|
gptkbp:instance_of
|
gptkb:software
|
|
gptkbp:can
|
inference requests
inference responses
|
|
gptkbp:can_be_configured_for
|
YAML files
|
|
gptkbp:can_be_extended_by
|
custom plugins
|
|
gptkbp:can_handle
|
multiple requests
|
|
gptkbp:community_support
|
gptkb:true
|
|
gptkbp:deployment
|
cloud platforms
on-premises servers
|
|
gptkbp:designed_for
|
production environments
|
|
gptkbp:developed_by
|
gptkb:Google
|
|
gptkbp:first_released
|
gptkb:2016
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
Tensor Flow Serving
|
|
gptkbp:integrates_with
|
gptkb:Kubernetes
gptkb:Docker
|
|
gptkbp:is_available_on
|
gptkb:Git_Hub
|
|
gptkbp:is_compatible_with
|
gptkb:TF_Lite
gptkb:TF_Hub
gptkb:TF_Model_Garden
|
|
gptkbp:is_documented_in
|
Tensor Flow documentation
|
|
gptkbp:is_open_source
|
gptkb:true
|
|
gptkbp:is_optimized_for
|
gptkb:performance
gptkb:resource_utilization
|
|
gptkbp:is_part_of
|
Tensor Flow ecosystem
ML model deployment pipeline
|
|
gptkbp:is_scalable
|
gptkb:true
|
|
gptkbp:is_served_by
|
machine learning models
|
|
gptkbp:is_supported_by
|
Tensor Flow community
|
|
gptkbp:is_used_by
|
data scientists
machine learning engineers
|
|
gptkbp:is_used_for
|
serving models
serving predictions
|
|
gptkbp:is_used_in
|
gptkb:machine_learning
data analysis
AI applications
real-time inference
batch inference
|
|
gptkbp:offers
|
load balancing
monitoring capabilities
|
|
gptkbp:provides
|
REST API
low latency
high throughput
model management features
g RPC API
|
|
gptkbp:supports
|
canary deployments
multiple model formats
versioning of models
A/ B testing
Tensor Flow models
|
|
gptkbp:used_for
|
model serving
|
|
gptkbp:written_in
|
gptkb:C++
|
|
gptkbp:bfsParent
|
gptkb:Tensor_Flow
|
|
gptkbp:bfsLayer
|
4
|