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=74791260fb1704ef7932d7d440272ff1c942e646`	08/08/2025 4:15 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_REF=74791260fb1704ef7932d7d440272ff1c942e646`	08/08/2025 4:15 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.nvidia.build.id=197421210`	08/08/2025 4:15 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`NVIDIA_BUILD_ID=197421210`	08/08/2025 4:15 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_ID=197421210`	08/08/2025 4:15 PM UTC
sha256:e442e1d016313ea34923d1e73052cd8358d063aa19e46b16b32eb8b3bb9c9a9b	COPY	`entrypoint.d/ /opt/nvidia/entrypoint.d/`	08/08/2025 4:15 PM UTC
sha256:e2fce1a7e1fa7f219842c1a9c02dd470751c3a06b52db27e9c5b0512ea802883	RUN	`NVIDIA_TENSORRT_VERSION=25.08 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`	08/08/2025 4:15 PM UTC
sha256:394dd368f41bf8db36a0c64d9cdcda3bae8ac027f955582ae1133963aede2872	COPY	`README.md README.md`	08/08/2025 4:15 PM UTC
sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1	WORKDIR	`/workspace`	08/08/2025 4:15 PM UTC
sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1	RUN	`NVIDIA_TENSORRT_VERSION=25.08 TRTOSS_VERSION=master PYVER=3.12 ENABLE_MITMPROXY= L4T= /tmp/manage_cert.sh uninstall`	08/08/2025 4:15 PM UTC