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=271514cde14531ae6919e0d60f5c1ce3aadba048`	11/14/2024 11:55 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_REF=271514cde14531ae6919e0d60f5c1ce3aadba048`	11/14/2024 11:55 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.nvidia.build.id=122385182`	11/14/2024 11:55 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`NVIDIA_BUILD_ID=122385182`	11/14/2024 11:55 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_ID=122385182`	11/14/2024 11:55 PM UTC
sha256:4d64d583ec508c9582f4fa8d095470b97bdacda5982e217d57a70855c6e6dbff	COPY	`entrypoint.d/ /opt/nvidia/entrypoint.d/`	11/14/2024 11:55 PM UTC
sha256:694f1577030df6ba74eccfec6d54afeb7c7a15956d681e8bc45e132aad579cdb	RUN	`NVIDIA_TENSORRT_VERSION=24.11 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`	11/14/2024 11:55 PM UTC
sha256:953e7fd8e80cb8c0802d17ee0a6a5c2b1d37aeca73cb4bbf1f0c584e03fcc47b	COPY	`README.md README.md`	11/14/2024 11:55 PM UTC
sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1	WORKDIR	`/workspace`	11/14/2024 11:55 PM UTC
sha256:b48a5fafcaba74eb5d7e7665601509e2889285b50a04b5b639a23f8adc818157	ADD	`docs.tgz /`	11/14/2024 11:55 PM UTC