apiVersion: lumbridge/v1
kind: EvalSuite
metadata:
  name: performance
  version: 1
  description: "Repeated streamed requests measuring TTFT, client-observed prefill, and decode throughput."
  tags: [performance, latency, throughput]
defaults:
  max_tokens: 256
  temperature: 0.0
  repeat: 3
  system: "Answer directly in plain text."
cases:
  - id: short-prefill
    category: latency
    prompt: "Explain why unified-memory admission control prevents system thrashing. Give a detailed answer."
    max_tokens: 256
  - id: structured-decode
    category: throughput
    prompt: "Write twenty numbered, one-sentence operational checks for an AI inference server."
    max_tokens: 384