more models for vLLM Benchmark Suite (#35086)
Signed-off-by: louie-tsai <louie.tsai@intel.com>
This commit is contained in:
@@ -72,17 +72,6 @@
|
||||
"random-output-len": 128
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_llama8B_tp4_random_128_128",
|
||||
"server_parameters": {
|
||||
"tensor_parallel_size": 4
|
||||
},
|
||||
"client_parameters": {
|
||||
"dataset_name": "random",
|
||||
"random-input-len": 128,
|
||||
"random-output-len": 128
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_llama8B_tp1_random_128_2048",
|
||||
"server_parameters": {
|
||||
@@ -105,17 +94,6 @@
|
||||
"random-output-len": 2048
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_llama8B_tp4_random_128_2048",
|
||||
"server_parameters": {
|
||||
"tensor_parallel_size": 4
|
||||
},
|
||||
"client_parameters": {
|
||||
"dataset_name": "random",
|
||||
"random-input-len": 128,
|
||||
"random-output-len": 2048
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_llama8B_tp1_random_2048_128",
|
||||
"server_parameters": {
|
||||
@@ -139,14 +117,25 @@
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_llama8B_tp4_random_2048_128",
|
||||
"test_name": "serving_llama8B_tp1_random_2048_2048",
|
||||
"server_parameters": {
|
||||
"tensor_parallel_size": 4
|
||||
"tensor_parallel_size": 1
|
||||
},
|
||||
"client_parameters": {
|
||||
"dataset_name": "random",
|
||||
"random-input-len": 2048,
|
||||
"random-output-len": 128
|
||||
"random-output-len": 2048
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_llama8B_tp2_random_2048_2048",
|
||||
"server_parameters": {
|
||||
"tensor_parallel_size": 2
|
||||
},
|
||||
"client_parameters": {
|
||||
"dataset_name": "random",
|
||||
"random-input-len": 2048,
|
||||
"random-output-len": 2048
|
||||
}
|
||||
}
|
||||
]
|
||||
|
||||
Reference in New Issue
Block a user