64903b8e30
Signed-off-by: wangyu <410167048@qq.com> Signed-off-by: [Your Name] [Your Email] Signed-off-by: [Your Name] <your.email@example.com> Co-authored-by: Cursor <cursoragent@cursor.com> Co-authored-by: amy-why-3459 <wuhaiyan17@huawei.com>
296 lines
6.9 KiB
JSON
296 lines
6.9 KiB
JSON
[
|
|
{
|
|
"test_name": "test_qwen3_omni_chunk",
|
|
"mark": [
|
|
{
|
|
"hardware_marks": {
|
|
"res": {
|
|
"cuda": ["H100", "B200"],
|
|
"npu": "A3"
|
|
},
|
|
"num_cards": 2
|
|
}
|
|
},
|
|
"full_model",
|
|
"omni"
|
|
],
|
|
"server_params": {
|
|
"model": "Qwen/Qwen3-Omni-30B-A3B-Instruct",
|
|
"extra_cli_args": [
|
|
"--async-chunk"
|
|
]
|
|
},
|
|
"benchmark_params": [
|
|
{
|
|
"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": {
|
|
"H100": {
|
|
"mean_audio_rtf": [
|
|
0.1098
|
|
]
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"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": {
|
|
"H100": {
|
|
"mean_audio_rtf": [
|
|
0.1335
|
|
]
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"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": {
|
|
"H100": {
|
|
"mean_audio_rtf": [
|
|
0.1798
|
|
]
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"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": {
|
|
"H100": {
|
|
"mean_e2el_ms": [
|
|
756.8415
|
|
]
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"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": {
|
|
"H100": {
|
|
"mean_e2el_ms": [
|
|
694.9777
|
|
]
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"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": {
|
|
"H100": {
|
|
"mean_e2el_ms": [
|
|
1006.1663
|
|
]
|
|
}
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"test_name": "test_qwen3_omni_chunk_cuda",
|
|
"mark": [
|
|
{
|
|
"hardware_marks": {
|
|
"res": {
|
|
"cuda": ["H100", "B200"]
|
|
},
|
|
"num_cards": 2
|
|
}
|
|
},
|
|
"omni",
|
|
"slow"
|
|
],
|
|
"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,
|
|
32,
|
|
128
|
|
],
|
|
"max_concurrency": [
|
|
1,
|
|
8,
|
|
32
|
|
],
|
|
"random_input_len": 100,
|
|
"random_output_len": 100,
|
|
"ignore_eos": true,
|
|
"extra_body": {
|
|
"modalities": [
|
|
"text"
|
|
]
|
|
},
|
|
"percentile-metrics": "ttft,tpot,itl,e2el",
|
|
"baseline": {
|
|
"H100": {
|
|
"mean_e2el_ms": [
|
|
4354.8945,
|
|
9861.1687,
|
|
18716.709
|
|
]
|
|
}
|
|
}
|
|
}
|
|
]
|
|
}
|
|
]
|