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
9ada1300d7e6e6e07d5971a6ab58a0c63ece4737c49e6445cd0452a3dfff900aCONFIG
Entrypoint /opt/nvidia/nvidia_entrypoint.sh; WorkingDir /opt/tritonserver
01/27/2026 10:29 PM UTC
de2a6e4ac1a29e65e837dca7e246a6b5f8147932825f3040420701880b8e3b79LABEL
com.amazonaws.sagemaker.capabilities.multi-models=true
01/27/2026 10:29 PM UTC
15cacb5c8f5cb27d76ca6daff2d18c1f7f32be80bd0e8b1998ee6f98f5f255dfLABEL
com.amazonaws.sagemaker.capabilities.accept-bind-to-port=true
01/27/2026 10:29 PM UTC
3cbda468f899bdaee285a5e0aa8495d5f6fd792014e2e10cce43936fe0606705RUN
TRITON_VERSION=2.65.0 TRITON_CONTAINER_VERSION=26.01 pip3 install -r python/openai/requirements.txt
01/27/2026 10:29 PM UTC
e91c8bd68968fb411d41387fa066ee81c1893e10e85da1383a97ce9d57b96ea7RUN
TRITON_VERSION=2.65.0 TRITON_CONTAINER_VERSION=26.01 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]
01/27/2026 10:29 PM UTC
2002145cc2e057965eacb18f004cfa7352eed9d8481073da9c912d9fbc5fc248COPY
--chown=1000:1000 NVIDIA_Deep_Learning_Container_License.pdf .
01/27/2026 10:28 PM UTC
6d4bbd09da7a2d4d337dcebc4a334d838702269fd44f63c475ab4acf183dc6daWORKDIR
/opt/tritonserver
01/27/2026 10:28 PM UTC
6eeb43ab0f17181452574560046568e9706c09e4d2a990e40de29530f1df4e06COPY
--chown=1000:1000 build/install tritonserver
01/27/2026 10:28 PM UTC
e0aa9911346db571848a4618ed4c8767ec3421f97cc934a68fd16800ee687bd9WORKDIR
/opt
01/27/2026 10:28 PM UTC
d3d8567a81a5b90e21f45e6c9b950236967e5d011c4bf66f598f95234791b526LABEL
com.nvidia.build.ref=c2536fda2e5c6fa09b84b08768f450a39a608761
01/27/2026 10:28 PM 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.