reports/vllm_openai_9b_c256.json
131 B · 7 lines · json Raw
1 {
2 "n": 4000,
3 "concurrency": 256,
4 "req_per_s": 205.33828358228774,
5 "p50_ms": 1175.9506464004517,
6 "p90_ms": 1598.2293844223022
7 }