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=ee54bb7b648bdbfa7d210c64eef2c00b94a39dd8`	03/07/2025 5:38 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_REF=ee54bb7b648bdbfa7d210c64eef2c00b94a39dd8`	03/07/2025 5:38 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.nvidia.build.id=147944270`	03/07/2025 5:38 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`NVIDIA_BUILD_ID=147944270`	03/07/2025 5:38 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_ID=147944270`	03/07/2025 5:38 PM UTC
sha256:f52f6405c5dd7d89b21e91cb3f35cbdfc80b43871992a304ec14bd9051722395	COPY	`entrypoint.d/ /opt/nvidia/entrypoint.d/`	03/07/2025 5:38 PM UTC
sha256:841c2ec4248230eed6a409902d5be3563f951a9fe1bc5ab8df81e83d5830f4d1	RUN	`NVIDIA_TENSORRT_VERSION=25.03 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`	03/07/2025 5:38 PM UTC
sha256:09f1f9b881efb84e348efbbca3e0d0dc50e231a54b5f7294ec0d76a2e4abddb4	COPY	`README.md README.md`	03/07/2025 5:38 PM UTC
sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1	WORKDIR	`/workspace`	03/07/2025 5:38 PM UTC
sha256:b48a5fafcaba74eb5d7e7665601509e2889285b50a04b5b639a23f8adc818157	ADD	`docs.tgz /`	03/07/2025 5:38 PM UTC