Files
lai_automatisierung/benchmarks/inference/results/20260831T132015Z/summary.json
Christian Meyer 407af8099b
Some checks failed
CI / test (push) Has been cancelled
CI / test (pull_request) Has been cancelled
docs: record Qwen MLX benchmark results
2026-08-31 16:39:37 +02:00

54 lines
1.7 KiB
JSON

[
{
"runtime": "vllm-metal",
"model": "qwen3.8-27b-mxfp8",
"concurrency": 1,
"requests": 5,
"successes": 5,
"failures": 0,
"ttft_s_mean": 0.37155269999057056,
"ttft_s_p50": 0.4171057919738814,
"ttft_s_p95": 0.4531440335791558,
"total_s_mean": 7.930883799993898,
"total_s_p50": 8.838838333962485,
"total_s_p95": 8.998963149765041,
"prompt_tps_mean": null,
"prompt_tps_p50": null,
"prompt_tps_p95": null,
"decode_tps_mean": 15.079897408512505,
"decode_tps_p50": 15.126147490283795,
"decode_tps_p95": 15.196162811046243,
"request_tps_mean": 14.380896425252896,
"request_tps_p50": 14.386982882152838,
"request_tps_p95": 14.53502856074605,
"aggregate_output_tps_mean": 14.380548747737752,
"aggregate_output_tps_p50": 14.386712701914696,
"aggregate_output_tps_p95": 14.534638049200744
},
{
"runtime": "vllm-metal",
"model": "qwen3.8-27b-mxfp8",
"concurrency": 4,
"requests": 20,
"successes": 20,
"failures": 0,
"ttft_s_mean": 1.255672066603438,
"ttft_s_p50": 1.3144360205042176,
"ttft_s_p95": 1.419064954231726,
"total_s_mean": 12.251293779097614,
"total_s_p50": 12.702340687508695,
"total_s_p95": 13.641910566360457,
"prompt_tps_mean": null,
"prompt_tps_p50": null,
"prompt_tps_p95": null,
"decode_tps_mean": 10.500220268362742,
"decode_tps_p50": 10.485677148644122,
"decode_tps_p95": 11.071162546140778,
"request_tps_mean": 9.417789343799708,
"request_tps_p50": 9.430282582501674,
"request_tps_p95": 10.077752113288362,
"aggregate_output_tps_mean": 35.09087333775396,
"aggregate_output_tps_p50": 34.96408475660248,
"aggregate_output_tps_p95": 35.52678209465127
}
]