TensorFlow-TensorRT (TF-TRT)
GPTKB entity
Statements (28)
Predicate | Object |
---|---|
gptkbp:instanceOf |
gptkb:software
|
gptkbp:acceleration |
neural network inference
|
gptkbp:category |
gptkb:artificial_intelligence
gptkb:machine_learning gptkb:software |
gptkbp:compatibleWith |
gptkb:TensorFlow_2.x
TensorFlow 1.x |
gptkbp:developedBy |
gptkb:Google
|
gptkbp:enables |
FP16 precision
INT8 precision dynamic tensor memory management |
gptkbp:firstReleased |
2017
|
https://www.w3.org/2000/01/rdf-schema#label |
TensorFlow-TensorRT (TF-TRT)
|
gptkbp:improves |
throughput
|
gptkbp:integratesWith |
gptkb:TensorFlow
gptkb:NVIDIA_TensorRT |
gptkbp:license |
gptkb:Apache_License_2.0
|
gptkbp:officialWebsite |
https://docs.nvidia.com/deeplearning/frameworks/tf-trt-user-guide/index.html
|
gptkbp:openSource |
true
|
gptkbp:platform |
gptkb:NVIDIA_GPUs
|
gptkbp:purpose |
deep learning inference optimization
|
gptkbp:reduces |
inference latency
|
gptkbp:supports |
gptkb:Keras_models
gptkb:SavedModel_format |
gptkbp:usedFor |
model optimization
production deployment |
gptkbp:bfsParent |
gptkb:TensorRT
|
gptkbp:bfsLayer |
6
|