Files
vllm-omni/tests/dfx/perf/tests/test_qwen_omni.json
T
2026-05-01 22:47:24 +08:00

451 lines
17 KiB
JSON

[
{
"test_name": "test_qwen3_omni",
"server_params": {
"model": "Qwen/Qwen3-Omni-30B-A3B-Instruct",
"extra_cli_args": ["--no-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": [1000, 3000, 5000, 7000, 9000],
"mean_audio_ttfp_ms": [30000, 60000, 90000, 120000, 150000],
"mean_audio_rtf": [0.35, 0.45, 0.55, 0.65, 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": [2000],
"mean_audio_ttfp_ms": [10000],
"mean_audio_rtf": [0.25]
}
},
{
"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": [6000],
"mean_audio_ttfp_ms": [15000],
"mean_audio_rtf": [0.45]
}
},
{
"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": [12000],
"mean_audio_ttfp_ms": [18000],
"mean_audio_rtf": [0.9]
}
}
]
},
{
"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],
"max_concurrency": [1, 4, 8, 16],
"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": [1000, 3000, 5000, 7000],
"mean_audio_ttfp_ms": [1000, 3000, 5000, 7000],
"mean_audio_rtf": [0.2, 0.35, 0.6, 0.85]
}
},
{
"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": [2000],
"mean_audio_ttfp_ms": [2000],
"mean_audio_rtf": [0.25]
}
},
{
"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": [6000],
"mean_audio_ttfp_ms": [6000],
"mean_audio_rtf": [0.7]
}
},
{
"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": [12000],
"mean_audio_ttfp_ms": [12000],
"mean_audio_rtf": [1.0]
}
},
{
"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": [1000, 3000, 5000, 7000, 9000]
}
},
{
"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": [2000]
}
},
{
"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": [6000]
}
},
{
"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": [6000]
}
}
]
},
{
"test_name": "test_qwen3_omni_vllm_text",
"server_params": {
"model": "Qwen/Qwen3-Omni-30B-A3B-Instruct",
"use_omni": false,
"extra_cli_args": ["--no-enable-prefix-caching"]
},
"benchmark_params": [
{
"dataset_name": "random",
"backend": "vllm",
"model": "Qwen/Qwen3-Omni-30B-A3B-Instruct",
"endpoint": "/v1/completions",
"num_prompts": [4, 16, 32, 64, 128],
"max_concurrency": [1, 4, 8, 16, 32],
"random_input_len": 2500,
"random_output_len": 900,
"temperature": 0.4,
"top_p": 0.9,
"top_k": 1,
"seed": 42,
"repetition_penalty": 1.05,
"ignore_eos": true,
"extra_body": {
"modalities": ["text"]
},
"percentile-metrics": "ttft,tpot,itl,e2el",
"baseline": {
"mean_ttft_ms": [1000, 3000, 5000, 7000, 9000]
}
},
{
"dataset_name": "random-mm",
"backend": "vllm",
"model": "Qwen/Qwen3-Omni-30B-A3B-Instruct",
"endpoint": "/v1/completions",
"num_prompts": [10],
"request_rate": [0.1],
"random_input_len": 100,
"random_output_len": 100,
"random_range_ratio": 0.0,
"temperature": 0.4,
"top_p": 0.9,
"top_k": 1,
"seed": 42,
"repetition_penalty": 1.05,
"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": [2000]
}
},
{
"dataset_name": "random-mm",
"backend": "vllm",
"model": "Qwen/Qwen3-Omni-30B-A3B-Instruct",
"endpoint": "/v1/completions",
"num_prompts": [40],
"request_rate": [0.5],
"random_input_len": 100,
"random_output_len": 100,
"random_range_ratio": 0.0,
"temperature": 0.4,
"top_p": 0.9,
"top_k": 1,
"seed": 42,
"repetition_penalty": 1.05,
"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": [6000]
}
},
{
"dataset_name": "random-mm",
"backend": "vllm",
"model": "Qwen/Qwen3-Omni-30B-A3B-Instruct",
"endpoint": "/v1/completions",
"num_prompts": [100],
"request_rate": [1.0],
"random_input_len": 100,
"random_output_len": 100,
"random_range_ratio": 0.0,
"temperature": 0.4,
"top_p": 0.9,
"top_k": 1,
"seed": 42,
"repetition_penalty": 1.05,
"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": [6000]
}
}
]
}
]