76dacf3fa0
### What this PR does / why we need it? This is a post patch of #1014, for some convenience optimization - Set cached dataset path for speed - Use pypi to install escli-tool - Add benchmark results convert script to have a developer-friendly result - Patch the `benchmark_dataset.py` to disable streaming load for internet - Add more trigger ways for different purpose, `pr` for debug, `schedule` for daily test, `dispatch` and `pr-labled` for manual testing of a single(current) commit - Disable latency test for `qwen-2.5-vl`, (This script does not support multi-modal yet) ### Does this PR introduce _any_ user-facing change? No ### How was this patch tested? CI passed --------- Signed-off-by: wangli <wangli858794774@gmail.com>
54 lines
1.2 KiB
JSON
54 lines
1.2 KiB
JSON
[
|
|
{
|
|
"test_name": "serving_qwen2_5vl_7B_tp1",
|
|
"qps_list": [
|
|
1,
|
|
4,
|
|
16,
|
|
"inf"
|
|
],
|
|
"server_parameters": {
|
|
"model": "Qwen/Qwen2.5-VL-7B-Instruct",
|
|
"tensor_parallel_size": 1,
|
|
"swap_space": 16,
|
|
"disable_log_stats": "",
|
|
"disable_log_requests": "",
|
|
"trust_remote_code": "",
|
|
"max_model_len": 16384
|
|
},
|
|
"client_parameters": {
|
|
"model": "Qwen/Qwen2.5-VL-7B-Instruct",
|
|
"backend": "openai-chat",
|
|
"dataset_name": "hf",
|
|
"hf_split": "train",
|
|
"endpoint": "/v1/chat/completions",
|
|
"dataset_path": "lmarena-ai/vision-arena-bench-v0.1",
|
|
"num_prompts": 200
|
|
}
|
|
},
|
|
{
|
|
"test_name": "serving_qwen3_8B_tp1",
|
|
"qps_list": [
|
|
1,
|
|
4,
|
|
16,
|
|
"inf"
|
|
],
|
|
"server_parameters": {
|
|
"model": "Qwen/Qwen3-8B",
|
|
"tensor_parallel_size": 1,
|
|
"swap_space": 16,
|
|
"disable_log_stats": "",
|
|
"disable_log_requests": "",
|
|
"load_format": "dummy"
|
|
},
|
|
"client_parameters": {
|
|
"model": "Qwen/Qwen3-8B",
|
|
"backend": "vllm",
|
|
"dataset_name": "sharegpt",
|
|
"dataset_path": "/github/home/.cache/datasets/ShareGPT_V3_unfiltered_cleaned_split.json",
|
|
"num_prompts": 200
|
|
}
|
|
}
|
|
]
|