forked from EngineX-Ascend/enginex-ascend-910-vllm
v0.10.1rc1
This commit is contained in:
23
benchmarks/tests/latency-tests.json
Normal file
23
benchmarks/tests/latency-tests.json
Normal file
@@ -0,0 +1,23 @@
|
||||
[
|
||||
{
|
||||
"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
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "latency_qwen2_5_7B_tp1",
|
||||
"parameters": {
|
||||
"model": "Qwen/Qwen2.5-7B-Instruct",
|
||||
"tensor_parallel_size": 1,
|
||||
"load_format": "dummy",
|
||||
"num_iters_warmup": 5,
|
||||
"num_iters": 15
|
||||
}
|
||||
}
|
||||
]
|
||||
Reference in New Issue
Block a user