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=5b86d9d3c95575ce34bee1917721b6bc75be00e8`	04/28/2021 8:09 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_REF`	04/28/2021 8:09 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.nvidia.build.id=22596545`	04/28/2021 8:09 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`NVIDIA_BUILD_ID=22596545`	04/28/2021 8:09 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_ID`	04/28/2021 8:09 PM UTC
sha256:96a9cb041d47688f14bdb4ce905cfe011e8bb6ecd7a4a93f462e62f72a9fb60d	COPY	`NVIDIA_Deep_Learning_Container_License.pdf /workspace/`	04/28/2021 8:09 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENTRYPOINT	`/usr/local/bin/nvidia_entrypoint.sh`	04/28/2021 8:09 PM UTC
sha256:7c52591e023ae89d915876076b54e9e43fbefd36b7a2f46667b2aad3e84be4af	COPY	`nvidia_entrypoint.sh /usr/local/bin`	04/28/2021 8:09 PM UTC
sha256:d4fe104f447e482d32cd529275634b2a394017a9de543b42e9e6c0341a8721f9	RUN	`NVIDIA_TENSORRT_VERSION=21.05 TRTOSS_VERSION=master PYVER=3.8 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`	04/28/2021 8:09 PM UTC
sha256:d1ca610e334569e23d0ac4ffb344737de5969390cd0a8af31be2233ac14aacfc	COPY	`README.md README.md`	04/28/2021 8:09 PM UTC