PerformanceEnvelopeReport
Read-only snapshot of one node's performance envelopes.
Attributes: generated_at: UTC ISO-8601 time the snapshot was computed. envelopes: One summary per observed (hardware x model x engine x quant).
generatedAtGeneratedat (string)required
envelopes object[]required
Array [
hardwareClassHardwareclass (string)required
modelIdModelid (string)required
backendBackend (string)required
quantizationQuantization (string)required
buckets object[]required
Array [
concurrencyConcurrency (integer)required
requestCountRequestcount (integer)required
successCountSuccesscount (integer)required
errorCountErrorcount (integer)required
ttftSecondsP50 objectrequired
anyOf
- number
- null
number
ttftSecondsP90 objectrequired
anyOf
- number
- null
number
decodeTpsMean objectrequired
anyOf
- number
- null
number
decodeTpsP50 objectrequired
anyOf
- number
- null
number
aggregateDecodeTps objectrequired
anyOf
- number
- null
number
]
kneeConcurrency objectrequired
anyOf
- integer
- null
integer
batchesBatches (boolean)required
observationCountObservationcount (integer)required
]
PerformanceEnvelopeReport
{
"generatedAt": "string",
"envelopes": [
{
"hardwareClass": "string",
"modelId": "string",
"backend": "string",
"quantization": "string",
"buckets": [
{
"concurrency": 0,
"requestCount": 0,
"successCount": 0,
"errorCount": 0,
"ttftSecondsP50": 0,
"ttftSecondsP90": 0,
"decodeTpsMean": 0,
"decodeTpsP50": 0,
"aggregateDecodeTps": 0
}
],
"kneeConcurrency": 0,
"batches": true,
"observationCount": 0
}
]
}