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
e29f8b2a6c4a7de1ddfed243ce359c55de66347f472a6c19557ce047a7e2a791	CONFIG	`Entrypoint /opt/nvidia/nvidia_entrypoint.sh; WorkingDir /opt/tritonserver`	12/19/2025 12:54 AM UTC
57f25a16862cbd8b745998f0573f4c8bac4bf4b51a2f7d3ca8ab746e5634a80c	RUN	`TRITON_VERSION=2.64.0 TRITON_CONTAINER_VERSION=25.12 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]`	12/19/2025 12:54 AM UTC
dacf3cf2c311c92ffc1f8019d6ca0738d565fc286bc7f9cc2de473fa91e7b1c3	COPY	`--chown=1000:1000 NVIDIA_Deep_Learning_Container_License.pdf .`	12/19/2025 12:54 AM UTC
a709076985bf19747d3fc1ec6dcea33b505ba5c8c0b9fd1c7a781161f24d3c5f	WORKDIR	`/opt/tritonserver`	12/19/2025 12:54 AM UTC
4d70d02b7ce3840a551c763bcc7c00b6b28fbc42a1ed866a249af23c77e394ea	COPY	`--chown=1000:1000 build/install tritonserver`	12/19/2025 12:54 AM UTC
43a185b462528d66041805485867818341d1e17f3cf7e97a969d1cda05bc7993	WORKDIR	`/opt`	12/19/2025 12:54 AM UTC
75ce4a0f66530bbb09f6a14da45c00759a0a272f2997b8a48d5702263e6f5d2b	LABEL	`com.nvidia.build.ref=9bf730f9c9c3d98fa3d2fd5ef82f0aa5bd7c5d45`	12/19/2025 12:54 AM UTC
a391832856e2187d6282af88b10f201e844a8cf0f4ea4eeb5bd062076ad4972d	LABEL	`com.nvidia.build.id=246541557`	12/19/2025 12:54 AM UTC
c80dd01d178e444b55de689cde922092f5cba78cacfd9b38a88317c3a71e8a4b	ENV	`NVIDIA_BUILD_ID=246541557`	12/19/2025 12:54 AM UTC
1f71f99726158af10962104a64dff2aad7bf4aaa408b3743166bc7e0bc31d8ea	COPY	`docker/entrypoint.d/ /opt/nvidia/entrypoint.d/`	12/19/2025 12:54 AM UTC