search

hustvl / Vim

Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model
Apache License 2.0
2.55k stars 159 forks source link

RuntimeError: GET was unable to find an engine to execute this computation #75

Closed Syuling closed 2 months ago

Syuling commented 2 months ago

Hi, I followed the tutorial and installed： cuda 11.8 python 3.10.13 pytorch 2.1.1 causal_conv1d 1.1.0 mamba-ssm 1.1.1 but there are still issue： File "/home/suyuling/Vim/vim/models_mamba.py", line 541, in forward x = self.forward_features(x, inference_params, if_random_cls_token_position=if_random_cls_token_position, if_random_token_rank=if_random_token_rank) File "/home/suyuling/Vim/vim/models_mamba.py", line 383, in forward_features x = self.patch_embed(x) File "/home/suyuling/anaconda3/envs/my_vim/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl return forward_call(*args, *kwargs) File "/home/suyuling/Vim/vim/models_mamba.py", line 59, in forward x = self.proj(x) File "/home/suyuling/anaconda3/envs/my_vim/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl return forward_call(args, **kwargs) File "/home/suyuling/anaconda3/envs/my_vim/lib/python3.10/site-packages/torch/nn/modules/conv.py", line 463, in forward return self._conv_forward(input, self.weight, self.bias) File "/home/suyuling/anaconda3/envs/my_vim/lib/python3.10/site-packages/torch/nn/modules/conv.py", line 459, in _conv_forward return F.conv2d(input, weight, bias, self.stride, RuntimeError: GET was unable to find an engine to execute this computation

Have you ever encountered this problem? Thank you very much!