Statements (50)
| Predicate | Object |
|---|---|
| gptkbp:instance_of |
gptkb:software
|
| gptkbp:developed_by |
gptkb:DJ
|
| gptkbp:has |
Python API
C++ API |
| gptkbp:has_feature |
debugging tools
profiling tools support for custom layers intelligent memory management layer-wise optimization |
| https://www.w3.org/2000/01/rdf-schema#label |
NVIDIA's Tensor RT
|
| gptkbp:includes |
layer fusion
kernel auto-tuning |
| gptkbp:integrates_with |
gptkb:cu_DNN
gptkb:CUDA |
| gptkbp:is_available_on |
gptkb:lake
gptkb:operating_system |
| gptkbp:is_compatible_with |
NVIDIAGP Us
|
| gptkbp:is_documented_in |
NVIDIA Developer Documentation
|
| gptkbp:is_optimized_for |
gptkb:microprocessor
gptkb:NVIDIA_Tesla gptkb:NVIDIA_A100 gptkb:NVIDIA_Jetson |
| gptkbp:is_part_of |
gptkb:NVIDIA_Deep_Learning_SDK
NVIDIA's software ecosystem NVIDIAAI platform |
| gptkbp:is_promoted_by |
NVIDIA conferences
NVIDIA tutorials NVIDIA webinars |
| gptkbp:is_supported_by |
NVIDIA Developer Program
|
| gptkbp:is_used_by |
data scientists
AI researchers machine learning engineers |
| gptkbp:is_used_for |
deep learning inference
|
| gptkbp:is_used_in |
gptkb:robot
gptkb:engine computer vision natural language processing cloud applications edge devices healthcare applications |
| gptkbp:offers |
model optimization tools
|
| gptkbp:provides |
high performance
dynamic tensor memory runtime AP Is |
| gptkbp:released_in |
gptkb:2016
|
| gptkbp:supports |
multi-GPU configurations
ONNX format F P16 precision IN T8 precision |
| gptkbp:updates |
by NVIDIA
|