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=648a99a0a7dec37686c6b156ef616c84d44038b4`	05/15/2025 2:43 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_REF=648a99a0a7dec37686c6b156ef616c84d44038b4`	05/15/2025 2:43 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.nvidia.build.id=168244664`	05/15/2025 2:43 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`NVIDIA_BUILD_ID=168244664`	05/15/2025 2:43 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_ID=168244664`	05/15/2025 2:43 AM UTC
sha256:2092f4bbbb3752f46639cdf80d7fc24058624c52ed8f7ce222209f6daf918158	COPY	`entrypoint.d/ /opt/nvidia/entrypoint.d/`	05/15/2025 2:43 AM UTC
sha256:47769e0d806cf04670c01054379b30696ac30a7553067b3ce8780e1f416e3ad6	RUN	`NVIDIA_TENSORRT_VERSION=25.05 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`	05/15/2025 2:43 AM UTC
sha256:5d04eea72f87166db81117528a966bdd7e02147fd0abbcb8d33ad7ee1656de38	COPY	`README.md README.md`	05/15/2025 2:43 AM UTC
sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1	WORKDIR	`/workspace`	05/15/2025 2:43 AM UTC
sha256:b48a5fafcaba74eb5d7e7665601509e2889285b50a04b5b639a23f8adc818157	ADD	`docs.tgz /`	05/15/2025 2:43 AM UTC