Skip to main content

Get this node's performance envelopes

GET 
/v1/diagnostics/performance-envelopes

Return the observe-only throughput-and-latency-versus-concurrency curve this API node has measured for each (hardware class x model x engine x quantization) it has served, including a simple knee estimate. Adaptive-concurrency Phase 0: data only, no behavior change.

Responses​

Successful Response