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
8f139fa8ef53a8fdd91cfe6001b9d7a86d1572bf666ac00a6b2e415c6ba1f13fCONFIG
Entrypoint /opt/nvidia/nvidia_entrypoint.sh; WorkingDir /opt/tritonserver
10/29/2025 6:31 PM UTC
cbbc68ab3418209c0c059fc68f40e8bd1df83026f9a7f7bcff5b24c269115e8eLABEL
com.amazonaws.sagemaker.capabilities.multi-models=true
10/29/2025 6:31 PM UTC
e537fd43366bd1d28d0106b16a55dd3f48c7d7ac38fcaa2360eed131d9dbb685LABEL
com.amazonaws.sagemaker.capabilities.accept-bind-to-port=true
10/29/2025 6:31 PM UTC
1fb6ee6911da096a034d0b3a132ce0cba7bc982d58bb93ed762c426312ad434dRUN
TRITON_VERSION=2.62.0 TRITON_CONTAINER_VERSION=25.10 BUILD_PUBLIC_VLLM=false PYVER=3.12 pip3 install -r python/openai/requirements.txt
10/29/2025 6:31 PM UTC
b707b59a76e64f84e0f9ce026eb320100ea8fbb087681ab8cc8faa2c95383a09RUN
TRITON_VERSION=2.62.0 TRITON_CONTAINER_VERSION=25.10 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]
10/29/2025 6:31 PM UTC
6314b74ff21ccbcc784dbaa6c9f6d829601b835cd87919563d670c810fd1700eCOPY
--chown=1000:1000 NVIDIA_Deep_Learning_Container_License.pdf .
10/29/2025 6:31 PM UTC
1cb91cc4bd6af42bd1c46436e66f38ce7c99fb024262e5956ac0067658444212WORKDIR
/opt/tritonserver
10/29/2025 6:31 PM UTC
8fd869e137fbeb6a2a3ca0840992d176e0839b5fb15fcd8a9966016e7c5232b5COPY
--chown=1000:1000 build/install tritonserver
10/29/2025 6:31 PM UTC
952263808f17d0712985d32c4b12e92eb1e5188c29ddf60e5cbfab9d825876f7WORKDIR
/opt
10/29/2025 6:31 PM UTC
ef30f342f48799f7840067f54a42d1cfd271ea7e974f632ed3bbb2fec766f935LABEL
com.nvidia.build.ref=374194f9f494599a028053e9d3f6771b7e37ef76
10/29/2025 6:31 PM UTC
...