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=8ba507063f9c83c11593bb28590f2fea2ef3253d`	09/03/2024 4:10 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_REF=8ba507063f9c83c11593bb28590f2fea2ef3253d`	09/03/2024 4:10 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.nvidia.build.id=109568881`	09/03/2024 4:10 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`NVIDIA_BUILD_ID=109568881`	09/03/2024 4:10 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_ID=109568881`	09/03/2024 4:10 PM UTC
sha256:c5bfd6f1514d9b9e9fc261e58d2af95eff4d85e6f042e4961cddcb978f63c4eb	COPY	`entrypoint.d/ /opt/nvidia/entrypoint.d/`	09/03/2024 4:10 PM UTC
sha256:652534c6e9b3e47cd87b317c4c0c0b65d998c33a505822668b236c7570c41b39	RUN	`NVIDIA_TENSORRT_VERSION=24.09 TRTOSS_VERSION=master PYVER=3.10 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`	09/03/2024 4:10 PM UTC
sha256:d7260704ec46babdef836ac66f85d5e0cba47993635b0876503d944cb2c0144e	COPY	`README.md README.md`	09/03/2024 4:10 PM UTC
sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1	WORKDIR	`/workspace`	09/03/2024 4:10 PM UTC
sha256:b48a5fafcaba74eb5d7e7665601509e2889285b50a04b5b639a23f8adc818157	ADD	`docs.tgz /`	09/03/2024 4:10 PM UTC