[Bug] 多卡测试llama-3-8b-vllm，精度为0

[normlpl]

Prerequisite

• I have searched Issues and Discussions but cannot get the expected help.
• The bug has not been fixed in the latest version.

Type

I'm evaluating with the officially supported tasks/models/datasets.

Environment

python run.py configs/vllm/eval_llama3_vllm.py

Reproduces the problem - code/configuration sample

from mmengine.config import read_base

with read_base():
from ..datasets.ARC_c.ARC_c_gen_1e0de5 import ARC_c_datasets
#from ..datasets.ARC_e.ARC_e_gen_1e0de5 import ARC_e_datasets
from ..summarizers.example import summarizer

datasets = sum([v for k, v in locals().items() if k.endswith("_datasets") or k == 'datasets'], [])
work_dir = './outputs/llama3/'

from opencompass.models import VLLM

models = [
dict(
type=VLLM,
abbr='llama-3-8b-vllm',
path="./models/Meta-Llama-3-8B",
model_kwargs=dict(tensor_parallel_size=4),
max_out_len=100,
max_seq_len=2048,
batch_size=16,
generation_kwargs=dict(temperature=0),
run_cfg=dict(num_gpus=4, num_procs=1),
)
]

Reproduces the problem - command or script

四张卡测试ARC精度，精度为0

Reproduces the problem - error message

Other information

No response

[acylam]

Hi @normlpl, would you check the predictions you get from this model?