54 lines
1.8 KiB
JSON
54 lines
1.8 KiB
JSON
[
|
|
{
|
|
"runtime": "ollama",
|
|
"model": "qwen3.8:27b-mxfp8",
|
|
"concurrency": 1,
|
|
"requests": 5,
|
|
"successes": 5,
|
|
"failures": 0,
|
|
"ttft_s_mean": 0.296576766599901,
|
|
"ttft_s_p50": 0.25913220801157877,
|
|
"ttft_s_p95": 0.5828672000090591,
|
|
"total_s_mean": 5.365511283196975,
|
|
"total_s_p50": 5.271547083975747,
|
|
"total_s_p95": 5.7278931244160045,
|
|
"prompt_tps_mean": 1579505.471393669,
|
|
"prompt_tps_p50": 423.79232394227944,
|
|
"prompt_tps_p95": 4040897.1304585882,
|
|
"decode_tps_mean": 22.074969591997284,
|
|
"decode_tps_p50": 22.737809958094928,
|
|
"decode_tps_p95": 26.029319910172887,
|
|
"request_tps_mean": 21.326224707051917,
|
|
"request_tps_p50": 22.22186664913243,
|
|
"request_tps_p95": 23.99720340744444,
|
|
"aggregate_output_tps_mean": 21.3238226965937,
|
|
"aggregate_output_tps_p50": 22.217896609947385,
|
|
"aggregate_output_tps_p95": 23.99517949790225
|
|
},
|
|
{
|
|
"runtime": "ollama",
|
|
"model": "qwen3.8:27b-mxfp8",
|
|
"concurrency": 4,
|
|
"requests": 20,
|
|
"successes": 20,
|
|
"failures": 0,
|
|
"ttft_s_mean": 9.275126714701765,
|
|
"ttft_s_p50": 9.394405500497669,
|
|
"ttft_s_p95": 18.583187756550615,
|
|
"total_s_mean": 15.170045258343453,
|
|
"total_s_p50": 14.90246445898083,
|
|
"total_s_p95": 24.08200175591046,
|
|
"prompt_tps_mean": 7067890.927047749,
|
|
"prompt_tps_p50": 6856543.23965746,
|
|
"prompt_tps_p95": 11845450.362447295,
|
|
"decode_tps_mean": 19.377795978907,
|
|
"decode_tps_p50": 19.039894932933024,
|
|
"decode_tps_p95": 22.784262218881533,
|
|
"request_tps_mean": 10.048677383124767,
|
|
"request_tps_p50": 7.0969869715907645,
|
|
"request_tps_p95": 21.739669344814565,
|
|
"aggregate_output_tps_mean": 19.35053924595546,
|
|
"aggregate_output_tps_p50": 20.179477104341757,
|
|
"aggregate_output_tps_p95": 20.562657512957074
|
|
}
|
|
] |