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=cd8aae3cb0dc2495311fcb817c0ba284080f6eb8`	01/23/2025 4:40 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_REF=cd8aae3cb0dc2495311fcb817c0ba284080f6eb8`	01/23/2025 4:40 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.nvidia.build.id=135893872`	01/23/2025 4:40 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`NVIDIA_BUILD_ID=135893872`	01/23/2025 4:40 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_ID=135893872`	01/23/2025 4:40 AM UTC
sha256:1cfcb3e0e26c0c735a94212ee6bbc2f6cdb74449a0e56157a3eb2fca15bba9f2	COPY	`entrypoint.d/ /opt/nvidia/entrypoint.d/`	01/23/2025 4:40 AM UTC
sha256:5c4c7ad95c34433d28f2a7d1778f207f3408a799e3bac9c080cc664f377a06ec	RUN	`NVIDIA_TENSORRT_VERSION=25.01 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`	01/23/2025 4:40 AM UTC
sha256:0037d9708b36910a0ef4fd531bf56e3392684168f28f76fcdc05e891da1a88c0	COPY	`README.md README.md`	01/23/2025 4:40 AM UTC
sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1	WORKDIR	`/workspace`	01/23/2025 4:40 AM UTC
sha256:b48a5fafcaba74eb5d7e7665601509e2889285b50a04b5b639a23f8adc818157	ADD	`docs.tgz /`	01/23/2025 4:40 AM UTC