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

[CI] Update perf json baselines (#4289)

Browse Source 
Signed-off-by: Alicia <115451386+congw729@users.noreply.github.com>
Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com>
Signed-off-by: herotai214 <herotai214@gmail.com>
Signed-off-by: bjf-frz <frz123db@gmail.com>
Signed-off-by: dengyunyang <584797741@qq.com>
Signed-off-by: Huang, Zeyu <11222265+fhfuih@users.noreply.github.com>
Signed-off-by: CHEN <116010019@link.cuhk.edu.cn>
Signed-off-by: NumberWan <wantszkin2003@gmail.com>
Co-authored-by: amy-why-3459 <wuhaiyan17@huawei.com>
Co-authored-by: herotai214 <herotai214@gmail.com>
Co-authored-by: bjf-frz <frz123db@gmail.com>
Co-authored-by: dengyunyang <584797741@qq.com>
Co-authored-by: Huang, Zeyu <11222265+fhfuih@users.noreply.github.com>
Co-authored-by: CHEN <116010019@link.cuhk.edu.cn>
Co-authored-by: rein yang <73573651+R2-Y@users.noreply.github.com>
Co-authored-by: NumberWan <wantszkin2003@gmail.com>
This commit is contained in:
Aliciaamy-why-3459herotai214bjf-frzdengyunyangHuang, ZeyuCHENrein yangNumberWan
 authored and GitHub committed 2026-06-17 14:02:50 +08:00
1 parent d897852258
commit 1761253005
12 files changed
+278 -236
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

tests/dfx/perf/tests/test_hunyuan_image3_it2i.json
+14 -7
View File
@@ -41,7 +41,11 @@
"tensor_parallel_size": 2,
"hf_overrides": {
"rope_parameters": {
"mrope_section": [0, 32, 32],
"mrope_section": [
0,
32,
32
],
"rope_type": "default"
}
},
@@ -58,7 +62,9 @@
"max_tokens": 8192,
"detokenize": true,
"skip_special_tokens": false,
"stop_token_ids": [128025]
"stop_token_ids": [
128025
]
}
},
{
@@ -106,7 +112,9 @@
"content": [
{
"prompt": "新年宠物海报，Q版圆润的可爱标题“新年快乐汪”，副标题“HAPPY NEW YEAR”。 鱼眼镜头，背景是房间门口，近景，上传的主体歪头笑，围着红色围巾，戴着红色毛线帽，高清，绒毛细节，面部特写。 宝丽莱相纸，超现实主义，写实主义，胶片摄影，打印颗粒感肌理。肌理，超写实，复古感。",
"image_urls": ["https://raw.githubusercontent.com/Tencent-Hunyuan/HunyuanImage-3.0/main/assets/demo_instruct_imgs/input_0_0.png"],
"image_urls": [
"https://raw.githubusercontent.com/Tencent-Hunyuan/HunyuanImage-3.0/main/assets/demo_instruct_imgs/input_0_0.png"
],
"num_inference_steps": 8,
"seed": 42,
"guidance_scale": 1.0
@@ -119,10 +127,9 @@
"num-prompts": 96,
"skip-performance-assertion": true,
"baseline": {
"throughput_qps": 0.1,
"latency_p99": 44.46,
"latency_mean": 35.57,
"latency_std_dev": 0.5,
"throughput_qps": 0.1874,
"latency_p99": 101.852,
"latency_mean": 79.0385,
"peak_memory_mb_max": 70000,
"peak_memory_mb_mean": 70000
}
tests/dfx/perf/tests/test_hunyuan_image_tp4.json
+5 -4
View File
@@ -23,10 +23,11 @@
"max-concurrency": 1,
"skip-performance-assertion": true,
"baseline": {
"throughput_qps": 0.21,
"latency_p99": 4.9235,
"peak_memory_mb_max": 57576,
"peak_memory_mb_mean": 57576
"throughput_qps": 0.213,
"latency_mean": 4.6953,
"latency_p99": 4.8601,
"peak_memory_mb_max": 56912.0,
"peak_memory_mb_mean": 56912.0
}
}
]
tests/dfx/perf/tests/test_qwen3_omni_async_chunk.json
+39 -39
View File
@@ -32,25 +32,25 @@
"percentile-metrics": "ttft,tpot,itl,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"mean_ttft_ms": [
135.4379,
187.0896,
400,
300,
400,
600,
900
435.675,
724.6836
],
"mean_e2el_ms": [
26000,
43000,
52000,
72000,
109000
17619.9851,
34811.8335,
43656.9501,
56657.1548,
85097.6016
],
"mean_audio_rtf": [
0.15,
0.30,
0.35,
0.50,
0.75
0.1279,
0.2238,
0.2735,
0.3712,
0.5634
]
}
},
@@ -79,13 +79,13 @@
"percentile-metrics": "ttft,tpot,itl,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"mean_ttft_ms": [
600
340.329
],
"mean_e2el_ms": [
6000
4305.477
],
"mean_audio_rtf": [
0.20
0.1305
]
}
},
@@ -116,13 +116,13 @@
"percentile-metrics": "ttft,tpot,itl,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"mean_ttft_ms": [
300
220.0909
],
"mean_e2el_ms": [
7000
5475.9565
],
"mean_audio_rtf": [
0.25
0.1818
]
}
},
@@ -155,13 +155,13 @@
"percentile-metrics": "ttft,tpot,itl,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"mean_ttft_ms": [
700
450.0155
],
"mean_e2el_ms": [
11000
8516.8316
],
"mean_audio_rtf": [
0.35
0.2717
]
}
},
@@ -194,18 +194,18 @@
"percentile-metrics": "ttft,tpot,itl,e2el",
"baseline": {
"mean_ttft_ms": [
100,
300,
500,
800,
1500
78.4278,
195.8037,
333.7318,
561.805,
1038.043
],
"mean_e2el_ms": [
5000,
8000,
10000,
14000,
20000
4288.3029,
7429.9429,
9451.6184,
12607.5292,
18153.2547
]
}
},
@@ -239,10 +239,10 @@
"percentile-metrics": "ttft,tpot,itl,e2el",
"baseline": {
"mean_ttft_ms": [
500
275.3875
],
"mean_e2el_ms": [
1000
730.6995
]
}
},
@@ -278,10 +278,10 @@
"percentile-metrics": "ttft,tpot,itl,e2el",
"baseline": {
"mean_ttft_ms": [
200
166.2201
],
"mean_e2el_ms": [
800
673.5789
]
}
},
@@ -319,10 +319,10 @@
"percentile-metrics": "ttft,tpot,itl,e2el",
"baseline": {
"mean_ttft_ms": [
600
357.7781
],
"mean_e2el_ms": [
1300
953.3493
]
}
}
tests/dfx/perf/tests/test_qwen3_omni_no_async_chunk.json
+24 -24
View File
@@ -32,25 +32,25 @@
"percentile-metrics": "ttft,tpot,itl,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"mean_ttft_ms": [
400,
300,
400,
600,
900
109.1218,
247.4411,
354.9384,
447.7885,
694.7487
],
"mean_e2el_ms": [
32000,
34000,
45000,
61000,
90000
22413.667,
30808.9715,
35677.844,
46345.8978,
68350.4853
],
"mean_audio_rtf": [
0.20,
0.25,
0.30,
0.45,
0.60
0.1695,
0.2033,
0.2467,
0.3234,
0.4438
]
}
},
@@ -79,13 +79,13 @@
"percentile-metrics": "ttft,tpot,itl,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"mean_ttft_ms": [
500
323.3573
],
"mean_e2el_ms": [
6000
4623.4173
],
"mean_audio_rtf": [
0.20
0.1406
]
}
},
@@ -116,13 +116,13 @@
"percentile-metrics": "ttft,tpot,itl,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"mean_ttft_ms": [
300
215.4502
],
"mean_e2el_ms": [
7000
4924.149
],
"mean_audio_rtf": [
0.20
0.1637
]
}
},
@@ -155,13 +155,13 @@
"percentile-metrics": "ttft,tpot,itl,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"mean_ttft_ms": [
700
442.5815
],
"mean_e2el_ms": [
9000
6441.0986
],
"mean_audio_rtf": [
0.30
0.2091
]
}
}
tests/dfx/perf/tests/test_qwen3_omni_vllm_text.json
+16 -16
View File
@@ -40,18 +40,18 @@
"percentile-metrics": "ttft,tpot,itl,e2el",
"baseline": {
"mean_ttft_ms": [
300,
300,
1000,
600,
800
69.1276,
255.1882,
310.639,
422.0337,
532.0582
],
"mean_e2el_ms": [
6000,
8000,
11000,
13000,
17000
4382.7211,
7510.3815,
9440.4854,
12553.0186,
16932.6065
]
}
},
@@ -86,10 +86,10 @@
"percentile-metrics": "ttft,tpot,itl,e2el",
"baseline": {
"mean_ttft_ms": [
30
26.3381
],
"mean_e2el_ms": [
540
485.2436
]
}
},
@@ -126,10 +126,10 @@
"percentile-metrics": "ttft,tpot,itl,e2el",
"baseline": {
"mean_ttft_ms": [
30
26.4517
],
"mean_e2el_ms": [
600
517.2017
]
}
},
@@ -168,10 +168,10 @@
"percentile-metrics": "ttft,tpot,itl,e2el",
"baseline": {
"mean_ttft_ms": [
40
27.6972
],
"mean_e2el_ms": [
700
561.3684
]
}
}
tests/dfx/perf/tests/test_qwen_image_edit_2511_vllm_omni.json
+20 -20
View File
@@ -22,10 +22,10 @@
"num-input-images": 2,
"enable-negative-prompt": true,
"baseline": {
"throughput_qps": 0.06,
"latency_mean": 20,
"peak_memory_mb_max": 57000,
"peak_memory_mb_mean": 57000
"throughput_qps": 0.0721,
"latency_mean": 13.8398,
"peak_memory_mb_max": 54731.4,
"peak_memory_mb_mean": 54731.4
}
},
{
@@ -40,10 +40,10 @@
"num-input-images": 2,
"enable-negative-prompt": true,
"baseline": {
"throughput_qps": 0.01,
"latency_mean": 60,
"peak_memory_mb_max": 67000,
"peak_memory_mb_mean": 67000
"throughput_qps": 0.0186,
"latency_mean": 53.6942,
"peak_memory_mb_max": 64402.4,
"peak_memory_mb_mean": 64402.4
}
}
]
@@ -75,10 +75,10 @@
"num-input-images": 2,
"enable-negative-prompt": true,
"baseline": {
"throughput_qps": 0.05,
"latency_mean": 20,
"peak_memory_mb_max": 55000,
"peak_memory_mb_mean": 55000
"throughput_qps": 0.0538,
"latency_mean": 18.5591,
"peak_memory_mb_max": 53485.0,
"peak_memory_mb_mean": 53485.0
}
}
]
@@ -120,10 +120,10 @@
"num-input-images": 2,
"enable-negative-prompt": true,
"baseline": {
"throughput_qps": 0.21,
"latency_mean": 10,
"peak_memory_mb_max": 57000,
"peak_memory_mb_mean": 57000
"throughput_qps": 0.2776,
"latency_mean": 3.5938,
"peak_memory_mb_max": 55214.0,
"peak_memory_mb_mean": 55214.0
}
},
{
@@ -138,10 +138,10 @@
"num-input-images": 2,
"enable-negative-prompt": true,
"baseline": {
"throughput_qps": 0.08,
"latency_mean": 20,
"peak_memory_mb_max": 66000,
"peak_memory_mb_mean": 66000
"throughput_qps": 0.1051,
"latency_mean": 9.4918,
"peak_memory_mb_max": 64265.6,
"peak_memory_mb_mean": 64265.6
}
}
]
tests/dfx/perf/tests/test_qwen_image_edit_vllm_omni.json
+20 -20
View File
@@ -21,10 +21,10 @@
"max-concurrency": 1,
"enable-negative-prompt": true,
"baseline": {
"throughput_qps": 0.1,
"latency_mean": 10,
"peak_memory_mb_max": 57000,
"peak_memory_mb_mean": 57000
"throughput_qps": 0.1129,
"latency_mean": 8.8352,
"peak_memory_mb_max": 55356.5,
"peak_memory_mb_mean": 55356.5
}
},
{
@@ -38,10 +38,10 @@
"max-concurrency": 1,
"enable-negative-prompt": true,
"baseline": {
"throughput_qps": 0.02,
"latency_mean": 50,
"peak_memory_mb_max": 65000,
"peak_memory_mb_mean": 65000
"throughput_qps": 0.0240,
"latency_mean": 41.5686,
"peak_memory_mb_max": 62762.7,
"peak_memory_mb_mean": 62762.7
}
}
]
@@ -72,10 +72,10 @@
"max-concurrency": 1,
"enable-negative-prompt": true,
"baseline": {
"throughput_qps": 0.06,
"latency_mean": 20,
"peak_memory_mb_max": 56000,
"peak_memory_mb_mean": 56000
"throughput_qps": 0.0672,
"latency_mean": 14.8517,
"peak_memory_mb_max": 53931.5,
"peak_memory_mb_mean": 53931.5
}
}
]
@@ -116,10 +116,10 @@
"max-concurrency": 1,
"enable-negative-prompt": true,
"baseline": {
"throughput_qps": 0.26,
"latency_mean": 10,
"peak_memory_mb_max": 58000,
"peak_memory_mb_mean": 58000
"throughput_qps": 0.2879,
"latency_mean": 3.4701,
"peak_memory_mb_max": 55525.6,
"peak_memory_mb_mean": 55525.6
}
},
{
@@ -133,10 +133,10 @@
"max-concurrency": 1,
"enable-negative-prompt": true,
"baseline": {
"throughput_qps": 0.1,
"latency_mean": 10,
"peak_memory_mb_max": 67000,
"peak_memory_mb_mean": 67000
"throughput_qps": 0.1113,
"latency_mean": 8.9656,
"peak_memory_mb_max": 63758.3,
"peak_memory_mb_mean": 63758.3
}
}
]
tests/dfx/perf/tests/test_qwen_image_layered_vllm_omni.json
+8 -8
View File
@@ -21,10 +21,10 @@
"max-concurrency": 1,
"enable-negative-prompt": true,
"baseline": {
"throughput_qps": 0.05,
"latency_mean": 20,
"peak_memory_mb_max": 63000,
"peak_memory_mb_mean": 63000
"throughput_qps": 0.0703,
"latency_mean": 14.208,
"peak_memory_mb_max": 60543.5,
"peak_memory_mb_mean": 60543.5
}
},
{
@@ -38,10 +38,10 @@
"max-concurrency": 1,
"enable-negative-prompt": true,
"baseline": {
"throughput_qps": 0.03,
"latency_mean": 30,
"peak_memory_mb_max": 63000,
"peak_memory_mb_mean": 63000
"throughput_qps": 0.0417,
"latency_mean": 23.914,
"peak_memory_mb_max": 60543.5,
"peak_memory_mb_mean": 60543.5
}
}
]
tests/dfx/perf/tests/test_qwen_image_vllm_omni.json
+21 -21
View File
@@ -21,9 +21,9 @@
"max-concurrency": 1,
"enable-negative-prompt": true,
"baseline": {
"throughput_qps": 0.35,
"latency_mean": 3,
"peak_memory_mb_mean": 56000
"throughput_qps": 0.4153,
"latency_mean": 2.4065,
"peak_memory_mb_mean": 52289.9
}
},
{
@@ -37,9 +37,9 @@
"max-concurrency": 1,
"enable-negative-prompt": true,
"baseline": {
"throughput_qps": 0.03,
"latency_mean": 26,
"peak_memory_mb_mean": 65000
"throughput_qps": 0.0423,
"latency_mean": 23.5991,
"peak_memory_mb_mean": 61360.5
}
}
]
@@ -67,8 +67,8 @@
"max-concurrency": 1,
"enable-negative-prompt": true,
"baseline": {
"throughput_qps": 0.35,
"latency_mean": 3,
"throughput_qps": 0.4175,
"latency_mean": 2.3953,
"peak_memory_mb_mean": 56000
}
},
@@ -83,8 +83,8 @@
"max-concurrency": 1,
"enable-negative-prompt": true,
"baseline": {
"throughput_qps": 0.03,
"latency_mean": 26,
"throughput_qps": 0.0423,
"latency_mean": 23.5768,
"peak_memory_mb_mean": 65000
}
}
@@ -116,9 +116,9 @@
"max-concurrency": 1,
"enable-negative-prompt": true,
"baseline": {
"throughput_qps": 0.11,
"latency_mean": 9,
"peak_memory_mb_mean": 55000
"throughput_qps": 0.1214,
"latency_mean": 8.2211,
"peak_memory_mb_mean": 51704.7
}
}
]
@@ -159,9 +159,9 @@
"max-concurrency": 1,
"enable-negative-prompt": true,
"baseline": {
"throughput_qps": 0.46,
"latency_mean": 3,
"peak_memory_mb_mean": 56000
"throughput_qps": 0.559,
"latency_mean": 1.794,
"peak_memory_mb_mean": 52397.6775
}
},
{
@@ -175,9 +175,9 @@
"max-concurrency": 1,
"enable-negative-prompt": true,
"baseline": {
"throughput_qps": 0.18,
"latency_mean": 6,
"peak_memory_mb_mean": 67000
"throughput_qps": 0.1918,
"latency_mean": 5.2022,
"peak_memory_mb_mean": 61468.8
}
}
]
@@ -209,8 +209,8 @@
"warmup-num-inference-steps": 20,
"enable-negative-prompt": true,
"baseline": {
"throughput_qps": [0.30, 0.50, 0.60, 0.70],
"latency_mean": [3.50, 4.00, 7.00, 12.00],
"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]
}
}
tests/dfx/perf/tests/test_tts.json
+89 -55
View File
@@ -27,10 +27,10 @@
"percentile-metrics": "ttft,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"median_audio_ttfp_ms": [
3000
122.4504
],
"median_audio_rtf": [
0.6
0.1472
]
}
},
@@ -55,19 +55,19 @@
"percentile-metrics": "ttft,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"median_audio_ttfp_ms": [
1000,
3000,
14000
199.1197,
647.1272,
4777.2714
],
"median_audio_rtf": [
0.70,
1.15,
3.90
0.2899,
0.3642,
1.2282
],
"audio_throughput": [
12,
14,
14
20.5634,
40.634,
43.0758
]
}
},
@@ -129,10 +129,10 @@
"percentile-metrics": "ttft,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"median_audio_ttfp_ms": [
2000
43.5669
],
"median_audio_rtf": [
0.40
0.1247
]
}
},
@@ -162,19 +162,19 @@
"percentile-metrics": "ttft,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"median_audio_ttfp_ms": [
300,
1000,
5000
65.9174,
713.7727,
5941.7179
],
"median_audio_rtf": [
0.25,
0.35,
1.10
0.1626,
0.3148,
1.1662
],
"audio_throughput": [
30,
40,
40
31.9068,
49.6268,
48.3091
]
}
},
@@ -228,13 +228,13 @@
"percentile-metrics": "ttft,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"median_audio_ttfp_ms": [
100
49.6105
],
"median_audio_rtf": [
0.20
0.1361
],
"audio_throughput": [
10
10.0881
]
}
},
@@ -259,10 +259,10 @@
"percentile-metrics": "ttft,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"median_audio_ttfp_ms": [
100
45.5391
],
"median_audio_rtf": [
0.15
0.1271
]
}
},
@@ -291,19 +291,19 @@
"percentile-metrics": "ttft,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"median_audio_ttfp_ms": [
100,
1000,
5000
66.1471,
587.5877,
4960.3726
],
"median_audio_rtf": [
0.25,
0.40,
1.20
0.1637,
0.3143,
1.1703
],
"audio_throughput": [
30,
40,
40
35.1923,
48.9046,
48.0505
]
}
},
@@ -328,10 +328,10 @@
"percentile-metrics": "ttft,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"median_audio_ttfp_ms": [
100
49.3466
],
"median_audio_rtf": [
0.20
0.1349
],
"audio_throughput": [
9
@@ -353,14 +353,24 @@
"backend": "openai-audio-speech",
"endpoint": "/v1/audio/speech",
"dataset_path": "benchmarks/build_dataset/seed_tts_smoke",
"num_prompts": [20],
"max_concurrency": [1],
"num_prompts": [
20
],
"max_concurrency": [
1
],
"seed_tts_locale": "en",
"extra_body": {"voice": "casual_male"},
"extra_body": {
"voice": "casual_male"
},
"percentile-metrics": "ttft,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"median_audio_ttfp_ms": [150],
"median_audio_rtf": [0.15]
"median_audio_ttfp_ms": [
150
],
"median_audio_rtf": [
0.15
]
}
},
{
@@ -370,15 +380,27 @@
"backend": "openai-audio-speech",
"endpoint": "/v1/audio/speech",
"dataset_path": "benchmarks/build_dataset/seed_tts_smoke",
"num_prompts": [80],
"max_concurrency": [8],
"num_prompts": [
80
],
"max_concurrency": [
8
],
"seed_tts_locale": "en",
"extra_body": {"voice": "casual_male"},
"extra_body": {
"voice": "casual_male"
},
"percentile-metrics": "ttft,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"median_audio_ttfp_ms": [1500],
"median_audio_rtf": [0.30],
"audio_throughput": [30.0]
"median_audio_ttfp_ms": [
1500
],
"median_audio_rtf": [
0.3
],
"audio_throughput": [
30.0
]
}
},
{
@@ -388,15 +410,27 @@
"backend": "openai-audio-speech",
"endpoint": "/v1/audio/speech",
"dataset_path": "benchmarks/build_dataset/seed_tts_smoke",
"num_prompts": [100],
"request_rate": [2.0],
"num_prompts": [
100
],
"request_rate": [
2.0
],
"seed_tts_locale": "en",
"extra_body": {"voice": "casual_male"},
"extra_body": {
"voice": "casual_male"
},
"percentile-metrics": "ttft,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"median_audio_ttfp_ms": [3000],
"median_audio_rtf": [0.25],
"audio_throughput": [4.0]
"median_audio_ttfp_ms": [
3000
],
"median_audio_rtf": [
0.25
],
"audio_throughput": [
4.0
]
}
}
]
tests/dfx/perf/tests/test_voxcpm2.json
+13 -13
View File
@@ -23,10 +23,10 @@
"percentile-metrics": "ttft,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"median_audio_ttfp_ms": [
600
113.9351
],
"median_audio_rtf": [
0.2
0.0427
]
}
},
@@ -47,13 +47,13 @@
"percentile-metrics": "ttft,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"median_audio_ttfp_ms": [
3500
415.9187
],
"median_audio_rtf": [
0.85
0.1462
],
"audio_throughput": [
8
20.0128
]
}
},
@@ -100,10 +100,10 @@
"percentile-metrics": "ttft,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"median_audio_ttfp_ms": [
350
66.2748
],
"median_audio_rtf": [
0.15
0.0366
]
}
},
@@ -127,13 +127,13 @@
"percentile-metrics": "ttft,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"median_audio_ttfp_ms": [
3000
307.6373
],
"median_audio_rtf": [
0.5
0.1056
],
"audio_throughput": [
10
64.5428
]
}
},
@@ -157,13 +157,13 @@
"percentile-metrics": "ttft,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"median_audio_ttfp_ms": [
500
70.0958
],
"median_audio_rtf": [
0.3
0.0424
],
"audio_throughput": [
5
16.075
]
}
},
tests/dfx/perf/tests/test_wan22_i2v_vllm_omni.json
+9 -9
View File
@@ -30,9 +30,9 @@
}
],
"baseline": {
"throughput_qps": 0.04,
"latency_mean": 30,
"peak_memory_mb_mean": 75000
"throughput_qps": 0.0465,
"latency_mean": 21.4354,
"peak_memory_mb_mean": 72557.58
}
}
]
@@ -72,9 +72,9 @@
}
],
"baseline": {
"throughput_qps": 0.06,
"latency_mean": 20,
"peak_memory_mb_mean": 48000
"throughput_qps": 0.0642,
"latency_mean": 15.5589,
"peak_memory_mb_mean": 45742.88
}
},
{
@@ -97,9 +97,9 @@
}
],
"baseline": {
"throughput_qps": 0.01,
"latency_mean": 90,
"peak_memory_mb_mean": 56000
"throughput_qps": 0.0128,
"latency_mean": 77.8565,
"peak_memory_mb_mean": 53947.84
}
}
]