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
bcaf6fd8be9c4d134d9d5d6d41a461a8e1fe6e1642aed9befd3625e69a19b7f7CONFIG
Entrypoint /opt/nvidia/nvidia_entrypoint.sh
04/24/2026 1:11 AM UTC
fa24c067ef100a540260fad9941cc1be3458135ab52a557a26442c06832fd057COPY
docker/entrypoint.d/ /opt/nvidia/entrypoint.d/
04/24/2026 1:11 AM UTC
a1d60edec72330ccaa8db894bcc3f7dbfaf71c9a2cc1a1e4e9d937393ffc235cENV
NVIDIA_PRODUCT_NAME=Triton Server Base
04/24/2026 1:11 AM UTC
0541d9318ee11b8ab526355bb9bfe936d7c9dc5501bdaa2dac69a2aa83de315bENV
NVIDIA_BUILD_ID=304383827
04/24/2026 1:11 AM UTC
2b276652e8435c735ace4d1df9a16d3d1b9ea676036f5995ff1d72f9dd33356bENV
NVIDIA_TRITON_SERVER_BASE_VERSION=26.04
04/24/2026 1:11 AM UTC
367a582393eb93284a24df77061a2bba731c18b6c6c422cc7c48213474887cfaARG
NVIDIA_BUILD_ID=304383827
04/24/2026 1:11 AM UTC
76f0b47f628bb02734fc9f4bfac8ebc10ce94bb6625e49c41342795cb1cb635eARG
NVIDIA_TRITON_SERVER_BASE_VERSION=26.04
04/24/2026 1:11 AM UTC
8774116763ab1500e0ff0d7c8c0fe22d72998e305b56d18ea361772ae27c0462RUN
TARGETARCH=amd64 ENABLE_FIPS=0 ENABLE_MITMPROXY=0 /tmp/manage_cert.sh uninstall
04/11/2026 7:48 PM UTC
2ed918159e5844c3abd0a660c4312399109a0cac246475a1276c1f2780fbf189ENV
LIBRARY_PATH=/usr/local/cuda/lib64/stubs:/usr/local/cuda/lib64/stubs:
04/11/2026 7:48 PM UTC
e4ca442ddbcbb6f8a8e090fab54c5b1e93a4e562a133c923a054754ebea6f6beRUN
RUN |3 TARGETARCH=amd64 ENABLE_FIPS=0 ENABLE_MITMPROXY=0 /bin/sh -c set -exo pipefail export ARTIFACTORY_USER=$(cat /run/secrets/ARTIFACTORY_USER) export ARTIFACTORY_TOKEN=$(cat /run/secrets/ARTIFACTORY_TOKEN) export DEVEL=1 BASE=0 /nvidia/build-scripts/installNCU.sh /nvidia/build-scripts/installCUDA.sh /nvidia/build-scripts/installLIBS.sh /nvidia/build-scripts/installNCCL.sh # https://jirasw.nvidia.com/browse/DLR-4957 to get the headers and static files with symlinks to the common location DPKG_DIVERT=1 STATIC=1 /nvidia/build-scripts/installNVSHMEM.sh /nvidia/build-scripts/installCUDNN.sh /nvidia/build-scripts/installTRT.sh ARTIFACTORY_CLOUD=1 /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
04/11/2026 7:48 PM UTC
...