Triton Inference Server · JSON-LD Context
Triton Context
JSON-LD context defining the semantic vocabulary for Triton from Triton Inference Server.
0 Classes
9 Properties
5 Namespaces
Namespaces
triton:
https://developer.nvidia.com/schemas/triton/
schema:
https://schema.org/
xsd:
http://www.w3.org/2001/XMLSchema#
dcterms:
http://purl.org/dc/terms/
ml:
http://www.w3.org/ns/mls#
Properties
| Property | Type | Container |
|---|---|---|
| Model | ||
| Tensor | ||
| InferenceRequest | ||
| InferenceResponse | ||
| ModelStatistics | ||
| ServerMetadata | ||
| InstanceGroup | ||
| SharedMemoryRegion | ||
| RepositoryEntry |
JSON-LD Document
{
"@context": {
"@version": 1.1,
"triton": "https://developer.nvidia.com/schemas/triton/",
"schema": "https://schema.org/",
"xsd": "http://www.w3.org/2001/XMLSchema#",
"dcterms": "http://purl.org/dc/terms/",
"ml": "http://www.w3.org/ns/mls#",
"Model": {
"@id": "triton:Model",
"@context": {
"name": "schema:name",
"platform": "triton:platform",
"backend": "triton:backend",
"maxBatchSize": {
"@id": "triton:maxBatchSize",
"@type": "xsd:integer"
},
"versions": "triton:versions",
"inputs": "triton:inputs",
"outputs": "triton:outputs",
"instanceGroup": "triton:instanceGroup",
"dynamicBatching": "triton:dynamicBatching",
"sequenceBatching": "triton:sequenceBatching"
}
},
"Tensor": {
"@id": "triton:Tensor",
"@context": {
"name": "schema:name",
"datatype": "triton:datatype",
"shape": "triton:shape",
"data": "triton:data"
}
},
"InferenceRequest": {
"@id": "triton:InferenceRequest",
"@context": {
"requestId": "schema:identifier",
"inputs": "triton:inputs",
"outputs": "triton:outputs",
"sequenceId": "triton:sequenceId",
"sequenceStart": {
"@id": "triton:sequenceStart",
"@type": "xsd:boolean"
},
"sequenceEnd": {
"@id": "triton:sequenceEnd",
"@type": "xsd:boolean"
},
"priority": {
"@id": "triton:priority",
"@type": "xsd:integer"
},
"timeout": {
"@id": "triton:timeout",
"@type": "xsd:integer"
}
}
},
"InferenceResponse": {
"@id": "triton:InferenceResponse",
"@context": {
"responseId": "schema:identifier",
"modelName": "triton:modelName",
"modelVersion": "triton:modelVersion",
"outputs": "triton:outputs"
}
},
"ModelStatistics": {
"@id": "triton:ModelStatistics",
"@context": {
"name": "schema:name",
"version": "schema:version",
"lastInference": {
"@id": "triton:lastInference",
"@type": "xsd:dateTime"
},
"inferenceCount": {
"@id": "triton:inferenceCount",
"@type": "xsd:integer"
},
"executionCount": {
"@id": "triton:executionCount",
"@type": "xsd:integer"
}
}
},
"ServerMetadata": {
"@id": "triton:ServerMetadata",
"@context": {
"name": "schema:name",
"version": "schema:softwareVersion",
"extensions": "triton:extensions"
}
},
"InstanceGroup": {
"@id": "triton:InstanceGroup",
"@context": {
"name": "schema:name",
"kind": "triton:deviceKind",
"count": {
"@id": "triton:instanceCount",
"@type": "xsd:integer"
},
"gpus": "triton:gpuDevices"
}
},
"SharedMemoryRegion": {
"@id": "triton:SharedMemoryRegion",
"@context": {
"name": "schema:name",
"key": "triton:sharedMemoryKey",
"offset": {
"@id": "triton:offset",
"@type": "xsd:integer"
},
"byteSize": {
"@id": "triton:byteSize",
"@type": "xsd:integer"
}
}
},
"RepositoryEntry": {
"@id": "triton:RepositoryEntry",
"@context": {
"name": "schema:name",
"version": "schema:version",
"state": "triton:modelState",
"reason": "triton:stateReason"
}
}
}
}