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=7b5c7c41b0e01821616c4302c3ef517c1d1f6a47`	06/03/2024 7:46 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_REF`	06/03/2024 7:46 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.nvidia.build.id=95852338`	06/03/2024 7:46 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`NVIDIA_BUILD_ID=95852338`	06/03/2024 7:46 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_ID`	06/03/2024 7:46 PM UTC
sha256:31cc5f6241349e1f99c09420245f868aa7a3ca3c63b3300ef50132c90996cefa	COPY	`entrypoint.d/ /opt/nvidia/entrypoint.d/`	06/03/2024 7:46 PM UTC
sha256:e7f68e191dd5fc978d59e003da0e0bf4f581adc73ed7dadd1d3b50194a1c6015	RUN	`NVIDIA_TENSORRT_VERSION=24.06 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`	06/03/2024 7:46 PM UTC
sha256:ba1cf6d1ae3d0eeeb62b76a59a08ce34c18d5908defc612d25abbd2390ed9686	COPY	`README.md README.md`	06/03/2024 7:46 PM UTC
sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1	WORKDIR	`/workspace`	06/03/2024 7:46 PM UTC
sha256:b48a5fafcaba74eb5d7e7665601509e2889285b50a04b5b639a23f8adc818157	ADD	`docs.tgz /`	06/03/2024 7:46 PM UTC