218f21de21
### What this PR does / why we need it? - Add qwen2.5-7b test - Optimize the documentation to be more developer-friendly Signed-off-by: xuedinge233 <damow890@gmail.com> Co-authored-by: xuedinge233 <damow890@gmail.com>
51 lines
1.2 KiB
JSON
51 lines
1.2 KiB
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
|
|
}
|
|
},
|
|
{
|
|
"test_name": "serving_qwen2_5_7B_tp1",
|
|
"qps_list": [
|
|
1,
|
|
4,
|
|
16,
|
|
"inf"
|
|
],
|
|
"server_parameters": {
|
|
"model": "Qwen/Qwen2.5-7B-Instruct",
|
|
"tensor_parallel_size": 1,
|
|
"swap_space": 16,
|
|
"disable_log_stats": "",
|
|
"disable_log_requests": "",
|
|
"load_format": "dummy"
|
|
},
|
|
"client_parameters": {
|
|
"model": "Qwen/Qwen2.5-7B-Instruct",
|
|
"backend": "vllm",
|
|
"dataset_name": "sharegpt",
|
|
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
|
|
"num_prompts": 200
|
|
}
|
|
}
|
|
]
|