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
sha256:60f0d9979840e61ea6e3084344617422df69b2ad7f65118aec72fedabda752ca	COPY	`docker/sagemaker/serve /usr/bin/.`	07/25/2026 7:45 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.amazonaws.sagemaker.capabilities.multi-models=true`	07/25/2026 7:45 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.amazonaws.sagemaker.capabilities.accept-bind-to-port=true`	07/25/2026 7:45 PM UTC
sha256:1a53de032a15d1dfeee49920b4a1d9081809e5ff16d264fd66c7663f68d78668	RUN	`TRITON_VERSION=2.71.0 TRITON_CONTAINER_VERSION=26.07 /bin/bash -c pip3 install -r python/openai/requirements.txt`	07/25/2026 7:45 PM UTC
sha256:9d64825cbc4ae64a40d7b9cb4b869ab2fb89730ba1b0bc3519b6be36dfee23d0	RUN	`TRITON_VERSION=2.71.0 TRITON_CONTAINER_VERSION=26.07 /bin/bash -c set -e; for pkg in tritonserver tritonfrontend; do wheels=$(find /opt/tritonserver/python -maxdepth 1 -type f -name "${pkg}-.whl"); if [ -z "$wheels" ]; then echo "ERROR: ${pkg}-.whl missing from /opt/tritonserver/python -- build did not stage the wheel into the image" >&2; exit 1; fi; printf '%s\n' "$wheels" \| xargs -I {} pip install --upgrade "{}[all]"; done`	07/25/2026 7:45 PM UTC
sha256:e412fb88280dd2669280c589db4087a2859c6a3ca7ab4bc3fcdfea49678455bc	COPY	`NVIDIA_Deep_Learning_Container_License.pdf .`	07/25/2026 7:45 PM UTC
sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1	WORKDIR	`/opt/tritonserver`	07/25/2026 7:45 PM UTC
sha256:0ee6dcaf9b9c9232e9efa5afcfc7db53e99dd95455557dbc7609de053cadad04	COPY	`build/install tritonserver`	07/25/2026 7:45 PM UTC
sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1	WORKDIR	`/opt`	07/25/2026 7:45 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.nvidia.build.ref=a2baab4da6d90d5b21280b303187e8984c66f19a`	07/25/2026 7:45 PM UTC