d9fb027068
### What this PR does / why we need it? Add benchmark workflows ### Does this PR introduce _any_ user-facing change? No ### How was this patch tested? Run locally --------- Signed-off-by: wangli <wangli858794774@gmail.com>
24 lines
495 B
JSON
24 lines
495 B
JSON
[
|
|
{
|
|
"test_name": "latency_qwen2_5vl_7B_tp1",
|
|
"parameters": {
|
|
"model": "Qwen/Qwen2.5-VL-7B-Instruct",
|
|
"tensor_parallel_size": 1,
|
|
"max_model_len": 16384,
|
|
"num_iters_warmup": 5,
|
|
"num_iters": 15
|
|
}
|
|
},
|
|
{
|
|
"test_name": "latency_qwen3_8B_tp1",
|
|
"parameters": {
|
|
"model": "Qwen/Qwen3-8B",
|
|
"tensor_parallel_size": 1,
|
|
"load_format": "dummy",
|
|
"max_model_len": 16384,
|
|
"num_iters_warmup": 5,
|
|
"num_iters": 15
|
|
}
|
|
}
|
|
]
|