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=d9cd0ebffdc337605a7fcb86d7089e71d53b46ee`	12/01/2023 1:36 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_REF`	12/01/2023 1:36 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.nvidia.build.id=76057045`	12/01/2023 1:36 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`NVIDIA_BUILD_ID=76057045`	12/01/2023 1:36 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_ID`	12/01/2023 1:36 AM UTC
sha256:6cc02dddc8945672e54fdf272c767ffbf3158b82108bbab86d26db2683fcbdbe	COPY	`entrypoint.d/ /opt/nvidia/entrypoint.d/`	12/01/2023 1:36 AM UTC
sha256:766a990f0dc03386aafea2fb7b9b21a9f8116b0c9d95f6c16980345420f09bf2	RUN	`NVIDIA_TENSORRT_VERSION=23.12 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`	12/01/2023 1:36 AM UTC
sha256:2c30510643e31de6493713032fcb014178901217e6b5d7c03a50859ce718cb98	COPY	`README.md README.md`	12/01/2023 1:36 AM UTC
sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1	WORKDIR	`/workspace`	12/01/2023 1:36 AM UTC
sha256:b48a5fafcaba74eb5d7e7665601509e2889285b50a04b5b639a23f8adc818157	ADD	`docs.tgz /`	12/01/2023 1:36 AM UTC