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.

LayerLabelCreated
ab598041a65aeb13c1d923dd23af0a660ceb176e0812abc1261331a0ba67af3aCONFIG
Entrypoint /opt/nvidia/nvidia_entrypoint.sh; WorkingDir /opt/tritonserver
11/20/2025 9:14 PM UTC
7cda82b896315707df6132a3093033af9f7c0462d59d1ecf357262a18e452fbbLABEL
com.amazonaws.sagemaker.capabilities.multi-models=true
11/20/2025 9:14 PM UTC
981174998947aa3935544cb7f2608b4643f00604e3f51a9a245b521c728da178LABEL
com.amazonaws.sagemaker.capabilities.accept-bind-to-port=true
11/20/2025 9:14 PM UTC
eaf067a19a706faa3bd4625ffe379ad92bad2a53a49ac2f20e7644f7c8f7d5baRUN
TRITON_VERSION=2.63.0 TRITON_CONTAINER_VERSION=25.11 BUILD_PUBLIC_VLLM=false PYVER=3.12 pip3 install -r python/openai/requirements.txt
11/20/2025 9:14 PM UTC
875bce1c80e513e83175e63deff101b0564dab3bcc9ad30236c7efe33029198aRUN
TRITON_VERSION=2.63.0 TRITON_CONTAINER_VERSION=25.11 BUILD_PUBLIC_VLLM=false PYVER=3.12 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]
11/20/2025 9:14 PM UTC
7a1e0d90a8f0ed70f2ad82e1ab917e2d32a3e46ba7c7245ba1f6c3672a729dc7COPY
--chown=1000:1000 NVIDIA_Deep_Learning_Container_License.pdf .
11/20/2025 9:14 PM UTC
2bd93b2d00798b026fd9cdce83694ad86e96c857770b551c49e852f69c7039baWORKDIR
/opt/tritonserver
11/20/2025 9:14 PM UTC
f441dbc0f05add9a1f939b5af21e43723311369f15d57b93b09e6cf3a9c5dc73COPY
--chown=1000:1000 build/install tritonserver
11/20/2025 9:14 PM UTC
e869264d0990b4e6dbb632fa67a3ea6a9a179cec2c5df830c29c06bb74549126WORKDIR
/opt
11/20/2025 9:14 PM UTC
22fd56e319c94847c926a045b691d7f77a6752bef7cdfe7509cb1bf6fe700a02LABEL
com.nvidia.build.ref=cc221d499acd606668317ca89e5a056a30ec4c90
11/20/2025 9:14 PM UTC
...