hustvl / Vim

[ICML 2024] Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model
Apache License 2.0
2.98k stars 201 forks source link

Problem about selective_scan_interface.py line 177 :conv1d_out = causal_conv1d_cuda.causal_conv1d_fwd(x, conv1d_weight, conv1d_bias,None, True) #95

Open Mahaha613 opened 4 months ago

Mahaha613 commented 4 months ago

TypeError causal_conv1d_fwd(): incompatible function arguments. The following argument types are supported:

  1. (arg0: torch.Tensor, arg1: torch.Tensor, arg2: Optional[torch.Tensor], arg3: Optional[torch.Tensor], arg4: Optional[torch.Tensor], arg5: Optional[torch.Tensor], arg6: bool) -> torch.Tensor
RunyuanLiu commented 4 months ago

I have the same question ,do you have solved it!

bobo-242 commented 4 months ago

I need a solution to this problem, please