ContainersNVIDIADeepSeek-R1NVIDIALlama-3.1-Nemotron-70B-InstructNVIDIAPyTorch
CollectionsNVIDIAOmniverse Kit (FB)NVIDIADeepStream SDKNVIDIAOmniverse Kit App Streaming
ModelsNVIDIAStyleGAN3 pretrained modelsNVIDIAPeopleNetNVIDIATrafficCamNet
ResourcesNVIDIAKit SDK - Windows (PB25h1)NVIDIAKit SDK - Linux (PB25h1)NVIDIARiva Skills Quick Start
Helm ChartsNVIDIAGPU OperatorNVIDIANVIDIA NIM Operator
NVIDIA
NVIDIA
Triton Inference Server
Container
NVIDIA
NVIDIA
Triton Inference Server

Triton Inference Server is an open source software that lets teams deploy trained AI models from any framework, from local or cloud storage and on any GPU- or CPU-based infrastructure in the cloud, data center, or embedded devices.

NVIDIA AI Enterprise Supported
LayerLabelCreated
75eef349f19261697718c3c9b5db8bab0f70de713c24dfd6dd5a67808075bc8fCONFIG
Entrypoint /opt/nvidia/nvidia_entrypoint.sh; WorkingDir /workspace
10/29/2025 6:28 PM UTC
9d41fef018b41f8de9ecb63250cbd3d65fac9ef61f42c6da93b68741b08c3ad6ENV
LD_LIBRARY_PATH=/opt/hpcx/ompi/lib:/workspace/install/lib:/usr/local/cuda/compat/lib:/usr/local/nvidia/lib:/usr/local/nvidia/lib64
10/29/2025 6:28 PM UTC
60fbd3fe0d45073fdb626a0ae60b17cf900bc36a99d791c5bdaeb8bc5797cda1ENV
LD_LIBRARY_PATH=/workspace/install/lib:/usr/local/cuda/compat/lib:/usr/local/nvidia/lib:/usr/local/nvidia/lib64
10/29/2025 6:28 PM UTC
8bd7c6f9a413ba46d54db52f4858a680e434baf3216a3a9224f30586ed8f0698ENV
PATH=/workspace/install/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
10/29/2025 6:28 PM UTC
3e319f3d1db8ad3c789babc916068d4e67132c02873bf507ef9c01d630dd85beENV
NVIDIA_BUILD_ID=226999193
10/29/2025 6:28 PM UTC
458db28cc6751ddf403fc7f96460f70e9bbbd35b4f585d331d65cecc2ebd03a2ENV
NVIDIA_TRITON_SERVER_SDK_VERSION=25.10
10/29/2025 6:28 PM UTC
4651488641ccda2551b38984361deebe0910ab932066dce4a405a4a25712fa49ARG
NVIDIA_BUILD_ID=226999193
10/29/2025 6:28 PM UTC
a251b36fd71bc96ea6daf9e74d1d5367e66dab764780ed0ff4ad08e76538427aARG
NVIDIA_TRITON_SERVER_SDK_VERSION=25.10
10/29/2025 6:28 PM UTC
b73aa5748b30100e76a89bc9971c78397eae6a6162bfdd74eebf7a670a6eefb0RUN
DCGM_VERSION=4.4.0-1 TRITON_REPO_ORGANIZATION=https://github.com/triton-inference-server TRITON_CORE_REPO_TAG=r25.10 TARGETPLATFORM=linux/amd64 TRITON_ENABLE_GPU=ON sed 's/Server/Server SDK/' /opt/nvidia/entrypoint.d/10-banner.txt | sed 's/^===/=======/' > /opt/nvidia/entrypoint.d/10-banner.new &&
  mv /opt/nvidia/entrypoint.d/10-banner.new /opt/nvidia/entrypoint.d/10-banner.txt
10/29/2025 6:28 PM UTC
2c1a2a3bdcee8bd375650bb9ec043c1931b05ad0005648f179fd1675174869e8COPY
docker/entrypoint.d/ /opt/nvidia/entrypoint.d/
10/29/2025 6:28 PM UTC
...