AI/ML Systems

Learn AI/ML Patterns Observe

AI/ML Systems

Opening…

PERF-004Derivationtrack →

Estimate cost per request: GPU at $1/hour serves 3600 requests/hour. What is the per-request compute cost?

Context fixture

{
  "gpu": "$1/hr",
  "rps": 1
}

Hints · 0/3

Your answer

related lab: measure-the-service-not-just-the-model →0 attempts