NVIDIA Triton Inference Server

GPTKB entity

Predicate	Object
gptkbp:instanceOf	gptkb:software
gptkbp:category	machine learning infrastructure model serving AI software
gptkbp:deployment	gptkb:cloud_service gptkb:Docker gptkb:Kubernetes on-premises edge
gptkbp:developedBy	gptkb:NVIDIA
gptkbp:documentation	https://github.com/triton-inference-server/server/blob/main/docs/user_guide.md
gptkbp:firstReleased	2019
gptkbp:formerName	gptkb:NVIDIA_TensorRT_Inference_Server
https://www.w3.org/2000/01/rdf-schema#label	NVIDIA Triton Inference Server
gptkbp:license	gptkb:Apache_License_2.0
gptkbp:mainLanguage	gptkb:Python gptkb:C++
gptkbp:officialWebsite	https://developer.nvidia.com/nvidia-triton-inference-server
gptkbp:openSource	true
gptkbp:platform	gptkb:Python gptkb:TensorFlow gptkb:DALI gptkb:FIL gptkb:NVIDIA_GPU gptkb:ONNX_Runtime gptkb:OpenVINO gptkb:TensorRT gptkb:ARM_CPU gptkb:x86_CPU gptkb:JAX gptkb:PyTorch gptkb:Hugging_Face_Transformers
gptkbp:purpose	model inference serving machine learning models
gptkbp:repository	https://github.com/triton-inference-server/server
gptkbp:supportsBatching	true
gptkbp:supportsGRPCAPI	true
gptkbp:supportsMetrics	gptkb:Prometheus gptkb:OpenMetrics
gptkbp:supportsModelEnsembling	true
gptkbp:supportsModelVersioning	true
gptkbp:supportsMultiModelDeployment	true
gptkbp:supportsRESTAPI	true
gptkbp:usedFor	AI model deployment deep learning inference machine learning inference
gptkbp:bfsParent	gptkb:NVIDIA_AI
gptkbp:bfsLayer	5