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:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`TCMALLOC_RELEASE_RATE=200`	05/19/2026 12:45 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`LD_LIBRARY_PATH=/opt/hpcx/ompi/lib:/workspace/install/lib:/usr/local/cuda/compat/lib:/usr/local/nvidia/lib:/usr/local/nvidia/lib64`	05/19/2026 12:45 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`LD_LIBRARY_PATH=/workspace/install/lib:/usr/local/cuda/compat/lib:/usr/local/nvidia/lib:/usr/local/nvidia/lib64`	05/19/2026 12:45 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`PATH=/workspace/install/bin:/usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/local/mpi/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/local/ucx/bin:/opt/amazon/efa/bin`	05/19/2026 12:45 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`NVIDIA_BUILD_ID=321060096`	05/19/2026 12:45 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`NVIDIA_TRITON_SERVER_SDK_VERSION=26.05`	05/19/2026 12:45 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_ID=321060096`	05/19/2026 12:45 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_TRITON_SERVER_SDK_VERSION=26.05`	05/19/2026 12:45 AM UTC
sha256:fd221c53850c3ed6dc418bc7260ce2e6a2303aff448462d6c4409d6c8aea0c63	RUN	DCGM_VERSION=4.5.3-1 TRITON_REPO_ORGANIZATION=https://github.com/triton-inference-server TRITON_CORE_REPO_TAG=r26.05 TARGETPLATFORM=linux/amd64 TRITON_ENABLE_GPU=ON TRITON_MODEL_ANALYZER_REPO_TAG=r26.05 TRITON_MODEL_ANALYZER_REPO=https://github.com/triton-inference-server/model_analyzer@r26.05 sed 's/Server/Server SDK/' /opt/nvidia/entrypoint.d/10-banner.txt \| sed 's/^===/=======/' > /opt/nvidia/entrypoint.d/10-banner.new && mv /opt/nvidia/entrypoint.d/10-banner.new /opt/nvidia/entrypoint.d/10-banner.txt	05/19/2026 12:45 AM UTC
sha256:fcfd8f6c9bac62f7b46ee5eabdf8a467b0100a8b6daaf7c07962dbb33c7c4544	COPY	`docker/entrypoint.d/ /opt/nvidia/entrypoint.d/`	05/19/2026 12:45 AM UTC