Files
vllm-omni/tests/dfx/perf/tests/test_minicpmo_4_5_ready.json
T

82 lines
1.8 KiB
JSON

[
{
"test_name": "test_minicpmo_4_5_ready",
"mark": [
{
"hardware_marks": {
"res": {
"cuda": "H100",
"npu": "A3"
},
"num_cards": 1
}
},
"core_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": [
10,
40
],
"max_concurrency": [
1,
4
],
"no_oversample": true,
"disable_shuffle": 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": [
0.9731,
1.1986
],
"mean_ttft_ms": [
152.5665,
270.2559
],
"mean_e2el_ms": [
1027.2953,
3306.3735
],
"mean_audio_ttfp_ms": [
458.1553,
2030.2335
],
"mean_audio_rtf": [
0.2357,
0.791
]
}
}
}
]
}
]