[Test] Add Omni Model Performance Benchmark Test (#1321)
Signed-off-by: yenuo26 <410167048@qq.com> Signed-off-by: wangyu <53896905+yenuo26@users.noreply.github.com>
This commit is contained in:
wangyu authored and GitHub committed
1 parent
00bd07b82b
commit
f4867ec175
5 files changed
+693
-35
No files matched your search
@@ -0,0 +1,266 @@
|
||||
[
|
||||
{
|
||||
"test_name": "test_qwen3_omni",
|
||||
"server_params": {
|
||||
"model": "Qwen/Qwen3-Omni-30B-A3B-Instruct",
|
||||
"stage_config_name": "qwen3_omni.yaml"
|
||||
},
|
||||
"benchmark_params": [
|
||||
{
|
||||
"dataset_name": "random",
|
||||
"num_prompts": [
|
||||
10,
|
||||
40,
|
||||
100
|
||||
],
|
||||
"request_rate": [
|
||||
0.1,
|
||||
0.5,
|
||||
1
|
||||
],
|
||||
"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": 100000,
|
||||
"mean_audio_ttfp_ms": 100000,
|
||||
"mean_audio_rtf": 100000
|
||||
}
|
||||
},
|
||||
{
|
||||
"dataset_name": "random",
|
||||
"num_prompts": [
|
||||
10,
|
||||
40,
|
||||
100
|
||||
],
|
||||
"max_concurrency": [
|
||||
1,
|
||||
4,
|
||||
10
|
||||
],
|
||||
"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": 100000,
|
||||
"mean_audio_ttfp_ms": 100000,
|
||||
"mean_audio_rtf": 100000
|
||||
}
|
||||
},
|
||||
{
|
||||
"dataset_name": "random-mm",
|
||||
"num_prompts": [
|
||||
10,
|
||||
40,
|
||||
100
|
||||
],
|
||||
"max_concurrency": [
|
||||
1,
|
||||
4,
|
||||
10
|
||||
],
|
||||
"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,
|
||||
"random_mm_limit_mm_per_prompt": {
|
||||
"image": 1,
|
||||
"video": 1,
|
||||
"audio": 1
|
||||
},
|
||||
"random_mm_bucket_config": {
|
||||
"(32, 32, 1)": 0.5,
|
||||
"(0, 1, 1)": 0.1,
|
||||
"(32, 32, 2)": 0.4
|
||||
},
|
||||
"percentile-metrics": "ttft,tpot,itl,e2el,audio_rtf,audio_ttfp,audio_duration",
|
||||
"baseline": {
|
||||
"mean_ttft_ms": 100000,
|
||||
"mean_audio_ttfp_ms": 100000,
|
||||
"mean_audio_rtf": 100000
|
||||
}
|
||||
},
|
||||
{
|
||||
"dataset_name": "random-mm",
|
||||
"num_prompts": [
|
||||
10,
|
||||
40,
|
||||
100
|
||||
],
|
||||
"request_rate": [
|
||||
0.1,
|
||||
0.5,
|
||||
1
|
||||
],
|
||||
"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,
|
||||
"random_mm_limit_mm_per_prompt": {
|
||||
"image": 1,
|
||||
"video": 1,
|
||||
"audio": 1
|
||||
},
|
||||
"random_mm_bucket_config": {
|
||||
"(32, 32, 1)": 0.5,
|
||||
"(0, 1, 1)": 0.1,
|
||||
"(32, 32, 2)": 0.4
|
||||
},
|
||||
"percentile-metrics": "ttft,tpot,itl,e2el,audio_rtf,audio_ttfp,audio_duration",
|
||||
"baseline": {
|
||||
"mean_ttft_ms": 100000,
|
||||
"mean_audio_ttfp_ms": 100000,
|
||||
"mean_audio_rtf": 100000
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"test_name": "test_qwen3_omni_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",
|
||||
"num_prompts": [
|
||||
10,
|
||||
40,
|
||||
100
|
||||
],
|
||||
"request_rate": [
|
||||
0.1,
|
||||
0.5,
|
||||
1
|
||||
],
|
||||
"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": 100000,
|
||||
"mean_audio_ttfp_ms": 100000,
|
||||
"mean_audio_rtf": 100000
|
||||
}
|
||||
},
|
||||
{
|
||||
"dataset_name": "random",
|
||||
"num_prompts": [
|
||||
10,
|
||||
40,
|
||||
100
|
||||
],
|
||||
"max_concurrency": [
|
||||
1,
|
||||
4,
|
||||
10
|
||||
],
|
||||
"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": 100000,
|
||||
"mean_audio_ttfp_ms": 100000,
|
||||
"mean_audio_rtf": 100000
|
||||
}
|
||||
},
|
||||
{
|
||||
"dataset_name": "random-mm",
|
||||
"num_prompts": [
|
||||
10,
|
||||
40,
|
||||
100
|
||||
],
|
||||
"max_concurrency": [
|
||||
1,
|
||||
4,
|
||||
10
|
||||
],
|
||||
"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,
|
||||
"random_mm_limit_mm_per_prompt": {
|
||||
"image": 1,
|
||||
"video": 1,
|
||||
"audio": 1
|
||||
},
|
||||
"random_mm_bucket_config": {
|
||||
"(32, 32, 1)": 0.5,
|
||||
"(0, 1, 1)": 0.1,
|
||||
"(32, 32, 2)": 0.4
|
||||
},
|
||||
"percentile-metrics": "ttft,tpot,itl,e2el,audio_rtf,audio_ttfp,audio_duration",
|
||||
"baseline": {
|
||||
"mean_ttft_ms": 100000,
|
||||
"mean_audio_ttfp_ms": 100000,
|
||||
"mean_audio_rtf": 100000
|
||||
}
|
||||
},
|
||||
{
|
||||
"dataset_name": "random-mm",
|
||||
"num_prompts": [
|
||||
10,
|
||||
40,
|
||||
100
|
||||
],
|
||||
"request_rate": [
|
||||
0.1,
|
||||
0.5,
|
||||
1
|
||||
],
|
||||
"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,
|
||||
"random_mm_limit_mm_per_prompt": {
|
||||
"image": 1,
|
||||
"video": 1,
|
||||
"audio": 1
|
||||
},
|
||||
"random_mm_bucket_config": {
|
||||
"(32, 32, 1)": 0.5,
|
||||
"(0, 1, 1)": 0.1,
|
||||
"(32, 32, 2)": 0.4
|
||||
},
|
||||
"percentile-metrics": "ttft,tpot,itl,e2el,audio_rtf,audio_ttfp,audio_duration",
|
||||
"baseline": {
|
||||
"mean_ttft_ms": 100000,
|
||||
"mean_audio_ttfp_ms": 100000,
|
||||
"mean_audio_rtf": 100000
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
Reference in new issue
Block a user