|
gptkbp:instance_of
|
gptkb:software
|
|
gptkbp:can_be_used_in
|
cloud applications
edge devices
|
|
gptkbp:can_be_used_with
|
gptkb:Java
gptkb:C++
gptkb:Python
|
|
gptkbp:developed_by
|
gptkb:NVIDIA
|
|
gptkbp:enhances
|
model performance
|
|
gptkbp:has
|
community support
sample applications
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
NVIDIA Tensor RT
|
|
gptkbp:improves
|
throughput
|
|
gptkbp:includes
|
gptkb:Java_Runtime_Environment
|
|
gptkbp:integrates_with
|
gptkb:NVIDIA_CUDA
|
|
gptkbp:is_available_on
|
gptkb:Linux
gptkb:Docker
gptkb:Windows
|
|
gptkbp:is_compatible_with
|
gptkb:NVIDIA_DGX_systems
gptkb:NVIDIA_GPUs
|
|
gptkbp:is_documented_in
|
NVIDIA Developer Documentation
|
|
gptkbp:is_integrated_with
|
gptkb:NVIDIA_Triton_Inference_Server
|
|
gptkbp:is_optimized_for
|
gptkb:NVIDIA_Jetson
neural network models
custom layers
|
|
gptkbp:is_part_of
|
gptkb:NVIDIA_AI_platform
gptkb:NVIDIA_Deep_Learning_SDK
|
|
gptkbp:is_supported_by
|
NVIDIA Developer Program
|
|
gptkbp:is_updated_by
|
yes
|
|
gptkbp:is_used_in
|
gptkb:vehicles
gptkb:financial_services
gptkb:robotics
smart cities
healthcare applications
|
|
gptkbp:is_utilized_in
|
gptkb:AI_technology
computer vision
image recognition
natural language processing
speech recognition
customer service automation
fraud detection
predictive maintenance
recommendation systems
video analytics
|
|
gptkbp:offers
|
layer fusion
|
|
gptkbp:provides
|
API for developers
profiling tools
dynamic tensor memory
high-performance inference
|
|
gptkbp:reduces
|
latency
|
|
gptkbp:released_in
|
gptkb:2016
|
|
gptkbp:supports
|
multi-GPU configurations
ONNX format
FP16 precision
INT8 precision
Tensor Flow models
Py Torch models
Caffe models
|
|
gptkbp:used_for
|
deep learning inference
|
|
gptkbp:bfsParent
|
gptkb:NVIDIA_Corporation
gptkb:CUDA
gptkb:NVIDIA
|
|
gptkbp:bfsLayer
|
4
|