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
sha256:d5708269ee57e9820d548d15de46da722552602542d58cba259e1c9361a814f9RUN
TRITON_VERSION=2.63.0 TRITON_CONTAINER_VERSION=25.11 pip3 install -r python/openai/requirements.txt
11/20/2025 9:24 PM UTC
sha256:31300721cb928c54c0fb6975f3ff29921dc7aa59bc028097ec6e96c69a5671d1RUN
TRITON_VERSION=2.63.0 TRITON_CONTAINER_VERSION=25.11 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]
11/20/2025 9:24 PM UTC
sha256:dfb9f9f546b7eaf883d8e4bd3bf9991b0c49e838a2cfa3367a19d19421f146cfCOPY
--chown=1000:1000 NVIDIA_Deep_Learning_Container_License.pdf .
11/20/2025 9:24 PM UTC
sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1WORKDIR
/opt/tritonserver
11/20/2025 9:24 PM UTC
sha256:222523d549a43a50f6e20b96a57d0d86ab044e1df5588dff5023e78b9c0cfda8COPY
--chown=1000:1000 build/install tritonserver
11/20/2025 9:24 PM UTC
sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1WORKDIR
/opt
11/20/2025 9:24 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4LABEL
com.nvidia.build.ref=cc221d499acd606668317ca89e5a056a30ec4c90
11/20/2025 9:24 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4LABEL
com.nvidia.build.id=236082569
11/20/2025 9:24 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
NVIDIA_BUILD_ID=236082569
11/20/2025 9:24 PM UTC
sha256:d1db955ae8f46d15d1d50e5532655f6eeb3b71f648be9f0dcc499c4d6d5308c4COPY
docker/entrypoint.d/ /opt/nvidia/entrypoint.d/
11/20/2025 9:24 PM UTC
...