wangyuandHongsheng Liu
4e82192fd6
Signed-off-by: wangyu <410167048@qq.com> Signed-off-by: wangyu <53896905+yenuo26@users.noreply.github.com> Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
200 lines
6.2 KiB
JSON
200 lines
6.2 KiB
JSON
[
|
|
{
|
|
"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": [
|
|
300,
|
|
300,
|
|
1000,
|
|
600,
|
|
800
|
|
],
|
|
"mean_e2el_ms": [
|
|
6000,
|
|
8000,
|
|
11000,
|
|
13000,
|
|
17000
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"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": [
|
|
30
|
|
],
|
|
"mean_e2el_ms": [
|
|
540
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"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": [
|
|
30
|
|
],
|
|
"mean_e2el_ms": [
|
|
600
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"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": [
|
|
40
|
|
],
|
|
"mean_e2el_ms": [
|
|
700
|
|
]
|
|
}
|
|
}
|
|
]
|
|
}
|
|
]
|