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
6cc12b8a75f1d876d5d1c2110d727c86cb507e49accff6d40e62b741e1cc044f	CONFIG	`Entrypoint /opt/nvidia/nvidia_entrypoint.sh; WorkingDir /opt/tritonserver`	08/22/2025 1:13 AM UTC
0a210166117b6267ec5eeb8ba38ba7ed5892fd8c0f2d42fc3e6d49a6db20182a	RUN	`TRITON_VERSION=2.60.0 TRITON_CONTAINER_VERSION=25.08 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]`	08/22/2025 1:13 AM UTC
c3d2dcf0b4984828f4b188452ee5cde8197814d92d661f3a998303f23842ca8a	COPY	`--chown=1000:1000 NVIDIA_Deep_Learning_Container_License.pdf .`	08/22/2025 1:13 AM UTC
49441ad0a74896bc9205a47f3497afb61b03a3c4a0450339e2b2fea06aadabf8	WORKDIR	`/opt/tritonserver`	08/22/2025 1:13 AM UTC
92c0effa73da408115872425ad59beaaedc1cd1980f6f461e08700230dee1666	COPY	`--chown=1000:1000 build/install tritonserver`	08/22/2025 1:13 AM UTC
2bae1465192f092b384b0286ab12fe3dd8e13dc0f824f971677bf8f478b4ecab	WORKDIR	`/opt`	08/22/2025 1:12 AM UTC
6da0ff32b891fa13e5b3a99a8b289aaf4e1e128a870c62dab347a4e6a8e5caaa	LABEL	`com.nvidia.build.ref=8ced3b40794a0aed058b85333c4c4bb638de5476`	08/22/2025 1:12 AM UTC
b44e7194c684e308b51cb2ed001daebceae1f435737bcee6113e69f47d3851a4	LABEL	`com.nvidia.build.id=202022691`	08/22/2025 1:12 AM UTC
619ba1b2796c64665cbaa3f419d7218b7caa087932a77c6af47b458c802f3ec3	ENV	`NVIDIA_BUILD_ID=202022691`	08/22/2025 1:12 AM UTC
9bc18a94f9a0bf477c0ecefc3e534c562a0399e95eba831fb56d897613164ddd	COPY	`docker/entrypoint.d/ /opt/nvidia/entrypoint.d/`	08/22/2025 1:12 AM UTC