schema_version: "2.0"
benchmark:
  models:
    items:
      - name: "vllm/REPLACE-MODEL-NAME"
  endpoint:
    urls: ["https://ENDPOINT/v1"]
    type: "chat"
    streaming: true
  datasets:
    default:
      - name: "synthetic_long"
        type: "synthetic"
        prompt_template:
          content: "Summarize the following text concisely: {{text}}"
        variables:
          - name: "text"
            values: [
              "artificial intelligence",
              "quantum computing",
              "blockchain technology",
              "climate change",
              "machine learning",
              "renewable energy"
            ]
    strategy:
      type: "fixed"
      max_total_tokens: 1152    # input + output + padding
      input_tokens: 1024        # TARGET INPUT LENGTH: sweep 512 / 1024 / 2048 / 4096
      output_tokens: 128
  phases:
    - type: "concurrency"
      name: "prefill_stress"
      duration: 300             # 5 minutes
      sessions: 10              # fixed low concurrency
  tokenizer:
    name: "builtin"