Triton Inference Server

NVIDIA

Container

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.

NVIDIA AI Enterprise Supported

Layer	Label		Created
3299d933eefe2fc7f7f6ec5efa649a56f568aaec43d94a1c35e5ed0b9f52fe77	CONFIG	`Entrypoint /opt/nvidia/nvidia_entrypoint.sh; WorkingDir /opt/tritonserver`	07/28/2025 4:07 PM UTC
3161b21c098d370328456ddeb6be56819feaf4ce2789c26998d1d34fd24abd82	RUN	`TRITON_VERSION=2.59.1 TRITON_CONTAINER_VERSION=25.07 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]`	07/28/2025 4:07 PM UTC
db829df46c3b715d2a591d67eb2e9034256ecdb1a87738beeca8c79f55792c60	COPY	`--chown=1000:1000 NVIDIA_Deep_Learning_Container_License.pdf .`	07/28/2025 4:07 PM UTC
3e242f5924a0668e049578810064773eccf6a2bfdc15b6687c2bcf3ea8d7405c	WORKDIR	`/opt/tritonserver`	07/28/2025 4:07 PM UTC
05945d5923f923447d61d82dbd5b5d2f1f622774a6b1f1cfc4d6d7e6ffbe7841	COPY	`--chown=1000:1000 build/install tritonserver`	07/28/2025 4:07 PM UTC
9d2b8b02100bd9a73eb4d260fe8f66aef5a0274b599931b24031454ba791f238	WORKDIR	`/opt`	07/28/2025 4:07 PM UTC
1b897f55e3bf0c3b190284dd02c3735d3106de8677bc5f6de2eeb6d6b35acf09	LABEL	`com.nvidia.build.ref=94e3a7cf3e836818273f6a353849cd3f9fc26b5a`	07/28/2025 4:07 PM UTC
7ef3aa72202799682d52155d820a975e8aae2fe7de34e0fcbba7e5b73be4a7df	LABEL	`com.nvidia.build.id=193148867`	07/28/2025 4:07 PM UTC
22c5e1ae388fb8589e40e962990f3f6001cd9aaec13b191b71ec2a440eb9f97f	ENV	`NVIDIA_BUILD_ID=193148867`	07/28/2025 4:07 PM UTC
5e4f94dafc7ddc114c301451d4fa67c695bd44028770e3212401b55a6e6a9812	COPY	`docker/entrypoint.d/ /opt/nvidia/entrypoint.d/`	07/28/2025 4:07 PM UTC