87 lines
3.2 KiB
JSON
87 lines
3.2 KiB
JSON
[
|
|
{
|
|
"test_name": "test_qwen3_omni_stability",
|
|
"server_params": {
|
|
"model": "Qwen/Qwen3-Omni-30B-A3B-Instruct",
|
|
"stage_config_name": "qwen3_omni.yaml"
|
|
},
|
|
"benchmark_params": [
|
|
{
|
|
"dataset_name": "random",
|
|
"backend": "openai-chat-omni",
|
|
"endpoint": "/v1/chat/completions",
|
|
"duration_sec": 300,
|
|
"request_rate": 0.2,
|
|
"num_prompts_per_batch": 10,
|
|
"random_input_len": 2500,
|
|
"random_output_len": 900,
|
|
"ignore_eos": true,
|
|
"percentile-metrics": "ttft,tpot,itl,e2el,audio_rtf,audio_ttfp,audio_duration"
|
|
},
|
|
{
|
|
"dataset_name": "random",
|
|
"backend": "openai-chat-omni",
|
|
"endpoint": "/v1/chat/completions",
|
|
"duration_sec": 300,
|
|
"max_concurrency": 2,
|
|
"num_prompts_per_batch": 10,
|
|
"random_input_len": 2500,
|
|
"random_output_len": 900,
|
|
"ignore_eos": true,
|
|
"percentile-metrics": "ttft,tpot,itl,e2el,audio_rtf,audio_ttfp,audio_duration"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"test_name": "test_qwen3_omni_stability_async_chunk",
|
|
"server_params": {
|
|
"model": "Qwen/Qwen3-Omni-30B-A3B-Instruct",
|
|
"stage_config_name": "qwen3_omni.yaml",
|
|
"update": {
|
|
"async_chunk": true,
|
|
"stage_args": {
|
|
"0": {
|
|
"engine_args.custom_process_next_stage_input_func": "vllm_omni.model_executor.stage_input_processors.qwen3_omni.thinker2talker_async_chunk"
|
|
},
|
|
"1": {
|
|
"engine_args.custom_process_next_stage_input_func": "vllm_omni.model_executor.stage_input_processors.qwen3_omni.talker2code2wav_async_chunk"
|
|
}
|
|
}
|
|
},
|
|
"delete": {
|
|
"stage_args": {
|
|
"2": [
|
|
"custom_process_input_func"
|
|
]
|
|
}
|
|
}
|
|
},
|
|
"benchmark_params": [
|
|
{
|
|
"dataset_name": "random",
|
|
"backend": "openai-chat-omni",
|
|
"endpoint": "/v1/chat/completions",
|
|
"duration_sec": 300,
|
|
"request_rate": 0.2,
|
|
"num_prompts_per_batch": 10,
|
|
"random_input_len": 2500,
|
|
"random_output_len": 900,
|
|
"ignore_eos": true,
|
|
"percentile-metrics": "ttft,tpot,itl,e2el,audio_rtf,audio_ttfp,audio_duration"
|
|
},
|
|
{
|
|
"dataset_name": "random",
|
|
"backend": "openai-chat-omni",
|
|
"endpoint": "/v1/chat/completions",
|
|
"duration_sec": 300,
|
|
"max_concurrency": 2,
|
|
"num_prompts_per_batch": 10,
|
|
"random_input_len": 2500,
|
|
"random_output_len": 900,
|
|
"ignore_eos": true,
|
|
"percentile-metrics": "ttft,tpot,itl,e2el,audio_rtf,audio_ttfp,audio_duration"
|
|
}
|
|
]
|
|
}
|
|
]
|