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
28bb0beda45e87564df4288c4b79cdfa290c42b25d826509d5f5b9c0903d690dCONFIG
Entrypoint /opt/nvidia/nvidia_entrypoint.sh; WorkingDir /opt/tritonserver
05/19/2026 1:11 AM UTC
878ece8c37cb2d8a985e35b4a1c6e2850a2d7ce76da5098910d80702dae6643bLABEL
com.amazonaws.sagemaker.capabilities.multi-models=true
05/19/2026 1:11 AM UTC
842614c22e0c5880cbfc176e08713aed7213af45142f02bd41f8f906e4d887daLABEL
com.amazonaws.sagemaker.capabilities.accept-bind-to-port=true
05/19/2026 1:11 AM UTC
51555152fbc5273e2f7bcb5c6821855b3416dd897930c3f1adbbc56ba47404acRUN
TRITON_VERSION=2.69.0 TRITON_CONTAINER_VERSION=26.05 pip3 install -r python/openai/requirements.txt
05/19/2026 1:11 AM UTC
92e9292325953d01bda7a87bf51800898c0566b087a174024556ed801b15bd69RUN
TRITON_VERSION=2.69.0 TRITON_CONTAINER_VERSION=26.05 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]
05/19/2026 1:11 AM UTC
0137f2275abda4fb9bfdd1535a6ef6e60818016dcb6d111987b34c3fde997bf2COPY
--chown=1000:1000 NVIDIA_Deep_Learning_Container_License.pdf .
05/19/2026 1:11 AM UTC
d3e0118772cbefb83efabae7717f19fb61fec49974587e5c92764a9644eca1a7WORKDIR
/opt/tritonserver
05/19/2026 1:11 AM UTC
5855f5e2910ba4656fb86f2d4bff7de563efb89292a99395c0643718e0b7768fCOPY
--chown=1000:1000 build/install tritonserver
05/19/2026 1:11 AM UTC
3d7a42b764c8978ad16cc91e24dcc9e365ba3ed74e0836620c6a14bc1e38f236WORKDIR
/opt
05/19/2026 1:11 AM UTC
f05431b98308eaba13f58ad0f1843683c7dfd4bbbe70c59383701e626dd2d9dbLABEL
com.nvidia.build.ref=84b0640223ddce28a0887ac64fb53a0d1d436c72
05/19/2026 1:11 AM UTC
...

NVIDIA uses cookies to improve your experience on our web site. We and our third-party partners also use cookies and other tools to collect and record information you provide as well as information about your interactions with our websites for performance improvement, analytics, and to assist in marketing efforts. By clicking "Accept All", you consent to our use of cookies and other tools as described in our Cookie Policy. You can manage your cookie settings by clicking on "Manage Settings." By continuing to use this site or by clicking one of the buttons below, you agree to our Terms of Service (which contains important waivers). Please see our Privacy Policy for more information on our privacy practices.