wangyuandHongsheng Liu
4e82192fd6
Signed-off-by: wangyu <410167048@qq.com> Signed-off-by: wangyu <53896905+yenuo26@users.noreply.github.com> Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
332 lines
11 KiB
JSON
332 lines
11 KiB
JSON
[
|
|
{
|
|
"test_name": "test_qwen3_omni_chunk",
|
|
"server_params": {
|
|
"model": "Qwen/Qwen3-Omni-30B-A3B-Instruct",
|
|
"extra_cli_args": [
|
|
"--async-chunk"
|
|
]
|
|
},
|
|
"benchmark_params": [
|
|
{
|
|
"dataset_name": "random",
|
|
"backend": "openai-chat-omni",
|
|
"endpoint": "/v1/chat/completions",
|
|
"num_prompts": [
|
|
4,
|
|
16,
|
|
32,
|
|
64,
|
|
128
|
|
],
|
|
"max_concurrency": [
|
|
1,
|
|
4,
|
|
8,
|
|
16,
|
|
32
|
|
],
|
|
"random_input_len": 2500,
|
|
"random_output_len": 900,
|
|
"ignore_eos": true,
|
|
"percentile-metrics": "ttft,tpot,itl,e2el,audio_rtf,audio_ttfp,audio_duration",
|
|
"baseline": {
|
|
"mean_ttft_ms": [
|
|
400,
|
|
300,
|
|
400,
|
|
600,
|
|
900
|
|
],
|
|
"mean_e2el_ms": [
|
|
26000,
|
|
43000,
|
|
52000,
|
|
72000,
|
|
109000
|
|
],
|
|
"mean_audio_rtf": [
|
|
0.15,
|
|
0.30,
|
|
0.35,
|
|
0.50,
|
|
0.75
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"dataset_name": "random-mm",
|
|
"backend": "openai-chat-omni",
|
|
"endpoint": "/v1/chat/completions",
|
|
"num_prompts": [
|
|
10
|
|
],
|
|
"request_rate": [
|
|
0.1
|
|
],
|
|
"random_input_len": 100,
|
|
"random_output_len": 100,
|
|
"random_range_ratio": 0.0,
|
|
"ignore_eos": true,
|
|
"random_mm_base_items_per_request": 1,
|
|
"random_mm_num_mm_items_range_ratio": 0.5,
|
|
"random_mm_limit_mm_per_prompt": {
|
|
"audio": 1
|
|
},
|
|
"random_mm_bucket_config": {
|
|
"(0, 60, 3)": 1.0
|
|
},
|
|
"percentile-metrics": "ttft,tpot,itl,e2el,audio_rtf,audio_ttfp,audio_duration",
|
|
"baseline": {
|
|
"mean_ttft_ms": [
|
|
600
|
|
],
|
|
"mean_e2el_ms": [
|
|
6000
|
|
],
|
|
"mean_audio_rtf": [
|
|
0.20
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"dataset_name": "random-mm",
|
|
"backend": "openai-chat-omni",
|
|
"endpoint": "/v1/chat/completions",
|
|
"num_prompts": [
|
|
40
|
|
],
|
|
"request_rate": [
|
|
0.5
|
|
],
|
|
"random_input_len": 100,
|
|
"random_output_len": 100,
|
|
"random_range_ratio": 0.0,
|
|
"ignore_eos": true,
|
|
"random_mm_base_items_per_request": 2,
|
|
"random_mm_num_mm_items_range_ratio": 0.5,
|
|
"random_mm_limit_mm_per_prompt": {
|
|
"image": 1,
|
|
"video": 1
|
|
},
|
|
"random_mm_bucket_config": {
|
|
"(256, 256, 1)": 0.5,
|
|
"(720, 1280, 2)": 0.5
|
|
},
|
|
"percentile-metrics": "ttft,tpot,itl,e2el,audio_rtf,audio_ttfp,audio_duration",
|
|
"baseline": {
|
|
"mean_ttft_ms": [
|
|
300
|
|
],
|
|
"mean_e2el_ms": [
|
|
7000
|
|
],
|
|
"mean_audio_rtf": [
|
|
0.25
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"dataset_name": "random-mm",
|
|
"backend": "openai-chat-omni",
|
|
"endpoint": "/v1/chat/completions",
|
|
"num_prompts": [
|
|
100
|
|
],
|
|
"request_rate": [
|
|
1.0
|
|
],
|
|
"random_input_len": 100,
|
|
"random_output_len": 100,
|
|
"random_range_ratio": 0.0,
|
|
"ignore_eos": true,
|
|
"random_mm_base_items_per_request": 3,
|
|
"random_mm_num_mm_items_range_ratio": 0.5,
|
|
"random_mm_limit_mm_per_prompt": {
|
|
"image": 1,
|
|
"video": 1,
|
|
"audio": 1
|
|
},
|
|
"random_mm_bucket_config": {
|
|
"(256, 256, 1)": 0.34,
|
|
"(720, 1280, 2)": 0.33,
|
|
"(0, 60, 3)": 0.33
|
|
},
|
|
"percentile-metrics": "ttft,tpot,itl,e2el,audio_rtf,audio_ttfp,audio_duration",
|
|
"baseline": {
|
|
"mean_ttft_ms": [
|
|
700
|
|
],
|
|
"mean_e2el_ms": [
|
|
11000
|
|
],
|
|
"mean_audio_rtf": [
|
|
0.35
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"dataset_name": "random",
|
|
"backend": "openai-chat-omni",
|
|
"endpoint": "/v1/chat/completions",
|
|
"num_prompts": [
|
|
4,
|
|
16,
|
|
32,
|
|
64,
|
|
128
|
|
],
|
|
"max_concurrency": [
|
|
1,
|
|
4,
|
|
8,
|
|
16,
|
|
32
|
|
],
|
|
"random_input_len": 2500,
|
|
"random_output_len": 900,
|
|
"ignore_eos": true,
|
|
"extra_body": {
|
|
"modalities": [
|
|
"text"
|
|
]
|
|
},
|
|
"percentile-metrics": "ttft,tpot,itl,e2el",
|
|
"baseline": {
|
|
"mean_ttft_ms": [
|
|
100,
|
|
300,
|
|
500,
|
|
800,
|
|
1500
|
|
],
|
|
"mean_e2el_ms": [
|
|
5000,
|
|
8000,
|
|
10000,
|
|
14000,
|
|
20000
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"dataset_name": "random-mm",
|
|
"backend": "openai-chat-omni",
|
|
"endpoint": "/v1/chat/completions",
|
|
"num_prompts": [
|
|
10
|
|
],
|
|
"request_rate": [
|
|
0.1
|
|
],
|
|
"random_input_len": 100,
|
|
"random_output_len": 100,
|
|
"random_range_ratio": 0.0,
|
|
"ignore_eos": true,
|
|
"extra_body": {
|
|
"modalities": [
|
|
"text"
|
|
]
|
|
},
|
|
"random_mm_base_items_per_request": 1,
|
|
"random_mm_num_mm_items_range_ratio": 0.5,
|
|
"random_mm_limit_mm_per_prompt": {
|
|
"audio": 1
|
|
},
|
|
"random_mm_bucket_config": {
|
|
"(0, 60, 3)": 1.0
|
|
},
|
|
"percentile-metrics": "ttft,tpot,itl,e2el",
|
|
"baseline": {
|
|
"mean_ttft_ms": [
|
|
500
|
|
],
|
|
"mean_e2el_ms": [
|
|
1000
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"dataset_name": "random-mm",
|
|
"backend": "openai-chat-omni",
|
|
"endpoint": "/v1/chat/completions",
|
|
"num_prompts": [
|
|
40
|
|
],
|
|
"request_rate": [
|
|
0.5
|
|
],
|
|
"random_input_len": 100,
|
|
"random_output_len": 100,
|
|
"random_range_ratio": 0.0,
|
|
"ignore_eos": true,
|
|
"extra_body": {
|
|
"modalities": [
|
|
"text"
|
|
]
|
|
},
|
|
"random_mm_base_items_per_request": 2,
|
|
"random_mm_num_mm_items_range_ratio": 0.5,
|
|
"random_mm_limit_mm_per_prompt": {
|
|
"image": 1,
|
|
"video": 1
|
|
},
|
|
"random_mm_bucket_config": {
|
|
"(256, 256, 1)": 0.5,
|
|
"(720, 1280, 2)": 0.5
|
|
},
|
|
"percentile-metrics": "ttft,tpot,itl,e2el",
|
|
"baseline": {
|
|
"mean_ttft_ms": [
|
|
200
|
|
],
|
|
"mean_e2el_ms": [
|
|
800
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"dataset_name": "random-mm",
|
|
"backend": "openai-chat-omni",
|
|
"endpoint": "/v1/chat/completions",
|
|
"num_prompts": [
|
|
100
|
|
],
|
|
"request_rate": [
|
|
1.0
|
|
],
|
|
"random_input_len": 100,
|
|
"random_output_len": 100,
|
|
"random_range_ratio": 0.0,
|
|
"ignore_eos": true,
|
|
"extra_body": {
|
|
"modalities": [
|
|
"text"
|
|
]
|
|
},
|
|
"random_mm_base_items_per_request": 3,
|
|
"random_mm_num_mm_items_range_ratio": 0.5,
|
|
"random_mm_limit_mm_per_prompt": {
|
|
"image": 1,
|
|
"video": 1,
|
|
"audio": 1
|
|
},
|
|
"random_mm_bucket_config": {
|
|
"(256, 256, 1)": 0.34,
|
|
"(720, 1280, 2)": 0.33,
|
|
"(0, 60, 3)": 0.33
|
|
},
|
|
"percentile-metrics": "ttft,tpot,itl,e2el",
|
|
"baseline": {
|
|
"mean_ttft_ms": [
|
|
600
|
|
],
|
|
"mean_e2el_ms": [
|
|
1300
|
|
]
|
|
}
|
|
}
|
|
]
|
|
}
|
|
]
|