33 lines
971 B
JSON
33 lines
971 B
JSON
[
|
|
{
|
|
"test_name": "throughput_llama8B_tp1",
|
|
"environment_variables": {
|
|
"VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
|
|
"VLLM_CPU_KVCACHE_SPACE": 40
|
|
},
|
|
"parameters": {
|
|
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
|
|
"tensor_parallel_size": 1,
|
|
"load_format": "dummy",
|
|
"dataset": "./ShareGPT_V3_unfiltered_cleaned_split.json",
|
|
"num_prompts": 200,
|
|
"backend": "vllm"
|
|
}
|
|
},
|
|
{
|
|
"test_name": "throughput_llama8B_tp4",
|
|
"environment_variables": {
|
|
"VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
|
|
"VLLM_CPU_KVCACHE_SPACE": 40
|
|
},
|
|
"parameters": {
|
|
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
|
|
"tensor_parallel_size": 4,
|
|
"load_format": "dummy",
|
|
"dataset": "./ShareGPT_V3_unfiltered_cleaned_split.json",
|
|
"num_prompts": 200,
|
|
"backend": "vllm"
|
|
}
|
|
}
|
|
]
|