866ce7168c
### What this PR does / why we need it? - Run benchmark scripts will Download model from modelscope Signed-off-by: wangli <wangli858794774@gmail.com>
27 lines
604 B
JSON
27 lines
604 B
JSON
[
|
|
{
|
|
"test_name": "serving_llama8B_tp1",
|
|
"qps_list": [
|
|
1,
|
|
4,
|
|
16,
|
|
"inf"
|
|
],
|
|
"server_parameters": {
|
|
"model": "LLM-Research/Meta-Llama-3.1-8B-Instruct",
|
|
"tensor_parallel_size": 1,
|
|
"swap_space": 16,
|
|
"disable_log_stats": "",
|
|
"disable_log_requests": "",
|
|
"load_format": "dummy"
|
|
},
|
|
"client_parameters": {
|
|
"model": "LLM-Research/Meta-Llama-3.1-8B-Instruct",
|
|
"backend": "vllm",
|
|
"dataset_name": "sharegpt",
|
|
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
|
|
"num_prompts": 200
|
|
}
|
|
}
|
|
]
|