|
gptkbp:instance_of
|
gptkb:Google
gptkb:software
|
|
gptkbp:can_be_used_for
|
gptkb:NVIDIA_GPUs
|
|
gptkbp:developed_by
|
gptkb:NVIDIA
|
|
gptkbp:enhances
|
latency
throughput
|
|
gptkbp:has
|
community support
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
Tensor RT
|
|
gptkbp:integrates_with
|
gptkb:Tensor_Flow
gptkb:Py_Torch
|
|
gptkbp:is_available_on
|
gptkb:Linux
gptkb:Docker
gptkb:Windows
|
|
gptkbp:is_compatible_with
|
gptkb:CUDA
gptkb:Tensor_RT_Inference_Server
|
|
gptkbp:is_designed_for
|
high-performance computing
|
|
gptkbp:is_documented_in
|
NVIDIA Developer Documentation
|
|
gptkbp:is_optimized_for
|
neural network models
NVIDIA hardware
low-latency inference
high-throughput inference
|
|
gptkbp:is_part_of
|
gptkb:NVIDIA_DGX_systems
gptkb:NVIDIA_AI_Research
gptkb:NVIDIA_AI_platform
gptkb:NVIDIA_Deep_Learning_SDK
gptkb:NVIDIA_Jetson_platform
|
|
gptkbp:is_scalable
|
large models
|
|
gptkbp:is_supported_by
|
NVIDIA forums
NVIDIA Git Hub repository
|
|
gptkbp:is_updated_by
|
by NVIDIA
|
|
gptkbp:is_used_by
|
data scientists
AI researchers
machine learning engineers
|
|
gptkbp:is_used_for
|
real-time applications
|
|
gptkbp:is_used_in
|
gptkb:vehicles
gptkb:robotics
image recognition
natural language processing
video analytics
healthcare applications
|
|
gptkbp:offers
|
model optimization tools
|
|
gptkbp:provides
|
gptkb:Performance_Monitoring
dynamic tensor memory
layer fusion
high-performance inference
API for Python
API for C++
intuitive debugging tools
|
|
gptkbp:released_in
|
gptkb:2016
|
|
gptkbp:released_on
|
gptkb:2016
|
|
gptkbp:supports
|
multi-GPU configurations
ONNX format
FP16 precision
INT8 precision
|
|
gptkbp:used_for
|
deep learning inference
|
|
gptkbp:used_in
|
real-time inference
|
|
gptkbp:bfsParent
|
gptkb:Py_Torch
gptkb:NVIDIA
|
|
gptkbp:bfsLayer
|
4
|