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

Update perf baseline base on 7/5-7/11 7 days avg. (#5231)

Browse Source 
Signed-off-by: Alicia <115451386+congw729@users.noreply.github.com>
This commit is contained in:
Alicia authored and GitHub committed 2026-07-21 12:26:22 +00:00
1 parent 779466becb
commit 0034eaa9c3
13 files changed
+197 -197
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

tests/dfx/perf/tests/test_bagel_vllm_omni.json
+16 -16
View File
@@ -40,10 +40,10 @@
"max-concurrency": 1,
"enable-negative-prompt": true,
"baseline": {
"throughput_qps": 0.3678,
"latency_mean": 2.691,
"peak_memory_mb_max": 33083.6,
"peak_memory_mb_mean": 33082.5
"throughput_qps": 0.495,
"latency_mean": 2.0238,
"peak_memory_mb_max": 29393.4286,
"peak_memory_mb_mean": 29392.7143
}
}
]
@@ -90,10 +90,10 @@
"enable-negative-prompt": true,
"num-input-images": 1,
"baseline": {
"throughput_qps": 0.3124,
"latency_mean": 3.1686,
"peak_memory_mb_max": 33448.8,
"peak_memory_mb_mean": 33447.7
"throughput_qps": 0.3451,
"latency_mean": 2.9031,
"peak_memory_mb_max": 30480.2857,
"peak_memory_mb_mean": 30479.2857
}
}
]
@@ -139,10 +139,10 @@
"max-concurrency": 1,
"enable-negative-prompt": true,
"baseline": {
"throughput_qps": 0.3746,
"latency_mean": 2.6425,
"peak_memory_mb_max": 33077.0,
"peak_memory_mb_mean": 33077.0
"throughput_qps": 0.5048,
"latency_mean": 1.987,
"peak_memory_mb_max": 29380.0,
"peak_memory_mb_mean": 29380.0
}
}
]
@@ -189,10 +189,10 @@
"enable-negative-prompt": true,
"num-input-images": 1,
"baseline": {
"throughput_qps": 0.1349,
"latency_mean": 7.339,
"peak_memory_mb_max": 33321.2,
"peak_memory_mb_mean": 33321.2
"throughput_qps": 0.149,
"latency_mean": 6.7157,
"peak_memory_mb_max": 30574.0,
"peak_memory_mb_mean": 30574.0
}
}
]
tests/dfx/perf/tests/test_higgs_audio_v3.json
+5 -5
View File
@@ -47,10 +47,10 @@
"percentile-metrics": "ttft,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"median_audio_ttfp_ms": [
3000
223.3584
],
"median_audio_rtf": [
0.5
0.4393
]
}
},
@@ -71,13 +71,13 @@
"percentile-metrics": "ttft,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"median_audio_ttfp_ms": [
5000
276.575
],
"median_audio_rtf": [
1.2
0.5073
],
"audio_throughput": [
30
27.3728
]
}
}
tests/dfx/perf/tests/test_qwen3_omni_async_chunk.json
+40 -40
View File
@@ -44,25 +44,25 @@
"percentile-metrics": "ttft,tpot,itl,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"mean_ttft_ms": [
135.4379,
187.0896,
400,
435.675,
724.6836
96.4061,
140.8147,
271.9025,
362.2916,
507.776
],
"mean_e2el_ms": [
17619.9851,
34811.8335,
43656.9501,
56657.1548,
85097.6016
18507.4582,
28365.4956,
31907.9613,
48161.5829,
72630.8601
],
"mean_audio_rtf": [
0.1279,
0.2238,
0.2735,
0.3712,
0.5634
0.1175,
0.18,
0.2359,
0.3278,
0.6296
]
}
},
@@ -91,13 +91,13 @@
"percentile-metrics": "ttft,tpot,itl,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"mean_ttft_ms": [
340.329
354.0951
],
"mean_e2el_ms": [
4305.477
3952.5615
],
"mean_audio_rtf": [
0.1305
0.117
]
}
},
@@ -128,13 +128,13 @@
"percentile-metrics": "ttft,tpot,itl,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"mean_ttft_ms": [
220.0909
259.6317
],
"mean_e2el_ms": [
5475.9565
4253.3009
],
"mean_audio_rtf": [
0.1818
0.1448
]
}
},
@@ -167,13 +167,13 @@
"percentile-metrics": "ttft,tpot,itl,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"mean_ttft_ms": [
450.0155
457.4453
],
"mean_e2el_ms": [
8516.8316
5912.5623
],
"mean_audio_rtf": [
0.2717
0.1967
]
}
},
@@ -206,18 +206,18 @@
"percentile-metrics": "ttft,tpot,itl,e2el",
"baseline": {
"mean_ttft_ms": [
78.4278,
195.8037,
333.7318,
561.805,
1038.043
90.8033,
202.1779,
326.5864,
544.8914,
961.3929
],
"mean_e2el_ms": [
4288.3029,
7429.9429,
9451.6184,
12607.5292,
18153.2547
4517.3411,
7857.9711,
9861.1687,
13283.3363,
19541.0736
]
}
},
@@ -251,10 +251,10 @@
"percentile-metrics": "ttft,tpot,itl,e2el",
"baseline": {
"mean_ttft_ms": [
275.3875
318.048
],
"mean_e2el_ms": [
730.6995
807.6114
]
}
},
@@ -290,10 +290,10 @@
"percentile-metrics": "ttft,tpot,itl,e2el",
"baseline": {
"mean_ttft_ms": [
166.2201
186.168
],
"mean_e2el_ms": [
673.5789
726.1137
]
}
},
@@ -331,10 +331,10 @@
"percentile-metrics": "ttft,tpot,itl,e2el",
"baseline": {
"mean_ttft_ms": [
357.7781
375.5282
],
"mean_e2el_ms": [
953.3493
1006.1663
]
}
}
tests/dfx/perf/tests/test_qwen3_omni_multi_replicas.json
+13 -13
View File
@@ -35,10 +35,10 @@
"ignore_eos": true,
"percentile-metrics": "ttft,tpot,itl,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"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]
"mean_ttft_ms": [130.5751, 278.6469, 324.7249, 911.6085],
"mean_tpot_ms": [7.9854, 11.1209, 16.1507, 20.7485],
"mean_audio_ttfp_ms": [486.486, 954.1791, 1289.6514, 2196.8275],
"mean_audio_rtf": [0.1896, 0.3962, 0.4098, 0.7322]
}
},
{
@@ -61,9 +61,9 @@
},
"percentile-metrics": "ttft,tpot,itl,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"mean_ttft_ms": [377],
"mean_audio_ttfp_ms": [684],
"mean_audio_rtf": [0.14]
"mean_ttft_ms": [340.5122],
"mean_audio_ttfp_ms": [463.0752],
"mean_audio_rtf": [0.1153]
}
},
{
@@ -88,9 +88,9 @@
},
"percentile-metrics": "ttft,tpot,itl,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"mean_ttft_ms": [228],
"mean_audio_ttfp_ms": [686],
"mean_audio_rtf": [0.16]
"mean_ttft_ms": [236.926],
"mean_audio_ttfp_ms": [395.2182],
"mean_audio_rtf": [0.1259]
}
},
{
@@ -117,9 +117,9 @@
},
"percentile-metrics": "ttft,tpot,itl,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"mean_ttft_ms": [522],
"mean_audio_ttfp_ms": [1119],
"mean_audio_rtf": [0.21]
"mean_ttft_ms": [470.6126],
"mean_audio_ttfp_ms": [665.5474],
"mean_audio_rtf": [0.166]
}
}
]
tests/dfx/perf/tests/test_qwen3_omni_no_async_chunk.json
+24 -24
View File
@@ -44,25 +44,25 @@
"percentile-metrics": "ttft,tpot,itl,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"mean_ttft_ms": [
109.1218,
247.4411,
354.9384,
447.7885,
694.7487
115.8348,
173.1823,
446.672,
464.5985,
3420.0634
],
"mean_e2el_ms": [
22413.667,
30808.9715,
35677.844,
46345.8978,
68350.4853
25070.9523,
31992.0646,
37619.7669,
50393.8257,
136619.2743
],
"mean_audio_rtf": [
0.1695,
0.2033,
0.2467,
0.3234,
0.4438
0.169,
0.2111,
0.2475,
0.3551,
0.9266
]
}
},
@@ -91,13 +91,13 @@
"percentile-metrics": "ttft,tpot,itl,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"mean_ttft_ms": [
323.3573
343.1377
],
"mean_e2el_ms": [
4623.4173
4811.1123
],
"mean_audio_rtf": [
0.1406
0.1463
]
}
},
@@ -128,13 +128,13 @@
"percentile-metrics": "ttft,tpot,itl,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"mean_ttft_ms": [
215.4502
245.5446
],
"mean_e2el_ms": [
4924.149
5019.1256
],
"mean_audio_rtf": [
0.1637
0.1713
]
}
},
@@ -167,13 +167,13 @@
"percentile-metrics": "ttft,tpot,itl,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"mean_ttft_ms": [
442.5815
506.1407
],
"mean_e2el_ms": [
6441.0986
6814.9656
],
"mean_audio_rtf": [
0.2091
0.2213
]
}
}
tests/dfx/perf/tests/test_qwen3_omni_vllm_text.json
+16 -16
View File
@@ -52,18 +52,18 @@
"percentile-metrics": "ttft,tpot,itl,e2el",
"baseline": {
"mean_ttft_ms": [
69.1276,
255.1882,
310.639,
422.0337,
532.0582
69.8081,
173.0651,
271.8108,
413.4079,
497.2546
],
"mean_e2el_ms": [
4382.7211,
7510.3815,
9440.4854,
12553.0186,
16932.6065
4720.8225,
7937.2532,
9962.3566,
13724.5479,
18324.091
]
}
},
@@ -98,10 +98,10 @@
"percentile-metrics": "ttft,tpot,itl,e2el",
"baseline": {
"mean_ttft_ms": [
26.3381
25.9477
],
"mean_e2el_ms": [
485.2436
517.3155
]
}
},
@@ -138,10 +138,10 @@
"percentile-metrics": "ttft,tpot,itl,e2el",
"baseline": {
"mean_ttft_ms": [
26.4517
26.7056
],
"mean_e2el_ms": [
517.2017
551.308
]
}
},
@@ -180,10 +180,10 @@
"percentile-metrics": "ttft,tpot,itl,e2el",
"baseline": {
"mean_ttft_ms": [
27.6972
27.6906
],
"mean_e2el_ms": [
561.3684
596.5284
]
}
}
tests/dfx/perf/tests/test_qwen_image_edit_2511_vllm_omni.json
+10 -10
View File
@@ -36,8 +36,8 @@
"baseline": {
"throughput_qps": 0.0721,
"latency_mean": 13.8398,
"peak_memory_mb_max": 54731.4,
"peak_memory_mb_mean": 54731.4
"peak_memory_mb_max": 57610.0,
"peak_memory_mb_mean": 57610.0
}
},
{
@@ -54,8 +54,8 @@
"baseline": {
"throughput_qps": 0.0186,
"latency_mean": 53.6942,
"peak_memory_mb_max": 64402.4,
"peak_memory_mb_mean": 64402.4
"peak_memory_mb_max": 67790.0,
"peak_memory_mb_mean": 67790.0
}
}
]
@@ -101,8 +101,8 @@
"baseline": {
"throughput_qps": 0.0538,
"latency_mean": 18.5591,
"peak_memory_mb_max": 53485.0,
"peak_memory_mb_mean": 53485.0
"peak_memory_mb_max": 56449.4286,
"peak_memory_mb_mean": 56449.4286
}
}
]
@@ -158,8 +158,8 @@
"baseline": {
"throughput_qps": 0.2776,
"latency_mean": 3.5938,
"peak_memory_mb_max": 55214.0,
"peak_memory_mb_mean": 55214.0
"peak_memory_mb_max": 58113.7143,
"peak_memory_mb_mean": 58075.1429
}
},
{
@@ -176,8 +176,8 @@
"baseline": {
"throughput_qps": 0.1051,
"latency_mean": 9.4918,
"peak_memory_mb_max": 64265.6,
"peak_memory_mb_mean": 64265.6
"peak_memory_mb_max": 68107.4286,
"peak_memory_mb_mean": 68107.4286
}
}
]
tests/dfx/perf/tests/test_qwen_image_edit_vllm_omni.json
+11 -11
View File
@@ -35,8 +35,8 @@
"baseline": {
"throughput_qps": 0.1129,
"latency_mean": 8.8352,
"peak_memory_mb_max": 55356.5,
"peak_memory_mb_mean": 55356.5
"peak_memory_mb_max": 58572.0,
"peak_memory_mb_mean": 58572.0
}
},
{
@@ -50,10 +50,10 @@
"max-concurrency": 1,
"enable-negative-prompt": true,
"baseline": {
"throughput_qps": 0.0240,
"throughput_qps": 0.024,
"latency_mean": 41.5686,
"peak_memory_mb_max": 62762.7,
"peak_memory_mb_mean": 62762.7
"peak_memory_mb_max": 66368.0,
"peak_memory_mb_mean": 66368.0
}
}
]
@@ -98,8 +98,8 @@
"baseline": {
"throughput_qps": 0.0672,
"latency_mean": 14.8517,
"peak_memory_mb_max": 53931.5,
"peak_memory_mb_mean": 53931.5
"peak_memory_mb_max": 57076.0,
"peak_memory_mb_mean": 57076.0
}
}
]
@@ -154,8 +154,8 @@
"baseline": {
"throughput_qps": 0.2879,
"latency_mean": 3.4701,
"peak_memory_mb_max": 55525.6,
"peak_memory_mb_mean": 55525.6
"peak_memory_mb_max": 58758.0,
"peak_memory_mb_mean": 58758.0
}
},
{
@@ -171,8 +171,8 @@
"baseline": {
"throughput_qps": 0.1113,
"latency_mean": 8.9656,
"peak_memory_mb_max": 63758.3,
"peak_memory_mb_mean": 63758.3
"peak_memory_mb_max": 67424.0,
"peak_memory_mb_mean": 67424.0
}
}
]
tests/dfx/perf/tests/test_qwen_image_layered_vllm_omni.json
+4 -4
View File
@@ -35,8 +35,8 @@
"baseline": {
"throughput_qps": 0.0703,
"latency_mean": 14.208,
"peak_memory_mb_max": 60543.5,
"peak_memory_mb_mean": 60543.5
"peak_memory_mb_max": 63225.1429,
"peak_memory_mb_mean": 63225.1429
}
},
{
@@ -52,8 +52,8 @@
"baseline": {
"throughput_qps": 0.0417,
"latency_mean": 23.914,
"peak_memory_mb_max": 60543.5,
"peak_memory_mb_mean": 60543.5
"peak_memory_mb_max": 63225.1429,
"peak_memory_mb_mean": 63225.1429
}
}
]
tests/dfx/perf/tests/test_qwen_image_vllm_omni.json
+8 -8
View File
@@ -35,7 +35,7 @@
"baseline": {
"throughput_qps": 0.4153,
"latency_mean": 2.4065,
"peak_memory_mb_mean": 52289.9
"peak_memory_mb_mean": 55121.4286
}
},
{
@@ -51,7 +51,7 @@
"baseline": {
"throughput_qps": 0.0423,
"latency_mean": 23.5991,
"peak_memory_mb_mean": 61360.5
"peak_memory_mb_mean": 65118.0
}
}
]
@@ -93,7 +93,7 @@
"baseline": {
"throughput_qps": 0.4175,
"latency_mean": 2.3953,
"peak_memory_mb_mean": 56000
"peak_memory_mb_mean": 55088.5714
}
},
{
@@ -109,7 +109,7 @@
"baseline": {
"throughput_qps": 0.0423,
"latency_mean": 23.5768,
"peak_memory_mb_mean": 65000
"peak_memory_mb_mean": 66012.2857
}
}
]
@@ -154,7 +154,7 @@
"baseline": {
"throughput_qps": 0.1214,
"latency_mean": 8.2211,
"peak_memory_mb_mean": 51704.7
"peak_memory_mb_mean": 54501.1429
}
}
]
@@ -209,7 +209,7 @@
"baseline": {
"throughput_qps": 0.559,
"latency_mean": 1.794,
"peak_memory_mb_mean": 52397.6775
"peak_memory_mb_mean": 55290.5714
}
},
{
@@ -225,7 +225,7 @@
"baseline": {
"throughput_qps": 0.1918,
"latency_mean": 5.2022,
"peak_memory_mb_mean": 61468.8
"peak_memory_mb_mean": 64838.8571
}
}
]
@@ -271,7 +271,7 @@
"baseline": {
"throughput_qps": [0.4125, 0.6714, 0.6674, 0.8159],
"latency_mean": [2.4215, 2.992, 5.9293, 9.656],
"peak_memory_mb_mean": [67000, 67000, 67000, 67000]
"peak_memory_mb_mean": [55147.4286, 55148.0, 55150.4643, 55152.3821]
}
}
]
tests/dfx/perf/tests/test_tts.json
+30 -30
View File
@@ -40,10 +40,10 @@
"percentile-metrics": "ttft,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"median_audio_ttfp_ms": [
139.9434
141.2791
],
"median_audio_rtf": [
0.1683
0.1591
]
}
},
@@ -68,7 +68,7 @@
"percentile-metrics": "ttft,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"median_audio_ttfp_ms": [
227.5653,
226.747,
647.1272,
4777.2714
],
@@ -78,9 +78,9 @@
1.2282
],
"audio_throughput": [
23.501,
40.634,
43.0758
24.2296,
40.3552,
43.2572
]
}
},
@@ -154,10 +154,10 @@
"percentile-metrics": "ttft,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"median_audio_ttfp_ms": [
49.7908
46.8434
],
"median_audio_rtf": [
0.1425
0.1367
]
}
},
@@ -197,9 +197,9 @@
1.1662
],
"audio_throughput": [
36.465,
49.6268,
48.3091
38.3858,
55.3523,
68.7032
]
}
},
@@ -253,13 +253,13 @@
"percentile-metrics": "ttft,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"median_audio_ttfp_ms": [
56.6977
56.746
],
"median_audio_rtf": [
0.1555
0.1571
],
"audio_throughput": [
11.5292
11.1226
]
}
},
@@ -284,10 +284,10 @@
"percentile-metrics": "ttft,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"median_audio_ttfp_ms": [
52.0447
46.3479
],
"median_audio_rtf": [
0.1452
0.1352
]
}
},
@@ -326,9 +326,9 @@
1.1703
],
"audio_throughput": [
40.2198,
48.9046,
48.0505
38.9378,
55.1846,
71.5708
]
}
},
@@ -353,13 +353,13 @@
"percentile-metrics": "ttft,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"median_audio_ttfp_ms": [
56.3961
55.5029
],
"median_audio_rtf": [
0.1542
0.1508
],
"audio_throughput": [
9.6672
9.4885
]
}
}
@@ -403,10 +403,10 @@
"percentile-metrics": "ttft,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"median_audio_ttfp_ms": [
150
82.1886
],
"median_audio_rtf": [
0.15
0.1241
]
}
},
@@ -430,13 +430,13 @@
"percentile-metrics": "ttft,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"median_audio_ttfp_ms": [
1500
160.9168
],
"median_audio_rtf": [
0.3
0.1907
],
"audio_throughput": [
30.0
39.2332
]
}
},
@@ -460,13 +460,13 @@
"percentile-metrics": "ttft,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"median_audio_ttfp_ms": [
3000
100.1265
],
"median_audio_rtf": [
0.25
0.1437
],
"audio_throughput": [
4.0
11.7605
]
}
}
tests/dfx/perf/tests/test_voxcpm2.json
+11 -11
View File
@@ -38,10 +38,10 @@
"percentile-metrics": "ttft,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"median_audio_ttfp_ms": [
130.2115
137.645
],
"median_audio_rtf": [
0.0488
0.0497
]
}
},
@@ -65,10 +65,10 @@
475.3357
],
"median_audio_rtf": [
0.1671
0.1243
],
"audio_throughput": [
22.8717
36.6358
]
}
},
@@ -115,10 +115,10 @@
"percentile-metrics": "ttft,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"median_audio_ttfp_ms": [
75.7427
79.6927
],
"median_audio_rtf": [
0.0419
0.0423
]
}
},
@@ -142,13 +142,13 @@
"percentile-metrics": "ttft,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"median_audio_ttfp_ms": [
351.5855
262.6212
],
"median_audio_rtf": [
0.1207
0.0753
],
"audio_throughput": [
73.7632
103.5843
]
}
},
@@ -175,10 +175,10 @@
80.1095
],
"median_audio_rtf": [
0.0485
0.0479
],
"audio_throughput": [
18.3715
17.2918
]
}
},
tests/dfx/perf/tests/test_wan22_i2v_vllm_omni.json
+9 -9
View File
@@ -42,9 +42,9 @@
}
],
"baseline": {
"throughput_qps": 0.0465,
"latency_mean": 21.4354,
"peak_memory_mb_mean": 72557.58
"throughput_qps": 0.0434,
"latency_mean": 23.0654,
"peak_memory_mb_mean": 76360.0
}
}
]
@@ -96,9 +96,9 @@
}
],
"baseline": {
"throughput_qps": 0.0642,
"latency_mean": 15.5589,
"peak_memory_mb_mean": 45742.88
"throughput_qps": 0.0606,
"latency_mean": 16.4928,
"peak_memory_mb_mean": 47164.8
}
},
{
@@ -121,9 +121,9 @@
}
],
"baseline": {
"throughput_qps": 0.0128,
"latency_mean": 77.8565,
"peak_memory_mb_mean": 53947.84
"throughput_qps": 0.0124,
"latency_mean": 80.7784,
"peak_memory_mb_mean": 55374.3429
}
}
]