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
13a5f75d5aee4b82f40dd2ec6ac957695844934f9e41760433c60b6e5ae28761CONFIG
Entrypoint /opt/nvidia/nvidia_entrypoint.sh; WorkingDir /opt/tritonserver
06/18/2025 10:44 PM UTC
2493a8794f26f4412823d2fa3e6abe89ec7dad0353d77d8f83f5de02983452dfLABEL
com.amazonaws.sagemaker.capabilities.accept-bind-to-port=true
06/18/2025 10:44 PM UTC
317eb997eee311eae8467802f489bb71c355ed3bf4500bbf80ffa545ebb67024RUN
TRITON_VERSION=2.59.0 TRITON_CONTAINER_VERSION=25.06 chown triton-server:triton-server /opt/tritonserver/caches
06/18/2025 10:44 PM UTC
2369ac9956358a93b332dd8f77dc7ed557428479d3ed51df32011655184c5f5eCOPY
--chown=1000:1000 /opt/tritonserver/caches/local /opt/tritonserver/caches/local
06/18/2025 10:44 PM UTC
5dfaaebb25b5119d3aeee8ef8a1780b212731aacbf986305433c929a92a04b3eRUN
TRITON_VERSION=2.59.0 TRITON_CONTAINER_VERSION=25.06 chown triton-server:triton-server /opt/tritonserver/repoagents
06/18/2025 10:44 PM UTC
50d52b58db22b8a7b1068c50485e6bc941aed96b116053408c393d12ee82cd2fCOPY
--chown=1000:1000 /opt/tritonserver/repoagents/checksum /opt/tritonserver/repoagents/checksum
06/18/2025 10:44 PM UTC
2dc1a09dd228872885206e96fbabe0dac231c2f64d8fbea1a6fa87eaa1c74fcdRUN
TRITON_VERSION=2.59.0 TRITON_CONTAINER_VERSION=25.06 chown triton-server:triton-server /opt/tritonserver/backends
06/18/2025 10:44 PM UTC
afc6bccfae3933ccef067d53bc3d029a159869ad8f362858910798c106fc23c4COPY
--chown=1000:1000 /opt/tritonserver/backends/python /opt/tritonserver/backends/python
06/18/2025 10:44 PM UTC
5933e7db6ca5f3dc04e05fcd0d13991faf1094d5ce5084ed215b348c273b768bCOPY
--chown=1000:1000 /opt/tritonserver/backends/identity /opt/tritonserver/backends/identity
06/18/2025 10:44 PM UTC
044023c546662184a19e57da9ffdf327169a003e684e4eae80647417218ad2ffCOPY
--chown=1000:1000 /opt/tritonserver/backends/pytorch /opt/tritonserver/backends/pytorch
06/18/2025 10:44 PM UTC
...