Files
vllm-omni/tests/dfx/perf/tests/test_qwen3_omni_multi_replicas.json
T

128 lines
3.8 KiB
JSON

[
{
"test_name": "test_qwen3_omni_3gpu_replica2",
"mark": [
{
"hardware_marks": {
"res": {
"cuda": "H100"
},
"num_cards": 3
}
},
"full_model",
"omni"
],
"server_params": {
"model": "Qwen/Qwen3-Omni-30B-A3B-Instruct",
"stage_overrides": {
"1": {"num_replicas": 2, "devices": "1,2"},
"2": {"num_replicas": 2, "devices": "1,2"}
},
"extra_cli_args": [
"--async-chunk"
]
},
"benchmark_params": [
{
"dataset_name": "random",
"backend": "openai-chat-omni",
"endpoint": "/v1/chat/completions",
"num_prompts": [128, 128, 128, 128],
"max_concurrency": [8, 16, 24, 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": [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]
}
},
{
"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": [340.5122],
"mean_audio_ttfp_ms": [463.0752],
"mean_audio_rtf": [0.1153]
}
},
{
"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": [236.926],
"mean_audio_ttfp_ms": [395.2182],
"mean_audio_rtf": [0.1259]
}
},
{
"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": [470.6126],
"mean_audio_ttfp_ms": [665.5474],
"mean_audio_rtf": [0.166]
}
}
]
}
]