /root/.wgetrc # buildkit
                        
# 2025-05-15 07:04:54  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
                        
# 2025-05-15 07:04:54  0.00B 设置环境变量 NVIDIA_REQUIRE_JETPACK_HOST_MOUNTS
ENV NVIDIA_REQUIRE_JETPACK_HOST_MOUNTS=
                        
# 2025-05-15 07:04:54  0.00B 定义构建参数
ARG JETPACK_HOST_MOUNTS=
                        
# 2025-04-28 17:44:51  0.00B 
/bin/sh -c #(nop)  CMD ["/bin/bash"]
                        
# 2025-04-28 17:44:50  78.10MB 
/bin/sh -c #(nop) ADD file:ad85a9d7b0a74c2140bd51d9c4559cca392991e0c95f84cb139347348e5d1f9a in / 
                        
# 2025-04-28 17:44:48  0.00B 
/bin/sh -c #(nop)  LABEL org.opencontainers.image.version=24.04
                        
# 2025-04-28 17:44:48  0.00B 
/bin/sh -c #(nop)  LABEL org.opencontainers.image.ref.name=ubuntu
                        
# 2025-04-28 17:44:48  0.00B 
/bin/sh -c #(nop)  ARG LAUNCHPAD_BUILD_ARCH
                        
# 2025-04-28 17:44:48  0.00B 
/bin/sh -c #(nop)  ARG RELEASE
                        
                    

镜像信息

{
    "Id": "sha256:4a686c2e51fa05a5faee7a34333bcb84e29aebae1b9f48a40befe2aba4e4dc7c",
    "RepoTags": [
        "nvcr.io/nvidia/tritonserver:25.05-vllm-python-py3",
        "swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/nvcr.io/nvidia/tritonserver:25.05-vllm-python-py3"
    ],
    "RepoDigests": [
        "nvcr.io/nvidia/tritonserver@sha256:a5f7caedf2ca6a3afcf18e590870611abd4ed7272fd36e32a04e9f8b28704451",
        "swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/nvcr.io/nvidia/tritonserver@sha256:1f70f5e4186d2901ef0f6fa478e0caa2c24c9aeb9128943baf2f0db17fb3a81c"
    ],
    "Parent": "",
    "Comment": "buildkit.dockerfile.v0",
    "Created": "2025-05-29T17:25:56.025988625Z",
    "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=2.4.4",
            "HPCX_VERSION=2.23",
            "MOFED_VERSION=5.4-rdmacore50.0",
            "OPENUCX_VERSION=1.19.0",
            "OPENMPI_VERSION=4.1.7",
            "RDMACORE_VERSION=50.0",
            "EFA_VERSION=1.38.1",
            "AWS_OFI_NCCL_VERSION=1.14.0",
            "OPAL_PREFIX=/opt/hpcx/ompi",
            "OMPI_MCA_coll_hcoll_enable=0",
            "CUDA_VERSION=12.9.0.043",
            "CUDA_DRIVER_VERSION=575.51.03",
            "_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=2.26.5",
            "CUBLAS_VERSION=12.9.0.13",
            "CUFFT_VERSION=11.4.0.6",
            "CURAND_VERSION=10.3.10.19",
            "CUSPARSE_VERSION=12.5.9.5",
            "CUSPARSELT_VERSION=0.7.1.0",
            "CUSOLVER_VERSION=11.7.4.40",
            "NPP_VERSION=12.4.0.27",
            "NVJPEG_VERSION=12.4.0.16",
            "CUFILE_VERSION=1.14.0.30",
            "NVJITLINK_VERSION=12.9.41",
            "CUBLASMP_VERSION=0.4.0.789",
            "CAL_VERSION=0.4.4.50",
            "NVSHMEM_VERSION=3.2.5",
            "CUDNN_VERSION=9.10.1.4",
            "CUDNN_FRONTEND_VERSION=1.11.0",
            "TRT_VERSION=10.10.0.31",
            "TRTOSS_VERSION=",
            "NSIGHT_SYSTEMS_VERSION=2025.3.1.90",
            "NSIGHT_COMPUTE_VERSION=2025.2.0.11",
            "DALI_VERSION=1.49.0",
            "DALI_BUILD=",
            "DALI_URL_SUFFIX=120",
            "POLYGRAPHY_VERSION=0.49.20",
            "TRANSFORMER_ENGINE_VERSION=2.3",
            "MODEL_OPT_VERSION=0.27.1",
            "CUDA_ARCH_LIST=7.5 8.0 8.6 9.0 10.0 12.0",
            "LD_LIBRARY_PATH=/usr/local/lib:/usr/local/lib/python3.12/dist-packages/torch/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:",
            "PIP_BREAK_SYSTEM_PACKAGES=1",
            "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=172940304"
        ],
        "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": "172940304",
            "com.nvidia.build.ref": "313ba108edee8e3c37fb123e32bbf760acf67069",
            "com.nvidia.cal.version": "0.4.4.50",
            "com.nvidia.cublas.version": "12.9.0.13",
            "com.nvidia.cublasmp.version": "0.4.0.789",
            "com.nvidia.cuda.version": "9.0",
            "com.nvidia.cudnn.version": "9.10.1.4",
            "com.nvidia.cufft.version": "11.4.0.6",
            "com.nvidia.curand.version": "10.3.10.19",
            "com.nvidia.cusolver.version": "11.7.4.40",
            "com.nvidia.cusparse.version": "12.5.9.5",
            "com.nvidia.cusparselt.version": "0.7.1.0",
            "com.nvidia.nccl.version": "2.26.5",
            "com.nvidia.npp.version": "12.4.0.27",
            "com.nvidia.nsightcompute.version": "2025.2.0.11",
            "com.nvidia.nsightsystems.version": "2025.3.1.90",
            "com.nvidia.nvjpeg.version": "12.4.0.16",
            "com.nvidia.tensorrt.version": "10.10.0.31",
            "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": 23931282316,
    "GraphDriver": {
        "Data": {
            "LowerDir": "/var/lib/docker/overlay2/1203cdd890787929e194fdc7389f136e2f5ab503e9ef60dc9c8de14bdde815b1/diff:/var/lib/docker/overlay2/20d4aa8b07c092734763bd72097ef52f97beca27c577a6e6e9d3fea4afc616c3/diff:/var/lib/docker/overlay2/207eeb28caac79c2b16156f80f3bed1fc1bcd68f64674938578c39777ea4bd31/diff:/var/lib/docker/overlay2/97083c365fb28bcd1676d5b427045533b3e8e4e66425ab58f69f15275d27937d/diff:/var/lib/docker/overlay2/8cde9128b4b0b9fa2b5b43708eba95298d93a67f0031efb91dc1aa0cabe6cf5e/diff:/var/lib/docker/overlay2/90b8be73ae418a01f12906bcb90d08763a22645882ce253f136ba60fc8450a4e/diff:/var/lib/docker/overlay2/f9a35cdfe8c053384d5222a949a2e22bd34947cb792841b75805687d7e9d38e3/diff:/var/lib/docker/overlay2/853875547a310f7a1c54d42c75ef36cc2cce82c469ce6cb88fd3d09992844308/diff:/var/lib/docker/overlay2/8d33cfc6c754d0f5f019f2904f180094a6b1401eeb233d322e76188fdf0eb899/diff:/var/lib/docker/overlay2/939569a0477ae001906b25543d072335bb63169ad5330ee0e434385157824bbf/diff:/var/lib/docker/overlay2/998b1ffaeb4431924b153d7a72402339dde97cbe53b8219c6bc77c7c783ed2f7/diff:/var/lib/docker/overlay2/9bc3d6fd78b7acb1661e262423a2999d5a7821beb74cef716a5dd1386a29a37e/diff:/var/lib/docker/overlay2/cd18fe7aafb8d436a5d3d67df9788042766de02d2c7d316b0661a72fe4c739a8/diff:/var/lib/docker/overlay2/99bf2ae666cb408717e3945f3de728654405e523bcfffa5b86459de8c905b726/diff:/var/lib/docker/overlay2/158f19013e1fa65d89201fdc043a9b164936a7a0f5da2090ca6aaefc07f0b467/diff:/var/lib/docker/overlay2/8b0d591eb29004c73b7bce66ea2e477aea60787b0ef270a6c575d9af2632c1cb/diff:/var/lib/docker/overlay2/fccd0bbbd96d2369386205e33de4e277acf8e35a4a13593302dc4a5eca0648cd/diff:/var/lib/docker/overlay2/b478fb6c92076ad4a8b2ff72e63435662b0e350a4464db9491fab072a801a39d/diff:/var/lib/docker/overlay2/26708af5fe563dbb36da642fa644468a09ea4d965eaa9a9a38e27731f9ce18fe/diff:/var/lib/docker/overlay2/ce7bb55a21cb91e9535cbdb2072f8c45622d704b01e33d5c9a7a85171dd44039/diff:/var/lib/docker/overlay2/4b186af628663a2b5d6265de020e032c73d23fb349a9e537ecf53007c52cca3f/diff:/var/lib/docker/overlay2/2e377d34574ed0e7dc8925cff14046ba4cf9dd3c5048f7e9478606ea0c060a53/diff:/var/lib/docker/overlay2/8a8bdfc6030321b1a99854413f179a5520d379d9ad37529b827365c6d4863cdd/diff:/var/lib/docker/overlay2/39323fc31ccbad0ef9809f4540d284bee203d8c4d8df4c555b50b857b66787f6/diff:/var/lib/docker/overlay2/4be20ea47b8d46a5e4e35e48486c6caf40d192b0fa896efbd05d4eb13e338e13/diff:/var/lib/docker/overlay2/34b3d6aa91707eeb359b4052531cc3613897f833858c750d197faa969759758a/diff:/var/lib/docker/overlay2/162e980b37e529c6a75ee93cee86eced14c4d8e2ce84541f9600b11d9b44022b/diff:/var/lib/docker/overlay2/ac854687171d0eebb1a632c357523421cde0e0e2f561879567071227cdd2ca6f/diff:/var/lib/docker/overlay2/24b2d69ce293f91f1532424317e44481481aad5e798c41ab2d89cb6290a48981/diff:/var/lib/docker/overlay2/288db680d0ecc781c5bc792e65aafeff9228f23b1e20f526712e5ceb765fa326/diff:/var/lib/docker/overlay2/9ce06fd5639458d55a6f9a2b8d845868b58d8d518a461b503a87c6e1a4483e44/diff:/var/lib/docker/overlay2/3cabfacd28530472d28a02461d14b94f630814dc8774afab3edd1f8232ae3585/diff:/var/lib/docker/overlay2/804f0900c22a22c0ab47f8a0a361f520535ca58c85e6793865a1afff531414a9/diff",
            "MergedDir": "/var/lib/docker/overlay2/c49574e75457c0be9f4d1cbb7109a3d6c95e3ccb48ad3e633bd85a5658ff639d/merged",
            "UpperDir": "/var/lib/docker/overlay2/c49574e75457c0be9f4d1cbb7109a3d6c95e3ccb48ad3e633bd85a5658ff639d/diff",
            "WorkDir": "/var/lib/docker/overlay2/c49574e75457c0be9f4d1cbb7109a3d6c95e3ccb48ad3e633bd85a5658ff639d/work"
        },
        "Name": "overlay2"
    },
    "RootFS": {
        "Type": "layers",
        "Layers": [
            "sha256:8901a649dd5a9284fa6206a08f3ba3b5a12fddbfd2f82c880e68cdb699d98bfb",
            "sha256:5f70bf18a086007016e948b04aed3b82103a36bea41755b6cddfaf10ace3c6ef",
            "sha256:04d63d8d6192024fb76fe5ff3b4dbbdf1c5525a7e566c0c6d575251ed6974491",
            "sha256:261dd6ce2db8fc09070cb6938667466eb45027384cec2b20c377bd43ccbf8e34",
            "sha256:e70befb623977c7a495f3b4c9bcec5cfb3f492bc1c61139da04be6162910f1cc",
            "sha256:74b431e8e4c1d2cb42d306fd5bc335df86102c95adedf3c60a259ba30aa4c654",
            "sha256:8baae5d0e2f1d4c69af2b6b99ff7642067ade8ab30439538fea88f18f5d951c0",
            "sha256:5be4749445a709a20eebb83a3fac11073c605546bf0ca774bf1a0051c117ce15",
            "sha256:f85fae2533b1caf1a02816393a08637d2e18c85d36925476f71f720b1cf60477",
            "sha256:2376e045cc7955851e3e2aa62f642f986559d537c51d8d4ded8753037ed89e18",
            "sha256:01c6adcd728c958428cd8d65a564a82c0d778202c79d83c0323d6a874a67196b",
            "sha256:5ca4c71f1ccd4a91afee91bb2dcd8f33f8dcb85956f6a3f69656f6932e3f0ed0",
            "sha256:900cb8a04129d56ac6ccd6202b19e323545949bd5b55c00afdea676fc9e78ae9",
            "sha256:c6edfce02c7a42fd0a54662058c594133afeaf3cfd89637cdd7a952506fb0738",
            "sha256:de6941693e07fc917fcb13cc5e48412f7d92a59cd6e51c8e3fd027b4d71273c4",
            "sha256:911e6a49a72cff1b24ad9b5d9df99b6faaf1350a9e516749c0a60651b0f196ce",
            "sha256:35171b6926ca4cb8c518221dd3880a470c2e1e1d3ae40aa6baf81943b3a5358a",
            "sha256:78f080159b4adbc9676ae0e3b6077c9f190040acbb9a7dcfbae7518ed4482b8c",
            "sha256:a4e985ccf24c4d29949ac5a4be40d2731bc4afd04469012570401fbf894554d4",
            "sha256:19f2915f279f45704f35494d37e8ae6e11ae0a042d76c2627c054b4166ca4d24",
            "sha256:355312c86fe18eb68c97d411c1a65dce6909eba3d94b613f509166ec98a6eb1d",
            "sha256:f876c32a146330ba07d9f3db39cfbe914cfc9562b425b79714d965cdaa2a4c3d",
            "sha256:2e58080bdfbb29afc472d6e4f221188aa577645fb154a63a2ef22cd92aecbd0e",
            "sha256:333fd5601f577f5e11cc3b005da269a55e2949817194288e1786ebd2c4b7997d",
            "sha256:170855739bf58583cd83dc98b05aebc6018f2198c201b1428660460b701e16de",
            "sha256:5f70bf18a086007016e948b04aed3b82103a36bea41755b6cddfaf10ace3c6ef",
            "sha256:d34f36ca334f37d365c4ecb2ea1a3cb00bb357b0235264bf61d1eaafdc7fe7c3",
            "sha256:5f70bf18a086007016e948b04aed3b82103a36bea41755b6cddfaf10ace3c6ef",
            "sha256:6d7c623a9c52fb0ba012a3d8311479155bb7c9f8f705adc6b958cf2d87921f46",
            "sha256:5f70bf18a086007016e948b04aed3b82103a36bea41755b6cddfaf10ace3c6ef",
            "sha256:46401504846a88ed6b17be4c0be68def73167e5f11b4aa3edc5864528255d59e",
            "sha256:e1edb3514e4aad104126abae74f5192ed9d13c129f1c6f13153cba6c447e02ff",
            "sha256:24f50596ae58d788dc214b2713ca235766ffe17462699e5ebafc1185879ae1c2",
            "sha256:5739b899c7bdfab00ba03323b22c6f7845c4e0a7a4080c7c32d071c3f28b0581"
        ]
    },
    "Metadata": {
        "LastTagTime": "2025-06-17T01:20:48.701023465+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
1567

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

linux/amd64 docker.io19.59GB2025-05-22 00:46
2122

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

linux/amd64 docker.io30.15GB2025-05-25 02:51
1191

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

linux/amd64 docker.io14.00GB2025-06-04 06:32
875

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

linux/amd64 docker.io32.90GB2025-06-09 03:41
1244

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

linux/amd64 docker.io23.34GB2025-06-15 02:52
808

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

linux/amd64 docker.io23.93GB2025-06-17 01:33
1267

docker.io/nvcr.io/nvidia/tritonserver:23.05-py3

linux/amd64 docker.io12.88GB2026-01-30 00:29
489
检测到您正在使用广告拦截插件,本站为公益站点,依赖广告维持运转 🙏 查看如何关闭 ×