TECH RADAR / MEASUREMENT & EVALUATION
AIPerf
Endpoint load generation and performance metrics.
What it covers
Concurrency, request-rate and trace-replay workloads, with latency metrics.
What we would check
Use representative input/output lengths, report errors, and distinguish warmup from steady-state measurements.
Go to the source
A curated ecosystem entry. The evaluation guidance is our interpretation, not a report of a completed test or a performance ranking.