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=d92db07b3318128d6ea2b18b53291c4de1d7d38a`	02/19/2025 7:29 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_REF=d92db07b3318128d6ea2b18b53291c4de1d7d38a`	02/19/2025 7:29 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	LABEL	`com.nvidia.build.id=143088447`	02/19/2025 7:29 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ENV	`NVIDIA_BUILD_ID=143088447`	02/19/2025 7:29 PM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4	ARG	`NVIDIA_BUILD_ID=143088447`	02/19/2025 7:29 PM UTC
sha256:34b90508eaff72a5a9a596b3c968e70a56cdc5df707f12791555bcca465216fd	COPY	`entrypoint.d/ /opt/nvidia/entrypoint.d/`	02/19/2025 7:29 PM UTC
sha256:feebb21bab7cf79ba6739b1b62644a4797decb87b4ee8a5830f0c4d2f4cd60ef	RUN	`NVIDIA_TENSORRT_VERSION=25.02 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`	02/19/2025 7:29 PM UTC
sha256:622cd2e83ad2f1485f80431f276aa77c7c771a3aff0ccc01d090f1d98f11b301	COPY	`README.md README.md`	02/19/2025 7:29 PM UTC
sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1	WORKDIR	`/workspace`	02/19/2025 7:29 PM UTC
sha256:b48a5fafcaba74eb5d7e7665601509e2889285b50a04b5b639a23f8adc818157	ADD	`docs.tgz /`	02/19/2025 7:29 PM UTC