Files
vllm-omni/tests/dfx/perf/tests/test_qwen3_omni_async_chunk.json
T

344 lines
8.0 KiB
JSON

[
{
"test_name": "test_qwen3_omni_chunk",
"mark": [
{
"hardware_marks": {
"res": {
"cuda": "H100"
},
"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",
"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": [
135.4379,
187.0896,
400,
435.675,
724.6836
],
"mean_e2el_ms": [
17619.9851,
34811.8335,
43656.9501,
56657.1548,
85097.6016
],
"mean_audio_rtf": [
0.1279,
0.2238,
0.2735,
0.3712,
0.5634
]
}
},
{
"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": [
340.329
],
"mean_e2el_ms": [
4305.477
],
"mean_audio_rtf": [
0.1305
]
}
},
{
"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": [
220.0909
],
"mean_e2el_ms": [
5475.9565
],
"mean_audio_rtf": [
0.1818
]
}
},
{
"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": [
450.0155
],
"mean_e2el_ms": [
8516.8316
],
"mean_audio_rtf": [
0.2717
]
}
},
{
"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": [
78.4278,
195.8037,
333.7318,
561.805,
1038.043
],
"mean_e2el_ms": [
4288.3029,
7429.9429,
9451.6184,
12607.5292,
18153.2547
]
}
},
{
"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": [
275.3875
],
"mean_e2el_ms": [
730.6995
]
}
},
{
"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": [
166.2201
],
"mean_e2el_ms": [
673.5789
]
}
},
{
"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": [
357.7781
],
"mean_e2el_ms": [
953.3493
]
}
}
]
}
]