TensorRT | NVIDIA NGC

NVIDIA

TensorRT

Container

NVIDIA

TensorRT

NVIDIA TensorRT is a C++ library that facilitates high-performance inference on NVIDIA graphics processing units (GPUs). TensorRT takes a trained network and produces a highly optimized runtime engine that performs inference for that network.

NVIDIA AI Enterprise Supported

Layer	Label		Created
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.nvidia.build.ref=39e44ee4210889e7f10594ef59ffcc26f76274f6`	04/15/2025 5:28 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_REF=39e44ee4210889e7f10594ef59ffcc26f76274f6`	04/15/2025 5:28 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.nvidia.build.id=159049473`	04/15/2025 5:28 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`NVIDIA_BUILD_ID=159049473`	04/15/2025 5:28 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_ID=159049473`	04/15/2025 5:28 PM UTC
sha256:8197e914d0b1d92a9941b4b730f646ba3f4be0a89d3e47ff74d1c008272dc670	COPY	`entrypoint.d/ /opt/nvidia/entrypoint.d/`	04/15/2025 5:28 PM UTC
sha256:e20f103a820bdffa18f86d3ae7946200e1694bf212beeeb9099d72386b6578f6	RUN	`NVIDIA_TENSORRT_VERSION=25.04 TRTOSS_VERSION=master PYVER=3.12 ln -sf ${_CUDA_COMPAT_PATH}/lib.real ${_CUDA_COMPAT_PATH}/lib && echo ${_CUDA_COMPAT_PATH}/lib > /etc/ld.so.conf.d/00-cuda-compat.conf && ldconfig && rm -f ${_CUDA_COMPAT_PATH}/lib`	04/15/2025 5:28 PM UTC
sha256:c46c8e8c7378ec3f8fc6da0aefc4ebd45b8f30f92828d92b776b16bb8319c4f9	COPY	`README.md README.md`	04/15/2025 5:28 PM UTC
sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1	WORKDIR	`/workspace`	04/15/2025 5:28 PM UTC
sha256:b48a5fafcaba74eb5d7e7665601509e2889285b50a04b5b639a23f8adc818157	ADD	`docs.tgz /`	04/15/2025 5:28 PM UTC