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
8dcc84a2d483fcedd285560b49419e27999fa338c6105dc6b31bd6f757960fb6	CONFIG	`Entrypoint /opt/nvidia/nvidia_entrypoint.sh; WorkingDir /opt/tritonserver`	01/27/2026 11:26 PM UTC
edc8ed21233dd82c5c66f1b031f37e594cfb9acbbfa231f109ce6faeff2242ea	RUN	`TRITON_VERSION=2.65.0 TRITON_CONTAINER_VERSION=26.01 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]`	01/27/2026 11:26 PM UTC
2e01af66cf1456ab2ea2b2280a3c8494db44c9de491310c41d2cd60a046592da	COPY	`--chown=1000:1000 NVIDIA_Deep_Learning_Container_License.pdf .`	01/27/2026 11:25 PM UTC
809ad3ea08442040315b6a936b246cda34c2d42b342aafdbb64dafec328fb72a	WORKDIR	`/opt/tritonserver`	01/27/2026 11:25 PM UTC
99d1772448b113af355d392908cf60346d7f0382930a7aaeb61e6ad573d11533	COPY	`--chown=1000:1000 build/install tritonserver`	01/27/2026 11:25 PM UTC
d1b20b3ff8618370c13b561ca4071618240ad7fe94f2bcc719deaf1ffc04f76b	WORKDIR	`/opt`	01/27/2026 11:25 PM UTC
b072ce52d6e6f4be92f62cd07d758447247f7b16cbb2d3b5635897ac1862cf8a	LABEL	`com.nvidia.build.ref=c2536fda2e5c6fa09b84b08768f450a39a608761`	01/27/2026 11:25 PM UTC
3dc92adbfd0244811debbf49df56c6f3a585313d38822e54aa04b927f6970db1	LABEL	`com.nvidia.build.id=259402043`	01/27/2026 11:25 PM UTC
78b76cca1ff2cdaeb179c9fe1869a850f8313b3c11ab8e568aa34dd22edeae0b	ENV	`NVIDIA_BUILD_ID=259402043`	01/27/2026 11:25 PM UTC
76d08d1db277fc9b79eca23d8479e94cb6de22e230bbfce4a42fd6c34e5ccbb1	COPY	`docker/entrypoint.d/ /opt/nvidia/entrypoint.d/`	01/27/2026 11:25 PM UTC