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
d87e404a21522b7135e05f0abc5fde83e314f284772ba4b5c793a0f4e2749db4CONFIG
Entrypoint /opt/nvidia/nvidia_entrypoint.sh; WorkingDir /opt/tritonserver
06/24/2026 11:17 PM UTC
db42907fb724ebdd4e5482e3866dd0c5e1c82271e5b052f335836efb922e345cLABEL
com.amazonaws.sagemaker.capabilities.multi-models=true
06/24/2026 11:17 PM UTC
56fa6d7d7eb5cb40a8f06bd31e4ad40863550e514cfe4d514d08ba2817d15d70LABEL
com.amazonaws.sagemaker.capabilities.accept-bind-to-port=true
06/24/2026 11:17 PM UTC
615cd622c23c78b6ef638f7c785a9fb6358a910ce2365f4af844850735ca2b8dRUN
TRITON_VERSION=2.70.0 TRITON_CONTAINER_VERSION=26.06 pip3 install -r python/openai/requirements.txt
06/24/2026 11:17 PM UTC
80062782013a704f84c0b8d9319d43c6f16acd6d8cae7818f1a4d1303161d997RUN
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 11:16 PM UTC
490a7396291eb897ddcdda129c4c5d48c3016f46134c55f3cee4b9f77a43b448COPY
NVIDIA_Deep_Learning_Container_License.pdf .
06/24/2026 11:16 PM UTC
c29864e68dcca6c525e028cba9db97c37dbf0c14977287be5fa6ab913d1ab12eWORKDIR
/opt/tritonserver
06/24/2026 11:16 PM UTC
8cd5ed48e5862725deb01215545b13e8c68dd794d07439712545c6fe02aa6bd4COPY
build/install tritonserver
06/24/2026 11:16 PM UTC
130b808d4cdd0c3d9fd468080a26595476ca207d55dbe132bac9a868f6651aa1WORKDIR
/opt
06/24/2026 11:16 PM UTC
90af7b4ba681a59bafe033495dc6ff294b477f02a7909c781f230af2e6b9746cLABEL
com.nvidia.build.ref=04a5082d584f92086a02a47a5f3e75e4d644e1f6
06/24/2026 11:16 PM UTC
...