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=e05e63dddcf27ecd0ce162253545dfeb6d23e69b`	06/12/2025 7:51 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_REF=e05e63dddcf27ecd0ce162253545dfeb6d23e69b`	06/12/2025 7:51 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.nvidia.build.id=177567330`	06/12/2025 7:51 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`NVIDIA_BUILD_ID=177567330`	06/12/2025 7:51 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_ID=177567330`	06/12/2025 7:51 AM UTC
sha256:907f3226fb792ad7d38ae4e5214ab1676c2edca236442e84fbd7217c4fc92a03	COPY	`entrypoint.d/ /opt/nvidia/entrypoint.d/`	06/12/2025 7:51 AM UTC
sha256:f0b481f1e207c35a0bf21a7d6d006adc678614be47c57c036c70b687f7cf1fa3	RUN	`NVIDIA_TENSORRT_VERSION=25.06 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`	06/12/2025 7:51 AM UTC
sha256:20073d86c9930ab82024a454e395c3aa7b9e1be9360358e860b7cbe5aa3e78bc	COPY	`README.md README.md`	06/12/2025 7:51 AM UTC
sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1	WORKDIR	`/workspace`	06/12/2025 7:51 AM UTC
sha256:b48a5fafcaba74eb5d7e7665601509e2889285b50a04b5b639a23f8adc818157	ADD	`docs.tgz /`	06/12/2025 7:51 AM UTC