schema_version: "2.0"
benchmark:
  models:
    items:
      - name: "vllm/MODEL-NAME-HERE"
    strategy: "round_robin"
  endpoint:
    urls:
      - "https://ENDPOINT/v1"
    type: "chat"
    streaming: true
    headers:
      Authorization: "Bearer ${API_KEY}"
  # --- Option A: Public dataset (ShareGPT) ---
  datasets:
    - type: "public"
      name: "main"
      dataset: "sharegpt"
      sampling: "shuffle"
  # --- Option B: Synthetic dataset (no download) ---
  # datasets:
  #   - type: "synthetic"
  #     name: "main"
  #     entries: 100
  #     isl:
  #       type: "fixed"
  #       value: 512
  #     osl:
  #       type: "fixed"
  #       value: 128
  phases:
    - type: "concurrency"
      name: "profiling"
      # Choose ONE: requests OR duration
      requests: 50          # for count-based (sales, capacity)
      sessions: 1           # concurrency level (overridden by --concurrency CLI flag)
      # duration: 600       # for time-based (steady-state)
  tokenizer:
    name: "builtin"