llm judge eval error:failed with code 134

[daimeiquan]

OS：
WSL Ubuntu 24.04

shell:
python run.py --models hf_qwen2_5_0_5b_instruct --datasets PubMedQA_llmjudge_gen

error:
.../opencompass/opencompass/runners/local.py - _launch - 241 - task OpenICLEval[qwen2.5-0.5b-instruct/PubMedQA] fail, see
outputs/default/20251002_215819/logs/eval/qwen2.5-0.5b-instruct/PubMedQA.out
.../opencompass/opencompass/runners/base.py - summarize - 64 - OpenICLEval[qwen2.5-0.5b-instruct/PubMedQA] failed with code 134

logs/eval/qwen2.5-0.5b-instruct/PubMedQA.out:
free(): double free detected in tcache 2
Aborted (core dumped)

.../opencompass/opencompass/configs/datasets/PubMedQA/PubMedQA_llmjudge_gen_f00302.py:

judge_cfg=dict( type='opencompass.models.OpenAISDK', path='qwen3:8b', key='ollama', openai_api_base='http://localhost:11434/v1', query_per_second=5, max_out_len=256, batch_size=8, meta_template=dict( round=[ dict(role='HUMAN', api_role='HUMAN'), dict(role='BOT', api_role='BOT', generate=True), ] ), ),

pip list：
`
Package Version Editable project location

---

absl-py 2.3.1
accelerate 1.10.1
addict 2.4.0
aiohappyeyeballs 2.6.1
aiohttp 3.12.15
aiosignal 1.4.0
alpaca_eval 0.6
annotated-types 0.7.0
anthropic 0.69.0
antlr4-python3-runtime 4.11.0
anyio 4.11.0
async-timeout 5.0.1
attrs 25.3.0
beautifulsoup4 4.14.2
boto3 1.28.43
botocore 1.31.43
brotlicffi 1.0.9.2
cachetools 6.2.0
certifi 2025.8.3
cffi 2.0.0
chardet 5.2.0
charset-normalizer 3.3.2
click 8.3.0
cn2an 0.5.23
colorama 0.4.6
contourpy 1.3.2
cpm-kernels 1.0.11
cryptography 46.0.1
cycler 0.12.1
dashscope 1.24.6
datasets 3.6.0
decorator 5.2.1
dill 0.3.8
dingo-python 1.5.0
distro 1.9.0
docstring_parser 0.17.0
einops 0.8.1
evaluate 0.4.6
exceptiongroup 1.3.0
faiss-gpu 1.7.2
fastapi 0.117.1
fasttext-wheel 0.9.2
filelock 3.17.0
fire 0.7.1
fonttools 4.60.0
frozenlist 1.7.0
fsspec 2025.3.0
func_timeout 4.3.5
fuzzywuzzy 0.18.0
gmpy2 2.2.1
google 3.0.0
gradio_client 1.13.3
h11 0.16.0
h5py 3.14.0
hanziconv 0.3.2
hf-xet 1.1.10
httpcore 1.0.9
httpx 0.27.2
huggingface-hub 0.35.1
human-eval 1.0.3
idna 3.7
immutabledict 4.2.1
importlib_metadata 8.7.0
jieba 0.42.1
Jinja2 3.1.6
jiter 0.11.0
jmespath 1.0.1
joblib 1.5.2
json5 0.12.1
jsonlines 4.0.0
jsonpatch 1.33
jsonpointer 3.0.0
kiwisolver 1.4.9
langdetect 1.0.9
langid 1.1.6
latex2sympy2_extended 1.10.2
Levenshtein 0.27.1
ltp 4.2.14
ltp-core 0.1.4
ltp-extension 0.1.13
lxml 6.0.2
markdown-it-py 4.0.0
MarkupSafe 3.0.2
math-verify 0.8.0
matplotlib 3.10.6
mdurl 0.1.2
mkl_fft 1.3.11
mkl_random 1.2.8
mkl-service 2.4.0
mmengine 0.10.7
mmengine-lite 0.10.7
mpmath 1.3.0
multidict 6.6.4
multiprocess 0.70.16
nest-asyncio 1.6.0
networkx 3.4.2
nltk 3.9.1
numpy 1.26.4
nvidia-cublas-cu12 12.9.1.4
nvidia-cuda-cupti-cu12 12.9.79
nvidia-cuda-nvrtc-cu12 12.9.86
nvidia-cuda-runtime-cu12 12.9.79
nvidia-cudnn-cu12 9.10.2.21
nvidia-cufft-cu12 11.4.1.4
nvidia-cufile-cu12 1.14.1.1
nvidia-curand-cu12 10.3.10.19
nvidia-cusolver-cu12 11.7.5.82
nvidia-cusparse-cu12 12.5.10.65
nvidia-cusparselt-cu12 0.7.1
nvidia-nccl-cu12 2.27.3
nvidia-nvjitlink-cu12 12.9.86
nvidia-nvtx-cu12 12.9.79
openai 1.56.2
OpenCC 1.1.9
opencompass 0.5.0
opencv-python 4.11.0.86
opencv-python-headless 4.11.0.86
packaging 25.0
pandas 1.5.3
patsy 1.0.1
Pillow 9.4.0
pip 25.2
platformdirs 4.4.0
portalocker 3.2.0
prettytable 3.16.0
proces 0.1.7
propcache 0.3.2
protobuf 6.32.1
psutil 7.1.0
py 1.11.0
pyahocorasick 2.2.0
pyarrow 21.0.0
pybind11 3.0.1
pycparser 2.23
pycryptodome 3.23.0
pydantic 2.11.9
pydantic_core 2.33.2
pyext 0.7
Pygments 2.19.2
PyJWT 2.8.0
pyparsing 3.2.5
pyphen 0.17.2
pypinyin 0.55.0
PySocks 1.7.1
python-dateutil 2.9.0.post0
python-dotenv 1.1.1
python-Levenshtein 0.27.1
pytorch-triton 3.1.0+cf34004b8a
pytz 2025.2
PyYAML 6.0.2
rank-bm25 0.2.2
RapidFuzz 3.14.1
rdkit 2025.3.6
regex 2025.9.18
requests 2.32.5
retry 0.9.2
retrying 1.4.2
rich 14.1.0
rouge 1.0.1
rouge-chinese 1.0.3
rouge_score 0.1.2
s3transfer 0.6.2
sacrebleu 2.5.1
safetensors 0.6.2
scikit-learn 1.5.0
scipy 1.15.3
seaborn 0.13.2
sentence-transformers 5.1.1
setuptools 78.1.1
shellingham 1.5.4
six 1.17.0
sniffio 1.3.1
soupsieve 2.8
spark-ai-python 0.4.5
sseclient-py 1.7.2
starlette 0.48.0
sympy 1.13.3
tabulate 0.9.0
tenacity 9.1.2
tencentcloud-sdk-python 3.0.1470
termcolor 3.1.0
textstat 0.7.10
threadpoolctl 3.6.0
tiktoken 0.11.0
timeout-decorator 0.5.0
tokenizers 0.22.1
toml 0.10.2
tomli 2.2.1
torch 2.8.0+cu129
torchvision 0.23.0+cu129
tqdm 4.67.1
transformers 4.56.2
tree-sitter 0.21.3
tree-sitter-languages 1.10.2
triton 3.4.0
typer 0.19.2
typing_extensions 4.15.0
typing-inspection 0.4.1
urllib3 1.26.20
uvicorn 0.37.0
volcengine 1.0.201
volcengine-python-sdk 4.0.22
wcwidth 0.2.14
websocket-client 1.8.0
websockets 15.0.1
wheel 0.45.1
wonderwords 2.2.0
wordninja 2.0.0
xxhash 3.5.0
yapf 0.43.0
yarl 1.20.1
zhipuai 2.1.5.20250825
zhon 2.1.1
zipp 3.23.0
`