15 lines
315 B
JSON
15 lines
315 B
JSON
|
[
|
||
|
|
{
|
||
|
|
"test_name": "throughput_llama8B_tp1",
|
||
|
|
"parameters": {
|
||
|
|
"model": "meta-llama/Llama-3.1-8B-Instruct",
|
||
|
|
"tensor_parallel_size": 1,
|
||
|
|
"load_format": "dummy",
|
||
|
|
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
|
||
|
|
"num_prompts": 200,
|
||
|
|
"backend": "vllm"
|
||
|
|
}
|
||
|
|
}
|
||
|
|
]
|
||
|
|
|