| { |
| "schema_demo": true, |
| "model": "example-llm-8b-instruct", |
| "backend": "vLLM-style schema demo", |
| "host": { |
| "machine": "illustrative-example", |
| "platform": "synthetic; no benchmark was run" |
| }, |
| "total_input_tokens": 24000, |
| "total_generated_tokens": 6000, |
| "request_throughput": 4.2, |
| "output_token_throughput": 850.5, |
| "mean_ttft_ms": 128.4, |
| "median_ttft_ms": 112.7, |
| "p99_ttft_ms": 244.1, |
| "mean_tpot_ms": 21.8, |
| "median_tpot_ms": 20.2, |
| "p99_tpot_ms": 36.6, |
| "mean_itl_ms": 20.9, |
| "median_itl_ms": 19.8, |
| "p99_itl_ms": 34.7, |
| "mean_request_latency_ms": 1480.0, |
| "median_request_latency_ms": 1392.0, |
| "p99_request_latency_ms": 2600.0, |
| "source_note": "Synthetic schema demonstration only. These are not measured LLM performance results." |
| } |
|
|
