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=ba56432c7d5a2178d1e104da8d2e85edba7f8c23`	08/06/2023 8:41 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_REF`	08/06/2023 8:41 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.nvidia.build.id=66128967`	08/06/2023 8:41 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`NVIDIA_BUILD_ID=66128967`	08/06/2023 8:41 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_ID`	08/06/2023 8:41 PM UTC
sha256:49bdc9abf8a437ccff67cc11490ba52c976577992909856a86be872a34d3b950	COPY	`entrypoint.d/ /opt/nvidia/entrypoint.d/`	08/06/2023 8:41 PM UTC
sha256:90eae6faa5cc5ba62f12c25915cdfb1a7a51abfba0d05cb5818c3f908f4e345f	RUN	`NVIDIA_TENSORRT_VERSION=23.08 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`	08/06/2023 8:41 PM UTC
sha256:82a3436133b2b17bb407c7fe488932aa0ca55411f23ab55c34a6134b287c6a27	COPY	`README.md README.md`	08/06/2023 8:41 PM UTC
sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1	WORKDIR	`/workspace`	08/06/2023 8:41 PM UTC
sha256:b48a5fafcaba74eb5d7e7665601509e2889285b50a04b5b639a23f8adc818157	ADD	`docs.tgz /`	08/06/2023 8:41 PM UTC