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
de1d6a7be0ecb9cca1e3eccd9ab13f1b2d9976d1a096ea29ba59708a4667c5e3CONFIG
Entrypoint /opt/nvidia/nvidia_entrypoint.sh; WorkingDir /opt/tritonserver
06/24/2026 11:42 PM UTC
ffce8fde732e8ce4481a6fa3497825ad206e791ad305f9af1ac408f995b0ed1cCOPY
docker/sagemaker/serve /usr/bin/.
06/24/2026 11:42 PM UTC
7800dd2603a681f14338252d35e3def45438b5fc2f9d2aeb83d21285d71c4d13LABEL
com.amazonaws.sagemaker.capabilities.multi-models=true
06/24/2026 11:42 PM UTC
15039c2817e9af16e58db83e5507689fc65e9b0d97a8f7b65b5657439b38d39fLABEL
com.amazonaws.sagemaker.capabilities.accept-bind-to-port=true
06/24/2026 11:42 PM UTC
f878d4dfc95ad6ac5437ed2b8a8db7fa92acc4cb1eac9a03a4287f5301e0d000RUN
TRITON_VERSION=2.70.0 TRITON_CONTAINER_VERSION=26.06 pip3 install -r python/openai/requirements.txt
06/24/2026 11:42 PM UTC
62849b28db8b8d45c67b0929ebc8dd49b16f8acdbe027b7e1edaadf2b154f1d1RUN
TRITON_VERSION=2.70.0 TRITON_CONTAINER_VERSION=26.06 set -e; for pkg in tritonserver tritonfrontend; do wheels=$(find /opt/tritonserver/python -maxdepth 1 -type f -name "${pkg}-*.whl"); if [ -z "$wheels" ]; then echo "ERROR: ${pkg}-*.whl missing from /opt/tritonserver/python -- build did not stage the wheel into the image" >&2; exit 1; fi; printf '%s\n' "$wheels" | xargs -I {} pip install --upgrade "{}[all]"; done
06/24/2026 11:42 PM UTC
873e68b906700592ee6678c1c3d6db903754edc335cf5b92e4229fbabc117970COPY
NVIDIA_Deep_Learning_Container_License.pdf .
06/24/2026 11:42 PM UTC
8e6713f6da6ede2d5a297c138b5e17d650a13c2ff70749947e4f1e389647fdf7WORKDIR
/opt/tritonserver
06/24/2026 11:42 PM UTC
4fa3b5c3ff78de0d7cd49a239162daaf8a443242bac8661b1958f0f1988cfbe9COPY
build/install tritonserver
06/24/2026 11:42 PM UTC
8657fffdbd2ee952d23c182f1a4eb07e6359625b44f1dc13a8a28ee936839710WORKDIR
/opt
06/24/2026 11:42 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.