anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

[Fix] Update Qwen3 Omni multi-replica perf baselines (#4175)

Browse Source 
Signed-off-by: Chenguang ZHENG <645327136@qq.com>
This commit is contained in:
Chenguang Zheng authored and GitHub committed 2026-06-05 09:22:53 +00:00
1 parent 6cefe91370
commit b3dd0a4baf
1 file changed
+13 -13
Download Patch File Download Diff File Expand all files Collapse all files
tests/dfx/perf/tests/test_qwen3_omni_multi_replicas.json
+13 -13
View File
@@ -23,10 +23,10 @@
"ignore_eos": true,
"percentile-metrics": "ttft,tpot,itl,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"mean_ttft_ms": [1000, 2000, 3000, 4000],
"mean_tpot_ms": [200, 200, 200, 200],
"mean_audio_ttfp_ms": [10000, 15000, 20000, 25000],
"mean_audio_rtf": [1.5, 1.5, 1.5, 1.5]
"mean_ttft_ms": [203, 283, 470, 869],
"mean_tpot_ms": [28, 36, 41, 45],
"mean_audio_ttfp_ms": [861, 1200, 1528, 2100],
"mean_audio_rtf": [0.24, 0.30, 0.35, 0.39]
}
},
{
@@ -49,9 +49,9 @@
},
"percentile-metrics": "ttft,tpot,itl,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"mean_ttft_ms": [2000],
"mean_audio_ttfp_ms": [2000],
"mean_audio_rtf": [0.25]
"mean_ttft_ms": [377],
"mean_audio_ttfp_ms": [684],
"mean_audio_rtf": [0.14]
}
},
{
@@ -76,9 +76,9 @@
},
"percentile-metrics": "ttft,tpot,itl,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"mean_ttft_ms": [6000],
"mean_audio_ttfp_ms": [6000],
"mean_audio_rtf": [0.7]
"mean_ttft_ms": [228],
"mean_audio_ttfp_ms": [686],
"mean_audio_rtf": [0.16]
}
},
{
@@ -105,9 +105,9 @@
},
"percentile-metrics": "ttft,tpot,itl,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"mean_ttft_ms": [12000],
"mean_audio_ttfp_ms": [12000],
"mean_audio_rtf": [1.0]
"mean_ttft_ms": [522],
"mean_audio_ttfp_ms": [1119],
"mean_audio_rtf": [0.21]
}
}
]