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
23ffd9e592c95e7a89be6687124af1ebfe91f29c1af26c00bb2697e9c427051dCONFIG
Entrypoint /opt/nvidia/nvidia_entrypoint.sh; WorkingDir /opt/tritonserver
07/28/2025 3:59 PM UTC
2b611afabbd8907b570d0006c51dfaa224137899f2878ed1166405618c79cb45LABEL
com.amazonaws.sagemaker.capabilities.multi-models=true
07/28/2025 3:59 PM UTC
c14f31dfc0d1006c2532e1bf4e0675f5227144d5487c64646a7f4ae292adfed9LABEL
com.amazonaws.sagemaker.capabilities.accept-bind-to-port=true
07/28/2025 3:59 PM UTC
7748bee03a41dd3458e01c60118913b9ad150597f8b67a117d7ea8f2c2a4dc6fRUN
TRITON_VERSION=2.59.1 TRITON_CONTAINER_VERSION=25.07 BUILD_PUBLIC_VLLM=false PYVER=3.12 pip3 install -r python/openai/requirements.txt
07/28/2025 3:59 PM UTC
9e8e45eea5240c1018cbfa285227c1bcf5139d47a73517dfb923ba8842089d5fRUN
TRITON_VERSION=2.59.1 TRITON_CONTAINER_VERSION=25.07 BUILD_PUBLIC_VLLM=false PYVER=3.12 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]
07/28/2025 3:59 PM UTC
423d06cb1bd401666d37541b1bca9b713f076582e00c4f3a4ad45bd15f14e776COPY
--chown=1000:1000 NVIDIA_Deep_Learning_Container_License.pdf .
07/28/2025 3:59 PM UTC
1b87b8faf947aa7d65652aaaf09f2791140bd480268f35d972c5b949c111390eWORKDIR
/opt/tritonserver
07/28/2025 3:59 PM UTC
0bd76ec6d0ee727857ff32ef0d339c3a23707184533e127c049d558d702a2b87COPY
--chown=1000:1000 build/install tritonserver
07/28/2025 3:59 PM UTC
c490d9a487d330131a170d8b9637988072e5eb9a252ff8127ed18f8e1fc5d81aWORKDIR
/opt
07/28/2025 3:59 PM UTC
28b17c7c26054f46a20c0a6bd3a811406fab288ff309c2149d916ce87a9c3f7aLABEL
com.nvidia.build.ref=94e3a7cf3e836818273f6a353849cd3f9fc26b5a
07/28/2025 3:59 PM UTC
...