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=897d16030872297b4332d4a28eb0a27d48bd9511`	03/11/2024 4:35 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_REF`	03/11/2024 4:35 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.nvidia.build.id=85505822`	03/11/2024 4:35 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`NVIDIA_BUILD_ID=85505822`	03/11/2024 4:35 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_ID`	03/11/2024 4:35 PM UTC
sha256:ec99340b6e2719a006302b4923bebc69fcaf64ad0e9de95450fb27ce727d0cd9	COPY	`entrypoint.d/ /opt/nvidia/entrypoint.d/`	03/11/2024 4:35 PM UTC
sha256:bd0eb64889c8141672fd6670aa08a7607f6c7ccf5c52886c00a0df341680dc82	RUN	`NVIDIA_TENSORRT_VERSION=24.03 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`	03/11/2024 4:35 PM UTC
sha256:39ca9bc63a69bfaf6e853048bdad2bd8f4ff19550289760bf082540950f3b43b	COPY	`README.md README.md`	03/11/2024 4:35 PM UTC
sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1	WORKDIR	`/workspace`	03/11/2024 4:37 PM UTC
sha256:b48a5fafcaba74eb5d7e7665601509e2889285b50a04b5b639a23f8adc818157	ADD	`docs.tgz /`	03/11/2024 4:37 PM UTC