关于 Blas xGEMMBatched launch failed 的报错

[Zhudongsheng75]

请问我在16g显存的gpu上测试 roformer-sim，总是会有如下报错：

tensorflow.python.framework.errors_impl.InternalError: Blas xGEMMBatched launch failed : a.shape=[192,17,64], b.shape=[192,17,64], m=17, n=17, k=64, batch_size=192
[[node model_3/Transformer-0-MultiHeadSelfAttention/einsum/Einsum (defined at /anaconda3/envs/nlp_tf/lib/python3.7/site-packages/bert4keras/layers.py:445) ]] [Op:__inference_predict_function_22308]

Errors may have originated from an input operation.
Input Source operations connected to node model_3/Transformer-0-MultiHeadSelfAttention/einsum/Einsum:
model_3/Transformer-0-MultiHeadSelfAttention/add_1 (defined at /anaconda3/envs/nlp_tf/lib/python3.7/site-packages/bert4keras/layers.py:443)
model_3/Transformer-0-MultiHeadSelfAttention/add (defined at /anaconda3/envs/nlp_tf/lib/python3.7/site-packages/bert4keras/layers.py:440)

Function call stack:
predict_function

请问这是什么原因呢？