|
gptkbp:instanceOf
|
gptkb:software
|
|
gptkbp:abbreviation
|
gptkb:TensorRT
|
|
gptkbp:API
|
command line interface
C++ API
Python API
|
|
gptkbp:category
|
gptkb:artificial_intelligence
gptkb:machine_learning
|
|
gptkbp:developer
|
gptkb:Nvidia
|
|
gptkbp:documentation
|
https://docs.nvidia.com/deeplearning/tensorrt/
|
|
gptkbp:feature
|
FP16 precision
INT8 precision
dynamic tensor memory
kernel auto-tuning
layer fusion
multi-stream execution
support for DLA (Deep Learning Accelerator)
|
|
gptkbp:firstReleased
|
2017
|
|
gptkbp:format
|
gptkb:TensorFlow
gptkb:UFF
gptkb:Caffe
gptkb:ONNX
optimized engine
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
Nvidia TensorRT
|
|
gptkbp:integration
|
gptkb:Nvidia_CUDA
gptkb:Nvidia_DeepStream
gptkb:Nvidia_Triton_Inference_Server
gptkb:Nvidia_cuDNN
|
|
gptkbp:latestReleaseVersion
|
8.6
|
|
gptkbp:license
|
proprietary
|
|
gptkbp:operatingSystem
|
gptkb:Windows
gptkb:Linux
|
|
gptkbp:platform
|
gptkb:TensorFlow
gptkb:Nvidia_GPU
gptkb:Nvidia_Jetson
gptkb:PyTorch
gptkb:ONNX
|
|
gptkbp:programmingLanguage
|
gptkb:Python
gptkb:C++
|
|
gptkbp:purpose
|
deep learning inference optimization
|
|
gptkbp:uses
|
autonomous vehicles
natural language processing
robotics
recommendation systems
medical imaging
|
|
gptkbp:website
|
https://developer.nvidia.com/tensorrt
|
|
gptkbp:bfsParent
|
gptkb:Nvidia
|
|
gptkbp:bfsLayer
|
5
|