|
gptkbp:instance_of
|
gptkb:Amazon_Web_Services
|
|
gptkbp:can_handle
|
multiple requests
|
|
gptkbp:deployment
|
gptkb:cloud_computing
on-premises
edge devices
|
|
gptkbp:developed_by
|
gptkb:NVIDIA
|
|
gptkbp:enables
|
high-performance inference
|
|
gptkbp:features
|
metrics and logging
model versioning
ensemble models
dynamic batching
multi-model serving
|
|
gptkbp:has
|
open-source license
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
NVIDIA Triton Inference Server
|
|
gptkbp:is_available_on
|
gptkb:Git_Hub
|
|
gptkbp:is_compatible_with
|
gptkb:NVIDIA_GPUs
x86 CPUs
|
|
gptkbp:is_designed_for
|
production environments
real-time inference
batch inference
|
|
gptkbp:is_designed_to
|
reduce latency
simplify deployment
increase throughput
|
|
gptkbp:is_integrated_with
|
gptkb:Kubernetes
gptkb:Docker
|
|
gptkbp:is_optimized_for
|
NVIDIA hardware
|
|
gptkbp:is_part_of
|
gptkb:NVIDIA_AI_platform
MLOps workflow
|
|
gptkbp:is_used_by
|
gptkb:developers
gptkb:researchers
data scientists
|
|
gptkbp:is_used_in
|
gptkb:machine_learning
deep learning
AI applications
|
|
gptkbp:provides
|
load balancing
scalability
model management
model repository
HTTP/g RPC APIs
|
|
gptkbp:supports
|
gptkb:Tensor_Flow
gptkb:Web_Socket
gptkb:Java
gptkb:C++
gptkb:Python
gptkb:Tensor_RT
gptkb:Py_Torch
gptkb:ONNX_Runtime
RESTful APIs
GPU acceleration
canary deployments
multiple frameworks
A/ B testing
CPU inference
|
|
gptkbp:bfsParent
|
gptkb:NVIDIA_Corporation
gptkb:Py_Torch
gptkb:NVIDIA
|
|
gptkbp:bfsLayer
|
4
|