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:b745b875310a903737da0933bc0a59cdfcde2d5631f5c9d982e7318027adf600COPY
--chown=1000:1000 docker/sagemaker/serve /usr/bin/.
01/27/2026 10:18 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4LABEL
com.amazonaws.sagemaker.capabilities.multi-models=true
01/27/2026 10:18 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4LABEL
com.amazonaws.sagemaker.capabilities.accept-bind-to-port=true
01/27/2026 10:18 PM UTC
sha256:f2875469449c23e747312204b02cc613f8456c3f99ac8d3ea719258c82e18aa9RUN
TRITON_VERSION=2.65.0 TRITON_CONTAINER_VERSION=26.01 BUILD_PUBLIC_VLLM=false PYVER=3.12 pip3 install -r python/openai/requirements.txt
01/27/2026 10:18 PM UTC
sha256:9898f73d5dae8c7cc0612a38d55a17a65ee522b062ac38bd80b74dd33e209d94RUN
TRITON_VERSION=2.65.0 TRITON_CONTAINER_VERSION=26.01 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]
01/27/2026 10:17 PM UTC
sha256:e4438cb3125e3cfdef5f6cf988d52429f21042b20631c882e9801460272cb745COPY
--chown=1000:1000 NVIDIA_Deep_Learning_Container_License.pdf .
01/27/2026 10:17 PM UTC
sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1WORKDIR
/opt/tritonserver
01/27/2026 10:17 PM UTC
sha256:4af1219c4d2ae079bcfbd0003e905c2945817f4e67dc26bb26b70cce76121e0aCOPY
--chown=1000:1000 build/install tritonserver
01/27/2026 10:17 PM UTC
sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1WORKDIR
/opt
01/27/2026 10:17 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4LABEL
com.nvidia.build.ref=c2536fda2e5c6fa09b84b08768f450a39a608761
01/27/2026 10:17 PM UTC
...