Nvidia Triton Inference Server

GPTKB entity

Statements (57)
Predicate Object
gptkbp:instanceOf inference server
gptkbp:developedBy gptkb:Nvidia
gptkbp:documentation https://github.com/triton-inference-server/server
gptkbp:feature gptkb:model
A/B testing
model monitoring
metrics
auto-scaling
model versioning
model explainability
custom backends
custom postprocessors
custom preprocessors
dynamic batching
model configuration
model control API
model ensemble
model health
model statistics
model warmup
multi-model serving
multi-node deployment
streaming inference
gptkbp:firstReleased 2019
https://www.w3.org/2000/01/rdf-schema#label Nvidia Triton Inference Server
gptkbp:latestReleaseVersion 2024-05-22
2.41.0
gptkbp:license gptkb:Apache_License_2.0
gptkbp:officialWebsite https://developer.nvidia.com/nvidia-triton-inference-server
gptkbp:openSource true
gptkbp:platform gptkb:Python
gptkb:Windows
gptkb:cloud_service
gptkb:microprocessor
gptkb:ARM
gptkb:TensorFlow
gptkb:DALI
gptkb:FIL
gptkb:Nvidia_GPU
gptkb:ONNX_Runtime
gptkb:OpenVINO
gptkb:TensorRT
gptkb:Linux
gptkb:Docker
gptkb:Kubernetes
gptkb:PyTorch
gptkbp:supportsProtocol gptkb:gRPC
C API
HTTP/REST
gptkbp:uses cloud deployment
enterprise AI
AI model deployment
deep learning inference
edge deployment
machine learning inference
gptkbp:bfsParent gptkb:Nvidia
gptkbp:bfsLayer 5