Inline Datasets

1
schemaVersion: "2.0"
2
benchmark:
3
  model: meta-llama/Llama-3.1-8B-Instruct
4
  endpoint:
5
    url: http://localhost:8000/v1/chat/completions
6
  dataset:
7
    type: file
8
    format: single_turn
9
    records:
10
      - {text: "What is machine learning?"}
11
      - {text: "Explain GANs in two sentences.", output_length: 200}
12
      - {text: "Define reinforcement learning."}
13
  phases:
14
    type: concurrency
15
    concurrency: 2
16
    requests: 100

1
benchmark:
2
  dataset:
3
    type: file
4
    format: multi_turn
5
    records:
6
      - session_id: chat_1
7
        turns:
8
          - {text: "What is machine learning?"}
9
          - {text: "Can you give me an example?"}
10
      - session_id: chat_2
11
        turns:
12
          - {text: "Explain neural networks."}
13
          - {text: "How do they differ from traditional algorithms?"}
14
          - {text: "Which architecture for image classification?"}

1
benchmark:
2
  dataset:
3
    type: file
4
    format: random_pool
5
    sampling: random
6
    records:
7
      - {text: "Common query", type: random_pool}
8
      - {text: "Less common query", type: random_pool}
9
      - {text: "Rare query", type: random_pool}

1
benchmark:
2
  dataset:
3
    type: file
4
    format: random_pool
5
    records:
6
      queries:
7
        - {text: "What is your refund policy?", type: random_pool}
8
        - {text: "How do I reset my password?", type: random_pool}
9
      passages:
10
        - {text: "Refunds are processed within 5 business days.", type: random_pool}
11
        - {text: "Click 'Forgot password' on the login page.", type: random_pool}

1
benchmark:
2
  dataset:
3
    type: file
4
    format: mooncake_trace
5
    synthesis:
6
      speedup_ratio: 2.0    # replay 2x faster (1.0 = real-time, 0.5 = 2x slower)
7
    records:
8
      - {timestamp: 0,    input_length: 512,  output_length: 128, hash_ids: [1, 2, 3]}
9
      - {timestamp: 100,  input_length: 1024, output_length: 256, hash_ids: [4, 5]}
10
      - {timestamp: 250,  input_length: 256,  output_length: 64,  hash_ids: [1, 2]}