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=3938305b10ee55eca059d15b3b4aab26dd3e0f39`	09/06/2025 3:59 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_REF=3938305b10ee55eca059d15b3b4aab26dd3e0f39`	09/06/2025 3:59 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.nvidia.build.id=207438968`	09/06/2025 3:59 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`NVIDIA_BUILD_ID=207438968`	09/06/2025 3:59 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_ID=207438968`	09/06/2025 3:59 AM UTC
sha256:9a60916754e8441977e9f5ac14901be797b23038df1a841a47059466f301041b	COPY	`entrypoint.d/ /opt/nvidia/entrypoint.d/`	09/06/2025 3:59 AM UTC
sha256:47622c306bc772f11c657d4c3b7ef36bd005bdac7296c7e677bde6fe3996ed1e	RUN	`NVIDIA_TENSORRT_VERSION=25.09 TRTOSS_VERSION=master PYVER=3.12 ENABLE_MITMPROXY= L4T= 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`	09/06/2025 3:59 AM UTC
sha256:957476a5901e911cc7570cfb15136250bedf831b56ae461276ccb24be71df556	COPY	`README.md README.md`	09/06/2025 3:59 AM UTC
sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1	WORKDIR	`/workspace`	09/06/2025 3:59 AM UTC
sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1	RUN	`NVIDIA_TENSORRT_VERSION=25.09 TRTOSS_VERSION=master PYVER=3.12 ENABLE_MITMPROXY= L4T= /tmp/manage_cert.sh uninstall`	09/06/2025 3:59 AM UTC