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
sha256:159f11da2040ee402888e510ebe35d21498fc80d0f01ad0badb7c18402806a3fRUN
TRITON_VERSION=2.66.0 TRITON_CONTAINER_VERSION=26.02 pip3 install -r python/openai/requirements.txt
02/13/2026 7:27 PM UTC
sha256:15dc33b12c067b15d1aa6292d20fc086bd03c183b9fa78564c49ddd15e3cc236RUN
TRITON_VERSION=2.66.0 TRITON_CONTAINER_VERSION=26.02 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]
02/13/2026 7:27 PM UTC
sha256:8eec8cf3ec58f38da175369a2c213f9fbb8637017237f53fb4e17c994d3417d1COPY
--chown=1000:1000 NVIDIA_Deep_Learning_Container_License.pdf .
02/13/2026 7:26 PM UTC
sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1WORKDIR
/opt/tritonserver
02/13/2026 7:26 PM UTC
sha256:6d208029d2d8829cb1d3775fd85d216842e3d358767552d7341b68d70a16abddCOPY
--chown=1000:1000 build/install tritonserver
02/13/2026 7:26 PM UTC
sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1WORKDIR
/opt
02/13/2026 7:26 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4LABEL
com.nvidia.build.ref=90e8ae01b64a8511866ce5d876eab9d6179c8eee
02/13/2026 7:26 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4LABEL
com.nvidia.build.id=267853693
02/13/2026 7:26 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
NVIDIA_BUILD_ID=267853693
02/13/2026 7:26 PM UTC
sha256:e99e665f49fb7d59e10dcf5f0b5c5a0c461244128e1d898780bff1377579961eCOPY
docker/entrypoint.d/ /opt/nvidia/entrypoint.d/
02/13/2026 7:26 PM UTC
...