training error Cuda

[sokolegg]

/usr/local/lib/python3.10/dist-packages/torch/nn/modules/linear.py in forward(self, input) 112 113 def forward(self, input: Tensor) -> Tensor: --> 114 return F.linear(input, self.weight, self.bias) 115 116 def extra_repr(self) -> str:

RuntimeError: CUDA error: CUBLAS_STATUS_INTERNAL_ERROR when calling cublasLtMatmul with transpose_mat1 1 transpose_mat2 0 m 4096 n 4 k 64 mat1_ld 64 mat2_ld 64 result_ld 4096 abcType 14 computeType 68 scaleType 0

[Junxiao-Ma]

I have the same issue ,have you solved it?