Skip to main content

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
    ttftSecondsP90 objectrequired
    anyOf
    number
    decodeTpsMean objectrequired
    anyOf
    number
    decodeTpsP50 objectrequired
    anyOf
    number
    aggregateDecodeTps objectrequired
    anyOf
    number
  • ]
  • kneeConcurrency objectrequired
    anyOf
    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
    }
    ]
    }