Files
vllm-omni/tests/dfx/perf/tests/test_minicpmo_4_5.json
T
2026-08-11 14:53:49 +08:00

88 lines
1.9 KiB
JSON

[
{
"test_name": "test_minicpmo_4_5",
"mark": [
{
"hardware_marks": {
"res": {
"cuda": "H100",
"npu": "A3"
},
"num_cards": 1
}
},
"full_model",
"omni"
],
"server_params": {
"model": "openbmb/MiniCPM-o-4_5",
"extra_cli_args": [
"--deploy-config",
"vllm_omni/deploy/minicpmo_4_5.yaml",
"--trust-remote-code"
]
},
"benchmark_params": [
{
"dataset_name": "seed-tts",
"dataset_path": "zhaochenyang20/seed-tts-eval",
"backend": "openai-chat-omni",
"endpoint": "/v1/chat/completions",
"num_prompts": [
32,
64,
128
],
"max_concurrency": [
1,
4,
8
],
"no_oversample": true,
"trust_remote_code": true,
"seed_tts_locale": "en",
"extra_body": {
"modalities": [
"text",
"audio"
],
"chat_template_kwargs": {
"enable_thinking": false,
"use_tts_template": true
}
},
"percentile-metrics": "ttft,e2el,audio_ttfp,audio_rtf,audio_duration",
"baseline": {
"H100": {
"request_throughput": [
0.7803,
1.1008,
1.2027
],
"mean_ttft_ms": [
166.9764,
307.7133,
323.584
],
"mean_e2el_ms": [
1361.1682,
3800.6332,
6961.8636
],
"mean_audio_ttfp_ms": [
635.8099,
1615.6591,
2888.9831
],
"mean_audio_rtf": [
0.3151,
0.8568,
1.5425
]
}
}
}
]
}
]